|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Xen-changelog] Merge with ia64-unstable.hg
# HG changeset patch
# User djm@xxxxxxxxxxxxxxx
# Node ID a83ac0806d6b900eafac6e6942352f88fe89d449
# Parent 35b74976f5986786e00cc51f8c2b7cf2c5d0f768
# Parent 8328317e60ab3655d919e94a8a2ffce82edec73f
Merge with ia64-unstable.hg
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/vcpu.c
--- a/xen/arch/ia64/vcpu.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/vcpu.c Fri Jul 15 13:39:50 2005
@@ -53,8 +53,15 @@
#define PRIVOP_COUNT_ADDR(x,y) do {} while (0)
#endif
+unsigned long dtlb_translate_count = 0;
+unsigned long tr_translate_count = 0;
+unsigned long phys_translate_count = 0;
+
unsigned long vcpu_verbose = 0;
#define verbose(a...) do {if (vcpu_verbose) printf(a);} while(0)
+
+extern TR_ENTRY *match_tr(VCPU *vcpu, unsigned long ifa);
+extern TR_ENTRY *match_dtlb(VCPU *vcpu, unsigned long ifa);
/**************************************************************************
VCPU general register access routines
@@ -224,6 +231,9 @@
//else printf("but nothing pending\n");
}
#endif
+ if (enabling_interrupts &&
+ vcpu_check_pending_interrupts(vcpu) != SPURIOUS_VECTOR)
+ PSCB(vcpu,pending_interruption) = 1;
return IA64_NO_FAULT;
}
@@ -267,6 +277,9 @@
return IA64_EXTINT_VECTOR;
}
#endif
+ if (enabling_interrupts &&
+ vcpu_check_pending_interrupts(vcpu) != SPURIOUS_VECTOR)
+ PSCB(vcpu,pending_interruption) = 1;
return IA64_NO_FAULT;
}
@@ -531,6 +544,11 @@
/**************************************************************************
VCPU interrupt control register access routines
**************************************************************************/
+
+void vcpu_pend_unspecified_interrupt(VCPU *vcpu)
+{
+ PSCB(vcpu,pending_interruption) = 1;
+}
void vcpu_pend_interrupt(VCPU *vcpu, UINT64 vector)
{
@@ -1241,28 +1259,117 @@
return (IA64_ILLOP_FAULT);
}
+#define itir_ps(itir) ((itir >> 2) & 0x3f)
+#define itir_mask(itir) (~((1UL << itir_ps(itir)) - 1))
+
+unsigned long vhpt_translate_count = 0;
+int in_vcpu_tpa = 0;
+
+IA64FAULT vcpu_translate(VCPU *vcpu, UINT64 address, BOOLEAN is_data, UINT64
*pteval, UINT64 *itir)
+{
+ unsigned long pta, pta_mask, iha, pte, ps;
+ TR_ENTRY *trp;
+ ia64_rr rr;
+
+ if (!(address >> 61)) {
+ if (!PSCB(vcpu,metaphysical_mode)) {
+ REGS *regs = vcpu_regs(vcpu);
+ unsigned long viip = PSCB(vcpu,iip);
+ unsigned long vipsr = PSCB(vcpu,ipsr);
+ unsigned long iip = regs->cr_iip;
+ unsigned long ipsr = regs->cr_ipsr;
+#if 0
+ printk("vcpu_translate: bad address %p, viip=%p,
vipsr=%p, iip=%p, ipsr=%p\n", address, viip, vipsr, iip, ipsr);
+ if (in_vcpu_tpa) printk("vcpu_translate called from
vcpu_tpa\n");
+ while(1);
+ panic_domain(0,"vcpu_translate: bad address %p\n",
address);
+#endif
+ printk("vcpu_translate: bad address %p, viip=%p,
vipsr=%p, iip=%p, ipsr=%p continuing\n", address, viip, vipsr, iip, ipsr);
+ }
+
+ *pteval = (address & _PAGE_PPN_MASK) | __DIRTY_BITS |
_PAGE_PL_2 | _PAGE_AR_RWX;
+ *itir = PAGE_SHIFT << 2;
+ phys_translate_count++;
+ return IA64_NO_FAULT;
+ }
+
+ /* check translation registers */
+ if ((trp = match_tr(vcpu,address))) {
+ tr_translate_count++;
+ *pteval = trp->page_flags;
+ *itir = trp->itir;
+ return IA64_NO_FAULT;
+ }
+
+ /* check 1-entry TLB */
+ if ((trp = match_dtlb(vcpu,address))) {
+ dtlb_translate_count++;
+if (!in_vcpu_tpa) printf("vcpu_translate: found in vdtlb\n");
+ *pteval = trp->page_flags;
+ *itir = trp->itir;
+ return IA64_NO_FAULT;
+ }
+
+ /* check guest VHPT */
+ pta = PSCB(vcpu,pta);
+ rr.rrval = PSCB(vcpu,rrs)[address>>61];
+ if (rr.ve && (pta & IA64_PTA_VE))
+ {
+ if (pta & IA64_PTA_VF)
+ {
+ /* long format VHPT - not implemented */
+ return (is_data ? IA64_DATA_TLB_VECTOR :
IA64_INST_TLB_VECTOR);
+ }
+ else
+ {
+ /* short format VHPT */
+
+ /* avoid recursively walking VHPT */
+ pta_mask = (itir_mask(pta) << 3) >> 3;
+ if (((address ^ pta) & pta_mask) == 0)
+ return (is_data ? IA64_DATA_TLB_VECTOR :
IA64_INST_TLB_VECTOR);
+
+ vcpu_thash(vcpu, address, &iha);
+ if (__copy_from_user(&pte, (void *)iha, sizeof(pte)) !=
0)
+ return IA64_VHPT_TRANS_VECTOR;
+
+ /*
+ * Optimisation: this VHPT walker aborts on not-present
pages
+ * instead of inserting a not-present translation, this
allows
+ * vectoring directly to the miss handler.
+ \ */
+ if (pte & _PAGE_P)
+ {
+ *pteval = pte;
+ *itir = vcpu_get_itir_on_fault(vcpu,address);
+ vhpt_translate_count++;
+ return IA64_NO_FAULT;
+ }
+ return (is_data ? IA64_DATA_TLB_VECTOR :
IA64_INST_TLB_VECTOR);
+ }
+ }
+ return (is_data ? IA64_ALT_DATA_TLB_VECTOR : IA64_ALT_INST_TLB_VECTOR);
+}
+
IA64FAULT vcpu_tpa(VCPU *vcpu, UINT64 vadr, UINT64 *padr)
{
- extern TR_ENTRY *match_tr(VCPU *,UINT64);
- unsigned long match_dtlb(VCPU *, unsigned long, unsigned long *,
unsigned long *);
- TR_ENTRY *trp;
- UINT64 mask, pteval, mp_pte, ps;
-
-extern unsigned long privop_trace;
- if (pteval = match_dtlb(vcpu, vadr, &ps, &mp_pte) && (mp_pte != -1UL)) {
- mask = (1L << ps) - 1;
- *padr = ((mp_pte & _PAGE_PPN_MASK) & ~mask) | (vadr & mask);
- verbose("vcpu_tpa: addr=%p @%p, successful,
padr=%p\n",vadr,PSCB(vcpu,iip),*padr);
+ UINT64 pteval, itir, mask;
+ IA64FAULT fault;
+
+in_vcpu_tpa=1;
+ fault = vcpu_translate(vcpu, vadr, 1, &pteval, &itir);
+in_vcpu_tpa=0;
+ if (fault == IA64_NO_FAULT)
+ {
+ mask = itir_mask(itir);
+ *padr = (pteval & _PAGE_PPN_MASK & mask) | (vadr & ~mask);
return (IA64_NO_FAULT);
}
- if (trp=match_tr(current,vadr)) {
- mask = (1L << trp->ps) - 1;
- *padr = ((trp->ppn << 12) & ~mask) | (vadr & mask);
- verbose("vcpu_tpa: addr=%p @%p, successful,
padr=%p\n",vadr,PSCB(vcpu,iip),*padr);
- return (IA64_NO_FAULT);
- }
- verbose("vcpu_tpa addr=%p, @%p, forcing data
miss\n",vadr,PSCB(vcpu,iip));
- return vcpu_force_data_miss(vcpu, vadr);
+ else
+ {
+ PSCB(vcpu,tmp[0]) = vadr; // save ifa in vcpu structure,
then specify IA64_FORCED_IFA
+ return (fault | IA64_FORCED_IFA);
+ }
}
IA64FAULT vcpu_tak(VCPU *vcpu, UINT64 vadr, UINT64 *key)
@@ -1392,20 +1499,24 @@
// if reg > 3
switch(reg) {
case 0:
+ memcpy(pval,"Xen/ia64",8);
+ break;
case 1:
- memcpy(pval,"Xen/ia64",8);
+ *pval = 0;
break;
case 2:
*pval = 0;
break;
case 3:
- *pval = 0; //FIXME: See vol1, 3.1.11
+ *pval = ia64_get_cpuid(3);
break;
case 4:
- *pval = 1; //FIXME: See vol1, 3.1.11
+ *pval = ia64_get_cpuid(4);
break;
default:
- *pval = 0; //FIXME: See vol1, 3.1.11
+ if (reg > (ia64_get_cpuid(3) & 0xff))
+ return IA64_RSVDREG_FAULT;
+ *pval = ia64_get_cpuid(reg);
break;
}
return (IA64_NO_FAULT);
@@ -1614,15 +1725,12 @@
// NOTE: returns a physical pte, NOT a "metaphysical" pte, so do not check
// the physical address contained for correctness
-unsigned long match_dtlb(VCPU *vcpu, unsigned long ifa, unsigned long *ps,
unsigned long *mp_pte)
+TR_ENTRY *match_dtlb(VCPU *vcpu, unsigned long ifa)
{
TR_ENTRY *trp;
- if (trp = vcpu_match_tr_entry(vcpu,&vcpu->arch.dtlb,ifa,1)) {
- if (ps) *ps = trp->ps;
- if (mp_pte) *mp_pte = vcpu->arch.dtlb_pte;
- return (trp->page_flags);
- }
+ if (trp = vcpu_match_tr_entry(vcpu,&vcpu->arch.dtlb,ifa,1))
+ return (&vcpu->arch.dtlb);
return 0UL;
}
@@ -1679,11 +1787,12 @@
// TODO: Only allowed for current vcpu
UINT64 mpaddr, ps;
IA64FAULT fault;
- unsigned long match_dtlb(VCPU *, unsigned long, unsigned long *,
unsigned long *);
+ TR_ENTRY *trp;
unsigned long lookup_domain_mpa(struct domain *,unsigned long);
unsigned long pteval, dom_imva;
- if (pteval = match_dtlb(vcpu, vadr, NULL, NULL)) {
+ if ((trp = match_dtlb(vcpu,vadr))) {
+ pteval = trp->page_flags;
dom_imva = __va(pteval & _PFN_MASK);
ia64_fc(dom_imva);
return IA64_NO_FAULT;
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/hypercall.c
--- a/xen/arch/ia64/hypercall.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/hypercall.c Fri Jul 15 13:39:50 2005
@@ -16,21 +16,26 @@
#include <asm/dom_fw.h>
extern unsigned long translate_domain_mpaddr(unsigned long);
-extern struct ia64_sal_retval pal_emulator_static(UINT64);
+extern struct ia64_pal_retval xen_pal_emulator(UINT64,UINT64,UINT64,UINT64);
extern struct ia64_sal_retval
sal_emulator(UINT64,UINT64,UINT64,UINT64,UINT64,UINT64,UINT64,UINT64);
+
+unsigned long idle_when_pending = 0;
+unsigned long pal_halt_light_count = 0;
int
ia64_hypercall (struct pt_regs *regs)
{
struct vcpu *v = (struct domain *) current;
struct ia64_sal_retval x;
+ struct ia64_pal_retval y;
unsigned long *tv, *tc;
+ int pi;
switch (regs->r2) {
case FW_HYPERCALL_PAL_CALL:
//printf("*** PAL hypercall: index=%d\n",regs->r28);
//FIXME: This should call a C routine
-#if 1
+#if 0
// This is very conservative, but avoids a possible
// (and deadly) freeze in paravirtualized domains due
// to a yet-to-be-found bug where pending_interruption
@@ -38,25 +43,34 @@
// in the idle loop, this should resolve it
v->vcpu_info->arch.pending_interruption = 1;
#endif
- x = pal_emulator_static(regs->r28);
if (regs->r28 == PAL_HALT_LIGHT) {
-#if 1
#define SPURIOUS_VECTOR 15
- if (vcpu_check_pending_interrupts(v)!=SPURIOUS_VECTOR) {
-// int pi = vcpu_check_pending_interrupts(v);
+ pi = vcpu_check_pending_interrupts(v);
+ if (pi != SPURIOUS_VECTOR) {
+ if (!v->vcpu_info->arch.pending_interruption)
+ idle_when_pending++;
+ vcpu_pend_unspecified_interrupt(v);
//printf("idle w/int#%d pending!\n",pi);
//this shouldn't happen, but it apparently does quite a bit! so don't
//allow it to happen... i.e. if a domain has an interrupt pending and
//it tries to halt itself because it thinks it is idle, just return here
//as deliver_pending_interrupt is called on the way out and will deliver it
}
- else
-#endif
- do_sched_op(SCHEDOP_yield);
+ else {
+ pal_halt_light_count++;
+ do_sched_op(SCHEDOP_yield);
+ }
//break;
}
- regs->r8 = x.status; regs->r9 = x.v0;
- regs->r10 = x.v1; regs->r11 = x.v2;
+ else if (regs->r28 >= PAL_COPY_PAL) { /* FIXME */
+ printf("stacked PAL hypercalls not supported\n");
+ regs->r8 = -1;
+ break;
+ }
+ else y = xen_pal_emulator(regs->r28,regs->r29,
+ regs->r30,regs->r31);
+ regs->r8 = y.status; regs->r9 = y.v0;
+ regs->r10 = y.v1; regs->r11 = y.v2;
break;
case FW_HYPERCALL_SAL_CALL:
x = sal_emulator(vcpu_get_gr(v,32),vcpu_get_gr(v,33),
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/hyperprivop.S
--- a/xen/arch/ia64/hyperprivop.S Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/hyperprivop.S Fri Jul 15 13:39:50 2005
@@ -14,8 +14,15 @@
#include <asm/system.h>
#include <public/arch-ia64.h>
+#if 1 // change to 0 to turn off all fast paths
+#define FAST_HYPERPRIVOPS
#define FAST_HYPERPRIVOP_CNT
#define FAST_REFLECT_CNT
+#define FAST_TICK
+#define FAST_BREAK
+#define FAST_ACCESS_REFLECT
+#undef RFI_TO_INTERRUPT // not working yet
+#endif
// FIXME: This is defined in include/asm-ia64/hw_irq.h but this
// doesn't appear to be include'able from assembly?
@@ -45,6 +52,9 @@
// r19 == vpsr.ic (low 32 bits) | vpsr.i (high 32 bits)
// r31 == pr
GLOBAL_ENTRY(fast_hyperprivop)
+#ifndef FAST_HYPERPRIVOPS // see beginning of file
+ br.sptk.many dispatch_break_fault ;;
+#endif
// HYPERPRIVOP_SSM_I?
// assumes domain interrupts pending, so just do it
cmp.eq p7,p6=XEN_HYPER_SSM_I,r17
@@ -124,6 +134,10 @@
// HYPERPRIVOP_ITC_I?
cmp.eq p7,p6=XEN_HYPER_ITC_I,r17
(p7) br.sptk.many hyper_itc_i;;
+
+ // HYPERPRIVOP_THASH?
+ cmp.eq p7,p6=XEN_HYPER_THASH,r17
+(p7) br.sptk.many hyper_thash;;
// if not one of the above, give up for now and do it the slow way
br.sptk.many dispatch_break_fault ;;
@@ -276,17 +290,17 @@
// r30 == cr.ivr
// r29 == rp
GLOBAL_ENTRY(fast_tick_reflect)
-#define FAST_TICK
-#ifndef FAST_TICK
+#ifndef FAST_TICK // see beginning of file
br.cond.sptk.many rp;;
#endif
mov r28=IA64_TIMER_VECTOR;;
cmp.ne p6,p0=r28,r30
(p6) br.cond.spnt.few rp;;
movl r20=(PERCPU_ADDR)+IA64_CPUINFO_ITM_NEXT_OFFSET;;
- ld8 r21=[r20];;
+ ld8 r26=[r20];;
mov r27=ar.itc;;
- cmp.ltu p6,p0=r21,r27
+ adds r27=200,r27;; // safety margin
+ cmp.ltu p6,p0=r26,r27
(p6) br.cond.spnt.few rp;;
mov r17=cr.ipsr;;
// slow path if: ipsr.be==1, ipsr.pp==1
@@ -296,14 +310,16 @@
extr.u r21=r17,IA64_PSR_PP_BIT,1 ;;
cmp.ne p6,p0=r21,r0
(p6) br.cond.spnt.few rp;;
+ // definitely have a domain tick
+ mov cr.eoi=r0;;
+ mov rp=r29;;
+ mov cr.itm=r26;; // ensure next tick
#ifdef FAST_REFLECT_CNT
movl r20=fast_reflect_count+((0x3000>>8)*8);;
ld8 r21=[r20];;
adds r21=1,r21;;
st8 [r20]=r21;;
#endif
- mov cr.eoi=r0;;
- mov rp=r29;;
// vcpu_pend_timer(current)
movl r18=XSI_PSR_IC;;
adds r20=XSI_ITV_OFS-XSI_PSR_IC_OFS,r18 ;;
@@ -440,15 +456,13 @@
END(fast_tick_reflect)
// reflect domain breaks directly to domain
-// FIXME: DOES NOT WORK YET
// r16 == cr.isr
// r17 == cr.iim
// r18 == XSI_PSR_IC
// r19 == vpsr.ic (low 32 bits) | vpsr.i (high 32 bits)
// r31 == pr
GLOBAL_ENTRY(fast_break_reflect)
-#define FAST_BREAK
-#ifndef FAST_BREAK
+#ifndef FAST_BREAK // see beginning of file
br.sptk.many dispatch_break_fault ;;
#endif
mov r30=cr.ipsr;;
@@ -471,15 +485,30 @@
cmp.eq p7,p0=r22,r17;
(p7) br.spnt.few dispatch_break_fault ;;
#endif
-#ifdef FAST_REFLECT_CNT
- movl r20=fast_reflect_count+((0x2c00>>8)*8);;
- ld8 r21=[r20];;
- adds r21=1,r21;;
- st8 [r20]=r21;;
-#endif
+ movl r20=0x2c00;
// save iim in shared_info
adds r21=XSI_IIM_OFS-XSI_PSR_IC_OFS,r18 ;;
st8 [r21]=r17;;
+ // fall through
+
+
+// reflect to domain ivt+r20
+// sets up isr,iip,ipsr,ifs (FIXME: do iipa too)
+// r16 == cr.isr
+// r18 == XSI_PSR_IC
+// r20 == offset into ivt
+// r29 == iip
+// r30 == ipsr
+// r31 == pr
+ENTRY(fast_reflect)
+#ifdef FAST_REFLECT_CNT
+ movl r22=fast_reflect_count;
+ shr r23=r20,5;;
+ add r22=r22,r23;;
+ ld8 r21=[r22];;
+ adds r21=1,r21;;
+ st8 [r22]=r21;;
+#endif
// save iip in shared_info (DON'T POINT TO NEXT INSTRUCTION!)
adds r21=XSI_IIP_OFS-XSI_PSR_IC_OFS,r18 ;;
st8 [r21]=r29;;
@@ -504,9 +533,9 @@
or r30=r30,r28;;
and r30=r30,r27;;
// also set shared_mem ipsr.i and ipsr.ic appropriately
- ld8 r20=[r18];;
- extr.u r22=r20,32,32
- cmp4.eq p6,p7=r20,r0;;
+ ld8 r24=[r18];;
+ extr.u r22=r24,32,32
+ cmp4.eq p6,p7=r24,r0;;
(p6) dep r30=0,r30,IA64_PSR_IC_BIT,1
(p7) dep r30=-1,r30,IA64_PSR_IC_BIT,1 ;;
cmp4.eq p6,p7=r22,r0;;
@@ -520,13 +549,13 @@
// cover and set shared_mem precover_ifs to cr.ifs
// set shared_mem ifs and incomplete_regframe to 0
cover ;;
- mov r20=cr.ifs;;
+ mov r24=cr.ifs;;
adds r21=XSI_INCOMPL_REG_OFS-XSI_PSR_IC_OFS,r18 ;;
st4 [r21]=r0 ;;
adds r21=XSI_IFS_OFS-XSI_PSR_IC_OFS,r18 ;;
st8 [r21]=r0 ;;
adds r21=XSI_PRECOVER_IFS_OFS-XSI_PSR_IC_OFS,r18 ;;
- st8 [r21]=r20 ;;
+ st8 [r21]=r24 ;;
// vpsr.i = vpsr.ic = 0 on delivery of interruption
st8 [r18]=r0;;
// FIXME: need to save iipa and isr to be arch-compliant
@@ -534,22 +563,30 @@
mov r22=IA64_KR(CURRENT);;
adds r22=IA64_VCPU_IVA_OFFSET,r22;;
ld8 r23=[r22];;
- movl r24=0x2c00;;
- add r24=r24,r23;;
- mov cr.iip=r24;;
+ add r20=r20,r23;;
+ mov cr.iip=r20;;
// OK, now all set to go except for switch to virtual bank0
mov r30=r2; mov r29=r3;;
adds r2=XSI_BANK1_OFS-XSI_PSR_IC_OFS,r18;
adds r3=(XSI_BANK1_OFS+8)-XSI_PSR_IC_OFS,r18;;
bsw.1;;
- st8 [r2]=r16,16; st8 [r3]=r17,16 ;;
- st8 [r2]=r18,16; st8 [r3]=r19,16 ;;
- st8 [r2]=r20,16; st8 [r3]=r21,16 ;;
- st8 [r2]=r22,16; st8 [r3]=r23,16 ;;
- st8 [r2]=r24,16; st8 [r3]=r25,16 ;;
- st8 [r2]=r26,16; st8 [r3]=r27,16 ;;
- st8 [r2]=r28,16; st8 [r3]=r29,16 ;;
- st8 [r2]=r30,16; st8 [r3]=r31,16 ;;
+ // FIXME: need to handle ar.unat!
+ .mem.offset 0,0; st8.spill [r2]=r16,16;
+ .mem.offset 8,0; st8.spill [r3]=r17,16 ;;
+ .mem.offset 0,0; st8.spill [r2]=r18,16;
+ .mem.offset 8,0; st8.spill [r3]=r19,16 ;;
+ .mem.offset 0,0; st8.spill [r2]=r20,16;
+ .mem.offset 8,0; st8.spill [r3]=r21,16 ;;
+ .mem.offset 0,0; st8.spill [r2]=r22,16;
+ .mem.offset 8,0; st8.spill [r3]=r23,16 ;;
+ .mem.offset 0,0; st8.spill [r2]=r24,16;
+ .mem.offset 8,0; st8.spill [r3]=r25,16 ;;
+ .mem.offset 0,0; st8.spill [r2]=r26,16;
+ .mem.offset 8,0; st8.spill [r3]=r27,16 ;;
+ .mem.offset 0,0; st8.spill [r2]=r28,16;
+ .mem.offset 8,0; st8.spill [r3]=r29,16 ;;
+ .mem.offset 0,0; st8.spill [r2]=r30,16;
+ .mem.offset 8,0; st8.spill [r3]=r31,16 ;;
movl r31=XSI_IPSR;;
bsw.0 ;;
mov r2=r30; mov r3=r29;;
@@ -558,6 +595,44 @@
mov pr=r31,-1 ;;
rfi
;;
+
+// reflect access faults (0x2400,0x2800,0x5300) directly to domain
+// r16 == isr
+// r17 == ifa
+// r19 == reflect number (only pass-thru to dispatch_reflection)
+// r20 == offset into ivt
+// r31 == pr
+GLOBAL_ENTRY(fast_access_reflect)
+#ifndef FAST_ACCESS_REFLECT // see beginning of file
+ br.spnt.few dispatch_reflection ;;
+#endif
+ mov r30=cr.ipsr;;
+ mov r29=cr.iip;;
+ extr.u r21=r30,IA64_PSR_BE_BIT,1 ;;
+ cmp.ne p7,p0=r21,r0
+(p7) br.spnt.few dispatch_reflection ;;
+ extr.u r21=r30,IA64_PSR_PP_BIT,1 ;;
+ cmp.ne p7,p0=r21,r0
+(p7) br.spnt.few dispatch_reflection ;;
+ extr.u r21=r30,IA64_PSR_CPL0_BIT,2 ;;
+ cmp.eq p7,p0=r21,r0
+(p7) br.spnt.few dispatch_reflection ;;
+ movl r18=XSI_PSR_IC;;
+ ld8 r21=[r18];;
+ cmp.eq p7,p0=r0,r21
+(p7) br.spnt.few dispatch_reflection ;;
+ // set shared_mem ifa, FIXME: should we validate it?
+ mov r17=cr.ifa;;
+ adds r21=XSI_IFA_OFS-XSI_PSR_IC_OFS,r18 ;;
+ st8 [r21]=r17 ;;
+ // get rr[ifa] and save to itir in shared memory (extra bits ignored)
+ shr.u r22=r17,61
+ adds r23=XSI_ITIR_OFS-XSI_PSR_IC_OFS,r18
+ adds r21=XSI_RR0_OFS-XSI_PSR_IC_OFS,r18 ;;
+ shladd r22=r22,3,r21;;
+ ld8 r22=[r22];;
+ st8 [r23]=r22;;
+ br.cond.sptk.many fast_reflect;;
// ensure that, if giving up, registers at entry to fast_hyperprivop unchanged
@@ -606,7 +681,7 @@
cmp.ltu p0,p7=r22,r23 ;; // if !(iip<low) &&
(p7) cmp.geu p0,p7=r22,r24 ;; // !(iip>=high)
(p7) br.spnt.few dispatch_break_fault ;;
-#ifndef RFI_TO_INTERRUPT
+#ifndef RFI_TO_INTERRUPT // see beginning of file
cmp.ne p6,p0=r30,r0
(p6) br.cond.spnt.few dispatch_break_fault ;;
#endif
@@ -1312,8 +1387,146 @@
;;
END(hyper_set_rr)
+// this routine was derived from optimized assembly output from
+// vcpu_thash so it is dense and difficult to read but it works
+// On entry:
+// r18 == XSI_PSR_IC
+// r31 == pr
+GLOBAL_ENTRY(hyper_thash)
+#ifdef FAST_HYPERPRIVOP_CNT
+ movl r20=fast_hyperpriv_cnt+(8*XEN_HYPER_THASH);;
+ ld8 r21=[r20];;
+ adds r21=1,r21;;
+ st8 [r20]=r21;;
+#endif
+ shr.u r20 = r8, 61
+ addl r25 = 1, r0
+ movl r17 = 0xe000000000000000
+ ;;
+ and r21 = r17, r8 // VHPT_Addr1
+ ;;
+ shladd r28 = r20, 3, r18
+ adds r19 = XSI_PTA_OFS-XSI_PSR_IC_OFS, r18
+ ;;
+ adds r27 = XSI_RR0_OFS-XSI_PSR_IC_OFS, r28
+ addl r28 = 32767, r0
+ ld8 r24 = [r19] // pta
+ ;;
+ ld8 r23 = [r27] // rrs[vadr>>61]
+ extr.u r26 = r24, 2, 6
+ ;;
+ extr.u r22 = r23, 2, 6
+ shl r30 = r25, r26
+ ;;
+ shr.u r19 = r8, r22
+ shr.u r29 = r24, 15
+ ;;
+ adds r17 = -1, r30
+ ;;
+ shladd r27 = r19, 3, r0
+ extr.u r26 = r17, 15, 46
+ ;;
+ andcm r24 = r29, r26
+ and r19 = r28, r27
+ shr.u r25 = r27, 15
+ ;;
+ and r23 = r26, r25
+ ;;
+ or r22 = r24, r23
+ ;;
+ dep.z r20 = r22, 15, 46
+ ;;
+ or r16 = r20, r21
+ ;;
+ or r8 = r19, r16
+ // done, update iip/ipsr to next instruction
+ mov r24=cr.ipsr
+ mov r25=cr.iip;;
+ extr.u r26=r24,41,2 ;;
+ cmp.eq p6,p7=2,r26 ;;
+(p6) mov r26=0
+(p6) adds r25=16,r25
+(p7) adds r26=1,r26
+ ;;
+ dep r24=r26,r24,41,2
+ ;;
+ mov cr.ipsr=r24
+ mov cr.iip=r25
+ mov pr=r31,-1 ;;
+ rfi
+ ;;
+END(hyper_thash)
+
ENTRY(hyper_ptc_ga)
- br.spnt.many dispatch_break_fault ;;
+#ifdef CONFIG_SMP
+FIXME: ptc.ga instruction requires spinlock for SMP
+#endif
+ // FIXME: validate not flushing Xen addresses
+#ifdef FAST_HYPERPRIVOP_CNT
+ movl r20=fast_hyperpriv_cnt+(8*XEN_HYPER_PTC_GA);;
+ ld8 r21=[r20];;
+ adds r21=1,r21;;
+ st8 [r20]=r21;;
+#endif
+ mov r28=r8
+ extr.u r19=r9,2,6 // addr_range=1<<((r9&0xfc)>>2)
+ mov r20=1
+ shr.u r24=r8,61
+ addl r27=56,r0 // PAGE_SHIFT<<2 (for ptc.ga)
+ movl r26=0x8000000000000000 // INVALID_TI_TAG
+ mov r30=ar.lc
+ ;;
+ shl r19=r20,r19
+ cmp.eq p7,p0=7,r24
+(p7) br.spnt.many dispatch_break_fault ;; // slow way for rr7
+ ;;
+ cmp.le p7,p0=r19,r0 // skip flush if size<=0
+(p7) br.cond.dpnt 2f ;;
+ extr.u r24=r19,0,PAGE_SHIFT
+ shr.u r23=r19,PAGE_SHIFT ;; // repeat loop for n pages
+ cmp.ne p7,p0=r24,r0 ;;
+(p7) adds r23=1,r23 ;; // n_pages<size<n_pages+1? extra iter
+ mov ar.lc=r23
+ movl r29=PAGE_SIZE;;
+1:
+ thash r25=r28 ;;
+ adds r25=16,r25 ;;
+ ld8 r24=[r25] ;;
+ // FIXME: should check if tag matches, not just blow it away
+ or r24=r26,r24 ;; // vhpt_entry->ti_tag = 1
+ st8 [r25]=r24
+ ptc.ga r28,r27 ;;
+ srlz.i ;;
+ add r28=r29,r28
+ br.cloop.sptk.few 1b
+ ;;
+2:
+ mov ar.lc=r30 ;;
+ mov r29=cr.ipsr
+ mov r30=cr.iip;;
+ mov r27=IA64_KR(CURRENT);;
+ adds r25=IA64_VCPU_DTLB_OFFSET,r27
+ adds r26=IA64_VCPU_ITLB_OFFSET,r27;;
+ ld8 r24=[r25]
+ ld8 r27=[r26] ;;
+ and r24=-2,r24
+ and r27=-2,r27 ;;
+ st8 [r25]=r24 // set 1-entry i/dtlb as not present
+ st8 [r26]=r27 ;;
+ // increment to point to next instruction
+ extr.u r26=r29,41,2 ;;
+ cmp.eq p6,p7=2,r26 ;;
+(p6) mov r26=0
+(p6) adds r30=16,r30
+(p7) adds r26=1,r26
+ ;;
+ dep r29=r26,r29,41,2
+ ;;
+ mov cr.ipsr=r29
+ mov cr.iip=r30
+ mov pr=r31,-1 ;;
+ rfi
+ ;;
END(hyper_ptc_ga)
ENTRY(hyper_itc_d)
@@ -1323,4 +1536,3 @@
ENTRY(hyper_itc_i)
br.spnt.many dispatch_break_fault ;;
END(hyper_itc_i)
-
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/vmx_entry.S
--- a/xen/arch/ia64/vmx_entry.S Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/vmx_entry.S Fri Jul 15 13:39:50 2005
@@ -217,7 +217,7 @@
alloc loc0=ar.pfs,0,1,1,0
adds out0=16,r12
;;
- br.call.sptk.many b0=vmx_deliver_pending_interrupt
+ br.call.sptk.many b0=leave_hypervisor_tail
mov ar.pfs=loc0
adds r8=IA64_VPD_BASE_OFFSET,r13
;;
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/vmx_init.c
--- a/xen/arch/ia64/vmx_init.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/vmx_init.c Fri Jul 15 13:39:50 2005
@@ -40,6 +40,7 @@
#include <asm/vmmu.h>
#include <public/arch-ia64.h>
#include <asm/vmx_phy_mode.h>
+#include <asm/processor.h>
#include <asm/vmx.h>
#include <xen/mm.h>
@@ -225,6 +226,17 @@
vmx_purge_double_mapping(dom_rr7, KERNEL_START,
(u64)v->arch.vtlb->ts->vhpt->hash);
+ /* Need to save KR when domain switch, though HV itself doesn;t
+ * use them.
+ */
+ v->arch.arch_vmx.vkr[0] = ia64_get_kr(0);
+ v->arch.arch_vmx.vkr[1] = ia64_get_kr(1);
+ v->arch.arch_vmx.vkr[2] = ia64_get_kr(2);
+ v->arch.arch_vmx.vkr[3] = ia64_get_kr(3);
+ v->arch.arch_vmx.vkr[4] = ia64_get_kr(4);
+ v->arch.arch_vmx.vkr[5] = ia64_get_kr(5);
+ v->arch.arch_vmx.vkr[6] = ia64_get_kr(6);
+ v->arch.arch_vmx.vkr[7] = ia64_get_kr(7);
}
/* Even guest is in physical mode, we still need such double mapping */
@@ -234,6 +246,7 @@
u64 status, psr;
u64 old_rr0, dom_rr7, rr0_xen_start, rr0_vhpt;
u64 pte_xen, pte_vhpt;
+ int i;
status = ia64_pal_vp_restore(v->arch.arch_vmx.vpd, 0);
if (status != PAL_STATUS_SUCCESS)
@@ -246,6 +259,14 @@
(u64)v->arch.vtlb->ts->vhpt->hash,
pte_xen, pte_vhpt);
+ ia64_set_kr(0, v->arch.arch_vmx.vkr[0]);
+ ia64_set_kr(1, v->arch.arch_vmx.vkr[1]);
+ ia64_set_kr(2, v->arch.arch_vmx.vkr[2]);
+ ia64_set_kr(3, v->arch.arch_vmx.vkr[3]);
+ ia64_set_kr(4, v->arch.arch_vmx.vkr[4]);
+ ia64_set_kr(5, v->arch.arch_vmx.vkr[5]);
+ ia64_set_kr(6, v->arch.arch_vmx.vkr[6]);
+ ia64_set_kr(7, v->arch.arch_vmx.vkr[7]);
/* Guest vTLB is not required to be switched explicitly, since
* anchored in vcpu */
}
@@ -290,7 +311,7 @@
vmx_create_vp(v);
/* Set this ed to be vmx */
- v->arch.arch_vmx.flags = 1;
+ set_bit(ARCH_VMX_VMCS_LOADED, &v->arch.arch_vmx.flags);
/* Other vmx specific initialization work */
}
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/dom_fw.c
--- a/xen/arch/ia64/dom_fw.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/dom_fw.c Fri Jul 15 13:39:50 2005
@@ -154,7 +154,7 @@
return 1;
}
-extern void pal_emulator_static (void);
+extern struct ia64_pal_retval pal_emulator_static (unsigned long);
/* Macro to emulate SAL call using legacy IN and OUT calls to CF8, CFC etc.. */
@@ -220,17 +220,14 @@
*/
status = 0;
if (index == SAL_FREQ_BASE) {
- switch (in1) {
+ if (!running_on_sim)
+ status = ia64_sal_freq_base(in1,&r9,&r10);
+ else switch (in1) {
case SAL_FREQ_BASE_PLATFORM:
r9 = 200000000;
break;
case SAL_FREQ_BASE_INTERVAL_TIMER:
- /*
- * Is this supposed to be the cr.itc frequency
- * or something platform specific? The SAL
- * doc ain't exactly clear on this...
- */
r9 = 700000000;
break;
@@ -285,6 +282,116 @@
return ((struct sal_ret_values) {status, r9, r10, r11});
}
+struct ia64_pal_retval
+xen_pal_emulator(unsigned long index, unsigned long in1,
+ unsigned long in2, unsigned long in3)
+{
+ long r9 = 0;
+ long r10 = 0;
+ long r11 = 0;
+ long status = -1;
+
+ if (running_on_sim) return pal_emulator_static(index);
+ if (index >= PAL_COPY_PAL) {
+ printk("xen_pal_emulator: UNIMPLEMENTED PAL CALL %d!!!!\n",
+ index);
+ }
+ else switch (index) {
+ case PAL_MEM_ATTRIB:
+ status = ia64_pal_mem_attrib(&r9);
+ break;
+ case PAL_FREQ_BASE:
+ status = ia64_pal_freq_base(&r9);
+ break;
+ case PAL_PROC_GET_FEATURES:
+ status = ia64_pal_proc_get_features(&r9,&r10,&r11);
+ break;
+ case PAL_BUS_GET_FEATURES:
+ status = ia64_pal_bus_get_features(&r9,&r10,&r11);
+ break;
+ case PAL_FREQ_RATIOS:
+ status = ia64_pal_freq_ratios(&r9,&r10,&r11);
+ break;
+ case PAL_PTCE_INFO:
+ {
+ ia64_ptce_info_t ptce;
+ status = ia64_get_ptce(&ptce);
+ if (status != 0) break;
+ r9 = ptce.base;
+ r10 = (ptce.count[0]<<32)|(ptce.count[1]&0xffffffffL);
+ r11 = (ptce.stride[0]<<32)|(ptce.stride[1]&0xffffffffL);
+ }
+ break;
+ case PAL_VERSION:
+ status = ia64_pal_version(&r9,&r10);
+ break;
+ case PAL_VM_PAGE_SIZE:
+ status = ia64_pal_vm_page_size(&r9,&r10);
+ break;
+ case PAL_DEBUG_INFO:
+ status = ia64_pal_debug_info(&r9,&r10);
+ break;
+ case PAL_CACHE_SUMMARY:
+ status = ia64_pal_cache_summary(&r9,&r10);
+ break;
+ case PAL_VM_SUMMARY:
+ status = ia64_pal_vm_summary(&r9,&r10);
+ break;
+ case PAL_RSE_INFO:
+ status = ia64_pal_rse_info(&r9,&r10);
+ break;
+ case PAL_VM_INFO:
+ status = ia64_pal_vm_info(in1,in2,&r9,&r10);
+ break;
+ case PAL_REGISTER_INFO:
+ status = ia64_pal_register_info(in1,&r9,&r10);
+ break;
+ case PAL_CACHE_FLUSH:
+ /* FIXME */
+ printk("PAL_CACHE_FLUSH NOT IMPLEMENTED!\n");
+ BUG();
+ break;
+ case PAL_PERF_MON_INFO:
+ {
+ unsigned long pm_buffer[16];
+ int i;
+ status = ia64_pal_perf_mon_info(pm_buffer,&r9);
+ if (status != 0) {
+ while(1)
+ printk("PAL_PERF_MON_INFO fails
ret=%d\n",status);
+ break;
+ }
+ if (copy_to_user((void __user *)in1,pm_buffer,128)) {
+ while(1)
+ printk("xen_pal_emulator: PAL_PERF_MON_INFO "
+ "can't copy to user!!!!\n");
+ status = -1;
+ break;
+ }
+ }
+ break;
+ case PAL_CACHE_INFO:
+ {
+ pal_cache_config_info_t ci;
+ status = ia64_pal_cache_config_info(in1,in2,&ci);
+ if (status != 0) break;
+ r9 = ci.pcci_info_1.pcci1_data;
+ r10 = ci.pcci_info_2.pcci2_data;
+ }
+ break;
+ case PAL_VM_TR_READ: /* FIXME: vcpu_get_tr?? */
+ printk("PAL_VM_TR_READ NOT IMPLEMENTED, IGNORED!\n");
+ break;
+ case PAL_HALT_INFO: /* inappropriate info for guest? */
+ printk("PAL_HALT_INFO NOT IMPLEMENTED, IGNORED!\n");
+ break;
+ default:
+ printk("xen_pal_emulator: UNIMPLEMENTED PAL CALL %d!!!!\n",
+ index);
+ break;
+ }
+ return ((struct ia64_pal_retval) {status, r9, r10, r11});
+}
#define NFUNCPTRS 20
diff -r 35b74976f598 -r a83ac0806d6b xen/include/asm-ia64/vmx_vpd.h
--- a/xen/include/asm-ia64/vmx_vpd.h Fri Jul 15 12:52:02 2005
+++ b/xen/include/asm-ia64/vmx_vpd.h Fri Jul 15 13:39:50 2005
@@ -19,8 +19,8 @@
* Kun Tian (Kevin Tian) (kevin.tian@xxxxxxxxx)
*/
-#ifndef _VPD_H_
-#define _VPD_H_
+#ifndef _ASM_IA64_VMX_VPD_H_
+#define _ASM_IA64_VMX_VPD_H_
#ifndef __ASSEMBLY__
@@ -123,6 +123,7 @@
vpd_t *vpd;
vtime_t vtm;
unsigned long vrr[8];
+ unsigned long vkr[8];
unsigned long mrr5;
unsigned long mrr6;
unsigned long mrr7;
@@ -145,6 +146,7 @@
#define ARCH_VMX_VMCS_LAUNCH 1 /* Needs VMCS launch */
#define ARCH_VMX_VMCS_RESUME 2 /* Needs VMCS resume */
#define ARCH_VMX_IO_WAIT 3 /* Waiting for I/O completion */
+#define ARCH_VMX_INTR_ASSIST 4 /* Need DM's assist to issue intr */
#define VMX_DEBUG 1
@@ -191,4 +193,4 @@
#define VPD_VMM_VAIL_START_OFFSET 31744
-#endif /* _VPD_H_ */
+#endif /* _ASM_IA64_VMX_VPD_H_ */
diff -r 35b74976f598 -r a83ac0806d6b xen/include/asm-ia64/xenprocessor.h
--- a/xen/include/asm-ia64/xenprocessor.h Fri Jul 15 12:52:02 2005
+++ b/xen/include/asm-ia64/xenprocessor.h Fri Jul 15 13:39:50 2005
@@ -166,6 +166,16 @@
};
} ipi_d_t;
+typedef union {
+ __u64 val;
+ struct {
+ __u64 ig0 : 4;
+ __u64 mic : 4;
+ __u64 rsv : 8;
+ __u64 mmi : 1;
+ __u64 ig1 : 47;
+ };
+} tpr_t;
#define IA64_ISR_CODE_MASK0 0xf
#define IA64_UNIMPL_DADDR_FAULT 0x30
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/vmx_hypercall.c
--- a/xen/arch/ia64/vmx_hypercall.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/vmx_hypercall.c Fri Jul 15 13:39:50 2005
@@ -141,21 +141,27 @@
static int do_set_shared_page(VCPU *vcpu, u64 gpa)
{
u64 shared_info, o_info;
+ struct domain *d = vcpu->domain;
+ struct vcpu *v;
if(vcpu->domain!=dom0)
return -EPERM;
shared_info = __gpa_to_mpa(vcpu->domain, gpa);
o_info = (u64)vcpu->domain->shared_info;
- vcpu->domain->shared_info= (shared_info_t *)__va(shared_info);
+ d->shared_info= (shared_info_t *)__va(shared_info);
/* Copy existing shared info into new page */
- if (!o_info) {
- memcpy((void*)vcpu->domain->shared_info, (void*)o_info, PAGE_SIZE);
- /* If original page belongs to xen heap, then relinguish back
- * to xen heap. Or else, leave to domain itself to decide.
- */
- if (likely(IS_XEN_HEAP_FRAME(virt_to_page(o_info))))
- free_xenheap_page(o_info);
- }
+ if (o_info) {
+ memcpy((void*)d->shared_info, (void*)o_info, PAGE_SIZE);
+ for_each_vcpu(d, v) {
+ v->vcpu_info = &d->shared_info->vcpu_data[v->vcpu_id];
+ }
+ /* If original page belongs to xen heap, then relinguish back
+ * to xen heap. Or else, leave to domain itself to decide.
+ */
+ if (likely(IS_XEN_HEAP_FRAME(virt_to_page(o_info))))
+ free_xenheap_page(o_info);
+ } else
+ memset(d->shared_info, 0, PAGE_SIZE);
return 0;
}
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/Makefile
--- a/xen/arch/ia64/Makefile Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/Makefile Fri Jul 15 13:39:50 2005
@@ -15,7 +15,7 @@
ifeq ($(CONFIG_VTI),y)
OBJS += vmx_init.o vmx_virt.o vmx_vcpu.o vmx_process.o vmx_vsa.o vmx_ivt.o \
vmx_phy_mode.o vmx_utility.o vmx_interrupt.o vmx_entry.o vmmu.o \
- vtlb.o mmio.o vlsapic.o vmx_hypercall.o mm.o
+ vtlb.o mmio.o vlsapic.o vmx_hypercall.o mm.o vmx_support.o pal_emul.o
endif
# perfmon.o
# unwind.o needed for kernel unwinding (rare)
diff -r 35b74976f598 -r a83ac0806d6b xen/include/asm-ia64/privop.h
--- a/xen/include/asm-ia64/privop.h Fri Jul 15 12:52:02 2005
+++ b/xen/include/asm-ia64/privop.h Fri Jul 15 13:39:50 2005
@@ -138,6 +138,19 @@
IA64_INST inst;
struct { unsigned long qp:6, un14:14, r3:7, x6:6, x3:3, un1:1, major:4; };
} INST64_M47;
+typedef union U_INST64_M1{
+ IA64_INST inst;
+ struct { unsigned long qp:6, r1:7, un7:7, r3:7, x:1, hint:2, x6:6, m:1,
major:4; };
+} INST64_M1;
+typedef union U_INST64_M4 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, un7:7, r2:7, r3:7, x:1, hint:2, x6:6, m:1,
major:4; };
+} INST64_M4;
+typedef union U_INST64_M6 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, f1:7, un7:7, r3:7, x:1, hint:2, x6:6, m:1,
major:4; };
+} INST64_M6;
+
#endif // CONFIG_VTI
typedef union U_INST64 {
@@ -151,6 +164,11 @@
INST64_I26 I26; // mov register to ar (I unit)
INST64_I27 I27; // mov immediate to ar (I unit)
INST64_I28 I28; // mov from ar (I unit)
+#ifdef CONFIG_VTI
+ INST64_M1 M1; // ld integer
+ INST64_M4 M4; // st integer
+ INST64_M6 M6; // ldfd floating pointer
+#endif // CONFIG_VTI
INST64_M28 M28; // purge translation cache entry
INST64_M29 M29; // mov register to ar (M unit)
INST64_M30 M30; // mov immediate to ar (M unit)
diff -r 35b74976f598 -r a83ac0806d6b xen/include/asm-ia64/domain.h
--- a/xen/include/asm-ia64/domain.h Fri Jul 15 12:52:02 2005
+++ b/xen/include/asm-ia64/domain.h Fri Jul 15 13:39:50 2005
@@ -42,8 +42,6 @@
* max_pages in domain struct, which indicates maximum memory size
*/
unsigned long max_pfn;
- unsigned int section_nr;
- mm_section_t *sections; /* Describe memory hole except for Dom0 */
#endif //CONFIG_VTI
u64 xen_vastart;
u64 xen_vaend;
@@ -88,6 +86,8 @@
void (*schedule_tail) (struct vcpu *);
struct trap_bounce trap_bounce;
thash_cb_t *vtlb;
+ char irq_new_pending;
+ char irq_new_condition; // vpsr.i/vtpr change, check for pending VHPI
//for phycial emulation
unsigned long old_rsc;
int mode_flags;
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/mm.c
--- a/xen/arch/ia64/mm.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/mm.c Fri Jul 15 13:39:50 2005
@@ -95,7 +95,7 @@
#include <asm/vmx_vcpu.h>
#include <asm/vmmu.h>
#include <asm/regionreg.h>
-
+#include <asm/vmx_mm_def.h>
/*
uregs->ptr is virtual address
uregs->val is pte value
@@ -109,8 +109,9 @@
mmu_update_t req;
ia64_rr rr;
thash_cb_t *hcb;
- thash_data_t entry={0};
+ thash_data_t entry={0},*ovl;
vcpu = current;
+ search_section_t sections;
hcb = vmx_vcpu_get_vtlb(vcpu);
for ( i = 0; i < count; i++ )
{
@@ -124,8 +125,18 @@
entry.cl = DSIDE_TLB;
rr = vmx_vcpu_rr(vcpu, req.ptr);
entry.ps = rr.ps;
+ entry.key = redistribute_rid(rr.rid);
entry.rid = rr.rid;
- vtlb_insert(hcb, &entry, req.ptr);
+ entry.vadr = PAGEALIGN(req.ptr,entry.ps);
+ sections.tr = 1;
+ sections.tc = 0;
+ ovl = thash_find_overlap(hcb, &entry, sections);
+ if (ovl) {
+ // generate MCA.
+ panic("Tlb conflict!!");
+ return;
+ }
+ thash_purge_and_insert(hcb, &entry);
}else if(cmd == MMU_MACHPHYS_UPDATE){
mfn = req.ptr >>PAGE_SHIFT;
gpfn = req.val;
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/vmx_process.c
--- a/xen/arch/ia64/vmx_process.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/vmx_process.c Fri Jul 15 13:39:50 2005
@@ -45,7 +45,9 @@
#include <asm/dom_fw.h>
#include <asm/vmx_vcpu.h>
#include <asm/kregs.h>
+#include <asm/vmx.h>
#include <asm/vmx_mm_def.h>
+#include <xen/mm.h>
/* reset all PSR field to 0, except up,mfl,mfh,pk,dt,rt,mc,it */
#define INITIAL_PSR_VALUE_AT_INTERRUPTION 0x0000001808028034
@@ -53,7 +55,7 @@
extern struct ia64_sal_retval pal_emulator_static(UINT64);
extern struct ia64_sal_retval
sal_emulator(UINT64,UINT64,UINT64,UINT64,UINT64,UINT64,UINT64,UINT64);
extern void rnat_consumption (VCPU *vcpu);
-
+#define DOMN_PAL_REQUEST 0x110000
IA64FAULT
vmx_ia64_handle_break (unsigned long ifa, struct pt_regs *regs, unsigned long
isr, unsigned long iim)
{
@@ -148,7 +150,10 @@
regs->r2);
#endif
vmx_vcpu_increment_iip(current);
- } else
+ }else if(iim == DOMN_PAL_REQUEST){
+ pal_emul(current);
+ vmx_vcpu_increment_iip(current);
+ } else
vmx_reflect_interruption(ifa,isr,iim,11);
}
@@ -187,26 +192,43 @@
// ONLY gets called from ia64_leave_kernel
// ONLY call with interrupts disabled?? (else might miss one?)
// NEVER successful if already reflecting a trap/fault because psr.i==0
-void vmx_deliver_pending_interrupt(struct pt_regs *regs)
+void leave_hypervisor_tail(struct pt_regs *regs)
{
struct domain *d = current->domain;
struct vcpu *v = current;
// FIXME: Will this work properly if doing an RFI???
if (!is_idle_task(d) ) { // always comes from guest
- //vcpu_poke_timer(v);
- //if (vcpu_deliverable_interrupts(v)) {
- // unsigned long isr = regs->cr_ipsr & IA64_PSR_RI;
- // foodpi();
- // reflect_interruption(0,isr,0,regs,IA64_EXTINT_VECTOR);
- //}
extern void vmx_dorfirfi(void);
struct pt_regs *user_regs = vcpu_regs(current);
+ if (local_softirq_pending())
+ do_softirq();
+ local_irq_disable();
+
if (user_regs != regs)
printk("WARNING: checking pending interrupt in nested
interrupt!!!\n");
- if (regs->cr_iip == *(unsigned long *)vmx_dorfirfi)
- return;
- vmx_check_pending_irq(v);
+
+ /* VMX Domain N has other interrupt source, saying DM */
+ if (test_bit(ARCH_VMX_INTR_ASSIST, &v->arch.arch_vmx.flags))
+ vmx_intr_assist(v);
+
+ /* FIXME: Check event pending indicator, and set
+ * pending bit if necessary to inject back to guest.
+ * Should be careful about window between this check
+ * and above assist, since IOPACKET_PORT shouldn't be
+ * injected into vmx domain.
+ *
+ * Now hardcode the vector as 0x10 temporarily
+ */
+ if
(event_pending(v)&&(!((v->arch.arch_vmx.in_service[0])&(1UL<<0x10)))) {
+ VPD_CR(v, irr[0]) |= 1UL << 0x10;
+ v->arch.irq_new_pending = 1;
+ }
+
+ if ( v->arch.irq_new_pending ) {
+ v->arch.irq_new_pending = 0;
+ vmx_check_pending_irq(v);
+ }
}
}
@@ -244,7 +266,11 @@
return;
}
if((vec==2)&&(!vpsr.dt)){
- physical_dtlb_miss(vcpu, vadr);
+
if(vcpu->domain!=dom0&&__gpfn_is_io(vcpu->domain,(vadr<<1)>>(PAGE_SHIFT+1))){
+ emulate_io_inst(vcpu,((vadr<<1)>>1),4); // UC
+ }else{
+ physical_dtlb_miss(vcpu, vadr);
+ }
return;
}
vrr = vmx_vcpu_rr(vcpu,vadr);
@@ -255,6 +281,11 @@
// prepare_if_physical_mode(vcpu);
if(data=vtlb_lookup_ex(vtlb, vrr.rid, vadr,type)){
+ if(vcpu->domain!=dom0&&type==DSIDE_TLB && __gpfn_is_io(vcpu->domain,
data->ppn>>(PAGE_SHIFT-12))){
+
vadr=(vadr&((1UL<<data->ps)-1))+(data->ppn>>(data->ps-12)<<data->ps);
+ emulate_io_inst(vcpu, vadr, data->ma);
+ return IA64_FAULT;
+ }
if ( data->ps != vrr.ps ) {
machine_tlb_insert(vcpu, data);
}
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/vmx_virt.c
--- a/xen/arch/ia64/vmx_virt.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/vmx_virt.c Fri Jul 15 13:39:50 2005
@@ -1276,7 +1276,13 @@
}
-
+static void post_emulation_action(VCPU *vcpu)
+{
+ if ( vcpu->arch.irq_new_condition ) {
+ vcpu->arch.irq_new_condition = 0;
+ vhpi_detection(vcpu);
+ }
+}
//#define BYPASS_VMAL_OPCODE
extern IA64_SLOT_TYPE slot_types[0x20][3];
@@ -1336,7 +1342,7 @@
slot = ((struct ia64_psr *)&(regs->cr_ipsr))->ri;
if (!slot) inst.inst = bundle.slot0;
else if (slot == 1)
- inst.inst = bundle.slot1a + (bundle.slot1b<<23);
+ inst.inst = bundle.slot1a + (bundle.slot1b<<18);
else if (slot == 2) inst.inst = bundle.slot2;
else printf("priv_handle_op: illegal slot: %d\n", slot);
slot_type = slot_types[bundle.template][slot];
@@ -1478,9 +1484,11 @@
status=IA64_FAULT;
break;
default:
- printf("unknown cause %d:\n", cause);
+ printf("unknown cause %d, iip: %lx, ipsr: %lx\n",
cause,regs->cr_iip,regs->cr_ipsr);
+ while(1);
/* For unknown cause, let hardware to re-execute */
status=IA64_RETRY;
+ break;
// panic("unknown cause in virtualization intercept");
};
@@ -1494,6 +1502,7 @@
}
recover_if_physical_mode(vcpu);
+ post_emulation_action (vcpu);
//TODO set_irq_check(v);
return;
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/vmx_vcpu.c
--- a/xen/arch/ia64/vmx_vcpu.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/vmx_vcpu.c Fri Jul 15 13:39:50 2005
@@ -22,8 +22,6 @@
* Yaozu Dong (Eddie Dong) (Eddie.dong@xxxxxxxxx)
* Xuefei Xu (Anthony Xu) (Anthony.xu@xxxxxxxxx)
*/
-
-
#include <linux/sched.h>
#include <public/arch-ia64.h>
@@ -71,8 +69,8 @@
//unsigned long last_guest_rsm = 0x0;
struct guest_psr_bundle{
- unsigned long ip;
- unsigned long psr;
+ unsigned long ip;
+ unsigned long psr;
};
struct guest_psr_bundle guest_psr_buf[100];
@@ -107,20 +105,24 @@
IA64_PSR_SS | IA64_PSR_ED | IA64_PSR_IA
));
+ if ( !old_psr.i && (value & IA64_PSR_I) ) {
+ // vpsr.i 0->1
+ vcpu->arch.irq_new_condition = 1;
+ }
new_psr.val=vmx_vcpu_get_psr(vcpu);
{
- struct xen_regs *regs = vcpu_regs(vcpu);
- guest_psr_buf[guest_psr_index].ip = regs->cr_iip;
- guest_psr_buf[guest_psr_index].psr = new_psr.val;
- if (++guest_psr_index >= 100)
- guest_psr_index = 0;
+ struct xen_regs *regs = vcpu_regs(vcpu);
+ guest_psr_buf[guest_psr_index].ip = regs->cr_iip;
+ guest_psr_buf[guest_psr_index].psr = new_psr.val;
+ if (++guest_psr_index >= 100)
+ guest_psr_index = 0;
}
#if 0
if (old_psr.i != new_psr.i) {
- if (old_psr.i)
- last_guest_rsm = vcpu_regs(vcpu)->cr_iip;
- else
- last_guest_rsm = 0;
+ if (old_psr.i)
+ last_guest_rsm = vcpu_regs(vcpu)->cr_iip;
+ else
+ last_guest_rsm = 0;
}
#endif
@@ -270,8 +272,8 @@
{
va &= ~ (PSIZE(ps)-1);
if ( va == 0x2000000002908000UL ||
- va == 0x600000000000C000UL ) {
- stop();
+ va == 0x600000000000C000UL ) {
+ stop();
}
if (tlb_debug) printf("%s at %lx %lx\n", str, va, 1UL<<ps);
}
@@ -433,4 +435,11 @@
return IA64_NO_FAULT;
}
-
+IA64FAULT
+vmx_vcpu_set_tpr(VCPU *vcpu, u64 val)
+{
+ VPD_CR(vcpu,tpr)=val;
+ vcpu->arch.irq_new_condition = 1;
+ return IA64_NO_FAULT;
+}
+
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/privop.c
--- a/xen/arch/ia64/privop.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/privop.c Fri Jul 15 13:39:50 2005
@@ -1033,6 +1033,41 @@
}
#endif
+extern unsigned long dtlb_translate_count;
+extern unsigned long tr_translate_count;
+extern unsigned long phys_translate_count;
+extern unsigned long vhpt_translate_count;
+extern unsigned long lazy_cover_count;
+extern unsigned long idle_when_pending;
+extern unsigned long pal_halt_light_count;
+extern unsigned long context_switch_count;
+
+int dump_misc_stats(char *buf)
+{
+ char *s = buf;
+ s += sprintf(s,"Virtual TR translations: %d\n",tr_translate_count);
+ s += sprintf(s,"Virtual VHPT translations: %d\n",vhpt_translate_count);
+ s += sprintf(s,"Virtual DTLB translations: %d\n",dtlb_translate_count);
+ s += sprintf(s,"Physical translations: %d\n",phys_translate_count);
+ s += sprintf(s,"Idle when pending: %d\n",idle_when_pending);
+ s += sprintf(s,"PAL_HALT_LIGHT (no pending):
%d\n",pal_halt_light_count);
+ s += sprintf(s,"context switches: %d\n",context_switch_count);
+ s += sprintf(s,"Lazy covers: %d\n",lazy_cover_count);
+ return s - buf;
+}
+
+void zero_misc_stats(void)
+{
+ dtlb_translate_count = 0;
+ tr_translate_count = 0;
+ phys_translate_count = 0;
+ vhpt_translate_count = 0;
+ lazy_cover_count = 0;
+ pal_halt_light_count = 0;
+ idle_when_pending = 0;
+ context_switch_count = 0;
+}
+
int dump_hyperprivop_counts(char *buf)
{
int i;
@@ -1072,6 +1107,7 @@
#ifdef PRIVOP_ADDR_COUNT
n += dump_privop_addrs(buf + n);
#endif
+ n += dump_misc_stats(buf + n);
if (len < TMPBUFLEN) return -1;
if (__copy_to_user(ubuf,buf,n)) return -1;
return n;
@@ -1086,6 +1122,7 @@
#ifdef PRIVOP_ADDR_COUNT
zero_privop_addrs();
#endif
+ zero_misc_stats();
zero_reflect_counts();
if (len < TMPBUFLEN) return -1;
if (__copy_to_user(ubuf,buf,n)) return -1;
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/vmx_phy_mode.c
--- a/xen/arch/ia64/vmx_phy_mode.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/vmx_phy_mode.c Fri Jul 15 13:39:50 2005
@@ -119,30 +119,67 @@
vcpu->arch.old_rsc = 0;
vcpu->arch.mode_flags = GUEST_IN_PHY;
- psr = ia64_clear_ic();
-
- ia64_set_rr((VRN0<<VRN_SHIFT), vcpu->domain->arch.emul_phy_rr0.rrval);
- ia64_srlz_d();
- ia64_set_rr((VRN4<<VRN_SHIFT), vcpu->domain->arch.emul_phy_rr4.rrval);
- ia64_srlz_d();
+ return;
+}
+
+extern u64 get_mfn(domid_t domid, u64 gpfn, u64 pages);
#if 0
- /* FIXME: temp workaround to support guest physical mode */
-ia64_itr(0x1, IA64_TEMP_PHYSICAL, dom0_start,
- pte_val(pfn_pte((dom0_start >> PAGE_SHIFT), PAGE_KERNEL)),
- 28);
-ia64_itr(0x2, IA64_TEMP_PHYSICAL, dom0_start,
- pte_val(pfn_pte((dom0_start >> PAGE_SHIFT), PAGE_KERNEL)),
- 28);
-ia64_srlz_i();
+void
+physical_itlb_miss_domn(VCPU *vcpu, u64 vadr)
+{
+ u64 psr;
+ IA64_PSR vpsr;
+ u64 mppn,gppn,mpp1,gpp1;
+ struct domain *d;
+ static u64 test=0;
+ d=vcpu->domain;
+ if(test)
+ panic("domn physical itlb miss happen\n");
+ else
+ test=1;
+ vpsr.val=vmx_vcpu_get_psr(vcpu);
+ gppn=(vadr<<1)>>13;
+ mppn = get_mfn(DOMID_SELF,gppn,1);
+ mppn=(mppn<<12)|(vpsr.cpl<<7);
+ gpp1=0;
+ mpp1 = get_mfn(DOMID_SELF,gpp1,1);
+ mpp1=(mpp1<<12)|(vpsr.cpl<<7);
+// if(vadr>>63)
+// mppn |= PHY_PAGE_UC;
+// else
+// mppn |= PHY_PAGE_WB;
+ mpp1 |= PHY_PAGE_WB;
+ psr=ia64_clear_ic();
+ ia64_itr(0x1, IA64_TEMP_PHYSICAL, vadr&(~0xfff), (mppn|PHY_PAGE_WB), 24);
+ ia64_srlz_i();
+ ia64_itr(0x2, IA64_TEMP_PHYSICAL, vadr&(~0xfff), (mppn|PHY_PAGE_WB), 24);
+ ia64_stop();
+ ia64_srlz_i();
+ ia64_itr(0x1, IA64_TEMP_PHYSICAL+1, vadr&(~0x8000000000000fffUL),
(mppn|PHY_PAGE_WB), 24);
+ ia64_srlz_i();
+ ia64_itr(0x2, IA64_TEMP_PHYSICAL+1, vadr&(~0x8000000000000fffUL),
(mppn|PHY_PAGE_WB), 24);
+ ia64_stop();
+ ia64_srlz_i();
+ ia64_itr(0x1, IA64_TEMP_PHYSICAL+2, gpp1&(~0xfff), mpp1, 28);
+ ia64_srlz_i();
+ ia64_itr(0x2, IA64_TEMP_PHYSICAL+2, gpp1&(~0xfff), mpp1, 28);
+ ia64_stop();
+ ia64_srlz_i();
+ ia64_set_psr(psr);
+ ia64_srlz_i();
+ return;
+}
#endif
- ia64_set_psr(psr);
- ia64_srlz_i();
- return;
-}
-
-extern u64 get_mfn(domid_t domid, u64 gpfn, u64 pages);
+
void
physical_itlb_miss(VCPU *vcpu, u64 vadr)
+{
+ physical_itlb_miss_dom0(vcpu, vadr);
+}
+
+
+void
+physical_itlb_miss_dom0(VCPU *vcpu, u64 vadr)
{
u64 psr;
IA64_PSR vpsr;
@@ -150,7 +187,11 @@
vpsr.val=vmx_vcpu_get_psr(vcpu);
gppn=(vadr<<1)>>13;
mppn = get_mfn(DOMID_SELF,gppn,1);
- mppn=(mppn<<12)|(vpsr.cpl<<7)|PHY_PAGE_WB;
+ mppn=(mppn<<12)|(vpsr.cpl<<7);
+// if(vadr>>63)
+// mppn |= PHY_PAGE_UC;
+// else
+ mppn |= PHY_PAGE_WB;
psr=ia64_clear_ic();
ia64_itc(1,vadr&(~0xfff),mppn,EMUL_PHY_PAGE_SHIFT);
@@ -159,12 +200,15 @@
return;
}
+
void
physical_dtlb_miss(VCPU *vcpu, u64 vadr)
{
u64 psr;
IA64_PSR vpsr;
u64 mppn,gppn;
+// if(vcpu->domain!=dom0)
+// panic("dom n physical dtlb miss happen\n");
vpsr.val=vmx_vcpu_get_psr(vcpu);
gppn=(vadr<<1)>>13;
mppn = get_mfn(DOMID_SELF,gppn,1);
@@ -209,6 +253,8 @@
* mode in same region
*/
if (is_physical_mode(vcpu)) {
+ if (vcpu->arch.mode_flags & GUEST_PHY_EMUL)
+ panic("Unexpected domain switch in phy emul\n");
ia64_set_rr((VRN0 << VRN_SHIFT),
vcpu->domain->arch.emul_phy_rr0.rrval);
ia64_set_rr((VRN4 << VRN_SHIFT),
@@ -262,15 +308,10 @@
psr=ia64_clear_ic();
mrr=vmx_vcpu_rr(vcpu,VRN0<<VRN_SHIFT);
- mrr.rid = VRID_2_MRID(vcpu,mrr.rid);
-//VRID_2_MRID(vcpu,mrr.rid);
- mrr.ve = 1;
- ia64_set_rr(VRN0<<VRN_SHIFT, mrr.rrval );
+ ia64_set_rr(VRN0<<VRN_SHIFT, vmx_vrrtomrr(vcpu, mrr.rrval));
ia64_srlz_d();
mrr=vmx_vcpu_rr(vcpu,VRN4<<VRN_SHIFT);
- mrr.rid = VRID_2_MRID(vcpu,mrr.rid);
- mrr.ve = 1;
- ia64_set_rr(VRN4<<VRN_SHIFT, mrr.rrval );
+ ia64_set_rr(VRN4<<VRN_SHIFT, vmx_vrrtomrr(vcpu, mrr.rrval));
ia64_srlz_d();
ia64_set_psr(psr);
ia64_srlz_i();
@@ -377,8 +418,10 @@
void
prepare_if_physical_mode(VCPU *vcpu)
{
- if (is_physical_mode(vcpu))
+ if (is_physical_mode(vcpu)) {
+ vcpu->arch.mode_flags |= GUEST_PHY_EMUL;
switch_to_virtual_rid(vcpu);
+ }
return;
}
@@ -386,8 +429,10 @@
void
recover_if_physical_mode(VCPU *vcpu)
{
- if (is_physical_mode(vcpu))
+ if (is_physical_mode(vcpu)) {
+ vcpu->arch.mode_flags &= ~GUEST_PHY_EMUL;
switch_to_physical_rid(vcpu);
- return;
-}
-
+ }
+ return;
+}
+
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/domain.c
--- a/xen/arch/ia64/domain.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/domain.c Fri Jul 15 13:39:50 2005
@@ -37,10 +37,13 @@
#include <asm/asm-offsets.h> /* for IA64_THREAD_INFO_SIZE */
#include <asm/vcpu.h> /* for function declarations */
+#include <public/arch-ia64.h>
#ifdef CONFIG_VTI
#include <asm/vmx.h>
#include <asm/vmx_vcpu.h>
+#include <asm/vmx_vpd.h>
#include <asm/pal.h>
+#include <public/io/ioreq.h>
#endif // CONFIG_VTI
#define CONFIG_DOMAIN0_CONTIGUOUS
@@ -203,18 +206,20 @@
* after up.
*/
d->shared_info = (void *)alloc_xenheap_page();
-
- /* FIXME: Because full virtual cpu info is placed in this area,
- * it's unlikely to put it into one shareinfo page. Later
- * need split vcpu context from vcpu_info and conforms to
- * normal xen convention.
+ /* Now assume all vcpu info and event indicators can be
+ * held in one shared page. Definitely later we need to
+ * consider more about it
*/
- v->vcpu_info = (void *)alloc_xenheap_page();
- if (!v->vcpu_info) {
- printk("ERROR/HALTING: CAN'T ALLOC PAGE\n");
- while (1);
- }
- memset(v->vcpu_info, 0, PAGE_SIZE);
+
+ memset(d->shared_info, 0, PAGE_SIZE);
+ v->vcpu_info = &d->shared_info->vcpu_data[v->vcpu_id];
+ /* Mask all events, and specific port will be unmasked
+ * when customer subscribes to it.
+ */
+ if(v == d->vcpu[0]) {
+ memset(&d->shared_info->evtchn_mask[0], 0xff,
+ sizeof(d->shared_info->evtchn_mask));
+ }
/* Allocate per-domain vTLB and vhpt */
v->arch.vtlb = init_domain_tlb(v);
@@ -291,6 +296,7 @@
c->shared = v->domain->shared_info->arch;
}
+#ifndef CONFIG_VTI
int arch_set_info_guest(struct vcpu *v, struct vcpu_guest_context *c)
{
struct pt_regs *regs = (struct pt_regs *) ((unsigned long) v +
IA64_STK_OFFSET) - 1;
@@ -312,6 +318,79 @@
v->domain->shared_info->arch = c->shared;
return 0;
}
+#else // CONFIG_VTI
+int arch_set_info_guest(
+ struct vcpu *v, struct vcpu_guest_context *c)
+{
+ struct domain *d = v->domain;
+ int i, rc, ret;
+ unsigned long progress = 0;
+
+ if ( test_bit(_VCPUF_initialised, &v->vcpu_flags) )
+ return 0;
+
+ /* Lazy FP not implemented yet */
+ clear_bit(_VCPUF_fpu_initialised, &v->vcpu_flags);
+ if ( c->flags & VGCF_FPU_VALID )
+ set_bit(_VCPUF_fpu_initialised, &v->vcpu_flags);
+
+ /* Sync d/i cache conservatively, after domain N is loaded */
+ ret = ia64_pal_cache_flush(3, 0, &progress, NULL);
+ if (ret != PAL_STATUS_SUCCESS)
+ panic("PAL CACHE FLUSH failed for dom[%d].\n",
+ v->domain->domain_id);
+ DPRINTK("Sync i/d cache for dom%d image SUCC\n",
+ v->domain->domain_id);
+
+ /* Physical mode emulation initialization, including
+ * emulation ID allcation and related memory request
+ */
+ physical_mode_init(v);
+
+ /* FIXME: only support PMT table continuously by far */
+ d->arch.pmt = __va(c->pt_base);
+ d->arch.max_pfn = c->pt_max_pfn;
+ v->arch.arch_vmx.vmx_platform.shared_page_va = __va(c->share_io_pg);
+ memset((char *)__va(c->share_io_pg),0,PAGE_SIZE);
+
+ if (c->flags & VGCF_VMX_GUEST) {
+ if (!vmx_enabled)
+ panic("No VMX hardware feature for vmx domain.\n");
+
+ vmx_final_setup_domain(d);
+
+ /* One more step to enable interrupt assist */
+ set_bit(ARCH_VMX_INTR_ASSIST, &v->arch.arch_vmx.flags);
+ }
+
+ vlsapic_reset(v);
+ vtm_init(v);
+
+ /* Only open one port for I/O and interrupt emulation */
+ if (v == d->vcpu[0]) {
+ memset(&d->shared_info->evtchn_mask[0], 0xff,
+ sizeof(d->shared_info->evtchn_mask));
+ clear_bit(IOPACKET_PORT, &d->shared_info->evtchn_mask[0]);
+ }
+ /* Setup domain context. Actually IA-64 is a bit different with
+ * x86, with almost all system resources better managed by HV
+ * directly. CP only needs to provide start IP of guest, which
+ * ideally is the load address of guest Firmware.
+ */
+ new_thread(v, c->guest_iip, 0, 0);
+
+
+ d->xen_vastart = 0xf000000000000000;
+ d->xen_vaend = 0xf300000000000000;
+ d->arch.breakimm = 0x1000 + d->domain_id;
+ v->arch._thread.on_ustack = 0;
+
+ /* Don't redo final setup */
+ set_bit(_VCPUF_initialised, &v->vcpu_flags);
+
+ return 0;
+}
+#endif // CONFIG_VTI
void arch_do_boot_vcpu(struct vcpu *v)
{
@@ -361,7 +440,10 @@
init_all_rr(v);
if (VMX_DOMAIN(v)) {
- VMX_VPD(v,vgr[12]) = dom_fw_setup(d,saved_command_line,256L);
+ if (d == dom0) {
+ VMX_VPD(v,vgr[12]) =
dom_fw_setup(d,saved_command_line,256L);
+ printk("new_thread, done with dom_fw_setup\n");
+ }
/* Virtual processor context setup */
VMX_VPD(v, vpsr) = IA64_PSR_BN;
VPD_CR(v, dcr) = 0;
@@ -556,6 +638,7 @@
}
// FIXME: ONLY USE FOR DOMAIN PAGE_SIZE == PAGE_SIZE
+#ifndef CONFIG_VTI
unsigned long domain_mpa_to_imva(struct domain *d, unsigned long mpaddr)
{
unsigned long pte = lookup_domain_mpa(d,mpaddr);
@@ -566,6 +649,14 @@
imva |= mpaddr & ~PAGE_MASK;
return(imva);
}
+#else // CONFIG_VTI
+unsigned long domain_mpa_to_imva(struct domain *d, unsigned long mpaddr)
+{
+ unsigned long imva = __gpa_to_mpa(d, mpaddr);
+
+ return __va(imva);
+}
+#endif // CONFIG_VTI
// remove following line if not privifying in memory
//#define HAVE_PRIVIFY_MEMORY
@@ -812,6 +903,17 @@
/* ... */
}
+/*
+ * Domain 0 has direct access to all devices absolutely. However
+ * the major point of this stub here, is to allow alloc_dom_mem
+ * handled with order > 0 request. Dom0 requires that bit set to
+ * allocate memory for other domains.
+ */
+void physdev_init_dom0(struct domain *d)
+{
+ set_bit(_DOMF_physdev_access, &d->domain_flags);
+}
+
extern unsigned long running_on_sim;
unsigned int vmx_dom0 = 0;
int construct_dom0(struct domain *d,
@@ -963,6 +1065,7 @@
set_bit(_DOMF_constructed, &d->domain_flags);
new_thread(v, pkern_entry, 0, 0);
+ physdev_init_dom0(d);
// FIXME: Hack for keyboard input
#ifdef CLONE_DOMAIN0
if (d == dom0)
@@ -978,6 +1081,8 @@
return 0;
}
+
+
#else //CONFIG_VTI
int construct_dom0(struct domain *d,
diff -r 35b74976f598 -r a83ac0806d6b xen/include/asm-ia64/ia64_int.h
--- a/xen/include/asm-ia64/ia64_int.h Fri Jul 15 12:52:02 2005
+++ b/xen/include/asm-ia64/ia64_int.h Fri Jul 15 13:39:50 2005
@@ -3,11 +3,11 @@
//#include "ia64.h"
-#define IA64_VHPT_TRANS_VECTOR 0x0000 /* UNUSED */
+#define IA64_VHPT_TRANS_VECTOR 0x0000
#define IA64_INST_TLB_VECTOR 0x0400
#define IA64_DATA_TLB_VECTOR 0x0800
-#define IA64_ALT_INST_TLB_VECTOR 0x0c00 /* UNUSED */
-#define IA64_ALT_DATA_TLB_VECTOR 0x1000 /* UNUSED */
+#define IA64_ALT_INST_TLB_VECTOR 0x0c00
+#define IA64_ALT_DATA_TLB_VECTOR 0x1000
#define IA64_DATA_NESTED_TLB_VECTOR 0x1400
#define IA64_INST_KEY_MISS_VECTOR 0x1800
#define IA64_DATA_KEY_MISS_VECTOR 0x1c00
@@ -33,12 +33,11 @@
#define IA64_TAKEN_BRANCH_TRAP_VECTOR 0x5f00
#define IA64_SINGLE_STEP_TRAP_VECTOR 0x6000
-#define IA64_NO_FAULT 0x0000
-#define IA64_RFI_IN_PROGRESS 0x0001
-#define IA64_RETRY 0x0002
+#define IA64_NO_FAULT 0x0001
+#define IA64_RFI_IN_PROGRESS 0x0002
+#define IA64_RETRY 0x0003
#ifdef CONFIG_VTI
-#define IA64_FAULT 0x0001
-#define IA64_INJ_FAULT 0x0005
+#define IA64_FAULT 0x0002
#endif //CONFIG_VTI
#define IA64_FORCED_IFA 0x0004
#define IA64_ILLOP_FAULT (IA64_GENEX_VECTOR | 0x00)
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/process.c
--- a/xen/arch/ia64/process.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/process.c Fri Jul 15 13:39:50 2005
@@ -75,8 +75,6 @@
}
#endif // CONFIG_VTI
}
-
-extern TR_ENTRY *match_tr(struct vcpu *v, unsigned long ifa);
void tdpfoo(void) { }
@@ -260,140 +258,29 @@
++pending_false_positive;
}
}
+unsigned long lazy_cover_count = 0;
int handle_lazy_cover(struct vcpu *v, unsigned long isr, struct pt_regs *regs)
{
if (!PSCB(v,interrupt_collection_enabled)) {
- if (isr & IA64_ISR_IR) {
-// printf("Handling lazy cover\n");
- PSCB(v,ifs) = regs->cr_ifs;
- PSCB(v,incomplete_regframe) = 1;
- regs->cr_ifs = 0;
- return(1); // retry same instruction with cr.ifs off
- }
+ PSCB(v,ifs) = regs->cr_ifs;
+ PSCB(v,incomplete_regframe) = 1;
+ regs->cr_ifs = 0;
+ lazy_cover_count++;
+ return(1); // retry same instruction with cr.ifs off
}
return(0);
}
-#define IS_XEN_ADDRESS(d,a) ((a >= d->xen_vastart) && (a <= d->xen_vaend))
-
-void xen_handle_domain_access(unsigned long address, unsigned long isr, struct
pt_regs *regs, unsigned long itir)
-{
- struct domain *d = (struct domain *) current->domain;
- struct domain *ed = (struct vcpu *) current;
- TR_ENTRY *trp;
- unsigned long psr = regs->cr_ipsr, mask, flags;
+void ia64_do_page_fault (unsigned long address, unsigned long isr, struct
pt_regs *regs, unsigned long itir)
+{
unsigned long iip = regs->cr_iip;
// FIXME should validate address here
- unsigned long pteval, mpaddr, ps;
- unsigned long lookup_domain_mpa(struct domain *,unsigned long);
- unsigned long match_dtlb(struct vcpu *,unsigned long, unsigned long *,
unsigned long *);
+ unsigned long pteval;
+ unsigned long is_data = !((isr >> IA64_ISR_X_BIT) & 1UL);
IA64FAULT fault;
-// NEED TO HANDLE THREE CASES:
-// 1) domain is in metaphysical mode
-// 2) domain address is in TR
-// 3) domain address is not in TR (reflect data miss)
-
- // got here trying to read a privop bundle
- //if (d->metaphysical_mode) {
- if (PSCB(current,metaphysical_mode) && !(address>>61)) { //FIXME
- if (d == dom0) {
- if (address < dom0_start || address >= dom0_start +
dom0_size) {
- printk("xen_handle_domain_access: out-of-bounds"
- "dom0 mpaddr %p! continuing...\n",mpaddr);
- tdpfoo();
- }
- }
- pteval = lookup_domain_mpa(d,address);
- //FIXME: check return value?
- // would be nice to have a counter here
- vcpu_itc_no_srlz(ed,2,address,pteval,-1UL,PAGE_SHIFT);
- return;
- }
-if (address < 0x4000) printf("WARNING: page_fault @%p, iip=%p\n",address,iip);
-
- if (trp = match_tr(current,address)) {
- // FIXME address had better be pre-validated on insert
- pteval =
translate_domain_pte(trp->page_flags,address,trp->itir);
-
vcpu_itc_no_srlz(current,6,address,pteval,-1UL,(trp->itir>>2)&0x3f);
- return;
- }
- // if we are fortunate enough to have it in the 1-entry TLB...
- if (pteval = match_dtlb(ed,address,&ps,NULL)) {
- vcpu_itc_no_srlz(ed,6,address,pteval,-1UL,ps);
- return;
- }
- if (ia64_done_with_exception(regs)) {
-//if (!(uacnt++ & 0x3ff)) printk("*** xen_handle_domain_access: successfully
handled cnt=%d iip=%p, addr=%p...\n",uacnt,iip,address);
- return;
- }
- else {
- // should never happen. If it does, region 0 addr may
- // indicate a bad xen pointer
- printk("*** xen_handle_domain_access: exception table"
- " lookup failed, iip=%p, addr=%p, spinning...\n",
- iip,address);
- panic_domain(regs,"*** xen_handle_domain_access: exception
table"
- " lookup failed, iip=%p, addr=%p, spinning...\n",
- iip,address);
- }
-}
-
-void ia64_do_page_fault (unsigned long address, unsigned long isr, struct
pt_regs *regs, unsigned long itir)
-{
- struct domain *d = (struct domain *) current->domain;
- TR_ENTRY *trp;
- unsigned long psr = regs->cr_ipsr, mask, flags;
- unsigned long iip = regs->cr_iip;
- // FIXME should validate address here
- unsigned long iha, pteval, mpaddr;
- unsigned long lookup_domain_mpa(struct domain *,unsigned long);
- unsigned long is_data = !((isr >> IA64_ISR_X_BIT) & 1UL);
- unsigned long vector;
- IA64FAULT fault;
-
-
- //The right way is put in VHPT and take another miss!
-
- // weak attempt to avoid doing both I/D tlb insert to avoid
- // problems for privop bundle fetch, doesn't work, deal with later
- if (IS_XEN_ADDRESS(d,iip) && !IS_XEN_ADDRESS(d,address)) {
- xen_handle_domain_access(address, isr, regs, itir);
-
- return;
- }
-
- // FIXME: no need to pass itir in to this routine as we need to
- // compute the virtual itir anyway (based on domain's RR.ps)
- // AND ACTUALLY reflect_interruption doesn't use it anyway!
- itir = vcpu_get_itir_on_fault(current,address);
-
- if (PSCB(current,metaphysical_mode) && (is_data || !(address>>61))) {
//FIXME
- // FIXME should validate mpaddr here
- if (d == dom0) {
- if (address < dom0_start || address >= dom0_start +
dom0_size) {
- printk("ia64_do_page_fault: out-of-bounds dom0
mpaddr %p, iip=%p! continuing...\n",address,iip);
- printk("ia64_do_page_fault: out-of-bounds dom0
mpaddr %p, old iip=%p!\n",address,current->vcpu_info->arch.iip);
- tdpfoo();
- }
- }
- pteval = lookup_domain_mpa(d,address);
- // FIXME, must be inlined or potential for nested fault here!
-
vcpu_itc_no_srlz(current,is_data?2:1,address,pteval,-1UL,PAGE_SHIFT);
- return;
- }
- if (trp = match_tr(current,address)) {
- // FIXME address had better be pre-validated on insert
- pteval =
translate_domain_pte(trp->page_flags,address,trp->itir);
-
vcpu_itc_no_srlz(current,is_data?2:1,address,pteval,-1UL,(trp->itir>>2)&0x3f);
- return;
- }
-
- if (handle_lazy_cover(current, isr, regs)) return;
-if (!(address>>61)) {
-panic_domain(0,"ia64_do_page_fault: @%p???, iip=%p, b0=%p, itc=%p
(spinning...)\n",address,iip,regs->b0,ia64_get_itc());
-}
+ if ((isr & IA64_ISR_IR) && handle_lazy_cover(current, isr, regs))
return;
if ((isr & IA64_ISR_SP)
|| ((isr & IA64_ISR_NA) && (isr & IA64_ISR_CODE_MASK) ==
IA64_ISR_CODE_LFETCH))
{
@@ -406,37 +293,29 @@
return;
}
- if (vcpu_get_rr_ve(current, address) && (PSCB(current,pta) &
IA64_PTA_VE))
+ fault = vcpu_translate(current,address,is_data,&pteval,&itir);
+ if (fault == IA64_NO_FAULT)
{
- if (PSCB(current,pta) & IA64_PTA_VF)
- {
- /* long format VHPT - not implemented */
- vector = is_data ? IA64_DATA_TLB_VECTOR :
IA64_INST_TLB_VECTOR;
- }
- else
- {
- /* short format VHPT */
- vcpu_thash(current, address, &iha);
- if (__copy_from_user(&pteval, iha, sizeof(pteval)) == 0)
- {
- /*
- * Optimisation: this VHPT walker aborts on
not-present pages
- * instead of inserting a not-present
translation, this allows
- * vectoring directly to the miss handler.
- \ */
- if (pteval & _PAGE_P)
- {
- pteval =
translate_domain_pte(pteval,address,itir);
-
vcpu_itc_no_srlz(current,is_data?6:1,address,pteval,-1UL,(itir>>2)&0x3f);
- return;
- }
- else vector = is_data ? IA64_DATA_TLB_VECTOR :
IA64_INST_TLB_VECTOR;
- }
- else vector = IA64_VHPT_TRANS_VECTOR;
- }
- }
- else vector = is_data ? IA64_ALT_DATA_TLB_VECTOR :
IA64_ALT_INST_TLB_VECTOR;
- reflect_interruption(address, isr, itir, regs, vector);
+ pteval = translate_domain_pte(pteval,address,itir);
+
vcpu_itc_no_srlz(current,is_data?2:1,address,pteval,-1UL,(itir>>2)&0x3f);
+ return;
+ }
+ else if (IS_VMM_ADDRESS(iip))
+ {
+ if (!ia64_done_with_exception(regs)) {
+ // should never happen. If it does, region 0 addr may
+ // indicate a bad xen pointer
+ printk("*** xen_handle_domain_access: exception table"
+ " lookup failed, iip=%p, addr=%p, spinning...\n",
+ iip,address);
+ panic_domain(regs,"*** xen_handle_domain_access:
exception table"
+ " lookup failed, iip=%p, addr=%p, spinning...\n",
+ iip,address);
+ }
+ return;
+ }
+
+ reflect_interruption(address, isr, 0, regs, fault);
}
void
@@ -865,6 +744,6 @@
while(vector);
return;
}
- if (check_lazy_cover && handle_lazy_cover(v, isr, regs)) return;
+ if (check_lazy_cover && (isr & IA64_ISR_IR) && handle_lazy_cover(v,
isr, regs)) return;
reflect_interruption(ifa,isr,itir,regs,vector);
}
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/xensetup.c
--- a/xen/arch/ia64/xensetup.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/xensetup.c Fri Jul 15 13:39:50 2005
@@ -14,7 +14,7 @@
//#include <xen/delay.h>
#include <xen/compile.h>
//#include <xen/console.h>
-//#include <xen/serial.h>
+#include <xen/serial.h>
#include <xen/trace.h>
#include <asm/meminit.h>
#include <asm/page.h>
@@ -30,7 +30,6 @@
#ifdef CLONE_DOMAIN0
struct domain *clones[CLONE_DOMAIN0];
#endif
-extern struct domain *dom0;
extern unsigned long domain0_ready;
int find_max_pfn (unsigned long, unsigned long, void *);
diff -r 35b74976f598 -r a83ac0806d6b xen/include/public/arch-ia64.h
--- a/xen/include/public/arch-ia64.h Fri Jul 15 12:52:02 2005
+++ b/xen/include/public/arch-ia64.h Fri Jul 15 13:39:50 2005
@@ -181,6 +181,16 @@
} arch_shared_info_t; // DON'T PACK
typedef struct vcpu_guest_context {
+#define VGCF_FPU_VALID (1<<0)
+#define VGCF_VMX_GUEST (1<<1)
+#define VGCF_IN_KERNEL (1<<2)
+ unsigned long flags; /* VGCF_* flags */
+ unsigned long pt_base; /* PMT table base */
+ unsigned long pt_max_pfn; /* Max pfn including holes */
+ unsigned long share_io_pg; /* Shared page for I/O emulation */
+ unsigned long vm_assist; /* VMASST_TYPE_* bitmap, now none on IPF */
+ unsigned long guest_iip; /* Guest entry point */
+
struct pt_regs regs;
arch_vcpu_info_t vcpu;
arch_shared_info_t shared;
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/xenmisc.c
--- a/xen/arch/ia64/xenmisc.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/xenmisc.c Fri Jul 15 13:39:50 2005
@@ -257,6 +257,8 @@
void cs10foo(void) {}
void cs01foo(void) {}
+unsigned long context_switch_count = 0;
+
// context_switch
void context_switch(struct vcpu *prev, struct vcpu *next)
{
@@ -276,6 +278,7 @@
/* Housekeeping for prev domain */
#endif // CONFIG_VTI
+ context_switch_count++;
switch_to(prev,next,prev);
#ifdef CONFIG_VTI
/* Post-setup for new domain */
diff -r 35b74976f598 -r a83ac0806d6b xen/include/asm-ia64/config.h
--- a/xen/include/asm-ia64/config.h Fri Jul 15 12:52:02 2005
+++ b/xen/include/asm-ia64/config.h Fri Jul 15 13:39:50 2005
@@ -49,6 +49,7 @@
extern unsigned long xenheap_phys_end;
extern unsigned long xen_pstart;
extern unsigned long xenheap_size;
+extern struct domain *dom0;
extern unsigned long dom0_start;
extern unsigned long dom0_size;
diff -r 35b74976f598 -r a83ac0806d6b xen/include/asm-ia64/vcpu.h
--- a/xen/include/asm-ia64/vcpu.h Fri Jul 15 12:52:02 2005
+++ b/xen/include/asm-ia64/vcpu.h Fri Jul 15 13:39:50 2005
@@ -135,6 +135,7 @@
extern IA64FAULT vcpu_ptc_ga(VCPU *vcpu, UINT64 vadr, UINT64 addr_range);
extern IA64FAULT vcpu_ptr_d(VCPU *vcpu,UINT64 vadr, UINT64 addr_range);
extern IA64FAULT vcpu_ptr_i(VCPU *vcpu,UINT64 vadr, UINT64 addr_range);
+extern IA64FAULT vcpu_translate(VCPU *vcpu, UINT64 address, BOOLEAN is_data,
UINT64 *pteval, UINT64 *itir);
extern IA64FAULT vcpu_tpa(VCPU *vcpu, UINT64 vadr, UINT64 *padr);
/* misc */
extern IA64FAULT vcpu_rfi(VCPU *vcpu);
@@ -150,5 +151,4 @@
extern UINT64 vcpu_get_tmp(VCPU *, UINT64);
extern void vcpu_set_tmp(VCPU *, UINT64, UINT64);
-
#endif
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/ivt.S
--- a/xen/arch/ia64/ivt.S Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/ivt.S Fri Jul 15 13:39:50 2005
@@ -666,7 +666,12 @@
// 0x2400 Entry 9 (size 64 bundles) Instruction Access-bit (27)
ENTRY(iaccess_bit)
#ifdef XEN
- REFLECT(9)
+ mov r31=pr;
+ mov r16=cr.isr
+ mov r17=cr.ifa
+ mov r19=9
+ movl r20=0x2400
+ br.sptk.many fast_access_reflect;;
#endif
DBG_FAULT(9)
// Like Entry 8, except for instruction access
@@ -734,7 +739,12 @@
// 0x2800 Entry 10 (size 64 bundles) Data Access-bit (15,55)
ENTRY(daccess_bit)
#ifdef XEN
- REFLECT(10)
+ mov r31=pr;
+ mov r16=cr.isr
+ mov r17=cr.ifa
+ mov r19=10
+ movl r20=0x2800
+ br.sptk.many fast_access_reflect;;
#endif
DBG_FAULT(10)
// Like Entry 8, except for data access
@@ -921,10 +931,10 @@
;;
#ifdef XEN
mov r30=cr.ivr // pass cr.ivr as first arg
- // FIXME: this is a hack... use cpuinfo.pgd_quick because its
+ // FIXME: this is a hack... use cpuinfo.ksoftirqd because its
// not used anywhere else and we need a place to stash ivr and
// there's no registers available unused by SAVE_MIN/REST
- movl r29=(PERCPU_ADDR)+IA64_CPUINFO_PGD_QUICK_OFFSET;;
+ movl r29=(PERCPU_ADDR)+IA64_CPUINFO_KSOFTIRQD_OFFSET;;
st8 [r29]=r30;;
movl r28=slow_interrupt;;
mov r29=rp;;
@@ -944,7 +954,7 @@
;;
alloc r14=ar.pfs,0,0,2,0 // must be first in an insn group
#ifdef XEN
- movl out0=(PERCPU_ADDR)+IA64_CPUINFO_PGD_QUICK_OFFSET;;
+ movl out0=(PERCPU_ADDR)+IA64_CPUINFO_KSOFTIRQD_OFFSET;;
ld8 out0=[out0];;
#else
mov out0=cr.ivr // pass cr.ivr as first arg
@@ -1395,7 +1405,12 @@
// 0x5300 Entry 23 (size 16 bundles) Data Access Rights (14,53)
ENTRY(daccess_rights)
#ifdef XEN
- REFLECT(23)
+ mov r31=pr;
+ mov r16=cr.isr
+ mov r17=cr.ifa
+ mov r19=23
+ movl r20=0x5300
+ br.sptk.many fast_access_reflect;;
#endif
DBG_FAULT(23)
mov r16=cr.ifa
@@ -1821,7 +1836,7 @@
#ifdef XEN
.org ia64_ivt+0x8000
-ENTRY(dispatch_reflection)
+GLOBAL_ENTRY(dispatch_reflection)
/*
* Input:
* psr.ic: off
diff -r 35b74976f598 -r a83ac0806d6b xen/include/asm-ia64/vmx_phy_mode.h
--- a/xen/include/asm-ia64/vmx_phy_mode.h Fri Jul 15 12:52:02 2005
+++ b/xen/include/asm-ia64/vmx_phy_mode.h Fri Jul 15 13:39:50 2005
@@ -83,6 +83,7 @@
#define IA64_RSC_MODE 0x0000000000000003
#define XEN_RR7_RID (0xf00010)
#define GUEST_IN_PHY 0x1
+#define GUEST_PHY_EMUL 0x2
extern int valid_mm_mode[];
extern int mm_switch_table[][8];
extern void physical_mode_init(VCPU *);
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/asm-offsets.c
--- a/xen/arch/ia64/asm-offsets.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/asm-offsets.c Fri Jul 15 13:39:50 2005
@@ -46,6 +46,8 @@
DEFINE(XSI_PSR_IC, (SHAREDINFO_ADDR+offsetof(vcpu_info_t,
arch.interrupt_collection_enabled)));
DEFINE(XSI_PSR_I_OFS, offsetof(vcpu_info_t,
arch.interrupt_delivery_enabled));
DEFINE(XSI_IIP_OFS, offsetof(vcpu_info_t, arch.iip));
+ DEFINE(XSI_IFA_OFS, offsetof(vcpu_info_t, arch.ifa));
+ DEFINE(XSI_ITIR_OFS, offsetof(vcpu_info_t, arch.itir));
DEFINE(XSI_IPSR, (SHAREDINFO_ADDR+offsetof(vcpu_info_t, arch.ipsr)));
DEFINE(XSI_IPSR_OFS, offsetof(vcpu_info_t, arch.ipsr));
DEFINE(XSI_IFS_OFS, offsetof(vcpu_info_t, arch.ifs));
@@ -61,6 +63,7 @@
DEFINE(XSI_PEND_OFS, offsetof(vcpu_info_t, arch.pending_interruption));
DEFINE(XSI_RR0_OFS, offsetof(vcpu_info_t, arch.rrs[0]));
DEFINE(XSI_TPR_OFS, offsetof(vcpu_info_t, arch.tpr));
+ DEFINE(XSI_PTA_OFS, offsetof (vcpu_info_t, arch.pta));
DEFINE(XSI_ITV_OFS, offsetof(vcpu_info_t, arch.itv));
//DEFINE(IA64_TASK_BLOCKED_OFFSET,offsetof (struct task_struct,
blocked));
//DEFINE(IA64_TASK_CLEAR_CHILD_TID_OFFSET,offsetof (struct task_struct,
clear_child_tid));
@@ -85,10 +88,12 @@
DEFINE(IA64_VCPU_ENDING_RID_OFFSET, offsetof (struct vcpu,
arch.ending_rid));
DEFINE(IA64_VCPU_DOMAIN_ITM_OFFSET, offsetof (struct vcpu,
arch.domain_itm));
DEFINE(IA64_VCPU_DOMAIN_ITM_LAST_OFFSET, offsetof (struct vcpu,
arch.domain_itm_last));
+ DEFINE(IA64_VCPU_ITLB_OFFSET, offsetof (struct vcpu, arch.itlb));
+ DEFINE(IA64_VCPU_DTLB_OFFSET, offsetof (struct vcpu, arch.dtlb));
BLANK();
DEFINE(IA64_CPUINFO_ITM_NEXT_OFFSET, offsetof (struct cpuinfo_ia64,
itm_next));
- DEFINE(IA64_CPUINFO_PGD_QUICK_OFFSET, offsetof (struct cpuinfo_ia64,
pgd_quick));
+ DEFINE(IA64_CPUINFO_KSOFTIRQD_OFFSET, offsetof (struct cpuinfo_ia64,
ksoftirqd));
//DEFINE(IA64_SIGHAND_SIGLOCK_OFFSET,offsetof (struct sighand_struct,
siglock));
@@ -219,6 +224,7 @@
#ifdef CONFIG_VTI
DEFINE(IA64_VPD_BASE_OFFSET, offsetof (struct vcpu, arch.arch_vmx.vpd));
+ DEFINE(IA64_VLSAPIC_INSVC_BASE_OFFSET, offsetof (struct vcpu,
arch.arch_vmx.in_service[0]));
DEFINE(IA64_VPD_CR_VPTA_OFFSET, offsetof (cr_t, pta));
DEFINE(XXX_THASH_SIZE, sizeof (thash_data_t));
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/vtlb.c
--- a/xen/arch/ia64/vtlb.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/vtlb.c Fri Jul 15 13:39:50 2005
@@ -26,7 +26,7 @@
#include <asm/vmx_mm_def.h>
#include <asm/gcc_intrin.h>
#include <xen/interrupt.h>
-#include <asm/vcpu.h>
+#include <asm/vmx_vcpu.h>
#define MAX_CCH_LENGTH 40
@@ -401,6 +401,8 @@
panic("Can't convert to machine VHPT entry\n");
}
hash_table->next = cch;
+ if(hash_table->tag==hash_table->next->tag)
+ while(1);
}
return /*hash_table*/;
}
@@ -466,10 +468,11 @@
static thash_data_t *thash_rem_cch(thash_cb_t *hcb, thash_data_t *cch)
{
thash_data_t *next;
-
+
if ( ++cch_depth > MAX_CCH_LENGTH ) {
printf ("cch length > MAX_CCH_LENGTH, exceed the expected length\n");
- }
+ while(1);
+ }
if ( cch -> next ) {
next = thash_rem_cch(hcb, cch->next);
}
diff -r 35b74976f598 -r a83ac0806d6b xen/include/asm-ia64/vmx.h
--- a/xen/include/asm-ia64/vmx.h Fri Jul 15 12:52:02 2005
+++ b/xen/include/asm-ia64/vmx.h Fri Jul 15 13:39:50 2005
@@ -35,4 +35,6 @@
extern void vmx_purge_double_mapping(u64, u64, u64);
extern void vmx_change_double_mapping(struct vcpu *v, u64 oldrr7, u64 newrr7);
+extern void vmx_wait_io(void);
+extern void vmx_io_assist(struct vcpu *v);
#endif /* _ASM_IA64_VT_H */
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/vlsapic.c
--- a/xen/arch/ia64/vlsapic.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/vlsapic.c Fri Jul 15 13:39:50 2005
@@ -133,7 +133,7 @@
// FIXME: should use local_irq_disable & local_irq_enable ??
local_irq_save(spsr);
guest_itc = now_itc(vtm);
- update_last_itc(vtm, guest_itc);
+// update_last_itc(vtm, guest_itc);
local_irq_restore(spsr);
return guest_itc;
@@ -174,12 +174,12 @@
/* Interrupt must be disabled at this point */
extern u64 tick_to_ns(u64 tick);
-#define TIMER_SLOP (50*1000) /* ns */ /* copy from ac_timer.c */
+#define TIMER_SLOP (50*1000) /* ns */ /* copy from ac_timer.c */
void vtm_interruption_update(VCPU *vcpu, vtime_t* vtm)
{
uint64_t cur_itc,vitm,vitv;
uint64_t expires;
- long diff_now, diff_last;
+ long diff_now, diff_last;
uint64_t spsr;
vitv = VPD_CR(vcpu, itv);
@@ -237,21 +237,30 @@
#define NMI_VECTOR 2
#define ExtINT_VECTOR 0
-
+#define NULL_VECTOR -1
#define VLSAPIC_INSVC(vcpu, i) ((vcpu)->arch.arch_vmx.in_service[i])
-/*
- * LID-CR64: Keep in vpd.
- * IVR-CR65: (RO) see guest_read_ivr().
- * TPR-CR66: Keep in vpd, acceleration enabled.
- * EOI-CR67: see guest_write_eoi().
- * IRR0-3 - CR68-71: (RO) Keep in vpd irq_pending[]
- * can move to vpd for optimization.
- * ITV: in time virtualization.
- * PMV: Keep in vpd initialized as 0x10000.
- * CMCV: Keep in vpd initialized as 0x10000.
- * LRR0-1: Keep in vpd, initialized as 0x10000.
- *
- */
+static void update_vhpi(VCPU *vcpu, int vec)
+{
+ u64 vhpi;
+ if ( vec == NULL_VECTOR ) {
+ vhpi = 0;
+ }
+ else if ( vec == NMI_VECTOR ) { // NMI
+ vhpi = 32;
+ } else if (vec == ExtINT_VECTOR) { //ExtINT
+ vhpi = 16;
+ }
+ else {
+ vhpi = vec / 16;
+ }
+
+ VMX_VPD(vcpu,vhpi) = vhpi;
+ // TODO: Add support for XENO
+ if ( VMX_VPD(vcpu,vac).a_int ) {
+ ia64_call_vsa ( PAL_VPS_SET_PENDING_INTERRUPT,
+ (uint64_t) &(vcpu->arch.arch_vmx.vpd), 0, 0,0,0,0,0);
+ }
+}
void vlsapic_reset(VCPU *vcpu)
{
@@ -268,9 +277,11 @@
VPD_CR(vcpu, cmcv) = 0x10000;
VPD_CR(vcpu, lrr0) = 0x10000; // default reset value?
VPD_CR(vcpu, lrr1) = 0x10000; // default reset value?
+ update_vhpi(vcpu, NULL_VECTOR);
for ( i=0; i<4; i++) {
VLSAPIC_INSVC(vcpu,i) = 0;
}
+ DPRINTK("VLSAPIC inservice base=%lp\n", &VLSAPIC_INSVC(vcpu,0) );
}
/*
@@ -281,7 +292,7 @@
*/
static __inline__ int highest_bits(uint64_t *dat)
{
- uint64_t bits, bitnum=-1;
+ uint64_t bits, bitnum;
int i;
/* loop for all 256 bits */
@@ -292,12 +303,12 @@
return i*64+bitnum;
}
}
- return -1;
+ return NULL_VECTOR;
}
/*
* Return 0-255 for pending irq.
- * -1 when no pending.
+ * NULL_VECTOR: when no pending.
*/
static int highest_pending_irq(VCPU *vcpu)
{
@@ -320,7 +331,7 @@
static int is_higher_irq(int pending, int inservice)
{
return ( (pending >> 4) > (inservice>>4) ||
- ((pending != -1) && (inservice == -1)) );
+ ((pending != NULL_VECTOR) && (inservice == NULL_VECTOR)) );
}
static int is_higher_class(int pending, int mic)
@@ -332,41 +343,97 @@
{
return (vec == 1 || ((vec <= 14 && vec >= 3)));
}
+
+#define IRQ_NO_MASKED 0
+#define IRQ_MASKED_BY_VTPR 1
+#define IRQ_MASKED_BY_INSVC 2 // masked by inservice IRQ
/* See Table 5-8 in SDM vol2 for the definition */
static int
-irq_masked(VCPU *vcpu, int h_pending, int h_inservice)
-{
- uint64_t vtpr;
-
- vtpr = VPD_CR(vcpu, tpr);
-
- if ( h_pending == NMI_VECTOR && h_inservice != NMI_VECTOR )
+_xirq_masked(VCPU *vcpu, int h_pending, int h_inservice)
+{
+ tpr_t vtpr;
+ uint64_t mmi;
+
+ vtpr.val = VPD_CR(vcpu, tpr);
+
+ if ( h_inservice == NMI_VECTOR ) {
+ return IRQ_MASKED_BY_INSVC;
+ }
+ if ( h_pending == NMI_VECTOR ) {
// Non Maskable Interrupt
- return 0;
-
- if ( h_pending == ExtINT_VECTOR && h_inservice >= 16)
- return (vtpr>>16)&1; // vtpr.mmi
-
- if ( !(vtpr&(1UL<<16)) &&
- is_higher_irq(h_pending, h_inservice) &&
- is_higher_class(h_pending, (vtpr>>4)&0xf) )
- return 0;
-
- return 1;
-}
-
+ return IRQ_NO_MASKED;
+ }
+ if ( h_inservice == ExtINT_VECTOR ) {
+ return IRQ_MASKED_BY_INSVC;
+ }
+ mmi = vtpr.mmi;
+ if ( h_pending == ExtINT_VECTOR ) {
+ if ( mmi ) {
+ // mask all external IRQ
+ return IRQ_MASKED_BY_VTPR;
+ }
+ else {
+ return IRQ_NO_MASKED;
+ }
+ }
+
+ if ( is_higher_irq(h_pending, h_inservice) ) {
+ if ( !mmi && is_higher_class(h_pending, vtpr.mic) ) {
+ return IRQ_NO_MASKED;
+ }
+ else {
+ return IRQ_MASKED_BY_VTPR;
+ }
+ }
+ else {
+ return IRQ_MASKED_BY_INSVC;
+ }
+}
+
+static int irq_masked(VCPU *vcpu, int h_pending, int h_inservice)
+{
+ int mask;
+
+ mask = _xirq_masked(vcpu, h_pending, h_inservice);
+ return mask;
+}
+
+
+/*
+ * May come from virtualization fault or
+ * nested host interrupt.
+ */
void vmx_vcpu_pend_interrupt(VCPU *vcpu, UINT64 vector)
{
uint64_t spsr;
if (vector & ~0xff) {
- printf("vmx_vcpu_pend_interrupt: bad vector\n");
+ DPRINTK("vmx_vcpu_pend_interrupt: bad vector\n");
return;
}
local_irq_save(spsr);
VPD_CR(vcpu,irr[vector>>6]) |= 1UL<<(vector&63);
local_irq_restore(spsr);
+ vcpu->arch.irq_new_pending = 1;
+}
+
+/*
+ * Add batch of pending interrupt.
+ * The interrupt source is contained in pend_irr[0-3] with
+ * each bits stand for one interrupt.
+ */
+void vmx_vcpu_pend_batch_interrupt(VCPU *vcpu, UINT64 *pend_irr)
+{
+ uint64_t spsr;
+ int i;
+
+ local_irq_save(spsr);
+ for (i=0 ; i<4; i++ ) {
+ VPD_CR(vcpu,irr[i]) |= pend_irr[i];
+ }
+ local_irq_restore(spsr);
+ vcpu->arch.irq_new_pending = 1;
}
/*
@@ -383,7 +450,7 @@
*/
int vmx_check_pending_irq(VCPU *vcpu)
{
- uint64_t spsr;
+ uint64_t spsr, mask;
int h_pending, h_inservice;
int injected=0;
uint64_t isr;
@@ -391,22 +458,25 @@
local_irq_save(spsr);
h_pending = highest_pending_irq(vcpu);
- if ( h_pending == -1 ) goto chk_irq_exit;
+ if ( h_pending == NULL_VECTOR ) goto chk_irq_exit;
h_inservice = highest_inservice_irq(vcpu);
vpsr.val = vmx_vcpu_get_psr(vcpu);
- if ( vpsr.i &&
- !irq_masked(vcpu, h_pending, h_inservice) ) {
- //inject_guest_irq(v);
+ mask = irq_masked(vcpu, h_pending, h_inservice);
+ if ( vpsr.i && IRQ_NO_MASKED == mask ) {
isr = vpsr.val & IA64_PSR_RI;
if ( !vpsr.ic )
panic("Interrupt when IC=0\n");
vmx_reflect_interruption(0,isr,0, 12 ); // EXT IRQ
injected = 1;
}
- else if ( VMX_VPD(vcpu,vac).a_int &&
- is_higher_irq(h_pending,h_inservice) ) {
- vmx_inject_vhpi(vcpu,h_pending);
+ else if ( mask == IRQ_MASKED_BY_INSVC ) {
+ // cann't inject VHPI
+// DPRINTK("IRQ masked by higher inservice\n");
+ }
+ else {
+ // masked by vpsr.i or vtpr.
+ update_vhpi(vcpu,h_pending);
}
chk_irq_exit:
@@ -414,17 +484,21 @@
return injected;
}
+/*
+ * Only coming from virtualization fault.
+ */
void guest_write_eoi(VCPU *vcpu)
{
int vec;
uint64_t spsr;
vec = highest_inservice_irq(vcpu);
- if ( vec < 0 ) panic("Wrong vector to EOI\n");
+ if ( vec == NULL_VECTOR ) panic("Wrong vector to EOI\n");
local_irq_save(spsr);
VLSAPIC_INSVC(vcpu,vec>>6) &= ~(1UL <<(vec&63));
local_irq_restore(spsr);
VPD_CR(vcpu, eoi)=0; // overwrite the data
+ vmx_check_pending_irq(vcpu);
}
uint64_t guest_read_vivr(VCPU *vcpu)
@@ -435,37 +509,54 @@
local_irq_save(spsr);
vec = highest_pending_irq(vcpu);
h_inservice = highest_inservice_irq(vcpu);
- if ( vec < 0 || irq_masked(vcpu, vec, h_inservice) ) {
+ if ( vec == NULL_VECTOR ||
+ irq_masked(vcpu, vec, h_inservice) != IRQ_NO_MASKED ) {
local_irq_restore(spsr);
return IA64_SPURIOUS_INT_VECTOR;
}
VLSAPIC_INSVC(vcpu,vec>>6) |= (1UL <<(vec&63));
VPD_CR(vcpu, irr[vec>>6]) &= ~(1UL <<(vec&63));
-
- h_inservice = highest_inservice_irq(vcpu);
- next = highest_pending_irq(vcpu);
- if ( VMX_VPD(vcpu,vac).a_int &&
- (is_higher_irq(next, h_inservice) || (next == -1)) )
- vmx_inject_vhpi(vcpu, next);
+ update_vhpi(vcpu, NULL_VECTOR); // clear VHPI till EOI or IRR write
local_irq_restore(spsr);
return (uint64_t)vec;
}
-void vmx_inject_vhpi(VCPU *vcpu, u8 vec)
-{
- VMX_VPD(vcpu,vhpi) = vec / 16;
-
-
- // non-maskable
- if ( vec == NMI_VECTOR ) // NMI
- VMX_VPD(vcpu,vhpi) = 32;
- else if (vec == ExtINT_VECTOR) //ExtINT
- VMX_VPD(vcpu,vhpi) = 16;
- else if (vec == -1)
- VMX_VPD(vcpu,vhpi) = 0; /* Nothing pending */
-
- ia64_call_vsa ( PAL_VPS_SET_PENDING_INTERRUPT,
- (uint64_t) &(vcpu->arch.arch_vmx.vpd), 0, 0,0,0,0,0);
-}
-
+static void generate_exirq(VCPU *vcpu)
+{
+ IA64_PSR vpsr;
+ uint64_t isr;
+
+ vpsr.val = vmx_vcpu_get_psr(vcpu);
+ update_vhpi(vcpu, NULL_VECTOR);
+ isr = vpsr.val & IA64_PSR_RI;
+ if ( !vpsr.ic )
+ panic("Interrupt when IC=0\n");
+ vmx_reflect_interruption(0,isr,0, 12 ); // EXT IRQ
+}
+
+vhpi_detection(VCPU *vcpu)
+{
+ uint64_t threshold,vhpi;
+ tpr_t vtpr;
+ IA64_PSR vpsr;
+
+ vpsr.val = vmx_vcpu_get_psr(vcpu);
+ vtpr.val = VPD_CR(vcpu, tpr);
+
+ threshold = ((!vpsr.i) << 5) | (vtpr.mmi << 4) | vtpr.mic;
+ vhpi = VMX_VPD(vcpu,vhpi);
+ if ( vhpi > threshold ) {
+ // interrupt actived
+ generate_exirq (vcpu);
+ }
+}
+
+vmx_vexirq(VCPU *vcpu)
+{
+ static uint64_t vexirq_count=0;
+
+ vexirq_count ++;
+ printk("Virtual ex-irq %ld\n", vexirq_count);
+ generate_exirq (vcpu);
+}
diff -r 35b74976f598 -r a83ac0806d6b xen/include/asm-ia64/xensystem.h
--- a/xen/include/asm-ia64/xensystem.h Fri Jul 15 12:52:02 2005
+++ b/xen/include/asm-ia64/xensystem.h Fri Jul 15 13:39:50 2005
@@ -33,6 +33,8 @@
#ifdef CONFIG_VTI
extern struct task_struct *vmx_ia64_switch_to (void *next_task);
#define __switch_to(prev,next,last) do { \
+ ia64_save_fpu(prev->arch._thread.fph); \
+ ia64_load_fpu(next->arch._thread.fph); \
if (VMX_DOMAIN(prev)) \
vmx_save_state(prev); \
else { \
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/mmio.c
--- a/xen/arch/ia64/mmio.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/mmio.c Fri Jul 15 13:39:50 2005
@@ -27,7 +27,13 @@
#include <asm/gcc_intrin.h>
#include <xen/interrupt.h>
#include <asm/vmx_vcpu.h>
-
+#include <asm/privop.h>
+#include <asm/types.h>
+#include <public/io/ioreq.h>
+#include <asm/mm.h>
+#include <asm/vmx.h>
+
+/*
struct mmio_list *lookup_mmio(u64 gpa, struct mmio_list *mio_base)
{
int i;
@@ -37,65 +43,194 @@
}
return NULL;
}
-
-
-extern void pib_write(VCPU *vcpu, void *src, uint64_t pib_off, size_t s, int
ma);
-static inline void mmio_write(VCPU *vcpu, void *src, u64 dest_pa, size_t s,
int ma)
+*/
+
+#define PIB_LOW_HALF(ofst) !(ofst&(1<<20))
+#define PIB_OFST_INTA 0x1E0000
+#define PIB_OFST_XTP 0x1E0008
+
+static void pib_write(VCPU *vcpu, void *src, uint64_t pib_off, size_t s, int
ma)
+{
+ switch (pib_off) {
+ case PIB_OFST_INTA:
+ panic("Undefined write on PIB INTA\n");
+ break;
+ case PIB_OFST_XTP:
+ if ( s == 1 && ma == 4 /* UC */) {
+ vmx_vcpu_get_plat(vcpu)->xtp = *(uint8_t *)src;
+ }
+ else {
+ panic("Undefined write on PIB XTP\n");
+ }
+ break;
+ default:
+ if ( PIB_LOW_HALF(pib_off) ) { // lower half
+ if ( s != 8 || ma != 0x4 /* UC */ ) {
+ panic("Undefined IPI-LHF write!\n");
+ }
+ else {
+ write_ipi(vcpu, pib_off, *(uint64_t *)src);
+ // TODO for SM-VP
+ }
+ }
+ else { // upper half
+ printf("IPI-UHF write %lx\n",pib_off);
+ panic("Not support yet for SM-VP\n");
+ }
+ break;
+ }
+}
+
+static void pib_read(VCPU *vcpu, uint64_t pib_off, void *dest, size_t s, int
ma)
+{
+ switch (pib_off) {
+ case PIB_OFST_INTA:
+ // todo --- emit on processor system bus.
+ if ( s == 1 && ma == 4) { // 1 byte load
+ // TODO: INTA read from IOSAPIC
+ }
+ else {
+ panic("Undefined read on PIB INTA\n");
+ }
+ break;
+ case PIB_OFST_XTP:
+ if ( s == 1 && ma == 4) {
+ *((uint8_t*)dest) = vmx_vcpu_get_plat(vcpu)->xtp;
+ }
+ else {
+ panic("Undefined read on PIB XTP\n");
+ }
+ break;
+ default:
+ if ( PIB_LOW_HALF(pib_off) ) { // lower half
+ if ( s != 8 || ma != 4 ) {
+ panic("Undefined IPI-LHF read!\n");
+ }
+ else {
+#ifdef IPI_DEBUG
+ printf("IPI-LHF read %lx\n",pib_off);
+#endif
+ *(uint64_t *)dest = 0; // TODO for SM-VP
+ }
+ }
+ else { // upper half
+ if ( s != 1 || ma != 4 ) {
+ panic("Undefined PIB-UHF read!\n");
+ }
+ else {
+#ifdef IPI_DEBUG
+ printf("IPI-UHF read %lx\n",pib_off);
+#endif
+ *(uint8_t *)dest = 0; // TODO for SM-VP
+ }
+ }
+ break;
+ }
+}
+
+static void low_mmio_access(VCPU *vcpu, u64 pa, u64 *val, size_t s, int dir)
+{
+ struct vcpu *v = current;
+ vcpu_iodata_t *vio;
+ ioreq_t *p;
+ unsigned long addr;
+
+ vio = (vcpu_iodata_t *) v->arch.arch_vmx.vmx_platform.shared_page_va;
+ if (vio == 0) {
+ panic("bad shared page: %lx", (unsigned long)vio);
+ }
+ p = &vio->vp_ioreq;
+ p->addr = pa;
+ p->size = 1<<s;
+ p->count = 1;
+ p->dir = dir;
+ if(dir==IOREQ_WRITE) //write;
+ p->u.data = *val;
+ p->pdata_valid = 0;
+ p->port_mm = 1;
+ p->df = 0;
+
+ set_bit(ARCH_VMX_IO_WAIT, &v->arch.arch_vmx.flags);
+ p->state = STATE_IOREQ_READY;
+ evtchn_send(IOPACKET_PORT);
+ vmx_wait_io();
+ if(dir){ //read
+ *val=p->u.data;
+ }
+ return;
+}
+#define TO_LEGACY_IO(pa) (((pa)>>12<<2)|((pa)&0x3))
+
+static void legacy_io_access(VCPU *vcpu, u64 pa, u64 *val, size_t s, int dir)
+{
+ struct vcpu *v = current;
+ vcpu_iodata_t *vio;
+ ioreq_t *p;
+ unsigned long addr;
+
+ vio = (vcpu_iodata_t *) v->arch.arch_vmx.vmx_platform.shared_page_va;
+ if (vio == 0) {
+ panic("bad shared page: %lx");
+ }
+ p = &vio->vp_ioreq;
+ p->addr = TO_LEGACY_IO(pa&0x3ffffffUL);
+ p->size = 1<<s;
+ p->count = 1;
+ p->dir = dir;
+ if(dir==IOREQ_WRITE) //write;
+ p->u.data = *val;
+ p->pdata_valid = 0;
+ p->port_mm = 0;
+ p->df = 0;
+
+ set_bit(ARCH_VMX_IO_WAIT, &v->arch.arch_vmx.flags);
+ p->state = STATE_IOREQ_READY;
+ evtchn_send(IOPACKET_PORT);
+ vmx_wait_io();
+ if(dir){ //read
+ *val=p->u.data;
+ }
+ return;
+}
+
+static void mmio_access(VCPU *vcpu, u64 src_pa, u64 *dest, size_t s, int ma,
int dir)
{
struct virutal_platform_def *v_plat;
- struct mmio_list *mio;
-
+ //mmio_type_t iot;
+ unsigned long iot;
+ iot=__gpfn_is_io(vcpu->domain, src_pa>>PAGE_SHIFT);
v_plat = vmx_vcpu_get_plat(vcpu);
- mio = lookup_mmio(dest_pa, v_plat->mmio);
- if ( mio == NULL )
- panic ("Wrong address for MMIO\n");
-
- switch (mio->iot) {
- case PIB_MMIO:
- pib_write(vcpu, src, dest_pa - v_plat->pib_base, s, ma);
- break;
- case VGA_BUFF:
- case CHIPSET_IO:
- case LOW_MMIO:
- case LEGACY_IO:
- case IO_SAPIC:
+
+ switch (iot) {
+ case GPFN_PIB:
+ if(!dir)
+ pib_write(vcpu, src_pa - v_plat->pib_base, dest, s, ma);
+ else
+ pib_read(vcpu, src_pa - v_plat->pib_base, dest, s, ma);
+ break;
+ case GPFN_GFW:
+ break;
+ case GPFN_FRAME_BUFFER:
+ case GPFN_LOW_MMIO:
+ low_mmio_access(vcpu, src_pa, dest, s, dir);
+ break;
+ case GPFN_LEGACY_IO:
+ legacy_io_access(vcpu, src_pa, dest, s, dir);
+ break;
+ case GPFN_IOSAPIC:
default:
+ panic("Bad I/O access\n");
break;
}
return;
}
-static inline void mmio_read(VCPU *vcpu, u64 src_pa, void *dest, size_t s, int
ma)
-{
- struct virutal_platform_def *v_plat;
- struct mmio_list *mio;
-
- v_plat = vmx_vcpu_get_plat(vcpu);
- mio = lookup_mmio(src_pa, v_plat->mmio);
- if ( mio == NULL )
- panic ("Wrong address for MMIO\n");
-
- switch (mio->iot) {
- case PIB_MMIO:
- pib_read(vcpu, src_pa - v_plat->pib_base, dest, s, ma);
- break;
- case VGA_BUFF:
- case CHIPSET_IO:
- case LOW_MMIO:
- case LEGACY_IO:
- case IO_SAPIC:
- default:
- break;
- }
- return;
-}
-
/*
* Read or write data in guest virtual address mode.
*/
-
+/*
void
-memwrite_v(VCPU *vcpu, thash_data_t *vtlb, void *src, void *dest, size_t s)
+memwrite_v(VCPU *vcpu, thash_data_t *vtlb, u64 *src, u64 *dest, size_t s)
{
uint64_t pa;
@@ -108,7 +243,7 @@
void
-memwrite_p(VCPU *vcpu, void *src, void *dest, size_t s)
+memwrite_p(VCPU *vcpu, u64 *src, u64 *dest, size_t s)
{
uint64_t pa = (uint64_t)dest;
int ma;
@@ -116,9 +251,9 @@
if ( pa & (1UL <<63) ) {
// UC
ma = 4;
- pa <<=1;
+ pa <<=1;
pa >>=1;
- }
+ }
else {
// WBL
ma = 0; // using WB for WBL
@@ -127,7 +262,7 @@
}
void
-memread_v(VCPU *vcpu, thash_data_t *vtlb, void *src, void *dest, size_t s)
+memread_v(VCPU *vcpu, thash_data_t *vtlb, u64 *src, u64 *dest, size_t s)
{
uint64_t pa;
@@ -135,12 +270,12 @@
panic("Normal memory write shouldn't go to this point!");
pa = PPN_2_PA(vtlb->ppn);
pa += POFFSET((u64)src, vtlb->ps);
-
+
mmio_read(vcpu, pa, dest, s, vtlb->ma);
}
void
-memread_p(VCPU *vcpu, void *src, void *dest, size_t s)
+memread_p(VCPU *vcpu, u64 *src, u64 *dest, size_t s)
{
uint64_t pa = (uint64_t)src;
int ma;
@@ -148,19 +283,16 @@
if ( pa & (1UL <<63) ) {
// UC
ma = 4;
- pa <<=1;
+ pa <<=1;
pa >>=1;
- }
+ }
else {
// WBL
ma = 0; // using WB for WBL
}
mmio_read(vcpu, pa, dest, s, ma);
}
-
-#define PIB_LOW_HALF(ofst) !(ofst&(1<<20))
-#define PIB_OFST_INTA 0x1E0000
-#define PIB_OFST_XTP 0x1E0008
+*/
/*
@@ -182,23 +314,22 @@
panic ("Inject guest PMI!\n");
break;
case 4: // NMI
- vmx_vcpu_pend_interrupt (vcpu, 2);
+ vmx_vcpu_pend_interrupt (vcpu, 2);
break;
case 5: // INIT
// TODO -- inject guest INIT
panic ("Inject guest INIT!\n");
break;
case 7: // ExtINT
- vmx_vcpu_pend_interrupt (vcpu, 0);
- break;
-
+ vmx_vcpu_pend_interrupt (vcpu, 0);
+ break;
case 1:
case 3:
case 6:
default:
panic ("Deliver reserved IPI!\n");
break;
- }
+ }
}
/*
@@ -209,7 +340,6 @@
int i;
VCPU *vcpu;
LID lid;
-
for (i=0; i<MAX_VIRT_CPUS; i++) {
vcpu = d->vcpu[i];
lid.val = VPD_CR(vcpu, lid);
@@ -226,7 +356,7 @@
static int write_ipi (VCPU *vcpu, uint64_t addr, uint64_t value)
{
VCPU *target_cpu;
-
+
target_cpu = lid_2_vcpu(vcpu->domain,
((ipi_a_t)addr).id, ((ipi_a_t)addr).eid);
if ( target_cpu == NULL ) panic("Unknown IPI cpu\n");
@@ -243,83 +373,89 @@
}
}
-void pib_write(VCPU *vcpu, void *src, uint64_t pib_off, size_t s, int ma)
-{
-
- switch (pib_off) {
- case PIB_OFST_INTA:
- panic("Undefined write on PIB INTA\n");
- break;
- case PIB_OFST_XTP:
- if ( s == 1 && ma == 4 /* UC */) {
- vmx_vcpu_get_plat(vcpu)->xtp = *(uint8_t *)src;
- }
- else {
- panic("Undefined write on PIB XTP\n");
- }
- break;
- default:
- if ( PIB_LOW_HALF(pib_off) ) { // lower half
- if ( s != 8 || ma != 0x4 /* UC */ ) {
- panic("Undefined IPI-LHF write!\n");
- }
- else {
- write_ipi(vcpu, pib_off, *(uint64_t *)src);
- // TODO for SM-VP
- }
- }
- else { // upper half
- printf("IPI-UHF write %lx\n",pib_off);
- panic("Not support yet for SM-VP\n");
- }
- break;
- }
-}
-
-void pib_read(VCPU *vcpu, uint64_t pib_off, void *dest, size_t s, int ma)
-{
- switch (pib_off) {
- case PIB_OFST_INTA:
- // todo --- emit on processor system bus.
- if ( s == 1 && ma == 4) { // 1 byte load
- // TODO: INTA read from IOSAPIC
- }
- else {
- panic("Undefined read on PIB INTA\n");
- }
- break;
- case PIB_OFST_XTP:
- if ( s == 1 && ma == 4) {
- *((uint8_t*)dest) = vmx_vcpu_get_plat(vcpu)->xtp;
- }
- else {
- panic("Undefined read on PIB XTP\n");
- }
- break;
- default:
- if ( PIB_LOW_HALF(pib_off) ) { // lower half
- if ( s != 8 || ma != 4 ) {
- panic("Undefined IPI-LHF read!\n");
- }
- else {
-#ifdef IPI_DEBUG
- printf("IPI-LHF read %lx\n",pib_off);
-#endif
- *(uint64_t *)dest = 0; // TODO for SM-VP
- }
- }
- else { // upper half
- if ( s != 1 || ma != 4 ) {
- panic("Undefined PIB-UHF read!\n");
- }
- else {
-#ifdef IPI_DEBUG
- printf("IPI-UHF read %lx\n",pib_off);
-#endif
- *(uint8_t *)dest = 0; // TODO for SM-VP
- }
- }
- break;
- }
-}
-
+
+/*
+ dir 1: read 0:write
+ inst_type 0:integer 1:floating point
+ */
+extern IA64_BUNDLE __vmx_get_domain_bundle(u64 iip);
+
+
+void emulate_io_inst(VCPU *vcpu, u64 padr, u64 ma)
+{
+ REGS *regs;
+ IA64_BUNDLE bundle;
+ int slot, dir, inst_type=0;
+ size_t size;
+ u64 data, value, slot1a, slot1b;
+ INST64 inst;
+ regs=vcpu_regs(vcpu);
+ bundle = __vmx_get_domain_bundle(regs->cr_iip);
+ slot = ((struct ia64_psr *)&(regs->cr_ipsr))->ri;
+ if (!slot) inst.inst = bundle.slot0;
+ else if (slot == 1){
+ slot1a=bundle.slot1a;
+ slot1b=bundle.slot1b;
+ inst.inst =slot1a + (slot1b<<18);
+ }
+ else if (slot == 2) inst.inst = bundle.slot2;
+
+ if(inst.M1.major==4&&inst.M1.m==0&&inst.M1.x==0){
+ inst_type=0; //fp
+ size=(inst.M1.x6&0x3);
+ if((inst.M1.x6>>2)>0xb){ // write
+ vmx_vcpu_get_gr(vcpu,inst.M4.r2,&data);
+ dir=IOREQ_WRITE; //write
+ }else if((inst.M1.x6>>2)<0xb){ // read
+ vmx_vcpu_get_gr(vcpu,inst.M1.r1,&value);
+ dir=IOREQ_READ;
+ }else{
+ printf("This memory access instruction can't be emulated one :
%lx\n",inst.inst);
+ while(1);
+ }
+ }else if(inst.M6.major==6&&inst.M6.m==0&&inst.M6.x==0&&inst.M6.x6==3){
+ inst_type=1; //fp
+ dir=IOREQ_READ;
+ size=3; //ldfd
+ }else{
+ printf("This memory access instruction can't be emulated two: %lx\n
",inst.inst);
+ while(1);
+ }
+
+ if(dir==IOREQ_WRITE){
+ mmio_access(vcpu, padr, &data, size, ma, dir);
+ }else{
+ mmio_access(vcpu, padr, &data, size, ma, dir);
+ if(size==0)
+ data = (value & 0xffffffffffffff00U) | (data & 0xffU);
+ else if(size==1)
+ data = (value & 0xffffffffffff0000U) | (data & 0xffffU);
+ else if(size==2)
+ data = (value & 0xffffffff00000000U) | (data & 0xffffffffU);
+
+ if(inst_type==0){ //gp
+ vmx_vcpu_set_gr(vcpu,inst.M1.r1,data,0);
+ }else{
+ panic("Don't support ldfd now !");
+/* switch(inst.M6.f1){
+
+ case 6:
+ regs->f6=(struct ia64_fpreg)data;
+ case 7:
+ regs->f7=(struct ia64_fpreg)data;
+ case 8:
+ regs->f8=(struct ia64_fpreg)data;
+ case 9:
+ regs->f9=(struct ia64_fpreg)data;
+ case 10:
+ regs->f10=(struct ia64_fpreg)data;
+ case 11:
+ regs->f11=(struct ia64_fpreg)data;
+ default :
+ ia64_ldfs(inst.M6.f1,&data);
+ }
+*/
+ }
+ }
+ vmx_vcpu_increment_iip(vcpu);
+}
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/vmx_minstate.h
--- a/xen/arch/ia64/vmx_minstate.h Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/vmx_minstate.h Fri Jul 15 13:39:50 2005
@@ -148,10 +148,14 @@
mov r20=r1; /* A */ \
mov r26=ar.unat; /* M */ \
mov r29=cr.ipsr; /* M */ \
+ mov r18=cr.isr; \
COVER; /* B;; (or nothing) */ \
;; \
- tbit.z p6,p7=r29,IA64_PSR_VM_BIT; \
+ tbit.z p6,p0=r29,IA64_PSR_VM_BIT; \
+ tbit.nz.or p6,p0 = r18,39; \
+ ;; \
(p6) br.sptk.few vmx_panic; \
+ tbit.z p0,p15=r29,IA64_PSR_I_BIT; \
mov r1=r16; \
/* mov r21=r16; */ \
/* switch from user to kernel RBS: */ \
diff -r 35b74976f598 -r a83ac0806d6b xen/include/asm-ia64/vmx_vcpu.h
--- a/xen/include/asm-ia64/vmx_vcpu.h Fri Jul 15 12:52:02 2005
+++ b/xen/include/asm-ia64/vmx_vcpu.h Fri Jul 15 13:39:50 2005
@@ -53,7 +53,7 @@
#define VMM_RR_SHIFT 20
#define VMM_RR_MASK ((1UL<<VMM_RR_SHIFT)-1)
-#define VRID_2_MRID(vcpu,rid) ((rid) & VMM_RR_MASK) | \
+//#define VRID_2_MRID(vcpu,rid) ((rid) & VMM_RR_MASK) | \
((vcpu->domain->domain_id) << VMM_RR_SHIFT)
extern u64 indirect_reg_igfld_MASK ( int type, int index, u64 value);
extern u64 cr_igfld_mask (int index, u64 value);
@@ -69,7 +69,7 @@
extern IA64FAULT vmx_vcpu_cover(VCPU *vcpu);
extern thash_cb_t *vmx_vcpu_get_vtlb(VCPU *vcpu);
extern thash_cb_t *vmx_vcpu_get_vhpt(VCPU *vcpu);
-ia64_rr vmx_vcpu_rr(VCPU *vcpu,UINT64 vadr);
+extern ia64_rr vmx_vcpu_rr(VCPU *vcpu,UINT64 vadr);
extern IA64FAULT vmx_vcpu_set_rr(VCPU *vcpu, UINT64 reg, UINT64 val);
extern IA64FAULT vmx_vcpu_get_rr(VCPU *vcpu, UINT64 reg, UINT64 *pval);
extern IA64FAULT vmx_vcpu_get_pkr(VCPU *vcpu, UINT64 reg, UINT64 *pval);
@@ -112,10 +112,10 @@
extern void vmx_inject_vhpi(VCPU *vcpu, u8 vec);
extern void vmx_vcpu_pend_interrupt(VCPU *vcpu, UINT64 vector);
extern struct virutal_platform_def *vmx_vcpu_get_plat(VCPU *vcpu);
-extern void memread_p(VCPU *vcpu, void *src, void *dest, size_t s);
-extern void memread_v(VCPU *vcpu, thash_data_t *vtlb, void *src, void *dest,
size_t s);
-extern void memwrite_v(VCPU *vcpu, thash_data_t *vtlb, void *src, void *dest,
size_t s);
-extern void memwrite_p(VCPU *vcpu, void *src, void *dest, size_t s);
+extern void memread_p(VCPU *vcpu, u64 *src, u64 *dest, size_t s);
+extern void memread_v(VCPU *vcpu, thash_data_t *vtlb, u64 *src, u64 *dest,
size_t s);
+extern void memwrite_v(VCPU *vcpu, thash_data_t *vtlb, u64 *src, u64 *dest,
size_t s);
+extern void memwrite_p(VCPU *vcpu, u64 *src, u64 *dest, size_t s);
/**************************************************************************
@@ -401,14 +401,8 @@
VPD_CR(vcpu,lid)=val;
return IA64_NO_FAULT;
}
-static inline
-IA64FAULT
-vmx_vcpu_set_tpr(VCPU *vcpu, u64 val)
-{
- VPD_CR(vcpu,tpr)=val;
- //TODO
- return IA64_NO_FAULT;
-}
+extern IA64FAULT vmx_vcpu_set_tpr(VCPU *vcpu, u64 val);
+
static inline
IA64FAULT
vmx_vcpu_set_eoi(VCPU *vcpu, u64 val)
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/vmx_ivt.S
--- a/xen/arch/ia64/vmx_ivt.S Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/vmx_ivt.S Fri Jul 15 13:39:50 2005
@@ -347,11 +347,16 @@
mov r31=pr
mov r19=11
mov r30=cr.iim
- mov r29=0x1100
- ;;
- cmp4.eq p6,p7=r29,r30
+ movl r29=0x1100
+ ;;
+ cmp.eq p6,p7=r30,r0
+ (p6) br.sptk vmx_fault_11
+ ;;
+ cmp.eq p6,p7=r29,r30
(p6) br.dptk.few vmx_hypercall_dispatch
(p7) br.sptk.many vmx_dispatch_break_fault
+ ;;
+ VMX_FAULT(11);
END(vmx_break_fault)
.org vmx_ia64_ivt+0x3000
@@ -363,6 +368,8 @@
mov r29=cr.ipsr
;;
tbit.z p6,p7=r29,IA64_PSR_VM_BIT
+ tbit.z p0,p15=r29,IA64_PSR_I_BIT
+ ;;
(p7) br.sptk vmx_dispatch_interrupt
;;
mov r27=ar.rsc /* M */
@@ -447,7 +454,7 @@
;;
srlz.i
;;
- ssm psr.i
+ (p15) ssm psr.i
adds r3=8,r2 // set up second base pointer for SAVE_REST
srlz.i // ensure everybody knows psr.ic is back on
;;
@@ -508,9 +515,12 @@
.org vmx_ia64_ivt+0x3400
/////////////////////////////////////////////////////////////////////////////////////////
// 0x3400 Entry 13 (size 64 bundles) Reserved
+ENTRY(vmx_virtual_exirq)
VMX_DBG_FAULT(13)
- VMX_FAULT(13)
-
+ mov r31=pr
+ mov r19=13
+ br.sptk vmx_dispatch_vexirq
+END(vmx_virtual_exirq)
.org vmx_ia64_ivt+0x3800
/////////////////////////////////////////////////////////////////////////////////////////
@@ -876,7 +886,7 @@
;;
srlz.i // guarantee that interruption collection is on
;;
- ssm psr.i // restore psr.i
+ (p15) ssm psr.i // restore psr.i
adds r3=16,r2 // set up second base pointer
;;
VMX_SAVE_REST
@@ -887,8 +897,6 @@
END(vmx_dispatch_reflection)
ENTRY(vmx_dispatch_virtualization_fault)
- cmp.eq pEml,pNonEml=r0,r0 /* force pEml =1, save r4 ~ r7 */
- ;;
VMX_SAVE_MIN_WITH_COVER_R19
;;
alloc r14=ar.pfs,0,0,3,0 // now it's safe (must be first in insn
group!)
@@ -899,7 +907,7 @@
;;
srlz.i // guarantee that interruption collection is on
;;
- ssm psr.i // restore psr.i
+ (p15) ssm psr.i // restore psr.i
adds r3=16,r2 // set up second base pointer
;;
VMX_SAVE_REST
@@ -910,6 +918,24 @@
END(vmx_dispatch_virtualization_fault)
+ENTRY(vmx_dispatch_vexirq)
+ VMX_SAVE_MIN_WITH_COVER_R19
+ alloc r14=ar.pfs,0,0,1,0
+ mov out0=r13
+
+ ssm psr.ic
+ ;;
+ srlz.i // guarantee that interruption collection is on
+ ;;
+ (p15) ssm psr.i // restore psr.i
+ adds r3=16,r2 // set up second base pointer
+ ;;
+ VMX_SAVE_REST
+ movl r14=ia64_leave_hypervisor
+ ;;
+ mov rp=r14
+ br.call.sptk.many b6=vmx_vexirq
+END(vmx_dispatch_vexirq)
ENTRY(vmx_dispatch_tlb_miss)
VMX_SAVE_MIN_WITH_COVER_R19
@@ -922,7 +948,7 @@
;;
srlz.i // guarantee that interruption collection is on
;;
- ssm psr.i // restore psr.i
+ (p15) ssm psr.i // restore psr.i
adds r3=16,r2 // set up second base pointer
;;
VMX_SAVE_REST
@@ -947,7 +973,7 @@
;;
srlz.i // guarantee that interruption collection is on
;;
- ssm psr.i // restore psr.i
+ (p15)ssm psr.i // restore psr.i
adds r3=16,r2 // set up second base pointer
;;
VMX_SAVE_REST
@@ -965,7 +991,7 @@
;;
srlz.i // guarantee that interruption collection is on
;;
- ssm psr.i // restore psr.i
+ (p15) ssm psr.i // restore psr.i
adds r3=16,r2 // set up second base pointer
;;
VMX_SAVE_REST
@@ -987,8 +1013,6 @@
ENTRY(vmx_dispatch_interrupt)
- cmp.ne pEml,pNonEml=r0,r0 /* force pNonEml =1, don't save r4 ~ r7 */
- ;;
VMX_SAVE_MIN_WITH_COVER_R19 // uses r31; defines r2 and r3
;;
alloc r14=ar.pfs,0,0,2,0 // must be first in an insn group
@@ -999,7 +1023,7 @@
;;
srlz.i
;;
- ssm psr.i
+ (p15) ssm psr.i
adds r3=16,r2 // set up second base pointer for SAVE_REST
;;
VMX_SAVE_REST
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/vhpt.c
--- a/xen/arch/ia64/vhpt.c Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/vhpt.c Fri Jul 15 13:39:50 2005
@@ -90,9 +90,10 @@
void vhpt_multiple_insert(unsigned long vaddr, unsigned long pte, unsigned
long logps)
{
unsigned long mask = (1L << logps) - 1;
+ extern long running_on_sim;
int i;
- if (logps-PAGE_SHIFT > 10) {
+ if (logps-PAGE_SHIFT > 10 && !running_on_sim) {
// if this happens, we may want to revisit this algorithm
printf("vhpt_multiple_insert:logps-PAGE_SHIFT>10,spinning..\n");
while(1);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/bootsetup.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/bootsetup.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,41 @@
+
+#ifndef _X86_64_BOOTSETUP_H
+#define _X86_64_BOOTSETUP_H 1
+
+extern char x86_boot_params[2048];
+
+/*
+ * This is set up by the setup-routine at boot-time
+ */
+#define PARAM ((unsigned char *)x86_boot_params)
+#define SCREEN_INFO (*(struct screen_info *) (PARAM+0))
+#define EXT_MEM_K (*(unsigned short *) (PARAM+2))
+#define ALT_MEM_K (*(unsigned int *) (PARAM+0x1e0))
+#define E820_MAP_NR (*(char*) (PARAM+E820NR))
+#define E820_MAP ((struct e820entry *) (PARAM+E820MAP))
+#define APM_BIOS_INFO (*(struct apm_bios_info *) (PARAM+0x40))
+#define DRIVE_INFO (*(struct drive_info_struct *) (PARAM+0x80))
+#define SYS_DESC_TABLE (*(struct sys_desc_table_struct*)(PARAM+0xa0))
+#define MOUNT_ROOT_RDONLY (*(unsigned short *) (PARAM+0x1F2))
+#define RAMDISK_FLAGS (*(unsigned short *) (PARAM+0x1F8))
+#define SAVED_VIDEO_MODE (*(unsigned short *) (PARAM+0x1FA))
+#define ORIG_ROOT_DEV (*(unsigned short *) (PARAM+0x1FC))
+#define AUX_DEVICE_INFO (*(unsigned char *) (PARAM+0x1FF))
+#define LOADER_TYPE (*(unsigned char *) (PARAM+0x210))
+#define KERNEL_START (*(unsigned int *) (PARAM+0x214))
+
+#define INITRD_START (__pa(xen_start_info.mod_start))
+#define INITRD_SIZE (xen_start_info.mod_len)
+#define EDID_INFO (*(struct edid_info *) (PARAM+0x440))
+
+#define EDD_NR (*(unsigned char *) (PARAM+EDDNR))
+#define EDD_MBR_SIG_NR (*(unsigned char *) (PARAM+EDD_MBR_SIG_NR_BUF))
+#define EDD_MBR_SIGNATURE ((unsigned int *) (PARAM+EDD_MBR_SIG_BUF))
+#define EDD_BUF ((struct edd_info *) (PARAM+EDDBUF))
+#define COMMAND_LINE saved_command_line
+
+#define RAMDISK_IMAGE_START_MASK 0x07FF
+#define RAMDISK_PROMPT_FLAG 0x8000
+#define RAMDISK_LOAD_FLAG 0x4000
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/lib/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/lib/Makefile Fri Jul 15 13:39:50 2005
@@ -0,0 +1,15 @@
+
+.S.o:
+ $(CC) $(AFLAGS) -c $< -o $*.o
+
+L_TARGET = lib.a
+
+obj-y = checksum.o old-checksum.o delay.o \
+ usercopy.o getuser.o \
+ memcpy.o strstr.o xen_proc.o
+
+obj-$(CONFIG_X86_USE_3DNOW) += mmx.o
+obj-$(CONFIG_HAVE_DEC_LOCK) += dec_and_lock.o
+obj-$(CONFIG_DEBUG_IOVIRT) += iodebug.o
+
+include $(TOPDIR)/Rules.make
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/spinlock.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/spinlock.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,250 @@
+#ifndef __ASM_SPINLOCK_H
+#define __ASM_SPINLOCK_H
+
+#include <asm/atomic.h>
+#include <asm/rwlock.h>
+#include <asm/page.h>
+#include <linux/config.h>
+#include <linux/compiler.h>
+
+asmlinkage int printk(const char * fmt, ...)
+ __attribute__ ((format (printf, 1, 2)));
+
+/*
+ * Your basic SMP spinlocks, allowing only a single CPU anywhere
+ */
+
+typedef struct {
+ volatile unsigned int slock;
+#ifdef CONFIG_DEBUG_SPINLOCK
+ unsigned magic;
+#endif
+#ifdef CONFIG_PREEMPT
+ unsigned int break_lock;
+#endif
+} spinlock_t;
+
+#define SPINLOCK_MAGIC 0xdead4ead
+
+#ifdef CONFIG_DEBUG_SPINLOCK
+#define SPINLOCK_MAGIC_INIT , SPINLOCK_MAGIC
+#else
+#define SPINLOCK_MAGIC_INIT /* */
+#endif
+
+#define SPIN_LOCK_UNLOCKED (spinlock_t) { 1 SPINLOCK_MAGIC_INIT }
+
+#define spin_lock_init(x) do { *(x) = SPIN_LOCK_UNLOCKED; } while(0)
+
+/*
+ * Simple spin lock operations. There are two variants, one clears IRQ's
+ * on the local processor, one does not.
+ *
+ * We make no fairness assumptions. They have a cost.
+ */
+
+#define spin_is_locked(x) (*(volatile signed char *)(&(x)->slock) <= 0)
+#define spin_unlock_wait(x) do { barrier(); } while(spin_is_locked(x))
+
+#define spin_lock_string \
+ "\n1:\t" \
+ "lock ; decb %0\n\t" \
+ "jns 3f\n" \
+ "2:\t" \
+ "rep;nop\n\t" \
+ "cmpb $0,%0\n\t" \
+ "jle 2b\n\t" \
+ "jmp 1b\n" \
+ "3:\n\t"
+
+#define spin_lock_string_flags \
+ "\n1:\t" \
+ "lock ; decb %0\n\t" \
+ "jns 4f\n\t" \
+ "2:\t" \
+ "testl $0x200, %1\n\t" \
+ "jz 3f\n\t" \
+ "#sti\n\t" \
+ "3:\t" \
+ "rep;nop\n\t" \
+ "cmpb $0, %0\n\t" \
+ "jle 3b\n\t" \
+ "#cli\n\t" \
+ "jmp 1b\n" \
+ "4:\n\t"
+
+/*
+ * This works. Despite all the confusion.
+ * (except on PPro SMP or if we are using OOSTORE)
+ * (PPro errata 66, 92)
+ */
+
+#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE)
+
+#define spin_unlock_string \
+ "movb $1,%0" \
+ :"=m" (lock->slock) : : "memory"
+
+
+static inline void _raw_spin_unlock(spinlock_t *lock)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK
+ BUG_ON(lock->magic != SPINLOCK_MAGIC);
+ BUG_ON(!spin_is_locked(lock));
+#endif
+ __asm__ __volatile__(
+ spin_unlock_string
+ );
+}
+
+#else
+
+#define spin_unlock_string \
+ "xchgb %b0, %1" \
+ :"=q" (oldval), "=m" (lock->slock) \
+ :"0" (oldval) : "memory"
+
+static inline void _raw_spin_unlock(spinlock_t *lock)
+{
+ char oldval = 1;
+#ifdef CONFIG_DEBUG_SPINLOCK
+ BUG_ON(lock->magic != SPINLOCK_MAGIC);
+ BUG_ON(!spin_is_locked(lock));
+#endif
+ __asm__ __volatile__(
+ spin_unlock_string
+ );
+}
+
+#endif
+
+static inline int _raw_spin_trylock(spinlock_t *lock)
+{
+ char oldval;
+ __asm__ __volatile__(
+ "xchgb %b0,%1"
+ :"=q" (oldval), "=m" (lock->slock)
+ :"0" (0) : "memory");
+ return oldval > 0;
+}
+
+static inline void _raw_spin_lock(spinlock_t *lock)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK
+ if (unlikely(lock->magic != SPINLOCK_MAGIC)) {
+ printk("eip: %p\n", __builtin_return_address(0));
+ BUG();
+ }
+#endif
+ __asm__ __volatile__(
+ spin_lock_string
+ :"=m" (lock->slock) : : "memory");
+}
+
+static inline void _raw_spin_lock_flags (spinlock_t *lock, unsigned long flags)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK
+ if (unlikely(lock->magic != SPINLOCK_MAGIC)) {
+ printk("eip: %p\n", __builtin_return_address(0));
+ BUG();
+ }
+#endif
+ __asm__ __volatile__(
+ spin_lock_string_flags
+ :"=m" (lock->slock) : "r" (flags) : "memory");
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers
+ * but only one writer.
+ *
+ * NOTE! it is quite common to have readers in interrupts
+ * but no interrupt writers. For those circumstances we
+ * can "mix" irq-safe locks - any writer needs to get a
+ * irq-safe write-lock, but readers can get non-irqsafe
+ * read-locks.
+ */
+typedef struct {
+ volatile unsigned int lock;
+#ifdef CONFIG_DEBUG_SPINLOCK
+ unsigned magic;
+#endif
+#ifdef CONFIG_PREEMPT
+ unsigned int break_lock;
+#endif
+} rwlock_t;
+
+#define RWLOCK_MAGIC 0xdeaf1eed
+
+#ifdef CONFIG_DEBUG_SPINLOCK
+#define RWLOCK_MAGIC_INIT , RWLOCK_MAGIC
+#else
+#define RWLOCK_MAGIC_INIT /* */
+#endif
+
+#define RW_LOCK_UNLOCKED (rwlock_t) { RW_LOCK_BIAS RWLOCK_MAGIC_INIT }
+
+#define rwlock_init(x) do { *(x) = RW_LOCK_UNLOCKED; } while(0)
+
+/**
+ * read_can_lock - would read_trylock() succeed?
+ * @lock: the rwlock in question.
+ */
+#define read_can_lock(x) ((int)(x)->lock > 0)
+
+/**
+ * write_can_lock - would write_trylock() succeed?
+ * @lock: the rwlock in question.
+ */
+#define write_can_lock(x) ((x)->lock == RW_LOCK_BIAS)
+
+/*
+ * On x86, we implement read-write locks as a 32-bit counter
+ * with the high bit (sign) being the "contended" bit.
+ *
+ * The inline assembly is non-obvious. Think about it.
+ *
+ * Changed to use the same technique as rw semaphores. See
+ * semaphore.h for details. -ben
+ */
+/* the spinlock helpers are in arch/i386/kernel/semaphore.c */
+
+static inline void _raw_read_lock(rwlock_t *rw)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK
+ BUG_ON(rw->magic != RWLOCK_MAGIC);
+#endif
+ __build_read_lock(rw, "__read_lock_failed");
+}
+
+static inline void _raw_write_lock(rwlock_t *rw)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK
+ BUG_ON(rw->magic != RWLOCK_MAGIC);
+#endif
+ __build_write_lock(rw, "__write_lock_failed");
+}
+
+#define _raw_read_unlock(rw) asm volatile("lock ; incl %0" :"=m"
((rw)->lock) : : "memory")
+#define _raw_write_unlock(rw) asm volatile("lock ; addl $" RW_LOCK_BIAS_STR
",%0":"=m" ((rw)->lock) : : "memory")
+
+static inline int _raw_read_trylock(rwlock_t *lock)
+{
+ atomic_t *count = (atomic_t *)lock;
+ atomic_dec(count);
+ if (atomic_read(count) >= 0)
+ return 1;
+ atomic_inc(count);
+ return 0;
+}
+
+static inline int _raw_write_trylock(rwlock_t *lock)
+{
+ atomic_t *count = (atomic_t *)lock;
+ if (atomic_sub_and_test(RW_LOCK_BIAS, count))
+ return 1;
+ atomic_add(RW_LOCK_BIAS, count);
+ return 0;
+}
+
+#endif /* __ASM_SPINLOCK_H */
diff -r 35b74976f598 -r a83ac0806d6b linux-2.6.11-xen-sparse/arch/xen/Kconfig
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/Kconfig Fri Jul 15 13:39:50 2005
@@ -0,0 +1,196 @@
+#
+# For a description of the syntax of this configuration file,
+# see Documentation/kbuild/kconfig-language.txt.
+#
+
+mainmenu "Linux Kernel Configuration"
+
+config XEN
+ bool
+ default y
+ help
+ This is the Linux Xen port.
+
+config ARCH_XEN
+ bool
+ default y
+
+
+config NO_IDLE_HZ
+ bool
+ default y
+
+
+menu "XEN"
+
+config XEN_PRIVILEGED_GUEST
+ bool "Privileged Guest (domain 0)"
+ default n
+ select XEN_PHYSDEV_ACCESS
+ help
+ Support for privileged operation (domain 0)
+
+config XEN_PHYSDEV_ACCESS
+ bool "Physical device access"
+ default XEN_PRIVILEGED_GUEST
+ help
+ Assume access is available to physical hardware devices
+ (e.g., hard drives, network cards). This allows you to configure
+ such devices and also includes some low-level support that is
+ otherwise not compiled into the kernel.
+
+config XEN_BLKDEV_BACKEND
+ bool "Block-device backend driver"
+ depends on XEN_PHYSDEV_ACCESS
+ default y
+ help
+ The block-device backend driver allows the kernel to export its
+ block devices to other guests via a high-performance shared-memory
+ interface.
+
+config XEN_BLKDEV_TAP_BE
+ bool "Block Tap support for backend driver (DANGEROUS)"
+ depends on XEN_BLKDEV_BACKEND
+ default n
+ help
+ If you intend to use the block tap driver, the backend domain will
+ not know the domain id of the real frontend, and so will not be able
+ to map its data pages. This modifies the backend to attempt to map
+ from both the tap domain and the real frontend. This presents a
+ security risk, and so should ONLY be used for development
+ with the blktap. This option will be removed as the block drivers
are
+ modified to use grant tables.
+
+config XEN_BLKDEV_GRANT
+ bool "Grant table substrate for block drivers"
+ depends on !XEN_BLKDEV_TAP_BE
+ default y
+ help
+ This introduces the use of grant tables as a data exhange mechanism
+ between the frontend and backend block drivers. This currently
+ conflicts with the block tap.
+
+config XEN_NETDEV_BACKEND
+ bool "Network-device backend driver"
+ depends on XEN_PHYSDEV_ACCESS
+ default y
+ help
+ The network-device backend driver allows the kernel to export its
+ network devices to other guests via a high-performance shared-memory
+ interface.
+
+config XEN_BLKDEV_FRONTEND
+ bool "Block-device frontend driver"
+ default y
+ help
+ The block-device frontend driver allows the kernel to access block
+ devices mounted within another guest OS. Unless you are building a
+ dedicated device-driver domain, or your master control domain
+ (domain 0), then you almost certainly want to say Y here.
+
+config XEN_NETDEV_FRONTEND
+ bool "Network-device frontend driver"
+ default y
+ help
+ The network-device frontend driver allows the kernel to access
+ network interfaces within another guest OS. Unless you are building a
+ dedicated device-driver domain, or your master control domain
+ (domain 0), then you almost certainly want to say Y here.
+
+config XEN_NETDEV_FRONTEND_PIPELINED_TRANSMITTER
+ bool "Pipelined transmitter (DANGEROUS)"
+ depends on XEN_NETDEV_FRONTEND
+ default n
+ help
+ The driver will assume that the backend is pipelining packets for
+ transmission: whenever packets are pending in the remote backend,
+ the driver will not send asynchronous notifications when it queues
+ additional packets for transmission.
+ If the backend is a dumb domain, such as a transparent Ethernet
+ bridge with no local IP interface, it is safe to say Y here to get
+ slightly lower network overhead.
+ If the backend has a local IP interface; or may be doing smart things
+ like reassembling packets to perform firewall filtering; or if you
+ are unsure; or if you experience network hangs when this option is
+ enabled; then you must say N here.
+
+config XEN_BLKDEV_TAP
+ bool "Block device tap driver"
+ default n
+ help
+ This driver allows a VM to interact on block device channels
+ to other VMs. Block messages may be passed through or redirected
+ to a character device, allowing device prototyping in application
+ space. Odds are that you want to say N here.
+
+config XEN_SHADOW_MODE
+ bool "Fake shadow mode"
+ default n
+ help
+ fakes out a shadow mode kernel
+
+
+config XEN_SCRUB_PAGES
+ bool "Scrub memory before freeing it to Xen"
+ default y
+ help
+ Erase memory contents before freeing it back to Xen's global
+ pool. This ensures that any secrets contained within that
+ memory (e.g., private keys) cannot be found by other guests that
+ may be running on the machine. Most people will want to say Y here.
+ If security is not a concern then you may increase performance by
+ saying N.
+
+choice
+ prompt "Processor Type"
+ default XEN_X86
+
+config XEN_X86
+ bool "X86"
+ help
+ Choose this option if your computer is a X86 architecture.
+
+config XEN_X86_64
+ bool "X86_64"
+ help
+ Choose this option if your computer is a X86_64 architecture.
+
+endchoice
+
+endmenu
+
+config HAVE_ARCH_DEV_ALLOC_SKB
+ bool
+ default y
+
+source "init/Kconfig"
+
+if XEN_X86
+source "arch/xen/i386/Kconfig"
+endif
+
+if XEN_X86_64
+source "arch/xen/x86_64/Kconfig"
+endif
+
+menu "Executable file formats"
+
+source "fs/Kconfig.binfmt"
+
+endmenu
+
+source "arch/xen/Kconfig.drivers"
+
+if XEN_PRIVILEGED_GUEST
+menu "Power management options"
+source "drivers/acpi/Kconfig"
+endmenu
+endif
+
+source "fs/Kconfig"
+
+source "security/Kconfig"
+
+source "crypto/Kconfig"
+
+source "lib/Kconfig"
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/Makefile Fri Jul 15 13:39:50 2005
@@ -0,0 +1,103 @@
+#
+# i386/Makefile
+#
+# This file is included by the global makefile so that you can add your own
+# architecture-specific flags and dependencies. Remember to do have actions
+# for "archclean" cleaning up for this architecture.
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License. See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 1994 by Linus Torvalds
+#
+# 19990713 Artur Skawina <skawina@xxxxxxxxxxxxx>
+# Added '-march' and '-mpreferred-stack-boundary' support
+#
+
+XENARCH := $(subst ",,$(CONFIG_XENARCH))
+
+LDFLAGS := -m elf_i386
+LDFLAGS_vmlinux :=
+CHECK := $(CHECK) -D__i386__=1
+
+CFLAGS += -m32
+AFLAGS += -m32
+
+CFLAGS += -pipe -msoft-float
+
+# prevent gcc from keeping the stack 16 byte aligned
+CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2,)
+
+align := $(cc-option-align)
+cflags-$(CONFIG_M386) += -march=i386
+cflags-$(CONFIG_M486) += -march=i486
+cflags-$(CONFIG_M586) += -march=i586
+cflags-$(CONFIG_M586TSC) += -march=i586
+cflags-$(CONFIG_M586MMX) += $(call
cc-option,-march=pentium-mmx,-march=i586)
+cflags-$(CONFIG_M686) += -march=i686
+cflags-$(CONFIG_MPENTIUMII) += -march=i686 $(call cc-option,-mtune=pentium2)
+cflags-$(CONFIG_MPENTIUMIII) += -march=i686 $(call cc-option,-mtune=pentium3)
+cflags-$(CONFIG_MPENTIUMM) += -march=i686 $(call cc-option,-mtune=pentium3)
+cflags-$(CONFIG_MPENTIUM4) += -march=i686 $(call cc-option,-mtune=pentium4)
+cflags-$(CONFIG_MK6) += -march=k6
+# Please note, that patches that add -march=athlon-xp and friends are
pointless.
+# They make zero difference whatsosever to performance at this time.
+cflags-$(CONFIG_MK7) += $(call cc-option,-march=athlon,-march=i686
$(align)-functions=4)
+cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,$(call
cc-option,-march=athlon,-march=i686 $(align)-functions=4))
+cflags-$(CONFIG_MCRUSOE) += -march=i686 $(align)-functions=0
$(align)-jumps=0 $(align)-loops=0
+cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call
cc-option,-mtune=pentium3) $(align)-functions=0 $(align)-jumps=0
$(align)-loops=0
+cflags-$(CONFIG_MWINCHIPC6) += $(call
cc-option,-march=winchip-c6,-march=i586)
+cflags-$(CONFIG_MWINCHIP2) += $(call cc-option,-march=winchip2,-march=i586)
+cflags-$(CONFIG_MWINCHIP3D) += $(call cc-option,-march=winchip2,-march=i586)
+cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486)
$(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
+cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686)
+
+# AMD Elan support
+cflags-$(CONFIG_X86_ELAN) += -march=i486
+
+# -mregparm=3 works ok on gcc-3.0 and later
+#
+GCC_VERSION := $(shell $(CONFIG_SHELL)
$(srctree)/scripts/gcc-version.sh $(CC))
+cflags-$(CONFIG_REGPARM) += $(shell if [ $(GCC_VERSION) -ge 0300 ] ;
then echo "-mregparm=3"; fi ;)
+
+# Disable unit-at-a-time mode, it makes gcc use a lot more stack
+# due to the lack of sharing of stacklots.
+CFLAGS += $(call cc-option,-fno-unit-at-a-time,)
+
+CFLAGS += $(cflags-y)
+
+head-y := arch/xen/i386/kernel/head.o arch/xen/i386/kernel/init_task.o
+
+libs-y += arch/i386/lib/
+core-y += arch/xen/i386/kernel/ \
+ arch/xen/i386/mm/ \
+ arch/xen/i386/mach-default/ \
+ arch/i386/crypto/
+# \
+# arch/xen/$(mcore-y)/
+drivers-$(CONFIG_MATH_EMULATION) += arch/i386/math-emu/
+drivers-$(CONFIG_PCI) += arch/xen/i386/pci/
+# must be linked after kernel/
+drivers-$(CONFIG_OPROFILE) += arch/i386/oprofile/
+drivers-$(CONFIG_PM) += arch/i386/power/
+
+# for clean
+obj- += kernel/ mm/ pci/
+#obj- += ../../i386/lib/ ../../i386/mm/
+#../../i386/$(mcore-y)/
+#obj- += ../../i386/pci/ ../../i386/oprofile/ ../../i386/power/
+
+xenflags-y += -Iinclude/asm-xen/asm-i386/mach-xen \
+ -Iinclude/asm-i386/mach-default
+CFLAGS += $(xenflags-y)
+AFLAGS += $(xenflags-y)
+
+prepare: include/asm-$(XENARCH)/asm_offsets.h
+CLEAN_FILES += include/asm-$(XENARCH)/asm_offsets.h
+
+arch/$(XENARCH)/kernel/asm-offsets.s: include/asm include/.asm-ignore \
+ include/linux/version.h include/config/MARKER
+
+include/asm-$(XENARCH)/asm_offsets.h: arch/$(XENARCH)/kernel/asm-offsets.s
+ $(call filechk,gen-asm-offsets)
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/vga.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/vga.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,42 @@
+/*
+ * Access to VGA videoram
+ *
+ * (c) 1998 Martin Mares <mj@xxxxxx>
+ */
+
+#ifndef _LINUX_ASM_VGA_H_
+#define _LINUX_ASM_VGA_H_
+
+#include <asm/io.h>
+
+extern unsigned char *vgacon_mmap;
+
+static unsigned long VGA_MAP_MEM(unsigned long x)
+{
+ if( vgacon_mmap == NULL )
+ {
+ /* This is our first time in this function. This whole thing
+ is a rather grim hack. We know we're going to get asked
+ to map a 32KB region between 0xb0000 and 0xb8000 because
+ that's what VGAs are. We used the boot time permanent
+ fixed map region, and map it to machine pages.
+ */
+ if( x != 0xb8000 )
+ panic("Argghh! VGA Console is weird. 1:%08lx\n",x);
+
+ vgacon_mmap = (unsigned char*) bt_ioremap( 0xa0000, 128*1024 );
+ return (unsigned long) (vgacon_mmap+x-0xa0000);
+ }
+ else
+ {
+ if( x != 0xc0000 && x != 0xa0000 ) /* vidmem_end or charmap fonts */
+ panic("Argghh! VGA Console is weird. 2:%08lx\n",x);
+ return (unsigned long) (vgacon_mmap+x-0xa0000);
+ }
+ return 0;
+}
+
+static inline unsigned char vga_readb(unsigned char * x) { return (*(x)); }
+static inline void vga_writeb(unsigned char x, unsigned char *y) { *(y) = (x);
}
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/kernel/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/kernel/Makefile Fri Jul 15 13:39:50 2005
@@ -0,0 +1,18 @@
+#
+# Makefile for the linux kernel.
+#
+
+XENARCH := $(subst ",,$(CONFIG_XENARCH))
+
+CPPFLAGS_vmlinux.lds += -U$(XENARCH)
+
+$(obj)/vmlinux.lds.S:
+ @ln -fsn $(srctree)/arch/$(XENARCH)/kernel/vmlinux.lds.S $@
+
+extra-y += vmlinux.lds
+
+obj-y := ctrl_if.o evtchn.o fixup.o reboot.o gnttab.o devmem.o
+
+obj-$(CONFIG_PROC_FS) += xen_proc.o
+obj-$(CONFIG_NET) += skbuff.o
+obj-$(CONFIG_SMP) += smp.o
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/processor.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/processor.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,474 @@
+/*
+ * include/asm-x86_64/processor.h
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ */
+
+#ifndef __ASM_X86_64_PROCESSOR_H
+#define __ASM_X86_64_PROCESSOR_H
+
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/types.h>
+#include <asm/sigcontext.h>
+#include <asm/cpufeature.h>
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <asm/msr.h>
+#include <asm/current.h>
+#include <asm/system.h>
+#include <asm/mmsegment.h>
+#include <asm/percpu.h>
+#include <linux/personality.h>
+
+#define TF_MASK 0x00000100
+#define IF_MASK 0x00000200
+#define IOPL_MASK 0x00003000
+#define NT_MASK 0x00004000
+#define VM_MASK 0x00020000
+#define AC_MASK 0x00040000
+#define VIF_MASK 0x00080000 /* virtual interrupt flag */
+#define VIP_MASK 0x00100000 /* virtual interrupt pending */
+#define ID_MASK 0x00200000
+
+#define desc_empty(desc) \
+ (!((desc)->a + (desc)->b))
+
+#define desc_equal(desc1, desc2) \
+ (((desc1)->a == (desc2)->a) && ((desc1)->b == (desc2)->b))
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#define current_text_addr() ({ void *pc; asm volatile("leaq
1f(%%rip),%0\n1:":"=r"(pc)); pc; })
+
+/*
+ * CPU type and hardware bug flags. Kept separately for each CPU.
+ */
+
+struct cpuinfo_x86 {
+ __u8 x86; /* CPU family */
+ __u8 x86_vendor; /* CPU vendor */
+ __u8 x86_model;
+ __u8 x86_mask;
+ int cpuid_level; /* Maximum supported CPUID level, -1=no CPUID */
+ __u32 x86_capability[NCAPINTS];
+ char x86_vendor_id[16];
+ char x86_model_id[64];
+ int x86_cache_size; /* in KB */
+ int x86_clflush_size;
+ int x86_cache_alignment;
+ int x86_tlbsize; /* number of 4K pages in DTLB/ITLB combined(in
pages)*/
+ __u8 x86_virt_bits, x86_phys_bits;
+ __u8 x86_num_cores;
+ __u8 x86_apicid;
+ __u32 x86_power;
+ __u32 x86_cpuid_level; /* Max CPUID function supported */
+ unsigned long loops_per_jiffy;
+} ____cacheline_aligned;
+
+#define X86_VENDOR_INTEL 0
+#define X86_VENDOR_CYRIX 1
+#define X86_VENDOR_AMD 2
+#define X86_VENDOR_UMC 3
+#define X86_VENDOR_NEXGEN 4
+#define X86_VENDOR_CENTAUR 5
+#define X86_VENDOR_RISE 6
+#define X86_VENDOR_TRANSMETA 7
+#define X86_VENDOR_NUM 8
+#define X86_VENDOR_UNKNOWN 0xff
+
+#ifdef CONFIG_SMP
+extern struct cpuinfo_x86 cpu_data[];
+#define current_cpu_data cpu_data[smp_processor_id()]
+#else
+#define cpu_data (&boot_cpu_data)
+#define current_cpu_data boot_cpu_data
+#endif
+
+extern char ignore_irq13;
+
+extern void identify_cpu(struct cpuinfo_x86 *);
+extern void print_cpu_info(struct cpuinfo_x86 *);
+extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
+extern void dodgy_tsc(void);
+
+/*
+ * EFLAGS bits
+ */
+#define X86_EFLAGS_CF 0x00000001 /* Carry Flag */
+#define X86_EFLAGS_PF 0x00000004 /* Parity Flag */
+#define X86_EFLAGS_AF 0x00000010 /* Auxillary carry Flag */
+#define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */
+#define X86_EFLAGS_SF 0x00000080 /* Sign Flag */
+#define X86_EFLAGS_TF 0x00000100 /* Trap Flag */
+#define X86_EFLAGS_IF 0x00000200 /* Interrupt Flag */
+#define X86_EFLAGS_DF 0x00000400 /* Direction Flag */
+#define X86_EFLAGS_OF 0x00000800 /* Overflow Flag */
+#define X86_EFLAGS_IOPL 0x00003000 /* IOPL mask */
+#define X86_EFLAGS_NT 0x00004000 /* Nested Task */
+#define X86_EFLAGS_RF 0x00010000 /* Resume Flag */
+#define X86_EFLAGS_VM 0x00020000 /* Virtual Mode */
+#define X86_EFLAGS_AC 0x00040000 /* Alignment Check */
+#define X86_EFLAGS_VIF 0x00080000 /* Virtual Interrupt Flag */
+#define X86_EFLAGS_VIP 0x00100000 /* Virtual Interrupt Pending */
+#define X86_EFLAGS_ID 0x00200000 /* CPUID detection flag */
+
+/*
+ * Intel CPU features in CR4
+ */
+#define X86_CR4_VME 0x0001 /* enable vm86 extensions */
+#define X86_CR4_PVI 0x0002 /* virtual interrupts flag enable */
+#define X86_CR4_TSD 0x0004 /* disable time stamp at ipl 3 */
+#define X86_CR4_DE 0x0008 /* enable debugging extensions */
+#define X86_CR4_PSE 0x0010 /* enable page size extensions */
+#define X86_CR4_PAE 0x0020 /* enable physical address extensions */
+#define X86_CR4_MCE 0x0040 /* Machine check enable */
+#define X86_CR4_PGE 0x0080 /* enable global pages */
+#define X86_CR4_PCE 0x0100 /* enable performance counters at ipl 3
*/
+#define X86_CR4_OSFXSR 0x0200 /* enable fast FPU save and restore */
+#define X86_CR4_OSXMMEXCPT 0x0400 /* enable unmasked SSE exceptions */
+
+/*
+ * Save the cr4 feature set we're using (ie
+ * Pentium 4MB enable and PPro Global page
+ * enable), so that any CPU's that boot up
+ * after us can get the correct flags.
+ */
+extern unsigned long mmu_cr4_features;
+
+static inline void set_in_cr4 (unsigned long mask)
+{
+ mmu_cr4_features |= mask;
+ switch (mask) {
+ case X86_CR4_OSFXSR:
+ case X86_CR4_OSXMMEXCPT:
+ break;
+ default:
+ do {
+ const char *msg = "Xen unsupported cr4 update\n";
+ (void)HYPERVISOR_console_io(
+ CONSOLEIO_write, __builtin_strlen(msg),
+ (char *)msg);
+ BUG();
+ } while (0);
+ }
+}
+
+#define load_cr3(pgdir) do { \
+ xen_pt_switch(__pa(pgdir)); \
+ per_cpu(cur_pgd, smp_processor_id()) = pgdir; \
+} while (/* CONSTCOND */0)
+
+/*
+ * Bus types
+ */
+#define MCA_bus 0
+#define MCA_bus__is_a_macro
+
+
+/*
+ * User space process size. 47bits.
+ */
+#define TASK_SIZE (0x800000000000UL)
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define IA32_PAGE_OFFSET ((current->personality & ADDR_LIMIT_3GB) ? 0xc0000000
: 0xFFFFe000)
+#define TASK_UNMAPPED_32 PAGE_ALIGN(IA32_PAGE_OFFSET/3)
+#define TASK_UNMAPPED_64 PAGE_ALIGN(TASK_SIZE/3)
+#define TASK_UNMAPPED_BASE \
+ (test_thread_flag(TIF_IA32) ? TASK_UNMAPPED_32 : TASK_UNMAPPED_64)
+
+/*
+ * Size of io_bitmap.
+ */
+#define IO_BITMAP_BITS 65536
+#define IO_BITMAP_BYTES (IO_BITMAP_BITS/8)
+#define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long))
+#define IO_BITMAP_OFFSET offsetof(struct tss_struct,io_bitmap)
+#define INVALID_IO_BITMAP_OFFSET 0x8000
+
+struct i387_fxsave_struct {
+ u16 cwd;
+ u16 swd;
+ u16 twd;
+ u16 fop;
+ u64 rip;
+ u64 rdp;
+ u32 mxcsr;
+ u32 mxcsr_mask;
+ u32 st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */
+ u32 xmm_space[64]; /* 16*16 bytes for each XMM-reg = 128 bytes */
+ u32 padding[24];
+} __attribute__ ((aligned (16)));
+
+union i387_union {
+ struct i387_fxsave_struct fxsave;
+};
+
+struct tss_struct {
+ u32 reserved1;
+ u64 rsp0;
+ u64 rsp1;
+ u64 rsp2;
+ u64 reserved2;
+ u64 ist[7];
+ u32 reserved3;
+ u32 reserved4;
+ u16 reserved5;
+ u16 io_bitmap_base;
+ /*
+ * The extra 1 is there because the CPU will access an
+ * additional byte beyond the end of the IO permission
+ * bitmap. The extra byte must be all 1 bits, and must
+ * be within the limit. Thus we have:
+ *
+ * 128 bytes, the bitmap itself, for ports 0..0x3ff
+ * 8 bytes, for an extra "long" of ~0UL
+ */
+ unsigned long io_bitmap[IO_BITMAP_LONGS + 1];
+} __attribute__((packed)) ____cacheline_aligned;
+
+extern struct cpuinfo_x86 boot_cpu_data;
+DECLARE_PER_CPU(struct tss_struct,init_tss);
+DECLARE_PER_CPU(pgd_t *, cur_pgd);
+
+#define ARCH_MIN_TASKALIGN 16
+
+struct thread_struct {
+ unsigned long rsp0;
+ unsigned long rsp;
+ unsigned long userrsp; /* Copy from PDA */
+ unsigned long fs;
+ unsigned long gs;
+ unsigned int io_pl;
+ unsigned short es, ds, fsindex, gsindex;
+/* Hardware debugging registers */
+ unsigned long debugreg0;
+ unsigned long debugreg1;
+ unsigned long debugreg2;
+ unsigned long debugreg3;
+ unsigned long debugreg6;
+ unsigned long debugreg7;
+/* fault info */
+ unsigned long cr2, trap_no, error_code;
+/* floating point info */
+ union i387_union i387 __attribute__((aligned(16)));
+/* IO permissions. the bitmap could be moved into the GDT, that would make
+ switch faster for a limited number of ioperm using tasks. -AK */
+ int ioperm;
+ unsigned long *io_bitmap_ptr;
+ unsigned io_bitmap_max;
+/* cached TLS descriptors. */
+ u64 tls_array[GDT_ENTRY_TLS_ENTRIES];
+} __attribute__((aligned(16)));
+
+#define INIT_THREAD {}
+
+#define INIT_MMAP \
+{ &init_mm, 0, 0, NULL, PAGE_SHARED, VM_READ | VM_WRITE | VM_EXEC, 1, NULL,
NULL }
+
+#define STACKFAULT_STACK 1
+#define DOUBLEFAULT_STACK 2
+#define NMI_STACK 3
+#define DEBUG_STACK 4
+#define MCE_STACK 5
+#define N_EXCEPTION_STACKS 5 /* hw limit: 7 */
+#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
+#define EXCEPTION_STACK_ORDER 0
+
+#define start_thread(regs,new_rip,new_rsp) do { \
+ asm volatile("movl %0,%%fs; movl %0,%%es; movl %0,%%ds": :"r" (0));
\
+ load_gs_index(0);
\
+ (regs)->rip = (new_rip);
\
+ (regs)->rsp = (new_rsp);
\
+ write_pda(oldrsp, (new_rsp));
\
+ (regs)->cs = __USER_CS;
\
+ (regs)->ss = __USER_DS;
\
+ (regs)->eflags = 0x200;
\
+ set_fs(USER_DS);
\
+} while(0)
+
+struct task_struct;
+struct mm_struct;
+
+/* Free all resources held by a thread. */
+extern void release_thread(struct task_struct *);
+
+/* Prepare to copy thread state - unlazy all lazy status */
+extern void prepare_to_copy(struct task_struct *tsk);
+
+/*
+ * create a kernel thread without removing it from tasklists
+ */
+extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
+
+/*
+ * Return saved PC of a blocked thread.
+ * What is this good for? it will be always the scheduler or ret_from_fork.
+ */
+#define thread_saved_pc(t) (*(unsigned long *)((t)->thread.rsp - 8))
+
+extern unsigned long get_wchan(struct task_struct *p);
+#define KSTK_EIP(tsk) \
+ (((struct pt_regs *)(tsk->thread.rsp0 - sizeof(struct pt_regs)))->rip)
+#define KSTK_ESP(tsk) -1 /* sorry. doesn't work for syscall. */
+
+
+struct microcode_header {
+ unsigned int hdrver;
+ unsigned int rev;
+ unsigned int date;
+ unsigned int sig;
+ unsigned int cksum;
+ unsigned int ldrver;
+ unsigned int pf;
+ unsigned int datasize;
+ unsigned int totalsize;
+ unsigned int reserved[3];
+};
+
+struct microcode {
+ struct microcode_header hdr;
+ unsigned int bits[0];
+};
+
+typedef struct microcode microcode_t;
+typedef struct microcode_header microcode_header_t;
+
+/* microcode format is extended from prescott processors */
+struct extended_signature {
+ unsigned int sig;
+ unsigned int pf;
+ unsigned int cksum;
+};
+
+struct extended_sigtable {
+ unsigned int count;
+ unsigned int cksum;
+ unsigned int reserved[3];
+ struct extended_signature sigs[0];
+};
+
+/* '6' because it used to be for P6 only (but now covers Pentium 4 as well) */
+#define MICROCODE_IOCFREE _IO('6',0)
+
+
+#define ASM_NOP1 K8_NOP1
+#define ASM_NOP2 K8_NOP2
+#define ASM_NOP3 K8_NOP3
+#define ASM_NOP4 K8_NOP4
+#define ASM_NOP5 K8_NOP5
+#define ASM_NOP6 K8_NOP6
+#define ASM_NOP7 K8_NOP7
+#define ASM_NOP8 K8_NOP8
+
+/* Opteron nops */
+#define K8_NOP1 ".byte 0x90\n"
+#define K8_NOP2 ".byte 0x66,0x90\n"
+#define K8_NOP3 ".byte 0x66,0x66,0x90\n"
+#define K8_NOP4 ".byte 0x66,0x66,0x66,0x90\n"
+#define K8_NOP5 K8_NOP3 K8_NOP2
+#define K8_NOP6 K8_NOP3 K8_NOP3
+#define K8_NOP7 K8_NOP4 K8_NOP3
+#define K8_NOP8 K8_NOP4 K8_NOP4
+
+#define ASM_NOP_MAX 8
+
+/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
+extern inline void rep_nop(void)
+{
+ __asm__ __volatile__("rep;nop": : :"memory");
+}
+
+/* Stop speculative execution */
+extern inline void sync_core(void)
+{
+ int tmp;
+ asm volatile("cpuid" : "=a" (tmp) : "0" (1) :
"ebx","ecx","edx","memory");
+}
+
+#define cpu_has_fpu 1
+
+#define ARCH_HAS_PREFETCH
+static inline void prefetch(void *x)
+{
+ asm volatile("prefetcht0 %0" :: "m" (*(unsigned long *)x));
+}
+
+#define ARCH_HAS_PREFETCHW 1
+static inline void prefetchw(void *x)
+{
+ alternative_input(ASM_NOP5,
+ "prefetchw (%1)",
+ X86_FEATURE_3DNOW,
+ "r" (x));
+}
+
+#define ARCH_HAS_SPINLOCK_PREFETCH 1
+
+#define spin_lock_prefetch(x) prefetchw(x)
+
+#define cpu_relax() rep_nop()
+
+/*
+ * NSC/Cyrix CPU configuration register indexes
+ */
+#define CX86_CCR0 0xc0
+#define CX86_CCR1 0xc1
+#define CX86_CCR2 0xc2
+#define CX86_CCR3 0xc3
+#define CX86_CCR4 0xe8
+#define CX86_CCR5 0xe9
+#define CX86_CCR6 0xea
+#define CX86_CCR7 0xeb
+#define CX86_DIR0 0xfe
+#define CX86_DIR1 0xff
+#define CX86_ARR_BASE 0xc4
+#define CX86_RCR_BASE 0xdc
+
+/*
+ * NSC/Cyrix CPU indexed register access macros
+ */
+
+#define getCx86(reg) ({ outb((reg), 0x22); inb(0x23); })
+
+#define setCx86(reg, data) do { \
+ outb((reg), 0x22); \
+ outb((data), 0x23); \
+} while (0)
+
+static inline void __monitor(const void *eax, unsigned long ecx,
+ unsigned long edx)
+{
+ /* "monitor %eax,%ecx,%edx;" */
+ asm volatile(
+ ".byte 0x0f,0x01,0xc8;"
+ : :"a" (eax), "c" (ecx), "d"(edx));
+}
+
+static inline void __mwait(unsigned long eax, unsigned long ecx)
+{
+ /* "mwait %eax,%ecx;" */
+ asm volatile(
+ ".byte 0x0f,0x01,0xc9;"
+ : :"a" (eax), "c" (ecx));
+}
+
+#define stack_current() \
+({ \
+ struct thread_info *ti; \
+ asm("andq %%rsp,%0; ":"=r" (ti) : "0" (CURRENT_MASK)); \
+ ti->task; \
+})
+
+#define cache_line_size() (boot_cpu_data.x86_cache_alignment)
+
+extern unsigned long boot_option_idle_override;
+/* Boot loader type from the setup header */
+extern int bootloader_type;
+
+#endif /* __ASM_X86_64_PROCESSOR_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/io_ports.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/io_ports.h
Fri Jul 15 13:39:50 2005
@@ -0,0 +1,30 @@
+/*
+ * arch/i386/mach-generic/io_ports.h
+ *
+ * Machine specific IO port address definition for generic.
+ * Written by Osamu Tomita <tomita@xxxxxxxxxxx>
+ */
+#ifndef _MACH_IO_PORTS_H
+#define _MACH_IO_PORTS_H
+
+/* i8253A PIT registers */
+#define PIT_MODE 0x43
+#define PIT_CH0 0x40
+#define PIT_CH2 0x42
+
+/* i8259A PIC registers */
+#define PIC_MASTER_CMD 0x20
+#define PIC_MASTER_IMR 0x21
+#define PIC_MASTER_ISR PIC_MASTER_CMD
+#define PIC_MASTER_POLL PIC_MASTER_ISR
+#define PIC_MASTER_OCW3 PIC_MASTER_ISR
+#define PIC_SLAVE_CMD 0xa0
+#define PIC_SLAVE_IMR 0xa1
+
+/* i8259A PIC related value */
+#define PIC_CASCADE_IR 2
+#define MASTER_ICW4_DEFAULT 0x01
+#define SLAVE_ICW4_DEFAULT 0x01
+#define PIC_ICW4_AEOI 2
+
+#endif /* !_MACH_IO_PORTS_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/Makefile Fri Jul 15 13:39:50 2005
@@ -0,0 +1,92 @@
+#
+# x86_64/Makefile
+#
+# This file is included by the global makefile so that you can add your own
+# architecture-specific flags and dependencies. Remember to do have actions
+# for "archclean" and "archdep" for cleaning up and making dependencies for
+# this architecture
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License. See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 1994 by Linus Torvalds
+#
+# 19990713 Artur Skawina <skawina@xxxxxxxxxxxxx>
+# Added '-march' and '-mpreferred-stack-boundary' support
+# 20000913 Pavel Machek <pavel@xxxxxxx>
+# Converted for x86_64 architecture
+# 20010105 Andi Kleen, add IA32 compiler.
+# ....and later removed it again....
+# 20050205 Jun Nakajima <jun.nakajima@xxxxxxxxx>
+# Modified for Xen
+#
+# $Id: Makefile,v 1.31 2002/03/22 15:56:07 ak Exp $
+
+#
+# early bootup linking needs 32bit. You can either use real 32bit tools
+# here or 64bit tools in 32bit mode.
+#
+XENARCH := $(subst ",,$(CONFIG_XENARCH))
+
+IA32_CC := $(CC) $(CPPFLAGS) -m32 -O2 -fomit-frame-pointer
+IA32_LD := $(LD) -m elf_i386
+IA32_AS := $(CC) $(AFLAGS) -m32 -Wa,--32 -traditional -c
+IA32_OBJCOPY := $(CROSS_COMPILE)objcopy
+IA32_CPP := $(CROSS_COMPILE)gcc -m32 -E
+export IA32_CC IA32_LD IA32_AS IA32_OBJCOPY IA32_CPP
+
+
+LDFLAGS := -m elf_x86_64
+#LDFLAGS_vmlinux := -e stext
+
+CHECKFLAGS += -D__x86_64__ -m64
+
+cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
+cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)
+CFLAGS += $(cflags-y)
+
+CFLAGS += -mno-red-zone
+CFLAGS += -mcmodel=kernel
+CFLAGS += -pipe
+# this makes reading assembly source easier, but produces worse code
+# actually it makes the kernel smaller too.
+CFLAGS += -fno-reorder-blocks
+CFLAGS += -Wno-sign-compare
+ifneq ($(CONFIG_DEBUG_INFO),y)
+CFLAGS += -fno-asynchronous-unwind-tables
+# -fweb shrinks the kernel a bit, but the difference is very small
+# it also messes up debugging, so don't use it for now.
+#CFLAGS += $(call cc-option,-fweb)
+endif
+# -funit-at-a-time shrinks the kernel .text considerably
+# unfortunately it makes reading oopses harder.
+CFLAGS += $(call cc-option,-funit-at-a-time,)
+
+head-y := arch/xen/x86_64/kernel/head.o arch/xen/x86_64/kernel/head64.o
arch/xen/x86_64/kernel/init_task.o
+
+libs-y += arch/x86_64/lib/
+core-y += arch/xen/x86_64/kernel/
arch/xen/x86_64/mm/
+core-$(CONFIG_IA32_EMULATION) += arch/xen/x86_64/ia32/
+drivers-$(CONFIG_PCI) += arch/xen/x86_64/pci/
+drivers-$(CONFIG_OPROFILE) += arch/x86_64/oprofile/
+
+# for clean
+obj- += kernel/ mm/ pci/
+
+xenflags-y += -Iinclude/asm-xen/asm-x86_64/mach-xen
+
+CFLAGS += $(xenflags-y)
+AFLAGS += $(xenflags-y)
+
+prepare: include/asm-$(XENARCH)/asm_offset.h
+CLEAN_FILES += include/asm-$(XENARCH)/asm_offset.h
+
+arch/$(XENARCH)/kernel/asm-offsets.s: include/asm include/.asm-ignore \
+ include/linux/version.h include/config/MARKER
+
+
+include/asm-$(XENARCH)/asm_offset.h: arch/xen/x86_64/kernel/asm-offsets.s
+ $(call filechk,gen-asm-offsets)
+ ln -fsn asm_offset.h include/asm-$(XENARCH)/offset.h
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/usbfront/xhci.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/usbfront/xhci.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,183 @@
+/******************************************************************************
+ * xhci.h
+ *
+ * Private definitions for the Xen Virtual USB Controller. Based on
+ * drivers/usb/host/uhci.h from Linux. Copyright for the imported content is
+ * retained by the original authors.
+ *
+ * Modifications are:
+ * Copyright (C) 2004 Intel Research Cambridge
+ * Copyright (C) 2004, 2005 Mark Williamson
+ */
+
+#ifndef __LINUX_XHCI_H
+#define __LINUX_XHCI_H
+
+#include <linux/list.h>
+#include <linux/usb.h>
+#include <asm-xen/xen-public/io/usbif.h>
+#include <linux/spinlock.h>
+
+/* xhci_port_t - current known state of a virtual hub ports */
+typedef struct {
+ unsigned int cs :1; /* Connection status. */
+ unsigned int cs_chg :1; /* Connection status change. */
+ unsigned int pe :1; /* Port enable. */
+ unsigned int pe_chg :1; /* Port enable change. */
+ unsigned int susp :1; /* Suspended. */
+ unsigned int lsda :1; /* Low speed device attached. */
+ unsigned int pr :1; /* Port reset. */
+} xhci_port_t;
+
+/* struct virt_root_hub - state related to the virtual root hub */
+struct virt_root_hub {
+ struct usb_device *dev;
+ int devnum; /* Address of Root Hub endpoint */
+ struct urb *urb;
+ void *int_addr;
+ int send;
+ int interval;
+ int numports;
+ int c_p_r[8];
+ struct timer_list rh_int_timer;
+ spinlock_t port_state_lock;
+ xhci_port_t *ports;
+};
+
+/* struct xhci - contains the state associated with a single USB interface */
+struct xhci {
+
+#ifdef CONFIG_PROC_FS
+ /* procfs */
+ int num;
+ struct proc_dir_entry *proc_entry;
+#endif
+
+ int evtchn; /* Interdom channel to backend */
+ int irq; /* Bound to evtchn */
+ enum {
+ USBIF_STATE_CONNECTED = 2,
+ USBIF_STATE_DISCONNECTED = 1,
+ USBIF_STATE_CLOSED = 0
+ } state; /* State of this USB interface */
+ unsigned long recovery; /* boolean recovery in progress flag */
+
+ unsigned long bandwidth;
+
+ struct usb_bus *bus;
+
+ /* Main list of URB's currently controlled by this HC */
+ spinlock_t urb_list_lock;
+ struct list_head urb_list; /* P: xhci->urb_list_lock */
+
+ /* List of URB's awaiting completion callback */
+ spinlock_t complete_list_lock;
+ struct list_head complete_list; /* P: xhci->complete_list_lock
*/
+
+ struct virt_root_hub rh; /* private data of the virtual root hub
*/
+
+ spinlock_t ring_lock;
+ usbif_front_ring_t usb_ring;
+
+ int awaiting_reset;
+};
+
+/* per-URB private data structure for the host controller */
+struct urb_priv {
+ struct urb *urb;
+ usbif_iso_t *schedule;
+ struct usb_device *dev;
+
+ int in_progress : 1; /* QH was queued (not linked in) */
+ int short_control_packet : 1; /* If we get a short packet during */
+ /* a control transfer, retrigger */
+ /* the status phase */
+
+ int status; /* Final status */
+
+ unsigned long inserttime; /* In jiffies */
+
+ struct list_head complete_list; /* P: xhci->complete_list_lock */
+};
+
+/*
+ * Locking in xhci.c
+ *
+ * spinlocks are used extensively to protect the many lists and data
+ * structures we have. It's not that pretty, but it's necessary. We
+ * need to be done with all of the locks (except complete_list_lock) when
+ * we call urb->complete. I've tried to make it simple enough so I don't
+ * have to spend hours racking my brain trying to figure out if the
+ * locking is safe.
+ *
+ * Here's the safe locking order to prevent deadlocks:
+ *
+ * #1 xhci->urb_list_lock
+ * #2 urb->lock
+ * #3 xhci->urb_remove_list_lock
+ * #4 xhci->complete_list_lock
+ *
+ * If you're going to grab 2 or more locks at once, ALWAYS grab the lock
+ * at the lowest level FIRST and NEVER grab locks at the same level at the
+ * same time.
+ *
+ * So, if you need xhci->urb_list_lock, grab it before you grab urb->lock
+ */
+
+/* -------------------------------------------------------------------------
+ Virtual Root HUB
+ ------------------------------------------------------------------------- */
+/* destination of request */
+#define RH_DEVICE 0x00
+#define RH_INTERFACE 0x01
+#define RH_ENDPOINT 0x02
+#define RH_OTHER 0x03
+
+#define RH_CLASS 0x20
+#define RH_VENDOR 0x40
+
+/* Requests: bRequest << 8 | bmRequestType */
+#define RH_GET_STATUS 0x0080
+#define RH_CLEAR_FEATURE 0x0100
+#define RH_SET_FEATURE 0x0300
+#define RH_SET_ADDRESS 0x0500
+#define RH_GET_DESCRIPTOR 0x0680
+#define RH_SET_DESCRIPTOR 0x0700
+#define RH_GET_CONFIGURATION 0x0880
+#define RH_SET_CONFIGURATION 0x0900
+#define RH_GET_STATE 0x0280
+#define RH_GET_INTERFACE 0x0A80
+#define RH_SET_INTERFACE 0x0B00
+#define RH_SYNC_FRAME 0x0C80
+/* Our Vendor Specific Request */
+#define RH_SET_EP 0x2000
+
+/* Hub port features */
+#define RH_PORT_CONNECTION 0x00
+#define RH_PORT_ENABLE 0x01
+#define RH_PORT_SUSPEND 0x02
+#define RH_PORT_OVER_CURRENT 0x03
+#define RH_PORT_RESET 0x04
+#define RH_PORT_POWER 0x08
+#define RH_PORT_LOW_SPEED 0x09
+#define RH_C_PORT_CONNECTION 0x10
+#define RH_C_PORT_ENABLE 0x11
+#define RH_C_PORT_SUSPEND 0x12
+#define RH_C_PORT_OVER_CURRENT 0x13
+#define RH_C_PORT_RESET 0x14
+
+/* Hub features */
+#define RH_C_HUB_LOCAL_POWER 0x00
+#define RH_C_HUB_OVER_CURRENT 0x01
+#define RH_DEVICE_REMOTE_WAKEUP 0x00
+#define RH_ENDPOINT_STALL 0x01
+
+/* Our Vendor Specific feature */
+#define RH_REMOVE_EP 0x00
+
+#define RH_ACK 0x01
+#define RH_REQ_ERR -1
+#define RH_NACK 0x00
+
+#endif
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/drivers/char/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/drivers/char/Makefile Fri Jul 15 13:39:50 2005
@@ -0,0 +1,361 @@
+#
+# Makefile for the kernel character device drivers.
+#
+# Note! Dependencies are done automagically by 'make dep', which also
+# removes any old dependencies. DON'T put your own dependencies here
+# unless it's something special (ie not a .c file).
+#
+# Note 2! The CFLAGS definitions are now inherited from the
+# parent makes..
+#
+
+#
+# This file contains the font map for the default (hardware) font
+#
+FONTMAPFILE = cp437.uni
+
+O_TARGET := char.o
+
+obj-y += mem.o tty_io.o n_tty.o tty_ioctl.o raw.o pty.o misc.o random.o
+
+# All of the (potential) objects that export symbols.
+# This list comes from 'grep -l EXPORT_SYMBOL *.[hc]'.
+
+export-objs := busmouse.o console.o keyboard.o sysrq.o \
+ misc.o pty.o random.o selection.o serial.o \
+ sonypi.o tty_io.o tty_ioctl.o generic_serial.o \
+ au1000_gpio.o vac-serial.o hp_psaux.o nvram.o \
+ scx200.o fetchop.o
+
+mod-subdirs := joystick ftape drm drm-4.0 pcmcia
+
+list-multi :=
+
+KEYMAP =defkeymap.o
+KEYBD =pc_keyb.o
+CONSOLE =console.o
+SERIAL =serial.o
+
+ifeq ($(ARCH),xen)
+ ifneq ($(CONFIG_XEN_PHYSDEV_ACCESS),y)
+ KEYBD =
+ endif
+endif
+
+ifeq ($(ARCH),s390)
+ KEYMAP =
+ KEYBD =
+ CONSOLE =
+ SERIAL =
+endif
+
+ifeq ($(ARCH),mips)
+ ifneq ($(CONFIG_PC_KEYB),y)
+ KEYBD =
+ endif
+ ifeq ($(CONFIG_VR41XX_KIU),y)
+ KEYMAP =
+ KEYBD = vr41xx_keyb.o
+ endif
+endif
+
+ifeq ($(ARCH),s390x)
+ KEYMAP =
+ KEYBD =
+ CONSOLE =
+ SERIAL =
+endif
+
+ifeq ($(ARCH),m68k)
+ ifdef CONFIG_AMIGA
+ KEYBD = amikeyb.o
+ else
+ ifndef CONFIG_MAC
+ KEYBD =
+ endif
+ endif
+ SERIAL =
+endif
+
+ifeq ($(ARCH),parisc)
+ ifdef CONFIG_GSC_PS2
+ KEYBD = hp_psaux.o hp_keyb.o
+ else
+ KEYBD =
+ endif
+ ifdef CONFIG_SERIAL_MUX
+ CONSOLE += mux.o
+ endif
+ ifdef CONFIG_PDC_CONSOLE
+ CONSOLE += pdc_console.o
+ endif
+endif
+
+ifdef CONFIG_Q40
+ KEYBD += q40_keyb.o
+ SERIAL = serial.o
+endif
+
+ifdef CONFIG_APOLLO
+ KEYBD += dn_keyb.o
+endif
+
+ifeq ($(ARCH),parisc)
+ ifdef CONFIG_GSC_PS2
+ KEYBD = hp_psaux.o hp_keyb.o
+ else
+ KEYBD =
+ endif
+ ifdef CONFIG_PDC_CONSOLE
+ CONSOLE += pdc_console.o
+ endif
+endif
+
+ifeq ($(ARCH),arm)
+ ifneq ($(CONFIG_PC_KEYMAP),y)
+ KEYMAP =
+ endif
+ ifneq ($(CONFIG_PC_KEYB),y)
+ KEYBD =
+ endif
+endif
+
+ifeq ($(ARCH),sh)
+ KEYMAP =
+ KEYBD =
+ CONSOLE =
+ ifeq ($(CONFIG_SH_HP600),y)
+ KEYMAP = defkeymap.o
+ KEYBD = scan_keyb.o hp600_keyb.o
+ CONSOLE = console.o
+ endif
+ ifeq ($(CONFIG_SH_DMIDA),y)
+ # DMIDA does not connect the HD64465 PS/2 keyboard port
+ # but we allow for USB keyboards to be plugged in.
+ KEYMAP = defkeymap.o
+ KEYBD = # hd64465_keyb.o pc_keyb.o
+ CONSOLE = console.o
+ endif
+ ifeq ($(CONFIG_SH_EC3104),y)
+ KEYMAP = defkeymap.o
+ KEYBD = ec3104_keyb.o
+ CONSOLE = console.o
+ endif
+ ifeq ($(CONFIG_SH_DREAMCAST),y)
+ KEYMAP = defkeymap.o
+ KEYBD =
+ CONSOLE = console.o
+ endif
+endif
+
+ifeq ($(CONFIG_DECSTATION),y)
+ KEYMAP =
+ KEYBD =
+endif
+
+ifeq ($(CONFIG_BAGET_MIPS),y)
+ KEYBD =
+ SERIAL = vac-serial.o
+endif
+
+ifeq ($(CONFIG_NINO),y)
+ SERIAL =
+endif
+
+ifneq ($(CONFIG_SUN_SERIAL),)
+ SERIAL =
+endif
+
+ifeq ($(CONFIG_QTRONIX_KEYBOARD),y)
+ KEYBD = qtronix.o
+ KEYMAP = qtronixmap.o
+endif
+
+ifeq ($(CONFIG_DUMMY_KEYB),y)
+ KEYBD = dummy_keyb.o
+endif
+
+obj-$(CONFIG_VT) += vt.o vc_screen.o consolemap.o consolemap_deftbl.o
$(CONSOLE) selection.o
+obj-$(CONFIG_SERIAL) += $(SERIAL)
+obj-$(CONFIG_PARPORT_SERIAL) += parport_serial.o
+obj-$(CONFIG_SERIAL_HCDP) += hcdp_serial.o
+obj-$(CONFIG_SERIAL_21285) += serial_21285.o
+obj-$(CONFIG_SERIAL_SA1100) += serial_sa1100.o
+obj-$(CONFIG_SERIAL_AMBA) += serial_amba.o
+obj-$(CONFIG_TS_AU1X00_ADS7846) += au1000_ts.o
+obj-$(CONFIG_SERIAL_DEC) += decserial.o
+
+ifndef CONFIG_SUN_KEYBOARD
+ obj-$(CONFIG_VT) += keyboard.o $(KEYMAP) $(KEYBD)
+else
+ obj-$(CONFIG_PCI) += keyboard.o $(KEYMAP)
+endif
+
+obj-$(CONFIG_HIL) += hp_keyb.o
+obj-$(CONFIG_MAGIC_SYSRQ) += sysrq.o
+obj-$(CONFIG_ATARI_DSP56K) += dsp56k.o
+obj-$(CONFIG_ROCKETPORT) += rocket.o
+obj-$(CONFIG_MOXA_SMARTIO) += mxser.o
+obj-$(CONFIG_MOXA_INTELLIO) += moxa.o
+obj-$(CONFIG_DIGI) += pcxx.o
+obj-$(CONFIG_DIGIEPCA) += epca.o
+obj-$(CONFIG_CYCLADES) += cyclades.o
+obj-$(CONFIG_STALLION) += stallion.o
+obj-$(CONFIG_ISTALLION) += istallion.o
+obj-$(CONFIG_SIBYTE_SB1250_DUART) += sb1250_duart.o
+obj-$(CONFIG_COMPUTONE) += ip2.o ip2main.o
+obj-$(CONFIG_RISCOM8) += riscom8.o
+obj-$(CONFIG_ISI) += isicom.o
+obj-$(CONFIG_ESPSERIAL) += esp.o
+obj-$(CONFIG_SYNCLINK) += synclink.o
+obj-$(CONFIG_SYNCLINKMP) += synclinkmp.o
+obj-$(CONFIG_N_HDLC) += n_hdlc.o
+obj-$(CONFIG_SPECIALIX) += specialix.o
+obj-$(CONFIG_AMIGA_BUILTIN_SERIAL) += amiserial.o
+obj-$(CONFIG_A2232) += ser_a2232.o generic_serial.o
+obj-$(CONFIG_SX) += sx.o generic_serial.o
+obj-$(CONFIG_RIO) += rio/rio.o generic_serial.o
+obj-$(CONFIG_SH_SCI) += sh-sci.o generic_serial.o
+obj-$(CONFIG_SERIAL167) += serial167.o
+obj-$(CONFIG_MVME147_SCC) += generic_serial.o vme_scc.o
+obj-$(CONFIG_MVME162_SCC) += generic_serial.o vme_scc.o
+obj-$(CONFIG_BVME6000_SCC) += generic_serial.o vme_scc.o
+obj-$(CONFIG_HVC_CONSOLE) += hvc_console.o
+obj-$(CONFIG_SERIAL_TX3912) += generic_serial.o serial_tx3912.o
+obj-$(CONFIG_TXX927_SERIAL) += serial_txx927.o
+obj-$(CONFIG_SERIAL_TXX9) += generic_serial.o serial_txx9.o
+obj-$(CONFIG_IP22_SERIAL) += sgiserial.o
+obj-$(CONFIG_AU1X00_UART) += au1x00-serial.o
+obj-$(CONFIG_SGI_L1_SERIAL) += sn_serial.o
+
+subdir-$(CONFIG_RIO) += rio
+subdir-$(CONFIG_INPUT) += joystick
+
+obj-$(CONFIG_ATIXL_BUSMOUSE) += atixlmouse.o
+obj-$(CONFIG_LOGIBUSMOUSE) += logibusmouse.o
+obj-$(CONFIG_PRINTER) += lp.o
+obj-$(CONFIG_TIPAR) += tipar.o
+obj-$(CONFIG_OBMOUSE) += obmouse.o
+
+ifeq ($(CONFIG_INPUT),y)
+obj-y += joystick/js.o
+endif
+
+obj-$(CONFIG_FETCHOP) += fetchop.o
+obj-$(CONFIG_BUSMOUSE) += busmouse.o
+obj-$(CONFIG_DTLK) += dtlk.o
+obj-$(CONFIG_R3964) += n_r3964.o
+obj-$(CONFIG_APPLICOM) += applicom.o
+obj-$(CONFIG_SONYPI) += sonypi.o
+obj-$(CONFIG_MS_BUSMOUSE) += msbusmouse.o
+obj-$(CONFIG_82C710_MOUSE) += qpmouse.o
+obj-$(CONFIG_AMIGAMOUSE) += amigamouse.o
+obj-$(CONFIG_ATARIMOUSE) += atarimouse.o
+obj-$(CONFIG_ADBMOUSE) += adbmouse.o
+obj-$(CONFIG_PC110_PAD) += pc110pad.o
+obj-$(CONFIG_MK712_MOUSE) += mk712.o
+obj-$(CONFIG_RTC) += rtc.o
+obj-$(CONFIG_GEN_RTC) += genrtc.o
+obj-$(CONFIG_EFI_RTC) += efirtc.o
+obj-$(CONFIG_SGI_DS1286) += ds1286.o
+obj-$(CONFIG_MIPS_RTC) += mips_rtc.o
+obj-$(CONFIG_SGI_IP27_RTC) += ip27-rtc.o
+ifeq ($(CONFIG_PPC),)
+ obj-$(CONFIG_NVRAM) += nvram.o
+endif
+obj-$(CONFIG_TOSHIBA) += toshiba.o
+obj-$(CONFIG_I8K) += i8k.o
+obj-$(CONFIG_DS1620) += ds1620.o
+obj-$(CONFIG_DS1742) += ds1742.o
+obj-$(CONFIG_INTEL_RNG) += i810_rng.o
+obj-$(CONFIG_AMD_RNG) += amd768_rng.o
+obj-$(CONFIG_HW_RANDOM) += hw_random.o
+obj-$(CONFIG_AMD_PM768) += amd76x_pm.o
+obj-$(CONFIG_BRIQ_PANEL) += briq_panel.o
+
+obj-$(CONFIG_ITE_GPIO) += ite_gpio.o
+obj-$(CONFIG_AU1X00_GPIO) += au1000_gpio.o
+obj-$(CONFIG_AU1X00_USB_TTY) += au1000_usbtty.o
+obj-$(CONFIG_AU1X00_USB_RAW) += au1000_usbraw.o
+obj-$(CONFIG_COBALT_LCD) += lcd.o
+
+obj-$(CONFIG_QIC02_TAPE) += tpqic02.o
+
+subdir-$(CONFIG_FTAPE) += ftape
+subdir-$(CONFIG_DRM_OLD) += drm-4.0
+subdir-$(CONFIG_DRM_NEW) += drm
+subdir-$(CONFIG_PCMCIA) += pcmcia
+subdir-$(CONFIG_AGP) += agp
+
+ifeq ($(CONFIG_FTAPE),y)
+obj-y += ftape/ftape.o
+endif
+
+obj-$(CONFIG_H8) += h8.o
+obj-$(CONFIG_PPDEV) += ppdev.o
+obj-$(CONFIG_DZ) += dz.o
+obj-$(CONFIG_NWBUTTON) += nwbutton.o
+obj-$(CONFIG_NWFLASH) += nwflash.o
+obj-$(CONFIG_SCx200) += scx200.o
+obj-$(CONFIG_SCx200_GPIO) += scx200_gpio.o
+
+# Only one watchdog can succeed. We probe the hardware watchdog
+# drivers first, then the softdog driver. This means if your hardware
+# watchdog dies or is 'borrowed' for some reason the software watchdog
+# still gives you some cover.
+
+obj-$(CONFIG_PCWATCHDOG) += pcwd.o
+obj-$(CONFIG_ACQUIRE_WDT) += acquirewdt.o
+obj-$(CONFIG_ADVANTECH_WDT) += advantechwdt.o
+obj-$(CONFIG_IB700_WDT) += ib700wdt.o
+obj-$(CONFIG_MIXCOMWD) += mixcomwd.o
+obj-$(CONFIG_60XX_WDT) += sbc60xxwdt.o
+obj-$(CONFIG_W83877F_WDT) += w83877f_wdt.o
+obj-$(CONFIG_SC520_WDT) += sc520_wdt.o
+obj-$(CONFIG_WDT) += wdt.o
+obj-$(CONFIG_WDTPCI) += wdt_pci.o
+obj-$(CONFIG_21285_WATCHDOG) += wdt285.o
+obj-$(CONFIG_977_WATCHDOG) += wdt977.o
+obj-$(CONFIG_I810_TCO) += i810-tco.o
+obj-$(CONFIG_MACHZ_WDT) += machzwd.o
+obj-$(CONFIG_SH_WDT) += shwdt.o
+obj-$(CONFIG_EUROTECH_WDT) += eurotechwdt.o
+obj-$(CONFIG_ALIM7101_WDT) += alim7101_wdt.o
+obj-$(CONFIG_ALIM1535_WDT) += alim1535d_wdt.o
+obj-$(CONFIG_INDYDOG) += indydog.o
+obj-$(CONFIG_SC1200_WDT) += sc1200wdt.o
+obj-$(CONFIG_SCx200_WDT) += scx200_wdt.o
+obj-$(CONFIG_WAFER_WDT) += wafer5823wdt.o
+obj-$(CONFIG_SOFT_WATCHDOG) += softdog.o
+obj-$(CONFIG_INDYDOG) += indydog.o
+obj-$(CONFIG_8xx_WDT) += mpc8xx_wdt.o
+
+subdir-$(CONFIG_MWAVE) += mwave
+ifeq ($(CONFIG_MWAVE),y)
+ obj-y += mwave/mwave.o
+endif
+
+subdir-$(CONFIG_IPMI_HANDLER) += ipmi
+ifeq ($(CONFIG_IPMI_HANDLER),y)
+ obj-y += ipmi/ipmi.o
+endif
+
+include $(TOPDIR)/Rules.make
+
+fastdep:
+
+conmakehash: conmakehash.c
+ $(HOSTCC) $(HOSTCFLAGS) -o conmakehash conmakehash.c
+
+consolemap_deftbl.c: $(FONTMAPFILE) conmakehash
+ ./conmakehash $(FONTMAPFILE) > consolemap_deftbl.c
+
+consolemap_deftbl.o: consolemap_deftbl.c $(TOPDIR)/include/linux/types.h
+
+.DELETE_ON_ERROR:
+
+defkeymap.c: defkeymap.map
+ set -e ; loadkeys --mktable $< | sed -e 's/^static *//' > $@
+
+qtronixmap.c: qtronixmap.map
+ set -e ; loadkeys --mktable $< | sed -e 's/^static *//' > $@
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/irq.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/irq.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,36 @@
+#ifndef _ASM_IRQ_H
+#define _ASM_IRQ_H
+
+/*
+ * linux/include/asm/irq.h
+ *
+ * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ *
+ * IRQ/IPI changes taken from work by Thomas Radke
+ * <tomsoft@xxxxxxxxxxxxxxxxxxxxxxxxx>
+ */
+
+#include <linux/config.h>
+#include <linux/sched.h>
+/* include comes from machine specific directory */
+#include "irq_vectors.h"
+#include <asm/thread_info.h>
+
+static __inline__ int irq_canonicalize(int irq)
+{
+ return ((irq == 2) ? 9 : irq);
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+#define ARCH_HAS_NMI_WATCHDOG /* See include/linux/nmi.h */
+#endif
+
+#define KDB_VECTOR 0xf9
+
+# define irq_ctx_init(cpu) do { } while (0)
+
+struct irqaction;
+struct pt_regs;
+int handle_IRQ_event(unsigned int, struct pt_regs *, struct irqaction *);
+
+#endif /* _ASM_IRQ_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/process.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/process.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,769 @@
+/*
+ * linux/arch/i386/kernel/process.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000
+ */
+
+/*
+ * This file handles the architecture-dependent parts of process handling..
+ */
+
+#include <stdarg.h>
+
+#include <linux/cpu.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/elfcore.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/stddef.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/user.h>
+#include <linux/a.out.h>
+#include <linux/interrupt.h>
+#include <linux/config.h>
+#include <linux/utsname.h>
+#include <linux/delay.h>
+#include <linux/reboot.h>
+#include <linux/init.h>
+#include <linux/mc146818rtc.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/ptrace.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/ldt.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/irq.h>
+#include <asm/desc.h>
+#include <asm-xen/xen-public/physdev.h>
+#ifdef CONFIG_MATH_EMULATION
+#include <asm/math_emu.h>
+#endif
+
+#include <linux/irq.h>
+#include <linux/err.h>
+
+#include <asm/tlbflush.h>
+#include <asm/cpu.h>
+
+asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
+
+int hlt_counter;
+
+unsigned long boot_option_idle_override = 0;
+EXPORT_SYMBOL(boot_option_idle_override);
+
+/*
+ * Return saved PC of a blocked thread.
+ */
+unsigned long thread_saved_pc(struct task_struct *tsk)
+{
+ return ((unsigned long *)tsk->thread.esp)[3];
+}
+
+/*
+ * Powermanagement idle function, if any..
+ */
+void (*pm_idle)(void);
+static cpumask_t cpu_idle_map;
+
+void disable_hlt(void)
+{
+ hlt_counter++;
+}
+
+EXPORT_SYMBOL(disable_hlt);
+
+void enable_hlt(void)
+{
+ hlt_counter--;
+}
+
+EXPORT_SYMBOL(enable_hlt);
+
+/* XXX XEN doesn't use default_idle(), poll_idle(). Use xen_idle() instead. */
+extern void stop_hz_timer(void);
+extern void start_hz_timer(void);
+void xen_idle(void)
+{
+ local_irq_disable();
+
+ if (need_resched()) {
+ local_irq_enable();
+ } else {
+ stop_hz_timer();
+ HYPERVISOR_block(); /* implicit local_irq_enable() */
+ start_hz_timer();
+ }
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+#include <asm/nmi.h>
+/* We don't actually take CPU down, just spin without interrupts. */
+static inline void play_dead(void)
+{
+ /* Ack it */
+ __get_cpu_var(cpu_state) = CPU_DEAD;
+
+ /* We shouldn't have to disable interrupts while dead, but
+ * some interrupts just don't seem to go away, and this makes
+ * it "work" for testing purposes. */
+ /* Death loop */
+ while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE)
+ HYPERVISOR_yield();
+
+ local_irq_disable();
+ __flush_tlb_all();
+ cpu_set(smp_processor_id(), cpu_online_map);
+ local_irq_enable();
+}
+#else
+static inline void play_dead(void)
+{
+ BUG();
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+/*
+ * The idle thread. There's no useful work to be
+ * done, so just try to conserve power and have a
+ * low exit latency (ie sit in a loop waiting for
+ * somebody to say that they'd like to reschedule)
+ */
+void cpu_idle (void)
+{
+ int cpu = _smp_processor_id();
+
+ /* endless idle loop with no priority at all */
+ while (1) {
+ while (!need_resched()) {
+
+ if (cpu_isset(cpu, cpu_idle_map))
+ cpu_clear(cpu, cpu_idle_map);
+ rmb();
+
+ if (cpu_is_offline(cpu)) {
+#if defined(CONFIG_XEN) && defined(CONFIG_HOTPLUG_CPU)
+ /* Tell hypervisor to take vcpu down. */
+ HYPERVISOR_vcpu_down(cpu);
+#endif
+ play_dead();
+ }
+
+ irq_stat[cpu].idle_timestamp = jiffies;
+ xen_idle();
+ }
+ schedule();
+ }
+}
+
+void cpu_idle_wait(void)
+{
+ int cpu;
+ cpumask_t map;
+
+ for_each_online_cpu(cpu)
+ cpu_set(cpu, cpu_idle_map);
+
+ wmb();
+ do {
+ ssleep(1);
+ cpus_and(map, cpu_idle_map, cpu_online_map);
+ } while (!cpus_empty(map));
+}
+EXPORT_SYMBOL_GPL(cpu_idle_wait);
+
+/* XXX XEN doesn't use mwait_idle(), select_idle_routine(), idle_setup(). */
+/* Always use xen_idle() instead. */
+void __init select_idle_routine(const struct cpuinfo_x86 *c) {}
+
+void show_regs(struct pt_regs * regs)
+{
+ printk("\n");
+ printk("Pid: %d, comm: %20s\n", current->pid, current->comm);
+ printk("EIP: %04x:[<%08lx>] CPU: %d\n",0xffff & regs->xcs,regs->eip,
smp_processor_id());
+ print_symbol("EIP is at %s\n", regs->eip);
+
+ if (regs->xcs & 2)
+ printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp);
+ printk(" EFLAGS: %08lx %s (%s)\n",
+ regs->eflags, print_tainted(), system_utsname.release);
+ printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
+ regs->eax,regs->ebx,regs->ecx,regs->edx);
+ printk("ESI: %08lx EDI: %08lx EBP: %08lx",
+ regs->esi, regs->edi, regs->ebp);
+ printk(" DS: %04x ES: %04x\n",
+ 0xffff & regs->xds,0xffff & regs->xes);
+
+ show_trace(NULL, ®s->esp);
+}
+
+/*
+ * This gets run with %ebx containing the
+ * function to call, and %edx containing
+ * the "args".
+ */
+extern void kernel_thread_helper(void);
+__asm__(".section .text\n"
+ ".align 4\n"
+ "kernel_thread_helper:\n\t"
+ "movl %edx,%eax\n\t"
+ "pushl %edx\n\t"
+ "call *%ebx\n\t"
+ "pushl %eax\n\t"
+ "call do_exit\n"
+ ".previous");
+
+/*
+ * Create a kernel thread
+ */
+int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
+{
+ struct pt_regs regs;
+
+ memset(®s, 0, sizeof(regs));
+
+ regs.ebx = (unsigned long) fn;
+ regs.edx = (unsigned long) arg;
+
+ regs.xds = __USER_DS;
+ regs.xes = __USER_DS;
+ regs.orig_eax = -1;
+ regs.eip = (unsigned long) kernel_thread_helper;
+ regs.xcs = __KERNEL_CS;
+ regs.eflags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2;
+
+ /* Ok, create the new process.. */
+ return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, 0, NULL,
NULL);
+}
+
+/*
+ * Free current thread data structures etc..
+ */
+void exit_thread(void)
+{
+ struct task_struct *tsk = current;
+ struct thread_struct *t = &tsk->thread;
+
+ /* The process may have allocated an io port bitmap... nuke it. */
+ if (unlikely(NULL != t->io_bitmap_ptr)) {
+ physdev_op_t op = { 0 };
+ op.cmd = PHYSDEVOP_SET_IOBITMAP;
+ HYPERVISOR_physdev_op(&op);
+ kfree(t->io_bitmap_ptr);
+ t->io_bitmap_ptr = NULL;
+ }
+}
+
+void flush_thread(void)
+{
+ struct task_struct *tsk = current;
+
+ memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8);
+ memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
+ /*
+ * Forget coprocessor state..
+ */
+ clear_fpu(tsk);
+ clear_used_math();
+}
+
+void release_thread(struct task_struct *dead_task)
+{
+ if (dead_task->mm) {
+ // temporary debugging check
+ if (dead_task->mm->context.size) {
+ printk("WARNING: dead process %8s still has LDT?
<%p/%d>\n",
+ dead_task->comm,
+ dead_task->mm->context.ldt,
+ dead_task->mm->context.size);
+ BUG();
+ }
+ }
+
+ release_vm86_irqs(dead_task);
+}
+
+/*
+ * This gets called before we allocate a new thread and copy
+ * the current task into it.
+ */
+void prepare_to_copy(struct task_struct *tsk)
+{
+ unlazy_fpu(tsk);
+}
+
+int copy_thread(int nr, unsigned long clone_flags, unsigned long esp,
+ unsigned long unused,
+ struct task_struct * p, struct pt_regs * regs)
+{
+ struct pt_regs * childregs;
+ struct task_struct *tsk;
+ int err;
+
+ childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long)
p->thread_info)) - 1;
+ *childregs = *regs;
+ childregs->eax = 0;
+ childregs->esp = esp;
+
+ p->thread.esp = (unsigned long) childregs;
+ p->thread.esp0 = (unsigned long) (childregs+1);
+
+ p->thread.eip = (unsigned long) ret_from_fork;
+
+ savesegment(fs,p->thread.fs);
+ savesegment(gs,p->thread.gs);
+
+ tsk = current;
+ if (unlikely(NULL != tsk->thread.io_bitmap_ptr)) {
+ p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL);
+ if (!p->thread.io_bitmap_ptr) {
+ p->thread.io_bitmap_max = 0;
+ return -ENOMEM;
+ }
+ memcpy(p->thread.io_bitmap_ptr, tsk->thread.io_bitmap_ptr,
+ IO_BITMAP_BYTES);
+ }
+
+ /*
+ * Set a new TLS for the child thread?
+ */
+ if (clone_flags & CLONE_SETTLS) {
+ struct desc_struct *desc;
+ struct user_desc info;
+ int idx;
+
+ err = -EFAULT;
+ if (copy_from_user(&info, (void __user *)childregs->esi,
sizeof(info)))
+ goto out;
+ err = -EINVAL;
+ if (LDT_empty(&info))
+ goto out;
+
+ idx = info.entry_number;
+ if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
+ goto out;
+
+ desc = p->thread.tls_array + idx - GDT_ENTRY_TLS_MIN;
+ desc->a = LDT_entry_a(&info);
+ desc->b = LDT_entry_b(&info);
+ }
+
+ p->thread.io_pl = current->thread.io_pl;
+
+ err = 0;
+ out:
+ if (err && p->thread.io_bitmap_ptr) {
+ kfree(p->thread.io_bitmap_ptr);
+ p->thread.io_bitmap_max = 0;
+ }
+ return err;
+}
+
+/*
+ * fill in the user structure for a core dump..
+ */
+void dump_thread(struct pt_regs * regs, struct user * dump)
+{
+ int i;
+
+/* changed the size calculations - should hopefully work better. lbt */
+ dump->magic = CMAGIC;
+ dump->start_code = 0;
+ dump->start_stack = regs->esp & ~(PAGE_SIZE - 1);
+ dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT;
+ dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >>
PAGE_SHIFT;
+ dump->u_dsize -= dump->u_tsize;
+ dump->u_ssize = 0;
+ for (i = 0; i < 8; i++)
+ dump->u_debugreg[i] = current->thread.debugreg[i];
+
+ if (dump->start_stack < TASK_SIZE)
+ dump->u_ssize = ((unsigned long) (TASK_SIZE -
dump->start_stack)) >> PAGE_SHIFT;
+
+ dump->regs.ebx = regs->ebx;
+ dump->regs.ecx = regs->ecx;
+ dump->regs.edx = regs->edx;
+ dump->regs.esi = regs->esi;
+ dump->regs.edi = regs->edi;
+ dump->regs.ebp = regs->ebp;
+ dump->regs.eax = regs->eax;
+ dump->regs.ds = regs->xds;
+ dump->regs.es = regs->xes;
+ savesegment(fs,dump->regs.fs);
+ savesegment(gs,dump->regs.gs);
+ dump->regs.orig_eax = regs->orig_eax;
+ dump->regs.eip = regs->eip;
+ dump->regs.cs = regs->xcs;
+ dump->regs.eflags = regs->eflags;
+ dump->regs.esp = regs->esp;
+ dump->regs.ss = regs->xss;
+
+ dump->u_fpvalid = dump_fpu (regs, &dump->i387);
+}
+
+/*
+ * Capture the user space registers if the task is not running (in user space)
+ */
+int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs)
+{
+ struct pt_regs ptregs;
+
+ ptregs = *(struct pt_regs *)
+ ((unsigned long)tsk->thread_info+THREAD_SIZE - sizeof(ptregs));
+ ptregs.xcs &= 0xffff;
+ ptregs.xds &= 0xffff;
+ ptregs.xes &= 0xffff;
+ ptregs.xss &= 0xffff;
+
+ elf_core_copy_regs(regs, &ptregs);
+
+ boot_option_idle_override = 1;
+ return 1;
+}
+
+/*
+ * This special macro can be used to load a debugging register
+ */
+#define loaddebug(thread,register) \
+ HYPERVISOR_set_debugreg((register), \
+ (thread->debugreg[register]))
+
+/*
+ * switch_to(x,yn) should switch tasks from x to y.
+ *
+ * We fsave/fwait so that an exception goes off at the right time
+ * (as a call from the fsave or fwait in effect) rather than to
+ * the wrong process. Lazy FP saving no longer makes any sense
+ * with modern CPU's, and this simplifies a lot of things (SMP
+ * and UP become the same).
+ *
+ * NOTE! We used to use the x86 hardware context switching. The
+ * reason for not using it any more becomes apparent when you
+ * try to recover gracefully from saved state that is no longer
+ * valid (stale segment register values in particular). With the
+ * hardware task-switch, there is no way to fix up bad state in
+ * a reasonable manner.
+ *
+ * The fact that Intel documents the hardware task-switching to
+ * be slow is a fairly red herring - this code is not noticeably
+ * faster. However, there _is_ some room for improvement here,
+ * so the performance issues may eventually be a valid point.
+ * More important, however, is the fact that this allows us much
+ * more flexibility.
+ *
+ * The return value (in %eax) will be the "prev" task after
+ * the task-switch, and shows up in ret_from_fork in entry.S,
+ * for example.
+ */
+struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct
task_struct *next_p)
+{
+ struct thread_struct *prev = &prev_p->thread,
+ *next = &next_p->thread;
+ int cpu = smp_processor_id();
+ struct tss_struct *tss = &per_cpu(init_tss, cpu);
+ physdev_op_t iopl_op, iobmp_op;
+ multicall_entry_t _mcl[8], *mcl = _mcl;
+
+ /* XEN NOTE: FS/GS saved in switch_mm(), not here. */
+
+ /*
+ * This is basically '__unlazy_fpu', except that we queue a
+ * multicall to indicate FPU task switch, rather than
+ * synchronously trapping to Xen.
+ */
+ if (prev_p->thread_info->status & TS_USEDFPU) {
+ __save_init_fpu(prev_p); /* _not_ save_init_fpu() */
+ mcl->op = __HYPERVISOR_fpu_taskswitch;
+ mcl->args[0] = 1;
+ mcl++;
+ }
+
+ /*
+ * Reload esp0, LDT and the page table pointer:
+ * This is load_esp0(tss, next) with a multicall.
+ */
+ tss->esp0 = next->esp0;
+ mcl->op = __HYPERVISOR_stack_switch;
+ mcl->args[0] = tss->ss0;
+ mcl->args[1] = tss->esp0;
+ mcl++;
+
+ /*
+ * Load the per-thread Thread-Local Storage descriptor.
+ * This is load_TLS(next, cpu) with multicalls.
+ */
+#define C(i) do { \
+ if (unlikely(next->tls_array[i].a != prev->tls_array[i].a || \
+ next->tls_array[i].b != prev->tls_array[i].b)) { \
+ mcl->op = __HYPERVISOR_update_descriptor; \
+ mcl->args[0] = virt_to_machine(&get_cpu_gdt_table(cpu) \
+ [GDT_ENTRY_TLS_MIN + i]); \
+ mcl->args[1] = ((u32 *)&next->tls_array[i])[0]; \
+ mcl->args[2] = ((u32 *)&next->tls_array[i])[1]; \
+ mcl++; \
+ } \
+} while (0)
+ C(0); C(1); C(2);
+#undef C
+
+ if (unlikely(prev->io_pl != next->io_pl)) {
+ iopl_op.cmd = PHYSDEVOP_SET_IOPL;
+ iopl_op.u.set_iopl.iopl = next->io_pl;
+ mcl->op = __HYPERVISOR_physdev_op;
+ mcl->args[0] = (unsigned long)&iopl_op;
+ mcl++;
+ }
+
+ if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr)) {
+ iobmp_op.cmd =
+ PHYSDEVOP_SET_IOBITMAP;
+ iobmp_op.u.set_iobitmap.bitmap =
+ (unsigned long)next->io_bitmap_ptr;
+ iobmp_op.u.set_iobitmap.nr_ports =
+ next->io_bitmap_ptr ? IO_BITMAP_BITS : 0;
+ mcl->op = __HYPERVISOR_physdev_op;
+ mcl->args[0] = (unsigned long)&iobmp_op;
+ mcl++;
+ }
+
+ (void)HYPERVISOR_multicall(_mcl, mcl - _mcl);
+
+ /*
+ * Restore %fs and %gs if needed.
+ */
+ if (unlikely(next->fs | next->gs)) {
+ loadsegment(fs, next->fs);
+ loadsegment(gs, next->gs);
+ }
+
+ /*
+ * Now maybe reload the debug registers
+ */
+ if (unlikely(next->debugreg[7])) {
+ loaddebug(next, 0);
+ loaddebug(next, 1);
+ loaddebug(next, 2);
+ loaddebug(next, 3);
+ /* no 4 and 5 */
+ loaddebug(next, 6);
+ loaddebug(next, 7);
+ }
+
+ return prev_p;
+}
+
+asmlinkage int sys_fork(struct pt_regs regs)
+{
+ return do_fork(SIGCHLD, regs.esp, ®s, 0, NULL, NULL);
+}
+
+asmlinkage int sys_clone(struct pt_regs regs)
+{
+ unsigned long clone_flags;
+ unsigned long newsp;
+ int __user *parent_tidptr, *child_tidptr;
+
+ clone_flags = regs.ebx;
+ newsp = regs.ecx;
+ parent_tidptr = (int __user *)regs.edx;
+ child_tidptr = (int __user *)regs.edi;
+ if (!newsp)
+ newsp = regs.esp;
+ return do_fork(clone_flags, newsp, ®s, 0, parent_tidptr,
child_tidptr);
+}
+
+/*
+ * This is trivial, and on the face of it looks like it
+ * could equally well be done in user mode.
+ *
+ * Not so, for quite unobvious reasons - register pressure.
+ * In user mode vfork() cannot have a stack frame, and if
+ * done by calling the "clone()" system call directly, you
+ * do not have enough call-clobbered registers to hold all
+ * the information you need.
+ */
+asmlinkage int sys_vfork(struct pt_regs regs)
+{
+ return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.esp, ®s, 0,
NULL, NULL);
+}
+
+/*
+ * sys_execve() executes a new program.
+ */
+asmlinkage int sys_execve(struct pt_regs regs)
+{
+ int error;
+ char * filename;
+
+ filename = getname((char __user *) regs.ebx);
+ error = PTR_ERR(filename);
+ if (IS_ERR(filename))
+ goto out;
+ error = do_execve(filename,
+ (char __user * __user *) regs.ecx,
+ (char __user * __user *) regs.edx,
+ ®s);
+ if (error == 0) {
+ task_lock(current);
+ current->ptrace &= ~PT_DTRACE;
+ task_unlock(current);
+ /* Make sure we don't return using sysenter.. */
+ set_thread_flag(TIF_IRET);
+ }
+ putname(filename);
+out:
+ return error;
+}
+
+#define top_esp (THREAD_SIZE - sizeof(unsigned long))
+#define top_ebp (THREAD_SIZE - 2*sizeof(unsigned long))
+
+unsigned long get_wchan(struct task_struct *p)
+{
+ unsigned long ebp, esp, eip;
+ unsigned long stack_page;
+ int count = 0;
+ if (!p || p == current || p->state == TASK_RUNNING)
+ return 0;
+ stack_page = (unsigned long)p->thread_info;
+ esp = p->thread.esp;
+ if (!stack_page || esp < stack_page || esp > top_esp+stack_page)
+ return 0;
+ /* include/asm-i386/system.h:switch_to() pushes ebp last. */
+ ebp = *(unsigned long *) esp;
+ do {
+ if (ebp < stack_page || ebp > top_ebp+stack_page)
+ return 0;
+ eip = *(unsigned long *) (ebp+4);
+ if (!in_sched_functions(eip))
+ return eip;
+ ebp = *(unsigned long *) ebp;
+ } while (count++ < 16);
+ return 0;
+}
+
+/*
+ * sys_alloc_thread_area: get a yet unused TLS descriptor index.
+ */
+static int get_free_idx(void)
+{
+ struct thread_struct *t = ¤t->thread;
+ int idx;
+
+ for (idx = 0; idx < GDT_ENTRY_TLS_ENTRIES; idx++)
+ if (desc_empty(t->tls_array + idx))
+ return idx + GDT_ENTRY_TLS_MIN;
+ return -ESRCH;
+}
+
+/*
+ * Set a given TLS descriptor:
+ */
+asmlinkage int sys_set_thread_area(struct user_desc __user *u_info)
+{
+ struct thread_struct *t = ¤t->thread;
+ struct user_desc info;
+ struct desc_struct *desc;
+ int cpu, idx;
+
+ if (copy_from_user(&info, u_info, sizeof(info)))
+ return -EFAULT;
+ idx = info.entry_number;
+
+ /*
+ * index -1 means the kernel should try to find and
+ * allocate an empty descriptor:
+ */
+ if (idx == -1) {
+ idx = get_free_idx();
+ if (idx < 0)
+ return idx;
+ if (put_user(idx, &u_info->entry_number))
+ return -EFAULT;
+ }
+
+ if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
+ return -EINVAL;
+
+ desc = t->tls_array + idx - GDT_ENTRY_TLS_MIN;
+
+ /*
+ * We must not get preempted while modifying the TLS.
+ */
+ cpu = get_cpu();
+
+ if (LDT_empty(&info)) {
+ desc->a = 0;
+ desc->b = 0;
+ } else {
+ desc->a = LDT_entry_a(&info);
+ desc->b = LDT_entry_b(&info);
+ }
+ load_TLS(t, cpu);
+
+ put_cpu();
+
+ return 0;
+}
+
+/*
+ * Get the current Thread-Local Storage area:
+ */
+
+#define GET_BASE(desc) ( \
+ (((desc)->a >> 16) & 0x0000ffff) | \
+ (((desc)->b << 16) & 0x00ff0000) | \
+ ( (desc)->b & 0xff000000) )
+
+#define GET_LIMIT(desc) ( \
+ ((desc)->a & 0x0ffff) | \
+ ((desc)->b & 0xf0000) )
+
+#define GET_32BIT(desc) (((desc)->b >> 22) & 1)
+#define GET_CONTENTS(desc) (((desc)->b >> 10) & 3)
+#define GET_WRITABLE(desc) (((desc)->b >> 9) & 1)
+#define GET_LIMIT_PAGES(desc) (((desc)->b >> 23) & 1)
+#define GET_PRESENT(desc) (((desc)->b >> 15) & 1)
+#define GET_USEABLE(desc) (((desc)->b >> 20) & 1)
+
+asmlinkage int sys_get_thread_area(struct user_desc __user *u_info)
+{
+ struct user_desc info;
+ struct desc_struct *desc;
+ int idx;
+
+ if (get_user(idx, &u_info->entry_number))
+ return -EFAULT;
+ if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
+ return -EINVAL;
+
+ desc = current->thread.tls_array + idx - GDT_ENTRY_TLS_MIN;
+
+ info.entry_number = idx;
+ info.base_addr = GET_BASE(desc);
+ info.limit = GET_LIMIT(desc);
+ info.seg_32bit = GET_32BIT(desc);
+ info.contents = GET_CONTENTS(desc);
+ info.read_exec_only = !GET_WRITABLE(desc);
+ info.limit_in_pages = GET_LIMIT_PAGES(desc);
+ info.seg_not_present = !GET_PRESENT(desc);
+ info.useable = GET_USEABLE(desc);
+
+ if (copy_to_user(u_info, &info, sizeof(info)))
+ return -EFAULT;
+ return 0;
+}
+
diff -r 35b74976f598 -r a83ac0806d6b linux-2.6.11-xen-sparse/mm/highmem.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/mm/highmem.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,614 @@
+/*
+ * High memory handling common code and variables.
+ *
+ * (C) 1999 Andrea Arcangeli, SuSE GmbH, andrea@xxxxxxx
+ * Gerhard Wichert, Siemens AG, Gerhard.Wichert@xxxxxxxxxxxxxx
+ *
+ *
+ * Redesigned the x86 32-bit VM architecture to deal with
+ * 64-bit physical space. With current x86 CPUs this
+ * means up to 64 Gigabytes physical RAM.
+ *
+ * Rewrote high memory support to move the page cache into
+ * high memory. Implemented permanent (schedulable) kmaps
+ * based on Linus' idea.
+ *
+ * Copyright (C) 1999 Ingo Molnar <mingo@xxxxxxxxxx>
+ */
+
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/bio.h>
+#include <linux/pagemap.h>
+#include <linux/mempool.h>
+#include <linux/blkdev.h>
+#include <linux/init.h>
+#include <linux/hash.h>
+#include <linux/highmem.h>
+#include <asm/tlbflush.h>
+
+static mempool_t *page_pool, *isa_page_pool;
+
+static void *page_pool_alloc(int gfp_mask, void *data)
+{
+ int gfp = gfp_mask | (int) (long) data;
+
+ return alloc_page(gfp);
+}
+
+static void page_pool_free(void *page, void *data)
+{
+ __free_page(page);
+}
+
+/*
+ * Virtual_count is not a pure "count".
+ * 0 means that it is not mapped, and has not been mapped
+ * since a TLB flush - it is usable.
+ * 1 means that there are no users, but it has been mapped
+ * since the last TLB flush - so we can't use it.
+ * n means that there are (n-1) current users of it.
+ */
+#ifdef CONFIG_HIGHMEM
+static int pkmap_count[LAST_PKMAP];
+static unsigned int last_pkmap_nr;
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(kmap_lock);
+
+pte_t * pkmap_page_table;
+
+static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait);
+
+static void flush_all_zero_pkmaps(void)
+{
+ int i;
+
+ flush_cache_kmaps();
+
+ for (i = 0; i < LAST_PKMAP; i++) {
+ struct page *page;
+
+ /*
+ * zero means we don't have anything to do,
+ * >1 means that it is still in use. Only
+ * a count of 1 means that it is free but
+ * needs to be unmapped
+ */
+ if (pkmap_count[i] != 1)
+ continue;
+ pkmap_count[i] = 0;
+
+ /* sanity check */
+ if (pte_none(pkmap_page_table[i]))
+ BUG();
+
+ /*
+ * Don't need an atomic fetch-and-clear op here;
+ * no-one has the page mapped, and cannot get at
+ * its virtual address (and hence PTE) without first
+ * getting the kmap_lock (which is held here).
+ * So no dangers, even with speculative execution.
+ */
+ page = pte_page(pkmap_page_table[i]);
+ pte_clear(&pkmap_page_table[i]);
+
+ set_page_address(page, NULL);
+ }
+ flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));
+}
+
+static inline unsigned long map_new_virtual(struct page *page)
+{
+ unsigned long vaddr;
+ int count;
+
+start:
+ count = LAST_PKMAP;
+ /* Find an empty entry */
+ for (;;) {
+ last_pkmap_nr = (last_pkmap_nr + 1) & LAST_PKMAP_MASK;
+ if (!last_pkmap_nr) {
+ flush_all_zero_pkmaps();
+ count = LAST_PKMAP;
+ }
+ if (!pkmap_count[last_pkmap_nr])
+ break; /* Found a usable entry */
+ if (--count)
+ continue;
+
+ /*
+ * Sleep for somebody else to unmap their entries
+ */
+ {
+ DECLARE_WAITQUEUE(wait, current);
+
+ __set_current_state(TASK_UNINTERRUPTIBLE);
+ add_wait_queue(&pkmap_map_wait, &wait);
+ spin_unlock(&kmap_lock);
+ schedule();
+ remove_wait_queue(&pkmap_map_wait, &wait);
+ spin_lock(&kmap_lock);
+
+ /* Somebody else might have mapped it while we slept */
+ if (page_address(page))
+ return (unsigned long)page_address(page);
+
+ /* Re-start */
+ goto start;
+ }
+ }
+ vaddr = PKMAP_ADDR(last_pkmap_nr);
+ set_pte(&(pkmap_page_table[last_pkmap_nr]), mk_pte(page, kmap_prot));
+
+ pkmap_count[last_pkmap_nr] = 1;
+ set_page_address(page, (void *)vaddr);
+
+ return vaddr;
+}
+
+void kmap_flush_unused(void)
+{
+ spin_lock(&kmap_lock);
+ flush_all_zero_pkmaps();
+ spin_unlock(&kmap_lock);
+}
+
+EXPORT_SYMBOL(kmap_flush_unused);
+
+void fastcall *kmap_high(struct page *page)
+{
+ unsigned long vaddr;
+
+ /*
+ * For highmem pages, we can't trust "virtual" until
+ * after we have the lock.
+ *
+ * We cannot call this from interrupts, as it may block
+ */
+ spin_lock(&kmap_lock);
+ vaddr = (unsigned long)page_address(page);
+ if (!vaddr)
+ vaddr = map_new_virtual(page);
+ pkmap_count[PKMAP_NR(vaddr)]++;
+ if (pkmap_count[PKMAP_NR(vaddr)] < 2)
+ BUG();
+ spin_unlock(&kmap_lock);
+ return (void*) vaddr;
+}
+
+EXPORT_SYMBOL(kmap_high);
+
+void fastcall kunmap_high(struct page *page)
+{
+ unsigned long vaddr;
+ unsigned long nr;
+ int need_wakeup;
+
+ spin_lock(&kmap_lock);
+ vaddr = (unsigned long)page_address(page);
+ if (!vaddr)
+ BUG();
+ nr = PKMAP_NR(vaddr);
+
+ /*
+ * A count must never go down to zero
+ * without a TLB flush!
+ */
+ need_wakeup = 0;
+ switch (--pkmap_count[nr]) {
+ case 0:
+ BUG();
+ case 1:
+ /*
+ * Avoid an unnecessary wake_up() function call.
+ * The common case is pkmap_count[] == 1, but
+ * no waiters.
+ * The tasks queued in the wait-queue are guarded
+ * by both the lock in the wait-queue-head and by
+ * the kmap_lock. As the kmap_lock is held here,
+ * no need for the wait-queue-head's lock. Simply
+ * test if the queue is empty.
+ */
+ need_wakeup = waitqueue_active(&pkmap_map_wait);
+ }
+ spin_unlock(&kmap_lock);
+
+ /* do wake-up, if needed, race-free outside of the spin lock */
+ if (need_wakeup)
+ wake_up(&pkmap_map_wait);
+}
+
+EXPORT_SYMBOL(kunmap_high);
+
+#define POOL_SIZE 64
+
+static __init int init_emergency_pool(void)
+{
+ struct sysinfo i;
+ si_meminfo(&i);
+ si_swapinfo(&i);
+
+ if (!i.totalhigh)
+ return 0;
+
+ page_pool = mempool_create(POOL_SIZE, page_pool_alloc, page_pool_free,
NULL);
+ if (!page_pool)
+ BUG();
+ printk("highmem bounce pool size: %d pages\n", POOL_SIZE);
+
+ return 0;
+}
+
+__initcall(init_emergency_pool);
+
+/*
+ * highmem version, map in to vec
+ */
+static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
+{
+ unsigned long flags;
+ unsigned char *vto;
+
+ local_irq_save(flags);
+ vto = kmap_atomic(to->bv_page, KM_BOUNCE_READ);
+ memcpy(vto + to->bv_offset, vfrom, to->bv_len);
+ kunmap_atomic(vto, KM_BOUNCE_READ);
+ local_irq_restore(flags);
+}
+
+#else /* CONFIG_HIGHMEM */
+
+#define bounce_copy_vec(to, vfrom) \
+ memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom,
(to)->bv_len)
+
+#endif
+
+#define ISA_POOL_SIZE 16
+
+/*
+ * gets called "every" time someone init's a queue with BLK_BOUNCE_ISA
+ * as the max address, so check if the pool has already been created.
+ */
+int init_emergency_isa_pool(void)
+{
+ if (isa_page_pool)
+ return 0;
+
+ isa_page_pool = mempool_create(ISA_POOL_SIZE, page_pool_alloc,
page_pool_free, (void *) __GFP_DMA);
+ if (!isa_page_pool)
+ BUG();
+
+ printk("isa bounce pool size: %d pages\n", ISA_POOL_SIZE);
+ return 0;
+}
+
+/*
+ * Simple bounce buffer support for highmem pages. Depending on the
+ * queue gfp mask set, *to may or may not be a highmem page. kmap it
+ * always, it will do the Right Thing
+ */
+static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
+{
+ unsigned char *vfrom;
+ struct bio_vec *tovec, *fromvec;
+ int i;
+
+ __bio_for_each_segment(tovec, to, i, 0) {
+ fromvec = from->bi_io_vec + i;
+
+ /*
+ * not bounced
+ */
+ if (tovec->bv_page == fromvec->bv_page)
+ continue;
+
+ /*
+ * fromvec->bv_offset and fromvec->bv_len might have been
+ * modified by the block layer, so use the original copy,
+ * bounce_copy_vec already uses tovec->bv_len
+ */
+ vfrom = page_address(fromvec->bv_page) + tovec->bv_offset;
+
+ flush_dcache_page(tovec->bv_page);
+ bounce_copy_vec(tovec, vfrom);
+ }
+}
+
+static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
+{
+ struct bio *bio_orig = bio->bi_private;
+ struct bio_vec *bvec, *org_vec;
+ int i;
+
+ if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
+ set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags);
+
+ /*
+ * free up bounce indirect pages used
+ */
+ __bio_for_each_segment(bvec, bio, i, 0) {
+ org_vec = bio_orig->bi_io_vec + i;
+ if (bvec->bv_page == org_vec->bv_page)
+ continue;
+
+ mempool_free(bvec->bv_page, pool);
+ }
+
+ bio_endio(bio_orig, bio_orig->bi_size, err);
+ bio_put(bio);
+}
+
+static int bounce_end_io_write(struct bio *bio, unsigned int bytes_done,int
err)
+{
+ if (bio->bi_size)
+ return 1;
+
+ bounce_end_io(bio, page_pool, err);
+ return 0;
+}
+
+static int bounce_end_io_write_isa(struct bio *bio, unsigned int bytes_done,
int err)
+{
+ if (bio->bi_size)
+ return 1;
+
+ bounce_end_io(bio, isa_page_pool, err);
+ return 0;
+}
+
+static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err)
+{
+ struct bio *bio_orig = bio->bi_private;
+
+ if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+ copy_to_high_bio_irq(bio_orig, bio);
+
+ bounce_end_io(bio, pool, err);
+}
+
+static int bounce_end_io_read(struct bio *bio, unsigned int bytes_done, int
err)
+{
+ if (bio->bi_size)
+ return 1;
+
+ __bounce_end_io_read(bio, page_pool, err);
+ return 0;
+}
+
+static int bounce_end_io_read_isa(struct bio *bio, unsigned int bytes_done,
int err)
+{
+ if (bio->bi_size)
+ return 1;
+
+ __bounce_end_io_read(bio, isa_page_pool, err);
+ return 0;
+}
+
+static void __blk_queue_bounce(request_queue_t *q, struct bio **bio_orig,
+ mempool_t *pool)
+{
+ struct page *page;
+ struct bio *bio = NULL;
+ int i, rw = bio_data_dir(*bio_orig);
+ struct bio_vec *to, *from;
+
+ bio_for_each_segment(from, *bio_orig, i) {
+ page = from->bv_page;
+
+ /*
+ * is destination page below bounce pfn?
+ */
+ if (page_to_pfn(page) < q->bounce_pfn)
+ continue;
+
+ /*
+ * irk, bounce it
+ */
+ if (!bio)
+ bio = bio_alloc(GFP_NOIO, (*bio_orig)->bi_vcnt);
+
+ to = bio->bi_io_vec + i;
+
+ to->bv_page = mempool_alloc(pool, q->bounce_gfp);
+ to->bv_len = from->bv_len;
+ to->bv_offset = from->bv_offset;
+
+ if (rw == WRITE) {
+ char *vto, *vfrom;
+
+ flush_dcache_page(from->bv_page);
+ vto = page_address(to->bv_page) + to->bv_offset;
+ vfrom = kmap(from->bv_page) + from->bv_offset;
+ memcpy(vto, vfrom, to->bv_len);
+ kunmap(from->bv_page);
+ }
+ }
+
+ /*
+ * no pages bounced
+ */
+ if (!bio)
+ return;
+
+ /*
+ * at least one page was bounced, fill in possible non-highmem
+ * pages
+ */
+ __bio_for_each_segment(from, *bio_orig, i, 0) {
+ to = bio_iovec_idx(bio, i);
+ if (!to->bv_page) {
+ to->bv_page = from->bv_page;
+ to->bv_len = from->bv_len;
+ to->bv_offset = from->bv_offset;
+ }
+ }
+
+ bio->bi_bdev = (*bio_orig)->bi_bdev;
+ bio->bi_flags |= (1 << BIO_BOUNCED);
+ bio->bi_sector = (*bio_orig)->bi_sector;
+ bio->bi_rw = (*bio_orig)->bi_rw;
+
+ bio->bi_vcnt = (*bio_orig)->bi_vcnt;
+ bio->bi_idx = (*bio_orig)->bi_idx;
+ bio->bi_size = (*bio_orig)->bi_size;
+
+ if (pool == page_pool) {
+ bio->bi_end_io = bounce_end_io_write;
+ if (rw == READ)
+ bio->bi_end_io = bounce_end_io_read;
+ } else {
+ bio->bi_end_io = bounce_end_io_write_isa;
+ if (rw == READ)
+ bio->bi_end_io = bounce_end_io_read_isa;
+ }
+
+ bio->bi_private = *bio_orig;
+ *bio_orig = bio;
+}
+
+void blk_queue_bounce(request_queue_t *q, struct bio **bio_orig)
+{
+ mempool_t *pool;
+
+ /*
+ * for non-isa bounce case, just check if the bounce pfn is equal
+ * to or bigger than the highest pfn in the system -- in that case,
+ * don't waste time iterating over bio segments
+ */
+ if (!(q->bounce_gfp & GFP_DMA)) {
+ if (q->bounce_pfn >= blk_max_pfn)
+ return;
+ pool = page_pool;
+ } else {
+ BUG_ON(!isa_page_pool);
+ pool = isa_page_pool;
+ }
+
+ /*
+ * slow path
+ */
+ __blk_queue_bounce(q, bio_orig, pool);
+}
+
+EXPORT_SYMBOL(blk_queue_bounce);
+
+#if defined(HASHED_PAGE_VIRTUAL)
+
+#define PA_HASH_ORDER 7
+
+/*
+ * Describes one page->virtual association
+ */
+struct page_address_map {
+ struct page *page;
+ void *virtual;
+ struct list_head list;
+};
+
+/*
+ * page_address_map freelist, allocated from page_address_maps.
+ */
+static struct list_head page_address_pool; /* freelist */
+static spinlock_t pool_lock; /* protects page_address_pool */
+
+/*
+ * Hash table bucket
+ */
+static struct page_address_slot {
+ struct list_head lh; /* List of page_address_maps */
+ spinlock_t lock; /* Protect this bucket's list */
+} ____cacheline_aligned_in_smp page_address_htable[1<<PA_HASH_ORDER];
+
+static struct page_address_slot *page_slot(struct page *page)
+{
+ return &page_address_htable[hash_ptr(page, PA_HASH_ORDER)];
+}
+
+void *page_address(struct page *page)
+{
+ unsigned long flags;
+ void *ret;
+ struct page_address_slot *pas;
+
+ if (!PageHighMem(page))
+ return lowmem_page_address(page);
+
+ pas = page_slot(page);
+ ret = NULL;
+ spin_lock_irqsave(&pas->lock, flags);
+ if (!list_empty(&pas->lh)) {
+ struct page_address_map *pam;
+
+ list_for_each_entry(pam, &pas->lh, list) {
+ if (pam->page == page) {
+ ret = pam->virtual;
+ goto done;
+ }
+ }
+ }
+done:
+ spin_unlock_irqrestore(&pas->lock, flags);
+ return ret;
+}
+
+EXPORT_SYMBOL(page_address);
+
+void set_page_address(struct page *page, void *virtual)
+{
+ unsigned long flags;
+ struct page_address_slot *pas;
+ struct page_address_map *pam;
+
+ BUG_ON(!PageHighMem(page));
+
+ pas = page_slot(page);
+ if (virtual) { /* Add */
+ BUG_ON(list_empty(&page_address_pool));
+
+ spin_lock_irqsave(&pool_lock, flags);
+ pam = list_entry(page_address_pool.next,
+ struct page_address_map, list);
+ list_del(&pam->list);
+ spin_unlock_irqrestore(&pool_lock, flags);
+
+ pam->page = page;
+ pam->virtual = virtual;
+
+ spin_lock_irqsave(&pas->lock, flags);
+ list_add_tail(&pam->list, &pas->lh);
+ spin_unlock_irqrestore(&pas->lock, flags);
+ } else { /* Remove */
+ spin_lock_irqsave(&pas->lock, flags);
+ list_for_each_entry(pam, &pas->lh, list) {
+ if (pam->page == page) {
+ list_del(&pam->list);
+ spin_unlock_irqrestore(&pas->lock, flags);
+ spin_lock_irqsave(&pool_lock, flags);
+ list_add_tail(&pam->list, &page_address_pool);
+ spin_unlock_irqrestore(&pool_lock, flags);
+ goto done;
+ }
+ }
+ spin_unlock_irqrestore(&pas->lock, flags);
+ }
+done:
+ return;
+}
+
+static struct page_address_map page_address_maps[LAST_PKMAP];
+
+void __init page_address_init(void)
+{
+ int i;
+
+ INIT_LIST_HEAD(&page_address_pool);
+ for (i = 0; i < ARRAY_SIZE(page_address_maps); i++)
+ list_add(&page_address_maps[i].list, &page_address_pool);
+ for (i = 0; i < ARRAY_SIZE(page_address_htable); i++) {
+ INIT_LIST_HEAD(&page_address_htable[i].lh);
+ spin_lock_init(&page_address_htable[i].lock);
+ }
+ spin_lock_init(&pool_lock);
+}
+
+#endif /* defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blkfront/Kconfig
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blkfront/Kconfig Fri Jul 15
13:39:50 2005
@@ -0,0 +1,6 @@
+
+config XENBLOCK
+ tristate "Block device driver"
+ depends on ARCH_XEN
+ help
+ Block device driver for Xen
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/drivers/console/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/drivers/console/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,3 @@
+O_TARGET := drv.o
+obj-$(CONFIG_XEN_CONSOLE) := console.o
+include $(TOPDIR)/Rules.make
diff -r 35b74976f598 -r a83ac0806d6b linux-2.6.11-xen-sparse/drivers/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/Makefile Fri Jul 15 13:39:50 2005
@@ -0,0 +1,66 @@
+#
+# Makefile for the Linux kernel device drivers.
+#
+# 15 Sep 2000, Christoph Hellwig <hch@xxxxxxxxxxxxx>
+# Rewritten to use lists instead of if-statements.
+#
+
+obj-$(CONFIG_PCI) += pci/
+obj-$(CONFIG_PARISC) += parisc/
+obj-y += video/
+obj-$(CONFIG_ACPI_BOOT) += acpi/
+# PnP must come after ACPI since it will eventually need to check if acpi
+# was used and do nothing if so
+obj-$(CONFIG_PNP) += pnp/
+
+# char/ comes before serial/ etc so that the VT console is the boot-time
+# default.
+obj-y += char/
+
+# i810fb and intelfb depend on char/agp/
+obj-$(CONFIG_FB_I810) += video/i810/
+obj-$(CONFIG_FB_INTEL) += video/intelfb/
+
+# we also need input/serio early so serio bus is initialized by the time
+# serial drivers start registering their serio ports
+obj-$(CONFIG_SERIO) += input/serio/
+obj-y += serial/
+obj-$(CONFIG_PARPORT) += parport/
+obj-y += base/ block/ misc/ net/ media/
+obj-$(CONFIG_NUBUS) += nubus/
+obj-$(CONFIG_ATM) += atm/
+obj-$(CONFIG_PPC_PMAC) += macintosh/
+obj-$(CONFIG_ARCH_XEN) += xen/
+obj-$(CONFIG_IDE) += ide/
+obj-$(CONFIG_FC4) += fc4/
+obj-$(CONFIG_SCSI) += scsi/
+obj-$(CONFIG_FUSION) += message/
+obj-$(CONFIG_IEEE1394) += ieee1394/
+obj-y += cdrom/
+obj-$(CONFIG_MTD) += mtd/
+obj-$(CONFIG_PCCARD) += pcmcia/
+obj-$(CONFIG_DIO) += dio/
+obj-$(CONFIG_SBUS) += sbus/
+obj-$(CONFIG_ZORRO) += zorro/
+obj-$(CONFIG_MAC) += macintosh/
+obj-$(CONFIG_ATA_OVER_ETH) += block/aoe/
+obj-$(CONFIG_PARIDE) += block/paride/
+obj-$(CONFIG_TC) += tc/
+obj-$(CONFIG_USB) += usb/
+obj-$(CONFIG_USB_GADGET) += usb/gadget/
+obj-$(CONFIG_INPUT) += input/
+obj-$(CONFIG_GAMEPORT) += input/gameport/
+obj-$(CONFIG_I2O) += message/
+obj-$(CONFIG_I2C) += i2c/
+obj-$(CONFIG_W1) += w1/
+obj-$(CONFIG_PHONE) += telephony/
+obj-$(CONFIG_MD) += md/
+obj-$(CONFIG_BT) += bluetooth/
+obj-$(CONFIG_ISDN) += isdn/
+obj-$(CONFIG_MCA) += mca/
+obj-$(CONFIG_EISA) += eisa/
+obj-$(CONFIG_CPU_FREQ) += cpufreq/
+obj-$(CONFIG_MMC) += mmc/
+obj-$(CONFIG_INFINIBAND) += infiniband/
+obj-y += firmware/
+obj-$(CONFIG_CRYPTO) += crypto/
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/tlbflush.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/tlbflush.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,102 @@
+#ifndef _I386_TLBFLUSH_H
+#define _I386_TLBFLUSH_H
+
+#include <linux/config.h>
+#include <linux/mm.h>
+#include <asm/processor.h>
+
+#define __flush_tlb() xen_tlb_flush()
+#define __flush_tlb_global() xen_tlb_flush()
+#define __flush_tlb_all() xen_tlb_flush()
+
+extern unsigned long pgkern_mask;
+
+#define cpu_has_invlpg (boot_cpu_data.x86 > 3)
+
+#define __flush_tlb_single(addr) xen_invlpg(addr)
+
+#define __flush_tlb_one(addr) __flush_tlb_single(addr)
+
+/*
+ * TLB flushing:
+ *
+ * - flush_tlb() flushes the current mm struct TLBs
+ * - flush_tlb_all() flushes all processes TLBs
+ * - flush_tlb_mm(mm) flushes the specified mm context TLB's
+ * - flush_tlb_page(vma, vmaddr) flushes one page
+ * - flush_tlb_range(vma, start, end) flushes a range of pages
+ * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
+ * - flush_tlb_pgtables(mm, start, end) flushes a range of page tables
+ *
+ * ..but the i386 has somewhat limited tlb flushing capabilities,
+ * and page-granular flushes are available only on i486 and up.
+ */
+
+#ifndef CONFIG_SMP
+
+#define flush_tlb() __flush_tlb()
+#define flush_tlb_all() __flush_tlb_all()
+#define local_flush_tlb() __flush_tlb()
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+ if (mm == current->active_mm)
+ __flush_tlb();
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+ unsigned long addr)
+{
+ if (vma->vm_mm == current->active_mm)
+ __flush_tlb_one(addr);
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ if (vma->vm_mm == current->active_mm)
+ __flush_tlb();
+}
+
+#else
+
+#include <asm/smp.h>
+
+#define local_flush_tlb() \
+ __flush_tlb()
+
+extern void flush_tlb_all(void);
+extern void flush_tlb_current_task(void);
+extern void flush_tlb_mm(struct mm_struct *);
+extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
+
+#define flush_tlb() flush_tlb_current_task()
+
+static inline void flush_tlb_range(struct vm_area_struct * vma, unsigned long
start, unsigned long end)
+{
+ flush_tlb_mm(vma->vm_mm);
+}
+
+#define TLBSTATE_OK 1
+#define TLBSTATE_LAZY 2
+
+struct tlb_state
+{
+ struct mm_struct *active_mm;
+ int state;
+ char __cacheline_padding[L1_CACHE_BYTES-8];
+};
+DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate);
+
+
+#endif
+
+#define flush_tlb_kernel_range(start, end) flush_tlb_all()
+
+static inline void flush_tlb_pgtables(struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ /* i386 does not keep any page table caches in TLB */
+}
+
+#endif /* _I386_TLBFLUSH_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/arch_hooks.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/arch_hooks.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,27 @@
+#ifndef _ASM_ARCH_HOOKS_H
+#define _ASM_ARCH_HOOKS_H
+
+#include <linux/interrupt.h>
+
+/*
+ * linux/include/asm/arch_hooks.h
+ *
+ * define the architecture specific hooks
+ */
+
+/* these aren't arch hooks, they are generic routines
+ * that can be used by the hooks */
+extern void init_ISA_irqs(void);
+extern void apic_intr_init(void);
+extern void smp_intr_init(void);
+extern irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs
*regs);
+
+/* these are the defined hooks */
+extern void intr_init_hook(void);
+extern void pre_intr_init_hook(void);
+extern void pre_setup_arch_hook(void);
+extern void trap_init_hook(void);
+extern void time_init_hook(void);
+extern void mca_nmi_hook(void);
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blkfront/vbd.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blkfront/vbd.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,500 @@
+/******************************************************************************
+ * vbd.c
+ *
+ * XenLinux virtual block-device driver (xvd).
+ *
+ * Copyright (c) 2003-2004, Keir Fraser & Steve Hand
+ * Modifications by Mark A. Williamson are (c) Intel Research Cambridge
+ * Copyright (c) 2004-2005, Christian Limpach
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include "block.h"
+#include <linux/blkdev.h>
+#include <linux/list.h>
+
+/*
+ * For convenience we distinguish between ide, scsi and 'other' (i.e.,
+ * potentially combinations of the two) in the naming scheme and in a few other
+ * places.
+ */
+
+#define NUM_IDE_MAJORS 10
+#define NUM_SCSI_MAJORS 9
+#define NUM_VBD_MAJORS 1
+
+struct lvdisk
+{
+ blkif_sector_t capacity; /* 0: Size in terms of 512-byte sectors. */
+ blkif_vdev_t device; /* 8: Device number (opaque 16 bit value). */
+ u16 info;
+ struct list_head list;
+};
+
+static struct xlbd_type_info xlbd_ide_type = {
+ .partn_shift = 6,
+ .disks_per_major = 2,
+ .devname = "ide",
+ .diskname = "hd",
+};
+
+static struct xlbd_type_info xlbd_scsi_type = {
+ .partn_shift = 4,
+ .disks_per_major = 16,
+ .devname = "sd",
+ .diskname = "sd",
+};
+
+static struct xlbd_type_info xlbd_vbd_type = {
+ .partn_shift = 4,
+ .disks_per_major = 16,
+ .devname = "xvd",
+ .diskname = "xvd",
+};
+
+static struct xlbd_major_info *major_info[NUM_IDE_MAJORS + NUM_SCSI_MAJORS +
+ NUM_VBD_MAJORS];
+
+#define XLBD_MAJOR_IDE_START 0
+#define XLBD_MAJOR_SCSI_START (NUM_IDE_MAJORS)
+#define XLBD_MAJOR_VBD_START (NUM_IDE_MAJORS + NUM_SCSI_MAJORS)
+
+#define XLBD_MAJOR_IDE_RANGE XLBD_MAJOR_IDE_START ... XLBD_MAJOR_SCSI_START
- 1
+#define XLBD_MAJOR_SCSI_RANGE XLBD_MAJOR_SCSI_START ... XLBD_MAJOR_VBD_START
- 1
+#define XLBD_MAJOR_VBD_RANGE XLBD_MAJOR_VBD_START ... XLBD_MAJOR_VBD_START
+ NUM_VBD_MAJORS - 1
+
+/* Information about our VBDs. */
+#define MAX_VBDS 64
+struct list_head vbds_list;
+
+#define MAJOR_XEN(dev) ((dev)>>8)
+#define MINOR_XEN(dev) ((dev) & 0xff)
+
+static struct block_device_operations xlvbd_block_fops =
+{
+ .owner = THIS_MODULE,
+ .open = blkif_open,
+ .release = blkif_release,
+ .ioctl = blkif_ioctl,
+};
+
+spinlock_t blkif_io_lock = SPIN_LOCK_UNLOCKED;
+
+static struct lvdisk *xlvbd_device_alloc(void)
+{
+ struct lvdisk *disk;
+
+ disk = kmalloc(sizeof(*disk), GFP_KERNEL);
+ if (disk != NULL) {
+ memset(disk, 0, sizeof(*disk));
+ INIT_LIST_HEAD(&disk->list);
+ }
+ return disk;
+}
+
+static void xlvbd_device_free(struct lvdisk *disk)
+{
+ list_del(&disk->list);
+ kfree(disk);
+}
+
+static vdisk_t *xlvbd_probe(int *ret)
+{
+ blkif_response_t rsp;
+ blkif_request_t req;
+ vdisk_t *disk_info = NULL;
+ unsigned long buf;
+ int nr;
+
+ buf = __get_free_page(GFP_KERNEL);
+ if ((void *)buf == NULL)
+ goto out;
+
+ memset(&req, 0, sizeof(req));
+ req.operation = BLKIF_OP_PROBE;
+ req.nr_segments = 1;
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ blkif_control_probe_send(&req, &rsp,
+ (unsigned long)(virt_to_machine(buf)));
+#else
+ req.frame_and_sects[0] = virt_to_machine(buf) | 7;
+
+ blkif_control_send(&req, &rsp);
+#endif
+ if ( rsp.status <= 0 ) {
+ WPRINTK("Could not probe disks (%d)\n", rsp.status);
+ goto out;
+ }
+ nr = rsp.status;
+ if ( nr > MAX_VBDS )
+ nr = MAX_VBDS;
+
+ disk_info = kmalloc(nr * sizeof(vdisk_t), GFP_KERNEL);
+ if (disk_info != NULL)
+ memcpy(disk_info, (void *) buf, nr * sizeof(vdisk_t));
+
+ if (ret != NULL)
+ *ret = nr;
+
+out:
+ free_page(buf);
+ return disk_info;
+}
+
+static struct xlbd_major_info *xlbd_alloc_major_info(
+ int major, int minor, int index)
+{
+ struct xlbd_major_info *ptr;
+
+ ptr = kmalloc(sizeof(struct xlbd_major_info), GFP_KERNEL);
+ if (ptr == NULL)
+ return NULL;
+
+ memset(ptr, 0, sizeof(struct xlbd_major_info));
+
+ ptr->major = major;
+
+ switch (index) {
+ case XLBD_MAJOR_IDE_RANGE:
+ ptr->type = &xlbd_ide_type;
+ ptr->index = index - XLBD_MAJOR_IDE_START;
+ break;
+ case XLBD_MAJOR_SCSI_RANGE:
+ ptr->type = &xlbd_scsi_type;
+ ptr->index = index - XLBD_MAJOR_SCSI_START;
+ break;
+ case XLBD_MAJOR_VBD_RANGE:
+ ptr->type = &xlbd_vbd_type;
+ ptr->index = index - XLBD_MAJOR_VBD_START;
+ break;
+ }
+
+ if (register_blkdev(ptr->major, ptr->type->devname)) {
+ WPRINTK("can't get major %d with name %s\n",
+ ptr->major, ptr->type->devname);
+ kfree(ptr);
+ return NULL;
+ }
+
+ devfs_mk_dir(ptr->type->devname);
+ major_info[index] = ptr;
+ return ptr;
+}
+
+static struct xlbd_major_info *xlbd_get_major_info(int device)
+{
+ int major, minor, index;
+
+ major = MAJOR_XEN(device);
+ minor = MINOR_XEN(device);
+
+ switch (major) {
+ case IDE0_MAJOR: index = 0; break;
+ case IDE1_MAJOR: index = 1; break;
+ case IDE2_MAJOR: index = 2; break;
+ case IDE3_MAJOR: index = 3; break;
+ case IDE4_MAJOR: index = 4; break;
+ case IDE5_MAJOR: index = 5; break;
+ case IDE6_MAJOR: index = 6; break;
+ case IDE7_MAJOR: index = 7; break;
+ case IDE8_MAJOR: index = 8; break;
+ case IDE9_MAJOR: index = 9; break;
+ case SCSI_DISK0_MAJOR: index = 10; break;
+ case SCSI_DISK1_MAJOR ... SCSI_DISK7_MAJOR:
+ index = 11 + major - SCSI_DISK1_MAJOR;
+ break;
+ case SCSI_CDROM_MAJOR: index = 18; break;
+ default: index = 19; break;
+ }
+
+ return ((major_info[index] != NULL) ? major_info[index] :
+ xlbd_alloc_major_info(major, minor, index));
+}
+
+static int xlvbd_init_blk_queue(struct gendisk *gd, vdisk_t *disk)
+{
+ request_queue_t *rq;
+
+ rq = blk_init_queue(do_blkif_request, &blkif_io_lock);
+ if (rq == NULL)
+ return -1;
+
+ elevator_init(rq, "noop");
+
+ /* Hard sector size and max sectors impersonate the equiv. hardware. */
+ blk_queue_hardsect_size(rq, disk->sector_size);
+ blk_queue_max_sectors(rq, 512);
+
+ /* Each segment in a request is up to an aligned page in size. */
+ blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
+ blk_queue_max_segment_size(rq, PAGE_SIZE);
+
+ /* Ensure a merged request will fit in a single I/O ring slot. */
+ blk_queue_max_phys_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
+ blk_queue_max_hw_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
+
+ /* Make sure buffer addresses are sector-aligned. */
+ blk_queue_dma_alignment(rq, 511);
+
+ gd->queue = rq;
+
+ return 0;
+}
+
+struct gendisk *xlvbd_alloc_gendisk(
+ struct xlbd_major_info *mi, int minor, vdisk_t *disk)
+{
+ struct gendisk *gd;
+ struct xlbd_disk_info *di;
+ int nr_minors = 1;
+
+ di = kmalloc(sizeof(struct xlbd_disk_info), GFP_KERNEL);
+ if (di == NULL)
+ return NULL;
+ memset(di, 0, sizeof(*di));
+ di->mi = mi;
+ di->xd_device = disk->device;
+
+ if ((minor & ((1 << mi->type->partn_shift) - 1)) == 0)
+ nr_minors = 1 << mi->type->partn_shift;
+
+ gd = alloc_disk(nr_minors);
+ if (gd == NULL)
+ goto out;
+
+ if (nr_minors > 1)
+ sprintf(gd->disk_name, "%s%c", mi->type->diskname,
+ 'a' + mi->index * mi->type->disks_per_major +
+ (minor >> mi->type->partn_shift));
+ else
+ sprintf(gd->disk_name, "%s%c%d", mi->type->diskname,
+ 'a' + mi->index * mi->type->disks_per_major +
+ (minor >> mi->type->partn_shift),
+ minor & ((1 << mi->type->partn_shift) - 1));
+
+ gd->major = mi->major;
+ gd->first_minor = minor;
+ gd->fops = &xlvbd_block_fops;
+ gd->private_data = di;
+ set_capacity(gd, disk->capacity);
+
+ if (xlvbd_init_blk_queue(gd, disk)) {
+ del_gendisk(gd);
+ goto out;
+ }
+
+ di->rq = gd->queue;
+
+ if (disk->info & VDISK_READONLY)
+ set_disk_ro(gd, 1);
+
+ if (disk->info & VDISK_REMOVABLE)
+ gd->flags |= GENHD_FL_REMOVABLE;
+
+ if (disk->info & VDISK_CDROM)
+ gd->flags |= GENHD_FL_CD;
+
+ add_disk(gd);
+
+ return gd;
+
+out:
+ kfree(di);
+ return NULL;
+}
+
+static int xlvbd_device_add(struct list_head *list, vdisk_t *disk)
+{
+ struct lvdisk *new;
+ int minor;
+ dev_t device;
+ struct block_device *bd;
+ struct gendisk *gd;
+ struct xlbd_major_info *mi;
+
+ mi = xlbd_get_major_info(disk->device);
+ if (mi == NULL)
+ return -EPERM;
+
+ new = xlvbd_device_alloc();
+ if (new == NULL)
+ return -1;
+ new->capacity = disk->capacity;
+ new->device = disk->device;
+ new->info = disk->info;
+
+ minor = MINOR_XEN(disk->device);
+ device = MKDEV(mi->major, minor);
+
+ bd = bdget(device);
+ if (bd == NULL)
+ goto out;
+
+ gd = xlvbd_alloc_gendisk(mi, minor, disk);
+ if (gd == NULL)
+ goto out_bd;
+
+ list_add(&new->list, list);
+out_bd:
+ bdput(bd);
+out:
+ return 0;
+}
+
+static int xlvbd_device_del(struct lvdisk *disk)
+{
+ dev_t device;
+ struct block_device *bd;
+ struct gendisk *gd;
+ struct xlbd_disk_info *di;
+ int ret = 0, unused;
+ request_queue_t *rq;
+
+ device = MKDEV(MAJOR_XEN(disk->device), MINOR_XEN(disk->device));
+
+ bd = bdget(device);
+ if (bd == NULL)
+ return -1;
+
+ gd = get_gendisk(device, &unused);
+ di = gd->private_data;
+
+ if (di->mi->usage != 0) {
+ WPRINTK("disk removal failed: used [dev=%x]\n", device);
+ ret = -1;
+ goto out;
+ }
+
+ rq = gd->queue;
+ del_gendisk(gd);
+ put_disk(gd);
+ blk_cleanup_queue(rq);
+
+ xlvbd_device_free(disk);
+out:
+ bdput(bd);
+ return ret;
+}
+
+static int xlvbd_device_update(struct lvdisk *ldisk, vdisk_t *disk)
+{
+ dev_t device;
+ struct block_device *bd;
+ struct gendisk *gd;
+ int unused;
+
+ if ((ldisk->capacity == disk->capacity) && (ldisk->info == disk->info))
+ return 0;
+
+ device = MKDEV(MAJOR_XEN(ldisk->device), MINOR_XEN(ldisk->device));
+
+ bd = bdget(device);
+ if (bd == NULL)
+ return -1;
+
+ gd = get_gendisk(device, &unused);
+ set_capacity(gd, disk->capacity);
+ ldisk->capacity = disk->capacity;
+
+ bdput(bd);
+
+ return 0;
+}
+
+void xlvbd_refresh(void)
+{
+ vdisk_t *newdisks;
+ struct list_head *tmp, *tmp2;
+ struct lvdisk *disk;
+ int i, nr;
+
+ newdisks = xlvbd_probe(&nr);
+ if (newdisks == NULL) {
+ WPRINTK("failed to probe\n");
+ return;
+ }
+
+ i = 0;
+ list_for_each_safe(tmp, tmp2, &vbds_list) {
+ disk = list_entry(tmp, struct lvdisk, list);
+
+ for (i = 0; i < nr; i++) {
+ if ( !newdisks[i].device )
+ continue;
+ if ( disk->device == newdisks[i].device ) {
+ xlvbd_device_update(disk, &newdisks[i]);
+ newdisks[i].device = 0;
+ break;
+ }
+ }
+ if (i == nr) {
+ xlvbd_device_del(disk);
+ newdisks[i].device = 0;
+ }
+ }
+ for (i = 0; i < nr; i++)
+ if ( newdisks[i].device )
+ xlvbd_device_add(&vbds_list, &newdisks[i]);
+ kfree(newdisks);
+}
+
+/*
+ * xlvbd_update_vbds - reprobes the VBD status and performs updates driver
+ * state. The VBDs need to be updated in this way when the domain is
+ * initialised and also each time we receive an XLBLK_UPDATE event.
+ */
+void xlvbd_update_vbds(void)
+{
+ xlvbd_refresh();
+}
+
+/*
+ * Set up all the linux device goop for the virtual block devices
+ * (vbd's) that we know about. Note that although from the backend
+ * driver's p.o.v. VBDs are addressed simply an opaque 16-bit device
+ * number, the domain creation tools conventionally allocate these
+ * numbers to correspond to those used by 'real' linux -- this is just
+ * for convenience as it means e.g. that the same /etc/fstab can be
+ * used when booting with or without Xen.
+ */
+int xlvbd_init(void)
+{
+ int i, nr;
+ vdisk_t *disks;
+
+ INIT_LIST_HEAD(&vbds_list);
+
+ memset(major_info, 0, sizeof(major_info));
+
+ disks = xlvbd_probe(&nr);
+ if (disks == NULL) {
+ WPRINTK("failed to probe\n");
+ return -1;
+ }
+
+ for (i = 0; i < nr; i++)
+ xlvbd_device_add(&vbds_list, &disks[i]);
+
+ kfree(disks);
+ return 0;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/apic.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/apic.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,200 @@
+/*
+ * Local APIC handling, local APIC timers
+ *
+ * (c) 1999, 2000 Ingo Molnar <mingo@xxxxxxxxxx>
+ *
+ * Fixes
+ * Maciej W. Rozycki : Bits for genuine 82489DX APICs;
+ * thanks to Eric Gilmore
+ * and Rolf G. Tews
+ * for testing these extensively.
+ * Maciej W. Rozycki : Various updates and fixes.
+ * Mikael Pettersson : Power Management for UP-APIC.
+ * Pavel Machek and
+ * Mikael Pettersson : PM converted to driver model.
+ */
+
+#include <linux/config.h>
+#include <linux/init.h>
+
+#include <linux/mm.h>
+#include <linux/irq.h>
+#include <linux/delay.h>
+#include <linux/bootmem.h>
+#include <linux/smp_lock.h>
+#include <linux/interrupt.h>
+#include <linux/mc146818rtc.h>
+#include <linux/kernel_stat.h>
+#include <linux/sysdev.h>
+
+#include <asm/atomic.h>
+#include <asm/smp.h>
+#include <asm/mtrr.h>
+#include <asm/mpspec.h>
+#include <asm/desc.h>
+#include <asm/arch_hooks.h>
+#include <asm/hpet.h>
+
+#include "io_ports.h"
+
+/*
+ * Debug level
+ */
+int apic_verbosity;
+int disable_apic;
+
+void smp_local_timer_interrupt(struct pt_regs *regs)
+{
+ int cpu = smp_processor_id();
+
+ profile_tick(CPU_PROFILING, regs);
+#if 0
+ if (--per_cpu(prof_counter, cpu) <= 0) {
+ /*
+ * The multiplier may have changed since the last time we got
+ * to this point as a result of the user writing to
+ * /proc/profile. In this case we need to adjust the APIC
+ * timer accordingly.
+ *
+ * Interrupts are already masked off at this point.
+ */
+ per_cpu(prof_counter, cpu) = per_cpu(prof_multiplier, cpu);
+ if (per_cpu(prof_counter, cpu) !=
+ per_cpu(prof_old_multiplier, cpu)) {
+ __setup_APIC_LVTT(calibration_result/
+ per_cpu(prof_counter, cpu));
+ per_cpu(prof_old_multiplier, cpu) =
+ per_cpu(prof_counter, cpu);
+ }
+
+#ifdef CONFIG_SMP
+ update_process_times(user_mode(regs));
+#endif
+ }
+#endif
+
+ /*
+ * We take the 'long' return path, and there every subsystem
+ * grabs the appropriate locks (kernel lock/ irq lock).
+ *
+ * we might want to decouple profiling from the 'long path',
+ * and do the profiling totally in assembly.
+ *
+ * Currently this isn't too much of an issue (performance wise),
+ * we can take more than 100K local irqs per second on a 100 MHz P5.
+ */
+}
+
+/*
+ * Local APIC timer interrupt. This is the most natural way for doing
+ * local interrupts, but local timer interrupts can be emulated by
+ * broadcast interrupts too. [in case the hw doesn't support APIC timers]
+ *
+ * [ if a single-CPU system runs an SMP kernel then we call the local
+ * interrupt as well. Thus we cannot inline the local irq ... ]
+ */
+void smp_apic_timer_interrupt(struct pt_regs *regs)
+{
+ /*
+ * the NMI deadlock-detector uses this.
+ */
+ add_pda(apic_timer_irqs, 1);
+
+ /*
+ * NOTE! We'd better ACK the irq immediately,
+ * because timer handling can be slow.
+ */
+ ack_APIC_irq();
+ /*
+ * update_process_times() expects us to have done irq_enter().
+ * Besides, if we don't timer interrupts ignore the global
+ * interrupt lock, which is the WrongThing (tm) to do.
+ */
+ irq_enter();
+ smp_local_timer_interrupt(regs);
+ irq_exit();
+}
+
+/*
+ * This interrupt should _never_ happen with our APIC/SMP architecture
+ */
+asmlinkage void smp_spurious_interrupt(void)
+{
+ unsigned int v;
+ irq_enter();
+ /*
+ * Check if this really is a spurious interrupt and ACK it
+ * if it is a vectored one. Just in case...
+ * Spurious interrupts should not be ACKed.
+ */
+ v = apic_read(APIC_ISR + ((SPURIOUS_APIC_VECTOR & ~0x1f) >> 1));
+ if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f)))
+ ack_APIC_irq();
+
+#if 0
+ static unsigned long last_warning;
+ static unsigned long skipped;
+
+ /* see sw-dev-man vol 3, chapter 7.4.13.5 */
+ if (time_before(last_warning+30*HZ,jiffies)) {
+ printk(KERN_INFO "spurious APIC interrupt on CPU#%d, %ld
skipped.\n",
+ smp_processor_id(), skipped);
+ last_warning = jiffies;
+ skipped = 0;
+ } else {
+ skipped++;
+ }
+#endif
+ irq_exit();
+}
+
+/*
+ * This interrupt should never happen with our APIC/SMP architecture
+ */
+
+asmlinkage void smp_error_interrupt(void)
+{
+ unsigned int v, v1;
+
+ irq_enter();
+ /* First tickle the hardware, only then report what went on. -- REW */
+ v = apic_read(APIC_ESR);
+ apic_write(APIC_ESR, 0);
+ v1 = apic_read(APIC_ESR);
+ ack_APIC_irq();
+ atomic_inc(&irq_err_count);
+
+ /* Here is what the APIC error bits mean:
+ 0: Send CS error
+ 1: Receive CS error
+ 2: Send accept error
+ 3: Receive accept error
+ 4: Reserved
+ 5: Send illegal vector
+ 6: Received illegal vector
+ 7: Illegal register address
+ */
+ printk (KERN_DEBUG "APIC error on CPU%d: %02x(%02x)\n",
+ smp_processor_id(), v , v1);
+ irq_exit();
+}
+
+int get_physical_broadcast(void)
+{
+ return 0xff;
+}
+
+/*
+ * This initializes the IO-APIC and APIC hardware if this is
+ * a UP kernel.
+ */
+int __init APIC_init_uniprocessor (void)
+{
+#ifdef CONFIG_X86_IO_APIC
+ if (smp_found_config)
+ if (!skip_ioapic_setup && nr_ioapics)
+ setup_IO_APIC();
+#endif
+
+ return 0;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/defconfig-xen0
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/defconfig-xen0 Fri Jul 15 13:39:50 2005
@@ -0,0 +1,927 @@
+#
+# Automatically generated by make menuconfig: don't edit
+#
+CONFIG_XEN=y
+CONFIG_X86=y
+CONFIG_ISA=y
+# CONFIG_SBUS is not set
+CONFIG_UID16=y
+
+#
+# Xen
+#
+CONFIG_XEN_PRIVILEGED_GUEST=y
+CONFIG_XEN_PHYSDEV_ACCESS=y
+# CONFIG_XEN_USB_BACKEND is not set
+CONFIG_XEN_SCRUB_PAGES=y
+CONFIG_XEN_NETDEV_FRONTEND=y
+CONFIG_XEN_BLKDEV_FRONTEND=y
+CONFIG_XEN_BLKDEV_GRANT=y
+# CONFIG_XEN_USB_FRONTEND is not set
+CONFIG_NO_IDLE_HZ=y
+CONFIG_FOREIGN_PAGES=y
+
+#
+# Code maturity level options
+#
+CONFIG_EXPERIMENTAL=y
+
+#
+# Loadable module support
+#
+CONFIG_MODULES=y
+CONFIG_MODVERSIONS=y
+CONFIG_KMOD=y
+
+#
+# Processor type and features
+#
+CONFIG_M686=y
+# CONFIG_MPENTIUMIII is not set
+# CONFIG_MPENTIUM4 is not set
+# CONFIG_MK7 is not set
+# CONFIG_MK8 is not set
+# CONFIG_MVIAC3_2 is not set
+CONFIG_X86_WP_WORKS_OK=y
+CONFIG_X86_INVLPG=y
+CONFIG_X86_CMPXCHG=y
+CONFIG_X86_XADD=y
+CONFIG_X86_BSWAP=y
+CONFIG_X86_POPAD_OK=y
+# CONFIG_RWSEM_GENERIC_SPINLOCK is not set
+CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+CONFIG_X86_GOOD_APIC=y
+CONFIG_X86_PGE=y
+CONFIG_X86_USE_PPRO_CHECKSUM=y
+CONFIG_X86_TSC=y
+CONFIG_X86_L1_CACHE_SHIFT=5
+CONFIG_NOHIGHMEM=y
+# CONFIG_HIGHMEM4G is not set
+CONFIG_FORCE_MAX_ZONEORDER=11
+
+#
+# General setup
+#
+CONFIG_NET=y
+CONFIG_PCI=y
+CONFIG_PCI_NAMES=y
+CONFIG_HOTPLUG=y
+
+#
+# PCMCIA/CardBus support
+#
+# CONFIG_PCMCIA is not set
+
+#
+# PCI Hotplug Support
+#
+# CONFIG_HOTPLUG_PCI is not set
+# CONFIG_HOTPLUG_PCI_COMPAQ is not set
+# CONFIG_HOTPLUG_PCI_COMPAQ_NVRAM is not set
+# CONFIG_HOTPLUG_PCI_SHPC is not set
+# CONFIG_HOTPLUG_PCI_SHPC_POLL_EVENT_MODE is not set
+# CONFIG_HOTPLUG_PCI_PCIE is not set
+# CONFIG_HOTPLUG_PCI_PCIE_POLL_EVENT_MODE is not set
+CONFIG_SYSVIPC=y
+# CONFIG_BSD_PROCESS_ACCT is not set
+CONFIG_SYSCTL=y
+CONFIG_KCORE_ELF=y
+# CONFIG_KCORE_AOUT is not set
+CONFIG_BINFMT_AOUT=y
+CONFIG_BINFMT_ELF=y
+# CONFIG_BINFMT_MISC is not set
+# CONFIG_OOM_KILLER is not set
+
+#
+# Memory Technology Devices (MTD)
+#
+# CONFIG_MTD is not set
+
+#
+# Parallel port support
+#
+# CONFIG_PARPORT is not set
+
+#
+# Plug and Play configuration
+#
+CONFIG_PNP=y
+# CONFIG_ISAPNP is not set
+
+#
+# Block devices
+#
+# CONFIG_BLK_DEV_FD is not set
+# CONFIG_BLK_DEV_XD is not set
+# CONFIG_PARIDE is not set
+# CONFIG_BLK_CPQ_DA is not set
+# CONFIG_BLK_CPQ_CISS_DA is not set
+# CONFIG_CISS_SCSI_TAPE is not set
+# CONFIG_CISS_MONITOR_THREAD is not set
+# CONFIG_BLK_DEV_DAC960 is not set
+# CONFIG_BLK_DEV_UMEM is not set
+# CONFIG_BLK_DEV_SX8 is not set
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_NBD=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=4096
+CONFIG_BLK_DEV_INITRD=y
+# CONFIG_BLK_STATS is not set
+
+#
+# Multi-device support (RAID and LVM)
+#
+CONFIG_MD=y
+CONFIG_BLK_DEV_MD=y
+CONFIG_MD_LINEAR=y
+# CONFIG_MD_RAID0 is not set
+CONFIG_MD_RAID1=y
+# CONFIG_MD_RAID5 is not set
+# CONFIG_MD_MULTIPATH is not set
+CONFIG_BLK_DEV_LVM=y
+
+#
+# Networking options
+#
+CONFIG_PACKET=y
+CONFIG_PACKET_MMAP=y
+# CONFIG_NETLINK_DEV is not set
+CONFIG_NETFILTER=y
+# CONFIG_NETFILTER_DEBUG is not set
+CONFIG_FILTER=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+# CONFIG_IP_MULTICAST is not set
+# CONFIG_IP_ADVANCED_ROUTER is not set
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+# CONFIG_IP_PNP_BOOTP is not set
+# CONFIG_IP_PNP_RARP is not set
+# CONFIG_NET_IPIP is not set
+# CONFIG_NET_IPGRE is not set
+# CONFIG_ARPD is not set
+# CONFIG_INET_ECN is not set
+# CONFIG_SYN_COOKIES is not set
+
+#
+# IP: Netfilter Configuration
+#
+CONFIG_IP_NF_CONNTRACK=m
+CONFIG_IP_NF_FTP=m
+# CONFIG_IP_NF_AMANDA is not set
+CONFIG_IP_NF_TFTP=m
+CONFIG_IP_NF_IRC=m
+# CONFIG_IP_NF_QUEUE is not set
+CONFIG_IP_NF_IPTABLES=y
+# CONFIG_IP_NF_MATCH_LIMIT is not set
+# CONFIG_IP_NF_MATCH_MAC is not set
+# CONFIG_IP_NF_MATCH_PKTTYPE is not set
+# CONFIG_IP_NF_MATCH_MARK is not set
+# CONFIG_IP_NF_MATCH_MULTIPORT is not set
+# CONFIG_IP_NF_MATCH_TOS is not set
+# CONFIG_IP_NF_MATCH_RECENT is not set
+# CONFIG_IP_NF_MATCH_ECN is not set
+# CONFIG_IP_NF_MATCH_DSCP is not set
+# CONFIG_IP_NF_MATCH_AH_ESP is not set
+# CONFIG_IP_NF_MATCH_LENGTH is not set
+# CONFIG_IP_NF_MATCH_TTL is not set
+# CONFIG_IP_NF_MATCH_TCPMSS is not set
+# CONFIG_IP_NF_MATCH_HELPER is not set
+CONFIG_IP_NF_MATCH_STATE=m
+CONFIG_IP_NF_MATCH_CONNTRACK=m
+# CONFIG_IP_NF_MATCH_UNCLEAN is not set
+# CONFIG_IP_NF_MATCH_OWNER is not set
+CONFIG_IP_NF_MATCH_PHYSDEV=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+# CONFIG_IP_NF_TARGET_MIRROR is not set
+CONFIG_IP_NF_NAT=m
+CONFIG_IP_NF_NAT_NEEDED=y
+CONFIG_IP_NF_TARGET_MASQUERADE=m
+CONFIG_IP_NF_TARGET_REDIRECT=m
+# CONFIG_IP_NF_NAT_SNMP_BASIC is not set
+CONFIG_IP_NF_NAT_IRC=m
+CONFIG_IP_NF_NAT_FTP=m
+CONFIG_IP_NF_NAT_TFTP=m
+# CONFIG_IP_NF_MANGLE is not set
+CONFIG_IP_NF_TARGET_LOG=y
+CONFIG_IP_NF_TARGET_ULOG=y
+# CONFIG_IP_NF_TARGET_TCPMSS is not set
+# CONFIG_IP_NF_ARPTABLES is not set
+
+#
+# IP: Virtual Server Configuration
+#
+# CONFIG_IP_VS is not set
+# CONFIG_IPV6 is not set
+# CONFIG_KHTTPD is not set
+
+#
+# SCTP Configuration (EXPERIMENTAL)
+#
+# CONFIG_IP_SCTP is not set
+# CONFIG_ATM is not set
+CONFIG_VLAN_8021Q=y
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+# CONFIG_DECNET is not set
+CONFIG_BRIDGE=y
+CONFIG_BRIDGE_NF_EBTABLES=m
+CONFIG_BRIDGE_EBT_T_FILTER=m
+CONFIG_BRIDGE_EBT_T_NAT=m
+CONFIG_BRIDGE_EBT_BROUTE=m
+CONFIG_BRIDGE_EBT_LOG=m
+CONFIG_BRIDGE_EBT_IPF=m
+CONFIG_BRIDGE_EBT_ARPF=m
+CONFIG_BRIDGE_EBT_AMONG=m
+CONFIG_BRIDGE_EBT_LIMIT=m
+CONFIG_BRIDGE_EBT_VLANF=m
+CONFIG_BRIDGE_EBT_802_3=m
+CONFIG_BRIDGE_EBT_PKTTYPE=m
+CONFIG_BRIDGE_EBT_STP=m
+CONFIG_BRIDGE_EBT_MARKF=m
+CONFIG_BRIDGE_EBT_ARPREPLY=m
+CONFIG_BRIDGE_EBT_SNAT=m
+CONFIG_BRIDGE_EBT_DNAT=m
+CONFIG_BRIDGE_EBT_REDIRECT=m
+CONFIG_BRIDGE_EBT_MARK_T=m
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+# CONFIG_LLC is not set
+# CONFIG_NET_DIVERT is not set
+# CONFIG_ECONET is not set
+# CONFIG_WAN_ROUTER is not set
+# CONFIG_NET_FASTROUTE is not set
+# CONFIG_NET_HW_FLOWCONTROL is not set
+
+#
+# QoS and/or fair queueing
+#
+# CONFIG_NET_SCHED is not set
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+
+#
+# ATA/IDE/MFM/RLL support
+#
+CONFIG_IDE=y
+
+#
+# IDE, ATA and ATAPI Block devices
+#
+CONFIG_BLK_DEV_IDE=y
+# CONFIG_BLK_DEV_HD_IDE is not set
+# CONFIG_BLK_DEV_HD is not set
+# CONFIG_BLK_DEV_IDE_SATA is not set
+CONFIG_BLK_DEV_IDEDISK=y
+CONFIG_IDEDISK_MULTI_MODE=y
+CONFIG_IDEDISK_STROKE=y
+# CONFIG_BLK_DEV_IDECS is not set
+# CONFIG_BLK_DEV_DELKIN is not set
+CONFIG_BLK_DEV_IDECD=y
+CONFIG_BLK_DEV_IDETAPE=y
+CONFIG_BLK_DEV_IDEFLOPPY=y
+CONFIG_BLK_DEV_IDESCSI=y
+CONFIG_IDE_TASK_IOCTL=y
+CONFIG_BLK_DEV_CMD640=y
+CONFIG_BLK_DEV_CMD640_ENHANCED=y
+# CONFIG_BLK_DEV_ISAPNP is not set
+CONFIG_BLK_DEV_IDEPCI=y
+CONFIG_BLK_DEV_GENERIC=y
+CONFIG_IDEPCI_SHARE_IRQ=y
+CONFIG_BLK_DEV_IDEDMA_PCI=y
+CONFIG_BLK_DEV_OFFBOARD=y
+# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
+CONFIG_IDEDMA_PCI_AUTO=y
+# CONFIG_IDEDMA_ONLYDISK is not set
+CONFIG_BLK_DEV_IDEDMA=y
+# CONFIG_IDEDMA_PCI_WIP is not set
+CONFIG_BLK_DEV_ADMA100=y
+CONFIG_BLK_DEV_AEC62XX=y
+CONFIG_BLK_DEV_ALI15X3=y
+CONFIG_WDC_ALI15X3=y
+CONFIG_BLK_DEV_AMD74XX=y
+CONFIG_AMD74XX_OVERRIDE=y
+# CONFIG_BLK_DEV_ATIIXP is not set
+CONFIG_BLK_DEV_CMD64X=y
+CONFIG_BLK_DEV_TRIFLEX=y
+CONFIG_BLK_DEV_CY82C693=y
+CONFIG_BLK_DEV_CS5530=y
+CONFIG_BLK_DEV_HPT34X=y
+# CONFIG_HPT34X_AUTODMA is not set
+CONFIG_BLK_DEV_HPT366=y
+CONFIG_BLK_DEV_PIIX=y
+CONFIG_BLK_DEV_NS87415=y
+# CONFIG_BLK_DEV_OPTI621 is not set
+CONFIG_BLK_DEV_PDC202XX_OLD=y
+CONFIG_PDC202XX_BURST=y
+CONFIG_BLK_DEV_PDC202XX_NEW=y
+CONFIG_PDC202XX_FORCE=y
+CONFIG_BLK_DEV_RZ1000=y
+CONFIG_BLK_DEV_SC1200=y
+CONFIG_BLK_DEV_SVWKS=y
+CONFIG_BLK_DEV_SIIMAGE=y
+CONFIG_BLK_DEV_SIS5513=y
+CONFIG_BLK_DEV_SLC90E66=y
+CONFIG_BLK_DEV_TRM290=y
+CONFIG_BLK_DEV_VIA82CXXX=y
+CONFIG_IDE_CHIPSETS=y
+# CONFIG_BLK_DEV_4DRIVES is not set
+# CONFIG_BLK_DEV_ALI14XX is not set
+# CONFIG_BLK_DEV_DTC2278 is not set
+# CONFIG_BLK_DEV_HT6560B is not set
+# CONFIG_BLK_DEV_PDC4030 is not set
+# CONFIG_BLK_DEV_QD65XX is not set
+# CONFIG_BLK_DEV_UMC8672 is not set
+CONFIG_IDEDMA_AUTO=y
+# CONFIG_IDEDMA_IVB is not set
+# CONFIG_DMA_NONPCI is not set
+CONFIG_BLK_DEV_PDC202XX=y
+# CONFIG_BLK_DEV_ATARAID is not set
+# CONFIG_BLK_DEV_ATARAID_PDC is not set
+# CONFIG_BLK_DEV_ATARAID_HPT is not set
+# CONFIG_BLK_DEV_ATARAID_MEDLEY is not set
+# CONFIG_BLK_DEV_ATARAID_SII is not set
+
+#
+# SCSI support
+#
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_SD_EXTRA_DEVS=40
+# CONFIG_CHR_DEV_ST is not set
+# CONFIG_CHR_DEV_OSST is not set
+# CONFIG_BLK_DEV_SR is not set
+CONFIG_CHR_DEV_SG=y
+# CONFIG_SCSI_DEBUG_QUEUES is not set
+# CONFIG_SCSI_MULTI_LUN is not set
+# CONFIG_SCSI_CONSTANTS is not set
+# CONFIG_SCSI_LOGGING is not set
+
+#
+# SCSI low-level drivers
+#
+# CONFIG_BLK_DEV_3W_XXXX_RAID is not set
+# CONFIG_SCSI_7000FASST is not set
+# CONFIG_SCSI_ACARD is not set
+# CONFIG_SCSI_AHA152X is not set
+# CONFIG_SCSI_AHA1542 is not set
+# CONFIG_SCSI_AHA1740 is not set
+CONFIG_SCSI_AACRAID=y
+CONFIG_SCSI_AIC7XXX=y
+CONFIG_AIC7XXX_CMDS_PER_DEVICE=32
+CONFIG_AIC7XXX_RESET_DELAY_MS=15000
+# CONFIG_AIC7XXX_PROBE_EISA_VL is not set
+# CONFIG_AIC7XXX_BUILD_FIRMWARE is not set
+# CONFIG_AIC7XXX_DEBUG_ENABLE is not set
+CONFIG_AIC7XXX_DEBUG_MASK=0
+# CONFIG_AIC7XXX_REG_PRETTY_PRINT is not set
+CONFIG_SCSI_AIC79XX=y
+CONFIG_AIC79XX_CMDS_PER_DEVICE=32
+CONFIG_AIC79XX_RESET_DELAY_MS=15000
+# CONFIG_AIC79XX_BUILD_FIRMWARE is not set
+# CONFIG_AIC79XX_ENABLE_RD_STRM is not set
+# CONFIG_AIC79XX_DEBUG_ENABLE is not set
+CONFIG_AIC79XX_DEBUG_MASK=0
+# CONFIG_AIC79XX_REG_PRETTY_PRINT is not set
+# CONFIG_SCSI_DPT_I2O is not set
+# CONFIG_SCSI_ADVANSYS is not set
+# CONFIG_SCSI_IN2000 is not set
+# CONFIG_SCSI_AM53C974 is not set
+CONFIG_SCSI_MEGARAID=y
+# CONFIG_SCSI_MEGARAID2 is not set
+CONFIG_SCSI_SATA=y
+# CONFIG_SCSI_SATA_AHCI is not set
+# CONFIG_SCSI_SATA_SVW is not set
+CONFIG_SCSI_ATA_PIIX=y
+# CONFIG_SCSI_SATA_NV is not set
+# CONFIG_SCSI_SATA_QSTOR is not set
+CONFIG_SCSI_SATA_PROMISE=y
+CONFIG_SCSI_SATA_SX4=y
+CONFIG_SCSI_SATA_SIL=y
+CONFIG_SCSI_SATA_SIS=y
+# CONFIG_SCSI_SATA_ULI is not set
+CONFIG_SCSI_SATA_VIA=y
+CONFIG_SCSI_SATA_VITESSE=y
+CONFIG_SCSI_BUSLOGIC=y
+# CONFIG_SCSI_OMIT_FLASHPOINT is not set
+# CONFIG_SCSI_CPQFCTS is not set
+# CONFIG_SCSI_DMX3191D is not set
+# CONFIG_SCSI_DTC3280 is not set
+# CONFIG_SCSI_EATA is not set
+# CONFIG_SCSI_EATA_DMA is not set
+# CONFIG_SCSI_EATA_PIO is not set
+# CONFIG_SCSI_FUTURE_DOMAIN is not set
+# CONFIG_SCSI_GDTH is not set
+# CONFIG_SCSI_GENERIC_NCR5380 is not set
+# CONFIG_SCSI_IPS is not set
+# CONFIG_SCSI_INITIO is not set
+# CONFIG_SCSI_INIA100 is not set
+# CONFIG_SCSI_NCR53C406A is not set
+# CONFIG_SCSI_NCR53C7xx is not set
+CONFIG_SCSI_SYM53C8XX_2=y
+CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=1
+CONFIG_SCSI_SYM53C8XX_DEFAULT_TAGS=16
+CONFIG_SCSI_SYM53C8XX_MAX_TAGS=64
+# CONFIG_SCSI_SYM53C8XX_IOMAPPED is not set
+# CONFIG_SCSI_PAS16 is not set
+# CONFIG_SCSI_PCI2000 is not set
+# CONFIG_SCSI_PCI2220I is not set
+# CONFIG_SCSI_PSI240I is not set
+# CONFIG_SCSI_QLOGIC_FAS is not set
+# CONFIG_SCSI_QLOGIC_ISP is not set
+# CONFIG_SCSI_QLOGIC_FC is not set
+# CONFIG_SCSI_QLOGIC_1280 is not set
+# CONFIG_SCSI_SEAGATE is not set
+# CONFIG_SCSI_SIM710 is not set
+# CONFIG_SCSI_SYM53C416 is not set
+# CONFIG_SCSI_DC390T is not set
+# CONFIG_SCSI_T128 is not set
+# CONFIG_SCSI_U14_34F is not set
+# CONFIG_SCSI_ULTRASTOR is not set
+# CONFIG_SCSI_NSP32 is not set
+# CONFIG_SCSI_DEBUG is not set
+
+#
+# Fusion MPT device support
+#
+# CONFIG_FUSION is not set
+# CONFIG_FUSION_BOOT is not set
+# CONFIG_FUSION_ISENSE is not set
+# CONFIG_FUSION_CTL is not set
+# CONFIG_FUSION_LAN is not set
+
+#
+# IEEE 1394 (FireWire) support (EXPERIMENTAL)
+#
+# CONFIG_IEEE1394 is not set
+
+#
+# I2O device support
+#
+# CONFIG_I2O is not set
+# CONFIG_I2O_PCI is not set
+# CONFIG_I2O_BLOCK is not set
+# CONFIG_I2O_LAN is not set
+# CONFIG_I2O_SCSI is not set
+# CONFIG_I2O_PROC is not set
+
+#
+# Network device support
+#
+CONFIG_NETDEVICES=y
+
+#
+# ARCnet devices
+#
+# CONFIG_ARCNET is not set
+# CONFIG_DUMMY is not set
+# CONFIG_BONDING is not set
+# CONFIG_EQUALIZER is not set
+# CONFIG_TUN is not set
+# CONFIG_ETHERTAP is not set
+
+#
+# Ethernet (10 or 100Mbit)
+#
+CONFIG_NET_ETHERNET=y
+# CONFIG_SUNLANCE is not set
+# CONFIG_HAPPYMEAL is not set
+# CONFIG_SUNBMAC is not set
+# CONFIG_SUNQE is not set
+# CONFIG_SUNGEM is not set
+CONFIG_NET_VENDOR_3COM=y
+# CONFIG_EL1 is not set
+# CONFIG_EL2 is not set
+# CONFIG_ELPLUS is not set
+# CONFIG_EL16 is not set
+# CONFIG_EL3 is not set
+# CONFIG_3C515 is not set
+# CONFIG_ELMC is not set
+# CONFIG_ELMC_II is not set
+CONFIG_VORTEX=y
+# CONFIG_TYPHOON is not set
+# CONFIG_LANCE is not set
+# CONFIG_NET_VENDOR_SMC is not set
+# CONFIG_NET_VENDOR_RACAL is not set
+# CONFIG_AT1700 is not set
+# CONFIG_DEPCA is not set
+# CONFIG_HP100 is not set
+# CONFIG_NET_ISA is not set
+CONFIG_NET_PCI=y
+CONFIG_PCNET32=y
+# CONFIG_AMD8111_ETH is not set
+# CONFIG_ADAPTEC_STARFIRE is not set
+# CONFIG_AC3200 is not set
+# CONFIG_APRICOT is not set
+# CONFIG_B44 is not set
+# CONFIG_CS89x0 is not set
+# CONFIG_TULIP is not set
+# CONFIG_DE4X5 is not set
+# CONFIG_DGRS is not set
+# CONFIG_DM9102 is not set
+# CONFIG_EEPRO100 is not set
+# CONFIG_EEPRO100_PIO is not set
+CONFIG_E100=y
+# CONFIG_LNE390 is not set
+# CONFIG_FEALNX is not set
+# CONFIG_NATSEMI is not set
+CONFIG_NE2K_PCI=y
+# CONFIG_FORCEDETH is not set
+# CONFIG_NE3210 is not set
+# CONFIG_ES3210 is not set
+# CONFIG_8139CP is not set
+# CONFIG_8139TOO is not set
+# CONFIG_8139TOO_PIO is not set
+# CONFIG_8139TOO_TUNE_TWISTER is not set
+# CONFIG_8139TOO_8129 is not set
+# CONFIG_8139_OLD_RX_RESET is not set
+# CONFIG_SIS900 is not set
+# CONFIG_EPIC100 is not set
+# CONFIG_SUNDANCE is not set
+# CONFIG_SUNDANCE_MMIO is not set
+# CONFIG_TLAN is not set
+# CONFIG_VIA_RHINE is not set
+# CONFIG_VIA_RHINE_MMIO is not set
+# CONFIG_WINBOND_840 is not set
+# CONFIG_NET_POCKET is not set
+
+#
+# Ethernet (1000 Mbit)
+#
+# CONFIG_ACENIC is not set
+# CONFIG_DL2K is not set
+CONFIG_E1000=y
+# CONFIG_E1000_NAPI is not set
+# CONFIG_MYRI_SBUS is not set
+# CONFIG_NS83820 is not set
+# CONFIG_HAMACHI is not set
+# CONFIG_YELLOWFIN is not set
+# CONFIG_R8169 is not set
+# CONFIG_SK98LIN is not set
+CONFIG_TIGON3=y
+# CONFIG_FDDI is not set
+# CONFIG_HIPPI is not set
+# CONFIG_PLIP is not set
+# CONFIG_PPP is not set
+# CONFIG_SLIP is not set
+
+#
+# Wireless LAN (non-hamradio)
+#
+# CONFIG_NET_RADIO is not set
+
+#
+# Token Ring devices
+#
+# CONFIG_TR is not set
+# CONFIG_NET_FC is not set
+# CONFIG_RCPCI is not set
+# CONFIG_SHAPER is not set
+
+#
+# Wan interfaces
+#
+# CONFIG_WAN is not set
+
+#
+# Amateur Radio support
+#
+# CONFIG_HAMRADIO is not set
+
+#
+# IrDA (infrared) support
+#
+# CONFIG_IRDA is not set
+
+#
+# ISDN subsystem
+#
+# CONFIG_ISDN is not set
+
+#
+# Old CD-ROM drivers (not SCSI, not IDE)
+#
+# CONFIG_CD_NO_IDESCSI is not set
+
+#
+# Input core support
+#
+# CONFIG_INPUT is not set
+# CONFIG_INPUT_KEYBDEV is not set
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_INPUT_JOYDEV is not set
+# CONFIG_INPUT_EVDEV is not set
+# CONFIG_INPUT_UINPUT is not set
+
+#
+# Character devices
+#
+CONFIG_VT=y
+CONFIG_VT_CONSOLE=y
+# CONFIG_SERIAL is not set
+# CONFIG_SERIAL_EXTENDED is not set
+# CONFIG_SERIAL_NONSTANDARD is not set
+CONFIG_UNIX98_PTYS=y
+CONFIG_UNIX98_PTY_COUNT=256
+
+#
+# I2C support
+#
+# CONFIG_I2C is not set
+
+#
+# Mice
+#
+# CONFIG_BUSMOUSE is not set
+CONFIG_MOUSE=y
+CONFIG_PSMOUSE=y
+# CONFIG_82C710_MOUSE is not set
+# CONFIG_PC110_PAD is not set
+# CONFIG_MK712_MOUSE is not set
+
+#
+# Joysticks
+#
+# CONFIG_INPUT_GAMEPORT is not set
+# CONFIG_QIC02_TAPE is not set
+# CONFIG_IPMI_HANDLER is not set
+# CONFIG_IPMI_PANIC_EVENT is not set
+# CONFIG_IPMI_DEVICE_INTERFACE is not set
+# CONFIG_IPMI_KCS is not set
+# CONFIG_IPMI_WATCHDOG is not set
+
+#
+# Watchdog Cards
+#
+# CONFIG_WATCHDOG is not set
+# CONFIG_SCx200 is not set
+# CONFIG_SCx200_GPIO is not set
+# CONFIG_AMD_RNG is not set
+# CONFIG_INTEL_RNG is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_AMD_PM768 is not set
+# CONFIG_NVRAM is not set
+# CONFIG_RTC is not set
+# CONFIG_DTLK is not set
+# CONFIG_R3964 is not set
+# CONFIG_APPLICOM is not set
+# CONFIG_SONYPI is not set
+
+#
+# Ftape, the floppy tape device driver
+#
+# CONFIG_FTAPE is not set
+# CONFIG_AGP is not set
+
+#
+# Direct Rendering Manager (XFree86 DRI support)
+#
+# CONFIG_DRM is not set
+# CONFIG_MWAVE is not set
+# CONFIG_OBMOUSE is not set
+
+#
+# Multimedia devices
+#
+# CONFIG_VIDEO_DEV is not set
+
+#
+# File systems
+#
+# CONFIG_QUOTA is not set
+# CONFIG_QFMT_V2 is not set
+CONFIG_AUTOFS_FS=y
+CONFIG_AUTOFS4_FS=y
+# CONFIG_REISERFS_FS is not set
+# CONFIG_REISERFS_CHECK is not set
+# CONFIG_REISERFS_PROC_INFO is not set
+# CONFIG_ADFS_FS is not set
+# CONFIG_ADFS_FS_RW is not set
+# CONFIG_AFFS_FS is not set
+# CONFIG_HFS_FS is not set
+# CONFIG_HFSPLUS_FS is not set
+# CONFIG_BEFS_FS is not set
+# CONFIG_BEFS_DEBUG is not set
+# CONFIG_BFS_FS is not set
+CONFIG_EXT3_FS=y
+CONFIG_JBD=y
+# CONFIG_JBD_DEBUG is not set
+CONFIG_FAT_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_UMSDOS_FS=y
+CONFIG_VFAT_FS=y
+# CONFIG_EFS_FS is not set
+# CONFIG_JFFS_FS is not set
+# CONFIG_JFFS2_FS is not set
+# CONFIG_CRAMFS is not set
+CONFIG_TMPFS=y
+CONFIG_RAMFS=y
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+# CONFIG_JFS_FS is not set
+# CONFIG_JFS_DEBUG is not set
+# CONFIG_JFS_STATISTICS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_NTFS_FS is not set
+# CONFIG_NTFS_RW is not set
+# CONFIG_HPFS_FS is not set
+CONFIG_PROC_FS=y
+# CONFIG_DEVFS_FS is not set
+# CONFIG_DEVFS_MOUNT is not set
+# CONFIG_DEVFS_DEBUG is not set
+CONFIG_DEVPTS_FS=y
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_QNX4FS_RW is not set
+# CONFIG_ROMFS_FS is not set
+CONFIG_EXT2_FS=y
+# CONFIG_SYSV_FS is not set
+# CONFIG_UDF_FS is not set
+# CONFIG_UDF_RW is not set
+# CONFIG_UFS_FS is not set
+# CONFIG_UFS_FS_WRITE is not set
+# CONFIG_XFS_FS is not set
+# CONFIG_XFS_QUOTA is not set
+# CONFIG_XFS_RT is not set
+# CONFIG_XFS_TRACE is not set
+# CONFIG_XFS_DEBUG is not set
+
+#
+# Network File Systems
+#
+# CONFIG_CODA_FS is not set
+# CONFIG_INTERMEZZO_FS is not set
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+# CONFIG_NFS_DIRECTIO is not set
+CONFIG_ROOT_NFS=y
+CONFIG_NFSD=y
+CONFIG_NFSD_V3=y
+# CONFIG_NFSD_TCP is not set
+CONFIG_SUNRPC=y
+CONFIG_LOCKD=y
+CONFIG_LOCKD_V4=y
+# CONFIG_SMB_FS is not set
+# CONFIG_NCP_FS is not set
+# CONFIG_NCPFS_PACKET_SIGNING is not set
+# CONFIG_NCPFS_IOCTL_LOCKING is not set
+# CONFIG_NCPFS_STRONG is not set
+# CONFIG_NCPFS_NFS_NS is not set
+# CONFIG_NCPFS_OS2_NS is not set
+# CONFIG_NCPFS_SMALLDOS is not set
+# CONFIG_NCPFS_NLS is not set
+# CONFIG_NCPFS_EXTRAS is not set
+CONFIG_ZISOFS_FS=y
+
+#
+# Partition Types
+#
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_ACORN_PARTITION is not set
+# CONFIG_OSF_PARTITION is not set
+# CONFIG_AMIGA_PARTITION is not set
+# CONFIG_ATARI_PARTITION is not set
+# CONFIG_MAC_PARTITION is not set
+CONFIG_MSDOS_PARTITION=y
+# CONFIG_BSD_DISKLABEL is not set
+# CONFIG_MINIX_SUBPARTITION is not set
+# CONFIG_SOLARIS_X86_PARTITION is not set
+# CONFIG_UNIXWARE_DISKLABEL is not set
+# CONFIG_LDM_PARTITION is not set
+# CONFIG_SGI_PARTITION is not set
+# CONFIG_ULTRIX_PARTITION is not set
+# CONFIG_SUN_PARTITION is not set
+# CONFIG_EFI_PARTITION is not set
+# CONFIG_SMB_NLS is not set
+CONFIG_NLS=y
+
+#
+# Native Language Support
+#
+CONFIG_NLS_DEFAULT="iso8559-1"
+# CONFIG_NLS_CODEPAGE_437 is not set
+# CONFIG_NLS_CODEPAGE_737 is not set
+# CONFIG_NLS_CODEPAGE_775 is not set
+# CONFIG_NLS_CODEPAGE_850 is not set
+# CONFIG_NLS_CODEPAGE_852 is not set
+# CONFIG_NLS_CODEPAGE_855 is not set
+# CONFIG_NLS_CODEPAGE_857 is not set
+# CONFIG_NLS_CODEPAGE_860 is not set
+# CONFIG_NLS_CODEPAGE_861 is not set
+# CONFIG_NLS_CODEPAGE_862 is not set
+# CONFIG_NLS_CODEPAGE_863 is not set
+# CONFIG_NLS_CODEPAGE_864 is not set
+# CONFIG_NLS_CODEPAGE_865 is not set
+# CONFIG_NLS_CODEPAGE_866 is not set
+# CONFIG_NLS_CODEPAGE_869 is not set
+# CONFIG_NLS_CODEPAGE_936 is not set
+# CONFIG_NLS_CODEPAGE_950 is not set
+# CONFIG_NLS_CODEPAGE_932 is not set
+# CONFIG_NLS_CODEPAGE_949 is not set
+# CONFIG_NLS_CODEPAGE_874 is not set
+# CONFIG_NLS_ISO8859_8 is not set
+# CONFIG_NLS_CODEPAGE_1250 is not set
+# CONFIG_NLS_CODEPAGE_1251 is not set
+CONFIG_NLS_ISO8859_1=y
+# CONFIG_NLS_ISO8859_2 is not set
+# CONFIG_NLS_ISO8859_3 is not set
+# CONFIG_NLS_ISO8859_4 is not set
+# CONFIG_NLS_ISO8859_5 is not set
+# CONFIG_NLS_ISO8859_6 is not set
+# CONFIG_NLS_ISO8859_7 is not set
+# CONFIG_NLS_ISO8859_9 is not set
+# CONFIG_NLS_ISO8859_13 is not set
+# CONFIG_NLS_ISO8859_14 is not set
+# CONFIG_NLS_ISO8859_15 is not set
+# CONFIG_NLS_KOI8_R is not set
+# CONFIG_NLS_KOI8_U is not set
+# CONFIG_NLS_UTF8 is not set
+
+#
+# Console drivers
+#
+CONFIG_XEN_CONSOLE=y
+CONFIG_VGA_CONSOLE=y
+CONFIG_DUMMY_CONSOLE=y
+# CONFIG_VIDEO_SELECT is not set
+# CONFIG_MDA_CONSOLE is not set
+
+#
+# Frame-buffer support
+#
+# CONFIG_FB is not set
+
+#
+# Sound
+#
+# CONFIG_SOUND is not set
+
+#
+# USB support
+#
+# CONFIG_USB is not set
+
+#
+# Support for USB gadgets
+#
+# CONFIG_USB_GADGET is not set
+
+#
+# Bluetooth support
+#
+# CONFIG_BLUEZ is not set
+
+#
+# Kernel hacking
+#
+CONFIG_DEBUG_KERNEL=y
+# CONFIG_DEBUG_STACKOVERFLOW is not set
+# CONFIG_DEBUG_HIGHMEM is not set
+# CONFIG_DEBUG_SLAB is not set
+# CONFIG_DEBUG_IOVIRT is not set
+# CONFIG_MAGIC_SYSRQ is not set
+# CONFIG_DEBUG_SPINLOCK is not set
+# CONFIG_DEBUG_BUGVERBOSE is not set
+CONFIG_KALLSYMS=y
+# CONFIG_FRAME_POINTER is not set
+CONFIG_LOG_BUF_SHIFT=0
+
+#
+# Cryptographic options
+#
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_NULL=m
+CONFIG_CRYPTO_MD4=m
+CONFIG_CRYPTO_MD5=m
+CONFIG_CRYPTO_SHA1=m
+CONFIG_CRYPTO_SHA256=m
+CONFIG_CRYPTO_SHA512=m
+# CONFIG_CRYPTO_WP512 is not set
+CONFIG_CRYPTO_DES=m
+CONFIG_CRYPTO_BLOWFISH=m
+CONFIG_CRYPTO_TWOFISH=m
+CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_AES=m
+CONFIG_CRYPTO_CAST5=m
+CONFIG_CRYPTO_CAST6=m
+# CONFIG_CRYPTO_TEA is not set
+# CONFIG_CRYPTO_KHAZAD is not set
+# CONFIG_CRYPTO_ANUBIS is not set
+CONFIG_CRYPTO_ARC4=m
+CONFIG_CRYPTO_DEFLATE=m
+# CONFIG_CRYPTO_MICHAEL_MIC is not set
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Library routines
+#
+# CONFIG_CRC32 is not set
+CONFIG_ZLIB_INFLATE=y
+CONFIG_ZLIB_DEFLATE=m
+# CONFIG_FW_LOADER is not set
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/highmem.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/highmem.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,132 @@
+/*
+ * highmem.h: virtual kernel memory mappings for high memory
+ *
+ * Used in CONFIG_HIGHMEM systems for memory pages which
+ * are not addressable by direct kernel virtual addresses.
+ *
+ * Copyright (C) 1999 Gerhard Wichert, Siemens AG
+ * Gerhard.Wichert@xxxxxxxxxxxxxx
+ *
+ *
+ * Redesigned the x86 32-bit VM architecture to deal with
+ * up to 16 Terabyte physical memory. With current x86 CPUs
+ * we now support up to 64 Gigabytes physical RAM.
+ *
+ * Copyright (C) 1999 Ingo Molnar <mingo@xxxxxxxxxx>
+ */
+
+#ifndef _ASM_HIGHMEM_H
+#define _ASM_HIGHMEM_H
+
+#ifdef __KERNEL__
+
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <asm/kmap_types.h>
+#include <asm/pgtable.h>
+
+#ifdef CONFIG_DEBUG_HIGHMEM
+#define HIGHMEM_DEBUG 1
+#else
+#define HIGHMEM_DEBUG 0
+#endif
+
+/* declarations for highmem.c */
+extern unsigned long highstart_pfn, highend_pfn;
+
+extern pte_t *kmap_pte;
+extern pgprot_t kmap_prot;
+extern pte_t *pkmap_page_table;
+
+extern void kmap_init(void) __init;
+
+/*
+ * Right now we initialize only a single pte table. It can be extended
+ * easily, subsequent pte tables have to be allocated in one physical
+ * chunk of RAM.
+ */
+#define PKMAP_BASE (HYPERVISOR_VIRT_START - (1<<23))
+#ifdef CONFIG_X86_PAE
+#define LAST_PKMAP 512
+#else
+#define LAST_PKMAP 1024
+#endif
+#define LAST_PKMAP_MASK (LAST_PKMAP-1)
+#define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT)
+#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT))
+
+extern void * FASTCALL(kmap_high(struct page *page, int nonblocking));
+extern void FASTCALL(kunmap_high(struct page *page));
+
+#define kmap(page) __kmap(page, 0)
+#define kmap_nonblock(page) __kmap(page, 1)
+
+static inline void *__kmap(struct page *page, int nonblocking)
+{
+ if (in_interrupt())
+ out_of_line_bug();
+ if (page < highmem_start_page)
+ return page_address(page);
+ return kmap_high(page, nonblocking);
+}
+
+static inline void kunmap(struct page *page)
+{
+ if (in_interrupt())
+ out_of_line_bug();
+ if (page < highmem_start_page)
+ return;
+ kunmap_high(page);
+}
+
+/*
+ * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap
+ * gives a more generic (and caching) interface. But kmap_atomic can
+ * be used in IRQ contexts, so in some (very limited) cases we need
+ * it.
+ */
+static inline void *kmap_atomic(struct page *page, enum km_type type)
+{
+ enum fixed_addresses idx;
+ unsigned long vaddr;
+
+ if (page < highmem_start_page)
+ return page_address(page);
+
+ idx = type + KM_TYPE_NR*smp_processor_id();
+ vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+#if HIGHMEM_DEBUG
+ if (!pte_none(*(kmap_pte-idx)))
+ out_of_line_bug();
+#endif
+ set_pte(kmap_pte-idx, mk_pte(page, kmap_prot));
+ __flush_tlb_one(vaddr);
+
+ return (void*) vaddr;
+}
+
+static inline void kunmap_atomic(void *kvaddr, enum km_type type)
+{
+#if HIGHMEM_DEBUG
+ unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
+ enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
+
+ if (vaddr < FIXADDR_START) // FIXME
+ return;
+
+ if (vaddr != __fix_to_virt(FIX_KMAP_BEGIN+idx))
+ out_of_line_bug();
+
+ /*
+ * force other mappings to Oops if they'll try to access
+ * this pte without first remap it
+ */
+ pte_clear(kmap_pte-idx);
+ __flush_tlb_one(vaddr);
+#endif
+}
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_HIGHMEM_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/defconfig-xenU
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/defconfig-xenU Fri Jul 15 13:39:50 2005
@@ -0,0 +1,562 @@
+#
+# Automatically generated make config: don't edit
+#
+CONFIG_XEN=y
+CONFIG_X86=y
+CONFIG_ISA=y
+# CONFIG_SBUS is not set
+CONFIG_UID16=y
+
+#
+# Xen
+#
+# CONFIG_XEN_PRIVILEGED_GUEST is not set
+# CONFIG_XEN_PHYSDEV_ACCESS is not set
+CONFIG_XEN_SCRUB_PAGES=y
+CONFIG_XEN_NETDEV_FRONTEND=y
+CONFIG_XEN_BLKDEV_FRONTEND=y
+CONFIG_XEN_BLKDEV_GRANT=y
+# CONFIG_XEN_USB_FRONTEND is not set
+CONFIG_NO_IDLE_HZ=y
+# CONFIG_FOREIGN_PAGES is not set
+CONFIG_NETDEVICES=y
+# CONFIG_VT is not set
+
+#
+# Code maturity level options
+#
+CONFIG_EXPERIMENTAL=y
+
+#
+# Loadable module support
+#
+CONFIG_MODULES=y
+CONFIG_MODVERSIONS=y
+CONFIG_KMOD=y
+
+#
+# Processor type and features
+#
+CONFIG_M686=y
+# CONFIG_MPENTIUMIII is not set
+# CONFIG_MPENTIUM4 is not set
+# CONFIG_MK7 is not set
+# CONFIG_MK8 is not set
+# CONFIG_MVIAC3_2 is not set
+CONFIG_X86_WP_WORKS_OK=y
+CONFIG_X86_INVLPG=y
+CONFIG_X86_CMPXCHG=y
+CONFIG_X86_XADD=y
+CONFIG_X86_BSWAP=y
+CONFIG_X86_POPAD_OK=y
+# CONFIG_RWSEM_GENERIC_SPINLOCK is not set
+CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+CONFIG_X86_GOOD_APIC=y
+CONFIG_X86_PGE=y
+CONFIG_X86_USE_PPRO_CHECKSUM=y
+CONFIG_X86_TSC=y
+CONFIG_X86_L1_CACHE_SHIFT=5
+CONFIG_NOHIGHMEM=y
+# CONFIG_HIGHMEM4G is not set
+CONFIG_FORCE_MAX_ZONEORDER=11
+
+#
+# General setup
+#
+CONFIG_NET=y
+CONFIG_SYSVIPC=y
+# CONFIG_BSD_PROCESS_ACCT is not set
+CONFIG_SYSCTL=y
+CONFIG_KCORE_ELF=y
+# CONFIG_KCORE_AOUT is not set
+CONFIG_BINFMT_AOUT=y
+CONFIG_BINFMT_ELF=y
+# CONFIG_BINFMT_MISC is not set
+# CONFIG_OOM_KILLER is not set
+
+#
+# Networking options
+#
+CONFIG_PACKET=y
+CONFIG_PACKET_MMAP=y
+# CONFIG_NETLINK_DEV is not set
+CONFIG_NETFILTER=y
+# CONFIG_NETFILTER_DEBUG is not set
+CONFIG_FILTER=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+# CONFIG_IP_MULTICAST is not set
+# CONFIG_IP_ADVANCED_ROUTER is not set
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+# CONFIG_IP_PNP_BOOTP is not set
+# CONFIG_IP_PNP_RARP is not set
+# CONFIG_NET_IPIP is not set
+# CONFIG_NET_IPGRE is not set
+# CONFIG_ARPD is not set
+# CONFIG_INET_ECN is not set
+# CONFIG_SYN_COOKIES is not set
+
+#
+# IP: Netfilter Configuration
+#
+CONFIG_IP_NF_CONNTRACK=y
+CONFIG_IP_NF_FTP=y
+# CONFIG_IP_NF_AMANDA is not set
+CONFIG_IP_NF_TFTP=y
+CONFIG_IP_NF_IRC=y
+# CONFIG_IP_NF_QUEUE is not set
+CONFIG_IP_NF_IPTABLES=y
+# CONFIG_IP_NF_MATCH_LIMIT is not set
+# CONFIG_IP_NF_MATCH_MAC is not set
+# CONFIG_IP_NF_MATCH_PKTTYPE is not set
+# CONFIG_IP_NF_MATCH_MARK is not set
+# CONFIG_IP_NF_MATCH_MULTIPORT is not set
+# CONFIG_IP_NF_MATCH_TOS is not set
+# CONFIG_IP_NF_MATCH_RECENT is not set
+# CONFIG_IP_NF_MATCH_ECN is not set
+# CONFIG_IP_NF_MATCH_DSCP is not set
+# CONFIG_IP_NF_MATCH_AH_ESP is not set
+# CONFIG_IP_NF_MATCH_LENGTH is not set
+# CONFIG_IP_NF_MATCH_TTL is not set
+# CONFIG_IP_NF_MATCH_TCPMSS is not set
+# CONFIG_IP_NF_MATCH_HELPER is not set
+CONFIG_IP_NF_MATCH_STATE=y
+CONFIG_IP_NF_MATCH_CONNTRACK=y
+# CONFIG_IP_NF_MATCH_UNCLEAN is not set
+# CONFIG_IP_NF_MATCH_OWNER is not set
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+# CONFIG_IP_NF_TARGET_MIRROR is not set
+CONFIG_IP_NF_NAT=y
+CONFIG_IP_NF_NAT_NEEDED=y
+CONFIG_IP_NF_TARGET_MASQUERADE=y
+CONFIG_IP_NF_TARGET_REDIRECT=y
+# CONFIG_IP_NF_NAT_SNMP_BASIC is not set
+CONFIG_IP_NF_NAT_IRC=y
+CONFIG_IP_NF_NAT_FTP=y
+CONFIG_IP_NF_NAT_TFTP=y
+# CONFIG_IP_NF_MANGLE is not set
+CONFIG_IP_NF_TARGET_LOG=y
+CONFIG_IP_NF_TARGET_ULOG=y
+# CONFIG_IP_NF_TARGET_TCPMSS is not set
+# CONFIG_IP_NF_ARPTABLES is not set
+
+#
+# IP: Virtual Server Configuration
+#
+# CONFIG_IP_VS is not set
+# CONFIG_IPV6 is not set
+# CONFIG_KHTTPD is not set
+
+#
+# SCTP Configuration (EXPERIMENTAL)
+#
+# CONFIG_IP_SCTP is not set
+# CONFIG_ATM is not set
+CONFIG_VLAN_8021Q=y
+
+#
+#
+#
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+# CONFIG_DECNET is not set
+# CONFIG_BRIDGE is not set
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+# CONFIG_LLC is not set
+# CONFIG_NET_DIVERT is not set
+# CONFIG_ECONET is not set
+# CONFIG_WAN_ROUTER is not set
+# CONFIG_NET_FASTROUTE is not set
+# CONFIG_NET_HW_FLOWCONTROL is not set
+
+#
+# QoS and/or fair queueing
+#
+# CONFIG_NET_SCHED is not set
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+
+#
+# SCSI support
+#
+CONFIG_SCSI=y
+
+#
+# SCSI support type (disk, tape, CD-ROM)
+#
+CONFIG_BLK_DEV_SD=y
+CONFIG_SD_EXTRA_DEVS=40
+# CONFIG_CHR_DEV_ST is not set
+# CONFIG_CHR_DEV_OSST is not set
+# CONFIG_BLK_DEV_SR is not set
+CONFIG_CHR_DEV_SG=y
+
+#
+# Some SCSI devices (e.g. CD jukebox) support multiple LUNs
+#
+# CONFIG_SCSI_DEBUG_QUEUES is not set
+# CONFIG_SCSI_MULTI_LUN is not set
+# CONFIG_SCSI_CONSTANTS is not set
+# CONFIG_SCSI_LOGGING is not set
+
+#
+# SCSI low-level drivers
+#
+# CONFIG_SCSI_7000FASST is not set
+# CONFIG_SCSI_ACARD is not set
+# CONFIG_SCSI_AHA152X is not set
+# CONFIG_SCSI_AHA1542 is not set
+# CONFIG_SCSI_AHA1740 is not set
+# CONFIG_SCSI_AACRAID is not set
+# CONFIG_SCSI_AIC7XXX is not set
+# CONFIG_SCSI_AIC79XX is not set
+# CONFIG_SCSI_AIC7XXX_OLD is not set
+# CONFIG_SCSI_DPT_I2O is not set
+# CONFIG_SCSI_ADVANSYS is not set
+# CONFIG_SCSI_IN2000 is not set
+# CONFIG_SCSI_AM53C974 is not set
+# CONFIG_SCSI_MEGARAID is not set
+# CONFIG_SCSI_MEGARAID2 is not set
+# CONFIG_SCSI_SATA is not set
+# CONFIG_SCSI_SATA_AHCI is not set
+# CONFIG_SCSI_SATA_SVW is not set
+# CONFIG_SCSI_ATA_PIIX is not set
+# CONFIG_SCSI_SATA_NV is not set
+# CONFIG_SCSI_SATA_QSTOR is not set
+# CONFIG_SCSI_SATA_PROMISE is not set
+# CONFIG_SCSI_SATA_SX4 is not set
+# CONFIG_SCSI_SATA_SIL is not set
+# CONFIG_SCSI_SATA_SIS is not set
+# CONFIG_SCSI_SATA_ULI is not set
+# CONFIG_SCSI_SATA_VIA is not set
+# CONFIG_SCSI_SATA_VITESSE is not set
+# CONFIG_SCSI_BUSLOGIC is not set
+# CONFIG_SCSI_DMX3191D is not set
+# CONFIG_SCSI_DTC3280 is not set
+# CONFIG_SCSI_EATA is not set
+# CONFIG_SCSI_EATA_DMA is not set
+# CONFIG_SCSI_EATA_PIO is not set
+# CONFIG_SCSI_FUTURE_DOMAIN is not set
+# CONFIG_SCSI_GDTH is not set
+# CONFIG_SCSI_GENERIC_NCR5380 is not set
+# CONFIG_SCSI_IPS is not set
+# CONFIG_SCSI_INITIO is not set
+# CONFIG_SCSI_INIA100 is not set
+# CONFIG_SCSI_PPA is not set
+# CONFIG_SCSI_IMM is not set
+# CONFIG_SCSI_NCR53C406A is not set
+# CONFIG_SCSI_NCR53C7xx is not set
+# CONFIG_SCSI_PAS16 is not set
+# CONFIG_SCSI_PCI2000 is not set
+# CONFIG_SCSI_PCI2220I is not set
+# CONFIG_SCSI_PSI240I is not set
+# CONFIG_SCSI_QLOGIC_FAS is not set
+# CONFIG_SCSI_SEAGATE is not set
+# CONFIG_SCSI_SIM710 is not set
+# CONFIG_SCSI_SYM53C416 is not set
+# CONFIG_SCSI_T128 is not set
+# CONFIG_SCSI_U14_34F is not set
+# CONFIG_SCSI_ULTRASTOR is not set
+# CONFIG_SCSI_NSP32 is not set
+# CONFIG_SCSI_DEBUG is not set
+
+#
+# Block devices
+#
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_NBD=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=4096
+CONFIG_BLK_DEV_INITRD=y
+# CONFIG_BLK_STATS is not set
+# CONFIG_BLK_DEV_HD is not set
+
+#
+# Character devices
+#
+# CONFIG_VT is not set
+# CONFIG_SERIAL is not set
+# CONFIG_SERIAL_EXTENDED is not set
+# CONFIG_SERIAL_NONSTANDARD is not set
+CONFIG_UNIX98_PTYS=y
+CONFIG_UNIX98_PTY_COUNT=256
+# CONFIG_PRINTER is not set
+# CONFIG_PPDEV is not set
+# CONFIG_TIPAR is not set
+
+#
+# I2C support
+#
+# CONFIG_I2C is not set
+
+#
+# Mice
+#
+# CONFIG_BUSMOUSE is not set
+CONFIG_MOUSE=y
+CONFIG_PSMOUSE=y
+# CONFIG_82C710_MOUSE is not set
+# CONFIG_PC110_PAD is not set
+# CONFIG_MK712_MOUSE is not set
+
+#
+# Joysticks
+#
+# CONFIG_INPUT_GAMEPORT is not set
+# CONFIG_INPUT_NS558 is not set
+# CONFIG_INPUT_LIGHTNING is not set
+# CONFIG_INPUT_PCIGAME is not set
+# CONFIG_INPUT_CS461X is not set
+# CONFIG_INPUT_EMU10K1 is not set
+# CONFIG_INPUT_SERIO is not set
+# CONFIG_INPUT_SERPORT is not set
+
+#
+# Joysticks
+#
+# CONFIG_INPUT_ANALOG is not set
+# CONFIG_INPUT_A3D is not set
+# CONFIG_INPUT_ADI is not set
+# CONFIG_INPUT_COBRA is not set
+# CONFIG_INPUT_GF2K is not set
+# CONFIG_INPUT_GRIP is not set
+# CONFIG_INPUT_INTERACT is not set
+# CONFIG_INPUT_TMDC is not set
+# CONFIG_INPUT_SIDEWINDER is not set
+# CONFIG_INPUT_IFORCE_USB is not set
+# CONFIG_INPUT_IFORCE_232 is not set
+# CONFIG_INPUT_WARRIOR is not set
+# CONFIG_INPUT_MAGELLAN is not set
+# CONFIG_INPUT_SPACEORB is not set
+# CONFIG_INPUT_SPACEBALL is not set
+# CONFIG_INPUT_STINGER is not set
+# CONFIG_INPUT_DB9 is not set
+# CONFIG_INPUT_GAMECON is not set
+# CONFIG_INPUT_TURBOGRAFX is not set
+# CONFIG_QIC02_TAPE is not set
+# CONFIG_IPMI_HANDLER is not set
+# CONFIG_IPMI_PANIC_EVENT is not set
+# CONFIG_IPMI_DEVICE_INTERFACE is not set
+# CONFIG_IPMI_KCS is not set
+# CONFIG_IPMI_WATCHDOG is not set
+
+#
+# Watchdog Cards
+#
+# CONFIG_WATCHDOG is not set
+# CONFIG_SCx200 is not set
+# CONFIG_SCx200_GPIO is not set
+# CONFIG_AMD_RNG is not set
+# CONFIG_INTEL_RNG is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_AMD_PM768 is not set
+# CONFIG_NVRAM is not set
+# CONFIG_RTC is not set
+# CONFIG_DTLK is not set
+# CONFIG_R3964 is not set
+# CONFIG_APPLICOM is not set
+# CONFIG_SONYPI is not set
+
+#
+# Ftape, the floppy tape device driver
+#
+# CONFIG_FTAPE is not set
+# CONFIG_AGP is not set
+
+#
+# Direct Rendering Manager (XFree86 DRI support)
+#
+# CONFIG_DRM is not set
+# CONFIG_MWAVE is not set
+# CONFIG_OBMOUSE is not set
+
+#
+# File systems
+#
+# CONFIG_QUOTA is not set
+# CONFIG_QFMT_V2 is not set
+CONFIG_AUTOFS_FS=y
+CONFIG_AUTOFS4_FS=y
+# CONFIG_REISERFS_FS is not set
+# CONFIG_REISERFS_CHECK is not set
+# CONFIG_REISERFS_PROC_INFO is not set
+# CONFIG_ADFS_FS is not set
+# CONFIG_ADFS_FS_RW is not set
+# CONFIG_AFFS_FS is not set
+# CONFIG_HFS_FS is not set
+# CONFIG_HFSPLUS_FS is not set
+# CONFIG_BEFS_FS is not set
+# CONFIG_BEFS_DEBUG is not set
+# CONFIG_BFS_FS is not set
+CONFIG_EXT3_FS=y
+CONFIG_JBD=y
+# CONFIG_JBD_DEBUG is not set
+CONFIG_FAT_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_UMSDOS_FS=y
+CONFIG_VFAT_FS=y
+# CONFIG_EFS_FS is not set
+# CONFIG_JFFS_FS is not set
+# CONFIG_JFFS2_FS is not set
+# CONFIG_CRAMFS is not set
+CONFIG_TMPFS=y
+CONFIG_RAMFS=y
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+# CONFIG_JFS_FS is not set
+# CONFIG_JFS_DEBUG is not set
+# CONFIG_JFS_STATISTICS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_NTFS_FS is not set
+# CONFIG_NTFS_RW is not set
+# CONFIG_HPFS_FS is not set
+CONFIG_PROC_FS=y
+# CONFIG_DEVFS_FS is not set
+# CONFIG_DEVFS_MOUNT is not set
+# CONFIG_DEVFS_DEBUG is not set
+CONFIG_DEVPTS_FS=y
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_QNX4FS_RW is not set
+# CONFIG_ROMFS_FS is not set
+CONFIG_EXT2_FS=y
+# CONFIG_SYSV_FS is not set
+# CONFIG_UDF_FS is not set
+# CONFIG_UDF_RW is not set
+# CONFIG_UFS_FS is not set
+# CONFIG_UFS_FS_WRITE is not set
+# CONFIG_XFS_FS is not set
+# CONFIG_XFS_QUOTA is not set
+# CONFIG_XFS_RT is not set
+# CONFIG_XFS_TRACE is not set
+# CONFIG_XFS_DEBUG is not set
+
+#
+# Network File Systems
+#
+# CONFIG_CODA_FS is not set
+# CONFIG_INTERMEZZO_FS is not set
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+# CONFIG_NFS_DIRECTIO is not set
+CONFIG_ROOT_NFS=y
+CONFIG_NFSD=y
+CONFIG_NFSD_V3=y
+# CONFIG_NFSD_TCP is not set
+CONFIG_SUNRPC=y
+CONFIG_LOCKD=y
+CONFIG_LOCKD_V4=y
+# CONFIG_SMB_FS is not set
+# CONFIG_NCP_FS is not set
+# CONFIG_NCPFS_PACKET_SIGNING is not set
+# CONFIG_NCPFS_IOCTL_LOCKING is not set
+# CONFIG_NCPFS_STRONG is not set
+# CONFIG_NCPFS_NFS_NS is not set
+# CONFIG_NCPFS_OS2_NS is not set
+# CONFIG_NCPFS_SMALLDOS is not set
+# CONFIG_NCPFS_NLS is not set
+# CONFIG_NCPFS_EXTRAS is not set
+CONFIG_ZISOFS_FS=y
+
+#
+# Partition Types
+#
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_ACORN_PARTITION is not set
+# CONFIG_OSF_PARTITION is not set
+# CONFIG_AMIGA_PARTITION is not set
+# CONFIG_ATARI_PARTITION is not set
+# CONFIG_MAC_PARTITION is not set
+CONFIG_MSDOS_PARTITION=y
+# CONFIG_BSD_DISKLABEL is not set
+# CONFIG_MINIX_SUBPARTITION is not set
+# CONFIG_SOLARIS_X86_PARTITION is not set
+# CONFIG_UNIXWARE_DISKLABEL is not set
+# CONFIG_LDM_PARTITION is not set
+# CONFIG_SGI_PARTITION is not set
+# CONFIG_ULTRIX_PARTITION is not set
+# CONFIG_SUN_PARTITION is not set
+# CONFIG_EFI_PARTITION is not set
+# CONFIG_SMB_NLS is not set
+CONFIG_NLS=y
+
+#
+# Native Language Support
+#
+CONFIG_NLS_DEFAULT="iso8559-1"
+# CONFIG_NLS_CODEPAGE_437 is not set
+# CONFIG_NLS_CODEPAGE_737 is not set
+# CONFIG_NLS_CODEPAGE_775 is not set
+# CONFIG_NLS_CODEPAGE_850 is not set
+# CONFIG_NLS_CODEPAGE_852 is not set
+# CONFIG_NLS_CODEPAGE_855 is not set
+# CONFIG_NLS_CODEPAGE_857 is not set
+# CONFIG_NLS_CODEPAGE_860 is not set
+# CONFIG_NLS_CODEPAGE_861 is not set
+# CONFIG_NLS_CODEPAGE_862 is not set
+# CONFIG_NLS_CODEPAGE_863 is not set
+# CONFIG_NLS_CODEPAGE_864 is not set
+# CONFIG_NLS_CODEPAGE_865 is not set
+# CONFIG_NLS_CODEPAGE_866 is not set
+# CONFIG_NLS_CODEPAGE_869 is not set
+# CONFIG_NLS_CODEPAGE_936 is not set
+# CONFIG_NLS_CODEPAGE_950 is not set
+# CONFIG_NLS_CODEPAGE_932 is not set
+# CONFIG_NLS_CODEPAGE_949 is not set
+# CONFIG_NLS_CODEPAGE_874 is not set
+# CONFIG_NLS_ISO8859_8 is not set
+# CONFIG_NLS_CODEPAGE_1250 is not set
+# CONFIG_NLS_CODEPAGE_1251 is not set
+CONFIG_NLS_ISO8859_1=y
+# CONFIG_NLS_ISO8859_2 is not set
+# CONFIG_NLS_ISO8859_3 is not set
+# CONFIG_NLS_ISO8859_4 is not set
+# CONFIG_NLS_ISO8859_5 is not set
+# CONFIG_NLS_ISO8859_6 is not set
+# CONFIG_NLS_ISO8859_7 is not set
+# CONFIG_NLS_ISO8859_9 is not set
+# CONFIG_NLS_ISO8859_13 is not set
+# CONFIG_NLS_ISO8859_14 is not set
+# CONFIG_NLS_ISO8859_15 is not set
+# CONFIG_NLS_KOI8_R is not set
+# CONFIG_NLS_KOI8_U is not set
+# CONFIG_NLS_UTF8 is not set
+
+#
+# Console drivers
+#
+CONFIG_XEN_CONSOLE=y
+
+#
+# Kernel hacking
+#
+CONFIG_DEBUG_KERNEL=y
+# CONFIG_DEBUG_STACKOVERFLOW is not set
+# CONFIG_DEBUG_HIGHMEM is not set
+# CONFIG_DEBUG_SLAB is not set
+# CONFIG_DEBUG_IOVIRT is not set
+# CONFIG_MAGIC_SYSRQ is not set
+# CONFIG_DEBUG_SPINLOCK is not set
+# CONFIG_DEBUG_BUGVERBOSE is not set
+CONFIG_KALLSYMS=y
+# CONFIG_FRAME_POINTER is not set
+CONFIG_LOG_BUF_SHIFT=0
+
+#
+# Cryptographic options
+#
+# CONFIG_CRYPTO is not set
+
+#
+# Library routines
+#
+# CONFIG_CRC32 is not set
+CONFIG_ZLIB_INFLATE=y
+# CONFIG_ZLIB_DEFLATE is not set
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/mm/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/mm/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,31 @@
+#
+# Makefile for the linux x86_64-specific parts of the memory manager.
+#
+
+XENARCH := $(subst ",,$(CONFIG_XENARCH))
+
+CFLAGS += -Iarch/$(XENARCH)/mm
+
+obj-y := init.o fault.o ioremap.o pageattr.o
+c-obj-y := extable.o
+
+i386-obj-y := hypervisor.o
+
+#obj-y := init.o fault.o ioremap.o extable.o pageattr.o
+#c-obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+c-obj-$(CONFIG_DISCONTIGMEM) += numa.o
+c-obj-$(CONFIG_K8_NUMA) += k8topology.o
+
+hugetlbpage-y = ../../../i386/mm/hugetlbpage.o
+
+c-link :=
+
+$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)):
+ @ln -fsn $(srctree)/arch/x86_64/mm/$(notdir $@) $@
+
+$(patsubst %.o,$(obj)/%.c,$(i386-obj-y)):
+ ln -fsn $(srctree)/arch/xen/i386/mm/$(notdir $@) $@
+
+obj-y += $(c-obj-y) $(i386-obj-y)
+
+clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link) $(i386-obj-y))
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/arch/xen/mm/fault.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/mm/fault.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,302 @@
+/*
+ * linux/arch/i386/mm/fault.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ */
+
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/tty.h>
+#include <linux/vt_kern.h> /* For unblank_screen() */
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+#include <asm/hardirq.h>
+
+extern void die(const char *,struct pt_regs *,long);
+
+pgd_t *cur_pgd;
+
+extern spinlock_t timerlist_lock;
+
+/*
+ * Unlock any spinlocks which will prevent us from getting the
+ * message out (timerlist_lock is acquired through the
+ * console unblank code)
+ */
+void bust_spinlocks(int yes)
+{
+ spin_lock_init(&timerlist_lock);
+ if (yes) {
+ oops_in_progress = 1;
+ } else {
+ int loglevel_save = console_loglevel;
+#ifdef CONFIG_VT
+ unblank_screen();
+#endif
+ oops_in_progress = 0;
+ /*
+ * OK, the message is on the console. Now we call printk()
+ * without oops_in_progress set so that printk will give klogd
+ * a poke. Hold onto your hats...
+ */
+ console_loglevel = 15; /* NMI oopser may have shut the
console up */
+ printk(" ");
+ console_loglevel = loglevel_save;
+ }
+}
+
+/*
+ * This routine handles page faults. It determines the address,
+ * and the problem, and then passes it off to one of the appropriate
+ * routines.
+ *
+ * error_code:
+ * bit 0 == 0 means no page found, 1 means protection fault
+ * bit 1 == 0 means read, 1 means write
+ * bit 2 == 0 means kernel, 1 means user-mode
+ */
+asmlinkage void do_page_fault(struct pt_regs *regs,
+ unsigned long error_code,
+ unsigned long address)
+{
+ struct task_struct *tsk = current;
+ struct mm_struct *mm;
+ struct vm_area_struct * vma;
+ unsigned long page;
+ unsigned long fixup;
+ int write;
+ siginfo_t info;
+
+ /* Set the "privileged fault" bit to something sane. */
+ error_code &= 3;
+ error_code |= (regs->xcs & 2) << 1;
+
+ /*
+ * We fault-in kernel-space virtual memory on-demand. The
+ * 'reference' page table is init_mm.pgd.
+ *
+ * NOTE! We MUST NOT take any locks for this case. We may
+ * be in an interrupt or a critical region, and should
+ * only copy the information from the master page table,
+ * nothing more.
+ *
+ * This verifies that the fault happens in kernel space
+ * (error_code & 4) == 0, and that the fault was not a
+ * protection error (error_code & 1) == 0.
+ */
+ if (address >= TASK_SIZE && !(error_code & 5))
+ goto vmalloc_fault;
+
+ mm = tsk->mm;
+ info.si_code = SEGV_MAPERR;
+
+ /*
+ * If we're in an interrupt or have no user
+ * context, we must not take the fault..
+ */
+ if (in_interrupt() || !mm)
+ goto no_context;
+
+ down_read(&mm->mmap_sem);
+
+ vma = find_vma(mm, address);
+ if (!vma)
+ goto bad_area;
+ if (vma->vm_start <= address)
+ goto good_area;
+ if (!(vma->vm_flags & VM_GROWSDOWN))
+ goto bad_area;
+ if (error_code & 4) {
+ /*
+ * accessing the stack below %esp is always a bug.
+ * The "+ 32" is there due to some instructions (like
+ * pusha) doing post-decrement on the stack and that
+ * doesn't show up until later..
+ */
+ if (address + 32 < regs->esp)
+ goto bad_area;
+ }
+ if (expand_stack(vma, address))
+ goto bad_area;
+/*
+ * Ok, we have a good vm_area for this memory access, so
+ * we can handle it..
+ */
+good_area:
+ info.si_code = SEGV_ACCERR;
+ write = 0;
+ switch (error_code & 3) {
+ default: /* 3: write, present */
+ /* fall through */
+ case 2: /* write, not present */
+ if (!(vma->vm_flags & VM_WRITE))
+ goto bad_area;
+ write++;
+ break;
+ case 1: /* read, present */
+ goto bad_area;
+ case 0: /* read, not present */
+ if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+ goto bad_area;
+ }
+
+ survive:
+ /*
+ * If for any reason at all we couldn't handle the fault,
+ * make sure we exit gracefully rather than endlessly redo
+ * the fault.
+ */
+ switch (handle_mm_fault(mm, vma, address, write)) {
+ case 1:
+ tsk->min_flt++;
+ break;
+ case 2:
+ tsk->maj_flt++;
+ break;
+ case 0:
+ goto do_sigbus;
+ default:
+ goto out_of_memory;
+ }
+
+ up_read(&mm->mmap_sem);
+ return;
+
+/*
+ * Something tried to access memory that isn't in our memory map..
+ * Fix it, but check if it's kernel or user first..
+ */
+bad_area:
+ up_read(&mm->mmap_sem);
+
+ /* User mode accesses just cause a SIGSEGV */
+ if (error_code & 4) {
+ tsk->thread.cr2 = address;
+ /* Kernel addresses are always protection faults */
+ tsk->thread.error_code = error_code | (address >= TASK_SIZE);
+ tsk->thread.trap_no = 14;
+ info.si_signo = SIGSEGV;
+ info.si_errno = 0;
+ /* info.si_code has been set above */
+ info.si_addr = (void *)address;
+ force_sig_info(SIGSEGV, &info, tsk);
+ return;
+ }
+
+no_context:
+ /* Are we prepared to handle this kernel fault? */
+ if ((fixup = search_exception_table(regs->eip)) != 0) {
+ regs->eip = fixup;
+ return;
+ }
+
+/*
+ * Oops. The kernel tried to access some bad page. We'll have to
+ * terminate things with extreme prejudice.
+ */
+
+ bust_spinlocks(1);
+
+ if (address < PAGE_SIZE)
+ printk(KERN_ALERT "Unable to handle kernel NULL pointer
dereference");
+ else
+ printk(KERN_ALERT "Unable to handle kernel paging request");
+ printk(" at virtual address %08lx\n",address);
+ printk(" printing eip:\n");
+ printk("%08lx\n", regs->eip);
+ page = ((unsigned long *) cur_pgd)[address >> 22];
+ printk(KERN_ALERT "*pde=%08lx(%08lx)\n", page, machine_to_phys(page));
+ if (page & 1) {
+ page &= PAGE_MASK;
+ address &= 0x003ff000;
+ page = machine_to_phys(page);
+ page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT];
+ printk(KERN_ALERT "*pte=%08lx(%08lx)\n", page,
+ machine_to_phys(page));
+ }
+ die("Oops", regs, error_code);
+ bust_spinlocks(0);
+ do_exit(SIGKILL);
+
+/*
+ * We ran out of memory, or some other thing happened to us that made
+ * us unable to handle the page fault gracefully.
+ */
+out_of_memory:
+ if (tsk->pid == 1) {
+ yield();
+ goto survive;
+ }
+ up_read(&mm->mmap_sem);
+ printk("VM: killing process %s\n", tsk->comm);
+ if (error_code & 4)
+ do_exit(SIGKILL);
+ goto no_context;
+
+do_sigbus:
+ up_read(&mm->mmap_sem);
+
+ /*
+ * Send a sigbus, regardless of whether we were in kernel
+ * or user mode.
+ */
+ tsk->thread.cr2 = address;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = 14;
+ info.si_signo = SIGBUS;
+ info.si_errno = 0;
+ info.si_code = BUS_ADRERR;
+ info.si_addr = (void *)address;
+ force_sig_info(SIGBUS, &info, tsk);
+
+ /* Kernel mode? Handle exceptions or die */
+ if (!(error_code & 4))
+ goto no_context;
+ return;
+
+vmalloc_fault:
+ {
+ /*
+ * Synchronize this task's top level page-table
+ * with the 'reference' page table.
+ *
+ * Do _not_ use "tsk" here. We might be inside
+ * an interrupt in the middle of a task switch..
+ */
+ int offset = __pgd_offset(address);
+ pgd_t *pgd, *pgd_k;
+ pmd_t *pmd, *pmd_k;
+ pte_t *pte_k;
+
+ pgd = offset + cur_pgd;
+ pgd_k = init_mm.pgd + offset;
+
+ if (!pgd_present(*pgd_k))
+ goto no_context;
+ set_pgd(pgd, *pgd_k);
+
+ pmd = pmd_offset(pgd, address);
+ pmd_k = pmd_offset(pgd_k, address);
+ if (!pmd_present(*pmd_k))
+ goto no_context;
+ set_pmd(pmd, *pmd_k);
+
+ pte_k = pte_offset(pmd_k, address);
+ if (!pte_present(*pte_k))
+ goto no_context;
+ return;
+ }
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/drivers/netif/frontend/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/drivers/netif/frontend/Makefile Fri Jul
15 13:39:50 2005
@@ -0,0 +1,3 @@
+O_TARGET := drv.o
+obj-y := main.o
+include $(TOPDIR)/Rules.make
diff -r 35b74976f598 -r a83ac0806d6b linux-2.6.11-xen-sparse/drivers/char/mem.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/char/mem.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,733 @@
+/*
+ * linux/drivers/char/mem.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * Added devfs support.
+ * Jan-11-1998, C. Scott Ananian <cananian@xxxxxxxxxxxxxxxxxxxx>
+ * Shared /dev/zero mmaping support, Feb 2000, Kanoj Sarcar <kanoj@xxxxxxx>
+ */
+
+#include <linux/config.h>
+#include <linux/mm.h>
+#include <linux/miscdevice.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/mman.h>
+#include <linux/random.h>
+#include <linux/init.h>
+#include <linux/raw.h>
+#include <linux/tty.h>
+#include <linux/capability.h>
+#include <linux/smp_lock.h>
+#include <linux/devfs_fs_kernel.h>
+#include <linux/ptrace.h>
+#include <linux/device.h>
+
+#include <asm/uaccess.h>
+#include <asm/io.h>
+
+#ifdef CONFIG_IA64
+# include <linux/efi.h>
+#endif
+
+#if defined(CONFIG_S390_TAPE) && defined(CONFIG_S390_TAPE_CHAR)
+extern void tapechar_init(void);
+#endif
+
+/*
+ * Architectures vary in how they handle caching for addresses
+ * outside of main memory.
+ *
+ */
+static inline int uncached_access(struct file *file, unsigned long addr)
+{
+#if defined(__i386__)
+ /*
+ * On the PPro and successors, the MTRRs are used to set
+ * memory types for physical addresses outside main memory,
+ * so blindly setting PCD or PWT on those pages is wrong.
+ * For Pentiums and earlier, the surround logic should disable
+ * caching for the high addresses through the KEN pin, but
+ * we maintain the tradition of paranoia in this code.
+ */
+ if (file->f_flags & O_SYNC)
+ return 1;
+ return !( test_bit(X86_FEATURE_MTRR, boot_cpu_data.x86_capability) ||
+ test_bit(X86_FEATURE_K6_MTRR, boot_cpu_data.x86_capability) ||
+ test_bit(X86_FEATURE_CYRIX_ARR, boot_cpu_data.x86_capability)
||
+ test_bit(X86_FEATURE_CENTAUR_MCR,
boot_cpu_data.x86_capability) )
+ && addr >= __pa(high_memory);
+#elif defined(__x86_64__)
+ /*
+ * This is broken because it can generate memory type aliases,
+ * which can cause cache corruptions
+ * But it is only available for root and we have to be bug-to-bug
+ * compatible with i386.
+ */
+ if (file->f_flags & O_SYNC)
+ return 1;
+ /* same behaviour as i386. PAT always set to cached and MTRRs control
the
+ caching behaviour.
+ Hopefully a full PAT implementation will fix that soon. */
+ return 0;
+#elif defined(CONFIG_IA64)
+ /*
+ * On ia64, we ignore O_SYNC because we cannot tolerate memory
attribute aliases.
+ */
+ return !(efi_mem_attributes(addr) & EFI_MEMORY_WB);
+#elif defined(CONFIG_PPC64)
+ /* On PPC64, we always do non-cacheable access to the IO hole and
+ * cacheable elsewhere. Cache paradox can checkstop the CPU and
+ * the high_memory heuristic below is wrong on machines with memory
+ * above the IO hole... Ah, and of course, XFree86 doesn't pass
+ * O_SYNC when mapping us to tap IO space. Surprised ?
+ */
+ return !page_is_ram(addr >> PAGE_SHIFT);
+#else
+ /*
+ * Accessing memory above the top the kernel knows about or through a
file pointer
+ * that was marked O_SYNC will be done non-cached.
+ */
+ if (file->f_flags & O_SYNC)
+ return 1;
+ return addr >= __pa(high_memory);
+#endif
+}
+
+#ifndef ARCH_HAS_VALID_PHYS_ADDR_RANGE
+static inline int valid_phys_addr_range(unsigned long addr, size_t *count)
+{
+ unsigned long end_mem;
+
+ end_mem = __pa(high_memory);
+ if (addr >= end_mem)
+ return 0;
+
+ if (*count > end_mem - addr)
+ *count = end_mem - addr;
+
+ return 1;
+}
+#endif
+
+static ssize_t do_write_mem(void *p, unsigned long realp,
+ const char __user * buf, size_t count, loff_t *ppos)
+{
+ ssize_t written;
+ unsigned long copied;
+
+ written = 0;
+#if defined(__sparc__) || (defined(__mc68000__) && defined(CONFIG_MMU))
+ /* we don't have page 0 mapped on sparc and m68k.. */
+ if (realp < PAGE_SIZE) {
+ unsigned long sz = PAGE_SIZE-realp;
+ if (sz > count) sz = count;
+ /* Hmm. Do something? */
+ buf+=sz;
+ p+=sz;
+ count-=sz;
+ written+=sz;
+ }
+#endif
+ copied = copy_from_user(p, buf, count);
+ if (copied) {
+ ssize_t ret = written + (count - copied);
+
+ if (ret)
+ return ret;
+ return -EFAULT;
+ }
+ written += count;
+ *ppos += written;
+ return written;
+}
+
+#ifndef ARCH_HAS_DEV_MEM
+/*
+ * This funcion reads the *physical* memory. The f_pos points directly to the
+ * memory location.
+ */
+static ssize_t read_mem(struct file * file, char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long p = *ppos;
+ ssize_t read;
+
+ if (!valid_phys_addr_range(p, &count))
+ return -EFAULT;
+ read = 0;
+#if defined(__sparc__) || (defined(__mc68000__) && defined(CONFIG_MMU))
+ /* we don't have page 0 mapped on sparc and m68k.. */
+ if (p < PAGE_SIZE) {
+ unsigned long sz = PAGE_SIZE-p;
+ if (sz > count)
+ sz = count;
+ if (sz > 0) {
+ if (clear_user(buf, sz))
+ return -EFAULT;
+ buf += sz;
+ p += sz;
+ count -= sz;
+ read += sz;
+ }
+ }
+#endif
+ if (copy_to_user(buf, __va(p), count))
+ return -EFAULT;
+ read += count;
+ *ppos += read;
+ return read;
+}
+
+static ssize_t write_mem(struct file * file, const char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long p = *ppos;
+
+ if (!valid_phys_addr_range(p, &count))
+ return -EFAULT;
+ return do_write_mem(__va(p), p, buf, count, ppos);
+}
+#endif
+
+static int mmap_kmem(struct file * file, struct vm_area_struct * vma)
+{
+#ifdef pgprot_noncached
+ unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
+ int uncached;
+
+ uncached = uncached_access(file, offset);
+ if (uncached)
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+#endif
+
+ /* Remap-pfn-range will mark the range VM_IO and VM_RESERVED */
+ if (remap_pfn_range(vma,
+ vma->vm_start,
+ vma->vm_pgoff,
+ vma->vm_end-vma->vm_start,
+ vma->vm_page_prot))
+ return -EAGAIN;
+ return 0;
+}
+
+extern long vread(char *buf, char *addr, unsigned long count);
+extern long vwrite(char *buf, char *addr, unsigned long count);
+
+/*
+ * This function reads the *virtual* memory as seen by the kernel.
+ */
+static ssize_t read_kmem(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long p = *ppos;
+ ssize_t read = 0;
+ ssize_t virtr = 0;
+ char * kbuf; /* k-addr because vread() takes vmlist_lock rwlock */
+
+ if (p < (unsigned long) high_memory) {
+ read = count;
+ if (count > (unsigned long) high_memory - p)
+ read = (unsigned long) high_memory - p;
+
+#if defined(__sparc__) || (defined(__mc68000__) && defined(CONFIG_MMU))
+ /* we don't have page 0 mapped on sparc and m68k.. */
+ if (p < PAGE_SIZE && read > 0) {
+ size_t tmp = PAGE_SIZE - p;
+ if (tmp > read) tmp = read;
+ if (clear_user(buf, tmp))
+ return -EFAULT;
+ buf += tmp;
+ p += tmp;
+ read -= tmp;
+ count -= tmp;
+ }
+#endif
+ if (copy_to_user(buf, (char *)p, read))
+ return -EFAULT;
+ p += read;
+ buf += read;
+ count -= read;
+ }
+
+ if (count > 0) {
+ kbuf = (char *)__get_free_page(GFP_KERNEL);
+ if (!kbuf)
+ return -ENOMEM;
+ while (count > 0) {
+ int len = count;
+
+ if (len > PAGE_SIZE)
+ len = PAGE_SIZE;
+ len = vread(kbuf, (char *)p, len);
+ if (!len)
+ break;
+ if (copy_to_user(buf, kbuf, len)) {
+ free_page((unsigned long)kbuf);
+ return -EFAULT;
+ }
+ count -= len;
+ buf += len;
+ virtr += len;
+ p += len;
+ }
+ free_page((unsigned long)kbuf);
+ }
+ *ppos = p;
+ return virtr + read;
+}
+
+/*
+ * This function writes to the *virtual* memory as seen by the kernel.
+ */
+static ssize_t write_kmem(struct file * file, const char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long p = *ppos;
+ ssize_t wrote = 0;
+ ssize_t virtr = 0;
+ ssize_t written;
+ char * kbuf; /* k-addr because vwrite() takes vmlist_lock rwlock */
+
+ if (p < (unsigned long) high_memory) {
+
+ wrote = count;
+ if (count > (unsigned long) high_memory - p)
+ wrote = (unsigned long) high_memory - p;
+
+ written = do_write_mem((void*)p, p, buf, wrote, ppos);
+ if (written != wrote)
+ return written;
+ wrote = written;
+ p += wrote;
+ buf += wrote;
+ count -= wrote;
+ }
+
+ if (count > 0) {
+ kbuf = (char *)__get_free_page(GFP_KERNEL);
+ if (!kbuf)
+ return wrote ? wrote : -ENOMEM;
+ while (count > 0) {
+ int len = count;
+
+ if (len > PAGE_SIZE)
+ len = PAGE_SIZE;
+ if (len) {
+ written = copy_from_user(kbuf, buf, len);
+ if (written) {
+ ssize_t ret;
+
+ free_page((unsigned long)kbuf);
+ ret = wrote + virtr + (len - written);
+ return ret ? ret : -EFAULT;
+ }
+ }
+ len = vwrite(kbuf, (char *)p, len);
+ count -= len;
+ buf += len;
+ virtr += len;
+ p += len;
+ }
+ free_page((unsigned long)kbuf);
+ }
+
+ *ppos = p;
+ return virtr + wrote;
+}
+
+#if defined(CONFIG_ISA) || !defined(__mc68000__)
+static ssize_t read_port(struct file * file, char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long i = *ppos;
+ char __user *tmp = buf;
+
+ if (verify_area(VERIFY_WRITE,buf,count))
+ return -EFAULT;
+ while (count-- > 0 && i < 65536) {
+ if (__put_user(inb(i),tmp) < 0)
+ return -EFAULT;
+ i++;
+ tmp++;
+ }
+ *ppos = i;
+ return tmp-buf;
+}
+
+static ssize_t write_port(struct file * file, const char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long i = *ppos;
+ const char __user * tmp = buf;
+
+ if (verify_area(VERIFY_READ,buf,count))
+ return -EFAULT;
+ while (count-- > 0 && i < 65536) {
+ char c;
+ if (__get_user(c, tmp))
+ return -EFAULT;
+ outb(c,i);
+ i++;
+ tmp++;
+ }
+ *ppos = i;
+ return tmp-buf;
+}
+#endif
+
+static ssize_t read_null(struct file * file, char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ return 0;
+}
+
+static ssize_t write_null(struct file * file, const char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ return count;
+}
+
+#ifdef CONFIG_MMU
+/*
+ * For fun, we are using the MMU for this.
+ */
+static inline size_t read_zero_pagealigned(char __user * buf, size_t size)
+{
+ struct mm_struct *mm;
+ struct vm_area_struct * vma;
+ unsigned long addr=(unsigned long)buf;
+
+ mm = current->mm;
+ /* Oops, this was forgotten before. -ben */
+ down_read(&mm->mmap_sem);
+
+ /* For private mappings, just map in zero pages. */
+ for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) {
+ unsigned long count;
+
+ if (vma->vm_start > addr || (vma->vm_flags & VM_WRITE) == 0)
+ goto out_up;
+ if (vma->vm_flags & (VM_SHARED | VM_HUGETLB))
+ break;
+ count = vma->vm_end - addr;
+ if (count > size)
+ count = size;
+
+ zap_page_range(vma, addr, count, NULL);
+ zeromap_page_range(vma, addr, count, PAGE_COPY);
+
+ size -= count;
+ buf += count;
+ addr += count;
+ if (size == 0)
+ goto out_up;
+ }
+
+ up_read(&mm->mmap_sem);
+
+ /* The shared case is hard. Let's do the conventional zeroing. */
+ do {
+ unsigned long unwritten = clear_user(buf, PAGE_SIZE);
+ if (unwritten)
+ return size + unwritten - PAGE_SIZE;
+ cond_resched();
+ buf += PAGE_SIZE;
+ size -= PAGE_SIZE;
+ } while (size);
+
+ return size;
+out_up:
+ up_read(&mm->mmap_sem);
+ return size;
+}
+
+static ssize_t read_zero(struct file * file, char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long left, unwritten, written = 0;
+
+ if (!count)
+ return 0;
+
+ if (!access_ok(VERIFY_WRITE, buf, count))
+ return -EFAULT;
+
+ left = count;
+
+ /* do we want to be clever? Arbitrary cut-off */
+ if (count >= PAGE_SIZE*4) {
+ unsigned long partial;
+
+ /* How much left of the page? */
+ partial = (PAGE_SIZE-1) & -(unsigned long) buf;
+ unwritten = clear_user(buf, partial);
+ written = partial - unwritten;
+ if (unwritten)
+ goto out;
+ left -= partial;
+ buf += partial;
+ unwritten = read_zero_pagealigned(buf, left & PAGE_MASK);
+ written += (left & PAGE_MASK) - unwritten;
+ if (unwritten)
+ goto out;
+ buf += left & PAGE_MASK;
+ left &= ~PAGE_MASK;
+ }
+ unwritten = clear_user(buf, left);
+ written += left - unwritten;
+out:
+ return written ? written : -EFAULT;
+}
+
+static int mmap_zero(struct file * file, struct vm_area_struct * vma)
+{
+ if (vma->vm_flags & VM_SHARED)
+ return shmem_zero_setup(vma);
+ if (zeromap_page_range(vma, vma->vm_start, vma->vm_end - vma->vm_start,
vma->vm_page_prot))
+ return -EAGAIN;
+ return 0;
+}
+#else /* CONFIG_MMU */
+static ssize_t read_zero(struct file * file, char * buf,
+ size_t count, loff_t *ppos)
+{
+ size_t todo = count;
+
+ while (todo) {
+ size_t chunk = todo;
+
+ if (chunk > 4096)
+ chunk = 4096; /* Just for latency reasons */
+ if (clear_user(buf, chunk))
+ return -EFAULT;
+ buf += chunk;
+ todo -= chunk;
+ cond_resched();
+ }
+ return count;
+}
+
+static int mmap_zero(struct file * file, struct vm_area_struct * vma)
+{
+ return -ENOSYS;
+}
+#endif /* CONFIG_MMU */
+
+static ssize_t write_full(struct file * file, const char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ return -ENOSPC;
+}
+
+/*
+ * Special lseek() function for /dev/null and /dev/zero. Most notably, you
+ * can fopen() both devices with "a" now. This was previously impossible.
+ * -- SRB.
+ */
+
+static loff_t null_lseek(struct file * file, loff_t offset, int orig)
+{
+ return file->f_pos = 0;
+}
+
+/*
+ * The memory devices use the full 32/64 bits of the offset, and so we cannot
+ * check against negative addresses: they are ok. The return value is weird,
+ * though, in that case (0).
+ *
+ * also note that seeking relative to the "end of file" isn't supported:
+ * it has no meaning, so it returns -EINVAL.
+ */
+static loff_t memory_lseek(struct file * file, loff_t offset, int orig)
+{
+ loff_t ret;
+
+ down(&file->f_dentry->d_inode->i_sem);
+ switch (orig) {
+ case 0:
+ file->f_pos = offset;
+ ret = file->f_pos;
+ force_successful_syscall_return();
+ break;
+ case 1:
+ file->f_pos += offset;
+ ret = file->f_pos;
+ force_successful_syscall_return();
+ break;
+ default:
+ ret = -EINVAL;
+ }
+ up(&file->f_dentry->d_inode->i_sem);
+ return ret;
+}
+
+static int open_port(struct inode * inode, struct file * filp)
+{
+ return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
+}
+
+#define mmap_mem mmap_kmem
+#define zero_lseek null_lseek
+#define full_lseek null_lseek
+#define write_zero write_null
+#define read_full read_zero
+#define open_mem open_port
+#define open_kmem open_mem
+
+#ifndef ARCH_HAS_DEV_MEM
+static struct file_operations mem_fops = {
+ .llseek = memory_lseek,
+ .read = read_mem,
+ .write = write_mem,
+ .mmap = mmap_mem,
+ .open = open_mem,
+};
+#else
+extern struct file_operations mem_fops;
+#endif
+
+static struct file_operations kmem_fops = {
+ .llseek = memory_lseek,
+ .read = read_kmem,
+ .write = write_kmem,
+ .mmap = mmap_kmem,
+ .open = open_kmem,
+};
+
+static struct file_operations null_fops = {
+ .llseek = null_lseek,
+ .read = read_null,
+ .write = write_null,
+};
+
+#if defined(CONFIG_ISA) || !defined(__mc68000__)
+static struct file_operations port_fops = {
+ .llseek = memory_lseek,
+ .read = read_port,
+ .write = write_port,
+ .open = open_port,
+};
+#endif
+
+static struct file_operations zero_fops = {
+ .llseek = zero_lseek,
+ .read = read_zero,
+ .write = write_zero,
+ .mmap = mmap_zero,
+};
+
+static struct file_operations full_fops = {
+ .llseek = full_lseek,
+ .read = read_full,
+ .write = write_full,
+};
+
+static ssize_t kmsg_write(struct file * file, const char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ char *tmp;
+ int ret;
+
+ tmp = kmalloc(count + 1, GFP_KERNEL);
+ if (tmp == NULL)
+ return -ENOMEM;
+ ret = -EFAULT;
+ if (!copy_from_user(tmp, buf, count)) {
+ tmp[count] = 0;
+ ret = printk("%s", tmp);
+ }
+ kfree(tmp);
+ return ret;
+}
+
+static struct file_operations kmsg_fops = {
+ .write = kmsg_write,
+};
+
+static int memory_open(struct inode * inode, struct file * filp)
+{
+ switch (iminor(inode)) {
+ case 1:
+ filp->f_op = &mem_fops;
+ break;
+ case 2:
+ filp->f_op = &kmem_fops;
+ break;
+ case 3:
+ filp->f_op = &null_fops;
+ break;
+#if defined(CONFIG_ISA) || !defined(__mc68000__)
+ case 4:
+ filp->f_op = &port_fops;
+ break;
+#endif
+ case 5:
+ filp->f_op = &zero_fops;
+ break;
+ case 7:
+ filp->f_op = &full_fops;
+ break;
+ case 8:
+ filp->f_op = &random_fops;
+ break;
+ case 9:
+ filp->f_op = &urandom_fops;
+ break;
+ case 11:
+ filp->f_op = &kmsg_fops;
+ break;
+ default:
+ return -ENXIO;
+ }
+ if (filp->f_op && filp->f_op->open)
+ return filp->f_op->open(inode,filp);
+ return 0;
+}
+
+static struct file_operations memory_fops = {
+ .open = memory_open, /* just a selector for the real open */
+};
+
+static const struct {
+ unsigned int minor;
+ char *name;
+ umode_t mode;
+ struct file_operations *fops;
+} devlist[] = { /* list of minor devices */
+ {1, "mem", S_IRUSR | S_IWUSR | S_IRGRP, &mem_fops},
+ {2, "kmem", S_IRUSR | S_IWUSR | S_IRGRP, &kmem_fops},
+ {3, "null", S_IRUGO | S_IWUGO, &null_fops},
+#if defined(CONFIG_ISA) || !defined(__mc68000__)
+ {4, "port", S_IRUSR | S_IWUSR | S_IRGRP, &port_fops},
+#endif
+ {5, "zero", S_IRUGO | S_IWUGO, &zero_fops},
+ {7, "full", S_IRUGO | S_IWUGO, &full_fops},
+ {8, "random", S_IRUGO | S_IWUSR, &random_fops},
+ {9, "urandom", S_IRUGO | S_IWUSR, &urandom_fops},
+ {11,"kmsg", S_IRUGO | S_IWUSR, &kmsg_fops},
+};
+
+static struct class_simple *mem_class;
+
+static int __init chr_dev_init(void)
+{
+ int i;
+
+ if (register_chrdev(MEM_MAJOR,"mem",&memory_fops))
+ printk("unable to get major %d for memory devs\n", MEM_MAJOR);
+
+ mem_class = class_simple_create(THIS_MODULE, "mem");
+ for (i = 0; i < ARRAY_SIZE(devlist); i++) {
+ class_simple_device_add(mem_class,
+ MKDEV(MEM_MAJOR, devlist[i].minor),
+ NULL, devlist[i].name);
+ devfs_mk_cdev(MKDEV(MEM_MAJOR, devlist[i].minor),
+ S_IFCHR | devlist[i].mode, devlist[i].name);
+ }
+
+ return 0;
+}
+
+fs_initcall(chr_dev_init);
diff -r 35b74976f598 -r a83ac0806d6b patches/linux-2.6.11/rcu-nohz.patch
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/patches/linux-2.6.11/rcu-nohz.patch Fri Jul 15 13:39:50 2005
@@ -0,0 +1,16 @@
+diff -ur linux-2.6.11/kernel/rcupdate.c linux-2.6.11-rcu/kernel/rcupdate.c
+--- linux-2.6.11/kernel/rcupdate.c 2005-05-30 10:51:41 +01:00
++++ linux-2.6.11-rcu/kernel/rcupdate.c 2005-05-30 10:53:53 +01:00
+@@ -202,8 +202,11 @@
+ */
+ static void cpu_quiet(int cpu, struct rcu_ctrlblk *rcp, struct rcu_state *rsp)
+ {
++ cpumask_t mask;
++
+ cpu_clear(cpu, rsp->cpumask);
+- if (cpus_empty(rsp->cpumask)) {
++ cpus_andnot(mask, rsp->cpumask, nohz_cpu_mask);
++ if (cpus_empty(mask)) {
+ /* batch completed ! */
+ rcp->completed = rcp->cur;
+ rcu_start_batch(rcp, rsp, 0);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/x8664_ksyms.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/x8664_ksyms.c Fri Jul
15 13:39:50 2005
@@ -0,0 +1,225 @@
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/user.h>
+#include <linux/sched.h>
+#include <linux/in6.h>
+#include <linux/interrupt.h>
+#include <linux/smp_lock.h>
+#include <linux/pm.h>
+#include <linux/pci.h>
+#include <linux/apm_bios.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/syscalls.h>
+#include <linux/tty.h>
+#include <linux/ioctl32.h>
+
+#include <asm/semaphore.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/uaccess.h>
+#include <asm/checksum.h>
+#include <asm/io.h>
+#include <asm/delay.h>
+#include <asm/irq.h>
+#include <asm/mmx.h>
+#include <asm/desc.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/nmi.h>
+#include <asm/kdebug.h>
+#include <asm/unistd.h>
+#include <asm/tlbflush.h>
+#include <asm/kdebug.h>
+
+extern spinlock_t rtc_lock;
+
+#ifdef CONFIG_SMP
+extern void __write_lock_failed(rwlock_t *rw);
+extern void __read_lock_failed(rwlock_t *rw);
+#endif
+
+#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) ||
defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE)
+extern struct drive_info_struct drive_info;
+EXPORT_SYMBOL(drive_info);
+#endif
+
+extern unsigned long get_cmos_time(void);
+
+/* platform dependent support */
+EXPORT_SYMBOL(boot_cpu_data);
+//EXPORT_SYMBOL(dump_fpu);
+EXPORT_SYMBOL(__ioremap);
+EXPORT_SYMBOL(ioremap_nocache);
+EXPORT_SYMBOL(iounmap);
+EXPORT_SYMBOL(enable_irq);
+EXPORT_SYMBOL(disable_irq);
+EXPORT_SYMBOL(disable_irq_nosync);
+EXPORT_SYMBOL(probe_irq_mask);
+EXPORT_SYMBOL(kernel_thread);
+EXPORT_SYMBOL(pm_idle);
+#ifdef CONFIG_ACPI_BOOT
+EXPORT_SYMBOL(pm_power_off);
+#endif
+EXPORT_SYMBOL(get_cmos_time);
+
+EXPORT_SYMBOL(__down_failed);
+EXPORT_SYMBOL(__down_failed_interruptible);
+EXPORT_SYMBOL(__down_failed_trylock);
+EXPORT_SYMBOL(__up_wakeup);
+/* Networking helper routines. */
+EXPORT_SYMBOL(csum_partial_copy_nocheck);
+EXPORT_SYMBOL(ip_compute_csum);
+/* Delay loops */
+EXPORT_SYMBOL(__udelay);
+EXPORT_SYMBOL(__ndelay);
+EXPORT_SYMBOL(__delay);
+EXPORT_SYMBOL(__const_udelay);
+
+EXPORT_SYMBOL(__get_user_1);
+EXPORT_SYMBOL(__get_user_2);
+EXPORT_SYMBOL(__get_user_4);
+EXPORT_SYMBOL(__get_user_8);
+EXPORT_SYMBOL(__put_user_1);
+EXPORT_SYMBOL(__put_user_2);
+EXPORT_SYMBOL(__put_user_4);
+EXPORT_SYMBOL(__put_user_8);
+
+EXPORT_SYMBOL(strpbrk);
+EXPORT_SYMBOL(strstr);
+
+EXPORT_SYMBOL(strncpy_from_user);
+EXPORT_SYMBOL(__strncpy_from_user);
+EXPORT_SYMBOL(clear_user);
+EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(copy_user_generic);
+EXPORT_SYMBOL(copy_from_user);
+EXPORT_SYMBOL(copy_to_user);
+EXPORT_SYMBOL(copy_in_user);
+EXPORT_SYMBOL(strnlen_user);
+
+#ifdef CONFIG_PCI
+EXPORT_SYMBOL(pci_alloc_consistent);
+EXPORT_SYMBOL(pci_free_consistent);
+#endif
+
+#ifdef CONFIG_PCI
+EXPORT_SYMBOL(pcibios_penalize_isa_irq);
+EXPORT_SYMBOL(pci_mem_start);
+#endif
+
+EXPORT_SYMBOL(copy_page);
+EXPORT_SYMBOL(clear_page);
+
+EXPORT_SYMBOL(cpu_pda);
+#ifdef CONFIG_SMP
+EXPORT_SYMBOL(cpu_data);
+EXPORT_SYMBOL(cpu_online_map);
+EXPORT_SYMBOL(__write_lock_failed);
+EXPORT_SYMBOL(__read_lock_failed);
+
+EXPORT_SYMBOL(synchronize_irq);
+EXPORT_SYMBOL(smp_call_function);
+EXPORT_SYMBOL(cpu_callout_map);
+#endif
+
+#ifdef CONFIG_VT
+EXPORT_SYMBOL(screen_info);
+#endif
+
+EXPORT_SYMBOL(get_wchan);
+
+EXPORT_SYMBOL(rtc_lock);
+
+/* EXPORT_SYMBOL_GPL(set_nmi_callback);
+ EXPORT_SYMBOL_GPL(unset_nmi_callback); */
+
+/* Export string functions. We normally rely on gcc builtin for most of these,
+ but gcc sometimes decides not to inline them. */
+#undef memcpy
+#undef memset
+#undef memmove
+#undef memchr
+#undef strlen
+#undef strcpy
+#undef strncmp
+#undef strncpy
+#undef strchr
+#undef strcmp
+#undef strcpy
+#undef strcat
+#undef memcmp
+
+extern void * memset(void *,int,__kernel_size_t);
+extern size_t strlen(const char *);
+extern void * memmove(void * dest,const void *src,size_t count);
+extern char * strcpy(char * dest,const char *src);
+extern int strcmp(const char * cs,const char * ct);
+extern void *memchr(const void *s, int c, size_t n);
+extern void * memcpy(void *,const void *,__kernel_size_t);
+extern void * __memcpy(void *,const void *,__kernel_size_t);
+extern char * strcat(char *, const char *);
+extern int memcmp(const void * cs,const void * ct,size_t count);
+
+EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(strlen);
+EXPORT_SYMBOL(memmove);
+EXPORT_SYMBOL(strcpy);
+EXPORT_SYMBOL(strncmp);
+EXPORT_SYMBOL(strncpy);
+EXPORT_SYMBOL(strchr);
+EXPORT_SYMBOL(strcmp);
+EXPORT_SYMBOL(strcat);
+EXPORT_SYMBOL(strncat);
+EXPORT_SYMBOL(memchr);
+EXPORT_SYMBOL(strrchr);
+EXPORT_SYMBOL(strnlen);
+EXPORT_SYMBOL(memscan);
+EXPORT_SYMBOL(memcpy);
+EXPORT_SYMBOL(__memcpy);
+EXPORT_SYMBOL(memcmp);
+
+#ifdef CONFIG_RWSEM_XCHGADD_ALGORITHM
+/* prototypes are wrong, these are assembly with custom calling functions */
+extern void rwsem_down_read_failed_thunk(void);
+extern void rwsem_wake_thunk(void);
+extern void rwsem_downgrade_thunk(void);
+extern void rwsem_down_write_failed_thunk(void);
+EXPORT_SYMBOL(rwsem_down_read_failed_thunk);
+EXPORT_SYMBOL(rwsem_wake_thunk);
+EXPORT_SYMBOL(rwsem_downgrade_thunk);
+EXPORT_SYMBOL(rwsem_down_write_failed_thunk);
+#endif
+
+EXPORT_SYMBOL(empty_zero_page);
+
+#ifdef CONFIG_HAVE_DEC_LOCK
+EXPORT_SYMBOL(_atomic_dec_and_lock);
+#endif
+
+EXPORT_SYMBOL(die_chain);
+EXPORT_SYMBOL(register_die_notifier);
+
+#ifdef CONFIG_SMP
+EXPORT_SYMBOL(cpu_sibling_map);
+EXPORT_SYMBOL(smp_num_siblings);
+#endif
+
+extern void do_softirq_thunk(void);
+EXPORT_SYMBOL(do_softirq_thunk);
+
+void out_of_line_bug(void);
+EXPORT_SYMBOL(out_of_line_bug);
+
+EXPORT_SYMBOL(init_level4_pgt);
+
+extern unsigned long __supported_pte_mask;
+EXPORT_SYMBOL(__supported_pte_mask);
+
+#ifdef CONFIG_SMP
+EXPORT_SYMBOL(flush_tlb_page);
+EXPORT_SYMBOL_GPL(flush_tlb_all);
+#endif
+
+EXPORT_SYMBOL(cpu_khz);
diff -r 35b74976f598 -r a83ac0806d6b linux-2.6.11-xen-sparse/mm/mmap.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/mm/mmap.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,2108 @@
+/*
+ * mm/mmap.c
+ *
+ * Written by obz.
+ *
+ * Address space accounting code <alan@xxxxxxxxxx>
+ */
+
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/shm.h>
+#include <linux/mman.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+#include <linux/syscalls.h>
+#include <linux/init.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/personality.h>
+#include <linux/security.h>
+#include <linux/hugetlb.h>
+#include <linux/profile.h>
+#include <linux/module.h>
+#include <linux/acct.h>
+#include <linux/mount.h>
+#include <linux/mempolicy.h>
+#include <linux/rmap.h>
+
+#include <asm/uaccess.h>
+#include <asm/cacheflush.h>
+#include <asm/tlb.h>
+
+/*
+ * WARNING: the debugging will use recursive algorithms so never enable this
+ * unless you know what you are doing.
+ */
+#undef DEBUG_MM_RB
+
+/* description of effects of mapping type and prot in current implementation.
+ * this is due to the limited x86 page protection hardware. The expected
+ * behavior is in parens:
+ *
+ * map_type prot
+ * PROT_NONE PROT_READ PROT_WRITE PROT_EXEC
+ * MAP_SHARED r: (no) no r: (yes) yes r: (no) yes r: (no) yes
+ * w: (no) no w: (no) no w: (yes) yes w: (no) no
+ * x: (no) no x: (no) yes x: (no) yes x: (yes) yes
+ *
+ * MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes
+ * w: (no) no w: (no) no w: (copy) copy w: (no) no
+ * x: (no) no x: (no) yes x: (no) yes x: (yes) yes
+ *
+ */
+pgprot_t protection_map[16] = {
+ __P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111,
+ __S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111
+};
+
+int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
+int sysctl_overcommit_ratio = 50; /* default is 50% */
+int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
+atomic_t vm_committed_space = ATOMIC_INIT(0);
+
+/*
+ * Check that a process has enough memory to allocate a new virtual
+ * mapping. 0 means there is enough memory for the allocation to
+ * succeed and -ENOMEM implies there is not.
+ *
+ * We currently support three overcommit policies, which are set via the
+ * vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting
+ *
+ * Strict overcommit modes added 2002 Feb 26 by Alan Cox.
+ * Additional code 2002 Jul 20 by Robert Love.
+ *
+ * cap_sys_admin is 1 if the process has admin privileges, 0 otherwise.
+ *
+ * Note this is a helper function intended to be used by LSMs which
+ * wish to use this logic.
+ */
+int __vm_enough_memory(long pages, int cap_sys_admin)
+{
+ unsigned long free, allowed;
+
+ vm_acct_memory(pages);
+
+ /*
+ * Sometimes we want to use more memory than we have
+ */
+ if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS)
+ return 0;
+
+ if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
+ unsigned long n;
+
+ free = get_page_cache_size();
+ free += nr_swap_pages;
+
+ /*
+ * Any slabs which are created with the
+ * SLAB_RECLAIM_ACCOUNT flag claim to have contents
+ * which are reclaimable, under pressure. The dentry
+ * cache and most inode caches should fall into this
+ */
+ free += atomic_read(&slab_reclaim_pages);
+
+ /*
+ * Leave the last 3% for root
+ */
+ if (!cap_sys_admin)
+ free -= free / 32;
+
+ if (free > pages)
+ return 0;
+
+ /*
+ * nr_free_pages() is very expensive on large systems,
+ * only call if we're about to fail.
+ */
+ n = nr_free_pages();
+ if (!cap_sys_admin)
+ n -= n / 32;
+ free += n;
+
+ if (free > pages)
+ return 0;
+ vm_unacct_memory(pages);
+ return -ENOMEM;
+ }
+
+ allowed = (totalram_pages - hugetlb_total_pages())
+ * sysctl_overcommit_ratio / 100;
+ /*
+ * Leave the last 3% for root
+ */
+ if (!cap_sys_admin)
+ allowed -= allowed / 32;
+ allowed += total_swap_pages;
+
+ /* Don't let a single process grow too big:
+ leave 3% of the size of this process for other processes */
+ allowed -= current->mm->total_vm / 32;
+
+ if (atomic_read(&vm_committed_space) < allowed)
+ return 0;
+
+ vm_unacct_memory(pages);
+
+ return -ENOMEM;
+}
+
+EXPORT_SYMBOL(sysctl_overcommit_memory);
+EXPORT_SYMBOL(sysctl_overcommit_ratio);
+EXPORT_SYMBOL(sysctl_max_map_count);
+EXPORT_SYMBOL(vm_committed_space);
+EXPORT_SYMBOL(__vm_enough_memory);
+
+/*
+ * Requires inode->i_mapping->i_mmap_lock
+ */
+static void __remove_shared_vm_struct(struct vm_area_struct *vma,
+ struct file *file, struct address_space *mapping)
+{
+ if (vma->vm_flags & VM_DENYWRITE)
+ atomic_inc(&file->f_dentry->d_inode->i_writecount);
+ if (vma->vm_flags & VM_SHARED)
+ mapping->i_mmap_writable--;
+
+ flush_dcache_mmap_lock(mapping);
+ if (unlikely(vma->vm_flags & VM_NONLINEAR))
+ list_del_init(&vma->shared.vm_set.list);
+ else
+ vma_prio_tree_remove(vma, &mapping->i_mmap);
+ flush_dcache_mmap_unlock(mapping);
+}
+
+/*
+ * Remove one vm structure and free it.
+ */
+static void remove_vm_struct(struct vm_area_struct *vma)
+{
+ struct file *file = vma->vm_file;
+
+ might_sleep();
+ if (file) {
+ struct address_space *mapping = file->f_mapping;
+ spin_lock(&mapping->i_mmap_lock);
+ __remove_shared_vm_struct(vma, file, mapping);
+ spin_unlock(&mapping->i_mmap_lock);
+ }
+ if (vma->vm_ops && vma->vm_ops->close)
+ vma->vm_ops->close(vma);
+ if (file)
+ fput(file);
+ anon_vma_unlink(vma);
+ mpol_free(vma_policy(vma));
+ kmem_cache_free(vm_area_cachep, vma);
+}
+
+/*
+ * sys_brk() for the most part doesn't need the global kernel
+ * lock, except when an application is doing something nasty
+ * like trying to un-brk an area that has already been mapped
+ * to a regular file. in this case, the unmapping will need
+ * to invoke file system routines that need the global lock.
+ */
+asmlinkage unsigned long sys_brk(unsigned long brk)
+{
+ unsigned long rlim, retval;
+ unsigned long newbrk, oldbrk;
+ struct mm_struct *mm = current->mm;
+
+ down_write(&mm->mmap_sem);
+
+ if (brk < mm->end_code)
+ goto out;
+ newbrk = PAGE_ALIGN(brk);
+ oldbrk = PAGE_ALIGN(mm->brk);
+ if (oldbrk == newbrk)
+ goto set_brk;
+
+ /* Always allow shrinking brk. */
+ if (brk <= mm->brk) {
+ if (!do_munmap(mm, newbrk, oldbrk-newbrk))
+ goto set_brk;
+ goto out;
+ }
+
+ /* Check against rlimit.. */
+ rlim = current->signal->rlim[RLIMIT_DATA].rlim_cur;
+ if (rlim < RLIM_INFINITY && brk - mm->start_data > rlim)
+ goto out;
+
+ /* Check against existing mmap mappings. */
+ if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE))
+ goto out;
+
+ /* Ok, looks good - let it rip. */
+ if (do_brk(oldbrk, newbrk-oldbrk) != oldbrk)
+ goto out;
+set_brk:
+ mm->brk = brk;
+out:
+ retval = mm->brk;
+ up_write(&mm->mmap_sem);
+ return retval;
+}
+
+#ifdef DEBUG_MM_RB
+static int browse_rb(struct rb_root *root)
+{
+ int i = 0, j;
+ struct rb_node *nd, *pn = NULL;
+ unsigned long prev = 0, pend = 0;
+
+ for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+ struct vm_area_struct *vma;
+ vma = rb_entry(nd, struct vm_area_struct, vm_rb);
+ if (vma->vm_start < prev)
+ printk("vm_start %lx prev %lx\n", vma->vm_start, prev),
i = -1;
+ if (vma->vm_start < pend)
+ printk("vm_start %lx pend %lx\n", vma->vm_start, pend);
+ if (vma->vm_start > vma->vm_end)
+ printk("vm_end %lx < vm_start %lx\n", vma->vm_end,
vma->vm_start);
+ i++;
+ pn = nd;
+ }
+ j = 0;
+ for (nd = pn; nd; nd = rb_prev(nd)) {
+ j++;
+ }
+ if (i != j)
+ printk("backwards %d, forwards %d\n", j, i), i = 0;
+ return i;
+}
+
+void validate_mm(struct mm_struct *mm)
+{
+ int bug = 0;
+ int i = 0;
+ struct vm_area_struct *tmp = mm->mmap;
+ while (tmp) {
+ tmp = tmp->vm_next;
+ i++;
+ }
+ if (i != mm->map_count)
+ printk("map_count %d vm_next %d\n", mm->map_count, i), bug = 1;
+ i = browse_rb(&mm->mm_rb);
+ if (i != mm->map_count)
+ printk("map_count %d rb %d\n", mm->map_count, i), bug = 1;
+ if (bug)
+ BUG();
+}
+#else
+#define validate_mm(mm) do { } while (0)
+#endif
+
+static struct vm_area_struct *
+find_vma_prepare(struct mm_struct *mm, unsigned long addr,
+ struct vm_area_struct **pprev, struct rb_node ***rb_link,
+ struct rb_node ** rb_parent)
+{
+ struct vm_area_struct * vma;
+ struct rb_node ** __rb_link, * __rb_parent, * rb_prev;
+
+ __rb_link = &mm->mm_rb.rb_node;
+ rb_prev = __rb_parent = NULL;
+ vma = NULL;
+
+ while (*__rb_link) {
+ struct vm_area_struct *vma_tmp;
+
+ __rb_parent = *__rb_link;
+ vma_tmp = rb_entry(__rb_parent, struct vm_area_struct, vm_rb);
+
+ if (vma_tmp->vm_end > addr) {
+ vma = vma_tmp;
+ if (vma_tmp->vm_start <= addr)
+ return vma;
+ __rb_link = &__rb_parent->rb_left;
+ } else {
+ rb_prev = __rb_parent;
+ __rb_link = &__rb_parent->rb_right;
+ }
+ }
+
+ *pprev = NULL;
+ if (rb_prev)
+ *pprev = rb_entry(rb_prev, struct vm_area_struct, vm_rb);
+ *rb_link = __rb_link;
+ *rb_parent = __rb_parent;
+ return vma;
+}
+
+static inline void
+__vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
+ struct vm_area_struct *prev, struct rb_node *rb_parent)
+{
+ if (prev) {
+ vma->vm_next = prev->vm_next;
+ prev->vm_next = vma;
+ } else {
+ mm->mmap = vma;
+ if (rb_parent)
+ vma->vm_next = rb_entry(rb_parent,
+ struct vm_area_struct, vm_rb);
+ else
+ vma->vm_next = NULL;
+ }
+}
+
+void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
+ struct rb_node **rb_link, struct rb_node *rb_parent)
+{
+ rb_link_node(&vma->vm_rb, rb_parent, rb_link);
+ rb_insert_color(&vma->vm_rb, &mm->mm_rb);
+}
+
+static inline void __vma_link_file(struct vm_area_struct *vma)
+{
+ struct file * file;
+
+ file = vma->vm_file;
+ if (file) {
+ struct address_space *mapping = file->f_mapping;
+
+ if (vma->vm_flags & VM_DENYWRITE)
+ atomic_dec(&file->f_dentry->d_inode->i_writecount);
+ if (vma->vm_flags & VM_SHARED)
+ mapping->i_mmap_writable++;
+
+ flush_dcache_mmap_lock(mapping);
+ if (unlikely(vma->vm_flags & VM_NONLINEAR))
+ vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
+ else
+ vma_prio_tree_insert(vma, &mapping->i_mmap);
+ flush_dcache_mmap_unlock(mapping);
+ }
+}
+
+static void
+__vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
+ struct vm_area_struct *prev, struct rb_node **rb_link,
+ struct rb_node *rb_parent)
+{
+ __vma_link_list(mm, vma, prev, rb_parent);
+ __vma_link_rb(mm, vma, rb_link, rb_parent);
+ __anon_vma_link(vma);
+}
+
+static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
+ struct vm_area_struct *prev, struct rb_node **rb_link,
+ struct rb_node *rb_parent)
+{
+ struct address_space *mapping = NULL;
+
+ if (vma->vm_file)
+ mapping = vma->vm_file->f_mapping;
+
+ if (mapping) {
+ spin_lock(&mapping->i_mmap_lock);
+ vma->vm_truncate_count = mapping->truncate_count;
+ }
+ anon_vma_lock(vma);
+
+ __vma_link(mm, vma, prev, rb_link, rb_parent);
+ __vma_link_file(vma);
+
+ anon_vma_unlock(vma);
+ if (mapping)
+ spin_unlock(&mapping->i_mmap_lock);
+
+ mm->map_count++;
+ validate_mm(mm);
+}
+
+/*
+ * Helper for vma_adjust in the split_vma insert case:
+ * insert vm structure into list and rbtree and anon_vma,
+ * but it has already been inserted into prio_tree earlier.
+ */
+static void
+__insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
+{
+ struct vm_area_struct * __vma, * prev;
+ struct rb_node ** rb_link, * rb_parent;
+
+ __vma = find_vma_prepare(mm, vma->vm_start,&prev, &rb_link, &rb_parent);
+ if (__vma && __vma->vm_start < vma->vm_end)
+ BUG();
+ __vma_link(mm, vma, prev, rb_link, rb_parent);
+ mm->map_count++;
+}
+
+static inline void
+__vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma,
+ struct vm_area_struct *prev)
+{
+ prev->vm_next = vma->vm_next;
+ rb_erase(&vma->vm_rb, &mm->mm_rb);
+ if (mm->mmap_cache == vma)
+ mm->mmap_cache = prev;
+}
+
+/*
+ * We cannot adjust vm_start, vm_end, vm_pgoff fields of a vma that
+ * is already present in an i_mmap tree without adjusting the tree.
+ * The following helper function should be used when such adjustments
+ * are necessary. The "insert" vma (if any) is to be inserted
+ * before we drop the necessary locks.
+ */
+void vma_adjust(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ struct vm_area_struct *next = vma->vm_next;
+ struct vm_area_struct *importer = NULL;
+ struct address_space *mapping = NULL;
+ struct prio_tree_root *root = NULL;
+ struct file *file = vma->vm_file;
+ struct anon_vma *anon_vma = NULL;
+ long adjust_next = 0;
+ int remove_next = 0;
+
+ if (next && !insert) {
+ if (end >= next->vm_end) {
+ /*
+ * vma expands, overlapping all the next, and
+ * perhaps the one after too (mprotect case 6).
+ */
+again: remove_next = 1 + (end > next->vm_end);
+ end = next->vm_end;
+ anon_vma = next->anon_vma;
+ importer = vma;
+ } else if (end > next->vm_start) {
+ /*
+ * vma expands, overlapping part of the next:
+ * mprotect case 5 shifting the boundary up.
+ */
+ adjust_next = (end - next->vm_start) >> PAGE_SHIFT;
+ anon_vma = next->anon_vma;
+ importer = vma;
+ } else if (end < vma->vm_end) {
+ /*
+ * vma shrinks, and !insert tells it's not
+ * split_vma inserting another: so it must be
+ * mprotect case 4 shifting the boundary down.
+ */
+ adjust_next = - ((vma->vm_end - end) >> PAGE_SHIFT);
+ anon_vma = next->anon_vma;
+ importer = next;
+ }
+ }
+
+ if (file) {
+ mapping = file->f_mapping;
+ if (!(vma->vm_flags & VM_NONLINEAR))
+ root = &mapping->i_mmap;
+ spin_lock(&mapping->i_mmap_lock);
+ if (importer &&
+ vma->vm_truncate_count != next->vm_truncate_count) {
+ /*
+ * unmap_mapping_range might be in progress:
+ * ensure that the expanding vma is rescanned.
+ */
+ importer->vm_truncate_count = 0;
+ }
+ if (insert) {
+ insert->vm_truncate_count = vma->vm_truncate_count;
+ /*
+ * Put into prio_tree now, so instantiated pages
+ * are visible to arm/parisc __flush_dcache_page
+ * throughout; but we cannot insert into address
+ * space until vma start or end is updated.
+ */
+ __vma_link_file(insert);
+ }
+ }
+
+ /*
+ * When changing only vma->vm_end, we don't really need
+ * anon_vma lock: but is that case worth optimizing out?
+ */
+ if (vma->anon_vma)
+ anon_vma = vma->anon_vma;
+ if (anon_vma) {
+ spin_lock(&anon_vma->lock);
+ /*
+ * Easily overlooked: when mprotect shifts the boundary,
+ * make sure the expanding vma has anon_vma set if the
+ * shrinking vma had, to cover any anon pages imported.
+ */
+ if (importer && !importer->anon_vma) {
+ importer->anon_vma = anon_vma;
+ __anon_vma_link(importer);
+ }
+ }
+
+ if (root) {
+ flush_dcache_mmap_lock(mapping);
+ vma_prio_tree_remove(vma, root);
+ if (adjust_next)
+ vma_prio_tree_remove(next, root);
+ }
+
+ vma->vm_start = start;
+ vma->vm_end = end;
+ vma->vm_pgoff = pgoff;
+ if (adjust_next) {
+ next->vm_start += adjust_next << PAGE_SHIFT;
+ next->vm_pgoff += adjust_next;
+ }
+
+ if (root) {
+ if (adjust_next)
+ vma_prio_tree_insert(next, root);
+ vma_prio_tree_insert(vma, root);
+ flush_dcache_mmap_unlock(mapping);
+ }
+
+ if (remove_next) {
+ /*
+ * vma_merge has merged next into vma, and needs
+ * us to remove next before dropping the locks.
+ */
+ __vma_unlink(mm, next, vma);
+ if (file)
+ __remove_shared_vm_struct(next, file, mapping);
+ if (next->anon_vma)
+ __anon_vma_merge(vma, next);
+ } else if (insert) {
+ /*
+ * split_vma has split insert from vma, and needs
+ * us to insert it before dropping the locks
+ * (it may either follow vma or precede it).
+ */
+ __insert_vm_struct(mm, insert);
+ }
+
+ if (anon_vma)
+ spin_unlock(&anon_vma->lock);
+ if (mapping)
+ spin_unlock(&mapping->i_mmap_lock);
+
+ if (remove_next) {
+ if (file)
+ fput(file);
+ mm->map_count--;
+ mpol_free(vma_policy(next));
+ kmem_cache_free(vm_area_cachep, next);
+ /*
+ * In mprotect's case 6 (see comments on vma_merge),
+ * we must remove another next too. It would clutter
+ * up the code too much to do both in one go.
+ */
+ if (remove_next == 2) {
+ next = vma->vm_next;
+ goto again;
+ }
+ }
+
+ validate_mm(mm);
+}
+
+/*
+ * If the vma has a ->close operation then the driver probably needs to release
+ * per-vma resources, so we don't attempt to merge those.
+ */
+#define VM_SPECIAL (VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_RESERVED)
+
+static inline int is_mergeable_vma(struct vm_area_struct *vma,
+ struct file *file, unsigned long vm_flags)
+{
+ if (vma->vm_flags != vm_flags)
+ return 0;
+ if (vma->vm_file != file)
+ return 0;
+ if (vma->vm_ops && vma->vm_ops->close)
+ return 0;
+ return 1;
+}
+
+static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1,
+ struct anon_vma *anon_vma2)
+{
+ return !anon_vma1 || !anon_vma2 || (anon_vma1 == anon_vma2);
+}
+
+/*
+ * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff)
+ * in front of (at a lower virtual address and file offset than) the vma.
+ *
+ * We cannot merge two vmas if they have differently assigned (non-NULL)
+ * anon_vmas, nor if same anon_vma is assigned but offsets incompatible.
+ *
+ * We don't check here for the merged mmap wrapping around the end of pagecache
+ * indices (16TB on ia32) because do_mmap_pgoff() does not permit mmap's which
+ * wrap, nor mmaps which cover the final page at index -1UL.
+ */
+static int
+can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
+ struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
+{
+ if (is_mergeable_vma(vma, file, vm_flags) &&
+ is_mergeable_anon_vma(anon_vma, vma->anon_vma)) {
+ if (vma->vm_pgoff == vm_pgoff)
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff)
+ * beyond (at a higher virtual address and file offset than) the vma.
+ *
+ * We cannot merge two vmas if they have differently assigned (non-NULL)
+ * anon_vmas, nor if same anon_vma is assigned but offsets incompatible.
+ */
+static int
+can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
+ struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
+{
+ if (is_mergeable_vma(vma, file, vm_flags) &&
+ is_mergeable_anon_vma(anon_vma, vma->anon_vma)) {
+ pgoff_t vm_pglen;
+ vm_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+ if (vma->vm_pgoff + vm_pglen == vm_pgoff)
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out
+ * whether that can be merged with its predecessor or its successor.
+ * Or both (it neatly fills a hole).
+ *
+ * In most cases - when called for mmap, brk or mremap - [addr,end) is
+ * certain not to be mapped by the time vma_merge is called; but when
+ * called for mprotect, it is certain to be already mapped (either at
+ * an offset within prev, or at the start of next), and the flags of
+ * this area are about to be changed to vm_flags - and the no-change
+ * case has already been eliminated.
+ *
+ * The following mprotect cases have to be considered, where AAAA is
+ * the area passed down from mprotect_fixup, never extending beyond one
+ * vma, PPPPPP is the prev vma specified, and NNNNNN the next vma after:
+ *
+ * AAAA AAAA AAAA AAAA
+ * PPPPPPNNNNNN PPPPPPNNNNNN PPPPPPNNNNNN PPPPNNNNXXXX
+ * cannot merge might become might become might become
+ * PPNNNNNNNNNN PPPPPPPPPPNN PPPPPPPPPPPP 6 or
+ * mmap, brk or case 4 below case 5 below PPPPPPPPXXXX 7 or
+ * mremap move: PPPPNNNNNNNN 8
+ * AAAA
+ * PPPP NNNN PPPPPPPPPPPP PPPPPPPPNNNN PPPPNNNNNNNN
+ * might become case 1 below case 2 below case 3 below
+ *
+ * Odd one out? Case 8, because it extends NNNN but needs flags of XXXX:
+ * mprotect_fixup updates vm_flags & vm_page_prot on successful return.
+ */
+struct vm_area_struct *vma_merge(struct mm_struct *mm,
+ struct vm_area_struct *prev, unsigned long addr,
+ unsigned long end, unsigned long vm_flags,
+ struct anon_vma *anon_vma, struct file *file,
+ pgoff_t pgoff, struct mempolicy *policy)
+{
+ pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
+ struct vm_area_struct *area, *next;
+
+ /*
+ * We later require that vma->vm_flags == vm_flags,
+ * so this tests vma->vm_flags & VM_SPECIAL, too.
+ */
+ if (vm_flags & VM_SPECIAL)
+ return NULL;
+
+ if (prev)
+ next = prev->vm_next;
+ else
+ next = mm->mmap;
+ area = next;
+ if (next && next->vm_end == end) /* cases 6, 7, 8 */
+ next = next->vm_next;
+
+ /*
+ * Can it merge with the predecessor?
+ */
+ if (prev && prev->vm_end == addr &&
+ mpol_equal(vma_policy(prev), policy) &&
+ can_vma_merge_after(prev, vm_flags,
+ anon_vma, file, pgoff)) {
+ /*
+ * OK, it can. Can we now merge in the successor as well?
+ */
+ if (next && end == next->vm_start &&
+ mpol_equal(policy, vma_policy(next)) &&
+ can_vma_merge_before(next, vm_flags,
+ anon_vma, file, pgoff+pglen) &&
+ is_mergeable_anon_vma(prev->anon_vma,
+ next->anon_vma)) {
+ /* cases 1, 6 */
+ vma_adjust(prev, prev->vm_start,
+ next->vm_end, prev->vm_pgoff, NULL);
+ } else /* cases 2, 5, 7 */
+ vma_adjust(prev, prev->vm_start,
+ end, prev->vm_pgoff, NULL);
+ return prev;
+ }
+
+ /*
+ * Can this new request be merged in front of next?
+ */
+ if (next && end == next->vm_start &&
+ mpol_equal(policy, vma_policy(next)) &&
+ can_vma_merge_before(next, vm_flags,
+ anon_vma, file, pgoff+pglen)) {
+ if (prev && addr < prev->vm_end) /* case 4 */
+ vma_adjust(prev, prev->vm_start,
+ addr, prev->vm_pgoff, NULL);
+ else /* cases 3, 8 */
+ vma_adjust(area, addr, next->vm_end,
+ next->vm_pgoff - pglen, NULL);
+ return area;
+ }
+
+ return NULL;
+}
+
+/*
+ * find_mergeable_anon_vma is used by anon_vma_prepare, to check
+ * neighbouring vmas for a suitable anon_vma, before it goes off
+ * to allocate a new anon_vma. It checks because a repetitive
+ * sequence of mprotects and faults may otherwise lead to distinct
+ * anon_vmas being allocated, preventing vma merge in subsequent
+ * mprotect.
+ */
+struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma)
+{
+ struct vm_area_struct *near;
+ unsigned long vm_flags;
+
+ near = vma->vm_next;
+ if (!near)
+ goto try_prev;
+
+ /*
+ * Since only mprotect tries to remerge vmas, match flags
+ * which might be mprotected into each other later on.
+ * Neither mlock nor madvise tries to remerge at present,
+ * so leave their flags as obstructing a merge.
+ */
+ vm_flags = vma->vm_flags & ~(VM_READ|VM_WRITE|VM_EXEC);
+ vm_flags |= near->vm_flags & (VM_READ|VM_WRITE|VM_EXEC);
+
+ if (near->anon_vma && vma->vm_end == near->vm_start &&
+ mpol_equal(vma_policy(vma), vma_policy(near)) &&
+ can_vma_merge_before(near, vm_flags,
+ NULL, vma->vm_file, vma->vm_pgoff +
+ ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT)))
+ return near->anon_vma;
+try_prev:
+ /*
+ * It is potentially slow to have to call find_vma_prev here.
+ * But it's only on the first write fault on the vma, not
+ * every time, and we could devise a way to avoid it later
+ * (e.g. stash info in next's anon_vma_node when assigning
+ * an anon_vma, or when trying vma_merge). Another time.
+ */
+ if (find_vma_prev(vma->vm_mm, vma->vm_start, &near) != vma)
+ BUG();
+ if (!near)
+ goto none;
+
+ vm_flags = vma->vm_flags & ~(VM_READ|VM_WRITE|VM_EXEC);
+ vm_flags |= near->vm_flags & (VM_READ|VM_WRITE|VM_EXEC);
+
+ if (near->anon_vma && near->vm_end == vma->vm_start &&
+ mpol_equal(vma_policy(near), vma_policy(vma)) &&
+ can_vma_merge_after(near, vm_flags,
+ NULL, vma->vm_file, vma->vm_pgoff))
+ return near->anon_vma;
+none:
+ /*
+ * There's no absolute need to look only at touching neighbours:
+ * we could search further afield for "compatible" anon_vmas.
+ * But it would probably just be a waste of time searching,
+ * or lead to too many vmas hanging off the same anon_vma.
+ * We're trying to allow mprotect remerging later on,
+ * not trying to minimize memory used for anon_vmas.
+ */
+ return NULL;
+}
+
+#ifdef CONFIG_PROC_FS
+void __vm_stat_account(struct mm_struct *mm, unsigned long flags,
+ struct file *file, long pages)
+{
+ const unsigned long stack_flags
+ = VM_STACK_FLAGS & (VM_GROWSUP|VM_GROWSDOWN);
+
+#ifdef CONFIG_HUGETLB
+ if (flags & VM_HUGETLB) {
+ if (!(flags & VM_DONTCOPY))
+ mm->shared_vm += pages;
+ return;
+ }
+#endif /* CONFIG_HUGETLB */
+
+ if (file) {
+ mm->shared_vm += pages;
+ if ((flags & (VM_EXEC|VM_WRITE)) == VM_EXEC)
+ mm->exec_vm += pages;
+ } else if (flags & stack_flags)
+ mm->stack_vm += pages;
+ if (flags & (VM_RESERVED|VM_IO))
+ mm->reserved_vm += pages;
+}
+#endif /* CONFIG_PROC_FS */
+
+/*
+ * The caller must hold down_write(current->mm->mmap_sem).
+ */
+
+unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
+ unsigned long len, unsigned long prot,
+ unsigned long flags, unsigned long pgoff)
+{
+ struct mm_struct * mm = current->mm;
+ struct vm_area_struct * vma, * prev;
+ struct inode *inode;
+ unsigned int vm_flags;
+ int correct_wcount = 0;
+ int error;
+ struct rb_node ** rb_link, * rb_parent;
+ int accountable = 1;
+ unsigned long charged = 0;
+
+ if (file) {
+ if (is_file_hugepages(file))
+ accountable = 0;
+
+ if (!file->f_op || !file->f_op->mmap)
+ return -ENODEV;
+
+ if ((prot & PROT_EXEC) &&
+ (file->f_vfsmnt->mnt_flags & MNT_NOEXEC))
+ return -EPERM;
+ }
+ /*
+ * Does the application expect PROT_READ to imply PROT_EXEC?
+ *
+ * (the exception is when the underlying filesystem is noexec
+ * mounted, in which case we dont add PROT_EXEC.)
+ */
+ if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
+ if (!(file && (file->f_vfsmnt->mnt_flags & MNT_NOEXEC)))
+ prot |= PROT_EXEC;
+
+ if (!len)
+ return addr;
+
+ /* Careful about overflows.. */
+ len = PAGE_ALIGN(len);
+ if (!len || len > TASK_SIZE)
+ return -EINVAL;
+
+ /* offset overflow? */
+ if ((pgoff + (len >> PAGE_SHIFT)) < pgoff)
+ return -EINVAL;
+
+ /* Too many mappings? */
+ if (mm->map_count > sysctl_max_map_count)
+ return -ENOMEM;
+
+ /* Obtain the address to map to. we verify (or select) it and ensure
+ * that it represents a valid section of the address space.
+ */
+ addr = get_unmapped_area(file, addr, len, pgoff, flags);
+ if (addr & ~PAGE_MASK)
+ return addr;
+
+ /* Do simple checking here so the lower-level routines won't have
+ * to. we assume access permissions have been handled by the open
+ * of the memory object, so we don't do any here.
+ */
+ vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags) |
+ mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
+
+ if (flags & MAP_LOCKED) {
+ if (!can_do_mlock())
+ return -EPERM;
+ vm_flags |= VM_LOCKED;
+ }
+ /* mlock MCL_FUTURE? */
+ if (vm_flags & VM_LOCKED) {
+ unsigned long locked, lock_limit;
+ locked = mm->locked_vm << PAGE_SHIFT;
+ lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
+ locked += len;
+ if (locked > lock_limit && !capable(CAP_IPC_LOCK))
+ return -EAGAIN;
+ }
+
+ inode = file ? file->f_dentry->d_inode : NULL;
+
+ if (file) {
+ switch (flags & MAP_TYPE) {
+ case MAP_SHARED:
+ if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE))
+ return -EACCES;
+
+ /*
+ * Make sure we don't allow writing to an append-only
+ * file..
+ */
+ if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE))
+ return -EACCES;
+
+ /*
+ * Make sure there are no mandatory locks on the file.
+ */
+ if (locks_verify_locked(inode))
+ return -EAGAIN;
+
+ vm_flags |= VM_SHARED | VM_MAYSHARE;
+ if (!(file->f_mode & FMODE_WRITE))
+ vm_flags &= ~(VM_MAYWRITE | VM_SHARED);
+
+ /* fall through */
+ case MAP_PRIVATE:
+ if (!(file->f_mode & FMODE_READ))
+ return -EACCES;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+ } else {
+ switch (flags & MAP_TYPE) {
+ case MAP_SHARED:
+ vm_flags |= VM_SHARED | VM_MAYSHARE;
+ break;
+ case MAP_PRIVATE:
+ /*
+ * Set pgoff according to addr for anon_vma.
+ */
+ pgoff = addr >> PAGE_SHIFT;
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+
+ error = security_file_mmap(file, prot, flags);
+ if (error)
+ return error;
+
+ /* Clear old maps */
+ error = -ENOMEM;
+munmap_back:
+ vma = find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent);
+ if (vma && vma->vm_start < addr + len) {
+ if (do_munmap(mm, addr, len))
+ return -ENOMEM;
+ goto munmap_back;
+ }
+
+ /* Check against address space limit. */
+ if ((mm->total_vm << PAGE_SHIFT) + len
+ > current->signal->rlim[RLIMIT_AS].rlim_cur)
+ return -ENOMEM;
+
+ if (accountable && (!(flags & MAP_NORESERVE) ||
+ sysctl_overcommit_memory == OVERCOMMIT_NEVER)) {
+ if (vm_flags & VM_SHARED) {
+ /* Check memory availability in shmem_file_setup? */
+ vm_flags |= VM_ACCOUNT;
+ } else if (vm_flags & VM_WRITE) {
+ /*
+ * Private writable mapping: check memory availability
+ */
+ charged = len >> PAGE_SHIFT;
+ if (security_vm_enough_memory(charged))
+ return -ENOMEM;
+ vm_flags |= VM_ACCOUNT;
+ }
+ }
+
+ /*
+ * Can we just expand an old private anonymous mapping?
+ * The VM_SHARED test is necessary because shmem_zero_setup
+ * will create the file object for a shared anonymous map below.
+ */
+ if (!file && !(vm_flags & VM_SHARED) &&
+ vma_merge(mm, prev, addr, addr + len, vm_flags,
+ NULL, NULL, pgoff, NULL))
+ goto out;
+
+ /*
+ * Determine the object being mapped and call the appropriate
+ * specific mapper. the address has already been validated, but
+ * not unmapped, but the maps are removed from the list.
+ */
+ vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ if (!vma) {
+ error = -ENOMEM;
+ goto unacct_error;
+ }
+ memset(vma, 0, sizeof(*vma));
+
+ vma->vm_mm = mm;
+ vma->vm_start = addr;
+ vma->vm_end = addr + len;
+ vma->vm_flags = vm_flags;
+ vma->vm_page_prot = protection_map[vm_flags & 0x0f];
+ vma->vm_pgoff = pgoff;
+
+ if (file) {
+ error = -EINVAL;
+ if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
+ goto free_vma;
+ if (vm_flags & VM_DENYWRITE) {
+ error = deny_write_access(file);
+ if (error)
+ goto free_vma;
+ correct_wcount = 1;
+ }
+ vma->vm_file = file;
+ get_file(file);
+ error = file->f_op->mmap(file, vma);
+ if (error)
+ goto unmap_and_free_vma;
+ } else if (vm_flags & VM_SHARED) {
+ error = shmem_zero_setup(vma);
+ if (error)
+ goto free_vma;
+ }
+
+ /* We set VM_ACCOUNT in a shared mapping's vm_flags, to inform
+ * shmem_zero_setup (perhaps called through /dev/zero's ->mmap)
+ * that memory reservation must be checked; but that reservation
+ * belongs to shared memory object, not to vma: so now clear it.
+ */
+ if ((vm_flags & (VM_SHARED|VM_ACCOUNT)) == (VM_SHARED|VM_ACCOUNT))
+ vma->vm_flags &= ~VM_ACCOUNT;
+
+ /* Can addr have changed??
+ *
+ * Answer: Yes, several device drivers can do it in their
+ * f_op->mmap method. -DaveM
+ */
+ addr = vma->vm_start;
+ pgoff = vma->vm_pgoff;
+ vm_flags = vma->vm_flags;
+
+ if (!file || !vma_merge(mm, prev, addr, vma->vm_end,
+ vma->vm_flags, NULL, file, pgoff, vma_policy(vma))) {
+ file = vma->vm_file;
+ vma_link(mm, vma, prev, rb_link, rb_parent);
+ if (correct_wcount)
+ atomic_inc(&inode->i_writecount);
+ } else {
+ if (file) {
+ if (correct_wcount)
+ atomic_inc(&inode->i_writecount);
+ fput(file);
+ }
+ mpol_free(vma_policy(vma));
+ kmem_cache_free(vm_area_cachep, vma);
+ }
+out:
+ mm->total_vm += len >> PAGE_SHIFT;
+ __vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
+ if (vm_flags & VM_LOCKED) {
+ mm->locked_vm += len >> PAGE_SHIFT;
+ make_pages_present(addr, addr + len);
+ }
+ if (flags & MAP_POPULATE) {
+ up_write(&mm->mmap_sem);
+ sys_remap_file_pages(addr, len, 0,
+ pgoff, flags & MAP_NONBLOCK);
+ down_write(&mm->mmap_sem);
+ }
+ acct_update_integrals();
+ update_mem_hiwater();
+ return addr;
+
+unmap_and_free_vma:
+ if (correct_wcount)
+ atomic_inc(&inode->i_writecount);
+ vma->vm_file = NULL;
+ fput(file);
+
+ /* Undo any partial mapping done by a device driver. */
+ zap_page_range(vma, vma->vm_start, vma->vm_end - vma->vm_start, NULL);
+free_vma:
+ kmem_cache_free(vm_area_cachep, vma);
+unacct_error:
+ if (charged)
+ vm_unacct_memory(charged);
+ return error;
+}
+
+EXPORT_SYMBOL(do_mmap_pgoff);
+
+/* Get an address range which is currently unmapped.
+ * For shmat() with addr=0.
+ *
+ * Ugly calling convention alert:
+ * Return value with the low bits set means error value,
+ * ie
+ * if (ret & ~PAGE_MASK)
+ * error = ret;
+ *
+ * This function "knows" that -ENOMEM has the bits set.
+ */
+#ifndef HAVE_ARCH_UNMAPPED_AREA
+unsigned long
+arch_get_unmapped_area(struct file *filp, unsigned long addr,
+ unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ unsigned long start_addr;
+
+ if (len > TASK_SIZE)
+ return -ENOMEM;
+
+ if (addr) {
+ addr = PAGE_ALIGN(addr);
+ vma = find_vma(mm, addr);
+ if (TASK_SIZE - len >= addr &&
+ (!vma || addr + len <= vma->vm_start))
+ return addr;
+ }
+ start_addr = addr = mm->free_area_cache;
+
+full_search:
+ for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
+ /* At this point: (!vma || addr < vma->vm_end). */
+ if (TASK_SIZE - len < addr) {
+ /*
+ * Start a new search - just in case we missed
+ * some holes.
+ */
+ if (start_addr != TASK_UNMAPPED_BASE) {
+ start_addr = addr = TASK_UNMAPPED_BASE;
+ goto full_search;
+ }
+ return -ENOMEM;
+ }
+ if (!vma || addr + len <= vma->vm_start) {
+ /*
+ * Remember the place where we stopped the search:
+ */
+ mm->free_area_cache = addr + len;
+ return addr;
+ }
+ addr = vma->vm_end;
+ }
+}
+#endif
+
+void arch_unmap_area(struct vm_area_struct *area)
+{
+ /*
+ * Is this a new hole at the lowest possible address?
+ */
+ if (area->vm_start >= TASK_UNMAPPED_BASE &&
+ area->vm_start < area->vm_mm->free_area_cache)
+ area->vm_mm->free_area_cache = area->vm_start;
+}
+
+/*
+ * This mmap-allocator allocates new areas top-down from below the
+ * stack's low limit (the base):
+ */
+#ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+unsigned long
+arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
+ const unsigned long len, const unsigned long pgoff,
+ const unsigned long flags)
+{
+ struct vm_area_struct *vma, *prev_vma;
+ struct mm_struct *mm = current->mm;
+ unsigned long base = mm->mmap_base, addr = addr0;
+ int first_time = 1;
+
+ /* requested length too big for entire address space */
+ if (len > TASK_SIZE)
+ return -ENOMEM;
+
+ /* dont allow allocations above current base */
+ if (mm->free_area_cache > base)
+ mm->free_area_cache = base;
+
+ /* requesting a specific address */
+ if (addr) {
+ addr = PAGE_ALIGN(addr);
+ vma = find_vma(mm, addr);
+ if (TASK_SIZE - len >= addr &&
+ (!vma || addr + len <= vma->vm_start))
+ return addr;
+ }
+
+try_again:
+ /* make sure it can fit in the remaining address space */
+ if (mm->free_area_cache < len)
+ goto fail;
+
+ /* either no address requested or cant fit in requested address hole */
+ addr = (mm->free_area_cache - len) & PAGE_MASK;
+ do {
+ /*
+ * Lookup failure means no vma is above this address,
+ * i.e. return with success:
+ */
+ if (!(vma = find_vma_prev(mm, addr, &prev_vma)))
+ return addr;
+
+ /*
+ * new region fits between prev_vma->vm_end and
+ * vma->vm_start, use it:
+ */
+ if (addr+len <= vma->vm_start &&
+ (!prev_vma || (addr >= prev_vma->vm_end)))
+ /* remember the address as a hint for next time */
+ return (mm->free_area_cache = addr);
+ else
+ /* pull free_area_cache down to the first hole */
+ if (mm->free_area_cache == vma->vm_end)
+ mm->free_area_cache = vma->vm_start;
+
+ /* try just below the current vma->vm_start */
+ addr = vma->vm_start-len;
+ } while (len <= vma->vm_start);
+
+fail:
+ /*
+ * if hint left us with no space for the requested
+ * mapping then try again:
+ */
+ if (first_time) {
+ mm->free_area_cache = base;
+ first_time = 0;
+ goto try_again;
+ }
+ /*
+ * A failed mmap() very likely causes application failure,
+ * so fall back to the bottom-up function here. This scenario
+ * can happen with large stack limits and large mmap()
+ * allocations.
+ */
+ mm->free_area_cache = TASK_UNMAPPED_BASE;
+ addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
+ /*
+ * Restore the topdown base:
+ */
+ mm->free_area_cache = base;
+
+ return addr;
+}
+#endif
+
+void arch_unmap_area_topdown(struct vm_area_struct *area)
+{
+ /*
+ * Is this a new hole at the highest possible address?
+ */
+ if (area->vm_end > area->vm_mm->free_area_cache)
+ area->vm_mm->free_area_cache = area->vm_end;
+}
+
+unsigned long
+get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
+ unsigned long pgoff, unsigned long flags)
+{
+ if (flags & MAP_FIXED) {
+ unsigned long ret;
+
+ if (addr > TASK_SIZE - len)
+ return -ENOMEM;
+ if (addr & ~PAGE_MASK)
+ return -EINVAL;
+ if (file && is_file_hugepages(file)) {
+ /*
+ * Check if the given range is hugepage aligned, and
+ * can be made suitable for hugepages.
+ */
+ ret = prepare_hugepage_range(addr, len);
+ } else {
+ /*
+ * Ensure that a normal request is not falling in a
+ * reserved hugepage range. For some archs like IA-64,
+ * there is a separate region for hugepages.
+ */
+ ret = is_hugepage_only_range(addr, len);
+ }
+ if (ret)
+ return -EINVAL;
+ return addr;
+ }
+
+ if (file && file->f_op && file->f_op->get_unmapped_area)
+ return file->f_op->get_unmapped_area(file, addr, len,
+ pgoff, flags);
+
+ return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+}
+
+EXPORT_SYMBOL(get_unmapped_area);
+
+/* Look up the first VMA which satisfies addr < vm_end, NULL if none. */
+struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr)
+{
+ struct vm_area_struct *vma = NULL;
+
+ if (mm) {
+ /* Check the cache first. */
+ /* (Cache hit rate is typically around 35%.) */
+ vma = mm->mmap_cache;
+ if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
+ struct rb_node * rb_node;
+
+ rb_node = mm->mm_rb.rb_node;
+ vma = NULL;
+
+ while (rb_node) {
+ struct vm_area_struct * vma_tmp;
+
+ vma_tmp = rb_entry(rb_node,
+ struct vm_area_struct, vm_rb);
+
+ if (vma_tmp->vm_end > addr) {
+ vma = vma_tmp;
+ if (vma_tmp->vm_start <= addr)
+ break;
+ rb_node = rb_node->rb_left;
+ } else
+ rb_node = rb_node->rb_right;
+ }
+ if (vma)
+ mm->mmap_cache = vma;
+ }
+ }
+ return vma;
+}
+
+EXPORT_SYMBOL(find_vma);
+
+/* Same as find_vma, but also return a pointer to the previous VMA in *pprev.
*/
+struct vm_area_struct *
+find_vma_prev(struct mm_struct *mm, unsigned long addr,
+ struct vm_area_struct **pprev)
+{
+ struct vm_area_struct *vma = NULL, *prev = NULL;
+ struct rb_node * rb_node;
+ if (!mm)
+ goto out;
+
+ /* Guard against addr being lower than the first VMA */
+ vma = mm->mmap;
+
+ /* Go through the RB tree quickly. */
+ rb_node = mm->mm_rb.rb_node;
+
+ while (rb_node) {
+ struct vm_area_struct *vma_tmp;
+ vma_tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb);
+
+ if (addr < vma_tmp->vm_end) {
+ rb_node = rb_node->rb_left;
+ } else {
+ prev = vma_tmp;
+ if (!prev->vm_next || (addr < prev->vm_next->vm_end))
+ break;
+ rb_node = rb_node->rb_right;
+ }
+ }
+
+out:
+ *pprev = prev;
+ return prev ? prev->vm_next : vma;
+}
+
+/*
+ * Verify that the stack growth is acceptable and
+ * update accounting. This is shared with both the
+ * grow-up and grow-down cases.
+ */
+static int acct_stack_growth(struct vm_area_struct * vma, unsigned long size,
unsigned long grow)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ struct rlimit *rlim = current->signal->rlim;
+
+ /* address space limit tests */
+ if (mm->total_vm + grow > rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT)
+ return -ENOMEM;
+
+ /* Stack limit test */
+ if (size > rlim[RLIMIT_STACK].rlim_cur)
+ return -ENOMEM;
+
+ /* mlock limit tests */
+ if (vma->vm_flags & VM_LOCKED) {
+ unsigned long locked;
+ unsigned long limit;
+ locked = mm->locked_vm + grow;
+ limit = rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
+ if (locked > limit && !capable(CAP_IPC_LOCK))
+ return -ENOMEM;
+ }
+
+ /*
+ * Overcommit.. This must be the final test, as it will
+ * update security statistics.
+ */
+ if (security_vm_enough_memory(grow))
+ return -ENOMEM;
+
+ /* Ok, everything looks good - let it rip */
+ mm->total_vm += grow;
+ if (vma->vm_flags & VM_LOCKED)
+ mm->locked_vm += grow;
+ __vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow);
+ acct_update_integrals();
+ update_mem_hiwater();
+ return 0;
+}
+
+#ifdef CONFIG_STACK_GROWSUP
+/*
+ * vma is the first one with address > vma->vm_end. Have to extend vma.
+ */
+int expand_stack(struct vm_area_struct * vma, unsigned long address)
+{
+ int error;
+
+ if (!(vma->vm_flags & VM_GROWSUP))
+ return -EFAULT;
+
+ /*
+ * We must make sure the anon_vma is allocated
+ * so that the anon_vma locking is not a noop.
+ */
+ if (unlikely(anon_vma_prepare(vma)))
+ return -ENOMEM;
+ anon_vma_lock(vma);
+
+ /*
+ * vma->vm_start/vm_end cannot change under us because the caller
+ * is required to hold the mmap_sem in read mode. We need the
+ * anon_vma lock to serialize against concurrent expand_stacks.
+ */
+ address += 4 + PAGE_SIZE - 1;
+ address &= PAGE_MASK;
+ error = 0;
+
+ /* Somebody else might have raced and expanded it already */
+ if (address > vma->vm_end) {
+ unsigned long size, grow;
+
+ size = address - vma->vm_start;
+ grow = (address - vma->vm_end) >> PAGE_SHIFT;
+
+ error = acct_stack_growth(vma, size, grow);
+ if (!error)
+ vma->vm_end = address;
+ }
+ anon_vma_unlock(vma);
+ return error;
+}
+
+struct vm_area_struct *
+find_extend_vma(struct mm_struct *mm, unsigned long addr)
+{
+ struct vm_area_struct *vma, *prev;
+
+ addr &= PAGE_MASK;
+ vma = find_vma_prev(mm, addr, &prev);
+ if (vma && (vma->vm_start <= addr))
+ return vma;
+ if (!prev || expand_stack(prev, addr))
+ return NULL;
+ if (prev->vm_flags & VM_LOCKED) {
+ make_pages_present(addr, prev->vm_end);
+ }
+ return prev;
+}
+#else
+/*
+ * vma is the first one with address < vma->vm_start. Have to extend vma.
+ */
+int expand_stack(struct vm_area_struct *vma, unsigned long address)
+{
+ int error;
+
+ /*
+ * We must make sure the anon_vma is allocated
+ * so that the anon_vma locking is not a noop.
+ */
+ if (unlikely(anon_vma_prepare(vma)))
+ return -ENOMEM;
+ anon_vma_lock(vma);
+
+ /*
+ * vma->vm_start/vm_end cannot change under us because the caller
+ * is required to hold the mmap_sem in read mode. We need the
+ * anon_vma lock to serialize against concurrent expand_stacks.
+ */
+ address &= PAGE_MASK;
+ error = 0;
+
+ /* Somebody else might have raced and expanded it already */
+ if (address < vma->vm_start) {
+ unsigned long size, grow;
+
+ size = vma->vm_end - address;
+ grow = (vma->vm_start - address) >> PAGE_SHIFT;
+
+ error = acct_stack_growth(vma, size, grow);
+ if (!error) {
+ vma->vm_start = address;
+ vma->vm_pgoff -= grow;
+ }
+ }
+ anon_vma_unlock(vma);
+ return error;
+}
+
+struct vm_area_struct *
+find_extend_vma(struct mm_struct * mm, unsigned long addr)
+{
+ struct vm_area_struct * vma;
+ unsigned long start;
+
+ addr &= PAGE_MASK;
+ vma = find_vma(mm,addr);
+ if (!vma)
+ return NULL;
+ if (vma->vm_start <= addr)
+ return vma;
+ if (!(vma->vm_flags & VM_GROWSDOWN))
+ return NULL;
+ start = vma->vm_start;
+ if (expand_stack(vma, addr))
+ return NULL;
+ if (vma->vm_flags & VM_LOCKED) {
+ make_pages_present(addr, start);
+ }
+ return vma;
+}
+#endif
+
+/*
+ * Try to free as many page directory entries as we can,
+ * without having to work very hard at actually scanning
+ * the page tables themselves.
+ *
+ * Right now we try to free page tables if we have a nice
+ * PGDIR-aligned area that got free'd up. We could be more
+ * granular if we want to, but this is fast and simple,
+ * and covers the bad cases.
+ *
+ * "prev", if it exists, points to a vma before the one
+ * we just free'd - but there's no telling how much before.
+ */
+static void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *prev,
+ unsigned long start, unsigned long end)
+{
+ unsigned long first = start & PGDIR_MASK;
+ unsigned long last = end + PGDIR_SIZE - 1;
+ struct mm_struct *mm = tlb->mm;
+
+ if (last > MM_VM_SIZE(mm) || last < end)
+ last = MM_VM_SIZE(mm);
+
+ if (!prev) {
+ prev = mm->mmap;
+ if (!prev)
+ goto no_mmaps;
+ if (prev->vm_end > start) {
+ if (last > prev->vm_start)
+ last = prev->vm_start;
+ goto no_mmaps;
+ }
+ }
+ for (;;) {
+ struct vm_area_struct *next = prev->vm_next;
+
+ if (next) {
+ if (next->vm_start < start) {
+ prev = next;
+ continue;
+ }
+ if (last > next->vm_start)
+ last = next->vm_start;
+ }
+ if (prev->vm_end > first)
+ first = prev->vm_end;
+ break;
+ }
+no_mmaps:
+ if (last < first) /* for arches with discontiguous pgd indices */
+ return;
+ if (first < FIRST_USER_PGD_NR * PGDIR_SIZE)
+ first = FIRST_USER_PGD_NR * PGDIR_SIZE;
+ /* No point trying to free anything if we're in the same pte page */
+ if ((first & PMD_MASK) < (last & PMD_MASK)) {
+ clear_page_range(tlb, first, last);
+ flush_tlb_pgtables(mm, first, last);
+ }
+}
+
+/* Normal function to fix up a mapping
+ * This function is the default for when an area has no specific
+ * function. This may be used as part of a more specific routine.
+ *
+ * By the time this function is called, the area struct has been
+ * removed from the process mapping list.
+ */
+static void unmap_vma(struct mm_struct *mm, struct vm_area_struct *area)
+{
+ size_t len = area->vm_end - area->vm_start;
+
+ area->vm_mm->total_vm -= len >> PAGE_SHIFT;
+ if (area->vm_flags & VM_LOCKED)
+ area->vm_mm->locked_vm -= len >> PAGE_SHIFT;
+ vm_stat_unaccount(area);
+ area->vm_mm->unmap_area(area);
+ remove_vm_struct(area);
+}
+
+/*
+ * Update the VMA and inode share lists.
+ *
+ * Ok - we have the memory areas we should free on the 'free' list,
+ * so release them, and do the vma updates.
+ */
+static void unmap_vma_list(struct mm_struct *mm,
+ struct vm_area_struct *mpnt)
+{
+ do {
+ struct vm_area_struct *next = mpnt->vm_next;
+ unmap_vma(mm, mpnt);
+ mpnt = next;
+ } while (mpnt != NULL);
+ validate_mm(mm);
+}
+
+/*
+ * Get rid of page table information in the indicated region.
+ *
+ * Called with the page table lock held.
+ */
+static void unmap_region(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ struct vm_area_struct *prev,
+ unsigned long start,
+ unsigned long end)
+{
+ struct mmu_gather *tlb;
+ unsigned long nr_accounted = 0;
+
+ lru_add_drain();
+ tlb = tlb_gather_mmu(mm, 0);
+ unmap_vmas(&tlb, mm, vma, start, end, &nr_accounted, NULL);
+ vm_unacct_memory(nr_accounted);
+
+ if (is_hugepage_only_range(start, end - start))
+ hugetlb_free_pgtables(tlb, prev, start, end);
+ else
+ free_pgtables(tlb, prev, start, end);
+ tlb_finish_mmu(tlb, start, end);
+}
+
+/*
+ * Create a list of vma's touched by the unmap, removing them from the mm's
+ * vma list as we go..
+ */
+static void
+detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
+ struct vm_area_struct *prev, unsigned long end)
+{
+ struct vm_area_struct **insertion_point;
+ struct vm_area_struct *tail_vma = NULL;
+
+ insertion_point = (prev ? &prev->vm_next : &mm->mmap);
+ do {
+ rb_erase(&vma->vm_rb, &mm->mm_rb);
+ mm->map_count--;
+ tail_vma = vma;
+ vma = vma->vm_next;
+ } while (vma && vma->vm_start < end);
+ *insertion_point = vma;
+ tail_vma->vm_next = NULL;
+ mm->mmap_cache = NULL; /* Kill the cache. */
+}
+
+/*
+ * Split a vma into two pieces at address 'addr', a new vma is allocated
+ * either for the first part or the the tail.
+ */
+int split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
+ unsigned long addr, int new_below)
+{
+ struct mempolicy *pol;
+ struct vm_area_struct *new;
+
+ if (is_vm_hugetlb_page(vma) && (addr & ~HPAGE_MASK))
+ return -EINVAL;
+
+ if (mm->map_count >= sysctl_max_map_count)
+ return -ENOMEM;
+
+ new = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ if (!new)
+ return -ENOMEM;
+
+ /* most fields are the same, copy all, and then fixup */
+ *new = *vma;
+
+ if (new_below)
+ new->vm_end = addr;
+ else {
+ new->vm_start = addr;
+ new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT);
+ }
+
+ pol = mpol_copy(vma_policy(vma));
+ if (IS_ERR(pol)) {
+ kmem_cache_free(vm_area_cachep, new);
+ return PTR_ERR(pol);
+ }
+ vma_set_policy(new, pol);
+
+ if (new->vm_file)
+ get_file(new->vm_file);
+
+ if (new->vm_ops && new->vm_ops->open)
+ new->vm_ops->open(new);
+
+ if (new_below)
+ vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff +
+ ((addr - new->vm_start) >> PAGE_SHIFT), new);
+ else
+ vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new);
+
+ return 0;
+}
+
+/* Munmap is split into 2 main parts -- this part which finds
+ * what needs doing, and the areas themselves, which do the
+ * work. This now handles partial unmappings.
+ * Jeremy Fitzhardinge <jeremy@xxxxxxxx>
+ */
+int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
+{
+ unsigned long end;
+ struct vm_area_struct *mpnt, *prev, *last;
+
+ if ((start & ~PAGE_MASK) || start > TASK_SIZE || len > TASK_SIZE-start)
+ return -EINVAL;
+
+ if ((len = PAGE_ALIGN(len)) == 0)
+ return -EINVAL;
+
+ /* Find the first overlapping VMA */
+ mpnt = find_vma_prev(mm, start, &prev);
+ if (!mpnt)
+ return 0;
+ /* we have start < mpnt->vm_end */
+
+ /* if it doesn't overlap, we have nothing.. */
+ end = start + len;
+ if (mpnt->vm_start >= end)
+ return 0;
+
+ /*
+ * If we need to split any vma, do it now to save pain later.
+ *
+ * Note: mremap's move_vma VM_ACCOUNT handling assumes a partially
+ * unmapped vm_area_struct will remain in use: so lower split_vma
+ * places tmp vma above, and higher split_vma places tmp vma below.
+ */
+ if (start > mpnt->vm_start) {
+ int error = split_vma(mm, mpnt, start, 0);
+ if (error)
+ return error;
+ prev = mpnt;
+ }
+
+ /* Does it split the last one? */
+ last = find_vma(mm, end);
+ if (last && end > last->vm_start) {
+ int error = split_vma(mm, last, end, 1);
+ if (error)
+ return error;
+ }
+ mpnt = prev? prev->vm_next: mm->mmap;
+
+ /*
+ * Remove the vma's, and unmap the actual pages
+ */
+ detach_vmas_to_be_unmapped(mm, mpnt, prev, end);
+ spin_lock(&mm->page_table_lock);
+ unmap_region(mm, mpnt, prev, start, end);
+ spin_unlock(&mm->page_table_lock);
+
+ /* Fix up all other VM information */
+ unmap_vma_list(mm, mpnt);
+
+ return 0;
+}
+
+EXPORT_SYMBOL(do_munmap);
+
+asmlinkage long sys_munmap(unsigned long addr, size_t len)
+{
+ int ret;
+ struct mm_struct *mm = current->mm;
+
+ profile_munmap(addr);
+
+ down_write(&mm->mmap_sem);
+ ret = do_munmap(mm, addr, len);
+ up_write(&mm->mmap_sem);
+ return ret;
+}
+
+static inline void verify_mm_writelocked(struct mm_struct *mm)
+{
+#ifdef CONFIG_DEBUG_KERNEL
+ if (unlikely(down_read_trylock(&mm->mmap_sem))) {
+ WARN_ON(1);
+ up_read(&mm->mmap_sem);
+ }
+#endif
+}
+
+/*
+ * this is really a simplified "do_mmap". it only handles
+ * anonymous maps. eventually we may be able to do some
+ * brk-specific accounting here.
+ */
+unsigned long do_brk(unsigned long addr, unsigned long len)
+{
+ struct mm_struct * mm = current->mm;
+ struct vm_area_struct * vma, * prev;
+ unsigned long flags;
+ struct rb_node ** rb_link, * rb_parent;
+ pgoff_t pgoff = addr >> PAGE_SHIFT;
+
+ len = PAGE_ALIGN(len);
+ if (!len)
+ return addr;
+
+ if ((addr + len) > TASK_SIZE || (addr + len) < addr)
+ return -EINVAL;
+
+ /*
+ * mlock MCL_FUTURE?
+ */
+ if (mm->def_flags & VM_LOCKED) {
+ unsigned long locked, lock_limit;
+ locked = mm->locked_vm << PAGE_SHIFT;
+ lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
+ locked += len;
+ if (locked > lock_limit && !capable(CAP_IPC_LOCK))
+ return -EAGAIN;
+ }
+
+ /*
+ * mm->mmap_sem is required to protect against another thread
+ * changing the mappings in case we sleep.
+ */
+ verify_mm_writelocked(mm);
+
+ /*
+ * Clear old maps. this also does some error checking for us
+ */
+ munmap_back:
+ vma = find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent);
+ if (vma && vma->vm_start < addr + len) {
+ if (do_munmap(mm, addr, len))
+ return -ENOMEM;
+ goto munmap_back;
+ }
+
+ /* Check against address space limits *after* clearing old maps... */
+ if ((mm->total_vm << PAGE_SHIFT) + len
+ > current->signal->rlim[RLIMIT_AS].rlim_cur)
+ return -ENOMEM;
+
+ if (mm->map_count > sysctl_max_map_count)
+ return -ENOMEM;
+
+ if (security_vm_enough_memory(len >> PAGE_SHIFT))
+ return -ENOMEM;
+
+ flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
+
+ /* Can we just expand an old private anonymous mapping? */
+ if (vma_merge(mm, prev, addr, addr + len, flags,
+ NULL, NULL, pgoff, NULL))
+ goto out;
+
+ /*
+ * create a vma struct for an anonymous mapping
+ */
+ vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ if (!vma) {
+ vm_unacct_memory(len >> PAGE_SHIFT);
+ return -ENOMEM;
+ }
+ memset(vma, 0, sizeof(*vma));
+
+ vma->vm_mm = mm;
+ vma->vm_start = addr;
+ vma->vm_end = addr + len;
+ vma->vm_pgoff = pgoff;
+ vma->vm_flags = flags;
+ vma->vm_page_prot = protection_map[flags & 0x0f];
+ vma_link(mm, vma, prev, rb_link, rb_parent);
+out:
+ mm->total_vm += len >> PAGE_SHIFT;
+ if (flags & VM_LOCKED) {
+ mm->locked_vm += len >> PAGE_SHIFT;
+ make_pages_present(addr, addr + len);
+ }
+ acct_update_integrals();
+ update_mem_hiwater();
+ return addr;
+}
+
+EXPORT_SYMBOL(do_brk);
+
+/* Release all mmaps. */
+void exit_mmap(struct mm_struct *mm)
+{
+ struct mmu_gather *tlb;
+ struct vm_area_struct *vma;
+ unsigned long nr_accounted = 0;
+
+#ifdef arch_exit_mmap
+ arch_exit_mmap(mm);
+#endif
+
+ lru_add_drain();
+
+ spin_lock(&mm->page_table_lock);
+
+ tlb = tlb_gather_mmu(mm, 1);
+ flush_cache_mm(mm);
+ /* Use ~0UL here to ensure all VMAs in the mm are unmapped */
+ mm->map_count -= unmap_vmas(&tlb, mm, mm->mmap, 0,
+ ~0UL, &nr_accounted, NULL);
+ vm_unacct_memory(nr_accounted);
+ BUG_ON(mm->map_count); /* This is just debugging */
+ clear_page_range(tlb, FIRST_USER_PGD_NR * PGDIR_SIZE, MM_VM_SIZE(mm));
+
+ tlb_finish_mmu(tlb, 0, MM_VM_SIZE(mm));
+
+ vma = mm->mmap;
+ mm->mmap = mm->mmap_cache = NULL;
+ mm->mm_rb = RB_ROOT;
+ mm->rss = 0;
+ mm->total_vm = 0;
+ mm->locked_vm = 0;
+
+ spin_unlock(&mm->page_table_lock);
+
+ /*
+ * Walk the list again, actually closing and freeing it
+ * without holding any MM locks.
+ */
+ while (vma) {
+ struct vm_area_struct *next = vma->vm_next;
+ remove_vm_struct(vma);
+ vma = next;
+ }
+}
+
+/* Insert vm structure into process list sorted by address
+ * and into the inode's i_mmap tree. If vm_file is non-NULL
+ * then i_mmap_lock is taken here.
+ */
+int insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
+{
+ struct vm_area_struct * __vma, * prev;
+ struct rb_node ** rb_link, * rb_parent;
+
+ /*
+ * The vm_pgoff of a purely anonymous vma should be irrelevant
+ * until its first write fault, when page's anon_vma and index
+ * are set. But now set the vm_pgoff it will almost certainly
+ * end up with (unless mremap moves it elsewhere before that
+ * first wfault), so /proc/pid/maps tells a consistent story.
+ *
+ * By setting it to reflect the virtual start address of the
+ * vma, merges and splits can happen in a seamless way, just
+ * using the existing file pgoff checks and manipulations.
+ * Similarly in do_mmap_pgoff and in do_brk.
+ */
+ if (!vma->vm_file) {
+ BUG_ON(vma->anon_vma);
+ vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT;
+ }
+ __vma = find_vma_prepare(mm,vma->vm_start,&prev,&rb_link,&rb_parent);
+ if (__vma && __vma->vm_start < vma->vm_end)
+ return -ENOMEM;
+ vma_link(mm, vma, prev, rb_link, rb_parent);
+ return 0;
+}
+
+/*
+ * Copy the vma structure to a new location in the same mm,
+ * prior to moving page table entries, to effect an mremap move.
+ */
+struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
+ unsigned long addr, unsigned long len, pgoff_t pgoff)
+{
+ struct vm_area_struct *vma = *vmap;
+ unsigned long vma_start = vma->vm_start;
+ struct mm_struct *mm = vma->vm_mm;
+ struct vm_area_struct *new_vma, *prev;
+ struct rb_node **rb_link, *rb_parent;
+ struct mempolicy *pol;
+
+ /*
+ * If anonymous vma has not yet been faulted, update new pgoff
+ * to match new location, to increase its chance of merging.
+ */
+ if (!vma->vm_file && !vma->anon_vma)
+ pgoff = addr >> PAGE_SHIFT;
+
+ find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent);
+ new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
+ vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
+ if (new_vma) {
+ /*
+ * Source vma may have been merged into new_vma
+ */
+ if (vma_start >= new_vma->vm_start &&
+ vma_start < new_vma->vm_end)
+ *vmap = new_vma;
+ } else {
+ new_vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ if (new_vma) {
+ *new_vma = *vma;
+ pol = mpol_copy(vma_policy(vma));
+ if (IS_ERR(pol)) {
+ kmem_cache_free(vm_area_cachep, new_vma);
+ return NULL;
+ }
+ vma_set_policy(new_vma, pol);
+ new_vma->vm_start = addr;
+ new_vma->vm_end = addr + len;
+ new_vma->vm_pgoff = pgoff;
+ if (new_vma->vm_file)
+ get_file(new_vma->vm_file);
+ if (new_vma->vm_ops && new_vma->vm_ops->open)
+ new_vma->vm_ops->open(new_vma);
+ vma_link(mm, new_vma, prev, rb_link, rb_parent);
+ }
+ }
+ return new_vma;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blkback/vbd.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blkback/vbd.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,295 @@
+/******************************************************************************
+ * blkback/vbd.c
+ *
+ * Routines for managing virtual block devices (VBDs).
+ *
+ * NOTE: vbd_lock protects updates to the rb_tree against concurrent lookups
+ * in vbd_translate. All other lookups are implicitly protected because the
+ * only caller (the control message dispatch routine) serializes the calls.
+ *
+ * Copyright (c) 2003-2005, Keir Fraser & Steve Hand
+ */
+
+#include "common.h"
+
+struct vbd {
+ blkif_vdev_t vdevice; /* what the domain refers to this vbd as */
+ unsigned char readonly; /* Non-zero -> read-only */
+ unsigned char type; /* VDISK_xxx */
+ blkif_pdev_t pdevice; /* phys device that this vbd maps to */
+ struct block_device *bdev;
+ rb_node_t rb; /* for linking into R-B tree lookup struct */
+};
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+static inline dev_t vbd_map_devnum(blkif_pdev_t cookie)
+{ return MKDEV(cookie>>8, cookie&0xff); }
+#define vbd_sz(_v) ((_v)->bdev->bd_part ? \
+ (_v)->bdev->bd_part->nr_sects : (_v)->bdev->bd_disk->capacity)
+#define bdev_put(_b) blkdev_put(_b)
+#else
+#define vbd_sz(_v) (blk_size[MAJOR((_v)->pdevice)][MINOR((_v)->pdevice)]*2)
+#define bdev_put(_b) ((void)0)
+#define bdev_hardsect_size(_b) 512
+#endif
+
+void vbd_create(blkif_be_vbd_create_t *create)
+{
+ struct vbd *vbd;
+ rb_node_t **rb_p, *rb_parent = NULL;
+ blkif_t *blkif;
+ blkif_vdev_t vdevice = create->vdevice;
+
+ blkif = blkif_find_by_handle(create->domid, create->blkif_handle);
+ if ( unlikely(blkif == NULL) )
+ {
+ DPRINTK("vbd_create attempted for non-existent blkif (%u,%u)\n",
+ create->domid, create->blkif_handle);
+ create->status = BLKIF_BE_STATUS_INTERFACE_NOT_FOUND;
+ return;
+ }
+
+ rb_p = &blkif->vbd_rb.rb_node;
+ while ( *rb_p != NULL )
+ {
+ rb_parent = *rb_p;
+ vbd = rb_entry(rb_parent, struct vbd, rb);
+ if ( vdevice < vbd->vdevice )
+ {
+ rb_p = &rb_parent->rb_left;
+ }
+ else if ( vdevice > vbd->vdevice )
+ {
+ rb_p = &rb_parent->rb_right;
+ }
+ else
+ {
+ DPRINTK("vbd_create attempted for already existing vbd\n");
+ create->status = BLKIF_BE_STATUS_VBD_EXISTS;
+ return;
+ }
+ }
+
+ if ( unlikely((vbd = kmalloc(sizeof(struct vbd), GFP_KERNEL)) == NULL) )
+ {
+ DPRINTK("vbd_create: out of memory\n");
+ create->status = BLKIF_BE_STATUS_OUT_OF_MEMORY;
+ return;
+ }
+
+ vbd->vdevice = vdevice;
+ vbd->readonly = create->readonly;
+ vbd->type = 0;
+
+ /* Mask to 16-bit for compatibility with old tools */
+ vbd->pdevice = create->pdevice & 0xffff;
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+ vbd->bdev = open_by_devnum(
+ vbd_map_devnum(vbd->pdevice),
+ vbd->readonly ? FMODE_READ : FMODE_WRITE);
+ if ( IS_ERR(vbd->bdev) )
+ {
+ DPRINTK("vbd_creat: device %08x doesn't exist.\n", vbd->pdevice);
+ create->status = BLKIF_BE_STATUS_PHYSDEV_NOT_FOUND;
+ return;
+ }
+
+ if ( (vbd->bdev->bd_disk == NULL) )
+ {
+ DPRINTK("vbd_creat: device %08x doesn't exist.\n", vbd->pdevice);
+ create->status = BLKIF_BE_STATUS_PHYSDEV_NOT_FOUND;
+ bdev_put(vbd->bdev);
+ return;
+ }
+
+ if ( vbd->bdev->bd_disk->flags & GENHD_FL_CD )
+ vbd->type |= VDISK_CDROM;
+ if ( vbd->bdev->bd_disk->flags & GENHD_FL_REMOVABLE )
+ vbd->type |= VDISK_REMOVABLE;
+
+#else
+ if ( (blk_size[MAJOR(vbd->pdevice)] == NULL) || (vbd_sz(vbd) == 0) )
+ {
+ DPRINTK("vbd_creat: device %08x doesn't exist.\n", vbd->pdevice);
+ create->status = BLKIF_BE_STATUS_PHYSDEV_NOT_FOUND;
+ return;
+ }
+#endif
+
+ spin_lock(&blkif->vbd_lock);
+ rb_link_node(&vbd->rb, rb_parent, rb_p);
+ rb_insert_color(&vbd->rb, &blkif->vbd_rb);
+ spin_unlock(&blkif->vbd_lock);
+
+ DPRINTK("Successful creation of vdev=%04x (dom=%u)\n",
+ vdevice, create->domid);
+ create->status = BLKIF_BE_STATUS_OKAY;
+}
+
+
+void vbd_destroy(blkif_be_vbd_destroy_t *destroy)
+{
+ blkif_t *blkif;
+ struct vbd *vbd;
+ rb_node_t *rb;
+ blkif_vdev_t vdevice = destroy->vdevice;
+
+ blkif = blkif_find_by_handle(destroy->domid, destroy->blkif_handle);
+ if ( unlikely(blkif == NULL) )
+ {
+ DPRINTK("vbd_destroy attempted for non-existent blkif (%u,%u)\n",
+ destroy->domid, destroy->blkif_handle);
+ destroy->status = BLKIF_BE_STATUS_INTERFACE_NOT_FOUND;
+ return;
+ }
+
+ rb = blkif->vbd_rb.rb_node;
+ while ( rb != NULL )
+ {
+ vbd = rb_entry(rb, struct vbd, rb);
+ if ( vdevice < vbd->vdevice )
+ rb = rb->rb_left;
+ else if ( vdevice > vbd->vdevice )
+ rb = rb->rb_right;
+ else
+ goto found;
+ }
+
+ destroy->status = BLKIF_BE_STATUS_VBD_NOT_FOUND;
+ return;
+
+ found:
+ spin_lock(&blkif->vbd_lock);
+ rb_erase(rb, &blkif->vbd_rb);
+ spin_unlock(&blkif->vbd_lock);
+ bdev_put(vbd->bdev);
+ kfree(vbd);
+}
+
+
+void destroy_all_vbds(blkif_t *blkif)
+{
+ struct vbd *vbd;
+ rb_node_t *rb;
+
+ spin_lock(&blkif->vbd_lock);
+
+ while ( (rb = blkif->vbd_rb.rb_node) != NULL )
+ {
+ vbd = rb_entry(rb, struct vbd, rb);
+ rb_erase(rb, &blkif->vbd_rb);
+ spin_unlock(&blkif->vbd_lock);
+ bdev_put(vbd->bdev);
+ kfree(vbd);
+ spin_lock(&blkif->vbd_lock);
+ }
+
+ spin_unlock(&blkif->vbd_lock);
+}
+
+
+static void vbd_probe_single(
+ blkif_t *blkif, vdisk_t *vbd_info, struct vbd *vbd)
+{
+ vbd_info->device = vbd->vdevice;
+ vbd_info->info = vbd->type | (vbd->readonly ? VDISK_READONLY : 0);
+ vbd_info->capacity = vbd_sz(vbd);
+ vbd_info->sector_size = bdev_hardsect_size(vbd->bdev);
+}
+
+
+int vbd_probe(blkif_t *blkif, vdisk_t *vbd_info, int max_vbds)
+{
+ int rc = 0, nr_vbds = 0;
+ rb_node_t *rb;
+
+ spin_lock(&blkif->vbd_lock);
+
+ if ( (rb = blkif->vbd_rb.rb_node) == NULL )
+ goto out;
+
+ new_subtree:
+ /* STEP 1. Find least node (it'll be left-most). */
+ while ( rb->rb_left != NULL )
+ rb = rb->rb_left;
+
+ for ( ; ; )
+ {
+ /* STEP 2. Dealt with left subtree. Now process current node. */
+ vbd_probe_single(blkif, &vbd_info[nr_vbds],
+ rb_entry(rb, struct vbd, rb));
+ if ( ++nr_vbds == max_vbds )
+ goto out;
+
+ /* STEP 3. Process right subtree, if any. */
+ if ( rb->rb_right != NULL )
+ {
+ rb = rb->rb_right;
+ goto new_subtree;
+ }
+
+ /* STEP 4. Done both subtrees. Head back through ancesstors. */
+ for ( ; ; )
+ {
+ /* We're done when we get back to the root node. */
+ if ( rb->rb_parent == NULL )
+ goto out;
+ /* If we are left of parent, then parent is next to process. */
+ if ( rb->rb_parent->rb_left == rb )
+ break;
+ /* If we are right of parent, then we climb to grandparent. */
+ rb = rb->rb_parent;
+ }
+
+ rb = rb->rb_parent;
+ }
+
+ out:
+ spin_unlock(&blkif->vbd_lock);
+ return (rc == 0) ? nr_vbds : rc;
+}
+
+
+int vbd_translate(struct phys_req *req, blkif_t *blkif, int operation)
+{
+ struct vbd *vbd;
+ rb_node_t *rb;
+ int rc = -EACCES;
+
+ /* Take the vbd_lock because another thread could be updating the tree. */
+ spin_lock(&blkif->vbd_lock);
+
+ rb = blkif->vbd_rb.rb_node;
+ while ( rb != NULL )
+ {
+ vbd = rb_entry(rb, struct vbd, rb);
+ if ( req->dev < vbd->vdevice )
+ rb = rb->rb_left;
+ else if ( req->dev > vbd->vdevice )
+ rb = rb->rb_right;
+ else
+ goto found;
+ }
+
+ DPRINTK("vbd_translate; domain %u attempted to access "
+ "non-existent VBD.\n", blkif->domid);
+ rc = -ENODEV;
+ goto out;
+
+ found:
+
+ if ( (operation == WRITE) && vbd->readonly )
+ goto out;
+
+ if ( unlikely((req->sector_number + req->nr_sects) > vbd_sz(vbd)) )
+ goto out;
+
+ req->dev = vbd->pdevice;
+ req->bdev = vbd->bdev;
+ rc = 0;
+
+ out:
+ spin_unlock(&blkif->vbd_lock);
+ return rc;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-generic/pgtable.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-generic/pgtable.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,147 @@
+#ifndef _ASM_GENERIC_PGTABLE_H
+#define _ASM_GENERIC_PGTABLE_H
+
+#ifndef __HAVE_ARCH_PTEP_ESTABLISH
+/*
+ * Establish a new mapping:
+ * - flush the old one
+ * - update the page tables
+ * - inform the TLB about the new one
+ *
+ * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock.
+ *
+ * Note: the old pte is known to not be writable, so we don't need to
+ * worry about dirty bits etc getting lost.
+ */
+#ifndef __HAVE_ARCH_SET_PTE_ATOMIC
+#define ptep_establish(__vma, __address, __ptep, __entry) \
+do { \
+ set_pte(__ptep, __entry); \
+ flush_tlb_page(__vma, __address); \
+} while (0)
+#else /* __HAVE_ARCH_SET_PTE_ATOMIC */
+#define ptep_establish(__vma, __address, __ptep, __entry) \
+do { \
+ set_pte_atomic(__ptep, __entry); \
+ flush_tlb_page(__vma, __address); \
+} while (0)
+#endif /* __HAVE_ARCH_SET_PTE_ATOMIC */
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+/*
+ * Largely same as above, but only sets the access flags (dirty,
+ * accessed, and writable). Furthermore, we know it always gets set
+ * to a "more permissive" setting, which allows most architectures
+ * to optimize this.
+ */
+#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
+do { \
+ set_pte(__ptep, __entry); \
+ flush_tlb_page(__vma, __address); \
+} while (0)
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_ESTABLISH_NEW
+/*
+ * Establish a mapping where none previously existed
+ */
+#define ptep_establish_new(__vma, __address, __ptep, __entry) \
+do { \
+ set_pte(__ptep, __entry); \
+} while (0)
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline int ptep_test_and_clear_young(pte_t *ptep)
+{
+ pte_t pte = *ptep;
+ if (!pte_young(pte))
+ return 0;
+ set_pte(ptep, pte_mkold(pte));
+ return 1;
+}
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+#define ptep_clear_flush_young(__vma, __address, __ptep) \
+({ \
+ int __young = ptep_test_and_clear_young(__ptep); \
+ if (__young) \
+ flush_tlb_page(__vma, __address); \
+ __young; \
+})
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY
+static inline int ptep_test_and_clear_dirty(pte_t *ptep)
+{
+ pte_t pte = *ptep;
+ if (!pte_dirty(pte))
+ return 0;
+ set_pte(ptep, pte_mkclean(pte));
+ return 1;
+}
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_CLEAR_DIRTY_FLUSH
+#define ptep_clear_flush_dirty(__vma, __address, __ptep) \
+({ \
+ int __dirty = ptep_test_and_clear_dirty(__ptep); \
+ if (__dirty) \
+ flush_tlb_page(__vma, __address); \
+ __dirty; \
+})
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(pte_t *ptep)
+{
+ pte_t pte = *ptep;
+ pte_clear(ptep);
+ return pte;
+}
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
+#define ptep_clear_flush(__vma, __address, __ptep) \
+({ \
+ pte_t __pte = ptep_get_and_clear(__ptep); \
+ flush_tlb_page(__vma, __address); \
+ __pte; \
+})
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(pte_t *ptep)
+{
+ pte_t old_pte = *ptep;
+ set_pte(ptep, pte_wrprotect(old_pte));
+}
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_MKDIRTY
+static inline void ptep_mkdirty(pte_t *ptep)
+{
+ pte_t old_pte = *ptep;
+ set_pte(ptep, pte_mkdirty(old_pte));
+}
+#endif
+
+#ifndef __HAVE_ARCH_PTE_SAME
+#define pte_same(A,B) (pte_val(A) == pte_val(B))
+#endif
+
+#ifndef __HAVE_ARCH_PAGE_TEST_AND_CLEAR_DIRTY
+#define page_test_and_clear_dirty(page) (0)
+#endif
+
+#ifndef __HAVE_ARCH_PAGE_TEST_AND_CLEAR_YOUNG
+#define page_test_and_clear_young(page) (0)
+#endif
+
+#ifndef __HAVE_ARCH_PGD_OFFSET_GATE
+#define pgd_offset_gate(mm, addr) pgd_offset(mm, addr)
+#endif
+
+#endif /* _ASM_GENERIC_PGTABLE_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blkback/blkback.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blkback/blkback.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,756 @@
+/******************************************************************************
+ * arch/xen/drivers/blkif/backend/main.c
+ *
+ * Back-end of the driver for virtual block devices. This portion of the
+ * driver exports a 'unified' block-device interface that can be accessed
+ * by any operating system that implements a compatible front end. A
+ * reference front-end implementation can be found in:
+ * arch/xen/drivers/blkif/frontend
+ *
+ * Copyright (c) 2003-2004, Keir Fraser & Steve Hand
+ * Copyright (c) 2005, Christopher Clark
+ */
+
+#include "common.h"
+#include <asm-xen/evtchn.h>
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+#include <asm-xen/xen-public/grant_table.h>
+#endif
+
+/*
+ * These are rather arbitrary. They are fairly large because adjacent requests
+ * pulled from a communication ring are quite likely to end up being part of
+ * the same scatter/gather request at the disc.
+ *
+ * ** TRY INCREASING 'MAX_PENDING_REQS' IF WRITE SPEEDS SEEM TOO LOW **
+ * This will increase the chances of being able to write whole tracks.
+ * 64 should be enough to keep us competitive with Linux.
+ */
+#define MAX_PENDING_REQS 64
+#define BATCH_PER_DOMAIN 16
+
+static unsigned long mmap_vstart;
+#define MMAP_PAGES \
+ (MAX_PENDING_REQS * BLKIF_MAX_SEGMENTS_PER_REQUEST)
+#define MMAP_VADDR(_req,_seg) \
+ (mmap_vstart + \
+ ((_req) * BLKIF_MAX_SEGMENTS_PER_REQUEST * PAGE_SIZE) + \
+ ((_seg) * PAGE_SIZE))
+
+/*
+ * Each outstanding request that we've passed to the lower device layers has a
+ * 'pending_req' allocated to it. Each buffer_head that completes decrements
+ * the pendcnt towards zero. When it hits zero, the specified domain has a
+ * response queued for it, with the saved 'id' passed back.
+ */
+typedef struct {
+ blkif_t *blkif;
+ unsigned long id;
+ int nr_pages;
+ atomic_t pendcnt;
+ unsigned short operation;
+ int status;
+} pending_req_t;
+
+/*
+ * We can't allocate pending_req's in order, since they may complete out of
+ * order. We therefore maintain an allocation ring. This ring also indicates
+ * when enough work has been passed down -- at that point the allocation ring
+ * will be empty.
+ */
+static pending_req_t pending_reqs[MAX_PENDING_REQS];
+static unsigned char pending_ring[MAX_PENDING_REQS];
+static spinlock_t pend_prod_lock = SPIN_LOCK_UNLOCKED;
+/* NB. We use a different index type to differentiate from shared blk rings. */
+typedef unsigned int PEND_RING_IDX;
+#define MASK_PEND_IDX(_i) ((_i)&(MAX_PENDING_REQS-1))
+static PEND_RING_IDX pending_prod, pending_cons;
+#define NR_PENDING_REQS (MAX_PENDING_REQS - pending_prod + pending_cons)
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
+static kmem_cache_t *buffer_head_cachep;
+#else
+static request_queue_t *plugged_queue;
+static inline void flush_plugged_queue(void)
+{
+ request_queue_t *q = plugged_queue;
+ if ( q != NULL )
+ {
+ if ( q->unplug_fn != NULL )
+ q->unplug_fn(q);
+ blk_put_queue(q);
+ plugged_queue = NULL;
+ }
+}
+#endif
+
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+/* When using grant tables to map a frame for device access then the
+ * handle returned must be used to unmap the frame. This is needed to
+ * drop the ref count on the frame.
+ */
+static u16 pending_grant_handles[MMAP_PAGES];
+#define pending_handle(_idx, _i) \
+ (pending_grant_handles[((_idx) * BLKIF_MAX_SEGMENTS_PER_REQUEST) + (_i)])
+#define BLKBACK_INVALID_HANDLE (0xFFFF)
+#endif
+
+#ifdef CONFIG_XEN_BLKDEV_TAP_BE
+/*
+ * If the tap driver is used, we may get pages belonging to either the tap
+ * or (more likely) the real frontend. The backend must specify which domain
+ * a given page belongs to in update_va_mapping though. For the moment,
+ * the tap rewrites the ID field of the request to contain the request index
+ * and the id of the real front end domain.
+ */
+#define BLKTAP_COOKIE 0xbeadfeed
+static inline domid_t ID_TO_DOM(unsigned long id) { return (id >> 16); }
+#endif
+
+static int do_block_io_op(blkif_t *blkif, int max_to_do);
+static void dispatch_probe(blkif_t *blkif, blkif_request_t *req);
+static void dispatch_rw_block_io(blkif_t *blkif, blkif_request_t *req);
+static void make_response(blkif_t *blkif, unsigned long id,
+ unsigned short op, int st);
+
+static void fast_flush_area(int idx, int nr_pages)
+{
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ unsigned int i, invcount = 0;
+ u16 handle;
+
+ for ( i = 0; i < nr_pages; i++ )
+ {
+ if ( BLKBACK_INVALID_HANDLE != ( handle = pending_handle(idx, i) ) )
+ {
+ unmap[i].host_virt_addr = MMAP_VADDR(idx, i);
+ unmap[i].dev_bus_addr = 0;
+ unmap[i].handle = handle;
+ pending_handle(idx, i) = BLKBACK_INVALID_HANDLE;
+ invcount++;
+ }
+ }
+ if ( unlikely(HYPERVISOR_grant_table_op(
+ GNTTABOP_unmap_grant_ref, unmap, invcount)))
+ BUG();
+#else
+
+ multicall_entry_t mcl[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ int i;
+
+ for ( i = 0; i < nr_pages; i++ )
+ {
+ MULTI_update_va_mapping(mcl+i, MMAP_VADDR(idx, i),
+ __pte(0), 0);
+ }
+
+ mcl[nr_pages-1].args[2] = UVMF_TLB_FLUSH|UVMF_ALL;
+ if ( unlikely(HYPERVISOR_multicall(mcl, nr_pages) != 0) )
+ BUG();
+#endif
+}
+
+
+/******************************************************************
+ * BLOCK-DEVICE SCHEDULER LIST MAINTENANCE
+ */
+
+static struct list_head blkio_schedule_list;
+static spinlock_t blkio_schedule_list_lock;
+
+static int __on_blkdev_list(blkif_t *blkif)
+{
+ return blkif->blkdev_list.next != NULL;
+}
+
+static void remove_from_blkdev_list(blkif_t *blkif)
+{
+ unsigned long flags;
+ if ( !__on_blkdev_list(blkif) ) return;
+ spin_lock_irqsave(&blkio_schedule_list_lock, flags);
+ if ( __on_blkdev_list(blkif) )
+ {
+ list_del(&blkif->blkdev_list);
+ blkif->blkdev_list.next = NULL;
+ blkif_put(blkif);
+ }
+ spin_unlock_irqrestore(&blkio_schedule_list_lock, flags);
+}
+
+static void add_to_blkdev_list_tail(blkif_t *blkif)
+{
+ unsigned long flags;
+ if ( __on_blkdev_list(blkif) ) return;
+ spin_lock_irqsave(&blkio_schedule_list_lock, flags);
+ if ( !__on_blkdev_list(blkif) && (blkif->status == CONNECTED) )
+ {
+ list_add_tail(&blkif->blkdev_list, &blkio_schedule_list);
+ blkif_get(blkif);
+ }
+ spin_unlock_irqrestore(&blkio_schedule_list_lock, flags);
+}
+
+
+/******************************************************************
+ * SCHEDULER FUNCTIONS
+ */
+
+static DECLARE_WAIT_QUEUE_HEAD(blkio_schedule_wait);
+
+static int blkio_schedule(void *arg)
+{
+ DECLARE_WAITQUEUE(wq, current);
+
+ blkif_t *blkif;
+ struct list_head *ent;
+
+ daemonize(
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+ "xenblkd"
+#endif
+ );
+
+ for ( ; ; )
+ {
+ /* Wait for work to do. */
+ add_wait_queue(&blkio_schedule_wait, &wq);
+ set_current_state(TASK_INTERRUPTIBLE);
+ if ( (NR_PENDING_REQS == MAX_PENDING_REQS) ||
+ list_empty(&blkio_schedule_list) )
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ remove_wait_queue(&blkio_schedule_wait, &wq);
+
+ /* Queue up a batch of requests. */
+ while ( (NR_PENDING_REQS < MAX_PENDING_REQS) &&
+ !list_empty(&blkio_schedule_list) )
+ {
+ ent = blkio_schedule_list.next;
+ blkif = list_entry(ent, blkif_t, blkdev_list);
+ blkif_get(blkif);
+ remove_from_blkdev_list(blkif);
+ if ( do_block_io_op(blkif, BATCH_PER_DOMAIN) )
+ add_to_blkdev_list_tail(blkif);
+ blkif_put(blkif);
+ }
+
+ /* Push the batch through to disc. */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
+ run_task_queue(&tq_disk);
+#else
+ flush_plugged_queue();
+#endif
+ }
+}
+
+static void maybe_trigger_blkio_schedule(void)
+{
+ /*
+ * Needed so that two processes, who together make the following predicate
+ * true, don't both read stale values and evaluate the predicate
+ * incorrectly. Incredibly unlikely to stall the scheduler on x86, but...
+ */
+ smp_mb();
+
+ if ( (NR_PENDING_REQS < (MAX_PENDING_REQS/2)) &&
+ !list_empty(&blkio_schedule_list) )
+ wake_up(&blkio_schedule_wait);
+}
+
+
+
+/******************************************************************
+ * COMPLETION CALLBACK -- Called as bh->b_end_io()
+ */
+
+static void __end_block_io_op(pending_req_t *pending_req, int uptodate)
+{
+ unsigned long flags;
+
+ /* An error fails the entire request. */
+ if ( !uptodate )
+ {
+ DPRINTK("Buffer not up-to-date at end of operation\n");
+ pending_req->status = BLKIF_RSP_ERROR;
+ }
+
+ if ( atomic_dec_and_test(&pending_req->pendcnt) )
+ {
+ int pending_idx = pending_req - pending_reqs;
+ fast_flush_area(pending_idx, pending_req->nr_pages);
+ make_response(pending_req->blkif, pending_req->id,
+ pending_req->operation, pending_req->status);
+ blkif_put(pending_req->blkif);
+ spin_lock_irqsave(&pend_prod_lock, flags);
+ pending_ring[MASK_PEND_IDX(pending_prod++)] = pending_idx;
+ spin_unlock_irqrestore(&pend_prod_lock, flags);
+ maybe_trigger_blkio_schedule();
+ }
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
+static void end_block_io_op(struct buffer_head *bh, int uptodate)
+{
+ __end_block_io_op(bh->b_private, uptodate);
+ kmem_cache_free(buffer_head_cachep, bh);
+}
+#else
+static int end_block_io_op(struct bio *bio, unsigned int done, int error)
+{
+ if ( bio->bi_size != 0 )
+ return 1;
+ __end_block_io_op(bio->bi_private, !error);
+ bio_put(bio);
+ return error;
+}
+#endif
+
+
+/******************************************************************************
+ * NOTIFICATION FROM GUEST OS.
+ */
+
+irqreturn_t blkif_be_int(int irq, void *dev_id, struct pt_regs *regs)
+{
+ blkif_t *blkif = dev_id;
+ add_to_blkdev_list_tail(blkif);
+ maybe_trigger_blkio_schedule();
+ return IRQ_HANDLED;
+}
+
+
+
+/******************************************************************
+ * DOWNWARD CALLS -- These interface with the block-device layer proper.
+ */
+
+static int do_block_io_op(blkif_t *blkif, int max_to_do)
+{
+ blkif_back_ring_t *blk_ring = &blkif->blk_ring;
+ blkif_request_t *req;
+ RING_IDX i, rp;
+ int more_to_do = 0;
+
+ rp = blk_ring->sring->req_prod;
+ rmb(); /* Ensure we see queued requests up to 'rp'. */
+
+ for ( i = blk_ring->req_cons;
+ (i != rp) && !RING_REQUEST_CONS_OVERFLOW(blk_ring, i);
+ i++ )
+ {
+ if ( (max_to_do-- == 0) || (NR_PENDING_REQS == MAX_PENDING_REQS) )
+ {
+ more_to_do = 1;
+ break;
+ }
+
+ req = RING_GET_REQUEST(blk_ring, i);
+ switch ( req->operation )
+ {
+ case BLKIF_OP_READ:
+ case BLKIF_OP_WRITE:
+ dispatch_rw_block_io(blkif, req);
+ break;
+
+ case BLKIF_OP_PROBE:
+ dispatch_probe(blkif, req);
+ break;
+
+ default:
+ DPRINTK("error: unknown block io operation [%d]\n",
+ req->operation);
+ make_response(blkif, req->id, req->operation, BLKIF_RSP_ERROR);
+ break;
+ }
+ }
+
+ blk_ring->req_cons = i;
+ return more_to_do;
+}
+
+static void dispatch_probe(blkif_t *blkif, blkif_request_t *req)
+{
+ int rsp = BLKIF_RSP_ERROR;
+ int pending_idx = pending_ring[MASK_PEND_IDX(pending_cons)];
+
+ /* We expect one buffer only. */
+ if ( unlikely(req->nr_segments != 1) )
+ goto out;
+
+ /* Make sure the buffer is page-sized. */
+ if ( (blkif_first_sect(req->frame_and_sects[0]) != 0) ||
+ (blkif_last_sect(req->frame_and_sects[0]) != 7) )
+ goto out;
+
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ {
+ struct gnttab_map_grant_ref map;
+
+ map.host_virt_addr = MMAP_VADDR(pending_idx, 0);
+ map.flags = GNTMAP_host_map;
+ map.ref = blkif_gref_from_fas(req->frame_and_sects[0]);
+ map.dom = blkif->domid;
+
+ if ( unlikely(HYPERVISOR_grant_table_op(
+ GNTTABOP_map_grant_ref, &map, 1)))
+ BUG();
+
+ if ( map.handle < 0 )
+ goto out;
+
+ pending_handle(pending_idx, 0) = map.handle;
+ }
+#else /* else CONFIG_XEN_BLKDEV_GRANT */
+
+#ifdef CONFIG_XEN_BLKDEV_TAP_BE
+ /* Grab the real frontend out of the probe message. */
+ if (req->frame_and_sects[1] == BLKTAP_COOKIE)
+ blkif->is_blktap = 1;
+#endif
+
+
+#ifdef CONFIG_XEN_BLKDEV_TAP_BE
+ if ( HYPERVISOR_update_va_mapping_otherdomain(
+ MMAP_VADDR(pending_idx, 0),
+ (pte_t) { (req->frame_and_sects[0] & PAGE_MASK) | __PAGE_KERNEL },
+ 0, (blkif->is_blktap ? ID_TO_DOM(req->id) : blkif->domid) ) )
+
+ goto out;
+#else
+ if ( HYPERVISOR_update_va_mapping_otherdomain(
+ MMAP_VADDR(pending_idx, 0),
+ (pte_t) { (req->frame_and_sects[0] & PAGE_MASK) | __PAGE_KERNEL },
+ 0, blkif->domid) )
+
+ goto out;
+#endif
+#endif /* endif CONFIG_XEN_BLKDEV_GRANT */
+
+ rsp = vbd_probe(blkif, (vdisk_t *)MMAP_VADDR(pending_idx, 0),
+ PAGE_SIZE / sizeof(vdisk_t));
+
+ out:
+ fast_flush_area(pending_idx, 1);
+ make_response(blkif, req->id, req->operation, rsp);
+}
+
+static void dispatch_rw_block_io(blkif_t *blkif, blkif_request_t *req)
+{
+ extern void ll_rw_block(int rw, int nr, struct buffer_head * bhs[]);
+ int operation = (req->operation == BLKIF_OP_WRITE) ? WRITE : READ;
+ unsigned long fas = 0;
+ int i, pending_idx = pending_ring[MASK_PEND_IDX(pending_cons)];
+ pending_req_t *pending_req;
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ struct gnttab_map_grant_ref map[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+#else
+ unsigned long remap_prot;
+ multicall_entry_t mcl[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+#endif
+ struct phys_req preq;
+ struct {
+ unsigned long buf; unsigned int nsec;
+ } seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ unsigned int nseg;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
+ struct buffer_head *bh;
+#else
+ struct bio *bio = NULL, *biolist[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ int nbio = 0;
+ request_queue_t *q;
+#endif
+
+ /* Check that number of segments is sane. */
+ nseg = req->nr_segments;
+ if ( unlikely(nseg == 0) ||
+ unlikely(nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST) )
+ {
+ DPRINTK("Bad number of segments in request (%d)\n", nseg);
+ goto bad_descriptor;
+ }
+
+ preq.dev = req->device;
+ preq.sector_number = req->sector_number;
+ preq.nr_sects = 0;
+
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ for ( i = 0; i < nseg; i++ )
+ {
+ fas = req->frame_and_sects[i];
+ seg[i].nsec = blkif_last_sect(fas) - blkif_first_sect(fas) + 1;
+
+ if ( seg[i].nsec <= 0 )
+ goto bad_descriptor;
+ preq.nr_sects += seg[i].nsec;
+
+ map[i].host_virt_addr = MMAP_VADDR(pending_idx, i);
+ map[i].dom = blkif->domid;
+ map[i].ref = blkif_gref_from_fas(fas);
+ map[i].flags = GNTMAP_host_map;
+ if ( operation == WRITE )
+ map[i].flags |= GNTMAP_readonly;
+ }
+
+ if ( unlikely(HYPERVISOR_grant_table_op(
+ GNTTABOP_map_grant_ref, map, nseg)))
+ BUG();
+
+ for ( i = 0; i < nseg; i++ )
+ {
+ if ( unlikely(map[i].handle < 0) )
+ {
+ DPRINTK("invalid buffer -- could not remap it\n");
+ fast_flush_area(pending_idx, nseg);
+ goto bad_descriptor;
+ }
+
+ phys_to_machine_mapping[__pa(MMAP_VADDR(pending_idx, i))>>PAGE_SHIFT] =
+ FOREIGN_FRAME(map[i].dev_bus_addr);
+
+ pending_handle(pending_idx, i) = map[i].handle;
+ }
+#endif
+
+ for ( i = 0; i < nseg; i++ )
+ {
+ fas = req->frame_and_sects[i];
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ seg[i].buf = (map[i].dev_bus_addr << PAGE_SHIFT) |
+ (blkif_first_sect(fas) << 9);
+#else
+ seg[i].buf = (fas & PAGE_MASK) | (blkif_first_sect(fas) << 9);
+ seg[i].nsec = blkif_last_sect(fas) - blkif_first_sect(fas) + 1;
+ if ( seg[i].nsec <= 0 )
+ goto bad_descriptor;
+ preq.nr_sects += seg[i].nsec;
+#endif
+ }
+
+ if ( vbd_translate(&preq, blkif, operation) != 0 )
+ {
+ DPRINTK("access denied: %s of [%llu,%llu] on dev=%04x\n",
+ operation == READ ? "read" : "write", preq.sector_number,
+ preq.sector_number + preq.nr_sects, preq.dev);
+ goto bad_descriptor;
+ }
+
+#ifndef CONFIG_XEN_BLKDEV_GRANT
+ if ( operation == READ )
+ remap_prot = _PAGE_PRESENT|_PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_RW;
+ else
+ remap_prot = _PAGE_PRESENT|_PAGE_DIRTY|_PAGE_ACCESSED;
+
+ for ( i = 0; i < nseg; i++ )
+ {
+ MULTI_update_va_mapping_otherdomain(
+ mcl+i, MMAP_VADDR(pending_idx, i),
+ pfn_pte_ma(seg[i].buf >> PAGE_SHIFT, remap_prot),
+ 0, blkif->domid);
+#ifdef CONFIG_XEN_BLKDEV_TAP_BE
+ if ( blkif->is_blktap )
+ mcl[i].args[3] = ID_TO_DOM(req->id);
+#endif
+ phys_to_machine_mapping[__pa(MMAP_VADDR(pending_idx, i))>>PAGE_SHIFT] =
+ FOREIGN_FRAME(seg[i].buf >> PAGE_SHIFT);
+ }
+
+ BUG_ON(HYPERVISOR_multicall(mcl, nseg) != 0);
+
+ for ( i = 0; i < nseg; i++ )
+ {
+ if ( unlikely(mcl[i].result != 0) )
+ {
+ DPRINTK("invalid buffer -- could not remap it\n");
+ fast_flush_area(pending_idx, nseg);
+ goto bad_descriptor;
+ }
+ }
+#endif /* end ifndef CONFIG_XEN_BLKDEV_GRANT */
+
+ pending_req = &pending_reqs[pending_idx];
+ pending_req->blkif = blkif;
+ pending_req->id = req->id;
+ pending_req->operation = operation;
+ pending_req->status = BLKIF_RSP_OKAY;
+ pending_req->nr_pages = nseg;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
+
+ atomic_set(&pending_req->pendcnt, nseg);
+ pending_cons++;
+ blkif_get(blkif);
+
+ for ( i = 0; i < nseg; i++ )
+ {
+ bh = kmem_cache_alloc(buffer_head_cachep, GFP_KERNEL);
+ if ( unlikely(bh == NULL) )
+ {
+ __end_block_io_op(pending_req, 0);
+ continue;
+ }
+
+ memset(bh, 0, sizeof (struct buffer_head));
+
+ init_waitqueue_head(&bh->b_wait);
+ bh->b_size = seg[i].nsec << 9;
+ bh->b_dev = preq.dev;
+ bh->b_rdev = preq.dev;
+ bh->b_rsector = (unsigned long)preq.sector_number;
+ bh->b_data = (char *)MMAP_VADDR(pending_idx, i) +
+ (seg[i].buf & ~PAGE_MASK);
+ bh->b_page = virt_to_page(MMAP_VADDR(pending_idx, i));
+ bh->b_end_io = end_block_io_op;
+ bh->b_private = pending_req;
+
+ bh->b_state = (1 << BH_Mapped) | (1 << BH_Lock) |
+ (1 << BH_Req) | (1 << BH_Launder);
+ if ( operation == WRITE )
+ bh->b_state |= (1 << BH_JBD) | (1 << BH_Req) | (1 << BH_Uptodate);
+
+ atomic_set(&bh->b_count, 1);
+
+ /* Dispatch a single request. We'll flush it to disc later. */
+ generic_make_request(operation, bh);
+
+ preq.sector_number += seg[i].nsec;
+ }
+
+#else
+
+ for ( i = 0; i < nseg; i++ )
+ {
+ if ( ((int)preq.sector_number|(int)seg[i].nsec) &
+ ((bdev_hardsect_size(preq.bdev) >> 9) - 1) )
+ {
+ DPRINTK("Misaligned I/O request from domain %d", blkif->domid);
+ goto cleanup_and_fail;
+ }
+
+ while ( (bio == NULL) ||
+ (bio_add_page(bio,
+ virt_to_page(MMAP_VADDR(pending_idx, i)),
+ seg[i].nsec << 9,
+ seg[i].buf & ~PAGE_MASK) == 0) )
+ {
+ bio = biolist[nbio++] = bio_alloc(GFP_KERNEL, nseg-i);
+ if ( unlikely(bio == NULL) )
+ {
+ cleanup_and_fail:
+ for ( i = 0; i < (nbio-1); i++ )
+ bio_put(biolist[i]);
+ fast_flush_area(pending_idx, nseg);
+ goto bad_descriptor;
+ }
+
+ bio->bi_bdev = preq.bdev;
+ bio->bi_private = pending_req;
+ bio->bi_end_io = end_block_io_op;
+ bio->bi_sector = preq.sector_number;
+ }
+
+ preq.sector_number += seg[i].nsec;
+ }
+
+ if ( (q = bdev_get_queue(bio->bi_bdev)) != plugged_queue )
+ {
+ flush_plugged_queue();
+ blk_get_queue(q);
+ plugged_queue = q;
+ }
+
+ atomic_set(&pending_req->pendcnt, nbio);
+ pending_cons++;
+ blkif_get(blkif);
+
+ for ( i = 0; i < nbio; i++ )
+ submit_bio(operation, biolist[i]);
+
+#endif
+
+ return;
+
+ bad_descriptor:
+ make_response(blkif, req->id, req->operation, BLKIF_RSP_ERROR);
+}
+
+
+
+/******************************************************************
+ * MISCELLANEOUS SETUP / TEARDOWN / DEBUGGING
+ */
+
+
+static void make_response(blkif_t *blkif, unsigned long id,
+ unsigned short op, int st)
+{
+ blkif_response_t *resp;
+ unsigned long flags;
+ blkif_back_ring_t *blk_ring = &blkif->blk_ring;
+
+ /* Place on the response ring for the relevant domain. */
+ spin_lock_irqsave(&blkif->blk_ring_lock, flags);
+ resp = RING_GET_RESPONSE(blk_ring, blk_ring->rsp_prod_pvt);
+ resp->id = id;
+ resp->operation = op;
+ resp->status = st;
+ wmb(); /* Ensure other side can see the response fields. */
+ blk_ring->rsp_prod_pvt++;
+ RING_PUSH_RESPONSES(blk_ring);
+ spin_unlock_irqrestore(&blkif->blk_ring_lock, flags);
+
+ /* Kick the relevant domain. */
+ notify_via_evtchn(blkif->evtchn);
+}
+
+void blkif_deschedule(blkif_t *blkif)
+{
+ remove_from_blkdev_list(blkif);
+}
+
+static int __init blkif_init(void)
+{
+ int i;
+
+ if ( !(xen_start_info.flags & SIF_INITDOMAIN) &&
+ !(xen_start_info.flags & SIF_BLK_BE_DOMAIN) )
+ return 0;
+
+ blkif_interface_init();
+
+ if ( (mmap_vstart = allocate_empty_lowmem_region(MMAP_PAGES)) == 0 )
+ BUG();
+
+ pending_cons = 0;
+ pending_prod = MAX_PENDING_REQS;
+ memset(pending_reqs, 0, sizeof(pending_reqs));
+ for ( i = 0; i < MAX_PENDING_REQS; i++ )
+ pending_ring[i] = i;
+
+ spin_lock_init(&blkio_schedule_list_lock);
+ INIT_LIST_HEAD(&blkio_schedule_list);
+
+ if ( kernel_thread(blkio_schedule, 0, CLONE_FS | CLONE_FILES) < 0 )
+ BUG();
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
+ buffer_head_cachep = kmem_cache_create(
+ "buffer_head_cache", sizeof(struct buffer_head),
+ 0, SLAB_HWCACHE_ALIGN, NULL, NULL);
+#endif
+
+ blkif_ctrlif_init();
+
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ memset( pending_grant_handles, BLKBACK_INVALID_HANDLE, MMAP_PAGES );
+ printk(KERN_ALERT "Blkif backend is using grant tables.\n");
+#endif
+
+#ifdef CONFIG_XEN_BLKDEV_TAP_BE
+ printk(KERN_ALERT "NOTE: Blkif backend is running with tap support on!\n");
+#endif
+
+ return 0;
+}
+
+__initcall(blkif_init);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/vsyscall.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/vsyscall.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,190 @@
+/*
+ * linux/arch/x86_64/kernel/vsyscall.c
+ *
+ * Copyright (C) 2001 Andrea Arcangeli <andrea@xxxxxxx> SuSE
+ * Copyright 2003 Andi Kleen, SuSE Labs.
+ *
+ * Thanks to hpa@xxxxxxxxxxxxx for some useful hint.
+ * Special thanks to Ingo Molnar for his early experience with
+ * a different vsyscall implementation for Linux/IA32 and for the name.
+ *
+ * vsyscall 1 is located at -10Mbyte, vsyscall 2 is located
+ * at virtual address -10Mbyte+1024bytes etc... There are at max 8192
+ * vsyscalls. One vsyscall can reserve more than 1 slot to avoid
+ * jumping out of line if necessary.
+ *
+ * Note: the concept clashes with user mode linux. If you use UML just
+ * set the kernel.vsyscall sysctl to 0.
+ */
+
+/*
+ * TODO 2001-03-20:
+ *
+ * 1) make page fault handler detect faults on page1-page-last of the vsyscall
+ * virtual space, and make it increase %rip and write -ENOSYS in %rax (so
+ * we'll be able to upgrade to a new glibc without upgrading kernel after
+ * we add more vsyscalls.
+ * 2) Possibly we need a fixmap table for the vsyscalls too if we want
+ * to avoid SIGSEGV and we want to return -EFAULT from the vsyscalls as
well.
+ * Can we segfault inside a "syscall"? We can fix this anytime and those
fixes
+ * won't be visible for userspace. Not fixing this is a noop for correct
programs,
+ * broken programs will segfault and there's no security risk until we
choose to
+ * fix it.
+ *
+ * These are not urgent things that we need to address only before shipping
the first
+ * production binary kernels.
+ */
+
+#include <linux/time.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/timer.h>
+#include <linux/seqlock.h>
+#include <linux/jiffies.h>
+
+#include <asm/vsyscall.h>
+#include <asm/pgtable.h>
+#include <asm/page.h>
+#include <asm/fixmap.h>
+#include <asm/errno.h>
+#include <asm/io.h>
+
+#define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr)))
+#define force_inline __attribute__((always_inline)) inline
+
+int __sysctl_vsyscall __section_sysctl_vsyscall = 1;
+seqlock_t __xtime_lock __section_xtime_lock = SEQLOCK_UNLOCKED;
+
+#include <asm/unistd.h>
+
+static force_inline void timeval_normalize(struct timeval * tv)
+{
+ time_t __sec;
+
+ __sec = tv->tv_usec / 1000000;
+ if (__sec)
+ {
+ tv->tv_usec %= 1000000;
+ tv->tv_sec += __sec;
+ }
+}
+
+static force_inline void do_vgettimeofday(struct timeval * tv)
+{
+ long sequence, t;
+ unsigned long sec, usec;
+
+ do {
+ sequence = read_seqbegin(&__xtime_lock);
+
+ sec = __xtime.tv_sec;
+ usec = (__xtime.tv_nsec / 1000) +
+ (__jiffies - __wall_jiffies) * (1000000 / HZ);
+
+ if (__vxtime.mode == VXTIME_TSC) {
+ sync_core();
+ rdtscll(t);
+ if (t < __vxtime.last_tsc) t = __vxtime.last_tsc;
+ usec += ((t - __vxtime.last_tsc) *
+ __vxtime.tsc_quot) >> 32;
+ /* See comment in x86_64 do_gettimeofday. */
+ } else {
+ usec += ((readl((void *)fix_to_virt(VSYSCALL_HPET) +
0xf0) -
+ __vxtime.last) * __vxtime.quot) >> 32;
+ }
+ } while (read_seqretry(&__xtime_lock, sequence));
+
+ tv->tv_sec = sec + usec / 1000000;
+ tv->tv_usec = usec % 1000000;
+}
+
+/* RED-PEN may want to readd seq locking, but then the variable should be
write-once. */
+static force_inline void do_get_tz(struct timezone * tz)
+{
+ *tz = __sys_tz;
+}
+
+
+static force_inline int gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+ int ret;
+ asm volatile("syscall"
+ : "=a" (ret)
+ : "0" (__NR_gettimeofday),"D" (tv),"S" (tz) : __syscall_clobber
);
+ return ret;
+}
+
+static force_inline long time_syscall(long *t)
+{
+ long secs;
+ asm volatile("syscall"
+ : "=a" (secs)
+ : "0" (__NR_time),"D" (t) : __syscall_clobber);
+ return secs;
+}
+
+static int __vsyscall(0) vgettimeofday(struct timeval * tv, struct timezone *
tz)
+{
+ if (unlikely(!__sysctl_vsyscall))
+ return gettimeofday(tv,tz);
+ if (tv)
+ do_vgettimeofday(tv);
+ if (tz)
+ do_get_tz(tz);
+ return 0;
+}
+
+/* This will break when the xtime seconds get inaccurate, but that is
+ * unlikely */
+static time_t __vsyscall(1) vtime(time_t *t)
+{
+ if (unlikely(!__sysctl_vsyscall))
+ return time_syscall(t);
+ else if (t)
+ *t = __xtime.tv_sec;
+ return __xtime.tv_sec;
+}
+
+static long __vsyscall(2) venosys_0(void)
+{
+ return -ENOSYS;
+}
+
+static long __vsyscall(3) venosys_1(void)
+{
+ return -ENOSYS;
+
+}
+
+static void __init map_vsyscall(void)
+{
+ extern char __vsyscall_0;
+ unsigned long physaddr_page0 = __pa_symbol(&__vsyscall_0);
+
+ __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_page0, PAGE_KERNEL_VSYSCALL);
+}
+
+extern void __set_fixmap_user (enum fixed_addresses, unsigned long, pgprot_t);
+
+static void __init map_vsyscall_user(void)
+{
+ extern char __vsyscall_0;
+ unsigned long physaddr_page0 = __pa_symbol(&__vsyscall_0);
+
+ __set_fixmap_user(VSYSCALL_FIRST_PAGE, physaddr_page0,
PAGE_KERNEL_VSYSCALL);
+}
+
+static int __init vsyscall_init(void)
+{
+ BUG_ON(((unsigned long) &vgettimeofday !=
+ VSYSCALL_ADDR(__NR_vgettimeofday)));
+ BUG_ON((unsigned long) &vtime != VSYSCALL_ADDR(__NR_vtime));
+ BUG_ON((VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE)));
+ map_vsyscall();
+ map_vsyscall_user(); /* establish tranlation for user address space
*/
+ sysctl_vsyscall = 0; /* TBD */
+
+ return 0;
+}
+
+__initcall(vsyscall_init);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/timers/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/timers/Makefile Fri Jul
15 13:39:50 2005
@@ -0,0 +1,17 @@
+#
+# Makefile for x86 timers
+#
+
+XENARCH := $(subst ",,$(CONFIG_XENARCH))
+
+obj-y := timer_tsc.o
+c-obj-y :=
+
+c-link :=
+
+$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)):
+ @ln -fsn $(srctree)/arch/i386/kernel/timers/$(notdir $@) $@
+
+obj-y += $(c-obj-y)
+
+clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link))
diff -r 35b74976f598 -r a83ac0806d6b patches/linux-2.6.11/iomap.patch
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/patches/linux-2.6.11/iomap.patch Fri Jul 15 13:39:50 2005
@@ -0,0 +1,120 @@
+diff -ur linux-2.6.11/drivers/char/agp/frontend.c
linux-2.6.11-io/drivers/char/agp/frontend.c
+--- linux-2.6.11/drivers/char/agp/frontend.c 2005-03-02 07:37:49.000000000
+0000
++++ linux-2.6.11-io/drivers/char/agp/frontend.c 2005-03-15
17:38:30.000000000 +0000
+@@ -627,7 +627,7 @@
+ DBG("client vm_ops=%p", kerninfo.vm_ops);
+ if (kerninfo.vm_ops) {
+ vma->vm_ops = kerninfo.vm_ops;
+- } else if (remap_pfn_range(vma, vma->vm_start,
++ } else if (io_remap_pfn_range(vma, vma->vm_start,
+ (kerninfo.aper_base + offset) >> PAGE_SHIFT,
+ size, vma->vm_page_prot)) {
+ goto out_again;
+@@ -643,7 +643,7 @@
+ DBG("controller vm_ops=%p", kerninfo.vm_ops);
+ if (kerninfo.vm_ops) {
+ vma->vm_ops = kerninfo.vm_ops;
+- } else if (remap_pfn_range(vma, vma->vm_start,
++ } else if (io_remap_pfn_range(vma, vma->vm_start,
+ kerninfo.aper_base >> PAGE_SHIFT,
+ size, vma->vm_page_prot)) {
+ goto out_again;
+diff -ur linux-2.6.11/drivers/char/drm/drm_vm.c
linux-2.6.11-io/drivers/char/drm/drm_vm.c
+--- linux-2.6.11/drivers/char/drm/drm_vm.c 2005-03-02 07:38:33.000000000
+0000
++++ linux-2.6.11-io/drivers/char/drm/drm_vm.c 2005-03-15 17:43:26.000000000
+0000
+@@ -630,7 +630,7 @@
+ vma->vm_end - vma->vm_start,
+ vma->vm_page_prot, 0))
+ #else
+- if (remap_pfn_range(DRM_RPR_ARG(vma) vma->vm_start,
++ if (io_remap_pfn_range(vma, vma->vm_start,
+ (VM_OFFSET(vma) + offset) >> PAGE_SHIFT,
+ vma->vm_end - vma->vm_start,
+ vma->vm_page_prot))
+diff -ur linux-2.6.11/drivers/char/drm/i810_dma.c
linux-2.6.11-io/drivers/char/drm/i810_dma.c
+--- linux-2.6.11/drivers/char/drm/i810_dma.c 2005-03-02 07:37:55.000000000
+0000
++++ linux-2.6.11-io/drivers/char/drm/i810_dma.c 2005-03-15
17:53:36.000000000 +0000
+@@ -139,7 +139,7 @@
+ buf_priv->currently_mapped = I810_BUF_MAPPED;
+ unlock_kernel();
+
+- if (remap_pfn_range(DRM_RPR_ARG(vma) vma->vm_start,
++ if (io_remap_pfn_range(vma, vma->vm_start,
+ VM_OFFSET(vma) >> PAGE_SHIFT,
+ vma->vm_end - vma->vm_start,
+ vma->vm_page_prot)) return -EAGAIN;
+diff -ur linux-2.6.11/drivers/char/drm/i830_dma.c
linux-2.6.11-io/drivers/char/drm/i830_dma.c
+--- linux-2.6.11/drivers/char/drm/i830_dma.c 2005-03-02 07:37:48.000000000
+0000
++++ linux-2.6.11-io/drivers/char/drm/i830_dma.c 2005-03-15
17:53:46.000000000 +0000
+@@ -157,7 +157,7 @@
+ buf_priv->currently_mapped = I830_BUF_MAPPED;
+ unlock_kernel();
+
+- if (remap_pfn_range(DRM_RPR_ARG(vma) vma->vm_start,
++ if (io_remap_pfn_range(vma, vma->vm_start,
+ VM_OFFSET(vma) >> PAGE_SHIFT,
+ vma->vm_end - vma->vm_start,
+ vma->vm_page_prot)) return -EAGAIN;
+diff -ur linux-2.6.11/drivers/char/hpet.c linux-2.6.11-io/drivers/char/hpet.c
+--- linux-2.6.11/drivers/char/hpet.c 2005-03-02 07:38:10.000000000 +0000
++++ linux-2.6.11-io/drivers/char/hpet.c 2005-03-15 17:37:22.000000000
+0000
+@@ -76,6 +76,7 @@
+ struct hpets {
+ struct hpets *hp_next;
+ struct hpet __iomem *hp_hpet;
++ unsigned long hp_hpet_phys;
+ struct time_interpolator *hp_interpolator;
+ unsigned long hp_period;
+ unsigned long hp_delta;
+@@ -265,7 +266,7 @@
+ return -EINVAL;
+
+ devp = file->private_data;
+- addr = (unsigned long)devp->hd_hpet;
++ addr = devp->hd_hpets->hp_hpet_phys;
+
+ if (addr & (PAGE_SIZE - 1))
+ return -ENOSYS;
+@@ -274,7 +275,7 @@
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+ addr = __pa(addr);
+
+- if (remap_pfn_range(vma, vma->vm_start, addr >> PAGE_SHIFT,
++ if (io_remap_pfn_range(vma, vma->vm_start, addr >> PAGE_SHIFT,
+ PAGE_SIZE, vma->vm_page_prot)) {
+ printk(KERN_ERR "remap_pfn_range failed in hpet.c\n");
+ return -EAGAIN;
+@@ -795,6 +796,7 @@
+
+ hpetp->hp_which = hpet_nhpet++;
+ hpetp->hp_hpet = hdp->hd_address;
++ hpetp->hp_hpet_phys = hdp->hd_phys_address;
+
+ hpetp->hp_ntimer = hdp->hd_nirqs;
+
+diff -ur linux-2.6.11/drivers/sbus/char/flash.c
linux-2.6.11-io/drivers/sbus/char/flash.c
+--- linux-2.6.11/drivers/sbus/char/flash.c 2005-03-02 07:38:10.000000000
+0000
++++ linux-2.6.11-io/drivers/sbus/char/flash.c 2005-03-15 17:20:22.000000000
+0000
+@@ -75,7 +75,7 @@
+ pgprot_val(vma->vm_page_prot) |= _PAGE_E;
+ vma->vm_flags |= (VM_SHM | VM_LOCKED);
+
+- if (remap_pfn_range(vma, vma->vm_start, addr, size, vma->vm_page_prot))
++ if (io_remap_pfn_range(vma, vma->vm_start, addr, size,
vma->vm_page_prot))
+ return -EAGAIN;
+
+ return 0;
+diff -ur linux-2.6.11/include/linux/mm.h linux-2.6.11-io/include/linux/mm.h
+--- linux-2.6.11/include/linux/mm.h 2005-03-02 07:37:47.000000000 +0000
++++ linux-2.6.11-io/include/linux/mm.h 2005-03-15 17:03:46.000000000 +0000
+@@ -815,6 +815,10 @@
+ extern int check_user_page_readable(struct mm_struct *mm, unsigned long
address);
+ int remap_pfn_range(struct vm_area_struct *, unsigned long,
+ unsigned long, unsigned long, pgprot_t);
++/* Allow arch override for mapping of device and I/O (non-RAM) pages. */
++#ifndef io_remap_pfn_range
++#define io_remap_pfn_range remap_pfn_range
++#endif
+
+ #ifdef CONFIG_PROC_FS
+ void __vm_stat_account(struct mm_struct *, unsigned long, struct file *,
long);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/pgtable.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/pgtable.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,371 @@
+#ifndef _I386_PGTABLE_H
+#define _I386_PGTABLE_H
+
+#include <linux/config.h>
+
+/*
+ * The Linux memory management assumes a three-level page table setup. On
+ * the i386, we use that, but "fold" the mid level into the top-level page
+ * table, so that we physically have the same two-level page table as the
+ * i386 mmu expects.
+ *
+ * This file contains the functions and defines necessary to modify and use
+ * the i386 page table tree.
+ */
+#ifndef __ASSEMBLY__
+#include <asm/processor.h>
+#include <asm/hypervisor.h>
+#include <linux/threads.h>
+#include <asm/fixmap.h>
+
+#ifndef _I386_BITOPS_H
+#include <asm/bitops.h>
+#endif
+
+#define swapper_pg_dir 0
+extern void paging_init(void);
+
+/* Caches aren't brain-dead on the intel. */
+#define flush_cache_all() do { } while (0)
+#define flush_cache_mm(mm) do { } while (0)
+#define flush_cache_range(mm, start, end) do { } while (0)
+#define flush_cache_page(vma, vmaddr) do { } while (0)
+#define flush_page_to_ram(page) do { } while (0)
+#define flush_dcache_page(page) do { } while (0)
+#define flush_icache_range(start, end) do { } while (0)
+#define flush_icache_page(vma,pg) do { } while (0)
+#define flush_icache_user_range(vma,pg,adr,len) do { } while (0)
+
+extern unsigned long pgkern_mask;
+
+#define __flush_tlb() xen_tlb_flush()
+#define __flush_tlb_global() __flush_tlb()
+#define __flush_tlb_all() __flush_tlb_global()
+#define __flush_tlb_one(addr) xen_invlpg(addr)
+#define __flush_tlb_single(addr) xen_invlpg(addr)
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+extern unsigned long empty_zero_page[1024];
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * The Linux x86 paging architecture is 'compile-time dual-mode', it
+ * implements both the traditional 2-level x86 page tables and the
+ * newer 3-level PAE-mode page tables.
+ */
+#ifndef __ASSEMBLY__
+#if CONFIG_X86_PAE
+# include <asm/pgtable-3level.h>
+
+/*
+ * Need to initialise the X86 PAE caches
+ */
+extern void pgtable_cache_init(void);
+
+#else
+# include <asm/pgtable-2level.h>
+
+/*
+ * No page table caches to initialise
+ */
+#define pgtable_cache_init() do { } while (0)
+
+#endif
+#endif
+
+#define PMD_SIZE (1UL << PMD_SHIFT)
+#define PMD_MASK (~(PMD_SIZE-1))
+#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE-1))
+
+#define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE)
+#define FIRST_USER_PGD_NR 0
+
+#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
+#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)
+
+#define TWOLEVEL_PGDIR_SHIFT 22
+#define BOOT_USER_PGD_PTRS (__PAGE_OFFSET >> TWOLEVEL_PGDIR_SHIFT)
+#define BOOT_KERNEL_PGD_PTRS (1024-BOOT_USER_PGD_PTRS)
+
+
+#ifndef __ASSEMBLY__
+/* 4MB is just a nice "safety zone". Also, we align to a fresh pde. */
+#define VMALLOC_OFFSET (4*1024*1024)
+extern void * high_memory;
+#define VMALLOC_START (((unsigned long) high_memory + 2*VMALLOC_OFFSET-1) & \
+ ~(VMALLOC_OFFSET-1))
+#define VMALLOC_VMADDR(x) ((unsigned long)(x))
+#if CONFIG_HIGHMEM
+# define VMALLOC_END (PKMAP_BASE-2*PAGE_SIZE)
+#else
+# define VMALLOC_END (FIXADDR_START-2*PAGE_SIZE)
+#endif
+
+#define _PAGE_BIT_PRESENT 0
+#define _PAGE_BIT_RW 1
+#define _PAGE_BIT_USER 2
+#define _PAGE_BIT_PWT 3
+#define _PAGE_BIT_PCD 4
+#define _PAGE_BIT_ACCESSED 5
+#define _PAGE_BIT_DIRTY 6
+#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page, Pentium+, if
present.. */
+#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
+
+#define _PAGE_PRESENT 0x001
+#define _PAGE_RW 0x002
+#define _PAGE_USER 0x004
+#define _PAGE_PWT 0x008
+#define _PAGE_PCD 0x010
+#define _PAGE_ACCESSED 0x020
+#define _PAGE_DIRTY 0x040
+#define _PAGE_PSE 0x080 /* 4 MB (or 2MB) page, Pentium+, if present.. */
+#define _PAGE_GLOBAL 0x100 /* Global TLB entry PPro+ */
+
+#define _PAGE_PROTNONE 0x080 /* If not present */
+
+#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED
| _PAGE_DIRTY)
+#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED |
_PAGE_DIRTY)
+#define _PAGE_CHG_MASK (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+
+#define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
+#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |
_PAGE_ACCESSED)
+#define PAGE_COPY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+
+#define __PAGE_KERNEL \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
+#define __PAGE_KERNEL_NOCACHE \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_PCD | _PAGE_ACCESSED)
+#define __PAGE_KERNEL_RO \
+ (_PAGE_PRESENT | _PAGE_DIRTY | _PAGE_ACCESSED)
+
+#if 0
+#define MAKE_GLOBAL(x) __pgprot((x) | _PAGE_GLOBAL)
+#else
+#define MAKE_GLOBAL(x) __pgprot(x)
+#endif
+
+#define PAGE_KERNEL MAKE_GLOBAL(__PAGE_KERNEL)
+#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO)
+#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
+
+/*
+ * The i386 can't do page protection for execute, and considers that
+ * the same are read. Also, write permissions imply read permissions.
+ * This is the closest we can get..
+ */
+#define __P000 PAGE_NONE
+#define __P001 PAGE_READONLY
+#define __P010 PAGE_COPY
+#define __P011 PAGE_COPY
+#define __P100 PAGE_READONLY
+#define __P101 PAGE_READONLY
+#define __P110 PAGE_COPY
+#define __P111 PAGE_COPY
+
+#define __S000 PAGE_NONE
+#define __S001 PAGE_READONLY
+#define __S010 PAGE_SHARED
+#define __S011 PAGE_SHARED
+#define __S100 PAGE_READONLY
+#define __S101 PAGE_READONLY
+#define __S110 PAGE_SHARED
+#define __S111 PAGE_SHARED
+
+#define pte_present(x) ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
+#define pte_clear(xp) do { set_pte(xp, __pte(0)); } while (0)
+
+#define pmd_none(x) (!pmd_val(x))
+/* pmd_present doesn't just test the _PAGE_PRESENT bit since wr.p.t.
+ can temporarily clear it. */
+#define pmd_present(x) (pmd_val(x))
+#define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0)
+#define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER &
~_PAGE_PRESENT)) != (_KERNPG_TABLE & ~_PAGE_PRESENT))
+
+
+#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+static inline int pte_read(pte_t pte) { return (pte).pte_low &
_PAGE_USER; }
+static inline int pte_exec(pte_t pte) { return (pte).pte_low &
_PAGE_USER; }
+static inline int pte_dirty(pte_t pte) { return (pte).pte_low &
_PAGE_DIRTY; }
+static inline int pte_young(pte_t pte) { return (pte).pte_low &
_PAGE_ACCESSED; }
+static inline int pte_write(pte_t pte) { return (pte).pte_low &
_PAGE_RW; }
+
+static inline pte_t pte_rdprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER;
return pte; }
+static inline pte_t pte_exprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER;
return pte; }
+static inline pte_t pte_mkclean(pte_t pte) { (pte).pte_low &=
~_PAGE_DIRTY; return pte; }
+static inline pte_t pte_mkold(pte_t pte) { (pte).pte_low &=
~_PAGE_ACCESSED; return pte; }
+static inline pte_t pte_wrprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_RW;
return pte; }
+static inline pte_t pte_mkread(pte_t pte) { (pte).pte_low |= _PAGE_USER;
return pte; }
+static inline pte_t pte_mkexec(pte_t pte) { (pte).pte_low |= _PAGE_USER;
return pte; }
+static inline pte_t pte_mkdirty(pte_t pte) { (pte).pte_low |= _PAGE_DIRTY;
return pte; }
+static inline pte_t pte_mkyoung(pte_t pte) { (pte).pte_low |=
_PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkwrite(pte_t pte) { (pte).pte_low |= _PAGE_RW;
return pte; }
+
+static inline int ptep_test_and_clear_dirty(pte_t *ptep)
+{
+ if (!pte_dirty(*ptep))
+ return 0;
+ return test_and_clear_bit(_PAGE_BIT_DIRTY, &ptep->pte_low);
+}
+
+static inline int ptep_test_and_clear_young(pte_t *ptep)
+{
+ if (!pte_young(*ptep))
+ return 0;
+ return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte_low);
+}
+
+static inline void ptep_set_wrprotect(pte_t *ptep)
+{
+ if (pte_write(*ptep))
+ clear_bit(_PAGE_BIT_RW, &ptep->pte_low);
+}
+
+static inline void ptep_mkdirty(pte_t *ptep)
+{
+ if (!pte_dirty(*ptep))
+ set_bit(_PAGE_BIT_DIRTY, &ptep->pte_low);
+}
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ */
+
+#define mk_pte(page, pgprot) __mk_pte((page) - mem_map, (pgprot))
+
+/* This takes a physical page address that is used by the remapping functions
*/
+#define mk_pte_phys(physpage, pgprot) __mk_pte((physpage) >> PAGE_SHIFT,
pgprot)
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+ pte.pte_low &= _PAGE_CHG_MASK;
+ pte.pte_low |= pgprot_val(newprot);
+ return pte;
+}
+
+#define page_pte(page) page_pte_prot(page, __pgprot(0))
+
+#define pmd_page(pmd) \
+((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
+
+/* to find an entry in a page-table-directory. */
+#define pgd_index(address) ((address >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
+
+#define __pgd_offset(address) pgd_index(address)
+
+#define pgd_offset(mm, address) ((mm)->pgd+pgd_index(address))
+
+/* to find an entry in a kernel page-table-directory */
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+#define __pmd_offset(address) \
+ (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
+
+/* Find an entry in the third-level page table.. */
+#define __pte_offset(address) \
+ ((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_offset(dir, address) ((pte_t *) pmd_page(*(dir)) + \
+ __pte_offset(address))
+
+/*
+ * The i386 doesn't have any external MMU info: the kernel page
+ * tables contain all the necessary information.
+ */
+#define update_mmu_cache(vma,address,pte) do { } while (0)
+
+/* Encode and de-code a swap entry */
+#define SWP_TYPE(x) (((x).val >> 1) & 0x3f)
+#define SWP_OFFSET(x) ((x).val >> 8)
+#define SWP_ENTRY(type, offset) ((swp_entry_t) { ((type) << 1)
| ((offset) << 8) })
+#define pte_to_swp_entry(pte) ((swp_entry_t) { (pte).pte_low })
+#define swp_entry_to_pte(x) ((pte_t) { (x).val })
+
+struct page;
+int change_page_attr(struct page *, int, pgprot_t prot);
+
+static inline void __make_page_readonly(void *va)
+{
+ pgd_t *pgd = pgd_offset_k((unsigned long)va);
+ pmd_t *pmd = pmd_offset(pgd, (unsigned long)va);
+ pte_t *pte = pte_offset(pmd, (unsigned long)va);
+ set_pte(pte, pte_wrprotect(*pte));
+}
+
+static inline void __make_page_writable(void *va)
+{
+ pgd_t *pgd = pgd_offset_k((unsigned long)va);
+ pmd_t *pmd = pmd_offset(pgd, (unsigned long)va);
+ pte_t *pte = pte_offset(pmd, (unsigned long)va);
+ set_pte(pte, pte_mkwrite(*pte));
+}
+
+static inline void make_page_readonly(void *va)
+{
+ pgd_t *pgd = pgd_offset_k((unsigned long)va);
+ pmd_t *pmd = pmd_offset(pgd, (unsigned long)va);
+ pte_t *pte = pte_offset(pmd, (unsigned long)va);
+ set_pte(pte, pte_wrprotect(*pte));
+ if ( (unsigned long)va >= VMALLOC_START )
+ __make_page_readonly(machine_to_virt(
+ *(unsigned long *)pte&PAGE_MASK));
+}
+
+static inline void make_page_writable(void *va)
+{
+ pgd_t *pgd = pgd_offset_k((unsigned long)va);
+ pmd_t *pmd = pmd_offset(pgd, (unsigned long)va);
+ pte_t *pte = pte_offset(pmd, (unsigned long)va);
+ set_pte(pte, pte_mkwrite(*pte));
+ if ( (unsigned long)va >= VMALLOC_START )
+ __make_page_writable(machine_to_virt(
+ *(unsigned long *)pte&PAGE_MASK));
+}
+
+static inline void make_pages_readonly(void *va, unsigned int nr)
+{
+ while ( nr-- != 0 )
+ {
+ make_page_readonly(va);
+ va = (void *)((unsigned long)va + PAGE_SIZE);
+ }
+}
+
+static inline void make_pages_writable(void *va, unsigned int nr)
+{
+ while ( nr-- != 0 )
+ {
+ make_page_writable(va);
+ va = (void *)((unsigned long)va + PAGE_SIZE);
+ }
+}
+
+static inline unsigned long arbitrary_virt_to_machine(void *va)
+{
+ pgd_t *pgd = pgd_offset_k((unsigned long)va);
+ pmd_t *pmd = pmd_offset(pgd, (unsigned long)va);
+ pte_t *pte = pte_offset(pmd, (unsigned long)va);
+ unsigned long pa = (*(unsigned long *)pte) & PAGE_MASK;
+ return pa | ((unsigned long)va & (PAGE_SIZE-1));
+}
+
+#endif /* !__ASSEMBLY__ */
+
+/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
+#define PageSkip(page) (0)
+#define kern_addr_valid(addr) (1)
+
+#define io_remap_page_range remap_page_range
+
+#endif /* _I386_PGTABLE_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/kernel/gnttab.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/kernel/gnttab.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,390 @@
+/******************************************************************************
+ * gnttab.c
+ *
+ * Two sets of functionality:
+ * 1. Granting foreign access to our memory reservation.
+ * 2. Accessing others' memory reservations via grant references.
+ * (i.e., mechanisms for both sender and recipient of grant references)
+ *
+ * Copyright (c) 2005, Christopher Clark
+ * Copyright (c) 2004, K A Fraser
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <asm/pgtable.h>
+#include <asm/fixmap.h>
+#include <asm/uaccess.h>
+#include <asm-xen/xen_proc.h>
+#include <asm-xen/linux-public/privcmd.h>
+#include <asm-xen/gnttab.h>
+#include <asm-xen/synch_bitops.h>
+
+#if 1
+#define ASSERT(_p) \
+ if ( !(_p) ) { printk(KERN_ALERT"Assertion '%s': line %d, file %s\n", \
+ #_p , __LINE__, __FILE__); *(int*)0=0; }
+#else
+#define ASSERT(_p) ((void)0)
+#endif
+
+#define WPRINTK(fmt, args...) \
+ printk(KERN_WARNING "xen_grant: " fmt, ##args)
+
+
+EXPORT_SYMBOL(gnttab_grant_foreign_access);
+EXPORT_SYMBOL(gnttab_end_foreign_access);
+EXPORT_SYMBOL(gnttab_query_foreign_access);
+EXPORT_SYMBOL(gnttab_grant_foreign_transfer);
+EXPORT_SYMBOL(gnttab_end_foreign_transfer);
+EXPORT_SYMBOL(gnttab_alloc_grant_references);
+EXPORT_SYMBOL(gnttab_free_grant_references);
+EXPORT_SYMBOL(gnttab_claim_grant_reference);
+EXPORT_SYMBOL(gnttab_release_grant_reference);
+EXPORT_SYMBOL(gnttab_grant_foreign_access_ref);
+EXPORT_SYMBOL(gnttab_grant_foreign_transfer_ref);
+
+static grant_ref_t gnttab_free_list[NR_GRANT_ENTRIES];
+static grant_ref_t gnttab_free_head;
+
+static grant_entry_t *shared;
+
+/*
+ * Lock-free grant-entry allocator
+ */
+
+static inline int
+get_free_entry(
+ void)
+{
+ grant_ref_t fh, nfh = gnttab_free_head;
+ do { if ( unlikely((fh = nfh) == NR_GRANT_ENTRIES) ) return -1; }
+ while ( unlikely((nfh = cmpxchg(&gnttab_free_head, fh,
+ gnttab_free_list[fh])) != fh) );
+ return fh;
+}
+
+static inline void
+put_free_entry(
+ grant_ref_t ref)
+{
+ grant_ref_t fh, nfh = gnttab_free_head;
+ do { gnttab_free_list[ref] = fh = nfh; wmb(); }
+ while ( unlikely((nfh = cmpxchg(&gnttab_free_head, fh, ref)) != fh) );
+}
+
+/*
+ * Public grant-issuing interface functions
+ */
+
+int
+gnttab_grant_foreign_access(
+ domid_t domid, unsigned long frame, int readonly)
+{
+ int ref;
+
+ if ( unlikely((ref = get_free_entry()) == -1) )
+ return -ENOSPC;
+
+ shared[ref].frame = frame;
+ shared[ref].domid = domid;
+ wmb();
+ shared[ref].flags = GTF_permit_access | (readonly ? GTF_readonly : 0);
+
+ return ref;
+}
+
+void
+gnttab_grant_foreign_access_ref(
+ grant_ref_t ref, domid_t domid, unsigned long frame, int readonly)
+{
+ shared[ref].frame = frame;
+ shared[ref].domid = domid;
+ wmb();
+ shared[ref].flags = GTF_permit_access | (readonly ? GTF_readonly : 0);
+}
+
+
+int
+gnttab_query_foreign_access( grant_ref_t ref )
+{
+ u16 nflags;
+
+ nflags = shared[ref].flags;
+
+ return ( nflags & (GTF_reading|GTF_writing) );
+}
+
+void
+gnttab_end_foreign_access( grant_ref_t ref, int readonly )
+{
+ u16 flags, nflags;
+
+ nflags = shared[ref].flags;
+ do {
+ if ( (flags = nflags) & (GTF_reading|GTF_writing) )
+ printk(KERN_ALERT "WARNING: g.e. still in use!\n");
+ }
+ while ( (nflags = synch_cmpxchg(&shared[ref].flags, flags, 0)) != flags );
+
+ put_free_entry(ref);
+}
+
+int
+gnttab_grant_foreign_transfer(
+ domid_t domid, unsigned long pfn )
+{
+ int ref;
+
+ if ( unlikely((ref = get_free_entry()) == -1) )
+ return -ENOSPC;
+
+ shared[ref].frame = pfn;
+ shared[ref].domid = domid;
+ wmb();
+ shared[ref].flags = GTF_accept_transfer;
+
+ return ref;
+}
+
+void
+gnttab_grant_foreign_transfer_ref(
+ grant_ref_t ref, domid_t domid, unsigned long pfn )
+{
+ shared[ref].frame = pfn;
+ shared[ref].domid = domid;
+ wmb();
+ shared[ref].flags = GTF_accept_transfer;
+}
+
+unsigned long
+gnttab_end_foreign_transfer(
+ grant_ref_t ref)
+{
+ unsigned long frame = 0;
+ u16 flags;
+
+ flags = shared[ref].flags;
+ ASSERT(flags == (GTF_accept_transfer | GTF_transfer_committed));
+
+ /*
+ * If a transfer is committed then wait for the frame address to appear.
+ * Otherwise invalidate the grant entry against future use.
+ */
+ if ( likely(flags != GTF_accept_transfer) ||
+ (synch_cmpxchg(&shared[ref].flags, flags, 0) != GTF_accept_transfer) )
+ while ( unlikely((frame = shared[ref].frame) == 0) )
+ cpu_relax();
+
+ put_free_entry(ref);
+
+ return frame;
+}
+
+void
+gnttab_free_grant_references( u16 count, grant_ref_t head )
+{
+ /* TODO: O(N)...? */
+ grant_ref_t to_die = 0, next = head;
+ int i;
+
+ for ( i = 0; i < count; i++ )
+ {
+ to_die = next;
+ next = gnttab_free_list[next];
+ put_free_entry( to_die );
+ }
+}
+
+int
+gnttab_alloc_grant_references( u16 count,
+ grant_ref_t *head,
+ grant_ref_t *terminal )
+{
+ int i;
+ grant_ref_t h = gnttab_free_head;
+
+ for ( i = 0; i < count; i++ )
+ if ( unlikely(get_free_entry() == -1) )
+ goto not_enough_refs;
+
+ *head = h;
+ *terminal = gnttab_free_head;
+
+ return 0;
+
+not_enough_refs:
+ gnttab_free_head = h;
+ return -ENOSPC;
+}
+
+int
+gnttab_claim_grant_reference( grant_ref_t *private_head,
+ grant_ref_t terminal )
+{
+ grant_ref_t g;
+ if ( unlikely((g = *private_head) == terminal) )
+ return -ENOSPC;
+ *private_head = gnttab_free_list[g];
+ return g;
+}
+
+void
+gnttab_release_grant_reference( grant_ref_t *private_head,
+ grant_ref_t release )
+{
+ gnttab_free_list[release] = *private_head;
+ *private_head = release;
+}
+
+/*
+ * ProcFS operations
+ */
+
+#ifdef CONFIG_PROC_FS
+
+static struct proc_dir_entry *grant_pde;
+
+static int grant_ioctl(struct inode *inode, struct file *file,
+ unsigned int cmd, unsigned long data)
+{
+ int ret;
+ privcmd_hypercall_t hypercall;
+
+ /* XXX Need safety checks here if using for anything other
+ * than debugging */
+ return -ENOSYS;
+
+ if ( cmd != IOCTL_PRIVCMD_HYPERCALL )
+ return -ENOSYS;
+
+ if ( copy_from_user(&hypercall, (void *)data, sizeof(hypercall)) )
+ return -EFAULT;
+
+ if ( hypercall.op != __HYPERVISOR_grant_table_op )
+ return -ENOSYS;
+
+ /* hypercall-invoking asm taken from privcmd.c */
+ __asm__ __volatile__ (
+ "pushl %%ebx; pushl %%ecx; pushl %%edx; pushl %%esi; pushl %%edi; "
+ "movl 4(%%eax),%%ebx ;"
+ "movl 8(%%eax),%%ecx ;"
+ "movl 12(%%eax),%%edx ;"
+ "movl 16(%%eax),%%esi ;"
+ "movl 20(%%eax),%%edi ;"
+ "movl (%%eax),%%eax ;"
+ TRAP_INSTR "; "
+ "popl %%edi; popl %%esi; popl %%edx; popl %%ecx; popl %%ebx"
+ : "=a" (ret) : "0" (&hypercall) : "memory" );
+
+ return ret;
+}
+
+static struct file_operations grant_file_ops = {
+ ioctl: grant_ioctl,
+};
+
+static int grant_read(char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ int len;
+ unsigned int i;
+ grant_entry_t *gt;
+
+ gt = (grant_entry_t *)shared;
+ len = 0;
+
+ for ( i = 0; i < NR_GRANT_ENTRIES; i++ )
+ /* TODO: safety catch here until this can handle >PAGE_SIZE output */
+ if (len > (PAGE_SIZE - 200))
+ {
+ len += sprintf( page + len, "Truncated.\n");
+ break;
+ }
+
+ if ( gt[i].flags )
+ len += sprintf( page + len,
+ "Grant: ref (0x%x) flags (0x%hx) dom (0x%hx) frame
(0x%x)\n",
+ i,
+ gt[i].flags,
+ gt[i].domid,
+ gt[i].frame );
+
+ *eof = 1;
+ return len;
+}
+
+static int grant_write(struct file *file, const char __user *buffer,
+ unsigned long count, void *data)
+{
+ /* TODO: implement this */
+ return -ENOSYS;
+}
+
+#endif /* CONFIG_PROC_FS */
+
+int gnttab_resume(void)
+{
+ gnttab_setup_table_t setup;
+ unsigned long frames[NR_GRANT_FRAMES];
+ int i;
+
+ setup.dom = DOMID_SELF;
+ setup.nr_frames = NR_GRANT_FRAMES;
+ setup.frame_list = frames;
+
+ BUG_ON(HYPERVISOR_grant_table_op(GNTTABOP_setup_table, &setup, 1) != 0);
+ BUG_ON(setup.status != 0);
+
+ for ( i = 0; i < NR_GRANT_FRAMES; i++ )
+ set_fixmap(FIX_GNTTAB_END - i, frames[i] << PAGE_SHIFT);
+
+ return 0;
+}
+
+int gnttab_suspend(void)
+{
+ int i;
+
+ for ( i = 0; i < NR_GRANT_FRAMES; i++ )
+ clear_fixmap(FIX_GNTTAB_END - i);
+
+ return 0;
+}
+
+static int __init gnttab_init(void)
+{
+ int i;
+
+ BUG_ON(gnttab_resume());
+
+ shared = (grant_entry_t *)fix_to_virt(FIX_GNTTAB_END);
+
+ for ( i = 0; i < NR_GRANT_ENTRIES; i++ )
+ gnttab_free_list[i] = i + 1;
+
+#ifdef CONFIG_PROC_FS
+ /*
+ * /proc/xen/grant : used by libxc to access grant tables
+ */
+ if ( (grant_pde = create_xen_proc_entry("grant", 0600)) == NULL )
+ {
+ WPRINTK("Unable to create grant xen proc entry\n");
+ return -1;
+ }
+
+ grant_file_ops.read = grant_pde->proc_fops->read;
+ grant_file_ops.write = grant_pde->proc_fops->write;
+
+ grant_pde->proc_fops = &grant_file_ops;
+
+ grant_pde->read_proc = &grant_read;
+ grant_pde->write_proc = &grant_write;
+#endif
+
+ printk("Grant table initialized\n");
+ return 0;
+}
+
+__initcall(gnttab_init);
diff -r 35b74976f598 -r a83ac0806d6b linux-2.6.11-xen-sparse/net/core/skbuff.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/net/core/skbuff.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,1523 @@
+/*
+ * Routines having to do with the 'struct sk_buff' memory handlers.
+ *
+ * Authors: Alan Cox <iiitac@xxxxxxxxxxxxxx>
+ * Florian La Roche <rzsfl@xxxxxxxxxxxx>
+ *
+ * Version: $Id: skbuff.c,v 1.90 2001/11/07 05:56:19 davem Exp $
+ *
+ * Fixes:
+ * Alan Cox : Fixed the worst of the load
+ * balancer bugs.
+ * Dave Platt : Interrupt stacking fix.
+ * Richard Kooijman : Timestamp fixes.
+ * Alan Cox : Changed buffer format.
+ * Alan Cox : destructor hook for AF_UNIX etc.
+ * Linus Torvalds : Better skb_clone.
+ * Alan Cox : Added skb_copy.
+ * Alan Cox : Added all the changed routines Linus
+ * only put in the headers
+ * Ray VanTassle : Fixed --skb->lock in free
+ * Alan Cox : skb_copy copy arp field
+ * Andi Kleen : slabified it.
+ * Robert Olsson : Removed skb_head_pool
+ *
+ * NOTE:
+ * The __skb_ routines should be called with interrupts
+ * disabled, or you better be *real* sure that the operation is atomic
+ * with respect to whatever list is being frobbed (e.g. via lock_sock()
+ * or via disabling bottom half handlers, etc).
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+/*
+ * The functions in this file will not compile correctly with gcc 2.4.x
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/in.h>
+#include <linux/inet.h>
+#include <linux/slab.h>
+#include <linux/netdevice.h>
+#ifdef CONFIG_NET_CLS_ACT
+#include <net/pkt_sched.h>
+#endif
+#include <linux/string.h>
+#include <linux/skbuff.h>
+#include <linux/cache.h>
+#include <linux/rtnetlink.h>
+#include <linux/init.h>
+#include <linux/highmem.h>
+
+#include <net/protocol.h>
+#include <net/dst.h>
+#include <net/sock.h>
+#include <net/checksum.h>
+#include <net/xfrm.h>
+
+#include <asm/uaccess.h>
+#include <asm/system.h>
+
+static kmem_cache_t *skbuff_head_cache;
+
+/*
+ * Keep out-of-line to prevent kernel bloat.
+ * __builtin_return_address is not used because it is not always
+ * reliable.
+ */
+
+/**
+ * skb_over_panic - private function
+ * @skb: buffer
+ * @sz: size
+ * @here: address
+ *
+ * Out of line support code for skb_put(). Not user callable.
+ */
+void skb_over_panic(struct sk_buff *skb, int sz, void *here)
+{
+ printk(KERN_INFO "skput:over: %p:%d put:%d dev:%s",
+ here, skb->len, sz, skb->dev ? skb->dev->name : "<NULL>");
+ BUG();
+}
+
+/**
+ * skb_under_panic - private function
+ * @skb: buffer
+ * @sz: size
+ * @here: address
+ *
+ * Out of line support code for skb_push(). Not user callable.
+ */
+
+void skb_under_panic(struct sk_buff *skb, int sz, void *here)
+{
+ printk(KERN_INFO "skput:under: %p:%d put:%d dev:%s",
+ here, skb->len, sz, skb->dev ? skb->dev->name : "<NULL>");
+ BUG();
+}
+
+/* Allocate a new skbuff. We do this ourselves so we can fill in a few
+ * 'private' fields and also do memory statistics to find all the
+ * [BEEP] leaks.
+ *
+ */
+
+/**
+ * alloc_skb - allocate a network buffer
+ * @size: size to allocate
+ * @gfp_mask: allocation mask
+ *
+ * Allocate a new &sk_buff. The returned buffer has no headroom and a
+ * tail room of size bytes. The object has a reference count of one.
+ * The return is the buffer. On a failure the return is %NULL.
+ *
+ * Buffers may only be allocated from interrupts using a @gfp_mask of
+ * %GFP_ATOMIC.
+ */
+struct sk_buff *alloc_skb(unsigned int size, int gfp_mask)
+{
+ struct sk_buff *skb;
+ u8 *data;
+
+ /* Get the HEAD */
+ skb = kmem_cache_alloc(skbuff_head_cache,
+ gfp_mask & ~__GFP_DMA);
+ if (!skb)
+ goto out;
+
+ /* Get the DATA. Size must match skb_add_mtu(). */
+ size = SKB_DATA_ALIGN(size);
+ data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
+ if (!data)
+ goto nodata;
+
+ memset(skb, 0, offsetof(struct sk_buff, truesize));
+ skb->truesize = size + sizeof(struct sk_buff);
+ atomic_set(&skb->users, 1);
+ skb->head = data;
+ skb->data = data;
+ skb->tail = data;
+ skb->end = data + size;
+
+ atomic_set(&(skb_shinfo(skb)->dataref), 1);
+ skb_shinfo(skb)->nr_frags = 0;
+ skb_shinfo(skb)->tso_size = 0;
+ skb_shinfo(skb)->tso_segs = 0;
+ skb_shinfo(skb)->frag_list = NULL;
+out:
+ return skb;
+nodata:
+ kmem_cache_free(skbuff_head_cache, skb);
+ skb = NULL;
+ goto out;
+}
+
+/**
+ * alloc_skb_from_cache - allocate a network buffer
+ * @cp: kmem_cache from which to allocate the data area
+ * (object size must be big enough for @size bytes + skb overheads)
+ * @size: size to allocate
+ * @gfp_mask: allocation mask
+ *
+ * Allocate a new &sk_buff. The returned buffer has no headroom and
+ * tail room of size bytes. The object has a reference count of one.
+ * The return is the buffer. On a failure the return is %NULL.
+ *
+ * Buffers may only be allocated from interrupts using a @gfp_mask of
+ * %GFP_ATOMIC.
+ */
+struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp,
+ unsigned int size, int gfp_mask)
+{
+ struct sk_buff *skb;
+ u8 *data;
+
+ /* Get the HEAD */
+ skb = kmem_cache_alloc(skbuff_head_cache,
+ gfp_mask & ~__GFP_DMA);
+ if (!skb)
+ goto out;
+
+ /* Get the DATA. */
+ size = SKB_DATA_ALIGN(size);
+ data = kmem_cache_alloc(cp, gfp_mask);
+ if (!data)
+ goto nodata;
+
+ memset(skb, 0, offsetof(struct sk_buff, truesize));
+ skb->truesize = size + sizeof(struct sk_buff);
+ atomic_set(&skb->users, 1);
+ skb->head = data;
+ skb->data = data;
+ skb->tail = data;
+ skb->end = data + size;
+
+ atomic_set(&(skb_shinfo(skb)->dataref), 1);
+ skb_shinfo(skb)->nr_frags = 0;
+ skb_shinfo(skb)->tso_size = 0;
+ skb_shinfo(skb)->tso_segs = 0;
+ skb_shinfo(skb)->frag_list = NULL;
+out:
+ return skb;
+nodata:
+ kmem_cache_free(skbuff_head_cache, skb);
+ skb = NULL;
+ goto out;
+}
+
+
+static void skb_drop_fraglist(struct sk_buff *skb)
+{
+ struct sk_buff *list = skb_shinfo(skb)->frag_list;
+
+ skb_shinfo(skb)->frag_list = NULL;
+
+ do {
+ struct sk_buff *this = list;
+ list = list->next;
+ kfree_skb(this);
+ } while (list);
+}
+
+static void skb_clone_fraglist(struct sk_buff *skb)
+{
+ struct sk_buff *list;
+
+ for (list = skb_shinfo(skb)->frag_list; list; list = list->next)
+ skb_get(list);
+}
+
+void skb_release_data(struct sk_buff *skb)
+{
+ if (!skb->cloned ||
+ atomic_dec_and_test(&(skb_shinfo(skb)->dataref))) {
+ if (skb_shinfo(skb)->nr_frags) {
+ int i;
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
+ put_page(skb_shinfo(skb)->frags[i].page);
+ }
+
+ if (skb_shinfo(skb)->frag_list)
+ skb_drop_fraglist(skb);
+
+ kfree(skb->head);
+ }
+}
+
+/*
+ * Free an skbuff by memory without cleaning the state.
+ */
+void kfree_skbmem(struct sk_buff *skb)
+{
+ skb_release_data(skb);
+ kmem_cache_free(skbuff_head_cache, skb);
+}
+
+/**
+ * __kfree_skb - private function
+ * @skb: buffer
+ *
+ * Free an sk_buff. Release anything attached to the buffer.
+ * Clean the state. This is an internal helper function. Users should
+ * always call kfree_skb
+ */
+
+void __kfree_skb(struct sk_buff *skb)
+{
+ if (skb->list) {
+ printk(KERN_WARNING "Warning: kfree_skb passed an skb still "
+ "on a list (from %p).\n", NET_CALLER(skb));
+ BUG();
+ }
+
+ dst_release(skb->dst);
+#ifdef CONFIG_XFRM
+ secpath_put(skb->sp);
+#endif
+ if(skb->destructor) {
+ if (in_irq())
+ printk(KERN_WARNING "Warning: kfree_skb on "
+ "hard IRQ %p\n", NET_CALLER(skb));
+ skb->destructor(skb);
+ }
+#ifdef CONFIG_NETFILTER
+ nf_conntrack_put(skb->nfct);
+#ifdef CONFIG_BRIDGE_NETFILTER
+ nf_bridge_put(skb->nf_bridge);
+#endif
+#endif
+/* XXX: IS this still necessary? - JHS */
+#ifdef CONFIG_NET_SCHED
+ skb->tc_index = 0;
+#ifdef CONFIG_NET_CLS_ACT
+ skb->tc_verd = 0;
+ skb->tc_classid = 0;
+#endif
+#endif
+
+ kfree_skbmem(skb);
+}
+
+/**
+ * skb_clone - duplicate an sk_buff
+ * @skb: buffer to clone
+ * @gfp_mask: allocation priority
+ *
+ * Duplicate an &sk_buff. The new one is not owned by a socket. Both
+ * copies share the same packet data but not structure. The new
+ * buffer has a reference count of 1. If the allocation fails the
+ * function returns %NULL otherwise the new buffer is returned.
+ *
+ * If this function is called from an interrupt gfp_mask() must be
+ * %GFP_ATOMIC.
+ */
+
+struct sk_buff *skb_clone(struct sk_buff *skb, int gfp_mask)
+{
+ struct sk_buff *n = kmem_cache_alloc(skbuff_head_cache, gfp_mask);
+
+ if (!n)
+ return NULL;
+
+#define C(x) n->x = skb->x
+
+ n->next = n->prev = NULL;
+ n->list = NULL;
+ n->sk = NULL;
+ C(stamp);
+ C(dev);
+ C(real_dev);
+ C(h);
+ C(nh);
+ C(mac);
+ C(dst);
+ dst_clone(skb->dst);
+ C(sp);
+#ifdef CONFIG_INET
+ secpath_get(skb->sp);
+#endif
+ memcpy(n->cb, skb->cb, sizeof(skb->cb));
+ C(len);
+ C(data_len);
+ C(csum);
+ C(local_df);
+ n->cloned = 1;
+ C(proto_csum_valid);
+ C(proto_csum_blank);
+ C(pkt_type);
+ C(ip_summed);
+ C(priority);
+ C(protocol);
+ C(security);
+ n->destructor = NULL;
+#ifdef CONFIG_NETFILTER
+ C(nfmark);
+ C(nfcache);
+ C(nfct);
+ nf_conntrack_get(skb->nfct);
+ C(nfctinfo);
+#ifdef CONFIG_NETFILTER_DEBUG
+ C(nf_debug);
+#endif
+#ifdef CONFIG_BRIDGE_NETFILTER
+ C(nf_bridge);
+ nf_bridge_get(skb->nf_bridge);
+#endif
+#endif /*CONFIG_NETFILTER*/
+#if defined(CONFIG_HIPPI)
+ C(private);
+#endif
+#ifdef CONFIG_NET_SCHED
+ C(tc_index);
+#ifdef CONFIG_NET_CLS_ACT
+ n->tc_verd = SET_TC_VERD(skb->tc_verd,0);
+ n->tc_verd = CLR_TC_OK2MUNGE(skb->tc_verd);
+ n->tc_verd = CLR_TC_MUNGED(skb->tc_verd);
+ C(input_dev);
+ C(tc_classid);
+#endif
+
+#endif
+ C(truesize);
+ atomic_set(&n->users, 1);
+ C(head);
+ C(data);
+ C(tail);
+ C(end);
+
+ atomic_inc(&(skb_shinfo(skb)->dataref));
+ skb->cloned = 1;
+
+ return n;
+}
+
+static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
+{
+ /*
+ * Shift between the two data areas in bytes
+ */
+ unsigned long offset = new->data - old->data;
+
+ new->list = NULL;
+ new->sk = NULL;
+ new->dev = old->dev;
+ new->real_dev = old->real_dev;
+ new->priority = old->priority;
+ new->protocol = old->protocol;
+ new->dst = dst_clone(old->dst);
+#ifdef CONFIG_INET
+ new->sp = secpath_get(old->sp);
+#endif
+ new->h.raw = old->h.raw + offset;
+ new->nh.raw = old->nh.raw + offset;
+ new->mac.raw = old->mac.raw + offset;
+ memcpy(new->cb, old->cb, sizeof(old->cb));
+ new->local_df = old->local_df;
+ new->pkt_type = old->pkt_type;
+ new->stamp = old->stamp;
+ new->destructor = NULL;
+ new->security = old->security;
+#ifdef CONFIG_NETFILTER
+ new->nfmark = old->nfmark;
+ new->nfcache = old->nfcache;
+ new->nfct = old->nfct;
+ nf_conntrack_get(old->nfct);
+ new->nfctinfo = old->nfctinfo;
+#ifdef CONFIG_NETFILTER_DEBUG
+ new->nf_debug = old->nf_debug;
+#endif
+#ifdef CONFIG_BRIDGE_NETFILTER
+ new->nf_bridge = old->nf_bridge;
+ nf_bridge_get(old->nf_bridge);
+#endif
+#endif
+#ifdef CONFIG_NET_SCHED
+#ifdef CONFIG_NET_CLS_ACT
+ new->tc_verd = old->tc_verd;
+#endif
+ new->tc_index = old->tc_index;
+#endif
+ atomic_set(&new->users, 1);
+ skb_shinfo(new)->tso_size = skb_shinfo(old)->tso_size;
+ skb_shinfo(new)->tso_segs = skb_shinfo(old)->tso_segs;
+}
+
+/**
+ * skb_copy - create private copy of an sk_buff
+ * @skb: buffer to copy
+ * @gfp_mask: allocation priority
+ *
+ * Make a copy of both an &sk_buff and its data. This is used when the
+ * caller wishes to modify the data and needs a private copy of the
+ * data to alter. Returns %NULL on failure or the pointer to the buffer
+ * on success. The returned buffer has a reference count of 1.
+ *
+ * As by-product this function converts non-linear &sk_buff to linear
+ * one, so that &sk_buff becomes completely private and caller is allowed
+ * to modify all the data of returned buffer. This means that this
+ * function is not recommended for use in circumstances when only
+ * header is going to be modified. Use pskb_copy() instead.
+ */
+
+struct sk_buff *skb_copy(const struct sk_buff *skb, int gfp_mask)
+{
+ int headerlen = skb->data - skb->head;
+ /*
+ * Allocate the copy buffer
+ */
+ struct sk_buff *n = alloc_skb(skb->end - skb->head + skb->data_len,
+ gfp_mask);
+ if (!n)
+ return NULL;
+
+ /* Set the data pointer */
+ skb_reserve(n, headerlen);
+ /* Set the tail pointer and length */
+ skb_put(n, skb->len);
+ n->csum = skb->csum;
+ n->ip_summed = skb->ip_summed;
+
+ if (skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len))
+ BUG();
+
+ copy_skb_header(n, skb);
+ return n;
+}
+
+
+/**
+ * pskb_copy - create copy of an sk_buff with private head.
+ * @skb: buffer to copy
+ * @gfp_mask: allocation priority
+ *
+ * Make a copy of both an &sk_buff and part of its data, located
+ * in header. Fragmented data remain shared. This is used when
+ * the caller wishes to modify only header of &sk_buff and needs
+ * private copy of the header to alter. Returns %NULL on failure
+ * or the pointer to the buffer on success.
+ * The returned buffer has a reference count of 1.
+ */
+
+struct sk_buff *pskb_copy(struct sk_buff *skb, int gfp_mask)
+{
+ /*
+ * Allocate the copy buffer
+ */
+ struct sk_buff *n = alloc_skb(skb->end - skb->head, gfp_mask);
+
+ if (!n)
+ goto out;
+
+ /* Set the data pointer */
+ skb_reserve(n, skb->data - skb->head);
+ /* Set the tail pointer and length */
+ skb_put(n, skb_headlen(skb));
+ /* Copy the bytes */
+ memcpy(n->data, skb->data, n->len);
+ n->csum = skb->csum;
+ n->ip_summed = skb->ip_summed;
+
+ n->data_len = skb->data_len;
+ n->len = skb->len;
+
+ if (skb_shinfo(skb)->nr_frags) {
+ int i;
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i];
+ get_page(skb_shinfo(n)->frags[i].page);
+ }
+ skb_shinfo(n)->nr_frags = i;
+ }
+
+ if (skb_shinfo(skb)->frag_list) {
+ skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list;
+ skb_clone_fraglist(n);
+ }
+
+ copy_skb_header(n, skb);
+out:
+ return n;
+}
+
+/**
+ * pskb_expand_head - reallocate header of &sk_buff
+ * @skb: buffer to reallocate
+ * @nhead: room to add at head
+ * @ntail: room to add at tail
+ * @gfp_mask: allocation priority
+ *
+ * Expands (or creates identical copy, if &nhead and &ntail are zero)
+ * header of skb. &sk_buff itself is not changed. &sk_buff MUST have
+ * reference count of 1. Returns zero in the case of success or error,
+ * if expansion failed. In the last case, &sk_buff is not changed.
+ *
+ * All the pointers pointing into skb header may change and must be
+ * reloaded after call to this function.
+ */
+
+int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, int gfp_mask)
+{
+ int i;
+ u8 *data;
+ int size = nhead + (skb->end - skb->head) + ntail;
+ long off;
+
+ if (skb_shared(skb))
+ BUG();
+
+ size = SKB_DATA_ALIGN(size);
+
+ data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
+ if (!data)
+ goto nodata;
+
+ /* Copy only real data... and, alas, header. This should be
+ * optimized for the cases when header is void. */
+ memcpy(data + nhead, skb->head, skb->tail - skb->head);
+ memcpy(data + size, skb->end, sizeof(struct skb_shared_info));
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
+ get_page(skb_shinfo(skb)->frags[i].page);
+
+ if (skb_shinfo(skb)->frag_list)
+ skb_clone_fraglist(skb);
+
+ skb_release_data(skb);
+
+ off = (data + nhead) - skb->head;
+
+ skb->head = data;
+ skb->end = data + size;
+ skb->data += off;
+ skb->tail += off;
+ skb->mac.raw += off;
+ skb->h.raw += off;
+ skb->nh.raw += off;
+ skb->cloned = 0;
+ atomic_set(&skb_shinfo(skb)->dataref, 1);
+ return 0;
+
+nodata:
+ return -ENOMEM;
+}
+
+/* Make private copy of skb with writable head and some headroom */
+
+struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int
headroom)
+{
+ struct sk_buff *skb2;
+ int delta = headroom - skb_headroom(skb);
+
+ if (delta <= 0)
+ skb2 = pskb_copy(skb, GFP_ATOMIC);
+ else {
+ skb2 = skb_clone(skb, GFP_ATOMIC);
+ if (skb2 && pskb_expand_head(skb2, SKB_DATA_ALIGN(delta), 0,
+ GFP_ATOMIC)) {
+ kfree_skb(skb2);
+ skb2 = NULL;
+ }
+ }
+ return skb2;
+}
+
+
+/**
+ * skb_copy_expand - copy and expand sk_buff
+ * @skb: buffer to copy
+ * @newheadroom: new free bytes at head
+ * @newtailroom: new free bytes at tail
+ * @gfp_mask: allocation priority
+ *
+ * Make a copy of both an &sk_buff and its data and while doing so
+ * allocate additional space.
+ *
+ * This is used when the caller wishes to modify the data and needs a
+ * private copy of the data to alter as well as more space for new fields.
+ * Returns %NULL on failure or the pointer to the buffer
+ * on success. The returned buffer has a reference count of 1.
+ *
+ * You must pass %GFP_ATOMIC as the allocation priority if this function
+ * is called from an interrupt.
+ *
+ * BUG ALERT: ip_summed is not copied. Why does this work? Is it used
+ * only by netfilter in the cases when checksum is recalculated? --ANK
+ */
+struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
+ int newheadroom, int newtailroom, int gfp_mask)
+{
+ /*
+ * Allocate the copy buffer
+ */
+ struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom,
+ gfp_mask);
+ int head_copy_len, head_copy_off;
+
+ if (!n)
+ return NULL;
+
+ skb_reserve(n, newheadroom);
+
+ /* Set the tail pointer and length */
+ skb_put(n, skb->len);
+
+ head_copy_len = skb_headroom(skb);
+ head_copy_off = 0;
+ if (newheadroom <= head_copy_len)
+ head_copy_len = newheadroom;
+ else
+ head_copy_off = newheadroom - head_copy_len;
+
+ /* Copy the linear header and data. */
+ if (skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
+ skb->len + head_copy_len))
+ BUG();
+
+ copy_skb_header(n, skb);
+
+ return n;
+}
+
+/**
+ * skb_pad - zero pad the tail of an skb
+ * @skb: buffer to pad
+ * @pad: space to pad
+ *
+ * Ensure that a buffer is followed by a padding area that is zero
+ * filled. Used by network drivers which may DMA or transfer data
+ * beyond the buffer end onto the wire.
+ *
+ * May return NULL in out of memory cases.
+ */
+
+struct sk_buff *skb_pad(struct sk_buff *skb, int pad)
+{
+ struct sk_buff *nskb;
+
+ /* If the skbuff is non linear tailroom is always zero.. */
+ if (skb_tailroom(skb) >= pad) {
+ memset(skb->data+skb->len, 0, pad);
+ return skb;
+ }
+
+ nskb = skb_copy_expand(skb, skb_headroom(skb), skb_tailroom(skb) + pad,
GFP_ATOMIC);
+ kfree_skb(skb);
+ if (nskb)
+ memset(nskb->data+nskb->len, 0, pad);
+ return nskb;
+}
+
+/* Trims skb to length len. It can change skb pointers, if "realloc" is 1.
+ * If realloc==0 and trimming is impossible without change of data,
+ * it is BUG().
+ */
+
+int ___pskb_trim(struct sk_buff *skb, unsigned int len, int realloc)
+{
+ int offset = skb_headlen(skb);
+ int nfrags = skb_shinfo(skb)->nr_frags;
+ int i;
+
+ for (i = 0; i < nfrags; i++) {
+ int end = offset + skb_shinfo(skb)->frags[i].size;
+ if (end > len) {
+ if (skb_cloned(skb)) {
+ if (!realloc)
+ BUG();
+ if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ return -ENOMEM;
+ }
+ if (len <= offset) {
+ put_page(skb_shinfo(skb)->frags[i].page);
+ skb_shinfo(skb)->nr_frags--;
+ } else {
+ skb_shinfo(skb)->frags[i].size = len - offset;
+ }
+ }
+ offset = end;
+ }
+
+ if (offset < len) {
+ skb->data_len -= skb->len - len;
+ skb->len = len;
+ } else {
+ if (len <= skb_headlen(skb)) {
+ skb->len = len;
+ skb->data_len = 0;
+ skb->tail = skb->data + len;
+ if (skb_shinfo(skb)->frag_list && !skb_cloned(skb))
+ skb_drop_fraglist(skb);
+ } else {
+ skb->data_len -= skb->len - len;
+ skb->len = len;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * __pskb_pull_tail - advance tail of skb header
+ * @skb: buffer to reallocate
+ * @delta: number of bytes to advance tail
+ *
+ * The function makes a sense only on a fragmented &sk_buff,
+ * it expands header moving its tail forward and copying necessary
+ * data from fragmented part.
+ *
+ * &sk_buff MUST have reference count of 1.
+ *
+ * Returns %NULL (and &sk_buff does not change) if pull failed
+ * or value of new tail of skb in the case of success.
+ *
+ * All the pointers pointing into skb header may change and must be
+ * reloaded after call to this function.
+ */
+
+/* Moves tail of skb head forward, copying data from fragmented part,
+ * when it is necessary.
+ * 1. It may fail due to malloc failure.
+ * 2. It may change skb pointers.
+ *
+ * It is pretty complicated. Luckily, it is called only in exceptional cases.
+ */
+unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta)
+{
+ /* If skb has not enough free space at tail, get new one
+ * plus 128 bytes for future expansions. If we have enough
+ * room at tail, reallocate without expansion only if skb is cloned.
+ */
+ int i, k, eat = (skb->tail + delta) - skb->end;
+
+ if (eat > 0 || skb_cloned(skb)) {
+ if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0,
+ GFP_ATOMIC))
+ return NULL;
+ }
+
+ if (skb_copy_bits(skb, skb_headlen(skb), skb->tail, delta))
+ BUG();
+
+ /* Optimization: no fragments, no reasons to preestimate
+ * size of pulled pages. Superb.
+ */
+ if (!skb_shinfo(skb)->frag_list)
+ goto pull_pages;
+
+ /* Estimate size of pulled pages. */
+ eat = delta;
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ if (skb_shinfo(skb)->frags[i].size >= eat)
+ goto pull_pages;
+ eat -= skb_shinfo(skb)->frags[i].size;
+ }
+
+ /* If we need update frag list, we are in troubles.
+ * Certainly, it possible to add an offset to skb data,
+ * but taking into account that pulling is expected to
+ * be very rare operation, it is worth to fight against
+ * further bloating skb head and crucify ourselves here instead.
+ * Pure masohism, indeed. 8)8)
+ */
+ if (eat) {
+ struct sk_buff *list = skb_shinfo(skb)->frag_list;
+ struct sk_buff *clone = NULL;
+ struct sk_buff *insp = NULL;
+
+ do {
+ if (!list)
+ BUG();
+
+ if (list->len <= eat) {
+ /* Eaten as whole. */
+ eat -= list->len;
+ list = list->next;
+ insp = list;
+ } else {
+ /* Eaten partially. */
+
+ if (skb_shared(list)) {
+ /* Sucks! We need to fork list. :-( */
+ clone = skb_clone(list, GFP_ATOMIC);
+ if (!clone)
+ return NULL;
+ insp = list->next;
+ list = clone;
+ } else {
+ /* This may be pulled without
+ * problems. */
+ insp = list;
+ }
+ if (!pskb_pull(list, eat)) {
+ if (clone)
+ kfree_skb(clone);
+ return NULL;
+ }
+ break;
+ }
+ } while (eat);
+
+ /* Free pulled out fragments. */
+ while ((list = skb_shinfo(skb)->frag_list) != insp) {
+ skb_shinfo(skb)->frag_list = list->next;
+ kfree_skb(list);
+ }
+ /* And insert new clone at head. */
+ if (clone) {
+ clone->next = list;
+ skb_shinfo(skb)->frag_list = clone;
+ }
+ }
+ /* Success! Now we may commit changes to skb data. */
+
+pull_pages:
+ eat = delta;
+ k = 0;
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ if (skb_shinfo(skb)->frags[i].size <= eat) {
+ put_page(skb_shinfo(skb)->frags[i].page);
+ eat -= skb_shinfo(skb)->frags[i].size;
+ } else {
+ skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i];
+ if (eat) {
+ skb_shinfo(skb)->frags[k].page_offset += eat;
+ skb_shinfo(skb)->frags[k].size -= eat;
+ eat = 0;
+ }
+ k++;
+ }
+ }
+ skb_shinfo(skb)->nr_frags = k;
+
+ skb->tail += delta;
+ skb->data_len -= delta;
+
+ return skb->tail;
+}
+
+/* Copy some data bits from skb to kernel buffer. */
+
+int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len)
+{
+ int i, copy;
+ int start = skb_headlen(skb);
+
+ if (offset > (int)skb->len - len)
+ goto fault;
+
+ /* Copy header. */
+ if ((copy = start - offset) > 0) {
+ if (copy > len)
+ copy = len;
+ memcpy(to, skb->data + offset, copy);
+ if ((len -= copy) == 0)
+ return 0;
+ offset += copy;
+ to += copy;
+ }
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ int end;
+
+ BUG_TRAP(start <= offset + len);
+
+ end = start + skb_shinfo(skb)->frags[i].size;
+ if ((copy = end - offset) > 0) {
+ u8 *vaddr;
+
+ if (copy > len)
+ copy = len;
+
+ vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]);
+ memcpy(to,
+ vaddr + skb_shinfo(skb)->frags[i].page_offset+
+ offset - start, copy);
+ kunmap_skb_frag(vaddr);
+
+ if ((len -= copy) == 0)
+ return 0;
+ offset += copy;
+ to += copy;
+ }
+ start = end;
+ }
+
+ if (skb_shinfo(skb)->frag_list) {
+ struct sk_buff *list = skb_shinfo(skb)->frag_list;
+
+ for (; list; list = list->next) {
+ int end;
+
+ BUG_TRAP(start <= offset + len);
+
+ end = start + list->len;
+ if ((copy = end - offset) > 0) {
+ if (copy > len)
+ copy = len;
+ if (skb_copy_bits(list, offset - start,
+ to, copy))
+ goto fault;
+ if ((len -= copy) == 0)
+ return 0;
+ offset += copy;
+ to += copy;
+ }
+ start = end;
+ }
+ }
+ if (!len)
+ return 0;
+
+fault:
+ return -EFAULT;
+}
+
+/* Keep iterating until skb_iter_next returns false. */
+void skb_iter_first(const struct sk_buff *skb, struct skb_iter *i)
+{
+ i->len = skb_headlen(skb);
+ i->data = (unsigned char *)skb->data;
+ i->nextfrag = 0;
+ i->fraglist = NULL;
+}
+
+int skb_iter_next(const struct sk_buff *skb, struct skb_iter *i)
+{
+ /* Unmap previous, if not head fragment. */
+ if (i->nextfrag)
+ kunmap_skb_frag(i->data);
+
+ if (i->fraglist) {
+ fraglist:
+ /* We're iterating through fraglist. */
+ if (i->nextfrag < skb_shinfo(i->fraglist)->nr_frags) {
+ i->data = kmap_skb_frag(&skb_shinfo(i->fraglist)
+ ->frags[i->nextfrag]);
+ i->len = skb_shinfo(i->fraglist)->frags[i->nextfrag]
+ .size;
+ i->nextfrag++;
+ return 1;
+ }
+ /* Fragments with fragments? Too hard! */
+ BUG_ON(skb_shinfo(i->fraglist)->frag_list);
+ i->fraglist = i->fraglist->next;
+ if (!i->fraglist)
+ goto end;
+
+ i->len = skb_headlen(i->fraglist);
+ i->data = i->fraglist->data;
+ i->nextfrag = 0;
+ return 1;
+ }
+
+ if (i->nextfrag < skb_shinfo(skb)->nr_frags) {
+ i->data = kmap_skb_frag(&skb_shinfo(skb)->frags[i->nextfrag]);
+ i->len = skb_shinfo(skb)->frags[i->nextfrag].size;
+ i->nextfrag++;
+ return 1;
+ }
+
+ i->fraglist = skb_shinfo(skb)->frag_list;
+ if (i->fraglist)
+ goto fraglist;
+
+end:
+ /* Bug trap for callers */
+ i->data = NULL;
+ return 0;
+}
+
+void skb_iter_abort(const struct sk_buff *skb, struct skb_iter *i)
+{
+ /* Unmap previous, if not head fragment. */
+ if (i->data && i->nextfrag)
+ kunmap_skb_frag(i->data);
+ /* Bug trap for callers */
+ i->data = NULL;
+}
+
+/* Checksum skb data. */
+
+unsigned int skb_checksum(const struct sk_buff *skb, int offset,
+ int len, unsigned int csum)
+{
+ int start = skb_headlen(skb);
+ int i, copy = start - offset;
+ int pos = 0;
+
+ /* Checksum header. */
+ if (copy > 0) {
+ if (copy > len)
+ copy = len;
+ csum = csum_partial(skb->data + offset, copy, csum);
+ if ((len -= copy) == 0)
+ return csum;
+ offset += copy;
+ pos = copy;
+ }
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ int end;
+
+ BUG_TRAP(start <= offset + len);
+
+ end = start + skb_shinfo(skb)->frags[i].size;
+ if ((copy = end - offset) > 0) {
+ unsigned int csum2;
+ u8 *vaddr;
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+ if (copy > len)
+ copy = len;
+ vaddr = kmap_skb_frag(frag);
+ csum2 = csum_partial(vaddr + frag->page_offset +
+ offset - start, copy, 0);
+ kunmap_skb_frag(vaddr);
+ csum = csum_block_add(csum, csum2, pos);
+ if (!(len -= copy))
+ return csum;
+ offset += copy;
+ pos += copy;
+ }
+ start = end;
+ }
+
+ if (skb_shinfo(skb)->frag_list) {
+ struct sk_buff *list = skb_shinfo(skb)->frag_list;
+
+ for (; list; list = list->next) {
+ int end;
+
+ BUG_TRAP(start <= offset + len);
+
+ end = start + list->len;
+ if ((copy = end - offset) > 0) {
+ unsigned int csum2;
+ if (copy > len)
+ copy = len;
+ csum2 = skb_checksum(list, offset - start,
+ copy, 0);
+ csum = csum_block_add(csum, csum2, pos);
+ if ((len -= copy) == 0)
+ return csum;
+ offset += copy;
+ pos += copy;
+ }
+ start = end;
+ }
+ }
+ if (len)
+ BUG();
+
+ return csum;
+}
+
+/* Both of above in one bottle. */
+
+unsigned int skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
+ u8 *to, int len, unsigned int csum)
+{
+ int start = skb_headlen(skb);
+ int i, copy = start - offset;
+ int pos = 0;
+
+ /* Copy header. */
+ if (copy > 0) {
+ if (copy > len)
+ copy = len;
+ csum = csum_partial_copy_nocheck(skb->data + offset, to,
+ copy, csum);
+ if ((len -= copy) == 0)
+ return csum;
+ offset += copy;
+ to += copy;
+ pos = copy;
+ }
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ int end;
+
+ BUG_TRAP(start <= offset + len);
+
+ end = start + skb_shinfo(skb)->frags[i].size;
+ if ((copy = end - offset) > 0) {
+ unsigned int csum2;
+ u8 *vaddr;
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+ if (copy > len)
+ copy = len;
+ vaddr = kmap_skb_frag(frag);
+ csum2 = csum_partial_copy_nocheck(vaddr +
+ frag->page_offset +
+ offset - start, to,
+ copy, 0);
+ kunmap_skb_frag(vaddr);
+ csum = csum_block_add(csum, csum2, pos);
+ if (!(len -= copy))
+ return csum;
+ offset += copy;
+ to += copy;
+ pos += copy;
+ }
+ start = end;
+ }
+
+ if (skb_shinfo(skb)->frag_list) {
+ struct sk_buff *list = skb_shinfo(skb)->frag_list;
+
+ for (; list; list = list->next) {
+ unsigned int csum2;
+ int end;
+
+ BUG_TRAP(start <= offset + len);
+
+ end = start + list->len;
+ if ((copy = end - offset) > 0) {
+ if (copy > len)
+ copy = len;
+ csum2 = skb_copy_and_csum_bits(list,
+ offset - start,
+ to, copy, 0);
+ csum = csum_block_add(csum, csum2, pos);
+ if ((len -= copy) == 0)
+ return csum;
+ offset += copy;
+ to += copy;
+ pos += copy;
+ }
+ start = end;
+ }
+ }
+ if (len)
+ BUG();
+ return csum;
+}
+
+void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to)
+{
+ unsigned int csum;
+ long csstart;
+
+ if (skb->ip_summed == CHECKSUM_HW)
+ csstart = skb->h.raw - skb->data;
+ else
+ csstart = skb_headlen(skb);
+
+ if (csstart > skb_headlen(skb))
+ BUG();
+
+ memcpy(to, skb->data, csstart);
+
+ csum = 0;
+ if (csstart != skb->len)
+ csum = skb_copy_and_csum_bits(skb, csstart, to + csstart,
+ skb->len - csstart, 0);
+
+ if (skb->ip_summed == CHECKSUM_HW) {
+ long csstuff = csstart + skb->csum;
+
+ *((unsigned short *)(to + csstuff)) = csum_fold(csum);
+ }
+}
+
+/**
+ * skb_dequeue - remove from the head of the queue
+ * @list: list to dequeue from
+ *
+ * Remove the head of the list. The list lock is taken so the function
+ * may be used safely with other locking list functions. The head item is
+ * returned or %NULL if the list is empty.
+ */
+
+struct sk_buff *skb_dequeue(struct sk_buff_head *list)
+{
+ unsigned long flags;
+ struct sk_buff *result;
+
+ spin_lock_irqsave(&list->lock, flags);
+ result = __skb_dequeue(list);
+ spin_unlock_irqrestore(&list->lock, flags);
+ return result;
+}
+
+/**
+ * skb_dequeue_tail - remove from the tail of the queue
+ * @list: list to dequeue from
+ *
+ * Remove the tail of the list. The list lock is taken so the function
+ * may be used safely with other locking list functions. The tail item is
+ * returned or %NULL if the list is empty.
+ */
+struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list)
+{
+ unsigned long flags;
+ struct sk_buff *result;
+
+ spin_lock_irqsave(&list->lock, flags);
+ result = __skb_dequeue_tail(list);
+ spin_unlock_irqrestore(&list->lock, flags);
+ return result;
+}
+
+/**
+ * skb_queue_purge - empty a list
+ * @list: list to empty
+ *
+ * Delete all buffers on an &sk_buff list. Each buffer is removed from
+ * the list and one reference dropped. This function takes the list
+ * lock and is atomic with respect to other list locking functions.
+ */
+void skb_queue_purge(struct sk_buff_head *list)
+{
+ struct sk_buff *skb;
+ while ((skb = skb_dequeue(list)) != NULL)
+ kfree_skb(skb);
+}
+
+/**
+ * skb_queue_head - queue a buffer at the list head
+ * @list: list to use
+ * @newsk: buffer to queue
+ *
+ * Queue a buffer at the start of the list. This function takes the
+ * list lock and can be used safely with other locking &sk_buff functions
+ * safely.
+ *
+ * A buffer cannot be placed on two lists at the same time.
+ */
+void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&list->lock, flags);
+ __skb_queue_head(list, newsk);
+ spin_unlock_irqrestore(&list->lock, flags);
+}
+
+/**
+ * skb_queue_tail - queue a buffer at the list tail
+ * @list: list to use
+ * @newsk: buffer to queue
+ *
+ * Queue a buffer at the tail of the list. This function takes the
+ * list lock and can be used safely with other locking &sk_buff functions
+ * safely.
+ *
+ * A buffer cannot be placed on two lists at the same time.
+ */
+void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&list->lock, flags);
+ __skb_queue_tail(list, newsk);
+ spin_unlock_irqrestore(&list->lock, flags);
+}
+/**
+ * skb_unlink - remove a buffer from a list
+ * @skb: buffer to remove
+ *
+ * Place a packet after a given packet in a list. The list locks are taken
+ * and this function is atomic with respect to other list locked calls
+ *
+ * Works even without knowing the list it is sitting on, which can be
+ * handy at times. It also means that THE LIST MUST EXIST when you
+ * unlink. Thus a list must have its contents unlinked before it is
+ * destroyed.
+ */
+void skb_unlink(struct sk_buff *skb)
+{
+ struct sk_buff_head *list = skb->list;
+
+ if (list) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&list->lock, flags);
+ if (skb->list == list)
+ __skb_unlink(skb, skb->list);
+ spin_unlock_irqrestore(&list->lock, flags);
+ }
+}
+
+
+/**
+ * skb_append - append a buffer
+ * @old: buffer to insert after
+ * @newsk: buffer to insert
+ *
+ * Place a packet after a given packet in a list. The list locks are taken
+ * and this function is atomic with respect to other list locked calls.
+ * A buffer cannot be placed on two lists at the same time.
+ */
+
+void skb_append(struct sk_buff *old, struct sk_buff *newsk)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&old->list->lock, flags);
+ __skb_append(old, newsk);
+ spin_unlock_irqrestore(&old->list->lock, flags);
+}
+
+
+/**
+ * skb_insert - insert a buffer
+ * @old: buffer to insert before
+ * @newsk: buffer to insert
+ *
+ * Place a packet before a given packet in a list. The list locks are taken
+ * and this function is atomic with respect to other list locked calls
+ * A buffer cannot be placed on two lists at the same time.
+ */
+
+void skb_insert(struct sk_buff *old, struct sk_buff *newsk)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&old->list->lock, flags);
+ __skb_insert(newsk, old->prev, old, old->list);
+ spin_unlock_irqrestore(&old->list->lock, flags);
+}
+
+#if 0
+/*
+ * Tune the memory allocator for a new MTU size.
+ */
+void skb_add_mtu(int mtu)
+{
+ /* Must match allocation in alloc_skb */
+ mtu = SKB_DATA_ALIGN(mtu) + sizeof(struct skb_shared_info);
+
+ kmem_add_cache_size(mtu);
+}
+#endif
+
+static inline void skb_split_inside_header(struct sk_buff *skb,
+ struct sk_buff* skb1,
+ const u32 len, const int pos)
+{
+ int i;
+
+ memcpy(skb_put(skb1, pos - len), skb->data + len, pos - len);
+
+ /* And move data appendix as is. */
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
+ skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i];
+
+ skb_shinfo(skb1)->nr_frags = skb_shinfo(skb)->nr_frags;
+ skb_shinfo(skb)->nr_frags = 0;
+ skb1->data_len = skb->data_len;
+ skb1->len += skb1->data_len;
+ skb->data_len = 0;
+ skb->len = len;
+ skb->tail = skb->data + len;
+}
+
+static inline void skb_split_no_header(struct sk_buff *skb,
+ struct sk_buff* skb1,
+ const u32 len, int pos)
+{
+ int i, k = 0;
+ const int nfrags = skb_shinfo(skb)->nr_frags;
+
+ skb_shinfo(skb)->nr_frags = 0;
+ skb1->len = skb1->data_len = skb->len - len;
+ skb->len = len;
+ skb->data_len = len - pos;
+
+ for (i = 0; i < nfrags; i++) {
+ int size = skb_shinfo(skb)->frags[i].size;
+
+ if (pos + size > len) {
+ skb_shinfo(skb1)->frags[k] = skb_shinfo(skb)->frags[i];
+
+ if (pos < len) {
+ /* Split frag.
+ * We have to variants in this case:
+ * 1. Move all the frag to the second
+ * part, if it is possible. F.e.
+ * this approach is mandatory for TUX,
+ * where splitting is expensive.
+ * 2. Split is accurately. We make this.
+ */
+ get_page(skb_shinfo(skb)->frags[i].page);
+ skb_shinfo(skb1)->frags[0].page_offset += len -
pos;
+ skb_shinfo(skb1)->frags[0].size -= len - pos;
+ skb_shinfo(skb)->frags[i].size = len - pos;
+ skb_shinfo(skb)->nr_frags++;
+ }
+ k++;
+ } else
+ skb_shinfo(skb)->nr_frags++;
+ pos += size;
+ }
+ skb_shinfo(skb1)->nr_frags = k;
+}
+
+/**
+ * skb_split - Split fragmented skb to two parts at length len.
+ */
+void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len)
+{
+ int pos = skb_headlen(skb);
+
+ if (len < pos) /* Split line is inside header. */
+ skb_split_inside_header(skb, skb1, len, pos);
+ else /* Second chunk has no header, nothing to copy. */
+ skb_split_no_header(skb, skb1, len, pos);
+}
+
+void __init skb_init(void)
+{
+ skbuff_head_cache = kmem_cache_create("skbuff_head_cache",
+ sizeof(struct sk_buff),
+ 0,
+ SLAB_HWCACHE_ALIGN,
+ NULL, NULL);
+ if (!skbuff_head_cache)
+ panic("cannot create skbuff cache");
+}
+
+EXPORT_SYMBOL(___pskb_trim);
+EXPORT_SYMBOL(__kfree_skb);
+EXPORT_SYMBOL(__pskb_pull_tail);
+EXPORT_SYMBOL(alloc_skb);
+EXPORT_SYMBOL(pskb_copy);
+EXPORT_SYMBOL(pskb_expand_head);
+EXPORT_SYMBOL(skb_checksum);
+EXPORT_SYMBOL(skb_clone);
+EXPORT_SYMBOL(skb_clone_fraglist);
+EXPORT_SYMBOL(skb_copy);
+EXPORT_SYMBOL(skb_copy_and_csum_bits);
+EXPORT_SYMBOL(skb_copy_and_csum_dev);
+EXPORT_SYMBOL(skb_copy_bits);
+EXPORT_SYMBOL(skb_copy_expand);
+EXPORT_SYMBOL(skb_over_panic);
+EXPORT_SYMBOL(skb_pad);
+EXPORT_SYMBOL(skb_realloc_headroom);
+EXPORT_SYMBOL(skb_under_panic);
+EXPORT_SYMBOL(skb_dequeue);
+EXPORT_SYMBOL(skb_dequeue_tail);
+EXPORT_SYMBOL(skb_insert);
+EXPORT_SYMBOL(skb_queue_purge);
+EXPORT_SYMBOL(skb_queue_head);
+EXPORT_SYMBOL(skb_queue_tail);
+EXPORT_SYMBOL(skb_unlink);
+EXPORT_SYMBOL(skb_append);
+EXPORT_SYMBOL(skb_split);
+EXPORT_SYMBOL(skb_iter_first);
+EXPORT_SYMBOL(skb_iter_next);
+EXPORT_SYMBOL(skb_iter_abort);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/setup_arch_pre.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++
b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/setup_arch_pre.h
Fri Jul 15 13:39:50 2005
@@ -0,0 +1,5 @@
+/* Hook to call BIOS initialisation function */
+
+#define ARCH_SETUP machine_specific_arch_setup();
+
+static void __init machine_specific_arch_setup(void);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/pci/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/pci/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,32 @@
+XENARCH := $(subst ",,$(CONFIG_XENARCH))
+
+CFLAGS += -Iarch/$(XENARCH)/pci
+
+c-obj-y := i386.o
+
+c-obj-$(CONFIG_PCI_BIOS) += pcbios.o
+c-obj-$(CONFIG_PCI_MMCONFIG) += mmconfig.o
+c-obj-$(CONFIG_PCI_DIRECT) += direct.o
+
+c-pci-y := fixup.o
+c-pci-$(CONFIG_ACPI_PCI) += acpi.o
+c-pci-y += legacy.o
+# Make sure irq.o gets linked in after legacy.o
+l-pci-y += irq.o
+
+c-pci-$(CONFIG_X86_VISWS) := visws.o fixup.o
+pci-$(CONFIG_X86_VISWS) :=
+c-pci-$(CONFIG_X86_NUMAQ) := numa.o
+pci-$(CONFIG_X86_NUMAQ) := irq.o
+
+obj-y += $(pci-y)
+c-obj-y += $(c-pci-y) common.o
+
+c-link :=
+
+$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)):
+ @ln -fsn $(srctree)/arch/i386/pci/$(notdir $@) $@
+
+obj-y += $(c-obj-y) $(l-pci-y)
+
+clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link))
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/kernel/traps.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/kernel/traps.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,619 @@
+/*
+ * linux/arch/i386/traps.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000
+ */
+
+/*
+ * 'Traps.c' handles hardware traps and faults after we have saved some
+ * state in 'asm.s'.
+ */
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/timer.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#include <linux/highmem.h>
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/atomic.h>
+#include <asm/debugreg.h>
+#include <asm/desc.h>
+#include <asm/i387.h>
+
+#include <asm/smp.h>
+#include <asm/pgalloc.h>
+
+#include <asm/hypervisor.h>
+
+#include <linux/irq.h>
+#include <linux/module.h>
+
+asmlinkage int system_call(void);
+asmlinkage void lcall7(void);
+asmlinkage void lcall27(void);
+
+asmlinkage void divide_error(void);
+asmlinkage void debug(void);
+asmlinkage void int3(void);
+asmlinkage void overflow(void);
+asmlinkage void bounds(void);
+asmlinkage void invalid_op(void);
+asmlinkage void device_not_available(void);
+asmlinkage void double_fault(void);
+asmlinkage void coprocessor_segment_overrun(void);
+asmlinkage void invalid_TSS(void);
+asmlinkage void segment_not_present(void);
+asmlinkage void stack_segment(void);
+asmlinkage void general_protection(void);
+asmlinkage void page_fault(void);
+asmlinkage void coprocessor_error(void);
+asmlinkage void simd_coprocessor_error(void);
+asmlinkage void alignment_check(void);
+asmlinkage void fixup_4gb_segment(void);
+asmlinkage void machine_check(void);
+
+int kstack_depth_to_print = 24;
+
+
+/*
+ * If the address is either in the .text section of the
+ * kernel, or in the vmalloc'ed module regions, it *may*
+ * be the address of a calling routine
+ */
+
+#ifdef CONFIG_MODULES
+
+extern struct module *module_list;
+extern struct module kernel_module;
+
+static inline int kernel_text_address(unsigned long addr)
+{
+ int retval = 0;
+ struct module *mod;
+
+ if (addr >= (unsigned long) &_stext &&
+ addr <= (unsigned long) &_etext)
+ return 1;
+
+ for (mod = module_list; mod != &kernel_module; mod = mod->next) {
+ /* mod_bound tests for addr being inside the vmalloc'ed
+ * module area. Of course it'd be better to test only
+ * for the .text subset... */
+ if (mod_bound(addr, 0, mod)) {
+ retval = 1;
+ break;
+ }
+ }
+
+ return retval;
+}
+
+#else
+
+static inline int kernel_text_address(unsigned long addr)
+{
+ return (addr >= (unsigned long) &_stext &&
+ addr <= (unsigned long) &_etext);
+}
+
+#endif
+
+void show_trace(unsigned long * stack)
+{
+ int i;
+ unsigned long addr;
+
+ if (!stack)
+ stack = (unsigned long*)&stack;
+
+ printk("Call Trace: ");
+ i = 1;
+ while (((long) stack & (THREAD_SIZE-1)) != 0) {
+ addr = *stack++;
+ if (kernel_text_address(addr)) {
+ if (i && ((i % 6) == 0))
+ printk("\n ");
+ printk("[<%08lx>] ", addr);
+ i++;
+ }
+ }
+ printk("\n");
+}
+
+void show_trace_task(struct task_struct *tsk)
+{
+ unsigned long esp = tsk->thread.esp;
+
+ /* User space on another CPU? */
+ if ((esp ^ (unsigned long)tsk) & (PAGE_MASK<<1))
+ return;
+ show_trace((unsigned long *)esp);
+}
+
+void show_stack(unsigned long * esp)
+{
+ unsigned long *stack;
+ int i;
+
+ // debugging aid: "show_stack(NULL);" prints the
+ // back trace for this cpu.
+
+ if(esp==NULL)
+ esp=(unsigned long*)&esp;
+
+ stack = esp;
+ for(i=0; i < kstack_depth_to_print; i++) {
+ if (((long) stack & (THREAD_SIZE-1)) == 0)
+ break;
+ if (i && ((i % 8) == 0))
+ printk("\n ");
+ printk("%08lx ", *stack++);
+ }
+ printk("\n");
+ show_trace(esp);
+}
+
+void show_registers(struct pt_regs *regs)
+{
+ int in_kernel = 1;
+ unsigned long esp;
+ unsigned short ss;
+
+ esp = (unsigned long) (®s->esp);
+ ss = __KERNEL_DS;
+ if (regs->xcs & 2) {
+ in_kernel = 0;
+ esp = regs->esp;
+ ss = regs->xss & 0xffff;
+ }
+ printk(KERN_ALERT "CPU: %d\n", smp_processor_id() );
+ printk(KERN_ALERT "EIP: %04x:[<%08lx>] %s\n",
+ 0xffff & regs->xcs, regs->eip, print_tainted());
+ printk(KERN_ALERT "EFLAGS: %08lx\n",regs->eflags);
+ printk(KERN_ALERT "eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n",
+ regs->eax, regs->ebx, regs->ecx, regs->edx);
+ printk(KERN_ALERT "esi: %08lx edi: %08lx ebp: %08lx esp: %08lx\n",
+ regs->esi, regs->edi, regs->ebp, esp);
+ printk(KERN_ALERT "ds: %04x es: %04x ss: %04x\n",
+ regs->xds & 0xffff, regs->xes & 0xffff, ss);
+ printk(KERN_ALERT "Process %s (pid: %d, stackpage=%08lx)",
+ current->comm, current->pid, 4096+(unsigned long)current);
+ /*
+ * When in-kernel, we also print out the stack and code at the
+ * time of the fault..
+ */
+ if (in_kernel) {
+
+ printk(KERN_ALERT "\nStack: ");
+ show_stack((unsigned long*)esp);
+
+#if 0
+ {
+ int i;
+ printk(KERN_ALERT "\nCode: ");
+ if(regs->eip < PAGE_OFFSET)
+ goto bad;
+
+ for(i=0;i<20;i++)
+ {
+ unsigned char c;
+ if(__get_user(c, &((unsigned
char*)regs->eip)[i])) {
+bad:
+ printk(KERN_ALERT " Bad EIP value.");
+ break;
+ }
+ printk("%02x ", c);
+ }
+ }
+#endif
+ }
+ printk(KERN_ALERT "\n");
+}
+
+spinlock_t die_lock = SPIN_LOCK_UNLOCKED;
+
+void die(const char * str, struct pt_regs * regs, long err)
+{
+ console_verbose();
+ spin_lock_irq(&die_lock);
+ bust_spinlocks(1);
+ printk("%s: %04lx\n", str, err & 0xffff);
+ show_registers(regs);
+ bust_spinlocks(0);
+ spin_unlock_irq(&die_lock);
+ do_exit(SIGSEGV);
+}
+
+static inline void die_if_kernel(const char * str, struct pt_regs * regs, long
err)
+{
+ if (!(2 & regs->xcs))
+ die(str, regs, err);
+}
+
+
+static void inline do_trap(int trapnr, int signr, char *str,
+ struct pt_regs * regs, long error_code,
+ siginfo_t *info)
+{
+ if (!(regs->xcs & 2))
+ goto kernel_trap;
+
+ /*trap_signal:*/ {
+ struct task_struct *tsk = current;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = trapnr;
+ if (info)
+ force_sig_info(signr, info, tsk);
+ else
+ force_sig(signr, tsk);
+ return;
+ }
+
+ kernel_trap: {
+ unsigned long fixup = search_exception_table(regs->eip);
+ if (fixup)
+ regs->eip = fixup;
+ else
+ die(str, regs, error_code);
+ return;
+ }
+}
+
+#define DO_ERROR(trapnr, signr, str, name) \
+asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
+{ \
+ do_trap(trapnr, signr, str, regs, error_code, NULL); \
+}
+
+#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
+asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
+{ \
+ siginfo_t info; \
+ info.si_signo = signr; \
+ info.si_errno = 0; \
+ info.si_code = sicode; \
+ info.si_addr = (void *)siaddr; \
+ do_trap(trapnr, signr, str, regs, error_code, &info); \
+}
+
+DO_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->eip)
+DO_ERROR( 3, SIGTRAP, "int3", int3)
+DO_ERROR( 4, SIGSEGV, "overflow", overflow)
+DO_ERROR( 5, SIGSEGV, "bounds", bounds)
+DO_ERROR_INFO( 6, SIGILL, "invalid operand", invalid_op, ILL_ILLOPN,
regs->eip)
+DO_ERROR( 7, SIGSEGV, "device not available", device_not_available)
+DO_ERROR( 8, SIGSEGV, "double fault", double_fault)
+DO_ERROR( 9, SIGFPE, "coprocessor segment overrun",
coprocessor_segment_overrun)
+DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
+DO_ERROR(11, SIGBUS, "segment not present", segment_not_present)
+DO_ERROR(12, SIGBUS, "stack segment", stack_segment)
+DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0)
+DO_ERROR(18, SIGBUS, "machine check", machine_check)
+
+asmlinkage void do_general_protection(struct pt_regs * regs, long error_code)
+{
+ /*
+ * If we trapped on an LDT access then ensure that the default_ldt is
+ * loaded, if nothing else. We load default_ldt lazily because LDT
+ * switching costs time and many applications don't need it.
+ */
+ if ( unlikely((error_code & 6) == 4) )
+ {
+ unsigned long ldt;
+ __asm__ __volatile__ ( "sldt %0" : "=r" (ldt) );
+ if ( ldt == 0 )
+ {
+ xen_set_ldt((unsigned long)&default_ldt[0], 5);
+ return;
+ }
+ }
+
+ if (!(regs->xcs & 2))
+ goto gp_in_kernel;
+
+ current->thread.error_code = error_code;
+ current->thread.trap_no = 13;
+ force_sig(SIGSEGV, current);
+ return;
+
+gp_in_kernel:
+ {
+ unsigned long fixup;
+ fixup = search_exception_table(regs->eip);
+ if (fixup) {
+ regs->eip = fixup;
+ return;
+ }
+ die("general protection fault", regs, error_code);
+ }
+}
+
+
+asmlinkage void do_debug(struct pt_regs * regs, long error_code)
+{
+ unsigned int condition;
+ struct task_struct *tsk = current;
+ siginfo_t info;
+
+ condition = HYPERVISOR_get_debugreg(6);
+
+ /* Mask out spurious debug traps due to lazy DR7 setting */
+ if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) {
+ if (!tsk->thread.debugreg[7])
+ goto clear_dr7;
+ }
+
+ /* Save debug status register where ptrace can see it */
+ tsk->thread.debugreg[6] = condition;
+
+ /* Mask out spurious TF errors due to lazy TF clearing */
+ if (condition & DR_STEP) {
+ /*
+ * The TF error should be masked out only if the current
+ * process is not traced and if the TRAP flag has been set
+ * previously by a tracing process (condition detected by
+ * the PT_DTRACE flag); remember that the i386 TRAP flag
+ * can be modified by the process itself in user mode,
+ * allowing programs to debug themselves without the ptrace()
+ * interface.
+ */
+ if ((tsk->ptrace & (PT_DTRACE|PT_PTRACED)) == PT_DTRACE)
+ goto clear_TF;
+ }
+
+ /* Ok, finally something we can handle */
+ tsk->thread.trap_no = 1;
+ tsk->thread.error_code = error_code;
+ info.si_signo = SIGTRAP;
+ info.si_errno = 0;
+ info.si_code = TRAP_BRKPT;
+
+ /* If this is a kernel mode trap, save the user PC on entry to
+ * the kernel, that's what the debugger can make sense of.
+ */
+ info.si_addr = ((regs->xcs & 2) == 0) ? (void *)tsk->thread.eip :
+ (void *)regs->eip;
+ force_sig_info(SIGTRAP, &info, tsk);
+
+ /* Disable additional traps. They'll be re-enabled when
+ * the signal is delivered.
+ */
+ clear_dr7:
+ HYPERVISOR_set_debugreg(7, 0);
+ return;
+
+ clear_TF:
+ regs->eflags &= ~TF_MASK;
+ return;
+}
+
+
+/*
+ * Note that we play around with the 'TS' bit in an attempt to get
+ * the correct behaviour even in the presence of the asynchronous
+ * IRQ13 behaviour
+ */
+void math_error(void *eip)
+{
+ struct task_struct * task;
+ siginfo_t info;
+ unsigned short cwd, swd;
+
+ /*
+ * Save the info for the exception handler and clear the error.
+ */
+ task = current;
+ save_init_fpu(task);
+ task->thread.trap_no = 16;
+ task->thread.error_code = 0;
+ info.si_signo = SIGFPE;
+ info.si_errno = 0;
+ info.si_code = __SI_FAULT;
+ info.si_addr = eip;
+ /*
+ * (~cwd & swd) will mask out exceptions that are not set to unmasked
+ * status. 0x3f is the exception bits in these regs, 0x200 is the
+ * C1 reg you need in case of a stack fault, 0x040 is the stack
+ * fault bit. We should only be taking one exception at a time,
+ * so if this combination doesn't produce any single exception,
+ * then we have a bad program that isn't syncronizing its FPU usage
+ * and it will suffer the consequences since we won't be able to
+ * fully reproduce the context of the exception
+ */
+ cwd = get_fpu_cwd(task);
+ swd = get_fpu_swd(task);
+ switch (((~cwd) & swd & 0x3f) | (swd & 0x240)) {
+ case 0x000:
+ default:
+ break;
+ case 0x001: /* Invalid Op */
+ case 0x041: /* Stack Fault */
+ case 0x241: /* Stack Fault | Direction */
+ info.si_code = FPE_FLTINV;
+ break;
+ case 0x002: /* Denormalize */
+ case 0x010: /* Underflow */
+ info.si_code = FPE_FLTUND;
+ break;
+ case 0x004: /* Zero Divide */
+ info.si_code = FPE_FLTDIV;
+ break;
+ case 0x008: /* Overflow */
+ info.si_code = FPE_FLTOVF;
+ break;
+ case 0x020: /* Precision */
+ info.si_code = FPE_FLTRES;
+ break;
+ }
+ force_sig_info(SIGFPE, &info, task);
+}
+
+asmlinkage void do_coprocessor_error(struct pt_regs * regs, long error_code)
+{
+ ignore_irq13 = 1;
+ math_error((void *)regs->eip);
+}
+
+void simd_math_error(void *eip)
+{
+ struct task_struct * task;
+ siginfo_t info;
+ unsigned short mxcsr;
+
+ /*
+ * Save the info for the exception handler and clear the error.
+ */
+ task = current;
+ save_init_fpu(task);
+ task->thread.trap_no = 19;
+ task->thread.error_code = 0;
+ info.si_signo = SIGFPE;
+ info.si_errno = 0;
+ info.si_code = __SI_FAULT;
+ info.si_addr = eip;
+ /*
+ * The SIMD FPU exceptions are handled a little differently, as there
+ * is only a single status/control register. Thus, to determine which
+ * unmasked exception was caught we must mask the exception mask bits
+ * at 0x1f80, and then use these to mask the exception bits at 0x3f.
+ */
+ mxcsr = get_fpu_mxcsr(task);
+ switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) {
+ case 0x000:
+ default:
+ break;
+ case 0x001: /* Invalid Op */
+ info.si_code = FPE_FLTINV;
+ break;
+ case 0x002: /* Denormalize */
+ case 0x010: /* Underflow */
+ info.si_code = FPE_FLTUND;
+ break;
+ case 0x004: /* Zero Divide */
+ info.si_code = FPE_FLTDIV;
+ break;
+ case 0x008: /* Overflow */
+ info.si_code = FPE_FLTOVF;
+ break;
+ case 0x020: /* Precision */
+ info.si_code = FPE_FLTRES;
+ break;
+ }
+ force_sig_info(SIGFPE, &info, task);
+}
+
+asmlinkage void do_simd_coprocessor_error(struct pt_regs * regs,
+ long error_code)
+{
+ if (cpu_has_xmm) {
+ /* Handle SIMD FPU exceptions on PIII+ processors. */
+ ignore_irq13 = 1;
+ simd_math_error((void *)regs->eip);
+ } else {
+ die_if_kernel("cache flush denied", regs, error_code);
+ current->thread.trap_no = 19;
+ current->thread.error_code = error_code;
+ force_sig(SIGSEGV, current);
+ }
+}
+
+/*
+ * 'math_state_restore()' saves the current math information in the
+ * old math state array, and gets the new ones from the current task
+ *
+ * Careful.. There are problems with IBM-designed IRQ13 behaviour.
+ * Don't touch unless you *really* know how it works.
+ */
+asmlinkage void math_state_restore(struct pt_regs regs)
+{
+ /*
+ * A trap in kernel mode can be ignored. It'll be the fast XOR or
+ * copying libraries, which will correctly save/restore state and
+ * reset the TS bit in CR0.
+ */
+ if ( (regs.xcs & 2) == 0 )
+ return;
+
+ if (current->used_math) {
+ restore_fpu(current);
+ } else {
+ init_fpu();
+ }
+ current->flags |= PF_USEDFPU; /* So we fnsave on switch_to() */
+}
+
+
+#define _set_gate(gate_addr,type,dpl,addr) \
+do { \
+ int __d0, __d1; \
+ __asm__ __volatile__ ("movw %%dx,%%ax\n\t" \
+ "movw %4,%%dx\n\t" \
+ "movl %%eax,%0\n\t" \
+ "movl %%edx,%1" \
+ :"=m" (*((long *) (gate_addr))), \
+ "=m" (*(1+(long *) (gate_addr))), "=&a" (__d0), "=&d" (__d1) \
+ :"i" ((short) (0x8000+(dpl<<13)+(type<<8))), \
+ "3" ((char *) (addr)),"2" (__KERNEL_CS << 16)); \
+} while (0)
+
+static void __init set_call_gate(void *a, void *addr)
+{
+ _set_gate(a,12,3,addr);
+}
+
+
+/* NB. All these are "trap gates" (i.e. events_mask isn't cleared). */
+static trap_info_t trap_table[] = {
+ { 0, 0, __KERNEL_CS, (unsigned long)divide_error },
+ { 1, 0, __KERNEL_CS, (unsigned long)debug },
+ { 3, 3, __KERNEL_CS, (unsigned long)int3 },
+ { 4, 3, __KERNEL_CS, (unsigned long)overflow },
+ { 5, 3, __KERNEL_CS, (unsigned long)bounds },
+ { 6, 0, __KERNEL_CS, (unsigned long)invalid_op },
+ { 7, 0, __KERNEL_CS, (unsigned long)device_not_available },
+ { 8, 0, __KERNEL_CS, (unsigned long)double_fault },
+ { 9, 0, __KERNEL_CS, (unsigned long)coprocessor_segment_overrun },
+ { 10, 0, __KERNEL_CS, (unsigned long)invalid_TSS },
+ { 11, 0, __KERNEL_CS, (unsigned long)segment_not_present },
+ { 12, 0, __KERNEL_CS, (unsigned long)stack_segment },
+ { 13, 0, __KERNEL_CS, (unsigned long)general_protection },
+ { 14, 0, __KERNEL_CS, (unsigned long)page_fault },
+ { 15, 0, __KERNEL_CS, (unsigned long)fixup_4gb_segment },
+ { 16, 0, __KERNEL_CS, (unsigned long)coprocessor_error },
+ { 17, 0, __KERNEL_CS, (unsigned long)alignment_check },
+ { 18, 0, __KERNEL_CS, (unsigned long)machine_check },
+ { 19, 0, __KERNEL_CS, (unsigned long)simd_coprocessor_error },
+ { SYSCALL_VECTOR,
+ 3, __KERNEL_CS, (unsigned long)system_call },
+ { 0, 0, 0, 0 }
+};
+
+
+void __init trap_init(void)
+{
+ HYPERVISOR_set_trap_table(trap_table);
+
+ /*
+ * The default LDT is a single-entry callgate to lcall7 for iBCS and a
+ * callgate to lcall27 for Solaris/x86 binaries.
+ */
+ clear_page(&default_ldt[0]);
+ set_call_gate(&default_ldt[0],lcall7);
+ set_call_gate(&default_ldt[4],lcall27);
+ __make_page_readonly(&default_ldt[0]);
+
+ cpu_init();
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/mach-xen/setup_arch_pre.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++
b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/mach-xen/setup_arch_pre.h
Fri Jul 15 13:39:50 2005
@@ -0,0 +1,5 @@
+/* Hook to call BIOS initialisation function */
+
+#define ARCH_SETUP machine_specific_arch_setup();
+
+static void __init machine_specific_arch_setup(void);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blktap/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blktap/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,3 @@
+
+obj-y := blktap_userdev.o blktap_datapath.o blktap_controlmsg.o blktap.o
+
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/arch/xen/mm/init.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/mm/init.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,482 @@
+/*
+ * linux/arch/i386/mm/init.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ */
+
+#include <linux/config.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#ifdef CONFIG_BLK_DEV_INITRD
+#include <linux/blk.h>
+#endif
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/bootmem.h>
+#include <linux/slab.h>
+
+#include <asm/processor.h>
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/dma.h>
+#include <asm/apic.h>
+#include <asm/tlb.h>
+
+/* XEN: We *cannot* use mmx_clear_page() this early. Force dumb memset(). */
+#undef clear_page
+#define clear_page(page) memset((void *)(page), 0, PAGE_SIZE)
+
+mmu_gather_t mmu_gathers[NR_CPUS];
+unsigned long highstart_pfn, highend_pfn;
+static unsigned long totalram_pages;
+static unsigned long totalhigh_pages;
+
+int do_check_pgt_cache(int low, int high)
+{
+ int freed = 0;
+ if(pgtable_cache_size > high) {
+ do {
+ if (!QUICKLIST_EMPTY(pgd_quicklist)) {
+ free_pgd_slow(get_pgd_fast());
+ freed++;
+ }
+ if (!QUICKLIST_EMPTY(pte_quicklist)) {
+ pte_free_slow(pte_alloc_one_fast(NULL, 0));
+ freed++;
+ }
+ } while(pgtable_cache_size > low);
+ }
+ return freed;
+}
+
+/*
+ * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
+ * physical space so we can cache the place of the first one and move
+ * around without checking the pgd every time.
+ */
+
+#if CONFIG_HIGHMEM
+pte_t *kmap_pte;
+pgprot_t kmap_prot;
+
+#define kmap_get_fixmap_pte(vaddr) \
+ pte_offset(pmd_offset(pgd_offset_k(vaddr), (vaddr)), (vaddr))
+
+void __init kmap_init(void)
+{
+ unsigned long kmap_vstart;
+
+ /* cache the first kmap pte */
+ kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
+ kmap_pte = kmap_get_fixmap_pte(kmap_vstart);
+
+ kmap_prot = PAGE_KERNEL;
+}
+#endif /* CONFIG_HIGHMEM */
+
+void show_mem(void)
+{
+ int i, total = 0, reserved = 0;
+ int shared = 0, cached = 0;
+ int highmem = 0;
+
+ printk("Mem-info:\n");
+ show_free_areas();
+ printk("Free swap: %6dkB\n",nr_swap_pages<<(PAGE_SHIFT-10));
+ i = max_mapnr;
+ while (i-- > 0) {
+ total++;
+ if (PageHighMem(mem_map+i))
+ highmem++;
+ if (PageReserved(mem_map+i))
+ reserved++;
+ else if (PageSwapCache(mem_map+i))
+ cached++;
+ else if (page_count(mem_map+i))
+ shared += page_count(mem_map+i) - 1;
+ }
+ printk("%d pages of RAM\n", total);
+ printk("%d pages of HIGHMEM\n",highmem);
+ printk("%d reserved pages\n",reserved);
+ printk("%d pages shared\n",shared);
+ printk("%d pages swap cached\n",cached);
+ printk("%ld pages in page table cache\n",pgtable_cache_size);
+ show_buffers();
+}
+
+/* References to section boundaries */
+
+extern char _text, _etext, _edata, __bss_start, _end;
+extern char __init_begin, __init_end;
+
+static inline void set_pte_phys (unsigned long vaddr,
+ unsigned long phys, pgprot_t prot)
+{
+ pgd_t *pgd;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pgd = init_mm.pgd + __pgd_offset(vaddr);
+ if (pgd_none(*pgd)) {
+ printk("PAE BUG #00!\n");
+ return;
+ }
+ pmd = pmd_offset(pgd, vaddr);
+ if (pmd_none(*pmd)) {
+ printk("PAE BUG #01!\n");
+ return;
+ }
+ pte = pte_offset(pmd, vaddr);
+
+ set_pte(pte, (pte_t) { phys | pgprot_val(prot) });
+
+ /*
+ * It's enough to flush this one mapping.
+ * (PGE mappings get flushed as well)
+ */
+ __flush_tlb_one(vaddr);
+}
+
+void __set_fixmap(enum fixed_addresses idx, unsigned long phys,
+ pgprot_t flags)
+{
+ unsigned long address = __fix_to_virt(idx);
+
+ if (idx >= __end_of_fixed_addresses) {
+ printk("Invalid __set_fixmap\n");
+ return;
+ }
+ set_pte_phys(address, phys, flags);
+}
+
+void clear_fixmap(enum fixed_addresses idx)
+{
+ set_pte_phys(__fix_to_virt(idx), 0, __pgprot(0));
+}
+
+static void __init fixrange_init (unsigned long start,
+ unsigned long end, pgd_t *pgd_base)
+{
+ pgd_t *pgd, *kpgd;
+ pmd_t *pmd, *kpmd;
+ pte_t *pte, *kpte;
+ int i, j;
+ unsigned long vaddr;
+
+ vaddr = start;
+ i = __pgd_offset(vaddr);
+ j = __pmd_offset(vaddr);
+ pgd = pgd_base + i;
+
+ for ( ; (i < PTRS_PER_PGD) && (vaddr != end); pgd++, i++) {
+#if CONFIG_X86_PAE
+ if (pgd_none(*pgd)) {
+ pmd = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE);
+ set_pgd(pgd, __pgd(__pa(pmd) + 0x1));
+ if (pmd != pmd_offset(pgd, 0))
+ printk("PAE BUG #02!\n");
+ }
+ pmd = pmd_offset(pgd, vaddr);
+#else
+ pmd = (pmd_t *)pgd;
+#endif
+ for (; (j < PTRS_PER_PMD) && (vaddr != end); pmd++, j++) {
+ if (pmd_none(*pmd)) {
+ pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
+ clear_page(pte);
+ kpgd = pgd_offset_k((unsigned long)pte);
+ kpmd = pmd_offset(kpgd, (unsigned long)pte);
+ kpte = pte_offset(kpmd, (unsigned long)pte);
+ set_pte(kpte, pte_wrprotect(*kpte));
+ set_pmd(pmd, __pmd(_KERNPG_TABLE + __pa(pte)));
+ }
+ vaddr += PMD_SIZE;
+ }
+ j = 0;
+ }
+}
+
+
+static void __init pagetable_init (void)
+{
+ unsigned long vaddr, end, ram_end;
+ pgd_t *kpgd, *pgd, *pgd_base;
+ int i, j, k;
+ pmd_t *kpmd, *pmd;
+ pte_t *kpte, *pte, *pte_base;
+
+ ram_end = end = (unsigned long)__va(max_low_pfn * PAGE_SIZE);
+ if ( xen_start_info.nr_pages < max_low_pfn )
+ ram_end = (unsigned long)__va(xen_start_info.nr_pages * PAGE_SIZE);
+
+ pgd_base = init_mm.pgd;
+ i = __pgd_offset(PAGE_OFFSET);
+ pgd = pgd_base + i;
+
+ for (; i < PTRS_PER_PGD; pgd++, i++) {
+ vaddr = i*PGDIR_SIZE;
+ if (vaddr >= end)
+ break;
+ pmd = (pmd_t *)pgd;
+ for (j = 0; j < PTRS_PER_PMD; pmd++, j++) {
+ vaddr = i*PGDIR_SIZE + j*PMD_SIZE;
+ if (vaddr >= end)
+ break;
+
+ /* Filled in for us already? */
+ if ( pmd_val(*pmd) & _PAGE_PRESENT )
+ continue;
+
+ pte_base = pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
+ clear_page(pte_base);
+
+ for (k = 0; k < PTRS_PER_PTE; pte++, k++) {
+ vaddr = i*PGDIR_SIZE + j*PMD_SIZE + k*PAGE_SIZE;
+ if (vaddr >= ram_end)
+ break;
+ *pte = mk_pte_phys(__pa(vaddr), PAGE_KERNEL);
+ }
+ kpgd = pgd_offset_k((unsigned long)pte_base);
+ kpmd = pmd_offset(kpgd, (unsigned long)pte_base);
+ kpte = pte_offset(kpmd, (unsigned long)pte_base);
+ set_pte(kpte, pte_wrprotect(*kpte));
+ set_pmd(pmd, __pmd(_KERNPG_TABLE + __pa(pte_base)));
+ }
+ }
+
+ /*
+ * Fixed mappings, only the page table structure has to be
+ * created - mappings will be set by set_fixmap():
+ */
+ vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
+ fixrange_init(vaddr, HYPERVISOR_VIRT_START, init_mm.pgd);
+
+#if CONFIG_HIGHMEM
+ /*
+ * Permanent kmaps:
+ */
+ vaddr = PKMAP_BASE;
+ fixrange_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, init_mm.pgd);
+
+ pgd = init_mm.pgd + __pgd_offset(vaddr);
+ pmd = pmd_offset(pgd, vaddr);
+ pte = pte_offset(pmd, vaddr);
+ pkmap_page_table = pte;
+#endif
+}
+
+static void __init zone_sizes_init(void)
+{
+ unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0};
+ unsigned int max_dma, high, low;
+
+ max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
+ low = max_low_pfn;
+ high = highend_pfn;
+
+ if (low < max_dma)
+ zones_size[ZONE_DMA] = low;
+ else {
+ zones_size[ZONE_DMA] = max_dma;
+ zones_size[ZONE_NORMAL] = low - max_dma;
+#ifdef CONFIG_HIGHMEM
+ zones_size[ZONE_HIGHMEM] = high - low;
+#endif
+ }
+ free_area_init(zones_size);
+}
+
+void __init paging_init(void)
+{
+ pagetable_init();
+
+ zone_sizes_init();
+
+ /* Switch to the real shared_info page, and clear the dummy page. */
+ set_fixmap(FIX_SHARED_INFO, xen_start_info.shared_info);
+ HYPERVISOR_shared_info = (shared_info_t *)fix_to_virt(FIX_SHARED_INFO);
+ memset(empty_zero_page, 0, sizeof(empty_zero_page));
+
+#ifdef CONFIG_HIGHMEM
+ kmap_init();
+#endif
+}
+
+static inline int page_is_ram (unsigned long pagenr)
+{
+ return 1;
+}
+
+#ifdef CONFIG_HIGHMEM
+void __init one_highpage_init(struct page *page, int free_page)
+{
+ ClearPageReserved(page);
+ set_bit(PG_highmem, &page->flags);
+ atomic_set(&page->count, 1);
+ if ( free_page )
+ __free_page(page);
+ totalhigh_pages++;
+}
+#endif /* CONFIG_HIGHMEM */
+
+static void __init set_max_mapnr_init(void)
+{
+#ifdef CONFIG_HIGHMEM
+ highmem_start_page = mem_map + highstart_pfn;
+ max_mapnr = num_physpages = highend_pfn;
+ num_mappedpages = max_low_pfn;
+#else
+ max_mapnr = num_mappedpages = num_physpages = max_low_pfn;
+#endif
+}
+
+static int __init free_pages_init(void)
+{
+#ifdef CONFIG_HIGHMEM
+ int bad_ppro = 0;
+#endif
+ int reservedpages, pfn;
+
+ /* add only boot_pfn pages of low memory to free list.
+ * max_low_pfn may be sized for
+ * pages yet to be allocated from the hypervisor, or it may be set
+ * to override the xen_start_info amount of memory
+ */
+ int boot_pfn = min(xen_start_info.nr_pages,max_low_pfn);
+
+ /* this will put all low memory onto the freelists */
+ totalram_pages += free_all_bootmem();
+ /* XEN: init and count low-mem pages outside initial allocation. */
+ for (pfn = boot_pfn; pfn < max_low_pfn; pfn++) {
+ ClearPageReserved(&mem_map[pfn]);
+ atomic_set(&mem_map[pfn].count, 1);
+ totalram_pages++;
+ }
+
+ reservedpages = 0;
+ for (pfn = 0; pfn < boot_pfn ; pfn++) {
+ /*
+ * Only count reserved RAM pages
+ */
+ if (page_is_ram(pfn) && PageReserved(mem_map+pfn))
+ reservedpages++;
+ }
+#ifdef CONFIG_HIGHMEM
+ for (pfn = highend_pfn-1; pfn >= highstart_pfn; pfn--)
+ one_highpage_init((struct page *) (mem_map + pfn),
+ (pfn < xen_start_info.nr_pages));
+ totalram_pages += totalhigh_pages;
+#endif
+ return reservedpages;
+}
+
+void __init mem_init(void)
+{
+ int codesize, reservedpages, datasize, initsize;
+
+ if (!mem_map)
+ BUG();
+
+#ifdef CONFIG_HIGHMEM
+ /* check that fixmap and pkmap do not overlap */
+ if (PKMAP_BASE+LAST_PKMAP*PAGE_SIZE >= FIXADDR_START) {
+ printk(KERN_ERR "fixmap and kmap areas overlap - this will crash\n");
+ printk(KERN_ERR "pkstart: %lxh pkend: %lxh fixstart %lxh\n",
+ PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE, FIXADDR_START);
+ BUG();
+ }
+#endif
+
+ set_max_mapnr_init();
+
+ high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
+
+ /* clear the zero-page */
+ memset(empty_zero_page, 0, PAGE_SIZE);
+
+ reservedpages = free_pages_init();
+
+ codesize = (unsigned long) &_etext - (unsigned long) &_text;
+ datasize = (unsigned long) &_edata - (unsigned long) &_etext;
+ initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
+
+ printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, %dk
reserved, %dk data, %dk init, %ldk highmem)\n",
+ (unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
+ max_mapnr << (PAGE_SHIFT-10),
+ codesize >> 10,
+ reservedpages << (PAGE_SHIFT-10),
+ datasize >> 10,
+ initsize >> 10,
+ (unsigned long) (totalhigh_pages << (PAGE_SHIFT-10))
+ );
+
+ boot_cpu_data.wp_works_ok = 1;
+}
+
+void free_initmem(void)
+{
+ unsigned long addr;
+
+ addr = (unsigned long)(&__init_begin);
+ for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
+ ClearPageReserved(virt_to_page(addr));
+ set_page_count(virt_to_page(addr), 1);
+ free_page(addr);
+ totalram_pages++;
+ }
+ printk (KERN_INFO "Freeing unused kernel memory: %dk freed\n",
(&__init_end - &__init_begin) >> 10);
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void free_initrd_mem(unsigned long start, unsigned long end)
+{
+ if (start < end)
+ printk (KERN_INFO "Freeing initrd memory: %ldk freed\n", (end - start)
>> 10);
+ for (; start < end; start += PAGE_SIZE) {
+ ClearPageReserved(virt_to_page(start));
+ set_page_count(virt_to_page(start), 1);
+ free_page(start);
+ totalram_pages++;
+ }
+}
+#endif
+
+void si_meminfo(struct sysinfo *val)
+{
+ val->totalram = max_pfn;
+ val->sharedram = 0;
+ val->freeram = nr_free_pages();
+ val->bufferram = atomic_read(&buffermem_pages);
+ val->totalhigh = max_pfn-max_low_pfn;
+ val->freehigh = nr_free_highpages();
+ val->mem_unit = PAGE_SIZE;
+ return;
+}
+
+#if defined(CONFIG_X86_PAE)
+struct kmem_cache_s *pae_pgd_cachep;
+void __init pgtable_cache_init(void)
+{
+ /*
+ * PAE pgds must be 16-byte aligned:
+ */
+ pae_pgd_cachep = kmem_cache_create("pae_pgd", 32, 0,
+ SLAB_HWCACHE_ALIGN |
SLAB_MUST_HWCACHE_ALIGN, NULL, NULL);
+ if (!pae_pgd_cachep)
+ panic("init_pae(): Cannot alloc pae_pgd SLAB cache");
+}
+#endif /* CONFIG_X86_PAE */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/configs/xenU_defconfig_x86_64
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/configs/xenU_defconfig_x86_64 Fri Jul
15 13:39:50 2005
@@ -0,0 +1,897 @@
+#
+# Automatically generated make config: don't edit
+# Linux kernel version: 2.6.11.10-xenU
+# Mon May 23 15:07:58 2005
+#
+CONFIG_XEN=y
+CONFIG_ARCH_XEN=y
+CONFIG_NO_IDLE_HZ=y
+
+#
+# XEN
+#
+# CONFIG_XEN_PRIVILEGED_GUEST is not set
+# CONFIG_XEN_PHYSDEV_ACCESS is not set
+CONFIG_XEN_BLKDEV_GRANT=y
+CONFIG_XEN_BLKDEV_FRONTEND=y
+CONFIG_XEN_NETDEV_FRONTEND=y
+# CONFIG_XEN_NETDEV_FRONTEND_PIPELINED_TRANSMITTER is not set
+# CONFIG_XEN_BLKDEV_TAP is not set
+# CONFIG_XEN_SHADOW_MODE is not set
+CONFIG_XEN_SCRUB_PAGES=y
+# CONFIG_XEN_X86 is not set
+CONFIG_XEN_X86_64=y
+CONFIG_HAVE_ARCH_DEV_ALLOC_SKB=y
+
+#
+# Code maturity level options
+#
+CONFIG_EXPERIMENTAL=y
+CONFIG_CLEAN_COMPILE=y
+CONFIG_BROKEN_ON_SMP=y
+
+#
+# General setup
+#
+CONFIG_LOCALVERSION=""
+CONFIG_SWAP=y
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_BSD_PROCESS_ACCT=y
+# CONFIG_BSD_PROCESS_ACCT_V3 is not set
+CONFIG_SYSCTL=y
+CONFIG_AUDIT=y
+CONFIG_AUDITSYSCALL=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_HOTPLUG=y
+CONFIG_KOBJECT_UEVENT=y
+# CONFIG_IKCONFIG is not set
+# CONFIG_EMBEDDED is not set
+CONFIG_KALLSYMS=y
+CONFIG_KALLSYMS_EXTRA_PASS=y
+CONFIG_FUTEX=y
+CONFIG_EPOLL=y
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
+CONFIG_SHMEM=y
+CONFIG_CC_ALIGN_FUNCTIONS=0
+CONFIG_CC_ALIGN_LABELS=0
+CONFIG_CC_ALIGN_LOOPS=0
+CONFIG_CC_ALIGN_JUMPS=0
+# CONFIG_TINY_SHMEM is not set
+
+#
+# Loadable module support
+#
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_MODULE_FORCE_UNLOAD is not set
+CONFIG_OBSOLETE_MODPARM=y
+CONFIG_MODVERSIONS=y
+# CONFIG_MODULE_SRCVERSION_ALL is not set
+CONFIG_KMOD=y
+CONFIG_XENARCH="x86_64"
+CONFIG_X86=y
+CONFIG_MMU=y
+CONFIG_GENERIC_ISA_DMA=y
+CONFIG_GENERIC_IOMAP=y
+CONFIG_X86_CMPXCHG=y
+CONFIG_X86_L1_CACHE_SHIFT=7
+CONFIG_RWSEM_GENERIC_SPINLOCK=y
+CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_X86_GOOD_APIC=y
+# CONFIG_HPET_TIMER is not set
+# CONFIG_SMP is not set
+# CONFIG_PREEMPT is not set
+# CONFIG_MICROCODE is not set
+CONFIG_X86_CPUID=y
+# CONFIG_NUMA is not set
+# CONFIG_MTRR is not set
+# CONFIG_X86_LOCAL_APIC is not set
+# CONFIG_X86_IO_APIC is not set
+# CONFIG_PCI is not set
+CONFIG_EARLY_PRINTK=y
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_IRQ_PROBE=y
+
+#
+# X86_64 processor configuration
+#
+CONFIG_X86_64=y
+CONFIG_64BIT=y
+
+#
+# Processor type and features
+#
+CONFIG_MPSC=y
+# CONFIG_GENERIC_CPU is not set
+CONFIG_X86_L1_CACHE_BYTES=128
+# CONFIG_X86_TSC is not set
+# CONFIG_X86_MSR is not set
+CONFIG_DUMMY_IOMMU=y
+# CONFIG_X86_MCE is not set
+
+#
+# Power management options
+#
+# CONFIG_PM is not set
+
+#
+# CPU Frequency scaling
+#
+# CONFIG_CPU_FREQ is not set
+
+#
+# Bus options (PCI etc.)
+#
+# CONFIG_UNORDERED_IO is not set
+
+#
+# Executable file formats / Emulations
+#
+CONFIG_IA32_EMULATION=y
+# CONFIG_IA32_AOUT is not set
+#
+# Executable file formats
+#
+CONFIG_BINFMT_ELF=y
+CONFIG_BINFMT_MISC=y
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+CONFIG_STANDALONE=y
+CONFIG_PREVENT_FIRMWARE_BUILD=y
+CONFIG_FW_LOADER=y
+
+#
+# Block devices
+#
+CONFIG_BLK_DEV_FD=m
+# CONFIG_BLK_DEV_COW_COMMON is not set
+CONFIG_BLK_DEV_LOOP=m
+CONFIG_BLK_DEV_CRYPTOLOOP=m
+CONFIG_BLK_DEV_NBD=m
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=16
+CONFIG_BLK_DEV_RAM_SIZE=16384
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE=""
+CONFIG_LBD=y
+# CONFIG_CDROM_PKTCDVD is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+# CONFIG_ATA_OVER_ETH is not set
+
+#
+# SCSI device support
+#
+CONFIG_SCSI=m
+CONFIG_SCSI_PROC_FS=y
+
+#
+# SCSI support type (disk, tape, CD-ROM)
+#
+CONFIG_BLK_DEV_SD=m
+CONFIG_CHR_DEV_ST=m
+CONFIG_CHR_DEV_OSST=m
+CONFIG_BLK_DEV_SR=m
+CONFIG_BLK_DEV_SR_VENDOR=y
+CONFIG_CHR_DEV_SG=m
+
+#
+# Some SCSI devices (e.g. CD jukebox) support multiple LUNs
+#
+# CONFIG_SCSI_MULTI_LUN is not set
+CONFIG_SCSI_CONSTANTS=y
+CONFIG_SCSI_LOGGING=y
+
+#
+# SCSI Transport Attributes
+#
+CONFIG_SCSI_SPI_ATTRS=m
+CONFIG_SCSI_FC_ATTRS=m
+# CONFIG_SCSI_ISCSI_ATTRS is not set
+
+#
+# SCSI low-level drivers
+#
+CONFIG_SCSI_SATA=y
+# CONFIG_SCSI_DEBUG is not set
+
+#
+# Multi-device support (RAID and LVM)
+#
+CONFIG_MD=y
+CONFIG_BLK_DEV_MD=y
+CONFIG_MD_LINEAR=m
+CONFIG_MD_RAID0=m
+CONFIG_MD_RAID1=m
+CONFIG_MD_RAID10=m
+CONFIG_MD_RAID5=m
+CONFIG_MD_RAID6=m
+CONFIG_MD_MULTIPATH=m
+# CONFIG_MD_FAULTY is not set
+CONFIG_BLK_DEV_DM=m
+CONFIG_DM_CRYPT=m
+CONFIG_DM_SNAPSHOT=m
+CONFIG_DM_MIRROR=m
+CONFIG_DM_ZERO=m
+
+#
+# Networking support
+#
+CONFIG_NET=y
+
+#
+# Networking options
+#
+CONFIG_PACKET=y
+CONFIG_PACKET_MMAP=y
+CONFIG_NETLINK_DEV=y
+CONFIG_UNIX=y
+CONFIG_NET_KEY=m
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_FWMARK=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+# CONFIG_IP_PNP is not set
+CONFIG_NET_IPIP=m
+CONFIG_NET_IPGRE=m
+CONFIG_NET_IPGRE_BROADCAST=y
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+# CONFIG_ARPD is not set
+CONFIG_SYN_COOKIES=y
+CONFIG_INET_AH=m
+CONFIG_INET_ESP=m
+CONFIG_INET_IPCOMP=m
+CONFIG_INET_TUNNEL=m
+CONFIG_IP_TCPDIAG=y
+# CONFIG_IP_TCPDIAG_IPV6 is not set
+
+#
+# IP: Virtual Server Configuration
+#
+CONFIG_IP_VS=m
+# CONFIG_IP_VS_DEBUG is not set
+CONFIG_IP_VS_TAB_BITS=12
+
+#
+# IPVS transport protocol load balancing support
+#
+CONFIG_IP_VS_PROTO_TCP=y
+CONFIG_IP_VS_PROTO_UDP=y
+CONFIG_IP_VS_PROTO_ESP=y
+CONFIG_IP_VS_PROTO_AH=y
+
+#
+# IPVS scheduler
+#
+CONFIG_IP_VS_RR=m
+CONFIG_IP_VS_WRR=m
+CONFIG_IP_VS_LC=m
+CONFIG_IP_VS_WLC=m
+CONFIG_IP_VS_LBLC=m
+CONFIG_IP_VS_LBLCR=m
+CONFIG_IP_VS_DH=m
+CONFIG_IP_VS_SH=m
+CONFIG_IP_VS_SED=m
+CONFIG_IP_VS_NQ=m
+
+#
+# IPVS application helper
+#
+CONFIG_IP_VS_FTP=m
+CONFIG_IPV6=m
+CONFIG_IPV6_PRIVACY=y
+CONFIG_INET6_AH=m
+CONFIG_INET6_ESP=m
+CONFIG_INET6_IPCOMP=m
+CONFIG_INET6_TUNNEL=m
+CONFIG_IPV6_TUNNEL=m
+CONFIG_NETFILTER=y
+# CONFIG_NETFILTER_DEBUG is not set
+CONFIG_BRIDGE_NETFILTER=y
+
+#
+# IP: Netfilter Configuration
+#
+CONFIG_IP_NF_CONNTRACK=m
+CONFIG_IP_NF_CT_ACCT=y
+# CONFIG_IP_NF_CONNTRACK_MARK is not set
+CONFIG_IP_NF_CT_PROTO_SCTP=m
+CONFIG_IP_NF_FTP=m
+CONFIG_IP_NF_IRC=m
+CONFIG_IP_NF_TFTP=m
+CONFIG_IP_NF_AMANDA=m
+CONFIG_IP_NF_QUEUE=m
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_MATCH_LIMIT=m
+CONFIG_IP_NF_MATCH_IPRANGE=m
+CONFIG_IP_NF_MATCH_MAC=m
+CONFIG_IP_NF_MATCH_PKTTYPE=m
+CONFIG_IP_NF_MATCH_MARK=m
+CONFIG_IP_NF_MATCH_MULTIPORT=m
+CONFIG_IP_NF_MATCH_TOS=m
+CONFIG_IP_NF_MATCH_RECENT=m
+CONFIG_IP_NF_MATCH_ECN=m
+CONFIG_IP_NF_MATCH_DSCP=m
+CONFIG_IP_NF_MATCH_AH_ESP=m
+CONFIG_IP_NF_MATCH_LENGTH=m
+CONFIG_IP_NF_MATCH_TTL=m
+CONFIG_IP_NF_MATCH_TCPMSS=m
+CONFIG_IP_NF_MATCH_HELPER=m
+CONFIG_IP_NF_MATCH_STATE=m
+CONFIG_IP_NF_MATCH_CONNTRACK=m
+CONFIG_IP_NF_MATCH_OWNER=m
+CONFIG_IP_NF_MATCH_PHYSDEV=m
+CONFIG_IP_NF_MATCH_ADDRTYPE=m
+CONFIG_IP_NF_MATCH_REALM=m
+CONFIG_IP_NF_MATCH_SCTP=m
+CONFIG_IP_NF_MATCH_COMMENT=m
+# CONFIG_IP_NF_MATCH_HASHLIMIT is not set
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_TARGET_LOG=m
+CONFIG_IP_NF_TARGET_ULOG=m
+CONFIG_IP_NF_TARGET_TCPMSS=m
+CONFIG_IP_NF_NAT=m
+CONFIG_IP_NF_NAT_NEEDED=y
+CONFIG_IP_NF_TARGET_MASQUERADE=m
+CONFIG_IP_NF_TARGET_REDIRECT=m
+CONFIG_IP_NF_TARGET_NETMAP=m
+CONFIG_IP_NF_TARGET_SAME=m
+CONFIG_IP_NF_NAT_SNMP_BASIC=m
+CONFIG_IP_NF_NAT_IRC=m
+CONFIG_IP_NF_NAT_FTP=m
+CONFIG_IP_NF_NAT_TFTP=m
+CONFIG_IP_NF_NAT_AMANDA=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_IP_NF_TARGET_TOS=m
+CONFIG_IP_NF_TARGET_ECN=m
+CONFIG_IP_NF_TARGET_DSCP=m
+CONFIG_IP_NF_TARGET_MARK=m
+CONFIG_IP_NF_TARGET_CLASSIFY=m
+CONFIG_IP_NF_RAW=m
+CONFIG_IP_NF_TARGET_NOTRACK=m
+CONFIG_IP_NF_ARPTABLES=m
+CONFIG_IP_NF_ARPFILTER=m
+CONFIG_IP_NF_ARP_MANGLE=m
+
+#
+# IPv6: Netfilter Configuration
+#
+# CONFIG_IP6_NF_QUEUE is not set
+CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP6_NF_MATCH_LIMIT=m
+CONFIG_IP6_NF_MATCH_MAC=m
+CONFIG_IP6_NF_MATCH_RT=m
+CONFIG_IP6_NF_MATCH_OPTS=m
+CONFIG_IP6_NF_MATCH_FRAG=m
+CONFIG_IP6_NF_MATCH_HL=m
+CONFIG_IP6_NF_MATCH_MULTIPORT=m
+CONFIG_IP6_NF_MATCH_OWNER=m
+CONFIG_IP6_NF_MATCH_MARK=m
+CONFIG_IP6_NF_MATCH_IPV6HEADER=m
+CONFIG_IP6_NF_MATCH_AHESP=m
+CONFIG_IP6_NF_MATCH_LENGTH=m
+CONFIG_IP6_NF_MATCH_EUI64=m
+CONFIG_IP6_NF_MATCH_PHYSDEV=m
+CONFIG_IP6_NF_FILTER=m
+CONFIG_IP6_NF_TARGET_LOG=m
+CONFIG_IP6_NF_MANGLE=m
+CONFIG_IP6_NF_TARGET_MARK=m
+CONFIG_IP6_NF_RAW=m
+
+#
+# Bridge: Netfilter Configuration
+#
+CONFIG_BRIDGE_NF_EBTABLES=m
+CONFIG_BRIDGE_EBT_BROUTE=m
+CONFIG_BRIDGE_EBT_T_FILTER=m
+CONFIG_BRIDGE_EBT_T_NAT=m
+CONFIG_BRIDGE_EBT_802_3=m
+CONFIG_BRIDGE_EBT_AMONG=m
+CONFIG_BRIDGE_EBT_ARP=m
+CONFIG_BRIDGE_EBT_IP=m
+CONFIG_BRIDGE_EBT_LIMIT=m
+CONFIG_BRIDGE_EBT_MARK=m
+CONFIG_BRIDGE_EBT_PKTTYPE=m
+CONFIG_BRIDGE_EBT_STP=m
+CONFIG_BRIDGE_EBT_VLAN=m
+CONFIG_BRIDGE_EBT_ARPREPLY=m
+CONFIG_BRIDGE_EBT_DNAT=m
+CONFIG_BRIDGE_EBT_MARK_T=m
+CONFIG_BRIDGE_EBT_REDIRECT=m
+CONFIG_BRIDGE_EBT_SNAT=m
+CONFIG_BRIDGE_EBT_LOG=m
+# CONFIG_BRIDGE_EBT_ULOG is not set
+CONFIG_XFRM=y
+CONFIG_XFRM_USER=y
+
+#
+# SCTP Configuration (EXPERIMENTAL)
+#
+CONFIG_IP_SCTP=m
+# CONFIG_SCTP_DBG_MSG is not set
+# CONFIG_SCTP_DBG_OBJCNT is not set
+# CONFIG_SCTP_HMAC_NONE is not set
+# CONFIG_SCTP_HMAC_SHA1 is not set
+CONFIG_SCTP_HMAC_MD5=y
+CONFIG_ATM=m
+CONFIG_ATM_CLIP=m
+# CONFIG_ATM_CLIP_NO_ICMP is not set
+CONFIG_ATM_LANE=m
+# CONFIG_ATM_MPOA is not set
+CONFIG_ATM_BR2684=m
+# CONFIG_ATM_BR2684_IPFILTER is not set
+CONFIG_BRIDGE=m
+CONFIG_VLAN_8021Q=m
+# CONFIG_DECNET is not set
+CONFIG_LLC=m
+# CONFIG_LLC2 is not set
+CONFIG_IPX=m
+# CONFIG_IPX_INTERN is not set
+CONFIG_ATALK=m
+CONFIG_DEV_APPLETALK=y
+CONFIG_IPDDP=m
+CONFIG_IPDDP_ENCAP=y
+CONFIG_IPDDP_DECAP=y
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+CONFIG_NET_DIVERT=y
+# CONFIG_ECONET is not set
+CONFIG_WAN_ROUTER=m
+
+#
+# QoS and/or fair queueing
+#
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_CLK_JIFFIES=y
+# CONFIG_NET_SCH_CLK_GETTIMEOFDAY is not set
+# CONFIG_NET_SCH_CLK_CPU is not set
+CONFIG_NET_SCH_CBQ=m
+CONFIG_NET_SCH_HTB=m
+CONFIG_NET_SCH_HFSC=m
+CONFIG_NET_SCH_ATM=m
+CONFIG_NET_SCH_PRIO=m
+CONFIG_NET_SCH_RED=m
+CONFIG_NET_SCH_SFQ=m
+CONFIG_NET_SCH_TEQL=m
+CONFIG_NET_SCH_TBF=m
+CONFIG_NET_SCH_GRED=m
+CONFIG_NET_SCH_DSMARK=m
+CONFIG_NET_SCH_NETEM=m
+CONFIG_NET_SCH_INGRESS=m
+CONFIG_NET_QOS=y
+CONFIG_NET_ESTIMATOR=y
+CONFIG_NET_CLS=y
+CONFIG_NET_CLS_TCINDEX=m
+CONFIG_NET_CLS_ROUTE4=m
+CONFIG_NET_CLS_ROUTE=y
+CONFIG_NET_CLS_FW=m
+CONFIG_NET_CLS_U32=m
+CONFIG_CLS_U32_PERF=y
+CONFIG_NET_CLS_IND=y
+# CONFIG_CLS_U32_MARK is not set
+CONFIG_NET_CLS_RSVP=m
+CONFIG_NET_CLS_RSVP6=m
+# CONFIG_NET_CLS_ACT is not set
+CONFIG_NET_CLS_POLICE=y
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+CONFIG_NETPOLL=y
+# CONFIG_NETPOLL_RX is not set
+CONFIG_NETPOLL_TRAP=y
+CONFIG_NET_POLL_CONTROLLER=y
+# CONFIG_HAMRADIO is not set
+CONFIG_IRDA=m
+
+#
+# IrDA protocols
+#
+CONFIG_IRLAN=m
+CONFIG_IRNET=m
+CONFIG_IRCOMM=m
+# CONFIG_IRDA_ULTRA is not set
+
+#
+# IrDA options
+#
+CONFIG_IRDA_CACHE_LAST_LSAP=y
+CONFIG_IRDA_FAST_RR=y
+# CONFIG_IRDA_DEBUG is not set
+
+#
+# Infrared-port device drivers
+#
+
+#
+# SIR device drivers
+#
+CONFIG_IRTTY_SIR=m
+
+#
+# Dongle support
+#
+CONFIG_DONGLE=y
+CONFIG_ESI_DONGLE=m
+CONFIG_ACTISYS_DONGLE=m
+CONFIG_TEKRAM_DONGLE=m
+CONFIG_LITELINK_DONGLE=m
+CONFIG_MA600_DONGLE=m
+CONFIG_GIRBIL_DONGLE=m
+CONFIG_MCP2120_DONGLE=m
+CONFIG_OLD_BELKIN_DONGLE=m
+CONFIG_ACT200L_DONGLE=m
+
+#
+# Old SIR device drivers
+#
+# CONFIG_IRPORT_SIR is not set
+
+#
+# Old Serial dongle support
+#
+
+#
+# FIR device drivers
+#
+CONFIG_BT=m
+CONFIG_BT_L2CAP=m
+CONFIG_BT_SCO=m
+CONFIG_BT_RFCOMM=m
+CONFIG_BT_RFCOMM_TTY=y
+CONFIG_BT_BNEP=m
+CONFIG_BT_BNEP_MC_FILTER=y
+CONFIG_BT_BNEP_PROTO_FILTER=y
+CONFIG_BT_HIDP=m
+
+#
+# Bluetooth device drivers
+#
+CONFIG_BT_HCIUART=m
+CONFIG_BT_HCIUART_H4=y
+CONFIG_BT_HCIUART_BCSP=y
+CONFIG_BT_HCIUART_BCSP_TXCRC=y
+CONFIG_BT_HCIVHCI=m
+CONFIG_NETDEVICES=y
+CONFIG_DUMMY=m
+CONFIG_BONDING=m
+CONFIG_EQUALIZER=m
+CONFIG_TUN=m
+CONFIG_ETHERTAP=m
+
+#
+# Ethernet (10 or 100Mbit)
+#
+CONFIG_NET_ETHERNET=y
+CONFIG_MII=m
+
+#
+# Ethernet (1000 Mbit)
+#
+
+#
+# Ethernet (10000 Mbit)
+#
+
+#
+# Token Ring devices
+#
+
+#
+# Wireless LAN (non-hamradio)
+#
+CONFIG_NET_RADIO=y
+
+#
+# Obsolete Wireless cards support (pre-802.11)
+#
+# CONFIG_STRIP is not set
+CONFIG_ATMEL=m
+
+#
+# Wan interfaces
+#
+# CONFIG_WAN is not set
+
+#
+# ATM drivers
+#
+CONFIG_ATM_TCP=m
+CONFIG_PPP=m
+CONFIG_PPP_MULTILINK=y
+CONFIG_PPP_FILTER=y
+CONFIG_PPP_ASYNC=m
+CONFIG_PPP_SYNC_TTY=m
+CONFIG_PPP_DEFLATE=m
+# CONFIG_PPP_BSDCOMP is not set
+CONFIG_PPPOE=m
+CONFIG_PPPOATM=m
+# CONFIG_SLIP is not set
+# CONFIG_SHAPER is not set
+CONFIG_NETCONSOLE=m
+CONFIG_INPUT=m
+CONFIG_UNIX98_PTYS=y
+# CONFIG_LEGACY_PTYS is not set
+
+#
+# Character devices
+#
+
+#
+# File systems
+#
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_EXT2_FS_POSIX_ACL=y
+CONFIG_EXT2_FS_SECURITY=y
+CONFIG_EXT3_FS=m
+CONFIG_EXT3_FS_XATTR=y
+CONFIG_EXT3_FS_POSIX_ACL=y
+CONFIG_EXT3_FS_SECURITY=y
+CONFIG_JBD=m
+# CONFIG_JBD_DEBUG is not set
+CONFIG_FS_MBCACHE=y
+CONFIG_REISERFS_FS=m
+# CONFIG_REISERFS_CHECK is not set
+CONFIG_REISERFS_PROC_INFO=y
+CONFIG_REISERFS_FS_XATTR=y
+CONFIG_REISERFS_FS_POSIX_ACL=y
+CONFIG_REISERFS_FS_SECURITY=y
+CONFIG_JFS_FS=m
+CONFIG_JFS_POSIX_ACL=y
+# CONFIG_JFS_SECURITY is not set
+# CONFIG_JFS_DEBUG is not set
+# CONFIG_JFS_STATISTICS is not set
+CONFIG_FS_POSIX_ACL=y
+
+#
+# XFS support
+#
+CONFIG_XFS_FS=m
+CONFIG_XFS_EXPORT=y
+# CONFIG_XFS_RT is not set
+CONFIG_XFS_QUOTA=y
+CONFIG_XFS_SECURITY=y
+CONFIG_XFS_POSIX_ACL=y
+CONFIG_MINIX_FS=m
+CONFIG_ROMFS_FS=m
+CONFIG_QUOTA=y
+# CONFIG_QFMT_V1 is not set
+CONFIG_QFMT_V2=y
+CONFIG_QUOTACTL=y
+CONFIG_DNOTIFY=y
+CONFIG_AUTOFS_FS=m
+CONFIG_AUTOFS4_FS=m
+
+#
+# CD-ROM/DVD Filesystems
+#
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+CONFIG_ZISOFS_FS=y
+CONFIG_UDF_FS=m
+CONFIG_UDF_NLS=y
+
+#
+# DOS/FAT/NT Filesystems
+#
+CONFIG_FAT_FS=m
+CONFIG_MSDOS_FS=m
+CONFIG_VFAT_FS=m
+CONFIG_FAT_DEFAULT_CODEPAGE=437
+CONFIG_FAT_DEFAULT_IOCHARSET="ascii"
+# CONFIG_NTFS_FS is not set
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_SYSFS=y
+# CONFIG_DEVFS_FS is not set
+CONFIG_DEVPTS_FS_XATTR=y
+CONFIG_DEVPTS_FS_SECURITY=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_XATTR=y
+CONFIG_TMPFS_SECURITY=y
+# CONFIG_HUGETLBFS is not set
+# CONFIG_HUGETLB_PAGE is not set
+CONFIG_RAMFS=y
+
+#
+# Miscellaneous filesystems
+#
+# CONFIG_ADFS_FS is not set
+CONFIG_AFFS_FS=m
+CONFIG_HFS_FS=m
+CONFIG_HFSPLUS_FS=m
+CONFIG_BEFS_FS=m
+# CONFIG_BEFS_DEBUG is not set
+CONFIG_BFS_FS=m
+CONFIG_EFS_FS=m
+CONFIG_CRAMFS=m
+CONFIG_VXFS_FS=m
+# CONFIG_HPFS_FS is not set
+CONFIG_QNX4FS_FS=m
+CONFIG_SYSV_FS=m
+CONFIG_UFS_FS=m
+# CONFIG_UFS_FS_WRITE is not set
+
+#
+# Network File Systems
+#
+CONFIG_NFS_FS=m
+CONFIG_NFS_V3=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_DIRECTIO=y
+CONFIG_NFSD=m
+CONFIG_NFSD_V3=y
+CONFIG_NFSD_V4=y
+CONFIG_NFSD_TCP=y
+CONFIG_LOCKD=m
+CONFIG_LOCKD_V4=y
+CONFIG_EXPORTFS=m
+CONFIG_SUNRPC=m
+CONFIG_SUNRPC_GSS=m
+CONFIG_RPCSEC_GSS_KRB5=m
+CONFIG_RPCSEC_GSS_SPKM3=m
+CONFIG_SMB_FS=m
+# CONFIG_SMB_NLS_DEFAULT is not set
+CONFIG_CIFS=m
+# CONFIG_CIFS_STATS is not set
+CONFIG_CIFS_XATTR=y
+CONFIG_CIFS_POSIX=y
+# CONFIG_CIFS_EXPERIMENTAL is not set
+CONFIG_NCP_FS=m
+CONFIG_NCPFS_PACKET_SIGNING=y
+CONFIG_NCPFS_IOCTL_LOCKING=y
+CONFIG_NCPFS_STRONG=y
+CONFIG_NCPFS_NFS_NS=y
+CONFIG_NCPFS_OS2_NS=y
+CONFIG_NCPFS_SMALLDOS=y
+CONFIG_NCPFS_NLS=y
+CONFIG_NCPFS_EXTRAS=y
+# CONFIG_CODA_FS is not set
+# CONFIG_AFS_FS is not set
+
+#
+# Partition Types
+#
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_ACORN_PARTITION is not set
+CONFIG_OSF_PARTITION=y
+# CONFIG_AMIGA_PARTITION is not set
+# CONFIG_ATARI_PARTITION is not set
+CONFIG_MAC_PARTITION=y
+CONFIG_MSDOS_PARTITION=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_MINIX_SUBPARTITION=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_UNIXWARE_DISKLABEL=y
+# CONFIG_LDM_PARTITION is not set
+CONFIG_SGI_PARTITION=y
+# CONFIG_ULTRIX_PARTITION is not set
+CONFIG_SUN_PARTITION=y
+CONFIG_EFI_PARTITION=y
+
+#
+# Native Language Support
+#
+CONFIG_NLS=y
+CONFIG_NLS_DEFAULT="utf8"
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_CODEPAGE_737=m
+CONFIG_NLS_CODEPAGE_775=m
+CONFIG_NLS_CODEPAGE_850=m
+CONFIG_NLS_CODEPAGE_852=m
+CONFIG_NLS_CODEPAGE_855=m
+CONFIG_NLS_CODEPAGE_857=m
+CONFIG_NLS_CODEPAGE_860=m
+CONFIG_NLS_CODEPAGE_861=m
+CONFIG_NLS_CODEPAGE_862=m
+CONFIG_NLS_CODEPAGE_863=m
+CONFIG_NLS_CODEPAGE_864=m
+CONFIG_NLS_CODEPAGE_865=m
+CONFIG_NLS_CODEPAGE_866=m
+CONFIG_NLS_CODEPAGE_869=m
+CONFIG_NLS_CODEPAGE_936=m
+CONFIG_NLS_CODEPAGE_950=m
+CONFIG_NLS_CODEPAGE_932=m
+CONFIG_NLS_CODEPAGE_949=m
+CONFIG_NLS_CODEPAGE_874=m
+CONFIG_NLS_ISO8859_8=m
+CONFIG_NLS_CODEPAGE_1250=m
+CONFIG_NLS_CODEPAGE_1251=m
+CONFIG_NLS_ASCII=y
+CONFIG_NLS_ISO8859_1=m
+CONFIG_NLS_ISO8859_2=m
+CONFIG_NLS_ISO8859_3=m
+CONFIG_NLS_ISO8859_4=m
+CONFIG_NLS_ISO8859_5=m
+CONFIG_NLS_ISO8859_6=m
+CONFIG_NLS_ISO8859_7=m
+CONFIG_NLS_ISO8859_9=m
+CONFIG_NLS_ISO8859_13=m
+CONFIG_NLS_ISO8859_14=m
+CONFIG_NLS_ISO8859_15=m
+CONFIG_NLS_KOI8_R=m
+CONFIG_NLS_KOI8_U=m
+CONFIG_NLS_UTF8=m
+
+#
+# Security options
+#
+# CONFIG_KEYS is not set
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_CAPABILITIES=y
+# CONFIG_SECURITY_SECLVL is not set
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=1
+CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_SECURITY_SELINUX_DEVELOP=y
+CONFIG_SECURITY_SELINUX_AVC_STATS=y
+# CONFIG_SECURITY_SELINUX_MLS is not set
+
+#
+# Cryptographic options
+#
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_NULL=m
+CONFIG_CRYPTO_MD4=m
+CONFIG_CRYPTO_MD5=m
+CONFIG_CRYPTO_SHA1=y
+CONFIG_CRYPTO_SHA256=m
+CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_DES=m
+CONFIG_CRYPTO_BLOWFISH=m
+CONFIG_CRYPTO_TWOFISH=m
+CONFIG_CRYPTO_SERPENT=m
+# CONFIG_CRYPTO_AES is not set
+CONFIG_CRYPTO_CAST5=m
+CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_TEA=m
+CONFIG_CRYPTO_ARC4=m
+CONFIG_CRYPTO_KHAZAD=m
+# CONFIG_CRYPTO_ANUBIS is not set
+CONFIG_CRYPTO_DEFLATE=m
+CONFIG_CRYPTO_MICHAEL_MIC=m
+CONFIG_CRYPTO_CRC32C=m
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Hardware crypto devices
+#
+
+#
+# Library routines
+#
+CONFIG_CRC_CCITT=m
+CONFIG_CRC32=y
+CONFIG_LIBCRC32C=m
+CONFIG_ZLIB_INFLATE=y
+CONFIG_ZLIB_DEFLATE=m
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/lib/delay.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/lib/delay.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,52 @@
+/*
+ * Precise Delay Loops for i386
+ *
+ * Copyright (C) 1993 Linus Torvalds
+ * Copyright (C) 1997 Martin Mares <mj@xxxxxxxxxxxxxxxxxxxxxxxx>
+ *
+ * The __delay function must _NOT_ be inlined as its execution time
+ * depends wildly on alignment on many x86 processors. The additional
+ * jump magic is needed to get the timing stable on all the CPU's
+ * we have to worry about.
+ */
+
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <asm/processor.h>
+#include <asm/delay.h>
+
+#ifdef CONFIG_SMP
+#include <asm/smp.h>
+#endif
+
+void __delay(unsigned long loops)
+{
+ unsigned long bclock, now;
+
+ rdtscl(bclock);
+ do
+ {
+ rep_nop();
+ rdtscl(now);
+ } while ((now-bclock) < loops);
+}
+
+inline void __const_udelay(unsigned long xloops)
+{
+ int d0;
+ __asm__("mull %0"
+ :"=d" (xloops), "=&a" (d0)
+ :"1" (xloops),"0" (current_cpu_data.loops_per_jiffy));
+ __delay(xloops * HZ);
+}
+
+void __udelay(unsigned long usecs)
+{
+ __const_udelay(usecs * 0x000010c6); /* 2**32 / 1000000 */
+}
+
+void __ndelay(unsigned long nsecs)
+{
+ __const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/drivers/char/tty_io.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/drivers/char/tty_io.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,2891 @@
+/*
+ * linux/drivers/char/tty_io.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+/*
+ * 'tty_io.c' gives an orthogonal feeling to tty's, be they consoles
+ * or rs-channels. It also implements echoing, cooked mode etc.
+ *
+ * Kill-line thanks to John T Kohl, who also corrected VMIN = VTIME = 0.
+ *
+ * Modified by Theodore Ts'o, 9/14/92, to dynamically allocate the
+ * tty_struct and tty_queue structures. Previously there was an array
+ * of 256 tty_struct's which was statically allocated, and the
+ * tty_queue structures were allocated at boot time. Both are now
+ * dynamically allocated only when the tty is open.
+ *
+ * Also restructured routines so that there is more of a separation
+ * between the high-level tty routines (tty_io.c and tty_ioctl.c) and
+ * the low-level tty routines (serial.c, pty.c, console.c). This
+ * makes for cleaner and more compact code. -TYT, 9/17/92
+ *
+ * Modified by Fred N. van Kempen, 01/29/93, to add line disciplines
+ * which can be dynamically activated and de-activated by the line
+ * discipline handling modules (like SLIP).
+ *
+ * NOTE: pay no attention to the line discipline code (yet); its
+ * interface is still subject to change in this version...
+ * -- TYT, 1/31/92
+ *
+ * Added functionality to the OPOST tty handling. No delays, but all
+ * other bits should be there.
+ * -- Nick Holloway <alfie@xxxxxxxxxxxxxxxxx>, 27th May 1993.
+ *
+ * Rewrote canonical mode and added more termios flags.
+ * -- julian@xxxxxxxxxxxxxxxxxxxxxx (J. Cowley), 13Jan94
+ *
+ * Reorganized FASYNC support so mouse code can share it.
+ * -- ctm@xxxxxxxx, 9Sep95
+ *
+ * New TIOCLINUX variants added.
+ * -- mj@xxxxxxxxxxxxxxxxx, 19-Nov-95
+ *
+ * Restrict vt switching via ioctl()
+ * -- grif@xxxxxxxxxx, 5-Dec-95
+ *
+ * Move console and virtual terminal code to more appropriate files,
+ * implement CONFIG_VT and generalize console device interface.
+ * -- Marko Kohtala <Marko.Kohtala@xxxxxx>, March 97
+ *
+ * Rewrote init_dev and release_dev to eliminate races.
+ * -- Bill Hawes <whawes@xxxxxxxx>, June 97
+ *
+ * Added devfs support.
+ * -- C. Scott Ananian <cananian@xxxxxxxxxxxxxxxxxxxx>, 13-Jan-1998
+ *
+ * Added support for a Unix98-style ptmx device.
+ * -- C. Scott Ananian <cananian@xxxxxxxxxxxxxxxxxxxx>, 14-Jan-1998
+ *
+ * Reduced memory usage for older ARM systems
+ * -- Russell King <rmk@xxxxxxxxxxxxxxxx>
+ *
+ * Move do_SAK() into process context. Less stack use in devfs functions.
+ * alloc_tty_struct() always uses kmalloc() -- Andrew Morton
<andrewm@xxxxxxxxxx> 17Mar01
+ */
+
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/major.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/fcntl.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/tty.h>
+#include <linux/tty_driver.h>
+#include <linux/tty_flip.h>
+#include <linux/devpts_fs.h>
+#include <linux/file.h>
+#include <linux/console.h>
+#include <linux/timer.h>
+#include <linux/ctype.h>
+#include <linux/kd.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/poll.h>
+#include <linux/proc_fs.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/smp_lock.h>
+
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/bitops.h>
+
+#include <linux/kbd_kern.h>
+#include <linux/vt_kern.h>
+#include <linux/selection.h>
+#include <linux/devfs_fs_kernel.h>
+
+#include <linux/kmod.h>
+
+#ifdef CONFIG_XEN_CONSOLE
+extern void xen_console_init(void);
+#endif
+
+#ifdef CONFIG_VT
+extern void con_init_devfs (void);
+#endif
+
+extern void disable_early_printk(void);
+
+#define CONSOLE_DEV MKDEV(TTY_MAJOR,0)
+#define TTY_DEV MKDEV(TTYAUX_MAJOR,0)
+#define SYSCONS_DEV MKDEV(TTYAUX_MAJOR,1)
+#define PTMX_DEV MKDEV(TTYAUX_MAJOR,2)
+
+#undef TTY_DEBUG_HANGUP
+
+#define TTY_PARANOIA_CHECK 1
+#define CHECK_TTY_COUNT 1
+
+struct termios tty_std_termios; /* for the benefit of tty
drivers */
+struct tty_driver *tty_drivers; /* linked list of tty drivers */
+
+#ifdef CONFIG_UNIX98_PTYS
+extern struct tty_driver ptm_driver[]; /* Unix98 pty masters; for /dev/ptmx */
+extern struct tty_driver pts_driver[]; /* Unix98 pty slaves; for /dev/ptmx */
+#endif
+
+static void initialize_tty_struct(struct tty_struct *tty);
+
+static ssize_t tty_read(struct file *, char *, size_t, loff_t *);
+static ssize_t tty_write(struct file *, const char *, size_t, loff_t *);
+static unsigned int tty_poll(struct file *, poll_table *);
+static int tty_open(struct inode *, struct file *);
+static int tty_release(struct inode *, struct file *);
+int tty_ioctl(struct inode * inode, struct file * file,
+ unsigned int cmd, unsigned long arg);
+static int tty_fasync(int fd, struct file * filp, int on);
+extern int vme_scc_init (void);
+extern long vme_scc_console_init(void);
+extern int serial167_init(void);
+extern long serial167_console_init(void);
+extern void console_8xx_init(void);
+extern void au1x00_serial_console_init(void);
+extern int rs_8xx_init(void);
+extern void mac_scc_console_init(void);
+extern void hwc_console_init(void);
+extern void hwc_tty_init(void);
+extern void con3215_init(void);
+extern void tty3215_init(void);
+extern void tub3270_con_init(void);
+extern void tub3270_init(void);
+extern void rs285_console_init(void);
+extern void sa1100_rs_console_init(void);
+extern void sgi_serial_console_init(void);
+extern void sn_sal_serial_console_init(void);
+extern void sci_console_init(void);
+extern void dec_serial_console_init(void);
+extern void tx3912_console_init(void);
+extern void tx3912_rs_init(void);
+extern void txx927_console_init(void);
+extern void txx9_rs_init(void);
+extern void txx9_serial_console_init(void);
+extern void sb1250_serial_console_init(void);
+extern void arc_console_init(void);
+extern int hvc_console_init(void);
+
+#ifndef MIN
+#define MIN(a,b) ((a) < (b) ? (a) : (b))
+#endif
+#ifndef MAX
+#define MAX(a,b) ((a) < (b) ? (b) : (a))
+#endif
+
+static struct tty_struct *alloc_tty_struct(void)
+{
+ struct tty_struct *tty;
+
+ tty = kmalloc(sizeof(struct tty_struct), GFP_KERNEL);
+ if (tty)
+ memset(tty, 0, sizeof(struct tty_struct));
+ return tty;
+}
+
+static inline void free_tty_struct(struct tty_struct *tty)
+{
+ kfree(tty);
+}
+
+/*
+ * This routine returns the name of tty.
+ */
+static char *
+_tty_make_name(struct tty_struct *tty, const char *name, char *buf)
+{
+ int idx = (tty)?MINOR(tty->device) - tty->driver.minor_start:0;
+
+ if (!tty) /* Hmm. NULL pointer. That's fun. */
+ strcpy(buf, "NULL tty");
+ else
+ sprintf(buf, name,
+ idx + tty->driver.name_base);
+
+ return buf;
+}
+
+#define TTY_NUMBER(tty) (MINOR((tty)->device) - (tty)->driver.minor_start + \
+ (tty)->driver.name_base)
+
+char *tty_name(struct tty_struct *tty, char *buf)
+{
+ return _tty_make_name(tty, (tty)?tty->driver.name:NULL, buf);
+}
+
+inline int tty_paranoia_check(struct tty_struct *tty, kdev_t device,
+ const char *routine)
+{
+#ifdef TTY_PARANOIA_CHECK
+ static const char badmagic[] = KERN_WARNING
+ "Warning: bad magic number for tty struct (%s) in %s\n";
+ static const char badtty[] = KERN_WARNING
+ "Warning: null TTY for (%s) in %s\n";
+
+ if (!tty) {
+ printk(badtty, kdevname(device), routine);
+ return 1;
+ }
+ if (tty->magic != TTY_MAGIC) {
+ printk(badmagic, kdevname(device), routine);
+ return 1;
+ }
+#endif
+ return 0;
+}
+
+static int check_tty_count(struct tty_struct *tty, const char *routine)
+{
+#ifdef CHECK_TTY_COUNT
+ struct list_head *p;
+ int count = 0;
+
+ file_list_lock();
+ for(p = tty->tty_files.next; p != &tty->tty_files; p = p->next) {
+ if(list_entry(p, struct file, f_list)->private_data == tty)
+ count++;
+ }
+ file_list_unlock();
+ if (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver.subtype == PTY_TYPE_SLAVE &&
+ tty->link && tty->link->count)
+ count++;
+ if (tty->count != count) {
+ printk(KERN_WARNING "Warning: dev (%s) tty->count(%d) "
+ "!= #fd's(%d) in %s\n",
+ kdevname(tty->device), tty->count, count, routine);
+ return count;
+ }
+#endif
+ return 0;
+}
+
+/*
+ * This is probably overkill for real world processors but
+ * they are not on hot paths so a little discipline won't do
+ * any harm.
+ */
+
+static void tty_set_termios_ldisc(struct tty_struct *tty, int num)
+{
+ down(&tty->termios_sem);
+ tty->termios->c_line = num;
+ up(&tty->termios_sem);
+}
+
+/*
+ * This guards the refcounted line discipline lists. The lock
+ * must be taken with irqs off because there are hangup path
+ * callers who will do ldisc lookups and cannot sleep.
+ */
+
+spinlock_t tty_ldisc_lock = SPIN_LOCK_UNLOCKED;
+DECLARE_WAIT_QUEUE_HEAD(tty_ldisc_wait);
+struct tty_ldisc tty_ldiscs[NR_LDISCS]; /* line disc dispatch table */
+
+int tty_register_ldisc(int disc, struct tty_ldisc *new_ldisc)
+{
+
+ unsigned long flags;
+ int ret = 0;
+
+ if (disc < N_TTY || disc >= NR_LDISCS)
+ return -EINVAL;
+
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ if (new_ldisc) {
+ tty_ldiscs[disc] = *new_ldisc;
+ tty_ldiscs[disc].num = disc;
+ tty_ldiscs[disc].flags |= LDISC_FLAG_DEFINED;
+ tty_ldiscs[disc].refcount = 0;
+ } else {
+ if(tty_ldiscs[disc].refcount)
+ ret = -EBUSY;
+ else
+ tty_ldiscs[disc].flags &= ~LDISC_FLAG_DEFINED;
+ }
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+
+ return ret;
+
+}
+
+
+EXPORT_SYMBOL(tty_register_ldisc);
+
+struct tty_ldisc *tty_ldisc_get(int disc)
+{
+ unsigned long flags;
+ struct tty_ldisc *ld;
+
+ if (disc < N_TTY || disc >= NR_LDISCS)
+ return NULL;
+
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+
+ ld = &tty_ldiscs[disc];
+ /* Check the entry is defined */
+ if(ld->flags & LDISC_FLAG_DEFINED)
+ ld->refcount++;
+ else
+ ld = NULL;
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+ return ld;
+}
+
+EXPORT_SYMBOL_GPL(tty_ldisc_get);
+
+void tty_ldisc_put(int disc)
+{
+ struct tty_ldisc *ld;
+ unsigned long flags;
+
+ if (disc < N_TTY || disc >= NR_LDISCS)
+ BUG();
+
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ ld = &tty_ldiscs[disc];
+ if(ld->refcount <= 0)
+ BUG();
+ ld->refcount--;
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+}
+
+EXPORT_SYMBOL_GPL(tty_ldisc_put);
+
+void tty_ldisc_assign(struct tty_struct *tty, struct tty_ldisc *ld)
+{
+ tty->ldisc = *ld;
+ tty->ldisc.refcount = 0;
+}
+
+/**
+ * tty_ldisc_try - internal helper
+ * @tty: the tty
+ *
+ * Make a single attempt to grab and bump the refcount on
+ * the tty ldisc. Return 0 on failure or 1 on success. This is
+ * used to implement both the waiting and non waiting versions
+ * of tty_ldisc_ref
+ */
+
+static int tty_ldisc_try(struct tty_struct *tty)
+{
+ unsigned long flags;
+ struct tty_ldisc *ld;
+ int ret = 0;
+
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ ld = &tty->ldisc;
+ if(test_bit(TTY_LDISC, &tty->flags))
+ {
+ ld->refcount++;
+ ret = 1;
+ }
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+ return ret;
+}
+
+/**
+ * tty_ldisc_ref_wait - wait for the tty ldisc
+ * @tty: tty device
+ *
+ * Dereference the line discipline for the terminal and take a
+ * reference to it. If the line discipline is in flux then
+ * wait patiently until it changes.
+ *
+ * Note: Must not be called from an IRQ/timer context. The caller
+ * must also be careful not to hold other locks that will deadlock
+ * against a discipline change, such as an existing ldisc reference
+ * (which we check for)
+ */
+
+struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *tty)
+{
+ /* wait_event is a macro */
+ wait_event(tty_ldisc_wait, tty_ldisc_try(tty));
+ return &tty->ldisc;
+}
+
+EXPORT_SYMBOL_GPL(tty_ldisc_ref_wait);
+
+/**
+ * tty_ldisc_ref - get the tty ldisc
+ * @tty: tty device
+ *
+ * Dereference the line discipline for the terminal and take a
+ * reference to it. If the line discipline is in flux then
+ * return NULL. Can be called from IRQ and timer functions.
+ */
+
+struct tty_ldisc *tty_ldisc_ref(struct tty_struct *tty)
+{
+ if(tty_ldisc_try(tty))
+ return &tty->ldisc;
+ return NULL;
+}
+
+EXPORT_SYMBOL_GPL(tty_ldisc_ref);
+
+
+void tty_ldisc_deref(struct tty_ldisc *ld)
+{
+
+ unsigned long flags;
+
+ if(ld == NULL)
+ BUG();
+
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ if(ld->refcount == 0)
+ printk(KERN_EMERG "tty_ldisc_deref: no references.\n");
+ else
+ ld->refcount--;
+ if(ld->refcount == 0)
+ wake_up(&tty_ldisc_wait);
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+}
+
+EXPORT_SYMBOL_GPL(tty_ldisc_deref);
+
+/**
+ * tty_ldisc_enable - allow ldisc use
+ * @tty: terminal to activate ldisc on
+ *
+ * Set the TTY_LDISC flag when the line discipline can be called
+ * again. Do neccessary wakeups for existing sleepers.
+ *
+ * Note: nobody should set this bit except via this function. Clearing
+ * directly is allowed.
+ */
+
+static void tty_ldisc_enable(struct tty_struct *tty)
+{
+ set_bit(TTY_LDISC, &tty->flags);
+ wake_up(&tty_ldisc_wait);
+}
+
+/**
+ * tty_set_ldisc - set line discipline
+ * @tty: the terminal to set
+ * @ldisc: the line discipline
+ *
+ * Set the discipline of a tty line. Must be called from a process
+ * context.
+ */
+
+static int tty_set_ldisc(struct tty_struct *tty, int ldisc)
+{
+ int retval = 0;
+ struct tty_ldisc o_ldisc;
+ char buf[64];
+ unsigned long flags;
+ struct tty_ldisc *ld;
+
+ if ((ldisc < N_TTY) || (ldisc >= NR_LDISCS))
+ return -EINVAL;
+
+restart:
+
+ if (tty->ldisc.num == ldisc)
+ return 0; /* We are already in the desired discipline */
+
+ ld = tty_ldisc_get(ldisc);
+ /* Eduardo Blanco <ejbs@xxxxxxxxxxxx> */
+ /* Cyrus Durgin <cider@xxxxxxxxxxxxx> */
+ if (ld == NULL)
+ {
+ char modname [20];
+ sprintf(modname, "tty-ldisc-%d", ldisc);
+ request_module (modname);
+ ld = tty_ldisc_get(ldisc);
+ }
+
+ if (ld == NULL)
+ return -EINVAL;
+
+
+ o_ldisc = tty->ldisc;
+ tty_wait_until_sent(tty, 0);
+
+ /*
+ * Make sure we don't change while someone holds a
+ * reference to the line discipline. The TTY_LDISC bit
+ * prevents anyone taking a reference once it is clear.
+ * We need the lock to avoid racing reference takers.
+ */
+
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ if(tty->ldisc.refcount)
+ {
+ /* Free the new ldisc we grabbed. Must drop the lock
+ first. */
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+ tty_ldisc_put(ldisc);
+ /*
+ * There are several reasons we may be busy, including
+ * random momentary I/O traffic. We must therefore
+ * retry. We could distinguish between blocking ops
+ * and retries if we made tty_ldisc_wait() smarter. That
+ * is up for discussion.
+ */
+ if(wait_event_interruptible(tty_ldisc_wait, tty->ldisc.refcount
== 0) < 0)
+ return -ERESTARTSYS;
+ goto restart;
+ }
+ clear_bit(TTY_LDISC, &tty->flags);
+ clear_bit(TTY_DONT_FLIP, &tty->flags);
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+
+ /*
+ * From this point on we know nobody has an ldisc
+ * usage reference, nor can they obtain one until
+ * we say so later on.
+ */
+
+ /*
+ * Wait for ->hangup_work and ->flip.work handlers to terminate
+ */
+ run_task_queue(&tq_timer);
+ flush_scheduled_tasks();
+
+ /* Shutdown the current discipline. */
+ if (tty->ldisc.close)
+ (tty->ldisc.close)(tty);
+
+ /* Now set up the new line discipline. */
+ tty_ldisc_assign(tty, ld);
+ tty_set_termios_ldisc(tty, ldisc);
+ if (tty->ldisc.open)
+ retval = (tty->ldisc.open)(tty);
+ if (retval < 0) {
+ tty_ldisc_put(ldisc);
+ /* There is an outstanding reference here so this is safe */
+ tty_ldisc_assign(tty, tty_ldisc_get(o_ldisc.num));
+ tty_set_termios_ldisc(tty, tty->ldisc.num);
+ if (tty->ldisc.open && (tty->ldisc.open(tty) < 0)) {
+ tty_ldisc_put(o_ldisc.num);
+ /* This driver is always present */
+ tty_ldisc_assign(tty, tty_ldisc_get(N_TTY));
+ tty_set_termios_ldisc(tty, N_TTY);
+ if (tty->ldisc.open) {
+ int r = tty->ldisc.open(tty);
+
+ if (r < 0)
+ panic("Couldn't open N_TTY ldisc for "
+ "%s --- error %d.",
+ tty_name(tty, buf), r);
+ }
+ }
+ }
+ /* At this point we hold a reference to the new ldisc and a
+ reference to the old ldisc. If we ended up flipping back
+ to the existing ldisc we have two references to it */
+
+ if (tty->ldisc.num != o_ldisc.num && tty->driver.set_ldisc)
+ tty->driver.set_ldisc(tty);
+
+ tty_ldisc_put(o_ldisc.num);
+
+ /*
+ * Allow ldisc referencing to occur as soon as the driver
+ * ldisc callback completes.
+ */
+ tty_ldisc_enable(tty);
+
+ return retval;
+}
+
+/*
+ * This routine returns a tty driver structure, given a device number
+ */
+struct tty_driver *get_tty_driver(kdev_t device)
+{
+ int major, minor;
+ struct tty_driver *p;
+
+ minor = MINOR(device);
+ major = MAJOR(device);
+
+ for (p = tty_drivers; p; p = p->next) {
+ if (p->major != major)
+ continue;
+ if (minor < p->minor_start)
+ continue;
+ if (minor >= p->minor_start + p->num)
+ continue;
+ return p;
+ }
+ return NULL;
+}
+
+/*
+ * If we try to write to, or set the state of, a terminal and we're
+ * not in the foreground, send a SIGTTOU. If the signal is blocked or
+ * ignored, go ahead and perform the operation. (POSIX 7.2)
+ */
+int tty_check_change(struct tty_struct * tty)
+{
+ if (current->tty != tty)
+ return 0;
+ if (tty->pgrp <= 0) {
+ printk(KERN_WARNING "tty_check_change: tty->pgrp <= 0!\n");
+ return 0;
+ }
+ if (current->pgrp == tty->pgrp)
+ return 0;
+ if (is_ignored(SIGTTOU))
+ return 0;
+ if (is_orphaned_pgrp(current->pgrp))
+ return -EIO;
+ (void) kill_pg(current->pgrp,SIGTTOU,1);
+ return -ERESTARTSYS;
+}
+
+static ssize_t hung_up_tty_read(struct file * file, char * buf,
+ size_t count, loff_t *ppos)
+{
+ /* Can't seek (pread) on ttys. */
+ if (ppos != &file->f_pos)
+ return -ESPIPE;
+ return 0;
+}
+
+static ssize_t hung_up_tty_write(struct file * file, const char * buf,
+ size_t count, loff_t *ppos)
+{
+ /* Can't seek (pwrite) on ttys. */
+ if (ppos != &file->f_pos)
+ return -ESPIPE;
+ return -EIO;
+}
+
+/* No kernel lock held - none needed ;) */
+static unsigned int hung_up_tty_poll(struct file * filp, poll_table * wait)
+{
+ return POLLIN | POLLOUT | POLLERR | POLLHUP | POLLRDNORM | POLLWRNORM;
+}
+
+static int hung_up_tty_ioctl(struct inode * inode, struct file * file,
+ unsigned int cmd, unsigned long arg)
+{
+ return cmd == TIOCSPGRP ? -ENOTTY : -EIO;
+}
+
+static struct file_operations tty_fops = {
+ llseek: no_llseek,
+ read: tty_read,
+ write: tty_write,
+ poll: tty_poll,
+ ioctl: tty_ioctl,
+ open: tty_open,
+ release: tty_release,
+ fasync: tty_fasync,
+};
+
+static struct file_operations hung_up_tty_fops = {
+ llseek: no_llseek,
+ read: hung_up_tty_read,
+ write: hung_up_tty_write,
+ poll: hung_up_tty_poll,
+ ioctl: hung_up_tty_ioctl,
+ release: tty_release,
+};
+
+static spinlock_t redirect_lock = SPIN_LOCK_UNLOCKED;
+static struct file *redirect;
+
+/**
+ * tty_wakeup - request more data
+ * @tty: terminal
+ *
+ * Internal and external helper for wakeups of tty. This function
+ * informs the line discipline if present that the driver is ready\
+ * to receive more output data.
+ */
+
+void tty_wakeup(struct tty_struct *tty)
+{
+ struct tty_ldisc *ld;
+
+ if (test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) {
+ ld = tty_ldisc_ref(tty);
+ if(ld) {
+ if(ld->write_wakeup)
+ ld->write_wakeup(tty);
+ tty_ldisc_deref(ld);
+ }
+ }
+ wake_up_interruptible(&tty->write_wait);
+}
+
+/*
+ * tty_wakeup/tty_ldisc_flush are actually _GPL exports but we can't do
+ * that in 2.4 for modutils compat reasons.
+ */
+EXPORT_SYMBOL(tty_wakeup);
+
+
+void tty_ldisc_flush(struct tty_struct *tty)
+{
+ struct tty_ldisc *ld = tty_ldisc_ref(tty);
+ if(ld) {
+ if(ld->flush_buffer)
+ ld->flush_buffer(tty);
+ tty_ldisc_deref(ld);
+ }
+}
+
+
+/*
+ * tty_wakeup/tty_ldisc_flush are actually _GPL exports but we can't do
+ * that in 2.4 for modutils compat reasons.
+ */
+EXPORT_SYMBOL(tty_ldisc_flush);
+
+void do_tty_hangup(void *data)
+{
+ struct tty_struct *tty = (struct tty_struct *) data;
+ struct file * cons_filp = NULL;
+ struct file *f = NULL;
+ struct task_struct *p;
+ struct list_head *l;
+ struct tty_ldisc *ld;
+ int closecount = 0, n;
+
+ if (!tty)
+ return;
+
+ /* inuse_filps is protected by the single kernel lock */
+ lock_kernel();
+
+ spin_lock(&redirect_lock);
+ if (redirect && redirect->private_data == tty) {
+ f = redirect;
+ redirect = NULL;
+ }
+ spin_unlock(&redirect_lock);
+
+ check_tty_count(tty, "do_tty_hangup");
+ file_list_lock();
+ for (l = tty->tty_files.next; l != &tty->tty_files; l = l->next) {
+ struct file * filp = list_entry(l, struct file, f_list);
+ if (filp->f_dentry->d_inode->i_rdev == CONSOLE_DEV ||
+ filp->f_dentry->d_inode->i_rdev == SYSCONS_DEV) {
+ cons_filp = filp;
+ continue;
+ }
+ if (filp->f_op != &tty_fops)
+ continue;
+ closecount++;
+ tty_fasync(-1, filp, 0); /* can't block */
+ filp->f_op = &hung_up_tty_fops;
+ }
+ file_list_unlock();
+
+ /* FIXME! What are the locking issues here? This may me overdoing
things.. */
+ ld = tty_ldisc_ref(tty);
+ if(ld != NULL)
+ {
+ if (ld->flush_buffer)
+ ld->flush_buffer(tty);
+ if (tty->driver.flush_buffer)
+ tty->driver.flush_buffer(tty);
+ if ((test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) &&
ld->write_wakeup)
+ ld->write_wakeup(tty);
+ if (ld->hangup)
+ ld->hangup(tty);
+ }
+
+ /* FIXME: Once we trust the LDISC code better we can wait here for
+ ldisc completion and fix the driver call race */
+
+ wake_up_interruptible(&tty->write_wait);
+ wake_up_interruptible(&tty->read_wait);
+
+ /*
+ * Shutdown the current line discipline, and reset it to
+ * N_TTY.
+ */
+
+ if (tty->driver.flags & TTY_DRIVER_RESET_TERMIOS)
+ {
+ down(&tty->termios_sem);
+ *tty->termios = tty->driver.init_termios;
+ up(&tty->termios_sem);
+ }
+
+ /* Defer ldisc switch */
+ /* tty_deferred_ldisc_switch(N_TTY)
+ This should get done automatically when the port closes and
+ tty_release is called */
+
+ read_lock(&tasklist_lock);
+ for_each_task(p) {
+ if ((tty->session > 0) && (p->session == tty->session) &&
+ p->leader) {
+ send_sig(SIGHUP,p,1);
+ send_sig(SIGCONT,p,1);
+ if (tty->pgrp > 0)
+ p->tty_old_pgrp = tty->pgrp;
+ }
+ if (p->tty == tty)
+ p->tty = NULL;
+ }
+ read_unlock(&tasklist_lock);
+
+ tty->flags = 0;
+ tty->session = 0;
+ tty->pgrp = -1;
+ tty->ctrl_status = 0;
+ /*
+ * If one of the devices matches a console pointer, we
+ * cannot just call hangup() because that will cause
+ * tty->count and state->count to go out of sync.
+ * So we just call close() the right number of times.
+ */
+ if (cons_filp) {
+ if (tty->driver.close)
+ for (n = 0; n < closecount; n++)
+ tty->driver.close(tty, cons_filp);
+ } else if (tty->driver.hangup)
+ (tty->driver.hangup)(tty);
+
+ /* We don't want to have driver/ldisc interactions beyond
+ the ones we did here. The driver layer expects no
+ calls after ->hangup() from the ldisc side. However we
+ can't yet guarantee all that */
+
+ set_bit(TTY_HUPPED, &tty->flags);
+ if(ld) {
+ tty_ldisc_enable(tty);
+ tty_ldisc_deref(ld);
+ }
+ unlock_kernel();
+ if (f)
+ fput(f);
+}
+
+void tty_hangup(struct tty_struct * tty)
+{
+#ifdef TTY_DEBUG_HANGUP
+ char buf[64];
+
+ printk(KERN_DEBUG "%s hangup...\n", tty_name(tty, buf));
+#endif
+ schedule_task(&tty->tq_hangup);
+}
+
+void tty_vhangup(struct tty_struct * tty)
+{
+#ifdef TTY_DEBUG_HANGUP
+ char buf[64];
+
+ printk(KERN_DEBUG "%s vhangup...\n", tty_name(tty, buf));
+#endif
+ do_tty_hangup((void *) tty);
+}
+
+int tty_hung_up_p(struct file * filp)
+{
+ return (filp->f_op == &hung_up_tty_fops);
+}
+
+/*
+ * This function is typically called only by the session leader, when
+ * it wants to disassociate itself from its controlling tty.
+ *
+ * It performs the following functions:
+ * (1) Sends a SIGHUP and SIGCONT to the foreground process group
+ * (2) Clears the tty from being controlling the session
+ * (3) Clears the controlling tty for all processes in the
+ * session group.
+ *
+ * The argument on_exit is set to 1 if called when a process is
+ * exiting; it is 0 if called by the ioctl TIOCNOTTY.
+ */
+void disassociate_ctty(int on_exit)
+{
+ struct tty_struct *tty = current->tty;
+ struct task_struct *p;
+ int tty_pgrp = -1;
+
+ if (tty) {
+ tty_pgrp = tty->pgrp;
+ if (on_exit && tty->driver.type != TTY_DRIVER_TYPE_PTY)
+ tty_vhangup(tty);
+ } else {
+ if (current->tty_old_pgrp) {
+ kill_pg(current->tty_old_pgrp, SIGHUP, on_exit);
+ kill_pg(current->tty_old_pgrp, SIGCONT, on_exit);
+ }
+ return;
+ }
+ if (tty_pgrp > 0) {
+ kill_pg(tty_pgrp, SIGHUP, on_exit);
+ if (!on_exit)
+ kill_pg(tty_pgrp, SIGCONT, on_exit);
+ }
+
+ current->tty_old_pgrp = 0;
+ tty->session = 0;
+ tty->pgrp = -1;
+
+ read_lock(&tasklist_lock);
+ for_each_task(p)
+ if (p->session == current->session)
+ p->tty = NULL;
+ read_unlock(&tasklist_lock);
+}
+
+void stop_tty(struct tty_struct *tty)
+{
+ if (tty->stopped)
+ return;
+ tty->stopped = 1;
+ if (tty->link && tty->link->packet) {
+ tty->ctrl_status &= ~TIOCPKT_START;
+ tty->ctrl_status |= TIOCPKT_STOP;
+ wake_up_interruptible(&tty->link->read_wait);
+ }
+ if (tty->driver.stop)
+ (tty->driver.stop)(tty);
+}
+
+void start_tty(struct tty_struct *tty)
+{
+ if (!tty->stopped || tty->flow_stopped)
+ return;
+ tty->stopped = 0;
+ if (tty->link && tty->link->packet) {
+ tty->ctrl_status &= ~TIOCPKT_STOP;
+ tty->ctrl_status |= TIOCPKT_START;
+ wake_up_interruptible(&tty->link->read_wait);
+ }
+ if (tty->driver.start)
+ (tty->driver.start)(tty);
+ /* If we have a running line discipline it may need kicking */
+ tty_wakeup(tty);
+}
+
+static ssize_t tty_read(struct file * file, char * buf, size_t count,
+ loff_t *ppos)
+{
+ int i;
+ struct tty_struct * tty;
+ struct inode *inode;
+ struct tty_ldisc *ld;
+
+ /* Can't seek (pread) on ttys. */
+ if (ppos != &file->f_pos)
+ return -ESPIPE;
+
+ tty = (struct tty_struct *)file->private_data;
+ inode = file->f_dentry->d_inode;
+ if (tty_paranoia_check(tty, inode->i_rdev, "tty_read"))
+ return -EIO;
+ if (!tty || (test_bit(TTY_IO_ERROR, &tty->flags)))
+ return -EIO;
+
+ /* This check not only needs to be done before reading, but also
+ whenever read_chan() gets woken up after sleeping, so I've
+ moved it to there. This should only be done for the N_TTY
+ line discipline, anyway. Same goes for write_chan(). -- jlc. */
+#if 0
+ if ((inode->i_rdev != CONSOLE_DEV) && /* don't stop on /dev/console */
+ (tty->pgrp > 0) &&
+ (current->tty == tty) &&
+ (tty->pgrp != current->pgrp))
+ if (is_ignored(SIGTTIN) || is_orphaned_pgrp(current->pgrp))
+ return -EIO;
+ else {
+ (void) kill_pg(current->pgrp, SIGTTIN, 1);
+ return -ERESTARTSYS;
+ }
+#endif
+ /* We want to wait for the line discipline to sort out in this
+ situation */
+ ld = tty_ldisc_ref_wait(tty);
+ lock_kernel();
+ if (ld->read)
+ i = (ld->read)(tty,file,buf,count);
+ else
+ i = -EIO;
+ tty_ldisc_deref(ld);
+ unlock_kernel();
+ if (i > 0)
+ inode->i_atime = CURRENT_TIME;
+ return i;
+}
+
+/*
+ * Split writes up in sane blocksizes to avoid
+ * denial-of-service type attacks
+ */
+static inline ssize_t do_tty_write(
+ ssize_t (*write)(struct tty_struct *, struct file *, const unsigned
char *, size_t),
+ struct tty_struct *tty,
+ struct file *file,
+ const unsigned char *buf,
+ size_t count)
+{
+ ssize_t ret = 0, written = 0;
+
+ if (file->f_flags & O_NONBLOCK) {
+ if (down_trylock(&tty->atomic_write))
+ return -EAGAIN;
+ }
+ else {
+ if (down_interruptible(&tty->atomic_write))
+ return -ERESTARTSYS;
+ }
+ if ( test_bit(TTY_NO_WRITE_SPLIT, &tty->flags) ) {
+ lock_kernel();
+ written = write(tty, file, buf, count);
+ unlock_kernel();
+ } else {
+ for (;;) {
+ unsigned long size = MAX(PAGE_SIZE*2,16384);
+ if (size > count)
+ size = count;
+ lock_kernel();
+ ret = write(tty, file, buf, size);
+ unlock_kernel();
+ if (ret <= 0)
+ break;
+ written += ret;
+ buf += ret;
+ count -= ret;
+ if (!count)
+ break;
+ ret = -ERESTARTSYS;
+ if (signal_pending(current))
+ break;
+ if (current->need_resched)
+ schedule();
+ }
+ }
+ if (written) {
+ file->f_dentry->d_inode->i_mtime = CURRENT_TIME;
+ ret = written;
+ }
+ up(&tty->atomic_write);
+ return ret;
+}
+
+
+static ssize_t tty_write(struct file * file, const char * buf, size_t count,
+ loff_t *ppos)
+{
+ int is_console;
+ struct tty_struct * tty;
+ struct inode *inode = file->f_dentry->d_inode;
+ ssize_t ret;
+ struct tty_ldisc *ld;
+
+ /* Can't seek (pwrite) on ttys. */
+ if (ppos != &file->f_pos)
+ return -ESPIPE;
+
+ /*
+ * For now, we redirect writes from /dev/console as
+ * well as /dev/tty0.
+ */
+ inode = file->f_dentry->d_inode;
+ is_console = (inode->i_rdev == SYSCONS_DEV ||
+ inode->i_rdev == CONSOLE_DEV);
+
+ if (is_console) {
+ struct file *p = NULL;
+
+ spin_lock(&redirect_lock);
+ if (redirect) {
+ get_file(redirect);
+ p = redirect;
+ }
+ spin_unlock(&redirect_lock);
+
+ if (p) {
+ ssize_t res = p->f_op->write(p, buf, count, &p->f_pos);
+ fput(p);
+ return res;
+ }
+ }
+
+ tty = (struct tty_struct *)file->private_data;
+ if (tty_paranoia_check(tty, inode->i_rdev, "tty_write"))
+ return -EIO;
+ if (!tty || !tty->driver.write || (test_bit(TTY_IO_ERROR, &tty->flags)))
+ return -EIO;
+#if 0
+ if (!is_console && L_TOSTOP(tty) && (tty->pgrp > 0) &&
+ (current->tty == tty) && (tty->pgrp != current->pgrp)) {
+ if (is_orphaned_pgrp(current->pgrp))
+ return -EIO;
+ if (!is_ignored(SIGTTOU)) {
+ (void) kill_pg(current->pgrp, SIGTTOU, 1);
+ return -ERESTARTSYS;
+ }
+ }
+#endif
+
+ ld = tty_ldisc_ref_wait(tty);
+ if (!ld->write)
+ ret = -EIO;
+ else
+ ret = do_tty_write(ld->write, tty, file,
+ (const unsigned char __user *)buf, count);
+ tty_ldisc_deref(ld);
+ return ret;
+}
+
+/* Semaphore to protect creating and releasing a tty. This is shared with
+ vt.c for deeply disgusting hack reasons */
+static DECLARE_MUTEX(tty_sem);
+
+static void down_tty_sem(int index)
+{
+ down(&tty_sem);
+}
+
+static void up_tty_sem(int index)
+{
+ up(&tty_sem);
+}
+
+static void release_mem(struct tty_struct *tty, int idx);
+
+/*
+ * WSH 06/09/97: Rewritten to remove races and properly clean up after a
+ * failed open. The new code protects the open with a semaphore, so it's
+ * really quite straightforward. The semaphore locking can probably be
+ * relaxed for the (most common) case of reopening a tty.
+ */
+static int init_dev(kdev_t device, struct tty_struct **ret_tty)
+{
+ struct tty_struct *tty, *o_tty;
+ struct termios *tp, **tp_loc, *o_tp, **o_tp_loc;
+ struct termios *ltp, **ltp_loc, *o_ltp, **o_ltp_loc;
+ struct tty_driver *driver;
+ int retval=0;
+ int idx;
+
+ driver = get_tty_driver(device);
+ if (!driver)
+ return -ENODEV;
+
+ idx = MINOR(device) - driver->minor_start;
+
+ /*
+ * Check whether we need to acquire the tty semaphore to avoid
+ * race conditions. For now, play it safe.
+ */
+ down_tty_sem(idx);
+
+ /* check whether we're reopening an existing tty */
+ tty = driver->table[idx];
+ if (tty) goto fast_track;
+
+ /*
+ * First time open is complex, especially for PTY devices.
+ * This code guarantees that either everything succeeds and the
+ * TTY is ready for operation, or else the table slots are vacated
+ * and the allocated memory released. (Except that the termios
+ * and locked termios may be retained.)
+ */
+
+ o_tty = NULL;
+ tp = o_tp = NULL;
+ ltp = o_ltp = NULL;
+
+ tty = alloc_tty_struct();
+ if(!tty)
+ goto fail_no_mem;
+ initialize_tty_struct(tty);
+ tty->device = device;
+ tty->driver = *driver;
+
+ tp_loc = &driver->termios[idx];
+ if (!*tp_loc) {
+ tp = (struct termios *) kmalloc(sizeof(struct termios),
+ GFP_KERNEL);
+ if (!tp)
+ goto free_mem_out;
+ *tp = driver->init_termios;
+ }
+
+ ltp_loc = &driver->termios_locked[idx];
+ if (!*ltp_loc) {
+ ltp = (struct termios *) kmalloc(sizeof(struct termios),
+ GFP_KERNEL);
+ if (!ltp)
+ goto free_mem_out;
+ memset(ltp, 0, sizeof(struct termios));
+ }
+
+ if (driver->type == TTY_DRIVER_TYPE_PTY) {
+ o_tty = alloc_tty_struct();
+ if (!o_tty)
+ goto free_mem_out;
+ initialize_tty_struct(o_tty);
+ o_tty->device = (kdev_t) MKDEV(driver->other->major,
+ driver->other->minor_start + idx);
+ o_tty->driver = *driver->other;
+
+ o_tp_loc = &driver->other->termios[idx];
+ if (!*o_tp_loc) {
+ o_tp = (struct termios *)
+ kmalloc(sizeof(struct termios), GFP_KERNEL);
+ if (!o_tp)
+ goto free_mem_out;
+ *o_tp = driver->other->init_termios;
+ }
+
+ o_ltp_loc = &driver->other->termios_locked[idx];
+ if (!*o_ltp_loc) {
+ o_ltp = (struct termios *)
+ kmalloc(sizeof(struct termios), GFP_KERNEL);
+ if (!o_ltp)
+ goto free_mem_out;
+ memset(o_ltp, 0, sizeof(struct termios));
+ }
+
+ /*
+ * Everything allocated ... set up the o_tty structure.
+ */
+ driver->other->table[idx] = o_tty;
+ if (!*o_tp_loc)
+ *o_tp_loc = o_tp;
+ if (!*o_ltp_loc)
+ *o_ltp_loc = o_ltp;
+ o_tty->termios = *o_tp_loc;
+ o_tty->termios_locked = *o_ltp_loc;
+ (*driver->other->refcount)++;
+ if (driver->subtype == PTY_TYPE_MASTER)
+ o_tty->count++;
+
+ /* Establish the links in both directions */
+ tty->link = o_tty;
+ o_tty->link = tty;
+ }
+
+ /*
+ * All structures have been allocated, so now we install them.
+ * Failures after this point use release_mem to clean up, so
+ * there's no need to null out the local pointers.
+ */
+ driver->table[idx] = tty;
+
+ if (!*tp_loc)
+ *tp_loc = tp;
+ if (!*ltp_loc)
+ *ltp_loc = ltp;
+ tty->termios = *tp_loc;
+ tty->termios_locked = *ltp_loc;
+ (*driver->refcount)++;
+ tty->count++;
+
+ /*
+ * Structures all installed ... call the ldisc open routines.
+ * If we fail here just call release_mem to clean up. No need
+ * to decrement the use counts, as release_mem doesn't care.
+ */
+ if (tty->ldisc.open) {
+ retval = (tty->ldisc.open)(tty);
+ if (retval)
+ goto release_mem_out;
+ }
+ if (o_tty && o_tty->ldisc.open) {
+ retval = (o_tty->ldisc.open)(o_tty);
+ if (retval) {
+ if (tty->ldisc.close)
+ (tty->ldisc.close)(tty);
+ goto release_mem_out;
+ }
+ set_bit(TTY_LDISC, &o_tty->flags);
+ tty_ldisc_enable(o_tty);
+ }
+ tty_ldisc_enable(tty);
+ goto success;
+
+ /*
+ * This fast open can be used if the tty is already open.
+ * No memory is allocated, and the only failures are from
+ * attempting to open a closing tty or attempting multiple
+ * opens on a pty master.
+ */
+fast_track:
+ if (test_bit(TTY_CLOSING, &tty->flags)) {
+ retval = -EIO;
+ goto end_init;
+ }
+ if (driver->type == TTY_DRIVER_TYPE_PTY &&
+ driver->subtype == PTY_TYPE_MASTER) {
+ /*
+ * special case for PTY masters: only one open permitted,
+ * and the slave side open count is incremented as well.
+ */
+ if (tty->count) {
+ retval = -EIO;
+ goto end_init;
+ }
+ tty->link->count++;
+ }
+ tty->count++;
+ tty->driver = *driver; /* N.B. why do this every time?? */
+ /* FIXME */
+ if(!test_bit(TTY_LDISC, &tty->flags))
+ printk(KERN_ERR "init_dev but no ldisc\n");
+success:
+ *ret_tty = tty;
+
+ /* All paths come through here to release the semaphore */
+end_init:
+ up_tty_sem(idx);
+ return retval;
+
+ /* Release locally allocated memory ... nothing placed in slots */
+free_mem_out:
+ if (o_tp)
+ kfree(o_tp);
+ if (o_tty)
+ free_tty_struct(o_tty);
+ if (ltp)
+ kfree(ltp);
+ if (tp)
+ kfree(tp);
+ free_tty_struct(tty);
+
+fail_no_mem:
+ retval = -ENOMEM;
+ goto end_init;
+
+ /* call the tty release_mem routine to clean out this slot */
+release_mem_out:
+ printk(KERN_INFO "init_dev: ldisc open failed, "
+ "clearing slot %d\n", idx);
+ release_mem(tty, idx);
+ goto end_init;
+}
+
+/*
+ * Releases memory associated with a tty structure, and clears out the
+ * driver table slots.
+ */
+static void release_mem(struct tty_struct *tty, int idx)
+{
+ struct tty_struct *o_tty;
+ struct termios *tp;
+
+ if ((o_tty = tty->link) != NULL) {
+ o_tty->driver.table[idx] = NULL;
+ if (o_tty->driver.flags & TTY_DRIVER_RESET_TERMIOS) {
+ tp = o_tty->driver.termios[idx];
+ o_tty->driver.termios[idx] = NULL;
+ kfree(tp);
+ }
+ o_tty->magic = 0;
+ (*o_tty->driver.refcount)--;
+ list_del_init(&o_tty->tty_files);
+ free_tty_struct(o_tty);
+ }
+
+ tty->driver.table[idx] = NULL;
+ if (tty->driver.flags & TTY_DRIVER_RESET_TERMIOS) {
+ tp = tty->driver.termios[idx];
+ tty->driver.termios[idx] = NULL;
+ kfree(tp);
+ }
+ tty->magic = 0;
+ (*tty->driver.refcount)--;
+ list_del_init(&tty->tty_files);
+ free_tty_struct(tty);
+}
+
+/*
+ * Even releasing the tty structures is a tricky business.. We have
+ * to be very careful that the structures are all released at the
+ * same time, as interrupts might otherwise get the wrong pointers.
+ *
+ * WSH 09/09/97: rewritten to avoid some nasty race conditions that could
+ * lead to double frees or releasing memory still in use.
+ */
+static void release_dev(struct file * filp)
+{
+ struct tty_struct *tty, *o_tty;
+ int pty_master, tty_closing, o_tty_closing, do_sleep;
+ int idx;
+ char buf[64];
+ unsigned long flags;
+
+ tty = (struct tty_struct *)filp->private_data;
+ if (tty_paranoia_check(tty, filp->f_dentry->d_inode->i_rdev,
"release_dev"))
+ return;
+
+ check_tty_count(tty, "release_dev");
+
+ tty_fasync(-1, filp, 0);
+
+ idx = MINOR(tty->device) - tty->driver.minor_start;
+ pty_master = (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver.subtype == PTY_TYPE_MASTER);
+ o_tty = tty->link;
+
+#ifdef TTY_PARANOIA_CHECK
+ if (idx < 0 || idx >= tty->driver.num) {
+ printk(KERN_DEBUG "release_dev: bad idx when trying to "
+ "free (%s)\n", kdevname(tty->device));
+ return;
+ }
+ if (tty != tty->driver.table[idx]) {
+ printk(KERN_DEBUG "release_dev: driver.table[%d] not tty "
+ "for (%s)\n", idx, kdevname(tty->device));
+ return;
+ }
+ if (tty->termios != tty->driver.termios[idx]) {
+ printk(KERN_DEBUG "release_dev: driver.termios[%d] not termios "
+ "for (%s)\n",
+ idx, kdevname(tty->device));
+ return;
+ }
+ if (tty->termios_locked != tty->driver.termios_locked[idx]) {
+ printk(KERN_DEBUG "release_dev: driver.termios_locked[%d] not "
+ "termios_locked for (%s)\n",
+ idx, kdevname(tty->device));
+ return;
+ }
+#endif
+
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "release_dev of %s (tty count=%d)...",
+ tty_name(tty, buf), tty->count);
+#endif
+
+#ifdef TTY_PARANOIA_CHECK
+ if (tty->driver.other) {
+ if (o_tty != tty->driver.other->table[idx]) {
+ printk(KERN_DEBUG "release_dev: other->table[%d] "
+ "not o_tty for (%s)\n",
+ idx, kdevname(tty->device));
+ return;
+ }
+ if (o_tty->termios != tty->driver.other->termios[idx]) {
+ printk(KERN_DEBUG "release_dev: other->termios[%d] "
+ "not o_termios for (%s)\n",
+ idx, kdevname(tty->device));
+ return;
+ }
+ if (o_tty->termios_locked !=
+ tty->driver.other->termios_locked[idx]) {
+ printk(KERN_DEBUG "release_dev: other->termios_locked["
+ "%d] not o_termios_locked for (%s)\n",
+ idx, kdevname(tty->device));
+ return;
+ }
+ if (o_tty->link != tty) {
+ printk(KERN_DEBUG "release_dev: bad pty pointers\n");
+ return;
+ }
+ }
+#endif
+
+ if (tty->driver.close)
+ tty->driver.close(tty, filp);
+
+ /*
+ * Sanity check: if tty->count is going to zero, there shouldn't be
+ * any waiters on tty->read_wait or tty->write_wait. We test the
+ * wait queues and kick everyone out _before_ actually starting to
+ * close. This ensures that we won't block while releasing the tty
+ * structure.
+ *
+ * The test for the o_tty closing is necessary, since the master and
+ * slave sides may close in any order. If the slave side closes out
+ * first, its count will be one, since the master side holds an open.
+ * Thus this test wouldn't be triggered at the time the slave closes,
+ * so we do it now.
+ *
+ * Note that it's possible for the tty to be opened again while we're
+ * flushing out waiters. By recalculating the closing flags before
+ * each iteration we avoid any problems.
+ */
+ while (1) {
+ tty_closing = tty->count <= 1;
+ o_tty_closing = o_tty &&
+ (o_tty->count <= (pty_master ? 1 : 0));
+ do_sleep = 0;
+
+ if (tty_closing) {
+ if (waitqueue_active(&tty->read_wait)) {
+ wake_up(&tty->read_wait);
+ do_sleep++;
+ }
+ if (waitqueue_active(&tty->write_wait)) {
+ wake_up(&tty->write_wait);
+ do_sleep++;
+ }
+ }
+ if (o_tty_closing) {
+ if (waitqueue_active(&o_tty->read_wait)) {
+ wake_up(&o_tty->read_wait);
+ do_sleep++;
+ }
+ if (waitqueue_active(&o_tty->write_wait)) {
+ wake_up(&o_tty->write_wait);
+ do_sleep++;
+ }
+ }
+ if (!do_sleep)
+ break;
+
+ printk(KERN_WARNING "release_dev: %s: read/write wait queue "
+ "active!\n", tty_name(tty, buf));
+ schedule();
+ }
+
+ /*
+ * The closing flags are now consistent with the open counts on
+ * both sides, and we've completed the last operation that could
+ * block, so it's safe to proceed with closing.
+ */
+ if (pty_master) {
+ if (--o_tty->count < 0) {
+ printk(KERN_WARNING "release_dev: bad pty slave count "
+ "(%d) for %s\n",
+ o_tty->count, tty_name(o_tty, buf));
+ o_tty->count = 0;
+ }
+ }
+ if (--tty->count < 0) {
+ printk(KERN_WARNING "release_dev: bad tty->count (%d) for %s\n",
+ tty->count, tty_name(tty, buf));
+ tty->count = 0;
+ }
+
+ /*
+ * We've decremented tty->count, so we should zero out
+ * filp->private_data, to break the link between the tty and
+ * the file descriptor. Otherwise if filp_close() blocks before
+ * the file descriptor is removed from the inuse_filp
+ * list, check_tty_count() could observe a discrepancy and
+ * printk a warning message to the user.
+ */
+ filp->private_data = 0;
+
+ /*
+ * Perform some housekeeping before deciding whether to return.
+ *
+ * Set the TTY_CLOSING flag if this was the last open. In the
+ * case of a pty we may have to wait around for the other side
+ * to close, and TTY_CLOSING makes sure we can't be reopened.
+ */
+ if(tty_closing)
+ set_bit(TTY_CLOSING, &tty->flags);
+ if(o_tty_closing)
+ set_bit(TTY_CLOSING, &o_tty->flags);
+
+ /*
+ * If _either_ side is closing, make sure there aren't any
+ * processes that still think tty or o_tty is their controlling
+ * tty.
+ */
+ if (tty_closing || o_tty_closing) {
+ struct task_struct *p;
+
+ read_lock(&tasklist_lock);
+ for_each_task(p) {
+ if (p->tty == tty || (o_tty && p->tty == o_tty))
+ p->tty = NULL;
+ }
+ read_unlock(&tasklist_lock);
+ }
+
+ /* check whether both sides are closing ... */
+ if (!tty_closing || (o_tty && !o_tty_closing))
+ return;
+
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "freeing tty structure...");
+#endif
+
+ /*
+ * Prevent flush_to_ldisc() from rescheduling the work for later. Then
+ * kill any delayed work. As this is the final close it does not
+ * race with the set_ldisc code path.
+ */
+ clear_bit(TTY_LDISC, &tty->flags);
+ clear_bit(TTY_DONT_FLIP, &tty->flags);
+
+ /*
+ * Wait for ->hangup_work and ->flip.work handlers to terminate
+ */
+
+ run_task_queue(&tq_timer);
+ flush_scheduled_tasks();
+
+ /*
+ * Wait for any short term users (we know they are just driver
+ * side waiters as the file is closing so user count on the file
+ * side is zero.
+ */
+
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ while(tty->ldisc.refcount)
+ {
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+ wait_event(tty_ldisc_wait, tty->ldisc.refcount == 0);
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ }
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+
+ /*
+ * Shutdown the current line discipline, and reset it to N_TTY.
+ * N.B. why reset ldisc when we're releasing the memory??
+ * FIXME: this MUST get fixed for the new reflocking
+ */
+ if (tty->ldisc.close)
+ (tty->ldisc.close)(tty);
+ tty_ldisc_put(tty->ldisc.num);
+
+ /*
+ * Switch the line discipline back
+ */
+ tty_ldisc_assign(tty, tty_ldisc_get(N_TTY));
+ tty_set_termios_ldisc(tty,N_TTY);
+
+ if (o_tty) {
+ /* FIXME: could o_tty be in setldisc here ? */
+ clear_bit(TTY_LDISC, &o_tty->flags);
+ if (o_tty->ldisc.close)
+ (o_tty->ldisc.close)(o_tty);
+ tty_ldisc_put(o_tty->ldisc.num);
+ tty_ldisc_assign(o_tty, tty_ldisc_get(N_TTY));
+ tty_set_termios_ldisc(o_tty,N_TTY);
+ }
+
+ /*
+ * The release_mem function takes care of the details of clearing
+ * the slots and preserving the termios structure.
+ */
+ release_mem(tty, idx);
+}
+
+/*
+ * tty_open and tty_release keep up the tty count that contains the
+ * number of opens done on a tty. We cannot use the inode-count, as
+ * different inodes might point to the same tty.
+ *
+ * Open-counting is needed for pty masters, as well as for keeping
+ * track of serial lines: DTR is dropped when the last close happens.
+ * (This is not done solely through tty->count, now. - Ted 1/27/92)
+ *
+ * The termios state of a pty is reset on first open so that
+ * settings don't persist across reuse.
+ */
+static int tty_open(struct inode * inode, struct file * filp)
+{
+ struct tty_struct *tty;
+ int noctty, retval;
+ kdev_t device;
+ unsigned short saved_flags;
+ char buf[64];
+
+ saved_flags = filp->f_flags;
+retry_open:
+ noctty = filp->f_flags & O_NOCTTY;
+ device = inode->i_rdev;
+ if (device == TTY_DEV) {
+ if (!current->tty)
+ return -ENXIO;
+ device = current->tty->device;
+ filp->f_flags |= O_NONBLOCK; /* Don't let /dev/tty block */
+ /* noctty = 1; */
+ }
+#ifdef CONFIG_VT
+ if (device == CONSOLE_DEV) {
+ extern int fg_console;
+ device = MKDEV(TTY_MAJOR, fg_console + 1);
+ noctty = 1;
+ }
+#endif
+ if (device == SYSCONS_DEV) {
+ struct console *c = console_drivers;
+ while(c && !c->device)
+ c = c->next;
+ if (!c)
+ return -ENODEV;
+ device = c->device(c);
+ filp->f_flags |= O_NONBLOCK; /* Don't let /dev/console block */
+ noctty = 1;
+ }
+
+ if (device == PTMX_DEV) {
+#ifdef CONFIG_UNIX98_PTYS
+
+ /* find a free pty. */
+ int major, minor;
+ struct tty_driver *driver;
+
+ /* find a device that is not in use. */
+ retval = -1;
+ for ( major = 0 ; major < UNIX98_NR_MAJORS ; major++ ) {
+ driver = &ptm_driver[major];
+ for (minor = driver->minor_start ;
+ minor < driver->minor_start + driver->num ;
+ minor++) {
+ device = MKDEV(driver->major, minor);
+ if (!init_dev(device, &tty)) goto ptmx_found;
/* ok! */
+ }
+ }
+ return -EIO; /* no free ptys */
+ ptmx_found:
+ set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
+ minor -= driver->minor_start;
+ devpts_pty_new(driver->other->name_base + minor,
MKDEV(driver->other->major, minor + driver->other->minor_start));
+ tty_register_devfs(&pts_driver[major], DEVFS_FL_DEFAULT,
+ pts_driver[major].minor_start + minor);
+ noctty = 1;
+ goto init_dev_done;
+
+#else /* CONFIG_UNIX_98_PTYS */
+
+ return -ENODEV;
+
+#endif /* CONFIG_UNIX_98_PTYS */
+ }
+
+ retval = init_dev(device, &tty);
+ if (retval)
+ return retval;
+
+#ifdef CONFIG_UNIX98_PTYS
+init_dev_done:
+#endif
+ filp->private_data = tty;
+ file_move(filp, &tty->tty_files);
+ check_tty_count(tty, "tty_open");
+ if (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver.subtype == PTY_TYPE_MASTER)
+ noctty = 1;
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "opening %s...", tty_name(tty, buf));
+#endif
+ if (tty->driver.open)
+ retval = tty->driver.open(tty, filp);
+ else
+ retval = -ENODEV;
+ filp->f_flags = saved_flags;
+
+ if (!retval && test_bit(TTY_EXCLUSIVE, &tty->flags) && !suser())
+ retval = -EBUSY;
+
+ if (retval) {
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "error %d in opening %s...", retval,
+ tty_name(tty, buf));
+#endif
+
+ release_dev(filp);
+ if (retval != -ERESTARTSYS)
+ return retval;
+ if (signal_pending(current))
+ return retval;
+ schedule();
+ /*
+ * Need to reset f_op in case a hangup happened.
+ */
+ filp->f_op = &tty_fops;
+ goto retry_open;
+ }
+ if (!noctty &&
+ current->leader &&
+ !current->tty &&
+ tty->session == 0) {
+ task_lock(current);
+ current->tty = tty;
+ task_unlock(current);
+ current->tty_old_pgrp = 0;
+ tty->session = current->session;
+ tty->pgrp = current->pgrp;
+ }
+ if ((tty->driver.type == TTY_DRIVER_TYPE_SERIAL) &&
+ (tty->driver.subtype == SERIAL_TYPE_CALLOUT) &&
+ (tty->count == 1)) {
+ static int nr_warns;
+ if (nr_warns < 5) {
+ printk(KERN_WARNING "tty_io.c: "
+ "process %d (%s) used obsolete /dev/%s - "
+ "update software to use /dev/ttyS%d\n",
+ current->pid, current->comm,
+ tty_name(tty, buf), TTY_NUMBER(tty));
+ nr_warns++;
+ }
+ }
+ return 0;
+}
+
+static int tty_release(struct inode * inode, struct file * filp)
+{
+ lock_kernel();
+ release_dev(filp);
+ unlock_kernel();
+ return 0;
+}
+
+/* No kernel lock held - fine */
+static unsigned int tty_poll(struct file * filp, poll_table * wait)
+{
+ struct tty_struct * tty;
+ struct tty_ldisc *ld;
+ int ret = 0;
+
+ tty = (struct tty_struct *)filp->private_data;
+ if (tty_paranoia_check(tty, filp->f_dentry->d_inode->i_rdev,
"tty_poll"))
+ return 0;
+
+ ld = tty_ldisc_ref_wait(tty);
+ if (ld->poll)
+ ret = (ld->poll)(tty, filp, wait);
+ tty_ldisc_deref(ld);
+ return ret;
+}
+
+static int tty_fasync(int fd, struct file * filp, int on)
+{
+ struct tty_struct * tty;
+ int retval;
+
+ tty = (struct tty_struct *)filp->private_data;
+ if (tty_paranoia_check(tty, filp->f_dentry->d_inode->i_rdev,
"tty_fasync"))
+ return 0;
+
+ retval = fasync_helper(fd, filp, on, &tty->fasync);
+ if (retval <= 0)
+ return retval;
+
+ if (on) {
+ if (!waitqueue_active(&tty->read_wait))
+ tty->minimum_to_wake = 1;
+ if (filp->f_owner.pid == 0) {
+ filp->f_owner.pid = (-tty->pgrp) ? : current->pid;
+ filp->f_owner.uid = current->uid;
+ filp->f_owner.euid = current->euid;
+ }
+ } else {
+ if (!tty->fasync && !waitqueue_active(&tty->read_wait))
+ tty->minimum_to_wake = N_TTY_BUF_SIZE;
+ }
+ return 0;
+}
+
+static int tiocsti(struct tty_struct *tty, char * arg)
+{
+ char ch, mbz = 0;
+ struct tty_ldisc *ld;
+
+ if ((current->tty != tty) && !suser())
+ return -EPERM;
+ if (get_user(ch, arg))
+ return -EFAULT;
+ ld = tty_ldisc_ref_wait(tty);
+ ld->receive_buf(tty, &ch, &mbz, 1);
+ tty_ldisc_deref(ld);
+ return 0;
+}
+
+static int tiocgwinsz(struct tty_struct *tty, struct winsize * arg)
+{
+ if (copy_to_user(arg, &tty->winsize, sizeof(*arg)))
+ return -EFAULT;
+ return 0;
+}
+
+static int tiocswinsz(struct tty_struct *tty, struct tty_struct *real_tty,
+ struct winsize * arg)
+{
+ struct winsize tmp_ws;
+
+ if (copy_from_user(&tmp_ws, arg, sizeof(*arg)))
+ return -EFAULT;
+ if (!memcmp(&tmp_ws, &tty->winsize, sizeof(*arg)))
+ return 0;
+ if (tty->pgrp > 0)
+ kill_pg(tty->pgrp, SIGWINCH, 1);
+ if ((real_tty->pgrp != tty->pgrp) && (real_tty->pgrp > 0))
+ kill_pg(real_tty->pgrp, SIGWINCH, 1);
+ tty->winsize = tmp_ws;
+ real_tty->winsize = tmp_ws;
+ return 0;
+}
+
+static int tioccons(struct inode *inode, struct file *file)
+{
+ if (inode->i_rdev == SYSCONS_DEV ||
+ inode->i_rdev == CONSOLE_DEV) {
+ struct file *f;
+ if (!suser())
+ return -EPERM;
+ spin_lock(&redirect_lock);
+ f = redirect;
+ redirect = NULL;
+ spin_unlock(&redirect_lock);
+ if (f)
+ fput(f);
+ return 0;
+ }
+ spin_lock(&redirect_lock);
+ if (redirect) {
+ spin_unlock(&redirect_lock);
+ return -EBUSY;
+ }
+ get_file(file);
+ redirect = file;
+ spin_unlock(&redirect_lock);
+ return 0;
+}
+
+
+static int fionbio(struct file *file, int *arg)
+{
+ int nonblock;
+
+ if (get_user(nonblock, arg))
+ return -EFAULT;
+
+ if (nonblock)
+ file->f_flags |= O_NONBLOCK;
+ else
+ file->f_flags &= ~O_NONBLOCK;
+ return 0;
+}
+
+static int tiocsctty(struct tty_struct *tty, int arg)
+{
+ if (current->leader &&
+ (current->session == tty->session))
+ return 0;
+ /*
+ * The process must be a session leader and
+ * not have a controlling tty already.
+ */
+ if (!current->leader || current->tty)
+ return -EPERM;
+ if (tty->session > 0) {
+ /*
+ * This tty is already the controlling
+ * tty for another session group!
+ */
+ if ((arg == 1) && suser()) {
+ /*
+ * Steal it away
+ */
+ struct task_struct *p;
+
+ read_lock(&tasklist_lock);
+ for_each_task(p)
+ if (p->tty == tty)
+ p->tty = NULL;
+ read_unlock(&tasklist_lock);
+ } else
+ return -EPERM;
+ }
+ task_lock(current);
+ current->tty = tty;
+ task_unlock(current);
+ current->tty_old_pgrp = 0;
+ tty->session = current->session;
+ tty->pgrp = current->pgrp;
+ return 0;
+}
+
+static int tiocgpgrp(struct tty_struct *tty, struct tty_struct *real_tty,
pid_t *arg)
+{
+ /*
+ * (tty == real_tty) is a cheap way of
+ * testing if the tty is NOT a master pty.
+ */
+ if (tty == real_tty && current->tty != real_tty)
+ return -ENOTTY;
+ return put_user(real_tty->pgrp, arg);
+}
+
+static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty,
pid_t *arg)
+{
+ pid_t pgrp;
+ int retval = tty_check_change(real_tty);
+
+ if (retval == -EIO)
+ return -ENOTTY;
+ if (retval)
+ return retval;
+ if (!current->tty ||
+ (current->tty != real_tty) ||
+ (real_tty->session != current->session))
+ return -ENOTTY;
+ if (get_user(pgrp, (pid_t *) arg))
+ return -EFAULT;
+ if (pgrp < 0)
+ return -EINVAL;
+ if (session_of_pgrp(pgrp) != current->session)
+ return -EPERM;
+ real_tty->pgrp = pgrp;
+ return 0;
+}
+
+static int tiocgsid(struct tty_struct *tty, struct tty_struct *real_tty, pid_t
*arg)
+{
+ /*
+ * (tty == real_tty) is a cheap way of
+ * testing if the tty is NOT a master pty.
+ */
+ if (tty == real_tty && current->tty != real_tty)
+ return -ENOTTY;
+ if (real_tty->session <= 0)
+ return -ENOTTY;
+ return put_user(real_tty->session, arg);
+}
+
+static int tiocttygstruct(struct tty_struct *tty, struct tty_struct *arg)
+{
+ if (copy_to_user(arg, tty, sizeof(*arg)))
+ return -EFAULT;
+ return 0;
+}
+
+static int tiocsetd(struct tty_struct *tty, int *arg)
+{
+ int ldisc;
+
+ if (get_user(ldisc, arg))
+ return -EFAULT;
+ return tty_set_ldisc(tty, ldisc);
+}
+
+static int send_break(struct tty_struct *tty, int duration)
+{
+ tty->driver.break_ctl(tty, -1);
+ if (!signal_pending(current)) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(duration);
+ }
+ tty->driver.break_ctl(tty, 0);
+ if (signal_pending(current))
+ return -EINTR;
+ return 0;
+}
+
+static int tty_generic_brk(struct tty_struct *tty, struct file *file, unsigned
int cmd, unsigned long arg)
+{
+ if (cmd == TCSBRK && arg)
+ {
+ /* tcdrain case */
+ int retval = tty_check_change(tty);
+ if (retval)
+ return retval;
+ tty_wait_until_sent(tty, 0);
+ if (signal_pending(current))
+ return -EINTR;
+ }
+ return 0;
+}
+
+/*
+ * Split this up, as gcc can choke on it otherwise..
+ */
+int tty_ioctl(struct inode * inode, struct file * file,
+ unsigned int cmd, unsigned long arg)
+{
+ struct tty_struct *tty, *real_tty;
+ int retval;
+ struct tty_ldisc *ld;
+
+ tty = (struct tty_struct *)file->private_data;
+ if (tty_paranoia_check(tty, inode->i_rdev, "tty_ioctl"))
+ return -EINVAL;
+
+ real_tty = tty;
+ if (tty->driver.type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver.subtype == PTY_TYPE_MASTER)
+ real_tty = tty->link;
+
+ /*
+ * Break handling by driver
+ */
+ if (!tty->driver.break_ctl) {
+ switch(cmd) {
+ case TIOCSBRK:
+ case TIOCCBRK:
+ if (tty->driver.ioctl)
+ return tty->driver.ioctl(tty, file, cmd, arg);
+ return -EINVAL;
+
+ /* These two ioctl's always return success; even if */
+ /* the driver doesn't support them. */
+ case TCSBRK:
+ case TCSBRKP:
+ retval = -ENOIOCTLCMD;
+ if (tty->driver.ioctl)
+ retval = tty->driver.ioctl(tty, file, cmd, arg);
+ /* Not driver handled */
+ if (retval == -ENOIOCTLCMD)
+ retval = tty_generic_brk(tty, file, cmd, arg);
+ return retval;
+ }
+ }
+
+ /*
+ * Factor out some common prep work
+ */
+ switch (cmd) {
+ case TIOCSETD:
+ case TIOCSBRK:
+ case TIOCCBRK:
+ case TCSBRK:
+ case TCSBRKP:
+ retval = tty_check_change(tty);
+ if (retval)
+ return retval;
+ if (cmd != TIOCCBRK) {
+ tty_wait_until_sent(tty, 0);
+ if (signal_pending(current))
+ return -EINTR;
+ }
+ break;
+ }
+
+ switch (cmd) {
+ case TIOCSTI:
+ return tiocsti(tty, (char *)arg);
+ case TIOCGWINSZ:
+ return tiocgwinsz(tty, (struct winsize *) arg);
+ case TIOCSWINSZ:
+ return tiocswinsz(tty, real_tty, (struct winsize *)
arg);
+ case TIOCCONS:
+ return real_tty!=tty ? -EINVAL : tioccons(inode, file);
+ case FIONBIO:
+ return fionbio(file, (int *) arg);
+ case TIOCEXCL:
+ set_bit(TTY_EXCLUSIVE, &tty->flags);
+ return 0;
+ case TIOCNXCL:
+ clear_bit(TTY_EXCLUSIVE, &tty->flags);
+ return 0;
+ case TIOCNOTTY:
+ if (current->tty != tty)
+ return -ENOTTY;
+ if (current->leader)
+ disassociate_ctty(0);
+ task_lock(current);
+ current->tty = NULL;
+ task_unlock(current);
+ return 0;
+ case TIOCSCTTY:
+ return tiocsctty(tty, arg);
+ case TIOCGPGRP:
+ return tiocgpgrp(tty, real_tty, (pid_t *) arg);
+ case TIOCSPGRP:
+ return tiocspgrp(tty, real_tty, (pid_t *) arg);
+ case TIOCGSID:
+ return tiocgsid(tty, real_tty, (pid_t *) arg);
+ case TIOCGETD:
+ /* FIXME: check this is ok */
+ return put_user(tty->ldisc.num, (int *) arg);
+ case TIOCSETD:
+ return tiocsetd(tty, (int *) arg);
+#ifdef CONFIG_VT
+ case TIOCLINUX:
+ return tioclinux(tty, arg);
+#endif
+ case TIOCTTYGSTRUCT:
+ return tiocttygstruct(tty, (struct tty_struct *) arg);
+
+ /*
+ * Break handling
+ */
+ case TIOCSBRK: /* Turn break on, unconditionally */
+ tty->driver.break_ctl(tty, -1);
+ return 0;
+
+ case TIOCCBRK: /* Turn break off, unconditionally */
+ tty->driver.break_ctl(tty, 0);
+ return 0;
+ case TCSBRK: /* SVID version: non-zero arg --> no break */
+ /*
+ * XXX is the above comment correct, or the
+ * code below correct? Is this ioctl used at
+ * all by anyone?
+ */
+ if (!arg)
+ return send_break(tty, HZ/4);
+ return 0;
+ case TCSBRKP: /* support for POSIX tcsendbreak() */
+ return send_break(tty, arg ? arg*(HZ/10) : HZ/4);
+ }
+ if (tty->driver.ioctl) {
+ retval = (tty->driver.ioctl)(tty, file, cmd, arg);
+ if (retval != -ENOIOCTLCMD)
+ return retval;
+ }
+ ld = tty_ldisc_ref_wait(tty);
+ retval = -EINVAL;
+ if (ld->ioctl) {
+ retval = ld->ioctl(tty, file, cmd, arg);
+ if (retval == -ENOIOCTLCMD)
+ retval = -EINVAL;
+ }
+ tty_ldisc_deref(ld);
+ return retval;
+}
+
+
+/*
+ * This implements the "Secure Attention Key" --- the idea is to
+ * prevent trojan horses by killing all processes associated with this
+ * tty when the user hits the "Secure Attention Key". Required for
+ * super-paranoid applications --- see the Orange Book for more details.
+ *
+ * This code could be nicer; ideally it should send a HUP, wait a few
+ * seconds, then send a INT, and then a KILL signal. But you then
+ * have to coordinate with the init process, since all processes associated
+ * with the current tty must be dead before the new getty is allowed
+ * to spawn.
+ *
+ * Now, if it would be correct ;-/ The current code has a nasty hole -
+ * it doesn't catch files in flight. We may send the descriptor to ourselves
+ * via AF_UNIX socket, close it and later fetch from socket. FIXME.
+ *
+ * Nasty bug: do_SAK is being called in interrupt context. This can
+ * deadlock. We punt it up to process context. AKPM - 16Mar2001
+ */
+static void __do_SAK(void *arg)
+{
+#ifdef TTY_SOFT_SAK
+ tty_hangup(tty);
+#else
+ struct tty_struct *tty = arg;
+ struct task_struct *p;
+ int session;
+ int i;
+ struct file *filp;
+ struct tty_ldisc *disc;
+
+ if (!tty)
+ return;
+ session = tty->session;
+ /* We don't want an ldisc switch during this */
+ disc = tty_ldisc_ref(tty);
+ if (disc && disc->flush_buffer)
+ disc->flush_buffer(tty);
+ tty_ldisc_deref(disc);
+
+ if (tty->driver.flush_buffer)
+ tty->driver.flush_buffer(tty);
+
+ read_lock(&tasklist_lock);
+ for_each_task(p) {
+ if ((p->tty == tty) ||
+ ((session > 0) && (p->session == session))) {
+ send_sig(SIGKILL, p, 1);
+ continue;
+ }
+ task_lock(p);
+ if (p->files) {
+ read_lock(&p->files->file_lock);
+ for (i=0; i < p->files->max_fds; i++) {
+ filp = fcheck_files(p->files, i);
+ if (filp && (filp->f_op == &tty_fops) &&
+ (filp->private_data == tty)) {
+ send_sig(SIGKILL, p, 1);
+ break;
+ }
+ }
+ read_unlock(&p->files->file_lock);
+ }
+ task_unlock(p);
+ }
+ read_unlock(&tasklist_lock);
+#endif
+}
+
+/*
+ * The tq handling here is a little racy - tty->SAK_tq may already be queued.
+ * But there's no mechanism to fix that without futzing with tqueue_lock.
+ * Fortunately we don't need to worry, because if ->SAK_tq is already queued,
+ * the values which we write to it will be identical to the values which it
+ * already has. --akpm
+ */
+void do_SAK(struct tty_struct *tty)
+{
+ if (!tty)
+ return;
+ PREPARE_TQUEUE(&tty->SAK_tq, __do_SAK, tty);
+ schedule_task(&tty->SAK_tq);
+}
+
+/*
+ * This routine is called out of the software interrupt to flush data
+ * from the flip buffer to the line discipline.
+ */
+static void flush_to_ldisc(void *private_)
+{
+ struct tty_struct *tty = (struct tty_struct *) private_;
+ unsigned char *cp;
+ char *fp;
+ int count;
+ unsigned long flags;
+ struct tty_ldisc *disc;
+
+ disc = tty_ldisc_ref(tty);
+ if (disc == NULL) /* !TTY_LDISC */
+ return;
+
+ if (test_bit(TTY_DONT_FLIP, &tty->flags)) {
+ queue_task(&tty->flip.tqueue, &tq_timer);
+ goto out;
+ }
+ if (tty->flip.buf_num) {
+ cp = tty->flip.char_buf + TTY_FLIPBUF_SIZE;
+ fp = tty->flip.flag_buf + TTY_FLIPBUF_SIZE;
+ tty->flip.buf_num = 0;
+
+ save_flags(flags); cli();
+ tty->flip.char_buf_ptr = tty->flip.char_buf;
+ tty->flip.flag_buf_ptr = tty->flip.flag_buf;
+ } else {
+ cp = tty->flip.char_buf;
+ fp = tty->flip.flag_buf;
+ tty->flip.buf_num = 1;
+
+ save_flags(flags); cli();
+ tty->flip.char_buf_ptr = tty->flip.char_buf + TTY_FLIPBUF_SIZE;
+ tty->flip.flag_buf_ptr = tty->flip.flag_buf + TTY_FLIPBUF_SIZE;
+ }
+ count = tty->flip.count;
+ tty->flip.count = 0;
+ restore_flags(flags);
+
+ disc->receive_buf(tty, cp, fp, count);
+out:
+ tty_ldisc_deref(disc);
+}
+
+/*
+ * Call the ldisc flush directly from a driver. This function may
+ * return an error and need retrying by the user.
+ */
+
+int tty_push_data(struct tty_struct *tty, unsigned char *cp, unsigned char
*fp, int count)
+{
+ int ret = 0;
+ struct tty_ldisc *disc;
+
+ disc = tty_ldisc_ref(tty);
+ if(test_bit(TTY_DONT_FLIP, &tty->flags))
+ ret = -EAGAIN;
+ else if(disc == NULL)
+ ret = -EIO;
+ else
+ disc->receive_buf(tty, cp, fp, count);
+ tty_ldisc_deref(disc);
+ return ret;
+
+}
+
+/*
+ * Routine which returns the baud rate of the tty
+ *
+ * Note that the baud_table needs to be kept in sync with the
+ * include/asm/termbits.h file.
+ */
+static int baud_table[] = {
+ 0, 50, 75, 110, 134, 150, 200, 300, 600, 1200, 1800, 2400, 4800,
+ 9600, 19200, 38400, 57600, 115200, 230400, 460800,
+#ifdef __sparc__
+ 76800, 153600, 307200, 614400, 921600
+#else
+ 500000, 576000, 921600, 1000000, 1152000, 1500000, 2000000,
+ 2500000, 3000000, 3500000, 4000000
+#endif
+};
+
+static int n_baud_table = sizeof(baud_table)/sizeof(int);
+
+int tty_get_baud_rate(struct tty_struct *tty)
+{
+ unsigned int cflag, i;
+
+ cflag = tty->termios->c_cflag;
+
+ i = cflag & CBAUD;
+ if (i & CBAUDEX) {
+ i &= ~CBAUDEX;
+ if (i < 1 || i+15 >= n_baud_table)
+ tty->termios->c_cflag &= ~CBAUDEX;
+ else
+ i += 15;
+ }
+ if (i==15 && tty->alt_speed) {
+ if (!tty->warned) {
+ printk(KERN_WARNING "Use of setserial/setrocket to "
+ "set SPD_* flags is deprecated\n");
+ tty->warned = 1;
+ }
+ return(tty->alt_speed);
+ }
+
+ return baud_table[i];
+}
+
+void tty_flip_buffer_push(struct tty_struct *tty)
+{
+ if (tty->low_latency)
+ flush_to_ldisc((void *) tty);
+ else
+ queue_task(&tty->flip.tqueue, &tq_timer);
+}
+
+/*
+ * This subroutine initializes a tty structure.
+ */
+static void initialize_tty_struct(struct tty_struct *tty)
+{
+ memset(tty, 0, sizeof(struct tty_struct));
+ tty->magic = TTY_MAGIC;
+ tty_ldisc_assign(tty, tty_ldisc_get(N_TTY));
+ tty->pgrp = -1;
+ tty->flip.char_buf_ptr = tty->flip.char_buf;
+ tty->flip.flag_buf_ptr = tty->flip.flag_buf;
+ tty->flip.tqueue.routine = flush_to_ldisc;
+ tty->flip.tqueue.data = tty;
+ init_MUTEX(&tty->flip.pty_sem);
+ init_MUTEX(&tty->termios_sem);
+ init_waitqueue_head(&tty->write_wait);
+ init_waitqueue_head(&tty->read_wait);
+ tty->tq_hangup.routine = do_tty_hangup;
+ tty->tq_hangup.data = tty;
+ sema_init(&tty->atomic_read, 1);
+ sema_init(&tty->atomic_write, 1);
+ spin_lock_init(&tty->read_lock);
+ INIT_LIST_HEAD(&tty->tty_files);
+ INIT_TQUEUE(&tty->SAK_tq, 0, 0);
+}
+
+/*
+ * The default put_char routine if the driver did not define one.
+ */
+void tty_default_put_char(struct tty_struct *tty, unsigned char ch)
+{
+ tty->driver.write(tty, 0, &ch, 1);
+}
+
+/*
+ * Register a tty device described by <driver>, with minor number <minor>.
+ */
+void tty_register_devfs (struct tty_driver *driver, unsigned int flags,
unsigned minor)
+{
+#ifdef CONFIG_DEVFS_FS
+ umode_t mode = S_IFCHR | S_IRUSR | S_IWUSR;
+ kdev_t device = MKDEV (driver->major, minor);
+ int idx = minor - driver->minor_start;
+ char buf[32];
+
+ switch (device) {
+ case TTY_DEV:
+ case PTMX_DEV:
+ mode |= S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
+ break;
+ default:
+ if (driver->major == PTY_MASTER_MAJOR)
+ mode |= S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
+ break;
+ }
+ if ( (minor < driver->minor_start) ||
+ (minor >= driver->minor_start + driver->num) ) {
+ printk(KERN_ERR "Attempt to register invalid minor number "
+ "with devfs (%d:%d).\n", (int)driver->major,(int)minor);
+ return;
+ }
+# ifdef CONFIG_UNIX98_PTYS
+ if ( (driver->major >= UNIX98_PTY_SLAVE_MAJOR) &&
+ (driver->major < UNIX98_PTY_SLAVE_MAJOR + UNIX98_NR_MAJORS) )
+ flags |= DEVFS_FL_CURRENT_OWNER;
+# endif
+ sprintf(buf, driver->name, idx + driver->name_base);
+ devfs_register (NULL, buf, flags | DEVFS_FL_DEFAULT,
+ driver->major, minor, mode, &tty_fops, NULL);
+#endif /* CONFIG_DEVFS_FS */
+}
+
+void tty_unregister_devfs (struct tty_driver *driver, unsigned minor)
+{
+#ifdef CONFIG_DEVFS_FS
+ void * handle;
+ int idx = minor - driver->minor_start;
+ char buf[32];
+
+ sprintf(buf, driver->name, idx + driver->name_base);
+ handle = devfs_find_handle (NULL, buf, driver->major, minor,
+ DEVFS_SPECIAL_CHR, 0);
+ devfs_unregister (handle);
+#endif /* CONFIG_DEVFS_FS */
+}
+
+EXPORT_SYMBOL(tty_register_devfs);
+EXPORT_SYMBOL(tty_unregister_devfs);
+
+/*
+ * Called by a tty driver to register itself.
+ */
+int tty_register_driver(struct tty_driver *driver)
+{
+ int error;
+ int i;
+
+ if (driver->flags & TTY_DRIVER_INSTALLED)
+ return 0;
+
+ error = devfs_register_chrdev(driver->major, driver->name, &tty_fops);
+ if (error < 0)
+ return error;
+ else if(driver->major == 0)
+ driver->major = error;
+
+ if (!driver->put_char)
+ driver->put_char = tty_default_put_char;
+
+ driver->prev = 0;
+ driver->next = tty_drivers;
+ if (tty_drivers) tty_drivers->prev = driver;
+ tty_drivers = driver;
+
+ if ( !(driver->flags & TTY_DRIVER_NO_DEVFS) ) {
+ for(i = 0; i < driver->num; i++)
+ tty_register_devfs(driver, 0, driver->minor_start + i);
+ }
+ proc_tty_register_driver(driver);
+ return error;
+}
+
+/*
+ * Called by a tty driver to unregister itself.
+ */
+int tty_unregister_driver(struct tty_driver *driver)
+{
+ int retval;
+ struct tty_driver *p;
+ int i, found = 0;
+ struct termios *tp;
+ const char *othername = NULL;
+
+ if (*driver->refcount)
+ return -EBUSY;
+
+ for (p = tty_drivers; p; p = p->next) {
+ if (p == driver)
+ found++;
+ else if (p->major == driver->major)
+ othername = p->name;
+ }
+
+ if (!found)
+ return -ENOENT;
+
+ if (othername == NULL) {
+ retval = devfs_unregister_chrdev(driver->major, driver->name);
+ if (retval)
+ return retval;
+ } else
+ devfs_register_chrdev(driver->major, othername, &tty_fops);
+
+ if (driver->prev)
+ driver->prev->next = driver->next;
+ else
+ tty_drivers = driver->next;
+
+ if (driver->next)
+ driver->next->prev = driver->prev;
+
+ /*
+ * Free the termios and termios_locked structures because
+ * we don't want to get memory leaks when modular tty
+ * drivers are removed from the kernel.
+ */
+ for (i = 0; i < driver->num; i++) {
+ tp = driver->termios[i];
+ if (tp) {
+ driver->termios[i] = NULL;
+ kfree(tp);
+ }
+ tp = driver->termios_locked[i];
+ if (tp) {
+ driver->termios_locked[i] = NULL;
+ kfree(tp);
+ }
+ tty_unregister_devfs(driver, driver->minor_start + i);
+ }
+ proc_tty_unregister_driver(driver);
+ return 0;
+}
+
+
+/*
+ * Initialize the console device. This is called *early*, so
+ * we can't necessarily depend on lots of kernel help here.
+ * Just do some early initializations, and do the complex setup
+ * later.
+ */
+void __init console_init(void)
+{
+ /* Setup the default TTY line discipline. */
+ memset(tty_ldiscs, 0, NR_LDISCS*sizeof(struct tty_ldisc));
+ (void) tty_register_ldisc(N_TTY, &tty_ldisc_N_TTY);
+
+ /*
+ * Set up the standard termios. Individual tty drivers may
+ * deviate from this; this is used as a template.
+ */
+ memset(&tty_std_termios, 0, sizeof(struct termios));
+ memcpy(tty_std_termios.c_cc, INIT_C_CC, NCCS);
+ tty_std_termios.c_iflag = ICRNL | IXON;
+ tty_std_termios.c_oflag = OPOST | ONLCR;
+ tty_std_termios.c_cflag = B38400 | CS8 | CREAD | HUPCL;
+ tty_std_termios.c_lflag = ISIG | ICANON | ECHO | ECHOE | ECHOK |
+ ECHOCTL | ECHOKE | IEXTEN;
+
+ /*
+ * set up the console device so that later boot sequences can
+ * inform about problems etc..
+ */
+#ifdef CONFIG_EARLY_PRINTK
+ disable_early_printk();
+#endif
+
+#ifdef CONFIG_XEN_CONSOLE
+ xen_console_init();
+#endif
+
+#ifdef CONFIG_VT
+ con_init();
+#endif
+#ifdef CONFIG_AU1X00_SERIAL_CONSOLE
+ au1x00_serial_console_init();
+#endif
+#ifdef CONFIG_SERIAL_CONSOLE
+#if (defined(CONFIG_8xx) || defined(CONFIG_CPM2))
+ console_8xx_init();
+#elif defined(CONFIG_MAC_SERIAL) && defined(CONFIG_SERIAL)
+ if (_machine == _MACH_Pmac)
+ mac_scc_console_init();
+ else
+ serial_console_init();
+#elif defined(CONFIG_MAC_SERIAL)
+ mac_scc_console_init();
+#elif defined(CONFIG_PARISC)
+ pdc_console_init();
+#elif defined(CONFIG_SERIAL)
+ serial_console_init();
+#endif /* CONFIG_8xx */
+#if defined(CONFIG_MVME162_SCC) || defined(CONFIG_BVME6000_SCC) ||
defined(CONFIG_MVME147_SCC)
+ vme_scc_console_init();
+#endif
+#if defined(CONFIG_SERIAL167)
+ serial167_console_init();
+#endif
+#if defined(CONFIG_SH_SCI)
+ sci_console_init();
+#endif
+#endif
+#ifdef CONFIG_SERIAL_DEC_CONSOLE
+ dec_serial_console_init();
+#endif
+#ifdef CONFIG_TN3270_CONSOLE
+ tub3270_con_init();
+#endif
+#ifdef CONFIG_TN3215
+ con3215_init();
+#endif
+#ifdef CONFIG_HWC
+ hwc_console_init();
+#endif
+#ifdef CONFIG_STDIO_CONSOLE
+ stdio_console_init();
+#endif
+#ifdef CONFIG_SERIAL_21285_CONSOLE
+ rs285_console_init();
+#endif
+#ifdef CONFIG_SERIAL_SA1100_CONSOLE
+ sa1100_rs_console_init();
+#endif
+#ifdef CONFIG_ARC_CONSOLE
+ arc_console_init();
+#endif
+#ifdef CONFIG_SERIAL_AMBA_CONSOLE
+ ambauart_console_init();
+#endif
+#ifdef CONFIG_SERIAL_TX3912_CONSOLE
+ tx3912_console_init();
+#endif
+#ifdef CONFIG_TXX927_SERIAL_CONSOLE
+ txx927_console_init();
+#endif
+#ifdef CONFIG_SERIAL_TXX9_CONSOLE
+ txx9_serial_console_init();
+#endif
+#ifdef CONFIG_SIBYTE_SB1250_DUART_CONSOLE
+ sb1250_serial_console_init();
+#endif
+#ifdef CONFIG_IP22_SERIAL
+ sgi_serial_console_init();
+#endif
+}
+
+static struct tty_driver dev_tty_driver, dev_syscons_driver;
+#ifdef CONFIG_UNIX98_PTYS
+static struct tty_driver dev_ptmx_driver;
+#endif
+#ifdef CONFIG_HVC_CONSOLE
+ hvc_console_init();
+#endif
+#ifdef CONFIG_VT
+static struct tty_driver dev_console_driver;
+#endif
+
+/*
+ * Ok, now we can initialize the rest of the tty devices and can count
+ * on memory allocations, interrupts etc..
+ */
+void __init tty_init(void)
+{
+ /*
+ * dev_tty_driver and dev_console_driver are actually magic
+ * devices which get redirected at open time. Nevertheless,
+ * we register them so that register_chrdev is called
+ * appropriately.
+ */
+ memset(&dev_tty_driver, 0, sizeof(struct tty_driver));
+ dev_tty_driver.magic = TTY_DRIVER_MAGIC;
+ dev_tty_driver.driver_name = "/dev/tty";
+ dev_tty_driver.name = dev_tty_driver.driver_name + 5;
+ dev_tty_driver.name_base = 0;
+ dev_tty_driver.major = TTYAUX_MAJOR;
+ dev_tty_driver.minor_start = 0;
+ dev_tty_driver.num = 1;
+ dev_tty_driver.type = TTY_DRIVER_TYPE_SYSTEM;
+ dev_tty_driver.subtype = SYSTEM_TYPE_TTY;
+
+ if (tty_register_driver(&dev_tty_driver))
+ panic("Couldn't register /dev/tty driver\n");
+
+ dev_syscons_driver = dev_tty_driver;
+ dev_syscons_driver.driver_name = "/dev/console";
+ dev_syscons_driver.name = dev_syscons_driver.driver_name + 5;
+ dev_syscons_driver.major = TTYAUX_MAJOR;
+ dev_syscons_driver.minor_start = 1;
+ dev_syscons_driver.type = TTY_DRIVER_TYPE_SYSTEM;
+ dev_syscons_driver.subtype = SYSTEM_TYPE_SYSCONS;
+
+ if (tty_register_driver(&dev_syscons_driver))
+ panic("Couldn't register /dev/console driver\n");
+
+ /* console calls tty_register_driver() before kmalloc() works.
+ * Thus, we can't devfs_register() then. Do so now, instead.
+ */
+#ifdef CONFIG_VT
+ con_init_devfs();
+#endif
+
+#ifdef CONFIG_UNIX98_PTYS
+ dev_ptmx_driver = dev_tty_driver;
+ dev_ptmx_driver.driver_name = "/dev/ptmx";
+ dev_ptmx_driver.name = dev_ptmx_driver.driver_name + 5;
+ dev_ptmx_driver.major= MAJOR(PTMX_DEV);
+ dev_ptmx_driver.minor_start = MINOR(PTMX_DEV);
+ dev_ptmx_driver.type = TTY_DRIVER_TYPE_SYSTEM;
+ dev_ptmx_driver.subtype = SYSTEM_TYPE_SYSPTMX;
+
+ if (tty_register_driver(&dev_ptmx_driver))
+ panic("Couldn't register /dev/ptmx driver\n");
+#endif
+
+#ifdef CONFIG_VT
+ dev_console_driver = dev_tty_driver;
+ dev_console_driver.driver_name = "/dev/vc/0";
+ dev_console_driver.name = dev_console_driver.driver_name + 5;
+ dev_console_driver.major = TTY_MAJOR;
+ dev_console_driver.type = TTY_DRIVER_TYPE_SYSTEM;
+ dev_console_driver.subtype = SYSTEM_TYPE_CONSOLE;
+
+ if (tty_register_driver(&dev_console_driver))
+ panic("Couldn't register /dev/tty0 driver\n");
+
+ kbd_init();
+#endif
+
+#ifdef CONFIG_SGI_L1_SERIAL_CONSOLE
+ if (ia64_platform_is("sn2")) {
+ sn_sal_serial_console_init();
+ return; /* only one console right now for SN2 */
+ }
+#endif
+#ifdef CONFIG_ESPSERIAL /* init ESP before rs, so rs doesn't see the port */
+ espserial_init();
+#endif
+#if defined(CONFIG_MVME162_SCC) || defined(CONFIG_BVME6000_SCC) ||
defined(CONFIG_MVME147_SCC)
+ vme_scc_init();
+#endif
+#ifdef CONFIG_SERIAL_TX3912
+ tx3912_rs_init();
+#endif
+#ifdef CONFIG_ROCKETPORT
+ rp_init();
+#endif
+#ifdef CONFIG_SERIAL167
+ serial167_init();
+#endif
+#ifdef CONFIG_CYCLADES
+ cy_init();
+#endif
+#ifdef CONFIG_STALLION
+ stl_init();
+#endif
+#ifdef CONFIG_ISTALLION
+ stli_init();
+#endif
+#ifdef CONFIG_DIGI
+ pcxe_init();
+#endif
+#ifdef CONFIG_DIGIEPCA
+ pc_init();
+#endif
+#ifdef CONFIG_SPECIALIX
+ specialix_init();
+#endif
+#if (defined(CONFIG_8xx) || defined(CONFIG_CPM2))
+ rs_8xx_init();
+#endif /* CONFIG_8xx */
+ pty_init();
+#ifdef CONFIG_MOXA_SMARTIO
+ mxser_init();
+#endif
+#ifdef CONFIG_MOXA_INTELLIO
+ moxa_init();
+#endif
+#ifdef CONFIG_VT
+ vcs_init();
+#endif
+#ifdef CONFIG_TN3270
+ tub3270_init();
+#endif
+#ifdef CONFIG_TN3215
+ tty3215_init();
+#endif
+#ifdef CONFIG_HWC
+ hwc_tty_init();
+#endif
+#ifdef CONFIG_A2232
+ a2232board_init();
+#endif
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/pgtable.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/pgtable.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,494 @@
+#ifndef _I386_PGTABLE_H
+#define _I386_PGTABLE_H
+
+#include <linux/config.h>
+#include <asm-xen/hypervisor.h>
+
+/*
+ * The Linux memory management assumes a three-level page table setup. On
+ * the i386, we use that, but "fold" the mid level into the top-level page
+ * table, so that we physically have the same two-level page table as the
+ * i386 mmu expects.
+ *
+ * This file contains the functions and defines necessary to modify and use
+ * the i386 page table tree.
+ */
+#ifndef __ASSEMBLY__
+#include <asm/processor.h>
+#include <asm/fixmap.h>
+#include <linux/threads.h>
+
+#ifndef _I386_BITOPS_H
+#include <asm/bitops.h>
+#endif
+
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+extern unsigned long empty_zero_page[1024];
+extern pgd_t swapper_pg_dir[1024];
+extern kmem_cache_t *pgd_cache;
+extern kmem_cache_t *pmd_cache;
+extern spinlock_t pgd_lock;
+extern struct page *pgd_list;
+
+void pmd_ctor(void *, kmem_cache_t *, unsigned long);
+void pgd_ctor(void *, kmem_cache_t *, unsigned long);
+void pgd_dtor(void *, kmem_cache_t *, unsigned long);
+void pgtable_cache_init(void);
+void paging_init(void);
+
+/*
+ * The Linux x86 paging architecture is 'compile-time dual-mode', it
+ * implements both the traditional 2-level x86 page tables and the
+ * newer 3-level PAE-mode page tables.
+ */
+#ifdef CONFIG_X86_PAE
+# include <asm/pgtable-3level-defs.h>
+# define PMD_SIZE (1UL << PMD_SHIFT)
+# define PMD_MASK (~(PMD_SIZE-1))
+#else
+# include <asm/pgtable-2level-defs.h>
+#endif
+
+#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE-1))
+
+#define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE)
+#define FIRST_USER_PGD_NR 0
+
+#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
+#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)
+
+#define TWOLEVEL_PGDIR_SHIFT 22
+#define BOOT_USER_PGD_PTRS (__PAGE_OFFSET >> TWOLEVEL_PGDIR_SHIFT)
+#define BOOT_KERNEL_PGD_PTRS (1024-BOOT_USER_PGD_PTRS)
+
+/* Just any arbitrary offset to the start of the vmalloc VM area: the
+ * current 8MB value just means that there will be a 8MB "hole" after the
+ * physical memory until the kernel virtual memory starts. That means that
+ * any out-of-bounds memory accesses will hopefully be caught.
+ * The vmalloc() routines leaves a hole of 4kB between each vmalloced
+ * area for the same reason. ;)
+ */
+#define VMALLOC_OFFSET (8*1024*1024)
+#define VMALLOC_START (((unsigned long) high_memory + vmalloc_earlyreserve + \
+ 2*VMALLOC_OFFSET-1) & ~(VMALLOC_OFFSET-1))
+#ifdef CONFIG_HIGHMEM
+# define VMALLOC_END (PKMAP_BASE-2*PAGE_SIZE)
+#else
+# define VMALLOC_END (FIXADDR_START-2*PAGE_SIZE)
+#endif
+
+/*
+ * The 4MB page is guessing.. Detailed in the infamous "Chapter H"
+ * of the Pentium details, but assuming intel did the straightforward
+ * thing, this bit set in the page directory entry just means that
+ * the page directory entry points directly to a 4MB-aligned block of
+ * memory.
+ */
+#define _PAGE_BIT_PRESENT 0
+#define _PAGE_BIT_RW 1
+#define _PAGE_BIT_USER 2
+#define _PAGE_BIT_PWT 3
+#define _PAGE_BIT_PCD 4
+#define _PAGE_BIT_ACCESSED 5
+#define _PAGE_BIT_DIRTY 6
+#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page, Pentium+, if
present.. */
+#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
+#define _PAGE_BIT_UNUSED1 9 /* available for programmer */
+#define _PAGE_BIT_UNUSED2 10
+#define _PAGE_BIT_UNUSED3 11
+#define _PAGE_BIT_NX 63
+
+#define _PAGE_PRESENT 0x001
+#define _PAGE_RW 0x002
+#define _PAGE_USER 0x004
+#define _PAGE_PWT 0x008
+#define _PAGE_PCD 0x010
+#define _PAGE_ACCESSED 0x020
+#define _PAGE_DIRTY 0x040
+#define _PAGE_PSE 0x080 /* 4 MB (or 2MB) page, Pentium+, if present.. */
+#define _PAGE_GLOBAL 0x100 /* Global TLB entry PPro+ */
+#define _PAGE_UNUSED1 0x200 /* available for programmer */
+#define _PAGE_UNUSED2 0x400
+#define _PAGE_UNUSED3 0x800
+
+#define _PAGE_FILE 0x040 /* set:pagecache unset:swap */
+#define _PAGE_PROTNONE 0x080 /* If not present */
+#ifdef CONFIG_X86_PAE
+#define _PAGE_NX (1ULL<<_PAGE_BIT_NX)
+#else
+#define _PAGE_NX 0
+#endif
+
+#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED
| _PAGE_DIRTY)
+#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED |
_PAGE_DIRTY)
+#define _PAGE_CHG_MASK (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+
+#define PAGE_NONE \
+ __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
+#define PAGE_SHARED \
+ __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
+
+#define PAGE_SHARED_EXEC \
+ __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_COPY_NOEXEC \
+ __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
+#define PAGE_COPY_EXEC \
+ __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_COPY \
+ PAGE_COPY_NOEXEC
+#define PAGE_READONLY \
+ __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
+#define PAGE_READONLY_EXEC \
+ __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+
+#define _PAGE_KERNEL \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX)
+#define _PAGE_KERNEL_EXEC \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
+
+extern unsigned long long __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
+#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW)
+#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_PCD)
+#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE)
+#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE)
+
+#define PAGE_KERNEL __pgprot(__PAGE_KERNEL)
+#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO)
+#define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC)
+#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE)
+#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE)
+#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC)
+
+/*
+ * The i386 can't do page protection for execute, and considers that
+ * the same are read. Also, write permissions imply read permissions.
+ * This is the closest we can get..
+ */
+#define __P000 PAGE_NONE
+#define __P001 PAGE_READONLY
+#define __P010 PAGE_COPY
+#define __P011 PAGE_COPY
+#define __P100 PAGE_READONLY_EXEC
+#define __P101 PAGE_READONLY_EXEC
+#define __P110 PAGE_COPY_EXEC
+#define __P111 PAGE_COPY_EXEC
+
+#define __S000 PAGE_NONE
+#define __S001 PAGE_READONLY
+#define __S010 PAGE_SHARED
+#define __S011 PAGE_SHARED
+#define __S100 PAGE_READONLY_EXEC
+#define __S101 PAGE_READONLY_EXEC
+#define __S110 PAGE_SHARED_EXEC
+#define __S111 PAGE_SHARED_EXEC
+
+/*
+ * Define this if things work differently on an i386 and an i486:
+ * it will (on an i486) warn about kernel memory accesses that are
+ * done without a 'verify_area(VERIFY_WRITE,..)'
+ */
+#undef TEST_VERIFY_AREA
+
+/* The boot page tables (all created as a single array) */
+extern unsigned long pg0[];
+
+#define pte_present(x) ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
+#define pte_clear(xp) do { set_pte(xp, __pte(0)); } while (0)
+
+#define pmd_none(x) (!pmd_val(x))
+/* pmd_present doesn't just test the _PAGE_PRESENT bit since wr.p.t.
+ can temporarily clear it. */
+#define pmd_present(x) (pmd_val(x))
+#define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0)
+#define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER &
~_PAGE_PRESENT)) != (_KERNPG_TABLE & ~_PAGE_PRESENT))
+
+
+#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+static inline int pte_user(pte_t pte) { return (pte).pte_low &
_PAGE_USER; }
+static inline int pte_read(pte_t pte) { return (pte).pte_low &
_PAGE_USER; }
+static inline int pte_dirty(pte_t pte) { return (pte).pte_low &
_PAGE_DIRTY; }
+static inline int pte_young(pte_t pte) { return (pte).pte_low &
_PAGE_ACCESSED; }
+static inline int pte_write(pte_t pte) { return (pte).pte_low &
_PAGE_RW; }
+
+/*
+ * The following only works if pte_present() is not true.
+ */
+static inline int pte_file(pte_t pte) { return (pte).pte_low &
_PAGE_FILE; }
+
+static inline pte_t pte_rdprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER;
return pte; }
+static inline pte_t pte_exprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER;
return pte; }
+static inline pte_t pte_mkclean(pte_t pte) { (pte).pte_low &=
~_PAGE_DIRTY; return pte; }
+static inline pte_t pte_mkold(pte_t pte) { (pte).pte_low &=
~_PAGE_ACCESSED; return pte; }
+static inline pte_t pte_wrprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_RW;
return pte; }
+static inline pte_t pte_mkread(pte_t pte) { (pte).pte_low |= _PAGE_USER;
return pte; }
+static inline pte_t pte_mkexec(pte_t pte) { (pte).pte_low |= _PAGE_USER;
return pte; }
+static inline pte_t pte_mkdirty(pte_t pte) { (pte).pte_low |= _PAGE_DIRTY;
return pte; }
+static inline pte_t pte_mkyoung(pte_t pte) { (pte).pte_low |=
_PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkwrite(pte_t pte) { (pte).pte_low |= _PAGE_RW;
return pte; }
+
+#ifdef CONFIG_X86_PAE
+# include <asm/pgtable-3level.h>
+#else
+# include <asm/pgtable-2level.h>
+#endif
+
+static inline int ptep_test_and_clear_dirty(pte_t *ptep)
+{
+ if (!pte_dirty(*ptep))
+ return 0;
+ return test_and_clear_bit(_PAGE_BIT_DIRTY, &ptep->pte_low);
+}
+
+static inline int ptep_test_and_clear_young(pte_t *ptep)
+{
+ if (!pte_young(*ptep))
+ return 0;
+ return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte_low);
+}
+
+static inline void ptep_set_wrprotect(pte_t *ptep)
+{
+ if (pte_write(*ptep))
+ clear_bit(_PAGE_BIT_RW, &ptep->pte_low);
+}
+
+static inline void ptep_mkdirty(pte_t *ptep)
+{
+ if (!pte_dirty(*ptep))
+ set_bit(_PAGE_BIT_DIRTY, &ptep->pte_low);
+}
+
+/*
+ * Macro to mark a page protection value as "uncacheable". On processors
which do not support
+ * it, this is a no-op.
+ */
+#define pgprot_noncached(prot) ((boot_cpu_data.x86 > 3)
\
+ ? (__pgprot(pgprot_val(prot) | _PAGE_PCD |
_PAGE_PWT)) : (prot))
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ */
+
+#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
+#define mk_pte_huge(entry) ((entry).pte_low |= _PAGE_PRESENT | _PAGE_PSE)
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+ pte.pte_low &= _PAGE_CHG_MASK;
+ pte.pte_low |= pgprot_val(newprot);
+#ifdef CONFIG_X86_PAE
+ /*
+ * Chop off the NX bit (if present), and add the NX portion of
+ * the newprot (if present):
+ */
+ pte.pte_high &= ~(1 << (_PAGE_BIT_NX - 32));
+ pte.pte_high |= (pgprot_val(newprot) >> 32) & \
+ (__supported_pte_mask >> 32);
+#endif
+ return pte;
+}
+
+#define page_pte(page) page_pte_prot(page, __pgprot(0))
+
+#define pmd_large(pmd) \
+((pmd_val(pmd) & (_PAGE_PSE|_PAGE_PRESENT)) == (_PAGE_PSE|_PAGE_PRESENT))
+
+/*
+ * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
+ *
+ * this macro returns the index of the entry in the pgd page which would
+ * control the given virtual address
+ */
+#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
+#define pgd_index_k(addr) pgd_index(addr)
+
+/*
+ * pgd_offset() returns a (pgd_t *)
+ * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
+ */
+#define pgd_offset(mm, address) ((mm)->pgd+pgd_index(address))
+
+/*
+ * a shortcut which implies the use of the kernel's pgd, instead
+ * of a process's
+ */
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+/*
+ * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
+ *
+ * this macro returns the index of the entry in the pmd page which would
+ * control the given virtual address
+ */
+#define pmd_index(address) \
+ (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
+
+/*
+ * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
+ *
+ * this macro returns the index of the entry in the pte page which would
+ * control the given virtual address
+ */
+#define pte_index(address) \
+ (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_offset_kernel(dir, address) \
+ ((pte_t *) pmd_page_kernel(*(dir)) + pte_index(address))
+
+/*
+ * Helper function that returns the kernel pagetable entry controlling
+ * the virtual address 'address'. NULL means no pagetable entry present.
+ * NOTE: the return type is pte_t but if the pmd is PSE then we return it
+ * as a pte too.
+ */
+extern pte_t *lookup_address(unsigned long address);
+
+/*
+ * Make a given kernel text page executable/non-executable.
+ * Returns the previous executability setting of that page (which
+ * is used to restore the previous state). Used by the SMP bootup code.
+ * NOTE: this is an __init function for security reasons.
+ */
+#ifdef CONFIG_X86_PAE
+ extern int set_kernel_exec(unsigned long vaddr, int enable);
+#else
+ static inline int set_kernel_exec(unsigned long vaddr, int enable) { return
0;}
+#endif
+
+extern void noexec_setup(const char *str);
+
+#if defined(CONFIG_HIGHPTE)
+#define pte_offset_map(dir, address) \
+ ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)),KM_PTE0) + \
+ pte_index(address))
+#define pte_offset_map_nested(dir, address) \
+ ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)),KM_PTE1) + \
+ pte_index(address))
+#define pte_unmap(pte) kunmap_atomic(pte, KM_PTE0)
+#define pte_unmap_nested(pte) kunmap_atomic(pte, KM_PTE1)
+#else
+#define pte_offset_map(dir, address) \
+ ((pte_t *)page_address(pmd_page(*(dir))) + pte_index(address))
+#define pte_offset_map_nested(dir, address) pte_offset_map(dir, address)
+#define pte_unmap(pte) do { } while (0)
+#define pte_unmap_nested(pte) do { } while (0)
+#endif
+
+/*
+ * The i386 doesn't have any external MMU info: the kernel page
+ * tables contain all the necessary information.
+ *
+ * Also, we only update the dirty/accessed state if we set
+ * the dirty bit by hand in the kernel, since the hardware
+ * will do the accessed bit for us, and we don't want to
+ * race with other CPU's that might be updating the dirty
+ * bit at the same time.
+ */
+#define update_mmu_cache(vma,address,pte) do { } while (0)
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
+ do { \
+ if (__dirty) { \
+ if ( likely((__vma)->vm_mm == current->mm) ) { \
+ HYPERVISOR_update_va_mapping((__address),
(__entry), UVMF_INVLPG|UVMF_MULTI|(unsigned
long)((__vma)->vm_mm->cpu_vm_mask.bits)); \
+ } else { \
+ xen_l1_entry_update((__ptep), (__entry).pte_low); \
+ flush_tlb_page((__vma), (__address)); \
+ } \
+ } \
+ } while (0)
+
+#define __HAVE_ARCH_PTEP_ESTABLISH
+#define ptep_establish(__vma, __address, __ptep, __entry) \
+do { \
+ ptep_set_access_flags(__vma, __address, __ptep, __entry, 1); \
+} while (0)
+
+#define __HAVE_ARCH_PTEP_ESTABLISH_NEW
+#define ptep_establish_new(__vma, __address, __ptep, __entry) \
+do { \
+ if (likely((__vma)->vm_mm == current->mm)) { \
+ HYPERVISOR_update_va_mapping((__address), \
+ __entry, 0); \
+ } else { \
+ xen_l1_entry_update((__ptep), (__entry).pte_low); \
+ } \
+} while (0)
+
+#ifndef CONFIG_XEN_SHADOW_MODE
+void make_lowmem_page_readonly(void *va);
+void make_lowmem_page_writable(void *va);
+void make_page_readonly(void *va);
+void make_page_writable(void *va);
+void make_pages_readonly(void *va, unsigned int nr);
+void make_pages_writable(void *va, unsigned int nr);
+#else
+#define make_lowmem_page_readonly(_va) ((void)0)
+#define make_lowmem_page_writable(_va) ((void)0)
+#define make_page_readonly(_va) ((void)0)
+#define make_page_writable(_va) ((void)0)
+#define make_pages_readonly(_va, _nr) ((void)0)
+#define make_pages_writable(_va, _nr) ((void)0)
+#endif
+
+#define virt_to_ptep(__va) \
+({ \
+ pgd_t *__pgd = pgd_offset_k((unsigned long)(__va)); \
+ pud_t *__pud = pud_offset(__pgd, (unsigned long)(__va)); \
+ pmd_t *__pmd = pmd_offset(__pud, (unsigned long)(__va)); \
+ pte_offset_kernel(__pmd, (unsigned long)(__va)); \
+})
+
+#define arbitrary_virt_to_machine(__va)
\
+({ \
+ pte_t *__pte = virt_to_ptep(__va); \
+ unsigned long __pa = (*(unsigned long *)__pte) & PAGE_MASK; \
+ __pa | ((unsigned long)(__va) & (PAGE_SIZE-1)); \
+})
+
+#endif /* !__ASSEMBLY__ */
+
+#ifndef CONFIG_DISCONTIGMEM
+#define kern_addr_valid(addr) (1)
+#endif /* !CONFIG_DISCONTIGMEM */
+
+int direct_remap_area_pages(struct mm_struct *mm,
+ unsigned long address,
+ unsigned long machine_addr,
+ unsigned long size,
+ pgprot_t prot,
+ domid_t domid);
+int __direct_remap_area_pages(struct mm_struct *mm,
+ unsigned long address,
+ unsigned long size,
+ mmu_update_t *v);
+
+#define io_remap_page_range(vma,from,phys,size,prot) \
+direct_remap_area_pages(vma->vm_mm,from,phys,size,prot,DOMID_IO)
+
+#define io_remap_pfn_range(vma,from,pfn,size,prot) \
+direct_remap_area_pages(vma->vm_mm,from,pfn<<PAGE_SHIFT,size,prot,DOMID_IO)
+
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+#define __HAVE_ARCH_PTEP_MKDIRTY
+#define __HAVE_ARCH_PTE_SAME
+#include <asm-generic/pgtable.h>
+
+#endif /* _I386_PGTABLE_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/acpi/boot.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/acpi/boot.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,906 @@
+/*
+ * boot.c - Architecture-Specific Low-Level ACPI Boot Support
+ *
+ * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@xxxxxxxxx>
+ * Copyright (C) 2001 Jun Nakajima <jun.nakajima@xxxxxxxxx>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#include <linux/init.h>
+#include <linux/config.h>
+#include <linux/acpi.h>
+#include <linux/efi.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+
+#include <asm/pgtable.h>
+#include <asm/io_apic.h>
+#include <asm/apic.h>
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/mpspec.h>
+#ifdef CONFIG_XEN
+#include <asm/fixmap.h>
+#endif
+
+void (*pm_power_off)(void) = NULL;
+
+#ifdef CONFIG_X86_64
+
+static inline void acpi_madt_oem_check(char *oem_id, char *oem_table_id) { }
+extern void __init clustered_apic_check(void);
+static inline int ioapic_setup_disabled(void) { return 0; }
+#include <asm/proto.h>
+
+#else /* X86 */
+
+#ifdef CONFIG_X86_LOCAL_APIC
+#include <mach_apic.h>
+#include <mach_mpparse.h>
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+#endif /* X86 */
+
+#define BAD_MADT_ENTRY(entry, end) ( \
+ (!entry) || (unsigned long)entry + sizeof(*entry) > end || \
+ ((acpi_table_entry_header *)entry)->length != sizeof(*entry))
+
+#define PREFIX "ACPI: "
+
+#ifdef CONFIG_ACPI_PCI
+int acpi_noirq __initdata; /* skip ACPI IRQ initialization */
+int acpi_pci_disabled __initdata; /* skip ACPI PCI scan and IRQ initialization
*/
+#else
+int acpi_noirq __initdata = 1;
+int acpi_pci_disabled __initdata = 1;
+#endif
+int acpi_ht __initdata = 1; /* enable HT */
+
+int acpi_lapic;
+int acpi_ioapic;
+int acpi_strict;
+EXPORT_SYMBOL(acpi_strict);
+
+acpi_interrupt_flags acpi_sci_flags __initdata;
+int acpi_sci_override_gsi __initdata;
+int acpi_skip_timer_override __initdata;
+
+#ifdef CONFIG_X86_LOCAL_APIC
+static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
+#endif
+
+#ifndef __HAVE_ARCH_CMPXCHG
+#warning ACPI uses CMPXCHG, i486 and later hardware
+#endif
+
+#define MAX_MADT_ENTRIES 256
+u8 x86_acpiid_to_apicid[MAX_MADT_ENTRIES] =
+ { [0 ... MAX_MADT_ENTRIES-1] = 0xff };
+EXPORT_SYMBOL(x86_acpiid_to_apicid);
+
+/* --------------------------------------------------------------------------
+ Boot-time Configuration
+ --------------------------------------------------------------------------
*/
+
+/*
+ * The default interrupt routing model is PIC (8259). This gets
+ * overriden if IOAPICs are enumerated (below).
+ */
+enum acpi_irq_model_id acpi_irq_model = ACPI_IRQ_MODEL_PIC;
+
+#if defined(CONFIG_X86_64) && !defined(CONFIG_XEN)
+
+/* rely on all ACPI tables being in the direct mapping */
+char *__acpi_map_table(unsigned long phys_addr, unsigned long size)
+{
+ if (!phys_addr || !size)
+ return NULL;
+
+ if (phys_addr < (end_pfn_map << PAGE_SHIFT))
+ return __va(phys_addr);
+
+ return NULL;
+}
+
+#else
+
+/*
+ * Temporarily use the virtual area starting from FIX_IO_APIC_BASE_END,
+ * to map the target physical address. The problem is that set_fixmap()
+ * provides a single page, and it is possible that the page is not
+ * sufficient.
+ * By using this area, we can map up to MAX_IO_APICS pages temporarily,
+ * i.e. until the next __va_range() call.
+ *
+ * Important Safety Note: The fixed I/O APIC page numbers are *subtracted*
+ * from the fixed base. That's why we start at FIX_IO_APIC_BASE_END and
+ * count idx down while incrementing the phys address.
+ */
+char *__acpi_map_table(unsigned long phys, unsigned long size)
+{
+ unsigned long base, offset, mapped_size;
+ int idx;
+
+#ifndef CONFIG_XEN
+ if (phys + size < 8*1024*1024)
+ return __va(phys);
+#endif
+
+ offset = phys & (PAGE_SIZE - 1);
+ mapped_size = PAGE_SIZE - offset;
+ set_fixmap(FIX_ACPI_END, phys);
+ base = fix_to_virt(FIX_ACPI_END);
+
+ /*
+ * Most cases can be covered by the below.
+ */
+ idx = FIX_ACPI_END;
+ while (mapped_size < size) {
+ if (--idx < FIX_ACPI_BEGIN)
+ return NULL; /* cannot handle this */
+ phys += PAGE_SIZE;
+ set_fixmap(idx, phys);
+ mapped_size += PAGE_SIZE;
+ }
+
+ return ((unsigned char *) base + offset);
+}
+#endif
+
+#ifdef CONFIG_PCI_MMCONFIG
+static int __init acpi_parse_mcfg(unsigned long phys_addr, unsigned long size)
+{
+ struct acpi_table_mcfg *mcfg;
+
+ if (!phys_addr || !size)
+ return -EINVAL;
+
+ mcfg = (struct acpi_table_mcfg *) __acpi_map_table(phys_addr, size);
+ if (!mcfg) {
+ printk(KERN_WARNING PREFIX "Unable to map MCFG\n");
+ return -ENODEV;
+ }
+
+ if (mcfg->base_reserved) {
+ printk(KERN_ERR PREFIX "MMCONFIG not in low 4GB of memory\n");
+ return -ENODEV;
+ }
+
+ pci_mmcfg_base_addr = mcfg->base_address;
+
+ return 0;
+}
+#else
+#define acpi_parse_mcfg NULL
+#endif /* !CONFIG_PCI_MMCONFIG */
+
+#ifdef CONFIG_X86_LOCAL_APIC
+static int __init
+acpi_parse_madt (
+ unsigned long phys_addr,
+ unsigned long size)
+{
+ struct acpi_table_madt *madt = NULL;
+
+ if (!phys_addr || !size)
+ return -EINVAL;
+
+ madt = (struct acpi_table_madt *) __acpi_map_table(phys_addr, size);
+ if (!madt) {
+ printk(KERN_WARNING PREFIX "Unable to map MADT\n");
+ return -ENODEV;
+ }
+
+ if (madt->lapic_address) {
+ acpi_lapic_addr = (u64) madt->lapic_address;
+
+ printk(KERN_DEBUG PREFIX "Local APIC address 0x%08x\n",
+ madt->lapic_address);
+ }
+
+ acpi_madt_oem_check(madt->header.oem_id, madt->header.oem_table_id);
+
+ return 0;
+}
+
+
+static int __init
+acpi_parse_lapic (
+ acpi_table_entry_header *header, const unsigned long end)
+{
+ struct acpi_table_lapic *processor = NULL;
+
+ processor = (struct acpi_table_lapic*) header;
+
+ if (BAD_MADT_ENTRY(processor, end))
+ return -EINVAL;
+
+ acpi_table_print_madt_entry(header);
+
+ /* no utility in registering a disabled processor */
+ if (processor->flags.enabled == 0)
+ return 0;
+
+ x86_acpiid_to_apicid[processor->acpi_id] = processor->id;
+
+ mp_register_lapic (
+ processor->id, /* APIC ID */
+ processor->flags.enabled); /* Enabled? */
+
+ return 0;
+}
+
+static int __init
+acpi_parse_lapic_addr_ovr (
+ acpi_table_entry_header *header, const unsigned long end)
+{
+ struct acpi_table_lapic_addr_ovr *lapic_addr_ovr = NULL;
+
+ lapic_addr_ovr = (struct acpi_table_lapic_addr_ovr*) header;
+
+ if (BAD_MADT_ENTRY(lapic_addr_ovr, end))
+ return -EINVAL;
+
+ acpi_lapic_addr = lapic_addr_ovr->address;
+
+ return 0;
+}
+
+static int __init
+acpi_parse_lapic_nmi (
+ acpi_table_entry_header *header, const unsigned long end)
+{
+ struct acpi_table_lapic_nmi *lapic_nmi = NULL;
+
+ lapic_nmi = (struct acpi_table_lapic_nmi*) header;
+
+ if (BAD_MADT_ENTRY(lapic_nmi, end))
+ return -EINVAL;
+
+ acpi_table_print_madt_entry(header);
+
+ if (lapic_nmi->lint != 1)
+ printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n");
+
+ return 0;
+}
+
+
+#endif /*CONFIG_X86_LOCAL_APIC*/
+
+#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_ACPI_INTERPRETER)
+
+static int __init
+acpi_parse_ioapic (
+ acpi_table_entry_header *header, const unsigned long end)
+{
+ struct acpi_table_ioapic *ioapic = NULL;
+
+ ioapic = (struct acpi_table_ioapic*) header;
+
+ if (BAD_MADT_ENTRY(ioapic, end))
+ return -EINVAL;
+
+ acpi_table_print_madt_entry(header);
+
+ mp_register_ioapic (
+ ioapic->id,
+ ioapic->address,
+ ioapic->global_irq_base);
+
+ return 0;
+}
+
+/*
+ * Parse Interrupt Source Override for the ACPI SCI
+ */
+static void
+acpi_sci_ioapic_setup(u32 gsi, u16 polarity, u16 trigger)
+{
+ if (trigger == 0) /* compatible SCI trigger is level */
+ trigger = 3;
+
+ if (polarity == 0) /* compatible SCI polarity is low */
+ polarity = 3;
+
+ /* Command-line over-ride via acpi_sci= */
+ if (acpi_sci_flags.trigger)
+ trigger = acpi_sci_flags.trigger;
+
+ if (acpi_sci_flags.polarity)
+ polarity = acpi_sci_flags.polarity;
+
+ /*
+ * mp_config_acpi_legacy_irqs() already setup IRQs < 16
+ * If GSI is < 16, this will update its flags,
+ * else it will create a new mp_irqs[] entry.
+ */
+ mp_override_legacy_irq(gsi, polarity, trigger, gsi);
+
+ /*
+ * stash over-ride to indicate we've been here
+ * and for later update of acpi_fadt
+ */
+ acpi_sci_override_gsi = gsi;
+ return;
+}
+
+static int __init
+acpi_parse_int_src_ovr (
+ acpi_table_entry_header *header, const unsigned long end)
+{
+ struct acpi_table_int_src_ovr *intsrc = NULL;
+
+ intsrc = (struct acpi_table_int_src_ovr*) header;
+
+ if (BAD_MADT_ENTRY(intsrc, end))
+ return -EINVAL;
+
+ acpi_table_print_madt_entry(header);
+
+ if (intsrc->bus_irq == acpi_fadt.sci_int) {
+ acpi_sci_ioapic_setup(intsrc->global_irq,
+ intsrc->flags.polarity, intsrc->flags.trigger);
+ return 0;
+ }
+
+ if (acpi_skip_timer_override &&
+ intsrc->bus_irq == 0 && intsrc->global_irq == 2) {
+ printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n");
+ return 0;
+ }
+
+ mp_override_legacy_irq (
+ intsrc->bus_irq,
+ intsrc->flags.polarity,
+ intsrc->flags.trigger,
+ intsrc->global_irq);
+
+ return 0;
+}
+
+
+static int __init
+acpi_parse_nmi_src (
+ acpi_table_entry_header *header, const unsigned long end)
+{
+ struct acpi_table_nmi_src *nmi_src = NULL;
+
+ nmi_src = (struct acpi_table_nmi_src*) header;
+
+ if (BAD_MADT_ENTRY(nmi_src, end))
+ return -EINVAL;
+
+ acpi_table_print_madt_entry(header);
+
+ /* TBD: Support nimsrc entries? */
+
+ return 0;
+}
+
+#endif /* CONFIG_X86_IO_APIC */
+
+#ifdef CONFIG_ACPI_BUS
+
+/*
+ * acpi_pic_sci_set_trigger()
+ *
+ * use ELCR to set PIC-mode trigger type for SCI
+ *
+ * If a PIC-mode SCI is not recognized or gives spurious IRQ7's
+ * it may require Edge Trigger -- use "acpi_sci=edge"
+ *
+ * Port 0x4d0-4d1 are ECLR1 and ECLR2, the Edge/Level Control Registers
+ * for the 8259 PIC. bit[n] = 1 means irq[n] is Level, otherwise Edge.
+ * ECLR1 is IRQ's 0-7 (IRQ 0, 1, 2 must be 0)
+ * ECLR2 is IRQ's 8-15 (IRQ 8, 13 must be 0)
+ */
+
+void __init
+acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger)
+{
+ unsigned int mask = 1 << irq;
+ unsigned int old, new;
+
+ /* Real old ELCR mask */
+ old = inb(0x4d0) | (inb(0x4d1) << 8);
+
+ /*
+ * If we use ACPI to set PCI irq's, then we should clear ELCR
+ * since we will set it correctly as we enable the PCI irq
+ * routing.
+ */
+ new = acpi_noirq ? old : 0;
+
+ /*
+ * Update SCI information in the ELCR, it isn't in the PCI
+ * routing tables..
+ */
+ switch (trigger) {
+ case 1: /* Edge - clear */
+ new &= ~mask;
+ break;
+ case 3: /* Level - set */
+ new |= mask;
+ break;
+ }
+
+ if (old == new)
+ return;
+
+ printk(PREFIX "setting ELCR to %04x (from %04x)\n", new, old);
+ outb(new, 0x4d0);
+ outb(new >> 8, 0x4d1);
+}
+
+
+#endif /* CONFIG_ACPI_BUS */
+
+int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
+{
+#ifdef CONFIG_X86_IO_APIC
+ if (use_pci_vector() && !platform_legacy_irq(gsi))
+ *irq = IO_APIC_VECTOR(gsi);
+ else
+#endif
+ *irq = gsi;
+ return 0;
+}
+
+unsigned int acpi_register_gsi(u32 gsi, int edge_level, int active_high_low)
+{
+ unsigned int irq;
+ unsigned int plat_gsi = gsi;
+
+#ifdef CONFIG_X86_IO_APIC
+ if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC) {
+ plat_gsi = mp_register_gsi(gsi, edge_level, active_high_low);
+ }
+#endif
+ acpi_gsi_to_irq(plat_gsi, &irq);
+ return irq;
+}
+EXPORT_SYMBOL(acpi_register_gsi);
+
+/*
+ * ACPI based hotplug support for CPU
+ */
+#ifdef CONFIG_ACPI_HOTPLUG_CPU
+int
+acpi_map_lsapic(acpi_handle handle, int *pcpu)
+{
+ /* TBD */
+ return -EINVAL;
+}
+EXPORT_SYMBOL(acpi_map_lsapic);
+
+
+int
+acpi_unmap_lsapic(int cpu)
+{
+ /* TBD */
+ return -EINVAL;
+}
+EXPORT_SYMBOL(acpi_unmap_lsapic);
+#endif /* CONFIG_ACPI_HOTPLUG_CPU */
+
+static unsigned long __init
+acpi_scan_rsdp (
+ unsigned long start,
+ unsigned long length)
+{
+ unsigned long offset = 0;
+ unsigned long sig_len = sizeof("RSD PTR ") - 1;
+ unsigned long vstart = (unsigned long)isa_bus_to_virt(start);
+
+ /*
+ * Scan all 16-byte boundaries of the physical memory region for the
+ * RSDP signature.
+ */
+ for (offset = 0; offset < length; offset += 16) {
+ if (strncmp((char *) (vstart + offset), "RSD PTR ", sig_len))
+ continue;
+ return (start + offset);
+ }
+
+ return 0;
+}
+
+static int __init acpi_parse_sbf(unsigned long phys_addr, unsigned long size)
+{
+ struct acpi_table_sbf *sb;
+
+ if (!phys_addr || !size)
+ return -EINVAL;
+
+ sb = (struct acpi_table_sbf *) __acpi_map_table(phys_addr, size);
+ if (!sb) {
+ printk(KERN_WARNING PREFIX "Unable to map SBF\n");
+ return -ENODEV;
+ }
+
+ sbf_port = sb->sbf_cmos; /* Save CMOS port */
+
+ return 0;
+}
+
+
+#ifdef CONFIG_HPET_TIMER
+
+static int __init acpi_parse_hpet(unsigned long phys, unsigned long size)
+{
+ struct acpi_table_hpet *hpet_tbl;
+
+ if (!phys || !size)
+ return -EINVAL;
+
+ hpet_tbl = (struct acpi_table_hpet *) __acpi_map_table(phys, size);
+ if (!hpet_tbl) {
+ printk(KERN_WARNING PREFIX "Unable to map HPET\n");
+ return -ENODEV;
+ }
+
+ if (hpet_tbl->addr.space_id != ACPI_SPACE_MEM) {
+ printk(KERN_WARNING PREFIX "HPET timers must be located in "
+ "memory.\n");
+ return -1;
+ }
+
+#ifdef CONFIG_X86_64
+ vxtime.hpet_address = hpet_tbl->addr.addrl |
+ ((long) hpet_tbl->addr.addrh << 32);
+
+ printk(KERN_INFO PREFIX "HPET id: %#x base: %#lx\n",
+ hpet_tbl->id, vxtime.hpet_address);
+#else /* X86 */
+ {
+ extern unsigned long hpet_address;
+
+ hpet_address = hpet_tbl->addr.addrl;
+ printk(KERN_INFO PREFIX "HPET id: %#x base: %#lx\n",
+ hpet_tbl->id, hpet_address);
+ }
+#endif /* X86 */
+
+ return 0;
+}
+#else
+#define acpi_parse_hpet NULL
+#endif
+
+#ifdef CONFIG_X86_PM_TIMER
+extern u32 pmtmr_ioport;
+#endif
+
+static int __init acpi_parse_fadt(unsigned long phys, unsigned long size)
+{
+ struct fadt_descriptor_rev2 *fadt = NULL;
+
+ fadt = (struct fadt_descriptor_rev2*) __acpi_map_table(phys,size);
+ if(!fadt) {
+ printk(KERN_WARNING PREFIX "Unable to map FADT\n");
+ return 0;
+ }
+
+#ifdef CONFIG_ACPI_INTERPRETER
+ /* initialize sci_int early for INT_SRC_OVR MADT parsing */
+ acpi_fadt.sci_int = fadt->sci_int;
+#endif
+
+#ifdef CONFIG_X86_PM_TIMER
+ /* detect the location of the ACPI PM Timer */
+ if (fadt->revision >= FADT2_REVISION_ID) {
+ /* FADT rev. 2 */
+ if (fadt->xpm_tmr_blk.address_space_id !=
ACPI_ADR_SPACE_SYSTEM_IO)
+ return 0;
+
+ pmtmr_ioport = fadt->xpm_tmr_blk.address;
+ } else {
+ /* FADT rev. 1 */
+ pmtmr_ioport = fadt->V1_pm_tmr_blk;
+ }
+ if (pmtmr_ioport)
+ printk(KERN_INFO PREFIX "PM-Timer IO Port: %#x\n",
pmtmr_ioport);
+#endif
+ return 0;
+}
+
+
+unsigned long __init
+acpi_find_rsdp (void)
+{
+ unsigned long rsdp_phys = 0;
+
+ if (efi_enabled) {
+ if (efi.acpi20)
+ return __pa(efi.acpi20);
+ else if (efi.acpi)
+ return __pa(efi.acpi);
+ }
+ /*
+ * Scan memory looking for the RSDP signature. First search EBDA (low
+ * memory) paragraphs and then search upper memory (E0000-FFFFF).
+ */
+ rsdp_phys = acpi_scan_rsdp (0, 0x400);
+ if (!rsdp_phys)
+ rsdp_phys = acpi_scan_rsdp (0xE0000, 0x20000);
+
+ set_fixmap(FIX_ACPI_RSDP_PAGE, rsdp_phys);
+
+ return rsdp_phys;
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+/*
+ * Parse LAPIC entries in MADT
+ * returns 0 on success, < 0 on error
+ */
+static int __init
+acpi_parse_madt_lapic_entries(void)
+{
+ int count;
+
+ /*
+ * Note that the LAPIC address is obtained from the MADT (32-bit value)
+ * and (optionally) overriden by a LAPIC_ADDR_OVR entry (64-bit value).
+ */
+
+ count = acpi_table_parse_madt(ACPI_MADT_LAPIC_ADDR_OVR,
acpi_parse_lapic_addr_ovr, 0);
+ if (count < 0) {
+ printk(KERN_ERR PREFIX "Error parsing LAPIC address override
entry\n");
+ return count;
+ }
+
+ mp_register_lapic_address(acpi_lapic_addr);
+
+ count = acpi_table_parse_madt(ACPI_MADT_LAPIC, acpi_parse_lapic,
+ MAX_APICS);
+ if (!count) {
+ printk(KERN_ERR PREFIX "No LAPIC entries present\n");
+ /* TBD: Cleanup to allow fallback to MPS */
+ return -ENODEV;
+ }
+ else if (count < 0) {
+ printk(KERN_ERR PREFIX "Error parsing LAPIC entry\n");
+ /* TBD: Cleanup to allow fallback to MPS */
+ return count;
+ }
+
+ count = acpi_table_parse_madt(ACPI_MADT_LAPIC_NMI,
acpi_parse_lapic_nmi, 0);
+ if (count < 0) {
+ printk(KERN_ERR PREFIX "Error parsing LAPIC NMI entry\n");
+ /* TBD: Cleanup to allow fallback to MPS */
+ return count;
+ }
+ return 0;
+}
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_ACPI_INTERPRETER)
+/*
+ * Parse IOAPIC related entries in MADT
+ * returns 0 on success, < 0 on error
+ */
+static int __init
+acpi_parse_madt_ioapic_entries(void)
+{
+ int count;
+
+ /*
+ * ACPI interpreter is required to complete interrupt setup,
+ * so if it is off, don't enumerate the io-apics with ACPI.
+ * If MPS is present, it will handle them,
+ * otherwise the system will stay in PIC mode
+ */
+ if (acpi_disabled || acpi_noirq) {
+ return -ENODEV;
+ }
+
+ /*
+ * if "noapic" boot option, don't look for IO-APICs
+ */
+ if (skip_ioapic_setup) {
+ printk(KERN_INFO PREFIX "Skipping IOAPIC probe "
+ "due to 'noapic' option.\n");
+ return -ENODEV;
+ }
+
+ count = acpi_table_parse_madt(ACPI_MADT_IOAPIC, acpi_parse_ioapic,
MAX_IO_APICS);
+ if (!count) {
+ printk(KERN_ERR PREFIX "No IOAPIC entries present\n");
+ return -ENODEV;
+ }
+ else if (count < 0) {
+ printk(KERN_ERR PREFIX "Error parsing IOAPIC entry\n");
+ return count;
+ }
+
+ count = acpi_table_parse_madt(ACPI_MADT_INT_SRC_OVR,
acpi_parse_int_src_ovr, NR_IRQ_VECTORS);
+ if (count < 0) {
+ printk(KERN_ERR PREFIX "Error parsing interrupt source
overrides entry\n");
+ /* TBD: Cleanup to allow fallback to MPS */
+ return count;
+ }
+
+ /*
+ * If BIOS did not supply an INT_SRC_OVR for the SCI
+ * pretend we got one so we can set the SCI flags.
+ */
+ if (!acpi_sci_override_gsi)
+ acpi_sci_ioapic_setup(acpi_fadt.sci_int, 0, 0);
+
+ /* Fill in identity legacy mapings where no override */
+ mp_config_acpi_legacy_irqs();
+
+ count = acpi_table_parse_madt(ACPI_MADT_NMI_SRC, acpi_parse_nmi_src,
NR_IRQ_VECTORS);
+ if (count < 0) {
+ printk(KERN_ERR PREFIX "Error parsing NMI SRC entry\n");
+ /* TBD: Cleanup to allow fallback to MPS */
+ return count;
+ }
+
+ return 0;
+}
+#else
+static inline int acpi_parse_madt_ioapic_entries(void)
+{
+ return -1;
+}
+#endif /* !(CONFIG_X86_IO_APIC && CONFIG_ACPI_INTERPRETER) */
+
+
+static void __init
+acpi_process_madt(void)
+{
+#ifdef CONFIG_X86_LOCAL_APIC
+ int count, error;
+
+ count = acpi_table_parse(ACPI_APIC, acpi_parse_madt);
+ if (count >= 1) {
+
+ /*
+ * Parse MADT LAPIC entries
+ */
+ error = acpi_parse_madt_lapic_entries();
+ if (!error) {
+ acpi_lapic = 1;
+
+ /*
+ * Parse MADT IO-APIC entries
+ */
+ error = acpi_parse_madt_ioapic_entries();
+ if (!error) {
+ acpi_irq_model = ACPI_IRQ_MODEL_IOAPIC;
+ acpi_irq_balance_set(NULL);
+ acpi_ioapic = 1;
+
+ smp_found_config = 1;
+ clustered_apic_check();
+ }
+ }
+ if (error == -EINVAL) {
+ /*
+ * Dell Precision Workstation 410, 610 come here.
+ */
+ printk(KERN_ERR PREFIX "Invalid BIOS MADT, disabling
ACPI\n");
+ disable_acpi();
+ }
+ }
+#endif
+ return;
+}
+
+/*
+ * acpi_boot_table_init() and acpi_boot_init()
+ * called from setup_arch(), always.
+ * 1. checksums all tables
+ * 2. enumerates lapics
+ * 3. enumerates io-apics
+ *
+ * acpi_table_init() is separate to allow reading SRAT without
+ * other side effects.
+ *
+ * side effects of acpi_boot_init:
+ * acpi_lapic = 1 if LAPIC found
+ * acpi_ioapic = 1 if IOAPIC found
+ * if (acpi_lapic && acpi_ioapic) smp_found_config = 1;
+ * if acpi_blacklisted() acpi_disabled = 1;
+ * acpi_irq_model=...
+ * ...
+ *
+ * return value: (currently ignored)
+ * 0: success
+ * !0: failure
+ */
+
+int __init
+acpi_boot_table_init(void)
+{
+ int error;
+
+ /*
+ * If acpi_disabled, bail out
+ * One exception: acpi=ht continues far enough to enumerate LAPICs
+ */
+ if (acpi_disabled && !acpi_ht)
+ return 1;
+
+ /*
+ * Initialize the ACPI boot-time table parser.
+ */
+ error = acpi_table_init();
+ if (error) {
+ disable_acpi();
+ return error;
+ }
+
+#ifdef __i386__
+ check_acpi_pci();
+#endif
+
+ acpi_table_parse(ACPI_BOOT, acpi_parse_sbf);
+
+ /*
+ * blacklist may disable ACPI entirely
+ */
+ error = acpi_blacklisted();
+ if (error) {
+ extern int acpi_force;
+
+ if (acpi_force) {
+ printk(KERN_WARNING PREFIX "acpi=force override\n");
+ } else {
+ printk(KERN_WARNING PREFIX "Disabling ACPI support\n");
+ disable_acpi();
+ return error;
+ }
+ }
+
+ return 0;
+}
+
+
+int __init acpi_boot_init(void)
+{
+ /*
+ * If acpi_disabled, bail out
+ * One exception: acpi=ht continues far enough to enumerate LAPICs
+ */
+ if (acpi_disabled && !acpi_ht)
+ return 1;
+
+ acpi_table_parse(ACPI_BOOT, acpi_parse_sbf);
+
+ /*
+ * set sci_int and PM timer address
+ */
+ acpi_table_parse(ACPI_FADT, acpi_parse_fadt);
+
+ /*
+ * Process the Multiple APIC Description Table (MADT), if present
+ */
+ acpi_process_madt();
+
+ acpi_table_parse(ACPI_HPET, acpi_parse_hpet);
+ acpi_table_parse(ACPI_MCFG, acpi_parse_mcfg);
+
+ return 0;
+}
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blktap/blktap_datapath.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blktap/blktap_datapath.c Fri Jul
15 13:39:50 2005
@@ -0,0 +1,451 @@
+/******************************************************************************
+ * blktap_datapath.c
+ *
+ * XenLinux virtual block-device tap.
+ * Block request routing data path.
+ *
+ * Copyright (c) 2004, Andrew Warfield
+ * -- see full header in blktap.c
+ */
+
+#include "blktap.h"
+#include <asm-xen/evtchn.h>
+
+/*-----[ The data paths ]-------------------------------------------------*/
+
+/* Connection to a single backend domain. */
+blkif_front_ring_t blktap_be_ring;
+
+/*-----[ Tracking active requests ]---------------------------------------*/
+
+/* this must be the same as MAX_PENDING_REQS in blkback.c */
+#define MAX_ACTIVE_REQS ((ACTIVE_RING_IDX)64U)
+
+active_req_t active_reqs[MAX_ACTIVE_REQS];
+ACTIVE_RING_IDX active_req_ring[MAX_ACTIVE_REQS];
+spinlock_t active_req_lock = SPIN_LOCK_UNLOCKED;
+ACTIVE_RING_IDX active_prod, active_cons;
+#define MASK_ACTIVE_IDX(_i) ((_i)&(MAX_ACTIVE_REQS-1))
+#define ACTIVE_IDX(_ar) (_ar - active_reqs)
+#define NR_ACTIVE_REQS (MAX_ACTIVE_REQS - active_prod + active_cons)
+
+inline active_req_t *get_active_req(void)
+{
+ ACTIVE_RING_IDX idx;
+ active_req_t *ar;
+ unsigned long flags;
+
+ ASSERT(active_cons != active_prod);
+
+ spin_lock_irqsave(&active_req_lock, flags);
+ idx = active_req_ring[MASK_ACTIVE_IDX(active_cons++)];
+ ar = &active_reqs[idx];
+ spin_unlock_irqrestore(&active_req_lock, flags);
+
+ return ar;
+}
+
+inline void free_active_req(active_req_t *ar)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&active_req_lock, flags);
+ active_req_ring[MASK_ACTIVE_IDX(active_prod++)] = ACTIVE_IDX(ar);
+ spin_unlock_irqrestore(&active_req_lock, flags);
+}
+
+active_req_t *lookup_active_req(ACTIVE_RING_IDX idx)
+{
+ return &active_reqs[idx];
+}
+
+void active_reqs_init(void)
+{
+ ACTIVE_RING_IDX i;
+
+ active_cons = 0;
+ active_prod = MAX_ACTIVE_REQS;
+ memset(active_reqs, 0, sizeof(active_reqs));
+ for ( i = 0; i < MAX_ACTIVE_REQS; i++ )
+ active_req_ring[i] = i;
+}
+
+/* Requests passing through the tap to the backend hijack the id field
+ * in the request message. In it we put the AR index _AND_ the fe domid.
+ * the domid is used by the backend to map the pages properly.
+ */
+
+static inline unsigned long MAKE_ID(domid_t fe_dom, ACTIVE_RING_IDX idx)
+{
+ return ( (fe_dom << 16) | MASK_ACTIVE_IDX(idx) );
+}
+
+/*-----[ Ring helpers ]---------------------------------------------------*/
+
+static void maybe_trigger_blktap_schedule(void);
+
+inline int write_resp_to_fe_ring(blkif_t *blkif, blkif_response_t *rsp)
+{
+ blkif_response_t *resp_d;
+ active_req_t *ar;
+
+ ar = &active_reqs[ID_TO_IDX(rsp->id)];
+ rsp->id = ar->id;
+
+ resp_d = RING_GET_RESPONSE(&blkif->blk_ring,
+ blkif->blk_ring.rsp_prod_pvt);
+ memcpy(resp_d, rsp, sizeof(blkif_response_t));
+ wmb();
+ blkif->blk_ring.rsp_prod_pvt++;
+
+ blkif_put(ar->blkif);
+ free_active_req(ar);
+
+ return 0;
+}
+
+inline int write_req_to_be_ring(blkif_request_t *req)
+{
+ blkif_request_t *req_d;
+
+ if ( blktap_be_state != BLKIF_STATE_CONNECTED ) {
+ WPRINTK("Tap trying to access an unconnected backend!\n");
+ return 0;
+ }
+
+ req_d = RING_GET_REQUEST(&blktap_be_ring,
+ blktap_be_ring.req_prod_pvt);
+ memcpy(req_d, req, sizeof(blkif_request_t));
+ wmb();
+ blktap_be_ring.req_prod_pvt++;
+
+ return 0;
+}
+
+void kick_fe_domain(blkif_t *blkif)
+{
+ RING_PUSH_RESPONSES(&blkif->blk_ring);
+ notify_via_evtchn(blkif->evtchn);
+ DPRINTK("notified FE(dom %u)\n", blkif->domid);
+
+ /* We just feed up a batch of request slots... */
+ maybe_trigger_blktap_schedule();
+
+}
+
+void kick_be_domain(void)
+{
+ if ( blktap_be_state != BLKIF_STATE_CONNECTED )
+ return;
+
+ wmb(); /* Ensure that the frontend can see the requests. */
+ RING_PUSH_REQUESTS(&blktap_be_ring);
+ notify_via_evtchn(blktap_be_evtchn);
+ DPRINTK("notified BE\n");
+}
+
+/*-----[ Data to/from Frontend (client) VMs ]-----------------------------*/
+
+/*-----[ Scheduler list maint -from blkback ]--- */
+
+static struct list_head blkio_schedule_list;
+static spinlock_t blkio_schedule_list_lock;
+
+static int __on_blkdev_list(blkif_t *blkif)
+{
+ return blkif->blkdev_list.next != NULL;
+}
+
+static void remove_from_blkdev_list(blkif_t *blkif)
+{
+ unsigned long flags;
+ if ( !__on_blkdev_list(blkif) ) return;
+ spin_lock_irqsave(&blkio_schedule_list_lock, flags);
+ if ( __on_blkdev_list(blkif) )
+ {
+ list_del(&blkif->blkdev_list);
+ blkif->blkdev_list.next = NULL;
+ blkif_put(blkif);
+ }
+ spin_unlock_irqrestore(&blkio_schedule_list_lock, flags);
+}
+
+static void add_to_blkdev_list_tail(blkif_t *blkif)
+{
+ unsigned long flags;
+ if ( __on_blkdev_list(blkif) ) return;
+ spin_lock_irqsave(&blkio_schedule_list_lock, flags);
+ if ( !__on_blkdev_list(blkif) && (blkif->status == CONNECTED) )
+ {
+ list_add_tail(&blkif->blkdev_list, &blkio_schedule_list);
+ blkif_get(blkif);
+ }
+ spin_unlock_irqrestore(&blkio_schedule_list_lock, flags);
+}
+
+
+/*-----[ Scheduler functions - from blkback ]--- */
+
+static DECLARE_WAIT_QUEUE_HEAD(blkio_schedule_wait);
+
+static int do_block_io_op(blkif_t *blkif, int max_to_do);
+
+static int blkio_schedule(void *arg)
+{
+ DECLARE_WAITQUEUE(wq, current);
+
+ blkif_t *blkif;
+ struct list_head *ent;
+
+ daemonize(
+ "xentapd"
+ );
+
+ for ( ; ; )
+ {
+ /* Wait for work to do. */
+ add_wait_queue(&blkio_schedule_wait, &wq);
+ set_current_state(TASK_INTERRUPTIBLE);
+ if ( (NR_ACTIVE_REQS == MAX_ACTIVE_REQS) ||
+ list_empty(&blkio_schedule_list) )
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ remove_wait_queue(&blkio_schedule_wait, &wq);
+
+ /* Queue up a batch of requests. */
+ while ( (NR_ACTIVE_REQS < MAX_ACTIVE_REQS) &&
+ !list_empty(&blkio_schedule_list) )
+ {
+ ent = blkio_schedule_list.next;
+ blkif = list_entry(ent, blkif_t, blkdev_list);
+ blkif_get(blkif);
+ remove_from_blkdev_list(blkif);
+ if ( do_block_io_op(blkif, BATCH_PER_DOMAIN) )
+ add_to_blkdev_list_tail(blkif);
+ blkif_put(blkif);
+ }
+ }
+}
+
+static void maybe_trigger_blktap_schedule(void)
+{
+ /*
+ * Needed so that two processes, who together make the following predicate
+ * true, don't both read stale values and evaluate the predicate
+ * incorrectly. Incredibly unlikely to stall the scheduler on x86, but...
+ */
+ smp_mb();
+
+ if ( (NR_ACTIVE_REQS < (MAX_ACTIVE_REQS/2)) &&
+ !list_empty(&blkio_schedule_list) )
+ wake_up(&blkio_schedule_wait);
+}
+
+void blkif_deschedule(blkif_t *blkif)
+{
+ remove_from_blkdev_list(blkif);
+}
+
+void __init blkdev_schedule_init(void)
+{
+ spin_lock_init(&blkio_schedule_list_lock);
+ INIT_LIST_HEAD(&blkio_schedule_list);
+
+ if ( kernel_thread(blkio_schedule, 0, CLONE_FS | CLONE_FILES) < 0 )
+ BUG();
+}
+
+/*-----[ Interrupt entry from a frontend ]------ */
+
+irqreturn_t blkif_ptfe_int(int irq, void *dev_id, struct pt_regs *regs)
+{
+ blkif_t *blkif = dev_id;
+
+ add_to_blkdev_list_tail(blkif);
+ maybe_trigger_blktap_schedule();
+ return IRQ_HANDLED;
+}
+
+/*-----[ Other Frontend Ring functions ]-------- */
+
+/* irqreturn_t blkif_ptfe_int(int irq, void *dev_id, struct pt_regs *regs)*/
+static int do_block_io_op(blkif_t *blkif, int max_to_do)
+{
+ /* we have pending messages from the real frontend. */
+
+ blkif_request_t *req_s;
+ RING_IDX i, rp;
+ unsigned long flags;
+ active_req_t *ar;
+ int more_to_do = 0;
+ int notify_be = 0, notify_user = 0;
+
+ if (NR_ACTIVE_REQS == MAX_ACTIVE_REQS) return 1;
+
+ /* lock both rings */
+ spin_lock_irqsave(&blkif_io_lock, flags);
+
+ rp = blkif->blk_ring.sring->req_prod;
+ rmb();
+
+ for ( i = blkif->blk_ring.req_cons;
+ (i != rp) &&
+ !RING_REQUEST_CONS_OVERFLOW(&blkif->blk_ring, i);
+ i++ )
+ {
+
+ if ((--max_to_do == 0) || (NR_ACTIVE_REQS == MAX_ACTIVE_REQS))
+ {
+ more_to_do = 1;
+ break;
+ }
+
+ req_s = RING_GET_REQUEST(&blkif->blk_ring, i);
+ /* This is a new request:
+ * Assign an active request record, and remap the id.
+ */
+ ar = get_active_req();
+ ar->id = req_s->id;
+ ar->nr_pages = req_s->nr_segments;
+ blkif_get(blkif);
+ ar->blkif = blkif;
+ req_s->id = MAKE_ID(blkif->domid, ACTIVE_IDX(ar));
+ /* WPRINTK("%3u < %3lu\n", ID_TO_IDX(req_s->id), ar->id); */
+
+ /* FE -> BE interposition point is here. */
+
+ /* ------------------------------------------------------------- */
+ /* BLKIF_OP_PROBE_HACK: */
+ /* Signal to the backend that we are a tap domain. */
+
+ if (req_s->operation == BLKIF_OP_PROBE) {
+ DPRINTK("Adding BLKTAP_COOKIE to PROBE request.\n");
+ req_s->frame_and_sects[1] = BLKTAP_COOKIE;
+ }
+
+ /* ------------------------------------------------------------- */
+
+ /* If we are in MODE_INTERCEPT_FE or MODE_COPY_FE: */
+ if ( (blktap_mode & BLKTAP_MODE_INTERCEPT_FE) ||
+ (blktap_mode & BLKTAP_MODE_COPY_FE) ) {
+
+ /* Copy the response message to UFERing */
+ /* In MODE_INTERCEPT_FE, map attached pages into the app vma */
+ /* In MODE_COPY_FE_PAGES, copy attached pages into the app vma */
+
+ DPRINTK("req->UFERing\n");
+ blktap_write_fe_ring(req_s);
+ notify_user = 1;
+ }
+
+ /* If we are not in MODE_INTERCEPT_FE or MODE_INTERCEPT_BE: */
+ if ( !((blktap_mode & BLKTAP_MODE_INTERCEPT_FE) ||
+ (blktap_mode & BLKTAP_MODE_INTERCEPT_BE)) ) {
+
+ /* be included to prevent noise from the fe when its off */
+ /* copy the request message to the BERing */
+
+ DPRINTK("blktap: FERing[%u] -> BERing[%u]\n",
+ (unsigned)i & (RING_SIZE(&blktap_be_ring)-1),
+ (unsigned)blktap_be_ring.req_prod_pvt &
+ (RING_SIZE((&blktap_be_ring)-1)));
+
+ write_req_to_be_ring(req_s);
+ notify_be = 1;
+ }
+ }
+
+ blkif->blk_ring.req_cons = i;
+
+ /* unlock rings */
+ spin_unlock_irqrestore(&blkif_io_lock, flags);
+
+ if (notify_user)
+ blktap_kick_user();
+ if (notify_be)
+ kick_be_domain();
+
+ return more_to_do;
+}
+
+/*-----[ Data to/from Backend (server) VM ]------------------------------*/
+
+
+irqreturn_t blkif_ptbe_int(int irq, void *dev_id,
+ struct pt_regs *ptregs)
+{
+ blkif_response_t *resp_s;
+ blkif_t *blkif;
+ RING_IDX rp, i;
+ unsigned long flags;
+
+ DPRINTK("PT got BE interrupt.\n");
+
+ /* lock both rings */
+ spin_lock_irqsave(&blkif_io_lock, flags);
+
+ rp = blktap_be_ring.sring->rsp_prod;
+ rmb();
+
+ for ( i = blktap_be_ring.rsp_cons; i != rp; i++)
+ {
+ resp_s = RING_GET_RESPONSE(&blktap_be_ring, i);
+
+ /* BE -> FE interposition point is here. */
+
+ blkif = active_reqs[ID_TO_IDX(resp_s->id)].blkif;
+
+ /* If we are in MODE_INTERCEPT_BE or MODE_COPY_BE: */
+ if ( (blktap_mode & BLKTAP_MODE_INTERCEPT_BE) ||
+ (blktap_mode & BLKTAP_MODE_COPY_BE) ) {
+
+ /* Copy the response message to UBERing */
+ /* In MODE_INTERCEPT_BE, map attached pages into the app vma */
+ /* In MODE_COPY_BE_PAGES, copy attached pages into the app vma */
+
+ DPRINTK("rsp->UBERing\n");
+ blktap_write_be_ring(resp_s);
+ blktap_kick_user();
+
+ }
+
+ /* If we are NOT in MODE_INTERCEPT_BE or MODE_INTERCEPT_FE: */
+ if ( !((blktap_mode & BLKTAP_MODE_INTERCEPT_BE) ||
+ (blktap_mode & BLKTAP_MODE_INTERCEPT_FE)) ) {
+
+ /* (fe included to prevent random interference from the BE) */
+ /* Copy the response message to FERing */
+
+ DPRINTK("blktap: BERing[%u] -> FERing[%u]\n",
+ (unsigned)i & (RING_SIZE(&blkif->blk_ring)-1),
+ (unsigned)blkif->blk_ring.rsp_prod_pvt &
+ (RING_SIZE((&blkif->blk_ring)-1)));
+
+ write_resp_to_fe_ring(blkif, resp_s);
+ kick_fe_domain(blkif);
+
+ }
+ }
+
+ blktap_be_ring.rsp_cons = i;
+
+
+ spin_unlock_irqrestore(&blkif_io_lock, flags);
+
+ return IRQ_HANDLED;
+}
+
+/* Debug : print the current ring indices. */
+
+void print_be_ring_idxs(void)
+{
+ if (blktap_be_ring.sring != NULL) {
+ WPRINTK("BE Ring: \n--------\n");
+ WPRINTK("BE: rsp_cons: %2d, req_prod_prv: %2d "
+ "| req_prod: %2d, rsp_prod: %2d\n",
+ blktap_be_ring.rsp_cons,
+ blktap_be_ring.req_prod_pvt,
+ blktap_be_ring.sring->req_prod,
+ blktap_be_ring.sring->rsp_prod);
+ }
+}
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/Makefile Fri Jul 15 13:39:50 2005
@@ -0,0 +1,592 @@
+VERSION = 2
+PATCHLEVEL = 4
+SUBLEVEL = 30
+EXTRAVERSION =
+
+KERNELRELEASE=$(VERSION).$(PATCHLEVEL).$(SUBLEVEL)$(EXTRAVERSION)
+
+# SUBARCH always tells us the underlying machine architecture.
+# Unless overridden, by default ARCH is equivalent to SUBARCH.
+# This will be overriden for Xen and UML builds.
+SUBARCH := $(shell uname -m | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ -e
s/arm.*/arm/ -e s/sa110/arm/)
+ARCH ?= $(SUBARCH)
+
+## XXX The following hack can be discarded after users have adjusted to the
+## architectural name change 'xeno' -> 'xen'.
+ifeq ($(ARCH),xeno)
+ ARCH := xen
+endif
+
+KERNELPATH=kernel-$(shell echo $(KERNELRELEASE) | sed -e "s/-//g")
+
+CONFIG_SHELL := $(shell if [ -x "$$BASH" ]; then echo $$BASH; \
+ else if [ -x /bin/bash ]; then echo /bin/bash; \
+ else echo sh; fi ; fi)
+TOPDIR := $(shell /bin/pwd)
+
+HPATH = $(TOPDIR)/include
+FINDHPATH = $(HPATH)/asm $(HPATH)/linux $(HPATH)/scsi $(HPATH)/net
$(HPATH)/math-emu
+
+HOSTCC = gcc
+HOSTCFLAGS = -Wall -Wstrict-prototypes -O2 -fomit-frame-pointer
+
+CROSS_COMPILE =
+
+#
+# Include the make variables (CC, etc...)
+#
+
+AS = $(CROSS_COMPILE)as
+LD = $(CROSS_COMPILE)ld
+CC = $(CROSS_COMPILE)gcc
+CPP = $(CC) -E
+AR = $(CROSS_COMPILE)ar
+NM = $(CROSS_COMPILE)nm
+STRIP = $(CROSS_COMPILE)strip
+OBJCOPY = $(CROSS_COMPILE)objcopy
+OBJDUMP = $(CROSS_COMPILE)objdump
+MAKEFILES = $(TOPDIR)/.config
+GENKSYMS = /sbin/genksyms
+DEPMOD = /sbin/depmod
+MODFLAGS = -DMODULE
+CFLAGS_KERNEL =
+PERL = perl
+AWK = awk
+RPM := $(shell if [ -x "/usr/bin/rpmbuild" ]; then echo rpmbuild; \
+ else echo rpm; fi)
+
+export VERSION PATCHLEVEL SUBLEVEL EXTRAVERSION KERNELRELEASE ARCH \
+ CONFIG_SHELL TOPDIR HPATH HOSTCC HOSTCFLAGS CROSS_COMPILE AS LD CC \
+ CPP AR NM STRIP OBJCOPY OBJDUMP MAKE MAKEFILES GENKSYMS MODFLAGS PERL
AWK
+
+all: do-it-all
+
+#
+# Make "config" the default target if there is no configuration file or
+# "depend" the target if there is no top-level dependency information.
+#
+
+ifeq (.config,$(wildcard .config))
+include .config
+ifeq (.depend,$(wildcard .depend))
+include .depend
+do-it-all: Version vmlinux
+else
+CONFIGURATION = depend
+do-it-all: depend
+endif
+else
+CONFIGURATION = config
+do-it-all: config
+endif
+
+#
+# INSTALL_PATH specifies where to place the updated kernel and system map
+# images. Uncomment if you want to place them anywhere other than root.
+#
+
+#export INSTALL_PATH=/boot
+
+#
+# INSTALL_MOD_PATH specifies a prefix to MODLIB for module directory
+# relocations required by build roots. This is not defined in the
+# makefile but the arguement can be passed to make if needed.
+#
+
+MODLIB = $(INSTALL_MOD_PATH)/lib/modules/$(KERNELRELEASE)
+export MODLIB
+
+#
+# standard CFLAGS
+#
+
+CPPFLAGS := -D__KERNEL__ -I$(HPATH)
+
+CFLAGS := $(CPPFLAGS) -Wall -Wstrict-prototypes -Wno-trigraphs -O2 \
+ -fno-strict-aliasing -fno-common
+ifndef CONFIG_FRAME_POINTER
+CFLAGS += -fomit-frame-pointer
+endif
+AFLAGS := -D__ASSEMBLY__ $(CPPFLAGS)
+
+#
+# ROOT_DEV specifies the default root-device when making the image.
+# This can be either FLOPPY, CURRENT, /dev/xxxx or empty, in which case
+# the default of FLOPPY is used by 'build'.
+# This is i386 specific.
+#
+
+export ROOT_DEV = CURRENT
+
+#
+# If you want to preset the SVGA mode, uncomment the next line and
+# set SVGA_MODE to whatever number you want.
+# Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode.
+# The number is the same as you would ordinarily press at bootup.
+# This is i386 specific.
+#
+
+export SVGA_MODE = -DSVGA_MODE=NORMAL_VGA
+
+#
+# If you want the RAM disk device, define this to be the size in blocks.
+# This is i386 specific.
+#
+
+#export RAMDISK = -DRAMDISK=512
+
+CORE_FILES =kernel/kernel.o mm/mm.o fs/fs.o ipc/ipc.o
+NETWORKS =net/network.o
+
+LIBS =$(TOPDIR)/lib/lib.a
+SUBDIRS =kernel drivers mm fs net ipc lib crypto
+
+DRIVERS-n :=
+DRIVERS-y :=
+DRIVERS-m :=
+DRIVERS- :=
+
+DRIVERS-$(CONFIG_ACPI_BOOT) += drivers/acpi/acpi.o
+DRIVERS-$(CONFIG_PARPORT) += drivers/parport/driver.o
+DRIVERS-y += drivers/char/char.o \
+ drivers/block/block.o \
+ drivers/misc/misc.o \
+ drivers/net/net.o
+DRIVERS-$(CONFIG_AGP) += drivers/char/agp/agp.o
+DRIVERS-$(CONFIG_DRM_NEW) += drivers/char/drm/drm.o
+DRIVERS-$(CONFIG_DRM_OLD) += drivers/char/drm-4.0/drm.o
+DRIVERS-$(CONFIG_NUBUS) += drivers/nubus/nubus.a
+DRIVERS-$(CONFIG_NET_FC) += drivers/net/fc/fc.o
+DRIVERS-$(CONFIG_DEV_APPLETALK) += drivers/net/appletalk/appletalk.o
+DRIVERS-$(CONFIG_TR) += drivers/net/tokenring/tr.o
+DRIVERS-$(CONFIG_WAN) += drivers/net/wan/wan.o
+DRIVERS-$(CONFIG_ARCNET) += drivers/net/arcnet/arcnetdrv.o
+DRIVERS-$(CONFIG_ATM) += drivers/atm/atm.o
+DRIVERS-$(CONFIG_IDE) += drivers/ide/idedriver.o
+DRIVERS-$(CONFIG_FC4) += drivers/fc4/fc4.a
+DRIVERS-$(CONFIG_SCSI) += drivers/scsi/scsidrv.o
+DRIVERS-$(CONFIG_FUSION_BOOT) += drivers/message/fusion/fusion.o
+DRIVERS-$(CONFIG_IEEE1394) += drivers/ieee1394/ieee1394drv.o
+
+ifneq
($(CONFIG_CD_NO_IDESCSI)$(CONFIG_BLK_DEV_IDECD)$(CONFIG_BLK_DEV_SR)$(CONFIG_PARIDE_PCD),)
+DRIVERS-y += drivers/cdrom/driver.o
+endif
+
+DRIVERS-$(CONFIG_SOUND) += drivers/sound/sounddrivers.o
+DRIVERS-$(CONFIG_PCI) += drivers/pci/driver.o
+DRIVERS-$(CONFIG_MTD) += drivers/mtd/mtdlink.o
+DRIVERS-$(CONFIG_PCMCIA) += drivers/pcmcia/pcmcia.o
+DRIVERS-$(CONFIG_NET_PCMCIA) += drivers/net/pcmcia/pcmcia_net.o
+DRIVERS-$(CONFIG_NET_WIRELESS) += drivers/net/wireless/wireless_net.o
+DRIVERS-$(CONFIG_PCMCIA_CHRDEV) += drivers/char/pcmcia/pcmcia_char.o
+DRIVERS-$(CONFIG_DIO) += drivers/dio/dio.a
+DRIVERS-$(CONFIG_SBUS) += drivers/sbus/sbus_all.o
+DRIVERS-$(CONFIG_ZORRO) += drivers/zorro/driver.o
+DRIVERS-$(CONFIG_FC4) += drivers/fc4/fc4.a
+DRIVERS-$(CONFIG_PPC32) += drivers/macintosh/macintosh.o
+DRIVERS-$(CONFIG_MAC) += drivers/macintosh/macintosh.o
+DRIVERS-$(CONFIG_ISAPNP) += drivers/pnp/pnp.o
+DRIVERS-$(CONFIG_I2C) += drivers/i2c/i2c.o
+DRIVERS-$(CONFIG_VT) += drivers/video/video.o
+DRIVERS-$(CONFIG_PARIDE) += drivers/block/paride/paride.a
+DRIVERS-$(CONFIG_HAMRADIO) += drivers/net/hamradio/hamradio.o
+DRIVERS-$(CONFIG_TC) += drivers/tc/tc.a
+DRIVERS-$(CONFIG_USB) += drivers/usb/usbdrv.o
+DRIVERS-$(CONFIG_USB_GADGET) += drivers/usb/gadget/built-in.o
+DRIVERS-y +=drivers/media/media.o
+DRIVERS-$(CONFIG_INPUT) += drivers/input/inputdrv.o
+DRIVERS-$(CONFIG_HIL) += drivers/hil/hil.o
+DRIVERS-$(CONFIG_I2O) += drivers/message/i2o/i2o.o
+DRIVERS-$(CONFIG_IRDA) += drivers/net/irda/irda.o
+DRIVERS-$(CONFIG_PHONE) += drivers/telephony/telephony.o
+DRIVERS-$(CONFIG_MD) += drivers/md/mddev.o
+DRIVERS-$(CONFIG_GSC) += drivers/gsc/gscbus.o
+DRIVERS-$(CONFIG_BLUEZ) += drivers/bluetooth/bluetooth.o
+DRIVERS-$(CONFIG_HOTPLUG_PCI) += drivers/hotplug/vmlinux-obj.o
+DRIVERS-$(CONFIG_ISDN_BOOL) += drivers/isdn/vmlinux-obj.o
+DRIVERS-$(CONFIG_CRYPTO) += crypto/crypto.o
+
+DRIVERS := $(DRIVERS-y)
+
+
+# files removed with 'make clean'
+CLEAN_FILES = \
+ kernel/ksyms.lst include/linux/compile.h \
+ vmlinux System.map \
+ .tmp* \
+ drivers/char/consolemap_deftbl.c drivers/video/promcon_tbl.c \
+ drivers/char/conmakehash \
+ drivers/char/drm/*-mod.c \
+ drivers/pci/devlist.h drivers/pci/classlist.h drivers/pci/gen-devlist \
+ drivers/zorro/devlist.h drivers/zorro/gen-devlist \
+ drivers/sound/bin2hex drivers/sound/hex2hex \
+ drivers/atm/fore200e_mkfirm drivers/atm/{pca,sba}*{.bin,.bin1,.bin2} \
+ drivers/scsi/aic7xxx/aicasm/aicasm \
+ drivers/scsi/aic7xxx/aicasm/aicasm_gram.c \
+ drivers/scsi/aic7xxx/aicasm/aicasm_gram.h \
+ drivers/scsi/aic7xxx/aicasm/aicasm_macro_gram.c \
+ drivers/scsi/aic7xxx/aicasm/aicasm_macro_gram.h \
+ drivers/scsi/aic7xxx/aicasm/aicasm_macro_scan.c \
+ drivers/scsi/aic7xxx/aicasm/aicasm_scan.c \
+ drivers/scsi/aic7xxx/aicasm/aicdb.h \
+ drivers/scsi/aic7xxx/aicasm/y.tab.h \
+ drivers/scsi/53c700_d.h \
+ drivers/tc/lk201-map.c \
+ net/khttpd/make_times_h \
+ net/khttpd/times.h \
+ submenu* \
+ drivers/ieee1394/oui.c
+# directories removed with 'make clean'
+CLEAN_DIRS = \
+ modules
+
+# files removed with 'make mrproper'
+MRPROPER_FILES = \
+ include/linux/autoconf.h include/linux/version.h \
+ lib/crc32table.h lib/gen_crc32table \
+ drivers/net/hamradio/soundmodem/sm_tbl_{afsk1200,afsk2666,fsk9600}.h \
+ drivers/net/hamradio/soundmodem/sm_tbl_{hapn4800,psk4800}.h \
+ drivers/net/hamradio/soundmodem/sm_tbl_{afsk2400_7,afsk2400_8}.h \
+ drivers/net/hamradio/soundmodem/gentbl \
+ drivers/sound/*_boot.h drivers/sound/.*.boot \
+ drivers/sound/msndinit.c \
+ drivers/sound/msndperm.c \
+ drivers/sound/pndsperm.c \
+ drivers/sound/pndspini.c \
+ drivers/atm/fore200e_*_fw.c drivers/atm/.fore200e_*.fw \
+ .version .config* config.in config.old \
+ scripts/tkparse scripts/kconfig.tk scripts/kconfig.tmp \
+ scripts/lxdialog/*.o scripts/lxdialog/lxdialog \
+ .menuconfig.log \
+ include/asm \
+ .hdepend scripts/mkdep scripts/split-include scripts/docproc \
+ $(TOPDIR)/include/linux/modversions.h \
+ kernel.spec
+
+# directories removed with 'make mrproper'
+MRPROPER_DIRS = \
+ include/config \
+ $(TOPDIR)/include/linux/modules
+
+
+include arch/$(ARCH)/Makefile
+
+# Extra cflags for kbuild 2.4. The default is to forbid includes by kernel
code
+# from user space headers. Some UML code requires user space headers, in the
+# UML Makefiles add 'kbuild_2_4_nostdinc :=' before include Rules.make. No
+# other kernel code should include user space headers, if you need
+# 'kbuild_2_4_nostdinc :=' or -I/usr/include for kernel code and you are not
UML
+# then your code is broken! KAO.
+
+kbuild_2_4_nostdinc := -nostdinc -iwithprefix include
+export kbuild_2_4_nostdinc
+
+export CPPFLAGS CFLAGS CFLAGS_KERNEL AFLAGS AFLAGS_KERNEL
+
+export NETWORKS DRIVERS LIBS HEAD LDFLAGS LINKFLAGS MAKEBOOT ASFLAGS
+
+.S.s:
+ $(CPP) $(AFLAGS) $(AFLAGS_KERNEL) -traditional -o $*.s $<
+.S.o:
+ $(CC) $(AFLAGS) $(AFLAGS_KERNEL) -traditional -c -o $*.o $<
+
+Version: dummy
+ @rm -f include/linux/compile.h
+
+boot: vmlinux
+ @$(MAKE) CFLAGS="$(CFLAGS) $(CFLAGS_KERNEL)" -C arch/$(ARCH)/boot
+
+vmlinux: include/linux/version.h $(CONFIGURATION) init/main.o init/version.o
init/do_mounts.o linuxsubdirs
+ $(LD) $(LINKFLAGS) $(HEAD) init/main.o init/version.o init/do_mounts.o \
+ --start-group \
+ $(CORE_FILES) \
+ $(DRIVERS) \
+ $(NETWORKS) \
+ $(LIBS) \
+ --end-group \
+ -o vmlinux
+ $(NM) vmlinux | grep -v '\(compiled\)\|\(\.o$$\)\|\( [aUw]
\)\|\(\.\.ng$$\)\|\(LASH[RL]DI\)' | sort > System.map
+
+symlinks:
+ rm -f include/asm
+ ( cd include ; ln -sf asm-$(ARCH) asm)
+ @if [ ! -d include/linux/modules ]; then \
+ mkdir include/linux/modules; \
+ fi
+
+oldconfig: symlinks
+ $(CONFIG_SHELL) scripts/Configure -d arch/$(ARCH)/config.in
+
+xconfig: symlinks
+ $(MAKE) -C scripts kconfig.tk
+ wish -f scripts/kconfig.tk
+
+menuconfig: include/linux/version.h symlinks
+ $(MAKE) -C scripts/lxdialog all
+ $(CONFIG_SHELL) scripts/Menuconfig arch/$(ARCH)/config.in
+
+config: symlinks
+ $(CONFIG_SHELL) scripts/Configure arch/$(ARCH)/config.in
+
+include/config/MARKER: scripts/split-include include/linux/autoconf.h
+ scripts/split-include include/linux/autoconf.h include/config
+ @ touch include/config/MARKER
+
+linuxsubdirs: $(patsubst %, _dir_%, $(SUBDIRS))
+
+$(patsubst %, _dir_%, $(SUBDIRS)) : dummy include/linux/version.h
include/config/MARKER
+ $(MAKE) CFLAGS="$(CFLAGS) $(CFLAGS_KERNEL)" -C $(patsubst _dir_%, %, $@)
+
+$(TOPDIR)/include/linux/version.h: include/linux/version.h
+$(TOPDIR)/include/linux/compile.h: include/linux/compile.h
+
+newversion:
+ . scripts/mkversion > .tmpversion
+ @mv -f .tmpversion .version
+
+uts_len := 64
+uts_truncate := sed -e 's/\(.\{1,$(uts_len)\}\).*/\1/'
+
+include/linux/compile.h: $(CONFIGURATION) include/linux/version.h newversion
+ @echo -n \#`cat .version` > .ver1
+ @if [ -n "$(CONFIG_SMP)" ] ; then echo -n " SMP" >> .ver1; fi
+ @if [ -f .name ]; then echo -n \-`cat .name` >> .ver1; fi
+ @LANG=C echo ' '`date` >> .ver1
+ @echo \#define UTS_VERSION \"`cat .ver1 | $(uts_truncate)`\" > .ver
+ @LANG=C echo \#define LINUX_COMPILE_TIME \"`date +%T`\" >> .ver
+ @echo \#define LINUX_COMPILE_BY \"`whoami`\" >> .ver
+ @echo \#define LINUX_COMPILE_HOST \"`hostname | $(uts_truncate)`\" >>
.ver
+ @([ -x /bin/dnsdomainname ] && /bin/dnsdomainname > .ver1) || \
+ ([ -x /bin/domainname ] && /bin/domainname > .ver1) || \
+ echo > .ver1
+ @echo \#define LINUX_COMPILE_DOMAIN \"`cat .ver1 | $(uts_truncate)`\"
>> .ver
+ @echo \#define LINUX_COMPILER \"`$(CC) $(CFLAGS) -v 2>&1 | tail -n 1`\"
>> .ver
+ @mv -f .ver $@
+ @rm -f .ver1
+
+include/linux/version.h: ./Makefile
+ @expr length "$(KERNELRELEASE)" \<= $(uts_len) > /dev/null || \
+ (echo KERNELRELEASE \"$(KERNELRELEASE)\" exceeds $(uts_len)
characters >&2; false)
+ @echo \#define UTS_RELEASE \"$(KERNELRELEASE)\" > .ver
+ @echo \#define LINUX_VERSION_CODE `expr $(VERSION) \\* 65536 +
$(PATCHLEVEL) \\* 256 + $(SUBLEVEL)` >> .ver
+ @echo '#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c))'
>>.ver
+ @mv -f .ver $@
+
+comma := ,
+
+init/version.o: init/version.c include/linux/compile.h include/config/MARKER
+ $(CC) $(CFLAGS) $(CFLAGS_KERNEL) -DUTS_MACHINE='"$(SUBARCH)"'
-DKBUILD_BASENAME=$(subst $(comma),_,$(subst -,_,$(*F))) -c -o init/version.o
init/version.c
+
+init/main.o: init/main.c include/config/MARKER
+ $(CC) $(CFLAGS) $(CFLAGS_KERNEL) $(PROFILING) -DKBUILD_BASENAME=$(subst
$(comma),_,$(subst -,_,$(*F))) -c -o $@ $<
+
+init/do_mounts.o: init/do_mounts.c include/config/MARKER
+ $(CC) $(CFLAGS) $(CFLAGS_KERNEL) $(PROFILING) -DKBUILD_BASENAME=$(subst
$(comma),_,$(subst -,_,$(*F))) -c -o $@ $<
+
+fs lib mm ipc kernel drivers net: dummy
+ $(MAKE) CFLAGS="$(CFLAGS) $(CFLAGS_KERNEL)" $(subst $@, _dir_$@, $@)
+
+TAGS: dummy
+ { find include/asm-${ARCH} -name '*.h' -print ; \
+ find include -type d \( -name "asm-*" -o -name config \) -prune -o
-name '*.h' -print ; \
+ find $(SUBDIRS) init arch/${ARCH} -name '*.[chS]' ; } | grep -v SCCS |
grep -v '\.svn' | etags -
+
+# Exuberant ctags works better with -I
+tags: dummy
+ CTAGSF=`ctags --version | grep -i exuberant >/dev/null && echo "-I
__initdata,__exitdata,EXPORT_SYMBOL,EXPORT_SYMBOL_NOVERS"`; \
+ ctags $$CTAGSF `find include/asm-$(ARCH) -name '*.h'` && \
+ find include -type d \( -name "asm-*" -o -name config \) -prune -o
-name '*.h' -print | xargs ctags $$CTAGSF -a && \
+ find $(SUBDIRS) init -name '*.[ch]' | xargs ctags $$CTAGSF -a
+
+ifdef CONFIG_MODULES
+ifdef CONFIG_MODVERSIONS
+MODFLAGS += -DMODVERSIONS -include $(HPATH)/linux/modversions.h
+endif
+
+.PHONY: modules
+modules: $(patsubst %, _mod_%, $(SUBDIRS))
+
+.PHONY: $(patsubst %, _mod_%, $(SUBDIRS))
+$(patsubst %, _mod_%, $(SUBDIRS)) : include/linux/version.h
include/config/MARKER
+ $(MAKE) -C $(patsubst _mod_%, %, $@) CFLAGS="$(CFLAGS) $(MODFLAGS)"
MAKING_MODULES=1 modules
+
+.PHONY: modules_install
+modules_install: _modinst_ $(patsubst %, _modinst_%, $(SUBDIRS)) _modinst_post
+
+.PHONY: _modinst_
+_modinst_:
+ @rm -rf $(MODLIB)/kernel
+ @rm -f $(MODLIB)/build
+ @mkdir -p $(MODLIB)/kernel
+ @ln -s $(TOPDIR) $(MODLIB)/build
+
+# If System.map exists, run depmod. This deliberately does not have a
+# dependency on System.map since that would run the dependency tree on
+# vmlinux. This depmod is only for convenience to give the initial
+# boot a modules.dep even before / is mounted read-write. However the
+# boot script depmod is the master version.
+ifeq "$(strip $(INSTALL_MOD_PATH))" ""
+depmod_opts :=
+else
+depmod_opts := -b $(INSTALL_MOD_PATH) -r
+endif
+.PHONY: _modinst_post
+_modinst_post: _modinst_post_pcmcia
+ if [ -r System.map ]; then $(DEPMOD) -ae -F System.map $(depmod_opts)
$(KERNELRELEASE); fi
+
+# Backwards compatibilty symlinks for people still using old versions
+# of pcmcia-cs with hard coded pathnames on insmod. Remove
+# _modinst_post_pcmcia for kernel 2.4.1.
+.PHONY: _modinst_post_pcmcia
+_modinst_post_pcmcia:
+ cd $(MODLIB); \
+ mkdir -p pcmcia; \
+ find kernel -path '*/pcmcia/*' -name '*.o' | xargs -i -r ln -sf ../{}
pcmcia
+
+.PHONY: $(patsubst %, _modinst_%, $(SUBDIRS))
+$(patsubst %, _modinst_%, $(SUBDIRS)) :
+ $(MAKE) -C $(patsubst _modinst_%, %, $@) modules_install
+
+# modules disabled....
+
+else
+modules modules_install: dummy
+ @echo
+ @echo "The present kernel configuration has modules disabled."
+ @echo "Type 'make config' and enable loadable module support."
+ @echo "Then build a kernel with module support enabled."
+ @echo
+ @exit 1
+endif
+
+clean: archclean
+ find . \( -name '*.[oas]' -o -name core -o -name '.*.flags' \) -type f
-print \
+ | grep -v lxdialog/ | xargs rm -f
+ rm -f $(CLEAN_FILES)
+ rm -rf $(CLEAN_DIRS)
+ $(MAKE) -C Documentation/DocBook clean
+
+mrproper: clean archmrproper
+ find . \( -size 0 -o -name .depend \) -type f -print | xargs rm -f
+ rm -f $(MRPROPER_FILES)
+ rm -rf $(MRPROPER_DIRS)
+ $(MAKE) -C Documentation/DocBook mrproper
+
+distclean: mrproper
+ rm -f core `find . \( -not -type d \) -and \
+ \( -name '*.orig' -o -name '*.rej' -o -name '*~' \
+ -o -name '*.bak' -o -name '#*#' -o -name '.*.orig' \
+ -o -name '.*.rej' -o -name '.SUMS' -o -size 0 \) -type f
-print` TAGS tags
+
+backup: mrproper
+ cd .. && tar cf - linux/ | gzip -9 > backup.gz
+ sync
+
+sgmldocs:
+ chmod 755 $(TOPDIR)/scripts/docgen
+ chmod 755 $(TOPDIR)/scripts/gen-all-syms
+ chmod 755 $(TOPDIR)/scripts/kernel-doc
+ $(MAKE) -C $(TOPDIR)/Documentation/DocBook books
+
+psdocs: sgmldocs
+ $(MAKE) -C Documentation/DocBook ps
+
+pdfdocs: sgmldocs
+ $(MAKE) -C Documentation/DocBook pdf
+
+htmldocs: sgmldocs
+ $(MAKE) -C Documentation/DocBook html
+
+mandocs:
+ chmod 755 $(TOPDIR)/scripts/kernel-doc
+ chmod 755 $(TOPDIR)/scripts/split-man
+ $(MAKE) -C Documentation/DocBook man
+
+sums:
+ find . -type f -print | sort | xargs sum > .SUMS
+
+dep-files: scripts/mkdep archdep include/linux/version.h
+ rm -f .depend .hdepend
+ $(MAKE) $(patsubst %,_sfdep_%,$(SUBDIRS))
_FASTDEP_ALL_SUB_DIRS="$(SUBDIRS)"
+ifdef CONFIG_MODVERSIONS
+ $(MAKE) update-modverfile
+endif
+ scripts/mkdep -- `find $(FINDHPATH) \( -name SCCS -o -name .svn \)
-prune -o -follow -name \*.h ! -name modversions.h -print` > .hdepend
+ scripts/mkdep -- init/*.c > .depend
+
+ifdef CONFIG_MODVERSIONS
+MODVERFILE := $(TOPDIR)/include/linux/modversions.h
+else
+MODVERFILE :=
+endif
+export MODVERFILE
+
+depend dep: dep-files
+
+checkconfig:
+ find * -name '*.[hcS]' -type f -print | sort | xargs $(PERL) -w
scripts/checkconfig.pl
+
+checkhelp:
+ find * -name [cC]onfig.in -print | sort | xargs $(PERL) -w
scripts/checkhelp.pl
+
+checkincludes:
+ find * -name '*.[hcS]' -type f -print | sort | xargs $(PERL) -w
scripts/checkincludes.pl
+
+ifdef CONFIGURATION
+..$(CONFIGURATION):
+ @echo
+ @echo "You have a bad or nonexistent" .$(CONFIGURATION) ": running
'make" $(CONFIGURATION)"'"
+ @echo
+ $(MAKE) $(CONFIGURATION)
+ @echo
+ @echo "Successful. Try re-making (ignore the error that follows)"
+ @echo
+ exit 1
+
+#dummy: ..$(CONFIGURATION)
+dummy:
+
+else
+
+dummy:
+
+endif
+
+include Rules.make
+
+#
+# This generates dependencies for the .h files.
+#
+
+scripts/mkdep: scripts/mkdep.c
+ $(HOSTCC) $(HOSTCFLAGS) -o scripts/mkdep scripts/mkdep.c
+
+scripts/split-include: scripts/split-include.c
+ $(HOSTCC) $(HOSTCFLAGS) -o scripts/split-include scripts/split-include.c
+
+#
+# RPM target
+#
+# If you do a make spec before packing the tarball you can rpm -ta it
+#
+spec:
+ . scripts/mkspec >kernel.spec
+
+#
+# Build a tar ball, generate an rpm from it and pack the result
+# There arw two bits of magic here
+# 1) The use of /. to avoid tar packing just the symlink
+# 2) Removing the .dep files as they have source paths in them that
+# will become invalid
+#
+rpm: clean spec
+ find . \( -size 0 -o -name .depend -o -name .hdepend \) -type f -print
| xargs rm -f
+ set -e; \
+ cd $(TOPDIR)/.. ; \
+ ln -sf $(TOPDIR) $(KERNELPATH) ; \
+ tar -cvz --exclude CVS -f $(KERNELPATH).tar.gz $(KERNELPATH)/. ; \
+ rm $(KERNELPATH) ; \
+ cd $(TOPDIR) ; \
+ . scripts/mkversion > .version ; \
+ $(RPM) -ta $(TOPDIR)/../$(KERNELPATH).tar.gz ; \
+ rm $(TOPDIR)/../$(KERNELPATH).tar.gz
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blkfront/block.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blkfront/block.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,133 @@
+/******************************************************************************
+ * block.h
+ *
+ * Shared definitions between all levels of XenLinux Virtual block devices.
+ *
+ * Copyright (c) 2003-2004, Keir Fraser & Steve Hand
+ * Modifications by Mark A. Williamson are (c) Intel Research Cambridge
+ * Copyright (c) 2004-2005, Christian Limpach
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __XEN_DRIVERS_BLOCK_H__
+#define __XEN_DRIVERS_BLOCK_H__
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/hdreg.h>
+#include <linux/blkdev.h>
+#include <linux/major.h>
+#include <linux/devfs_fs_kernel.h>
+#include <asm-xen/xen-public/xen.h>
+#include <asm-xen/xen-public/io/blkif.h>
+#include <asm-xen/xen-public/io/ring.h>
+#include <asm/io.h>
+#include <asm/atomic.h>
+#include <asm/uaccess.h>
+
+#if 1
+#define IPRINTK(fmt, args...) \
+ printk(KERN_INFO "xen_blk: " fmt, ##args)
+#else
+#define IPRINTK(fmt, args...) ((void)0)
+#endif
+
+#if 1
+#define WPRINTK(fmt, args...) \
+ printk(KERN_WARNING "xen_blk: " fmt, ##args)
+#else
+#define WPRINTK(fmt, args...) ((void)0)
+#endif
+
+#if 0
+#define DPRINTK(_f, _a...) printk ( KERN_ALERT _f , ## _a )
+#else
+#define DPRINTK(_f, _a...) ((void)0)
+#endif
+
+#if 0
+#define DPRINTK_IOCTL(_f, _a...) printk ( KERN_ALERT _f , ## _a )
+#else
+#define DPRINTK_IOCTL(_f, _a...) ((void)0)
+#endif
+
+struct xlbd_type_info {
+ int partn_shift;
+ int disks_per_major;
+ char *devname;
+ char *diskname;
+};
+
+/*
+ * We have one of these per vbd, whether ide, scsi or 'other'. They
+ * hang in private_data off the gendisk structure. We may end up
+ * putting all kinds of interesting stuff here :-)
+ */
+struct xlbd_major_info {
+ int major;
+ int index;
+ int usage;
+ struct xlbd_type_info *type;
+};
+
+struct xlbd_disk_info {
+ int xd_device;
+ struct xlbd_major_info *mi;
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+ struct xlbd_disk_info *next_waiting;
+ request_queue_t *rq;
+#endif
+};
+
+typedef struct xen_block {
+ int usage;
+} xen_block_t;
+
+extern spinlock_t blkif_io_lock;
+
+extern int blkif_open(struct inode *inode, struct file *filep);
+extern int blkif_release(struct inode *inode, struct file *filep);
+extern int blkif_ioctl(struct inode *inode, struct file *filep,
+ unsigned command, unsigned long argument);
+extern int blkif_check(dev_t dev);
+extern int blkif_revalidate(dev_t dev);
+extern void blkif_control_send(blkif_request_t *req, blkif_response_t *rsp);
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+extern void blkif_control_probe_send(
+ blkif_request_t *req, blkif_response_t *rsp, unsigned long address);
+#endif
+extern void do_blkif_request (request_queue_t *rq);
+
+extern void xlvbd_update_vbds(void);
+
+/* Virtual block-device subsystem. */
+extern int xlvbd_init(void);
+extern void xlvbd_cleanup(void);
+
+#endif /* __XEN_DRIVERS_BLOCK_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/xor.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/xor.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,328 @@
+/*
+ * x86-64 changes / gcc fixes from Andi Kleen.
+ * Copyright 2002 Andi Kleen, SuSE Labs.
+ *
+ * This hasn't been optimized for the hammer yet, but there are likely
+ * no advantages to be gotten from x86-64 here anyways.
+ */
+
+typedef struct { unsigned long a,b; } __attribute__((aligned(16))) xmm_store_t;
+
+/* Doesn't use gcc to save the XMM registers, because there is no easy way to
+ tell it to do a clts before the register saving. */
+#define XMMS_SAVE do { \
+ preempt_disable(); \
+ if (!(current_thread_info()->status & TS_USEDFPU)) \
+ clts(); \
+ __asm__ __volatile__ ( \
+ "movups %%xmm0,(%1) ;\n\t" \
+ "movups %%xmm1,0x10(%1) ;\n\t" \
+ "movups %%xmm2,0x20(%1) ;\n\t" \
+ "movups %%xmm3,0x30(%1) ;\n\t" \
+ : "=&r" (cr0) \
+ : "r" (xmm_save) \
+ : "memory"); \
+} while(0)
+
+#define XMMS_RESTORE do { \
+ asm volatile ( \
+ "sfence ;\n\t" \
+ "movups (%1),%%xmm0 ;\n\t" \
+ "movups 0x10(%1),%%xmm1 ;\n\t" \
+ "movups 0x20(%1),%%xmm2 ;\n\t" \
+ "movups 0x30(%1),%%xmm3 ;\n\t" \
+ : \
+ : "r" (cr0), "r" (xmm_save) \
+ : "memory"); \
+ if (!(current_thread_info()->status & TS_USEDFPU)) \
+ stts(); \
+ preempt_enable(); \
+} while(0)
+
+#define OFFS(x) "16*("#x")"
+#define PF_OFFS(x) "256+16*("#x")"
+#define PF0(x) " prefetchnta "PF_OFFS(x)"(%[p1])
;\n"
+#define LD(x,y) " movaps "OFFS(x)"(%[p1]), %%xmm"#y"
;\n"
+#define ST(x,y) " movaps %%xmm"#y", "OFFS(x)"(%[p1])
;\n"
+#define PF1(x) " prefetchnta "PF_OFFS(x)"(%[p2]) ;\n"
+#define PF2(x) " prefetchnta "PF_OFFS(x)"(%[p3]) ;\n"
+#define PF3(x) " prefetchnta "PF_OFFS(x)"(%[p4]) ;\n"
+#define PF4(x) " prefetchnta "PF_OFFS(x)"(%[p5]) ;\n"
+#define PF5(x) " prefetchnta "PF_OFFS(x)"(%[p6]) ;\n"
+#define XO1(x,y) " xorps "OFFS(x)"(%[p2]), %%xmm"#y" ;\n"
+#define XO2(x,y) " xorps "OFFS(x)"(%[p3]), %%xmm"#y" ;\n"
+#define XO3(x,y) " xorps "OFFS(x)"(%[p4]), %%xmm"#y" ;\n"
+#define XO4(x,y) " xorps "OFFS(x)"(%[p5]), %%xmm"#y" ;\n"
+#define XO5(x,y) " xorps "OFFS(x)"(%[p6]), %%xmm"#y" ;\n"
+
+
+static void
+xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+ unsigned int lines = bytes >> 8;
+ unsigned long cr0;
+ xmm_store_t xmm_save[4];
+
+ XMMS_SAVE;
+
+ asm volatile (
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addq %[inc], %[p1] ;\n"
+ " addq %[inc], %[p2] ;\n"
+ " decl %[cnt] ; jnz 1b"
+ : [p1] "+r" (p1), [p2] "+r" (p2), [cnt] "+r" (lines)
+ : [inc] "r" (256UL)
+ : "memory");
+
+ XMMS_RESTORE;
+}
+
+static void
+xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3)
+{
+ unsigned int lines = bytes >> 8;
+ xmm_store_t xmm_save[4];
+ unsigned long cr0;
+
+ XMMS_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF2(i) \
+ PF2(i+2) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addq %[inc], %[p1] ;\n"
+ " addq %[inc], %[p2] ;\n"
+ " addq %[inc], %[p3] ;\n"
+ " decl %[cnt] ; jnz 1b"
+ : [cnt] "+r" (lines),
+ [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3)
+ : [inc] "r" (256UL)
+ : "memory");
+ XMMS_RESTORE;
+}
+
+static void
+xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4)
+{
+ unsigned int lines = bytes >> 8;
+ xmm_store_t xmm_save[4];
+ unsigned long cr0;
+
+ XMMS_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF2(i) \
+ PF2(i+2) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ PF3(i) \
+ PF3(i+2) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ XO3(i,0) \
+ XO3(i+1,1) \
+ XO3(i+2,2) \
+ XO3(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addq %[inc], %[p1] ;\n"
+ " addq %[inc], %[p2] ;\n"
+ " addq %[inc], %[p3] ;\n"
+ " addq %[inc], %[p4] ;\n"
+ " decl %[cnt] ; jnz 1b"
+ : [cnt] "+c" (lines),
+ [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4)
+ : [inc] "r" (256UL)
+ : "memory" );
+
+ XMMS_RESTORE;
+}
+
+static void
+xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+ unsigned int lines = bytes >> 8;
+ xmm_store_t xmm_save[4];
+ unsigned long cr0;
+
+ XMMS_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF2(i) \
+ PF2(i+2) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ PF3(i) \
+ PF3(i+2) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ PF4(i) \
+ PF4(i+2) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO3(i,0) \
+ XO3(i+1,1) \
+ XO3(i+2,2) \
+ XO3(i+3,3) \
+ XO4(i,0) \
+ XO4(i+1,1) \
+ XO4(i+2,2) \
+ XO4(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addq %[inc], %[p1] ;\n"
+ " addq %[inc], %[p2] ;\n"
+ " addq %[inc], %[p3] ;\n"
+ " addq %[inc], %[p4] ;\n"
+ " addq %[inc], %[p5] ;\n"
+ " decl %[cnt] ; jnz 1b"
+ : [cnt] "+c" (lines),
+ [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4),
+ [p5] "+r" (p5)
+ : [inc] "r" (256UL)
+ : "memory");
+
+ XMMS_RESTORE;
+}
+
+static struct xor_block_template xor_block_sse = {
+ .name = "generic_sse",
+ .do_2 = xor_sse_2,
+ .do_3 = xor_sse_3,
+ .do_4 = xor_sse_4,
+ .do_5 = xor_sse_5,
+};
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES \
+ do { \
+ xor_speed(&xor_block_sse); \
+ } while (0)
+
+/* We force the use of the SSE xor block because it can write around L2.
+ We may also be able to load into the L1 only depending on how the cpu
+ deals with a load to a line that is being prefetched. */
+#define XOR_SELECT_TEMPLATE(FASTEST) (&xor_block_sse)
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/xen_proc.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/xen_proc.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,13 @@
+
+#ifndef __ASM_XEN_PROC_H__
+#define __ASM_XEN_PROC_H__
+
+#include <linux/config.h>
+#include <linux/proc_fs.h>
+
+extern struct proc_dir_entry *create_xen_proc_entry(
+ const char *name, mode_t mode);
+extern void remove_xen_proc_entry(
+ const char *name);
+
+#endif /* __ASM_XEN_PROC_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/mmu.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/mmu.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,26 @@
+#ifndef __i386_MMU_H
+#define __i386_MMU_H
+
+#include <asm/semaphore.h>
+/*
+ * The i386 doesn't have a mmu context, but
+ * we put the segment information here.
+ *
+ * cpu_vm_mask is used to optimize ldt flushing.
+ */
+typedef struct {
+ int size;
+ struct semaphore sem;
+ void *ldt;
+ unsigned pinned:1;
+ struct list_head unpinned;
+} mm_context_t;
+
+extern struct list_head mm_unpinned;
+extern spinlock_t mm_unpinned_lock;
+
+/* mm/memory.c:exit_mmap hook */
+extern void _arch_exit_mmap(struct mm_struct *mm);
+#define arch_exit_mmap(_mm) _arch_exit_mmap(_mm)
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/include/linux/irq.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/linux/irq.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,80 @@
+#ifndef __irq_h
+#define __irq_h
+
+/*
+ * Please do not include this file in generic code. There is currently
+ * no requirement for any architecture to implement anything held
+ * within this file.
+ *
+ * Thanks. --rmk
+ */
+
+#include <linux/config.h>
+
+#if !defined(CONFIG_ARCH_S390)
+
+#include <linux/cache.h>
+#include <linux/spinlock.h>
+
+#include <asm/irq.h>
+#include <asm/ptrace.h>
+
+/*
+ * IRQ line status.
+ */
+#define IRQ_INPROGRESS 1 /* IRQ handler active - do not enter! */
+#define IRQ_DISABLED 2 /* IRQ disabled - do not enter! */
+#define IRQ_PENDING 4 /* IRQ pending - replay on enable */
+#define IRQ_REPLAY 8 /* IRQ has been replayed but not acked yet */
+#define IRQ_AUTODETECT 16 /* IRQ is being autodetected */
+#define IRQ_WAITING 32 /* IRQ not yet seen - for autodetection */
+#define IRQ_LEVEL 64 /* IRQ level triggered */
+#define IRQ_MASKED 128 /* IRQ masked - shouldn't be seen again */
+#define IRQ_PER_CPU 256 /* IRQ is per CPU */
+
+/*
+ * Interrupt controller descriptor. This is all we need
+ * to describe about the low-level hardware.
+ */
+struct hw_interrupt_type {
+ const char * typename;
+ unsigned int (*startup)(unsigned int irq);
+ void (*shutdown)(unsigned int irq);
+ void (*enable)(unsigned int irq);
+ void (*disable)(unsigned int irq);
+ void (*ack)(unsigned int irq);
+ void (*end)(unsigned int irq);
+ void (*set_affinity)(unsigned int irq, unsigned long mask);
+};
+
+typedef struct hw_interrupt_type hw_irq_controller;
+
+/*
+ * This is the "IRQ descriptor", which contains various information
+ * about the irq, including what kind of hardware handling it has,
+ * whether it is disabled etc etc.
+ *
+ * Pad this out to 32 bytes for cache and indexing reasons.
+ */
+typedef struct {
+ unsigned int status; /* IRQ status */
+ hw_irq_controller *handler;
+ struct irqaction *action; /* IRQ action list */
+ unsigned int depth; /* nested irq disables */
+ spinlock_t lock;
+} ____cacheline_aligned irq_desc_t;
+
+extern irq_desc_t irq_desc [NR_IRQS];
+
+#include <asm/hw_irq.h> /* the arch dependent stuff */
+
+extern int handle_IRQ_event(unsigned int, struct pt_regs *, struct irqaction
*);
+extern int setup_irq(unsigned int , struct irqaction * );
+extern int teardown_irq(unsigned int , struct irqaction * );
+
+extern hw_irq_controller no_irq_type; /* needed in every arch ? */
+extern void no_action(int cpl, void *dev_id, struct pt_regs *regs);
+
+#endif
+
+#endif /* __irq_h */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/pci/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/pci/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,38 @@
+#
+# Makefile for X86_64 specific PCI routines
+#
+# Reuse the i386 PCI subsystem
+#
+XENARCH := $(subst ",,$(CONFIG_XENARCH))
+CFLAGS += -Iarch/$(XENARCH)/pci
+
+CFLAGS += -Iarch/i386/pci
+
+c-i386-obj-y := i386.o
+c-i386-obj-y += fixup.o
+c-i386-obj-$(CONFIG_ACPI_PCI) += acpi.o
+c-i386-obj-y += legacy.o common.o
+c-i386-obj-$(CONFIG_PCI_DIRECT)+= direct.o
+c-xen-obj-y += irq.o
+# mmconfig has a 64bit special
+c-obj-$(CONFIG_PCI_MMCONFIG) += mmconfig.o
+
+c-obj-$(CONFIG_NUMA) += k8-bus.o
+
+c-link :=
+
+$(patsubst %.o,$(obj)/%.c,$(c-xen-obj-y)):
+ @ln -fsn $(srctree)/arch/xen/i386/pci/$(notdir $@) $@
+
+$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)):
+ @ln -fsn $(srctree)/arch/x86_64/pci/$(notdir $@) $@
+
+$(patsubst %.o,$(obj)/%.c,$(c-i386-obj-y)):
+ @ln -fsn $(srctree)/arch/i386/pci/$(notdir $@) $@
+
+obj-y += $(c-i386-obj-y) $(c-obj-y)
+obj-y += $(c-xen-obj-y)
+
+clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link))
+clean-files += $(patsubst %.o,%.c,$(c-i386-obj-y) $(c-i386-obj-))
+clean-files += $(patsubst %.o,%.c,$(c-xen-obj-y) $(c-xen-obj-))
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/synch_bitops.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/synch_bitops.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,140 @@
+#ifndef __XEN_SYNCH_BITOPS_H__
+#define __XEN_SYNCH_BITOPS_H__
+
+/*
+ * Copyright 1992, Linus Torvalds.
+ * Heavily modified to provide guaranteed strong synchronisation
+ * when communicating with Xen or other guest OSes running on other CPUs.
+ */
+
+#include <linux/config.h>
+
+#define ADDR (*(volatile long *) addr)
+
+static __inline__ void synch_set_bit(int nr, volatile void * addr)
+{
+ __asm__ __volatile__ (
+ "lock btsl %1,%0"
+ : "=m" (ADDR) : "Ir" (nr) : "memory" );
+}
+
+static __inline__ void synch_clear_bit(int nr, volatile void * addr)
+{
+ __asm__ __volatile__ (
+ "lock btrl %1,%0"
+ : "=m" (ADDR) : "Ir" (nr) : "memory" );
+}
+
+static __inline__ void synch_change_bit(int nr, volatile void * addr)
+{
+ __asm__ __volatile__ (
+ "lock btcl %1,%0"
+ : "=m" (ADDR) : "Ir" (nr) : "memory" );
+}
+
+static __inline__ int synch_test_and_set_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+ __asm__ __volatile__ (
+ "lock btsl %2,%1\n\tsbbl %0,%0"
+ : "=r" (oldbit), "=m" (ADDR) : "Ir" (nr) : "memory");
+ return oldbit;
+}
+
+static __inline__ int synch_test_and_clear_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+ __asm__ __volatile__ (
+ "lock btrl %2,%1\n\tsbbl %0,%0"
+ : "=r" (oldbit), "=m" (ADDR) : "Ir" (nr) : "memory");
+ return oldbit;
+}
+
+static __inline__ int synch_test_and_change_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+
+ __asm__ __volatile__ (
+ "lock btcl %2,%1\n\tsbbl %0,%0"
+ : "=r" (oldbit), "=m" (ADDR) : "Ir" (nr) : "memory");
+ return oldbit;
+}
+
+struct __synch_xchg_dummy { unsigned long a[100]; };
+#define __synch_xg(x) ((struct __synch_xchg_dummy *)(x))
+
+#define synch_cmpxchg(ptr, old, new) \
+((__typeof__(*(ptr)))__synch_cmpxchg((ptr),\
+ (unsigned long)(old), \
+ (unsigned long)(new), \
+ sizeof(*(ptr))))
+
+static inline unsigned long __synch_cmpxchg(volatile void *ptr,
+ unsigned long old,
+ unsigned long new, int size)
+{
+ unsigned long prev;
+ switch (size) {
+ case 1:
+ __asm__ __volatile__("lock; cmpxchgb %b1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__synch_xg(ptr)),
+ "0"(old)
+ : "memory");
+ return prev;
+ case 2:
+ __asm__ __volatile__("lock; cmpxchgw %w1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__synch_xg(ptr)),
+ "0"(old)
+ : "memory");
+ return prev;
+#ifdef CONFIG_X86_64
+ case 4:
+ __asm__ __volatile__("lock; cmpxchgl %k1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__synch_xg(ptr)),
+ "0"(old)
+ : "memory");
+ return prev;
+ case 8:
+ __asm__ __volatile__("lock; cmpxchgq %1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__synch_xg(ptr)),
+ "0"(old)
+ : "memory");
+ return prev;
+#else
+ case 4:
+ __asm__ __volatile__("lock; cmpxchgl %1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__synch_xg(ptr)),
+ "0"(old)
+ : "memory");
+ return prev;
+#endif
+ }
+ return old;
+}
+
+static __inline__ int synch_const_test_bit(int nr, const volatile void * addr)
+{
+ return ((1UL << (nr & 31)) &
+ (((const volatile unsigned int *) addr)[nr >> 5])) != 0;
+}
+
+static __inline__ int synch_var_test_bit(int nr, volatile void * addr)
+{
+ int oldbit;
+ __asm__ __volatile__ (
+ "btl %2,%1\n\tsbbl %0,%0"
+ : "=r" (oldbit) : "m" (ADDR), "Ir" (nr) );
+ return oldbit;
+}
+
+#define synch_test_bit(nr,addr) \
+(__builtin_constant_p(nr) ? \
+ synch_const_test_bit((nr),(addr)) : \
+ synch_var_test_bit((nr),(addr)))
+
+#endif /* __XEN_SYNCH_BITOPS_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/kernel/xen_proc.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/kernel/xen_proc.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,18 @@
+
+#include <linux/config.h>
+#include <linux/proc_fs.h>
+
+static struct proc_dir_entry *xen_base;
+
+struct proc_dir_entry *create_xen_proc_entry(const char *name, mode_t mode)
+{
+ if ( xen_base == NULL )
+ if ( (xen_base = proc_mkdir("xen", &proc_root)) == NULL )
+ panic("Couldn't create /proc/xen");
+ return create_proc_entry(name, mode, xen_base);
+}
+
+void remove_xen_proc_entry(const char *name)
+{
+ remove_proc_entry(name, xen_base);
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/i386_ksyms.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/i386_ksyms.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,194 @@
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/user.h>
+#include <linux/elfcore.h>
+#include <linux/mca.h>
+#include <linux/sched.h>
+#include <linux/in6.h>
+#include <linux/interrupt.h>
+#include <linux/smp_lock.h>
+#include <linux/pm.h>
+#include <linux/pci.h>
+#include <linux/apm_bios.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/tty.h>
+#include <linux/highmem.h>
+#include <linux/time.h>
+
+#include <asm/semaphore.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/uaccess.h>
+#include <asm/checksum.h>
+#include <asm/io.h>
+#include <asm/delay.h>
+#include <asm/irq.h>
+#include <asm/mmx.h>
+#include <asm/desc.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/nmi.h>
+#include <asm/ist.h>
+#include <asm/kdebug.h>
+
+extern void dump_thread(struct pt_regs *, struct user *);
+extern spinlock_t rtc_lock;
+
+/* This is definitely a GPL-only symbol */
+EXPORT_SYMBOL_GPL(cpu_gdt_table);
+
+#if defined(CONFIG_APM_MODULE)
+extern void machine_real_restart(unsigned char *, int);
+EXPORT_SYMBOL(machine_real_restart);
+extern void default_idle(void);
+EXPORT_SYMBOL(default_idle);
+#endif
+
+#ifdef CONFIG_SMP
+extern void FASTCALL( __write_lock_failed(rwlock_t *rw));
+extern void FASTCALL( __read_lock_failed(rwlock_t *rw));
+#endif
+
+#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) ||
defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE)
+extern struct drive_info_struct drive_info;
+EXPORT_SYMBOL(drive_info);
+#endif
+
+extern unsigned long cpu_khz;
+extern unsigned long get_cmos_time(void);
+
+/* platform dependent support */
+EXPORT_SYMBOL(boot_cpu_data);
+#ifdef CONFIG_DISCONTIGMEM
+EXPORT_SYMBOL(node_data);
+EXPORT_SYMBOL(physnode_map);
+#endif
+#ifdef CONFIG_X86_NUMAQ
+EXPORT_SYMBOL(xquad_portio);
+#endif
+EXPORT_SYMBOL(dump_thread);
+EXPORT_SYMBOL(dump_fpu);
+EXPORT_SYMBOL_GPL(kernel_fpu_begin);
+EXPORT_SYMBOL(__ioremap);
+EXPORT_SYMBOL(ioremap_nocache);
+EXPORT_SYMBOL(iounmap);
+EXPORT_SYMBOL(kernel_thread);
+EXPORT_SYMBOL(pm_idle);
+#ifdef CONFIG_ACPI_BOOT
+EXPORT_SYMBOL(pm_power_off);
+#endif
+EXPORT_SYMBOL(get_cmos_time);
+EXPORT_SYMBOL(cpu_khz);
+EXPORT_SYMBOL(apm_info);
+
+EXPORT_SYMBOL(__down_failed);
+EXPORT_SYMBOL(__down_failed_interruptible);
+EXPORT_SYMBOL(__down_failed_trylock);
+EXPORT_SYMBOL(__up_wakeup);
+/* Networking helper routines. */
+EXPORT_SYMBOL(csum_partial_copy_generic);
+/* Delay loops */
+EXPORT_SYMBOL(__ndelay);
+EXPORT_SYMBOL(__udelay);
+EXPORT_SYMBOL(__delay);
+EXPORT_SYMBOL(__const_udelay);
+
+EXPORT_SYMBOL(__get_user_1);
+EXPORT_SYMBOL(__get_user_2);
+EXPORT_SYMBOL(__get_user_4);
+
+EXPORT_SYMBOL(strpbrk);
+EXPORT_SYMBOL(strstr);
+
+EXPORT_SYMBOL(strncpy_from_user);
+EXPORT_SYMBOL(__strncpy_from_user);
+EXPORT_SYMBOL(clear_user);
+EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(__copy_from_user_ll);
+EXPORT_SYMBOL(__copy_to_user_ll);
+EXPORT_SYMBOL(strnlen_user);
+
+EXPORT_SYMBOL(dma_alloc_coherent);
+EXPORT_SYMBOL(dma_free_coherent);
+
+#ifdef CONFIG_PCI
+EXPORT_SYMBOL(pcibios_penalize_isa_irq);
+EXPORT_SYMBOL(pci_mem_start);
+#endif
+
+#ifdef CONFIG_PCI_BIOS
+EXPORT_SYMBOL(pcibios_set_irq_routing);
+EXPORT_SYMBOL(pcibios_get_irq_routing_table);
+#endif
+
+#ifdef CONFIG_X86_USE_3DNOW
+EXPORT_SYMBOL(_mmx_memcpy);
+EXPORT_SYMBOL(mmx_clear_page);
+EXPORT_SYMBOL(mmx_copy_page);
+#endif
+
+#ifdef CONFIG_X86_HT
+EXPORT_SYMBOL(smp_num_siblings);
+EXPORT_SYMBOL(cpu_sibling_map);
+#endif
+
+#ifdef CONFIG_SMP
+EXPORT_SYMBOL(cpu_data);
+EXPORT_SYMBOL(cpu_online_map);
+EXPORT_SYMBOL(cpu_callout_map);
+EXPORT_SYMBOL(__write_lock_failed);
+EXPORT_SYMBOL(__read_lock_failed);
+
+/* Global SMP stuff */
+EXPORT_SYMBOL(smp_call_function);
+
+/* TLB flushing */
+EXPORT_SYMBOL(flush_tlb_page);
+EXPORT_SYMBOL_GPL(flush_tlb_all);
+#endif
+
+#ifdef CONFIG_X86_IO_APIC
+EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
+#endif
+
+#ifdef CONFIG_MCA
+EXPORT_SYMBOL(machine_id);
+#endif
+
+#ifdef CONFIG_VT
+EXPORT_SYMBOL(screen_info);
+#endif
+
+EXPORT_SYMBOL(get_wchan);
+
+EXPORT_SYMBOL(rtc_lock);
+
+EXPORT_SYMBOL_GPL(set_nmi_callback);
+EXPORT_SYMBOL_GPL(unset_nmi_callback);
+
+#undef memcmp
+extern int memcmp(const void *,const void *,__kernel_size_t);
+EXPORT_SYMBOL(memcmp);
+
+EXPORT_SYMBOL(register_die_notifier);
+#ifdef CONFIG_HAVE_DEC_LOCK
+EXPORT_SYMBOL(_atomic_dec_and_lock);
+#endif
+
+EXPORT_SYMBOL(__PAGE_KERNEL);
+
+#ifdef CONFIG_HIGHMEM
+EXPORT_SYMBOL(kmap);
+EXPORT_SYMBOL(kunmap);
+EXPORT_SYMBOL(kmap_atomic);
+EXPORT_SYMBOL(kunmap_atomic);
+EXPORT_SYMBOL(kmap_atomic_to_page);
+#endif
+
+#if defined(CONFIG_X86_SPEEDSTEP_SMI) ||
defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE)
+EXPORT_SYMBOL(ist_info);
+#endif
+
+EXPORT_SYMBOL(csum_partial);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/setup.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/setup.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,1375 @@
+/*
+ * linux/arch/x86-64/kernel/setup.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ *
+ * Nov 2001 Dave Jones <davej@xxxxxxx>
+ * Forked from i386 setup code.
+ *
+ * $Id$
+ */
+
+/*
+ * This file handles the architecture-dependent parts of initialization
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/a.out.h>
+#include <linux/tty.h>
+#include <linux/ioport.h>
+#include <linux/delay.h>
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/initrd.h>
+#include <linux/highmem.h>
+#include <linux/bootmem.h>
+#include <linux/module.h>
+#include <asm/processor.h>
+#include <linux/console.h>
+#include <linux/seq_file.h>
+#include <linux/root_dev.h>
+#include <linux/pci.h>
+#include <linux/acpi.h>
+#include <linux/kallsyms.h>
+#include <linux/edd.h>
+#include <linux/percpu.h>
+#include <asm/mtrr.h>
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/msr.h>
+#include <asm/desc.h>
+#include <video/edid.h>
+#include <asm/e820.h>
+#include <asm/dma.h>
+#include <asm/mpspec.h>
+#include <asm/mmu_context.h>
+#include <asm/bootsetup.h>
+#include <asm/proto.h>
+#include <asm/setup.h>
+#include <asm/mach_apic.h>
+#include <asm/numa.h>
+#include <asm-xen/xen-public/physdev.h>
+#include "setup_arch_pre.h"
+#include <asm-xen/hypervisor.h>
+
+#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT)
+#define PFN_PHYS(x) ((x) << PAGE_SHIFT)
+
+#include <asm/mach-xen/setup_arch_post.h>
+
+extern unsigned long start_pfn;
+
+#if 0
+struct edid_info {
+ unsigned char dummy[128];
+};
+#endif
+
+extern struct edid_info edid_info;
+
+/* Allows setting of maximum possible memory size */
+unsigned long xen_override_max_pfn;
+/*
+ * Machine setup..
+ */
+
+struct cpuinfo_x86 boot_cpu_data;
+
+unsigned long mmu_cr4_features;
+EXPORT_SYMBOL_GPL(mmu_cr4_features);
+
+int acpi_disabled;
+EXPORT_SYMBOL(acpi_disabled);
+#ifdef CONFIG_ACPI_BOOT
+extern int __initdata acpi_ht;
+extern acpi_interrupt_flags acpi_sci_flags;
+int __initdata acpi_force = 0;
+#endif
+
+int acpi_numa __initdata;
+
+/* For PCI or other memory-mapped resources */
+unsigned long pci_mem_start = 0x10000000;
+
+/* Boot loader ID as an integer, for the benefit of proc_dointvec */
+int bootloader_type;
+
+unsigned long saved_video_mode;
+
+#ifdef CONFIG_SWIOTLB
+int swiotlb;
+EXPORT_SYMBOL(swiotlb);
+#endif
+
+/*
+ * Setup options
+ */
+struct drive_info_struct { char dummy[32]; } drive_info;
+struct screen_info screen_info;
+struct sys_desc_table_struct {
+ unsigned short length;
+ unsigned char table[0];
+};
+
+struct edid_info edid_info;
+struct e820map e820;
+
+unsigned char aux_device_present;
+
+extern int root_mountflags;
+extern char _text, _etext, _edata, _end;
+
+char command_line[COMMAND_LINE_SIZE];
+
+struct resource standard_io_resources[] = {
+ { .name = "dma1", .start = 0x00, .end = 0x1f,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO },
+ { .name = "pic1", .start = 0x20, .end = 0x21,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO },
+ { .name = "timer0", .start = 0x40, .end = 0x43,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO },
+ { .name = "timer1", .start = 0x50, .end = 0x53,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO },
+ { .name = "keyboard", .start = 0x60, .end = 0x6f,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO },
+ { .name = "dma page reg", .start = 0x80, .end = 0x8f,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO },
+ { .name = "pic2", .start = 0xa0, .end = 0xa1,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO },
+ { .name = "dma2", .start = 0xc0, .end = 0xdf,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO },
+ { .name = "fpu", .start = 0xf0, .end = 0xff,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO }
+};
+
+#define STANDARD_IO_RESOURCES \
+ (sizeof standard_io_resources / sizeof standard_io_resources[0])
+
+#define IORESOURCE_RAM (IORESOURCE_BUSY | IORESOURCE_MEM)
+
+struct resource data_resource = {
+ .name = "Kernel data",
+ .start = 0,
+ .end = 0,
+ .flags = IORESOURCE_RAM,
+};
+struct resource code_resource = {
+ .name = "Kernel code",
+ .start = 0,
+ .end = 0,
+ .flags = IORESOURCE_RAM,
+};
+
+#define IORESOURCE_ROM (IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM)
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+static struct resource system_rom_resource = {
+ .name = "System ROM",
+ .start = 0xf0000,
+ .end = 0xfffff,
+ .flags = IORESOURCE_ROM,
+};
+
+static struct resource extension_rom_resource = {
+ .name = "Extension ROM",
+ .start = 0xe0000,
+ .end = 0xeffff,
+ .flags = IORESOURCE_ROM,
+};
+
+static struct resource adapter_rom_resources[] = {
+ { .name = "Adapter ROM", .start = 0xc8000, .end = 0,
+ .flags = IORESOURCE_ROM },
+ { .name = "Adapter ROM", .start = 0, .end = 0,
+ .flags = IORESOURCE_ROM },
+ { .name = "Adapter ROM", .start = 0, .end = 0,
+ .flags = IORESOURCE_ROM },
+ { .name = "Adapter ROM", .start = 0, .end = 0,
+ .flags = IORESOURCE_ROM },
+ { .name = "Adapter ROM", .start = 0, .end = 0,
+ .flags = IORESOURCE_ROM },
+ { .name = "Adapter ROM", .start = 0, .end = 0,
+ .flags = IORESOURCE_ROM }
+};
+#endif
+
+#define ADAPTER_ROM_RESOURCES \
+ (sizeof adapter_rom_resources / sizeof adapter_rom_resources[0])
+
+static struct resource video_rom_resource = {
+ .name = "Video ROM",
+ .start = 0xc0000,
+ .end = 0xc7fff,
+ .flags = IORESOURCE_ROM,
+};
+
+static struct resource video_ram_resource = {
+ .name = "Video RAM area",
+ .start = 0xa0000,
+ .end = 0xbffff,
+ .flags = IORESOURCE_RAM,
+};
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+#define romsignature(x) (*(unsigned short *)(x) == 0xaa55)
+
+static int __init romchecksum(unsigned char *rom, unsigned long length)
+{
+ unsigned char *p, sum = 0;
+
+ for (p = rom; p < rom + length; p++)
+ sum += *p;
+ return sum == 0;
+}
+
+static void __init probe_roms(void)
+{
+ unsigned long start, length, upper;
+ unsigned char *rom;
+ int i;
+
+ /* video rom */
+ upper = adapter_rom_resources[0].start;
+ for (start = video_rom_resource.start; start < upper; start += 2048) {
+ rom = isa_bus_to_virt(start);
+ if (!romsignature(rom))
+ continue;
+
+ video_rom_resource.start = start;
+
+ /* 0 < length <= 0x7f * 512, historically */
+ length = rom[2] * 512;
+
+ /* if checksum okay, trust length byte */
+ if (length && romchecksum(rom, length))
+ video_rom_resource.end = start + length - 1;
+
+ request_resource(&iomem_resource, &video_rom_resource);
+ break;
+ }
+
+ start = (video_rom_resource.end + 1 + 2047) & ~2047UL;
+ if (start < upper)
+ start = upper;
+
+ /* system rom */
+ request_resource(&iomem_resource, &system_rom_resource);
+ upper = system_rom_resource.start;
+
+ /* check for extension rom (ignore length byte!) */
+ rom = isa_bus_to_virt(extension_rom_resource.start);
+ if (romsignature(rom)) {
+ length = extension_rom_resource.end -
extension_rom_resource.start + 1;
+ if (romchecksum(rom, length)) {
+ request_resource(&iomem_resource,
&extension_rom_resource);
+ upper = extension_rom_resource.start;
+ }
+ }
+
+ /* check for adapter roms on 2k boundaries */
+ for (i = 0; i < ADAPTER_ROM_RESOURCES && start < upper; start += 2048) {
+ rom = isa_bus_to_virt(start);
+ if (!romsignature(rom))
+ continue;
+
+ /* 0 < length <= 0x7f * 512, historically */
+ length = rom[2] * 512;
+
+ /* but accept any length that fits if checksum okay */
+ if (!length || start + length > upper || !romchecksum(rom,
length))
+ continue;
+
+ adapter_rom_resources[i].start = start;
+ adapter_rom_resources[i].end = start + length - 1;
+ request_resource(&iomem_resource, &adapter_rom_resources[i]);
+
+ start = adapter_rom_resources[i++].end & ~2047UL;
+ }
+}
+#endif
+
+/*
+ * Point at the empty zero page to start with. We map the real shared_info
+ * page as soon as fixmap is up and running.
+ */
+shared_info_t *HYPERVISOR_shared_info = (shared_info_t *)empty_zero_page;
+EXPORT_SYMBOL(HYPERVISOR_shared_info);
+
+u32 *phys_to_machine_mapping, *pfn_to_mfn_frame_list;
+
+EXPORT_SYMBOL(phys_to_machine_mapping);
+
+DEFINE_PER_CPU(multicall_entry_t, multicall_list[8]);
+DEFINE_PER_CPU(int, nr_multicall_ents);
+
+/* Raw start-of-day parameters from the hypervisor. */
+union xen_start_info_union xen_start_info_union;
+
+static __init void parse_cmdline_early (char ** cmdline_p)
+{
+ char c = ' ', *to = command_line, *from = COMMAND_LINE;
+ int len = 0, max_cmdline;
+
+ if ((max_cmdline = MAX_GUEST_CMDLINE) > COMMAND_LINE_SIZE)
+ max_cmdline = COMMAND_LINE_SIZE;
+ memcpy(saved_command_line, xen_start_info.cmd_line, max_cmdline);
+ /* Save unparsed command line copy for /proc/cmdline */
+ saved_command_line[max_cmdline-1] = '\0';
+
+ for (;;) {
+ if (c != ' ')
+ goto next_char;
+
+#ifdef CONFIG_SMP
+ /*
+ * If the BIOS enumerates physical processors before logical,
+ * maxcpus=N at enumeration-time can be used to disable HT.
+ */
+ else if (!memcmp(from, "maxcpus=", 8)) {
+ extern unsigned int maxcpus;
+
+ maxcpus = simple_strtoul(from + 8, NULL, 0);
+ }
+#endif
+#ifdef CONFIG_ACPI_BOOT
+ /* "acpi=off" disables both ACPI table parsing and interpreter
init */
+ if (!memcmp(from, "acpi=off", 8))
+ disable_acpi();
+
+ if (!memcmp(from, "acpi=force", 10)) {
+ /* add later when we do DMI horrors: */
+ acpi_force = 1;
+ acpi_disabled = 0;
+ }
+
+ /* acpi=ht just means: do ACPI MADT parsing
+ at bootup, but don't enable the full ACPI interpreter */
+ if (!memcmp(from, "acpi=ht", 7)) {
+ if (!acpi_force)
+ disable_acpi();
+ acpi_ht = 1;
+ }
+ else if (!memcmp(from, "pci=noacpi", 10))
+ acpi_disable_pci();
+ else if (!memcmp(from, "acpi=noirq", 10))
+ acpi_noirq_set();
+
+ else if (!memcmp(from, "acpi_sci=edge", 13))
+ acpi_sci_flags.trigger = 1;
+ else if (!memcmp(from, "acpi_sci=level", 14))
+ acpi_sci_flags.trigger = 3;
+ else if (!memcmp(from, "acpi_sci=high", 13))
+ acpi_sci_flags.polarity = 1;
+ else if (!memcmp(from, "acpi_sci=low", 12))
+ acpi_sci_flags.polarity = 3;
+
+ /* acpi=strict disables out-of-spec workarounds */
+ else if (!memcmp(from, "acpi=strict", 11)) {
+ acpi_strict = 1;
+ }
+#endif
+
+#if 0
+ if (!memcmp(from, "nolapic", 7) ||
+ !memcmp(from, "disableapic", 11))
+ disable_apic = 1;
+
+ if (!memcmp(from, "noapic", 6))
+ skip_ioapic_setup = 1;
+
+ if (!memcmp(from, "apic", 4)) {
+ skip_ioapic_setup = 0;
+ ioapic_force = 1;
+ }
+#endif
+
+ if (!memcmp(from, "mem=", 4))
+ parse_memopt(from+4, &from);
+
+#ifdef CONFIG_DISCONTIGMEM
+ if (!memcmp(from, "numa=", 5))
+ numa_setup(from+5);
+#endif
+
+#ifdef CONFIG_GART_IOMMU
+ if (!memcmp(from,"iommu=",6)) {
+ iommu_setup(from+6);
+ }
+#endif
+
+ if (!memcmp(from,"oops=panic", 10))
+ panic_on_oops = 1;
+
+ if (!memcmp(from, "noexec=", 7))
+ nonx_setup(from + 7);
+
+ next_char:
+ c = *(from++);
+ if (!c)
+ break;
+ if (COMMAND_LINE_SIZE <= ++len)
+ break;
+ *(to++) = c;
+ }
+ *to = '\0';
+ *cmdline_p = command_line;
+}
+
+#ifndef CONFIG_DISCONTIGMEM
+static void __init contig_initmem_init(void)
+{
+ unsigned long bootmap_size, bootmap;
+
+ /*
+ * partially used pages are not usable - thus
+ * we are rounding upwards:
+ */
+
+ bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
+ bootmap = start_pfn;
+ bootmap_size = init_bootmem(bootmap, end_pfn);
+ reserve_bootmem(bootmap, bootmap_size);
+
+ free_bootmem(start_pfn << PAGE_SHIFT, (end_pfn - start_pfn) <<
PAGE_SHIFT);
+ printk("Registering memory for bootmem: from %lx, size = %lx\n",
+ start_pfn << PAGE_SHIFT, (end_pfn - start_pfn) <<
PAGE_SHIFT);
+ /*
+ * This should cover kernel_end
+ */
+#if 0
+ reserve_bootmem(HIGH_MEMORY, (PFN_PHYS(start_pfn) +
+ bootmap_size + PAGE_SIZE-1) -
(HIGH_MEMORY));
+#endif
+ reserve_bootmem(0, (PFN_PHYS(start_pfn) +
+ bootmap_size + PAGE_SIZE-1));
+
+}
+#endif
+
+/* Use inline assembly to define this because the nops are defined
+ as inline assembly strings in the include files and we cannot
+ get them easily into strings. */
+asm("\t.data\nk8nops: "
+ K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
+ K8_NOP7 K8_NOP8);
+
+extern unsigned char k8nops[];
+static unsigned char *k8_nops[ASM_NOP_MAX+1] = {
+ NULL,
+ k8nops,
+ k8nops + 1,
+ k8nops + 1 + 2,
+ k8nops + 1 + 2 + 3,
+ k8nops + 1 + 2 + 3 + 4,
+ k8nops + 1 + 2 + 3 + 4 + 5,
+ k8nops + 1 + 2 + 3 + 4 + 5 + 6,
+ k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+};
+
+/* Replace instructions with better alternatives for this CPU type.
+
+ This runs before SMP is initialized to avoid SMP problems with
+ self modifying code. This implies that assymetric systems where
+ APs have less capabilities than the boot processor are not handled.
+ In this case boot with "noreplacement". */
+void apply_alternatives(void *start, void *end)
+{
+ struct alt_instr *a;
+ int diff, i, k;
+ for (a = start; (void *)a < end; a++) {
+ if (!boot_cpu_has(a->cpuid))
+ continue;
+
+ BUG_ON(a->replacementlen > a->instrlen);
+ __inline_memcpy(a->instr, a->replacement, a->replacementlen);
+ diff = a->instrlen - a->replacementlen;
+
+ /* Pad the rest with nops */
+ for (i = a->replacementlen; diff > 0; diff -= k, i += k) {
+ k = diff;
+ if (k > ASM_NOP_MAX)
+ k = ASM_NOP_MAX;
+ __inline_memcpy(a->instr + i, k8_nops[k], k);
+ }
+ }
+}
+
+static int no_replacement __initdata = 0;
+
+void __init alternative_instructions(void)
+{
+ extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
+ if (no_replacement)
+ return;
+ apply_alternatives(__alt_instructions, __alt_instructions_end);
+}
+
+static int __init noreplacement_setup(char *s)
+{
+ no_replacement = 1;
+ return 0;
+}
+
+__setup("noreplacement", noreplacement_setup);
+
+#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
+struct edd edd;
+#ifdef CONFIG_EDD_MODULE
+EXPORT_SYMBOL(edd);
+#endif
+/**
+ * copy_edd() - Copy the BIOS EDD information
+ * from boot_params into a safe place.
+ *
+ */
+static inline void copy_edd(void)
+{
+ memcpy(edd.mbr_signature, EDD_MBR_SIGNATURE, sizeof(edd.mbr_signature));
+ memcpy(edd.edd_info, EDD_BUF, sizeof(edd.edd_info));
+ edd.mbr_signature_nr = EDD_MBR_SIG_NR;
+ edd.edd_info_nr = EDD_NR;
+}
+#else
+static inline void copy_edd(void)
+{
+}
+#endif
+
+#if 0
+#define EBDA_ADDR_POINTER 0x40E
+static void __init reserve_ebda_region(void)
+{
+ unsigned int addr;
+ /**
+ * there is a real-mode segmented pointer pointing to the
+ * 4K EBDA area at 0x40E
+ */
+ addr = *(unsigned short *)phys_to_virt(EBDA_ADDR_POINTER);
+ addr <<= 4;
+ if (addr)
+ reserve_bootmem_generic(addr, PAGE_SIZE);
+}
+#endif
+
+/*
+ * Guest physical starts from 0.
+ */
+
+unsigned long __init xen_end_of_ram(void)
+{
+ unsigned long max_end_pfn = xen_start_info.nr_pages;
+
+ if ( xen_override_max_pfn < max_end_pfn)
+ xen_override_max_pfn = max_end_pfn;
+
+ return xen_override_max_pfn;
+}
+
+static void __init print_memory_map(char *who)
+{
+ int i;
+
+ for (i = 0; i < e820.nr_map; i++) {
+ early_printk(" %s: %016Lx - %016Lx ", who,
+ e820.map[i].addr,
+ e820.map[i].addr + e820.map[i].size);
+ switch (e820.map[i].type) {
+ case E820_RAM: early_printk("(usable)\n");
+ break;
+ case E820_RESERVED:
+ early_printk("(reserved)\n");
+ break;
+ case E820_ACPI:
+ early_printk("(ACPI data)\n");
+ break;
+ case E820_NVS:
+ early_printk("(ACPI NVS)\n");
+ break;
+ default: early_printk("type %u\n", e820.map[i].type);
+ break;
+ }
+ }
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+ unsigned long low_mem_size;
+ int i, j;
+ physdev_op_t op;
+
+#if 0
+ ROOT_DEV = old_decode_dev(ORIG_ROOT_DEV);
+#else
+ ROOT_DEV = MKDEV(RAMDISK_MAJOR,0);
+#endif
+ drive_info = DRIVE_INFO;
+
+#ifdef CONFIG_XEN_PHYSDEV_ACCESS
+ screen_info = SCREEN_INFO;
+#endif
+ edid_info = EDID_INFO;
+ aux_device_present = AUX_DEVICE_INFO;
+ saved_video_mode = SAVED_VIDEO_MODE;
+ bootloader_type = LOADER_TYPE;
+
+#ifdef CONFIG_BLK_DEV_RAM
+ rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK;
+ rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0);
+ rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0);
+#endif
+/* register_console(&xen_console); */
+
+#ifdef CONFIG_XEN_PHYSDEV_ACCESS
+ /* This is drawn from a dump from vgacon:startup in standard Linux. */
+ screen_info.orig_video_mode = 3;
+ screen_info.orig_video_isVGA = 1;
+ screen_info.orig_video_lines = 25;
+ screen_info.orig_video_cols = 80;
+ screen_info.orig_video_ega_bx = 3;
+ screen_info.orig_video_points = 16;
+#endif
+ ARCH_SETUP
+ print_memory_map(machine_specific_memory_setup());
+
+ /* copy_edd(); */
+
+ if (!MOUNT_ROOT_RDONLY)
+ root_mountflags &= ~MS_RDONLY;
+ init_mm.start_code = (unsigned long) &_text;
+ init_mm.end_code = (unsigned long) &_etext;
+ init_mm.end_data = (unsigned long) &_edata;
+/* init_mm.brk = (unsigned long) &_end; */
+ init_mm.brk = start_pfn << PAGE_SHIFT;
+
+
+#if 0 /* XEN: This is nonsense: kernel may not even be contiguous in RAM. */
+ code_resource.start = virt_to_phys(&_text);
+ code_resource.end = virt_to_phys(&_etext)-1;
+ data_resource.start = virt_to_phys(&_etext);
+ data_resource.end = virt_to_phys(&_edata)-1;
+#endif
+ parse_cmdline_early(cmdline_p);
+
+ early_identify_cpu(&boot_cpu_data);
+
+ /*
+ * partially used pages are not usable - thus
+ * we are rounding upwards:
+ */
+#if 0
+ end_pfn = e820_end_of_ram();
+#else
+ end_pfn = xen_end_of_ram();
+#endif
+
+ check_efer();
+
+ init_memory_mapping(0, (end_pfn << PAGE_SHIFT));
+
+#ifdef CONFIG_ACPI_NUMA
+ /*
+ * Parse SRAT to discover nodes.
+ */
+ acpi_numa_init();
+#endif
+
+#ifdef CONFIG_DISCONTIGMEM
+ numa_initmem_init(0, end_pfn);
+#else
+ contig_initmem_init();
+#endif
+
+ /* Reserve direct mapping and shared info etc. */
+// reserve_bootmem_generic(table_start << PAGE_SHIFT, (table_end + 1 -
table_start) << PAGE_SHIFT);
+
+// reserve_bootmem_generic(0, (table_end + 1) << PAGE_SHIFT);
+
+ /* reserve kernel */
+// kernel_end = round_up(__pa_symbol(&_end),PAGE_SIZE);
+
+#if 0
+ /*
+ * reserve physical page 0 - it's a special BIOS page on many boxes,
+ * enabling clean reboots, SMP operation, laptop functions.
+ */
+ reserve_bootmem_generic(0, PAGE_SIZE);
+#endif
+
+ /* reserve ebda region */
+/* reserve_ebda_region(); */
+
+#ifdef CONFIG_SMP
+ /*
+ * But first pinch a few for the stack/trampoline stuff
+ * FIXME: Don't need the extra page at 4K, but need to fix
+ * trampoline before removing it. (see the GDT stuff)
+ */
+ reserve_bootmem_generic(PAGE_SIZE, PAGE_SIZE);
+
+ /* Reserve SMP trampoline */
+ reserve_bootmem_generic(SMP_TRAMPOLINE_BASE, PAGE_SIZE);
+#endif
+
+#ifdef CONFIG_ACPI_SLEEP
+ /*
+ * Reserve low memory region for sleep support.
+ */
+ acpi_reserve_bootmem();
+#endif
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (xen_start_info.mod_start) {
+ if (INITRD_START + INITRD_SIZE <= (end_pfn << PAGE_SHIFT)) {
+ /*reserve_bootmem_generic(INITRD_START, INITRD_SIZE);*/
+ initrd_start = INITRD_START + PAGE_OFFSET;
+ initrd_end = initrd_start+INITRD_SIZE;
+ initrd_below_start_ok = 1;
+ } else {
+ printk(KERN_ERR "initrd extends beyond end of memory "
+ "(0x%08lx > 0x%08lx)\ndisabling initrd\n",
+ (unsigned long)(INITRD_START + INITRD_SIZE),
+ (unsigned long)(end_pfn << PAGE_SHIFT));
+ initrd_start = 0;
+ }
+ }
+#endif
+ paging_init();
+#ifdef CONFIG_X86_LOCAL_APIC
+ /*
+ * Find and reserve possible boot-time SMP configuration:
+ */
+ find_smp_config();
+#endif
+ /* Make sure we have a large enough P->M table. */
+ if (end_pfn > xen_start_info.nr_pages) {
+ phys_to_machine_mapping = alloc_bootmem(
+ max_pfn * sizeof(unsigned long));
+ memset(phys_to_machine_mapping, ~0,
+ max_pfn * sizeof(unsigned long));
+ memcpy(phys_to_machine_mapping,
+ (unsigned long *)xen_start_info.mfn_list,
+ xen_start_info.nr_pages * sizeof(unsigned long));
+ free_bootmem(
+ __pa(xen_start_info.mfn_list),
+ PFN_PHYS(PFN_UP(xen_start_info.nr_pages *
+ sizeof(unsigned long))));
+ }
+
+ pfn_to_mfn_frame_list = alloc_bootmem(PAGE_SIZE);
+
+ for ( i=0, j=0; i < end_pfn; i+=(PAGE_SIZE/sizeof(unsigned long)), j++ )
+ {
+ pfn_to_mfn_frame_list[j] =
+ virt_to_machine(&phys_to_machine_mapping[i]) >> PAGE_SHIFT;
+ }
+
+#if 0
+ check_ioapic();
+#endif
+
+#ifdef CONFIG_ACPI_BOOT
+ /*
+ * Initialize the ACPI boot-time table parser (gets the RSDP and SDT).
+ * Call this early for SRAT node setup.
+ */
+ acpi_boot_table_init();
+
+ /*
+ * Read APIC and some other early information from ACPI tables.
+ */
+ acpi_boot_init();
+#endif
+#ifdef CONFIG_X86_LOCAL_APIC
+ /*
+ * get boot-time SMP configuration:
+ */
+ if (smp_found_config)
+ get_smp_config();
+#ifndef CONFIG_XEN
+ init_apic_mappings();
+#endif
+#endif
+
+ /* XXX Disable irqdebug until we have a way to avoid interrupt
+ * conflicts. */
+/* noirqdebug_setup(""); */
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ /*
+ * Request address space for all standard RAM and ROM resources
+ * and also for regions reported as reserved by the e820.
+ */
+ probe_roms();
+#endif
+/* e820_reserve_resources(); */
+
+ request_resource(&iomem_resource, &video_ram_resource);
+
+ {
+ unsigned i;
+ /* request I/O space for devices used on all i[345]86 PCs */
+ for (i = 0; i < STANDARD_IO_RESOURCES; i++)
+ request_resource(&ioport_resource, &standard_io_resources[i]);
+ }
+
+ /* Will likely break when you have unassigned resources with more
+ than 4GB memory and bridges that don't support more than 4GB.
+ Doing it properly would require to use pci_alloc_consistent
+ in this case. */
+ low_mem_size = ((end_pfn << PAGE_SHIFT) + 0xfffff) & ~0xfffff;
+ if (low_mem_size > pci_mem_start)
+ pci_mem_start = low_mem_size;
+
+#ifdef CONFIG_GART_IOMMU
+ iommu_hole_init();
+#endif
+
+ op.cmd = PHYSDEVOP_SET_IOPL;
+ op.u.set_iopl.iopl = current->thread.io_pl = 1;
+ HYPERVISOR_physdev_op(&op);
+
+ if (xen_start_info.flags & SIF_INITDOMAIN) {
+ if (!(xen_start_info.flags & SIF_PRIVILEGED))
+ panic("Xen granted us console access "
+ "but not privileged status");
+
+#ifdef CONFIG_VT
+#if defined(CONFIG_VGA_CONSOLE)
+ conswitchp = &vga_con;
+#elif defined(CONFIG_DUMMY_CONSOLE)
+ conswitchp = &dummy_con;
+#endif
+#endif
+ } else {
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ extern const struct consw xennull_con;
+ extern int console_use_vt;
+#if defined(CONFIG_VGA_CONSOLE)
+ /* disable VGA driver */
+ ORIG_VIDEO_ISVGA = VIDEO_TYPE_VLFB;
+#endif
+ conswitchp = &xennull_con;
+ console_use_vt = 0;
+#endif
+ }
+}
+
+static int __init get_model_name(struct cpuinfo_x86 *c)
+{
+ unsigned int *v;
+
+ if (c->x86_cpuid_level < 0x80000004)
+ return 0;
+
+ v = (unsigned int *) c->x86_model_id;
+ cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]);
+ cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]);
+ cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
+ c->x86_model_id[48] = 0;
+ return 1;
+}
+
+
+static void __init display_cacheinfo(struct cpuinfo_x86 *c)
+{
+ unsigned int n, dummy, eax, ebx, ecx, edx;
+
+ n = c->x86_cpuid_level;
+
+ if (n >= 0x80000005) {
+ cpuid(0x80000005, &dummy, &ebx, &ecx, &edx);
+ printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache
%dK (%d bytes/line)\n",
+ edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
+ c->x86_cache_size=(ecx>>24)+(edx>>24);
+ /* On K8 L1 TLB is inclusive, so don't count it */
+ c->x86_tlbsize = 0;
+ }
+
+ if (n >= 0x80000006) {
+ cpuid(0x80000006, &dummy, &ebx, &ecx, &edx);
+ ecx = cpuid_ecx(0x80000006);
+ c->x86_cache_size = ecx >> 16;
+ c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff);
+
+ printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
+ c->x86_cache_size, ecx & 0xFF);
+ }
+
+ if (n >= 0x80000007)
+ cpuid(0x80000007, &dummy, &dummy, &dummy, &c->x86_power);
+ if (n >= 0x80000008) {
+ cpuid(0x80000008, &eax, &dummy, &dummy, &dummy);
+ c->x86_virt_bits = (eax >> 8) & 0xff;
+ c->x86_phys_bits = eax & 0xff;
+ }
+}
+
+
+static int __init init_amd(struct cpuinfo_x86 *c)
+{
+ int r;
+ int level;
+#ifdef CONFIG_NUMA
+ int cpu;
+#endif
+
+ /* Bit 31 in normal CPUID used for nonstandard 3DNow ID;
+ 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */
+ clear_bit(0*32+31, &c->x86_capability);
+
+ /* C-stepping K8? */
+ level = cpuid_eax(1);
+ if ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58)
+ set_bit(X86_FEATURE_K8_C, &c->x86_capability);
+
+ r = get_model_name(c);
+ if (!r) {
+ switch (c->x86) {
+ case 15:
+ /* Should distinguish Models here, but this is only
+ a fallback anyways. */
+ strcpy(c->x86_model_id, "Hammer");
+ break;
+ }
+ }
+ display_cacheinfo(c);
+
+ if (c->x86_cpuid_level >= 0x80000008) {
+ c->x86_num_cores = (cpuid_ecx(0x80000008) & 0xff) + 1;
+ if (c->x86_num_cores & (c->x86_num_cores - 1))
+ c->x86_num_cores = 1;
+
+#ifdef CONFIG_NUMA
+ /* On a dual core setup the lower bits of apic id
+ distingush the cores. Fix up the CPU<->node mappings
+ here based on that.
+ Assumes number of cores is a power of two.
+ When using SRAT use mapping from SRAT. */
+ cpu = c->x86_apicid;
+ if (acpi_numa <= 0 && c->x86_num_cores > 1) {
+ cpu_to_node[cpu] = cpu >> hweight32(c->x86_num_cores -
1);
+ if (!node_online(cpu_to_node[cpu]))
+ cpu_to_node[cpu] = first_node(node_online_map);
+ }
+ printk(KERN_INFO "CPU %d(%d) -> Node %d\n",
+ cpu, c->x86_num_cores, cpu_to_node[cpu]);
+#endif
+ }
+
+ return r;
+}
+
+static void __init detect_ht(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+ u32 eax, ebx, ecx, edx;
+ int index_lsb, index_msb, tmp;
+ int cpu = smp_processor_id();
+
+ if (!cpu_has(c, X86_FEATURE_HT))
+ return;
+
+ cpuid(1, &eax, &ebx, &ecx, &edx);
+ smp_num_siblings = (ebx & 0xff0000) >> 16;
+
+ if (smp_num_siblings == 1) {
+ printk(KERN_INFO "CPU: Hyper-Threading is disabled\n");
+ } else if (smp_num_siblings > 1) {
+ index_lsb = 0;
+ index_msb = 31;
+ /*
+ * At this point we only support two siblings per
+ * processor package.
+ */
+ if (smp_num_siblings > NR_CPUS) {
+ printk(KERN_WARNING "CPU: Unsupported number of the
siblings %d", smp_num_siblings);
+ smp_num_siblings = 1;
+ return;
+ }
+ tmp = smp_num_siblings;
+ while ((tmp & 1) == 0) {
+ tmp >>=1 ;
+ index_lsb++;
+ }
+ tmp = smp_num_siblings;
+ while ((tmp & 0x80000000 ) == 0) {
+ tmp <<=1 ;
+ index_msb--;
+ }
+ if (index_lsb != index_msb )
+ index_msb++;
+ phys_proc_id[cpu] = phys_pkg_id(index_msb);
+
+ printk(KERN_INFO "CPU: Physical Processor ID: %d\n",
+ phys_proc_id[cpu]);
+ }
+#endif
+}
+
+static void __init sched_cmp_hack(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+ /* AMD dual core looks like HT but isn't really. Hide it from the
+ scheduler. This works around problems with the domain scheduler.
+ Also probably gives slightly better scheduling and disables
+ SMT nice which is harmful on dual core.
+ TBD tune the domain scheduler for dual core. */
+ if (c->x86_vendor == X86_VENDOR_AMD && cpu_has(c,
X86_FEATURE_CMP_LEGACY))
+ smp_num_siblings = 1;
+#endif
+}
+
+static void __init init_intel(struct cpuinfo_x86 *c)
+{
+ /* Cache sizes */
+ unsigned n;
+
+ init_intel_cacheinfo(c);
+ n = c->x86_cpuid_level;
+ if (n >= 0x80000008) {
+ unsigned eax = cpuid_eax(0x80000008);
+ c->x86_virt_bits = (eax >> 8) & 0xff;
+ c->x86_phys_bits = eax & 0xff;
+ }
+
+ if (c->x86 == 15)
+ c->x86_cache_alignment = c->x86_clflush_size * 2;
+}
+
+void __init get_cpu_vendor(struct cpuinfo_x86 *c)
+{
+ char *v = c->x86_vendor_id;
+
+ if (!strcmp(v, "AuthenticAMD"))
+ c->x86_vendor = X86_VENDOR_AMD;
+ else if (!strcmp(v, "GenuineIntel"))
+ c->x86_vendor = X86_VENDOR_INTEL;
+ else
+ c->x86_vendor = X86_VENDOR_UNKNOWN;
+}
+
+struct cpu_model_info {
+ int vendor;
+ int family;
+ char *model_names[16];
+};
+
+/* Do some early cpuid on the boot CPU to get some parameter that are
+ needed before check_bugs. Everything advanced is in identify_cpu
+ below. */
+void __init early_identify_cpu(struct cpuinfo_x86 *c)
+{
+ u32 tfms;
+
+ c->loops_per_jiffy = loops_per_jiffy;
+ c->x86_cache_size = -1;
+ c->x86_vendor = X86_VENDOR_UNKNOWN;
+ c->x86_model = c->x86_mask = 0; /* So far unknown... */
+ c->x86_vendor_id[0] = '\0'; /* Unset */
+ c->x86_model_id[0] = '\0'; /* Unset */
+ c->x86_clflush_size = 64;
+ c->x86_cache_alignment = c->x86_clflush_size;
+ c->x86_num_cores = 1;
+ c->x86_apicid = c == &boot_cpu_data ? 0 : c - cpu_data;
+ c->x86_cpuid_level = 0;
+ memset(&c->x86_capability, 0, sizeof c->x86_capability);
+
+ /* Get vendor name */
+ cpuid(0x00000000, (unsigned int *)&c->cpuid_level,
+ (unsigned int *)&c->x86_vendor_id[0],
+ (unsigned int *)&c->x86_vendor_id[8],
+ (unsigned int *)&c->x86_vendor_id[4]);
+
+ get_cpu_vendor(c);
+
+ /* Initialize the standard set of capabilities */
+ /* Note that the vendor-specific code below might override */
+
+ /* Intel-defined flags: level 0x00000001 */
+ if (c->cpuid_level >= 0x00000001) {
+ __u32 misc;
+ cpuid(0x00000001, &tfms, &misc, &c->x86_capability[4],
+ &c->x86_capability[0]);
+ c->x86 = (tfms >> 8) & 0xf;
+ c->x86_model = (tfms >> 4) & 0xf;
+ c->x86_mask = tfms & 0xf;
+ if (c->x86 == 0xf) {
+ c->x86 += (tfms >> 20) & 0xff;
+ c->x86_model += ((tfms >> 16) & 0xF) << 4;
+ }
+ if (c->x86_capability[0] & (1<<19))
+ c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
+ c->x86_apicid = misc >> 24;
+ } else {
+ /* Have CPUID level 0 only - unheard of */
+ c->x86 = 4;
+ }
+}
+
+/*
+ * This does the hard work of actually picking apart the CPU stuff...
+ */
+void __init identify_cpu(struct cpuinfo_x86 *c)
+{
+ int i;
+ u32 xlvl;
+
+ early_identify_cpu(c);
+
+ /* AMD-defined flags: level 0x80000001 */
+ xlvl = cpuid_eax(0x80000000);
+ c->x86_cpuid_level = xlvl;
+ if ((xlvl & 0xffff0000) == 0x80000000) {
+ if (xlvl >= 0x80000001) {
+ c->x86_capability[1] = cpuid_edx(0x80000001);
+ c->x86_capability[5] = cpuid_ecx(0x80000001);
+ }
+ if (xlvl >= 0x80000004)
+ get_model_name(c); /* Default name */
+ }
+
+ /* Transmeta-defined flags: level 0x80860001 */
+ xlvl = cpuid_eax(0x80860000);
+ if ((xlvl & 0xffff0000) == 0x80860000) {
+ /* Don't set x86_cpuid_level here for now to not confuse. */
+ if (xlvl >= 0x80860001)
+ c->x86_capability[2] = cpuid_edx(0x80860001);
+ }
+
+ /*
+ * Vendor-specific initialization. In this section we
+ * canonicalize the feature flags, meaning if there are
+ * features a certain CPU supports which CPUID doesn't
+ * tell us, CPUID claiming incorrect flags, or other bugs,
+ * we handle them here.
+ *
+ * At the end of this section, c->x86_capability better
+ * indicate the features this CPU genuinely supports!
+ */
+ switch (c->x86_vendor) {
+ case X86_VENDOR_AMD:
+ init_amd(c);
+ break;
+
+ case X86_VENDOR_INTEL:
+ init_intel(c);
+ break;
+
+ case X86_VENDOR_UNKNOWN:
+ default:
+ display_cacheinfo(c);
+ break;
+ }
+
+ select_idle_routine(c);
+ detect_ht(c);
+ sched_cmp_hack(c);
+
+ /*
+ * On SMP, boot_cpu_data holds the common feature set between
+ * all CPUs; so make sure that we indicate which features are
+ * common between the CPUs. The first time this routine gets
+ * executed, c == &boot_cpu_data.
+ */
+ if (c != &boot_cpu_data) {
+ /* AND the already accumulated flags with these */
+ for (i = 0 ; i < NCAPINTS ; i++)
+ boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
+ }
+
+#ifdef CONFIG_X86_MCE
+ mcheck_init(c);
+#endif
+#ifdef CONFIG_NUMA
+ if (c != &boot_cpu_data)
+ numa_add_cpu(c - cpu_data);
+#endif
+}
+
+
+void __init print_cpu_info(struct cpuinfo_x86 *c)
+{
+ if (c->x86_model_id[0])
+ printk("%s", c->x86_model_id);
+
+ if (c->x86_mask || c->cpuid_level >= 0)
+ printk(" stepping %02x\n", c->x86_mask);
+ else
+ printk("\n");
+}
+
+/*
+ * Get CPU information for use by the procfs.
+ */
+
+static int show_cpuinfo(struct seq_file *m, void *v)
+{
+ struct cpuinfo_x86 *c = v;
+
+ /*
+ * These flag bits must match the definitions in <asm/cpufeature.h>.
+ * NULL means this bit is undefined or reserved; either way it doesn't
+ * have meaning as far as Linux is concerned. Note that it's important
+ * to realize there is a difference between this table and CPUID -- if
+ * applications want to get the raw CPUID data, they should access
+ * /dev/cpu/<cpu_nr>/cpuid instead.
+ */
+ static char *x86_cap_flags[] = {
+ /* Intel-defined */
+ "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce",
+ "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov",
+ "pat", "pse36", "pn", "clflush", NULL, "dts", "acpi", "mmx",
+ "fxsr", "sse", "sse2", "ss", "ht", "tm", "ia64", NULL,
+
+ /* AMD-defined */
+ "pni", NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, "nx", NULL, "mmxext", NULL,
+ NULL, "fxsr_opt", NULL, NULL, NULL, "lm", "3dnowext", "3dnow",
+
+ /* Transmeta-defined */
+ "recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+
+ /* Other (Linux-defined) */
+ "cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr", NULL, NULL,
NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+
+ /* Intel-defined (#2) */
+ "pni", NULL, NULL, "monitor", "ds_cpl", NULL, NULL, "est",
+ "tm2", NULL, "cid", NULL, NULL, "cx16", "xtpr", NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+
+ /* AMD-defined (#2) */
+ "lahf_lm", "cmp_legacy", NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL
+ };
+ static char *x86_power_flags[] = {
+ "ts", /* temperature sensor */
+ "fid", /* frequency id control */
+ "vid", /* voltage id control */
+ "ttp", /* thermal trip */
+ };
+
+
+#ifdef CONFIG_SMP
+ if (!cpu_online(c-cpu_data))
+ return 0;
+#endif
+
+ seq_printf(m,"processor\t: %u\n"
+ "vendor_id\t: %s\n"
+ "cpu family\t: %d\n"
+ "model\t\t: %d\n"
+ "model name\t: %s\n",
+ (unsigned)(c-cpu_data),
+ c->x86_vendor_id[0] ? c->x86_vendor_id : "unknown",
+ c->x86,
+ (int)c->x86_model,
+ c->x86_model_id[0] ? c->x86_model_id : "unknown");
+
+ if (c->x86_mask || c->cpuid_level >= 0)
+ seq_printf(m, "stepping\t: %d\n", c->x86_mask);
+ else
+ seq_printf(m, "stepping\t: unknown\n");
+
+ if (cpu_has(c,X86_FEATURE_TSC)) {
+ seq_printf(m, "cpu MHz\t\t: %u.%03u\n",
+ cpu_khz / 1000, (cpu_khz % 1000));
+ }
+
+ /* Cache size */
+ if (c->x86_cache_size >= 0)
+ seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size);
+
+#ifdef CONFIG_SMP
+ seq_printf(m, "physical id\t: %d\n", phys_proc_id[c - cpu_data]);
+ seq_printf(m, "siblings\t: %d\n", c->x86_num_cores * smp_num_siblings);
+#endif
+
+ seq_printf(m,
+ "fpu\t\t: yes\n"
+ "fpu_exception\t: yes\n"
+ "cpuid level\t: %d\n"
+ "wp\t\t: yes\n"
+ "flags\t\t:",
+ c->cpuid_level);
+
+ {
+ int i;
+ for ( i = 0 ; i < 32*NCAPINTS ; i++ )
+ if ( test_bit(i, &c->x86_capability) &&
+ x86_cap_flags[i] != NULL )
+ seq_printf(m, " %s", x86_cap_flags[i]);
+ }
+
+ seq_printf(m, "\nbogomips\t: %lu.%02lu\n",
+ c->loops_per_jiffy/(500000/HZ),
+ (c->loops_per_jiffy/(5000/HZ)) % 100);
+
+ if (c->x86_tlbsize > 0)
+ seq_printf(m, "TLB size\t: %d 4K pages\n", c->x86_tlbsize);
+ seq_printf(m, "clflush size\t: %d\n", c->x86_clflush_size);
+ seq_printf(m, "cache_alignment\t: %d\n", c->x86_cache_alignment);
+
+ seq_printf(m, "address sizes\t: %u bits physical, %u bits virtual\n",
+ c->x86_phys_bits, c->x86_virt_bits);
+
+ seq_printf(m, "power management:");
+ {
+ unsigned i;
+ for (i = 0; i < 32; i++)
+ if (c->x86_power & (1 << i)) {
+ if (i < ARRAY_SIZE(x86_power_flags))
+ seq_printf(m, " %s",
x86_power_flags[i]);
+ else
+ seq_printf(m, " [%d]", i);
+ }
+ }
+ seq_printf(m, "\n");
+
+ if (c->x86_num_cores > 1)
+ seq_printf(m, "cpu cores\t: %d\n", c->x86_num_cores);
+
+ seq_printf(m, "\n\n");
+
+ return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+ return *pos < NR_CPUS ? cpu_data + *pos : NULL;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ ++*pos;
+ return c_start(m, pos);
+}
+
+static void c_stop(struct seq_file *m, void *v)
+{
+}
+
+struct seq_operations cpuinfo_op = {
+ .start =c_start,
+ .next = c_next,
+ .stop = c_stop,
+ .show = show_cpuinfo,
+};
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/drivers/scsi/aic7xxx/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/drivers/scsi/aic7xxx/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,97 @@
+#
+# drivers/scsi/aic7xxx/Makefile
+#
+# Makefile for the Linux aic7xxx SCSI driver.
+#
+
+O_TARGET := aic7xxx_drv.o
+
+list-multi := aic7xxx.o aic79xx.o
+
+obj-$(CONFIG_SCSI_AIC7XXX) += aic7xxx.o
+ifeq ($(CONFIG_PCI),y)
+obj-$(CONFIG_SCSI_AIC79XX) += aic79xx.o
+endif
+
+EXTRA_CFLAGS += -I$(TOPDIR)/drivers/scsi -Werror
+#EXTRA_CFLAGS += -g
+
+# Platform Specific Files
+obj-aic7xxx = aic7xxx_osm.o aic7xxx_proc.o
+
+# Core Files
+obj-aic7xxx += aic7xxx_core.o aic7xxx_93cx6.o
+ifeq ($(CONFIG_AIC7XXX_REG_PRETTY_PRINT),y)
+obj-aic7xxx += aic7xxx_reg_print.o
+endif
+
+#EISA Specific Files
+AIC7XXX_EISA_ARCH = $(filter i386 alpha xen,$(ARCH))
+ifneq ($(AIC7XXX_EISA_ARCH),)
+obj-aic7xxx += aic7770.o
+# Platform Specific EISA Files
+obj-aic7xxx += aic7770_osm.o
+endif
+
+#PCI Specific Files
+ifeq ($(CONFIG_PCI),y)
+obj-aic7xxx += aic7xxx_pci.o
+# Platform Specific PCI Files
+obj-aic7xxx += aic7xxx_osm_pci.o
+endif
+
+# Platform Specific U320 Files
+obj-aic79xx = aic79xx_osm.o aic79xx_proc.o aic79xx_osm_pci.o
+# Core Files
+obj-aic79xx += aic79xx_core.o aic79xx_pci.o
+ifeq ($(CONFIG_AIC79XX_REG_PRETTY_PRINT),y)
+obj-aic79xx += aic79xx_reg_print.o
+endif
+
+# Override our module desitnation
+MOD_DESTDIR = $(shell cd .. && $(CONFIG_SHELL) $(TOPDIR)/scripts/pathdown.sh)
+
+include $(TOPDIR)/Rules.make
+
+aic7xxx_core.o: aic7xxx_seq.h
+$(obj-aic7xxx): aic7xxx_reg.h
+aic7xxx.o: aic7xxx_seq.h aic7xxx_reg.h $(obj-aic7xxx)
+ $(LD) $(LD_RFLAG) -r -o $@ $(obj-aic7xxx)
+
+aic79xx_core.o: aic79xx_seq.h
+$(obj-aic79xx): aic79xx_reg.h
+aic79xx.o: aic79xx_seq.h aic79xx_reg.h $(obj-aic79xx)
+ $(LD) $(LD_RFLAG) -r -o $@ $(obj-aic79xx)
+
+ifeq ($(CONFIG_AIC7XXX_BUILD_FIRMWARE),y)
+aic7xxx_gen = aic7xxx_seq.h aic7xxx_reg.h
+ifeq ($(CONFIG_AIC7XXX_REG_PRETTY_PRINT),y)
+aic7xxx_gen += aic7xxx_reg_print.c
+aic7xxx_asm_cmd = aicasm/aicasm -I. -r aic7xxx_reg.h \
+ -p aic7xxx_reg_print.c -i aic7xxx_osm.h \
+ -o aic7xxx_seq.h aic7xxx.seq
+else
+aic7xxx_asm_cmd = aicasm/aicasm -I. -r aic7xxx_reg.h \
+ -o aic7xxx_seq.h aic7xxx.seq
+endif
+$(aic7xxx_gen): aic7xxx.seq aic7xxx.reg aicasm/aicasm
+ $(aic7xxx_asm_cmd)
+endif
+
+ifeq ($(CONFIG_AIC79XX_BUILD_FIRMWARE),y)
+aic79xx_gen = aic79xx_seq.h aic79xx_reg.h
+ifeq ($(CONFIG_AIC79XX_REG_PRETTY_PRINT),y)
+aic79xx_gen += aic79xx_reg_print.c
+aic79xx_asm_cmd = aicasm/aicasm -I. -r aic79xx_reg.h \
+ -p aic79xx_reg_print.c -i aic79xx_osm.h \
+ -o aic79xx_seq.h aic79xx.seq
+else
+aic79xx_asm_cmd = aicasm/aicasm -I. -r aic79xx_reg.h \
+ -o aic79xx_seq.h aic79xx.seq
+endif
+$(aic79xx_gen): aic79xx.seq aic79xx.reg aicasm/aicasm
+ $(aic79xx_asm_cmd)
+endif
+
+aicasm/aicasm: aicasm/*.[chyl]
+ $(MAKE) -C aicasm
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/drivers/blkif/frontend/vbd.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/drivers/blkif/frontend/vbd.c Fri Jul
15 13:39:50 2005
@@ -0,0 +1,540 @@
+/******************************************************************************
+ * arch/xen/drivers/blkif/frontend/vbd.c
+ *
+ * Xenolinux virtual block-device driver.
+ *
+ * Copyright (c) 2003-2004, Keir Fraser & Steve Hand
+ * Modifications by Mark A. Williamson are (c) Intel Research Cambridge
+ */
+
+#include "common.h"
+#include <linux/blk.h>
+
+/*
+ * For convenience we distinguish between ide, scsi and 'other' (i.e.
+ * potentially combinations of the two) in the naming scheme and in a few
+ * other places (like default readahead, etc).
+ */
+#define XLIDE_MAJOR_NAME "hd"
+#define XLSCSI_MAJOR_NAME "sd"
+#define XLVBD_MAJOR_NAME "xvd"
+
+#define XLIDE_DEVS_PER_MAJOR 2
+#define XLSCSI_DEVS_PER_MAJOR 16
+#define XLVBD_DEVS_PER_MAJOR 16
+
+#define XLIDE_PARTN_SHIFT 6 /* amount to shift minor to get 'real' minor */
+#define XLIDE_MAX_PART (1 << XLIDE_PARTN_SHIFT) /* minors per ide vbd */
+
+#define XLSCSI_PARTN_SHIFT 4 /* amount to shift minor to get 'real' minor */
+#define XLSCSI_MAX_PART (1 << XLSCSI_PARTN_SHIFT) /* minors per scsi vbd */
+
+#define XLVBD_PARTN_SHIFT 4 /* amount to shift minor to get 'real' minor */
+#define XLVBD_MAX_PART (1 << XLVBD_PARTN_SHIFT) /* minors per 'other' vbd */
+
+/* The below are for the generic drivers/block/ll_rw_block.c code. */
+static int xlide_blksize_size[256];
+static int xlide_hardsect_size[256];
+static int xlide_max_sectors[256];
+static int xlscsi_blksize_size[256];
+static int xlscsi_hardsect_size[256];
+static int xlscsi_max_sectors[256];
+static int xlvbd_blksize_size[256];
+static int xlvbd_hardsect_size[256];
+static int xlvbd_max_sectors[256];
+
+/* Information about our VBDs. */
+#define MAX_VBDS 64
+static int nr_vbds;
+static vdisk_t *vbd_info;
+
+static struct block_device_operations xlvbd_block_fops =
+{
+ open: blkif_open,
+ release: blkif_release,
+ ioctl: blkif_ioctl,
+ check_media_change: blkif_check,
+ revalidate: blkif_revalidate,
+};
+
+static int xlvbd_get_vbd_info(vdisk_t *disk_info)
+{
+ vdisk_t *buf = (vdisk_t *)__get_free_page(GFP_KERNEL);
+ blkif_request_t req;
+ blkif_response_t rsp;
+ int nr;
+
+ memset(&req, 0, sizeof(req));
+ req.operation = BLKIF_OP_PROBE;
+ req.nr_segments = 1;
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ blkif_control_probe_send(&req, &rsp,
+ (unsigned long)(virt_to_machine(buf)));
+#else
+ req.frame_and_sects[0] = virt_to_machine(buf) | 7;
+
+ blkif_control_send(&req, &rsp);
+#endif
+
+ if ( rsp.status <= 0 )
+ {
+ printk(KERN_ALERT "Could not probe disks (%d)\n", rsp.status);
+ return -1;
+ }
+
+ if ( (nr = rsp.status) > MAX_VBDS )
+ nr = MAX_VBDS;
+ memcpy(disk_info, buf, nr * sizeof(vdisk_t));
+
+ return nr;
+}
+
+/*
+ * xlvbd_init_device - initialise a VBD device
+ * @disk: a vdisk_t describing the VBD
+ *
+ * Takes a vdisk_t * that describes a VBD the domain has access to.
+ * Performs appropriate initialisation and registration of the device.
+ *
+ * Care needs to be taken when making re-entrant calls to ensure that
+ * corruption does not occur. Also, devices that are in use should not have
+ * their details updated. This is the caller's responsibility.
+ */
+static int xlvbd_init_device(vdisk_t *xd)
+{
+ int device = xd->device;
+ int major = MAJOR(device);
+ int minor = MINOR(device);
+ int is_ide = IDE_DISK_MAJOR(major); /* is this an ide device? */
+ int is_scsi= SCSI_BLK_MAJOR(major); /* is this a scsi device? */
+ char *major_name;
+ struct gendisk *gd;
+ struct block_device *bd;
+ xl_disk_t *disk;
+ int i, rc = 0, max_part, partno;
+ unsigned long capacity;
+
+ unsigned char buf[64];
+
+ if ( (bd = bdget(device)) == NULL )
+ return -1;
+
+ if ( ((disk = xldev_to_xldisk(device)) != NULL) && (disk->usage != 0) )
+ {
+ printk(KERN_ALERT "VBD update failed - in use [dev=%x]\n", device);
+ rc = -1;
+ goto out;
+ }
+
+ if ( is_ide ) {
+
+ major_name = XLIDE_MAJOR_NAME;
+ max_part = XLIDE_MAX_PART;
+
+ } else if ( is_scsi ) {
+
+ major_name = XLSCSI_MAJOR_NAME;
+ max_part = XLSCSI_MAX_PART;
+
+ } else {
+
+ /* SMH: hmm - probably a CCISS driver or sim; assume CCISS for now */
+ printk(KERN_ALERT "Assuming device %02x:%02x is CCISS/SCSI\n",
+ major, minor);
+ is_scsi = 1;
+ major_name = "cciss";
+ max_part = XLSCSI_MAX_PART;
+
+ }
+
+ partno = minor & (max_part - 1);
+
+ if ( (gd = get_gendisk(device)) == NULL )
+ {
+ rc = register_blkdev(major, major_name, &xlvbd_block_fops);
+ if ( rc < 0 )
+ {
+ printk(KERN_ALERT "XL VBD: can't get major %d\n", major);
+ goto out;
+ }
+
+ if ( is_ide )
+ {
+ blksize_size[major] = xlide_blksize_size;
+ hardsect_size[major] = xlide_hardsect_size;
+ max_sectors[major] = xlide_max_sectors;
+ read_ahead[major] = 8;
+ }
+ else if ( is_scsi )
+ {
+ blksize_size[major] = xlscsi_blksize_size;
+ hardsect_size[major] = xlscsi_hardsect_size;
+ max_sectors[major] = xlscsi_max_sectors;
+ read_ahead[major] = 8;
+ }
+ else
+ {
+ blksize_size[major] = xlvbd_blksize_size;
+ hardsect_size[major] = xlvbd_hardsect_size;
+ max_sectors[major] = xlvbd_max_sectors;
+ read_ahead[major] = 8;
+ }
+
+ blk_init_queue(BLK_DEFAULT_QUEUE(major), do_blkif_request);
+
+ /*
+ * Turn off barking 'headactive' mode. We dequeue buffer heads as
+ * soon as we pass them to the back-end driver.
+ */
+ blk_queue_headactive(BLK_DEFAULT_QUEUE(major), 0);
+
+ /* Construct an appropriate gendisk structure. */
+ gd = kmalloc(sizeof(struct gendisk), GFP_KERNEL);
+ gd->major = major;
+ gd->major_name = major_name;
+
+ gd->max_p = max_part;
+ if ( is_ide )
+ {
+ gd->minor_shift = XLIDE_PARTN_SHIFT;
+ gd->nr_real = XLIDE_DEVS_PER_MAJOR;
+ }
+ else if ( is_scsi )
+ {
+ gd->minor_shift = XLSCSI_PARTN_SHIFT;
+ gd->nr_real = XLSCSI_DEVS_PER_MAJOR;
+ }
+ else
+ {
+ gd->minor_shift = XLVBD_PARTN_SHIFT;
+ gd->nr_real = XLVBD_DEVS_PER_MAJOR;
+ }
+
+ /*
+ ** The sizes[] and part[] arrays hold the sizes and other
+ ** information about every partition with this 'major' (i.e.
+ ** every disk sharing the 8 bit prefix * max partns per disk)
+ */
+ gd->sizes = kmalloc(max_part*gd->nr_real*sizeof(int), GFP_KERNEL);
+ gd->part = kmalloc(max_part*gd->nr_real*sizeof(struct hd_struct),
+ GFP_KERNEL);
+ memset(gd->sizes, 0, max_part * gd->nr_real * sizeof(int));
+ memset(gd->part, 0, max_part * gd->nr_real
+ * sizeof(struct hd_struct));
+
+
+ gd->real_devices = kmalloc(gd->nr_real * sizeof(xl_disk_t),
+ GFP_KERNEL);
+ memset(gd->real_devices, 0, gd->nr_real * sizeof(xl_disk_t));
+
+ gd->next = NULL;
+ gd->fops = &xlvbd_block_fops;
+
+ gd->de_arr = kmalloc(gd->nr_real * sizeof(*gd->de_arr),
+ GFP_KERNEL);
+ gd->flags = kmalloc(gd->nr_real * sizeof(*gd->flags), GFP_KERNEL);
+
+ memset(gd->de_arr, 0, gd->nr_real * sizeof(*gd->de_arr));
+ memset(gd->flags, 0, gd->nr_real * sizeof(*gd->flags));
+
+ add_gendisk(gd);
+
+ blk_size[major] = gd->sizes;
+ }
+
+ if ( xd->info & VDISK_READONLY )
+ set_device_ro(device, 1);
+
+ gd->flags[minor >> gd->minor_shift] |= GENHD_FL_XEN;
+
+ /* NB. Linux 2.4 only handles 32-bit sector offsets and capacities. */
+ capacity = (unsigned long)xd->capacity;
+
+ if ( partno != 0 )
+ {
+ /*
+ * If this was previously set up as a real disc we will have set
+ * up partition-table information. Virtual partitions override
+ * 'real' partitions, and the two cannot coexist on a device.
+ */
+ if ( !(gd->flags[minor >> gd->minor_shift] & GENHD_FL_VIRT_PARTNS) &&
+ (gd->sizes[minor & ~(max_part-1)] != 0) )
+ {
+ /*
+ * Any non-zero sub-partition entries must be cleaned out before
+ * installing 'virtual' partition entries. The two types cannot
+ * coexist, and virtual partitions are favoured.
+ */
+ kdev_t dev = device & ~(max_part-1);
+ for ( i = max_part - 1; i > 0; i-- )
+ {
+ invalidate_device(dev+i, 1);
+ gd->part[MINOR(dev+i)].start_sect = 0;
+ gd->part[MINOR(dev+i)].nr_sects = 0;
+ gd->sizes[MINOR(dev+i)] = 0;
+ }
+ printk(KERN_ALERT
+ "Virtual partitions found for /dev/%s - ignoring any "
+ "real partition information we may have found.\n",
+ disk_name(gd, MINOR(device), buf));
+ }
+
+ /* Need to skankily setup 'partition' information */
+ gd->part[minor].start_sect = 0;
+ gd->part[minor].nr_sects = capacity;
+ gd->sizes[minor] = capacity >>(BLOCK_SIZE_BITS-9);
+
+ gd->flags[minor >> gd->minor_shift] |= GENHD_FL_VIRT_PARTNS;
+ }
+ else
+ {
+ gd->part[minor].nr_sects = capacity;
+ gd->sizes[minor] = capacity>>(BLOCK_SIZE_BITS-9);
+
+ /* Some final fix-ups depending on the device type */
+ if ( xd->info & VDISK_REMOVABLE )
+ {
+ gd->flags[minor >> gd->minor_shift] |= GENHD_FL_REMOVABLE;
+ printk(KERN_ALERT
+ "Skipping partition check on %s /dev/%s\n",
+ (xd->info & VDISK_CDROM) ? "cdrom" : "removable",
+ disk_name(gd, MINOR(device), buf));
+ }
+ else
+ {
+ /* Only check partitions on real discs (not virtual!). */
+ if ( gd->flags[minor>>gd->minor_shift] & GENHD_FL_VIRT_PARTNS )
+ {
+ printk(KERN_ALERT
+ "Skipping partition check on virtual /dev/%s\n",
+ disk_name(gd, MINOR(device), buf));
+ break;
+ }
+ register_disk(gd, device, gd->max_p, &xlvbd_block_fops, capacity);
+ }
+ }
+
+ out:
+ bdput(bd);
+ return rc;
+}
+
+
+/*
+ * xlvbd_remove_device - remove a device node if possible
+ * @device: numeric device ID
+ *
+ * Updates the gendisk structure and invalidates devices.
+ *
+ * This is OK for now but in future, should perhaps consider where this should
+ * deallocate gendisks / unregister devices.
+ */
+static int xlvbd_remove_device(int device)
+{
+ int i, rc = 0, minor = MINOR(device);
+ struct gendisk *gd;
+ struct block_device *bd;
+ xl_disk_t *disk = NULL;
+
+ if ( (bd = bdget(device)) == NULL )
+ return -1;
+
+ if ( ((gd = get_gendisk(device)) == NULL) ||
+ ((disk = xldev_to_xldisk(device)) == NULL) )
+ BUG();
+
+ if ( disk->usage != 0 )
+ {
+ printk(KERN_ALERT "VBD removal failed - in use [dev=%x]\n", device);
+ rc = -1;
+ goto out;
+ }
+
+ if ( (minor & (gd->max_p-1)) != 0 )
+ {
+ /* 1: The VBD is mapped to a partition rather than a whole unit. */
+ invalidate_device(device, 1);
+ gd->part[minor].start_sect = 0;
+ gd->part[minor].nr_sects = 0;
+ gd->sizes[minor] = 0;
+
+ /* Clear the consists-of-virtual-partitions flag if possible. */
+ gd->flags[minor >> gd->minor_shift] &= ~GENHD_FL_VIRT_PARTNS;
+ for ( i = 1; i < gd->max_p; i++ )
+ if ( gd->sizes[(minor & ~(gd->max_p-1)) + i] != 0 )
+ gd->flags[minor >> gd->minor_shift] |= GENHD_FL_VIRT_PARTNS;
+
+ /*
+ * If all virtual partitions are now gone, and a 'whole unit' VBD is
+ * present, then we can try to grok the unit's real partition table.
+ */
+ if ( !(gd->flags[minor >> gd->minor_shift] & GENHD_FL_VIRT_PARTNS) &&
+ (gd->sizes[minor & ~(gd->max_p-1)] != 0) &&
+ !(gd->flags[minor >> gd->minor_shift] & GENHD_FL_REMOVABLE) )
+ {
+ register_disk(gd,
+ device&~(gd->max_p-1),
+ gd->max_p,
+ &xlvbd_block_fops,
+ gd->part[minor&~(gd->max_p-1)].nr_sects);
+ }
+ }
+ else
+ {
+ /*
+ * 2: The VBD is mapped to an entire 'unit'. Clear all partitions.
+ * NB. The partition entries are only cleared if there are no VBDs
+ * mapped to individual partitions on this unit.
+ */
+ i = gd->max_p - 1; /* Default: clear subpartitions as well. */
+ if ( gd->flags[minor >> gd->minor_shift] & GENHD_FL_VIRT_PARTNS )
+ i = 0; /* 'Virtual' mode: only clear the 'whole unit' entry. */
+ while ( i >= 0 )
+ {
+ invalidate_device(device+i, 1);
+ gd->part[minor+i].start_sect = 0;
+ gd->part[minor+i].nr_sects = 0;
+ gd->sizes[minor+i] = 0;
+ i--;
+ }
+ }
+
+ out:
+ bdput(bd);
+ return rc;
+}
+
+/*
+ * xlvbd_update_vbds - reprobes the VBD status and performs updates driver
+ * state. The VBDs need to be updated in this way when the domain is
+ * initialised and also each time we receive an XLBLK_UPDATE event.
+ */
+void xlvbd_update_vbds(void)
+{
+ int i, j, k, old_nr, new_nr;
+ vdisk_t *old_info, *new_info, *merged_info;
+
+ old_info = vbd_info;
+ old_nr = nr_vbds;
+
+ new_info = kmalloc(MAX_VBDS * sizeof(vdisk_t), GFP_KERNEL);
+ if (!new_info)
+ return;
+
+ if ( unlikely(new_nr = xlvbd_get_vbd_info(new_info)) < 0 )
+ goto out;
+
+ /*
+ * Final list maximum size is old list + new list. This occurs only when
+ * old list and new list do not overlap at all, and we cannot yet destroy
+ * VBDs in the old list because the usage counts are busy.
+ */
+ merged_info = kmalloc((old_nr + new_nr) * sizeof(vdisk_t), GFP_KERNEL);
+ if (!merged_info)
+ goto out;
+
+ /* @i tracks old list; @j tracks new list; @k tracks merged list. */
+ i = j = k = 0;
+
+ while ( (i < old_nr) && (j < new_nr) )
+ {
+ if ( old_info[i].device < new_info[j].device )
+ {
+ if ( xlvbd_remove_device(old_info[i].device) != 0 )
+ memcpy(&merged_info[k++], &old_info[i], sizeof(vdisk_t));
+ i++;
+ }
+ else if ( old_info[i].device > new_info[j].device )
+ {
+ if ( xlvbd_init_device(&new_info[j]) == 0 )
+ memcpy(&merged_info[k++], &new_info[j], sizeof(vdisk_t));
+ j++;
+ }
+ else
+ {
+ if ( ((old_info[i].capacity == new_info[j].capacity) &&
+ (old_info[i].info == new_info[j].info)) ||
+ (xlvbd_remove_device(old_info[i].device) != 0) )
+ memcpy(&merged_info[k++], &old_info[i], sizeof(vdisk_t));
+ else if ( xlvbd_init_device(&new_info[j]) == 0 )
+ memcpy(&merged_info[k++], &new_info[j], sizeof(vdisk_t));
+ i++; j++;
+ }
+ }
+
+ for ( ; i < old_nr; i++ )
+ {
+ if ( xlvbd_remove_device(old_info[i].device) != 0 )
+ memcpy(&merged_info[k++], &old_info[i], sizeof(vdisk_t));
+ }
+
+ for ( ; j < new_nr; j++ )
+ {
+ if ( xlvbd_init_device(&new_info[j]) == 0 )
+ memcpy(&merged_info[k++], &new_info[j], sizeof(vdisk_t));
+ }
+
+ vbd_info = merged_info;
+ nr_vbds = k;
+
+ kfree(old_info);
+out:
+ kfree(new_info);
+}
+
+
+/*
+ * Set up all the linux device goop for the virtual block devices (vbd's) that
+ * we know about. Note that although from the backend driver's p.o.v. VBDs are
+ * addressed simply an opaque 16-bit device number, the domain creation tools
+ * conventionally allocate these numbers to correspond to those used by 'real'
+ * linux -- this is just for convenience as it means e.g. that the same
+ * /etc/fstab can be used when booting with or without Xen.
+ */
+int xlvbd_init(void)
+{
+ int i;
+
+ /*
+ * If compiled as a module, we don't support unloading yet. We therefore
+ * permanently increment the reference count to disallow it.
+ */
+ SET_MODULE_OWNER(&xlvbd_block_fops);
+ MOD_INC_USE_COUNT;
+
+ /* Initialize the global arrays. */
+ for ( i = 0; i < 256; i++ )
+ {
+ xlide_blksize_size[i] = 1024;
+ xlide_hardsect_size[i] = 512;
+ xlide_max_sectors[i] = 512;
+
+ xlscsi_blksize_size[i] = 1024;
+ xlscsi_hardsect_size[i] = 512;
+ xlscsi_max_sectors[i] = 512;
+
+ xlvbd_blksize_size[i] = 512;
+ xlvbd_hardsect_size[i] = 512;
+ xlvbd_max_sectors[i] = 512;
+ }
+
+ vbd_info = kmalloc(MAX_VBDS * sizeof(vdisk_t), GFP_KERNEL);
+ if (!vbd_info)
+ return -ENOMEM;
+
+ nr_vbds = xlvbd_get_vbd_info(vbd_info);
+
+ if ( nr_vbds < 0 )
+ {
+ kfree(vbd_info);
+ vbd_info = NULL;
+ nr_vbds = 0;
+ }
+ else
+ {
+ for ( i = 0; i < nr_vbds; i++ )
+ xlvbd_init_device(&vbd_info[i]);
+ }
+
+ return 0;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/tlbflush.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/tlbflush.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,97 @@
+#ifndef _X8664_TLBFLUSH_H
+#define _X8664_TLBFLUSH_H
+
+#include <linux/config.h>
+#include <linux/mm.h>
+#include <asm/processor.h>
+
+#define __flush_tlb() xen_tlb_flush()
+
+/*
+ * Global pages have to be flushed a bit differently. Not a real
+ * performance problem because this does not happen often.
+ */
+#define __flush_tlb_global() xen_tlb_flush()
+
+
+extern unsigned long pgkern_mask;
+
+#define __flush_tlb_all() __flush_tlb_global()
+
+#define __flush_tlb_one(addr) xen_invlpg(addr)
+
+
+/*
+ * TLB flushing:
+ *
+ * - flush_tlb() flushes the current mm struct TLBs
+ * - flush_tlb_all() flushes all processes TLBs
+ * - flush_tlb_mm(mm) flushes the specified mm context TLB's
+ * - flush_tlb_page(vma, vmaddr) flushes one page
+ * - flush_tlb_range(vma, start, end) flushes a range of pages
+ * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
+ * - flush_tlb_pgtables(mm, start, end) flushes a range of page tables
+ *
+ * ..but the x86_64 has somewhat limited tlb flushing capabilities,
+ * and page-granular flushes are available only on i486 and up.
+ */
+
+#ifndef CONFIG_SMP
+
+#define flush_tlb() __flush_tlb()
+#define flush_tlb_all() __flush_tlb_all()
+#define local_flush_tlb() __flush_tlb()
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+ if (mm == current->active_mm)
+ __flush_tlb();
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+ unsigned long addr)
+{
+ if (vma->vm_mm == current->active_mm)
+ __flush_tlb_one(addr);
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ if (vma->vm_mm == current->active_mm)
+ __flush_tlb();
+}
+
+#else
+
+#include <asm/smp.h>
+
+#define local_flush_tlb() \
+ __flush_tlb()
+
+extern void flush_tlb_all(void);
+extern void flush_tlb_current_task(void);
+extern void flush_tlb_mm(struct mm_struct *);
+extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
+
+#define flush_tlb() flush_tlb_current_task()
+
+static inline void flush_tlb_range(struct vm_area_struct * vma, unsigned long
start, unsigned long end)
+{
+ flush_tlb_mm(vma->vm_mm);
+}
+
+#define TLBSTATE_OK 1
+#define TLBSTATE_LAZY 2
+
+#endif
+
+#define flush_tlb_kernel_range(start, end) flush_tlb_all()
+
+static inline void flush_tlb_pgtables(struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ /* x86_64 does not keep any page table caches in TLB */
+}
+
+#endif /* _X8664_TLBFLUSH_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/ia32/vsyscall-int80.S
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/ia32/vsyscall-int80.S Fri Jul
15 13:39:50 2005
@@ -0,0 +1,57 @@
+/*
+ * Code for the vsyscall page. This version uses the old int $0x80 method.
+ *
+ * NOTE:
+ * 1) __kernel_vsyscall _must_ be first in this page.
+ * 2) there are alignment constraints on this stub, see vsyscall-sigreturn.S
+ * for details.
+ */
+#include <asm/ia32_unistd.h>
+#include <asm/offset.h>
+
+ .text
+ .section .text.vsyscall,"ax"
+ .globl __kernel_vsyscall
+ .type __kernel_vsyscall,@function
+__kernel_vsyscall:
+.LSTART_vsyscall:
+ int $0x80
+ ret
+.LEND_vsyscall:
+ .size __kernel_vsyscall,.-.LSTART_vsyscall
+ .previous
+
+ .section .eh_frame,"a",@progbits
+.LSTARTFRAME:
+ .long .LENDCIE-.LSTARTCIE
+.LSTARTCIE:
+ .long 0 /* CIE ID */
+ .byte 1 /* Version number */
+ .string "zR" /* NUL-terminated augmentation string */
+ .uleb128 1 /* Code alignment factor */
+ .sleb128 -4 /* Data alignment factor */
+ .byte 8 /* Return address register column */
+ .uleb128 1 /* Augmentation value length */
+ .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
+ .byte 0x0c /* DW_CFA_def_cfa */
+ .uleb128 4
+ .uleb128 4
+ .byte 0x88 /* DW_CFA_offset, column 0x8 */
+ .uleb128 1
+ .align 4
+.LENDCIE:
+
+ .long .LENDFDE1-.LSTARTFDE1 /* Length FDE */
+.LSTARTFDE1:
+ .long .LSTARTFDE1-.LSTARTFRAME /* CIE pointer */
+ .long .LSTART_vsyscall-. /* PC-relative start address */
+ .long .LEND_vsyscall-.LSTART_vsyscall
+ .uleb128 0 /* Augmentation length */
+ .align 4
+.LENDFDE1:
+
+/*
+ * Get the common code for the sigreturn entry points.
+ */
+#define SYSCALL_ENTER_KERNEL int $0x80
+#include "vsyscall-sigreturn.S"
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/init_task.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/init_task.c Fri Jul
15 13:39:50 2005
@@ -0,0 +1,49 @@
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/init_task.h>
+#include <linux/fs.h>
+#include <linux/mqueue.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/desc.h>
+
+static struct fs_struct init_fs = INIT_FS;
+static struct files_struct init_files = INIT_FILES;
+static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
+static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
+struct mm_struct init_mm = INIT_MM(init_mm);
+
+EXPORT_SYMBOL(init_mm);
+
+/*
+ * Initial task structure.
+ *
+ * We need to make sure that this is 8192-byte aligned due to the
+ * way process stacks are handled. This is done by having a special
+ * "init_task" linker map entry..
+ */
+union thread_union init_thread_union
+ __attribute__((__section__(".data.init_task"))) =
+ { INIT_THREAD_INFO(init_task) };
+
+/*
+ * Initial task structure.
+ *
+ * All other task structs will be allocated on slabs in fork.c
+ */
+struct task_struct init_task = INIT_TASK(init_task);
+
+EXPORT_SYMBOL(init_task);
+/*
+ * per-CPU TSS segments. Threads are completely 'soft' on Linux,
+ * no more per-task TSS's. The TSS size is kept cacheline-aligned
+ * so they are allowed to end up in the .data.cacheline_aligned
+ * section. Since TSS's are completely CPU-local, we want them
+ * on exact cacheline boundaries, to eliminate cacheline ping-pong.
+ */
+DEFINE_PER_CPU(struct tss_struct, init_tss) ____cacheline_maxaligned_in_smp;
+
+#define ALIGN_TO_4K __attribute__((section(".data.init_task")))
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/mpparse.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/mpparse.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,1115 @@
+/*
+ * Intel Multiprocessor Specification 1.1 and 1.4
+ * compliant MP-table parsing routines.
+ *
+ * (c) 1995 Alan Cox, Building #3 <alan@xxxxxxxxxx>
+ * (c) 1998, 1999, 2000 Ingo Molnar <mingo@xxxxxxxxxx>
+ *
+ * Fixes
+ * Erich Boleyn : MP v1.4 and additional changes.
+ * Alan Cox : Added EBDA scanning
+ * Ingo Molnar : various cleanups and rewrites
+ * Maciej W. Rozycki: Bits for default MP configurations
+ * Paul Diefenbaugh: Added full ACPI support
+ */
+
+#include <linux/mm.h>
+#include <linux/irq.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/delay.h>
+#include <linux/config.h>
+#include <linux/bootmem.h>
+#include <linux/smp_lock.h>
+#include <linux/kernel_stat.h>
+#include <linux/mc146818rtc.h>
+#include <linux/bitops.h>
+
+#include <asm/smp.h>
+#include <asm/acpi.h>
+#include <asm/mtrr.h>
+#include <asm/mpspec.h>
+#include <asm/io_apic.h>
+
+#include <mach_apic.h>
+#include <mach_mpparse.h>
+#include <bios_ebda.h>
+
+/* Have we found an MP table */
+int smp_found_config;
+unsigned int __initdata maxcpus = NR_CPUS;
+
+/*
+ * Various Linux-internal data structures created from the
+ * MP-table.
+ */
+int apic_version [MAX_APICS];
+int mp_bus_id_to_type [MAX_MP_BUSSES];
+int mp_bus_id_to_node [MAX_MP_BUSSES];
+int mp_bus_id_to_local [MAX_MP_BUSSES];
+int quad_local_to_mp_bus_id [NR_CPUS/4][4];
+int mp_bus_id_to_pci_bus [MAX_MP_BUSSES] = { [0 ... MAX_MP_BUSSES-1] = -1 };
+int mp_current_pci_id;
+
+/* I/O APIC entries */
+struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS];
+
+/* # of MP IRQ source entries */
+struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+
+/* MP IRQ source entries */
+int mp_irq_entries;
+
+int nr_ioapics;
+
+int pic_mode;
+unsigned long mp_lapic_addr;
+
+/* Processor that is doing the boot up */
+unsigned int boot_cpu_physical_apicid = -1U;
+unsigned int boot_cpu_logical_apicid = -1U;
+/* Internal processor count */
+static unsigned int __initdata num_processors;
+
+/* Bitmask of physically existing CPUs */
+physid_mask_t phys_cpu_present_map;
+
+u8 bios_cpu_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID };
+
+/*
+ * Intel MP BIOS table parsing routines:
+ */
+
+
+/*
+ * Checksum an MP configuration block.
+ */
+
+static int __init mpf_checksum(unsigned char *mp, int len)
+{
+ int sum = 0;
+
+ while (len--)
+ sum += *mp++;
+
+ return sum & 0xFF;
+}
+
+/*
+ * Have to match translation table entries to main table entries by counter
+ * hence the mpc_record variable .... can't see a less disgusting way of
+ * doing this ....
+ */
+
+static int mpc_record;
+static struct mpc_config_translation *translation_table[MAX_MPC_ENTRY]
__initdata;
+
+#ifdef CONFIG_X86_NUMAQ
+static int MP_valid_apicid(int apicid, int version)
+{
+ return hweight_long(apicid & 0xf) == 1 && (apicid >> 4) != 0xf;
+}
+#elif !defined(CONFIG_XEN)
+static int MP_valid_apicid(int apicid, int version)
+{
+ if (version >= 0x14)
+ return apicid < 0xff;
+ else
+ return apicid < 0xf;
+}
+#endif
+
+#ifndef CONFIG_XEN
+void __init MP_processor_info (struct mpc_config_processor *m)
+{
+ int ver, apicid;
+ physid_mask_t tmp;
+
+ if (!(m->mpc_cpuflag & CPU_ENABLED))
+ return;
+
+ apicid = mpc_apic_id(m, translation_table[mpc_record]);
+
+ if (m->mpc_featureflag&(1<<0))
+ Dprintk(" Floating point unit present.\n");
+ if (m->mpc_featureflag&(1<<7))
+ Dprintk(" Machine Exception supported.\n");
+ if (m->mpc_featureflag&(1<<8))
+ Dprintk(" 64 bit compare & exchange supported.\n");
+ if (m->mpc_featureflag&(1<<9))
+ Dprintk(" Internal APIC present.\n");
+ if (m->mpc_featureflag&(1<<11))
+ Dprintk(" SEP present.\n");
+ if (m->mpc_featureflag&(1<<12))
+ Dprintk(" MTRR present.\n");
+ if (m->mpc_featureflag&(1<<13))
+ Dprintk(" PGE present.\n");
+ if (m->mpc_featureflag&(1<<14))
+ Dprintk(" MCA present.\n");
+ if (m->mpc_featureflag&(1<<15))
+ Dprintk(" CMOV present.\n");
+ if (m->mpc_featureflag&(1<<16))
+ Dprintk(" PAT present.\n");
+ if (m->mpc_featureflag&(1<<17))
+ Dprintk(" PSE present.\n");
+ if (m->mpc_featureflag&(1<<18))
+ Dprintk(" PSN present.\n");
+ if (m->mpc_featureflag&(1<<19))
+ Dprintk(" Cache Line Flush Instruction present.\n");
+ /* 20 Reserved */
+ if (m->mpc_featureflag&(1<<21))
+ Dprintk(" Debug Trace and EMON Store present.\n");
+ if (m->mpc_featureflag&(1<<22))
+ Dprintk(" ACPI Thermal Throttle Registers present.\n");
+ if (m->mpc_featureflag&(1<<23))
+ Dprintk(" MMX present.\n");
+ if (m->mpc_featureflag&(1<<24))
+ Dprintk(" FXSR present.\n");
+ if (m->mpc_featureflag&(1<<25))
+ Dprintk(" XMM present.\n");
+ if (m->mpc_featureflag&(1<<26))
+ Dprintk(" Willamette New Instructions present.\n");
+ if (m->mpc_featureflag&(1<<27))
+ Dprintk(" Self Snoop present.\n");
+ if (m->mpc_featureflag&(1<<28))
+ Dprintk(" HT present.\n");
+ if (m->mpc_featureflag&(1<<29))
+ Dprintk(" Thermal Monitor present.\n");
+ /* 30, 31 Reserved */
+
+
+ if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) {
+ Dprintk(" Bootup CPU\n");
+ boot_cpu_physical_apicid = m->mpc_apicid;
+ boot_cpu_logical_apicid = apicid;
+ }
+
+ if (num_processors >= NR_CPUS) {
+ printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached."
+ " Processor ignored.\n", NR_CPUS);
+ return;
+ }
+
+ if (num_processors >= maxcpus) {
+ printk(KERN_WARNING "WARNING: maxcpus limit of %i reached."
+ " Processor ignored.\n", maxcpus);
+ return;
+ }
+ num_processors++;
+ ver = m->mpc_apicver;
+
+ if (!MP_valid_apicid(apicid, ver)) {
+ printk(KERN_WARNING "Processor #%d INVALID. (Max ID: %d).\n",
+ m->mpc_apicid, MAX_APICS);
+ --num_processors;
+ return;
+ }
+
+ tmp = apicid_to_cpu_present(apicid);
+ physids_or(phys_cpu_present_map, phys_cpu_present_map, tmp);
+
+ /*
+ * Validate version
+ */
+ if (ver == 0x0) {
+ printk(KERN_WARNING "BIOS bug, APIC version is 0 for CPU#%d!
fixing up to 0x10. (tell your hw vendor)\n", m->mpc_apicid);
+ ver = 0x10;
+ }
+ apic_version[m->mpc_apicid] = ver;
+ bios_cpu_apicid[num_processors - 1] = m->mpc_apicid;
+}
+#else
+void __init MP_processor_info (struct mpc_config_processor *m)
+{
+ num_processors++;
+}
+#endif /* CONFIG_XEN */
+
+static void __init MP_bus_info (struct mpc_config_bus *m)
+{
+ char str[7];
+
+ memcpy(str, m->mpc_bustype, 6);
+ str[6] = 0;
+
+ mpc_oem_bus_info(m, str, translation_table[mpc_record]);
+
+ if (strncmp(str, BUSTYPE_ISA, sizeof(BUSTYPE_ISA)-1) == 0) {
+ mp_bus_id_to_type[m->mpc_busid] = MP_BUS_ISA;
+ } else if (strncmp(str, BUSTYPE_EISA, sizeof(BUSTYPE_EISA)-1) == 0) {
+ mp_bus_id_to_type[m->mpc_busid] = MP_BUS_EISA;
+ } else if (strncmp(str, BUSTYPE_PCI, sizeof(BUSTYPE_PCI)-1) == 0) {
+ mpc_oem_pci_bus(m, translation_table[mpc_record]);
+ mp_bus_id_to_type[m->mpc_busid] = MP_BUS_PCI;
+ mp_bus_id_to_pci_bus[m->mpc_busid] = mp_current_pci_id;
+ mp_current_pci_id++;
+ } else if (strncmp(str, BUSTYPE_MCA, sizeof(BUSTYPE_MCA)-1) == 0) {
+ mp_bus_id_to_type[m->mpc_busid] = MP_BUS_MCA;
+ } else if (strncmp(str, BUSTYPE_NEC98, sizeof(BUSTYPE_NEC98)-1) == 0) {
+ mp_bus_id_to_type[m->mpc_busid] = MP_BUS_NEC98;
+ } else {
+ printk(KERN_WARNING "Unknown bustype %s - ignoring\n", str);
+ }
+}
+
+static void __init MP_ioapic_info (struct mpc_config_ioapic *m)
+{
+ if (!(m->mpc_flags & MPC_APIC_USABLE))
+ return;
+
+ printk(KERN_INFO "I/O APIC #%d Version %d at 0x%lX.\n",
+ m->mpc_apicid, m->mpc_apicver, m->mpc_apicaddr);
+ if (nr_ioapics >= MAX_IO_APICS) {
+ printk(KERN_CRIT "Max # of I/O APICs (%d) exceeded (found
%d).\n",
+ MAX_IO_APICS, nr_ioapics);
+ panic("Recompile kernel with bigger MAX_IO_APICS!.\n");
+ }
+ if (!m->mpc_apicaddr) {
+ printk(KERN_ERR "WARNING: bogus zero I/O APIC address"
+ " found in MP table, skipping!\n");
+ return;
+ }
+ mp_ioapics[nr_ioapics] = *m;
+ nr_ioapics++;
+}
+
+static void __init MP_intsrc_info (struct mpc_config_intsrc *m)
+{
+ mp_irqs [mp_irq_entries] = *m;
+ Dprintk("Int: type %d, pol %d, trig %d, bus %d,"
+ " IRQ %02x, APIC ID %x, APIC INT %02x\n",
+ m->mpc_irqtype, m->mpc_irqflag & 3,
+ (m->mpc_irqflag >> 2) & 3, m->mpc_srcbus,
+ m->mpc_srcbusirq, m->mpc_dstapic, m->mpc_dstirq);
+ if (++mp_irq_entries == MAX_IRQ_SOURCES)
+ panic("Max # of irq sources exceeded!!\n");
+}
+
+static void __init MP_lintsrc_info (struct mpc_config_lintsrc *m)
+{
+ Dprintk("Lint: type %d, pol %d, trig %d, bus %d,"
+ " IRQ %02x, APIC ID %x, APIC LINT %02x\n",
+ m->mpc_irqtype, m->mpc_irqflag & 3,
+ (m->mpc_irqflag >> 2) &3, m->mpc_srcbusid,
+ m->mpc_srcbusirq, m->mpc_destapic, m->mpc_destapiclint);
+ /*
+ * Well it seems all SMP boards in existence
+ * use ExtINT/LVT1 == LINT0 and
+ * NMI/LVT2 == LINT1 - the following check
+ * will show us if this assumptions is false.
+ * Until then we do not have to add baggage.
+ */
+ if ((m->mpc_irqtype == mp_ExtINT) &&
+ (m->mpc_destapiclint != 0))
+ BUG();
+ if ((m->mpc_irqtype == mp_NMI) &&
+ (m->mpc_destapiclint != 1))
+ BUG();
+}
+
+#ifdef CONFIG_X86_NUMAQ
+static void __init MP_translation_info (struct mpc_config_translation *m)
+{
+ printk(KERN_INFO "Translation: record %d, type %d, quad %d, global %d,
local %d\n", mpc_record, m->trans_type, m->trans_quad, m->trans_global,
m->trans_local);
+
+ if (mpc_record >= MAX_MPC_ENTRY)
+ printk(KERN_ERR "MAX_MPC_ENTRY exceeded!\n");
+ else
+ translation_table[mpc_record] = m; /* stash this for later */
+ if (m->trans_quad < MAX_NUMNODES && !node_online(m->trans_quad))
+ node_set_online(m->trans_quad);
+}
+
+/*
+ * Read/parse the MPC oem tables
+ */
+
+static void __init smp_read_mpc_oem(struct mp_config_oemtable *oemtable, \
+ unsigned short oemsize)
+{
+ int count = sizeof (*oemtable); /* the header size */
+ unsigned char *oemptr = ((unsigned char *)oemtable)+count;
+
+ mpc_record = 0;
+ printk(KERN_INFO "Found an OEM MPC table at %8p - parsing it ... \n",
oemtable);
+ if (memcmp(oemtable->oem_signature,MPC_OEM_SIGNATURE,4))
+ {
+ printk(KERN_WARNING "SMP mpc oemtable: bad signature
[%c%c%c%c]!\n",
+ oemtable->oem_signature[0],
+ oemtable->oem_signature[1],
+ oemtable->oem_signature[2],
+ oemtable->oem_signature[3]);
+ return;
+ }
+ if (mpf_checksum((unsigned char *)oemtable,oemtable->oem_length))
+ {
+ printk(KERN_WARNING "SMP oem mptable: checksum error!\n");
+ return;
+ }
+ while (count < oemtable->oem_length) {
+ switch (*oemptr) {
+ case MP_TRANSLATION:
+ {
+ struct mpc_config_translation *m=
+ (struct mpc_config_translation *)oemptr;
+ MP_translation_info(m);
+ oemptr += sizeof(*m);
+ count += sizeof(*m);
+ ++mpc_record;
+ break;
+ }
+ default:
+ {
+ printk(KERN_WARNING "Unrecognised OEM table
entry type! - %d\n", (int) *oemptr);
+ return;
+ }
+ }
+ }
+}
+
+static inline void mps_oem_check(struct mp_config_table *mpc, char *oem,
+ char *productid)
+{
+ if (strncmp(oem, "IBM NUMA", 8))
+ printk("Warning! May not be a NUMA-Q system!\n");
+ if (mpc->mpc_oemptr)
+ smp_read_mpc_oem((struct mp_config_oemtable *) mpc->mpc_oemptr,
+ mpc->mpc_oemsize);
+}
+#endif /* CONFIG_X86_NUMAQ */
+
+/*
+ * Read/parse the MPC
+ */
+
+static int __init smp_read_mpc(struct mp_config_table *mpc)
+{
+ char str[16];
+ char oem[10];
+ int count=sizeof(*mpc);
+ unsigned char *mpt=((unsigned char *)mpc)+count;
+
+ if (memcmp(mpc->mpc_signature,MPC_SIGNATURE,4)) {
+ printk(KERN_ERR "SMP mptable: bad signature [0x%x]!\n",
+ *(u32 *)mpc->mpc_signature);
+ return 0;
+ }
+ if (mpf_checksum((unsigned char *)mpc,mpc->mpc_length)) {
+ printk(KERN_ERR "SMP mptable: checksum error!\n");
+ return 0;
+ }
+ if (mpc->mpc_spec!=0x01 && mpc->mpc_spec!=0x04) {
+ printk(KERN_ERR "SMP mptable: bad table version (%d)!!\n",
+ mpc->mpc_spec);
+ return 0;
+ }
+ if (!mpc->mpc_lapic) {
+ printk(KERN_ERR "SMP mptable: null local APIC address!\n");
+ return 0;
+ }
+ memcpy(oem,mpc->mpc_oem,8);
+ oem[8]=0;
+ printk(KERN_INFO "OEM ID: %s ",oem);
+
+ memcpy(str,mpc->mpc_productid,12);
+ str[12]=0;
+ printk("Product ID: %s ",str);
+
+ mps_oem_check(mpc, oem, str);
+
+ printk("APIC at: 0x%lX\n",mpc->mpc_lapic);
+
+ /*
+ * Save the local APIC address (it might be non-default) -- but only
+ * if we're not using ACPI.
+ */
+ if (!acpi_lapic)
+ mp_lapic_addr = mpc->mpc_lapic;
+
+ /*
+ * Now process the configuration blocks.
+ */
+ mpc_record = 0;
+ while (count < mpc->mpc_length) {
+ switch(*mpt) {
+ case MP_PROCESSOR:
+ {
+ struct mpc_config_processor *m=
+ (struct mpc_config_processor *)mpt;
+ /* ACPI may have already provided this data */
+ if (!acpi_lapic)
+ MP_processor_info(m);
+ mpt += sizeof(*m);
+ count += sizeof(*m);
+ break;
+ }
+ case MP_BUS:
+ {
+ struct mpc_config_bus *m=
+ (struct mpc_config_bus *)mpt;
+ MP_bus_info(m);
+ mpt += sizeof(*m);
+ count += sizeof(*m);
+ break;
+ }
+ case MP_IOAPIC:
+ {
+ struct mpc_config_ioapic *m=
+ (struct mpc_config_ioapic *)mpt;
+ MP_ioapic_info(m);
+ mpt+=sizeof(*m);
+ count+=sizeof(*m);
+ break;
+ }
+ case MP_INTSRC:
+ {
+ struct mpc_config_intsrc *m=
+ (struct mpc_config_intsrc *)mpt;
+
+ MP_intsrc_info(m);
+ mpt+=sizeof(*m);
+ count+=sizeof(*m);
+ break;
+ }
+ case MP_LINTSRC:
+ {
+ struct mpc_config_lintsrc *m=
+ (struct mpc_config_lintsrc *)mpt;
+ MP_lintsrc_info(m);
+ mpt+=sizeof(*m);
+ count+=sizeof(*m);
+ break;
+ }
+ default:
+ {
+ count = mpc->mpc_length;
+ break;
+ }
+ }
+ ++mpc_record;
+ }
+ clustered_apic_check();
+ if (!num_processors)
+ printk(KERN_ERR "SMP mptable: no processors registered!\n");
+ return num_processors;
+}
+
+static int __init ELCR_trigger(unsigned int irq)
+{
+ unsigned int port;
+
+ port = 0x4d0 + (irq >> 3);
+ return (inb(port) >> (irq & 7)) & 1;
+}
+
+static void __init construct_default_ioirq_mptable(int mpc_default_type)
+{
+ struct mpc_config_intsrc intsrc;
+ int i;
+ int ELCR_fallback = 0;
+
+ intsrc.mpc_type = MP_INTSRC;
+ intsrc.mpc_irqflag = 0; /* conforming */
+ intsrc.mpc_srcbus = 0;
+ intsrc.mpc_dstapic = mp_ioapics[0].mpc_apicid;
+
+ intsrc.mpc_irqtype = mp_INT;
+
+ /*
+ * If true, we have an ISA/PCI system with no IRQ entries
+ * in the MP table. To prevent the PCI interrupts from being set up
+ * incorrectly, we try to use the ELCR. The sanity check to see if
+ * there is good ELCR data is very simple - IRQ0, 1, 2 and 13 can
+ * never be level sensitive, so we simply see if the ELCR agrees.
+ * If it does, we assume it's valid.
+ */
+ if (mpc_default_type == 5) {
+ printk(KERN_INFO "ISA/PCI bus type with no IRQ information...
falling back to ELCR\n");
+
+ if (ELCR_trigger(0) || ELCR_trigger(1) || ELCR_trigger(2) ||
ELCR_trigger(13))
+ printk(KERN_WARNING "ELCR contains invalid data... not
using ELCR\n");
+ else {
+ printk(KERN_INFO "Using ELCR to identify PCI
interrupts\n");
+ ELCR_fallback = 1;
+ }
+ }
+
+ for (i = 0; i < 16; i++) {
+ switch (mpc_default_type) {
+ case 2:
+ if (i == 0 || i == 13)
+ continue; /* IRQ0 & IRQ13 not connected */
+ /* fall through */
+ default:
+ if (i == 2)
+ continue; /* IRQ2 is never connected */
+ }
+
+ if (ELCR_fallback) {
+ /*
+ * If the ELCR indicates a level-sensitive interrupt,
we
+ * copy that information over to the MP table in the
+ * irqflag field (level sensitive, active high
polarity).
+ */
+ if (ELCR_trigger(i))
+ intsrc.mpc_irqflag = 13;
+ else
+ intsrc.mpc_irqflag = 0;
+ }
+
+ intsrc.mpc_srcbusirq = i;
+ intsrc.mpc_dstirq = i ? i : 2; /* IRQ0 to INTIN2 */
+ MP_intsrc_info(&intsrc);
+ }
+
+ intsrc.mpc_irqtype = mp_ExtINT;
+ intsrc.mpc_srcbusirq = 0;
+ intsrc.mpc_dstirq = 0; /* 8259A to INTIN0 */
+ MP_intsrc_info(&intsrc);
+}
+
+static inline void __init construct_default_ISA_mptable(int mpc_default_type)
+{
+ struct mpc_config_processor processor;
+ struct mpc_config_bus bus;
+ struct mpc_config_ioapic ioapic;
+ struct mpc_config_lintsrc lintsrc;
+ int linttypes[2] = { mp_ExtINT, mp_NMI };
+ int i;
+
+ /*
+ * local APIC has default address
+ */
+ mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
+
+ /*
+ * 2 CPUs, numbered 0 & 1.
+ */
+ processor.mpc_type = MP_PROCESSOR;
+ /* Either an integrated APIC or a discrete 82489DX. */
+ processor.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01;
+ processor.mpc_cpuflag = CPU_ENABLED;
+ processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) |
+ (boot_cpu_data.x86_model << 4) |
+ boot_cpu_data.x86_mask;
+ processor.mpc_featureflag = boot_cpu_data.x86_capability[0];
+ processor.mpc_reserved[0] = 0;
+ processor.mpc_reserved[1] = 0;
+ for (i = 0; i < 2; i++) {
+ processor.mpc_apicid = i;
+ MP_processor_info(&processor);
+ }
+
+ bus.mpc_type = MP_BUS;
+ bus.mpc_busid = 0;
+ switch (mpc_default_type) {
+ default:
+ printk("???\n");
+ printk(KERN_ERR "Unknown standard configuration %d\n",
+ mpc_default_type);
+ /* fall through */
+ case 1:
+ case 5:
+ memcpy(bus.mpc_bustype, "ISA ", 6);
+ break;
+ case 2:
+ case 6:
+ case 3:
+ memcpy(bus.mpc_bustype, "EISA ", 6);
+ break;
+ case 4:
+ case 7:
+ memcpy(bus.mpc_bustype, "MCA ", 6);
+ }
+ MP_bus_info(&bus);
+ if (mpc_default_type > 4) {
+ bus.mpc_busid = 1;
+ memcpy(bus.mpc_bustype, "PCI ", 6);
+ MP_bus_info(&bus);
+ }
+
+ ioapic.mpc_type = MP_IOAPIC;
+ ioapic.mpc_apicid = 2;
+ ioapic.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01;
+ ioapic.mpc_flags = MPC_APIC_USABLE;
+ ioapic.mpc_apicaddr = 0xFEC00000;
+ MP_ioapic_info(&ioapic);
+
+ /*
+ * We set up most of the low 16 IO-APIC pins according to MPS rules.
+ */
+ construct_default_ioirq_mptable(mpc_default_type);
+
+ lintsrc.mpc_type = MP_LINTSRC;
+ lintsrc.mpc_irqflag = 0; /* conforming */
+ lintsrc.mpc_srcbusid = 0;
+ lintsrc.mpc_srcbusirq = 0;
+ lintsrc.mpc_destapic = MP_APIC_ALL;
+ for (i = 0; i < 2; i++) {
+ lintsrc.mpc_irqtype = linttypes[i];
+ lintsrc.mpc_destapiclint = i;
+ MP_lintsrc_info(&lintsrc);
+ }
+}
+
+static struct intel_mp_floating *mpf_found;
+
+/*
+ * Scan the memory blocks for an SMP configuration block.
+ */
+void __init get_smp_config (void)
+{
+ struct intel_mp_floating *mpf = mpf_found;
+
+ /*
+ * ACPI may be used to obtain the entire SMP configuration or just to
+ * enumerate/configure processors (CONFIG_ACPI_BOOT). Note that
+ * ACPI supports both logical (e.g. Hyper-Threading) and physical
+ * processors, where MPS only supports physical.
+ */
+ if (acpi_lapic && acpi_ioapic) {
+ printk(KERN_INFO "Using ACPI (MADT) for SMP configuration
information\n");
+ return;
+ }
+ else if (acpi_lapic)
+ printk(KERN_INFO "Using ACPI for processor (LAPIC)
configuration information\n");
+
+ printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n",
mpf->mpf_specification);
+ if (mpf->mpf_feature2 & (1<<7)) {
+ printk(KERN_INFO " IMCR and PIC compatibility mode.\n");
+ pic_mode = 1;
+ } else {
+ printk(KERN_INFO " Virtual Wire compatibility mode.\n");
+ pic_mode = 0;
+ }
+
+ /*
+ * Now see if we need to read further.
+ */
+ if (mpf->mpf_feature1 != 0) {
+
+ printk(KERN_INFO "Default MP configuration #%d\n",
mpf->mpf_feature1);
+ construct_default_ISA_mptable(mpf->mpf_feature1);
+
+ } else if (mpf->mpf_physptr) {
+
+ /*
+ * Read the physical hardware table. Anything here will
+ * override the defaults.
+ */
+ if (!smp_read_mpc(isa_bus_to_virt(mpf->mpf_physptr))) {
+ smp_found_config = 0;
+ printk(KERN_ERR "BIOS bug, MP table errors
detected!...\n");
+ printk(KERN_ERR "... disabling SMP support. (tell your
hw vendor)\n");
+ return;
+ }
+ /*
+ * If there are no explicit MP IRQ entries, then we are
+ * broken. We set up most of the low 16 IO-APIC pins to
+ * ISA defaults and hope it will work.
+ */
+ if (!mp_irq_entries) {
+ struct mpc_config_bus bus;
+
+ printk(KERN_ERR "BIOS bug, no explicit IRQ entries,
using default mptable. (tell your hw vendor)\n");
+
+ bus.mpc_type = MP_BUS;
+ bus.mpc_busid = 0;
+ memcpy(bus.mpc_bustype, "ISA ", 6);
+ MP_bus_info(&bus);
+
+ construct_default_ioirq_mptable(0);
+ }
+
+ } else
+ BUG();
+
+ printk(KERN_INFO "Processors: %d\n", num_processors);
+ /*
+ * Only use the first configuration found.
+ */
+}
+
+static int __init smp_scan_config (unsigned long base, unsigned long length)
+{
+ unsigned long *bp = isa_bus_to_virt(base);
+ struct intel_mp_floating *mpf;
+
+ Dprintk("Scan SMP from %p for %ld bytes.\n", bp,length);
+ if (sizeof(*mpf) != 16)
+ printk("Error: MPF size\n");
+
+ while (length > 0) {
+ mpf = (struct intel_mp_floating *)bp;
+ if ((*bp == SMP_MAGIC_IDENT) &&
+ (mpf->mpf_length == 1) &&
+ !mpf_checksum((unsigned char *)bp, 16) &&
+ ((mpf->mpf_specification == 1)
+ || (mpf->mpf_specification == 4)) ) {
+
+ smp_found_config = 1;
+ printk(KERN_INFO "found SMP MP-table at %08lx\n",
+ virt_to_phys(mpf));
+ if (mpf->mpf_physptr) {
+ /*
+ * We cannot access to MPC table to compute
+ * table size yet, as only few megabytes from
+ * the bottom is mapped now.
+ * PC-9800's MPC table places on the very last
+ * of physical memory; so that simply reserving
+ * PAGE_SIZE from mpg->mpf_physptr yields BUG()
+ * in reserve_bootmem.
+ */
+ unsigned long size = PAGE_SIZE;
+ unsigned long end = max_low_pfn * PAGE_SIZE;
+ if (mpf->mpf_physptr + size > end)
+ size = end - mpf->mpf_physptr;
+ reserve_bootmem(mpf->mpf_physptr, size);
+ }
+
+ mpf_found = mpf;
+ return 1;
+ }
+ bp += 4;
+ length -= 16;
+ }
+ return 0;
+}
+
+void __init find_smp_config (void)
+{
+ unsigned int address;
+
+ /*
+ * FIXME: Linux assumes you have 640K of base ram..
+ * this continues the error...
+ *
+ * 1) Scan the bottom 1K for a signature
+ * 2) Scan the top 1K of base RAM
+ * 3) Scan the 64K of bios
+ */
+ if (smp_scan_config(0x0,0x400) ||
+ smp_scan_config(639*0x400,0x400) ||
+ smp_scan_config(0xF0000,0x10000))
+ return;
+ /*
+ * If it is an SMP machine we should know now, unless the
+ * configuration is in an EISA/MCA bus machine with an
+ * extended bios data area.
+ *
+ * there is a real-mode segmented pointer pointing to the
+ * 4K EBDA area at 0x40E, calculate and scan it here.
+ *
+ * NOTE! There are Linux loaders that will corrupt the EBDA
+ * area, and as such this kind of SMP config may be less
+ * trustworthy, simply because the SMP table may have been
+ * stomped on during early boot. These loaders are buggy and
+ * should be fixed.
+ *
+ * MP1.4 SPEC states to only scan first 1K of 4K EBDA.
+ */
+
+ address = get_bios_ebda();
+ if (address)
+ smp_scan_config(address, 0x400);
+}
+
+/* --------------------------------------------------------------------------
+ ACPI-based MP Configuration
+ --------------------------------------------------------------------------
*/
+
+#ifdef CONFIG_ACPI_BOOT
+
+void __init mp_register_lapic_address (
+ u64 address)
+{
+#ifndef CONFIG_XEN
+ mp_lapic_addr = (unsigned long) address;
+
+ if (boot_cpu_physical_apicid == -1U)
+ boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID));
+
+ Dprintk("Boot CPU = %d\n", boot_cpu_physical_apicid);
+#endif
+}
+
+
+void __init mp_register_lapic (
+ u8 id,
+ u8 enabled)
+{
+ struct mpc_config_processor processor;
+ int boot_cpu = 0;
+
+ if (MAX_APICS - id <= 0) {
+ printk(KERN_WARNING "Processor #%d invalid (max %d)\n",
+ id, MAX_APICS);
+ return;
+ }
+
+ if (id == boot_cpu_physical_apicid)
+ boot_cpu = 1;
+
+#ifndef CONFIG_XEN
+ processor.mpc_type = MP_PROCESSOR;
+ processor.mpc_apicid = id;
+ processor.mpc_apicver = GET_APIC_VERSION(apic_read(APIC_LVR));
+ processor.mpc_cpuflag = (enabled ? CPU_ENABLED : 0);
+ processor.mpc_cpuflag |= (boot_cpu ? CPU_BOOTPROCESSOR : 0);
+ processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) |
+ (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask;
+ processor.mpc_featureflag = boot_cpu_data.x86_capability[0];
+ processor.mpc_reserved[0] = 0;
+ processor.mpc_reserved[1] = 0;
+#endif
+
+ MP_processor_info(&processor);
+}
+
+#if defined(CONFIG_X86_IO_APIC) && (defined(CONFIG_ACPI_INTERPRETER) ||
defined(CONFIG_ACPI_BOOT))
+
+#define MP_ISA_BUS 0
+#define MP_MAX_IOAPIC_PIN 127
+
+struct mp_ioapic_routing {
+ int apic_id;
+ int gsi_base;
+ int gsi_end;
+ u32 pin_programmed[4];
+} mp_ioapic_routing[MAX_IO_APICS];
+
+
+static int mp_find_ioapic (
+ int gsi)
+{
+ int i = 0;
+
+ /* Find the IOAPIC that manages this GSI. */
+ for (i = 0; i < nr_ioapics; i++) {
+ if ((gsi >= mp_ioapic_routing[i].gsi_base)
+ && (gsi <= mp_ioapic_routing[i].gsi_end))
+ return i;
+ }
+
+ printk(KERN_ERR "ERROR: Unable to locate IOAPIC for GSI %d\n", gsi);
+
+ return -1;
+}
+
+
+void __init mp_register_ioapic (
+ u8 id,
+ u32 address,
+ u32 gsi_base)
+{
+ int idx = 0;
+
+ if (nr_ioapics >= MAX_IO_APICS) {
+ printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded "
+ "(found %d)\n", MAX_IO_APICS, nr_ioapics);
+ panic("Recompile kernel with bigger MAX_IO_APICS!\n");
+ }
+ if (!address) {
+ printk(KERN_ERR "WARNING: Bogus (zero) I/O APIC address"
+ " found in MADT table, skipping!\n");
+ return;
+ }
+
+ idx = nr_ioapics++;
+
+ mp_ioapics[idx].mpc_type = MP_IOAPIC;
+ mp_ioapics[idx].mpc_flags = MPC_APIC_USABLE;
+ mp_ioapics[idx].mpc_apicaddr = address;
+
+ mp_ioapics[idx].mpc_apicid = io_apic_get_unique_id(idx, id);
+ mp_ioapics[idx].mpc_apicver = io_apic_get_version(idx);
+
+ /*
+ * Build basic GSI lookup table to facilitate gsi->io_apic lookups
+ * and to prevent reprogramming of IOAPIC pins (PCI GSIs).
+ */
+ mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].mpc_apicid;
+ mp_ioapic_routing[idx].gsi_base = gsi_base;
+ mp_ioapic_routing[idx].gsi_end = gsi_base +
+ io_apic_get_redir_entries(idx);
+
+ printk("IOAPIC[%d]: apic_id %d, version %d, address 0x%lx, "
+ "GSI %d-%d\n", idx, mp_ioapics[idx].mpc_apicid,
+ mp_ioapics[idx].mpc_apicver, mp_ioapics[idx].mpc_apicaddr,
+ mp_ioapic_routing[idx].gsi_base,
+ mp_ioapic_routing[idx].gsi_end);
+
+ return;
+}
+
+
+void __init mp_override_legacy_irq (
+ u8 bus_irq,
+ u8 polarity,
+ u8 trigger,
+ u32 gsi)
+{
+ struct mpc_config_intsrc intsrc;
+ int ioapic = -1;
+ int pin = -1;
+
+ /*
+ * Convert 'gsi' to 'ioapic.pin'.
+ */
+ ioapic = mp_find_ioapic(gsi);
+ if (ioapic < 0)
+ return;
+ pin = gsi - mp_ioapic_routing[ioapic].gsi_base;
+
+ /*
+ * TBD: This check is for faulty timer entries, where the override
+ * erroneously sets the trigger to level, resulting in a HUGE
+ * increase of timer interrupts!
+ */
+ if ((bus_irq == 0) && (trigger == 3))
+ trigger = 1;
+
+ intsrc.mpc_type = MP_INTSRC;
+ intsrc.mpc_irqtype = mp_INT;
+ intsrc.mpc_irqflag = (trigger << 2) | polarity;
+ intsrc.mpc_srcbus = MP_ISA_BUS;
+ intsrc.mpc_srcbusirq = bus_irq; /* IRQ */
+ intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; /* APIC ID */
+ intsrc.mpc_dstirq = pin; /* INTIN# */
+
+ Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, %d-%d\n",
+ intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3,
+ (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus,
+ intsrc.mpc_srcbusirq, intsrc.mpc_dstapic, intsrc.mpc_dstirq);
+
+ mp_irqs[mp_irq_entries] = intsrc;
+ if (++mp_irq_entries == MAX_IRQ_SOURCES)
+ panic("Max # of irq sources exceeded!\n");
+
+ return;
+}
+
+
+void __init mp_config_acpi_legacy_irqs (void)
+{
+ struct mpc_config_intsrc intsrc;
+ int i = 0;
+ int ioapic = -1;
+
+ /*
+ * Fabricate the legacy ISA bus (bus #31).
+ */
+ mp_bus_id_to_type[MP_ISA_BUS] = MP_BUS_ISA;
+ Dprintk("Bus #%d is ISA\n", MP_ISA_BUS);
+
+ /*
+ * ES7000 has no legacy identity mappings
+ */
+ if (es7000_plat)
+ return;
+
+ /*
+ * Locate the IOAPIC that manages the ISA IRQs (0-15).
+ */
+ ioapic = mp_find_ioapic(0);
+ if (ioapic < 0)
+ return;
+
+ intsrc.mpc_type = MP_INTSRC;
+ intsrc.mpc_irqflag = 0; /* Conforming */
+ intsrc.mpc_srcbus = MP_ISA_BUS;
+ intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid;
+
+ /*
+ * Use the default configuration for the IRQs 0-15. Unless
+ * overriden by (MADT) interrupt source override entries.
+ */
+ for (i = 0; i < 16; i++) {
+ int idx;
+
+ for (idx = 0; idx < mp_irq_entries; idx++) {
+ struct mpc_config_intsrc *irq = mp_irqs + idx;
+
+ /* Do we already have a mapping for this ISA IRQ? */
+ if (irq->mpc_srcbus == MP_ISA_BUS && irq->mpc_srcbusirq
== i)
+ break;
+
+ /* Do we already have a mapping for this IOAPIC pin */
+ if ((irq->mpc_dstapic == intsrc.mpc_dstapic) &&
+ (irq->mpc_dstirq == i))
+ break;
+ }
+
+ if (idx != mp_irq_entries) {
+ printk(KERN_DEBUG "ACPI: IRQ%d used by override.\n", i);
+ continue; /* IRQ already used */
+ }
+
+ intsrc.mpc_irqtype = mp_INT;
+ intsrc.mpc_srcbusirq = i; /* Identity mapped */
+ intsrc.mpc_dstirq = i;
+
+ Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, "
+ "%d-%d\n", intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3,
+ (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus,
+ intsrc.mpc_srcbusirq, intsrc.mpc_dstapic,
+ intsrc.mpc_dstirq);
+
+ mp_irqs[mp_irq_entries] = intsrc;
+ if (++mp_irq_entries == MAX_IRQ_SOURCES)
+ panic("Max # of irq sources exceeded!\n");
+ }
+}
+
+int mp_register_gsi (u32 gsi, int edge_level, int active_high_low)
+{
+ int ioapic = -1;
+ int ioapic_pin = 0;
+ int idx, bit = 0;
+
+#ifdef CONFIG_ACPI_BUS
+ /* Don't set up the ACPI SCI because it's already set up */
+ if (acpi_fadt.sci_int == gsi)
+ return gsi;
+#endif
+
+ ioapic = mp_find_ioapic(gsi);
+ if (ioapic < 0) {
+ printk(KERN_WARNING "No IOAPIC for GSI %u\n", gsi);
+ return gsi;
+ }
+
+ ioapic_pin = gsi - mp_ioapic_routing[ioapic].gsi_base;
+
+ if (ioapic_renumber_irq)
+ gsi = ioapic_renumber_irq(ioapic, gsi);
+
+ /*
+ * Avoid pin reprogramming. PRTs typically include entries
+ * with redundant pin->gsi mappings (but unique PCI devices);
+ * we only program the IOAPIC on the first.
+ */
+ bit = ioapic_pin % 32;
+ idx = (ioapic_pin < 32) ? 0 : (ioapic_pin / 32);
+ if (idx > 3) {
+ printk(KERN_ERR "Invalid reference to IOAPIC pin "
+ "%d-%d\n", mp_ioapic_routing[ioapic].apic_id,
+ ioapic_pin);
+ return gsi;
+ }
+ if ((1<<bit) & mp_ioapic_routing[ioapic].pin_programmed[idx]) {
+ Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n",
+ mp_ioapic_routing[ioapic].apic_id, ioapic_pin);
+ return gsi;
+ }
+
+ mp_ioapic_routing[ioapic].pin_programmed[idx] |= (1<<bit);
+
+ io_apic_set_pci_routing(ioapic, ioapic_pin, gsi,
+ edge_level == ACPI_EDGE_SENSITIVE ? 0 : 1,
+ active_high_low == ACPI_ACTIVE_HIGH ? 0 : 1);
+ return gsi;
+}
+
+#endif /*CONFIG_X86_IO_APIC && (CONFIG_ACPI_INTERPRETER || CONFIG_ACPI_BOOT)*/
+#endif /*CONFIG_ACPI_BOOT*/
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/arch/xen/config.in
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/config.in Fri Jul 15 13:39:50 2005
@@ -0,0 +1,337 @@
+#
+# For a description of the syntax of this configuration file,
+# see Documentation/kbuild/config-language.txt.
+#
+mainmenu_name "Linux Kernel Configuration"
+
+define_bool CONFIG_XEN y
+
+define_bool CONFIG_X86 y
+define_bool CONFIG_ISA y
+define_bool CONFIG_SBUS n
+
+define_bool CONFIG_UID16 y
+
+mainmenu_option next_comment
+comment 'Xen'
+bool 'Support for privileged operations (domain 0)' CONFIG_XEN_PRIVILEGED_GUEST
+bool 'Device-driver domain (physical device access)' CONFIG_XEN_PHYSDEV_ACCESS
+if [ "$CONFIG_XEN_PHYSDEV_ACCESS" = "y" ]; then
+ bool 'USB-device backend driver' CONFIG_XEN_USB_BACKEND
+fi
+bool 'Scrub memory before freeing it to Xen' CONFIG_XEN_SCRUB_PAGES
+bool 'Network-device frontend driver' CONFIG_XEN_NETDEV_FRONTEND
+bool 'Block-device frontend driver' CONFIG_XEN_BLKDEV_FRONTEND
+bool 'Block-device uses grant tables' CONFIG_XEN_BLKDEV_GRANT
+bool 'USB-device frontend driver' CONFIG_XEN_USB_FRONTEND
+endmenu
+# The IBM S/390 patch needs this.
+define_bool CONFIG_NO_IDLE_HZ y
+
+if [ "$CONFIG_XEN_PHYSDEV_ACCESS" = "y" ]; then
+ define_bool CONFIG_FOREIGN_PAGES y
+else
+ define_bool CONFIG_FOREIGN_PAGES n
+ define_bool CONFIG_NETDEVICES y
+ define_bool CONFIG_VT n
+fi
+
+mainmenu_option next_comment
+comment 'Code maturity level options'
+bool 'Prompt for development and/or incomplete code/drivers'
CONFIG_EXPERIMENTAL
+endmenu
+
+mainmenu_option next_comment
+comment 'Loadable module support'
+bool 'Enable loadable module support' CONFIG_MODULES
+if [ "$CONFIG_MODULES" = "y" ]; then
+ bool ' Set version information on all module symbols' CONFIG_MODVERSIONS
+ bool ' Kernel module loader' CONFIG_KMOD
+fi
+endmenu
+
+mainmenu_option next_comment
+comment 'Processor type and features'
+choice 'Processor family' \
+ "Pentium-Pro/Celeron/Pentium-II CONFIG_M686 \
+ Pentium-III/Celeron(Coppermine) CONFIG_MPENTIUMIII \
+ Pentium-4 CONFIG_MPENTIUM4 \
+ Athlon/Duron/K7 CONFIG_MK7 \
+ Opteron/Athlon64/Hammer/K8 CONFIG_MK8 \
+ VIA-C3-2 CONFIG_MVIAC3_2" Pentium-Pro
+
+ define_bool CONFIG_X86_WP_WORKS_OK y
+ define_bool CONFIG_X86_INVLPG y
+ define_bool CONFIG_X86_CMPXCHG y
+ define_bool CONFIG_X86_XADD y
+ define_bool CONFIG_X86_BSWAP y
+ define_bool CONFIG_X86_POPAD_OK y
+ define_bool CONFIG_RWSEM_GENERIC_SPINLOCK n
+ define_bool CONFIG_RWSEM_XCHGADD_ALGORITHM y
+
+ define_bool CONFIG_X86_GOOD_APIC y
+ define_bool CONFIG_X86_PGE y
+ define_bool CONFIG_X86_USE_PPRO_CHECKSUM y
+ define_bool CONFIG_X86_TSC y
+
+if [ "$CONFIG_M686" = "y" ]; then
+ define_int CONFIG_X86_L1_CACHE_SHIFT 5
+fi
+if [ "$CONFIG_MPENTIUMIII" = "y" ]; then
+ define_int CONFIG_X86_L1_CACHE_SHIFT 5
+fi
+if [ "$CONFIG_MPENTIUM4" = "y" ]; then
+ define_int CONFIG_X86_L1_CACHE_SHIFT 7
+fi
+if [ "$CONFIG_MK8" = "y" ]; then
+ define_bool CONFIG_MK7 y
+fi
+if [ "$CONFIG_MK7" = "y" ]; then
+ define_int CONFIG_X86_L1_CACHE_SHIFT 6
+ define_bool CONFIG_X86_USE_3DNOW y
+fi
+if [ "$CONFIG_MVIAC3_2" = "y" ]; then
+ define_int CONFIG_X86_L1_CACHE_SHIFT 5
+fi
+
+#if [ "$CONFIG_EXPERIMENTAL" = "y" ]; then
+# tristate 'BIOS Enhanced Disk Drive calls determine boot disk
(EXPERIMENTAL)' CONFIG_EDD
+#fi
+
+choice 'High Memory Support' \
+ "off CONFIG_NOHIGHMEM \
+ 4GB CONFIG_HIGHMEM4G" off
+# 64GB CONFIG_HIGHMEM64G" off
+if [ "$CONFIG_HIGHMEM4G" = "y" ]; then
+ define_bool CONFIG_HIGHMEM y
+fi
+if [ "$CONFIG_HIGHMEM64G" = "y" ]; then
+ define_bool CONFIG_HIGHMEM y
+ define_bool CONFIG_X86_PAE y
+fi
+
+if [ "$CONFIG_HIGHMEM" = "y" ]; then
+ bool 'HIGHMEM I/O support' CONFIG_HIGHIO
+fi
+
+define_int CONFIG_FORCE_MAX_ZONEORDER 11
+
+#bool 'Symmetric multi-processing support' CONFIG_SMP
+#if [ "$CONFIG_SMP" = "y" -a "$CONFIG_X86_CMPXCHG" = "y" ]; then
+# define_bool CONFIG_HAVE_DEC_LOCK y
+#fi
+endmenu
+
+mainmenu_option next_comment
+comment 'General setup'
+
+bool 'Networking support' CONFIG_NET
+
+if [ "$CONFIG_XEN_PHYSDEV_ACCESS" = "y" ]; then
+ bool 'PCI support' CONFIG_PCI
+ source drivers/pci/Config.in
+
+ bool 'Support for hot-pluggable devices' CONFIG_HOTPLUG
+
+ if [ "$CONFIG_HOTPLUG" = "y" ] ; then
+ source drivers/pcmcia/Config.in
+ source drivers/hotplug/Config.in
+ else
+ define_bool CONFIG_PCMCIA n
+ define_bool CONFIG_HOTPLUG_PCI n
+ fi
+fi
+
+bool 'System V IPC' CONFIG_SYSVIPC
+bool 'BSD Process Accounting' CONFIG_BSD_PROCESS_ACCT
+bool 'Sysctl support' CONFIG_SYSCTL
+if [ "$CONFIG_PROC_FS" = "y" ]; then
+ choice 'Kernel core (/proc/kcore) format' \
+ "ELF CONFIG_KCORE_ELF \
+ A.OUT CONFIG_KCORE_AOUT" ELF
+fi
+tristate 'Kernel support for a.out binaries' CONFIG_BINFMT_AOUT
+bool 'Kernel support for ELF binaries' CONFIG_BINFMT_ELF
+tristate 'Kernel support for MISC binaries' CONFIG_BINFMT_MISC
+bool 'Select task to kill on out of memory condition' CONFIG_OOM_KILLER
+
+endmenu
+
+if [ "$CONFIG_XEN_PHYSDEV_ACCESS" = "y" ]; then
+ source drivers/mtd/Config.in
+
+ source drivers/parport/Config.in
+
+ source drivers/pnp/Config.in
+
+ source drivers/block/Config.in
+
+ source drivers/md/Config.in
+fi
+
+if [ "$CONFIG_NET" = "y" ]; then
+ source net/Config.in
+fi
+
+if [ "$CONFIG_XEN_PHYSDEV_ACCESS" = "y" ]; then
+ mainmenu_option next_comment
+ comment 'ATA/IDE/MFM/RLL support'
+
+ tristate 'ATA/IDE/MFM/RLL support' CONFIG_IDE
+
+ if [ "$CONFIG_IDE" != "n" ]; then
+ source drivers/ide/Config.in
+ else
+ define_bool CONFIG_BLK_DEV_HD n
+ fi
+ endmenu
+fi
+
+mainmenu_option next_comment
+comment 'SCSI support'
+
+tristate 'SCSI support' CONFIG_SCSI
+
+if [ "$CONFIG_SCSI" != "n" ]; then
+ source drivers/scsi/Config.in
+fi
+endmenu
+
+if [ "$CONFIG_XEN_PHYSDEV_ACCESS" = "y" ]; then
+ source drivers/message/fusion/Config.in
+
+ source drivers/ieee1394/Config.in
+
+ source drivers/message/i2o/Config.in
+
+ if [ "$CONFIG_NET" = "y" ]; then
+ mainmenu_option next_comment
+ comment 'Network device support'
+
+ bool 'Network device support' CONFIG_NETDEVICES
+ if [ "$CONFIG_NETDEVICES" = "y" ]; then
+ source drivers/net/Config.in
+ if [ "$CONFIG_ATM" = "y" -o "$CONFIG_ATM" = "m" ]; then
+ source drivers/atm/Config.in
+ fi
+ fi
+ endmenu
+ fi
+
+ source net/ax25/Config.in
+
+ source net/irda/Config.in
+
+ mainmenu_option next_comment
+ comment 'ISDN subsystem'
+ if [ "$CONFIG_NET" != "n" ]; then
+ tristate 'ISDN support' CONFIG_ISDN
+ if [ "$CONFIG_ISDN" != "n" ]; then
+ source drivers/isdn/Config.in
+ fi
+ fi
+ endmenu
+
+ if [ "$CONFIG_ISA" = "y" ]; then
+ mainmenu_option next_comment
+ comment 'Old CD-ROM drivers (not SCSI, not IDE)'
+
+ bool 'Support non-SCSI/IDE/ATAPI CDROM drives' CONFIG_CD_NO_IDESCSI
+ if [ "$CONFIG_CD_NO_IDESCSI" != "n" ]; then
+ source drivers/cdrom/Config.in
+ fi
+ endmenu
+ fi
+
+ #
+ # input before char - char/joystick depends on it. As does USB.
+ #
+ source drivers/input/Config.in
+else
+ #
+ # Block device driver configuration
+ #
+ mainmenu_option next_comment
+ comment 'Block devices'
+ tristate 'Loopback device support' CONFIG_BLK_DEV_LOOP
+ dep_tristate 'Network block device support' CONFIG_BLK_DEV_NBD $CONFIG_NET
+ tristate 'RAM disk support' CONFIG_BLK_DEV_RAM
+ if [ "$CONFIG_BLK_DEV_RAM" = "y" -o "$CONFIG_BLK_DEV_RAM" = "m" ]; then
+ int ' Default RAM disk size' CONFIG_BLK_DEV_RAM_SIZE 4096
+ fi
+ dep_bool ' Initial RAM disk (initrd) support' CONFIG_BLK_DEV_INITRD
$CONFIG_BLK_DEV_RAM
+ bool 'Per partition statistics in /proc/partitions' CONFIG_BLK_STATS
+ define_bool CONFIG_BLK_DEV_HD n
+ endmenu
+fi
+
+source drivers/char/Config.in
+
+if [ "$CONFIG_XEN_PHYSDEV_ACCESS" = "y" -o "$CONFIG_XEN_USB_FRONTEND" = "y" ];
then
+ source drivers/media/Config.in
+fi
+
+source fs/Config.in
+
+mainmenu_option next_comment
+comment 'Console drivers'
+
+define_bool CONFIG_XEN_CONSOLE y
+
+if [ "$CONFIG_VT" = "y" ]; then
+ bool 'VGA text console' CONFIG_VGA_CONSOLE
+ bool 'Dummy console' CONFIG_DUMMY_CONSOLE
+ if [ "$CONFIG_XEN_PHYSDEV_ACCESS" = "y" ]; then
+ bool 'Video mode selection support' CONFIG_VIDEO_SELECT
+ if [ "$CONFIG_EXPERIMENTAL" = "y" ]; then
+ tristate 'MDA text console (dual-headed) (EXPERIMENTAL)'
CONFIG_MDA_CONSOLE
+ source drivers/video/Config.in
+ fi
+ fi
+fi
+endmenu
+
+if [ "$CONFIG_XEN_PHYSDEV_ACCESS" = "y" ]; then
+ mainmenu_option next_comment
+ comment 'Sound'
+
+ tristate 'Sound card support' CONFIG_SOUND
+ if [ "$CONFIG_SOUND" != "n" ]; then
+ source drivers/sound/Config.in
+ fi
+ endmenu
+fi
+
+if [ "$CONFIG_XEN_PHYSDEV_ACCESS" = "y" -o "$CONFIG_XEN_USB_FRONTEND" = "y" ];
then
+ if [ "$CONFIG_XEN_USB_FRONTEND" = "y" -o "$CONFIG_XEN_USB_BACKEND" = "y" ];
then
+ define_bool CONFIG_USB y
+ fi
+ source drivers/usb/Config.in
+fi
+
+if [ "$CONFIG_XEN_PHYSDEV_ACCESS" = "y" ]; then
+ source net/bluetooth/Config.in
+fi
+
+mainmenu_option next_comment
+comment 'Kernel hacking'
+
+bool 'Kernel debugging' CONFIG_DEBUG_KERNEL
+if [ "$CONFIG_DEBUG_KERNEL" != "n" ]; then
+ bool ' Check for stack overflows' CONFIG_DEBUG_STACKOVERFLOW
+ bool ' Debug high memory support' CONFIG_DEBUG_HIGHMEM
+ bool ' Debug memory allocations' CONFIG_DEBUG_SLAB
+ bool ' Memory mapped I/O debugging' CONFIG_DEBUG_IOVIRT
+ bool ' Magic SysRq key' CONFIG_MAGIC_SYSRQ
+ bool ' Spinlock debugging' CONFIG_DEBUG_SPINLOCK
+ bool ' Verbose BUG() reporting (adds 70K)' CONFIG_DEBUG_BUGVERBOSE
+ bool ' Load all symbols for debugging' CONFIG_KALLSYMS
+ bool ' Compile the kernel with frame pointers' CONFIG_FRAME_POINTER
+fi
+
+int 'Kernel messages buffer length shift (0 = default)' CONFIG_LOG_BUF_SHIFT 0
+
+endmenu
+
+source crypto/Config.in
+source lib/Config.in
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/kernel/devmem.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/kernel/devmem.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,158 @@
+/*
+ * Originally from linux/drivers/char/mem.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * Added devfs support.
+ * Jan-11-1998, C. Scott Ananian <cananian@xxxxxxxxxxxxxxxxxxxx>
+ * Shared /dev/zero mmaping support, Feb 2000, Kanoj Sarcar <kanoj@xxxxxxx>
+ */
+
+#include <linux/config.h>
+#include <linux/mm.h>
+#include <linux/miscdevice.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/mman.h>
+#include <linux/random.h>
+#include <linux/init.h>
+#include <linux/raw.h>
+#include <linux/tty.h>
+#include <linux/capability.h>
+#include <linux/smp_lock.h>
+#include <linux/devfs_fs_kernel.h>
+#include <linux/ptrace.h>
+#include <linux/device.h>
+#include <asm/pgalloc.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+
+static inline int uncached_access(struct file *file, unsigned long addr)
+{
+ if (file->f_flags & O_SYNC)
+ return 1;
+ /* Xen sets correct MTRR type on non-RAM for us. */
+ return 0;
+}
+
+/*
+ * This funcion reads the *physical* memory. The f_pos points directly to the
+ * memory location.
+ */
+static ssize_t read_mem(struct file * file, char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long i, p = *ppos;
+ ssize_t read = -EFAULT;
+ void *v;
+
+ if ((v = ioremap(p, count)) == NULL) {
+ /*
+ * Some programs (e.g., dmidecode) groove off into weird RAM
+ * areas where no table scan possibly exist (because Xen will
+ * have stomped on them!). These programs get rather upset if
+ * we let them know that Xen failed their access, so we fake
+ * out a read of all zeroes. :-)
+ */
+ for (i = 0; i < count; i++)
+ if (put_user(0, buf+i))
+ return -EFAULT;
+ return count;
+ }
+ if (copy_to_user(buf, v, count))
+ goto out;
+
+ read = count;
+ *ppos += read;
+out:
+ iounmap(v);
+ return read;
+}
+
+static ssize_t write_mem(struct file * file, const char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long p = *ppos;
+ ssize_t written = -EFAULT;
+ void *v;
+
+ if ((v = ioremap(p, count)) == NULL)
+ return -EFAULT;
+ if (copy_to_user(v, buf, count))
+ goto out;
+
+ written = count;
+ *ppos += written;
+out:
+ iounmap(v);
+ return written;
+}
+
+static int mmap_mem(struct file * file, struct vm_area_struct * vma)
+{
+ unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
+ int uncached;
+
+ uncached = uncached_access(file, offset);
+ if (uncached)
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+ /* Don't try to swap out physical pages.. */
+ vma->vm_flags |= VM_RESERVED;
+
+ /*
+ * Don't dump addresses that are not real memory to a core file.
+ */
+ if (uncached)
+ vma->vm_flags |= VM_IO;
+
+ if (io_remap_page_range(vma, vma->vm_start, offset,
+ vma->vm_end-vma->vm_start, vma->vm_page_prot))
+ return -EAGAIN;
+
+ return 0;
+}
+
+/*
+ * The memory devices use the full 32/64 bits of the offset, and so we cannot
+ * check against negative addresses: they are ok. The return value is weird,
+ * though, in that case (0).
+ *
+ * also note that seeking relative to the "end of file" isn't supported:
+ * it has no meaning, so it returns -EINVAL.
+ */
+static loff_t memory_lseek(struct file * file, loff_t offset, int orig)
+{
+ loff_t ret;
+
+ down(&file->f_dentry->d_inode->i_sem);
+ switch (orig) {
+ case 0:
+ file->f_pos = offset;
+ ret = file->f_pos;
+ force_successful_syscall_return();
+ break;
+ case 1:
+ file->f_pos += offset;
+ ret = file->f_pos;
+ force_successful_syscall_return();
+ break;
+ default:
+ ret = -EINVAL;
+ }
+ up(&file->f_dentry->d_inode->i_sem);
+ return ret;
+}
+
+static int open_mem(struct inode * inode, struct file * filp)
+{
+ return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
+}
+
+struct file_operations mem_fops = {
+ .llseek = memory_lseek,
+ .read = read_mem,
+ .write = write_mem,
+ .mmap = mmap_mem,
+ .open = open_mem,
+};
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/dma-mapping.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/dma-mapping.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,177 @@
+#ifndef _ASM_I386_DMA_MAPPING_H
+#define _ASM_I386_DMA_MAPPING_H
+
+#include <linux/mm.h>
+
+#include <asm/cache.h>
+#include <asm/io.h>
+#include <asm/scatterlist.h>
+
+#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
+#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
+
+void *dma_alloc_coherent(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, int flag);
+
+void dma_free_coherent(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle);
+
+static inline dma_addr_t
+dma_map_single(struct device *dev, void *ptr, size_t size,
+ enum dma_data_direction direction)
+{
+ BUG_ON(direction == DMA_NONE);
+ flush_write_buffers();
+ return virt_to_bus(ptr);
+}
+
+static inline void
+dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
+ enum dma_data_direction direction)
+{
+ BUG_ON(direction == DMA_NONE);
+}
+
+static inline int
+dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+ enum dma_data_direction direction)
+{
+ int i;
+
+ BUG_ON(direction == DMA_NONE);
+
+ for (i = 0; i < nents; i++ ) {
+ BUG_ON(!sg[i].page);
+
+ sg[i].dma_address = page_to_phys(sg[i].page) + sg[i].offset;
+ }
+
+ flush_write_buffers();
+ return nents;
+}
+
+static inline dma_addr_t
+dma_map_page(struct device *dev, struct page *page, unsigned long offset,
+ size_t size, enum dma_data_direction direction)
+{
+ BUG_ON(direction == DMA_NONE);
+ return page_to_phys(page) + offset;
+}
+
+static inline void
+dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
+ enum dma_data_direction direction)
+{
+ BUG_ON(direction == DMA_NONE);
+}
+
+
+static inline void
+dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
+ enum dma_data_direction direction)
+{
+ BUG_ON(direction == DMA_NONE);
+}
+
+static inline void
+dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
+ enum dma_data_direction direction)
+{
+}
+
+static inline void
+dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t
size,
+ enum dma_data_direction direction)
+{
+ flush_write_buffers();
+}
+
+static inline void
+dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
+ unsigned long offset, size_t size,
+ enum dma_data_direction direction)
+{
+}
+
+static inline void
+dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
+ unsigned long offset, size_t size,
+ enum dma_data_direction direction)
+{
+ flush_write_buffers();
+}
+
+static inline void
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
+ enum dma_data_direction direction)
+{
+}
+
+static inline void
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
+ enum dma_data_direction direction)
+{
+ flush_write_buffers();
+}
+
+static inline int
+dma_mapping_error(dma_addr_t dma_addr)
+{
+ return 0;
+}
+
+static inline int
+dma_supported(struct device *dev, u64 mask)
+{
+ /*
+ * we fall back to GFP_DMA when the mask isn't all 1s,
+ * so we can't guarantee allocations that must be
+ * within a tighter range than GFP_DMA..
+ */
+ if(mask < 0x00ffffff)
+ return 0;
+
+ return 1;
+}
+
+static inline int
+dma_set_mask(struct device *dev, u64 mask)
+{
+ if(!dev->dma_mask || !dma_supported(dev, mask))
+ return -EIO;
+
+ *dev->dma_mask = mask;
+
+ return 0;
+}
+
+static inline int
+dma_get_cache_alignment(void)
+{
+ /* no easy way to get cache size on all x86, so return the
+ * maximum possible, to be safe */
+ return (1 << L1_CACHE_SHIFT_MAX);
+}
+
+#define dma_is_consistent(d) (1)
+
+static inline void
+dma_cache_sync(void *vaddr, size_t size,
+ enum dma_data_direction direction)
+{
+ flush_write_buffers();
+}
+
+#define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
+extern int
+dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
+ dma_addr_t device_addr, size_t size, int flags);
+
+extern void
+dma_release_declared_memory(struct device *dev);
+
+extern void *
+dma_mark_declared_memory_occupied(struct device *dev,
+ dma_addr_t device_addr, size_t size);
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/vga.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/vga.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,20 @@
+/*
+ * Access to VGA videoram
+ *
+ * (c) 1998 Martin Mares <mj@xxxxxx>
+ */
+
+#ifndef _LINUX_ASM_VGA_H_
+#define _LINUX_ASM_VGA_H_
+
+/*
+ * On the PC, we can just recalculate addresses and then
+ * access the videoram directly without any black magic.
+ */
+
+#define VGA_MAP_MEM(x) (unsigned long)isa_bus_to_virt(x)
+
+#define vga_readb(x) (*(x))
+#define vga_writeb(x,y) (*(y) = (x))
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/include/linux/blk.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/linux/blk.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,409 @@
+#ifndef _BLK_H
+#define _BLK_H
+
+#include <linux/blkdev.h>
+#include <linux/locks.h>
+#include <linux/config.h>
+#include <linux/spinlock.h>
+
+/*
+ * Spinlock for protecting the request queue which
+ * is mucked around with in interrupts on potentially
+ * multiple CPU's..
+ */
+extern spinlock_t io_request_lock;
+
+/*
+ * Initialization functions.
+ */
+extern int isp16_init(void);
+extern int cdu31a_init(void);
+extern int acsi_init(void);
+extern int mcd_init(void);
+extern int mcdx_init(void);
+extern int sbpcd_init(void);
+extern int aztcd_init(void);
+extern int sony535_init(void);
+extern int gscd_init(void);
+extern int cm206_init(void);
+extern int optcd_init(void);
+extern int sjcd_init(void);
+extern int cdi_init(void);
+extern int hd_init(void);
+extern int ide_init(void);
+extern int xd_init(void);
+extern int mfm_init(void);
+extern int loop_init(void);
+extern int md_init(void);
+extern int ap_init(void);
+extern int ddv_init(void);
+extern int z2_init(void);
+extern int swim3_init(void);
+extern int swimiop_init(void);
+extern int amiga_floppy_init(void);
+extern int atari_floppy_init(void);
+extern int ez_init(void);
+extern int bpcd_init(void);
+extern int ps2esdi_init(void);
+extern int jsfd_init(void);
+extern int viodasd_init(void);
+extern int viocd_init(void);
+
+#if defined(CONFIG_ARCH_S390)
+extern int dasd_init(void);
+extern int xpram_init(void);
+extern int tapeblock_init(void);
+#endif /* CONFIG_ARCH_S390 */
+
+#if defined(CONFIG_XEN)
+extern int xlblk_init(void);
+#endif /* CONFIG_XEN */
+
+extern void set_device_ro(kdev_t dev,int flag);
+void add_blkdev_randomness(int major);
+
+extern int floppy_init(void);
+extern int rd_doload; /* 1 = load ramdisk, 0 = don't load */
+extern int rd_prompt; /* 1 = prompt for ramdisk, 0 = don't prompt */
+extern int rd_image_start; /* starting block # of image */
+
+#ifdef CONFIG_BLK_DEV_INITRD
+
+#define INITRD_MINOR 250 /* shouldn't collide with /dev/ram* too soon ... */
+
+extern unsigned long initrd_start,initrd_end;
+extern int initrd_below_start_ok; /* 1 if it is not an error if initrd_start <
memory_start */
+void initrd_init(void);
+
+#endif
+
+
+/*
+ * end_request() and friends. Must be called with the request queue spinlock
+ * acquired. All functions called within end_request() _must_be_ atomic.
+ *
+ * Several drivers define their own end_request and call
+ * end_that_request_first() and end_that_request_last()
+ * for parts of the original function. This prevents
+ * code duplication in drivers.
+ */
+
+static inline void blkdev_dequeue_request(struct request * req)
+{
+ list_del(&req->queue);
+}
+
+int end_that_request_first(struct request *req, int uptodate, char *name);
+void end_that_request_last(struct request *req);
+
+#if defined(MAJOR_NR) || defined(IDE_DRIVER)
+
+#undef DEVICE_ON
+#undef DEVICE_OFF
+
+/*
+ * Add entries as needed.
+ */
+
+#ifdef IDE_DRIVER
+
+#define DEVICE_NR(device) (MINOR(device) >> PARTN_BITS)
+#define DEVICE_NAME "ide"
+
+#elif (MAJOR_NR == RAMDISK_MAJOR)
+
+/* ram disk */
+#define DEVICE_NAME "ramdisk"
+#define DEVICE_NR(device) (MINOR(device))
+#define DEVICE_NO_RANDOM
+
+#elif (MAJOR_NR == Z2RAM_MAJOR)
+
+/* Zorro II Ram */
+#define DEVICE_NAME "Z2RAM"
+#define DEVICE_REQUEST do_z2_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == FLOPPY_MAJOR)
+
+static void floppy_off(unsigned int nr);
+
+#define DEVICE_NAME "floppy"
+#define DEVICE_INTR do_floppy
+#define DEVICE_REQUEST do_fd_request
+#define DEVICE_NR(device) ( (MINOR(device) & 3) | ((MINOR(device) & 0x80 ) >>
5 ))
+#define DEVICE_OFF(device) floppy_off(DEVICE_NR(device))
+
+#elif (MAJOR_NR == HD_MAJOR)
+
+/* Hard disk: timeout is 6 seconds. */
+#define DEVICE_NAME "hard disk"
+#define DEVICE_INTR do_hd
+#define TIMEOUT_VALUE (6*HZ)
+#define DEVICE_REQUEST do_hd_request
+#define DEVICE_NR(device) (MINOR(device)>>6)
+
+#elif (SCSI_DISK_MAJOR(MAJOR_NR))
+
+#define DEVICE_NAME "scsidisk"
+#define TIMEOUT_VALUE (2*HZ)
+#define DEVICE_NR(device) (((MAJOR(device) & SD_MAJOR_MASK) << (8 - 4)) +
(MINOR(device) >> 4))
+
+/* Kludge to use the same number for both char and block major numbers */
+#elif (MAJOR_NR == MD_MAJOR) && defined(MD_DRIVER)
+
+#define DEVICE_NAME "Multiple devices driver"
+#define DEVICE_REQUEST do_md_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == SCSI_TAPE_MAJOR)
+
+#define DEVICE_NAME "scsitape"
+#define DEVICE_INTR do_st
+#define DEVICE_NR(device) (MINOR(device) & 0x7f)
+
+#elif (MAJOR_NR == OSST_MAJOR)
+
+#define DEVICE_NAME "onstream"
+#define DEVICE_INTR do_osst
+#define DEVICE_NR(device) (MINOR(device) & 0x7f)
+#define DEVICE_ON(device)
+#define DEVICE_OFF(device)
+
+#elif (MAJOR_NR == SCSI_CDROM_MAJOR)
+
+#define DEVICE_NAME "CD-ROM"
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == XT_DISK_MAJOR)
+
+#define DEVICE_NAME "xt disk"
+#define DEVICE_REQUEST do_xd_request
+#define DEVICE_NR(device) (MINOR(device) >> 6)
+
+#elif (MAJOR_NR == PS2ESDI_MAJOR)
+
+#define DEVICE_NAME "PS/2 ESDI"
+#define DEVICE_REQUEST do_ps2esdi_request
+#define DEVICE_NR(device) (MINOR(device) >> 6)
+
+#elif (MAJOR_NR == CDU31A_CDROM_MAJOR)
+
+#define DEVICE_NAME "CDU31A"
+#define DEVICE_REQUEST do_cdu31a_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == ACSI_MAJOR) && (defined(CONFIG_ATARI_ACSI) ||
defined(CONFIG_ATARI_ACSI_MODULE))
+
+#define DEVICE_NAME "ACSI"
+#define DEVICE_INTR do_acsi
+#define DEVICE_REQUEST do_acsi_request
+#define DEVICE_NR(device) (MINOR(device) >> 4)
+
+#elif (MAJOR_NR == MITSUMI_CDROM_MAJOR)
+
+#define DEVICE_NAME "Mitsumi CD-ROM"
+/* #define DEVICE_INTR do_mcd */
+#define DEVICE_REQUEST do_mcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MITSUMI_X_CDROM_MAJOR)
+
+#define DEVICE_NAME "Mitsumi CD-ROM"
+/* #define DEVICE_INTR do_mcdx */
+#define DEVICE_REQUEST do_mcdx_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #1"
+#define DEVICE_REQUEST do_sbpcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM2_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #2"
+#define DEVICE_REQUEST do_sbpcd2_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM3_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #3"
+#define DEVICE_REQUEST do_sbpcd3_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MATSUSHITA_CDROM4_MAJOR)
+
+#define DEVICE_NAME "Matsushita CD-ROM controller #4"
+#define DEVICE_REQUEST do_sbpcd4_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == AZTECH_CDROM_MAJOR)
+
+#define DEVICE_NAME "Aztech CD-ROM"
+#define DEVICE_REQUEST do_aztcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == CDU535_CDROM_MAJOR)
+
+#define DEVICE_NAME "SONY-CDU535"
+#define DEVICE_INTR do_cdu535
+#define DEVICE_REQUEST do_cdu535_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == GOLDSTAR_CDROM_MAJOR)
+
+#define DEVICE_NAME "Goldstar R420"
+#define DEVICE_REQUEST do_gscd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == CM206_CDROM_MAJOR)
+#define DEVICE_NAME "Philips/LMS CD-ROM cm206"
+#define DEVICE_REQUEST do_cm206_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == OPTICS_CDROM_MAJOR)
+
+#define DEVICE_NAME "DOLPHIN 8000AT CD-ROM"
+#define DEVICE_REQUEST do_optcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == SANYO_CDROM_MAJOR)
+
+#define DEVICE_NAME "Sanyo H94A CD-ROM"
+#define DEVICE_REQUEST do_sjcd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == APBLOCK_MAJOR)
+
+#define DEVICE_NAME "apblock"
+#define DEVICE_REQUEST ap_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == DDV_MAJOR)
+
+#define DEVICE_NAME "ddv"
+#define DEVICE_REQUEST ddv_request
+#define DEVICE_NR(device) (MINOR(device)>>PARTN_BITS)
+
+#elif (MAJOR_NR == MFM_ACORN_MAJOR)
+
+#define DEVICE_NAME "mfm disk"
+#define DEVICE_INTR do_mfm
+#define DEVICE_REQUEST do_mfm_request
+#define DEVICE_NR(device) (MINOR(device) >> 6)
+
+#elif (MAJOR_NR == NBD_MAJOR)
+
+#define DEVICE_NAME "nbd"
+#define DEVICE_REQUEST do_nbd_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == MDISK_MAJOR)
+
+#define DEVICE_NAME "mdisk"
+#define DEVICE_REQUEST mdisk_request
+#define DEVICE_NR(device) (MINOR(device))
+
+#elif (MAJOR_NR == DASD_MAJOR)
+
+#define DEVICE_NAME "dasd"
+#define DEVICE_REQUEST do_dasd_request
+#define DEVICE_NR(device) (MINOR(device) >> PARTN_BITS)
+
+#elif (MAJOR_NR == I2O_MAJOR)
+
+#define DEVICE_NAME "I2O block"
+#define DEVICE_REQUEST i2ob_request
+#define DEVICE_NR(device) (MINOR(device)>>4)
+
+#elif (MAJOR_NR == COMPAQ_SMART2_MAJOR)
+
+#define DEVICE_NAME "ida"
+#define TIMEOUT_VALUE (25*HZ)
+#define DEVICE_REQUEST do_ida_request
+#define DEVICE_NR(device) (MINOR(device) >> 4)
+
+#endif /* MAJOR_NR == whatever */
+
+/* provide DEVICE_xxx defaults, if not explicitly defined
+ * above in the MAJOR_NR==xxx if-elif tree */
+#ifndef DEVICE_ON
+#define DEVICE_ON(device) do {} while (0)
+#endif
+#ifndef DEVICE_OFF
+#define DEVICE_OFF(device) do {} while (0)
+#endif
+
+#if (MAJOR_NR != SCSI_TAPE_MAJOR) && (MAJOR_NR != OSST_MAJOR)
+#if !defined(IDE_DRIVER)
+
+#ifndef CURRENT
+#define CURRENT
blkdev_entry_next_request(&blk_dev[MAJOR_NR].request_queue.queue_head)
+#endif
+#ifndef QUEUE_EMPTY
+#define QUEUE_EMPTY list_empty(&blk_dev[MAJOR_NR].request_queue.queue_head)
+#endif
+
+#ifndef DEVICE_NAME
+#define DEVICE_NAME "unknown"
+#endif
+
+#define CURRENT_DEV DEVICE_NR(CURRENT->rq_dev)
+
+#ifdef DEVICE_INTR
+static void (*DEVICE_INTR)(void) = NULL;
+#endif
+
+#define SET_INTR(x) (DEVICE_INTR = (x))
+
+#ifdef DEVICE_REQUEST
+static void (DEVICE_REQUEST)(request_queue_t *);
+#endif
+
+#ifdef DEVICE_INTR
+#define CLEAR_INTR SET_INTR(NULL)
+#else
+#define CLEAR_INTR
+#endif
+
+#define INIT_REQUEST \
+ if (QUEUE_EMPTY) {\
+ CLEAR_INTR; \
+ return; \
+ } \
+ if (MAJOR(CURRENT->rq_dev) != MAJOR_NR) \
+ panic(DEVICE_NAME ": request list destroyed"); \
+ if (CURRENT->bh) { \
+ if (!buffer_locked(CURRENT->bh)) \
+ panic(DEVICE_NAME ": block not locked"); \
+ }
+
+#endif /* !defined(IDE_DRIVER) */
+
+
+#ifndef LOCAL_END_REQUEST /* If we have our own end_request, we do not
want to include this mess */
+
+#if ! SCSI_BLK_MAJOR(MAJOR_NR) && (MAJOR_NR != COMPAQ_SMART2_MAJOR)
+
+static inline void end_request(int uptodate) {
+ struct request *req = CURRENT;
+
+ if (end_that_request_first(req, uptodate, DEVICE_NAME))
+ return;
+
+#ifndef DEVICE_NO_RANDOM
+ add_blkdev_randomness(MAJOR(req->rq_dev));
+#endif
+ DEVICE_OFF(req->rq_dev);
+ blkdev_dequeue_request(req);
+ end_that_request_last(req);
+}
+
+#endif /* ! SCSI_BLK_MAJOR(MAJOR_NR) */
+#endif /* LOCAL_END_REQUEST */
+
+#endif /* (MAJOR_NR != SCSI_TAPE_MAJOR) */
+#endif /* defined(MAJOR_NR) || defined(IDE_DRIVER) */
+
+#endif /* _BLK_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/irq.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/irq.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,65 @@
+#ifndef _ASM_IRQ_H
+#define _ASM_IRQ_H
+
+/*
+ * linux/include/asm/irq.h
+ *
+ * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ *
+ * IRQ/IPI changes taken from work by Thomas Radke
+ * <tomsoft@xxxxxxxxxxxxxxxxxxxxxxxxx>
+ */
+
+#include <linux/config.h>
+#include <asm/hypervisor.h>
+#include <asm/ptrace.h>
+
+/*
+ * The flat IRQ space is divided into two regions:
+ * 1. A one-to-one mapping of real physical IRQs. This space is only used
+ * if we have physical device-access privilege. This region is at the
+ * start of the IRQ space so that existing device drivers do not need
+ * to be modified to translate physical IRQ numbers into our IRQ space.
+ * 3. A dynamic mapping of inter-domain and Xen-sourced virtual IRQs. These
+ * are bound using the provided bind/unbind functions.
+ */
+
+#define PIRQ_BASE 0
+#define NR_PIRQS 128
+
+#define DYNIRQ_BASE (PIRQ_BASE + NR_PIRQS)
+#define NR_DYNIRQS 128
+
+#define NR_IRQS (NR_PIRQS + NR_DYNIRQS)
+
+#define pirq_to_irq(_x) ((_x) + PIRQ_BASE)
+#define irq_to_pirq(_x) ((_x) - PIRQ_BASE)
+
+#define dynirq_to_irq(_x) ((_x) + DYNIRQ_BASE)
+#define irq_to_dynirq(_x) ((_x) - DYNIRQ_BASE)
+
+/* Dynamic binding of event channels and VIRQ sources to Linux IRQ space. */
+extern int bind_virq_to_irq(int virq);
+extern void unbind_virq_from_irq(int virq);
+extern int bind_evtchn_to_irq(int evtchn);
+extern void unbind_evtchn_from_irq(int evtchn);
+
+static __inline__ int irq_cannonicalize(int irq)
+{
+ return (irq == 2) ? 9 : irq;
+}
+
+extern void disable_irq(unsigned int);
+extern void disable_irq_nosync(unsigned int);
+extern void enable_irq(unsigned int);
+
+extern void irq_suspend(void);
+extern void irq_resume(void);
+
+
+#define CPU_MASK_NONE 0
+
+/* XXX SMH: no-op for compat w/ 2.6 shared files */
+#define irq_ctx_init(cpu) do { ; } while (0)
+
+#endif /* _ASM_IRQ_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/apic.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/apic.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,83 @@
+/*
+ * Local APIC handling, local APIC timers
+ *
+ * (c) 1999, 2000 Ingo Molnar <mingo@xxxxxxxxxx>
+ *
+ * Fixes
+ * Maciej W. Rozycki : Bits for genuine 82489DX APICs;
+ * thanks to Eric Gilmore
+ * and Rolf G. Tews
+ * for testing these extensively.
+ * Maciej W. Rozycki : Various updates and fixes.
+ * Mikael Pettersson : Power Management for UP-APIC.
+ * Pavel Machek and
+ * Mikael Pettersson : PM converted to driver model.
+ */
+
+#include <linux/config.h>
+#include <linux/init.h>
+
+#include <linux/mm.h>
+#include <linux/irq.h>
+#include <linux/delay.h>
+#include <linux/bootmem.h>
+#include <linux/smp_lock.h>
+#include <linux/interrupt.h>
+#include <linux/mc146818rtc.h>
+#include <linux/kernel_stat.h>
+#include <linux/sysdev.h>
+
+#include <asm/atomic.h>
+#include <asm/smp.h>
+#include <asm/mtrr.h>
+#include <asm/mpspec.h>
+#include <asm/desc.h>
+#include <asm/arch_hooks.h>
+#include <asm/hpet.h>
+
+#include <mach_apic.h>
+
+#include "io_ports.h"
+
+/*
+ * Debug level
+ */
+int apic_verbosity;
+
+int get_physical_broadcast(void)
+{
+ return 0xff;
+}
+
+/*
+ * 'what should we do if we get a hw irq event on an illegal vector'.
+ * each architecture has to answer this themselves.
+ */
+void ack_bad_irq(unsigned int irq)
+{
+ printk("unexpected IRQ trap at vector %02x\n", irq);
+ /*
+ * Currently unexpected vectors happen only on SMP and APIC.
+ * We _must_ ack these because every local APIC has only N
+ * irq slots per priority level, and a 'hanging, unacked' IRQ
+ * holds up an irq slot - in excessive cases (when multiple
+ * unexpected vectors occur) that might lock up the APIC
+ * completely.
+ */
+ ack_APIC_irq();
+}
+
+/*
+ * This initializes the IO-APIC and APIC hardware if this is
+ * a UP kernel.
+ */
+int __init APIC_init_uniprocessor (void)
+{
+#ifdef CONFIG_X86_IO_APIC
+ if (smp_found_config)
+ if (!skip_ioapic_setup && nr_ioapics)
+ setup_IO_APIC();
+#endif
+
+ return 0;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/pci.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/pci.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,117 @@
+#ifndef __i386_PCI_H
+#define __i386_PCI_H
+
+#include <linux/config.h>
+
+#ifdef __KERNEL__
+#include <linux/mm.h> /* for struct page */
+
+/* Can be used to override the logic in pci_scan_bus for skipping
+ already-configured bus numbers - to be used for buggy BIOSes
+ or architectures with incomplete PCI setup by the loader */
+
+#ifdef CONFIG_PCI
+extern unsigned int pcibios_assign_all_busses(void);
+#else
+#define pcibios_assign_all_busses() 0
+#endif
+#define pcibios_scan_all_fns(a, b) 0
+
+extern unsigned long pci_mem_start;
+#define PCIBIOS_MIN_IO 0x1000
+#define PCIBIOS_MIN_MEM (pci_mem_start)
+
+#define PCIBIOS_MIN_CARDBUS_IO 0x4000
+
+void pcibios_config_init(void);
+struct pci_bus * pcibios_scan_root(int bus);
+
+void pcibios_set_master(struct pci_dev *dev);
+void pcibios_penalize_isa_irq(int irq);
+struct irq_routing_table *pcibios_get_irq_routing_table(void);
+int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq);
+
+/* Dynamic DMA mapping stuff.
+ * i386 has everything mapped statically.
+ */
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <asm/scatterlist.h>
+#include <linux/string.h>
+#include <asm/io.h>
+
+struct pci_dev;
+
+/* The PCI address space does equal the physical memory
+ * address space. The networking and block device layers use
+ * this boolean for bounce buffer decisions.
+ */
+#define PCI_DMA_BUS_IS_PHYS (1)
+
+/* pci_unmap_{page,single} is a nop so... */
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)
+#define pci_unmap_addr(PTR, ADDR_NAME) (0)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0)
+#define pci_unmap_len(PTR, LEN_NAME) (0)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL) do { } while (0)
+
+/* This is always fine. */
+#define pci_dac_dma_supported(pci_dev, mask) (1)
+
+static inline dma64_addr_t
+pci_dac_page_to_dma(struct pci_dev *pdev, struct page *page, unsigned long
offset, int direction)
+{
+ return ((dma64_addr_t) page_to_phys(page) +
+ (dma64_addr_t) offset);
+}
+
+static inline struct page *
+pci_dac_dma_to_page(struct pci_dev *pdev, dma64_addr_t dma_addr)
+{
+ return pfn_to_page(dma_addr >> PAGE_SHIFT);
+}
+
+static inline unsigned long
+pci_dac_dma_to_offset(struct pci_dev *pdev, dma64_addr_t dma_addr)
+{
+ return (dma_addr & ~PAGE_MASK);
+}
+
+static inline void
+pci_dac_dma_sync_single_for_cpu(struct pci_dev *pdev, dma64_addr_t dma_addr,
size_t len, int direction)
+{
+}
+
+static inline void
+pci_dac_dma_sync_single_for_device(struct pci_dev *pdev, dma64_addr_t
dma_addr, size_t len, int direction)
+{
+ flush_write_buffers();
+}
+
+#define HAVE_PCI_MMAP
+extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+ enum pci_mmap_state mmap_state, int
write_combine);
+
+
+static inline void pcibios_add_platform_entries(struct pci_dev *dev)
+{
+}
+
+#endif /* __KERNEL__ */
+
+/* implement the pci_ DMA API in terms of the generic device dma_ one */
+#include <asm-generic/pci-dma-compat.h>
+
+/* generic pci stuff */
+#include <asm-generic/pci.h>
+
+/* On Xen we have to scan all functions since Xen hides bridges from
+ * us. If a bridge is at fn=0 and that slot has a multifunction
+ * device, we won't find the additional devices without scanning all
+ * functions. */
+#undef pcibios_scan_all_fns
+#define pcibios_scan_all_fns(a, b) 1
+
+#endif /* __i386_PCI_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/page.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/page.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,203 @@
+#ifndef _I386_PAGE_H
+#define _I386_PAGE_H
+
+/* PAGE_SHIFT determines the page size */
+#define PAGE_SHIFT 12
+#define PAGE_SIZE (1UL << PAGE_SHIFT)
+#define PAGE_MASK (~(PAGE_SIZE-1))
+
+#define LARGE_PAGE_MASK (~(LARGE_PAGE_SIZE-1))
+#define LARGE_PAGE_SIZE (1UL << PMD_SHIFT)
+
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+
+#include <linux/config.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <asm-xen/xen-public/xen.h>
+#include <asm-xen/foreign_page.h>
+
+#define arch_free_page(_page,_order) \
+({ int foreign = PageForeign(_page); \
+ if (foreign) \
+ (PageForeignDestructor(_page))(_page); \
+ foreign; \
+})
+#define HAVE_ARCH_FREE_PAGE
+
+#ifdef CONFIG_XEN_SCRUB_PAGES
+#define scrub_pages(_p,_n) memset((void *)(_p), 0, (_n) << PAGE_SHIFT)
+#else
+#define scrub_pages(_p,_n) ((void)0)
+#endif
+
+#ifdef CONFIG_X86_USE_3DNOW
+
+#include <asm/mmx.h>
+
+#define clear_page(page) mmx_clear_page((void *)(page))
+#define copy_page(to,from) mmx_copy_page(to,from)
+
+#else
+
+#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER |
__GFP_ZERO, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+
+/*
+ * On older X86 processors it's not a win to use MMX here it seems.
+ * Maybe the K6-III ?
+ */
+
+#define clear_page(page) memset((void *)(page), 0, PAGE_SIZE)
+#define copy_page(to,from) memcpy((void *)(to), (void *)(from), PAGE_SIZE)
+
+#endif
+
+#define clear_user_page(page, vaddr, pg) clear_page(page)
+#define copy_user_page(to, from, vaddr, pg) copy_page(to, from)
+
+/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
+extern unsigned int *phys_to_machine_mapping;
+#define pfn_to_mfn(_pfn) ((unsigned long)(phys_to_machine_mapping[(_pfn)]))
+#define mfn_to_pfn(_mfn) ((unsigned long)(machine_to_phys_mapping[(_mfn)]))
+static inline unsigned long phys_to_machine(unsigned long phys)
+{
+ unsigned long machine = pfn_to_mfn(phys >> PAGE_SHIFT);
+ machine = (machine << PAGE_SHIFT) | (phys & ~PAGE_MASK);
+ return machine;
+}
+static inline unsigned long machine_to_phys(unsigned long machine)
+{
+ unsigned long phys = mfn_to_pfn(machine >> PAGE_SHIFT);
+ phys = (phys << PAGE_SHIFT) | (machine & ~PAGE_MASK);
+ return phys;
+}
+
+/*
+ * These are used to make use of C type-checking..
+ */
+extern int nx_enabled;
+#ifdef CONFIG_X86_PAE
+extern unsigned long long __supported_pte_mask;
+typedef struct { unsigned long pte_low, pte_high; } pte_t;
+typedef struct { unsigned long long pmd; } pmd_t;
+typedef struct { unsigned long long pgd; } pgd_t;
+typedef struct { unsigned long long pgprot; } pgprot_t;
+#define pmd_val(x) ((x).pmd)
+#define pte_val(x) ((x).pte_low | ((unsigned long long)(x).pte_high << 32))
+#define __pmd(x) ((pmd_t) { (x) } )
+#define HPAGE_SHIFT 21
+#else
+typedef struct { unsigned long pte_low; } pte_t;
+typedef struct { unsigned long pgd; } pgd_t;
+typedef struct { unsigned long pgprot; } pgprot_t;
+#define boot_pte_t pte_t /* or would you rather have a typedef */
+#define pte_val(x) (((x).pte_low & 1) ? machine_to_phys((x).pte_low) : \
+ (x).pte_low)
+#define pte_val_ma(x) ((x).pte_low)
+#define HPAGE_SHIFT 22
+#endif
+#define PTE_MASK PAGE_MASK
+
+#ifdef CONFIG_HUGETLB_PAGE
+#define HPAGE_SIZE ((1UL) << HPAGE_SHIFT)
+#define HPAGE_MASK (~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT)
+#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#endif
+
+
+static inline unsigned long pgd_val(pgd_t x)
+{
+ unsigned long ret = x.pgd;
+ if (ret) ret = machine_to_phys(ret);
+ return ret;
+}
+#define pgprot_val(x) ((x).pgprot)
+
+#define __pte(x) ({ unsigned long _x = (x); \
+ (((_x)&1) ? ((pte_t) {phys_to_machine(_x)}) : ((pte_t) {(_x)})); })
+#define __pte_ma(x) ((pte_t) { (x) } )
+#define __pgd(x) ({ unsigned long _x = (x); \
+ (((_x)&1) ? ((pgd_t) {phys_to_machine(_x)}) : ((pgd_t) {(_x)})); })
+#define __pgprot(x) ((pgprot_t) { (x) } )
+
+#endif /* !__ASSEMBLY__ */
+
+/* to align the pointer to the (next) page boundary */
+#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK)
+
+/*
+ * This handles the memory map.. We could make this a config
+ * option, but too many people screw it up, and too few need
+ * it.
+ *
+ * A __PAGE_OFFSET of 0xC0000000 means that the kernel has
+ * a virtual address space of one gigabyte, which limits the
+ * amount of physical memory you can use to about 950MB.
+ *
+ * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
+ * and CONFIG_HIGHMEM64G options in the kernel configuration.
+ */
+
+#ifndef __ASSEMBLY__
+
+/*
+ * This much address space is reserved for vmalloc() and iomap()
+ * as well as fixmap mappings.
+ */
+extern unsigned int __VMALLOC_RESERVE;
+
+/* Pure 2^n version of get_order */
+static __inline__ int get_order(unsigned long size)
+{
+ int order;
+
+ size = (size-1) >> (PAGE_SHIFT-1);
+ order = -1;
+ do {
+ size >>= 1;
+ order++;
+ } while (size);
+ return order;
+}
+
+extern int sysctl_legacy_va_layout;
+
+#endif /* __ASSEMBLY__ */
+
+#ifdef __ASSEMBLY__
+#define __PAGE_OFFSET (0xC0000000)
+#else
+#define __PAGE_OFFSET (0xC0000000UL)
+#endif
+
+
+#define PAGE_OFFSET ((unsigned long)__PAGE_OFFSET)
+#define VMALLOC_RESERVE ((unsigned long)__VMALLOC_RESERVE)
+#define MAXMEM
(HYPERVISOR_VIRT_START-__PAGE_OFFSET-__VMALLOC_RESERVE)
+#define __pa(x) ((unsigned long)(x)-PAGE_OFFSET)
+#define __va(x) ((void *)((unsigned
long)(x)+PAGE_OFFSET))
+#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
+#ifndef CONFIG_DISCONTIGMEM
+#define pfn_to_page(pfn) (mem_map + (pfn))
+#define page_to_pfn(page) ((unsigned long)((page) - mem_map))
+#define pfn_valid(pfn) ((pfn) < max_mapnr)
+#endif /* !CONFIG_DISCONTIGMEM */
+#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
+
+#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+
+#define VM_DATA_DEFAULT_FLAGS \
+ (VM_READ | VM_WRITE | \
+ ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
+ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+/* VIRT <-> MACHINE conversion */
+#define virt_to_machine(_a) (phys_to_machine(__pa(_a)))
+#define machine_to_virt(_m) (__va(machine_to_phys(_m)))
+
+#endif /* __KERNEL__ */
+
+#endif /* _I386_PAGE_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/mmu_context.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/mmu_context.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,108 @@
+#ifndef __I386_SCHED_H
+#define __I386_SCHED_H
+
+#include <linux/config.h>
+#include <asm/desc.h>
+#include <asm/atomic.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+
+/*
+ * Used for LDT copy/destruction.
+ */
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
+void destroy_context(struct mm_struct *mm);
+
+
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct
*tsk)
+{
+#if 0 /* XEN: no lazy tlb */
+ unsigned cpu = smp_processor_id();
+ if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK)
+ per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_LAZY;
+#endif
+}
+
+#define prepare_arch_switch(rq,next) __prepare_arch_switch()
+#define finish_arch_switch(rq, next) spin_unlock_irq(&(rq)->lock)
+#define task_running(rq, p) ((rq)->curr == (p))
+
+static inline void __prepare_arch_switch(void)
+{
+ /*
+ * Save away %fs and %gs. No need to save %es and %ds, as those
+ * are always kernel segments while inside the kernel. Must
+ * happen before reload of cr3/ldt (i.e., not in __switch_to).
+ */
+ __asm__ __volatile__ ( "movl %%fs,%0 ; movl %%gs,%1"
+ : "=m" (*(int *)¤t->thread.fs),
+ "=m" (*(int *)¤t->thread.gs));
+ __asm__ __volatile__ ( "movl %0,%%fs ; movl %0,%%gs"
+ : : "r" (0) );
+}
+
+extern void mm_pin(struct mm_struct *mm);
+extern void mm_unpin(struct mm_struct *mm);
+void mm_pin_all(void);
+
+static inline void switch_mm(struct mm_struct *prev,
+ struct mm_struct *next,
+ struct task_struct *tsk)
+{
+ int cpu = smp_processor_id();
+ struct mmuext_op _op[2], *op = _op;
+
+ if (likely(prev != next)) {
+ if (!next->context.pinned)
+ mm_pin(next);
+
+ /* stop flush ipis for the previous mm */
+ cpu_clear(cpu, prev->cpu_vm_mask);
+#if 0 /* XEN: no lazy tlb */
+ per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK;
+ per_cpu(cpu_tlbstate, cpu).active_mm = next;
+#endif
+ cpu_set(cpu, next->cpu_vm_mask);
+
+ /* Re-load page tables: load_cr3(next->pgd) */
+ per_cpu(cur_pgd, cpu) = next->pgd;
+ op->cmd = MMUEXT_NEW_BASEPTR;
+ op->mfn = pfn_to_mfn(__pa(next->pgd) >> PAGE_SHIFT);
+ op++;
+
+ /*
+ * load the LDT, if the LDT is different:
+ */
+ if (unlikely(prev->context.ldt != next->context.ldt)) {
+ /* load_LDT_nolock(&next->context, cpu) */
+ op->cmd = MMUEXT_SET_LDT;
+ op->linear_addr = (unsigned long)next->context.ldt;
+ op->nr_ents = next->context.size;
+ op++;
+ }
+
+ BUG_ON(HYPERVISOR_mmuext_op(_op, op-_op, NULL, DOMID_SELF));
+ }
+#if 0 /* XEN: no lazy tlb */
+ else {
+ per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK;
+ BUG_ON(per_cpu(cpu_tlbstate, cpu).active_mm != next);
+
+ if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
+ /* We were in lazy tlb mode and leave_mm disabled
+ * tlb flush IPI delivery. We must reload %cr3.
+ */
+ load_cr3(next->pgd);
+ load_LDT_nolock(&next->context, cpu);
+ }
+ }
+#endif
+}
+
+#define deactivate_mm(tsk, mm) \
+ asm("movl %0,%%fs ; movl %0,%%gs": :"r" (0))
+
+#define activate_mm(prev, next) \
+ switch_mm((prev),(next),NULL)
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blkback/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blkback/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,2 @@
+
+obj-y := blkback.o control.o interface.o vbd.o
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/kernel/time.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/kernel/time.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,721 @@
+/* -*- Mode:C; c-basic-offset:4; tab-width:4 -*-
+ ****************************************************************************
+ * (C) 2002-2003 - Rolf Neugebauer - Intel Research Cambridge
+ * (C) 2002-2003 - Keir Fraser - University of Cambridge
+ ****************************************************************************
+ *
+ * File: arch/xen/kernel/time.c
+ * Author: Rolf Neugebauer and Keir Fraser
+ *
+ * Description: Interface with Xen to get correct notion of time
+ */
+
+/*
+ * linux/arch/i386/kernel/time.c
+ *
+ * Copyright (C) 1991, 1992, 1995 Linus Torvalds
+ *
+ * This file contains the PC-specific time handling details:
+ * reading the RTC at bootup, etc..
+ * 1994-07-02 Alan Modra
+ * fixed set_rtc_mmss, fixed time.year for >= 2000, new mktime
+ * 1995-03-26 Markus Kuhn
+ * fixed 500 ms bug at call to set_rtc_mmss, fixed DS12887
+ * precision CMOS clock update
+ * 1996-05-03 Ingo Molnar
+ * fixed time warps in do_[slow|fast]_gettimeoffset()
+ * 1997-09-10 Updated NTP code according to technical memorandum Jan '96
+ * "A Kernel Model for Precision Timekeeping" by Dave Mills
+ * 1998-09-05 (Various)
+ * More robust do_fast_gettimeoffset() algorithm implemented
+ * (works with APM, Cyrix 6x86MX and Centaur C6),
+ * monotonic gettimeofday() with fast_get_timeoffset(),
+ * drift-proof precision TSC calibration on boot
+ * (C. Scott Ananian <cananian@xxxxxxxxxxxxxxxxxxxx>, Andrew D.
+ * Balsa <andrebalsa@xxxxxxxxxx>, Philip Gladstone <philip@xxxxxxxxxx>;
+ * ported from 2.0.35 Jumbo-9 by Michael Krause <m.krause@xxxxxxxxxxxxx>).
+ * 1998-12-16 Andrea Arcangeli
+ * Fixed Jumbo-9 code in 2.1.131: do_gettimeofday was missing 1 jiffy
+ * because was not accounting lost_ticks.
+ * 1998-12-24 Copyright (C) 1998 Andrea Arcangeli
+ * Fixed a xtime SMP race (we need the xtime_lock rw spinlock to
+ * serialize accesses to xtime/lost_ticks).
+ */
+
+#include <asm/smp.h>
+#include <asm/irq.h>
+#include <asm/msr.h>
+#include <asm/delay.h>
+#include <asm/mpspec.h>
+#include <asm/uaccess.h>
+#include <asm/processor.h>
+
+#include <asm/div64.h>
+#include <asm/hypervisor.h>
+#include <asm-xen/xen-public/dom0_ops.h>
+
+#include <linux/mc146818rtc.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/time.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/irq.h>
+#include <linux/sysctl.h>
+#include <linux/sysrq.h>
+
+spinlock_t rtc_lock = SPIN_LOCK_UNLOCKED;
+extern rwlock_t xtime_lock;
+extern unsigned long wall_jiffies;
+
+unsigned long cpu_khz; /* get this from Xen, used elsewhere */
+
+static unsigned int rdtsc_bitshift;
+static u32 st_scale_f; /* convert ticks -> usecs */
+static u32 st_scale_i; /* convert ticks -> usecs */
+
+/* These are peridically updated in shared_info, and then copied here. */
+static u32 shadow_tsc_stamp;
+static u64 shadow_system_time;
+static u32 shadow_time_version;
+static struct timeval shadow_tv;
+
+/*
+ * We use this to ensure that gettimeofday() is monotonically increasing. We
+ * only break this guarantee if the wall clock jumps backwards "a long way".
+ */
+static struct timeval last_seen_tv = {0,0};
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+/* Periodically propagate synchronised time base to the RTC and to Xen. */
+static long last_update_to_rtc, last_update_to_xen;
+#endif
+
+/* Periodically take synchronised time base from Xen, if we need it. */
+static long last_update_from_xen; /* UTC seconds when last read Xen clock. */
+
+/* Keep track of last time we did processing/updating of jiffies and xtime. */
+static u64 processed_system_time; /* System time (ns) at last processing. */
+
+#define NS_PER_TICK (1000000000ULL/HZ)
+
+#ifndef NSEC_PER_SEC
+#define NSEC_PER_SEC (1000000000L)
+#endif
+
+#define HANDLE_USEC_UNDERFLOW(_tv) \
+ do { \
+ while ( (_tv).tv_usec < 0 ) \
+ { \
+ (_tv).tv_usec += 1000000; \
+ (_tv).tv_sec--; \
+ } \
+ } while ( 0 )
+#define HANDLE_USEC_OVERFLOW(_tv) \
+ do { \
+ while ( (_tv).tv_usec >= 1000000 ) \
+ { \
+ (_tv).tv_usec -= 1000000; \
+ (_tv).tv_sec++; \
+ } \
+ } while ( 0 )
+static inline void __normalize_time(time_t *sec, s64 *nsec)
+{
+ while (*nsec >= NSEC_PER_SEC) {
+ (*nsec) -= NSEC_PER_SEC;
+ (*sec)++;
+ }
+ while (*nsec < 0) {
+ (*nsec) += NSEC_PER_SEC;
+ (*sec)--;
+ }
+}
+
+/* Dynamically-mapped IRQs. */
+static int time_irq, debug_irq;
+
+/* Does this guest OS track Xen time, or set its wall clock independently? */
+static int independent_wallclock = 0;
+static int __init __independent_wallclock(char *str)
+{
+ independent_wallclock = 1;
+ return 1;
+}
+__setup("independent_wallclock", __independent_wallclock);
+#define INDEPENDENT_WALLCLOCK() \
+ (independent_wallclock || (xen_start_info.flags & SIF_INITDOMAIN))
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+/*
+ * In order to set the CMOS clock precisely, set_rtc_mmss has to be
+ * called 500 ms after the second nowtime has started, because when
+ * nowtime is written into the registers of the CMOS clock, it will
+ * jump to the next second precisely 500 ms later. Check the Motorola
+ * MC146818A or Dallas DS12887 data sheet for details.
+ *
+ * BUG: This routine does not handle hour overflow properly; it just
+ * sets the minutes. Usually you'll only notice that after reboot!
+ */
+static int set_rtc_mmss(unsigned long nowtime)
+{
+ int retval = 0;
+ int real_seconds, real_minutes, cmos_minutes;
+ unsigned char save_control, save_freq_select;
+
+ /* gets recalled with irq locally disabled */
+ spin_lock(&rtc_lock);
+ save_control = CMOS_READ(RTC_CONTROL);
+ CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL);
+
+ save_freq_select = CMOS_READ(RTC_FREQ_SELECT);
+ CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT);
+
+ cmos_minutes = CMOS_READ(RTC_MINUTES);
+ if ( !(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD )
+ BCD_TO_BIN(cmos_minutes);
+
+ /*
+ * since we're only adjusting minutes and seconds, don't interfere with
+ * hour overflow. This avoids messing with unknown time zones but requires
+ * your RTC not to be off by more than 15 minutes
+ */
+ real_seconds = nowtime % 60;
+ real_minutes = nowtime / 60;
+ if ( ((abs(real_minutes - cmos_minutes) + 15)/30) & 1 )
+ real_minutes += 30; /* correct for half hour time zone */
+ real_minutes %= 60;
+
+ if ( abs(real_minutes - cmos_minutes) < 30 )
+ {
+ if ( !(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD )
+ {
+ BIN_TO_BCD(real_seconds);
+ BIN_TO_BCD(real_minutes);
+ }
+ CMOS_WRITE(real_seconds,RTC_SECONDS);
+ CMOS_WRITE(real_minutes,RTC_MINUTES);
+ }
+ else
+ {
+ printk(KERN_WARNING
+ "set_rtc_mmss: can't update from %d to %d\n",
+ cmos_minutes, real_minutes);
+ retval = -1;
+ }
+
+ /* The following flags have to be released exactly in this order,
+ * otherwise the DS12887 (popular MC146818A clone with integrated
+ * battery and quartz) will not reset the oscillator and will not
+ * update precisely 500 ms later. You won't find this mentioned in
+ * the Dallas Semiconductor data sheets, but who believes data
+ * sheets anyway ... -- Markus Kuhn
+ */
+ CMOS_WRITE(save_control, RTC_CONTROL);
+ CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
+ spin_unlock(&rtc_lock);
+
+ return retval;
+}
+#endif
+
+
+/*
+ * Reads a consistent set of time-base values from Xen, into a shadow data
+ * area. Must be called with the xtime_lock held for writing.
+ */
+static void __get_time_values_from_xen(void)
+{
+ do {
+ shadow_time_version = HYPERVISOR_shared_info->time_version2;
+ rmb();
+ shadow_tv.tv_sec = HYPERVISOR_shared_info->wc_sec;
+ shadow_tv.tv_usec = HYPERVISOR_shared_info->wc_usec;
+ shadow_tsc_stamp =
+ (u32)(HYPERVISOR_shared_info->tsc_timestamp >> rdtsc_bitshift);
+ shadow_system_time = HYPERVISOR_shared_info->system_time;
+ rmb();
+ }
+ while ( shadow_time_version != HYPERVISOR_shared_info->time_version1 );
+}
+
+#define TIME_VALUES_UP_TO_DATE \
+ ({ rmb(); (shadow_time_version == HYPERVISOR_shared_info->time_version2); })
+
+
+/*
+ * Returns the system time elapsed, in ns, since the current shadow_timestamp
+ * was calculated. Must be called with the xtime_lock held for reading.
+ */
+static inline unsigned long __get_time_delta_usecs(void)
+{
+ s32 delta_tsc;
+ u32 low;
+ u64 delta, tsc;
+
+ rdtscll(tsc);
+ low = (u32)(tsc >> rdtsc_bitshift);
+ delta_tsc = (s32)(low - shadow_tsc_stamp);
+ if ( unlikely(delta_tsc < 0) ) delta_tsc = 0;
+ delta = ((u64)delta_tsc * st_scale_f);
+ delta >>= 32;
+ delta += ((u64)delta_tsc * st_scale_i);
+
+ return (unsigned long)delta;
+}
+
+
+/*
+ * Returns the current time-of-day in UTC timeval format.
+ */
+void do_gettimeofday(struct timeval *tv)
+{
+ unsigned long flags, lost;
+ struct timeval _tv;
+ s64 nsec;
+
+ again:
+ read_lock_irqsave(&xtime_lock, flags);
+
+ _tv.tv_usec = __get_time_delta_usecs();
+ if ( (lost = (jiffies - wall_jiffies)) != 0 )
+ _tv.tv_usec += lost * (1000000 / HZ);
+ _tv.tv_sec = xtime.tv_sec;
+ _tv.tv_usec += xtime.tv_usec;
+
+ nsec = shadow_system_time - processed_system_time;
+ __normalize_time(&_tv.tv_sec, &nsec);
+ _tv.tv_usec += (long)nsec / 1000L;
+
+ if ( unlikely(!TIME_VALUES_UP_TO_DATE) )
+ {
+ /*
+ * We may have blocked for a long time, rendering our calculations
+ * invalid (e.g. the time delta may have overflowed). Detect that
+ * and recalculate with fresh values.
+ */
+ read_unlock_irqrestore(&xtime_lock, flags);
+ write_lock_irqsave(&xtime_lock, flags);
+ __get_time_values_from_xen();
+ write_unlock_irqrestore(&xtime_lock, flags);
+ goto again;
+ }
+
+ HANDLE_USEC_OVERFLOW(_tv);
+
+ /* Ensure that time-of-day is monotonically increasing. */
+ if ( (_tv.tv_sec < last_seen_tv.tv_sec) ||
+ ((_tv.tv_sec == last_seen_tv.tv_sec) &&
+ (_tv.tv_usec < last_seen_tv.tv_usec)) )
+ _tv = last_seen_tv;
+ last_seen_tv = _tv;
+
+ read_unlock_irqrestore(&xtime_lock, flags);
+
+ *tv = _tv;
+}
+
+
+/*
+ * Sets the current time-of-day based on passed-in UTC timeval parameter.
+ */
+void do_settimeofday(struct timeval *tv)
+{
+ struct timeval newtv;
+ s64 nsec;
+ suseconds_t usec;
+
+ if ( !INDEPENDENT_WALLCLOCK() )
+ return;
+
+ write_lock_irq(&xtime_lock);
+
+ /*
+ * Ensure we don't get blocked for a long time so that our time delta
+ * overflows. If that were to happen then our shadow time values would
+ * be stale, so we can retry with fresh ones.
+ */
+ again:
+ usec = tv->tv_usec - __get_time_delta_usecs();
+
+ nsec = shadow_system_time - processed_system_time;
+ __normalize_time(&tv->tv_sec, &nsec);
+ usec -= (long)nsec / 1000L;
+
+ if ( unlikely(!TIME_VALUES_UP_TO_DATE) )
+ {
+ __get_time_values_from_xen();
+ goto again;
+ }
+ tv->tv_usec = usec;
+
+ HANDLE_USEC_UNDERFLOW(*tv);
+
+ newtv = *tv;
+
+ tv->tv_usec -= (jiffies - wall_jiffies) * (1000000 / HZ);
+ HANDLE_USEC_UNDERFLOW(*tv);
+
+ xtime = *tv;
+ time_adjust = 0; /* stop active adjtime() */
+ time_status |= STA_UNSYNC;
+ time_maxerror = NTP_PHASE_LIMIT;
+ time_esterror = NTP_PHASE_LIMIT;
+
+ /* Reset all our running time counts. They make no sense now. */
+ last_seen_tv.tv_sec = 0;
+ last_update_from_xen = 0;
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ if ( xen_start_info.flags & SIF_INITDOMAIN )
+ {
+ dom0_op_t op;
+ last_update_to_rtc = last_update_to_xen = 0;
+ op.cmd = DOM0_SETTIME;
+ op.u.settime.secs = newtv.tv_sec;
+ op.u.settime.usecs = newtv.tv_usec;
+ op.u.settime.system_time = shadow_system_time;
+ write_unlock_irq(&xtime_lock);
+ HYPERVISOR_dom0_op(&op);
+ }
+ else
+#endif
+ {
+ write_unlock_irq(&xtime_lock);
+ }
+}
+
+
+asmlinkage long sys_stime(int *tptr)
+{
+ int value;
+ struct timeval tv;
+
+ if ( !capable(CAP_SYS_TIME) )
+ return -EPERM;
+
+ if ( get_user(value, tptr) )
+ return -EFAULT;
+
+ tv.tv_sec = value;
+ tv.tv_usec = 0;
+
+ do_settimeofday(&tv);
+
+ return 0;
+}
+
+
+/* Convert jiffies to system time. Call with xtime_lock held for reading. */
+static inline u64 __jiffies_to_st(unsigned long j)
+{
+ return processed_system_time + ((j - jiffies) * NS_PER_TICK);
+}
+
+
+static inline void do_timer_interrupt(int irq, void *dev_id,
+ struct pt_regs *regs)
+{
+ s64 delta;
+ unsigned long ticks = 0;
+ long sec_diff;
+
+ do {
+ __get_time_values_from_xen();
+
+ delta = (s64)(shadow_system_time +
+ ((s64)__get_time_delta_usecs() * 1000LL) -
+ processed_system_time);
+ }
+ while ( !TIME_VALUES_UP_TO_DATE );
+
+ if ( unlikely(delta < 0) )
+ {
+ printk("Timer ISR: Time went backwards: %lld\n", delta);
+ return;
+ }
+
+ /* Process elapsed jiffies since last call. */
+ while ( delta >= NS_PER_TICK )
+ {
+ ticks++;
+ delta -= NS_PER_TICK;
+ processed_system_time += NS_PER_TICK;
+ }
+
+ if ( ticks != 0 )
+ {
+ do_timer_ticks(ticks);
+
+ if ( user_mode(regs) )
+ update_process_times_us(ticks, 0);
+ else
+ update_process_times_us(0, ticks);
+ }
+
+ /*
+ * Take synchronised time from Xen once a minute if we're not
+ * synchronised ourselves, and we haven't chosen to keep an independent
+ * time base.
+ */
+ if ( !INDEPENDENT_WALLCLOCK() &&
+ ((time_status & STA_UNSYNC) != 0) &&
+ (xtime.tv_sec > (last_update_from_xen + 60)) )
+ {
+ /* Adjust shadow timeval for jiffies that haven't updated xtime yet. */
+ shadow_tv.tv_usec -= (jiffies - wall_jiffies) * (1000000/HZ);
+ HANDLE_USEC_UNDERFLOW(shadow_tv);
+
+ /*
+ * Reset our running time counts if they are invalidated by a warp
+ * backwards of more than 500ms.
+ */
+ sec_diff = xtime.tv_sec - shadow_tv.tv_sec;
+ if ( unlikely(abs(sec_diff) > 1) ||
+ unlikely(((sec_diff * 1000000) +
+ xtime.tv_usec - shadow_tv.tv_usec) > 500000) )
+ {
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ last_update_to_rtc = last_update_to_xen = 0;
+#endif
+ last_seen_tv.tv_sec = 0;
+ }
+
+ /* Update our unsynchronised xtime appropriately. */
+ xtime = shadow_tv;
+
+ last_update_from_xen = xtime.tv_sec;
+ }
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ if ( (xen_start_info.flags & SIF_INITDOMAIN) &&
+ ((time_status & STA_UNSYNC) == 0) )
+ {
+ /* Send synchronised time to Xen approximately every minute. */
+ if ( xtime.tv_sec > (last_update_to_xen + 60) )
+ {
+ dom0_op_t op;
+ struct timeval tv = xtime;
+
+ tv.tv_usec += (jiffies - wall_jiffies) * (1000000/HZ);
+ HANDLE_USEC_OVERFLOW(tv);
+
+ op.cmd = DOM0_SETTIME;
+ op.u.settime.secs = tv.tv_sec;
+ op.u.settime.usecs = tv.tv_usec;
+ op.u.settime.system_time = shadow_system_time;
+ HYPERVISOR_dom0_op(&op);
+
+ last_update_to_xen = xtime.tv_sec;
+ }
+
+ /*
+ * If we have an externally synchronized Linux clock, then update CMOS
+ * clock accordingly every ~11 minutes. Set_rtc_mmss() has to be called
+ * as close as possible to 500 ms before the new second starts.
+ */
+ if ( (xtime.tv_sec > (last_update_to_rtc + 660)) &&
+ (xtime.tv_usec >= (500000 - ((unsigned) tick) / 2)) &&
+ (xtime.tv_usec <= (500000 + ((unsigned) tick) / 2)) )
+ {
+ if ( set_rtc_mmss(xtime.tv_sec) == 0 )
+ last_update_to_rtc = xtime.tv_sec;
+ else
+ last_update_to_rtc = xtime.tv_sec - 600;
+ }
+ }
+#endif
+}
+
+
+static void timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+{
+ write_lock(&xtime_lock);
+ do_timer_interrupt(irq, NULL, regs);
+ write_unlock(&xtime_lock);
+}
+
+static struct irqaction irq_timer = {
+ timer_interrupt,
+ SA_INTERRUPT,
+ 0,
+ "timer",
+ NULL,
+ NULL
+};
+
+
+/*
+ * This function works out when the the next timer function has to be
+ * executed (by looking at the timer list) and sets the Xen one-shot
+ * domain timer to the appropriate value. This is typically called in
+ * cpu_idle() before the domain blocks.
+ *
+ * The function returns a non-0 value on error conditions.
+ *
+ * It must be called with interrupts disabled.
+ */
+extern spinlock_t timerlist_lock;
+int set_timeout_timer(void)
+{
+ struct timer_list *timer;
+ u64 alarm = 0;
+ int ret = 0;
+
+ spin_lock(&timerlist_lock);
+
+ /*
+ * This is safe against long blocking (since calculations are not based on
+ * TSC deltas). It is also safe against warped system time since
+ * suspend-resume is cooperative and we would first get locked out. It is
+ * safe against normal updates of jiffies since interrupts are off.
+ */
+ if ( (timer = next_timer_event()) != NULL )
+ alarm = __jiffies_to_st(timer->expires);
+
+ /* Tasks on the timer task queue expect to be executed on the next tick. */
+ if ( TQ_ACTIVE(tq_timer) )
+ alarm = __jiffies_to_st(jiffies + 1);
+
+ /* Failure is pretty bad, but we'd best soldier on. */
+ if ( HYPERVISOR_set_timer_op(alarm) != 0 )
+ ret = -1;
+
+ spin_unlock(&timerlist_lock);
+
+ return ret;
+}
+
+
+/* Time debugging. */
+static void dbg_time_int(int irq, void *dev_id, struct pt_regs *ptregs)
+{
+ unsigned long flags, j;
+ u64 s_now, j_st;
+ struct timeval s_tv, tv;
+
+ struct timer_list *timer;
+ u64 t_st;
+
+ read_lock_irqsave(&xtime_lock, flags);
+ s_tv.tv_sec = shadow_tv.tv_sec;
+ s_tv.tv_usec = shadow_tv.tv_usec;
+ s_now = shadow_system_time;
+ read_unlock_irqrestore(&xtime_lock, flags);
+
+ do_gettimeofday(&tv);
+
+ j = jiffies;
+ j_st = __jiffies_to_st(j);
+
+ timer = next_timer_event();
+ t_st = __jiffies_to_st(timer->expires);
+
+ printk(KERN_ALERT "time: shadow_st=0x%X:%08X\n",
+ (u32)(s_now>>32), (u32)s_now);
+ printk(KERN_ALERT "time: wct=%lds %ldus shadow_wct=%lds %ldus\n",
+ tv.tv_sec, tv.tv_usec, s_tv.tv_sec, s_tv.tv_usec);
+ printk(KERN_ALERT "time: jiffies=%lu(0x%X:%08X) timeout=%lu(0x%X:%08X)\n",
+ jiffies,(u32)(j_st>>32), (u32)j_st,
+ timer->expires,(u32)(t_st>>32), (u32)t_st);
+ printk(KERN_ALERT "time: processed_system_time=0x%X:%08X\n",
+ (u32)(processed_system_time>>32), (u32)processed_system_time);
+
+#ifdef CONFIG_MAGIC_SYSRQ
+ handle_sysrq('t',NULL,NULL,NULL);
+#endif
+}
+
+static struct irqaction dbg_time = {
+ dbg_time_int,
+ SA_SHIRQ,
+ 0,
+ "timer_dbg",
+ &dbg_time_int,
+ NULL
+};
+
+void __init time_init(void)
+{
+ unsigned long long alarm;
+ u64 __cpu_khz, __cpu_ghz, cpu_freq, scale, scale2;
+ unsigned int cpu_ghz;
+
+ __cpu_khz = __cpu_ghz = cpu_freq = HYPERVISOR_shared_info->cpu_freq;
+ do_div(__cpu_khz, 1000UL);
+ cpu_khz = (u32)__cpu_khz;
+ do_div(__cpu_ghz, 1000000000UL);
+ cpu_ghz = (unsigned int)__cpu_ghz;
+
+ printk("Xen reported: %lu.%03lu MHz processor.\n",
+ cpu_khz / 1000, cpu_khz % 1000);
+
+ xtime.tv_sec = HYPERVISOR_shared_info->wc_sec;
+ xtime.tv_usec = HYPERVISOR_shared_info->wc_usec;
+ processed_system_time = shadow_system_time;
+
+ for ( rdtsc_bitshift = 0; cpu_ghz != 0; rdtsc_bitshift++, cpu_ghz >>= 1 )
+ continue;
+
+ scale = 1000000LL << (32 + rdtsc_bitshift);
+ do_div(scale, (u32)cpu_freq);
+
+ if ( (cpu_freq >> 32) != 0 )
+ {
+ scale2 = 1000000LL << rdtsc_bitshift;
+ do_div(scale2, (u32)(cpu_freq>>32));
+ scale += scale2;
+ }
+
+ st_scale_f = scale & 0xffffffff;
+ st_scale_i = scale >> 32;
+
+ __get_time_values_from_xen();
+ processed_system_time = shadow_system_time;
+
+ time_irq = bind_virq_to_irq(VIRQ_TIMER);
+ debug_irq = bind_virq_to_irq(VIRQ_DEBUG);
+
+ (void)setup_irq(time_irq, &irq_timer);
+ (void)setup_irq(debug_irq, &dbg_time);
+
+ rdtscll(alarm);
+}
+
+void time_suspend(void)
+{
+}
+
+void time_resume(void)
+{
+ unsigned long flags;
+ write_lock_irqsave(&xtime_lock, flags);
+ /* Get timebases for new environment. */
+ __get_time_values_from_xen();
+ /* Reset our own concept of passage of system time. */
+ processed_system_time = shadow_system_time;
+ /* Accept a warp in UTC (wall-clock) time. */
+ last_seen_tv.tv_sec = 0;
+ /* Make sure we resync UTC time with Xen on next timer interrupt. */
+ last_update_from_xen = 0;
+ write_unlock_irqrestore(&xtime_lock, flags);
+}
+
+/*
+ * /proc/sys/xen: This really belongs in another file. It can stay here for
+ * now however.
+ */
+static ctl_table xen_subtable[] = {
+ {1, "independent_wallclock", &independent_wallclock,
+ sizeof(independent_wallclock), 0644, NULL, proc_dointvec},
+ {0}
+};
+static ctl_table xen_table[] = {
+ {123, "xen", NULL, 0, 0555, xen_subtable},
+ {0}
+};
+static int __init xen_sysctl_init(void)
+{
+ (void)register_sysctl_table(xen_table, 0);
+ return 0;
+}
+__initcall(xen_sysctl_init);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/char/tty_io.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/char/tty_io.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,2988 @@
+/*
+ * linux/drivers/char/tty_io.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+/*
+ * 'tty_io.c' gives an orthogonal feeling to tty's, be they consoles
+ * or rs-channels. It also implements echoing, cooked mode etc.
+ *
+ * Kill-line thanks to John T Kohl, who also corrected VMIN = VTIME = 0.
+ *
+ * Modified by Theodore Ts'o, 9/14/92, to dynamically allocate the
+ * tty_struct and tty_queue structures. Previously there was an array
+ * of 256 tty_struct's which was statically allocated, and the
+ * tty_queue structures were allocated at boot time. Both are now
+ * dynamically allocated only when the tty is open.
+ *
+ * Also restructured routines so that there is more of a separation
+ * between the high-level tty routines (tty_io.c and tty_ioctl.c) and
+ * the low-level tty routines (serial.c, pty.c, console.c). This
+ * makes for cleaner and more compact code. -TYT, 9/17/92
+ *
+ * Modified by Fred N. van Kempen, 01/29/93, to add line disciplines
+ * which can be dynamically activated and de-activated by the line
+ * discipline handling modules (like SLIP).
+ *
+ * NOTE: pay no attention to the line discipline code (yet); its
+ * interface is still subject to change in this version...
+ * -- TYT, 1/31/92
+ *
+ * Added functionality to the OPOST tty handling. No delays, but all
+ * other bits should be there.
+ * -- Nick Holloway <alfie@xxxxxxxxxxxxxxxxx>, 27th May 1993.
+ *
+ * Rewrote canonical mode and added more termios flags.
+ * -- julian@xxxxxxxxxxxxxxxxxxxxxx (J. Cowley), 13Jan94
+ *
+ * Reorganized FASYNC support so mouse code can share it.
+ * -- ctm@xxxxxxxx, 9Sep95
+ *
+ * New TIOCLINUX variants added.
+ * -- mj@xxxxxxxxxxxxxxxxx, 19-Nov-95
+ *
+ * Restrict vt switching via ioctl()
+ * -- grif@xxxxxxxxxx, 5-Dec-95
+ *
+ * Move console and virtual terminal code to more appropriate files,
+ * implement CONFIG_VT and generalize console device interface.
+ * -- Marko Kohtala <Marko.Kohtala@xxxxxx>, March 97
+ *
+ * Rewrote init_dev and release_dev to eliminate races.
+ * -- Bill Hawes <whawes@xxxxxxxx>, June 97
+ *
+ * Added devfs support.
+ * -- C. Scott Ananian <cananian@xxxxxxxxxxxxxxxxxxxx>, 13-Jan-1998
+ *
+ * Added support for a Unix98-style ptmx device.
+ * -- C. Scott Ananian <cananian@xxxxxxxxxxxxxxxxxxxx>, 14-Jan-1998
+ *
+ * Reduced memory usage for older ARM systems
+ * -- Russell King <rmk@xxxxxxxxxxxxxxxx>
+ *
+ * Move do_SAK() into process context. Less stack use in devfs functions.
+ * alloc_tty_struct() always uses kmalloc() -- Andrew Morton
<andrewm@xxxxxxxxxx> 17Mar01
+ */
+
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/major.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/fcntl.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/tty.h>
+#include <linux/tty_driver.h>
+#include <linux/tty_flip.h>
+#include <linux/devpts_fs.h>
+#include <linux/file.h>
+#include <linux/console.h>
+#include <linux/timer.h>
+#include <linux/ctype.h>
+#include <linux/kd.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/poll.h>
+#include <linux/proc_fs.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/smp_lock.h>
+#include <linux/device.h>
+#include <linux/idr.h>
+#include <linux/wait.h>
+#include <linux/bitops.h>
+
+#include <asm/uaccess.h>
+#include <asm/system.h>
+
+#include <linux/kbd_kern.h>
+#include <linux/vt_kern.h>
+#include <linux/selection.h>
+#include <linux/devfs_fs_kernel.h>
+
+#include <linux/kmod.h>
+
+#undef TTY_DEBUG_HANGUP
+
+#define TTY_PARANOIA_CHECK 1
+#define CHECK_TTY_COUNT 1
+
+struct termios tty_std_termios = { /* for the benefit of tty drivers */
+ .c_iflag = ICRNL | IXON,
+ .c_oflag = OPOST | ONLCR,
+ .c_cflag = B38400 | CS8 | CREAD | HUPCL,
+ .c_lflag = ISIG | ICANON | ECHO | ECHOE | ECHOK |
+ ECHOCTL | ECHOKE | IEXTEN,
+ .c_cc = INIT_C_CC
+};
+
+EXPORT_SYMBOL(tty_std_termios);
+
+/* This list gets poked at by procfs and various bits of boot up code. This
+ could do with some rationalisation such as pulling the tty proc function
+ into this file */
+
+LIST_HEAD(tty_drivers); /* linked list of tty drivers */
+
+/* Semaphore to protect creating and releasing a tty. This is shared with
+ vt.c for deeply disgusting hack reasons */
+DECLARE_MUTEX(tty_sem);
+
+int console_use_vt = 1;
+
+#ifdef CONFIG_UNIX98_PTYS
+extern struct tty_driver *ptm_driver; /* Unix98 pty masters; for /dev/ptmx */
+extern int pty_limit; /* Config limit on Unix98 ptys */
+static DEFINE_IDR(allocated_ptys);
+static DECLARE_MUTEX(allocated_ptys_lock);
+static int ptmx_open(struct inode *, struct file *);
+#endif
+
+extern void disable_early_printk(void);
+
+static void initialize_tty_struct(struct tty_struct *tty);
+
+static ssize_t tty_read(struct file *, char __user *, size_t, loff_t *);
+static ssize_t tty_write(struct file *, const char __user *, size_t, loff_t *);
+ssize_t redirected_tty_write(struct file *, const char __user *, size_t,
loff_t *);
+static unsigned int tty_poll(struct file *, poll_table *);
+static int tty_open(struct inode *, struct file *);
+static int tty_release(struct inode *, struct file *);
+int tty_ioctl(struct inode * inode, struct file * file,
+ unsigned int cmd, unsigned long arg);
+static int tty_fasync(int fd, struct file * filp, int on);
+extern void rs_360_init(void);
+static void release_mem(struct tty_struct *tty, int idx);
+
+
+static struct tty_struct *alloc_tty_struct(void)
+{
+ struct tty_struct *tty;
+
+ tty = kmalloc(sizeof(struct tty_struct), GFP_KERNEL);
+ if (tty)
+ memset(tty, 0, sizeof(struct tty_struct));
+ return tty;
+}
+
+static inline void free_tty_struct(struct tty_struct *tty)
+{
+ kfree(tty->write_buf);
+ kfree(tty);
+}
+
+#define TTY_NUMBER(tty) ((tty)->index + (tty)->driver->name_base)
+
+char *tty_name(struct tty_struct *tty, char *buf)
+{
+ if (!tty) /* Hmm. NULL pointer. That's fun. */
+ strcpy(buf, "NULL tty");
+ else
+ strcpy(buf, tty->name);
+ return buf;
+}
+
+EXPORT_SYMBOL(tty_name);
+
+inline int tty_paranoia_check(struct tty_struct *tty, struct inode *inode,
+ const char *routine)
+{
+#ifdef TTY_PARANOIA_CHECK
+ if (!tty) {
+ printk(KERN_WARNING
+ "null TTY for (%d:%d) in %s\n",
+ imajor(inode), iminor(inode), routine);
+ return 1;
+ }
+ if (tty->magic != TTY_MAGIC) {
+ printk(KERN_WARNING
+ "bad magic number for tty struct (%d:%d) in %s\n",
+ imajor(inode), iminor(inode), routine);
+ return 1;
+ }
+#endif
+ return 0;
+}
+
+static int check_tty_count(struct tty_struct *tty, const char *routine)
+{
+#ifdef CHECK_TTY_COUNT
+ struct list_head *p;
+ int count = 0;
+
+ file_list_lock();
+ list_for_each(p, &tty->tty_files) {
+ count++;
+ }
+ file_list_unlock();
+ if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver->subtype == PTY_TYPE_SLAVE &&
+ tty->link && tty->link->count)
+ count++;
+ if (tty->count != count) {
+ printk(KERN_WARNING "Warning: dev (%s) tty->count(%d) "
+ "!= #fd's(%d) in %s\n",
+ tty->name, tty->count, count, routine);
+ return count;
+ }
+#endif
+ return 0;
+}
+
+/*
+ * This is probably overkill for real world processors but
+ * they are not on hot paths so a little discipline won't do
+ * any harm.
+ */
+
+static void tty_set_termios_ldisc(struct tty_struct *tty, int num)
+{
+ down(&tty->termios_sem);
+ tty->termios->c_line = num;
+ up(&tty->termios_sem);
+}
+
+/*
+ * This guards the refcounted line discipline lists. The lock
+ * must be taken with irqs off because there are hangup path
+ * callers who will do ldisc lookups and cannot sleep.
+ */
+
+static DEFINE_SPINLOCK(tty_ldisc_lock);
+static DECLARE_WAIT_QUEUE_HEAD(tty_ldisc_wait);
+static struct tty_ldisc tty_ldiscs[NR_LDISCS]; /* line disc dispatch table
*/
+
+int tty_register_ldisc(int disc, struct tty_ldisc *new_ldisc)
+{
+ unsigned long flags;
+ int ret = 0;
+
+ if (disc < N_TTY || disc >= NR_LDISCS)
+ return -EINVAL;
+
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ if (new_ldisc) {
+ tty_ldiscs[disc] = *new_ldisc;
+ tty_ldiscs[disc].num = disc;
+ tty_ldiscs[disc].flags |= LDISC_FLAG_DEFINED;
+ tty_ldiscs[disc].refcount = 0;
+ } else {
+ if(tty_ldiscs[disc].refcount)
+ ret = -EBUSY;
+ else
+ tty_ldiscs[disc].flags &= ~LDISC_FLAG_DEFINED;
+ }
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+
+ return ret;
+}
+
+EXPORT_SYMBOL(tty_register_ldisc);
+
+struct tty_ldisc *tty_ldisc_get(int disc)
+{
+ unsigned long flags;
+ struct tty_ldisc *ld;
+
+ if (disc < N_TTY || disc >= NR_LDISCS)
+ return NULL;
+
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+
+ ld = &tty_ldiscs[disc];
+ /* Check the entry is defined */
+ if(ld->flags & LDISC_FLAG_DEFINED)
+ {
+ /* If the module is being unloaded we can't use it */
+ if (!try_module_get(ld->owner))
+ ld = NULL;
+ else /* lock it */
+ ld->refcount++;
+ }
+ else
+ ld = NULL;
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+ return ld;
+}
+
+EXPORT_SYMBOL_GPL(tty_ldisc_get);
+
+void tty_ldisc_put(int disc)
+{
+ struct tty_ldisc *ld;
+ unsigned long flags;
+
+ if (disc < N_TTY || disc >= NR_LDISCS)
+ BUG();
+
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ ld = &tty_ldiscs[disc];
+ if(ld->refcount == 0)
+ BUG();
+ ld->refcount --;
+ module_put(ld->owner);
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+}
+
+EXPORT_SYMBOL_GPL(tty_ldisc_put);
+
+static void tty_ldisc_assign(struct tty_struct *tty, struct tty_ldisc *ld)
+{
+ tty->ldisc = *ld;
+ tty->ldisc.refcount = 0;
+}
+
+/**
+ * tty_ldisc_try - internal helper
+ * @tty: the tty
+ *
+ * Make a single attempt to grab and bump the refcount on
+ * the tty ldisc. Return 0 on failure or 1 on success. This is
+ * used to implement both the waiting and non waiting versions
+ * of tty_ldisc_ref
+ */
+
+static int tty_ldisc_try(struct tty_struct *tty)
+{
+ unsigned long flags;
+ struct tty_ldisc *ld;
+ int ret = 0;
+
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ ld = &tty->ldisc;
+ if(test_bit(TTY_LDISC, &tty->flags))
+ {
+ ld->refcount++;
+ ret = 1;
+ }
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+ return ret;
+}
+
+/**
+ * tty_ldisc_ref_wait - wait for the tty ldisc
+ * @tty: tty device
+ *
+ * Dereference the line discipline for the terminal and take a
+ * reference to it. If the line discipline is in flux then
+ * wait patiently until it changes.
+ *
+ * Note: Must not be called from an IRQ/timer context. The caller
+ * must also be careful not to hold other locks that will deadlock
+ * against a discipline change, such as an existing ldisc reference
+ * (which we check for)
+ */
+
+struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *tty)
+{
+ /* wait_event is a macro */
+ wait_event(tty_ldisc_wait, tty_ldisc_try(tty));
+ if(tty->ldisc.refcount == 0)
+ printk(KERN_ERR "tty_ldisc_ref_wait\n");
+ return &tty->ldisc;
+}
+
+EXPORT_SYMBOL_GPL(tty_ldisc_ref_wait);
+
+/**
+ * tty_ldisc_ref - get the tty ldisc
+ * @tty: tty device
+ *
+ * Dereference the line discipline for the terminal and take a
+ * reference to it. If the line discipline is in flux then
+ * return NULL. Can be called from IRQ and timer functions.
+ */
+
+struct tty_ldisc *tty_ldisc_ref(struct tty_struct *tty)
+{
+ if(tty_ldisc_try(tty))
+ return &tty->ldisc;
+ return NULL;
+}
+
+EXPORT_SYMBOL_GPL(tty_ldisc_ref);
+
+/**
+ * tty_ldisc_deref - free a tty ldisc reference
+ * @ld: reference to free up
+ *
+ * Undoes the effect of tty_ldisc_ref or tty_ldisc_ref_wait. May
+ * be called in IRQ context.
+ */
+
+void tty_ldisc_deref(struct tty_ldisc *ld)
+{
+ unsigned long flags;
+
+ if(ld == NULL)
+ BUG();
+
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ if(ld->refcount == 0)
+ printk(KERN_ERR "tty_ldisc_deref: no references.\n");
+ else
+ ld->refcount--;
+ if(ld->refcount == 0)
+ wake_up(&tty_ldisc_wait);
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+}
+
+EXPORT_SYMBOL_GPL(tty_ldisc_deref);
+
+/**
+ * tty_ldisc_enable - allow ldisc use
+ * @tty: terminal to activate ldisc on
+ *
+ * Set the TTY_LDISC flag when the line discipline can be called
+ * again. Do neccessary wakeups for existing sleepers.
+ *
+ * Note: nobody should set this bit except via this function. Clearing
+ * directly is allowed.
+ */
+
+static void tty_ldisc_enable(struct tty_struct *tty)
+{
+ set_bit(TTY_LDISC, &tty->flags);
+ wake_up(&tty_ldisc_wait);
+}
+
+/**
+ * tty_set_ldisc - set line discipline
+ * @tty: the terminal to set
+ * @ldisc: the line discipline
+ *
+ * Set the discipline of a tty line. Must be called from a process
+ * context.
+ */
+
+static int tty_set_ldisc(struct tty_struct *tty, int ldisc)
+{
+ int retval = 0;
+ struct tty_ldisc o_ldisc;
+ char buf[64];
+ int work;
+ unsigned long flags;
+ struct tty_ldisc *ld;
+
+ if ((ldisc < N_TTY) || (ldisc >= NR_LDISCS))
+ return -EINVAL;
+
+restart:
+
+ if (tty->ldisc.num == ldisc)
+ return 0; /* We are already in the desired discipline */
+
+ ld = tty_ldisc_get(ldisc);
+ /* Eduardo Blanco <ejbs@xxxxxxxxxxxx> */
+ /* Cyrus Durgin <cider@xxxxxxxxxxxxx> */
+ if (ld == NULL) {
+ request_module("tty-ldisc-%d", ldisc);
+ ld = tty_ldisc_get(ldisc);
+ }
+ if (ld == NULL)
+ return -EINVAL;
+
+ o_ldisc = tty->ldisc;
+
+ tty_wait_until_sent(tty, 0);
+
+ /*
+ * Make sure we don't change while someone holds a
+ * reference to the line discipline. The TTY_LDISC bit
+ * prevents anyone taking a reference once it is clear.
+ * We need the lock to avoid racing reference takers.
+ */
+
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ if(tty->ldisc.refcount)
+ {
+ /* Free the new ldisc we grabbed. Must drop the lock
+ first. */
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+ tty_ldisc_put(ldisc);
+ /*
+ * There are several reasons we may be busy, including
+ * random momentary I/O traffic. We must therefore
+ * retry. We could distinguish between blocking ops
+ * and retries if we made tty_ldisc_wait() smarter. That
+ * is up for discussion.
+ */
+ if(wait_event_interruptible(tty_ldisc_wait, tty->ldisc.refcount
== 0) < 0)
+ return -ERESTARTSYS;
+ goto restart;
+ }
+ clear_bit(TTY_LDISC, &tty->flags);
+ clear_bit(TTY_DONT_FLIP, &tty->flags);
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+
+ /*
+ * From this point on we know nobody has an ldisc
+ * usage reference, nor can they obtain one until
+ * we say so later on.
+ */
+
+ work = cancel_delayed_work(&tty->flip.work);
+ /*
+ * Wait for ->hangup_work and ->flip.work handlers to terminate
+ */
+
+ flush_scheduled_work();
+ /* Shutdown the current discipline. */
+ if (tty->ldisc.close)
+ (tty->ldisc.close)(tty);
+
+ /* Now set up the new line discipline. */
+ tty_ldisc_assign(tty, ld);
+ tty_set_termios_ldisc(tty, ldisc);
+ if (tty->ldisc.open)
+ retval = (tty->ldisc.open)(tty);
+ if (retval < 0) {
+ tty_ldisc_put(ldisc);
+ /* There is an outstanding reference here so this is safe */
+ tty_ldisc_assign(tty, tty_ldisc_get(o_ldisc.num));
+ tty_set_termios_ldisc(tty, tty->ldisc.num);
+ if (tty->ldisc.open && (tty->ldisc.open(tty) < 0)) {
+ tty_ldisc_put(o_ldisc.num);
+ /* This driver is always present */
+ tty_ldisc_assign(tty, tty_ldisc_get(N_TTY));
+ tty_set_termios_ldisc(tty, N_TTY);
+ if (tty->ldisc.open) {
+ int r = tty->ldisc.open(tty);
+
+ if (r < 0)
+ panic("Couldn't open N_TTY ldisc for "
+ "%s --- error %d.",
+ tty_name(tty, buf), r);
+ }
+ }
+ }
+ /* At this point we hold a reference to the new ldisc and a
+ a reference to the old ldisc. If we ended up flipping back
+ to the existing ldisc we have two references to it */
+
+ if (tty->ldisc.num != o_ldisc.num && tty->driver->set_ldisc)
+ tty->driver->set_ldisc(tty);
+
+ tty_ldisc_put(o_ldisc.num);
+
+ /*
+ * Allow ldisc referencing to occur as soon as the driver
+ * ldisc callback completes.
+ */
+
+ tty_ldisc_enable(tty);
+
+ /* Restart it in case no characters kick it off. Safe if
+ already running */
+ if(work)
+ schedule_delayed_work(&tty->flip.work, 1);
+ return retval;
+}
+
+/*
+ * This routine returns a tty driver structure, given a device number
+ */
+static struct tty_driver *get_tty_driver(dev_t device, int *index)
+{
+ struct tty_driver *p;
+
+ list_for_each_entry(p, &tty_drivers, tty_drivers) {
+ dev_t base = MKDEV(p->major, p->minor_start);
+ if (device < base || device >= base + p->num)
+ continue;
+ *index = device - base;
+ return p;
+ }
+ return NULL;
+}
+
+/*
+ * If we try to write to, or set the state of, a terminal and we're
+ * not in the foreground, send a SIGTTOU. If the signal is blocked or
+ * ignored, go ahead and perform the operation. (POSIX 7.2)
+ */
+int tty_check_change(struct tty_struct * tty)
+{
+ if (current->signal->tty != tty)
+ return 0;
+ if (tty->pgrp <= 0) {
+ printk(KERN_WARNING "tty_check_change: tty->pgrp <= 0!\n");
+ return 0;
+ }
+ if (process_group(current) == tty->pgrp)
+ return 0;
+ if (is_ignored(SIGTTOU))
+ return 0;
+ if (is_orphaned_pgrp(process_group(current)))
+ return -EIO;
+ (void) kill_pg(process_group(current), SIGTTOU, 1);
+ return -ERESTARTSYS;
+}
+
+EXPORT_SYMBOL(tty_check_change);
+
+static ssize_t hung_up_tty_read(struct file * file, char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ return 0;
+}
+
+static ssize_t hung_up_tty_write(struct file * file, const char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ return -EIO;
+}
+
+/* No kernel lock held - none needed ;) */
+static unsigned int hung_up_tty_poll(struct file * filp, poll_table * wait)
+{
+ return POLLIN | POLLOUT | POLLERR | POLLHUP | POLLRDNORM | POLLWRNORM;
+}
+
+static int hung_up_tty_ioctl(struct inode * inode, struct file * file,
+ unsigned int cmd, unsigned long arg)
+{
+ return cmd == TIOCSPGRP ? -ENOTTY : -EIO;
+}
+
+static struct file_operations tty_fops = {
+ .llseek = no_llseek,
+ .read = tty_read,
+ .write = tty_write,
+ .poll = tty_poll,
+ .ioctl = tty_ioctl,
+ .open = tty_open,
+ .release = tty_release,
+ .fasync = tty_fasync,
+};
+
+#ifdef CONFIG_UNIX98_PTYS
+static struct file_operations ptmx_fops = {
+ .llseek = no_llseek,
+ .read = tty_read,
+ .write = tty_write,
+ .poll = tty_poll,
+ .ioctl = tty_ioctl,
+ .open = ptmx_open,
+ .release = tty_release,
+ .fasync = tty_fasync,
+};
+#endif
+
+static struct file_operations console_fops = {
+ .llseek = no_llseek,
+ .read = tty_read,
+ .write = redirected_tty_write,
+ .poll = tty_poll,
+ .ioctl = tty_ioctl,
+ .open = tty_open,
+ .release = tty_release,
+ .fasync = tty_fasync,
+};
+
+static struct file_operations hung_up_tty_fops = {
+ .llseek = no_llseek,
+ .read = hung_up_tty_read,
+ .write = hung_up_tty_write,
+ .poll = hung_up_tty_poll,
+ .ioctl = hung_up_tty_ioctl,
+ .release = tty_release,
+};
+
+static DEFINE_SPINLOCK(redirect_lock);
+static struct file *redirect;
+
+/**
+ * tty_wakeup - request more data
+ * @tty: terminal
+ *
+ * Internal and external helper for wakeups of tty. This function
+ * informs the line discipline if present that the driver is ready
+ * to receive more output data.
+ */
+
+void tty_wakeup(struct tty_struct *tty)
+{
+ struct tty_ldisc *ld;
+
+ if (test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) {
+ ld = tty_ldisc_ref(tty);
+ if(ld) {
+ if(ld->write_wakeup)
+ ld->write_wakeup(tty);
+ tty_ldisc_deref(ld);
+ }
+ }
+ wake_up_interruptible(&tty->write_wait);
+}
+
+EXPORT_SYMBOL_GPL(tty_wakeup);
+
+/**
+ * tty_ldisc_flush - flush line discipline queue
+ * @tty: tty
+ *
+ * Flush the line discipline queue (if any) for this tty. If there
+ * is no line discipline active this is a no-op.
+ */
+
+void tty_ldisc_flush(struct tty_struct *tty)
+{
+ struct tty_ldisc *ld = tty_ldisc_ref(tty);
+ if(ld) {
+ if(ld->flush_buffer)
+ ld->flush_buffer(tty);
+ tty_ldisc_deref(ld);
+ }
+}
+
+EXPORT_SYMBOL_GPL(tty_ldisc_flush);
+
+/*
+ * This can be called by the "eventd" kernel thread. That is process
synchronous,
+ * but doesn't hold any locks, so we need to make sure we have the appropriate
+ * locks for what we're doing..
+ */
+static void do_tty_hangup(void *data)
+{
+ struct tty_struct *tty = (struct tty_struct *) data;
+ struct file * cons_filp = NULL;
+ struct file *filp, *f = NULL;
+ struct task_struct *p;
+ struct tty_ldisc *ld;
+ int closecount = 0, n;
+
+ if (!tty)
+ return;
+
+ /* inuse_filps is protected by the single kernel lock */
+ lock_kernel();
+
+ spin_lock(&redirect_lock);
+ if (redirect && redirect->private_data == tty) {
+ f = redirect;
+ redirect = NULL;
+ }
+ spin_unlock(&redirect_lock);
+
+ check_tty_count(tty, "do_tty_hangup");
+ file_list_lock();
+ /* This breaks for file handles being sent over AF_UNIX sockets ? */
+ list_for_each_entry(filp, &tty->tty_files, f_list) {
+ if (filp->f_op->write == redirected_tty_write)
+ cons_filp = filp;
+ if (filp->f_op->write != tty_write)
+ continue;
+ closecount++;
+ tty_fasync(-1, filp, 0); /* can't block */
+ filp->f_op = &hung_up_tty_fops;
+ }
+ file_list_unlock();
+
+ /* FIXME! What are the locking issues here? This may me overdoing
things..
+ * this question is especially important now that we've removed the
irqlock. */
+
+ ld = tty_ldisc_ref(tty);
+ if(ld != NULL) /* We may have no line discipline at this point */
+ {
+ if (ld->flush_buffer)
+ ld->flush_buffer(tty);
+ if (tty->driver->flush_buffer)
+ tty->driver->flush_buffer(tty);
+ if ((test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) &&
+ ld->write_wakeup)
+ ld->write_wakeup(tty);
+ if (ld->hangup)
+ ld->hangup(tty);
+ }
+
+ /* FIXME: Once we trust the LDISC code better we can wait here for
+ ldisc completion and fix the driver call race */
+
+ wake_up_interruptible(&tty->write_wait);
+ wake_up_interruptible(&tty->read_wait);
+
+ /*
+ * Shutdown the current line discipline, and reset it to
+ * N_TTY.
+ */
+ if (tty->driver->flags & TTY_DRIVER_RESET_TERMIOS)
+ {
+ down(&tty->termios_sem);
+ *tty->termios = tty->driver->init_termios;
+ up(&tty->termios_sem);
+ }
+
+ /* Defer ldisc switch */
+ /* tty_deferred_ldisc_switch(N_TTY);
+
+ This should get done automatically when the port closes and
+ tty_release is called */
+
+ read_lock(&tasklist_lock);
+ if (tty->session > 0) {
+ do_each_task_pid(tty->session, PIDTYPE_SID, p) {
+ if (p->signal->tty == tty)
+ p->signal->tty = NULL;
+ if (!p->signal->leader)
+ continue;
+ send_group_sig_info(SIGHUP, SEND_SIG_PRIV, p);
+ send_group_sig_info(SIGCONT, SEND_SIG_PRIV, p);
+ if (tty->pgrp > 0)
+ p->signal->tty_old_pgrp = tty->pgrp;
+ } while_each_task_pid(tty->session, PIDTYPE_SID, p);
+ }
+ read_unlock(&tasklist_lock);
+
+ tty->flags = 0;
+ tty->session = 0;
+ tty->pgrp = -1;
+ tty->ctrl_status = 0;
+ /*
+ * If one of the devices matches a console pointer, we
+ * cannot just call hangup() because that will cause
+ * tty->count and state->count to go out of sync.
+ * So we just call close() the right number of times.
+ */
+ if (cons_filp) {
+ if (tty->driver->close)
+ for (n = 0; n < closecount; n++)
+ tty->driver->close(tty, cons_filp);
+ } else if (tty->driver->hangup)
+ (tty->driver->hangup)(tty);
+
+ /* We don't want to have driver/ldisc interactions beyond
+ the ones we did here. The driver layer expects no
+ calls after ->hangup() from the ldisc side. However we
+ can't yet guarantee all that */
+
+ set_bit(TTY_HUPPED, &tty->flags);
+ if (ld) {
+ tty_ldisc_enable(tty);
+ tty_ldisc_deref(ld);
+ }
+ unlock_kernel();
+ if (f)
+ fput(f);
+}
+
+void tty_hangup(struct tty_struct * tty)
+{
+#ifdef TTY_DEBUG_HANGUP
+ char buf[64];
+
+ printk(KERN_DEBUG "%s hangup...\n", tty_name(tty, buf));
+#endif
+ schedule_work(&tty->hangup_work);
+}
+
+EXPORT_SYMBOL(tty_hangup);
+
+void tty_vhangup(struct tty_struct * tty)
+{
+#ifdef TTY_DEBUG_HANGUP
+ char buf[64];
+
+ printk(KERN_DEBUG "%s vhangup...\n", tty_name(tty, buf));
+#endif
+ do_tty_hangup((void *) tty);
+}
+EXPORT_SYMBOL(tty_vhangup);
+
+int tty_hung_up_p(struct file * filp)
+{
+ return (filp->f_op == &hung_up_tty_fops);
+}
+
+EXPORT_SYMBOL(tty_hung_up_p);
+
+/*
+ * This function is typically called only by the session leader, when
+ * it wants to disassociate itself from its controlling tty.
+ *
+ * It performs the following functions:
+ * (1) Sends a SIGHUP and SIGCONT to the foreground process group
+ * (2) Clears the tty from being controlling the session
+ * (3) Clears the controlling tty for all processes in the
+ * session group.
+ *
+ * The argument on_exit is set to 1 if called when a process is
+ * exiting; it is 0 if called by the ioctl TIOCNOTTY.
+ */
+void disassociate_ctty(int on_exit)
+{
+ struct tty_struct *tty;
+ struct task_struct *p;
+ int tty_pgrp = -1;
+
+ lock_kernel();
+
+ down(&tty_sem);
+ tty = current->signal->tty;
+ if (tty) {
+ tty_pgrp = tty->pgrp;
+ up(&tty_sem);
+ if (on_exit && tty->driver->type != TTY_DRIVER_TYPE_PTY)
+ tty_vhangup(tty);
+ } else {
+ if (current->signal->tty_old_pgrp) {
+ kill_pg(current->signal->tty_old_pgrp, SIGHUP, on_exit);
+ kill_pg(current->signal->tty_old_pgrp, SIGCONT,
on_exit);
+ }
+ up(&tty_sem);
+ unlock_kernel();
+ return;
+ }
+ if (tty_pgrp > 0) {
+ kill_pg(tty_pgrp, SIGHUP, on_exit);
+ if (!on_exit)
+ kill_pg(tty_pgrp, SIGCONT, on_exit);
+ }
+
+ /* Must lock changes to tty_old_pgrp */
+ down(&tty_sem);
+ current->signal->tty_old_pgrp = 0;
+ tty->session = 0;
+ tty->pgrp = -1;
+
+ /* Now clear signal->tty under the lock */
+ read_lock(&tasklist_lock);
+ do_each_task_pid(current->signal->session, PIDTYPE_SID, p) {
+ p->signal->tty = NULL;
+ } while_each_task_pid(current->signal->session, PIDTYPE_SID, p);
+ read_unlock(&tasklist_lock);
+ up(&tty_sem);
+ unlock_kernel();
+}
+
+void stop_tty(struct tty_struct *tty)
+{
+ if (tty->stopped)
+ return;
+ tty->stopped = 1;
+ if (tty->link && tty->link->packet) {
+ tty->ctrl_status &= ~TIOCPKT_START;
+ tty->ctrl_status |= TIOCPKT_STOP;
+ wake_up_interruptible(&tty->link->read_wait);
+ }
+ if (tty->driver->stop)
+ (tty->driver->stop)(tty);
+}
+
+EXPORT_SYMBOL(stop_tty);
+
+void start_tty(struct tty_struct *tty)
+{
+ if (!tty->stopped || tty->flow_stopped)
+ return;
+ tty->stopped = 0;
+ if (tty->link && tty->link->packet) {
+ tty->ctrl_status &= ~TIOCPKT_STOP;
+ tty->ctrl_status |= TIOCPKT_START;
+ wake_up_interruptible(&tty->link->read_wait);
+ }
+ if (tty->driver->start)
+ (tty->driver->start)(tty);
+
+ /* If we have a running line discipline it may need kicking */
+ tty_wakeup(tty);
+ wake_up_interruptible(&tty->write_wait);
+}
+
+EXPORT_SYMBOL(start_tty);
+
+static ssize_t tty_read(struct file * file, char __user * buf, size_t count,
+ loff_t *ppos)
+{
+ int i;
+ struct tty_struct * tty;
+ struct inode *inode;
+ struct tty_ldisc *ld;
+
+ tty = (struct tty_struct *)file->private_data;
+ inode = file->f_dentry->d_inode;
+ if (tty_paranoia_check(tty, inode, "tty_read"))
+ return -EIO;
+ if (!tty || (test_bit(TTY_IO_ERROR, &tty->flags)))
+ return -EIO;
+
+ /* We want to wait for the line discipline to sort out in this
+ situation */
+ ld = tty_ldisc_ref_wait(tty);
+ lock_kernel();
+ if (ld->read)
+ i = (ld->read)(tty,file,buf,count);
+ else
+ i = -EIO;
+ tty_ldisc_deref(ld);
+ unlock_kernel();
+ if (i > 0)
+ inode->i_atime = current_fs_time(inode->i_sb);
+ return i;
+}
+
+/*
+ * Split writes up in sane blocksizes to avoid
+ * denial-of-service type attacks
+ */
+static inline ssize_t do_tty_write(
+ ssize_t (*write)(struct tty_struct *, struct file *, const unsigned
char *, size_t),
+ struct tty_struct *tty,
+ struct file *file,
+ const char __user *buf,
+ size_t count)
+{
+ ssize_t ret = 0, written = 0;
+ unsigned int chunk;
+
+ if (down_interruptible(&tty->atomic_write)) {
+ return -ERESTARTSYS;
+ }
+
+ /*
+ * We chunk up writes into a temporary buffer. This
+ * simplifies low-level drivers immensely, since they
+ * don't have locking issues and user mode accesses.
+ *
+ * But if TTY_NO_WRITE_SPLIT is set, we should use a
+ * big chunk-size..
+ *
+ * The default chunk-size is 2kB, because the NTTY
+ * layer has problems with bigger chunks. It will
+ * claim to be able to handle more characters than
+ * it actually does.
+ */
+ chunk = 2048;
+ if (test_bit(TTY_NO_WRITE_SPLIT, &tty->flags))
+ chunk = 65536;
+ if (count < chunk)
+ chunk = count;
+
+ /* write_buf/write_cnt is protected by the atomic_write semaphore */
+ if (tty->write_cnt < chunk) {
+ unsigned char *buf;
+
+ if (chunk < 1024)
+ chunk = 1024;
+
+ buf = kmalloc(chunk, GFP_KERNEL);
+ if (!buf) {
+ up(&tty->atomic_write);
+ return -ENOMEM;
+ }
+ kfree(tty->write_buf);
+ tty->write_cnt = chunk;
+ tty->write_buf = buf;
+ }
+
+ /* Do the write .. */
+ for (;;) {
+ size_t size = count;
+ if (size > chunk)
+ size = chunk;
+ ret = -EFAULT;
+ if (copy_from_user(tty->write_buf, buf, size))
+ break;
+ lock_kernel();
+ ret = write(tty, file, tty->write_buf, size);
+ unlock_kernel();
+ if (ret <= 0)
+ break;
+ written += ret;
+ buf += ret;
+ count -= ret;
+ if (!count)
+ break;
+ ret = -ERESTARTSYS;
+ if (signal_pending(current))
+ break;
+ cond_resched();
+ }
+ if (written) {
+ struct inode *inode = file->f_dentry->d_inode;
+ inode->i_mtime = current_fs_time(inode->i_sb);
+ ret = written;
+ }
+ up(&tty->atomic_write);
+ return ret;
+}
+
+
+static ssize_t tty_write(struct file * file, const char __user * buf, size_t
count,
+ loff_t *ppos)
+{
+ struct tty_struct * tty;
+ struct inode *inode = file->f_dentry->d_inode;
+ ssize_t ret;
+ struct tty_ldisc *ld;
+
+ tty = (struct tty_struct *)file->private_data;
+ if (tty_paranoia_check(tty, inode, "tty_write"))
+ return -EIO;
+ if (!tty || !tty->driver->write || (test_bit(TTY_IO_ERROR,
&tty->flags)))
+ return -EIO;
+
+ ld = tty_ldisc_ref_wait(tty);
+ if (!ld->write)
+ ret = -EIO;
+ else
+ ret = do_tty_write(ld->write, tty, file, buf, count);
+ tty_ldisc_deref(ld);
+ return ret;
+}
+
+ssize_t redirected_tty_write(struct file * file, const char __user * buf,
size_t count,
+ loff_t *ppos)
+{
+ struct file *p = NULL;
+
+ spin_lock(&redirect_lock);
+ if (redirect) {
+ get_file(redirect);
+ p = redirect;
+ }
+ spin_unlock(&redirect_lock);
+
+ if (p) {
+ ssize_t res;
+ res = vfs_write(p, buf, count, &p->f_pos);
+ fput(p);
+ return res;
+ }
+
+ return tty_write(file, buf, count, ppos);
+}
+
+static char ptychar[] = "pqrstuvwxyzabcde";
+
+static inline void pty_line_name(struct tty_driver *driver, int index, char *p)
+{
+ int i = index + driver->name_base;
+ /* ->name is initialized to "ttyp", but "tty" is expected */
+ sprintf(p, "%s%c%x",
+ driver->subtype == PTY_TYPE_SLAVE ? "tty" :
driver->name,
+ ptychar[i >> 4 & 0xf], i & 0xf);
+}
+
+static inline void tty_line_name(struct tty_driver *driver, int index, char *p)
+{
+ sprintf(p, "%s%d", driver->name, index + driver->name_base);
+}
+
+/*
+ * WSH 06/09/97: Rewritten to remove races and properly clean up after a
+ * failed open. The new code protects the open with a semaphore, so it's
+ * really quite straightforward. The semaphore locking can probably be
+ * relaxed for the (most common) case of reopening a tty.
+ */
+static int init_dev(struct tty_driver *driver, int idx,
+ struct tty_struct **ret_tty)
+{
+ struct tty_struct *tty, *o_tty;
+ struct termios *tp, **tp_loc, *o_tp, **o_tp_loc;
+ struct termios *ltp, **ltp_loc, *o_ltp, **o_ltp_loc;
+ int retval=0;
+
+ /* check whether we're reopening an existing tty */
+ if (driver->flags & TTY_DRIVER_DEVPTS_MEM) {
+ tty = devpts_get_tty(idx);
+ if (tty && driver->subtype == PTY_TYPE_MASTER)
+ tty = tty->link;
+ } else {
+ tty = driver->ttys[idx];
+ }
+ if (tty) goto fast_track;
+
+ /*
+ * First time open is complex, especially for PTY devices.
+ * This code guarantees that either everything succeeds and the
+ * TTY is ready for operation, or else the table slots are vacated
+ * and the allocated memory released. (Except that the termios
+ * and locked termios may be retained.)
+ */
+
+ if (!try_module_get(driver->owner)) {
+ retval = -ENODEV;
+ goto end_init;
+ }
+
+ o_tty = NULL;
+ tp = o_tp = NULL;
+ ltp = o_ltp = NULL;
+
+ tty = alloc_tty_struct();
+ if(!tty)
+ goto fail_no_mem;
+ initialize_tty_struct(tty);
+ tty->driver = driver;
+ tty->index = idx;
+ tty_line_name(driver, idx, tty->name);
+
+ if (driver->flags & TTY_DRIVER_DEVPTS_MEM) {
+ tp_loc = &tty->termios;
+ ltp_loc = &tty->termios_locked;
+ } else {
+ tp_loc = &driver->termios[idx];
+ ltp_loc = &driver->termios_locked[idx];
+ }
+
+ if (!*tp_loc) {
+ tp = (struct termios *) kmalloc(sizeof(struct termios),
+ GFP_KERNEL);
+ if (!tp)
+ goto free_mem_out;
+ *tp = driver->init_termios;
+ }
+
+ if (!*ltp_loc) {
+ ltp = (struct termios *) kmalloc(sizeof(struct termios),
+ GFP_KERNEL);
+ if (!ltp)
+ goto free_mem_out;
+ memset(ltp, 0, sizeof(struct termios));
+ }
+
+ if (driver->type == TTY_DRIVER_TYPE_PTY) {
+ o_tty = alloc_tty_struct();
+ if (!o_tty)
+ goto free_mem_out;
+ initialize_tty_struct(o_tty);
+ o_tty->driver = driver->other;
+ o_tty->index = idx;
+ tty_line_name(driver->other, idx, o_tty->name);
+
+ if (driver->flags & TTY_DRIVER_DEVPTS_MEM) {
+ o_tp_loc = &o_tty->termios;
+ o_ltp_loc = &o_tty->termios_locked;
+ } else {
+ o_tp_loc = &driver->other->termios[idx];
+ o_ltp_loc = &driver->other->termios_locked[idx];
+ }
+
+ if (!*o_tp_loc) {
+ o_tp = (struct termios *)
+ kmalloc(sizeof(struct termios), GFP_KERNEL);
+ if (!o_tp)
+ goto free_mem_out;
+ *o_tp = driver->other->init_termios;
+ }
+
+ if (!*o_ltp_loc) {
+ o_ltp = (struct termios *)
+ kmalloc(sizeof(struct termios), GFP_KERNEL);
+ if (!o_ltp)
+ goto free_mem_out;
+ memset(o_ltp, 0, sizeof(struct termios));
+ }
+
+ /*
+ * Everything allocated ... set up the o_tty structure.
+ */
+ if (!(driver->other->flags & TTY_DRIVER_DEVPTS_MEM)) {
+ driver->other->ttys[idx] = o_tty;
+ }
+ if (!*o_tp_loc)
+ *o_tp_loc = o_tp;
+ if (!*o_ltp_loc)
+ *o_ltp_loc = o_ltp;
+ o_tty->termios = *o_tp_loc;
+ o_tty->termios_locked = *o_ltp_loc;
+ driver->other->refcount++;
+ if (driver->subtype == PTY_TYPE_MASTER)
+ o_tty->count++;
+
+ /* Establish the links in both directions */
+ tty->link = o_tty;
+ o_tty->link = tty;
+ }
+
+ /*
+ * All structures have been allocated, so now we install them.
+ * Failures after this point use release_mem to clean up, so
+ * there's no need to null out the local pointers.
+ */
+ if (!(driver->flags & TTY_DRIVER_DEVPTS_MEM)) {
+ driver->ttys[idx] = tty;
+ }
+
+ if (!*tp_loc)
+ *tp_loc = tp;
+ if (!*ltp_loc)
+ *ltp_loc = ltp;
+ tty->termios = *tp_loc;
+ tty->termios_locked = *ltp_loc;
+ driver->refcount++;
+ tty->count++;
+
+ /*
+ * Structures all installed ... call the ldisc open routines.
+ * If we fail here just call release_mem to clean up. No need
+ * to decrement the use counts, as release_mem doesn't care.
+ */
+
+ if (tty->ldisc.open) {
+ retval = (tty->ldisc.open)(tty);
+ if (retval)
+ goto release_mem_out;
+ }
+ if (o_tty && o_tty->ldisc.open) {
+ retval = (o_tty->ldisc.open)(o_tty);
+ if (retval) {
+ if (tty->ldisc.close)
+ (tty->ldisc.close)(tty);
+ goto release_mem_out;
+ }
+ tty_ldisc_enable(o_tty);
+ }
+ tty_ldisc_enable(tty);
+ goto success;
+
+ /*
+ * This fast open can be used if the tty is already open.
+ * No memory is allocated, and the only failures are from
+ * attempting to open a closing tty or attempting multiple
+ * opens on a pty master.
+ */
+fast_track:
+ if (test_bit(TTY_CLOSING, &tty->flags)) {
+ retval = -EIO;
+ goto end_init;
+ }
+ if (driver->type == TTY_DRIVER_TYPE_PTY &&
+ driver->subtype == PTY_TYPE_MASTER) {
+ /*
+ * special case for PTY masters: only one open permitted,
+ * and the slave side open count is incremented as well.
+ */
+ if (tty->count) {
+ retval = -EIO;
+ goto end_init;
+ }
+ tty->link->count++;
+ }
+ tty->count++;
+ tty->driver = driver; /* N.B. why do this every time?? */
+
+ /* FIXME */
+ if(!test_bit(TTY_LDISC, &tty->flags))
+ printk(KERN_ERR "init_dev but no ldisc\n");
+success:
+ *ret_tty = tty;
+
+ /* All paths come through here to release the semaphore */
+end_init:
+ return retval;
+
+ /* Release locally allocated memory ... nothing placed in slots */
+free_mem_out:
+ if (o_tp)
+ kfree(o_tp);
+ if (o_tty)
+ free_tty_struct(o_tty);
+ if (ltp)
+ kfree(ltp);
+ if (tp)
+ kfree(tp);
+ free_tty_struct(tty);
+
+fail_no_mem:
+ module_put(driver->owner);
+ retval = -ENOMEM;
+ goto end_init;
+
+ /* call the tty release_mem routine to clean out this slot */
+release_mem_out:
+ printk(KERN_INFO "init_dev: ldisc open failed, "
+ "clearing slot %d\n", idx);
+ release_mem(tty, idx);
+ goto end_init;
+}
+
+/*
+ * Releases memory associated with a tty structure, and clears out the
+ * driver table slots.
+ */
+static void release_mem(struct tty_struct *tty, int idx)
+{
+ struct tty_struct *o_tty;
+ struct termios *tp;
+ int devpts = tty->driver->flags & TTY_DRIVER_DEVPTS_MEM;
+
+ if ((o_tty = tty->link) != NULL) {
+ if (!devpts)
+ o_tty->driver->ttys[idx] = NULL;
+ if (o_tty->driver->flags & TTY_DRIVER_RESET_TERMIOS) {
+ tp = o_tty->termios;
+ if (!devpts)
+ o_tty->driver->termios[idx] = NULL;
+ kfree(tp);
+
+ tp = o_tty->termios_locked;
+ if (!devpts)
+ o_tty->driver->termios_locked[idx] = NULL;
+ kfree(tp);
+ }
+ o_tty->magic = 0;
+ o_tty->driver->refcount--;
+ file_list_lock();
+ list_del_init(&o_tty->tty_files);
+ file_list_unlock();
+ free_tty_struct(o_tty);
+ }
+
+ if (!devpts)
+ tty->driver->ttys[idx] = NULL;
+ if (tty->driver->flags & TTY_DRIVER_RESET_TERMIOS) {
+ tp = tty->termios;
+ if (!devpts)
+ tty->driver->termios[idx] = NULL;
+ kfree(tp);
+
+ tp = tty->termios_locked;
+ if (!devpts)
+ tty->driver->termios_locked[idx] = NULL;
+ kfree(tp);
+ }
+
+ tty->magic = 0;
+ tty->driver->refcount--;
+ file_list_lock();
+ list_del_init(&tty->tty_files);
+ file_list_unlock();
+ module_put(tty->driver->owner);
+ free_tty_struct(tty);
+}
+
+/*
+ * Even releasing the tty structures is a tricky business.. We have
+ * to be very careful that the structures are all released at the
+ * same time, as interrupts might otherwise get the wrong pointers.
+ *
+ * WSH 09/09/97: rewritten to avoid some nasty race conditions that could
+ * lead to double frees or releasing memory still in use.
+ */
+static void release_dev(struct file * filp)
+{
+ struct tty_struct *tty, *o_tty;
+ int pty_master, tty_closing, o_tty_closing, do_sleep;
+ int devpts_master, devpts;
+ int idx;
+ char buf[64];
+ unsigned long flags;
+
+ tty = (struct tty_struct *)filp->private_data;
+ if (tty_paranoia_check(tty, filp->f_dentry->d_inode, "release_dev"))
+ return;
+
+ check_tty_count(tty, "release_dev");
+
+ tty_fasync(-1, filp, 0);
+
+ idx = tty->index;
+ pty_master = (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver->subtype == PTY_TYPE_MASTER);
+ devpts = (tty->driver->flags & TTY_DRIVER_DEVPTS_MEM) != 0;
+ devpts_master = pty_master && devpts;
+ o_tty = tty->link;
+
+#ifdef TTY_PARANOIA_CHECK
+ if (idx < 0 || idx >= tty->driver->num) {
+ printk(KERN_DEBUG "release_dev: bad idx when trying to "
+ "free (%s)\n", tty->name);
+ return;
+ }
+ if (!(tty->driver->flags & TTY_DRIVER_DEVPTS_MEM)) {
+ if (tty != tty->driver->ttys[idx]) {
+ printk(KERN_DEBUG "release_dev: driver.table[%d] not
tty "
+ "for (%s)\n", idx, tty->name);
+ return;
+ }
+ if (tty->termios != tty->driver->termios[idx]) {
+ printk(KERN_DEBUG "release_dev: driver.termios[%d] not
termios "
+ "for (%s)\n",
+ idx, tty->name);
+ return;
+ }
+ if (tty->termios_locked != tty->driver->termios_locked[idx]) {
+ printk(KERN_DEBUG "release_dev:
driver.termios_locked[%d] not "
+ "termios_locked for (%s)\n",
+ idx, tty->name);
+ return;
+ }
+ }
+#endif
+
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "release_dev of %s (tty count=%d)...",
+ tty_name(tty, buf), tty->count);
+#endif
+
+#ifdef TTY_PARANOIA_CHECK
+ if (tty->driver->other &&
+ !(tty->driver->flags & TTY_DRIVER_DEVPTS_MEM)) {
+ if (o_tty != tty->driver->other->ttys[idx]) {
+ printk(KERN_DEBUG "release_dev: other->table[%d] "
+ "not o_tty for (%s)\n",
+ idx, tty->name);
+ return;
+ }
+ if (o_tty->termios != tty->driver->other->termios[idx]) {
+ printk(KERN_DEBUG "release_dev: other->termios[%d] "
+ "not o_termios for (%s)\n",
+ idx, tty->name);
+ return;
+ }
+ if (o_tty->termios_locked !=
+ tty->driver->other->termios_locked[idx]) {
+ printk(KERN_DEBUG "release_dev: other->termios_locked["
+ "%d] not o_termios_locked for (%s)\n",
+ idx, tty->name);
+ return;
+ }
+ if (o_tty->link != tty) {
+ printk(KERN_DEBUG "release_dev: bad pty pointers\n");
+ return;
+ }
+ }
+#endif
+ if (tty->driver->close)
+ tty->driver->close(tty, filp);
+
+ /*
+ * Sanity check: if tty->count is going to zero, there shouldn't be
+ * any waiters on tty->read_wait or tty->write_wait. We test the
+ * wait queues and kick everyone out _before_ actually starting to
+ * close. This ensures that we won't block while releasing the tty
+ * structure.
+ *
+ * The test for the o_tty closing is necessary, since the master and
+ * slave sides may close in any order. If the slave side closes out
+ * first, its count will be one, since the master side holds an open.
+ * Thus this test wouldn't be triggered at the time the slave closes,
+ * so we do it now.
+ *
+ * Note that it's possible for the tty to be opened again while we're
+ * flushing out waiters. By recalculating the closing flags before
+ * each iteration we avoid any problems.
+ */
+ while (1) {
+ /* Guard against races with tty->count changes elsewhere and
+ opens on /dev/tty */
+
+ down(&tty_sem);
+ tty_closing = tty->count <= 1;
+ o_tty_closing = o_tty &&
+ (o_tty->count <= (pty_master ? 1 : 0));
+ up(&tty_sem);
+ do_sleep = 0;
+
+ if (tty_closing) {
+ if (waitqueue_active(&tty->read_wait)) {
+ wake_up(&tty->read_wait);
+ do_sleep++;
+ }
+ if (waitqueue_active(&tty->write_wait)) {
+ wake_up(&tty->write_wait);
+ do_sleep++;
+ }
+ }
+ if (o_tty_closing) {
+ if (waitqueue_active(&o_tty->read_wait)) {
+ wake_up(&o_tty->read_wait);
+ do_sleep++;
+ }
+ if (waitqueue_active(&o_tty->write_wait)) {
+ wake_up(&o_tty->write_wait);
+ do_sleep++;
+ }
+ }
+ if (!do_sleep)
+ break;
+
+ printk(KERN_WARNING "release_dev: %s: read/write wait queue "
+ "active!\n", tty_name(tty, buf));
+ schedule();
+ }
+
+ /*
+ * The closing flags are now consistent with the open counts on
+ * both sides, and we've completed the last operation that could
+ * block, so it's safe to proceed with closing.
+ */
+
+ down(&tty_sem);
+ if (pty_master) {
+ if (--o_tty->count < 0) {
+ printk(KERN_WARNING "release_dev: bad pty slave count "
+ "(%d) for %s\n",
+ o_tty->count, tty_name(o_tty, buf));
+ o_tty->count = 0;
+ }
+ }
+ if (--tty->count < 0) {
+ printk(KERN_WARNING "release_dev: bad tty->count (%d) for %s\n",
+ tty->count, tty_name(tty, buf));
+ tty->count = 0;
+ }
+ up(&tty_sem);
+
+ /*
+ * We've decremented tty->count, so we need to remove this file
+ * descriptor off the tty->tty_files list; this serves two
+ * purposes:
+ * - check_tty_count sees the correct number of file descriptors
+ * associated with this tty.
+ * - do_tty_hangup no longer sees this file descriptor as
+ * something that needs to be handled for hangups.
+ */
+ file_kill(filp);
+ filp->private_data = NULL;
+
+ /*
+ * Perform some housekeeping before deciding whether to return.
+ *
+ * Set the TTY_CLOSING flag if this was the last open. In the
+ * case of a pty we may have to wait around for the other side
+ * to close, and TTY_CLOSING makes sure we can't be reopened.
+ */
+ if(tty_closing)
+ set_bit(TTY_CLOSING, &tty->flags);
+ if(o_tty_closing)
+ set_bit(TTY_CLOSING, &o_tty->flags);
+
+ /*
+ * If _either_ side is closing, make sure there aren't any
+ * processes that still think tty or o_tty is their controlling
+ * tty.
+ */
+ if (tty_closing || o_tty_closing) {
+ struct task_struct *p;
+
+ read_lock(&tasklist_lock);
+ do_each_task_pid(tty->session, PIDTYPE_SID, p) {
+ p->signal->tty = NULL;
+ } while_each_task_pid(tty->session, PIDTYPE_SID, p);
+ if (o_tty)
+ do_each_task_pid(o_tty->session, PIDTYPE_SID, p) {
+ p->signal->tty = NULL;
+ } while_each_task_pid(o_tty->session, PIDTYPE_SID, p);
+ read_unlock(&tasklist_lock);
+ }
+
+ /* check whether both sides are closing ... */
+ if (!tty_closing || (o_tty && !o_tty_closing))
+ return;
+
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "freeing tty structure...");
+#endif
+ /*
+ * Prevent flush_to_ldisc() from rescheduling the work for later. Then
+ * kill any delayed work. As this is the final close it does not
+ * race with the set_ldisc code path.
+ */
+ clear_bit(TTY_LDISC, &tty->flags);
+ clear_bit(TTY_DONT_FLIP, &tty->flags);
+ cancel_delayed_work(&tty->flip.work);
+
+ /*
+ * Wait for ->hangup_work and ->flip.work handlers to terminate
+ */
+
+ flush_scheduled_work();
+
+ /*
+ * Wait for any short term users (we know they are just driver
+ * side waiters as the file is closing so user count on the file
+ * side is zero.
+ */
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ while(tty->ldisc.refcount)
+ {
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+ wait_event(tty_ldisc_wait, tty->ldisc.refcount == 0);
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ }
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+ /*
+ * Shutdown the current line discipline, and reset it to N_TTY.
+ * N.B. why reset ldisc when we're releasing the memory??
+ *
+ * FIXME: this MUST get fixed for the new reflocking
+ */
+ if (tty->ldisc.close)
+ (tty->ldisc.close)(tty);
+ tty_ldisc_put(tty->ldisc.num);
+
+ /*
+ * Switch the line discipline back
+ */
+ tty_ldisc_assign(tty, tty_ldisc_get(N_TTY));
+ tty_set_termios_ldisc(tty,N_TTY);
+ if (o_tty) {
+ /* FIXME: could o_tty be in setldisc here ? */
+ clear_bit(TTY_LDISC, &o_tty->flags);
+ if (o_tty->ldisc.close)
+ (o_tty->ldisc.close)(o_tty);
+ tty_ldisc_put(o_tty->ldisc.num);
+ tty_ldisc_assign(o_tty, tty_ldisc_get(N_TTY));
+ tty_set_termios_ldisc(o_tty,N_TTY);
+ }
+ /*
+ * The release_mem function takes care of the details of clearing
+ * the slots and preserving the termios structure.
+ */
+ release_mem(tty, idx);
+
+#ifdef CONFIG_UNIX98_PTYS
+ /* Make this pty number available for reallocation */
+ if (devpts) {
+ down(&allocated_ptys_lock);
+ idr_remove(&allocated_ptys, idx);
+ up(&allocated_ptys_lock);
+ }
+#endif
+
+}
+
+/*
+ * tty_open and tty_release keep up the tty count that contains the
+ * number of opens done on a tty. We cannot use the inode-count, as
+ * different inodes might point to the same tty.
+ *
+ * Open-counting is needed for pty masters, as well as for keeping
+ * track of serial lines: DTR is dropped when the last close happens.
+ * (This is not done solely through tty->count, now. - Ted 1/27/92)
+ *
+ * The termios state of a pty is reset on first open so that
+ * settings don't persist across reuse.
+ */
+static int tty_open(struct inode * inode, struct file * filp)
+{
+ struct tty_struct *tty;
+ int noctty, retval;
+ struct tty_driver *driver;
+ int index;
+ dev_t device = inode->i_rdev;
+ unsigned short saved_flags = filp->f_flags;
+
+ nonseekable_open(inode, filp);
+
+retry_open:
+ noctty = filp->f_flags & O_NOCTTY;
+ index = -1;
+ retval = 0;
+
+ down(&tty_sem);
+
+ if (device == MKDEV(TTYAUX_MAJOR,0)) {
+ if (!current->signal->tty) {
+ up(&tty_sem);
+ return -ENXIO;
+ }
+ driver = current->signal->tty->driver;
+ index = current->signal->tty->index;
+ filp->f_flags |= O_NONBLOCK; /* Don't let /dev/tty block */
+ /* noctty = 1; */
+ goto got_driver;
+ }
+#ifdef CONFIG_VT
+ if (console_use_vt && (device == MKDEV(TTY_MAJOR,0))) {
+ extern int fg_console;
+ extern struct tty_driver *console_driver;
+ driver = console_driver;
+ index = fg_console;
+ noctty = 1;
+ goto got_driver;
+ }
+#endif
+ if (device == MKDEV(TTYAUX_MAJOR,1)) {
+ driver = console_device(&index);
+ if (driver) {
+ /* Don't let /dev/console block */
+ filp->f_flags |= O_NONBLOCK;
+ noctty = 1;
+ goto got_driver;
+ }
+ up(&tty_sem);
+ return -ENODEV;
+ }
+
+ driver = get_tty_driver(device, &index);
+ if (!driver) {
+ up(&tty_sem);
+ return -ENODEV;
+ }
+got_driver:
+ retval = init_dev(driver, index, &tty);
+ up(&tty_sem);
+ if (retval)
+ return retval;
+
+ filp->private_data = tty;
+ file_move(filp, &tty->tty_files);
+ check_tty_count(tty, "tty_open");
+ if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver->subtype == PTY_TYPE_MASTER)
+ noctty = 1;
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "opening %s...", tty->name);
+#endif
+ if (!retval) {
+ if (tty->driver->open)
+ retval = tty->driver->open(tty, filp);
+ else
+ retval = -ENODEV;
+ }
+ filp->f_flags = saved_flags;
+
+ if (!retval && test_bit(TTY_EXCLUSIVE, &tty->flags) &&
!capable(CAP_SYS_ADMIN))
+ retval = -EBUSY;
+
+ if (retval) {
+#ifdef TTY_DEBUG_HANGUP
+ printk(KERN_DEBUG "error %d in opening %s...", retval,
+ tty->name);
+#endif
+ release_dev(filp);
+ if (retval != -ERESTARTSYS)
+ return retval;
+ if (signal_pending(current))
+ return retval;
+ schedule();
+ /*
+ * Need to reset f_op in case a hangup happened.
+ */
+ if (filp->f_op == &hung_up_tty_fops)
+ filp->f_op = &tty_fops;
+ goto retry_open;
+ }
+ if (!noctty &&
+ current->signal->leader &&
+ !current->signal->tty &&
+ tty->session == 0) {
+ task_lock(current);
+ current->signal->tty = tty;
+ task_unlock(current);
+ current->signal->tty_old_pgrp = 0;
+ tty->session = current->signal->session;
+ tty->pgrp = process_group(current);
+ }
+ return 0;
+}
+
+#ifdef CONFIG_UNIX98_PTYS
+static int ptmx_open(struct inode * inode, struct file * filp)
+{
+ struct tty_struct *tty;
+ int retval;
+ int index;
+ int idr_ret;
+
+ nonseekable_open(inode, filp);
+
+ /* find a device that is not in use. */
+ down(&allocated_ptys_lock);
+ if (!idr_pre_get(&allocated_ptys, GFP_KERNEL)) {
+ up(&allocated_ptys_lock);
+ return -ENOMEM;
+ }
+ idr_ret = idr_get_new(&allocated_ptys, NULL, &index);
+ if (idr_ret < 0) {
+ up(&allocated_ptys_lock);
+ if (idr_ret == -EAGAIN)
+ return -ENOMEM;
+ return -EIO;
+ }
+ if (index >= pty_limit) {
+ idr_remove(&allocated_ptys, index);
+ up(&allocated_ptys_lock);
+ return -EIO;
+ }
+ up(&allocated_ptys_lock);
+
+ down(&tty_sem);
+ retval = init_dev(ptm_driver, index, &tty);
+ up(&tty_sem);
+
+ if (retval)
+ goto out;
+
+ set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
+ filp->private_data = tty;
+ file_move(filp, &tty->tty_files);
+
+ retval = -ENOMEM;
+ if (devpts_pty_new(tty->link))
+ goto out1;
+
+ check_tty_count(tty, "tty_open");
+ retval = ptm_driver->open(tty, filp);
+ if (!retval)
+ return 0;
+out1:
+ release_dev(filp);
+out:
+ down(&allocated_ptys_lock);
+ idr_remove(&allocated_ptys, index);
+ up(&allocated_ptys_lock);
+ return retval;
+}
+#endif
+
+static int tty_release(struct inode * inode, struct file * filp)
+{
+ lock_kernel();
+ release_dev(filp);
+ unlock_kernel();
+ return 0;
+}
+
+/* No kernel lock held - fine */
+static unsigned int tty_poll(struct file * filp, poll_table * wait)
+{
+ struct tty_struct * tty;
+ struct tty_ldisc *ld;
+ int ret = 0;
+
+ tty = (struct tty_struct *)filp->private_data;
+ if (tty_paranoia_check(tty, filp->f_dentry->d_inode, "tty_poll"))
+ return 0;
+
+ ld = tty_ldisc_ref_wait(tty);
+ if (ld->poll)
+ ret = (ld->poll)(tty, filp, wait);
+ tty_ldisc_deref(ld);
+ return ret;
+}
+
+static int tty_fasync(int fd, struct file * filp, int on)
+{
+ struct tty_struct * tty;
+ int retval;
+
+ tty = (struct tty_struct *)filp->private_data;
+ if (tty_paranoia_check(tty, filp->f_dentry->d_inode, "tty_fasync"))
+ return 0;
+
+ retval = fasync_helper(fd, filp, on, &tty->fasync);
+ if (retval <= 0)
+ return retval;
+
+ if (on) {
+ if (!waitqueue_active(&tty->read_wait))
+ tty->minimum_to_wake = 1;
+ retval = f_setown(filp, (-tty->pgrp) ? : current->pid, 0);
+ if (retval)
+ return retval;
+ } else {
+ if (!tty->fasync && !waitqueue_active(&tty->read_wait))
+ tty->minimum_to_wake = N_TTY_BUF_SIZE;
+ }
+ return 0;
+}
+
+static int tiocsti(struct tty_struct *tty, char __user *p)
+{
+ char ch, mbz = 0;
+ struct tty_ldisc *ld;
+
+ if ((current->signal->tty != tty) && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ if (get_user(ch, p))
+ return -EFAULT;
+ ld = tty_ldisc_ref_wait(tty);
+ ld->receive_buf(tty, &ch, &mbz, 1);
+ tty_ldisc_deref(ld);
+ return 0;
+}
+
+static int tiocgwinsz(struct tty_struct *tty, struct winsize __user * arg)
+{
+ if (copy_to_user(arg, &tty->winsize, sizeof(*arg)))
+ return -EFAULT;
+ return 0;
+}
+
+static int tiocswinsz(struct tty_struct *tty, struct tty_struct *real_tty,
+ struct winsize __user * arg)
+{
+ struct winsize tmp_ws;
+
+ if (copy_from_user(&tmp_ws, arg, sizeof(*arg)))
+ return -EFAULT;
+ if (!memcmp(&tmp_ws, &tty->winsize, sizeof(*arg)))
+ return 0;
+#ifdef CONFIG_VT
+ if (tty->driver->type == TTY_DRIVER_TYPE_CONSOLE) {
+ unsigned int currcons = tty->index;
+ int rc;
+
+ acquire_console_sem();
+ rc = vc_resize(currcons, tmp_ws.ws_col, tmp_ws.ws_row);
+ release_console_sem();
+ if (rc)
+ return -ENXIO;
+ }
+#endif
+ if (tty->pgrp > 0)
+ kill_pg(tty->pgrp, SIGWINCH, 1);
+ if ((real_tty->pgrp != tty->pgrp) && (real_tty->pgrp > 0))
+ kill_pg(real_tty->pgrp, SIGWINCH, 1);
+ tty->winsize = tmp_ws;
+ real_tty->winsize = tmp_ws;
+ return 0;
+}
+
+static int tioccons(struct file *file)
+{
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ if (file->f_op->write == redirected_tty_write) {
+ struct file *f;
+ spin_lock(&redirect_lock);
+ f = redirect;
+ redirect = NULL;
+ spin_unlock(&redirect_lock);
+ if (f)
+ fput(f);
+ return 0;
+ }
+ spin_lock(&redirect_lock);
+ if (redirect) {
+ spin_unlock(&redirect_lock);
+ return -EBUSY;
+ }
+ get_file(file);
+ redirect = file;
+ spin_unlock(&redirect_lock);
+ return 0;
+}
+
+
+static int fionbio(struct file *file, int __user *p)
+{
+ int nonblock;
+
+ if (get_user(nonblock, p))
+ return -EFAULT;
+
+ if (nonblock)
+ file->f_flags |= O_NONBLOCK;
+ else
+ file->f_flags &= ~O_NONBLOCK;
+ return 0;
+}
+
+static int tiocsctty(struct tty_struct *tty, int arg)
+{
+ task_t *p;
+
+ if (current->signal->leader &&
+ (current->signal->session == tty->session))
+ return 0;
+ /*
+ * The process must be a session leader and
+ * not have a controlling tty already.
+ */
+ if (!current->signal->leader || current->signal->tty)
+ return -EPERM;
+ if (tty->session > 0) {
+ /*
+ * This tty is already the controlling
+ * tty for another session group!
+ */
+ if ((arg == 1) && capable(CAP_SYS_ADMIN)) {
+ /*
+ * Steal it away
+ */
+
+ read_lock(&tasklist_lock);
+ do_each_task_pid(tty->session, PIDTYPE_SID, p) {
+ p->signal->tty = NULL;
+ } while_each_task_pid(tty->session, PIDTYPE_SID, p);
+ read_unlock(&tasklist_lock);
+ } else
+ return -EPERM;
+ }
+ task_lock(current);
+ current->signal->tty = tty;
+ task_unlock(current);
+ current->signal->tty_old_pgrp = 0;
+ tty->session = current->signal->session;
+ tty->pgrp = process_group(current);
+ return 0;
+}
+
+static int tiocgpgrp(struct tty_struct *tty, struct tty_struct *real_tty,
pid_t __user *p)
+{
+ /*
+ * (tty == real_tty) is a cheap way of
+ * testing if the tty is NOT a master pty.
+ */
+ if (tty == real_tty && current->signal->tty != real_tty)
+ return -ENOTTY;
+ return put_user(real_tty->pgrp, p);
+}
+
+static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty,
pid_t __user *p)
+{
+ pid_t pgrp;
+ int retval = tty_check_change(real_tty);
+
+ if (retval == -EIO)
+ return -ENOTTY;
+ if (retval)
+ return retval;
+ if (!current->signal->tty ||
+ (current->signal->tty != real_tty) ||
+ (real_tty->session != current->signal->session))
+ return -ENOTTY;
+ if (get_user(pgrp, p))
+ return -EFAULT;
+ if (pgrp < 0)
+ return -EINVAL;
+ if (session_of_pgrp(pgrp) != current->signal->session)
+ return -EPERM;
+ real_tty->pgrp = pgrp;
+ return 0;
+}
+
+static int tiocgsid(struct tty_struct *tty, struct tty_struct *real_tty, pid_t
__user *p)
+{
+ /*
+ * (tty == real_tty) is a cheap way of
+ * testing if the tty is NOT a master pty.
+ */
+ if (tty == real_tty && current->signal->tty != real_tty)
+ return -ENOTTY;
+ if (real_tty->session <= 0)
+ return -ENOTTY;
+ return put_user(real_tty->session, p);
+}
+
+static int tiocsetd(struct tty_struct *tty, int __user *p)
+{
+ int ldisc;
+
+ if (get_user(ldisc, p))
+ return -EFAULT;
+ return tty_set_ldisc(tty, ldisc);
+}
+
+static int send_break(struct tty_struct *tty, int duration)
+{
+ tty->driver->break_ctl(tty, -1);
+ if (!signal_pending(current)) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(duration);
+ }
+ tty->driver->break_ctl(tty, 0);
+ if (signal_pending(current))
+ return -EINTR;
+ return 0;
+}
+
+static int
+tty_tiocmget(struct tty_struct *tty, struct file *file, int __user *p)
+{
+ int retval = -EINVAL;
+
+ if (tty->driver->tiocmget) {
+ retval = tty->driver->tiocmget(tty, file);
+
+ if (retval >= 0)
+ retval = put_user(retval, p);
+ }
+ return retval;
+}
+
+static int
+tty_tiocmset(struct tty_struct *tty, struct file *file, unsigned int cmd,
+ unsigned __user *p)
+{
+ int retval = -EINVAL;
+
+ if (tty->driver->tiocmset) {
+ unsigned int set, clear, val;
+
+ retval = get_user(val, p);
+ if (retval)
+ return retval;
+
+ set = clear = 0;
+ switch (cmd) {
+ case TIOCMBIS:
+ set = val;
+ break;
+ case TIOCMBIC:
+ clear = val;
+ break;
+ case TIOCMSET:
+ set = val;
+ clear = ~val;
+ break;
+ }
+
+ set &= TIOCM_DTR|TIOCM_RTS|TIOCM_OUT1|TIOCM_OUT2|TIOCM_LOOP;
+ clear &= TIOCM_DTR|TIOCM_RTS|TIOCM_OUT1|TIOCM_OUT2|TIOCM_LOOP;
+
+ retval = tty->driver->tiocmset(tty, file, set, clear);
+ }
+ return retval;
+}
+
+/*
+ * Split this up, as gcc can choke on it otherwise..
+ */
+int tty_ioctl(struct inode * inode, struct file * file,
+ unsigned int cmd, unsigned long arg)
+{
+ struct tty_struct *tty, *real_tty;
+ void __user *p = (void __user *)arg;
+ int retval;
+ struct tty_ldisc *ld;
+
+ tty = (struct tty_struct *)file->private_data;
+ if (tty_paranoia_check(tty, inode, "tty_ioctl"))
+ return -EINVAL;
+
+ real_tty = tty;
+ if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver->subtype == PTY_TYPE_MASTER)
+ real_tty = tty->link;
+
+ /*
+ * Break handling by driver
+ */
+ if (!tty->driver->break_ctl) {
+ switch(cmd) {
+ case TIOCSBRK:
+ case TIOCCBRK:
+ if (tty->driver->ioctl)
+ return tty->driver->ioctl(tty, file, cmd, arg);
+ return -EINVAL;
+
+ /* These two ioctl's always return success; even if */
+ /* the driver doesn't support them. */
+ case TCSBRK:
+ case TCSBRKP:
+ if (!tty->driver->ioctl)
+ return 0;
+ retval = tty->driver->ioctl(tty, file, cmd, arg);
+ if (retval == -ENOIOCTLCMD)
+ retval = 0;
+ return retval;
+ }
+ }
+
+ /*
+ * Factor out some common prep work
+ */
+ switch (cmd) {
+ case TIOCSETD:
+ case TIOCSBRK:
+ case TIOCCBRK:
+ case TCSBRK:
+ case TCSBRKP:
+ retval = tty_check_change(tty);
+ if (retval)
+ return retval;
+ if (cmd != TIOCCBRK) {
+ tty_wait_until_sent(tty, 0);
+ if (signal_pending(current))
+ return -EINTR;
+ }
+ break;
+ }
+
+ switch (cmd) {
+ case TIOCSTI:
+ return tiocsti(tty, p);
+ case TIOCGWINSZ:
+ return tiocgwinsz(tty, p);
+ case TIOCSWINSZ:
+ return tiocswinsz(tty, real_tty, p);
+ case TIOCCONS:
+ return real_tty!=tty ? -EINVAL : tioccons(file);
+ case FIONBIO:
+ return fionbio(file, p);
+ case TIOCEXCL:
+ set_bit(TTY_EXCLUSIVE, &tty->flags);
+ return 0;
+ case TIOCNXCL:
+ clear_bit(TTY_EXCLUSIVE, &tty->flags);
+ return 0;
+ case TIOCNOTTY:
+ if (current->signal->tty != tty)
+ return -ENOTTY;
+ if (current->signal->leader)
+ disassociate_ctty(0);
+ task_lock(current);
+ current->signal->tty = NULL;
+ task_unlock(current);
+ return 0;
+ case TIOCSCTTY:
+ return tiocsctty(tty, arg);
+ case TIOCGPGRP:
+ return tiocgpgrp(tty, real_tty, p);
+ case TIOCSPGRP:
+ return tiocspgrp(tty, real_tty, p);
+ case TIOCGSID:
+ return tiocgsid(tty, real_tty, p);
+ case TIOCGETD:
+ /* FIXME: check this is ok */
+ return put_user(tty->ldisc.num, (int __user *)p);
+ case TIOCSETD:
+ return tiocsetd(tty, p);
+#ifdef CONFIG_VT
+ case TIOCLINUX:
+ return tioclinux(tty, arg);
+#endif
+ /*
+ * Break handling
+ */
+ case TIOCSBRK: /* Turn break on, unconditionally */
+ tty->driver->break_ctl(tty, -1);
+ return 0;
+
+ case TIOCCBRK: /* Turn break off, unconditionally */
+ tty->driver->break_ctl(tty, 0);
+ return 0;
+ case TCSBRK: /* SVID version: non-zero arg --> no break */
+ /*
+ * XXX is the above comment correct, or the
+ * code below correct? Is this ioctl used at
+ * all by anyone?
+ */
+ if (!arg)
+ return send_break(tty, HZ/4);
+ return 0;
+ case TCSBRKP: /* support for POSIX tcsendbreak() */
+ return send_break(tty, arg ? arg*(HZ/10) : HZ/4);
+
+ case TIOCMGET:
+ return tty_tiocmget(tty, file, p);
+
+ case TIOCMSET:
+ case TIOCMBIC:
+ case TIOCMBIS:
+ return tty_tiocmset(tty, file, cmd, p);
+ }
+ if (tty->driver->ioctl) {
+ retval = (tty->driver->ioctl)(tty, file, cmd, arg);
+ if (retval != -ENOIOCTLCMD)
+ return retval;
+ }
+ ld = tty_ldisc_ref_wait(tty);
+ retval = -EINVAL;
+ if (ld->ioctl) {
+ retval = ld->ioctl(tty, file, cmd, arg);
+ if (retval == -ENOIOCTLCMD)
+ retval = -EINVAL;
+ }
+ tty_ldisc_deref(ld);
+ return retval;
+}
+
+
+/*
+ * This implements the "Secure Attention Key" --- the idea is to
+ * prevent trojan horses by killing all processes associated with this
+ * tty when the user hits the "Secure Attention Key". Required for
+ * super-paranoid applications --- see the Orange Book for more details.
+ *
+ * This code could be nicer; ideally it should send a HUP, wait a few
+ * seconds, then send a INT, and then a KILL signal. But you then
+ * have to coordinate with the init process, since all processes associated
+ * with the current tty must be dead before the new getty is allowed
+ * to spawn.
+ *
+ * Now, if it would be correct ;-/ The current code has a nasty hole -
+ * it doesn't catch files in flight. We may send the descriptor to ourselves
+ * via AF_UNIX socket, close it and later fetch from socket. FIXME.
+ *
+ * Nasty bug: do_SAK is being called in interrupt context. This can
+ * deadlock. We punt it up to process context. AKPM - 16Mar2001
+ */
+static void __do_SAK(void *arg)
+{
+#ifdef TTY_SOFT_SAK
+ tty_hangup(tty);
+#else
+ struct tty_struct *tty = arg;
+ struct task_struct *p;
+ int session;
+ int i;
+ struct file *filp;
+ struct tty_ldisc *disc;
+
+ if (!tty)
+ return;
+ session = tty->session;
+
+ /* We don't want an ldisc switch during this */
+ disc = tty_ldisc_ref(tty);
+ if (disc && disc->flush_buffer)
+ disc->flush_buffer(tty);
+ tty_ldisc_deref(disc);
+
+ if (tty->driver->flush_buffer)
+ tty->driver->flush_buffer(tty);
+
+ read_lock(&tasklist_lock);
+ do_each_task_pid(session, PIDTYPE_SID, p) {
+ if (p->signal->tty == tty || session > 0) {
+ printk(KERN_NOTICE "SAK: killed process %d"
+ " (%s): p->signal->session==tty->session\n",
+ p->pid, p->comm);
+ send_sig(SIGKILL, p, 1);
+ continue;
+ }
+ task_lock(p);
+ if (p->files) {
+ spin_lock(&p->files->file_lock);
+ for (i=0; i < p->files->max_fds; i++) {
+ filp = fcheck_files(p->files, i);
+ if (!filp)
+ continue;
+ if (filp->f_op->read == tty_read &&
+ filp->private_data == tty) {
+ printk(KERN_NOTICE "SAK: killed process
%d"
+ " (%s): fd#%d opened to the tty\n",
+ p->pid, p->comm, i);
+ send_sig(SIGKILL, p, 1);
+ break;
+ }
+ }
+ spin_unlock(&p->files->file_lock);
+ }
+ task_unlock(p);
+ } while_each_task_pid(session, PIDTYPE_SID, p);
+ read_unlock(&tasklist_lock);
+#endif
+}
+
+/*
+ * The tq handling here is a little racy - tty->SAK_work may already be queued.
+ * Fortunately we don't need to worry, because if ->SAK_work is already queued,
+ * the values which we write to it will be identical to the values which it
+ * already has. --akpm
+ */
+void do_SAK(struct tty_struct *tty)
+{
+ if (!tty)
+ return;
+ PREPARE_WORK(&tty->SAK_work, __do_SAK, tty);
+ schedule_work(&tty->SAK_work);
+}
+
+EXPORT_SYMBOL(do_SAK);
+
+/*
+ * This routine is called out of the software interrupt to flush data
+ * from the flip buffer to the line discipline.
+ */
+
+static void flush_to_ldisc(void *private_)
+{
+ struct tty_struct *tty = (struct tty_struct *) private_;
+ unsigned char *cp;
+ char *fp;
+ int count;
+ unsigned long flags;
+ struct tty_ldisc *disc;
+
+ disc = tty_ldisc_ref(tty);
+ if (disc == NULL) /* !TTY_LDISC */
+ return;
+
+ if (test_bit(TTY_DONT_FLIP, &tty->flags)) {
+ /*
+ * Do it after the next timer tick:
+ */
+ schedule_delayed_work(&tty->flip.work, 1);
+ goto out;
+ }
+ spin_lock_irqsave(&tty->read_lock, flags);
+ if (tty->flip.buf_num) {
+ cp = tty->flip.char_buf + TTY_FLIPBUF_SIZE;
+ fp = tty->flip.flag_buf + TTY_FLIPBUF_SIZE;
+ tty->flip.buf_num = 0;
+ tty->flip.char_buf_ptr = tty->flip.char_buf;
+ tty->flip.flag_buf_ptr = tty->flip.flag_buf;
+ } else {
+ cp = tty->flip.char_buf;
+ fp = tty->flip.flag_buf;
+ tty->flip.buf_num = 1;
+ tty->flip.char_buf_ptr = tty->flip.char_buf + TTY_FLIPBUF_SIZE;
+ tty->flip.flag_buf_ptr = tty->flip.flag_buf + TTY_FLIPBUF_SIZE;
+ }
+ count = tty->flip.count;
+ tty->flip.count = 0;
+ spin_unlock_irqrestore(&tty->read_lock, flags);
+
+ disc->receive_buf(tty, cp, fp, count);
+out:
+ tty_ldisc_deref(disc);
+}
+
+/*
+ * Routine which returns the baud rate of the tty
+ *
+ * Note that the baud_table needs to be kept in sync with the
+ * include/asm/termbits.h file.
+ */
+static int baud_table[] = {
+ 0, 50, 75, 110, 134, 150, 200, 300, 600, 1200, 1800, 2400, 4800,
+ 9600, 19200, 38400, 57600, 115200, 230400, 460800,
+#ifdef __sparc__
+ 76800, 153600, 307200, 614400, 921600
+#else
+ 500000, 576000, 921600, 1000000, 1152000, 1500000, 2000000,
+ 2500000, 3000000, 3500000, 4000000
+#endif
+};
+
+static int n_baud_table = ARRAY_SIZE(baud_table);
+
+/**
+ * tty_termios_baud_rate
+ * @termios: termios structure
+ *
+ * Convert termios baud rate data into a speed. This should be called
+ * with the termios lock held if this termios is a terminal termios
+ * structure. May change the termios data.
+ */
+
+int tty_termios_baud_rate(struct termios *termios)
+{
+ unsigned int cbaud;
+
+ cbaud = termios->c_cflag & CBAUD;
+
+ if (cbaud & CBAUDEX) {
+ cbaud &= ~CBAUDEX;
+
+ if (cbaud < 1 || cbaud + 15 > n_baud_table)
+ termios->c_cflag &= ~CBAUDEX;
+ else
+ cbaud += 15;
+ }
+ return baud_table[cbaud];
+}
+
+EXPORT_SYMBOL(tty_termios_baud_rate);
+
+/**
+ * tty_get_baud_rate - get tty bit rates
+ * @tty: tty to query
+ *
+ * Returns the baud rate as an integer for this terminal. The
+ * termios lock must be held by the caller and the terminal bit
+ * flags may be updated.
+ */
+
+int tty_get_baud_rate(struct tty_struct *tty)
+{
+ int baud = tty_termios_baud_rate(tty->termios);
+
+ if (baud == 38400 && tty->alt_speed) {
+ if (!tty->warned) {
+ printk(KERN_WARNING "Use of setserial/setrocket to "
+ "set SPD_* flags is deprecated\n");
+ tty->warned = 1;
+ }
+ baud = tty->alt_speed;
+ }
+
+ return baud;
+}
+
+EXPORT_SYMBOL(tty_get_baud_rate);
+
+/**
+ * tty_flip_buffer_push - terminal
+ * @tty: tty to push
+ *
+ * Queue a push of the terminal flip buffers to the line discipline. This
+ * function must not be called from IRQ context if tty->low_latency is set.
+ *
+ * In the event of the queue being busy for flipping the work will be
+ * held off and retried later.
+ */
+
+void tty_flip_buffer_push(struct tty_struct *tty)
+{
+ if (tty->low_latency)
+ flush_to_ldisc((void *) tty);
+ else
+ schedule_delayed_work(&tty->flip.work, 1);
+}
+
+EXPORT_SYMBOL(tty_flip_buffer_push);
+
+/*
+ * This subroutine initializes a tty structure.
+ */
+static void initialize_tty_struct(struct tty_struct *tty)
+{
+ memset(tty, 0, sizeof(struct tty_struct));
+ tty->magic = TTY_MAGIC;
+ tty_ldisc_assign(tty, tty_ldisc_get(N_TTY));
+ tty->pgrp = -1;
+ tty->flip.char_buf_ptr = tty->flip.char_buf;
+ tty->flip.flag_buf_ptr = tty->flip.flag_buf;
+ INIT_WORK(&tty->flip.work, flush_to_ldisc, tty);
+ init_MUTEX(&tty->flip.pty_sem);
+ init_MUTEX(&tty->termios_sem);
+ init_waitqueue_head(&tty->write_wait);
+ init_waitqueue_head(&tty->read_wait);
+ INIT_WORK(&tty->hangup_work, do_tty_hangup, tty);
+ sema_init(&tty->atomic_read, 1);
+ sema_init(&tty->atomic_write, 1);
+ spin_lock_init(&tty->read_lock);
+ INIT_LIST_HEAD(&tty->tty_files);
+ INIT_WORK(&tty->SAK_work, NULL, NULL);
+}
+
+/*
+ * The default put_char routine if the driver did not define one.
+ */
+static void tty_default_put_char(struct tty_struct *tty, unsigned char ch)
+{
+ tty->driver->write(tty, &ch, 1);
+}
+
+static struct class_simple *tty_class;
+
+/**
+ * tty_register_device - register a tty device
+ * @driver: the tty driver that describes the tty device
+ * @index: the index in the tty driver for this tty device
+ * @device: a struct device that is associated with this tty device.
+ * This field is optional, if there is no known struct device for this
+ * tty device it can be set to NULL safely.
+ *
+ * This call is required to be made to register an individual tty device if
+ * the tty driver's flags have the TTY_DRIVER_NO_DEVFS bit set. If that
+ * bit is not set, this function should not be called.
+ */
+void tty_register_device(struct tty_driver *driver, unsigned index,
+ struct device *device)
+{
+ char name[64];
+ dev_t dev = MKDEV(driver->major, driver->minor_start) + index;
+
+ if (index >= driver->num) {
+ printk(KERN_ERR "Attempt to register invalid tty line number "
+ " (%d).\n", index);
+ return;
+ }
+
+ devfs_mk_cdev(dev, S_IFCHR | S_IRUSR | S_IWUSR,
+ "%s%d", driver->devfs_name, index + driver->name_base);
+
+ if (driver->type == TTY_DRIVER_TYPE_PTY)
+ pty_line_name(driver, index, name);
+ else
+ tty_line_name(driver, index, name);
+ class_simple_device_add(tty_class, dev, device, name);
+}
+
+/**
+ * tty_unregister_device - unregister a tty device
+ * @driver: the tty driver that describes the tty device
+ * @index: the index in the tty driver for this tty device
+ *
+ * If a tty device is registered with a call to tty_register_device() then
+ * this function must be made when the tty device is gone.
+ */
+void tty_unregister_device(struct tty_driver *driver, unsigned index)
+{
+ devfs_remove("%s%d", driver->devfs_name, index + driver->name_base);
+ class_simple_device_remove(MKDEV(driver->major, driver->minor_start) +
index);
+}
+
+EXPORT_SYMBOL(tty_register_device);
+EXPORT_SYMBOL(tty_unregister_device);
+
+struct tty_driver *alloc_tty_driver(int lines)
+{
+ struct tty_driver *driver;
+
+ driver = kmalloc(sizeof(struct tty_driver), GFP_KERNEL);
+ if (driver) {
+ memset(driver, 0, sizeof(struct tty_driver));
+ driver->magic = TTY_DRIVER_MAGIC;
+ driver->num = lines;
+ /* later we'll move allocation of tables here */
+ }
+ return driver;
+}
+
+void put_tty_driver(struct tty_driver *driver)
+{
+ kfree(driver);
+}
+
+void tty_set_operations(struct tty_driver *driver, struct tty_operations *op)
+{
+ driver->open = op->open;
+ driver->close = op->close;
+ driver->write = op->write;
+ driver->put_char = op->put_char;
+ driver->flush_chars = op->flush_chars;
+ driver->write_room = op->write_room;
+ driver->chars_in_buffer = op->chars_in_buffer;
+ driver->ioctl = op->ioctl;
+ driver->set_termios = op->set_termios;
+ driver->throttle = op->throttle;
+ driver->unthrottle = op->unthrottle;
+ driver->stop = op->stop;
+ driver->start = op->start;
+ driver->hangup = op->hangup;
+ driver->break_ctl = op->break_ctl;
+ driver->flush_buffer = op->flush_buffer;
+ driver->set_ldisc = op->set_ldisc;
+ driver->wait_until_sent = op->wait_until_sent;
+ driver->send_xchar = op->send_xchar;
+ driver->read_proc = op->read_proc;
+ driver->write_proc = op->write_proc;
+ driver->tiocmget = op->tiocmget;
+ driver->tiocmset = op->tiocmset;
+}
+
+
+EXPORT_SYMBOL(alloc_tty_driver);
+EXPORT_SYMBOL(put_tty_driver);
+EXPORT_SYMBOL(tty_set_operations);
+
+/*
+ * Called by a tty driver to register itself.
+ */
+int tty_register_driver(struct tty_driver *driver)
+{
+ int error;
+ int i;
+ dev_t dev;
+ void **p = NULL;
+
+ if (driver->flags & TTY_DRIVER_INSTALLED)
+ return 0;
+
+ if (!(driver->flags & TTY_DRIVER_DEVPTS_MEM)) {
+ p = kmalloc(driver->num * 3 * sizeof(void *), GFP_KERNEL);
+ if (!p)
+ return -ENOMEM;
+ memset(p, 0, driver->num * 3 * sizeof(void *));
+ }
+
+ if (!driver->major) {
+ error = alloc_chrdev_region(&dev, driver->minor_start,
driver->num,
+ (char*)driver->name);
+ if (!error) {
+ driver->major = MAJOR(dev);
+ driver->minor_start = MINOR(dev);
+ }
+ } else {
+ dev = MKDEV(driver->major, driver->minor_start);
+ error = register_chrdev_region(dev, driver->num,
+ (char*)driver->name);
+ }
+ if (error < 0) {
+ kfree(p);
+ return error;
+ }
+
+ if (p) {
+ driver->ttys = (struct tty_struct **)p;
+ driver->termios = (struct termios **)(p + driver->num);
+ driver->termios_locked = (struct termios **)(p + driver->num *
2);
+ } else {
+ driver->ttys = NULL;
+ driver->termios = NULL;
+ driver->termios_locked = NULL;
+ }
+
+ cdev_init(&driver->cdev, &tty_fops);
+ driver->cdev.owner = driver->owner;
+ error = cdev_add(&driver->cdev, dev, driver->num);
+ if (error) {
+ cdev_del(&driver->cdev);
+ unregister_chrdev_region(dev, driver->num);
+ driver->ttys = NULL;
+ driver->termios = driver->termios_locked = NULL;
+ kfree(p);
+ return error;
+ }
+
+ if (!driver->put_char)
+ driver->put_char = tty_default_put_char;
+
+ list_add(&driver->tty_drivers, &tty_drivers);
+
+ if ( !(driver->flags & TTY_DRIVER_NO_DEVFS) ) {
+ for(i = 0; i < driver->num; i++)
+ tty_register_device(driver, i, NULL);
+ }
+ proc_tty_register_driver(driver);
+ return 0;
+}
+
+EXPORT_SYMBOL(tty_register_driver);
+
+/*
+ * Called by a tty driver to unregister itself.
+ */
+int tty_unregister_driver(struct tty_driver *driver)
+{
+ int i;
+ struct termios *tp;
+ void *p;
+
+ if (driver->refcount)
+ return -EBUSY;
+
+ unregister_chrdev_region(MKDEV(driver->major, driver->minor_start),
+ driver->num);
+
+ list_del(&driver->tty_drivers);
+
+ /*
+ * Free the termios and termios_locked structures because
+ * we don't want to get memory leaks when modular tty
+ * drivers are removed from the kernel.
+ */
+ for (i = 0; i < driver->num; i++) {
+ tp = driver->termios[i];
+ if (tp) {
+ driver->termios[i] = NULL;
+ kfree(tp);
+ }
+ tp = driver->termios_locked[i];
+ if (tp) {
+ driver->termios_locked[i] = NULL;
+ kfree(tp);
+ }
+ if (!(driver->flags & TTY_DRIVER_NO_DEVFS))
+ tty_unregister_device(driver, i);
+ }
+ p = driver->ttys;
+ proc_tty_unregister_driver(driver);
+ driver->ttys = NULL;
+ driver->termios = driver->termios_locked = NULL;
+ kfree(p);
+ cdev_del(&driver->cdev);
+ return 0;
+}
+
+EXPORT_SYMBOL(tty_unregister_driver);
+
+
+/*
+ * Initialize the console device. This is called *early*, so
+ * we can't necessarily depend on lots of kernel help here.
+ * Just do some early initializations, and do the complex setup
+ * later.
+ */
+void __init console_init(void)
+{
+ initcall_t *call;
+
+ /* Setup the default TTY line discipline. */
+ (void) tty_register_ldisc(N_TTY, &tty_ldisc_N_TTY);
+
+ /*
+ * set up the console device so that later boot sequences can
+ * inform about problems etc..
+ */
+#ifdef CONFIG_EARLY_PRINTK
+ disable_early_printk();
+#endif
+#ifdef CONFIG_SERIAL_68360
+ /* This is not a console initcall. I know not what it's doing here.
+ So I haven't moved it. dwmw2 */
+ rs_360_init();
+#endif
+ call = __con_initcall_start;
+ while (call < __con_initcall_end) {
+ (*call)();
+ call++;
+ }
+}
+
+#ifdef CONFIG_VT
+extern int vty_init(void);
+#endif
+
+static int __init tty_class_init(void)
+{
+ tty_class = class_simple_create(THIS_MODULE, "tty");
+ if (IS_ERR(tty_class))
+ return PTR_ERR(tty_class);
+ return 0;
+}
+
+postcore_initcall(tty_class_init);
+
+/* 3/2004 jmc: why do these devices exist? */
+
+static struct cdev tty_cdev, console_cdev;
+#ifdef CONFIG_UNIX98_PTYS
+static struct cdev ptmx_cdev;
+#endif
+#ifdef CONFIG_VT
+static struct cdev vc0_cdev;
+#endif
+
+/*
+ * Ok, now we can initialize the rest of the tty devices and can count
+ * on memory allocations, interrupts etc..
+ */
+static int __init tty_init(void)
+{
+ cdev_init(&tty_cdev, &tty_fops);
+ if (cdev_add(&tty_cdev, MKDEV(TTYAUX_MAJOR, 0), 1) ||
+ register_chrdev_region(MKDEV(TTYAUX_MAJOR, 0), 1, "/dev/tty") < 0)
+ panic("Couldn't register /dev/tty driver\n");
+ devfs_mk_cdev(MKDEV(TTYAUX_MAJOR, 0), S_IFCHR|S_IRUGO|S_IWUGO, "tty");
+ class_simple_device_add(tty_class, MKDEV(TTYAUX_MAJOR, 0), NULL, "tty");
+
+ cdev_init(&console_cdev, &console_fops);
+ if (cdev_add(&console_cdev, MKDEV(TTYAUX_MAJOR, 1), 1) ||
+ register_chrdev_region(MKDEV(TTYAUX_MAJOR, 1), 1, "/dev/console") <
0)
+ panic("Couldn't register /dev/console driver\n");
+ devfs_mk_cdev(MKDEV(TTYAUX_MAJOR, 1), S_IFCHR|S_IRUSR|S_IWUSR,
"console");
+ class_simple_device_add(tty_class, MKDEV(TTYAUX_MAJOR, 1), NULL,
"console");
+
+#ifdef CONFIG_UNIX98_PTYS
+ cdev_init(&ptmx_cdev, &ptmx_fops);
+ if (cdev_add(&ptmx_cdev, MKDEV(TTYAUX_MAJOR, 2), 1) ||
+ register_chrdev_region(MKDEV(TTYAUX_MAJOR, 2), 1, "/dev/ptmx") < 0)
+ panic("Couldn't register /dev/ptmx driver\n");
+ devfs_mk_cdev(MKDEV(TTYAUX_MAJOR, 2), S_IFCHR|S_IRUGO|S_IWUGO, "ptmx");
+ class_simple_device_add(tty_class, MKDEV(TTYAUX_MAJOR, 2), NULL,
"ptmx");
+#endif
+
+#ifdef CONFIG_VT
+ if (console_use_vt) {
+ cdev_init(&vc0_cdev, &console_fops);
+ if (cdev_add(&vc0_cdev, MKDEV(TTY_MAJOR, 0), 1) ||
+ register_chrdev_region(MKDEV(TTY_MAJOR, 0), 1,
+ "/dev/vc/0") < 0)
+ panic("Couldn't register /dev/tty0 driver\n");
+ devfs_mk_cdev(MKDEV(TTY_MAJOR, 0), S_IFCHR|S_IRUSR|S_IWUSR,
+ "vc/0");
+ class_simple_device_add(tty_class, MKDEV(TTY_MAJOR, 0), NULL,
+ "tty0");
+
+ vty_init();
+ }
+#endif
+ return 0;
+}
+module_init(tty_init);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/kernel/ldt.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/kernel/ldt.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,272 @@
+/*
+ * linux/kernel/ldt.c
+ *
+ * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds
+ * Copyright (C) 1999 Ingo Molnar <mingo@xxxxxxxxxx>
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+
+#include <asm/mmu_context.h>
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/ldt.h>
+#include <asm/desc.h>
+
+#ifdef CONFIG_SMP /* avoids "defined but not used" warnig */
+static void flush_ldt(void *mm)
+{
+ if (current->active_mm)
+ load_LDT(¤t->active_mm->context);
+}
+#endif
+
+static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
+{
+ void *oldldt;
+ void *newldt;
+ int oldsize;
+
+ if (mincount <= pc->size)
+ return 0;
+ oldsize = pc->size;
+ mincount = (mincount+511)&(~511);
+ if (mincount*LDT_ENTRY_SIZE > PAGE_SIZE)
+ newldt = vmalloc(mincount*LDT_ENTRY_SIZE);
+ else
+ newldt = kmalloc(mincount*LDT_ENTRY_SIZE, GFP_KERNEL);
+
+ if (!newldt)
+ return -ENOMEM;
+
+ if (oldsize)
+ memcpy(newldt, pc->ldt, oldsize*LDT_ENTRY_SIZE);
+
+ oldldt = pc->ldt;
+ memset(newldt+oldsize*LDT_ENTRY_SIZE, 0,
(mincount-oldsize)*LDT_ENTRY_SIZE);
+ wmb();
+ pc->ldt = newldt;
+ pc->size = mincount;
+ if (reload) {
+ make_pages_readonly(
+ pc->ldt,
+ (pc->size*LDT_ENTRY_SIZE)/PAGE_SIZE);
+ load_LDT(pc);
+#ifdef CONFIG_SMP
+ if (current->mm->cpu_vm_mask != (1<<smp_processor_id()))
+ smp_call_function(flush_ldt, 0, 1, 1);
+#endif
+ }
+ wmb();
+ if (oldsize) {
+ make_pages_writable(
+ oldldt, (oldsize*LDT_ENTRY_SIZE)/PAGE_SIZE);
+ if (oldsize*LDT_ENTRY_SIZE > PAGE_SIZE)
+ vfree(oldldt);
+ else
+ kfree(oldldt);
+ }
+ return 0;
+}
+
+static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
+{
+ int err = alloc_ldt(new, old->size, 0);
+ if (err < 0) {
+ printk(KERN_WARNING "ldt allocation failed\n");
+ new->size = 0;
+ return err;
+ }
+ memcpy(new->ldt, old->ldt, old->size*LDT_ENTRY_SIZE);
+ make_pages_readonly(new->ldt, (new->size*LDT_ENTRY_SIZE)/PAGE_SIZE);
+ return 0;
+}
+
+/*
+ * we do not have to muck with descriptors here, that is
+ * done in switch_mm() as needed.
+ */
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+ struct mm_struct * old_mm;
+ int retval = 0;
+
+ init_MUTEX(&mm->context.sem);
+ mm->context.size = 0;
+ old_mm = current->mm;
+ if (old_mm && old_mm->context.size > 0) {
+ down(&old_mm->context.sem);
+ retval = copy_ldt(&mm->context, &old_mm->context);
+ up(&old_mm->context.sem);
+ }
+ return retval;
+}
+
+/*
+ * No need to lock the MM as we are the last user
+ * Do not touch the ldt register, we are already
+ * in the next thread.
+ */
+void destroy_context(struct mm_struct *mm)
+{
+ if (mm->context.size) {
+ make_pages_writable(
+ mm->context.ldt,
+ (mm->context.size*LDT_ENTRY_SIZE)/PAGE_SIZE);
+ if (mm->context.size*LDT_ENTRY_SIZE > PAGE_SIZE)
+ vfree(mm->context.ldt);
+ else
+ kfree(mm->context.ldt);
+ mm->context.size = 0;
+ }
+}
+
+static int read_ldt(void * ptr, unsigned long bytecount)
+{
+ int err;
+ unsigned long size;
+ struct mm_struct * mm = current->mm;
+
+ if (!mm->context.size)
+ return 0;
+ if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES)
+ bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES;
+
+ down(&mm->context.sem);
+ size = mm->context.size*LDT_ENTRY_SIZE;
+ if (size > bytecount)
+ size = bytecount;
+
+ err = 0;
+ if (copy_to_user(ptr, mm->context.ldt, size))
+ err = -EFAULT;
+ up(&mm->context.sem);
+ if (err < 0)
+ return err;
+ if (size != bytecount) {
+ /* zero-fill the rest */
+ clear_user(ptr+size, bytecount-size);
+ }
+ return bytecount;
+}
+
+static int read_default_ldt(void * ptr, unsigned long bytecount)
+{
+ int err;
+ unsigned long size;
+ void *address;
+
+ err = 0;
+ address = &default_ldt[0];
+ size = 5*sizeof(struct desc_struct);
+ if (size > bytecount)
+ size = bytecount;
+
+ err = size;
+ if (copy_to_user(ptr, address, size))
+ err = -EFAULT;
+
+ return err;
+}
+
+static int write_ldt(void * ptr, unsigned long bytecount, int oldmode)
+{
+ struct mm_struct * mm = current->mm;
+ __u32 entry_1, entry_2, *lp;
+ unsigned long mach_lp;
+ int error;
+ struct modify_ldt_ldt_s ldt_info;
+
+ error = -EINVAL;
+ if (bytecount != sizeof(ldt_info))
+ goto out;
+ error = -EFAULT;
+ if (copy_from_user(&ldt_info, ptr, sizeof(ldt_info)))
+ goto out;
+
+ error = -EINVAL;
+ if (ldt_info.entry_number >= LDT_ENTRIES)
+ goto out;
+ if (ldt_info.contents == 3) {
+ if (oldmode)
+ goto out;
+ if (ldt_info.seg_not_present == 0)
+ goto out;
+ }
+
+ down(&mm->context.sem);
+ if (ldt_info.entry_number >= mm->context.size) {
+ error = alloc_ldt(¤t->mm->context,
ldt_info.entry_number+1, 1);
+ if (error < 0)
+ goto out_unlock;
+ }
+
+ lp = (__u32 *) ((ldt_info.entry_number << 3) + (char *)
mm->context.ldt);
+ mach_lp = arbitrary_virt_to_machine(lp);
+
+ /* Allow LDTs to be cleared by the user. */
+ if (ldt_info.base_addr == 0 && ldt_info.limit == 0) {
+ if (oldmode ||
+ (ldt_info.contents == 0 &&
+ ldt_info.read_exec_only == 1 &&
+ ldt_info.seg_32bit == 0 &&
+ ldt_info.limit_in_pages == 0 &&
+ ldt_info.seg_not_present == 1 &&
+ ldt_info.useable == 0 )) {
+ entry_1 = 0;
+ entry_2 = 0;
+ goto install;
+ }
+ }
+
+ entry_1 = ((ldt_info.base_addr & 0x0000ffff) << 16) |
+ (ldt_info.limit & 0x0ffff);
+ entry_2 = (ldt_info.base_addr & 0xff000000) |
+ ((ldt_info.base_addr & 0x00ff0000) >> 16) |
+ (ldt_info.limit & 0xf0000) |
+ ((ldt_info.read_exec_only ^ 1) << 9) |
+ (ldt_info.contents << 10) |
+ ((ldt_info.seg_not_present ^ 1) << 15) |
+ (ldt_info.seg_32bit << 22) |
+ (ldt_info.limit_in_pages << 23) |
+ 0x7000;
+ if (!oldmode)
+ entry_2 |= (ldt_info.useable << 20);
+
+ /* Install the new entry ... */
+install:
+ error = HYPERVISOR_update_descriptor(mach_lp, entry_1, entry_2);
+
+out_unlock:
+ up(&mm->context.sem);
+out:
+ return error;
+}
+
+asmlinkage int sys_modify_ldt(int func, void *ptr, unsigned long bytecount)
+{
+ int ret = -ENOSYS;
+
+ switch (func) {
+ case 0:
+ ret = read_ldt(ptr, bytecount);
+ break;
+ case 1:
+ ret = write_ldt(ptr, bytecount, 1);
+ break;
+ case 2:
+ ret = read_default_ldt(ptr, bytecount);
+ break;
+ case 0x11:
+ ret = write_ldt(ptr, bytecount, 0);
+ break;
+ }
+ return ret;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blktap/blktap_userdev.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blktap/blktap_userdev.c Fri Jul
15 13:39:50 2005
@@ -0,0 +1,478 @@
+/******************************************************************************
+ * blktap_userdev.c
+ *
+ * XenLinux virtual block-device tap.
+ * Control interface between the driver and a character device.
+ *
+ * Copyright (c) 2004, Andrew Warfield
+ *
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/miscdevice.h>
+#include <linux/errno.h>
+#include <linux/major.h>
+#include <linux/gfp.h>
+#include <linux/poll.h>
+#include <asm/pgalloc.h>
+#include <asm-xen/xen-public/io/blkif.h> /* for control ring. */
+
+#include "blktap.h"
+
+
+unsigned long blktap_mode = BLKTAP_MODE_PASSTHROUGH;
+
+/* Only one process may open /dev/xen/blktap at any time. */
+static unsigned long blktap_dev_inuse;
+unsigned long blktap_ring_ok; /* make this ring->state */
+
+/* for poll: */
+static wait_queue_head_t blktap_wait;
+
+/* Where things are inside the device mapping. */
+struct vm_area_struct *blktap_vma = NULL;
+unsigned long mmap_vstart;
+unsigned long rings_vstart;
+
+/* Rings up to user space. */
+static blkif_front_ring_t blktap_ufe_ring;
+static blkif_back_ring_t blktap_ube_ring;
+static ctrl_front_ring_t blktap_uctrl_ring;
+
+/* local prototypes */
+static int blktap_read_fe_ring(void);
+static int blktap_read_be_ring(void);
+
+/* -------[ blktap vm ops ]------------------------------------------- */
+
+static struct page *blktap_nopage(struct vm_area_struct *vma,
+ unsigned long address,
+ int *type)
+{
+ /*
+ * if the page has not been mapped in by the driver then generate
+ * a SIGBUS to the domain.
+ */
+
+ force_sig(SIGBUS, current);
+
+ return 0;
+}
+
+struct vm_operations_struct blktap_vm_ops = {
+ nopage: blktap_nopage,
+};
+
+/* -------[ blktap file ops ]----------------------------------------- */
+
+static int blktap_open(struct inode *inode, struct file *filp)
+{
+ blkif_sring_t *sring;
+ ctrl_sring_t *csring;
+
+ if ( test_and_set_bit(0, &blktap_dev_inuse) )
+ return -EBUSY;
+
+ printk(KERN_ALERT "blktap open.\n");
+
+ /* Allocate the ctrl ring. */
+ csring = (ctrl_sring_t *)get_zeroed_page(GFP_KERNEL);
+ if (csring == NULL)
+ goto fail_nomem;
+
+ SetPageReserved(virt_to_page(csring));
+
+ SHARED_RING_INIT(csring);
+ FRONT_RING_INIT(&blktap_uctrl_ring, csring, PAGE_SIZE);
+
+ /* Allocate the fe ring. */
+ sring = (blkif_sring_t *)get_zeroed_page(GFP_KERNEL);
+ if (sring == NULL)
+ goto fail_free_ctrl;
+
+ SetPageReserved(virt_to_page(sring));
+
+ SHARED_RING_INIT(sring);
+ FRONT_RING_INIT(&blktap_ufe_ring, sring, PAGE_SIZE);
+
+ /* Allocate the be ring. */
+ sring = (blkif_sring_t *)get_zeroed_page(GFP_KERNEL);
+ if (sring == NULL)
+ goto fail_free_fe;
+
+ SetPageReserved(virt_to_page(sring));
+
+ SHARED_RING_INIT(sring);
+ BACK_RING_INIT(&blktap_ube_ring, sring, PAGE_SIZE);
+
+ DPRINTK(KERN_ALERT "blktap open.\n");
+
+ return 0;
+
+ fail_free_ctrl:
+ free_page( (unsigned long) blktap_uctrl_ring.sring);
+
+ fail_free_fe:
+ free_page( (unsigned long) blktap_ufe_ring.sring);
+
+ fail_nomem:
+ return -ENOMEM;
+}
+
+static int blktap_release(struct inode *inode, struct file *filp)
+{
+ blktap_dev_inuse = 0;
+ blktap_ring_ok = 0;
+
+ printk(KERN_ALERT "blktap closed.\n");
+
+ /* Free the ring page. */
+ ClearPageReserved(virt_to_page(blktap_uctrl_ring.sring));
+ free_page((unsigned long) blktap_uctrl_ring.sring);
+
+ ClearPageReserved(virt_to_page(blktap_ufe_ring.sring));
+ free_page((unsigned long) blktap_ufe_ring.sring);
+
+ ClearPageReserved(virt_to_page(blktap_ube_ring.sring));
+ free_page((unsigned long) blktap_ube_ring.sring);
+
+ /* Clear any active mappings. */
+ if (blktap_vma != NULL) {
+ zap_page_range(blktap_vma, blktap_vma->vm_start,
+ blktap_vma->vm_end - blktap_vma->vm_start, NULL);
+ blktap_vma = NULL;
+ }
+
+ return 0;
+}
+
+/* Note on mmap:
+ * remap_pfn_range sets VM_IO on vma->vm_flags. In trying to make libaio
+ * work to do direct page access from userspace, this ended up being a
+ * problem. The bigger issue seems to be that there is no way to map
+ * a foreign page in to user space and have the virtual address of that
+ * page map sanely down to a mfn.
+ * Removing the VM_IO flag results in a loop in get_user_pages, as
+ * pfn_valid() always fails on a foreign page.
+ */
+static int blktap_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+ int size;
+
+ printk(KERN_ALERT "blktap mmap (%lx, %lx)\n",
+ vma->vm_start, vma->vm_end);
+
+ vma->vm_ops = &blktap_vm_ops;
+
+ size = vma->vm_end - vma->vm_start;
+ if ( size != ( (MMAP_PAGES + RING_PAGES) << PAGE_SHIFT ) ) {
+ printk(KERN_INFO
+ "blktap: you _must_ map exactly %d pages!\n",
+ MMAP_PAGES + RING_PAGES);
+ return -EAGAIN;
+ }
+
+ size >>= PAGE_SHIFT;
+ printk(KERN_INFO "blktap: 2 rings + %d pages.\n", size-1);
+
+ rings_vstart = vma->vm_start;
+ mmap_vstart = rings_vstart + (RING_PAGES << PAGE_SHIFT);
+
+ /* Map the ring pages to the start of the region and reserve it. */
+
+ /* not sure if I really need to do this... */
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+ DPRINTK("Mapping ctrl_ring page %lx.\n", __pa(blktap_uctrl_ring.sring));
+ if (remap_pfn_range(vma, vma->vm_start,
+ __pa(blktap_uctrl_ring.sring) >> PAGE_SHIFT,
+ PAGE_SIZE, vma->vm_page_prot)) {
+ WPRINTK("ctrl_ring: remap_pfn_range failure!\n");
+ }
+
+
+ DPRINTK("Mapping be_ring page %lx.\n", __pa(blktap_ube_ring.sring));
+ if (remap_pfn_range(vma, vma->vm_start + PAGE_SIZE,
+ __pa(blktap_ube_ring.sring) >> PAGE_SHIFT,
+ PAGE_SIZE, vma->vm_page_prot)) {
+ WPRINTK("be_ring: remap_pfn_range failure!\n");
+ }
+
+ DPRINTK("Mapping fe_ring page %lx.\n", __pa(blktap_ufe_ring.sring));
+ if (remap_pfn_range(vma, vma->vm_start + ( 2 * PAGE_SIZE ),
+ __pa(blktap_ufe_ring.sring) >> PAGE_SHIFT,
+ PAGE_SIZE, vma->vm_page_prot)) {
+ WPRINTK("fe_ring: remap_pfn_range failure!\n");
+ }
+
+ blktap_vma = vma;
+ blktap_ring_ok = 1;
+
+ return 0;
+}
+
+static int blktap_ioctl(struct inode *inode, struct file *filp,
+ unsigned int cmd, unsigned long arg)
+{
+ switch(cmd) {
+ case BLKTAP_IOCTL_KICK_FE: /* There are fe messages to process. */
+ return blktap_read_fe_ring();
+
+ case BLKTAP_IOCTL_KICK_BE: /* There are be messages to process. */
+ return blktap_read_be_ring();
+
+ case BLKTAP_IOCTL_SETMODE:
+ if (BLKTAP_MODE_VALID(arg)) {
+ blktap_mode = arg;
+ /* XXX: may need to flush rings here. */
+ printk(KERN_INFO "blktap: set mode to %lx\n", arg);
+ return 0;
+ }
+ case BLKTAP_IOCTL_PRINT_IDXS:
+ {
+ print_be_ring_idxs();
+ print_fe_ring_idxs();
+ WPRINTK("User Rings: \n-----------\n");
+ WPRINTK("UF: rsp_cons: %2d, req_prod_prv: %2d "
+ "| req_prod: %2d, rsp_prod: %2d\n",
+ blktap_ufe_ring.rsp_cons,
+ blktap_ufe_ring.req_prod_pvt,
+ blktap_ufe_ring.sring->req_prod,
+ blktap_ufe_ring.sring->rsp_prod);
+ WPRINTK("UB: req_cons: %2d, rsp_prod_prv: %2d "
+ "| req_prod: %2d, rsp_prod: %2d\n",
+ blktap_ube_ring.req_cons,
+ blktap_ube_ring.rsp_prod_pvt,
+ blktap_ube_ring.sring->req_prod,
+ blktap_ube_ring.sring->rsp_prod);
+
+ }
+ }
+ return -ENOIOCTLCMD;
+}
+
+static unsigned int blktap_poll(struct file *file, poll_table *wait)
+{
+ poll_wait(file, &blktap_wait, wait);
+
+ if ( RING_HAS_UNPUSHED_REQUESTS(&blktap_uctrl_ring) ||
+ RING_HAS_UNPUSHED_REQUESTS(&blktap_ufe_ring) ||
+ RING_HAS_UNPUSHED_RESPONSES(&blktap_ube_ring) ) {
+
+ RING_PUSH_REQUESTS(&blktap_uctrl_ring);
+ RING_PUSH_REQUESTS(&blktap_ufe_ring);
+ RING_PUSH_RESPONSES(&blktap_ube_ring);
+ return POLLIN | POLLRDNORM;
+ }
+
+ return 0;
+}
+
+void blktap_kick_user(void)
+{
+ /* blktap_ring->req_prod = blktap_req_prod; */
+ wake_up_interruptible(&blktap_wait);
+}
+
+static struct file_operations blktap_fops = {
+ owner: THIS_MODULE,
+ poll: blktap_poll,
+ ioctl: blktap_ioctl,
+ open: blktap_open,
+ release: blktap_release,
+ mmap: blktap_mmap,
+};
+
+/*-----[ Data to/from user space ]----------------------------------------*/
+
+
+int blktap_write_fe_ring(blkif_request_t *req)
+{
+ blkif_request_t *target;
+ int error, i;
+
+ /*
+ * This is called to pass a request from the real frontend domain's
+ * blkif ring to the character device.
+ */
+
+ if ( ! blktap_ring_ok ) {
+ DPRINTK("blktap: ufe_ring not ready for a request!\n");
+ return 0;
+ }
+
+ if ( RING_FULL(&blktap_ufe_ring) ) {
+ PRINTK("blktap: fe_ring is full, can't add.\n");
+ return 0;
+ }
+
+ target = RING_GET_REQUEST(&blktap_ufe_ring,
+ blktap_ufe_ring.req_prod_pvt);
+ memcpy(target, req, sizeof(*req));
+
+ /* Attempt to map the foreign pages directly in to the application */
+ for (i=0; i<target->nr_segments; i++) {
+
+ error = direct_remap_area_pages(blktap_vma->vm_mm,
+ MMAP_VADDR(ID_TO_IDX(req->id), i),
+ target->frame_and_sects[i] & PAGE_MASK,
+ PAGE_SIZE,
+ blktap_vma->vm_page_prot,
+ ID_TO_DOM(req->id));
+ if ( error != 0 ) {
+ printk(KERN_INFO "remapping attached page failed! (%d)\n", error);
+ /* the request is now dropped on the floor. */
+ return 0;
+ }
+ }
+
+ blktap_ufe_ring.req_prod_pvt++;
+
+ return 0;
+}
+
+int blktap_write_be_ring(blkif_response_t *rsp)
+{
+ blkif_response_t *target;
+
+ /*
+ * This is called to pass a request from the real backend domain's
+ * blkif ring to the character device.
+ */
+
+ if ( ! blktap_ring_ok ) {
+ DPRINTK("blktap: be_ring not ready for a request!\n");
+ return 0;
+ }
+
+ /* No test for fullness in the response direction. */
+
+ target = RING_GET_RESPONSE(&blktap_ube_ring,
+ blktap_ube_ring.rsp_prod_pvt);
+ memcpy(target, rsp, sizeof(*rsp));
+
+ /* no mapping -- pages were mapped in blktap_write_fe_ring() */
+
+ blktap_ube_ring.rsp_prod_pvt++;
+
+ return 0;
+}
+
+static int blktap_read_fe_ring(void)
+{
+ /* This is called to read responses from the UFE ring. */
+
+ RING_IDX i, rp;
+ blkif_response_t *resp_s;
+ blkif_t *blkif;
+ active_req_t *ar;
+
+ DPRINTK("blktap_read_fe_ring()\n");
+
+ /* if we are forwarding from UFERring to FERing */
+ if (blktap_mode & BLKTAP_MODE_INTERCEPT_FE) {
+
+ /* for each outstanding message on the UFEring */
+ rp = blktap_ufe_ring.sring->rsp_prod;
+ rmb();
+
+ for ( i = blktap_ufe_ring.rsp_cons; i != rp; i++ )
+ {
+ resp_s = RING_GET_RESPONSE(&blktap_ufe_ring, i);
+
+ DPRINTK("resp->fe_ring\n");
+ ar = lookup_active_req(ID_TO_IDX(resp_s->id));
+ blkif = ar->blkif;
+ zap_page_range(blktap_vma, MMAP_VADDR(ID_TO_IDX(resp_s->id), 0),
+ ar->nr_pages << PAGE_SHIFT, NULL);
+ write_resp_to_fe_ring(blkif, resp_s);
+ blktap_ufe_ring.rsp_cons = i + 1;
+ kick_fe_domain(blkif);
+ }
+ }
+ return 0;
+}
+
+static int blktap_read_be_ring(void)
+{
+ /* This is called to read requests from the UBE ring. */
+
+ RING_IDX i, rp;
+ blkif_request_t *req_s;
+
+ DPRINTK("blktap_read_be_ring()\n");
+
+ /* if we are forwarding from UFERring to FERing */
+ if (blktap_mode & BLKTAP_MODE_INTERCEPT_BE) {
+
+ /* for each outstanding message on the UFEring */
+ rp = blktap_ube_ring.sring->req_prod;
+ rmb();
+ for ( i = blktap_ube_ring.req_cons; i != rp; i++ )
+ {
+ req_s = RING_GET_REQUEST(&blktap_ube_ring, i);
+
+ DPRINTK("req->be_ring\n");
+ write_req_to_be_ring(req_s);
+ kick_be_domain();
+ }
+
+ blktap_ube_ring.req_cons = i;
+ }
+
+ return 0;
+}
+
+int blktap_write_ctrl_ring(ctrl_msg_t *msg)
+{
+ ctrl_msg_t *target;
+
+ if ( ! blktap_ring_ok ) {
+ DPRINTK("blktap: be_ring not ready for a request!\n");
+ return 0;
+ }
+
+ /* No test for fullness in the response direction. */
+
+ target = RING_GET_REQUEST(&blktap_uctrl_ring,
+ blktap_uctrl_ring.req_prod_pvt);
+ memcpy(target, msg, sizeof(*msg));
+
+ blktap_uctrl_ring.req_prod_pvt++;
+
+ /* currently treat the ring as unidirectional. */
+ blktap_uctrl_ring.rsp_cons = blktap_uctrl_ring.sring->rsp_prod;
+
+ return 0;
+
+}
+
+/* -------[ blktap module setup ]------------------------------------- */
+
+static struct miscdevice blktap_miscdev = {
+ .minor = BLKTAP_MINOR,
+ .name = "blktap",
+ .fops = &blktap_fops,
+ .devfs_name = "misc/blktap",
+};
+
+int blktap_init(void)
+{
+ int err;
+
+ err = misc_register(&blktap_miscdev);
+ if ( err != 0 )
+ {
+ printk(KERN_ALERT "Couldn't register /dev/misc/blktap (%d)\n", err);
+ return err;
+ }
+
+ init_waitqueue_head(&blktap_wait);
+
+
+ return 0;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/kernel/signal.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/kernel/signal.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,717 @@
+/*
+ * linux/arch/i386/kernel/signal.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson
+ * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/errno.h>
+#include <linux/wait.h>
+#include <linux/ptrace.h>
+#include <linux/unistd.h>
+#include <linux/stddef.h>
+#include <linux/tty.h>
+#include <linux/personality.h>
+#include <asm/ucontext.h>
+#include <asm/uaccess.h>
+#include <asm/i387.h>
+
+#define DEBUG_SIG 0
+
+#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
+
+int FASTCALL(do_signal(struct pt_regs *regs, sigset_t *oldset));
+
+int copy_siginfo_to_user(siginfo_t *to, siginfo_t *from)
+{
+ if (!access_ok (VERIFY_WRITE, to, sizeof(siginfo_t)))
+ return -EFAULT;
+ if (from->si_code < 0)
+ return __copy_to_user(to, from, sizeof(siginfo_t));
+ else {
+ int err;
+
+ /* If you change siginfo_t structure, please be sure
+ this code is fixed accordingly.
+ It should never copy any pad contained in the structure
+ to avoid security leaks, but must copy the generic
+ 3 ints plus the relevant union member. */
+ err = __put_user(from->si_signo, &to->si_signo);
+ err |= __put_user(from->si_errno, &to->si_errno);
+ err |= __put_user((short)from->si_code, &to->si_code);
+ /* First 32bits of unions are always present. */
+ err |= __put_user(from->si_pid, &to->si_pid);
+ switch (from->si_code >> 16) {
+ case __SI_FAULT >> 16:
+ break;
+ case __SI_CHLD >> 16:
+ err |= __put_user(from->si_utime, &to->si_utime);
+ err |= __put_user(from->si_stime, &to->si_stime);
+ err |= __put_user(from->si_status, &to->si_status);
+ default:
+ err |= __put_user(from->si_uid, &to->si_uid);
+ break;
+ /* case __SI_RT: This is not generated by the kernel as of now.
*/
+ }
+ return err;
+ }
+}
+
+/*
+ * Atomically swap in the new signal mask, and wait for a signal.
+ */
+asmlinkage int
+sys_sigsuspend(int history0, int history1, old_sigset_t mask)
+{
+ struct pt_regs * regs = (struct pt_regs *) &history0;
+ sigset_t saveset;
+
+ mask &= _BLOCKABLE;
+ spin_lock_irq(¤t->sigmask_lock);
+ saveset = current->blocked;
+ siginitset(¤t->blocked, mask);
+ recalc_sigpending(current);
+ spin_unlock_irq(¤t->sigmask_lock);
+
+ regs->eax = -EINTR;
+ while (1) {
+ current->state = TASK_INTERRUPTIBLE;
+ schedule();
+ if (do_signal(regs, &saveset))
+ return -EINTR;
+ }
+}
+
+asmlinkage int
+sys_rt_sigsuspend(sigset_t *unewset, size_t sigsetsize)
+{
+ struct pt_regs * regs = (struct pt_regs *) &unewset;
+ sigset_t saveset, newset;
+
+ /* XXX: Don't preclude handling different sized sigset_t's. */
+ if (sigsetsize != sizeof(sigset_t))
+ return -EINVAL;
+
+ if (copy_from_user(&newset, unewset, sizeof(newset)))
+ return -EFAULT;
+ sigdelsetmask(&newset, ~_BLOCKABLE);
+
+ spin_lock_irq(¤t->sigmask_lock);
+ saveset = current->blocked;
+ current->blocked = newset;
+ recalc_sigpending(current);
+ spin_unlock_irq(¤t->sigmask_lock);
+
+ regs->eax = -EINTR;
+ while (1) {
+ current->state = TASK_INTERRUPTIBLE;
+ schedule();
+ if (do_signal(regs, &saveset))
+ return -EINTR;
+ }
+}
+
+asmlinkage int
+sys_sigaction(int sig, const struct old_sigaction *act,
+ struct old_sigaction *oact)
+{
+ struct k_sigaction new_ka, old_ka;
+ int ret;
+
+ if (act) {
+ old_sigset_t mask;
+ if (verify_area(VERIFY_READ, act, sizeof(*act)) ||
+ __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
+ __get_user(new_ka.sa.sa_restorer, &act->sa_restorer))
+ return -EFAULT;
+ __get_user(new_ka.sa.sa_flags, &act->sa_flags);
+ __get_user(mask, &act->sa_mask);
+ siginitset(&new_ka.sa.sa_mask, mask);
+ }
+
+ ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
+
+ if (!ret && oact) {
+ if (verify_area(VERIFY_WRITE, oact, sizeof(*oact)) ||
+ __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
+ __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer))
+ return -EFAULT;
+ __put_user(old_ka.sa.sa_flags, &oact->sa_flags);
+ __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
+ }
+
+ return ret;
+}
+
+asmlinkage int
+sys_sigaltstack(const stack_t *uss, stack_t *uoss)
+{
+ struct pt_regs *regs = (struct pt_regs *) &uss;
+ return do_sigaltstack(uss, uoss, regs->esp);
+}
+
+
+/*
+ * Do a signal return; undo the signal stack.
+ */
+
+struct sigframe
+{
+ char *pretcode;
+ int sig;
+ struct sigcontext sc;
+ struct _fpstate fpstate;
+ unsigned long extramask[_NSIG_WORDS-1];
+ char retcode[8];
+};
+
+struct rt_sigframe
+{
+ char *pretcode;
+ int sig;
+ struct siginfo *pinfo;
+ void *puc;
+ struct siginfo info;
+ struct ucontext uc;
+ struct _fpstate fpstate;
+ char retcode[8];
+};
+
+static int
+restore_sigcontext(struct pt_regs *regs, struct sigcontext *sc, int *peax)
+{
+ unsigned int err = 0;
+
+#define COPY(x) err |= __get_user(regs->x, &sc->x)
+
+#define COPY_SEG(seg) \
+ { unsigned short tmp; \
+ err |= __get_user(tmp, &sc->seg); \
+ regs->x##seg = tmp; }
+
+#define COPY_SEG_STRICT(seg) \
+ { unsigned short tmp; \
+ err |= __get_user(tmp, &sc->seg); \
+ regs->x##seg = tmp|3; }
+
+#define GET_SEG(seg) \
+ { unsigned short tmp; \
+ err |= __get_user(tmp, &sc->seg); \
+ loadsegment(seg,tmp); }
+
+ GET_SEG(gs);
+ GET_SEG(fs);
+ COPY_SEG(es);
+ COPY_SEG(ds);
+ COPY(edi);
+ COPY(esi);
+ COPY(ebp);
+ COPY(esp);
+ COPY(ebx);
+ COPY(edx);
+ COPY(ecx);
+ COPY(eip);
+ COPY_SEG_STRICT(cs);
+ COPY_SEG_STRICT(ss);
+
+ {
+ unsigned int tmpflags;
+ err |= __get_user(tmpflags, &sc->eflags);
+ regs->eflags = (regs->eflags & ~0x40DD5) | (tmpflags & 0x40DD5);
+ regs->orig_eax = -1; /* disable syscall checks */
+ }
+
+ {
+ struct _fpstate * buf;
+ err |= __get_user(buf, &sc->fpstate);
+ if (buf) {
+ if (verify_area(VERIFY_READ, buf, sizeof(*buf)))
+ goto badframe;
+ err |= restore_i387(buf);
+ }
+ }
+
+ err |= __get_user(*peax, &sc->eax);
+ return err;
+
+badframe:
+ return 1;
+}
+
+asmlinkage int sys_sigreturn(unsigned long __unused)
+{
+ struct pt_regs *regs = (struct pt_regs *) &__unused;
+ struct sigframe *frame = (struct sigframe *)(regs->esp - 8);
+ sigset_t set;
+ int eax;
+
+ if (verify_area(VERIFY_READ, frame, sizeof(*frame)))
+ goto badframe;
+ if (__get_user(set.sig[0], &frame->sc.oldmask)
+ || (_NSIG_WORDS > 1
+ && __copy_from_user(&set.sig[1], &frame->extramask,
+ sizeof(frame->extramask))))
+ goto badframe;
+
+ sigdelsetmask(&set, ~_BLOCKABLE);
+ spin_lock_irq(¤t->sigmask_lock);
+ current->blocked = set;
+ recalc_sigpending(current);
+ spin_unlock_irq(¤t->sigmask_lock);
+
+ if (restore_sigcontext(regs, &frame->sc, &eax))
+ goto badframe;
+ return eax;
+
+badframe:
+ force_sig(SIGSEGV, current);
+ return 0;
+}
+
+asmlinkage int sys_rt_sigreturn(unsigned long __unused)
+{
+ struct pt_regs *regs = (struct pt_regs *) &__unused;
+ struct rt_sigframe *frame = (struct rt_sigframe *)(regs->esp - 4);
+ sigset_t set;
+ stack_t st;
+ int eax;
+
+ if (verify_area(VERIFY_READ, frame, sizeof(*frame)))
+ goto badframe;
+ if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+ goto badframe;
+
+ sigdelsetmask(&set, ~_BLOCKABLE);
+ spin_lock_irq(¤t->sigmask_lock);
+ current->blocked = set;
+ recalc_sigpending(current);
+ spin_unlock_irq(¤t->sigmask_lock);
+
+ if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &eax))
+ goto badframe;
+
+ if (__copy_from_user(&st, &frame->uc.uc_stack, sizeof(st)))
+ goto badframe;
+ /* It is more difficult to avoid calling this function than to
+ call it and ignore errors. */
+ do_sigaltstack(&st, NULL, regs->esp);
+
+ return eax;
+
+badframe:
+ force_sig(SIGSEGV, current);
+ return 0;
+}
+
+/*
+ * Set up a signal frame.
+ */
+
+static int
+setup_sigcontext(struct sigcontext *sc, struct _fpstate *fpstate,
+ struct pt_regs *regs, unsigned long mask)
+{
+ int tmp, err = 0;
+
+ tmp = 0;
+ __asm__("movl %%gs,%0" : "=r"(tmp): "0"(tmp));
+ err |= __put_user(tmp, (unsigned int *)&sc->gs);
+ __asm__("movl %%fs,%0" : "=r"(tmp): "0"(tmp));
+ err |= __put_user(tmp, (unsigned int *)&sc->fs);
+
+ err |= __put_user(regs->xes, (unsigned int *)&sc->es);
+ err |= __put_user(regs->xds, (unsigned int *)&sc->ds);
+ err |= __put_user(regs->edi, &sc->edi);
+ err |= __put_user(regs->esi, &sc->esi);
+ err |= __put_user(regs->ebp, &sc->ebp);
+ err |= __put_user(regs->esp, &sc->esp);
+ err |= __put_user(regs->ebx, &sc->ebx);
+ err |= __put_user(regs->edx, &sc->edx);
+ err |= __put_user(regs->ecx, &sc->ecx);
+ err |= __put_user(regs->eax, &sc->eax);
+ err |= __put_user(current->thread.trap_no, &sc->trapno);
+ err |= __put_user(current->thread.error_code, &sc->err);
+ err |= __put_user(regs->eip, &sc->eip);
+ err |= __put_user(regs->xcs, (unsigned int *)&sc->cs);
+ err |= __put_user(regs->eflags, &sc->eflags);
+ err |= __put_user(regs->esp, &sc->esp_at_signal);
+ err |= __put_user(regs->xss, (unsigned int *)&sc->ss);
+
+ tmp = save_i387(fpstate);
+ if (tmp < 0)
+ err = 1;
+ else
+ err |= __put_user(tmp ? fpstate : NULL, &sc->fpstate);
+
+ /* non-iBCS2 extensions.. */
+ err |= __put_user(mask, &sc->oldmask);
+ err |= __put_user(current->thread.cr2, &sc->cr2);
+
+ return err;
+}
+
+/*
+ * Determine which stack to use..
+ */
+static inline void *
+get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size)
+{
+ unsigned long esp;
+
+ /* Default to using normal stack */
+ esp = regs->esp;
+
+ /* This is the X/Open sanctioned signal stack switching. */
+ if (ka->sa.sa_flags & SA_ONSTACK) {
+ if (sas_ss_flags(esp) == 0)
+ esp = current->sas_ss_sp + current->sas_ss_size;
+ }
+
+ /* This is the legacy signal stack switching. */
+ else if ((regs->xss & 0xffff) != __USER_DS &&
+ !(ka->sa.sa_flags & SA_RESTORER) &&
+ ka->sa.sa_restorer) {
+ esp = (unsigned long) ka->sa.sa_restorer;
+ }
+
+ return (void *)((esp - frame_size) & -8ul);
+}
+
+static void setup_frame(int sig, struct k_sigaction *ka,
+ sigset_t *set, struct pt_regs * regs)
+{
+ struct sigframe *frame;
+ int err = 0;
+
+ frame = get_sigframe(ka, regs, sizeof(*frame));
+
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ goto give_sigsegv;
+
+ err |= __put_user((current->exec_domain
+ && current->exec_domain->signal_invmap
+ && sig < 32
+ ? current->exec_domain->signal_invmap[sig]
+ : sig),
+ &frame->sig);
+ if (err)
+ goto give_sigsegv;
+
+ err |= setup_sigcontext(&frame->sc, &frame->fpstate, regs, set->sig[0]);
+ if (err)
+ goto give_sigsegv;
+
+ if (_NSIG_WORDS > 1) {
+ err |= __copy_to_user(frame->extramask, &set->sig[1],
+ sizeof(frame->extramask));
+ }
+ if (err)
+ goto give_sigsegv;
+
+ /* Set up to return from userspace. If provided, use a stub
+ already in userspace. */
+ if (ka->sa.sa_flags & SA_RESTORER) {
+ err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
+ } else {
+ err |= __put_user(frame->retcode, &frame->pretcode);
+ /* This is popl %eax ; movl $,%eax ; int $0x80 */
+ err |= __put_user(0xb858, (short *)(frame->retcode+0));
+ err |= __put_user(__NR_sigreturn, (int *)(frame->retcode+2));
+ err |= __put_user(0x80cd, (short *)(frame->retcode+6));
+ }
+
+ if (err)
+ goto give_sigsegv;
+
+ /* Set up registers for signal handler */
+ regs->esp = (unsigned long) frame;
+ regs->eip = (unsigned long) ka->sa.sa_handler;
+
+ set_fs(USER_DS);
+ regs->xds = __USER_DS;
+ regs->xes = __USER_DS;
+ regs->xss = __USER_DS;
+ regs->xcs = __USER_CS;
+ regs->eflags &= ~TF_MASK;
+
+#if DEBUG_SIG
+ printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n",
+ current->comm, current->pid, frame, regs->eip, frame->pretcode);
+#endif
+
+ return;
+
+give_sigsegv:
+ if (sig == SIGSEGV)
+ ka->sa.sa_handler = SIG_DFL;
+ force_sig(SIGSEGV, current);
+}
+
+static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+ sigset_t *set, struct pt_regs * regs)
+{
+ struct rt_sigframe *frame;
+ int err = 0;
+
+ frame = get_sigframe(ka, regs, sizeof(*frame));
+
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ goto give_sigsegv;
+
+ err |= __put_user((current->exec_domain
+ && current->exec_domain->signal_invmap
+ && sig < 32
+ ? current->exec_domain->signal_invmap[sig]
+ : sig),
+ &frame->sig);
+ err |= __put_user(&frame->info, &frame->pinfo);
+ err |= __put_user(&frame->uc, &frame->puc);
+ err |= copy_siginfo_to_user(&frame->info, info);
+ if (err)
+ goto give_sigsegv;
+
+ /* Create the ucontext. */
+ err |= __put_user(0, &frame->uc.uc_flags);
+ err |= __put_user(0, &frame->uc.uc_link);
+ err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ err |= __put_user(sas_ss_flags(regs->esp),
+ &frame->uc.uc_stack.ss_flags);
+ err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate,
+ regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+ if (err)
+ goto give_sigsegv;
+
+ /* Set up to return from userspace. If provided, use a stub
+ already in userspace. */
+ if (ka->sa.sa_flags & SA_RESTORER) {
+ err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
+ } else {
+ err |= __put_user(frame->retcode, &frame->pretcode);
+ /* This is movl $,%eax ; int $0x80 */
+ err |= __put_user(0xb8, (char *)(frame->retcode+0));
+ err |= __put_user(__NR_rt_sigreturn, (int *)(frame->retcode+1));
+ err |= __put_user(0x80cd, (short *)(frame->retcode+5));
+ }
+
+ if (err)
+ goto give_sigsegv;
+
+ /* Set up registers for signal handler */
+ regs->esp = (unsigned long) frame;
+ regs->eip = (unsigned long) ka->sa.sa_handler;
+
+ set_fs(USER_DS);
+ regs->xds = __USER_DS;
+ regs->xes = __USER_DS;
+ regs->xss = __USER_DS;
+ regs->xcs = __USER_CS;
+ regs->eflags &= ~TF_MASK;
+
+#if DEBUG_SIG
+ printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n",
+ current->comm, current->pid, frame, regs->eip, frame->pretcode);
+#endif
+
+ return;
+
+give_sigsegv:
+ if (sig == SIGSEGV)
+ ka->sa.sa_handler = SIG_DFL;
+ force_sig(SIGSEGV, current);
+}
+
+/*
+ * OK, we're invoking a handler
+ */
+
+static void
+handle_signal(unsigned long sig, struct k_sigaction *ka,
+ siginfo_t *info, sigset_t *oldset, struct pt_regs * regs)
+{
+ /* Are we from a system call? */
+ if (regs->orig_eax >= 0) {
+ /* If so, check system call restarting.. */
+ switch (regs->eax) {
+ case -ERESTARTNOHAND:
+ regs->eax = -EINTR;
+ break;
+
+ case -ERESTARTSYS:
+ if (!(ka->sa.sa_flags & SA_RESTART)) {
+ regs->eax = -EINTR;
+ break;
+ }
+ /* fallthrough */
+ case -ERESTARTNOINTR:
+ regs->eax = regs->orig_eax;
+ regs->eip -= 2;
+ }
+ }
+
+ /* Set up the stack frame */
+ if (ka->sa.sa_flags & SA_SIGINFO)
+ setup_rt_frame(sig, ka, info, oldset, regs);
+ else
+ setup_frame(sig, ka, oldset, regs);
+
+ if (ka->sa.sa_flags & SA_ONESHOT)
+ ka->sa.sa_handler = SIG_DFL;
+
+ if (!(ka->sa.sa_flags & SA_NODEFER)) {
+ spin_lock_irq(¤t->sigmask_lock);
+ sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask);
+ sigaddset(¤t->blocked,sig);
+ recalc_sigpending(current);
+ spin_unlock_irq(¤t->sigmask_lock);
+ }
+}
+
+/*
+ * Note that 'init' is a special process: it doesn't get signals it doesn't
+ * want to handle. Thus you cannot kill init even with a SIGKILL even by
+ * mistake.
+ */
+int fastcall do_signal(struct pt_regs *regs, sigset_t *oldset)
+{
+ siginfo_t info;
+ struct k_sigaction *ka;
+
+ /*
+ * We want the common case to go fast, which
+ * is why we may in certain cases get here from
+ * kernel mode. Just return without doing anything
+ * if so.
+ */
+ if ((regs->xcs & 2) != 2)
+ return 1;
+
+ if (!oldset)
+ oldset = ¤t->blocked;
+
+ for (;;) {
+ unsigned long signr;
+
+ spin_lock_irq(¤t->sigmask_lock);
+ signr = dequeue_signal(¤t->blocked, &info);
+ spin_unlock_irq(¤t->sigmask_lock);
+
+ if (!signr)
+ break;
+
+ if ((current->ptrace & PT_PTRACED) && signr != SIGKILL) {
+ /* Let the debugger run. */
+ current->exit_code = signr;
+ current->state = TASK_STOPPED;
+ notify_parent(current, SIGCHLD);
+ schedule();
+
+ /* We're back. Did the debugger cancel the sig? */
+ if (!(signr = current->exit_code))
+ continue;
+ current->exit_code = 0;
+
+ /* The debugger continued. Ignore SIGSTOP. */
+ if (signr == SIGSTOP)
+ continue;
+
+ /* Update the siginfo structure. Is this good? */
+ if (signr != info.si_signo) {
+ info.si_signo = signr;
+ info.si_errno = 0;
+ info.si_code = SI_USER;
+ info.si_pid = current->p_pptr->pid;
+ info.si_uid = current->p_pptr->uid;
+ }
+
+ /* If the (new) signal is now blocked, requeue it. */
+ if (sigismember(¤t->blocked, signr)) {
+ send_sig_info(signr, &info, current);
+ continue;
+ }
+ }
+
+ ka = ¤t->sig->action[signr-1];
+ if (ka->sa.sa_handler == SIG_IGN) {
+ if (signr != SIGCHLD)
+ continue;
+ /* Check for SIGCHLD: it's special. */
+ while (sys_wait4(-1, NULL, WNOHANG, NULL) > 0)
+ /* nothing */;
+ continue;
+ }
+
+ if (ka->sa.sa_handler == SIG_DFL) {
+ int exit_code = signr;
+
+ /* Init gets no signals it doesn't want. */
+ if (current->pid == 1)
+ continue;
+
+ switch (signr) {
+ case SIGCONT: case SIGCHLD: case SIGWINCH: case SIGURG:
+ continue;
+
+ case SIGTSTP: case SIGTTIN: case SIGTTOU:
+ if (is_orphaned_pgrp(current->pgrp))
+ continue;
+ /* FALLTHRU */
+
+ case SIGSTOP: {
+ struct signal_struct *sig;
+ current->state = TASK_STOPPED;
+ current->exit_code = signr;
+ sig = current->p_pptr->sig;
+ if (sig && !(sig->action[SIGCHLD-1].sa.sa_flags
& SA_NOCLDSTOP))
+ notify_parent(current, SIGCHLD);
+ schedule();
+ continue;
+ }
+
+ case SIGQUIT: case SIGILL: case SIGTRAP:
+ case SIGABRT: case SIGFPE: case SIGSEGV:
+ case SIGBUS: case SIGSYS: case SIGXCPU: case SIGXFSZ:
+ if (do_coredump(signr, regs))
+ exit_code |= 0x80;
+ /* FALLTHRU */
+
+ default:
+ sig_exit(signr, exit_code, &info);
+ /* NOTREACHED */
+ }
+ }
+
+ /* Reenable any watchpoints before delivering the
+ * signal to user space. The processor register will
+ * have been cleared if the watchpoint triggered
+ * inside the kernel.
+ */
+ if ( current->thread.debugreg[7] != 0 )
+ HYPERVISOR_set_debugreg(7, current->thread.debugreg[7]);
+
+ /* Whee! Actually deliver the signal. */
+ handle_signal(signr, ka, &info, oldset, regs);
+ return 1;
+ }
+
+ /* Did we come from a system call? */
+ if (regs->orig_eax >= 0) {
+ /* Restart the system call - no handlers present */
+ if (regs->eax == -ERESTARTNOHAND ||
+ regs->eax == -ERESTARTSYS ||
+ regs->eax == -ERESTARTNOINTR) {
+ regs->eax = regs->orig_eax;
+ regs->eip -= 2;
+ }
+ }
+ return 0;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/keyboard.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/keyboard.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,74 @@
+/*
+ * linux/include/asm-i386/keyboard.h
+ *
+ * Created 3 Nov 1996 by Geert Uytterhoeven
+ */
+
+/*
+ * This file contains the i386 architecture specific keyboard definitions
+ */
+
+#ifndef _I386_KEYBOARD_H
+#define _I386_KEYBOARD_H
+
+#ifdef __KERNEL__
+
+#include <linux/kernel.h>
+#include <linux/ioport.h>
+#include <linux/kd.h>
+#include <linux/pm.h>
+#include <asm/io.h>
+
+#define KEYBOARD_IRQ 1
+#define DISABLE_KBD_DURING_INTERRUPTS 0
+
+extern int pckbd_setkeycode(unsigned int scancode, unsigned int keycode);
+extern int pckbd_getkeycode(unsigned int scancode);
+extern int pckbd_translate(unsigned char scancode, unsigned char *keycode,
+ char raw_mode);
+extern char pckbd_unexpected_up(unsigned char keycode);
+extern void pckbd_leds(unsigned char leds);
+extern void pckbd_init_hw(void);
+extern int pckbd_pm_resume(struct pm_dev *, pm_request_t, void *);
+extern pm_callback pm_kbd_request_override;
+extern unsigned char pckbd_sysrq_xlate[128];
+
+#define kbd_setkeycode pckbd_setkeycode
+#define kbd_getkeycode pckbd_getkeycode
+#define kbd_translate pckbd_translate
+#define kbd_unexpected_up pckbd_unexpected_up
+#define kbd_leds pckbd_leds
+#define kbd_init_hw pckbd_init_hw
+#define kbd_sysrq_xlate pckbd_sysrq_xlate
+
+#define SYSRQ_KEY 0x54
+
+#define kbd_controller_present() (xen_start_info.flags & SIF_INITDOMAIN)
+
+/* resource allocation */
+#define kbd_request_region()
+#define kbd_request_irq(handler) request_irq(KEYBOARD_IRQ, handler, 0, \
+ "keyboard", NULL)
+
+/* How to access the keyboard macros on this platform. */
+#define kbd_read_input() inb(KBD_DATA_REG)
+#define kbd_read_status() inb(KBD_STATUS_REG)
+#define kbd_write_output(val) outb(val, KBD_DATA_REG)
+#define kbd_write_command(val) outb(val, KBD_CNTL_REG)
+
+/* Some stoneage hardware needs delays after some operations. */
+#define kbd_pause() do { } while(0)
+
+/*
+ * Machine specific bits for the PS/2 driver
+ */
+
+#define AUX_IRQ 12
+
+#define aux_request_irq(hand, dev_id) \
+ request_irq(AUX_IRQ, hand, SA_SHIRQ, "PS/2 Mouse", dev_id)
+
+#define aux_free_irq(dev_id) free_irq(AUX_IRQ, dev_id)
+
+#endif /* __KERNEL__ */
+#endif /* _I386_KEYBOARD_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/mmu_context.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/mmu_context.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,126 @@
+#ifndef __X86_64_MMU_CONTEXT_H
+#define __X86_64_MMU_CONTEXT_H
+
+#include <linux/config.h>
+#include <asm/desc.h>
+#include <asm/atomic.h>
+#include <asm/pgalloc.h>
+#include <asm/page.h>
+#include <asm/pda.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+
+/*
+ * possibly do the LDT unload here?
+ */
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
+void destroy_context(struct mm_struct *mm);
+
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct
*tsk)
+{
+#if 0 /* XEN: no lazy tlb */
+ if (read_pda(mmu_state) == TLBSTATE_OK)
+ write_pda(mmu_state, TLBSTATE_LAZY);
+#endif
+}
+
+#define prepare_arch_switch(rq,next) __prepare_arch_switch()
+#define finish_arch_switch(rq, next) spin_unlock_irq(&(rq)->lock)
+#define task_running(rq, p) ((rq)->curr == (p))
+
+static inline void __prepare_arch_switch(void)
+{
+ /*
+ * Save away %es, %ds, %fs and %gs. Must happen before reload
+ * of cr3/ldt (i.e., not in __switch_to).
+ */
+ __asm__ __volatile__ (
+ "movl %%es,%0 ; movl %%ds,%1 ; movl %%fs,%2 ; movl %%gs,%3"
+ : "=m" (current->thread.es),
+ "=m" (current->thread.ds),
+ "=m" (current->thread.fsindex),
+ "=m" (current->thread.gsindex) );
+
+ if (current->thread.ds)
+ __asm__ __volatile__ ( "movl %0,%%ds" : : "r" (0) );
+
+ if (current->thread.es)
+ __asm__ __volatile__ ( "movl %0,%%es" : : "r" (0) );
+
+ if (current->thread.fsindex) {
+ __asm__ __volatile__ ( "movl %0,%%fs" : : "r" (0) );
+ current->thread.fs = 0;
+ }
+
+ if (current->thread.gsindex) {
+ load_gs_index(0);
+ current->thread.gs = 0;
+ }
+}
+
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+ struct task_struct *tsk)
+{
+ unsigned cpu = smp_processor_id();
+ struct mmuext_op _op[3], *op = _op;
+
+ if (likely(prev != next)) {
+ /* stop flush ipis for the previous mm */
+ clear_bit(cpu, &prev->cpu_vm_mask);
+#if 0 /* XEN: no lazy tlb */
+ write_pda(mmu_state, TLBSTATE_OK);
+ write_pda(active_mm, next);
+#endif
+ set_bit(cpu, &next->cpu_vm_mask);
+
+ /* load_cr3(next->pgd) */
+ per_cpu(cur_pgd, smp_processor_id()) = next->pgd;
+ op->cmd = MMUEXT_NEW_BASEPTR;
+ op->mfn = pfn_to_mfn(__pa(next->pgd) >> PAGE_SHIFT);
+ op++;
+
+ /* xen_new_user_pt(__pa(__user_pgd(next->pgd))) */
+ op->cmd = MMUEXT_NEW_USER_BASEPTR;
+ op->mfn = pfn_to_mfn(__pa(__user_pgd(next->pgd)) >> PAGE_SHIFT);
+ op++;
+
+ if (unlikely(next->context.ldt != prev->context.ldt)) {
+ /* load_LDT_nolock(&next->context, cpu) */
+ op->cmd = MMUEXT_SET_LDT;
+ op->linear_addr = (unsigned long)next->context.ldt;
+ op->nr_ents = next->context.size;
+ op++;
+ }
+
+ BUG_ON(HYPERVISOR_mmuext_op(_op, op-_op, NULL, DOMID_SELF));
+ }
+
+#if 0 /* XEN: no lazy tlb */
+ else {
+ write_pda(mmu_state, TLBSTATE_OK);
+ if (read_pda(active_mm) != next)
+ out_of_line_bug();
+ if(!test_and_set_bit(cpu, &next->cpu_vm_mask)) {
+ /* We were in lazy tlb mode and leave_mm disabled
+ * tlb flush IPI delivery. We must reload CR3
+ * to make sure to use no freed page tables.
+ */
+ load_cr3(next->pgd);
+ xen_new_user_pt(__pa(__user_pgd(next->pgd)));
+ load_LDT_nolock(&next->context, cpu);
+ }
+ }
+#endif
+}
+
+#define deactivate_mm(tsk,mm) do { \
+ load_gs_index(0); \
+ asm volatile("movl %0,%%fs"::"r"(0)); \
+} while(0)
+
+#define activate_mm(prev, next) do { \
+ switch_mm((prev),(next),NULL); \
+} while (0)
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/io_apic.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/io_apic.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,2051 @@
+/*
+ * Intel IO-APIC support for multi-Pentium hosts.
+ *
+ * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar, Hajnalka Szabo
+ *
+ * Many thanks to Stig Venaas for trying out countless experimental
+ * patches and reporting/debugging problems patiently!
+ *
+ * (c) 1999, Multiple IO-APIC support, developed by
+ * Ken-ichi Yaku <yaku@xxxxxxxxxxxxxxxxxxxx> and
+ * Hidemi Kishimoto <kisimoto@xxxxxxxxxxxxxxxxxxxx>,
+ * further tested and cleaned up by Zach Brown <zab@xxxxxxxxxx>
+ * and Ingo Molnar <mingo@xxxxxxxxxx>
+ *
+ * Fixes
+ * Maciej W. Rozycki : Bits for genuine 82489DX APICs;
+ * thanks to Eric Gilmore
+ * and Rolf G. Tews
+ * for testing these extensively
+ * Paul Diefenbaugh : Added full ACPI support
+ */
+
+#include <linux/mm.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/config.h>
+#include <linux/smp_lock.h>
+#include <linux/mc146818rtc.h>
+#include <linux/acpi.h>
+#include <linux/sysdev.h>
+
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/desc.h>
+#include <asm/proto.h>
+#include <asm/mach_apic.h>
+
+#define __apicdebuginit __init
+
+int sis_apic_bug; /* not actually supported, dummy for compile */
+
+static DEFINE_SPINLOCK(ioapic_lock);
+
+/*
+ * # of IRQ routing registers
+ */
+int nr_ioapic_registers[MAX_IO_APICS];
+
+/*
+ * Rough estimation of how many shared IRQs there are, can
+ * be changed anytime.
+ */
+#define MAX_PLUS_SHARED_IRQS NR_IRQS
+#define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS)
+
+/*
+ * This is performance-critical, we want to do it O(1)
+ *
+ * the indexing order of this array favors 1:1 mappings
+ * between pins and IRQs.
+ */
+
+static struct irq_pin_list {
+ short apic, pin, next;
+} irq_2_pin[PIN_MAP_SIZE];
+
+int vector_irq[NR_VECTORS] = { [0 ... NR_VECTORS - 1] = -1};
+#ifdef CONFIG_PCI_MSI
+#define vector_to_irq(vector) \
+ (platform_legacy_irq(vector) ? vector : vector_irq[vector])
+#else
+#define vector_to_irq(vector) (vector)
+#endif
+
+#ifdef CONFIG_XEN
+
+#include <asm-xen/xen-public/xen.h>
+#include <asm-xen/xen-public/physdev.h>
+
+/* Fake i8259 */
+#define make_8259A_irq(_irq) (io_apic_irqs &= ~(1UL<<(_irq)))
+#define disable_8259A_irq(_irq) ((void)0)
+#define i8259A_irq_pending(_irq) (0)
+
+unsigned long io_apic_irqs;
+
+static inline unsigned int xen_io_apic_read(unsigned int apic, unsigned int
reg)
+{
+ physdev_op_t op;
+ int ret;
+
+ op.cmd = PHYSDEVOP_APIC_READ;
+ op.u.apic_op.apic = mp_ioapics[apic].mpc_apicid;
+ op.u.apic_op.offset = reg;
+ ret = HYPERVISOR_physdev_op(&op);
+ if (ret)
+ return ret;
+ return op.u.apic_op.value;
+}
+
+static inline void xen_io_apic_write(unsigned int apic, unsigned int reg,
unsigned int value)
+{
+ physdev_op_t op;
+
+ op.cmd = PHYSDEVOP_APIC_WRITE;
+ op.u.apic_op.apic = mp_ioapics[apic].mpc_apicid;
+ op.u.apic_op.offset = reg;
+ op.u.apic_op.value = value;
+ HYPERVISOR_physdev_op(&op);
+}
+
+#define io_apic_read(a,r) xen_io_apic_read(a,r)
+#define io_apic_write(a,r,v) xen_io_apic_write(a,r,v)
+
+#define clear_IO_APIC() ((void)0)
+
+#endif /* !CONFIG_XEN */
+
+/*
+ * The common case is 1:1 IRQ<->pin mappings. Sometimes there are
+ * shared ISA-space IRQs, so we have to support them. We are super
+ * fast in the common case, and fast for shared ISA-space IRQs.
+ */
+static void add_pin_to_irq(unsigned int irq, int apic, int pin)
+{
+ static int first_free_entry = NR_IRQS;
+ struct irq_pin_list *entry = irq_2_pin + irq;
+
+ while (entry->next)
+ entry = irq_2_pin + entry->next;
+
+ if (entry->pin != -1) {
+ entry->next = first_free_entry;
+ entry = irq_2_pin + entry->next;
+ if (++first_free_entry >= PIN_MAP_SIZE)
+ panic("io_apic.c: whoops");
+ }
+ entry->apic = apic;
+ entry->pin = pin;
+}
+
+#ifndef CONFIG_XEN
+#define __DO_ACTION(R, ACTION, FINAL) \
+ \
+{ \
+ int pin; \
+ struct irq_pin_list *entry = irq_2_pin + irq; \
+ \
+ for (;;) { \
+ unsigned int reg; \
+ pin = entry->pin; \
+ if (pin == -1) \
+ break; \
+ reg = io_apic_read(entry->apic, 0x10 + R + pin*2); \
+ reg ACTION; \
+ io_apic_modify(entry->apic, reg); \
+ if (!entry->next) \
+ break; \
+ entry = irq_2_pin + entry->next; \
+ } \
+ FINAL; \
+}
+
+#define DO_ACTION(name,R,ACTION, FINAL)
\
+ \
+ static void name##_IO_APIC_irq (unsigned int irq) \
+ __DO_ACTION(R, ACTION, FINAL)
+
+DO_ACTION( __mask, 0, |= 0x00010000, io_apic_sync(entry->apic) )
+ /* mask = 1 */
+DO_ACTION( __unmask, 0, &= 0xfffeffff, )
+ /* mask = 0 */
+
+static void mask_IO_APIC_irq (unsigned int irq)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ __mask_IO_APIC_irq(irq);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+static void unmask_IO_APIC_irq (unsigned int irq)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ __unmask_IO_APIC_irq(irq);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
+{
+ struct IO_APIC_route_entry entry;
+ unsigned long flags;
+
+ /* Check delivery_mode to be sure we're not clearing an SMI pin */
+ spin_lock_irqsave(&ioapic_lock, flags);
+ *(((int*)&entry) + 0) = io_apic_read(apic, 0x10 + 2 * pin);
+ *(((int*)&entry) + 1) = io_apic_read(apic, 0x11 + 2 * pin);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ if (entry.delivery_mode == dest_SMI)
+ return;
+ /*
+ * Disable it in the IO-APIC irq-routing table:
+ */
+ memset(&entry, 0, sizeof(entry));
+ entry.mask = 1;
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(apic, 0x10 + 2 * pin, *(((int *)&entry) + 0));
+ io_apic_write(apic, 0x11 + 2 * pin, *(((int *)&entry) + 1));
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+static void clear_IO_APIC (void)
+{
+ int apic, pin;
+
+ for (apic = 0; apic < nr_ioapics; apic++)
+ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++)
+ clear_IO_APIC_pin(apic, pin);
+}
+
+#endif /* !CONFIG_XEN */
+
+/*
+ * support for broken MP BIOSs, enables hand-redirection of PIRQ0-7 to
+ * specific CPU-side IRQs.
+ */
+
+#define MAX_PIRQS 8
+int pirq_entries [MAX_PIRQS];
+int pirqs_enabled;
+int skip_ioapic_setup;
+int ioapic_force;
+
+/* dummy parsing: see setup.c */
+
+static int __init disable_ioapic_setup(char *str)
+{
+ skip_ioapic_setup = 1;
+ return 1;
+}
+
+static int __init enable_ioapic_setup(char *str)
+{
+ ioapic_force = 1;
+ skip_ioapic_setup = 0;
+ return 1;
+}
+
+
+__setup("noapic", disable_ioapic_setup);
+__setup("apic", enable_ioapic_setup);
+
+
+#include <asm/pci-direct.h>
+#include <linux/pci_ids.h>
+#include <linux/pci.h>
+
+/* Temporary Hack. Nvidia and VIA boards currently only work with IO-APIC
+ off. Check for an Nvidia or VIA PCI bridge and turn it off.
+ Use pci direct infrastructure because this runs before the PCI subsystem.
+
+ Can be overwritten with "apic"
+
+ And another hack to disable the IOMMU on VIA chipsets.
+
+ Kludge-O-Rama. */
+void __init check_ioapic(void)
+{
+ int num,slot,func;
+ if (ioapic_force)
+ return;
+
+ /* Poor man's PCI discovery */
+ for (num = 0; num < 32; num++) {
+ for (slot = 0; slot < 32; slot++) {
+ for (func = 0; func < 8; func++) {
+ u32 class;
+ u32 vendor;
+ u8 type;
+ class = read_pci_config(num,slot,func,
+ PCI_CLASS_REVISION);
+ if (class == 0xffffffff)
+ break;
+
+ if ((class >> 16) != PCI_CLASS_BRIDGE_PCI)
+ continue;
+
+ vendor = read_pci_config(num, slot, func,
+ PCI_VENDOR_ID);
+ vendor &= 0xffff;
+ switch (vendor) {
+ case PCI_VENDOR_ID_VIA:
+#ifdef CONFIG_GART_IOMMU
+ if ((end_pfn >=
(0xffffffff>>PAGE_SHIFT) ||
+ force_iommu) &&
+ !iommu_aperture_allowed) {
+ printk(KERN_INFO
+ "Looks like a VIA chipset. Disabling IOMMU. Overwrite with
\"iommu=allowed\"\n");
+ iommu_aperture_disabled = 1;
+ }
+#endif
+ return;
+ case PCI_VENDOR_ID_NVIDIA:
+#ifdef CONFIG_ACPI
+ /* All timer overrides on Nvidia
+ seem to be wrong. Skip them. */
+ acpi_skip_timer_override = 1;
+ printk(KERN_INFO
+ "Nvidia board detected. Ignoring ACPI timer override.\n");
+#endif
+ /* RED-PEN skip them on mptables too? */
+ return;
+ }
+
+ /* No multi-function device? */
+ type = read_pci_config_byte(num,slot,func,
+ PCI_HEADER_TYPE);
+ if (!(type & 0x80))
+ break;
+ }
+ }
+ }
+}
+
+static int __init ioapic_pirq_setup(char *str)
+{
+ int i, max;
+ int ints[MAX_PIRQS+1];
+
+ get_options(str, ARRAY_SIZE(ints), ints);
+
+ for (i = 0; i < MAX_PIRQS; i++)
+ pirq_entries[i] = -1;
+
+ pirqs_enabled = 1;
+ apic_printk(APIC_VERBOSE, "PIRQ redirection, working around broken
MP-BIOS.\n");
+ max = MAX_PIRQS;
+ if (ints[0] < MAX_PIRQS)
+ max = ints[0];
+
+ for (i = 0; i < max; i++) {
+ apic_printk(APIC_VERBOSE, "... PIRQ%d -> IRQ %d\n", i,
ints[i+1]);
+ /*
+ * PIRQs are mapped upside down, usually.
+ */
+ pirq_entries[MAX_PIRQS-i-1] = ints[i+1];
+ }
+ return 1;
+}
+
+__setup("pirq=", ioapic_pirq_setup);
+
+/*
+ * Find the IRQ entry number of a certain pin.
+ */
+static int find_irq_entry(int apic, int pin, int type)
+{
+ int i;
+
+ for (i = 0; i < mp_irq_entries; i++)
+ if (mp_irqs[i].mpc_irqtype == type &&
+ (mp_irqs[i].mpc_dstapic == mp_ioapics[apic].mpc_apicid ||
+ mp_irqs[i].mpc_dstapic == MP_APIC_ALL) &&
+ mp_irqs[i].mpc_dstirq == pin)
+ return i;
+
+ return -1;
+}
+
+#ifndef CONFIG_XEN
+/*
+ * Find the pin to which IRQ[irq] (ISA) is connected
+ */
+static int __init find_isa_irq_pin(int irq, int type)
+{
+ int i;
+
+ for (i = 0; i < mp_irq_entries; i++) {
+ int lbus = mp_irqs[i].mpc_srcbus;
+
+ if ((mp_bus_id_to_type[lbus] == MP_BUS_ISA ||
+ mp_bus_id_to_type[lbus] == MP_BUS_EISA ||
+ mp_bus_id_to_type[lbus] == MP_BUS_MCA) &&
+ (mp_irqs[i].mpc_irqtype == type) &&
+ (mp_irqs[i].mpc_srcbusirq == irq))
+
+ return mp_irqs[i].mpc_dstirq;
+ }
+ return -1;
+}
+#endif
+
+/*
+ * Find a specific PCI IRQ entry.
+ * Not an __init, possibly needed by modules
+ */
+static int pin_2_irq(int idx, int apic, int pin);
+
+int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
+{
+ int apic, i, best_guess = -1;
+
+ apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d,
pin:%d.\n",
+ bus, slot, pin);
+ if (mp_bus_id_to_pci_bus[bus] == -1) {
+ apic_printk(APIC_VERBOSE, "PCI BIOS passed nonexistent PCI bus
%d!\n", bus);
+ return -1;
+ }
+ for (i = 0; i < mp_irq_entries; i++) {
+ int lbus = mp_irqs[i].mpc_srcbus;
+
+ for (apic = 0; apic < nr_ioapics; apic++)
+ if (mp_ioapics[apic].mpc_apicid ==
mp_irqs[i].mpc_dstapic ||
+ mp_irqs[i].mpc_dstapic == MP_APIC_ALL)
+ break;
+
+ if ((mp_bus_id_to_type[lbus] == MP_BUS_PCI) &&
+ !mp_irqs[i].mpc_irqtype &&
+ (bus == lbus) &&
+ (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) {
+ int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq);
+
+ if (!(apic || IO_APIC_IRQ(irq)))
+ continue;
+
+ if (pin == (mp_irqs[i].mpc_srcbusirq & 3))
+ return irq;
+ /*
+ * Use the first all-but-pin matching entry as a
+ * best-guess fuzzy result for broken mptables.
+ */
+ if (best_guess < 0)
+ best_guess = irq;
+ }
+ }
+ return best_guess;
+}
+
+/*
+ * EISA Edge/Level control register, ELCR
+ */
+static int EISA_ELCR(unsigned int irq)
+{
+ if (irq < 16) {
+ unsigned int port = 0x4d0 + (irq >> 3);
+ return (inb(port) >> (irq & 7)) & 1;
+ }
+ apic_printk(APIC_VERBOSE, "Broken MPtable reports ISA irq %d\n", irq);
+ return 0;
+}
+
+/* EISA interrupts are always polarity zero and can be edge or level
+ * trigger depending on the ELCR value. If an interrupt is listed as
+ * EISA conforming in the MP table, that means its trigger type must
+ * be read in from the ELCR */
+
+#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mpc_srcbusirq))
+#define default_EISA_polarity(idx) (0)
+
+/* ISA interrupts are always polarity zero edge triggered,
+ * when listed as conforming in the MP table. */
+
+#define default_ISA_trigger(idx) (0)
+#define default_ISA_polarity(idx) (0)
+
+/* PCI interrupts are always polarity one level triggered,
+ * when listed as conforming in the MP table. */
+
+#define default_PCI_trigger(idx) (1)
+#define default_PCI_polarity(idx) (1)
+
+/* MCA interrupts are always polarity zero level triggered,
+ * when listed as conforming in the MP table. */
+
+#define default_MCA_trigger(idx) (1)
+#define default_MCA_polarity(idx) (0)
+
+static int __init MPBIOS_polarity(int idx)
+{
+ int bus = mp_irqs[idx].mpc_srcbus;
+ int polarity;
+
+ /*
+ * Determine IRQ line polarity (high active or low active):
+ */
+ switch (mp_irqs[idx].mpc_irqflag & 3)
+ {
+ case 0: /* conforms, ie. bus-type dependent polarity */
+ {
+ switch (mp_bus_id_to_type[bus])
+ {
+ case MP_BUS_ISA: /* ISA pin */
+ {
+ polarity = default_ISA_polarity(idx);
+ break;
+ }
+ case MP_BUS_EISA: /* EISA pin */
+ {
+ polarity = default_EISA_polarity(idx);
+ break;
+ }
+ case MP_BUS_PCI: /* PCI pin */
+ {
+ polarity = default_PCI_polarity(idx);
+ break;
+ }
+ case MP_BUS_MCA: /* MCA pin */
+ {
+ polarity = default_MCA_polarity(idx);
+ break;
+ }
+ default:
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ polarity = 1;
+ break;
+ }
+ }
+ break;
+ }
+ case 1: /* high active */
+ {
+ polarity = 0;
+ break;
+ }
+ case 2: /* reserved */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ polarity = 1;
+ break;
+ }
+ case 3: /* low active */
+ {
+ polarity = 1;
+ break;
+ }
+ default: /* invalid */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ polarity = 1;
+ break;
+ }
+ }
+ return polarity;
+}
+
+static int MPBIOS_trigger(int idx)
+{
+ int bus = mp_irqs[idx].mpc_srcbus;
+ int trigger;
+
+ /*
+ * Determine IRQ trigger mode (edge or level sensitive):
+ */
+ switch ((mp_irqs[idx].mpc_irqflag>>2) & 3)
+ {
+ case 0: /* conforms, ie. bus-type dependent */
+ {
+ switch (mp_bus_id_to_type[bus])
+ {
+ case MP_BUS_ISA: /* ISA pin */
+ {
+ trigger = default_ISA_trigger(idx);
+ break;
+ }
+ case MP_BUS_EISA: /* EISA pin */
+ {
+ trigger = default_EISA_trigger(idx);
+ break;
+ }
+ case MP_BUS_PCI: /* PCI pin */
+ {
+ trigger = default_PCI_trigger(idx);
+ break;
+ }
+ case MP_BUS_MCA: /* MCA pin */
+ {
+ trigger = default_MCA_trigger(idx);
+ break;
+ }
+ default:
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ trigger = 1;
+ break;
+ }
+ }
+ break;
+ }
+ case 1: /* edge */
+ {
+ trigger = 0;
+ break;
+ }
+ case 2: /* reserved */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ trigger = 1;
+ break;
+ }
+ case 3: /* level */
+ {
+ trigger = 1;
+ break;
+ }
+ default: /* invalid */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ trigger = 0;
+ break;
+ }
+ }
+ return trigger;
+}
+
+static inline int irq_polarity(int idx)
+{
+ return MPBIOS_polarity(idx);
+}
+
+static inline int irq_trigger(int idx)
+{
+ return MPBIOS_trigger(idx);
+}
+
+static int pin_2_irq(int idx, int apic, int pin)
+{
+ int irq, i;
+ int bus = mp_irqs[idx].mpc_srcbus;
+
+ /*
+ * Debugging check, we are in big trouble if this message pops up!
+ */
+ if (mp_irqs[idx].mpc_dstirq != pin)
+ printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n");
+
+ switch (mp_bus_id_to_type[bus])
+ {
+ case MP_BUS_ISA: /* ISA pin */
+ case MP_BUS_EISA:
+ case MP_BUS_MCA:
+ {
+ irq = mp_irqs[idx].mpc_srcbusirq;
+ break;
+ }
+ case MP_BUS_PCI: /* PCI pin */
+ {
+ /*
+ * PCI IRQs are mapped in order
+ */
+ i = irq = 0;
+ while (i < apic)
+ irq += nr_ioapic_registers[i++];
+ irq += pin;
+ break;
+ }
+ default:
+ {
+ printk(KERN_ERR "unknown bus type %d.\n",bus);
+ irq = 0;
+ break;
+ }
+ }
+
+ /*
+ * PCI IRQ command line redirection. Yes, limits are hardcoded.
+ */
+ if ((pin >= 16) && (pin <= 23)) {
+ if (pirq_entries[pin-16] != -1) {
+ if (!pirq_entries[pin-16]) {
+ apic_printk(APIC_VERBOSE, "disabling PIRQ%d\n",
pin-16);
+ } else {
+ irq = pirq_entries[pin-16];
+ apic_printk(APIC_VERBOSE, "using PIRQ%d -> IRQ
%d\n",
+ pin-16, irq);
+ }
+ }
+ }
+ return irq;
+}
+
+static inline int IO_APIC_irq_trigger(int irq)
+{
+ int apic, idx, pin;
+
+ for (apic = 0; apic < nr_ioapics; apic++) {
+ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
+ idx = find_irq_entry(apic,pin,mp_INT);
+ if ((idx != -1) && (irq == pin_2_irq(idx,apic,pin)))
+ return irq_trigger(idx);
+ }
+ }
+ /*
+ * nonexistent IRQs are edge default
+ */
+ return 0;
+}
+
+/* irq_vectors is indexed by the sum of all RTEs in all I/O APICs. */
+u8 irq_vector[NR_IRQ_VECTORS];
+
+int assign_irq_vector(int irq)
+{
+ static int current_vector = FIRST_DEVICE_VECTOR;
+ physdev_op_t op;
+
+ BUG_ON(irq >= NR_IRQ_VECTORS);
+ if (irq != AUTO_ASSIGN && IO_APIC_VECTOR(irq) > 0)
+ return IO_APIC_VECTOR(irq);
+
+ op.cmd = PHYSDEVOP_ASSIGN_VECTOR;
+ op.u.irq_op.irq = irq;
+ if (HYPERVISOR_physdev_op(&op))
+ return -ENOSPC;
+ current_vector = op.u.irq_op.vector;
+
+ vector_irq[current_vector] = irq;
+ if (irq != AUTO_ASSIGN)
+ IO_APIC_VECTOR(irq) = current_vector;
+
+ return current_vector;
+}
+
+extern void (*interrupt[NR_IRQS])(void);
+#ifndef CONFIG_XEN
+static struct hw_interrupt_type ioapic_level_type;
+static struct hw_interrupt_type ioapic_edge_type;
+
+#define IOAPIC_AUTO -1
+#define IOAPIC_EDGE 0
+#define IOAPIC_LEVEL 1
+
+static inline void ioapic_register_intr(int irq, int vector, unsigned long
trigger)
+{
+ if (use_pci_vector() && !platform_legacy_irq(irq)) {
+ if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
+ trigger == IOAPIC_LEVEL)
+ irq_desc[vector].handler = &ioapic_level_type;
+ else
+ irq_desc[vector].handler = &ioapic_edge_type;
+ set_intr_gate(vector, interrupt[vector]);
+ } else {
+ if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
+ trigger == IOAPIC_LEVEL)
+ irq_desc[irq].handler = &ioapic_level_type;
+ else
+ irq_desc[irq].handler = &ioapic_edge_type;
+ set_intr_gate(vector, interrupt[irq]);
+ }
+}
+#else
+#define ioapic_register_intr(_irq,_vector,_trigger) ((void)0)
+#endif /* !CONFIG_XEN */
+
+void __init setup_IO_APIC_irqs(void)
+{
+ struct IO_APIC_route_entry entry;
+ int apic, pin, idx, irq, first_notcon = 1, vector;
+ unsigned long flags;
+
+ apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
+
+ for (apic = 0; apic < nr_ioapics; apic++) {
+ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
+
+ /*
+ * add it to the IO-APIC irq-routing table:
+ */
+ memset(&entry,0,sizeof(entry));
+
+ entry.delivery_mode = INT_DELIVERY_MODE;
+ entry.dest_mode = INT_DEST_MODE;
+ entry.mask = 0; /* enable IRQ */
+ entry.dest.logical.logical_dest =
cpu_mask_to_apicid(TARGET_CPUS);
+
+ idx = find_irq_entry(apic,pin,mp_INT);
+ if (idx == -1) {
+ if (first_notcon) {
+ apic_printk(APIC_VERBOSE, KERN_DEBUG " IO-APIC
(apicid-pin) %d-%d", mp_ioapics[apic].mpc_apicid, pin);
+ first_notcon = 0;
+ } else
+ apic_printk(APIC_VERBOSE, ", %d-%d",
mp_ioapics[apic].mpc_apicid, pin);
+ continue;
+ }
+
+ entry.trigger = irq_trigger(idx);
+ entry.polarity = irq_polarity(idx);
+
+ if (irq_trigger(idx)) {
+ entry.trigger = 1;
+ entry.mask = 1;
+ entry.dest.logical.logical_dest =
cpu_mask_to_apicid(TARGET_CPUS);
+ }
+
+ irq = pin_2_irq(idx, apic, pin);
+ add_pin_to_irq(irq, apic, pin);
+
+ if (/* !apic && */ !IO_APIC_IRQ(irq))
+ continue;
+
+ if (IO_APIC_IRQ(irq)) {
+ vector = assign_irq_vector(irq);
+ entry.vector = vector;
+
+ ioapic_register_intr(irq, vector, IOAPIC_AUTO);
+ if (!apic && (irq < 16))
+ disable_8259A_irq(irq);
+ }
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(apic, 0x11+2*pin, *(((int *)&entry)+1));
+ io_apic_write(apic, 0x10+2*pin, *(((int *)&entry)+0));
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ }
+ }
+
+ if (!first_notcon)
+ apic_printk(APIC_VERBOSE," not connected.\n");
+}
+
+#ifndef CONFIG_XEN
+/*
+ * Set up the 8259A-master output pin as broadcast to all
+ * CPUs.
+ */
+void __init setup_ExtINT_IRQ0_pin(unsigned int pin, int vector)
+{
+ struct IO_APIC_route_entry entry;
+ unsigned long flags;
+
+ memset(&entry,0,sizeof(entry));
+
+ disable_8259A_irq(0);
+
+ /* mask LVT0 */
+ apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
+
+ /*
+ * We use logical delivery to get the timer IRQ
+ * to the first CPU.
+ */
+ entry.dest_mode = INT_DEST_MODE;
+ entry.mask = 0; /* unmask IRQ now */
+ entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS);
+ entry.delivery_mode = INT_DELIVERY_MODE;
+ entry.polarity = 0;
+ entry.trigger = 0;
+ entry.vector = vector;
+
+ /*
+ * The timer IRQ doesn't have to know that behind the
+ * scene we have a 8259A-master in AEOI mode ...
+ */
+ irq_desc[0].handler = &ioapic_edge_type;
+
+ /*
+ * Add it to the IO-APIC irq-routing table:
+ */
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(0, 0x11+2*pin, *(((int *)&entry)+1));
+ io_apic_write(0, 0x10+2*pin, *(((int *)&entry)+0));
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ enable_8259A_irq(0);
+}
+
+void __init UNEXPECTED_IO_APIC(void)
+{
+}
+
+void __apicdebuginit print_IO_APIC(void)
+{
+ int apic, i;
+ union IO_APIC_reg_00 reg_00;
+ union IO_APIC_reg_01 reg_01;
+ union IO_APIC_reg_02 reg_02;
+ unsigned long flags;
+
+ if (apic_verbosity == APIC_QUIET)
+ return;
+
+ printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
+ for (i = 0; i < nr_ioapics; i++)
+ printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
+ mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]);
+
+ /*
+ * We are a bit conservative about what we expect. We have to
+ * know about every hardware change ASAP.
+ */
+ printk(KERN_INFO "testing the IO APIC.......................\n");
+
+ for (apic = 0; apic < nr_ioapics; apic++) {
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(apic, 0);
+ reg_01.raw = io_apic_read(apic, 1);
+ if (reg_01.bits.version >= 0x10)
+ reg_02.raw = io_apic_read(apic, 2);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ printk("\n");
+ printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid);
+ printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
+ printk(KERN_DEBUG "....... : physical APIC id: %02X\n",
reg_00.bits.ID);
+ if (reg_00.bits.__reserved_1 || reg_00.bits.__reserved_2)
+ UNEXPECTED_IO_APIC();
+
+ printk(KERN_DEBUG ".... register #01: %08X\n", *(int *)®_01);
+ printk(KERN_DEBUG "....... : max redirection entries: %04X\n",
reg_01.bits.entries);
+ if ( (reg_01.bits.entries != 0x0f) && /* older (Neptune) boards */
+ (reg_01.bits.entries != 0x17) && /* typical ISA+PCI boards */
+ (reg_01.bits.entries != 0x1b) && /* Compaq Proliant boards */
+ (reg_01.bits.entries != 0x1f) && /* dual Xeon boards */
+ (reg_01.bits.entries != 0x22) && /* bigger Xeon boards */
+ (reg_01.bits.entries != 0x2E) &&
+ (reg_01.bits.entries != 0x3F) &&
+ (reg_01.bits.entries != 0x03)
+ )
+ UNEXPECTED_IO_APIC();
+
+ printk(KERN_DEBUG "....... : PRQ implemented: %X\n",
reg_01.bits.PRQ);
+ printk(KERN_DEBUG "....... : IO APIC version: %04X\n",
reg_01.bits.version);
+ if ( (reg_01.bits.version != 0x01) && /* 82489DX IO-APICs */
+ (reg_01.bits.version != 0x02) && /* 82801BA IO-APICs (ICH2) */
+ (reg_01.bits.version != 0x10) && /* oldest IO-APICs */
+ (reg_01.bits.version != 0x11) && /* Pentium/Pro IO-APICs */
+ (reg_01.bits.version != 0x13) && /* Xeon IO-APICs */
+ (reg_01.bits.version != 0x20) /* Intel P64H (82806 AA) */
+ )
+ UNEXPECTED_IO_APIC();
+ if (reg_01.bits.__reserved_1 || reg_01.bits.__reserved_2)
+ UNEXPECTED_IO_APIC();
+
+ if (reg_01.bits.version >= 0x10) {
+ printk(KERN_DEBUG ".... register #02: %08X\n", reg_02.raw);
+ printk(KERN_DEBUG "....... : arbitration: %02X\n",
reg_02.bits.arbitration);
+ if (reg_02.bits.__reserved_1 || reg_02.bits.__reserved_2)
+ UNEXPECTED_IO_APIC();
+ }
+
+ printk(KERN_DEBUG ".... IRQ redirection table:\n");
+
+ printk(KERN_DEBUG " NR Log Phy Mask Trig IRR Pol"
+ " Stat Dest Deli Vect: \n");
+
+ for (i = 0; i <= reg_01.bits.entries; i++) {
+ struct IO_APIC_route_entry entry;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ *(((int *)&entry)+0) = io_apic_read(apic, 0x10+i*2);
+ *(((int *)&entry)+1) = io_apic_read(apic, 0x11+i*2);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ printk(KERN_DEBUG " %02x %03X %02X ",
+ i,
+ entry.dest.logical.logical_dest,
+ entry.dest.physical.physical_dest
+ );
+
+ printk("%1d %1d %1d %1d %1d %1d %1d %02X\n",
+ entry.mask,
+ entry.trigger,
+ entry.irr,
+ entry.polarity,
+ entry.delivery_status,
+ entry.dest_mode,
+ entry.delivery_mode,
+ entry.vector
+ );
+ }
+ }
+ if (use_pci_vector())
+ printk(KERN_INFO "Using vector-based indexing\n");
+ printk(KERN_DEBUG "IRQ to pin mappings:\n");
+ for (i = 0; i < NR_IRQS; i++) {
+ struct irq_pin_list *entry = irq_2_pin + i;
+ if (entry->pin < 0)
+ continue;
+ if (use_pci_vector() && !platform_legacy_irq(i))
+ printk(KERN_DEBUG "IRQ%d ", IO_APIC_VECTOR(i));
+ else
+ printk(KERN_DEBUG "IRQ%d ", i);
+ for (;;) {
+ printk("-> %d:%d", entry->apic, entry->pin);
+ if (!entry->next)
+ break;
+ entry = irq_2_pin + entry->next;
+ }
+ printk("\n");
+ }
+
+ printk(KERN_INFO ".................................... done.\n");
+
+ return;
+}
+
+static __apicdebuginit void print_APIC_bitfield (int base)
+{
+ unsigned int v;
+ int i, j;
+
+ if (apic_verbosity == APIC_QUIET)
+ return;
+
+ printk(KERN_DEBUG "0123456789abcdef0123456789abcdef\n" KERN_DEBUG);
+ for (i = 0; i < 8; i++) {
+ v = apic_read(base + i*0x10);
+ for (j = 0; j < 32; j++) {
+ if (v & (1<<j))
+ printk("1");
+ else
+ printk("0");
+ }
+ printk("\n");
+ }
+}
+
+void __apicdebuginit print_local_APIC(void * dummy)
+{
+ unsigned int v, ver, maxlvt;
+
+ if (apic_verbosity == APIC_QUIET)
+ return;
+
+ printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
+ smp_processor_id(), hard_smp_processor_id());
+ v = apic_read(APIC_ID);
+ printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, GET_APIC_ID(v));
+ v = apic_read(APIC_LVR);
+ printk(KERN_INFO "... APIC VERSION: %08x\n", v);
+ ver = GET_APIC_VERSION(v);
+ maxlvt = get_maxlvt();
+
+ v = apic_read(APIC_TASKPRI);
+ printk(KERN_DEBUG "... APIC TASKPRI: %08x (%02x)\n", v, v &
APIC_TPRI_MASK);
+
+ if (APIC_INTEGRATED(ver)) { /* !82489DX */
+ v = apic_read(APIC_ARBPRI);
+ printk(KERN_DEBUG "... APIC ARBPRI: %08x (%02x)\n", v,
+ v & APIC_ARBPRI_MASK);
+ v = apic_read(APIC_PROCPRI);
+ printk(KERN_DEBUG "... APIC PROCPRI: %08x\n", v);
+ }
+
+ v = apic_read(APIC_EOI);
+ printk(KERN_DEBUG "... APIC EOI: %08x\n", v);
+ v = apic_read(APIC_RRR);
+ printk(KERN_DEBUG "... APIC RRR: %08x\n", v);
+ v = apic_read(APIC_LDR);
+ printk(KERN_DEBUG "... APIC LDR: %08x\n", v);
+ v = apic_read(APIC_DFR);
+ printk(KERN_DEBUG "... APIC DFR: %08x\n", v);
+ v = apic_read(APIC_SPIV);
+ printk(KERN_DEBUG "... APIC SPIV: %08x\n", v);
+
+ printk(KERN_DEBUG "... APIC ISR field:\n");
+ print_APIC_bitfield(APIC_ISR);
+ printk(KERN_DEBUG "... APIC TMR field:\n");
+ print_APIC_bitfield(APIC_TMR);
+ printk(KERN_DEBUG "... APIC IRR field:\n");
+ print_APIC_bitfield(APIC_IRR);
+
+ if (APIC_INTEGRATED(ver)) { /* !82489DX */
+ if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
+ apic_write(APIC_ESR, 0);
+ v = apic_read(APIC_ESR);
+ printk(KERN_DEBUG "... APIC ESR: %08x\n", v);
+ }
+
+ v = apic_read(APIC_ICR);
+ printk(KERN_DEBUG "... APIC ICR: %08x\n", v);
+ v = apic_read(APIC_ICR2);
+ printk(KERN_DEBUG "... APIC ICR2: %08x\n", v);
+
+ v = apic_read(APIC_LVTT);
+ printk(KERN_DEBUG "... APIC LVTT: %08x\n", v);
+
+ if (maxlvt > 3) { /* PC is LVT#4. */
+ v = apic_read(APIC_LVTPC);
+ printk(KERN_DEBUG "... APIC LVTPC: %08x\n", v);
+ }
+ v = apic_read(APIC_LVT0);
+ printk(KERN_DEBUG "... APIC LVT0: %08x\n", v);
+ v = apic_read(APIC_LVT1);
+ printk(KERN_DEBUG "... APIC LVT1: %08x\n", v);
+
+ if (maxlvt > 2) { /* ERR is LVT#3. */
+ v = apic_read(APIC_LVTERR);
+ printk(KERN_DEBUG "... APIC LVTERR: %08x\n", v);
+ }
+
+ v = apic_read(APIC_TMICT);
+ printk(KERN_DEBUG "... APIC TMICT: %08x\n", v);
+ v = apic_read(APIC_TMCCT);
+ printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v);
+ v = apic_read(APIC_TDCR);
+ printk(KERN_DEBUG "... APIC TDCR: %08x\n", v);
+ printk("\n");
+}
+
+void print_all_local_APICs (void)
+{
+ on_each_cpu(print_local_APIC, NULL, 1, 1);
+}
+
+void __apicdebuginit print_PIC(void)
+{
+ extern spinlock_t i8259A_lock;
+ unsigned int v;
+ unsigned long flags;
+
+ if (apic_verbosity == APIC_QUIET)
+ return;
+
+ printk(KERN_DEBUG "\nprinting PIC contents\n");
+
+ spin_lock_irqsave(&i8259A_lock, flags);
+
+ v = inb(0xa1) << 8 | inb(0x21);
+ printk(KERN_DEBUG "... PIC IMR: %04x\n", v);
+
+ v = inb(0xa0) << 8 | inb(0x20);
+ printk(KERN_DEBUG "... PIC IRR: %04x\n", v);
+
+ outb(0x0b,0xa0);
+ outb(0x0b,0x20);
+ v = inb(0xa0) << 8 | inb(0x20);
+ outb(0x0a,0xa0);
+ outb(0x0a,0x20);
+
+ spin_unlock_irqrestore(&i8259A_lock, flags);
+
+ printk(KERN_DEBUG "... PIC ISR: %04x\n", v);
+
+ v = inb(0x4d1) << 8 | inb(0x4d0);
+ printk(KERN_DEBUG "... PIC ELCR: %04x\n", v);
+}
+#else
+void __init print_IO_APIC(void) { }
+#endif /* !CONFIG_XEN */
+
+static void __init enable_IO_APIC(void)
+{
+ union IO_APIC_reg_01 reg_01;
+ int i;
+ unsigned long flags;
+
+ for (i = 0; i < PIN_MAP_SIZE; i++) {
+ irq_2_pin[i].pin = -1;
+ irq_2_pin[i].next = 0;
+ }
+ if (!pirqs_enabled)
+ for (i = 0; i < MAX_PIRQS; i++)
+ pirq_entries[i] = -1;
+
+ /*
+ * The number of IO-APIC IRQ registers (== #pins):
+ */
+ for (i = 0; i < nr_ioapics; i++) {
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_01.raw = io_apic_read(i, 1);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ nr_ioapic_registers[i] = reg_01.bits.entries+1;
+ }
+
+ /*
+ * Do not trust the IO-APIC being empty at bootup
+ */
+ clear_IO_APIC();
+}
+
+/*
+ * Not an __init, needed by the reboot code
+ */
+void disable_IO_APIC(void)
+{
+ /*
+ * Clear the IO-APIC before rebooting:
+ */
+ clear_IO_APIC();
+#ifndef CONFIG_XEN
+ disconnect_bsp_APIC();
+#endif
+}
+
+/*
+ * function to set the IO-APIC physical IDs based on the
+ * values stored in the MPC table.
+ *
+ * by Matt Domsch <Matt_Domsch@xxxxxxxx> Tue Dec 21 12:25:05 CST 1999
+ */
+#ifndef CONFIG_XEN
+static void __init setup_ioapic_ids_from_mpc (void)
+{
+ union IO_APIC_reg_00 reg_00;
+ int apic;
+ int i;
+ unsigned char old_id;
+ unsigned long flags;
+
+ /*
+ * Set the IOAPIC ID to the value stored in the MPC table.
+ */
+ for (apic = 0; apic < nr_ioapics; apic++) {
+
+ /* Read the register 0 value */
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(apic, 0);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ old_id = mp_ioapics[apic].mpc_apicid;
+
+
+ printk(KERN_INFO "Using IO-APIC %d\n",
mp_ioapics[apic].mpc_apicid);
+
+
+ /*
+ * We need to adjust the IRQ routing table
+ * if the ID changed.
+ */
+ if (old_id != mp_ioapics[apic].mpc_apicid)
+ for (i = 0; i < mp_irq_entries; i++)
+ if (mp_irqs[i].mpc_dstapic == old_id)
+ mp_irqs[i].mpc_dstapic
+ = mp_ioapics[apic].mpc_apicid;
+
+ /*
+ * Read the right value from the MPC table and
+ * write it into the ID register.
+ */
+ apic_printk(APIC_VERBOSE,KERN_INFO "...changing IO-APIC
physical APIC ID to %d ...",
+ mp_ioapics[apic].mpc_apicid);
+
+ reg_00.bits.ID = mp_ioapics[apic].mpc_apicid;
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(apic, 0, reg_00.raw);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ /*
+ * Sanity check
+ */
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(apic, 0);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ if (reg_00.bits.ID != mp_ioapics[apic].mpc_apicid)
+ printk("could not set ID!\n");
+ else
+ apic_printk(APIC_VERBOSE," ok.\n");
+ }
+}
+#else
+static void __init setup_ioapic_ids_from_mpc(void) { }
+#endif
+
+/*
+ * There is a nasty bug in some older SMP boards, their mptable lies
+ * about the timer IRQ. We do the following to work around the situation:
+ *
+ * - timer IRQ defaults to IO-APIC IRQ
+ * - if this function detects that timer IRQs are defunct, then we fall
+ * back to ISA timer IRQs
+ */
+#ifndef CONFIG_XEN
+static int __init timer_irq_works(void)
+{
+ unsigned long t1 = jiffies;
+
+ local_irq_enable();
+ /* Let ten ticks pass... */
+ mdelay((10 * 1000) / HZ);
+
+ /*
+ * Expect a few ticks at least, to be sure some possible
+ * glue logic does not lock up after one or two first
+ * ticks in a non-ExtINT mode. Also the local APIC
+ * might have cached one ExtINT interrupt. Finally, at
+ * least one tick may be lost due to delays.
+ */
+
+ /* jiffies wrap? */
+ if (jiffies - t1 > 4)
+ return 1;
+ return 0;
+}
+
+/*
+ * In the SMP+IOAPIC case it might happen that there are an unspecified
+ * number of pending IRQ events unhandled. These cases are very rare,
+ * so we 'resend' these IRQs via IPIs, to the same CPU. It's much
+ * better to do it this way as thus we do not have to be aware of
+ * 'pending' interrupts in the IRQ path, except at this point.
+ */
+/*
+ * Edge triggered needs to resend any interrupt
+ * that was delayed but this is now handled in the device
+ * independent code.
+ */
+
+/*
+ * Starting up a edge-triggered IO-APIC interrupt is
+ * nasty - we need to make sure that we get the edge.
+ * If it is already asserted for some reason, we need
+ * return 1 to indicate that is was pending.
+ *
+ * This is not complete - we should be able to fake
+ * an edge even if it isn't on the 8259A...
+ */
+
+static unsigned int startup_edge_ioapic_irq(unsigned int irq)
+{
+ int was_pending = 0;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ if (irq < 16) {
+ disable_8259A_irq(irq);
+ if (i8259A_irq_pending(irq))
+ was_pending = 1;
+ }
+ __unmask_IO_APIC_irq(irq);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return was_pending;
+}
+
+/*
+ * Once we have recorded IRQ_PENDING already, we can mask the
+ * interrupt for real. This prevents IRQ storms from unhandled
+ * devices.
+ */
+static void ack_edge_ioapic_irq(unsigned int irq)
+{
+ if ((irq_desc[irq].status & (IRQ_PENDING | IRQ_DISABLED))
+ == (IRQ_PENDING | IRQ_DISABLED))
+ mask_IO_APIC_irq(irq);
+ ack_APIC_irq();
+}
+
+/*
+ * Level triggered interrupts can just be masked,
+ * and shutting down and starting up the interrupt
+ * is the same as enabling and disabling them -- except
+ * with a startup need to return a "was pending" value.
+ *
+ * Level triggered interrupts are special because we
+ * do not touch any IO-APIC register while handling
+ * them. We ack the APIC in the end-IRQ handler, not
+ * in the start-IRQ-handler. Protection against reentrance
+ * from the same interrupt is still provided, both by the
+ * generic IRQ layer and by the fact that an unacked local
+ * APIC does not accept IRQs.
+ */
+static unsigned int startup_level_ioapic_irq (unsigned int irq)
+{
+ unmask_IO_APIC_irq(irq);
+
+ return 0; /* don't check for pending */
+}
+
+static void end_level_ioapic_irq (unsigned int irq)
+{
+ ack_APIC_irq();
+}
+
+static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
+{
+ unsigned long flags;
+ unsigned int dest;
+
+ dest = cpu_mask_to_apicid(mask);
+
+ /*
+ * Only the high 8 bits are valid.
+ */
+ dest = SET_APIC_LOGICAL_ID(dest);
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ __DO_ACTION(1, = dest, )
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+#ifdef CONFIG_PCI_MSI
+static unsigned int startup_edge_ioapic_vector(unsigned int vector)
+{
+ int irq = vector_to_irq(vector);
+
+ return startup_edge_ioapic_irq(irq);
+}
+
+static void ack_edge_ioapic_vector(unsigned int vector)
+{
+ int irq = vector_to_irq(vector);
+
+ ack_edge_ioapic_irq(irq);
+}
+
+static unsigned int startup_level_ioapic_vector (unsigned int vector)
+{
+ int irq = vector_to_irq(vector);
+
+ return startup_level_ioapic_irq (irq);
+}
+
+static void end_level_ioapic_vector (unsigned int vector)
+{
+ int irq = vector_to_irq(vector);
+
+ end_level_ioapic_irq(irq);
+}
+
+static void mask_IO_APIC_vector (unsigned int vector)
+{
+ int irq = vector_to_irq(vector);
+
+ mask_IO_APIC_irq(irq);
+}
+
+static void unmask_IO_APIC_vector (unsigned int vector)
+{
+ int irq = vector_to_irq(vector);
+
+ unmask_IO_APIC_irq(irq);
+}
+
+static void set_ioapic_affinity_vector (unsigned int vector,
+ cpumask_t cpu_mask)
+{
+ int irq = vector_to_irq(vector);
+
+ set_ioapic_affinity_irq(irq, cpu_mask);
+}
+#endif
+
+/*
+ * Level and edge triggered IO-APIC interrupts need different handling,
+ * so we use two separate IRQ descriptors. Edge triggered IRQs can be
+ * handled with the level-triggered descriptor, but that one has slightly
+ * more overhead. Level-triggered interrupts cannot be handled with the
+ * edge-triggered handler, without risking IRQ storms and other ugly
+ * races.
+ */
+
+static struct hw_interrupt_type ioapic_edge_type = {
+ .typename = "IO-APIC-edge",
+ .startup = startup_edge_ioapic,
+ .shutdown = shutdown_edge_ioapic,
+ .enable = enable_edge_ioapic,
+ .disable = disable_edge_ioapic,
+ .ack = ack_edge_ioapic,
+ .end = end_edge_ioapic,
+ .set_affinity = set_ioapic_affinity,
+};
+
+static struct hw_interrupt_type ioapic_level_type = {
+ .typename = "IO-APIC-level",
+ .startup = startup_level_ioapic,
+ .shutdown = shutdown_level_ioapic,
+ .enable = enable_level_ioapic,
+ .disable = disable_level_ioapic,
+ .ack = mask_and_ack_level_ioapic,
+ .end = end_level_ioapic,
+ .set_affinity = set_ioapic_affinity,
+};
+#endif /* !CONFIG_XEN */
+
+static inline void init_IO_APIC_traps(void)
+{
+ int irq;
+
+ /*
+ * NOTE! The local APIC isn't very good at handling
+ * multiple interrupts at the same interrupt level.
+ * As the interrupt level is determined by taking the
+ * vector number and shifting that right by 4, we
+ * want to spread these out a bit so that they don't
+ * all fall in the same interrupt level.
+ *
+ * Also, we've got to be careful not to trash gate
+ * 0x80, because int 0x80 is hm, kind of importantish. ;)
+ */
+ for (irq = 0; irq < NR_IRQS ; irq++) {
+ int tmp = irq;
+ if (use_pci_vector()) {
+ if (!platform_legacy_irq(tmp))
+ if ((tmp = vector_to_irq(tmp)) == -1)
+ continue;
+ }
+ if (IO_APIC_IRQ(tmp) && !IO_APIC_VECTOR(tmp)) {
+ /*
+ * Hmm.. We don't have an entry for this,
+ * so default to an old-fashioned 8259
+ * interrupt if we can..
+ */
+ if (irq < 16)
+ make_8259A_irq(irq);
+#ifndef CONFIG_XEN
+ else
+ /* Strange. Oh, well.. */
+ irq_desc[irq].handler = &no_irq_type;
+#endif
+ }
+ }
+}
+
+#ifndef CONFIG_XEN
+static void enable_lapic_irq (unsigned int irq)
+{
+ unsigned long v;
+
+ v = apic_read(APIC_LVT0);
+ apic_write_around(APIC_LVT0, v & ~APIC_LVT_MASKED);
+}
+
+static void disable_lapic_irq (unsigned int irq)
+{
+ unsigned long v;
+
+ v = apic_read(APIC_LVT0);
+ apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED);
+}
+
+static void ack_lapic_irq (unsigned int irq)
+{
+ ack_APIC_irq();
+}
+
+static void end_lapic_irq (unsigned int i) { /* nothing */ }
+
+static struct hw_interrupt_type lapic_irq_type = {
+ .typename = "local-APIC-edge",
+ .startup = NULL, /* startup_irq() not used for IRQ0 */
+ .shutdown = NULL, /* shutdown_irq() not used for IRQ0 */
+ .enable = enable_lapic_irq,
+ .disable = disable_lapic_irq,
+ .ack = ack_lapic_irq,
+ .end = end_lapic_irq,
+};
+
+static void setup_nmi (void)
+{
+ /*
+ * Dirty trick to enable the NMI watchdog ...
+ * We put the 8259A master into AEOI mode and
+ * unmask on all local APICs LVT0 as NMI.
+ *
+ * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire')
+ * is from Maciej W. Rozycki - so we do not have to EOI from
+ * the NMI handler or the timer interrupt.
+ */
+ printk(KERN_INFO "activating NMI Watchdog ...");
+
+ enable_NMI_through_LVT0(NULL);
+
+ printk(" done.\n");
+}
+
+/*
+ * This looks a bit hackish but it's about the only one way of sending
+ * a few INTA cycles to 8259As and any associated glue logic. ICR does
+ * not support the ExtINT mode, unfortunately. We need to send these
+ * cycles as some i82489DX-based boards have glue logic that keeps the
+ * 8259A interrupt line asserted until INTA. --macro
+ */
+static inline void unlock_ExtINT_logic(void)
+{
+ int pin, i;
+ struct IO_APIC_route_entry entry0, entry1;
+ unsigned char save_control, save_freq_select;
+ unsigned long flags;
+
+ pin = find_isa_irq_pin(8, mp_INT);
+ if (pin == -1)
+ return;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ *(((int *)&entry0) + 1) = io_apic_read(0, 0x11 + 2 * pin);
+ *(((int *)&entry0) + 0) = io_apic_read(0, 0x10 + 2 * pin);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ clear_IO_APIC_pin(0, pin);
+
+ memset(&entry1, 0, sizeof(entry1));
+
+ entry1.dest_mode = 0; /* physical delivery */
+ entry1.mask = 0; /* unmask IRQ now */
+ entry1.dest.physical.physical_dest = hard_smp_processor_id();
+ entry1.delivery_mode = dest_ExtINT;
+ entry1.polarity = entry0.polarity;
+ entry1.trigger = 0;
+ entry1.vector = 0;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry1) + 1));
+ io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry1) + 0));
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ save_control = CMOS_READ(RTC_CONTROL);
+ save_freq_select = CMOS_READ(RTC_FREQ_SELECT);
+ CMOS_WRITE((save_freq_select & ~RTC_RATE_SELECT) | 0x6,
+ RTC_FREQ_SELECT);
+ CMOS_WRITE(save_control | RTC_PIE, RTC_CONTROL);
+
+ i = 100;
+ while (i-- > 0) {
+ mdelay(10);
+ if ((CMOS_READ(RTC_INTR_FLAGS) & RTC_PF) == RTC_PF)
+ i -= 10;
+ }
+
+ CMOS_WRITE(save_control, RTC_CONTROL);
+ CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
+ clear_IO_APIC_pin(0, pin);
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry0) + 1));
+ io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry0) + 0));
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+/*
+ * This code may look a bit paranoid, but it's supposed to cooperate with
+ * a wide range of boards and BIOS bugs. Fortunately only the timer IRQ
+ * is so screwy. Thanks to Brian Perkins for testing/hacking this beast
+ * fanatically on his truly buggy board.
+ */
+static inline void check_timer(void)
+{
+ int pin1, pin2;
+ int vector;
+
+ /*
+ * get/set the timer IRQ vector:
+ */
+ disable_8259A_irq(0);
+ vector = assign_irq_vector(0);
+ set_intr_gate(vector, interrupt[0]);
+
+ /*
+ * Subtle, code in do_timer_interrupt() expects an AEOI
+ * mode for the 8259A whenever interrupts are routed
+ * through I/O APICs. Also IRQ0 has to be enabled in
+ * the 8259A which implies the virtual wire has to be
+ * disabled in the local APIC.
+ */
+ apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
+ init_8259A(1);
+ enable_8259A_irq(0);
+
+ pin1 = find_isa_irq_pin(0, mp_INT);
+ pin2 = find_isa_irq_pin(0, mp_ExtINT);
+
+ apic_printk(APIC_VERBOSE,KERN_INFO "..TIMER: vector=0x%02X pin1=%d
pin2=%d\n", vector, pin1, pin2);
+
+ if (pin1 != -1) {
+ /*
+ * Ok, does IRQ0 through the IOAPIC work?
+ */
+ unmask_IO_APIC_irq(0);
+ if (timer_irq_works()) {
+ nmi_watchdog_default();
+ if (nmi_watchdog == NMI_IO_APIC) {
+ disable_8259A_irq(0);
+ setup_nmi();
+ enable_8259A_irq(0);
+ check_nmi_watchdog();
+ }
+ return;
+ }
+ clear_IO_APIC_pin(0, pin1);
+ apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: 8254 timer not
connected to IO-APIC\n");
+ }
+
+ apic_printk(APIC_VERBOSE,KERN_INFO "...trying to set up timer (IRQ0)
through the 8259A ... ");
+ if (pin2 != -1) {
+ apic_printk(APIC_VERBOSE,"\n..... (found pin %d) ...", pin2);
+ /*
+ * legacy devices should be connected to IO APIC #0
+ */
+ setup_ExtINT_IRQ0_pin(pin2, vector);
+ if (timer_irq_works()) {
+ printk("works.\n");
+ nmi_watchdog_default();
+ if (nmi_watchdog == NMI_IO_APIC) {
+ setup_nmi();
+ check_nmi_watchdog();
+ }
+ return;
+ }
+ /*
+ * Cleanup, just in case ...
+ */
+ clear_IO_APIC_pin(0, pin2);
+ }
+ printk(" failed.\n");
+
+ if (nmi_watchdog) {
+ printk(KERN_WARNING "timer doesn't work through the IO-APIC -
disabling NMI Watchdog!\n");
+ nmi_watchdog = 0;
+ }
+
+ apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as
Virtual Wire IRQ...");
+
+ disable_8259A_irq(0);
+ irq_desc[0].handler = &lapic_irq_type;
+ apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector); /* Fixed mode */
+ enable_8259A_irq(0);
+
+ if (timer_irq_works()) {
+ apic_printk(APIC_QUIET, " works.\n");
+ return;
+ }
+ apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector);
+ apic_printk(APIC_VERBOSE," failed.\n");
+
+ apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as
ExtINT IRQ...");
+
+ init_8259A(0);
+ make_8259A_irq(0);
+ apic_write_around(APIC_LVT0, APIC_DM_EXTINT);
+
+ unlock_ExtINT_logic();
+
+ if (timer_irq_works()) {
+ apic_printk(APIC_VERBOSE," works.\n");
+ return;
+ }
+ apic_printk(APIC_VERBOSE," failed :(.\n");
+ panic("IO-APIC + timer doesn't work! Try using the 'noapic' kernel
parameter\n");
+}
+#else
+#define check_timer() ((void)0)
+#endif /* !CONFIG_XEN */
+
+/*
+ *
+ * IRQ's that are handled by the PIC in the MPS IOAPIC case.
+ * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ.
+ * Linux doesn't really care, as it's not actually used
+ * for any interrupt handling anyway.
+ */
+#define PIC_IRQS (1<<2)
+
+void __init setup_IO_APIC(void)
+{
+ enable_IO_APIC();
+
+ if (acpi_ioapic)
+ io_apic_irqs = ~0; /* all IRQs go through IOAPIC */
+ else
+ io_apic_irqs = ~PIC_IRQS;
+
+ apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n");
+
+ /*
+ * Set up the IO-APIC IRQ routing table.
+ */
+ if (!acpi_ioapic)
+ setup_ioapic_ids_from_mpc();
+#ifndef CONFIG_XEN
+ sync_Arb_IDs();
+#endif /* !CONFIG_XEN */
+ setup_IO_APIC_irqs();
+ init_IO_APIC_traps();
+ check_timer();
+ if (!acpi_ioapic)
+ print_IO_APIC();
+}
+
+struct sysfs_ioapic_data {
+ struct sys_device dev;
+ struct IO_APIC_route_entry entry[0];
+};
+static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS];
+
+static int ioapic_suspend(struct sys_device *dev, u32 state)
+{
+ struct IO_APIC_route_entry *entry;
+ struct sysfs_ioapic_data *data;
+ unsigned long flags;
+ int i;
+
+ data = container_of(dev, struct sysfs_ioapic_data, dev);
+ entry = data->entry;
+ spin_lock_irqsave(&ioapic_lock, flags);
+ for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) {
+ *(((int *)entry) + 1) = io_apic_read(dev->id, 0x11 + 2 * i);
+ *(((int *)entry) + 0) = io_apic_read(dev->id, 0x10 + 2 * i);
+ }
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return 0;
+}
+
+static int ioapic_resume(struct sys_device *dev)
+{
+ struct IO_APIC_route_entry *entry;
+ struct sysfs_ioapic_data *data;
+ unsigned long flags;
+ union IO_APIC_reg_00 reg_00;
+ int i;
+
+ data = container_of(dev, struct sysfs_ioapic_data, dev);
+ entry = data->entry;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(dev->id, 0);
+ if (reg_00.bits.ID != mp_ioapics[dev->id].mpc_apicid) {
+ reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid;
+ io_apic_write(dev->id, 0, reg_00.raw);
+ }
+ for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) {
+ io_apic_write(dev->id, 0x11+2*i, *(((int *)entry)+1));
+ io_apic_write(dev->id, 0x10+2*i, *(((int *)entry)+0));
+ }
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return 0;
+}
+
+static struct sysdev_class ioapic_sysdev_class = {
+ set_kset_name("ioapic"),
+ .suspend = ioapic_suspend,
+ .resume = ioapic_resume,
+};
+
+static int __init ioapic_init_sysfs(void)
+{
+ struct sys_device * dev;
+ int i, size, error = 0;
+
+ error = sysdev_class_register(&ioapic_sysdev_class);
+ if (error)
+ return error;
+
+ for (i = 0; i < nr_ioapics; i++ ) {
+ size = sizeof(struct sys_device) + nr_ioapic_registers[i]
+ * sizeof(struct IO_APIC_route_entry);
+ mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL);
+ if (!mp_ioapic_data[i]) {
+ printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
+ continue;
+ }
+ memset(mp_ioapic_data[i], 0, size);
+ dev = &mp_ioapic_data[i]->dev;
+ dev->id = i;
+ dev->cls = &ioapic_sysdev_class;
+ error = sysdev_register(dev);
+ if (error) {
+ kfree(mp_ioapic_data[i]);
+ mp_ioapic_data[i] = NULL;
+ printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
+ continue;
+ }
+ }
+
+ return 0;
+}
+
+device_initcall(ioapic_init_sysfs);
+
+/* --------------------------------------------------------------------------
+ ACPI-based IOAPIC Configuration
+ --------------------------------------------------------------------------
*/
+
+#ifdef CONFIG_ACPI_BOOT
+
+#define IO_APIC_MAX_ID 0xFE
+
+int __init io_apic_get_unique_id (int ioapic, int apic_id)
+{
+#ifndef CONFIG_XEN
+ union IO_APIC_reg_00 reg_00;
+ static physid_mask_t apic_id_map;
+ unsigned long flags;
+ int i = 0;
+
+ /*
+ * The P4 platform supports up to 256 APIC IDs on two separate APIC
+ * buses (one for LAPICs, one for IOAPICs), where predecessors only
+ * supports up to 16 on one shared APIC bus.
+ *
+ * TBD: Expand LAPIC/IOAPIC support on P4-class systems to take full
+ * advantage of new APIC bus architecture.
+ */
+
+ if (physids_empty(apic_id_map))
+ apic_id_map = phys_cpu_present_map;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(ioapic, 0);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ if (apic_id >= IO_APIC_MAX_ID) {
+ apic_printk(APIC_QUIET, KERN_WARNING "IOAPIC[%d]: Invalid
apic_id %d, trying "
+ "%d\n", ioapic, apic_id, reg_00.bits.ID);
+ apic_id = reg_00.bits.ID;
+ }
+
+ /*
+ * Every APIC in a system must have a unique ID or we get lots of nice
+ * 'stuck on smp_invalidate_needed IPI wait' messages.
+ */
+ if (physid_isset(apic_id, apic_id_map)) {
+
+ for (i = 0; i < IO_APIC_MAX_ID; i++) {
+ if (!physid_isset(i, apic_id_map))
+ break;
+ }
+
+ if (i == IO_APIC_MAX_ID)
+ panic("Max apic_id exceeded!\n");
+
+ apic_printk(APIC_VERBOSE, KERN_WARNING "IOAPIC[%d]: apic_id %d
already used, "
+ "trying %d\n", ioapic, apic_id, i);
+
+ apic_id = i;
+ }
+
+ physid_set(apic_id, apic_id_map);
+
+ if (reg_00.bits.ID != apic_id) {
+ reg_00.bits.ID = apic_id;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(ioapic, 0, reg_00.raw);
+ reg_00.raw = io_apic_read(ioapic, 0);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ /* Sanity check */
+ if (reg_00.bits.ID != apic_id)
+ panic("IOAPIC[%d]: Unable change apic_id!\n", ioapic);
+ }
+
+ apic_printk(APIC_VERBOSE,KERN_INFO "IOAPIC[%d]: Assigned apic_id %d\n",
ioapic, apic_id);
+#endif /* !CONFIG_XEN */
+
+ return apic_id;
+}
+
+
+int __init io_apic_get_version (int ioapic)
+{
+ union IO_APIC_reg_01 reg_01;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_01.raw = io_apic_read(ioapic, 1);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return reg_01.bits.version;
+}
+
+
+int __init io_apic_get_redir_entries (int ioapic)
+{
+ union IO_APIC_reg_01 reg_01;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_01.raw = io_apic_read(ioapic, 1);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return reg_01.bits.entries;
+}
+
+
+int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int
active_high_low)
+{
+ struct IO_APIC_route_entry entry;
+ unsigned long flags;
+
+ if (!IO_APIC_IRQ(irq)) {
+ apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference
to IRQ 0\n",
+ ioapic);
+ return -EINVAL;
+ }
+
+ /*
+ * Generate a PCI IRQ routing entry and program the IOAPIC accordingly.
+ * Note that we mask (disable) IRQs now -- these get enabled when the
+ * corresponding device driver registers for this IRQ.
+ */
+
+ memset(&entry,0,sizeof(entry));
+
+ entry.delivery_mode = INT_DELIVERY_MODE;
+ entry.dest_mode = INT_DEST_MODE;
+ entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS);
+ entry.trigger = edge_level;
+ entry.polarity = active_high_low;
+ entry.mask = 1; /* Disabled (masked) */
+
+ /*
+ * IRQs < 16 are already in the irq_2_pin[] map
+ */
+ if (irq >= 16)
+ add_pin_to_irq(irq, ioapic, pin);
+
+ entry.vector = assign_irq_vector(irq);
+
+ apic_printk(APIC_VERBOSE,KERN_DEBUG "IOAPIC[%d]: Set PCI routing entry
(%d-%d -> 0x%x -> "
+ "IRQ %d Mode:%i Active:%i)\n", ioapic,
+ mp_ioapics[ioapic].mpc_apicid, pin, entry.vector, irq,
+ edge_level, active_high_low);
+
+ ioapic_register_intr(irq, entry.vector, edge_level);
+
+ if (!ioapic && (irq < 16))
+ disable_8259A_irq(irq);
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(ioapic, 0x11+2*pin, *(((int *)&entry)+1));
+ io_apic_write(ioapic, 0x10+2*pin, *(((int *)&entry)+0));
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return 0;
+}
+
+#endif /*CONFIG_ACPI_BOOT*/
+
+
+#ifndef CONFIG_XEN
+/*
+ * This function currently is only a helper for the i386 smp boot process where
+ * we need to reprogram the ioredtbls to cater for the cpus which have come
online
+ * so mask in all cases should simply be TARGET_CPUS
+ */
+void __init setup_ioapic_dest(void)
+{
+ int pin, ioapic, irq, irq_entry;
+
+ if (skip_ioapic_setup == 1)
+ return;
+
+ for (ioapic = 0; ioapic < nr_ioapics; ioapic++) {
+ for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
+ irq_entry = find_irq_entry(ioapic, pin, mp_INT);
+ if (irq_entry == -1)
+ continue;
+ irq = pin_2_irq(irq_entry, ioapic, pin);
+ set_ioapic_affinity_irq(irq, TARGET_CPUS);
+ }
+
+ }
+}
+#endif /* !CONFIG_XEN */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/netfront/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/netfront/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,2 @@
+
+obj-y := netfront.o
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/usbback/interface.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/usbback/interface.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,252 @@
+/******************************************************************************
+ * arch/xen/drivers/usbif/backend/interface.c
+ *
+ * USB device interface management.
+ *
+ * by Mark Williamson, Copyright (c) 2004
+ */
+
+
+/******************************************************************************
+ * arch/xen/drivers/blkif/backend/interface.c
+ *
+ * Block-device interface management.
+ *
+ * Copyright (c) 2004, Keir Fraser
+ */
+
+#include "common.h"
+
+#define USBIF_HASHSZ 1024
+#define USBIF_HASH(_d) (((int)(_d))&(USBIF_HASHSZ-1))
+
+static kmem_cache_t *usbif_priv_cachep;
+static usbif_priv_t *usbif_priv_hash[USBIF_HASHSZ];
+
+usbif_priv_t *usbif_find(domid_t domid)
+{
+ usbif_priv_t *up = usbif_priv_hash[USBIF_HASH(domid)];
+ while ( (up != NULL ) && ( up->domid != domid ) )
+ up = up->hash_next;
+ return up;
+}
+
+static void __usbif_disconnect_complete(void *arg)
+{
+ usbif_priv_t *usbif = (usbif_priv_t *)arg;
+ ctrl_msg_t cmsg;
+ usbif_be_disconnect_t disc;
+
+ /*
+ * These can't be done in usbif_disconnect() because at that point there
+ * may be outstanding requests at the device whose asynchronous responses
+ * must still be notified to the remote driver.
+ */
+ unbind_evtchn_from_irq(usbif->evtchn);
+ vfree(usbif->usb_ring.sring);
+
+ /* Construct the deferred response message. */
+ cmsg.type = CMSG_USBIF_BE;
+ cmsg.subtype = CMSG_USBIF_BE_DISCONNECT;
+ cmsg.id = usbif->disconnect_rspid;
+ cmsg.length = sizeof(usbif_be_disconnect_t);
+ disc.domid = usbif->domid;
+ disc.status = USBIF_BE_STATUS_OKAY;
+ memcpy(cmsg.msg, &disc, sizeof(disc));
+
+ /*
+ * Make sure message is constructed /before/ status change, because
+ * after the status change the 'usbif' structure could be deallocated at
+ * any time. Also make sure we send the response /after/ status change,
+ * as otherwise a subsequent CONNECT request could spuriously fail if
+ * another CPU doesn't see the status change yet.
+ */
+ mb();
+ if ( usbif->status != DISCONNECTING )
+ BUG();
+ usbif->status = DISCONNECTED;
+ mb();
+
+ /* Send the successful response. */
+ ctrl_if_send_response(&cmsg);
+}
+
+void usbif_disconnect_complete(usbif_priv_t *up)
+{
+ INIT_WORK(&up->work, __usbif_disconnect_complete, (void *)up);
+ schedule_work(&up->work);
+}
+
+void usbif_create(usbif_be_create_t *create)
+{
+ domid_t domid = create->domid;
+ usbif_priv_t **pup, *up;
+
+ if ( (up = kmem_cache_alloc(usbif_priv_cachep, GFP_KERNEL)) == NULL )
+ {
+ DPRINTK("Could not create usbif: out of memory\n");
+ create->status = USBIF_BE_STATUS_OUT_OF_MEMORY;
+ return;
+ }
+
+ memset(up, 0, sizeof(*up));
+ up->domid = domid;
+ up->status = DISCONNECTED;
+ spin_lock_init(&up->usb_ring_lock);
+ atomic_set(&up->refcnt, 0);
+
+ pup = &usbif_priv_hash[USBIF_HASH(domid)];
+ while ( *pup != NULL )
+ {
+ if ( (*pup)->domid == domid )
+ {
+ create->status = USBIF_BE_STATUS_INTERFACE_EXISTS;
+ kmem_cache_free(usbif_priv_cachep, up);
+ return;
+ }
+ pup = &(*pup)->hash_next;
+ }
+
+ up->hash_next = *pup;
+ *pup = up;
+
+ create->status = USBIF_BE_STATUS_OKAY;
+}
+
+void usbif_destroy(usbif_be_destroy_t *destroy)
+{
+ domid_t domid = destroy->domid;
+ usbif_priv_t **pup, *up;
+
+ pup = &usbif_priv_hash[USBIF_HASH(domid)];
+ while ( (up = *pup) != NULL )
+ {
+ if ( up->domid == domid )
+ {
+ if ( up->status != DISCONNECTED )
+ goto still_connected;
+ goto destroy;
+ }
+ pup = &up->hash_next;
+ }
+
+ destroy->status = USBIF_BE_STATUS_INTERFACE_NOT_FOUND;
+ return;
+
+ still_connected:
+ destroy->status = USBIF_BE_STATUS_INTERFACE_CONNECTED;
+ return;
+
+ destroy:
+ *pup = up->hash_next;
+ usbif_release_ports(up);
+ kmem_cache_free(usbif_priv_cachep, up);
+ destroy->status = USBIF_BE_STATUS_OKAY;
+}
+
+void usbif_connect(usbif_be_connect_t *connect)
+{
+ domid_t domid = connect->domid;
+ unsigned int evtchn = connect->evtchn;
+ unsigned long shmem_frame = connect->shmem_frame;
+ struct vm_struct *vma;
+ pgprot_t prot;
+ int error;
+ usbif_priv_t *up;
+ usbif_sring_t *sring;
+
+ up = usbif_find(domid);
+ if ( unlikely(up == NULL) )
+ {
+ DPRINTK("usbif_connect attempted for non-existent usbif (%u)\n",
+ connect->domid);
+ connect->status = USBIF_BE_STATUS_INTERFACE_NOT_FOUND;
+ return;
+ }
+
+ if ( (vma = get_vm_area(PAGE_SIZE, VM_IOREMAP)) == NULL )
+ {
+ connect->status = USBIF_BE_STATUS_OUT_OF_MEMORY;
+ return;
+ }
+
+ prot = __pgprot(_KERNPG_TABLE);
+ error = direct_remap_area_pages(&init_mm, VMALLOC_VMADDR(vma->addr),
+ shmem_frame<<PAGE_SHIFT, PAGE_SIZE,
+ prot, domid);
+ if ( error != 0 )
+ {
+ if ( error == -ENOMEM )
+ connect->status = USBIF_BE_STATUS_OUT_OF_MEMORY;
+ else if ( error == -EFAULT )
+ connect->status = USBIF_BE_STATUS_MAPPING_ERROR;
+ else
+ connect->status = USBIF_BE_STATUS_ERROR;
+ vfree(vma->addr);
+ return;
+ }
+
+ if ( up->status != DISCONNECTED )
+ {
+ connect->status = USBIF_BE_STATUS_INTERFACE_CONNECTED;
+ vfree(vma->addr);
+ return;
+ }
+
+ sring = (usbif_sring_t *)vma->addr;
+ SHARED_RING_INIT(sring);
+ BACK_RING_INIT(&up->usb_ring, sring, PAGE_SIZE);
+
+ up->evtchn = evtchn;
+ up->irq = bind_evtchn_to_irq(evtchn);
+ up->shmem_frame = shmem_frame;
+ up->status = CONNECTED;
+ usbif_get(up);
+
+ request_irq(up->irq, usbif_be_int, 0, "usbif-backend", up);
+
+ connect->status = USBIF_BE_STATUS_OKAY;
+}
+
+/* Remove URBs for this interface before destroying it. */
+void usbif_deschedule(usbif_priv_t *up)
+{
+ remove_from_usbif_list(up);
+}
+
+int usbif_disconnect(usbif_be_disconnect_t *disconnect, u8 rsp_id)
+{
+ domid_t domid = disconnect->domid;
+ usbif_priv_t *up;
+
+ up = usbif_find(domid);
+ if ( unlikely(up == NULL) )
+ {
+ DPRINTK("usbif_disconnect attempted for non-existent usbif"
+ " (%u)\n", disconnect->domid);
+ disconnect->status = USBIF_BE_STATUS_INTERFACE_NOT_FOUND;
+ return 1; /* Caller will send response error message. */
+ }
+
+ if ( up->status == CONNECTED )
+ {
+ up->status = DISCONNECTING;
+ up->disconnect_rspid = rsp_id;
+ wmb(); /* Let other CPUs see the status change. */
+ free_irq(up->irq, up);
+ usbif_deschedule(up);
+ usbif_put(up);
+ return 0; /* Caller should not send response message. */
+ }
+
+ disconnect->status = USBIF_BE_STATUS_OKAY;
+ return 1;
+}
+
+void __init usbif_interface_init(void)
+{
+ usbif_priv_cachep = kmem_cache_create("usbif_priv_cache",
+ sizeof(usbif_priv_t),
+ 0, 0, NULL, NULL);
+ memset(usbif_priv_hash, 0, sizeof(usbif_priv_hash));
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/linux-public/suspend.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/linux-public/suspend.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,43 @@
+/******************************************************************************
+ * suspend.h
+ *
+ * Copyright (c) 2003-2004, K A Fraser
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __ASM_XEN_SUSPEND_H__
+#define __ASM_XEN_SUSPEND_H__
+
+typedef struct suspend_record_st {
+ /* To be filled in before resume. */
+ start_info_t resume_info;
+ /*
+ * The number of a machine frame containing, in sequence, the number of
+ * each machine frame that contains PFN -> MFN translation table data.
+ */
+ unsigned long pfn_to_mfn_frame_list;
+ /* Number of entries in the PFN -> MFN translation table. */
+ unsigned long nr_pfns;
+} suspend_record_t;
+
+#endif /* __ASM_XEN_SUSPEND_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/smp.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/smp.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,154 @@
+#ifndef __ASM_SMP_H
+#define __ASM_SMP_H
+
+/*
+ * We need the APIC definitions automatically as part of 'smp.h'
+ */
+#ifndef __ASSEMBLY__
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/bitops.h>
+extern int disable_apic;
+#endif
+
+#ifdef CONFIG_X86_LOCAL_APIC
+#ifndef __ASSEMBLY__
+#include <asm/fixmap.h>
+#include <asm/mpspec.h>
+#ifdef CONFIG_X86_IO_APIC
+#include <asm/io_apic.h>
+#endif
+#include <asm/apic.h>
+#include <asm/thread_info.h>
+#endif
+#endif
+
+#ifdef CONFIG_SMP
+#ifndef ASSEMBLY
+
+#include <asm/pda.h>
+
+struct pt_regs;
+
+/*
+ * Private routines/data
+ */
+
+extern void smp_alloc_memory(void);
+extern cpumask_t cpu_online_map;
+extern volatile unsigned long smp_invalidate_needed;
+extern int pic_mode;
+extern int smp_num_siblings;
+extern void smp_flush_tlb(void);
+extern void smp_message_irq(int cpl, void *dev_id, struct pt_regs *regs);
+extern void smp_send_reschedule(int cpu);
+extern void smp_invalidate_rcv(void); /* Process an NMI */
+extern void (*mtrr_hook) (void);
+extern void zap_low_mappings(void);
+void smp_stop_cpu(void);
+extern cpumask_t cpu_sibling_map[NR_CPUS];
+extern u8 phys_proc_id[NR_CPUS];
+
+#define SMP_TRAMPOLINE_BASE 0x6000
+
+/*
+ * On x86 all CPUs are mapped 1:1 to the APIC space.
+ * This simplifies scheduling and IPI sending and
+ * compresses data structures.
+ */
+
+extern cpumask_t cpu_callout_map;
+extern cpumask_t cpu_callin_map;
+#define cpu_possible_map cpu_callout_map
+
+static inline int num_booting_cpus(void)
+{
+ return cpus_weight(cpu_callout_map);
+}
+
+#define __smp_processor_id() read_pda(cpunumber)
+
+#ifdef CONFIG_X86_LOCAL_APIC
+extern __inline int hard_smp_processor_id(void)
+{
+ /* we don't want to mark this access volatile - bad code generation */
+ return GET_APIC_ID(*(unsigned int *)(APIC_BASE+APIC_ID));
+}
+#endif
+
+#define safe_smp_processor_id() (disable_apic ? 0 :
x86_apicid_to_cpu(hard_smp_processor_id()))
+
+#endif /* !ASSEMBLY */
+
+#define NO_PROC_ID 0xFF /* No processor magic marker */
+
+#endif
+
+#ifndef ASSEMBLY
+/*
+ * Some lowlevel functions might want to know about
+ * the real APIC ID <-> CPU # mapping.
+ */
+extern u8 x86_cpu_to_apicid[NR_CPUS]; /* physical ID */
+extern u8 x86_cpu_to_log_apicid[NR_CPUS];
+extern u8 bios_cpu_apicid[];
+#ifdef CONFIG_X86_LOCAL_APIC
+static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+{
+ return cpus_addr(cpumask)[0];
+}
+
+static inline int x86_apicid_to_cpu(u8 apicid)
+{
+ int i;
+
+ for (i = 0; i < NR_CPUS; ++i)
+ if (x86_cpu_to_apicid[i] == apicid)
+ return i;
+
+ /* No entries in x86_cpu_to_apicid? Either no MPS|ACPI,
+ * or called too early. Either way, we must be CPU 0. */
+ if (x86_cpu_to_apicid[0] == BAD_APICID)
+ return 0;
+
+ return -1;
+}
+
+static inline int cpu_present_to_apicid(int mps_cpu)
+{
+ if (mps_cpu < NR_CPUS)
+ return (int)bios_cpu_apicid[mps_cpu];
+ else
+ return BAD_APICID;
+}
+#endif
+
+#endif /* !ASSEMBLY */
+
+#ifndef CONFIG_SMP
+#define stack_smp_processor_id() 0
+#define safe_smp_processor_id() 0
+#define cpu_logical_map(x) (x)
+#else
+#include <asm/thread_info.h>
+#define stack_smp_processor_id() \
+({ \
+ struct thread_info *ti; \
+ __asm__("andq %%rsp,%0; ":"=r" (ti) : "0" (CURRENT_MASK)); \
+ ti->cpu; \
+})
+#endif
+
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_X86_LOCAL_APIC
+static __inline int logical_smp_processor_id(void)
+{
+ /* we don't want to mark this access volatile - bad code generation */
+ return GET_APIC_LOGICAL_ID(*(unsigned long *)(APIC_BASE+APIC_LDR));
+}
+#endif
+#endif
+
+#endif
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/desc.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/desc.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,37 @@
+#ifndef __ARCH_DESC_H
+#define __ARCH_DESC_H
+
+#include <asm/ldt.h>
+
+#ifndef __ASSEMBLY__
+
+struct desc_struct {
+ unsigned long a,b;
+};
+
+struct Xgt_desc_struct {
+ unsigned short size;
+ unsigned long address __attribute__((packed));
+};
+
+extern struct desc_struct default_ldt[];
+
+static inline void clear_LDT(void)
+{
+ xen_set_ldt(0, 0);
+}
+
+static inline void load_LDT(mm_context_t *pc)
+{
+ void *segments = pc->ldt;
+ int count = pc->size;
+
+ if ( count == 0 )
+ segments = NULL;
+
+ xen_set_ldt((unsigned long)segments, count);
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ARCH_DESC_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/netback/netback.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/netback/netback.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,823 @@
+/******************************************************************************
+ * drivers/xen/netback/netback.c
+ *
+ * Back-end of the driver for virtual network devices. This portion of the
+ * driver exports a 'unified' network-device interface that can be accessed
+ * by any operating system that implements a compatible front end. A
+ * reference front-end implementation can be found in:
+ * drivers/xen/netfront/netfront.c
+ *
+ * Copyright (c) 2002-2005, K A Fraser
+ */
+
+#include "common.h"
+#include <asm-xen/balloon.h>
+#include <asm-xen/evtchn.h>
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
+#include <linux/delay.h>
+#endif
+
+static void netif_idx_release(u16 pending_idx);
+static void netif_page_release(struct page *page);
+static void make_tx_response(netif_t *netif,
+ u16 id,
+ s8 st);
+static int make_rx_response(netif_t *netif,
+ u16 id,
+ s8 st,
+ memory_t addr,
+ u16 size,
+ u16 csum_valid);
+
+static void net_tx_action(unsigned long unused);
+static DECLARE_TASKLET(net_tx_tasklet, net_tx_action, 0);
+
+static void net_rx_action(unsigned long unused);
+static DECLARE_TASKLET(net_rx_tasklet, net_rx_action, 0);
+
+static struct timer_list net_timer;
+
+static struct sk_buff_head rx_queue;
+static multicall_entry_t rx_mcl[NETIF_RX_RING_SIZE*2+1];
+static mmu_update_t rx_mmu[NETIF_RX_RING_SIZE];
+static struct mmuext_op rx_mmuext[NETIF_RX_RING_SIZE];
+static unsigned char rx_notify[NR_EVENT_CHANNELS];
+
+/* Don't currently gate addition of an interface to the tx scheduling list. */
+#define tx_work_exists(_if) (1)
+
+#define MAX_PENDING_REQS 256
+static unsigned long mmap_vstart;
+#define MMAP_VADDR(_req) (mmap_vstart + ((_req) * PAGE_SIZE))
+
+#define PKT_PROT_LEN 64
+
+static struct {
+ netif_tx_request_t req;
+ netif_t *netif;
+} pending_tx_info[MAX_PENDING_REQS];
+static u16 pending_ring[MAX_PENDING_REQS];
+typedef unsigned int PEND_RING_IDX;
+#define MASK_PEND_IDX(_i) ((_i)&(MAX_PENDING_REQS-1))
+static PEND_RING_IDX pending_prod, pending_cons;
+#define NR_PENDING_REQS (MAX_PENDING_REQS - pending_prod + pending_cons)
+
+/* Freed TX SKBs get batched on this ring before return to pending_ring. */
+static u16 dealloc_ring[MAX_PENDING_REQS];
+static PEND_RING_IDX dealloc_prod, dealloc_cons;
+
+static struct sk_buff_head tx_queue;
+static multicall_entry_t tx_mcl[MAX_PENDING_REQS];
+
+static struct list_head net_schedule_list;
+static spinlock_t net_schedule_list_lock;
+
+#define MAX_MFN_ALLOC 64
+static unsigned long mfn_list[MAX_MFN_ALLOC];
+static unsigned int alloc_index = 0;
+static spinlock_t mfn_lock = SPIN_LOCK_UNLOCKED;
+
+static unsigned long alloc_mfn(void)
+{
+ unsigned long mfn = 0, flags;
+ spin_lock_irqsave(&mfn_lock, flags);
+ if ( unlikely(alloc_index == 0) )
+ alloc_index = HYPERVISOR_dom_mem_op(
+ MEMOP_increase_reservation, mfn_list, MAX_MFN_ALLOC, 0);
+ if ( alloc_index != 0 )
+ mfn = mfn_list[--alloc_index];
+ spin_unlock_irqrestore(&mfn_lock, flags);
+ return mfn;
+}
+
+static void free_mfn(unsigned long mfn)
+{
+ unsigned long flags;
+ spin_lock_irqsave(&mfn_lock, flags);
+ if ( alloc_index != MAX_MFN_ALLOC )
+ mfn_list[alloc_index++] = mfn;
+ else if ( HYPERVISOR_dom_mem_op(MEMOP_decrease_reservation,
+ &mfn, 1, 0) != 1 )
+ BUG();
+ spin_unlock_irqrestore(&mfn_lock, flags);
+}
+
+static inline void maybe_schedule_tx_action(void)
+{
+ smp_mb();
+ if ( (NR_PENDING_REQS < (MAX_PENDING_REQS/2)) &&
+ !list_empty(&net_schedule_list) )
+ tasklet_schedule(&net_tx_tasklet);
+}
+
+/*
+ * A gross way of confirming the origin of an skb data page. The slab
+ * allocator abuses a field in the page struct to cache the kmem_cache_t ptr.
+ */
+static inline int is_xen_skb(struct sk_buff *skb)
+{
+ extern kmem_cache_t *skbuff_cachep;
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+ kmem_cache_t *cp = (kmem_cache_t *)virt_to_page(skb->head)->lru.next;
+#else
+ kmem_cache_t *cp = (kmem_cache_t *)virt_to_page(skb->head)->list.next;
+#endif
+ return (cp == skbuff_cachep);
+}
+
+int netif_be_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ netif_t *netif = netdev_priv(dev);
+
+ ASSERT(skb->dev == dev);
+
+ /* Drop the packet if the target domain has no receive buffers. */
+ if ( !netif->active ||
+ (netif->rx_req_cons == netif->rx->req_prod) ||
+ ((netif->rx_req_cons-netif->rx_resp_prod) == NETIF_RX_RING_SIZE) )
+ goto drop;
+
+ /*
+ * We do not copy the packet unless:
+ * 1. The data is shared; or
+ * 2. The data is not allocated from our special cache.
+ * NB. We also couldn't cope with fragmented packets, but we won't get
+ * any because we not advertise the NETIF_F_SG feature.
+ */
+ if ( skb_shared(skb) || skb_cloned(skb) || !is_xen_skb(skb) )
+ {
+ int hlen = skb->data - skb->head;
+ struct sk_buff *nskb = dev_alloc_skb(hlen + skb->len);
+ if ( unlikely(nskb == NULL) )
+ goto drop;
+ skb_reserve(nskb, hlen);
+ __skb_put(nskb, skb->len);
+ if (skb_copy_bits(skb, -hlen, nskb->data - hlen, skb->len + hlen))
+ BUG();
+ nskb->dev = skb->dev;
+ nskb->proto_csum_valid = skb->proto_csum_valid;
+ dev_kfree_skb(skb);
+ skb = nskb;
+ }
+
+ netif->rx_req_cons++;
+ netif_get(netif);
+
+ skb_queue_tail(&rx_queue, skb);
+ tasklet_schedule(&net_rx_tasklet);
+
+ return 0;
+
+ drop:
+ netif->stats.tx_dropped++;
+ dev_kfree_skb(skb);
+ return 0;
+}
+
+#if 0
+static void xen_network_done_notify(void)
+{
+ static struct net_device *eth0_dev = NULL;
+ if ( unlikely(eth0_dev == NULL) )
+ eth0_dev = __dev_get_by_name("eth0");
+ netif_rx_schedule(eth0_dev);
+}
+/*
+ * Add following to poll() function in NAPI driver (Tigon3 is example):
+ * if ( xen_network_done() )
+ * tg3_enable_ints(tp);
+ */
+int xen_network_done(void)
+{
+ return skb_queue_empty(&rx_queue);
+}
+#endif
+
+static void net_rx_action(unsigned long unused)
+{
+ netif_t *netif;
+ s8 status;
+ u16 size, id, evtchn;
+ multicall_entry_t *mcl;
+ mmu_update_t *mmu;
+ struct mmuext_op *mmuext;
+ unsigned long vdata, mdata, new_mfn;
+ struct sk_buff_head rxq;
+ struct sk_buff *skb;
+ u16 notify_list[NETIF_RX_RING_SIZE];
+ int notify_nr = 0;
+
+ skb_queue_head_init(&rxq);
+
+ mcl = rx_mcl;
+ mmu = rx_mmu;
+ mmuext = rx_mmuext;
+ while ( (skb = skb_dequeue(&rx_queue)) != NULL )
+ {
+ netif = netdev_priv(skb->dev);
+ vdata = (unsigned long)skb->data;
+ mdata = virt_to_machine(vdata);
+
+ /* Memory squeeze? Back off for an arbitrary while. */
+ if ( (new_mfn = alloc_mfn()) == 0 )
+ {
+ if ( net_ratelimit() )
+ printk(KERN_WARNING "Memory squeeze in netback driver.\n");
+ mod_timer(&net_timer, jiffies + HZ);
+ skb_queue_head(&rx_queue, skb);
+ break;
+ }
+
+ /*
+ * Set the new P2M table entry before reassigning the old data page.
+ * Heed the comment in pgtable-2level.h:pte_page(). :-)
+ */
+ phys_to_machine_mapping[__pa(skb->data) >> PAGE_SHIFT] = new_mfn;
+
+ MULTI_update_va_mapping(mcl, vdata,
+ pfn_pte_ma(new_mfn, PAGE_KERNEL), 0);
+ mcl++;
+
+ mcl->op = __HYPERVISOR_mmuext_op;
+ mcl->args[0] = (unsigned long)mmuext;
+ mcl->args[1] = 1;
+ mcl->args[2] = 0;
+ mcl->args[3] = netif->domid;
+ mcl++;
+
+ mmuext->cmd = MMUEXT_REASSIGN_PAGE;
+ mmuext->mfn = mdata >> PAGE_SHIFT;
+ mmuext++;
+
+ mmu->ptr = (new_mfn << PAGE_SHIFT) | MMU_MACHPHYS_UPDATE;
+ mmu->val = __pa(vdata) >> PAGE_SHIFT;
+ mmu++;
+
+ __skb_queue_tail(&rxq, skb);
+
+ /* Filled the batch queue? */
+ if ( (mcl - rx_mcl) == ARRAY_SIZE(rx_mcl) )
+ break;
+ }
+
+ if ( mcl == rx_mcl )
+ return;
+
+ mcl->op = __HYPERVISOR_mmu_update;
+ mcl->args[0] = (unsigned long)rx_mmu;
+ mcl->args[1] = mmu - rx_mmu;
+ mcl->args[2] = 0;
+ mcl->args[3] = DOMID_SELF;
+ mcl++;
+
+ mcl[-3].args[2] = UVMF_TLB_FLUSH|UVMF_ALL;
+ if ( unlikely(HYPERVISOR_multicall(rx_mcl, mcl - rx_mcl) != 0) )
+ BUG();
+
+ mcl = rx_mcl;
+ mmuext = rx_mmuext;
+ while ( (skb = __skb_dequeue(&rxq)) != NULL )
+ {
+ netif = netdev_priv(skb->dev);
+ size = skb->tail - skb->data;
+
+ /* Rederive the machine addresses. */
+ new_mfn = mcl[0].args[1] >> PAGE_SHIFT;
+ mdata = ((mmuext[0].mfn << PAGE_SHIFT) |
+ ((unsigned long)skb->data & ~PAGE_MASK));
+
+ atomic_set(&(skb_shinfo(skb)->dataref), 1);
+ skb_shinfo(skb)->nr_frags = 0;
+ skb_shinfo(skb)->frag_list = NULL;
+
+ netif->stats.tx_bytes += size;
+ netif->stats.tx_packets++;
+
+ /* The update_va_mapping() must not fail. */
+ BUG_ON(mcl[0].result != 0);
+
+ /* Check the reassignment error code. */
+ status = NETIF_RSP_OKAY;
+ if ( unlikely(mcl[1].result != 0) )
+ {
+ DPRINTK("Failed MMU update transferring to DOM%u\n", netif->domid);
+ free_mfn(mdata >> PAGE_SHIFT);
+ status = NETIF_RSP_ERROR;
+ }
+
+ evtchn = netif->evtchn;
+ id = netif->rx->ring[MASK_NETIF_RX_IDX(netif->rx_resp_prod)].req.id;
+ if ( make_rx_response(netif, id, status, mdata,
+ size, skb->proto_csum_valid) &&
+ (rx_notify[evtchn] == 0) )
+ {
+ rx_notify[evtchn] = 1;
+ notify_list[notify_nr++] = evtchn;
+ }
+
+ netif_put(netif);
+ dev_kfree_skb(skb);
+
+ mcl += 2;
+ mmuext += 1;
+ }
+
+ while ( notify_nr != 0 )
+ {
+ evtchn = notify_list[--notify_nr];
+ rx_notify[evtchn] = 0;
+ notify_via_evtchn(evtchn);
+ }
+
+ /* More work to do? */
+ if ( !skb_queue_empty(&rx_queue) && !timer_pending(&net_timer) )
+ tasklet_schedule(&net_rx_tasklet);
+#if 0
+ else
+ xen_network_done_notify();
+#endif
+}
+
+static void net_alarm(unsigned long unused)
+{
+ tasklet_schedule(&net_rx_tasklet);
+}
+
+struct net_device_stats *netif_be_get_stats(struct net_device *dev)
+{
+ netif_t *netif = netdev_priv(dev);
+ return &netif->stats;
+}
+
+static int __on_net_schedule_list(netif_t *netif)
+{
+ return netif->list.next != NULL;
+}
+
+static void remove_from_net_schedule_list(netif_t *netif)
+{
+ spin_lock_irq(&net_schedule_list_lock);
+ if ( likely(__on_net_schedule_list(netif)) )
+ {
+ list_del(&netif->list);
+ netif->list.next = NULL;
+ netif_put(netif);
+ }
+ spin_unlock_irq(&net_schedule_list_lock);
+}
+
+static void add_to_net_schedule_list_tail(netif_t *netif)
+{
+ if ( __on_net_schedule_list(netif) )
+ return;
+
+ spin_lock_irq(&net_schedule_list_lock);
+ if ( !__on_net_schedule_list(netif) && netif->active )
+ {
+ list_add_tail(&netif->list, &net_schedule_list);
+ netif_get(netif);
+ }
+ spin_unlock_irq(&net_schedule_list_lock);
+}
+
+void netif_schedule_work(netif_t *netif)
+{
+ if ( (netif->tx_req_cons != netif->tx->req_prod) &&
+ ((netif->tx_req_cons-netif->tx_resp_prod) != NETIF_TX_RING_SIZE) )
+ {
+ add_to_net_schedule_list_tail(netif);
+ maybe_schedule_tx_action();
+ }
+}
+
+void netif_deschedule_work(netif_t *netif)
+{
+ remove_from_net_schedule_list(netif);
+}
+
+
+static void tx_credit_callback(unsigned long data)
+{
+ netif_t *netif = (netif_t *)data;
+ netif->remaining_credit = netif->credit_bytes;
+ netif_schedule_work(netif);
+}
+
+static void net_tx_action(unsigned long unused)
+{
+ struct list_head *ent;
+ struct sk_buff *skb;
+ netif_t *netif;
+ netif_tx_request_t txreq;
+ u16 pending_idx;
+ NETIF_RING_IDX i;
+ multicall_entry_t *mcl;
+ PEND_RING_IDX dc, dp;
+ unsigned int data_len;
+
+ if ( (dc = dealloc_cons) == (dp = dealloc_prod) )
+ goto skip_dealloc;
+
+ mcl = tx_mcl;
+ while ( dc != dp )
+ {
+ pending_idx = dealloc_ring[MASK_PEND_IDX(dc++)];
+ MULTI_update_va_mapping(mcl, MMAP_VADDR(pending_idx),
+ __pte(0), 0);
+ mcl++;
+ }
+
+ mcl[-1].args[2] = UVMF_TLB_FLUSH|UVMF_ALL;
+ if ( unlikely(HYPERVISOR_multicall(tx_mcl, mcl - tx_mcl) != 0) )
+ BUG();
+
+ mcl = tx_mcl;
+ while ( dealloc_cons != dp )
+ {
+ /* The update_va_mapping() must not fail. */
+ BUG_ON(mcl[0].result != 0);
+
+ pending_idx = dealloc_ring[MASK_PEND_IDX(dealloc_cons++)];
+
+ netif = pending_tx_info[pending_idx].netif;
+
+ make_tx_response(netif, pending_tx_info[pending_idx].req.id,
+ NETIF_RSP_OKAY);
+
+ pending_ring[MASK_PEND_IDX(pending_prod++)] = pending_idx;
+
+ /*
+ * Scheduling checks must happen after the above response is posted.
+ * This avoids a possible race with a guest OS on another CPU if that
+ * guest is testing against 'resp_prod' when deciding whether to notify
+ * us when it queues additional packets.
+ */
+ mb();
+ if ( (netif->tx_req_cons != netif->tx->req_prod) &&
+ ((netif->tx_req_cons-netif->tx_resp_prod) != NETIF_TX_RING_SIZE) )
+ add_to_net_schedule_list_tail(netif);
+
+ netif_put(netif);
+
+ mcl++;
+ }
+
+ skip_dealloc:
+ mcl = tx_mcl;
+ while ( (NR_PENDING_REQS < MAX_PENDING_REQS) &&
+ !list_empty(&net_schedule_list) )
+ {
+ /* Get a netif from the list with work to do. */
+ ent = net_schedule_list.next;
+ netif = list_entry(ent, netif_t, list);
+ netif_get(netif);
+ remove_from_net_schedule_list(netif);
+
+ /* Work to do? */
+ i = netif->tx_req_cons;
+ if ( (i == netif->tx->req_prod) ||
+ ((i-netif->tx_resp_prod) == NETIF_TX_RING_SIZE) )
+ {
+ netif_put(netif);
+ continue;
+ }
+
+ rmb(); /* Ensure that we see the request before we copy it. */
+ memcpy(&txreq, &netif->tx->ring[MASK_NETIF_TX_IDX(i)].req,
+ sizeof(txreq));
+
+ /* Credit-based scheduling. */
+ if ( txreq.size > netif->remaining_credit )
+ {
+ unsigned long now = jiffies;
+ unsigned long next_credit =
+ netif->credit_timeout.expires +
+ msecs_to_jiffies(netif->credit_usec / 1000);
+
+ /* Timer could already be pending in some rare cases. */
+ if ( timer_pending(&netif->credit_timeout) )
+ break;
+
+ /* Already passed the point at which we can replenish credit? */
+ if ( time_after_eq(now, next_credit) )
+ {
+ netif->credit_timeout.expires = now;
+ netif->remaining_credit = netif->credit_bytes;
+ }
+
+ /* Still too big to send right now? Then set a timer callback. */
+ if ( txreq.size > netif->remaining_credit )
+ {
+ netif->remaining_credit = 0;
+ netif->credit_timeout.expires = next_credit;
+ netif->credit_timeout.data = (unsigned long)netif;
+ netif->credit_timeout.function = tx_credit_callback;
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+ add_timer_on(&netif->credit_timeout, smp_processor_id());
+#else
+ add_timer(&netif->credit_timeout);
+#endif
+ break;
+ }
+ }
+ netif->remaining_credit -= txreq.size;
+
+ /*
+ * Why the barrier? It ensures that the frontend sees updated req_cons
+ * before we check for more work to schedule.
+ */
+ netif->tx->req_cons = ++netif->tx_req_cons;
+ mb();
+
+ netif_schedule_work(netif);
+
+ if ( unlikely(txreq.size < ETH_HLEN) ||
+ unlikely(txreq.size > ETH_FRAME_LEN) )
+ {
+ DPRINTK("Bad packet size: %d\n", txreq.size);
+ make_tx_response(netif, txreq.id, NETIF_RSP_ERROR);
+ netif_put(netif);
+ continue;
+ }
+
+ /* No crossing a page boundary as the payload mustn't fragment. */
+ if ( unlikely(((txreq.addr & ~PAGE_MASK) + txreq.size) >= PAGE_SIZE) )
+ {
+ DPRINTK("txreq.addr: %lx, size: %u, end: %lu\n",
+ txreq.addr, txreq.size,
+ (txreq.addr &~PAGE_MASK) + txreq.size);
+ make_tx_response(netif, txreq.id, NETIF_RSP_ERROR);
+ netif_put(netif);
+ continue;
+ }
+
+ pending_idx = pending_ring[MASK_PEND_IDX(pending_cons)];
+
+ data_len = (txreq.size > PKT_PROT_LEN) ? PKT_PROT_LEN : txreq.size;
+
+ if ( unlikely((skb = alloc_skb(data_len+16, GFP_ATOMIC)) == NULL) )
+ {
+ DPRINTK("Can't allocate a skb in start_xmit.\n");
+ make_tx_response(netif, txreq.id, NETIF_RSP_ERROR);
+ netif_put(netif);
+ break;
+ }
+
+ /* Packets passed to netif_rx() must have some headroom. */
+ skb_reserve(skb, 16);
+
+ MULTI_update_va_mapping_otherdomain(
+ mcl, MMAP_VADDR(pending_idx),
+ pfn_pte_ma(txreq.addr >> PAGE_SHIFT, PAGE_KERNEL),
+ 0, netif->domid);
+ mcl++;
+
+ memcpy(&pending_tx_info[pending_idx].req, &txreq, sizeof(txreq));
+ pending_tx_info[pending_idx].netif = netif;
+ *((u16 *)skb->data) = pending_idx;
+
+ __skb_queue_tail(&tx_queue, skb);
+
+ pending_cons++;
+
+ /* Filled the batch queue? */
+ if ( (mcl - tx_mcl) == ARRAY_SIZE(tx_mcl) )
+ break;
+ }
+
+ if ( mcl == tx_mcl )
+ return;
+
+ if ( unlikely(HYPERVISOR_multicall(tx_mcl, mcl - tx_mcl) != 0) )
+ BUG();
+
+ mcl = tx_mcl;
+ while ( (skb = __skb_dequeue(&tx_queue)) != NULL )
+ {
+ pending_idx = *((u16 *)skb->data);
+ netif = pending_tx_info[pending_idx].netif;
+ memcpy(&txreq, &pending_tx_info[pending_idx].req, sizeof(txreq));
+
+ /* Check the remap error code. */
+ if ( unlikely(mcl[0].result != 0) )
+ {
+ DPRINTK("Bad page frame\n");
+ make_tx_response(netif, txreq.id, NETIF_RSP_ERROR);
+ netif_put(netif);
+ kfree_skb(skb);
+ mcl++;
+ pending_ring[MASK_PEND_IDX(pending_prod++)] = pending_idx;
+ continue;
+ }
+
+ phys_to_machine_mapping[__pa(MMAP_VADDR(pending_idx)) >> PAGE_SHIFT] =
+ FOREIGN_FRAME(txreq.addr >> PAGE_SHIFT);
+
+ data_len = (txreq.size > PKT_PROT_LEN) ? PKT_PROT_LEN : txreq.size;
+
+ __skb_put(skb, data_len);
+ memcpy(skb->data,
+ (void *)(MMAP_VADDR(pending_idx)|(txreq.addr&~PAGE_MASK)),
+ data_len);
+
+ if ( data_len < txreq.size )
+ {
+ /* Append the packet payload as a fragment. */
+ skb_shinfo(skb)->frags[0].page =
+ virt_to_page(MMAP_VADDR(pending_idx));
+ skb_shinfo(skb)->frags[0].size = txreq.size - data_len;
+ skb_shinfo(skb)->frags[0].page_offset =
+ (txreq.addr + data_len) & ~PAGE_MASK;
+ skb_shinfo(skb)->nr_frags = 1;
+ }
+ else
+ {
+ /* Schedule a response immediately. */
+ netif_idx_release(pending_idx);
+ }
+
+ skb->data_len = txreq.size - data_len;
+ skb->len += skb->data_len;
+
+ skb->dev = netif->dev;
+ skb->protocol = eth_type_trans(skb, skb->dev);
+
+ /* No checking needed on localhost, but remember the field is blank. */
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ skb->proto_csum_valid = 1;
+ skb->proto_csum_blank = txreq.csum_blank;
+
+ netif->stats.rx_bytes += txreq.size;
+ netif->stats.rx_packets++;
+
+ netif_rx(skb);
+ netif->dev->last_rx = jiffies;
+
+ mcl++;
+ }
+}
+
+static void netif_idx_release(u16 pending_idx)
+{
+ static spinlock_t _lock = SPIN_LOCK_UNLOCKED;
+ unsigned long flags;
+
+ spin_lock_irqsave(&_lock, flags);
+ dealloc_ring[MASK_PEND_IDX(dealloc_prod++)] = pending_idx;
+ spin_unlock_irqrestore(&_lock, flags);
+
+ tasklet_schedule(&net_tx_tasklet);
+}
+
+static void netif_page_release(struct page *page)
+{
+ u16 pending_idx = page - virt_to_page(mmap_vstart);
+
+ /* Ready for next use. */
+ set_page_count(page, 1);
+
+ netif_idx_release(pending_idx);
+}
+
+irqreturn_t netif_be_int(int irq, void *dev_id, struct pt_regs *regs)
+{
+ netif_t *netif = dev_id;
+ if ( tx_work_exists(netif) )
+ {
+ add_to_net_schedule_list_tail(netif);
+ maybe_schedule_tx_action();
+ }
+ return IRQ_HANDLED;
+}
+
+static void make_tx_response(netif_t *netif,
+ u16 id,
+ s8 st)
+{
+ NETIF_RING_IDX i = netif->tx_resp_prod;
+ netif_tx_response_t *resp;
+
+ resp = &netif->tx->ring[MASK_NETIF_TX_IDX(i)].resp;
+ resp->id = id;
+ resp->status = st;
+ wmb();
+ netif->tx->resp_prod = netif->tx_resp_prod = ++i;
+
+ mb(); /* Update producer before checking event threshold. */
+ if ( i == netif->tx->event )
+ notify_via_evtchn(netif->evtchn);
+}
+
+static int make_rx_response(netif_t *netif,
+ u16 id,
+ s8 st,
+ memory_t addr,
+ u16 size,
+ u16 csum_valid)
+{
+ NETIF_RING_IDX i = netif->rx_resp_prod;
+ netif_rx_response_t *resp;
+
+ resp = &netif->rx->ring[MASK_NETIF_RX_IDX(i)].resp;
+ resp->addr = addr;
+ resp->csum_valid = csum_valid;
+ resp->id = id;
+ resp->status = (s16)size;
+ if ( st < 0 )
+ resp->status = (s16)st;
+ wmb();
+ netif->rx->resp_prod = netif->rx_resp_prod = ++i;
+
+ mb(); /* Update producer before checking event threshold. */
+ return (i == netif->rx->event);
+}
+
+static irqreturn_t netif_be_dbg(int irq, void *dev_id, struct pt_regs *regs)
+{
+ struct list_head *ent;
+ netif_t *netif;
+ int i = 0;
+
+ printk(KERN_ALERT "netif_schedule_list:\n");
+ spin_lock_irq(&net_schedule_list_lock);
+
+ list_for_each ( ent, &net_schedule_list )
+ {
+ netif = list_entry(ent, netif_t, list);
+ printk(KERN_ALERT " %d: private(rx_req_cons=%08x rx_resp_prod=%08x\n",
+ i, netif->rx_req_cons, netif->rx_resp_prod);
+ printk(KERN_ALERT " tx_req_cons=%08x tx_resp_prod=%08x)\n",
+ netif->tx_req_cons, netif->tx_resp_prod);
+ printk(KERN_ALERT " shared(rx_req_prod=%08x rx_resp_prod=%08x\n",
+ netif->rx->req_prod, netif->rx->resp_prod);
+ printk(KERN_ALERT " rx_event=%08x tx_req_prod=%08x\n",
+ netif->rx->event, netif->tx->req_prod);
+ printk(KERN_ALERT " tx_resp_prod=%08x, tx_event=%08x)\n",
+ netif->tx->resp_prod, netif->tx->event);
+ i++;
+ }
+
+ spin_unlock_irq(&net_schedule_list_lock);
+ printk(KERN_ALERT " ** End of netif_schedule_list **\n");
+
+ return IRQ_HANDLED;
+}
+
+static int __init netback_init(void)
+{
+ int i;
+ struct page *page;
+
+ if ( !(xen_start_info.flags & SIF_NET_BE_DOMAIN) &&
+ !(xen_start_info.flags & SIF_INITDOMAIN) )
+ return 0;
+
+ printk("Initialising Xen netif backend\n");
+
+ /* We can increase reservation by this much in net_rx_action(). */
+ balloon_update_driver_allowance(NETIF_RX_RING_SIZE);
+
+ skb_queue_head_init(&rx_queue);
+ skb_queue_head_init(&tx_queue);
+
+ init_timer(&net_timer);
+ net_timer.data = 0;
+ net_timer.function = net_alarm;
+
+ netif_interface_init();
+
+ mmap_vstart = allocate_empty_lowmem_region(MAX_PENDING_REQS);
+ BUG_ON(mmap_vstart == 0);
+
+ for ( i = 0; i < MAX_PENDING_REQS; i++ )
+ {
+ page = virt_to_page(MMAP_VADDR(i));
+ set_page_count(page, 1);
+ SetPageForeign(page, netif_page_release);
+ }
+
+ pending_cons = 0;
+ pending_prod = MAX_PENDING_REQS;
+ for ( i = 0; i < MAX_PENDING_REQS; i++ )
+ pending_ring[i] = i;
+
+ spin_lock_init(&net_schedule_list_lock);
+ INIT_LIST_HEAD(&net_schedule_list);
+
+ netif_ctrlif_init();
+
+ (void)request_irq(bind_virq_to_irq(VIRQ_DEBUG),
+ netif_be_dbg, SA_SHIRQ,
+ "net-be-dbg", &netif_be_dbg);
+
+ return 0;
+}
+
+static void netback_cleanup(void)
+{
+ BUG();
+}
+
+module_init(netback_init);
+module_exit(netback_cleanup);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/hypercall.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/hypercall.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,505 @@
+/******************************************************************************
+ * hypercall.h
+ *
+ * Linux-specific hypervisor handling.
+ *
+ * Copyright (c) 2002-2004, K A Fraser
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+/*
+ * Benjamin Liu <benjamin.liu@xxxxxxxxx>
+ * Jun Nakajima <jun.nakajima@xxxxxxxxx>
+ * Ported to x86-64.
+ *
+ */
+
+#ifndef __HYPERCALL_H__
+#define __HYPERCALL_H__
+#include <asm-xen/xen-public/xen.h>
+
+#define __syscall_clobber "r11","rcx","memory"
+
+/*
+ * Assembler stubs for hyper-calls.
+ */
+static inline int
+HYPERVISOR_set_trap_table(
+ trap_info_t *table)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_set_trap_table), "D" (table)
+ : __syscall_clobber );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_mmu_update(
+ mmu_update_t *req, int count, int *success_count, domid_t domid)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ "movq %5, %%r10;" TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_mmu_update), "D" (req), "S"
((long)count),
+ "d" (success_count), "g" ((unsigned long)domid)
+ : __syscall_clobber, "r10" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_mmuext_op(
+ struct mmuext_op *op, int count, int *success_count, domid_t domid)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ "movq %5, %%r10;" TRAP_INSTR
+ : "=a" (ret)
+ : "0" (__HYPERVISOR_mmuext_op), "D" (op), "S" ((long)count),
+ "d" (success_count), "g" ((unsigned long)domid)
+ : __syscall_clobber, "r10" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_set_gdt(
+ unsigned long *frame_list, int entries)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_set_gdt), "D" (frame_list), "S"
((long)entries)
+ : __syscall_clobber );
+
+
+ return ret;
+}
+static inline int
+HYPERVISOR_stack_switch(
+ unsigned long ss, unsigned long esp)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_stack_switch), "D" (ss), "S" (esp)
+ : __syscall_clobber );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_set_callbacks(
+ unsigned long event_address, unsigned long failsafe_address,
+ unsigned long syscall_address)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_set_callbacks), "D" (event_address),
+ "S" (failsafe_address), "d" (syscall_address)
+ : __syscall_clobber );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_fpu_taskswitch(
+ int set)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" ((unsigned long)__HYPERVISOR_fpu_taskswitch),
+ "D" ((unsigned long) set) : __syscall_clobber );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_yield(
+ void)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_sched_op), "D" ((unsigned
long)SCHEDOP_yield)
+ : __syscall_clobber );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_block(
+ void)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_sched_op), "D" ((unsigned
long)SCHEDOP_block)
+ : __syscall_clobber );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_shutdown(
+ void)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_sched_op),
+ "D" ((unsigned long)(SCHEDOP_shutdown | (SHUTDOWN_poweroff <<
SCHEDOP_reasonshift)))
+ : __syscall_clobber );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_reboot(
+ void)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_sched_op),
+ "D" ((unsigned long)(SCHEDOP_shutdown | (SHUTDOWN_reboot <<
SCHEDOP_reasonshift)))
+ : __syscall_clobber );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_suspend(
+ unsigned long srec)
+{
+ int ret;
+
+ /* NB. On suspend, control software expects a suspend record in %esi. */
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_sched_op),
+ "D" ((unsigned long)(SCHEDOP_shutdown | (SHUTDOWN_suspend <<
SCHEDOP_reasonshift))),
+ "S" (srec)
+ : __syscall_clobber );
+
+ return ret;
+}
+
+/*
+ * We can have the timeout value in a single argument for the hypercall, but
+ * that will break the common code.
+ */
+static inline long
+HYPERVISOR_set_timer_op(
+ u64 timeout)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_set_timer_op),
+ "D" (timeout)
+ : __syscall_clobber );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_dom0_op(
+ dom0_op_t *dom0_op)
+{
+ int ret;
+
+ dom0_op->interface_version = DOM0_INTERFACE_VERSION;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_dom0_op), "D" (dom0_op)
+ : __syscall_clobber );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_set_debugreg(
+ int reg, unsigned long value)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_set_debugreg), "D" ((unsigned
long)reg), "S" (value)
+ : __syscall_clobber );
+
+ return ret;
+}
+
+static inline unsigned long
+HYPERVISOR_get_debugreg(
+ int reg)
+{
+ unsigned long ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_get_debugreg), "D" ((unsigned
long)reg)
+ : __syscall_clobber );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_update_descriptor(
+ unsigned long ma, unsigned long word)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_update_descriptor), "D" (ma),
+ "S" (word)
+ : __syscall_clobber );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_dom_mem_op(
+ unsigned int op, unsigned long *extent_list,
+ unsigned long nr_extents, unsigned int extent_order)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ "movq %5,%%r10; movq %6,%%r8;" TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_dom_mem_op), "D" ((unsigned
long)op), "S" (extent_list),
+ "d" (nr_extents), "g" ((unsigned long) extent_order), "g" ((unsigned
long) DOMID_SELF)
+ : __syscall_clobber,"r8","r10");
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_multicall(
+ void *call_list, int nr_calls)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_multicall), "D" (call_list), "S"
((unsigned long)nr_calls)
+ : __syscall_clobber);
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_update_va_mapping(
+ unsigned long page_nr, pte_t new_val, unsigned long flags)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_update_va_mapping),
+ "D" (page_nr), "S" (new_val.pte), "d" (flags)
+ : __syscall_clobber);
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_event_channel_op(
+ void *op)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_event_channel_op), "D" (op)
+ : __syscall_clobber);
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_xen_version(
+ int cmd)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_xen_version), "D" ((unsigned
long)cmd)
+ : __syscall_clobber);
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_console_io(
+ int cmd, int count, char *str)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_console_io), "D" ((unsigned
long)cmd), "S" ((unsigned long)count), "d" (str)
+ : __syscall_clobber);
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_physdev_op(
+ void *physdev_op)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_physdev_op), "D" (physdev_op)
+ : __syscall_clobber);
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_grant_table_op(
+ unsigned int cmd, void *uop, unsigned int count)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_grant_table_op), "D" ((unsigned
long)cmd), "S" ((unsigned long)uop), "d" (count)
+ : __syscall_clobber);
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_update_va_mapping_otherdomain(
+ unsigned long page_nr, pte_t new_val, unsigned long flags, domid_t domid)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ "movq %5, %%r10;" TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_update_va_mapping_otherdomain),
+ "D" (page_nr), "S" (new_val.pte), "d" (flags), "g" ((unsigned
long)domid)
+ : __syscall_clobber,"r10");
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_vm_assist(
+ unsigned int cmd, unsigned int type)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_vm_assist), "D" ((unsigned
long)cmd), "S" ((unsigned long)type)
+ : __syscall_clobber);
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_switch_to_user(void)
+{
+ int ret;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret) : "0" ((unsigned long)__HYPERVISOR_switch_to_user) :
__syscall_clobber );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_boot_vcpu(
+ unsigned long vcpu, vcpu_guest_context_t *ctxt)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" (__HYPERVISOR_boot_vcpu), "D" (vcpu), "S" (ctxt)
+ : __syscall_clobber);
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_set_segment_base(
+ int reg, unsigned long value)
+{
+ int ret;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret)
+ : "0" ((unsigned long)__HYPERVISOR_set_segment_base), "D" ((unsigned
long)reg), "S" (value)
+ : __syscall_clobber );
+
+ return ret;
+}
+
+#endif /* __HYPERCALL_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/pci/irq.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/pci/irq.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,1125 @@
+/*
+ * Low-Level PCI Support for PC -- Routing of Interrupts
+ *
+ * (c) 1999--2000 Martin Mares <mj@xxxxxx>
+ */
+
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/dmi.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/io_apic.h>
+#include <asm/hw_irq.h>
+#include <linux/acpi.h>
+
+#include "pci.h"
+
+#define DBG printk
+
+#define PIRQ_SIGNATURE (('$' << 0) + ('P' << 8) + ('I' << 16) + ('R' << 24))
+#define PIRQ_VERSION 0x0100
+
+static int broken_hp_bios_irq9;
+static int acer_tm360_irqrouting;
+
+static struct irq_routing_table *pirq_table;
+
+static int pirq_enable_irq(struct pci_dev *dev);
+
+/*
+ * Never use: 0, 1, 2 (timer, keyboard, and cascade)
+ * Avoid using: 13, 14 and 15 (FP error and IDE).
+ * Penalize: 3, 4, 6, 7, 12 (known ISA uses: serial, floppy, parallel and
mouse)
+ */
+unsigned int pcibios_irq_mask = 0xfff8;
+
+static int pirq_penalty[16] = {
+ 1000000, 1000000, 1000000, 1000, 1000, 0, 1000, 1000,
+ 0, 0, 0, 0, 1000, 100000, 100000, 100000
+};
+
+struct irq_router {
+ char *name;
+ u16 vendor, device;
+ int (*get)(struct pci_dev *router, struct pci_dev *dev, int pirq);
+ int (*set)(struct pci_dev *router, struct pci_dev *dev, int pirq, int
new);
+};
+
+struct irq_router_handler {
+ u16 vendor;
+ int (*probe)(struct irq_router *r, struct pci_dev *router, u16 device);
+};
+
+int (*pcibios_enable_irq)(struct pci_dev *dev) = NULL;
+
+/*
+ * Search 0xf0000 -- 0xfffff for the PCI IRQ Routing Table.
+ */
+
+static struct irq_routing_table * __init pirq_find_routing_table(void)
+{
+ u8 *addr;
+ struct irq_routing_table *rt;
+ int i;
+ u8 sum;
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ for(addr = (u8 *) isa_bus_to_virt(0xf0000); addr < (u8 *)
isa_bus_to_virt(0x100000); addr += 16) {
+ rt = (struct irq_routing_table *) addr;
+ if (rt->signature != PIRQ_SIGNATURE ||
+ rt->version != PIRQ_VERSION ||
+ rt->size % 16 ||
+ rt->size < sizeof(struct irq_routing_table))
+ continue;
+ sum = 0;
+ for(i=0; i<rt->size; i++)
+ sum += addr[i];
+ if (!sum) {
+ DBG("PCI: Interrupt Routing Table found at 0x%p\n", rt);
+ return rt;
+ }
+ }
+#endif
+
+ return NULL;
+}
+
+/*
+ * If we have a IRQ routing table, use it to search for peer host
+ * bridges. It's a gross hack, but since there are no other known
+ * ways how to get a list of buses, we have to go this way.
+ */
+
+static void __init pirq_peer_trick(void)
+{
+ struct irq_routing_table *rt = pirq_table;
+ u8 busmap[256];
+ int i;
+ struct irq_info *e;
+
+ memset(busmap, 0, sizeof(busmap));
+ for(i=0; i < (rt->size - sizeof(struct irq_routing_table)) /
sizeof(struct irq_info); i++) {
+ e = &rt->slots[i];
+#ifdef DEBUG
+ {
+ int j;
+ DBG("%02x:%02x slot=%02x", e->bus, e->devfn/8, e->slot);
+ for(j=0; j<4; j++)
+ DBG(" %d:%02x/%04x", j, e->irq[j].link,
e->irq[j].bitmap);
+ DBG("\n");
+ }
+#endif
+ busmap[e->bus] = 1;
+ }
+ for(i = 1; i < 256; i++) {
+ if (!busmap[i] || pci_find_bus(0, i))
+ continue;
+ if (pci_scan_bus(i, &pci_root_ops, NULL))
+ printk(KERN_INFO "PCI: Discovered primary peer bus %02x
[IRQ]\n", i);
+ }
+ pcibios_last_bus = -1;
+}
+
+/*
+ * Code for querying and setting of IRQ routes on various interrupt routers.
+ */
+
+void eisa_set_level_irq(unsigned int irq)
+{
+ unsigned char mask = 1 << (irq & 7);
+ unsigned int port = 0x4d0 + (irq >> 3);
+ unsigned char val;
+ static u16 eisa_irq_mask;
+
+ if (irq >= 16 || (1 << irq) & eisa_irq_mask)
+ return;
+
+ eisa_irq_mask |= (1 << irq);
+ printk("PCI: setting IRQ %u as level-triggered\n", irq);
+ val = inb(port);
+ if (!(val & mask)) {
+ DBG(" -> edge");
+ outb(val | mask, port);
+ }
+}
+
+/*
+ * Common IRQ routing practice: nybbles in config space,
+ * offset by some magic constant.
+ */
+static unsigned int read_config_nybble(struct pci_dev *router, unsigned
offset, unsigned nr)
+{
+ u8 x;
+ unsigned reg = offset + (nr >> 1);
+
+ pci_read_config_byte(router, reg, &x);
+ return (nr & 1) ? (x >> 4) : (x & 0xf);
+}
+
+static void write_config_nybble(struct pci_dev *router, unsigned offset,
unsigned nr, unsigned int val)
+{
+ u8 x;
+ unsigned reg = offset + (nr >> 1);
+
+ pci_read_config_byte(router, reg, &x);
+ x = (nr & 1) ? ((x & 0x0f) | (val << 4)) : ((x & 0xf0) | val);
+ pci_write_config_byte(router, reg, x);
+}
+
+/*
+ * ALI pirq entries are damn ugly, and completely undocumented.
+ * This has been figured out from pirq tables, and it's not a pretty
+ * picture.
+ */
+static int pirq_ali_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ static unsigned char irqmap[16] = { 0, 9, 3, 10, 4, 5, 7, 6, 1, 11, 0,
12, 0, 14, 0, 15 };
+
+ return irqmap[read_config_nybble(router, 0x48, pirq-1)];
+}
+
+static int pirq_ali_set(struct pci_dev *router, struct pci_dev *dev, int pirq,
int irq)
+{
+ static unsigned char irqmap[16] = { 0, 8, 0, 2, 4, 5, 7, 6, 0, 1, 3, 9,
11, 0, 13, 15 };
+ unsigned int val = irqmap[irq];
+
+ if (val) {
+ write_config_nybble(router, 0x48, pirq-1, val);
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * The Intel PIIX4 pirq rules are fairly simple: "pirq" is
+ * just a pointer to the config space.
+ */
+static int pirq_piix_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ u8 x;
+
+ pci_read_config_byte(router, pirq, &x);
+ return (x < 16) ? x : 0;
+}
+
+static int pirq_piix_set(struct pci_dev *router, struct pci_dev *dev, int
pirq, int irq)
+{
+ pci_write_config_byte(router, pirq, irq);
+ return 1;
+}
+
+/*
+ * The VIA pirq rules are nibble-based, like ALI,
+ * but without the ugly irq number munging.
+ * However, PIRQD is in the upper instead of lower 4 bits.
+ */
+static int pirq_via_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ return read_config_nybble(router, 0x55, pirq == 4 ? 5 : pirq);
+}
+
+static int pirq_via_set(struct pci_dev *router, struct pci_dev *dev, int pirq,
int irq)
+{
+ write_config_nybble(router, 0x55, pirq == 4 ? 5 : pirq, irq);
+ return 1;
+}
+
+/*
+ * ITE 8330G pirq rules are nibble-based
+ * FIXME: pirqmap may be { 1, 0, 3, 2 },
+ * 2+3 are both mapped to irq 9 on my system
+ */
+static int pirq_ite_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ static unsigned char pirqmap[4] = { 1, 0, 2, 3 };
+ return read_config_nybble(router,0x43, pirqmap[pirq-1]);
+}
+
+static int pirq_ite_set(struct pci_dev *router, struct pci_dev *dev, int pirq,
int irq)
+{
+ static unsigned char pirqmap[4] = { 1, 0, 2, 3 };
+ write_config_nybble(router, 0x43, pirqmap[pirq-1], irq);
+ return 1;
+}
+
+/*
+ * OPTI: high four bits are nibble pointer..
+ * I wonder what the low bits do?
+ */
+static int pirq_opti_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ return read_config_nybble(router, 0xb8, pirq >> 4);
+}
+
+static int pirq_opti_set(struct pci_dev *router, struct pci_dev *dev, int
pirq, int irq)
+{
+ write_config_nybble(router, 0xb8, pirq >> 4, irq);
+ return 1;
+}
+
+/*
+ * Cyrix: nibble offset 0x5C
+ * 0x5C bits 7:4 is INTB bits 3:0 is INTA
+ * 0x5D bits 7:4 is INTD bits 3:0 is INTC
+ */
+static int pirq_cyrix_get(struct pci_dev *router, struct pci_dev *dev, int
pirq)
+{
+ return read_config_nybble(router, 0x5C, (pirq-1)^1);
+}
+
+static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int
pirq, int irq)
+{
+ write_config_nybble(router, 0x5C, (pirq-1)^1, irq);
+ return 1;
+}
+
+/*
+ * PIRQ routing for SiS 85C503 router used in several SiS chipsets.
+ * We have to deal with the following issues here:
+ * - vendors have different ideas about the meaning of link values
+ * - some onboard devices (integrated in the chipset) have special
+ * links and are thus routed differently (i.e. not via PCI INTA-INTD)
+ * - different revision of the router have a different layout for
+ * the routing registers, particularly for the onchip devices
+ *
+ * For all routing registers the common thing is we have one byte
+ * per routeable link which is defined as:
+ * bit 7 IRQ mapping enabled (0) or disabled (1)
+ * bits [6:4] reserved (sometimes used for onchip devices)
+ * bits [3:0] IRQ to map to
+ * allowed: 3-7, 9-12, 14-15
+ * reserved: 0, 1, 2, 8, 13
+ *
+ * The config-space registers located at 0x41/0x42/0x43/0x44 are
+ * always used to route the normal PCI INT A/B/C/D respectively.
+ * Apparently there are systems implementing PCI routing table using
+ * link values 0x01-0x04 and others using 0x41-0x44 for PCI INTA..D.
+ * We try our best to handle both link mappings.
+ *
+ * Currently (2003-05-21) it appears most SiS chipsets follow the
+ * definition of routing registers from the SiS-5595 southbridge.
+ * According to the SiS 5595 datasheets the revision id's of the
+ * router (ISA-bridge) should be 0x01 or 0xb0.
+ *
+ * Furthermore we've also seen lspci dumps with revision 0x00 and 0xb1.
+ * Looks like these are used in a number of SiS 5xx/6xx/7xx chipsets.
+ * They seem to work with the current routing code. However there is
+ * some concern because of the two USB-OHCI HCs (original SiS 5595
+ * had only one). YMMV.
+ *
+ * Onchip routing for router rev-id 0x01/0xb0 and probably 0x00/0xb1:
+ *
+ * 0x61: IDEIRQ:
+ * bits [6:5] must be written 01
+ * bit 4 channel-select primary (0), secondary (1)
+ *
+ * 0x62: USBIRQ:
+ * bit 6 OHCI function disabled (0), enabled (1)
+ *
+ * 0x6a: ACPI/SCI IRQ: bits 4-6 reserved
+ *
+ * 0x7e: Data Acq. Module IRQ - bits 4-6 reserved
+ *
+ * We support USBIRQ (in addition to INTA-INTD) and keep the
+ * IDE, ACPI and DAQ routing untouched as set by the BIOS.
+ *
+ * Currently the only reported exception is the new SiS 65x chipset
+ * which includes the SiS 69x southbridge. Here we have the 85C503
+ * router revision 0x04 and there are changes in the register layout
+ * mostly related to the different USB HCs with USB 2.0 support.
+ *
+ * Onchip routing for router rev-id 0x04 (try-and-error observation)
+ *
+ * 0x60/0x61/0x62/0x63: 1xEHCI and 3xOHCI (companion) USB-HCs
+ * bit 6-4 are probably unused, not like 5595
+ */
+
+#define PIRQ_SIS_IRQ_MASK 0x0f
+#define PIRQ_SIS_IRQ_DISABLE 0x80
+#define PIRQ_SIS_USB_ENABLE 0x40
+
+static int pirq_sis_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ u8 x;
+ int reg;
+
+ reg = pirq;
+ if (reg >= 0x01 && reg <= 0x04)
+ reg += 0x40;
+ pci_read_config_byte(router, reg, &x);
+ return (x & PIRQ_SIS_IRQ_DISABLE) ? 0 : (x & PIRQ_SIS_IRQ_MASK);
+}
+
+static int pirq_sis_set(struct pci_dev *router, struct pci_dev *dev, int pirq,
int irq)
+{
+ u8 x;
+ int reg;
+
+ reg = pirq;
+ if (reg >= 0x01 && reg <= 0x04)
+ reg += 0x40;
+ pci_read_config_byte(router, reg, &x);
+ x &= ~(PIRQ_SIS_IRQ_MASK | PIRQ_SIS_IRQ_DISABLE);
+ x |= irq ? irq: PIRQ_SIS_IRQ_DISABLE;
+ pci_write_config_byte(router, reg, x);
+ return 1;
+}
+
+
+/*
+ * VLSI: nibble offset 0x74 - educated guess due to routing table and
+ * config space of VLSI 82C534 PCI-bridge/router (1004:0102)
+ * Tested on HP OmniBook 800 covering PIRQ 1, 2, 4, 8 for onboard
+ * devices, PIRQ 3 for non-pci(!) soundchip and (untested) PIRQ 6
+ * for the busbridge to the docking station.
+ */
+
+static int pirq_vlsi_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ if (pirq > 8) {
+ printk(KERN_INFO "VLSI router pirq escape (%d)\n", pirq);
+ return 0;
+ }
+ return read_config_nybble(router, 0x74, pirq-1);
+}
+
+static int pirq_vlsi_set(struct pci_dev *router, struct pci_dev *dev, int
pirq, int irq)
+{
+ if (pirq > 8) {
+ printk(KERN_INFO "VLSI router pirq escape (%d)\n", pirq);
+ return 0;
+ }
+ write_config_nybble(router, 0x74, pirq-1, irq);
+ return 1;
+}
+
+/*
+ * ServerWorks: PCI interrupts mapped to system IRQ lines through Index
+ * and Redirect I/O registers (0x0c00 and 0x0c01). The Index register
+ * format is (PCIIRQ## | 0x10), e.g.: PCIIRQ10=0x1a. The Redirect
+ * register is a straight binary coding of desired PIC IRQ (low nibble).
+ *
+ * The 'link' value in the PIRQ table is already in the correct format
+ * for the Index register. There are some special index values:
+ * 0x00 for ACPI (SCI), 0x01 for USB, 0x02 for IDE0, 0x04 for IDE1,
+ * and 0x03 for SMBus.
+ */
+static int pirq_serverworks_get(struct pci_dev *router, struct pci_dev *dev,
int pirq)
+{
+ outb_p(pirq, 0xc00);
+ return inb(0xc01) & 0xf;
+}
+
+static int pirq_serverworks_set(struct pci_dev *router, struct pci_dev *dev,
int pirq, int irq)
+{
+ outb_p(pirq, 0xc00);
+ outb_p(irq, 0xc01);
+ return 1;
+}
+
+/* Support for AMD756 PCI IRQ Routing
+ * Jhon H. Caicedo <jhcaiced@xxxxxxxxxxx>
+ * Jun/21/2001 0.2.0 Release, fixed to use "nybble" functions... (jhcaiced)
+ * Jun/19/2001 Alpha Release 0.1.0 (jhcaiced)
+ * The AMD756 pirq rules are nibble-based
+ * offset 0x56 0-3 PIRQA 4-7 PIRQB
+ * offset 0x57 0-3 PIRQC 4-7 PIRQD
+ */
+static int pirq_amd756_get(struct pci_dev *router, struct pci_dev *dev, int
pirq)
+{
+ u8 irq;
+ irq = 0;
+ if (pirq <= 4)
+ {
+ irq = read_config_nybble(router, 0x56, pirq - 1);
+ }
+ printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d get irq :
%2d\n",
+ dev->vendor, dev->device, pirq, irq);
+ return irq;
+}
+
+static int pirq_amd756_set(struct pci_dev *router, struct pci_dev *dev, int
pirq, int irq)
+{
+ printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d SET irq :
%2d\n",
+ dev->vendor, dev->device, pirq, irq);
+ if (pirq <= 4)
+ {
+ write_config_nybble(router, 0x56, pirq - 1, irq);
+ }
+ return 1;
+}
+
+#ifdef CONFIG_PCI_BIOS
+
+static int pirq_bios_set(struct pci_dev *router, struct pci_dev *dev, int
pirq, int irq)
+{
+ struct pci_dev *bridge;
+ int pin = pci_get_interrupt_pin(dev, &bridge);
+ return pcibios_set_irq_routing(bridge, pin, irq);
+}
+
+#endif
+
+static __init int intel_router_probe(struct irq_router *r, struct pci_dev
*router, u16 device)
+{
+ static struct pci_device_id pirq_440gx[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL,
PCI_DEVICE_ID_INTEL_82443GX_0) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL,
PCI_DEVICE_ID_INTEL_82443GX_2) },
+ { },
+ };
+
+ /* 440GX has a proprietary PIRQ router -- don't use it */
+ if (pci_dev_present(pirq_440gx))
+ return 0;
+
+ switch(device)
+ {
+ case PCI_DEVICE_ID_INTEL_82371FB_0:
+ case PCI_DEVICE_ID_INTEL_82371SB_0:
+ case PCI_DEVICE_ID_INTEL_82371AB_0:
+ case PCI_DEVICE_ID_INTEL_82371MX:
+ case PCI_DEVICE_ID_INTEL_82443MX_0:
+ case PCI_DEVICE_ID_INTEL_82801AA_0:
+ case PCI_DEVICE_ID_INTEL_82801AB_0:
+ case PCI_DEVICE_ID_INTEL_82801BA_0:
+ case PCI_DEVICE_ID_INTEL_82801BA_10:
+ case PCI_DEVICE_ID_INTEL_82801CA_0:
+ case PCI_DEVICE_ID_INTEL_82801CA_12:
+ case PCI_DEVICE_ID_INTEL_82801DB_0:
+ case PCI_DEVICE_ID_INTEL_82801E_0:
+ case PCI_DEVICE_ID_INTEL_82801EB_0:
+ case PCI_DEVICE_ID_INTEL_ESB_1:
+ case PCI_DEVICE_ID_INTEL_ICH6_0:
+ case PCI_DEVICE_ID_INTEL_ICH6_1:
+ case PCI_DEVICE_ID_INTEL_ICH7_0:
+ case PCI_DEVICE_ID_INTEL_ICH7_1:
+ r->name = "PIIX/ICH";
+ r->get = pirq_piix_get;
+ r->set = pirq_piix_set;
+ return 1;
+ }
+ return 0;
+}
+
+static __init int via_router_probe(struct irq_router *r, struct pci_dev
*router, u16 device)
+{
+ /* FIXME: We should move some of the quirk fixup stuff here */
+ switch(device)
+ {
+ case PCI_DEVICE_ID_VIA_82C586_0:
+ case PCI_DEVICE_ID_VIA_82C596:
+ case PCI_DEVICE_ID_VIA_82C686:
+ case PCI_DEVICE_ID_VIA_8231:
+ /* FIXME: add new ones for 8233/5 */
+ r->name = "VIA";
+ r->get = pirq_via_get;
+ r->set = pirq_via_set;
+ return 1;
+ }
+ return 0;
+}
+
+static __init int vlsi_router_probe(struct irq_router *r, struct pci_dev
*router, u16 device)
+{
+ switch(device)
+ {
+ case PCI_DEVICE_ID_VLSI_82C534:
+ r->name = "VLSI 82C534";
+ r->get = pirq_vlsi_get;
+ r->set = pirq_vlsi_set;
+ return 1;
+ }
+ return 0;
+}
+
+
+static __init int serverworks_router_probe(struct irq_router *r, struct
pci_dev *router, u16 device)
+{
+ switch(device)
+ {
+ case PCI_DEVICE_ID_SERVERWORKS_OSB4:
+ case PCI_DEVICE_ID_SERVERWORKS_CSB5:
+ r->name = "ServerWorks";
+ r->get = pirq_serverworks_get;
+ r->set = pirq_serverworks_set;
+ return 1;
+ }
+ return 0;
+}
+
+static __init int sis_router_probe(struct irq_router *r, struct pci_dev
*router, u16 device)
+{
+ if (device != PCI_DEVICE_ID_SI_503)
+ return 0;
+
+ r->name = "SIS";
+ r->get = pirq_sis_get;
+ r->set = pirq_sis_set;
+ return 1;
+}
+
+static __init int cyrix_router_probe(struct irq_router *r, struct pci_dev
*router, u16 device)
+{
+ switch(device)
+ {
+ case PCI_DEVICE_ID_CYRIX_5520:
+ r->name = "NatSemi";
+ r->get = pirq_cyrix_get;
+ r->set = pirq_cyrix_set;
+ return 1;
+ }
+ return 0;
+}
+
+static __init int opti_router_probe(struct irq_router *r, struct pci_dev
*router, u16 device)
+{
+ switch(device)
+ {
+ case PCI_DEVICE_ID_OPTI_82C700:
+ r->name = "OPTI";
+ r->get = pirq_opti_get;
+ r->set = pirq_opti_set;
+ return 1;
+ }
+ return 0;
+}
+
+static __init int ite_router_probe(struct irq_router *r, struct pci_dev
*router, u16 device)
+{
+ switch(device)
+ {
+ case PCI_DEVICE_ID_ITE_IT8330G_0:
+ r->name = "ITE";
+ r->get = pirq_ite_get;
+ r->set = pirq_ite_set;
+ return 1;
+ }
+ return 0;
+}
+
+static __init int ali_router_probe(struct irq_router *r, struct pci_dev
*router, u16 device)
+{
+ switch(device)
+ {
+ case PCI_DEVICE_ID_AL_M1533:
+ case PCI_DEVICE_ID_AL_M1563:
+ printk("PCI: Using ALI IRQ Router\n");
+ r->name = "ALI";
+ r->get = pirq_ali_get;
+ r->set = pirq_ali_set;
+ return 1;
+ }
+ return 0;
+}
+
+static __init int amd_router_probe(struct irq_router *r, struct pci_dev
*router, u16 device)
+{
+ switch(device)
+ {
+ case PCI_DEVICE_ID_AMD_VIPER_740B:
+ r->name = "AMD756";
+ break;
+ case PCI_DEVICE_ID_AMD_VIPER_7413:
+ r->name = "AMD766";
+ break;
+ case PCI_DEVICE_ID_AMD_VIPER_7443:
+ r->name = "AMD768";
+ break;
+ default:
+ return 0;
+ }
+ r->get = pirq_amd756_get;
+ r->set = pirq_amd756_set;
+ return 1;
+}
+
+static __initdata struct irq_router_handler pirq_routers[] = {
+ { PCI_VENDOR_ID_INTEL, intel_router_probe },
+ { PCI_VENDOR_ID_AL, ali_router_probe },
+ { PCI_VENDOR_ID_ITE, ite_router_probe },
+ { PCI_VENDOR_ID_VIA, via_router_probe },
+ { PCI_VENDOR_ID_OPTI, opti_router_probe },
+ { PCI_VENDOR_ID_SI, sis_router_probe },
+ { PCI_VENDOR_ID_CYRIX, cyrix_router_probe },
+ { PCI_VENDOR_ID_VLSI, vlsi_router_probe },
+ { PCI_VENDOR_ID_SERVERWORKS, serverworks_router_probe },
+ { PCI_VENDOR_ID_AMD, amd_router_probe },
+ /* Someone with docs needs to add the ATI Radeon IGP */
+ { 0, NULL }
+};
+static struct irq_router pirq_router;
+static struct pci_dev *pirq_router_dev;
+
+
+/*
+ * FIXME: should we have an option to say "generic for
+ * chipset" ?
+ */
+
+static void __init pirq_find_router(struct irq_router *r)
+{
+ struct irq_routing_table *rt = pirq_table;
+ struct irq_router_handler *h;
+
+#ifdef CONFIG_PCI_BIOS
+ if (!rt->signature) {
+ printk(KERN_INFO "PCI: Using BIOS for IRQ routing\n");
+ r->set = pirq_bios_set;
+ r->name = "BIOS";
+ return;
+ }
+#endif
+
+ /* Default unless a driver reloads it */
+ r->name = "default";
+ r->get = NULL;
+ r->set = NULL;
+
+ DBG("PCI: Attempting to find IRQ router for %04x:%04x\n",
+ rt->rtr_vendor, rt->rtr_device);
+
+ pirq_router_dev = pci_find_slot(rt->rtr_bus, rt->rtr_devfn);
+ if (!pirq_router_dev) {
+ DBG("PCI: Interrupt router not found at %02x:%02x\n",
rt->rtr_bus, rt->rtr_devfn);
+ return;
+ }
+
+ for( h = pirq_routers; h->vendor; h++) {
+ /* First look for a router match */
+ if (rt->rtr_vendor == h->vendor && h->probe(r, pirq_router_dev,
rt->rtr_device))
+ break;
+ /* Fall back to a device match */
+ if (pirq_router_dev->vendor == h->vendor && h->probe(r,
pirq_router_dev, pirq_router_dev->device))
+ break;
+ }
+ printk(KERN_INFO "PCI: Using IRQ router %s [%04x/%04x] at %s\n",
+ pirq_router.name,
+ pirq_router_dev->vendor,
+ pirq_router_dev->device,
+ pci_name(pirq_router_dev));
+}
+
+static struct irq_info *pirq_get_info(struct pci_dev *dev)
+{
+ struct irq_routing_table *rt = pirq_table;
+ int entries = (rt->size - sizeof(struct irq_routing_table)) /
sizeof(struct irq_info);
+ struct irq_info *info;
+
+ for (info = rt->slots; entries--; info++)
+ if (info->bus == dev->bus->number && PCI_SLOT(info->devfn) ==
PCI_SLOT(dev->devfn))
+ return info;
+ return NULL;
+}
+
+static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
+{
+ u8 pin;
+ struct irq_info *info;
+ int i, pirq, newirq;
+ int irq = 0;
+ u32 mask;
+ struct irq_router *r = &pirq_router;
+ struct pci_dev *dev2 = NULL;
+ char *msg = NULL;
+
+ /* Find IRQ pin */
+ pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+ if (!pin) {
+ DBG(" -> no interrupt pin\n");
+ return 0;
+ }
+ pin = pin - 1;
+
+ /* Find IRQ routing entry */
+
+ if (!pirq_table)
+ return 0;
+
+ DBG("IRQ for %s[%c]", pci_name(dev), 'A' + pin);
+ info = pirq_get_info(dev);
+ if (!info) {
+ DBG(" -> not found in routing table\n");
+ return 0;
+ }
+ pirq = info->irq[pin].link;
+ mask = info->irq[pin].bitmap;
+ if (!pirq) {
+ DBG(" -> not routed\n");
+ return 0;
+ }
+ DBG(" -> PIRQ %02x, mask %04x, excl %04x", pirq, mask,
pirq_table->exclusive_irqs);
+ mask &= pcibios_irq_mask;
+
+ /* Work around broken HP Pavilion Notebooks which assign USB to
+ IRQ 9 even though it is actually wired to IRQ 11 */
+
+ if (broken_hp_bios_irq9 && pirq == 0x59 && dev->irq == 9) {
+ dev->irq = 11;
+ pci_write_config_byte(dev, PCI_INTERRUPT_LINE, 11);
+ r->set(pirq_router_dev, dev, pirq, 11);
+ }
+
+ /* same for Acer Travelmate 360, but with CB and irq 11 -> 10 */
+ if (acer_tm360_irqrouting && dev->irq == 11 && dev->vendor ==
PCI_VENDOR_ID_O2) {
+ pirq = 0x68;
+ mask = 0x400;
+ dev->irq = r->get(pirq_router_dev, dev, pirq);
+ pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq);
+ }
+
+ /*
+ * Find the best IRQ to assign: use the one
+ * reported by the device if possible.
+ */
+ newirq = dev->irq;
+ if (!((1 << newirq) & mask)) {
+ if ( pci_probe & PCI_USE_PIRQ_MASK) newirq = 0;
+ else printk(KERN_WARNING "PCI: IRQ %i for device %s doesn't
match PIRQ mask - try pci=usepirqmask\n", newirq, pci_name(dev));
+ }
+ if (!newirq && assign) {
+ for (i = 0; i < 16; i++) {
+ if (!(mask & (1 << i)))
+ continue;
+ if (pirq_penalty[i] < pirq_penalty[newirq] &&
can_request_irq(i, SA_SHIRQ))
+ newirq = i;
+ }
+ }
+ DBG(" -> newirq=%d", newirq);
+
+ /* Check if it is hardcoded */
+ if ((pirq & 0xf0) == 0xf0) {
+ irq = pirq & 0xf;
+ DBG(" -> hardcoded IRQ %d\n", irq);
+ msg = "Hardcoded";
+ } else if ( r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \
+ ((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask)) ) {
+ DBG(" -> got IRQ %d\n", irq);
+ msg = "Found";
+ } else if (newirq && r->set && (dev->class >> 8) !=
PCI_CLASS_DISPLAY_VGA) {
+ DBG(" -> assigning IRQ %d", newirq);
+ if (r->set(pirq_router_dev, dev, pirq, newirq)) {
+ eisa_set_level_irq(newirq);
+ DBG(" ... OK\n");
+ msg = "Assigned";
+ irq = newirq;
+ }
+ }
+
+ if (!irq) {
+ DBG(" ... failed\n");
+ if (newirq && mask == (1 << newirq)) {
+ msg = "Guessed";
+ irq = newirq;
+ } else
+ return 0;
+ }
+ printk(KERN_INFO "PCI: %s IRQ %d for device %s\n", msg, irq,
pci_name(dev));
+
+ /* Update IRQ for all devices with the same pirq value */
+ while ((dev2 = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev2)) != NULL) {
+ pci_read_config_byte(dev2, PCI_INTERRUPT_PIN, &pin);
+ if (!pin)
+ continue;
+ pin--;
+ info = pirq_get_info(dev2);
+ if (!info)
+ continue;
+ if (info->irq[pin].link == pirq) {
+ /* We refuse to override the dev->irq information. Give
a warning! */
+ if ( dev2->irq && dev2->irq != irq && \
+ (!(pci_probe & PCI_USE_PIRQ_MASK) || \
+ ((1 << dev2->irq) & mask)) ) {
+#ifndef CONFIG_PCI_MSI
+ printk(KERN_INFO "IRQ routing conflict for %s,
have irq %d, want irq %d\n",
+ pci_name(dev2), dev2->irq, irq);
+#endif
+ continue;
+ }
+ dev2->irq = irq;
+ pirq_penalty[irq]++;
+ if (dev != dev2)
+ printk(KERN_INFO "PCI: Sharing IRQ %d with
%s\n", irq, pci_name(dev2));
+ }
+ }
+ return 1;
+}
+
+static void __init pcibios_fixup_irqs(void)
+{
+ struct pci_dev *dev = NULL;
+ u8 pin;
+
+ DBG("PCI: IRQ fixup\n");
+ while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+ /*
+ * If the BIOS has set an out of range IRQ number, just ignore
it.
+ * Also keep track of which IRQ's are already in use.
+ */
+ if (dev->irq >= 16) {
+ DBG("%s: ignoring bogus IRQ %d\n", pci_name(dev),
dev->irq);
+ dev->irq = 0;
+ }
+ /* If the IRQ is already assigned to a PCI device, ignore its
ISA use penalty */
+ if (pirq_penalty[dev->irq] >= 100 && pirq_penalty[dev->irq] <
100000)
+ pirq_penalty[dev->irq] = 0;
+ pirq_penalty[dev->irq]++;
+ }
+
+ dev = NULL;
+ while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+ pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+#ifdef CONFIG_X86_IO_APIC
+ /*
+ * Recalculate IRQ numbers if we use the I/O APIC.
+ */
+ if (io_apic_assign_pci_irqs)
+ {
+ int irq;
+
+ if (pin) {
+ pin--; /* interrupt pins are numbered
starting from 1 */
+ irq =
IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin);
+ /*
+ * Busses behind bridges are typically not listed in the MP-table.
+ * In this case we have to look up the IRQ based on the parent bus,
+ * parent slot, and pin number. The SMP code detects such bridged
+ * busses itself so we should get into this branch reliably.
+ */
+ if (irq < 0 && dev->bus->parent) { /* go back
to the bridge */
+ struct pci_dev * bridge =
dev->bus->self;
+
+ pin = (pin + PCI_SLOT(dev->devfn)) % 4;
+ irq =
IO_APIC_get_PCI_irq_vector(bridge->bus->number,
+
PCI_SLOT(bridge->devfn), pin);
+ if (irq >= 0)
+ printk(KERN_WARNING "PCI: using
PPB %s[%c] to get irq %d\n",
+ pci_name(bridge), 'A' +
pin, irq);
+ }
+ if (irq >= 0) {
+ if (use_pci_vector() &&
+ !platform_legacy_irq(irq))
+ irq = IO_APIC_VECTOR(irq);
+
+ printk(KERN_INFO "PCI->APIC IRQ
transform: %s[%c] -> IRQ %d\n",
+ pci_name(dev), 'A' + pin, irq);
+ dev->irq = irq;
+ }
+ }
+ }
+#endif
+ /*
+ * Still no IRQ? Try to lookup one...
+ */
+ if (pin && !dev->irq)
+ pcibios_lookup_irq(dev, 0);
+ }
+}
+
+/*
+ * Work around broken HP Pavilion Notebooks which assign USB to
+ * IRQ 9 even though it is actually wired to IRQ 11
+ */
+static int __init fix_broken_hp_bios_irq9(struct dmi_system_id *d)
+{
+ if (!broken_hp_bios_irq9) {
+ broken_hp_bios_irq9 = 1;
+ printk(KERN_INFO "%s detected - fixing broken IRQ routing\n",
d->ident);
+ }
+ return 0;
+}
+
+/*
+ * Work around broken Acer TravelMate 360 Notebooks which assign
+ * Cardbus to IRQ 11 even though it is actually wired to IRQ 10
+ */
+static int __init fix_acer_tm360_irqrouting(struct dmi_system_id *d)
+{
+ if (!acer_tm360_irqrouting) {
+ acer_tm360_irqrouting = 1;
+ printk(KERN_INFO "%s detected - fixing broken IRQ routing\n",
d->ident);
+ }
+ return 0;
+}
+
+static struct dmi_system_id __initdata pciirq_dmi_table[] = {
+ {
+ .callback = fix_broken_hp_bios_irq9,
+ .ident = "HP Pavilion N5400 Series Laptop",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_BIOS_VERSION, "GE.M1.03"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "HP Pavilion Notebook
Model GE"),
+ DMI_MATCH(DMI_BOARD_VERSION, "OmniBook N32N-736"),
+ },
+ },
+ {
+ .callback = fix_acer_tm360_irqrouting,
+ .ident = "Acer TravelMate 36x Laptop",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 360"),
+ },
+ },
+ { }
+};
+
+static int __init pcibios_irq_init(void)
+{
+ DBG("PCI: IRQ init\n");
+
+ if (pcibios_enable_irq || raw_pci_ops == NULL)
+ return 0;
+
+ dmi_check_system(pciirq_dmi_table);
+
+ pirq_table = pirq_find_routing_table();
+
+#ifdef CONFIG_PCI_BIOS
+ if (!pirq_table && (pci_probe & PCI_BIOS_IRQ_SCAN))
+ pirq_table = pcibios_get_irq_routing_table();
+#endif
+ if (pirq_table) {
+ pirq_peer_trick();
+ pirq_find_router(&pirq_router);
+ if (pirq_table->exclusive_irqs) {
+ int i;
+ for (i=0; i<16; i++)
+ if (!(pirq_table->exclusive_irqs & (1 << i)))
+ pirq_penalty[i] += 100;
+ }
+ /* If we're using the I/O APIC, avoid using the PCI IRQ routing
table */
+ if (io_apic_assign_pci_irqs)
+ pirq_table = NULL;
+ }
+
+ pcibios_enable_irq = pirq_enable_irq;
+
+ pcibios_fixup_irqs();
+ return 0;
+}
+
+subsys_initcall(pcibios_irq_init);
+
+
+static void pirq_penalize_isa_irq(int irq)
+{
+ /*
+ * If any ISAPnP device reports an IRQ in its list of possible
+ * IRQ's, we try to avoid assigning it to PCI devices.
+ */
+ if (irq < 16)
+ pirq_penalty[irq] += 100;
+}
+
+void pcibios_penalize_isa_irq(int irq)
+{
+#ifdef CONFIG_ACPI_PCI
+ if (!acpi_noirq)
+ acpi_penalize_isa_irq(irq);
+ else
+#endif
+ pirq_penalize_isa_irq(irq);
+}
+
+static int pirq_enable_irq(struct pci_dev *dev)
+{
+ u8 pin;
+ extern int via_interrupt_line_quirk;
+ struct pci_dev *temp_dev;
+
+ pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+ if (pin && !pcibios_lookup_irq(dev, 1) && !dev->irq) {
+ char *msg;
+ msg = "";
+ if (io_apic_assign_pci_irqs) {
+ int irq;
+
+ if (pin) {
+ pin--; /* interrupt pins are numbered
starting from 1 */
+ irq =
IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin);
+ /*
+ * Busses behind bridges are typically not
listed in the MP-table.
+ * In this case we have to look up the IRQ
based on the parent bus,
+ * parent slot, and pin number. The SMP code
detects such bridged
+ * busses itself so we should get into this
branch reliably.
+ */
+ temp_dev = dev;
+ while (irq < 0 && dev->bus->parent) { /* go
back to the bridge */
+ struct pci_dev * bridge =
dev->bus->self;
+
+ pin = (pin + PCI_SLOT(dev->devfn)) % 4;
+ irq =
IO_APIC_get_PCI_irq_vector(bridge->bus->number,
+
PCI_SLOT(bridge->devfn), pin);
+ if (irq >= 0)
+ printk(KERN_WARNING "PCI: using
PPB %s[%c] to get irq %d\n",
+ pci_name(bridge), 'A' +
pin, irq);
+ dev = bridge;
+ }
+ dev = temp_dev;
+ if (irq >= 0) {
+#ifdef CONFIG_PCI_MSI
+ if (!platform_legacy_irq(irq))
+ irq = IO_APIC_VECTOR(irq);
+#endif
+ printk(KERN_INFO "PCI->APIC IRQ
transform: %s[%c] -> IRQ %d\n",
+ pci_name(dev), 'A' + pin, irq);
+ dev->irq = irq;
+ return 0;
+ } else
+ msg = " Probably buggy MP table.";
+ }
+ } else if (pci_probe & PCI_BIOS_IRQ_SCAN)
+ msg = "";
+ else
+ msg = " Please try using pci=biosirq.";
+
+ /* With IDE legacy devices the IRQ lookup failure is not a
problem.. */
+ if (dev->class >> 8 == PCI_CLASS_STORAGE_IDE && !(dev->class &
0x5))
+ return 0;
+
+ printk(KERN_WARNING "PCI: No IRQ known for interrupt pin %c of
device %s.%s\n",
+ 'A' + pin - 1, pci_name(dev), msg);
+ }
+ /* VIA bridges use interrupt line for apic/pci steering across
+ the V-Link */
+ else if (via_interrupt_line_quirk)
+ pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq & 15);
+ return 0;
+}
+
+int pci_vector_resources(int last, int nr_released)
+{
+ int count = nr_released;
+
+ int next = last;
+ int offset = (last % 8);
+
+ while (next < FIRST_SYSTEM_VECTOR) {
+ next += 8;
+#ifdef CONFIG_X86_64
+ if (next == IA32_SYSCALL_VECTOR)
+ continue;
+#else
+ if (next == SYSCALL_VECTOR)
+ continue;
+#endif
+ count++;
+ if (next >= FIRST_SYSTEM_VECTOR) {
+ if (offset%8) {
+ next = FIRST_DEVICE_VECTOR + offset;
+ offset++;
+ continue;
+ }
+ count--;
+ }
+ }
+
+ return count;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/agp.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/agp.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,37 @@
+#ifndef AGP_H
+#define AGP_H 1
+
+#include <asm/pgtable.h>
+#include <asm/cacheflush.h>
+#include <asm/system.h>
+
+/*
+ * Functions to keep the agpgart mappings coherent with the MMU.
+ * The GART gives the CPU a physical alias of pages in memory. The alias
region is
+ * mapped uncacheable. Make sure there are no conflicting mappings
+ * with different cachability attributes for the same page. This avoids
+ * data corruption on some CPUs.
+ */
+
+int map_page_into_agp(struct page *page);
+int unmap_page_from_agp(struct page *page);
+#define flush_agp_mappings() global_flush_tlb()
+
+/* Could use CLFLUSH here if the cpu supports it. But then it would
+ need to be called for each cacheline of the whole page so it may not be
+ worth it. Would need a page for it. */
+#define flush_agp_cache() wbinvd()
+
+/* Convert a physical address to an address suitable for the GART. */
+#define phys_to_gart(x) phys_to_machine(x)
+#define gart_to_phys(x) machine_to_phys(x)
+
+/* GATT allocation. Returns/accepts GATT kernel virtual address. */
+#define alloc_gatt_pages(order) ({
\
+ char *_t; dma_addr_t _d; \
+ _t = dma_alloc_coherent(NULL,PAGE_SIZE<<(order),&_d,GFP_KERNEL); \
+ _t; })
+#define free_gatt_pages(table, order) \
+ dma_free_coherent(NULL,PAGE_SIZE<<(order),(table),virt_to_bus(table))
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/drivers/block/ll_rw_blk.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/drivers/block/ll_rw_blk.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,1663 @@
+/*
+ * linux/drivers/block/ll_rw_blk.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * Copyright (C) 1994, Karl Keyte: Added support for disk statistics
+ * Elevator latency, (C) 2000 Andrea Arcangeli <andrea@xxxxxxx> SuSE
+ * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@xxxxxxx>
+ * kernel-doc documentation started by NeilBrown <neilb@xxxxxxxxxxxxxxx> -
July2000
+ */
+
+/*
+ * This handles all read/write requests to block devices
+ */
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/config.h>
+#include <linux/locks.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/init.h>
+#include <linux/smp_lock.h>
+#include <linux/completion.h>
+#include <linux/bootmem.h>
+
+#include <asm/system.h>
+#include <asm/io.h>
+#include <linux/blk.h>
+#include <linux/highmem.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+
+/*
+ * MAC Floppy IWM hooks
+ */
+
+#ifdef CONFIG_MAC_FLOPPY_IWM
+extern int mac_floppy_init(void);
+#endif
+
+/*
+ * For the allocated request tables
+ */
+static kmem_cache_t *request_cachep;
+
+/*
+ * The "disk" task queue is used to start the actual requests
+ * after a plug
+ */
+DECLARE_TASK_QUEUE(tq_disk);
+
+/*
+ * Protect the request list against multiple users..
+ *
+ * With this spinlock the Linux block IO subsystem is 100% SMP threaded
+ * from the IRQ event side, and almost 100% SMP threaded from the syscall
+ * side (we still have protect against block device array operations, and
+ * the do_request() side is casually still unsafe. The kernel lock protects
+ * this part currently.).
+ *
+ * there is a fair chance that things will work just OK if these functions
+ * are called with no global kernel lock held ...
+ */
+spinlock_t io_request_lock = SPIN_LOCK_UNLOCKED;
+
+/* This specifies how many sectors to read ahead on the disk. */
+
+int read_ahead[MAX_BLKDEV];
+
+/* blk_dev_struct is:
+ * *request_fn
+ * *current_request
+ */
+struct blk_dev_struct blk_dev[MAX_BLKDEV]; /* initialized by blk_dev_init() */
+
+/*
+ * blk_size contains the size of all block-devices in units of 1024 byte
+ * sectors:
+ *
+ * blk_size[MAJOR][MINOR]
+ *
+ * if (!blk_size[MAJOR]) then no minor size checking is done.
+ */
+int * blk_size[MAX_BLKDEV];
+
+/*
+ * blksize_size contains the size of all block-devices:
+ *
+ * blksize_size[MAJOR][MINOR]
+ *
+ * if (!blksize_size[MAJOR]) then 1024 bytes is assumed.
+ */
+int * blksize_size[MAX_BLKDEV];
+
+/*
+ * hardsect_size contains the size of the hardware sector of a device.
+ *
+ * hardsect_size[MAJOR][MINOR]
+ *
+ * if (!hardsect_size[MAJOR])
+ * then 512 bytes is assumed.
+ * else
+ * sector_size is hardsect_size[MAJOR][MINOR]
+ * This is currently set by some scsi devices and read by the msdos fs driver.
+ * Other uses may appear later.
+ */
+int * hardsect_size[MAX_BLKDEV];
+
+/*
+ * The following tunes the read-ahead algorithm in mm/filemap.c
+ */
+int * max_readahead[MAX_BLKDEV];
+
+/*
+ * Max number of sectors per request
+ */
+int * max_sectors[MAX_BLKDEV];
+
+unsigned long blk_max_low_pfn, blk_max_pfn;
+int blk_nohighio = 0;
+
+int block_dump = 0;
+
+static struct timer_list writeback_timer;
+
+static inline int get_max_sectors(kdev_t dev)
+{
+ if (!max_sectors[MAJOR(dev)])
+ return MAX_SECTORS;
+ return max_sectors[MAJOR(dev)][MINOR(dev)];
+}
+
+static inline request_queue_t *__blk_get_queue(kdev_t dev)
+{
+ struct blk_dev_struct *bdev = blk_dev + MAJOR(dev);
+
+ if (bdev->queue)
+ return bdev->queue(dev);
+ else
+ return &blk_dev[MAJOR(dev)].request_queue;
+}
+
+request_queue_t *blk_get_queue(kdev_t dev)
+{
+ return __blk_get_queue(dev);
+}
+
+static int __blk_cleanup_queue(struct request_list *list)
+{
+ struct list_head *head = &list->free;
+ struct request *rq;
+ int i = 0;
+
+ while (!list_empty(head)) {
+ rq = list_entry(head->next, struct request, queue);
+ list_del(&rq->queue);
+ kmem_cache_free(request_cachep, rq);
+ i++;
+ };
+
+ if (i != list->count)
+ printk("request list leak!\n");
+
+ list->count = 0;
+ return i;
+}
+
+/**
+ * blk_cleanup_queue: - release a &request_queue_t when it is no longer needed
+ * @q: the request queue to be released
+ *
+ * Description:
+ * blk_cleanup_queue is the pair to blk_init_queue(). It should
+ * be called when a request queue is being released; typically
+ * when a block device is being de-registered. Currently, its
+ * primary task it to free all the &struct request structures that
+ * were allocated to the queue.
+ * Caveat:
+ * Hopefully the low level driver will have finished any
+ * outstanding requests first...
+ **/
+void blk_cleanup_queue(request_queue_t * q)
+{
+ int count = q->nr_requests;
+
+ count -= __blk_cleanup_queue(&q->rq);
+
+ if (count)
+ printk("blk_cleanup_queue: leaked requests (%d)\n", count);
+ if (atomic_read(&q->nr_sectors))
+ printk("blk_cleanup_queue: leaked sectors (%d)\n",
atomic_read(&q->nr_sectors));
+
+ memset(q, 0, sizeof(*q));
+}
+
+/**
+ * blk_queue_headactive - indicate whether head of request queue may be active
+ * @q: The queue which this applies to.
+ * @active: A flag indication where the head of the queue is active.
+ *
+ * Description:
+ * The driver for a block device may choose to leave the currently active
+ * request on the request queue, removing it only when it has completed.
+ * The queue handling routines assume this by default for safety reasons
+ * and will not involve the head of the request queue in any merging or
+ * reordering of requests when the queue is unplugged (and thus may be
+ * working on this particular request).
+ *
+ * If a driver removes requests from the queue before processing them, then
+ * it may indicate that it does so, there by allowing the head of the queue
+ * to be involved in merging and reordering. This is done be calling
+ * blk_queue_headactive() with an @active flag of %0.
+ *
+ * If a driver processes several requests at once, it must remove them (or
+ * at least all but one of them) from the request queue.
+ *
+ * When a queue is plugged the head will be assumed to be inactive.
+ **/
+
+void blk_queue_headactive(request_queue_t * q, int active)
+{
+ q->head_active = active;
+}
+
+/**
+ * blk_queue_throttle_sectors - indicates you will call sector throttling funcs
+ * @q: The queue which this applies to.
+ * @active: A flag indication if you want sector throttling on
+ *
+ * Description:
+ * The sector throttling code allows us to put a limit on the number of
+ * sectors pending io to the disk at a given time, sending @active nonzero
+ * indicates you will call blk_started_sectors and blk_finished_sectors in
+ * addition to calling blk_started_io and blk_finished_io in order to
+ * keep track of the number of sectors in flight.
+ **/
+
+void blk_queue_throttle_sectors(request_queue_t * q, int active)
+{
+ q->can_throttle = active;
+}
+
+/**
+ * blk_queue_make_request - define an alternate make_request function for a
device
+ * @q: the request queue for the device to be affected
+ * @mfn: the alternate make_request function
+ *
+ * Description:
+ * The normal way for &struct buffer_heads to be passed to a device
+ * driver is for them to be collected into requests on a request
+ * queue, and then to allow the device driver to select requests
+ * off that queue when it is ready. This works well for many block
+ * devices. However some block devices (typically virtual devices
+ * such as md or lvm) do not benefit from the processing on the
+ * request queue, and are served best by having the requests passed
+ * directly to them. This can be achieved by providing a function
+ * to blk_queue_make_request().
+ *
+ * Caveat:
+ * The driver that does this *must* be able to deal appropriately
+ * with buffers in "highmemory", either by calling bh_kmap() to get
+ * a kernel mapping, to by calling create_bounce() to create a
+ * buffer in normal memory.
+ **/
+
+void blk_queue_make_request(request_queue_t * q, make_request_fn * mfn)
+{
+ q->make_request_fn = mfn;
+}
+
+/**
+ * blk_queue_bounce_limit - set bounce buffer limit for queue
+ * @q: the request queue for the device
+ * @dma_addr: bus address limit
+ *
+ * Description:
+ * Different hardware can have different requirements as to what pages
+ * it can do I/O directly to. A low level driver can call
+ * blk_queue_bounce_limit to have lower memory pages allocated as bounce
+ * buffers for doing I/O to pages residing above @page. By default
+ * the block layer sets this to the highest numbered "low" memory page.
+ **/
+void blk_queue_bounce_limit(request_queue_t *q, u64 dma_addr)
+{
+ unsigned long bounce_pfn = dma_addr >> PAGE_SHIFT;
+ unsigned long mb = dma_addr >> 20;
+ static request_queue_t *old_q;
+
+ /*
+ * keep this for debugging for now...
+ */
+ if (dma_addr != BLK_BOUNCE_HIGH && q != old_q) {
+ old_q = q;
+ printk("blk: queue %p, ", q);
+ if (dma_addr == BLK_BOUNCE_ANY)
+ printk("no I/O memory limit\n");
+ else
+ printk("I/O limit %luMb (mask 0x%Lx)\n", mb,
+ (long long) dma_addr);
+ }
+
+ q->bounce_pfn = bounce_pfn;
+}
+
+
+/*
+ * can we merge the two segments, or do we need to start a new one?
+ */
+static inline int __blk_seg_merge_ok(struct buffer_head *bh, struct
buffer_head *nxt)
+{
+ /*
+ * if bh and nxt are contigous and don't cross a 4g boundary, it's ok
+ */
+ if (BH_CONTIG(bh, nxt) && BH_PHYS_4G(bh, nxt))
+ return 1;
+
+ return 0;
+}
+
+int blk_seg_merge_ok(struct buffer_head *bh, struct buffer_head *nxt)
+{
+ return __blk_seg_merge_ok(bh, nxt);
+}
+
+static inline int ll_new_segment(request_queue_t *q, struct request *req, int
max_segments)
+{
+ if (req->nr_segments < max_segments) {
+ req->nr_segments++;
+ return 1;
+ }
+ return 0;
+}
+
+static int ll_back_merge_fn(request_queue_t *q, struct request *req,
+ struct buffer_head *bh, int max_segments)
+{
+ if (__blk_seg_merge_ok(req->bhtail, bh))
+ return 1;
+
+ return ll_new_segment(q, req, max_segments);
+}
+
+static int ll_front_merge_fn(request_queue_t *q, struct request *req,
+ struct buffer_head *bh, int max_segments)
+{
+ if (__blk_seg_merge_ok(bh, req->bh))
+ return 1;
+
+ return ll_new_segment(q, req, max_segments);
+}
+
+static int ll_merge_requests_fn(request_queue_t *q, struct request *req,
+ struct request *next, int max_segments)
+{
+ int total_segments = req->nr_segments + next->nr_segments;
+
+ if (__blk_seg_merge_ok(req->bhtail, next->bh))
+ total_segments--;
+
+ if (total_segments > max_segments)
+ return 0;
+
+ req->nr_segments = total_segments;
+ return 1;
+}
+
+/*
+ * "plug" the device if there are no outstanding requests: this will
+ * force the transfer to start only after we have put all the requests
+ * on the list.
+ *
+ * This is called with interrupts off and no requests on the queue.
+ * (and with the request spinlock acquired)
+ */
+static void generic_plug_device(request_queue_t *q, kdev_t dev)
+{
+ /*
+ * no need to replug device
+ */
+ if (!list_empty(&q->queue_head) || q->plugged)
+ return;
+
+ q->plugged = 1;
+ queue_task(&q->plug_tq, &tq_disk);
+}
+
+/*
+ * remove the plug and let it rip..
+ */
+static inline void __generic_unplug_device(request_queue_t *q)
+{
+ if (q->plugged) {
+ q->plugged = 0;
+ if (!list_empty(&q->queue_head))
+ q->request_fn(q);
+ }
+}
+
+void generic_unplug_device(void *data)
+{
+ request_queue_t *q = (request_queue_t *) data;
+ unsigned long flags;
+
+ spin_lock_irqsave(&io_request_lock, flags);
+ __generic_unplug_device(q);
+ spin_unlock_irqrestore(&io_request_lock, flags);
+}
+
+/** blk_grow_request_list
+ * @q: The &request_queue_t
+ * @nr_requests: how many requests are desired
+ *
+ * More free requests are added to the queue's free lists, bringing
+ * the total number of requests to @nr_requests.
+ *
+ * The requests are added equally to the request queue's read
+ * and write freelists.
+ *
+ * This function can sleep.
+ *
+ * Returns the (new) number of requests which the queue has available.
+ */
+int blk_grow_request_list(request_queue_t *q, int nr_requests, int
max_queue_sectors)
+{
+ unsigned long flags;
+ /* Several broken drivers assume that this function doesn't sleep,
+ * this causes system hangs during boot.
+ * As a temporary fix, make the function non-blocking.
+ */
+ spin_lock_irqsave(&io_request_lock, flags);
+ while (q->nr_requests < nr_requests) {
+ struct request *rq;
+
+ rq = kmem_cache_alloc(request_cachep, SLAB_ATOMIC);
+ if (rq == NULL)
+ break;
+ memset(rq, 0, sizeof(*rq));
+ rq->rq_status = RQ_INACTIVE;
+ list_add(&rq->queue, &q->rq.free);
+ q->rq.count++;
+
+ q->nr_requests++;
+ }
+
+ /*
+ * Wakeup waiters after both one quarter of the
+ * max-in-fligh queue and one quarter of the requests
+ * are available again.
+ */
+
+ q->batch_requests = q->nr_requests / 4;
+ if (q->batch_requests > 32)
+ q->batch_requests = 32;
+ q->batch_sectors = max_queue_sectors / 4;
+
+ q->max_queue_sectors = max_queue_sectors;
+
+ BUG_ON(!q->batch_sectors);
+ atomic_set(&q->nr_sectors, 0);
+
+ spin_unlock_irqrestore(&io_request_lock, flags);
+ return q->nr_requests;
+}
+
+static void blk_init_free_list(request_queue_t *q)
+{
+ struct sysinfo si;
+ int megs; /* Total memory, in megabytes */
+ int nr_requests, max_queue_sectors = MAX_QUEUE_SECTORS;
+
+ INIT_LIST_HEAD(&q->rq.free);
+ q->rq.count = 0;
+ q->rq.pending[READ] = q->rq.pending[WRITE] = 0;
+ q->nr_requests = 0;
+
+ si_meminfo(&si);
+ megs = si.totalram >> (20 - PAGE_SHIFT);
+ nr_requests = MAX_NR_REQUESTS;
+ if (megs < 30) {
+ nr_requests /= 2;
+ max_queue_sectors /= 2;
+ }
+ /* notice early if anybody screwed the defaults */
+ BUG_ON(!nr_requests);
+ BUG_ON(!max_queue_sectors);
+
+ blk_grow_request_list(q, nr_requests, max_queue_sectors);
+
+ init_waitqueue_head(&q->wait_for_requests);
+
+ spin_lock_init(&q->queue_lock);
+}
+
+static int __make_request(request_queue_t * q, int rw, struct buffer_head *
bh);
+
+/**
+ * blk_init_queue - prepare a request queue for use with a block device
+ * @q: The &request_queue_t to be initialised
+ * @rfn: The function to be called to process requests that have been
+ * placed on the queue.
+ *
+ * Description:
+ * If a block device wishes to use the standard request handling procedures,
+ * which sorts requests and coalesces adjacent requests, then it must
+ * call blk_init_queue(). The function @rfn will be called when there
+ * are requests on the queue that need to be processed. If the device
+ * supports plugging, then @rfn may not be called immediately when requests
+ * are available on the queue, but may be called at some time later instead.
+ * Plugged queues are generally unplugged when a buffer belonging to one
+ * of the requests on the queue is needed, or due to memory pressure.
+ *
+ * @rfn is not required, or even expected, to remove all requests off the
+ * queue, but only as many as it can handle at a time. If it does leave
+ * requests on the queue, it is responsible for arranging that the requests
+ * get dealt with eventually.
+ *
+ * A global spin lock $io_request_lock must be held while manipulating the
+ * requests on the request queue.
+ *
+ * The request on the head of the queue is by default assumed to be
+ * potentially active, and it is not considered for re-ordering or merging
+ * whenever the given queue is unplugged. This behaviour can be changed with
+ * blk_queue_headactive().
+ *
+ * Note:
+ * blk_init_queue() must be paired with a blk_cleanup_queue() call
+ * when the block device is deactivated (such as at module unload).
+ **/
+void blk_init_queue(request_queue_t * q, request_fn_proc * rfn)
+{
+ INIT_LIST_HEAD(&q->queue_head);
+ elevator_init(&q->elevator, ELEVATOR_LINUS);
+ blk_init_free_list(q);
+ q->request_fn = rfn;
+ q->back_merge_fn = ll_back_merge_fn;
+ q->front_merge_fn = ll_front_merge_fn;
+ q->merge_requests_fn = ll_merge_requests_fn;
+ q->make_request_fn = __make_request;
+ q->plug_tq.sync = 0;
+ q->plug_tq.routine = &generic_unplug_device;
+ q->plug_tq.data = q;
+ q->plugged = 0;
+ q->can_throttle = 0;
+
+ /*
+ * These booleans describe the queue properties. We set the
+ * default (and most common) values here. Other drivers can
+ * use the appropriate functions to alter the queue properties.
+ * as appropriate.
+ */
+ q->plug_device_fn = generic_plug_device;
+ q->head_active = 1;
+
+ blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
+}
+
+#define blkdev_free_rq(list) list_entry((list)->next, struct request, queue);
+/*
+ * Get a free request. io_request_lock must be held and interrupts
+ * disabled on the way in. Returns NULL if there are no free requests.
+ */
+static struct request *get_request(request_queue_t *q, int rw)
+{
+ struct request *rq = NULL;
+ struct request_list *rl = &q->rq;
+
+ if (blk_oversized_queue(q)) {
+ int rlim = q->nr_requests >> 5;
+
+ if (rlim < 4)
+ rlim = 4;
+
+ /*
+ * if its a write, or we have more than a handful of reads
+ * pending, bail out
+ */
+ if ((rw == WRITE) || (rw == READ && rl->pending[READ] > rlim))
+ return NULL;
+ if (blk_oversized_queue_reads(q))
+ return NULL;
+ }
+
+ if (!list_empty(&rl->free)) {
+ rq = blkdev_free_rq(&rl->free);
+ list_del(&rq->queue);
+ rl->count--;
+ rl->pending[rw]++;
+ rq->rq_status = RQ_ACTIVE;
+ rq->cmd = rw;
+ rq->special = NULL;
+ rq->q = q;
+ }
+
+ return rq;
+}
+
+/*
+ * Here's the request allocation design, low latency version:
+ *
+ * 1: Blocking on request exhaustion is a key part of I/O throttling.
+ *
+ * 2: We want to be `fair' to all requesters. We must avoid starvation, and
+ * attempt to ensure that all requesters sleep for a similar duration.
Hence
+ * no stealing requests when there are other processes waiting.
+ *
+ * There used to be more here, attempting to allow a process to send in a
+ * number of requests once it has woken up. But, there's no way to
+ * tell if a process has just been woken up, or if it is a new process
+ * coming in to steal requests from the waiters. So, we give up and force
+ * everyone to wait fairly.
+ *
+ * So here's what we do:
+ *
+ * a) A READA requester fails if free_requests < batch_requests
+ *
+ * We don't want READA requests to prevent sleepers from ever
+ * waking. Note that READA is used extremely rarely - a few
+ * filesystems use it for directory readahead.
+ *
+ * When a process wants a new request:
+ *
+ * b) If free_requests == 0, the requester sleeps in FIFO manner, and
+ * the queue full condition is set. The full condition is not
+ * cleared until there are no longer any waiters. Once the full
+ * condition is set, all new io must wait, hopefully for a very
+ * short period of time.
+ *
+ * When a request is released:
+ *
+ * c) If free_requests < batch_requests, do nothing.
+ *
+ * d) If free_requests >= batch_requests, wake up a single waiter.
+ *
+ * As each waiter gets a request, he wakes another waiter. We do this
+ * to prevent a race where an unplug might get run before a request makes
+ * it's way onto the queue. The result is a cascade of wakeups, so delaying
+ * the initial wakeup until we've got batch_requests available helps avoid
+ * wakeups where there aren't any requests available yet.
+ */
+
+static struct request *__get_request_wait(request_queue_t *q, int rw)
+{
+ register struct request *rq;
+ DECLARE_WAITQUEUE(wait, current);
+
+ add_wait_queue_exclusive(&q->wait_for_requests, &wait);
+
+ do {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ spin_lock_irq(&io_request_lock);
+ if (blk_oversized_queue(q) || q->rq.count == 0) {
+ __generic_unplug_device(q);
+ spin_unlock_irq(&io_request_lock);
+ schedule();
+ spin_lock_irq(&io_request_lock);
+ }
+ rq = get_request(q, rw);
+ spin_unlock_irq(&io_request_lock);
+ } while (rq == NULL);
+ remove_wait_queue(&q->wait_for_requests, &wait);
+ current->state = TASK_RUNNING;
+
+ return rq;
+}
+
+static void get_request_wait_wakeup(request_queue_t *q, int rw)
+{
+ /*
+ * avoid losing an unplug if a second __get_request_wait did the
+ * generic_unplug_device while our __get_request_wait was running
+ * w/o the queue_lock held and w/ our request out of the queue.
+ */
+ if (waitqueue_active(&q->wait_for_requests))
+ wake_up(&q->wait_for_requests);
+}
+
+/* RO fail safe mechanism */
+
+static long ro_bits[MAX_BLKDEV][8];
+
+int is_read_only(kdev_t dev)
+{
+ int minor,major;
+
+ major = MAJOR(dev);
+ minor = MINOR(dev);
+ if (major < 0 || major >= MAX_BLKDEV) return 0;
+ return ro_bits[major][minor >> 5] & (1 << (minor & 31));
+}
+
+void set_device_ro(kdev_t dev,int flag)
+{
+ int minor,major;
+
+ major = MAJOR(dev);
+ minor = MINOR(dev);
+ if (major < 0 || major >= MAX_BLKDEV) return;
+ if (flag) ro_bits[major][minor >> 5] |= 1 << (minor & 31);
+ else ro_bits[major][minor >> 5] &= ~(1 << (minor & 31));
+}
+
+inline void drive_stat_acct (kdev_t dev, int rw,
+ unsigned long nr_sectors, int new_io)
+{
+ unsigned int major = MAJOR(dev);
+ unsigned int index;
+
+ index = disk_index(dev);
+ if ((index >= DK_MAX_DISK) || (major >= DK_MAX_MAJOR))
+ return;
+
+ kstat.dk_drive[major][index] += new_io;
+ if (rw == READ) {
+ kstat.dk_drive_rio[major][index] += new_io;
+ kstat.dk_drive_rblk[major][index] += nr_sectors;
+ } else if (rw == WRITE) {
+ kstat.dk_drive_wio[major][index] += new_io;
+ kstat.dk_drive_wblk[major][index] += nr_sectors;
+ } else
+ printk(KERN_ERR "drive_stat_acct: cmd not R/W?\n");
+}
+
+#ifdef CONFIG_BLK_STATS
+/*
+ * Return up to two hd_structs on which to do IO accounting for a given
+ * request.
+ *
+ * On a partitioned device, we want to account both against the partition
+ * and against the whole disk.
+ */
+static void locate_hd_struct(struct request *req,
+ struct hd_struct **hd1,
+ struct hd_struct **hd2)
+{
+ struct gendisk *gd;
+
+ *hd1 = NULL;
+ *hd2 = NULL;
+
+ gd = get_gendisk(req->rq_dev);
+ if (gd && gd->part) {
+ /* Mask out the partition bits: account for the entire disk */
+ int devnr = MINOR(req->rq_dev) >> gd->minor_shift;
+ int whole_minor = devnr << gd->minor_shift;
+
+ *hd1 = &gd->part[whole_minor];
+ if (whole_minor != MINOR(req->rq_dev))
+ *hd2= &gd->part[MINOR(req->rq_dev)];
+ }
+}
+
+/*
+ * Round off the performance stats on an hd_struct.
+ *
+ * The average IO queue length and utilisation statistics are maintained
+ * by observing the current state of the queue length and the amount of
+ * time it has been in this state for.
+ * Normally, that accounting is done on IO completion, but that can result
+ * in more than a second's worth of IO being accounted for within any one
+ * second, leading to >100% utilisation. To deal with that, we do a
+ * round-off before returning the results when reading /proc/partitions,
+ * accounting immediately for all queue usage up to the current jiffies and
+ * restarting the counters again.
+ */
+void disk_round_stats(struct hd_struct *hd)
+{
+ unsigned long now = jiffies;
+
+ hd->aveq += (hd->ios_in_flight * (jiffies - hd->last_queue_change));
+ hd->last_queue_change = now;
+
+ if (hd->ios_in_flight)
+ hd->io_ticks += (now - hd->last_idle_time);
+ hd->last_idle_time = now;
+}
+
+static inline void down_ios(struct hd_struct *hd)
+{
+ disk_round_stats(hd);
+ --hd->ios_in_flight;
+}
+
+static inline void up_ios(struct hd_struct *hd)
+{
+ disk_round_stats(hd);
+ ++hd->ios_in_flight;
+}
+
+static void account_io_start(struct hd_struct *hd, struct request *req,
+ int merge, int sectors)
+{
+ switch (req->cmd) {
+ case READ:
+ if (merge)
+ hd->rd_merges++;
+ hd->rd_sectors += sectors;
+ break;
+ case WRITE:
+ if (merge)
+ hd->wr_merges++;
+ hd->wr_sectors += sectors;
+ break;
+ }
+ if (!merge)
+ up_ios(hd);
+}
+
+static void account_io_end(struct hd_struct *hd, struct request *req)
+{
+ unsigned long duration = jiffies - req->start_time;
+ switch (req->cmd) {
+ case READ:
+ hd->rd_ticks += duration;
+ hd->rd_ios++;
+ break;
+ case WRITE:
+ hd->wr_ticks += duration;
+ hd->wr_ios++;
+ break;
+ }
+ down_ios(hd);
+}
+
+void req_new_io(struct request *req, int merge, int sectors)
+{
+ struct hd_struct *hd1, *hd2;
+
+ locate_hd_struct(req, &hd1, &hd2);
+ if (hd1)
+ account_io_start(hd1, req, merge, sectors);
+ if (hd2)
+ account_io_start(hd2, req, merge, sectors);
+}
+
+void req_merged_io(struct request *req)
+{
+ struct hd_struct *hd1, *hd2;
+
+ locate_hd_struct(req, &hd1, &hd2);
+ if (hd1)
+ down_ios(hd1);
+ if (hd2)
+ down_ios(hd2);
+}
+
+void req_finished_io(struct request *req)
+{
+ struct hd_struct *hd1, *hd2;
+
+ locate_hd_struct(req, &hd1, &hd2);
+ if (hd1)
+ account_io_end(hd1, req);
+ if (hd2)
+ account_io_end(hd2, req);
+}
+EXPORT_SYMBOL(req_finished_io);
+#endif /* CONFIG_BLK_STATS */
+
+/*
+ * add-request adds a request to the linked list.
+ * io_request_lock is held and interrupts disabled, as we muck with the
+ * request queue list.
+ *
+ * By this point, req->cmd is always either READ/WRITE, never READA,
+ * which is important for drive_stat_acct() above.
+ */
+static inline void add_request(request_queue_t * q, struct request * req,
+ struct list_head *insert_here)
+{
+ drive_stat_acct(req->rq_dev, req->cmd, req->nr_sectors, 1);
+
+ if (!q->plugged && q->head_active && insert_here == &q->queue_head) {
+ spin_unlock_irq(&io_request_lock);
+ BUG();
+ }
+
+ /*
+ * elevator indicated where it wants this request to be
+ * inserted at elevator_merge time
+ */
+ list_add(&req->queue, insert_here);
+}
+
+/*
+ * Must be called with io_request_lock held and interrupts disabled
+ */
+void blkdev_release_request(struct request *req)
+{
+ request_queue_t *q = req->q;
+
+ req->rq_status = RQ_INACTIVE;
+ req->q = NULL;
+
+ /*
+ * Request may not have originated from ll_rw_blk. if not,
+ * assume it has free buffers and check waiters
+ */
+ if (q) {
+ struct request_list *rl = &q->rq;
+ int oversized_batch = 0;
+
+ if (q->can_throttle)
+ oversized_batch = blk_oversized_queue_batch(q);
+ rl->count++;
+ /*
+ * paranoia check
+ */
+ if (req->cmd == READ || req->cmd == WRITE)
+ rl->pending[req->cmd]--;
+ if (rl->pending[READ] > q->nr_requests)
+ printk("blk: reads: %u\n", rl->pending[READ]);
+ if (rl->pending[WRITE] > q->nr_requests)
+ printk("blk: writes: %u\n", rl->pending[WRITE]);
+ if (rl->pending[READ] + rl->pending[WRITE] > q->nr_requests)
+ printk("blk: r/w: %u + %u > %u\n", rl->pending[READ],
rl->pending[WRITE], q->nr_requests);
+ list_add(&req->queue, &rl->free);
+ if (rl->count >= q->batch_requests && !oversized_batch) {
+ smp_mb();
+ if (waitqueue_active(&q->wait_for_requests))
+ wake_up(&q->wait_for_requests);
+ }
+ }
+}
+
+/*
+ * Has to be called with the request spinlock acquired
+ */
+static void attempt_merge(request_queue_t * q,
+ struct request *req,
+ int max_sectors,
+ int max_segments)
+{
+ struct request *next;
+
+ next = blkdev_next_request(req);
+ if (req->sector + req->nr_sectors != next->sector)
+ return;
+ if (req->cmd != next->cmd
+ || req->rq_dev != next->rq_dev
+ || req->nr_sectors + next->nr_sectors > max_sectors
+ || next->waiting)
+ return;
+ /*
+ * If we are not allowed to merge these requests, then
+ * return. If we are allowed to merge, then the count
+ * will have been updated to the appropriate number,
+ * and we shouldn't do it here too.
+ */
+ if (!q->merge_requests_fn(q, req, next, max_segments))
+ return;
+
+ q->elevator.elevator_merge_req_fn(req, next);
+
+ /* At this point we have either done a back merge
+ * or front merge. We need the smaller start_time of
+ * the merged requests to be the current request
+ * for accounting purposes.
+ */
+ if (time_after(req->start_time, next->start_time))
+ req->start_time = next->start_time;
+
+ req->bhtail->b_reqnext = next->bh;
+ req->bhtail = next->bhtail;
+ req->nr_sectors = req->hard_nr_sectors += next->hard_nr_sectors;
+ list_del(&next->queue);
+
+ /* One last thing: we have removed a request, so we now have one
+ less expected IO to complete for accounting purposes. */
+ req_merged_io(req);
+
+ blkdev_release_request(next);
+}
+
+static inline void attempt_back_merge(request_queue_t * q,
+ struct request *req,
+ int max_sectors,
+ int max_segments)
+{
+ if (&req->queue == q->queue_head.prev)
+ return;
+ attempt_merge(q, req, max_sectors, max_segments);
+}
+
+static inline void attempt_front_merge(request_queue_t * q,
+ struct list_head * head,
+ struct request *req,
+ int max_sectors,
+ int max_segments)
+{
+ struct list_head * prev;
+
+ prev = req->queue.prev;
+ if (head == prev)
+ return;
+ attempt_merge(q, blkdev_entry_to_request(prev), max_sectors,
max_segments);
+}
+
+static int __make_request(request_queue_t * q, int rw,
+ struct buffer_head * bh)
+{
+ unsigned int sector, count, sync;
+ int max_segments = MAX_SEGMENTS;
+ struct request * req, *freereq = NULL;
+ int rw_ahead, max_sectors, el_ret;
+ struct list_head *head, *insert_here;
+ int latency;
+ elevator_t *elevator = &q->elevator;
+ int should_wake = 0;
+
+ count = bh->b_size >> 9;
+ sector = bh->b_rsector;
+ sync = test_and_clear_bit(BH_Sync, &bh->b_state);
+
+ rw_ahead = 0; /* normal case; gets changed below for READA */
+ switch (rw) {
+ case READA:
+#if 0 /* bread() misinterprets failed READA attempts as IO errors on SMP */
+ rw_ahead = 1;
+#endif
+ rw = READ; /* drop into READ */
+ case READ:
+ case WRITE:
+ latency = elevator_request_latency(elevator, rw);
+ break;
+ default:
+ BUG();
+ goto end_io;
+ }
+
+ /* We'd better have a real physical mapping!
+ Check this bit only if the buffer was dirty and just locked
+ down by us so at this point flushpage will block and
+ won't clear the mapped bit under us. */
+ if (!buffer_mapped(bh))
+ BUG();
+
+ /*
+ * Temporary solution - in 2.5 this will be done by the lowlevel
+ * driver. Create a bounce buffer if the buffer data points into
+ * high memory - keep the original buffer otherwise.
+ */
+ bh = blk_queue_bounce(q, rw, bh);
+
+/* look for a free request. */
+ /*
+ * Try to coalesce the new request with old requests
+ */
+ max_sectors = get_max_sectors(bh->b_rdev);
+
+ req = NULL;
+ head = &q->queue_head;
+ /*
+ * Now we acquire the request spinlock, we have to be mega careful
+ * not to schedule or do something nonatomic
+ */
+ spin_lock_irq(&io_request_lock);
+
+again:
+ insert_here = head->prev;
+
+ if (list_empty(head)) {
+ q->plug_device_fn(q, bh->b_rdev); /* is atomic */
+ goto get_rq;
+ } else if (q->head_active && !q->plugged)
+ head = head->next;
+
+ el_ret = elevator->elevator_merge_fn(q, &req, head, bh, rw,max_sectors);
+ switch (el_ret) {
+
+ case ELEVATOR_BACK_MERGE:
+ if (!q->back_merge_fn(q, req, bh, max_segments)) {
+ insert_here = &req->queue;
+ break;
+ }
+ req->bhtail->b_reqnext = bh;
+ req->bhtail = bh;
+ req->nr_sectors = req->hard_nr_sectors += count;
+ blk_started_io(count);
+ blk_started_sectors(req, count);
+ drive_stat_acct(req->rq_dev, req->cmd, count, 0);
+ req_new_io(req, 1, count);
+ attempt_back_merge(q, req, max_sectors, max_segments);
+ goto out;
+
+ case ELEVATOR_FRONT_MERGE:
+ if (!q->front_merge_fn(q, req, bh, max_segments)) {
+ insert_here = req->queue.prev;
+ break;
+ }
+ bh->b_reqnext = req->bh;
+ req->bh = bh;
+ /*
+ * may not be valid, but queues not having bounce
+ * enabled for highmem pages must not look at
+ * ->buffer anyway
+ */
+ req->buffer = bh->b_data;
+ req->current_nr_sectors = req->hard_cur_sectors = count;
+ req->sector = req->hard_sector = sector;
+ req->nr_sectors = req->hard_nr_sectors += count;
+ blk_started_io(count);
+ blk_started_sectors(req, count);
+ drive_stat_acct(req->rq_dev, req->cmd, count, 0);
+ req_new_io(req, 1, count);
+ attempt_front_merge(q, head, req, max_sectors,
max_segments);
+ goto out;
+
+ /*
+ * elevator says don't/can't merge. get new request
+ */
+ case ELEVATOR_NO_MERGE:
+ /*
+ * use elevator hints as to where to insert the
+ * request. if no hints, just add it to the back
+ * of the queue
+ */
+ if (req)
+ insert_here = &req->queue;
+ break;
+
+ default:
+ printk("elevator returned crap (%d)\n", el_ret);
+ BUG();
+ }
+
+get_rq:
+ if (freereq) {
+ req = freereq;
+ freereq = NULL;
+ } else {
+ /*
+ * See description above __get_request_wait()
+ */
+ if (rw_ahead) {
+ if (q->rq.count < q->batch_requests ||
blk_oversized_queue_batch(q)) {
+ spin_unlock_irq(&io_request_lock);
+ goto end_io;
+ }
+ req = get_request(q, rw);
+ if (req == NULL)
+ BUG();
+ } else {
+ req = get_request(q, rw);
+ if (req == NULL) {
+ spin_unlock_irq(&io_request_lock);
+ freereq = __get_request_wait(q, rw);
+ head = &q->queue_head;
+ spin_lock_irq(&io_request_lock);
+ should_wake = 1;
+ goto again;
+ }
+ }
+ }
+
+/* fill up the request-info, and add it to the queue */
+ req->elevator_sequence = latency;
+ req->cmd = rw;
+ req->errors = 0;
+ req->hard_sector = req->sector = sector;
+ req->hard_nr_sectors = req->nr_sectors = count;
+ req->current_nr_sectors = req->hard_cur_sectors = count;
+ req->nr_segments = 1; /* Always 1 for a new request. */
+ req->nr_hw_segments = 1; /* Always 1 for a new request. */
+ req->buffer = bh->b_data;
+ req->waiting = NULL;
+ req->bh = bh;
+ req->bhtail = bh;
+ req->rq_dev = bh->b_rdev;
+ req->start_time = jiffies;
+ req_new_io(req, 0, count);
+ blk_started_io(count);
+ blk_started_sectors(req, count);
+ add_request(q, req, insert_here);
+out:
+ if (freereq)
+ blkdev_release_request(freereq);
+ if (should_wake)
+ get_request_wait_wakeup(q, rw);
+ if (sync)
+ __generic_unplug_device(q);
+ spin_unlock_irq(&io_request_lock);
+ return 0;
+end_io:
+ bh->b_end_io(bh, test_bit(BH_Uptodate, &bh->b_state));
+ return 0;
+}
+
+/**
+ * generic_make_request: hand a buffer head to it's device driver for I/O
+ * @rw: READ, WRITE, or READA - what sort of I/O is desired.
+ * @bh: The buffer head describing the location in memory and on the device.
+ *
+ * generic_make_request() is used to make I/O requests of block
+ * devices. It is passed a &struct buffer_head and a &rw value. The
+ * %READ and %WRITE options are (hopefully) obvious in meaning. The
+ * %READA value means that a read is required, but that the driver is
+ * free to fail the request if, for example, it cannot get needed
+ * resources immediately.
+ *
+ * generic_make_request() does not return any status. The
+ * success/failure status of the request, along with notification of
+ * completion, is delivered asynchronously through the bh->b_end_io
+ * function described (one day) else where.
+ *
+ * The caller of generic_make_request must make sure that b_page,
+ * b_addr, b_size are set to describe the memory buffer, that b_rdev
+ * and b_rsector are set to describe the device address, and the
+ * b_end_io and optionally b_private are set to describe how
+ * completion notification should be signaled. BH_Mapped should also
+ * be set (to confirm that b_dev and b_blocknr are valid).
+ *
+ * generic_make_request and the drivers it calls may use b_reqnext,
+ * and may change b_rdev and b_rsector. So the values of these fields
+ * should NOT be depended on after the call to generic_make_request.
+ * Because of this, the caller should record the device address
+ * information in b_dev and b_blocknr.
+ *
+ * Apart from those fields mentioned above, no other fields, and in
+ * particular, no other flags, are changed by generic_make_request or
+ * any lower level drivers.
+ * */
+void generic_make_request (int rw, struct buffer_head * bh)
+{
+ int major = MAJOR(bh->b_rdev);
+ int minorsize = 0;
+ request_queue_t *q;
+
+ if (!bh->b_end_io)
+ BUG();
+
+ /* Test device size, when known. */
+ if (blk_size[major])
+ minorsize = blk_size[major][MINOR(bh->b_rdev)];
+ if (minorsize) {
+ unsigned long maxsector = (minorsize << 1) + 1;
+ unsigned long sector = bh->b_rsector;
+ unsigned int count = bh->b_size >> 9;
+
+ if (maxsector < count || maxsector - count < sector) {
+ /* Yecch */
+ bh->b_state &= ~(1 << BH_Dirty);
+
+ /* This may well happen - the kernel calls bread()
+ without checking the size of the device, e.g.,
+ when mounting a device. */
+ printk(KERN_INFO
+ "attempt to access beyond end of device\n");
+ printk(KERN_INFO "%s: rw=%d, want=%ld, limit=%d\n",
+ kdevname(bh->b_rdev), rw,
+ (sector + count)>>1, minorsize);
+
+ bh->b_end_io(bh, 0);
+ return;
+ }
+ }
+
+ /*
+ * Resolve the mapping until finished. (drivers are
+ * still free to implement/resolve their own stacking
+ * by explicitly returning 0)
+ */
+ /* NOTE: we don't repeat the blk_size check for each new device.
+ * Stacking drivers are expected to know what they are doing.
+ */
+ do {
+ q = __blk_get_queue(bh->b_rdev);
+ if (!q) {
+ printk(KERN_ERR
+ "generic_make_request: Trying to access "
+ "nonexistent block-device %s (%ld)\n",
+ kdevname(bh->b_rdev), bh->b_rsector);
+ buffer_IO_error(bh);
+ break;
+ }
+ } while (q->make_request_fn(q, rw, bh));
+}
+
+
+/**
+ * submit_bh: submit a buffer_head to the block device later for I/O
+ * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
+ * @bh: The &struct buffer_head which describes the I/O
+ *
+ * submit_bh() is very similar in purpose to generic_make_request(), and
+ * uses that function to do most of the work.
+ *
+ * The extra functionality provided by submit_bh is to determine
+ * b_rsector from b_blocknr and b_size, and to set b_rdev from b_dev.
+ * This is is appropriate for IO requests that come from the buffer
+ * cache and page cache which (currently) always use aligned blocks.
+ */
+void submit_bh(int rw, struct buffer_head * bh)
+{
+ int count = bh->b_size >> 9;
+
+ if (!test_bit(BH_Lock, &bh->b_state))
+ BUG();
+
+ set_bit(BH_Req, &bh->b_state);
+ set_bit(BH_Launder, &bh->b_state);
+
+ /*
+ * First step, 'identity mapping' - RAID or LVM might
+ * further remap this.
+ */
+ bh->b_rdev = bh->b_dev;
+ bh->b_rsector = bh->b_blocknr * count;
+
+ get_bh(bh);
+ generic_make_request(rw, bh);
+
+ /* fix race condition with wait_on_buffer() */
+ smp_mb(); /* spin_unlock may have inclusive semantics */
+ if (waitqueue_active(&bh->b_wait))
+ wake_up(&bh->b_wait);
+
+ if (block_dump)
+ printk(KERN_DEBUG "%s: %s block %lu/%u on %s\n", current->comm,
rw == WRITE ? "WRITE" : "READ", bh->b_rsector, count, kdevname(bh->b_rdev));
+
+ put_bh(bh);
+ switch (rw) {
+ case WRITE:
+ kstat.pgpgout += count;
+ break;
+ default:
+ kstat.pgpgin += count;
+ break;
+ }
+}
+
+/**
+ * ll_rw_block: low-level access to block devices
+ * @rw: whether to %READ or %WRITE or maybe %READA (readahead)
+ * @nr: number of &struct buffer_heads in the array
+ * @bhs: array of pointers to &struct buffer_head
+ *
+ * ll_rw_block() takes an array of pointers to &struct buffer_heads,
+ * and requests an I/O operation on them, either a %READ or a %WRITE.
+ * The third %READA option is described in the documentation for
+ * generic_make_request() which ll_rw_block() calls.
+ *
+ * This function provides extra functionality that is not in
+ * generic_make_request() that is relevant to buffers in the buffer
+ * cache or page cache. In particular it drops any buffer that it
+ * cannot get a lock on (with the BH_Lock state bit), any buffer that
+ * appears to be clean when doing a write request, and any buffer that
+ * appears to be up-to-date when doing read request. Further it marks
+ * as clean buffers that are processed for writing (the buffer cache
+ * wont assume that they are actually clean until the buffer gets
+ * unlocked).
+ *
+ * ll_rw_block sets b_end_io to simple completion handler that marks
+ * the buffer up-to-date (if approriate), unlocks the buffer and wakes
+ * any waiters. As client that needs a more interesting completion
+ * routine should call submit_bh() (or generic_make_request())
+ * directly.
+ *
+ * Caveat:
+ * All of the buffers must be for the same device, and must also be
+ * of the current approved size for the device. */
+
+void ll_rw_block(int rw, int nr, struct buffer_head * bhs[])
+{
+ unsigned int major;
+ int correct_size;
+ int i;
+
+ if (!nr)
+ return;
+
+ major = MAJOR(bhs[0]->b_dev);
+
+ /* Determine correct block size for this device. */
+ correct_size = get_hardsect_size(bhs[0]->b_dev);
+
+ /* Verify requested block sizes. */
+ for (i = 0; i < nr; i++) {
+ struct buffer_head *bh = bhs[i];
+ if (bh->b_size % correct_size) {
+ printk(KERN_NOTICE "ll_rw_block: device %s: "
+ "only %d-char blocks implemented (%u)\n",
+ kdevname(bhs[0]->b_dev),
+ correct_size, bh->b_size);
+ goto sorry;
+ }
+ }
+
+ if ((rw & WRITE) && is_read_only(bhs[0]->b_dev)) {
+ printk(KERN_NOTICE "Can't write to read-only device %s\n",
+ kdevname(bhs[0]->b_dev));
+ goto sorry;
+ }
+
+ for (i = 0; i < nr; i++) {
+ struct buffer_head *bh = bhs[i];
+
+ lock_buffer(bh);
+
+ /* We have the buffer lock */
+ atomic_inc(&bh->b_count);
+ bh->b_end_io = end_buffer_io_sync;
+
+ switch(rw) {
+ case WRITE:
+ if (!atomic_set_buffer_clean(bh))
+ /* Hmmph! Nothing to write */
+ goto end_io;
+ __mark_buffer_clean(bh);
+ break;
+
+ case READA:
+ case READ:
+ if (buffer_uptodate(bh))
+ /* Hmmph! Already have it */
+ goto end_io;
+ break;
+ default:
+ BUG();
+ end_io:
+ bh->b_end_io(bh, test_bit(BH_Uptodate, &bh->b_state));
+ continue;
+ }
+
+ submit_bh(rw, bh);
+ }
+ return;
+
+sorry:
+ /* Make sure we don't get infinite dirty retries.. */
+ for (i = 0; i < nr; i++)
+ mark_buffer_clean(bhs[i]);
+}
+
+#ifdef CONFIG_STRAM_SWAP
+extern int stram_device_init (void);
+#endif
+
+static void blk_writeback_timer(unsigned long data)
+{
+ wakeup_bdflush();
+ wakeup_kupdate();
+}
+
+/**
+ * end_that_request_first - end I/O on one buffer.
+ * @req: the request being processed
+ * @uptodate: 0 for I/O error
+ * @name: the name printed for an I/O error
+ *
+ * Description:
+ * Ends I/O on the first buffer attached to @req, and sets it up
+ * for the next buffer_head (if any) in the cluster.
+ *
+ * Return:
+ * 0 - we are done with this request, call end_that_request_last()
+ * 1 - still buffers pending for this request
+ *
+ * Caveat:
+ * Drivers implementing their own end_request handling must call
+ * blk_finished_io() appropriately.
+ **/
+
+int end_that_request_first (struct request *req, int uptodate, char *name)
+{
+ struct buffer_head * bh;
+ int nsect;
+
+ req->errors = 0;
+ if (!uptodate)
+ printk("end_request: I/O error, dev %s (%s), sector %lu\n",
+ kdevname(req->rq_dev), name, req->sector);
+
+ if ((bh = req->bh) != NULL) {
+ nsect = bh->b_size >> 9;
+ blk_finished_io(nsect);
+ blk_finished_sectors(req, nsect);
+ req->bh = bh->b_reqnext;
+ bh->b_reqnext = NULL;
+ bh->b_end_io(bh, uptodate);
+ if ((bh = req->bh) != NULL) {
+ req->hard_sector += nsect;
+ req->hard_nr_sectors -= nsect;
+ req->sector = req->hard_sector;
+ req->nr_sectors = req->hard_nr_sectors;
+
+ req->current_nr_sectors = bh->b_size >> 9;
+ req->hard_cur_sectors = req->current_nr_sectors;
+ if (req->nr_sectors < req->current_nr_sectors) {
+ req->nr_sectors = req->current_nr_sectors;
+ printk("end_request: buffer-list destroyed\n");
+ }
+ req->buffer = bh->b_data;
+ return 1;
+ }
+ }
+ return 0;
+}
+
+extern int laptop_mode;
+
+void end_that_request_last(struct request *req)
+{
+ struct completion *waiting = req->waiting;
+
+ /*
+ * schedule the writeout of pending dirty data when the disk is idle
+ */
+ if (laptop_mode && req->cmd == READ)
+ mod_timer(&writeback_timer, jiffies + 5 * HZ);
+
+ req_finished_io(req);
+ blkdev_release_request(req);
+ if (waiting)
+ complete(waiting);
+}
+
+int __init blk_dev_init(void)
+{
+ struct blk_dev_struct *dev;
+
+ request_cachep = kmem_cache_create("blkdev_requests",
+ sizeof(struct request),
+ 0, SLAB_HWCACHE_ALIGN, NULL, NULL);
+
+ if (!request_cachep)
+ panic("Can't create request pool slab cache\n");
+
+ for (dev = blk_dev + MAX_BLKDEV; dev-- != blk_dev;)
+ dev->queue = NULL;
+
+ memset(ro_bits,0,sizeof(ro_bits));
+ memset(max_readahead, 0, sizeof(max_readahead));
+ memset(max_sectors, 0, sizeof(max_sectors));
+
+ blk_max_low_pfn = max_low_pfn - 1;
+ blk_max_pfn = max_pfn - 1;
+
+ init_timer(&writeback_timer);
+ writeback_timer.function = blk_writeback_timer;
+
+#ifdef CONFIG_AMIGA_Z2RAM
+ z2_init();
+#endif
+#ifdef CONFIG_STRAM_SWAP
+ stram_device_init();
+#endif
+#ifdef CONFIG_ISP16_CDI
+ isp16_init();
+#endif
+#ifdef CONFIG_BLK_DEV_PS2
+ ps2esdi_init();
+#endif
+#ifdef CONFIG_BLK_DEV_XD
+ xd_init();
+#endif
+#ifdef CONFIG_BLK_DEV_MFM
+ mfm_init();
+#endif
+#ifdef CONFIG_PARIDE
+ { extern void paride_init(void); paride_init(); };
+#endif
+#ifdef CONFIG_MAC_FLOPPY
+ swim3_init();
+#endif
+#ifdef CONFIG_BLK_DEV_SWIM_IOP
+ swimiop_init();
+#endif
+#ifdef CONFIG_AMIGA_FLOPPY
+ amiga_floppy_init();
+#endif
+#ifdef CONFIG_ATARI_FLOPPY
+ atari_floppy_init();
+#endif
+#ifdef CONFIG_BLK_DEV_FD
+ floppy_init();
+#else
+#if defined(__i386__) && !defined(CONFIG_XEN) /* Do we even need this? */
+ outb_p(0xc, 0x3f2);
+#endif
+#endif
+#ifdef CONFIG_CDU31A
+ cdu31a_init();
+#endif
+#ifdef CONFIG_ATARI_ACSI
+ acsi_init();
+#endif
+#ifdef CONFIG_MCD
+ mcd_init();
+#endif
+#ifdef CONFIG_MCDX
+ mcdx_init();
+#endif
+#ifdef CONFIG_SBPCD
+ sbpcd_init();
+#endif
+#ifdef CONFIG_AZTCD
+ aztcd_init();
+#endif
+#ifdef CONFIG_CDU535
+ sony535_init();
+#endif
+#ifdef CONFIG_GSCD
+ gscd_init();
+#endif
+#ifdef CONFIG_CM206
+ cm206_init();
+#endif
+#ifdef CONFIG_OPTCD
+ optcd_init();
+#endif
+#ifdef CONFIG_SJCD
+ sjcd_init();
+#endif
+#ifdef CONFIG_APBLOCK
+ ap_init();
+#endif
+#ifdef CONFIG_DDV
+ ddv_init();
+#endif
+#ifdef CONFIG_MDISK
+ mdisk_init();
+#endif
+#ifdef CONFIG_DASD
+ dasd_init();
+#endif
+#if defined(CONFIG_S390_TAPE) && defined(CONFIG_S390_TAPE_BLOCK)
+ tapeblock_init();
+#endif
+#ifdef CONFIG_BLK_DEV_XPRAM
+ xpram_init();
+#endif
+
+#ifdef CONFIG_SUN_JSFLASH
+ jsfd_init();
+#endif
+
+#if defined(CONFIG_XEN_BLKDEV_FRONTEND)
+ xlblk_init();
+#endif
+
+ return 0;
+};
+
+EXPORT_SYMBOL(io_request_lock);
+EXPORT_SYMBOL(end_that_request_first);
+EXPORT_SYMBOL(end_that_request_last);
+EXPORT_SYMBOL(blk_grow_request_list);
+EXPORT_SYMBOL(blk_init_queue);
+EXPORT_SYMBOL(blk_get_queue);
+EXPORT_SYMBOL(blk_cleanup_queue);
+EXPORT_SYMBOL(blk_queue_headactive);
+EXPORT_SYMBOL(blk_queue_throttle_sectors);
+EXPORT_SYMBOL(blk_queue_make_request);
+EXPORT_SYMBOL(generic_make_request);
+EXPORT_SYMBOL(blkdev_release_request);
+EXPORT_SYMBOL(generic_unplug_device);
+EXPORT_SYMBOL(blk_queue_bounce_limit);
+EXPORT_SYMBOL(blk_max_low_pfn);
+EXPORT_SYMBOL(blk_max_pfn);
+EXPORT_SYMBOL(blk_seg_merge_ok);
+EXPORT_SYMBOL(blk_nohighio);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/processor.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/processor.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,684 @@
+/*
+ * include/asm-i386/processor.h
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ */
+
+#ifndef __ASM_I386_PROCESSOR_H
+#define __ASM_I386_PROCESSOR_H
+
+#include <asm/vm86.h>
+#include <asm/math_emu.h>
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/types.h>
+#include <asm/sigcontext.h>
+#include <asm/cpufeature.h>
+#include <asm/msr.h>
+#include <asm/system.h>
+#include <linux/cache.h>
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <asm/percpu.h>
+
+/* flag for disabling the tsc */
+extern int tsc_disable;
+
+struct desc_struct {
+ unsigned long a,b;
+};
+
+#define desc_empty(desc) \
+ (!((desc)->a + (desc)->b))
+
+#define desc_equal(desc1, desc2) \
+ (((desc1)->a == (desc2)->a) && ((desc1)->b == (desc2)->b))
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#define current_text_addr() ({ void *pc; __asm__("movl $1f,%0\n1:":"=g" (pc));
pc; })
+
+/*
+ * CPU type and hardware bug flags. Kept separately for each CPU.
+ * Members of this structure are referenced in head.S, so think twice
+ * before touching them. [mj]
+ */
+
+struct cpuinfo_x86 {
+ __u8 x86; /* CPU family */
+ __u8 x86_vendor; /* CPU vendor */
+ __u8 x86_model;
+ __u8 x86_mask;
+ char wp_works_ok; /* It doesn't on 386's */
+ char hlt_works_ok; /* Problems on some 486Dx4's and old 386's */
+ char hard_math;
+ char rfu;
+ int cpuid_level; /* Maximum supported CPUID level, -1=no
CPUID */
+ unsigned long x86_capability[NCAPINTS];
+ char x86_vendor_id[16];
+ char x86_model_id[64];
+ int x86_cache_size; /* in KB - valid for CPUS which support this
+ call */
+ int x86_cache_alignment; /* In bytes */
+ int fdiv_bug;
+ int f00f_bug;
+ int coma_bug;
+ unsigned long loops_per_jiffy;
+ unsigned char x86_num_cores;
+} __attribute__((__aligned__(SMP_CACHE_BYTES)));
+
+#define X86_VENDOR_INTEL 0
+#define X86_VENDOR_CYRIX 1
+#define X86_VENDOR_AMD 2
+#define X86_VENDOR_UMC 3
+#define X86_VENDOR_NEXGEN 4
+#define X86_VENDOR_CENTAUR 5
+#define X86_VENDOR_RISE 6
+#define X86_VENDOR_TRANSMETA 7
+#define X86_VENDOR_NSC 8
+#define X86_VENDOR_NUM 9
+#define X86_VENDOR_UNKNOWN 0xff
+
+/*
+ * capabilities of CPUs
+ */
+
+extern struct cpuinfo_x86 boot_cpu_data;
+extern struct cpuinfo_x86 new_cpu_data;
+extern struct tss_struct doublefault_tss;
+DECLARE_PER_CPU(struct tss_struct, init_tss);
+DECLARE_PER_CPU(pgd_t *, cur_pgd);
+
+#ifdef CONFIG_SMP
+extern struct cpuinfo_x86 cpu_data[];
+#define current_cpu_data cpu_data[smp_processor_id()]
+#else
+#define cpu_data (&boot_cpu_data)
+#define current_cpu_data boot_cpu_data
+#endif
+
+extern int phys_proc_id[NR_CPUS];
+extern char ignore_fpu_irq;
+
+extern void identify_cpu(struct cpuinfo_x86 *);
+extern void print_cpu_info(struct cpuinfo_x86 *);
+extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
+extern void dodgy_tsc(void);
+
+#ifdef CONFIG_X86_HT
+extern void detect_ht(struct cpuinfo_x86 *c);
+#else
+static inline void detect_ht(struct cpuinfo_x86 *c) {}
+#endif
+
+/*
+ * EFLAGS bits
+ */
+#define X86_EFLAGS_CF 0x00000001 /* Carry Flag */
+#define X86_EFLAGS_PF 0x00000004 /* Parity Flag */
+#define X86_EFLAGS_AF 0x00000010 /* Auxillary carry Flag */
+#define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */
+#define X86_EFLAGS_SF 0x00000080 /* Sign Flag */
+#define X86_EFLAGS_TF 0x00000100 /* Trap Flag */
+#define X86_EFLAGS_IF 0x00000200 /* Interrupt Flag */
+#define X86_EFLAGS_DF 0x00000400 /* Direction Flag */
+#define X86_EFLAGS_OF 0x00000800 /* Overflow Flag */
+#define X86_EFLAGS_IOPL 0x00003000 /* IOPL mask */
+#define X86_EFLAGS_NT 0x00004000 /* Nested Task */
+#define X86_EFLAGS_RF 0x00010000 /* Resume Flag */
+#define X86_EFLAGS_VM 0x00020000 /* Virtual Mode */
+#define X86_EFLAGS_AC 0x00040000 /* Alignment Check */
+#define X86_EFLAGS_VIF 0x00080000 /* Virtual Interrupt Flag */
+#define X86_EFLAGS_VIP 0x00100000 /* Virtual Interrupt Pending */
+#define X86_EFLAGS_ID 0x00200000 /* CPUID detection flag */
+
+/*
+ * Generic CPUID function
+ * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx
+ * resulting in stale register contents being returned.
+ */
+static inline void cpuid(int op, int *eax, int *ebx, int *ecx, int *edx)
+{
+ __asm__("cpuid"
+ : "=a" (*eax),
+ "=b" (*ebx),
+ "=c" (*ecx),
+ "=d" (*edx)
+ : "0" (op), "c"(0));
+}
+
+/*
+ * CPUID functions returning a single datum
+ */
+static inline unsigned int cpuid_eax(unsigned int op)
+{
+ unsigned int eax;
+
+ __asm__("cpuid"
+ : "=a" (eax)
+ : "0" (op)
+ : "bx", "cx", "dx");
+ return eax;
+}
+static inline unsigned int cpuid_ebx(unsigned int op)
+{
+ unsigned int eax, ebx;
+
+ __asm__("cpuid"
+ : "=a" (eax), "=b" (ebx)
+ : "0" (op)
+ : "cx", "dx" );
+ return ebx;
+}
+static inline unsigned int cpuid_ecx(unsigned int op)
+{
+ unsigned int eax, ecx;
+
+ __asm__("cpuid"
+ : "=a" (eax), "=c" (ecx)
+ : "0" (op)
+ : "bx", "dx" );
+ return ecx;
+}
+static inline unsigned int cpuid_edx(unsigned int op)
+{
+ unsigned int eax, edx;
+
+ __asm__("cpuid"
+ : "=a" (eax), "=d" (edx)
+ : "0" (op)
+ : "bx", "cx");
+ return edx;
+}
+
+#define load_cr3(pgdir) do { \
+ xen_pt_switch(__pa(pgdir)); \
+ per_cpu(cur_pgd, smp_processor_id()) = pgdir; \
+} while (/* CONSTCOND */0)
+
+
+/*
+ * Intel CPU features in CR4
+ */
+#define X86_CR4_VME 0x0001 /* enable vm86 extensions */
+#define X86_CR4_PVI 0x0002 /* virtual interrupts flag enable */
+#define X86_CR4_TSD 0x0004 /* disable time stamp at ipl 3 */
+#define X86_CR4_DE 0x0008 /* enable debugging extensions */
+#define X86_CR4_PSE 0x0010 /* enable page size extensions */
+#define X86_CR4_PAE 0x0020 /* enable physical address extensions */
+#define X86_CR4_MCE 0x0040 /* Machine check enable */
+#define X86_CR4_PGE 0x0080 /* enable global pages */
+#define X86_CR4_PCE 0x0100 /* enable performance counters at ipl 3
*/
+#define X86_CR4_OSFXSR 0x0200 /* enable fast FPU save and restore */
+#define X86_CR4_OSXMMEXCPT 0x0400 /* enable unmasked SSE exceptions */
+
+/*
+ * Save the cr4 feature set we're using (ie
+ * Pentium 4MB enable and PPro Global page
+ * enable), so that any CPU's that boot up
+ * after us can get the correct flags.
+ */
+extern unsigned long mmu_cr4_features;
+
+static inline void set_in_cr4 (unsigned long mask)
+{
+ mmu_cr4_features |= mask;
+ switch (mask) {
+ case X86_CR4_OSFXSR:
+ case X86_CR4_OSXMMEXCPT:
+ break;
+ default:
+ do {
+ const char *msg = "Xen unsupported cr4 update\n";
+ (void)HYPERVISOR_console_io(
+ CONSOLEIO_write, __builtin_strlen(msg),
+ (char *)msg);
+ BUG();
+ } while (0);
+ }
+}
+
+static inline void clear_in_cr4 (unsigned long mask)
+{
+ mmu_cr4_features &= ~mask;
+ __asm__("movl %%cr4,%%eax\n\t"
+ "andl %0,%%eax\n\t"
+ "movl %%eax,%%cr4\n"
+ : : "irg" (~mask)
+ :"ax");
+}
+
+/*
+ * NSC/Cyrix CPU configuration register indexes
+ */
+
+#define CX86_PCR0 0x20
+#define CX86_GCR 0xb8
+#define CX86_CCR0 0xc0
+#define CX86_CCR1 0xc1
+#define CX86_CCR2 0xc2
+#define CX86_CCR3 0xc3
+#define CX86_CCR4 0xe8
+#define CX86_CCR5 0xe9
+#define CX86_CCR6 0xea
+#define CX86_CCR7 0xeb
+#define CX86_PCR1 0xf0
+#define CX86_DIR0 0xfe
+#define CX86_DIR1 0xff
+#define CX86_ARR_BASE 0xc4
+#define CX86_RCR_BASE 0xdc
+
+/*
+ * NSC/Cyrix CPU indexed register access macros
+ */
+
+#define getCx86(reg) ({ outb((reg), 0x22); inb(0x23); })
+
+#define setCx86(reg, data) do { \
+ outb((reg), 0x22); \
+ outb((data), 0x23); \
+} while (0)
+
+static inline void __monitor(const void *eax, unsigned long ecx,
+ unsigned long edx)
+{
+ /* "monitor %eax,%ecx,%edx;" */
+ asm volatile(
+ ".byte 0x0f,0x01,0xc8;"
+ : :"a" (eax), "c" (ecx), "d"(edx));
+}
+
+static inline void __mwait(unsigned long eax, unsigned long ecx)
+{
+ /* "mwait %eax,%ecx;" */
+ asm volatile(
+ ".byte 0x0f,0x01,0xc9;"
+ : :"a" (eax), "c" (ecx));
+}
+
+/* from system description table in BIOS. Mostly for MCA use, but
+others may find it useful. */
+extern unsigned int machine_id;
+extern unsigned int machine_submodel_id;
+extern unsigned int BIOS_revision;
+extern unsigned int mca_pentium_flag;
+
+/* Boot loader type from the setup header */
+extern int bootloader_type;
+
+/*
+ * User space process size: 3GB (default).
+ */
+#define TASK_SIZE (PAGE_OFFSET)
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 3))
+
+#define HAVE_ARCH_PICK_MMAP_LAYOUT
+
+/*
+ * Size of io_bitmap.
+ */
+#define IO_BITMAP_BITS 65536
+#define IO_BITMAP_BYTES (IO_BITMAP_BITS/8)
+#define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long))
+#define IO_BITMAP_OFFSET offsetof(struct tss_struct,io_bitmap)
+#define INVALID_IO_BITMAP_OFFSET 0x8000
+#define INVALID_IO_BITMAP_OFFSET_LAZY 0x9000
+
+struct i387_fsave_struct {
+ long cwd;
+ long swd;
+ long twd;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */
+ long status; /* software status information */
+};
+
+struct i387_fxsave_struct {
+ unsigned short cwd;
+ unsigned short swd;
+ unsigned short twd;
+ unsigned short fop;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long mxcsr;
+ long mxcsr_mask;
+ long st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */
+ long xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */
+ long padding[56];
+} __attribute__ ((aligned (16)));
+
+struct i387_soft_struct {
+ long cwd;
+ long swd;
+ long twd;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */
+ unsigned char ftop, changed, lookahead, no_update, rm, alimit;
+ struct info *info;
+ unsigned long entry_eip;
+};
+
+union i387_union {
+ struct i387_fsave_struct fsave;
+ struct i387_fxsave_struct fxsave;
+ struct i387_soft_struct soft;
+};
+
+typedef struct {
+ unsigned long seg;
+} mm_segment_t;
+
+struct thread_struct;
+
+struct tss_struct {
+ unsigned short back_link,__blh;
+ unsigned long esp0;
+ unsigned short ss0,__ss0h;
+ unsigned long esp1;
+ unsigned short ss1,__ss1h; /* ss1 is used to cache
MSR_IA32_SYSENTER_CS */
+ unsigned long esp2;
+ unsigned short ss2,__ss2h;
+ unsigned long __cr3;
+ unsigned long eip;
+ unsigned long eflags;
+ unsigned long eax,ecx,edx,ebx;
+ unsigned long esp;
+ unsigned long ebp;
+ unsigned long esi;
+ unsigned long edi;
+ unsigned short es, __esh;
+ unsigned short cs, __csh;
+ unsigned short ss, __ssh;
+ unsigned short ds, __dsh;
+ unsigned short fs, __fsh;
+ unsigned short gs, __gsh;
+ unsigned short ldt, __ldth;
+ unsigned short trace, io_bitmap_base;
+ /*
+ * The extra 1 is there because the CPU will access an
+ * additional byte beyond the end of the IO permission
+ * bitmap. The extra byte must be all 1 bits, and must
+ * be within the limit.
+ */
+ unsigned long io_bitmap[IO_BITMAP_LONGS + 1];
+ /*
+ * Cache the current maximum and the last task that used the bitmap:
+ */
+ unsigned long io_bitmap_max;
+ struct thread_struct *io_bitmap_owner;
+ /*
+ * pads the TSS to be cacheline-aligned (size is 0x100)
+ */
+ unsigned long __cacheline_filler[35];
+ /*
+ * .. and then another 0x100 bytes for emergency kernel stack
+ */
+ unsigned long stack[64];
+} __attribute__((packed));
+
+#define ARCH_MIN_TASKALIGN 16
+
+struct thread_struct {
+/* cached TLS descriptors. */
+ struct desc_struct tls_array[GDT_ENTRY_TLS_ENTRIES];
+ unsigned long esp0;
+ unsigned long sysenter_cs;
+ unsigned long eip;
+ unsigned long esp;
+ unsigned long fs;
+ unsigned long gs;
+ unsigned int io_pl;
+/* Hardware debugging registers */
+ unsigned long debugreg[8]; /* %%db0-7 debug registers */
+/* fault info */
+ unsigned long cr2, trap_no, error_code;
+/* floating point info */
+ union i387_union i387;
+/* virtual 86 mode info */
+ struct vm86_struct __user * vm86_info;
+ unsigned long screen_bitmap;
+ unsigned long v86flags, v86mask, saved_esp0;
+ unsigned int saved_fs, saved_gs;
+/* IO permissions */
+ unsigned long *io_bitmap_ptr;
+/* max allowed port in the bitmap, in bytes: */
+ unsigned long io_bitmap_max;
+};
+
+#define INIT_THREAD { \
+ .vm86_info = NULL, \
+ .sysenter_cs = __KERNEL_CS, \
+ .io_bitmap_ptr = NULL, \
+}
+
+/*
+ * Note that the .io_bitmap member must be extra-big. This is because
+ * the CPU will access an additional byte beyond the end of the IO
+ * permission bitmap. The extra byte must be all 1 bits, and must
+ * be within the limit.
+ */
+#define INIT_TSS { \
+ .esp0 = sizeof(init_stack) + (long)&init_stack, \
+ .ss0 = __KERNEL_DS, \
+ .ss1 = __KERNEL_CS, \
+ .ldt = GDT_ENTRY_LDT, \
+ .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, \
+ .io_bitmap = { [ 0 ... IO_BITMAP_LONGS] = ~0 }, \
+}
+
+static inline void load_esp0(struct tss_struct *tss, struct thread_struct
*thread)
+{
+ tss->esp0 = thread->esp0;
+ /* This can only happen when SEP is enabled, no need to test
"SEP"arately */
+ if (unlikely(tss->ss1 != thread->sysenter_cs)) {
+ tss->ss1 = thread->sysenter_cs;
+ wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
+ }
+ HYPERVISOR_stack_switch(tss->ss0, tss->esp0);
+}
+
+#define start_thread(regs, new_eip, new_esp) do { \
+ __asm__("movl %0,%%fs ; movl %0,%%gs": :"r" (0)); \
+ set_fs(USER_DS); \
+ regs->xds = __USER_DS; \
+ regs->xes = __USER_DS; \
+ regs->xss = __USER_DS; \
+ regs->xcs = __USER_CS; \
+ regs->eip = new_eip; \
+ regs->esp = new_esp; \
+} while (0)
+
+/* Forward declaration, a strange C thing */
+struct task_struct;
+struct mm_struct;
+
+/* Free all resources held by a thread. */
+extern void release_thread(struct task_struct *);
+
+/* Prepare to copy thread state - unlazy all lazy status */
+extern void prepare_to_copy(struct task_struct *tsk);
+
+/*
+ * create a kernel thread without removing it from tasklists
+ */
+extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
+
+extern unsigned long thread_saved_pc(struct task_struct *tsk);
+void show_trace(struct task_struct *task, unsigned long *stack);
+
+unsigned long get_wchan(struct task_struct *p);
+
+#define THREAD_SIZE_LONGS (THREAD_SIZE/sizeof(unsigned long))
+#define KSTK_TOP(info) \
+({ \
+ unsigned long *__ptr = (unsigned long *)(info); \
+ (unsigned long)(&__ptr[THREAD_SIZE_LONGS]); \
+})
+
+#define task_pt_regs(task) \
+({ \
+ struct pt_regs *__regs__; \
+ __regs__ = (struct pt_regs *)KSTK_TOP((task)->thread_info); \
+ __regs__ - 1; \
+})
+
+#define KSTK_EIP(task) (task_pt_regs(task)->eip)
+#define KSTK_ESP(task) (task_pt_regs(task)->esp)
+
+
+struct microcode_header {
+ unsigned int hdrver;
+ unsigned int rev;
+ unsigned int date;
+ unsigned int sig;
+ unsigned int cksum;
+ unsigned int ldrver;
+ unsigned int pf;
+ unsigned int datasize;
+ unsigned int totalsize;
+ unsigned int reserved[3];
+};
+
+struct microcode {
+ struct microcode_header hdr;
+ unsigned int bits[0];
+};
+
+typedef struct microcode microcode_t;
+typedef struct microcode_header microcode_header_t;
+
+/* microcode format is extended from prescott processors */
+struct extended_signature {
+ unsigned int sig;
+ unsigned int pf;
+ unsigned int cksum;
+};
+
+struct extended_sigtable {
+ unsigned int count;
+ unsigned int cksum;
+ unsigned int reserved[3];
+ struct extended_signature sigs[0];
+};
+/* '6' because it used to be for P6 only (but now covers Pentium 4 as well) */
+#define MICROCODE_IOCFREE _IO('6',0)
+
+/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
+static inline void rep_nop(void)
+{
+ __asm__ __volatile__("rep;nop": : :"memory");
+}
+
+#define cpu_relax() rep_nop()
+
+/* generic versions from gas */
+#define GENERIC_NOP1 ".byte 0x90\n"
+#define GENERIC_NOP2 ".byte 0x89,0xf6\n"
+#define GENERIC_NOP3 ".byte 0x8d,0x76,0x00\n"
+#define GENERIC_NOP4 ".byte 0x8d,0x74,0x26,0x00\n"
+#define GENERIC_NOP5 GENERIC_NOP1 GENERIC_NOP4
+#define GENERIC_NOP6 ".byte 0x8d,0xb6,0x00,0x00,0x00,0x00\n"
+#define GENERIC_NOP7 ".byte 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00\n"
+#define GENERIC_NOP8 GENERIC_NOP1 GENERIC_NOP7
+
+/* Opteron nops */
+#define K8_NOP1 GENERIC_NOP1
+#define K8_NOP2 ".byte 0x66,0x90\n"
+#define K8_NOP3 ".byte 0x66,0x66,0x90\n"
+#define K8_NOP4 ".byte 0x66,0x66,0x66,0x90\n"
+#define K8_NOP5 K8_NOP3 K8_NOP2
+#define K8_NOP6 K8_NOP3 K8_NOP3
+#define K8_NOP7 K8_NOP4 K8_NOP3
+#define K8_NOP8 K8_NOP4 K8_NOP4
+
+/* K7 nops */
+/* uses eax dependencies (arbitary choice) */
+#define K7_NOP1 GENERIC_NOP1
+#define K7_NOP2 ".byte 0x8b,0xc0\n"
+#define K7_NOP3 ".byte 0x8d,0x04,0x20\n"
+#define K7_NOP4 ".byte 0x8d,0x44,0x20,0x00\n"
+#define K7_NOP5 K7_NOP4 ASM_NOP1
+#define K7_NOP6 ".byte 0x8d,0x80,0,0,0,0\n"
+#define K7_NOP7 ".byte 0x8D,0x04,0x05,0,0,0,0\n"
+#define K7_NOP8 K7_NOP7 ASM_NOP1
+
+#ifdef CONFIG_MK8
+#define ASM_NOP1 K8_NOP1
+#define ASM_NOP2 K8_NOP2
+#define ASM_NOP3 K8_NOP3
+#define ASM_NOP4 K8_NOP4
+#define ASM_NOP5 K8_NOP5
+#define ASM_NOP6 K8_NOP6
+#define ASM_NOP7 K8_NOP7
+#define ASM_NOP8 K8_NOP8
+#elif defined(CONFIG_MK7)
+#define ASM_NOP1 K7_NOP1
+#define ASM_NOP2 K7_NOP2
+#define ASM_NOP3 K7_NOP3
+#define ASM_NOP4 K7_NOP4
+#define ASM_NOP5 K7_NOP5
+#define ASM_NOP6 K7_NOP6
+#define ASM_NOP7 K7_NOP7
+#define ASM_NOP8 K7_NOP8
+#else
+#define ASM_NOP1 GENERIC_NOP1
+#define ASM_NOP2 GENERIC_NOP2
+#define ASM_NOP3 GENERIC_NOP3
+#define ASM_NOP4 GENERIC_NOP4
+#define ASM_NOP5 GENERIC_NOP5
+#define ASM_NOP6 GENERIC_NOP6
+#define ASM_NOP7 GENERIC_NOP7
+#define ASM_NOP8 GENERIC_NOP8
+#endif
+
+#define ASM_NOP_MAX 8
+
+/* Prefetch instructions for Pentium III and AMD Athlon */
+/* It's not worth to care about 3dnow! prefetches for the K6
+ because they are microcoded there and very slow.
+ However we don't do prefetches for pre XP Athlons currently
+ That should be fixed. */
+#define ARCH_HAS_PREFETCH
+extern inline void prefetch(const void *x)
+{
+ alternative_input(ASM_NOP4,
+ "prefetchnta (%1)",
+ X86_FEATURE_XMM,
+ "r" (x));
+}
+
+#define ARCH_HAS_PREFETCH
+#define ARCH_HAS_PREFETCHW
+#define ARCH_HAS_SPINLOCK_PREFETCH
+
+/* 3dnow! prefetch to get an exclusive cache line. Useful for
+ spinlocks to avoid one state transition in the cache coherency protocol. */
+extern inline void prefetchw(const void *x)
+{
+ alternative_input(ASM_NOP4,
+ "prefetchw (%1)",
+ X86_FEATURE_3DNOW,
+ "r" (x));
+}
+#define spin_lock_prefetch(x) prefetchw(x)
+
+extern void select_idle_routine(const struct cpuinfo_x86 *c);
+
+#define cache_line_size() (boot_cpu_data.x86_cache_alignment)
+
+extern unsigned long boot_option_idle_override;
+
+#endif /* __ASM_I386_PROCESSOR_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/usbback/common.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/usbback/common.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,85 @@
+
+#ifndef __USBIF__BACKEND__COMMON_H__
+#define __USBIF__BACKEND__COMMON_H__
+
+#include <linux/config.h>
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/rbtree.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <asm/io.h>
+#include <asm/setup.h>
+#include <asm/pgalloc.h>
+#include <asm-xen/ctrl_if.h>
+#include <asm-xen/hypervisor.h>
+
+#include <asm-xen/xen-public/io/usbif.h>
+
+#if 0
+#define ASSERT(_p) \
+ if ( !(_p) ) { printk("Assertion '%s' failed, line %d, file %s", #_p , \
+ __LINE__, __FILE__); *(int*)0=0; }
+#define DPRINTK(_f, _a...) printk(KERN_ALERT "(file=%s, line=%d) " _f, \
+ __FILE__ , __LINE__ , ## _a )
+#else
+#define ASSERT(_p) ((void)0)
+#define DPRINTK(_f, _a...) ((void)0)
+#endif
+
+typedef struct usbif_priv_st usbif_priv_t;
+
+struct usbif_priv_st {
+ /* Unique identifier for this interface. */
+ domid_t domid;
+ unsigned int handle;
+ /* Physical parameters of the comms window. */
+ unsigned long shmem_frame;
+ unsigned int evtchn;
+ int irq;
+ /* Comms Information */
+ usbif_back_ring_t usb_ring;
+ /* Private fields. */
+ enum { DISCONNECTED, DISCONNECTING, CONNECTED } status;
+ /*
+ * DISCONNECT response is deferred until pending requests are ack'ed.
+ * We therefore need to store the id from the original request.
+ */
+ u8 disconnect_rspid;
+ usbif_priv_t *hash_next;
+ struct list_head usbif_list;
+ spinlock_t usb_ring_lock;
+ atomic_t refcnt;
+
+ struct work_struct work;
+};
+
+void usbif_create(usbif_be_create_t *create);
+void usbif_destroy(usbif_be_destroy_t *destroy);
+void usbif_connect(usbif_be_connect_t *connect);
+int usbif_disconnect(usbif_be_disconnect_t *disconnect, u8 rsp_id);
+void usbif_disconnect_complete(usbif_priv_t *up);
+
+void usbif_release_port(usbif_be_release_port_t *msg);
+int usbif_claim_port(usbif_be_claim_port_t *msg);
+void usbif_release_ports(usbif_priv_t *up);
+
+usbif_priv_t *usbif_find(domid_t domid);
+#define usbif_get(_b) (atomic_inc(&(_b)->refcnt))
+#define usbif_put(_b) \
+ do { \
+ if ( atomic_dec_and_test(&(_b)->refcnt) ) \
+ usbif_disconnect_complete(_b); \
+ } while (0)
+
+
+void usbif_interface_init(void);
+void usbif_ctrlif_init(void);
+
+void usbif_deschedule(usbif_priv_t *up);
+void remove_from_usbif_list(usbif_priv_t *up);
+
+irqreturn_t usbif_be_int(int irq, void *dev_id, struct pt_regs *regs);
+
+#endif /* __USBIF__BACKEND__COMMON_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/processor.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/processor.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,483 @@
+/*
+ * include/asm-i386/processor.h
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ */
+
+#ifndef __ASM_I386_PROCESSOR_H
+#define __ASM_I386_PROCESSOR_H
+
+#include <asm/vm86.h>
+#include <asm/math_emu.h>
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/types.h>
+#include <asm/sigcontext.h>
+#include <asm/cpufeature.h>
+#include <linux/cache.h>
+#include <linux/config.h>
+#include <linux/threads.h>
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#define current_text_addr() ({ void *pc; __asm__("movl $1f,%0\n1:":"=g" (pc));
pc; })
+
+/*
+ * CPU type and hardware bug flags. Kept separately for each CPU.
+ * Members of this structure are referenced in head.S, so think twice
+ * before touching them. [mj]
+ */
+
+struct cpuinfo_x86 {
+ __u8 x86; /* CPU family */
+ __u8 x86_vendor; /* CPU vendor */
+ __u8 x86_model;
+ __u8 x86_mask;
+ char wp_works_ok; /* It doesn't on 386's */
+ char hlt_works_ok; /* Problems on some 486Dx4's and old 386's */
+ char hard_math;
+ char rfu;
+ int cpuid_level; /* Maximum supported CPUID level, -1=no
CPUID */
+ __u32 x86_capability[NCAPINTS];
+ char x86_vendor_id[16];
+ char x86_model_id[64];
+ int x86_cache_size; /* in KB - valid for CPUS which support this
+ call */
+ int fdiv_bug;
+ int f00f_bug;
+ int coma_bug;
+ unsigned long loops_per_jiffy;
+ unsigned long *pgd_quick;
+ unsigned long *pmd_quick;
+ unsigned long *pte_quick;
+ unsigned long pgtable_cache_sz;
+} __attribute__((__aligned__(SMP_CACHE_BYTES)));
+
+#define X86_VENDOR_INTEL 0
+#define X86_VENDOR_CYRIX 1
+#define X86_VENDOR_AMD 2
+#define X86_VENDOR_UMC 3
+#define X86_VENDOR_NEXGEN 4
+#define X86_VENDOR_CENTAUR 5
+#define X86_VENDOR_RISE 6
+#define X86_VENDOR_TRANSMETA 7
+#define X86_VENDOR_NSC 8
+#define X86_VENDOR_SIS 9
+#define X86_VENDOR_UNKNOWN 0xff
+
+/*
+ * capabilities of CPUs
+ */
+
+extern struct cpuinfo_x86 boot_cpu_data;
+extern struct tss_struct init_tss[NR_CPUS];
+
+#ifdef CONFIG_SMP
+extern struct cpuinfo_x86 cpu_data[];
+#define current_cpu_data cpu_data[smp_processor_id()]
+#else
+#define cpu_data (&boot_cpu_data)
+#define current_cpu_data boot_cpu_data
+#endif
+
+extern char ignore_irq13;
+
+extern void identify_cpu(struct cpuinfo_x86 *);
+extern void print_cpu_info(struct cpuinfo_x86 *);
+
+/*
+ * EFLAGS bits
+ */
+#define X86_EFLAGS_CF 0x00000001 /* Carry Flag */
+#define X86_EFLAGS_PF 0x00000004 /* Parity Flag */
+#define X86_EFLAGS_AF 0x00000010 /* Auxillary carry Flag */
+#define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */
+#define X86_EFLAGS_SF 0x00000080 /* Sign Flag */
+#define X86_EFLAGS_TF 0x00000100 /* Trap Flag */
+#define X86_EFLAGS_IF 0x00000200 /* Interrupt Flag */
+#define X86_EFLAGS_DF 0x00000400 /* Direction Flag */
+#define X86_EFLAGS_OF 0x00000800 /* Overflow Flag */
+#define X86_EFLAGS_IOPL 0x00003000 /* IOPL mask */
+#define X86_EFLAGS_NT 0x00004000 /* Nested Task */
+#define X86_EFLAGS_RF 0x00010000 /* Resume Flag */
+#define X86_EFLAGS_VM 0x00020000 /* Virtual Mode */
+#define X86_EFLAGS_AC 0x00040000 /* Alignment Check */
+#define X86_EFLAGS_VIF 0x00080000 /* Virtual Interrupt Flag */
+#define X86_EFLAGS_VIP 0x00100000 /* Virtual Interrupt Pending */
+#define X86_EFLAGS_ID 0x00200000 /* CPUID detection flag */
+
+/*
+ * Generic CPUID function
+ */
+static inline void cpuid(int op, int *eax, int *ebx, int *ecx, int *edx)
+{
+ __asm__("cpuid"
+ : "=a" (*eax),
+ "=b" (*ebx),
+ "=c" (*ecx),
+ "=d" (*edx)
+ : "0" (op));
+}
+
+/*
+ * CPUID functions returning a single datum
+ */
+static inline unsigned int cpuid_eax(unsigned int op)
+{
+ unsigned int eax;
+
+ __asm__("cpuid"
+ : "=a" (eax)
+ : "0" (op)
+ : "bx", "cx", "dx");
+ return eax;
+}
+static inline unsigned int cpuid_ebx(unsigned int op)
+{
+ unsigned int eax, ebx;
+
+ __asm__("cpuid"
+ : "=a" (eax), "=b" (ebx)
+ : "0" (op)
+ : "cx", "dx" );
+ return ebx;
+}
+static inline unsigned int cpuid_ecx(unsigned int op)
+{
+ unsigned int eax, ecx;
+
+ __asm__("cpuid"
+ : "=a" (eax), "=c" (ecx)
+ : "0" (op)
+ : "bx", "dx" );
+ return ecx;
+}
+static inline unsigned int cpuid_edx(unsigned int op)
+{
+ unsigned int eax, edx;
+
+ __asm__("cpuid"
+ : "=a" (eax), "=d" (edx)
+ : "0" (op)
+ : "bx", "cx");
+ return edx;
+}
+
+/*
+ * Intel CPU features in CR4
+ */
+#define X86_CR4_VME 0x0001 /* enable vm86 extensions */
+#define X86_CR4_PVI 0x0002 /* virtual interrupts flag enable */
+#define X86_CR4_TSD 0x0004 /* disable time stamp at ipl 3 */
+#define X86_CR4_DE 0x0008 /* enable debugging extensions */
+#define X86_CR4_PSE 0x0010 /* enable page size extensions */
+#define X86_CR4_PAE 0x0020 /* enable physical address extensions */
+#define X86_CR4_MCE 0x0040 /* Machine check enable */
+#define X86_CR4_PGE 0x0080 /* enable global pages */
+#define X86_CR4_PCE 0x0100 /* enable performance counters at ipl 3
*/
+#define X86_CR4_OSFXSR 0x0200 /* enable fast FPU save and restore */
+#define X86_CR4_OSXMMEXCPT 0x0400 /* enable unmasked SSE exceptions */
+
+#define load_cr3(pgdir) \
+ asm volatile("movl %0,%%cr3": :"r" (__pa(pgdir)));
+
+extern unsigned long mmu_cr4_features;
+
+#include <asm/hypervisor.h>
+
+static inline void set_in_cr4 (unsigned long mask)
+{
+ BUG();
+}
+
+static inline void clear_in_cr4 (unsigned long mask)
+{
+ BUG();
+}
+
+/*
+ * Cyrix CPU configuration register indexes
+ */
+#define CX86_CCR0 0xc0
+#define CX86_CCR1 0xc1
+#define CX86_CCR2 0xc2
+#define CX86_CCR3 0xc3
+#define CX86_CCR4 0xe8
+#define CX86_CCR5 0xe9
+#define CX86_CCR6 0xea
+#define CX86_CCR7 0xeb
+#define CX86_DIR0 0xfe
+#define CX86_DIR1 0xff
+#define CX86_ARR_BASE 0xc4
+#define CX86_RCR_BASE 0xdc
+
+/*
+ * Cyrix CPU indexed register access macros
+ */
+
+#define getCx86(reg) ({ outb((reg), 0x22); inb(0x23); })
+
+#define setCx86(reg, data) do { \
+ outb((reg), 0x22); \
+ outb((data), 0x23); \
+} while (0)
+
+/*
+ * Bus types (default is ISA, but people can check others with these..)
+ */
+#ifdef CONFIG_EISA
+extern int EISA_bus;
+#else
+#define EISA_bus (0)
+#endif
+extern int MCA_bus;
+
+/* from system description table in BIOS. Mostly for MCA use, but
+others may find it useful. */
+extern unsigned int machine_id;
+extern unsigned int machine_submodel_id;
+extern unsigned int BIOS_revision;
+extern unsigned int mca_pentium_flag;
+
+/*
+ * User space process size: 3GB (default).
+ */
+#define TASK_SIZE (PAGE_OFFSET)
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE (TASK_SIZE / 3)
+
+/*
+ * Size of io_bitmap in longwords: 32 is ports 0-0x3ff.
+ */
+#define IO_BITMAP_SIZE 32
+#define IO_BITMAP_BYTES (IO_BITMAP_SIZE * 4)
+#define IO_BITMAP_OFFSET offsetof(struct tss_struct,io_bitmap)
+#define INVALID_IO_BITMAP_OFFSET 0x8000
+
+struct i387_fsave_struct {
+ long cwd;
+ long swd;
+ long twd;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */
+ long status; /* software status information */
+};
+
+struct i387_fxsave_struct {
+ unsigned short cwd;
+ unsigned short swd;
+ unsigned short twd;
+ unsigned short fop;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long mxcsr;
+ long reserved;
+ long st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */
+ long xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */
+ long padding[56];
+} __attribute__ ((aligned (16)));
+
+struct i387_soft_struct {
+ long cwd;
+ long swd;
+ long twd;
+ long fip;
+ long fcs;
+ long foo;
+ long fos;
+ long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */
+ unsigned char ftop, changed, lookahead, no_update, rm, alimit;
+ struct info *info;
+ unsigned long entry_eip;
+};
+
+union i387_union {
+ struct i387_fsave_struct fsave;
+ struct i387_fxsave_struct fxsave;
+ struct i387_soft_struct soft;
+};
+
+typedef struct {
+ unsigned long seg;
+} mm_segment_t;
+
+struct tss_struct {
+ unsigned short back_link,__blh;
+ unsigned long esp0;
+ unsigned short ss0,__ss0h;
+ unsigned long esp1;
+ unsigned short ss1,__ss1h;
+ unsigned long esp2;
+ unsigned short ss2,__ss2h;
+ unsigned long __cr3;
+ unsigned long eip;
+ unsigned long eflags;
+ unsigned long eax,ecx,edx,ebx;
+ unsigned long esp;
+ unsigned long ebp;
+ unsigned long esi;
+ unsigned long edi;
+ unsigned short es, __esh;
+ unsigned short cs, __csh;
+ unsigned short ss, __ssh;
+ unsigned short ds, __dsh;
+ unsigned short fs, __fsh;
+ unsigned short gs, __gsh;
+ unsigned short ldt, __ldth;
+ unsigned short trace, bitmap;
+ unsigned long io_bitmap[IO_BITMAP_SIZE+1];
+ /*
+ * pads the TSS to be cacheline-aligned (size is 0x100)
+ */
+ unsigned long __cacheline_filler[5];
+};
+
+struct thread_struct {
+ unsigned long esp0;
+ unsigned long eip;
+ unsigned long esp;
+ unsigned long fs;
+ unsigned long gs;
+ unsigned int io_pl;
+/* Hardware debugging registers */
+ unsigned long debugreg[8]; /* %%db0-7 debug registers */
+/* fault info */
+ unsigned long cr2, trap_no, error_code;
+/* floating point info */
+ union i387_union i387;
+/* virtual 86 mode info */
+ struct vm86_struct * vm86_info;
+ unsigned long screen_bitmap;
+ unsigned long v86flags, v86mask, saved_esp0;
+};
+
+#define INIT_THREAD { sizeof(init_stack) + (long) &init_stack, \
+ 0, 0, 0, 0, 0, 0, {0}, 0, 0, 0, {{0}}, 0, 0, 0, 0, 0 }
+
+#define INIT_TSS { \
+ 0,0, /* back_link, __blh */ \
+ sizeof(init_stack) + (long) &init_stack, /* esp0 */ \
+ __KERNEL_DS, 0, /* ss0 */ \
+ 0,0,0,0,0,0, /* stack1, stack2 */ \
+ 0, /* cr3 */ \
+ 0,0, /* eip,eflags */ \
+ 0,0,0,0, /* eax,ecx,edx,ebx */ \
+ 0,0,0,0, /* esp,ebp,esi,edi */ \
+ 0,0,0,0,0,0, /* es,cs,ss */ \
+ 0,0,0,0,0,0, /* ds,fs,gs */ \
+ 0,0, /* ldt */ \
+ 0, INVALID_IO_BITMAP_OFFSET, /* tace, bitmap */ \
+ {~0, } /* ioperm */ \
+}
+
+#define start_thread(regs, new_eip, new_esp) do { \
+ __asm__("movl %0,%%fs ; movl %0,%%gs": :"r" (0)); \
+ set_fs(USER_DS); \
+ regs->xds = __USER_DS; \
+ regs->xes = __USER_DS; \
+ regs->xss = __USER_DS; \
+ regs->xcs = __USER_CS; \
+ regs->eip = new_eip; \
+ regs->esp = new_esp; \
+} while (0)
+
+/* Forward declaration, a strange C thing */
+struct task_struct;
+struct mm_struct;
+
+/* Free all resources held by a thread. */
+extern void release_thread(struct task_struct *);
+/*
+ * create a kernel thread without removing it from tasklists
+ */
+extern int arch_kernel_thread(int (*fn)(void *), void * arg, unsigned long
flags);
+
+/* Copy and release all segment info associated with a VM
+ * Unusable due to lack of error handling, use {init_new,destroy}_context
+ * instead.
+ */
+static inline void copy_segments(struct task_struct *p, struct mm_struct * mm)
{ }
+static inline void release_segments(struct mm_struct * mm) { }
+
+/*
+ * Return saved PC of a blocked thread.
+ */
+static inline unsigned long thread_saved_pc(struct thread_struct *t)
+{
+ return ((unsigned long *)t->esp)[3];
+}
+
+unsigned long get_wchan(struct task_struct *p);
+#define KSTK_EIP(tsk) (((unsigned long *)(4096+(unsigned long)(tsk)))[1019])
+#define KSTK_ESP(tsk) (((unsigned long *)(4096+(unsigned long)(tsk)))[1022])
+
+#define THREAD_SIZE (2*PAGE_SIZE)
+#define alloc_task_struct() ((struct task_struct *)
__get_free_pages(GFP_KERNEL,1))
+#define free_task_struct(p) free_pages((unsigned long) (p), 1)
+#define get_task_struct(tsk) atomic_inc(&virt_to_page(tsk)->count)
+
+#define init_task (init_task_union.task)
+#define init_stack (init_task_union.stack)
+
+struct microcode {
+ unsigned int hdrver;
+ unsigned int rev;
+ unsigned int date;
+ unsigned int sig;
+ unsigned int cksum;
+ unsigned int ldrver;
+ unsigned int pf;
+ unsigned int reserved[5];
+ unsigned int bits[500];
+};
+
+/* '6' because it used to be for P6 only (but now covers Pentium 4 as well) */
+#define MICROCODE_IOCFREE _IO('6',0)
+
+/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
+static inline void rep_nop(void)
+{
+ __asm__ __volatile__("rep;nop" ::: "memory");
+}
+
+#define cpu_relax() rep_nop()
+
+/* Prefetch instructions for Pentium III and AMD Athlon */
+#if defined(CONFIG_MPENTIUMIII) || defined (CONFIG_MPENTIUM4)
+
+#define ARCH_HAS_PREFETCH
+extern inline void prefetch(const void *x)
+{
+ __asm__ __volatile__ ("prefetchnta (%0)" : : "r"(x));
+}
+
+#elif CONFIG_X86_USE_3DNOW
+
+#define ARCH_HAS_PREFETCH
+#define ARCH_HAS_PREFETCHW
+#define ARCH_HAS_SPINLOCK_PREFETCH
+
+extern inline void prefetch(const void *x)
+{
+ __asm__ __volatile__ ("prefetch (%0)" : : "r"(x));
+}
+
+extern inline void prefetchw(const void *x)
+{
+ __asm__ __volatile__ ("prefetchw (%0)" : : "r"(x));
+}
+#define spin_lock_prefetch(x) prefetchw(x)
+
+#endif
+
+#endif /* __ASM_I386_PROCESSOR_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/smp.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/smp.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,624 @@
+/*
+ * Intel SMP support routines.
+ *
+ * (c) 1995 Alan Cox, Building #3 <alan@xxxxxxxxxx>
+ * (c) 1998-99, 2000 Ingo Molnar <mingo@xxxxxxxxxx>
+ *
+ * This code is released under the GNU General Public License version 2 or
+ * later.
+ */
+
+#include <linux/init.h>
+
+#include <linux/mm.h>
+#include <linux/irq.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/smp_lock.h>
+#include <linux/kernel_stat.h>
+#include <linux/mc146818rtc.h>
+#include <linux/cache.h>
+#include <linux/interrupt.h>
+#include <linux/cpu.h>
+
+#include <asm/mtrr.h>
+#include <asm/tlbflush.h>
+#if 0
+#include <mach_apic.h>
+#endif
+#include <asm-xen/evtchn.h>
+
+#define xxprint(msg) HYPERVISOR_console_io(CONSOLEIO_write, strlen(msg), msg)
+
+/*
+ * Some notes on x86 processor bugs affecting SMP operation:
+ *
+ * Pentium, Pentium Pro, II, III (and all CPUs) have bugs.
+ * The Linux implications for SMP are handled as follows:
+ *
+ * Pentium III / [Xeon]
+ * None of the E1AP-E3AP errata are visible to the user.
+ *
+ * E1AP. see PII A1AP
+ * E2AP. see PII A2AP
+ * E3AP. see PII A3AP
+ *
+ * Pentium II / [Xeon]
+ * None of the A1AP-A3AP errata are visible to the user.
+ *
+ * A1AP. see PPro 1AP
+ * A2AP. see PPro 2AP
+ * A3AP. see PPro 7AP
+ *
+ * Pentium Pro
+ * None of 1AP-9AP errata are visible to the normal user,
+ * except occasional delivery of 'spurious interrupt' as trap #15.
+ * This is very rare and a non-problem.
+ *
+ * 1AP. Linux maps APIC as non-cacheable
+ * 2AP. worked around in hardware
+ * 3AP. fixed in C0 and above steppings microcode update.
+ * Linux does not use excessive STARTUP_IPIs.
+ * 4AP. worked around in hardware
+ * 5AP. symmetric IO mode (normal Linux operation) not affected.
+ * 'noapic' mode has vector 0xf filled out properly.
+ * 6AP. 'noapic' mode might be affected - fixed in later steppings
+ * 7AP. We do not assume writes to the LVT deassering IRQs
+ * 8AP. We do not enable low power mode (deep sleep) during MP bootup
+ * 9AP. We do not use mixed mode
+ *
+ * Pentium
+ * There is a marginal case where REP MOVS on 100MHz SMP
+ * machines with B stepping processors can fail. XXX should provide
+ * an L1cache=Writethrough or L1cache=off option.
+ *
+ * B stepping CPUs may hang. There are hardware work arounds
+ * for this. We warn about it in case your board doesn't have the work
+ * arounds. Basically thats so I can tell anyone with a B stepping
+ * CPU and SMP problems "tough".
+ *
+ * Specific items [From Pentium Processor Specification Update]
+ *
+ * 1AP. Linux doesn't use remote read
+ * 2AP. Linux doesn't trust APIC errors
+ * 3AP. We work around this
+ * 4AP. Linux never generated 3 interrupts of the same priority
+ * to cause a lost local interrupt.
+ * 5AP. Remote read is never used
+ * 6AP. not affected - worked around in hardware
+ * 7AP. not affected - worked around in hardware
+ * 8AP. worked around in hardware - we get explicit CS errors if not
+ * 9AP. only 'noapic' mode affected. Might generate spurious
+ * interrupts, we log only the first one and count the
+ * rest silently.
+ * 10AP. not affected - worked around in hardware
+ * 11AP. Linux reads the APIC between writes to avoid this, as per
+ * the documentation. Make sure you preserve this as it affects
+ * the C stepping chips too.
+ * 12AP. not affected - worked around in hardware
+ * 13AP. not affected - worked around in hardware
+ * 14AP. we always deassert INIT during bootup
+ * 15AP. not affected - worked around in hardware
+ * 16AP. not affected - worked around in hardware
+ * 17AP. not affected - worked around in hardware
+ * 18AP. not affected - worked around in hardware
+ * 19AP. not affected - worked around in BIOS
+ *
+ * If this sounds worrying believe me these bugs are either ___RARE___,
+ * or are signal timing bugs worked around in hardware and there's
+ * about nothing of note with C stepping upwards.
+ */
+
+DEFINE_PER_CPU(struct tlb_state, cpu_tlbstate) ____cacheline_aligned = {
&init_mm, 0, };
+
+/*
+ * the following functions deal with sending IPIs between CPUs.
+ *
+ * We use 'broadcast', CPU->CPU IPIs and self-IPIs too.
+ */
+
+static inline int __prepare_ICR (unsigned int shortcut, int vector)
+{
+ return APIC_DM_FIXED | shortcut | vector | APIC_DEST_LOGICAL;
+}
+
+static inline int __prepare_ICR2 (unsigned int mask)
+{
+ return SET_APIC_DEST_FIELD(mask);
+}
+
+DECLARE_PER_CPU(int, ipi_to_evtchn[NR_IPIS]);
+
+static inline void __send_IPI_one(unsigned int cpu, int vector)
+{
+ unsigned int evtchn;
+
+ evtchn = per_cpu(ipi_to_evtchn, cpu)[vector];
+ // printk("send_IPI_mask_bitmask cpu %d vector %d evtchn %d\n", cpu,
vector, evtchn);
+ if (evtchn) {
+#if 0
+ shared_info_t *s = HYPERVISOR_shared_info;
+ while (synch_test_bit(evtchn, &s->evtchn_pending[0]) ||
+ synch_test_bit(evtchn, &s->evtchn_mask[0]))
+ ;
+#endif
+ notify_via_evtchn(evtchn);
+ } else
+ printk("send_IPI to unbound port %d/%d",
+ cpu, vector);
+}
+
+void __send_IPI_shortcut(unsigned int shortcut, int vector)
+{
+ int cpu;
+
+ switch (shortcut) {
+ case APIC_DEST_SELF:
+ __send_IPI_one(smp_processor_id(), vector);
+ break;
+ case APIC_DEST_ALLBUT:
+ for (cpu = 0; cpu < NR_CPUS; ++cpu) {
+ if (cpu == smp_processor_id())
+ continue;
+ if (cpu_isset(cpu, cpu_online_map)) {
+ __send_IPI_one(cpu, vector);
+ }
+ }
+ break;
+ default:
+ printk("XXXXXX __send_IPI_shortcut %08x vector %d\n", shortcut,
+ vector);
+ break;
+ }
+}
+
+void fastcall send_IPI_self(int vector)
+{
+ __send_IPI_shortcut(APIC_DEST_SELF, vector);
+}
+
+/*
+ * This is only used on smaller machines.
+ */
+void send_IPI_mask_bitmask(cpumask_t mask, int vector)
+{
+ unsigned long flags;
+ unsigned int cpu;
+
+ local_irq_save(flags);
+ WARN_ON(cpus_addr(mask)[0] & ~cpus_addr(cpu_online_map)[0]);
+
+ for (cpu = 0; cpu < NR_CPUS; ++cpu) {
+ if (cpu_isset(cpu, mask)) {
+ __send_IPI_one(cpu, vector);
+ }
+ }
+
+ local_irq_restore(flags);
+}
+
+inline void send_IPI_mask_sequence(cpumask_t mask, int vector)
+{
+
+ send_IPI_mask_bitmask(mask, vector);
+}
+
+#include <mach_ipi.h> /* must come after the send_IPI functions above for
inlining */
+
+#if 0 /* XEN */
+/*
+ * Smarter SMP flushing macros.
+ * c/o Linus Torvalds.
+ *
+ * These mean you can really definitely utterly forget about
+ * writing to user space from interrupts. (Its not allowed anyway).
+ *
+ * Optimizations Manfred Spraul <manfred@xxxxxxxxxxxxxxxx>
+ */
+
+static cpumask_t flush_cpumask;
+static struct mm_struct * flush_mm;
+static unsigned long flush_va;
+static DEFINE_SPINLOCK(tlbstate_lock);
+#define FLUSH_ALL 0xffffffff
+
+/*
+ * We cannot call mmdrop() because we are in interrupt context,
+ * instead update mm->cpu_vm_mask.
+ *
+ * We need to reload %cr3 since the page tables may be going
+ * away from under us..
+ */
+static inline void leave_mm (unsigned long cpu)
+{
+ if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK)
+ BUG();
+ cpu_clear(cpu, per_cpu(cpu_tlbstate, cpu).active_mm->cpu_vm_mask);
+ load_cr3(swapper_pg_dir);
+}
+
+/*
+ *
+ * The flush IPI assumes that a thread switch happens in this order:
+ * [cpu0: the cpu that switches]
+ * 1) switch_mm() either 1a) or 1b)
+ * 1a) thread switch to a different mm
+ * 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask);
+ * Stop ipi delivery for the old mm. This is not synchronized with
+ * the other cpus, but smp_invalidate_interrupt ignore flush ipis
+ * for the wrong mm, and in the worst case we perform a superflous
+ * tlb flush.
+ * 1a2) set cpu_tlbstate to TLBSTATE_OK
+ * Now the smp_invalidate_interrupt won't call leave_mm if cpu0
+ * was in lazy tlb mode.
+ * 1a3) update cpu_tlbstate[].active_mm
+ * Now cpu0 accepts tlb flushes for the new mm.
+ * 1a4) cpu_set(cpu, new_mm->cpu_vm_mask);
+ * Now the other cpus will send tlb flush ipis.
+ * 1a4) change cr3.
+ * 1b) thread switch without mm change
+ * cpu_tlbstate[].active_mm is correct, cpu0 already handles
+ * flush ipis.
+ * 1b1) set cpu_tlbstate to TLBSTATE_OK
+ * 1b2) test_and_set the cpu bit in cpu_vm_mask.
+ * Atomically set the bit [other cpus will start sending flush ipis],
+ * and test the bit.
+ * 1b3) if the bit was 0: leave_mm was called, flush the tlb.
+ * 2) switch %%esp, ie current
+ *
+ * The interrupt must handle 2 special cases:
+ * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm.
+ * - the cpu performs speculative tlb reads, i.e. even if the cpu only
+ * runs in kernel space, the cpu could load tlb entries for user space
+ * pages.
+ *
+ * The good news is that cpu_tlbstate is local to each cpu, no
+ * write/read ordering problems.
+ */
+
+/*
+ * TLB flush IPI:
+ *
+ * 1) Flush the tlb entries if the cpu uses the mm that's being flushed.
+ * 2) Leave the mm if we are in the lazy tlb mode.
+ */
+
+irqreturn_t smp_invalidate_interrupt(int irq, void *dev_id,
+ struct pt_regs *regs)
+{
+ unsigned long cpu;
+
+ cpu = get_cpu();
+
+ if (!cpu_isset(cpu, flush_cpumask))
+ goto out;
+ /*
+ * This was a BUG() but until someone can quote me the
+ * line from the intel manual that guarantees an IPI to
+ * multiple CPUs is retried _only_ on the erroring CPUs
+ * its staying as a return
+ *
+ * BUG();
+ */
+
+ if (flush_mm == per_cpu(cpu_tlbstate, cpu).active_mm) {
+ if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) {
+ if (flush_va == FLUSH_ALL)
+ local_flush_tlb();
+ else
+ __flush_tlb_one(flush_va);
+ } else
+ leave_mm(cpu);
+ }
+ smp_mb__before_clear_bit();
+ cpu_clear(cpu, flush_cpumask);
+ smp_mb__after_clear_bit();
+out:
+ put_cpu_no_resched();
+
+ return IRQ_HANDLED;
+}
+
+static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
+ unsigned long va)
+{
+ /*
+ * A couple of (to be removed) sanity checks:
+ *
+ * - current CPU must not be in mask
+ * - mask must exist :)
+ */
+ BUG_ON(cpus_empty(cpumask));
+ BUG_ON(cpu_isset(smp_processor_id(), cpumask));
+ BUG_ON(!mm);
+
+ /* If a CPU which we ran on has gone down, OK. */
+ cpus_and(cpumask, cpumask, cpu_online_map);
+ if (cpus_empty(cpumask))
+ return;
+
+ /*
+ * i'm not happy about this global shared spinlock in the
+ * MM hot path, but we'll see how contended it is.
+ * Temporarily this turns IRQs off, so that lockups are
+ * detected by the NMI watchdog.
+ */
+ spin_lock(&tlbstate_lock);
+
+ flush_mm = mm;
+ flush_va = va;
+#if NR_CPUS <= BITS_PER_LONG
+ atomic_set_mask(cpumask, &flush_cpumask);
+#else
+ {
+ int k;
+ unsigned long *flush_mask = (unsigned long *)&flush_cpumask;
+ unsigned long *cpu_mask = (unsigned long *)&cpumask;
+ for (k = 0; k < BITS_TO_LONGS(NR_CPUS); ++k)
+ atomic_set_mask(cpu_mask[k], &flush_mask[k]);
+ }
+#endif
+ /*
+ * We have to send the IPI only to
+ * CPUs affected.
+ */
+ send_IPI_mask(cpumask, INVALIDATE_TLB_VECTOR);
+
+ while (!cpus_empty(flush_cpumask))
+ /* nothing. lockup detection does not belong here */
+ mb();
+
+ flush_mm = NULL;
+ flush_va = 0;
+ spin_unlock(&tlbstate_lock);
+}
+
+void flush_tlb_current_task(void)
+{
+ struct mm_struct *mm = current->mm;
+ cpumask_t cpu_mask;
+
+ preempt_disable();
+ cpu_mask = mm->cpu_vm_mask;
+ cpu_clear(smp_processor_id(), cpu_mask);
+
+ local_flush_tlb();
+ if (!cpus_empty(cpu_mask))
+ flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
+ preempt_enable();
+}
+
+void flush_tlb_mm (struct mm_struct * mm)
+{
+ cpumask_t cpu_mask;
+
+ preempt_disable();
+ cpu_mask = mm->cpu_vm_mask;
+ cpu_clear(smp_processor_id(), cpu_mask);
+
+ if (current->active_mm == mm) {
+ if (current->mm)
+ local_flush_tlb();
+ else
+ leave_mm(smp_processor_id());
+ }
+ if (!cpus_empty(cpu_mask))
+ flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
+
+ preempt_enable();
+}
+
+void flush_tlb_page(struct vm_area_struct * vma, unsigned long va)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ cpumask_t cpu_mask;
+
+ preempt_disable();
+ cpu_mask = mm->cpu_vm_mask;
+ cpu_clear(smp_processor_id(), cpu_mask);
+
+ if (current->active_mm == mm) {
+ if(current->mm)
+ __flush_tlb_one(va);
+ else
+ leave_mm(smp_processor_id());
+ }
+
+ if (!cpus_empty(cpu_mask))
+ flush_tlb_others(cpu_mask, mm, va);
+
+ preempt_enable();
+}
+
+static void do_flush_tlb_all(void* info)
+{
+ unsigned long cpu = smp_processor_id();
+
+ __flush_tlb_all();
+ if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_LAZY)
+ leave_mm(cpu);
+}
+
+void flush_tlb_all(void)
+{
+ on_each_cpu(do_flush_tlb_all, NULL, 1, 1);
+}
+
+#else
+
+irqreturn_t smp_invalidate_interrupt(int irq, void *dev_id,
+ struct pt_regs *regs)
+{ return 0; }
+void flush_tlb_current_task(void)
+{ xen_tlb_flush_mask(¤t->mm->cpu_vm_mask); }
+void flush_tlb_mm(struct mm_struct * mm)
+{ xen_tlb_flush_mask(&mm->cpu_vm_mask); }
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
+{ xen_invlpg_mask(&vma->vm_mm->cpu_vm_mask, va); }
+void flush_tlb_all(void)
+{ xen_tlb_flush_all(); }
+
+#endif /* XEN */
+
+/*
+ * this function sends a 'reschedule' IPI to another CPU.
+ * it goes straight through and wastes no time serializing
+ * anything. Worst case is that we lose a reschedule ...
+ */
+void smp_send_reschedule(int cpu)
+{
+ WARN_ON(cpu_is_offline(cpu));
+ send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR);
+}
+
+/*
+ * Structure and data for smp_call_function(). This is designed to minimise
+ * static memory requirements. It also looks cleaner.
+ */
+static DEFINE_SPINLOCK(call_lock);
+
+struct call_data_struct {
+ void (*func) (void *info);
+ void *info;
+ atomic_t started;
+ atomic_t finished;
+ int wait;
+};
+
+static struct call_data_struct * call_data;
+
+/*
+ * this function sends a 'generic call function' IPI to all other CPUs
+ * in the system.
+ */
+
+int smp_call_function (void (*func) (void *info), void *info, int nonatomic,
+ int wait)
+/*
+ * [SUMMARY] Run a function on all other CPUs.
+ * <func> The function to run. This must be fast and non-blocking.
+ * <info> An arbitrary pointer to pass to the function.
+ * <nonatomic> currently unused.
+ * <wait> If true, wait (atomically) until function has completed on other
CPUs.
+ * [RETURNS] 0 on success, else a negative status code. Does not return until
+ * remote CPUs are nearly ready to execute <<func>> or are or have executed.
+ *
+ * You must not call this function with disabled interrupts or from a
+ * hardware interrupt handler or from a bottom half handler.
+ */
+{
+ struct call_data_struct data;
+ int cpus;
+
+ /* Holding any lock stops cpus from going down. */
+ spin_lock(&call_lock);
+ cpus = num_online_cpus()-1;
+
+ if (!cpus) {
+ spin_unlock(&call_lock);
+ return 0;
+ }
+
+ /* Can deadlock when called with interrupts disabled */
+ WARN_ON(irqs_disabled());
+
+ data.func = func;
+ data.info = info;
+ atomic_set(&data.started, 0);
+ data.wait = wait;
+ if (wait)
+ atomic_set(&data.finished, 0);
+
+ call_data = &data;
+ mb();
+
+ /* Send a message to all other CPUs and wait for them to respond */
+ send_IPI_allbutself(CALL_FUNCTION_VECTOR);
+
+ /* Wait for response */
+ while (atomic_read(&data.started) != cpus)
+ barrier();
+
+ if (wait)
+ while (atomic_read(&data.finished) != cpus)
+ barrier();
+ spin_unlock(&call_lock);
+
+ return 0;
+}
+
+static void stop_this_cpu (void * dummy)
+{
+ /*
+ * Remove this CPU:
+ */
+ cpu_clear(smp_processor_id(), cpu_online_map);
+ local_irq_disable();
+#if 1
+ xxprint("stop_this_cpu disable_local_APIC\n");
+#else
+ disable_local_APIC();
+#endif
+ if (cpu_data[smp_processor_id()].hlt_works_ok)
+ for(;;) __asm__("hlt");
+ for (;;);
+}
+
+/*
+ * this function calls the 'stop' function on all other CPUs in the system.
+ */
+
+void smp_send_stop(void)
+{
+ smp_call_function(stop_this_cpu, NULL, 1, 0);
+
+ local_irq_disable();
+#if 1
+ xxprint("smp_send_stop disable_local_APIC\n");
+#else
+ disable_local_APIC();
+#endif
+ local_irq_enable();
+}
+
+/*
+ * Reschedule call back. Nothing to do,
+ * all the work is done automatically when
+ * we return from the interrupt.
+ */
+irqreturn_t smp_reschedule_interrupt(int irq, void *dev_id,
+ struct pt_regs *regs)
+{
+
+ return IRQ_HANDLED;
+}
+
+#include <linux/kallsyms.h>
+irqreturn_t smp_call_function_interrupt(int irq, void *dev_id,
+ struct pt_regs *regs)
+{
+ void (*func) (void *info) = call_data->func;
+ void *info = call_data->info;
+ int wait = call_data->wait;
+
+ /*
+ * Notify initiating CPU that I've grabbed the data and am
+ * about to execute the function
+ */
+ mb();
+ atomic_inc(&call_data->started);
+ /*
+ * At this point the info structure may be out of scope unless wait==1
+ */
+ irq_enter();
+ (*func)(info);
+ irq_exit();
+
+ if (wait) {
+ mb();
+ atomic_inc(&call_data->finished);
+ }
+
+ return IRQ_HANDLED;
+}
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/xenbus.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/xenbus.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,143 @@
+#ifndef _ASM_XEN_XENBUS_H
+#define _ASM_XEN_XENBUS_H
+/******************************************************************************
+ * xenbus.h
+ *
+ * Talks to Xen Store to figure out what devices we have.
+ *
+ * Copyright (C) 2005 Rusty Russell, IBM Corporation
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+#include <linux/device.h>
+#include <asm/semaphore.h>
+
+/* A xenbus device. */
+struct xenbus_device {
+ char *devicetype;
+ char *subtype;
+ char *nodename;
+ int id;
+ struct device dev;
+};
+
+static inline struct xenbus_device *to_xenbus_device(struct device *dev)
+{
+ return container_of(dev, struct xenbus_device, dev);
+}
+
+struct xenbus_device_id
+{
+ /* .../device/<device_type>/<identifier> */
+ char devicetype[32]; /* General class of device. */
+ char subtype[32]; /* Contents of "subtype" for this device */
+};
+
+/* A xenbus driver. */
+struct xenbus_driver {
+ char *name;
+ struct module *owner;
+ const struct xenbus_device_id *ids;
+ /* Called when xenstore is connected. */
+ int (*connect) (struct xenbus_driver * drv);
+
+ int (*probe) (struct xenbus_device * dev, const struct
xenbus_device_id * id);
+ int (*remove) (struct xenbus_device * dev);
+ int (*configure)(struct xenbus_device * dev);
+
+ struct device_driver driver;
+};
+
+struct xenbus_evtchn {
+ unsigned long dom1;
+ unsigned long port1;
+ unsigned long dom2;
+ unsigned long port2;
+};
+
+static inline struct xenbus_driver *to_xenbus_driver(struct device_driver *drv)
+{
+ return container_of(drv, struct xenbus_driver, driver);
+}
+
+int xenbus_register_driver(struct xenbus_driver *drv);
+void xenbus_unregister_driver(struct xenbus_driver *drv);
+
+int xenbus_register_backend(struct xenbus_driver *drv);
+void xenbus_unregister_backend(struct xenbus_driver *drv);
+
+/* Iterator over xenbus devices (frontend). */
+int xenbus_for_each_dev(struct xenbus_device * start, void * data,
+ int (*fn)(struct xenbus_device *, void *));
+
+/* Iterator over xenbus drivers (frontend). */
+int xenbus_for_each_drv(struct xenbus_driver * start, void * data,
+ int (*fn)(struct xenbus_driver *, void *));
+
+/* Iterator over xenbus drivers (backend). */
+int xenbus_for_each_backend(struct xenbus_driver * start, void * data,
+ int (*fn)(struct xenbus_driver *, void *));
+
+/* Caller must hold this lock to call these functions. */
+extern struct semaphore xs_lock;
+
+char **xs_directory(const char *path, unsigned int *num);
+void *xs_read(const char *path, unsigned int *len);
+int xs_write(const char *path,
+ const void *data, unsigned int len, int createflags);
+int xs_mkdir(const char *path);
+int xs_exists(const char *path);
+int xs_mkdirs(const char *path);
+int xs_rm(const char *path);
+int xs_transaction_start(const char *subtree);
+int xs_transaction_end(int abort);
+char *xs_get_domain_path(domid_t domid);
+
+/* Register callback to watch this node. */
+struct xenbus_watch
+{
+ struct list_head list;
+ char *node;
+ unsigned int priority;
+ void (*callback)(struct xenbus_watch *, const char *node);
+};
+
+int register_xenbus_watch(struct xenbus_watch *watch);
+void unregister_xenbus_watch(struct xenbus_watch *watch);
+
+char *xenbus_path(const char *dir, const char *name);
+char *xenbus_read(const char *dir, const char *name, unsigned int *data_n);
+int xenbus_write(const char *dir, const char *name,
+ const char *data, int data_n);
+
+int xenbus_read_string(const char *dir, const char *name, char **val);
+int xenbus_write_string(const char *dir, const char *name, const char *val);
+int xenbus_read_ulong(const char *dir, const char *name, unsigned long *val);
+int xenbus_write_ulong(const char *dir, const char *name, unsigned long val);
+int xenbus_read_long(const char *dir, const char *name, long *val);
+int xenbus_write_long(const char *dir, const char *name, long val);
+int xenbus_read_mac(const char *dir, const char *name, unsigned char mac[6]);
+int xenbus_write_mac(const char *dir, const char *name, const unsigned char
mac[6]);
+int xenbus_read_evtchn(const char *dir, const char *name, struct xenbus_evtchn
*evtchn);
+int xenbus_message(const char *dir, const char *val, ...);
+
+#endif /* _ASM_XEN_XENBUS_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/drivers/balloon/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/drivers/balloon/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,4 @@
+O_TARGET := drv.o
+export-objs := balloon.o
+obj-y := balloon.o
+include $(TOPDIR)/Rules.make
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/mkbuildtree
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/mkbuildtree Fri Jul 15 13:39:50 2005
@@ -0,0 +1,292 @@
+#!/bin/bash
+
+# mkbuildtree <build tree>
+#
+# Creates symbolic links in <build tree> for the sparse tree
+# in the current directory.
+
+# Script to determine the relative path between two directories.
+# Copyright (c) D. J. Hawkey Jr. 2002
+# Fixed for Xen project by K. Fraser in 2003.
+abs_to_rel ()
+{
+ local CWD SRCPATH
+
+ if [ "$1" != "/" -a "${1##*[^/]}" = "/" ]; then
+ SRCPATH=${1%?}
+ else
+ SRCPATH=$1
+ fi
+ if [ "$2" != "/" -a "${2##*[^/]}" = "/" ]; then
+ DESTPATH=${2%?}
+ else
+ DESTPATH=$2
+ fi
+
+ CWD=$PWD
+ [ "${1%%[^/]*}" != "/" ] && cd $1 && SRCPATH=$PWD
+ [ "${2%%[^/]*}" != "/" ] && cd $2 && DESTPATH=$PWD
+ [ "$CWD" != "$PWD" ] && cd $CWD
+
+ BASEPATH=$SRCPATH
+
+ [ "$SRCPATH" = "$DESTPATH" ] && DESTPATH="." && return
+ [ "$SRCPATH" = "/" ] && DESTPATH=${DESTPATH#?} && return
+
+ while [ "$BASEPATH/" != "${DESTPATH%${DESTPATH#$BASEPATH/}}" ]; do
+ BASEPATH=${BASEPATH%/*}
+ done
+
+ SRCPATH=${SRCPATH#$BASEPATH}
+ DESTPATH=${DESTPATH#$BASEPATH}
+ DESTPATH=${DESTPATH#?}
+ while [ -n "$SRCPATH" ]; do
+ SRCPATH=${SRCPATH%/*}
+ DESTPATH="../$DESTPATH"
+ done
+
+ [ -z "$BASEPATH" ] && BASEPATH="/"
+ [ "${DESTPATH##*[^/]}" = "/" ] && DESTPATH=${DESTPATH%?}
+}
+
+# relative_lndir <target_dir>
+# Creates a tree of symlinks in the current working directory that mirror
+# real files in <target_dir>. <target_dir> should be relative to the current
+# working directory. Symlinks in <target_dir> are ignored. Source-control files
+# are ignored.
+relative_lndir ()
+{
+ local SYMLINK_DIR REAL_DIR pref i j
+ SYMLINK_DIR=$PWD
+ REAL_DIR=$1
+ (
+ cd $REAL_DIR
+ for i in `find . -type d | grep -v SCCS`; do
+ [ -d $SYMLINK_DIR/$i ] || mkdir -p $SYMLINK_DIR/$i
+ (
+ cd $i
+ pref=`echo $i | sed -e 's#/[^/]*#../#g' -e 's#^\.##'`
+ for j in `find . -maxdepth 1 -type f -o -type l`; do
+ ln -sf ${pref}${REAL_DIR}/$i/$j ${SYMLINK_DIR}/$i/$j
+ done
+ )
+ done
+ )
+}
+
+[ "$1" == "" ] && { echo "Syntax: $0 <linux tree to xenify>"; exit 1; }
+
+# Get absolute path to the destination directory
+pushd . >/dev/null
+cd ${1} || { echo "cannot cd to ${1}"; exit 1; }
+AD=$PWD
+popd >/dev/null
+
+# Get absolute path to the source directory
+AS=`pwd`
+
+# Get path to source, relative to destination
+abs_to_rel ${AD} ${AS}
+RS=$DESTPATH
+
+# Remove old copies of files and directories at the destination
+for i in `find . -type f -o -type l` ; do rm -f ${AD}/${i#./} ; done
+
+# We now work from the destination directory
+cd ${AD} || { echo "cannot cd to ${AD}"; exit 1; }
+
+# Remove old symlinks
+for i in `find . -type l`; do rm -f $i; done
+
+# Create symlinks of files and directories which exist in the sparse source
+relative_lndir ${RS}
+rm -f mkbuildtree
+
+set ${RS}/../linux-2.6.*-xen-sparse
+[ "$1" == "${RS}/../linux-2.6.*-xen-parse" ] && { echo "no Linux 2.6 sparse
tree at ${RS}/../linux-2.6.*-xen-sparse"; exit 1; }
+LINUX_26="$1"
+
+
+# Create links to the shared definitions of the Xen interfaces.
+rm -rf ${AD}/include/asm-xen/xen-public
+mkdir ${AD}/include/asm-xen/xen-public
+cd ${AD}/include/asm-xen/xen-public
+relative_lndir ../../../${RS}/../xen/include/public
+
+# Create a link to the shared definitions for the control interface
+cd ${AD}/include/asm-xen
+
+## Symlinks for files:
+## - which are identical in the i386 and xen-i386 architecture-dependent
+## subdirectories.
+## - which are identical in the Linux 2.6 and Linux 2.4 ports.
+
+cd ${AD}/include/asm-xen
+ln -sf ../asm-i386/a.out.h
+ln -sf ../asm-i386/apicdef.h
+ln -sf ../asm-i386/apic.h
+ln -sf ../asm-i386/atomic.h
+ln -sf ../asm-i386/bitops.h
+ln -sf ../asm-i386/boot.h
+ln -sf ../asm-i386/byteorder.h
+ln -sf ../asm-i386/cache.h
+ln -sf ../asm-i386/checksum.h
+ln -sf ../asm-i386/cpufeature.h
+ln -sf ../asm-i386/current.h
+ln -sf ../asm-i386/debugreg.h
+ln -sf ../asm-i386/delay.h
+ln -sf ../asm-i386/div64.h
+ln -sf ../asm-i386/dma.h
+ln -sf ../asm-i386/elf.h
+ln -sf ../asm-i386/errno.h
+ln -sf ../asm-i386/fcntl.h
+ln -sf ../asm-i386/floppy.h
+ln -sf ../asm-i386/hardirq.h
+ln -sf ../asm-i386/hdreg.h
+ln -sf ../asm-i386/i387.h
+ln -sf ../asm-i386/ide.h
+ln -sf ../asm-i386/init.h
+ln -sf ../asm-i386/io_apic.h
+ln -sf ../asm-i386/ioctl.h
+ln -sf ../asm-i386/ioctls.h
+ln -sf ../asm-i386/ipcbuf.h
+ln -sf ../asm-i386/ipc.h
+ln -sf ../asm-i386/kmap_types.h
+ln -sf ../asm-i386/ldt.h
+ln -sf ../asm-i386/linux_logo.h
+ln -sf ../asm-i386/locks.h
+ln -sf ../asm-i386/math_emu.h
+ln -sf ../asm-i386/mc146818rtc.h
+ln -sf ../asm-i386/mca_dma.h
+ln -sf ../asm-i386/mman.h
+ln -sf ../asm-i386/mmu.h
+ln -sf ../asm-i386/mmx.h
+ln -sf ../asm-i386/mpspec.h
+ln -sf ../asm-i386/msgbuf.h
+ln -sf ../asm-i386/msr.h
+ln -sf ../asm-i386/mtrr.h
+ln -sf ../asm-i386/namei.h
+ln -sf ../asm-i386/param.h
+ln -sf ../asm-i386/parport.h
+ln -sf ../asm-i386/pgtable-3level.h
+ln -sf ../asm-i386/poll.h
+ln -sf ../asm-i386/posix_types.h
+ln -sf ../asm-i386/ptrace.h
+ln -sf ../asm-i386/resource.h
+ln -sf ../asm-i386/rwlock.h
+ln -sf ../asm-i386/rwsem.h
+ln -sf ../asm-i386/scatterlist.h
+ln -sf ../asm-i386/semaphore.h
+ln -sf ../asm-i386/sembuf.h
+ln -sf ../asm-i386/serial.h
+ln -sf ../asm-i386/setup.h
+ln -sf ../asm-i386/shmbuf.h
+ln -sf ../asm-i386/shmparam.h
+ln -sf ../asm-i386/sigcontext.h
+ln -sf ../asm-i386/siginfo.h
+ln -sf ../asm-i386/signal.h
+ln -sf ../asm-i386/smplock.h
+ln -sf ../asm-i386/socket.h
+ln -sf ../asm-i386/sockios.h
+ln -sf ../asm-i386/softirq.h
+ln -sf ../asm-i386/spinlock.h
+ln -sf ../asm-i386/statfs.h
+ln -sf ../asm-i386/stat.h
+ln -sf ../asm-i386/string-486.h
+ln -sf ../asm-i386/string.h
+ln -sf ../asm-i386/termbits.h
+ln -sf ../asm-i386/termios.h
+ln -sf ../asm-i386/timex.h
+ln -sf ../asm-i386/tlb.h
+ln -sf ../asm-i386/types.h
+ln -sf ../asm-i386/uaccess.h
+ln -sf ../asm-i386/ucontext.h
+ln -sf ../asm-i386/unaligned.h
+ln -sf ../asm-i386/unistd.h
+ln -sf ../asm-i386/user.h
+ln -sf ../asm-i386/vm86.h
+ln -sf ../../${LINUX_26}/include/asm-xen/balloon.h
+ln -sf ../../${LINUX_26}/include/asm-xen/ctrl_if.h
+ln -sf ../../${LINUX_26}/include/asm-xen/evtchn.h
+ln -sf ../../${LINUX_26}/include/asm-xen/gnttab.h
+ln -sf ../../${LINUX_26}/include/asm-xen/hypervisor.h
+ln -sf ../../${LINUX_26}/include/asm-xen/xen_proc.h
+ln -sf ../../${LINUX_26}/include/asm-xen/asm-i386/synch_bitops.h
+ln -sf ../../${LINUX_26}/include/asm-xen/asm-i386/hypercall.h
+
+mkdir -p linux-public && cd linux-public
+ln -sf ../../../${LINUX_26}/include/asm-xen/linux-public/privcmd.h
+ln -sf ../../../${LINUX_26}/include/asm-xen/linux-public/suspend.h
+
+cd ${AD}/arch/xen/kernel
+ln -sf ../../i386/kernel/i387.c
+ln -sf ../../i386/kernel/init_task.c
+ln -sf ../../i386/kernel/pci-i386.c
+ln -sf ../../i386/kernel/pci-i386.h
+ln -sf ../../i386/kernel/ptrace.c
+ln -sf ../../i386/kernel/semaphore.c
+ln -sf ../../i386/kernel/sys_i386.c
+ln -sf ../../../${LINUX_26}/arch/xen/kernel/ctrl_if.c
+ln -sf ../../../${LINUX_26}/arch/xen/kernel/evtchn.c
+ln -sf ../../../${LINUX_26}/arch/xen/kernel/fixup.c
+ln -sf ../../../${LINUX_26}/arch/xen/kernel/gnttab.c
+ln -sf ../../../${LINUX_26}/arch/xen/kernel/reboot.c
+ln -sf ../../../${LINUX_26}/arch/xen/kernel/skbuff.c
+
+cd ${AD}/arch/xen/lib
+ln -sf ../../i386/lib/checksum.S
+ln -sf ../../i386/lib/dec_and_lock.c
+ln -sf ../../i386/lib/getuser.S
+ln -sf ../../i386/lib/iodebug.c
+ln -sf ../../i386/lib/memcpy.c
+ln -sf ../../i386/lib/mmx.c
+ln -sf ../../i386/lib/old-checksum.c
+ln -sf ../../i386/lib/strstr.c
+ln -sf ../../i386/lib/usercopy.c
+ln -sf ../../../${LINUX_26}/arch/xen/kernel/xen_proc.c
+
+cd ${AD}/arch/xen/mm
+ln -sf ../../i386/mm/extable.c
+ln -sf ../../i386/mm/pageattr.c
+ln -sf ../../../${LINUX_26}/arch/xen/i386/mm/hypervisor.c
+
+cd ${AD}/arch/xen/drivers/balloon
+ln -sf ../../../../${LINUX_26}/drivers/xen/balloon/balloon.c
+
+cd ${AD}/arch/xen/drivers/console
+ln -sf ../../../../${LINUX_26}/drivers/xen/console/console.c
+
+cd ${AD}/arch/xen/drivers/dom0
+ln -sf ../../../../${LINUX_26}/drivers/xen/privcmd/privcmd.c core.c
+
+cd ${AD}/arch/xen/drivers/evtchn
+ln -sf ../../../../${LINUX_26}/drivers/xen/evtchn/evtchn.c
+
+cd ${AD}/arch/xen/drivers/netif/frontend
+ln -sf ../../../../../${LINUX_26}/drivers/xen/netfront/netfront.c main.c
+
+cd ${AD}/arch/xen/drivers/netif/backend
+ln -sf ../../../../../${LINUX_26}/drivers/xen/netback/common.h
+ln -sf ../../../../../${LINUX_26}/drivers/xen/netback/control.c
+ln -sf ../../../../../${LINUX_26}/drivers/xen/netback/interface.c
+ln -sf ../../../../../${LINUX_26}/drivers/xen/netback/netback.c main.c
+
+cd ${AD}/arch/xen/drivers/blkif/backend
+ln -sf ../../../../../${LINUX_26}/drivers/xen/blkback/common.h
+ln -sf ../../../../../${LINUX_26}/drivers/xen/blkback/blkback.c main.c
+ln -sf ../../../../../${LINUX_26}/drivers/xen/blkback/control.c
+ln -sf ../../../../../${LINUX_26}/drivers/xen/blkback/interface.c
+ln -sf ../../../../../${LINUX_26}/drivers/xen/blkback/vbd.c
+
+cd ${AD}/arch/xen/drivers/blkif/frontend
+ln -sf ../../../../../${LINUX_26}/drivers/xen/blkfront/blkfront.c
+
+cd ${AD}/arch/xen/drivers/usbif/frontend
+ln -sf ../../../../../${LINUX_26}/drivers/xen/usbfront/usbfront.c main.c
+ln -sf ../../../../../${LINUX_26}/drivers/xen/usbfront/xhci.h
+
+cd ${AD}/arch/xen/drivers/usbif/backend
+ln -sf ../../../../../${LINUX_26}/drivers/xen/usbback/common.h
+ln -sf ../../../../../${LINUX_26}/drivers/xen/usbback/control.c
+ln -sf ../../../../../${LINUX_26}/drivers/xen/usbback/interface.c
+ln -sf ../../../../../${LINUX_26}/drivers/xen/usbback/usbback.c main.c
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/param.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/param.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,22 @@
+#ifndef _ASMx86_64_PARAM_H
+#define _ASMx86_64_PARAM_H
+
+#ifdef __KERNEL__
+# define HZ 100 /* Internal kernel timer frequency */
+# define USER_HZ 100 /* .. some user interfaces are in
"ticks" */
+# define CLOCKS_PER_SEC (USER_HZ) /* like times() */
+#endif
+
+#ifndef HZ
+#define HZ 100
+#endif
+
+#define EXEC_PAGESIZE 4096
+
+#ifndef NOGROUP
+#define NOGROUP (-1)
+#endif
+
+#define MAXHOSTNAMELEN 64 /* max length of hostname */
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/netback/common.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/netback/common.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,103 @@
+/******************************************************************************
+ * arch/xen/drivers/netif/backend/common.h
+ */
+
+#ifndef __NETIF__BACKEND__COMMON_H__
+#define __NETIF__BACKEND__COMMON_H__
+
+#include <linux/config.h>
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/ip.h>
+#include <linux/in.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <asm-xen/ctrl_if.h>
+#include <asm-xen/xen-public/io/netif.h>
+#include <asm/io.h>
+#include <asm/pgalloc.h>
+
+#if 0
+#define ASSERT(_p) \
+ if ( !(_p) ) { printk("Assertion '%s' failed, line %d, file %s", #_p , \
+ __LINE__, __FILE__); *(int*)0=0; }
+#define DPRINTK(_f, _a...) printk(KERN_ALERT "(file=%s, line=%d) " _f, \
+ __FILE__ , __LINE__ , ## _a )
+#else
+#define ASSERT(_p) ((void)0)
+#define DPRINTK(_f, _a...) ((void)0)
+#endif
+
+typedef struct netif_st {
+ /* Unique identifier for this interface. */
+ domid_t domid;
+ unsigned int handle;
+
+ u8 fe_dev_addr[6];
+
+ /* Physical parameters of the comms window. */
+ unsigned long tx_shmem_frame;
+ unsigned long rx_shmem_frame;
+ unsigned int evtchn;
+ int irq;
+
+ /* The shared rings and indexes. */
+ netif_tx_interface_t *tx;
+ netif_rx_interface_t *rx;
+
+ /* Private indexes into shared ring. */
+ NETIF_RING_IDX rx_req_cons;
+ NETIF_RING_IDX rx_resp_prod; /* private version of shared variable */
+ NETIF_RING_IDX tx_req_cons;
+ NETIF_RING_IDX tx_resp_prod; /* private version of shared variable */
+
+ /* Transmit shaping: allow 'credit_bytes' every 'credit_usec'. */
+ unsigned long credit_bytes;
+ unsigned long credit_usec;
+ unsigned long remaining_credit;
+ struct timer_list credit_timeout;
+
+ /* Miscellaneous private stuff. */
+ enum { DISCONNECTED, DISCONNECTING, CONNECTED } status;
+ int active;
+ /*
+ * DISCONNECT response is deferred until pending requests are ack'ed.
+ * We therefore need to store the id from the original request.
+ */
+ u8 disconnect_rspid;
+ struct netif_st *hash_next;
+ struct list_head list; /* scheduling list */
+ atomic_t refcnt;
+ struct net_device *dev;
+ struct net_device_stats stats;
+
+ struct work_struct work;
+} netif_t;
+
+void netif_create(netif_be_create_t *create);
+void netif_destroy(netif_be_destroy_t *destroy);
+void netif_creditlimit(netif_be_creditlimit_t *creditlimit);
+void netif_connect(netif_be_connect_t *connect);
+int netif_disconnect(netif_be_disconnect_t *disconnect, u8 rsp_id);
+void netif_disconnect_complete(netif_t *netif);
+netif_t *netif_find_by_handle(domid_t domid, unsigned int handle);
+#define netif_get(_b) (atomic_inc(&(_b)->refcnt))
+#define netif_put(_b) \
+ do { \
+ if ( atomic_dec_and_test(&(_b)->refcnt) ) \
+ netif_disconnect_complete(_b); \
+ } while (0)
+
+void netif_interface_init(void);
+void netif_ctrlif_init(void);
+
+void netif_schedule_work(netif_t *netif);
+void netif_deschedule_work(netif_t *netif);
+
+int netif_be_start_xmit(struct sk_buff *skb, struct net_device *dev);
+struct net_device_stats *netif_be_get_stats(struct net_device *dev);
+irqreturn_t netif_be_int(int irq, void *dev_id, struct pt_regs *regs);
+
+#endif /* __NETIF__BACKEND__COMMON_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/netback/interface.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/netback/interface.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,381 @@
+/******************************************************************************
+ * arch/xen/drivers/netif/backend/interface.c
+ *
+ * Network-device interface management.
+ *
+ * Copyright (c) 2004-2005, Keir Fraser
+ */
+
+#include "common.h"
+#include <linux/rtnetlink.h>
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+#define VMALLOC_VMADDR(x) ((unsigned long)(x))
+#endif
+
+#define NETIF_HASHSZ 1024
+#define NETIF_HASH(_d,_h) (((int)(_d)^(int)(_h))&(NETIF_HASHSZ-1))
+
+static netif_t *netif_hash[NETIF_HASHSZ];
+
+netif_t *netif_find_by_handle(domid_t domid, unsigned int handle)
+{
+ netif_t *netif = netif_hash[NETIF_HASH(domid, handle)];
+ while ( (netif != NULL) &&
+ ((netif->domid != domid) || (netif->handle != handle)) )
+ netif = netif->hash_next;
+ return netif;
+}
+
+static void __netif_up(netif_t *netif)
+{
+ struct net_device *dev = netif->dev;
+ spin_lock_bh(&dev->xmit_lock);
+ netif->active = 1;
+ spin_unlock_bh(&dev->xmit_lock);
+ (void)request_irq(netif->irq, netif_be_int, 0, dev->name, netif);
+ netif_schedule_work(netif);
+}
+
+static void __netif_down(netif_t *netif)
+{
+ struct net_device *dev = netif->dev;
+ spin_lock_bh(&dev->xmit_lock);
+ netif->active = 0;
+ spin_unlock_bh(&dev->xmit_lock);
+ free_irq(netif->irq, netif);
+ netif_deschedule_work(netif);
+}
+
+static int net_open(struct net_device *dev)
+{
+ netif_t *netif = netdev_priv(dev);
+ if ( netif->status == CONNECTED )
+ __netif_up(netif);
+ netif_start_queue(dev);
+ return 0;
+}
+
+static int net_close(struct net_device *dev)
+{
+ netif_t *netif = netdev_priv(dev);
+ netif_stop_queue(dev);
+ if ( netif->status == CONNECTED )
+ __netif_down(netif);
+ return 0;
+}
+
+static void __netif_disconnect_complete(void *arg)
+{
+ netif_t *netif = (netif_t *)arg;
+ ctrl_msg_t cmsg;
+ netif_be_disconnect_t disc;
+
+ /*
+ * These can't be done in netif_disconnect() because at that point there
+ * may be outstanding requests in the network stack whose asynchronous
+ * responses must still be notified to the remote driver.
+ */
+ unbind_evtchn_from_irq(netif->evtchn);
+ vfree(netif->tx); /* Frees netif->rx as well. */
+
+ /* Construct the deferred response message. */
+ cmsg.type = CMSG_NETIF_BE;
+ cmsg.subtype = CMSG_NETIF_BE_DISCONNECT;
+ cmsg.id = netif->disconnect_rspid;
+ cmsg.length = sizeof(netif_be_disconnect_t);
+ disc.domid = netif->domid;
+ disc.netif_handle = netif->handle;
+ disc.status = NETIF_BE_STATUS_OKAY;
+ memcpy(cmsg.msg, &disc, sizeof(disc));
+
+ /*
+ * Make sure message is constructed /before/ status change, because
+ * after the status change the 'netif' structure could be deallocated at
+ * any time. Also make sure we send the response /after/ status change,
+ * as otherwise a subsequent CONNECT request could spuriously fail if
+ * another CPU doesn't see the status change yet.
+ */
+ mb();
+ if ( netif->status != DISCONNECTING )
+ BUG();
+ netif->status = DISCONNECTED;
+ mb();
+
+ /* Send the successful response. */
+ ctrl_if_send_response(&cmsg);
+}
+
+void netif_disconnect_complete(netif_t *netif)
+{
+ INIT_WORK(&netif->work, __netif_disconnect_complete, (void *)netif);
+ schedule_work(&netif->work);
+}
+
+void netif_create(netif_be_create_t *create)
+{
+ int err = 0;
+ domid_t domid = create->domid;
+ unsigned int handle = create->netif_handle;
+ struct net_device *dev;
+ netif_t **pnetif, *netif;
+ char name[IFNAMSIZ] = {};
+
+ snprintf(name, IFNAMSIZ - 1, "vif%u.%u", domid, handle);
+ dev = alloc_netdev(sizeof(netif_t), name, ether_setup);
+ if ( dev == NULL )
+ {
+ DPRINTK("Could not create netif: out of memory\n");
+ create->status = NETIF_BE_STATUS_OUT_OF_MEMORY;
+ return;
+ }
+
+ netif = netdev_priv(dev);
+ memset(netif, 0, sizeof(*netif));
+ netif->domid = domid;
+ netif->handle = handle;
+ netif->status = DISCONNECTED;
+ atomic_set(&netif->refcnt, 0);
+ netif->dev = dev;
+
+ netif->credit_bytes = netif->remaining_credit = ~0UL;
+ netif->credit_usec = 0UL;
+ init_timer(&netif->credit_timeout);
+
+ pnetif = &netif_hash[NETIF_HASH(domid, handle)];
+ while ( *pnetif != NULL )
+ {
+ if ( ((*pnetif)->domid == domid) && ((*pnetif)->handle == handle) )
+ {
+ DPRINTK("Could not create netif: already exists\n");
+ create->status = NETIF_BE_STATUS_INTERFACE_EXISTS;
+ free_netdev(dev);
+ return;
+ }
+ pnetif = &(*pnetif)->hash_next;
+ }
+
+ dev->hard_start_xmit = netif_be_start_xmit;
+ dev->get_stats = netif_be_get_stats;
+ dev->open = net_open;
+ dev->stop = net_close;
+ dev->features = NETIF_F_NO_CSUM;
+
+ /* Disable queuing. */
+ dev->tx_queue_len = 0;
+
+ if ( (create->be_mac[0] == 0) && (create->be_mac[1] == 0) &&
+ (create->be_mac[2] == 0) && (create->be_mac[3] == 0) &&
+ (create->be_mac[4] == 0) && (create->be_mac[5] == 0) )
+ {
+ /*
+ * Initialise a dummy MAC address. We choose the numerically largest
+ * non-broadcast address to prevent the address getting stolen by an
+ * Ethernet bridge for STP purposes. (FE:FF:FF:FF:FF:FF)
+ */
+ memset(dev->dev_addr, 0xFF, ETH_ALEN);
+ dev->dev_addr[0] &= ~0x01;
+ }
+ else
+ {
+ memcpy(dev->dev_addr, create->be_mac, ETH_ALEN);
+ }
+
+ memcpy(netif->fe_dev_addr, create->mac, ETH_ALEN);
+
+ rtnl_lock();
+ err = register_netdevice(dev);
+ rtnl_unlock();
+
+ if ( err != 0 )
+ {
+ DPRINTK("Could not register new net device %s: err=%d\n",
+ dev->name, err);
+ create->status = NETIF_BE_STATUS_OUT_OF_MEMORY;
+ free_netdev(dev);
+ return;
+ }
+
+ netif->hash_next = *pnetif;
+ *pnetif = netif;
+
+ DPRINTK("Successfully created netif\n");
+ create->status = NETIF_BE_STATUS_OKAY;
+}
+
+void netif_destroy(netif_be_destroy_t *destroy)
+{
+ domid_t domid = destroy->domid;
+ unsigned int handle = destroy->netif_handle;
+ netif_t **pnetif, *netif;
+
+ pnetif = &netif_hash[NETIF_HASH(domid, handle)];
+ while ( (netif = *pnetif) != NULL )
+ {
+ if ( (netif->domid == domid) && (netif->handle == handle) )
+ {
+ if ( netif->status != DISCONNECTED )
+ goto still_connected;
+ goto destroy;
+ }
+ pnetif = &netif->hash_next;
+ }
+
+ destroy->status = NETIF_BE_STATUS_INTERFACE_NOT_FOUND;
+ return;
+
+ still_connected:
+ destroy->status = NETIF_BE_STATUS_INTERFACE_CONNECTED;
+ return;
+
+ destroy:
+ *pnetif = netif->hash_next;
+ unregister_netdev(netif->dev);
+ free_netdev(netif->dev);
+ destroy->status = NETIF_BE_STATUS_OKAY;
+}
+
+void netif_creditlimit(netif_be_creditlimit_t *creditlimit)
+{
+ domid_t domid = creditlimit->domid;
+ unsigned int handle = creditlimit->netif_handle;
+ netif_t *netif;
+
+ netif = netif_find_by_handle(domid, handle);
+ if ( unlikely(netif == NULL) )
+ {
+ DPRINTK("netif_creditlimit attempted for non-existent netif"
+ " (%u,%u)\n", creditlimit->domid, creditlimit->netif_handle);
+ creditlimit->status = NETIF_BE_STATUS_INTERFACE_NOT_FOUND;
+ return;
+ }
+
+ /* Set the credit limit (reset remaining credit to new limit). */
+ netif->credit_bytes = netif->remaining_credit = creditlimit->credit_bytes;
+ netif->credit_usec = creditlimit->period_usec;
+
+ if ( netif->status == CONNECTED )
+ {
+ /*
+ * Schedule work so that any packets waiting under previous credit
+ * limit are dealt with (acts like a replenishment point).
+ */
+ netif->credit_timeout.expires = jiffies;
+ netif_schedule_work(netif);
+ }
+
+ creditlimit->status = NETIF_BE_STATUS_OKAY;
+}
+
+void netif_connect(netif_be_connect_t *connect)
+{
+ domid_t domid = connect->domid;
+ unsigned int handle = connect->netif_handle;
+ unsigned int evtchn = connect->evtchn;
+ unsigned long tx_shmem_frame = connect->tx_shmem_frame;
+ unsigned long rx_shmem_frame = connect->rx_shmem_frame;
+ struct vm_struct *vma;
+ pgprot_t prot;
+ int error;
+ netif_t *netif;
+
+ netif = netif_find_by_handle(domid, handle);
+ if ( unlikely(netif == NULL) )
+ {
+ DPRINTK("netif_connect attempted for non-existent netif (%u,%u)\n",
+ connect->domid, connect->netif_handle);
+ connect->status = NETIF_BE_STATUS_INTERFACE_NOT_FOUND;
+ return;
+ }
+
+ if ( netif->status != DISCONNECTED )
+ {
+ connect->status = NETIF_BE_STATUS_INTERFACE_CONNECTED;
+ return;
+ }
+
+ if ( (vma = get_vm_area(2*PAGE_SIZE, VM_IOREMAP)) == NULL )
+ {
+ connect->status = NETIF_BE_STATUS_OUT_OF_MEMORY;
+ return;
+ }
+
+ prot = __pgprot(_KERNPG_TABLE);
+ error = direct_remap_area_pages(&init_mm,
+ VMALLOC_VMADDR(vma->addr),
+ tx_shmem_frame<<PAGE_SHIFT, PAGE_SIZE,
+ prot, domid);
+ error |= direct_remap_area_pages(&init_mm,
+ VMALLOC_VMADDR(vma->addr) + PAGE_SIZE,
+ rx_shmem_frame<<PAGE_SHIFT, PAGE_SIZE,
+ prot, domid);
+ if ( error != 0 )
+ {
+ if ( error == -ENOMEM )
+ connect->status = NETIF_BE_STATUS_OUT_OF_MEMORY;
+ else if ( error == -EFAULT )
+ connect->status = NETIF_BE_STATUS_MAPPING_ERROR;
+ else
+ connect->status = NETIF_BE_STATUS_ERROR;
+ vfree(vma->addr);
+ return;
+ }
+
+ netif->evtchn = evtchn;
+ netif->irq = bind_evtchn_to_irq(evtchn);
+ netif->tx_shmem_frame = tx_shmem_frame;
+ netif->rx_shmem_frame = rx_shmem_frame;
+ netif->tx =
+ (netif_tx_interface_t *)vma->addr;
+ netif->rx =
+ (netif_rx_interface_t *)((char *)vma->addr + PAGE_SIZE);
+ netif->tx->resp_prod = netif->rx->resp_prod = 0;
+ netif_get(netif);
+ wmb(); /* Other CPUs see new state before interface is started. */
+
+ rtnl_lock();
+ netif->status = CONNECTED;
+ wmb();
+ if ( netif_running(netif->dev) )
+ __netif_up(netif);
+ rtnl_unlock();
+
+ connect->status = NETIF_BE_STATUS_OKAY;
+}
+
+int netif_disconnect(netif_be_disconnect_t *disconnect, u8 rsp_id)
+{
+ domid_t domid = disconnect->domid;
+ unsigned int handle = disconnect->netif_handle;
+ netif_t *netif;
+
+ netif = netif_find_by_handle(domid, handle);
+ if ( unlikely(netif == NULL) )
+ {
+ DPRINTK("netif_disconnect attempted for non-existent netif"
+ " (%u,%u)\n", disconnect->domid, disconnect->netif_handle);
+ disconnect->status = NETIF_BE_STATUS_INTERFACE_NOT_FOUND;
+ return 1; /* Caller will send response error message. */
+ }
+
+ if ( netif->status == CONNECTED )
+ {
+ rtnl_lock();
+ netif->status = DISCONNECTING;
+ netif->disconnect_rspid = rsp_id;
+ wmb();
+ if ( netif_running(netif->dev) )
+ __netif_down(netif);
+ rtnl_unlock();
+ netif_put(netif);
+ return 0; /* Caller should not send response message. */
+ }
+
+ disconnect->status = NETIF_BE_STATUS_OKAY;
+ return 1;
+}
+
+void netif_interface_init(void)
+{
+ memset(netif_hash, 0, sizeof(netif_hash));
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/drivers/dom0/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/drivers/dom0/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,3 @@
+O_TARGET := drv.o
+obj-y := core.o
+include $(TOPDIR)/Rules.make
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/head.S
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/head.S Fri Jul 15
13:39:50 2005
@@ -0,0 +1,186 @@
+
+#include <linux/config.h>
+
+.section __xen_guest
+ .ascii "GUEST_OS=linux,GUEST_VER=2.6"
+ .ascii ",XEN_VER=3.0"
+ .ascii ",VIRT_BASE=0xC0000000"
+ .ascii ",LOADER=generic"
+ .byte 0
+
+.text
+#include <linux/threads.h>
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/thread_info.h>
+#include <asm/asm_offsets.h>
+#include <asm-xen/xen-public/arch-x86_32.h>
+
+/*
+ * References to members of the new_cpu_data structure.
+ */
+
+#define X86 new_cpu_data+CPUINFO_x86
+#define X86_VENDOR new_cpu_data+CPUINFO_x86_vendor
+#define X86_MODEL new_cpu_data+CPUINFO_x86_model
+#define X86_MASK new_cpu_data+CPUINFO_x86_mask
+#define X86_HARD_MATH new_cpu_data+CPUINFO_hard_math
+#define X86_CPUID new_cpu_data+CPUINFO_cpuid_level
+#define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability
+#define X86_VENDOR_ID new_cpu_data+CPUINFO_x86_vendor_id
+
+ENTRY(startup_32)
+ cld
+
+ /* Copy the necessary stuff from xen_start_info structure. */
+ mov $xen_start_info_union,%edi
+ mov $512,%ecx
+ rep movsl
+
+#ifdef CONFIG_SMP
+ENTRY(startup_32_smp)
+ cld
+#endif /* CONFIG_SMP */
+
+ /* Set up the stack pointer */
+ lss stack_start,%esp
+
+checkCPUtype:
+
+ /* get vendor info */
+ xorl %eax,%eax # call CPUID with 0 -> return vendor ID
+ cpuid
+ movl %eax,X86_CPUID # save CPUID level
+ movl %ebx,X86_VENDOR_ID # lo 4 chars
+ movl %edx,X86_VENDOR_ID+4 # next 4 chars
+ movl %ecx,X86_VENDOR_ID+8 # last 4 chars
+
+ movl $1,%eax # Use the CPUID instruction to get CPU type
+ cpuid
+ movb %al,%cl # save reg for future use
+ andb $0x0f,%ah # mask processor family
+ movb %ah,X86
+ andb $0xf0,%al # mask model
+ shrb $4,%al
+ movb %al,X86_MODEL
+ andb $0x0f,%cl # mask mask revision
+ movb %cl,X86_MASK
+ movl %edx,X86_CAPABILITY
+
+ incb ready
+
+ xorl %eax,%eax # Clear FS/GS and LDT
+ movl %eax,%fs
+ movl %eax,%gs
+ cld # gcc2 wants the direction flag cleared at all
times
+
+#ifdef CONFIG_SMP
+ movb ready, %cl
+ cmpb $1,%cl
+ je 1f # the first CPU calls start_kernel
+ # all other CPUs call initialize_secondary
+ call initialize_secondary
+ jmp L6
+1:
+#endif /* CONFIG_SMP */
+ call start_kernel
+L6:
+ jmp L6 # main should never return here, but
+ # just in case, we know what happens.
+
+ENTRY(lgdt_finish)
+ movl $(__KERNEL_DS),%eax # reload all the segment registers
+ movw %ax,%ss # after changing gdt.
+
+ movl $(__USER_DS),%eax # DS/ES contains default USER segment
+ movw %ax,%ds
+ movw %ax,%es
+
+ popl %eax # reload CS by intersegment return
+ pushl $(__KERNEL_CS)
+ pushl %eax
+ lret
+
+ENTRY(stack_start)
+ .long init_thread_union+THREAD_SIZE
+ .long __BOOT_DS
+
+ready: .byte 0
+
+.globl idt_descr
+.globl cpu_gdt_descr
+
+ ALIGN
+ .word 0 # 32-bit align idt_desc.address
+idt_descr:
+ .word IDT_ENTRIES*8-1 # idt contains 256 entries
+ .long idt_table
+
+# boot GDT descriptor (later on used by CPU#0):
+ .word 0 # 32 bit align gdt_desc.address
+cpu_gdt_descr:
+ .word GDT_SIZE
+ .long cpu_gdt_table
+
+ .fill NR_CPUS-1,8,0 # space for the other GDT descriptors
+
+.org 0x1000
+ENTRY(empty_zero_page)
+
+.org 0x2000
+ENTRY(swapper_pg_dir)
+
+.org 0x3000
+ENTRY(cpu_gdt_table)
+ .quad 0x0000000000000000 /* NULL descriptor */
+ .quad 0x0000000000000000 /* 0x0b reserved */
+ .quad 0x0000000000000000 /* 0x13 reserved */
+ .quad 0x0000000000000000 /* 0x1b reserved */
+ .quad 0x0000000000000000 /* 0x20 unused */
+ .quad 0x0000000000000000 /* 0x28 unused */
+ .quad 0x0000000000000000 /* 0x33 TLS entry 1 */
+ .quad 0x0000000000000000 /* 0x3b TLS entry 2 */
+ .quad 0x0000000000000000 /* 0x43 TLS entry 3 */
+ .quad 0x0000000000000000 /* 0x4b reserved */
+ .quad 0x0000000000000000 /* 0x53 reserved */
+ .quad 0x0000000000000000 /* 0x5b reserved */
+
+ .quad 0x00cfbb000000c3ff /* 0x60 kernel 4GB code at 0x00000000 */
+ .quad 0x00cfb3000000c3ff /* 0x68 kernel 4GB data at 0x00000000 */
+ .quad 0x00cffb000000c3ff /* 0x73 user 4GB code at 0x00000000 */
+ .quad 0x00cff3000000c3ff /* 0x7b user 4GB data at 0x00000000 */
+
+ .quad 0x0000000000000000 /* 0x80 TSS descriptor */
+ .quad 0x0000000000000000 /* 0x88 LDT descriptor */
+
+ /* Segments used for calling PnP BIOS */
+ .quad 0x0000000000000000 /* 0x90 32-bit code */
+ .quad 0x0000000000000000 /* 0x98 16-bit code */
+ .quad 0x0000000000000000 /* 0xa0 16-bit data */
+ .quad 0x0000000000000000 /* 0xa8 16-bit data */
+ .quad 0x0000000000000000 /* 0xb0 16-bit data */
+ /*
+ * The APM segments have byte granularity and their bases
+ * and limits are set at run time.
+ */
+ .quad 0x0000000000000000 /* 0xb8 APM CS code */
+ .quad 0x0000000000000000 /* 0xc0 APM CS 16 code (16 bit) */
+ .quad 0x0000000000000000 /* 0xc8 APM DS data */
+
+ .quad 0x0000000000000000 /* 0xd0 - unused */
+ .quad 0x0000000000000000 /* 0xd8 - unused */
+ .quad 0x0000000000000000 /* 0xe0 - unused */
+ .quad 0x0000000000000000 /* 0xe8 - unused */
+ .quad 0x0000000000000000 /* 0xf0 - unused */
+ .quad 0x0000000000000000 /* 0xf8 - GDT entry 31: double-fault
TSS */
+ .fill GDT_ENTRIES-32,8,0
+
+.org 0x4000
+ENTRY(default_ldt)
+
+.org 0x5000
+/*
+ * Real beginning of normal "text" segment
+ */
+ENTRY(stext)
+ENTRY(_stext)
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/smpboot_hooks.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++
b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/smpboot_hooks.h
Fri Jul 15 13:39:50 2005
@@ -0,0 +1,55 @@
+/* two abstractions specific to kernel/smpboot.c, mainly to cater to visws
+ * which needs to alter them. */
+
+static inline void smpboot_clear_io_apic_irqs(void)
+{
+#ifdef CONFIG_X86_IO_APIC
+ io_apic_irqs = 0;
+#endif
+}
+
+static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
+{
+#if 1
+ printk("smpboot_setup_warm_reset_vector\n");
+#else
+ CMOS_WRITE(0xa, 0xf);
+ local_flush_tlb();
+ Dprintk("1.\n");
+ *((volatile unsigned short *) TRAMPOLINE_HIGH) = start_eip >> 4;
+ Dprintk("2.\n");
+ *((volatile unsigned short *) TRAMPOLINE_LOW) = start_eip & 0xf;
+ Dprintk("3.\n");
+#endif
+}
+
+static inline void smpboot_restore_warm_reset_vector(void)
+{
+ /*
+ * Install writable page 0 entry to set BIOS data area.
+ */
+ local_flush_tlb();
+
+ /*
+ * Paranoid: Set warm reset code and vector here back
+ * to default values.
+ */
+ CMOS_WRITE(0, 0xf);
+
+ *((volatile long *) phys_to_virt(0x467)) = 0;
+}
+
+static inline void smpboot_setup_io_apic(void)
+{
+#ifdef CONFIG_X86_IO_APIC
+ /*
+ * Here we can be sure that there is an IO-APIC in the system. Let's
+ * go and set it up:
+ */
+ if (!skip_ioapic_setup && nr_ioapics)
+ setup_IO_APIC();
+#endif
+}
+
+
+#define smp_found_config (HYPERVISOR_shared_info->n_vcpu > 1)
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/mpparse.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/mpparse.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,954 @@
+/*
+ * Intel Multiprocessor Specification 1.1 and 1.4
+ * compliant MP-table parsing routines.
+ *
+ * (c) 1995 Alan Cox, Building #3 <alan@xxxxxxxxxx>
+ * (c) 1998, 1999, 2000 Ingo Molnar <mingo@xxxxxxxxxx>
+ *
+ * Fixes
+ * Erich Boleyn : MP v1.4 and additional changes.
+ * Alan Cox : Added EBDA scanning
+ * Ingo Molnar : various cleanups and rewrites
+ * Maciej W. Rozycki: Bits for default MP configurations
+ * Paul Diefenbaugh: Added full ACPI support
+ */
+
+#include <linux/mm.h>
+#include <linux/irq.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/config.h>
+#include <linux/bootmem.h>
+#include <linux/smp_lock.h>
+#include <linux/kernel_stat.h>
+#include <linux/mc146818rtc.h>
+#include <linux/acpi.h>
+
+#include <asm/smp.h>
+#include <asm/mtrr.h>
+#include <asm/mpspec.h>
+#include <asm/pgalloc.h>
+#include <asm/io_apic.h>
+#include <asm/proto.h>
+
+/* Have we found an MP table */
+int smp_found_config;
+unsigned int __initdata maxcpus = NR_CPUS;
+
+int acpi_found_madt;
+
+/*
+ * Various Linux-internal data structures created from the
+ * MP-table.
+ */
+int apic_version [MAX_APICS];
+unsigned char mp_bus_id_to_type [MAX_MP_BUSSES] = { [0 ... MAX_MP_BUSSES-1] =
-1 };
+int mp_bus_id_to_pci_bus [MAX_MP_BUSSES] = { [0 ... MAX_MP_BUSSES-1] = -1 };
+cpumask_t pci_bus_to_cpumask [256] = { [0 ... 255] = CPU_MASK_ALL };
+
+int mp_current_pci_id = 0;
+/* I/O APIC entries */
+struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS];
+
+/* # of MP IRQ source entries */
+struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+
+/* MP IRQ source entries */
+int mp_irq_entries;
+
+int nr_ioapics;
+int pic_mode;
+unsigned long mp_lapic_addr = 0;
+
+
+
+/* Processor that is doing the boot up */
+unsigned int boot_cpu_id = -1U;
+/* Internal processor count */
+static unsigned int num_processors = 0;
+
+/* Bitmask of physically existing CPUs */
+physid_mask_t phys_cpu_present_map = PHYSID_MASK_NONE;
+
+/* ACPI MADT entry parsing functions */
+#ifdef CONFIG_ACPI_BOOT
+extern struct acpi_boot_flags acpi_boot;
+#ifdef CONFIG_X86_LOCAL_APIC
+extern int acpi_parse_lapic (acpi_table_entry_header *header);
+extern int acpi_parse_lapic_addr_ovr (acpi_table_entry_header *header);
+extern int acpi_parse_lapic_nmi (acpi_table_entry_header *header);
+#endif /*CONFIG_X86_LOCAL_APIC*/
+#ifdef CONFIG_X86_IO_APIC
+extern int acpi_parse_ioapic (acpi_table_entry_header *header);
+#endif /*CONFIG_X86_IO_APIC*/
+#endif /*CONFIG_ACPI_BOOT*/
+
+u8 bios_cpu_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID };
+
+
+/*
+ * Intel MP BIOS table parsing routines:
+ */
+
+/*
+ * Checksum an MP configuration block.
+ */
+
+static int __init mpf_checksum(unsigned char *mp, int len)
+{
+ int sum = 0;
+
+ while (len--)
+ sum += *mp++;
+
+ return sum & 0xFF;
+}
+
+#ifndef CONFIG_XEN
+static void __init MP_processor_info (struct mpc_config_processor *m)
+{
+ int ver;
+
+ if (!(m->mpc_cpuflag & CPU_ENABLED))
+ return;
+
+ printk(KERN_INFO "Processor #%d %d:%d APIC version %d\n",
+ m->mpc_apicid,
+ (m->mpc_cpufeature & CPU_FAMILY_MASK)>>8,
+ (m->mpc_cpufeature & CPU_MODEL_MASK)>>4,
+ m->mpc_apicver);
+
+ if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) {
+ Dprintk(" Bootup CPU\n");
+ boot_cpu_id = m->mpc_apicid;
+ }
+ if (num_processors >= NR_CPUS) {
+ printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached."
+ " Processor ignored.\n", NR_CPUS);
+ return;
+ }
+ if (num_processors >= maxcpus) {
+ printk(KERN_WARNING "WARNING: maxcpus limit of %i reached."
+ " Processor ignored.\n", maxcpus);
+ return;
+ }
+
+ num_processors++;
+
+ if (m->mpc_apicid > MAX_APICS) {
+ printk(KERN_ERR "Processor #%d INVALID. (Max ID: %d).\n",
+ m->mpc_apicid, MAX_APICS);
+ return;
+ }
+ ver = m->mpc_apicver;
+
+ physid_set(m->mpc_apicid, phys_cpu_present_map);
+ /*
+ * Validate version
+ */
+ if (ver == 0x0) {
+ printk(KERN_ERR "BIOS bug, APIC version is 0 for CPU#%d! fixing
up to 0x10. (tell your hw vendor)\n", m->mpc_apicid);
+ ver = 0x10;
+ }
+ apic_version[m->mpc_apicid] = ver;
+ bios_cpu_apicid[num_processors - 1] = m->mpc_apicid;
+}
+#else
+void __init MP_processor_info (struct mpc_config_processor *m)
+{
+ num_processors++;
+}
+#endif /* CONFIG_XEN */
+
+static void __init MP_bus_info (struct mpc_config_bus *m)
+{
+ char str[7];
+
+ memcpy(str, m->mpc_bustype, 6);
+ str[6] = 0;
+ Dprintk("Bus #%d is %s\n", m->mpc_busid, str);
+
+ if (strncmp(str, "ISA", 3) == 0) {
+ mp_bus_id_to_type[m->mpc_busid] = MP_BUS_ISA;
+ } else if (strncmp(str, "EISA", 4) == 0) {
+ mp_bus_id_to_type[m->mpc_busid] = MP_BUS_EISA;
+ } else if (strncmp(str, "PCI", 3) == 0) {
+ mp_bus_id_to_type[m->mpc_busid] = MP_BUS_PCI;
+ mp_bus_id_to_pci_bus[m->mpc_busid] = mp_current_pci_id;
+ mp_current_pci_id++;
+ } else if (strncmp(str, "MCA", 3) == 0) {
+ mp_bus_id_to_type[m->mpc_busid] = MP_BUS_MCA;
+ } else {
+ printk(KERN_ERR "Unknown bustype %s\n", str);
+ }
+}
+
+static void __init MP_ioapic_info (struct mpc_config_ioapic *m)
+{
+ if (!(m->mpc_flags & MPC_APIC_USABLE))
+ return;
+
+ printk("I/O APIC #%d Version %d at 0x%X.\n",
+ m->mpc_apicid, m->mpc_apicver, m->mpc_apicaddr);
+ if (nr_ioapics >= MAX_IO_APICS) {
+ printk(KERN_ERR "Max # of I/O APICs (%d) exceeded (found
%d).\n",
+ MAX_IO_APICS, nr_ioapics);
+ panic("Recompile kernel with bigger MAX_IO_APICS!.\n");
+ }
+ if (!m->mpc_apicaddr) {
+ printk(KERN_ERR "WARNING: bogus zero I/O APIC address"
+ " found in MP table, skipping!\n");
+ return;
+ }
+ mp_ioapics[nr_ioapics] = *m;
+ nr_ioapics++;
+}
+
+static void __init MP_intsrc_info (struct mpc_config_intsrc *m)
+{
+ mp_irqs [mp_irq_entries] = *m;
+ Dprintk("Int: type %d, pol %d, trig %d, bus %d,"
+ " IRQ %02x, APIC ID %x, APIC INT %02x\n",
+ m->mpc_irqtype, m->mpc_irqflag & 3,
+ (m->mpc_irqflag >> 2) & 3, m->mpc_srcbus,
+ m->mpc_srcbusirq, m->mpc_dstapic, m->mpc_dstirq);
+ if (++mp_irq_entries == MAX_IRQ_SOURCES)
+ panic("Max # of irq sources exceeded!!\n");
+}
+
+static void __init MP_lintsrc_info (struct mpc_config_lintsrc *m)
+{
+ Dprintk("Lint: type %d, pol %d, trig %d, bus %d,"
+ " IRQ %02x, APIC ID %x, APIC LINT %02x\n",
+ m->mpc_irqtype, m->mpc_irqflag & 3,
+ (m->mpc_irqflag >> 2) &3, m->mpc_srcbusid,
+ m->mpc_srcbusirq, m->mpc_destapic, m->mpc_destapiclint);
+ /*
+ * Well it seems all SMP boards in existence
+ * use ExtINT/LVT1 == LINT0 and
+ * NMI/LVT2 == LINT1 - the following check
+ * will show us if this assumptions is false.
+ * Until then we do not have to add baggage.
+ */
+ if ((m->mpc_irqtype == mp_ExtINT) &&
+ (m->mpc_destapiclint != 0))
+ BUG();
+ if ((m->mpc_irqtype == mp_NMI) &&
+ (m->mpc_destapiclint != 1))
+ BUG();
+}
+
+/*
+ * Read/parse the MPC
+ */
+
+static int __init smp_read_mpc(struct mp_config_table *mpc)
+{
+ char str[16];
+ int count=sizeof(*mpc);
+ unsigned char *mpt=((unsigned char *)mpc)+count;
+
+ if (memcmp(mpc->mpc_signature,MPC_SIGNATURE,4)) {
+ printk("SMP mptable: bad signature [%c%c%c%c]!\n",
+ mpc->mpc_signature[0],
+ mpc->mpc_signature[1],
+ mpc->mpc_signature[2],
+ mpc->mpc_signature[3]);
+ return 0;
+ }
+ if (mpf_checksum((unsigned char *)mpc,mpc->mpc_length)) {
+ printk("SMP mptable: checksum error!\n");
+ return 0;
+ }
+ if (mpc->mpc_spec!=0x01 && mpc->mpc_spec!=0x04) {
+ printk(KERN_ERR "SMP mptable: bad table version (%d)!!\n",
+ mpc->mpc_spec);
+ return 0;
+ }
+ if (!mpc->mpc_lapic) {
+ printk(KERN_ERR "SMP mptable: null local APIC address!\n");
+ return 0;
+ }
+ memcpy(str,mpc->mpc_oem,8);
+ str[8]=0;
+ printk(KERN_INFO "OEM ID: %s ",str);
+
+ memcpy(str,mpc->mpc_productid,12);
+ str[12]=0;
+ printk(KERN_INFO "Product ID: %s ",str);
+
+ printk(KERN_INFO "APIC at: 0x%X\n",mpc->mpc_lapic);
+
+ /* save the local APIC address, it might be non-default */
+ if (!acpi_lapic)
+ mp_lapic_addr = mpc->mpc_lapic;
+
+ /*
+ * Now process the configuration blocks.
+ */
+ while (count < mpc->mpc_length) {
+ switch(*mpt) {
+ case MP_PROCESSOR:
+ {
+ struct mpc_config_processor *m=
+ (struct mpc_config_processor *)mpt;
+ if (!acpi_lapic)
+ MP_processor_info(m);
+ mpt += sizeof(*m);
+ count += sizeof(*m);
+ break;
+ }
+ case MP_BUS:
+ {
+ struct mpc_config_bus *m=
+ (struct mpc_config_bus *)mpt;
+ MP_bus_info(m);
+ mpt += sizeof(*m);
+ count += sizeof(*m);
+ break;
+ }
+ case MP_IOAPIC:
+ {
+ struct mpc_config_ioapic *m=
+ (struct mpc_config_ioapic *)mpt;
+ MP_ioapic_info(m);
+ mpt+=sizeof(*m);
+ count+=sizeof(*m);
+ break;
+ }
+ case MP_INTSRC:
+ {
+ struct mpc_config_intsrc *m=
+ (struct mpc_config_intsrc *)mpt;
+
+ MP_intsrc_info(m);
+ mpt+=sizeof(*m);
+ count+=sizeof(*m);
+ break;
+ }
+ case MP_LINTSRC:
+ {
+ struct mpc_config_lintsrc *m=
+ (struct mpc_config_lintsrc *)mpt;
+ MP_lintsrc_info(m);
+ mpt+=sizeof(*m);
+ count+=sizeof(*m);
+ break;
+ }
+ }
+ }
+ clustered_apic_check();
+ if (!num_processors)
+ printk(KERN_ERR "SMP mptable: no processors registered!\n");
+ return num_processors;
+}
+
+static int __init ELCR_trigger(unsigned int irq)
+{
+ unsigned int port;
+
+ port = 0x4d0 + (irq >> 3);
+ return (inb(port) >> (irq & 7)) & 1;
+}
+
+static void __init construct_default_ioirq_mptable(int mpc_default_type)
+{
+ struct mpc_config_intsrc intsrc;
+ int i;
+ int ELCR_fallback = 0;
+
+ intsrc.mpc_type = MP_INTSRC;
+ intsrc.mpc_irqflag = 0; /* conforming */
+ intsrc.mpc_srcbus = 0;
+ intsrc.mpc_dstapic = mp_ioapics[0].mpc_apicid;
+
+ intsrc.mpc_irqtype = mp_INT;
+
+ /*
+ * If true, we have an ISA/PCI system with no IRQ entries
+ * in the MP table. To prevent the PCI interrupts from being set up
+ * incorrectly, we try to use the ELCR. The sanity check to see if
+ * there is good ELCR data is very simple - IRQ0, 1, 2 and 13 can
+ * never be level sensitive, so we simply see if the ELCR agrees.
+ * If it does, we assume it's valid.
+ */
+ if (mpc_default_type == 5) {
+ printk(KERN_INFO "ISA/PCI bus type with no IRQ information...
falling back to ELCR\n");
+
+ if (ELCR_trigger(0) || ELCR_trigger(1) || ELCR_trigger(2) ||
ELCR_trigger(13))
+ printk(KERN_ERR "ELCR contains invalid data... not
using ELCR\n");
+ else {
+ printk(KERN_INFO "Using ELCR to identify PCI
interrupts\n");
+ ELCR_fallback = 1;
+ }
+ }
+
+ for (i = 0; i < 16; i++) {
+ switch (mpc_default_type) {
+ case 2:
+ if (i == 0 || i == 13)
+ continue; /* IRQ0 & IRQ13 not connected */
+ /* fall through */
+ default:
+ if (i == 2)
+ continue; /* IRQ2 is never connected */
+ }
+
+ if (ELCR_fallback) {
+ /*
+ * If the ELCR indicates a level-sensitive interrupt,
we
+ * copy that information over to the MP table in the
+ * irqflag field (level sensitive, active high
polarity).
+ */
+ if (ELCR_trigger(i))
+ intsrc.mpc_irqflag = 13;
+ else
+ intsrc.mpc_irqflag = 0;
+ }
+
+ intsrc.mpc_srcbusirq = i;
+ intsrc.mpc_dstirq = i ? i : 2; /* IRQ0 to INTIN2 */
+ MP_intsrc_info(&intsrc);
+ }
+
+ intsrc.mpc_irqtype = mp_ExtINT;
+ intsrc.mpc_srcbusirq = 0;
+ intsrc.mpc_dstirq = 0; /* 8259A to INTIN0 */
+ MP_intsrc_info(&intsrc);
+}
+
+static inline void __init construct_default_ISA_mptable(int mpc_default_type)
+{
+ struct mpc_config_processor processor;
+ struct mpc_config_bus bus;
+ struct mpc_config_ioapic ioapic;
+ struct mpc_config_lintsrc lintsrc;
+ int linttypes[2] = { mp_ExtINT, mp_NMI };
+ int i;
+
+ /*
+ * local APIC has default address
+ */
+ mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
+
+ /*
+ * 2 CPUs, numbered 0 & 1.
+ */
+ processor.mpc_type = MP_PROCESSOR;
+ /* Either an integrated APIC or a discrete 82489DX. */
+ processor.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01;
+ processor.mpc_cpuflag = CPU_ENABLED;
+ processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) |
+ (boot_cpu_data.x86_model << 4) |
+ boot_cpu_data.x86_mask;
+ processor.mpc_featureflag = boot_cpu_data.x86_capability[0];
+ processor.mpc_reserved[0] = 0;
+ processor.mpc_reserved[1] = 0;
+ for (i = 0; i < 2; i++) {
+ processor.mpc_apicid = i;
+ MP_processor_info(&processor);
+ }
+
+ bus.mpc_type = MP_BUS;
+ bus.mpc_busid = 0;
+ switch (mpc_default_type) {
+ default:
+ printk(KERN_ERR "???\nUnknown standard configuration
%d\n",
+ mpc_default_type);
+ /* fall through */
+ case 1:
+ case 5:
+ memcpy(bus.mpc_bustype, "ISA ", 6);
+ break;
+ case 2:
+ case 6:
+ case 3:
+ memcpy(bus.mpc_bustype, "EISA ", 6);
+ break;
+ case 4:
+ case 7:
+ memcpy(bus.mpc_bustype, "MCA ", 6);
+ }
+ MP_bus_info(&bus);
+ if (mpc_default_type > 4) {
+ bus.mpc_busid = 1;
+ memcpy(bus.mpc_bustype, "PCI ", 6);
+ MP_bus_info(&bus);
+ }
+
+ ioapic.mpc_type = MP_IOAPIC;
+ ioapic.mpc_apicid = 2;
+ ioapic.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01;
+ ioapic.mpc_flags = MPC_APIC_USABLE;
+ ioapic.mpc_apicaddr = 0xFEC00000;
+ MP_ioapic_info(&ioapic);
+
+ /*
+ * We set up most of the low 16 IO-APIC pins according to MPS rules.
+ */
+ construct_default_ioirq_mptable(mpc_default_type);
+
+ lintsrc.mpc_type = MP_LINTSRC;
+ lintsrc.mpc_irqflag = 0; /* conforming */
+ lintsrc.mpc_srcbusid = 0;
+ lintsrc.mpc_srcbusirq = 0;
+ lintsrc.mpc_destapic = MP_APIC_ALL;
+ for (i = 0; i < 2; i++) {
+ lintsrc.mpc_irqtype = linttypes[i];
+ lintsrc.mpc_destapiclint = i;
+ MP_lintsrc_info(&lintsrc);
+ }
+}
+
+static struct intel_mp_floating *mpf_found;
+
+/*
+ * Scan the memory blocks for an SMP configuration block.
+ */
+void __init get_smp_config (void)
+{
+ struct intel_mp_floating *mpf = mpf_found;
+
+ /*
+ * ACPI may be used to obtain the entire SMP configuration or just to
+ * enumerate/configure processors (CONFIG_ACPI_BOOT). Note that
+ * ACPI supports both logical (e.g. Hyper-Threading) and physical
+ * processors, where MPS only supports physical.
+ */
+ if (acpi_lapic && acpi_ioapic) {
+ printk(KERN_INFO "Using ACPI (MADT) for SMP configuration
information\n");
+ return;
+ }
+ else if (acpi_lapic)
+ printk(KERN_INFO "Using ACPI for processor (LAPIC)
configuration information\n");
+
+ printk("Intel MultiProcessor Specification v1.%d\n",
mpf->mpf_specification);
+ if (mpf->mpf_feature2 & (1<<7)) {
+ printk(KERN_INFO " IMCR and PIC compatibility mode.\n");
+ pic_mode = 1;
+ } else {
+ printk(KERN_INFO " Virtual Wire compatibility mode.\n");
+ pic_mode = 0;
+ }
+
+ /*
+ * Now see if we need to read further.
+ */
+ if (mpf->mpf_feature1 != 0) {
+
+ printk(KERN_INFO "Default MP configuration #%d\n",
mpf->mpf_feature1);
+ construct_default_ISA_mptable(mpf->mpf_feature1);
+
+ } else if (mpf->mpf_physptr) {
+
+ /*
+ * Read the physical hardware table. Anything here will
+ * override the defaults.
+ */
+ if (!smp_read_mpc(isa_bus_to_virt(mpf->mpf_physptr))) {
+ smp_found_config = 0;
+ printk(KERN_ERR "BIOS bug, MP table errors
detected!...\n");
+ printk(KERN_ERR "... disabling SMP support. (tell your
hw vendor)\n");
+ return;
+ }
+ /*
+ * If there are no explicit MP IRQ entries, then we are
+ * broken. We set up most of the low 16 IO-APIC pins to
+ * ISA defaults and hope it will work.
+ */
+ if (!mp_irq_entries) {
+ struct mpc_config_bus bus;
+
+ printk(KERN_ERR "BIOS bug, no explicit IRQ entries,
using default mptable. (tell your hw vendor)\n");
+
+ bus.mpc_type = MP_BUS;
+ bus.mpc_busid = 0;
+ memcpy(bus.mpc_bustype, "ISA ", 6);
+ MP_bus_info(&bus);
+
+ construct_default_ioirq_mptable(0);
+ }
+
+ } else
+ BUG();
+
+ printk(KERN_INFO "Processors: %d\n", num_processors);
+ /*
+ * Only use the first configuration found.
+ */
+}
+
+static int __init smp_scan_config (unsigned long base, unsigned long length)
+{
+ extern void __bad_mpf_size(void);
+ unsigned int *bp = isa_bus_to_virt(base);
+ struct intel_mp_floating *mpf;
+
+ Dprintk("Scan SMP from %p for %ld bytes.\n", bp,length);
+ if (sizeof(*mpf) != 16)
+ __bad_mpf_size();
+
+ while (length > 0) {
+ mpf = (struct intel_mp_floating *)bp;
+ if ((*bp == SMP_MAGIC_IDENT) &&
+ (mpf->mpf_length == 1) &&
+ !mpf_checksum((unsigned char *)bp, 16) &&
+ ((mpf->mpf_specification == 1)
+ || (mpf->mpf_specification == 4)) ) {
+
+ smp_found_config = 1;
+ mpf_found = mpf;
+ return 1;
+ }
+ bp += 4;
+ length -= 16;
+ }
+ return 0;
+}
+
+void __init find_intel_smp (void)
+{
+ unsigned int address;
+
+ /*
+ * FIXME: Linux assumes you have 640K of base ram..
+ * this continues the error...
+ *
+ * 1) Scan the bottom 1K for a signature
+ * 2) Scan the top 1K of base RAM
+ * 3) Scan the 64K of bios
+ */
+ if (smp_scan_config(0x0,0x400) ||
+ smp_scan_config(639*0x400,0x400) ||
+ smp_scan_config(0xF0000,0x10000))
+ return;
+ /*
+ * If it is an SMP machine we should know now, unless the
+ * configuration is in an EISA/MCA bus machine with an
+ * extended bios data area.
+ *
+ * there is a real-mode segmented pointer pointing to the
+ * 4K EBDA area at 0x40E, calculate and scan it here.
+ *
+ * NOTE! There are Linux loaders that will corrupt the EBDA
+ * area, and as such this kind of SMP config may be less
+ * trustworthy, simply because the SMP table may have been
+ * stomped on during early boot. These loaders are buggy and
+ * should be fixed.
+ */
+
+ address = *(unsigned short *)phys_to_virt(0x40E);
+ address <<= 4;
+ if (smp_scan_config(address, 0x1000))
+ return;
+
+ /* If we have come this far, we did not find an MP table */
+ printk(KERN_INFO "No mptable found.\n");
+}
+
+/*
+ * - Intel MP Configuration Table
+ */
+void __init find_smp_config (void)
+{
+#ifdef CONFIG_X86_LOCAL_APIC
+ find_intel_smp();
+#endif
+}
+
+
+/* --------------------------------------------------------------------------
+ ACPI-based MP Configuration
+ --------------------------------------------------------------------------
*/
+
+#ifdef CONFIG_ACPI_BOOT
+
+void __init mp_register_lapic_address (
+ u64 address)
+{
+#ifndef CONFIG_XEN
+ mp_lapic_addr = (unsigned long) address;
+
+ if (boot_cpu_id == -1U)
+ boot_cpu_id = GET_APIC_ID(apic_read(APIC_ID));
+
+ Dprintk("Boot CPU = %d\n", boot_cpu_physical_apicid);
+#endif
+}
+
+
+void __init mp_register_lapic (
+ u8 id,
+ u8 enabled)
+{
+ struct mpc_config_processor processor;
+ int boot_cpu = 0;
+
+ if (id >= MAX_APICS) {
+ printk(KERN_WARNING "Processor #%d invalid (max %d)\n",
+ id, MAX_APICS);
+ return;
+ }
+
+ if (id == boot_cpu_physical_apicid)
+ boot_cpu = 1;
+
+#ifndef CONFIG_XEN
+ processor.mpc_type = MP_PROCESSOR;
+ processor.mpc_apicid = id;
+ processor.mpc_apicver = 0x10; /* TBD: lapic version */
+ processor.mpc_cpuflag = (enabled ? CPU_ENABLED : 0);
+ processor.mpc_cpuflag |= (boot_cpu ? CPU_BOOTPROCESSOR : 0);
+ processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) |
+ (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask;
+ processor.mpc_featureflag = boot_cpu_data.x86_capability[0];
+ processor.mpc_reserved[0] = 0;
+ processor.mpc_reserved[1] = 0;
+#endif
+
+ MP_processor_info(&processor);
+}
+
+#ifdef CONFIG_X86_IO_APIC
+
+#define MP_ISA_BUS 0
+#define MP_MAX_IOAPIC_PIN 127
+
+struct mp_ioapic_routing {
+ int apic_id;
+ int gsi_start;
+ int gsi_end;
+ u32 pin_programmed[4];
+} mp_ioapic_routing[MAX_IO_APICS];
+
+
+static int mp_find_ioapic (
+ int gsi)
+{
+ int i = 0;
+
+ /* Find the IOAPIC that manages this GSI. */
+ for (i = 0; i < nr_ioapics; i++) {
+ if ((gsi >= mp_ioapic_routing[i].gsi_start)
+ && (gsi <= mp_ioapic_routing[i].gsi_end))
+ return i;
+ }
+
+ printk(KERN_ERR "ERROR: Unable to locate IOAPIC for GSI %d\n", gsi);
+
+ return -1;
+}
+
+
+void __init mp_register_ioapic (
+ u8 id,
+ u32 address,
+ u32 gsi_base)
+{
+ int idx = 0;
+
+ if (nr_ioapics >= MAX_IO_APICS) {
+ printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded "
+ "(found %d)\n", MAX_IO_APICS, nr_ioapics);
+ panic("Recompile kernel with bigger MAX_IO_APICS!\n");
+ }
+ if (!address) {
+ printk(KERN_ERR "WARNING: Bogus (zero) I/O APIC address"
+ " found in MADT table, skipping!\n");
+ return;
+ }
+
+ idx = nr_ioapics++;
+
+ mp_ioapics[idx].mpc_type = MP_IOAPIC;
+ mp_ioapics[idx].mpc_flags = MPC_APIC_USABLE;
+ mp_ioapics[idx].mpc_apicaddr = address;
+
+ mp_ioapics[idx].mpc_apicid = io_apic_get_unique_id(idx, id);
+ mp_ioapics[idx].mpc_apicver = io_apic_get_version(idx);
+
+ /*
+ * Build basic IRQ lookup table to facilitate gsi->io_apic lookups
+ * and to prevent reprogramming of IOAPIC pins (PCI IRQs).
+ */
+ mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].mpc_apicid;
+ mp_ioapic_routing[idx].gsi_start = gsi_base;
+ mp_ioapic_routing[idx].gsi_end = gsi_base +
+ io_apic_get_redir_entries(idx);
+
+ printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, "
+ "GSI %d-%d\n", idx, mp_ioapics[idx].mpc_apicid,
+ mp_ioapics[idx].mpc_apicver, mp_ioapics[idx].mpc_apicaddr,
+ mp_ioapic_routing[idx].gsi_start,
+ mp_ioapic_routing[idx].gsi_end);
+
+ return;
+}
+
+
+void __init mp_override_legacy_irq (
+ u8 bus_irq,
+ u8 polarity,
+ u8 trigger,
+ u32 gsi)
+{
+ struct mpc_config_intsrc intsrc;
+ int ioapic = -1;
+ int pin = -1;
+
+ /*
+ * Convert 'gsi' to 'ioapic.pin'.
+ */
+ ioapic = mp_find_ioapic(gsi);
+ if (ioapic < 0)
+ return;
+ pin = gsi - mp_ioapic_routing[ioapic].gsi_start;
+
+ /*
+ * TBD: This check is for faulty timer entries, where the override
+ * erroneously sets the trigger to level, resulting in a HUGE
+ * increase of timer interrupts!
+ */
+ if ((bus_irq == 0) && (trigger == 3))
+ trigger = 1;
+
+ intsrc.mpc_type = MP_INTSRC;
+ intsrc.mpc_irqtype = mp_INT;
+ intsrc.mpc_irqflag = (trigger << 2) | polarity;
+ intsrc.mpc_srcbus = MP_ISA_BUS;
+ intsrc.mpc_srcbusirq = bus_irq; /* IRQ */
+ intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; /* APIC ID */
+ intsrc.mpc_dstirq = pin; /* INTIN# */
+
+ Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, %d-%d\n",
+ intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3,
+ (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus,
+ intsrc.mpc_srcbusirq, intsrc.mpc_dstapic, intsrc.mpc_dstirq);
+
+ mp_irqs[mp_irq_entries] = intsrc;
+ if (++mp_irq_entries == MAX_IRQ_SOURCES)
+ panic("Max # of irq sources exceeded!\n");
+
+ return;
+}
+
+
+void __init mp_config_acpi_legacy_irqs (void)
+{
+ struct mpc_config_intsrc intsrc;
+ int i = 0;
+ int ioapic = -1;
+
+ /*
+ * Fabricate the legacy ISA bus (bus #31).
+ */
+ mp_bus_id_to_type[MP_ISA_BUS] = MP_BUS_ISA;
+ Dprintk("Bus #%d is ISA\n", MP_ISA_BUS);
+
+ /*
+ * Locate the IOAPIC that manages the ISA IRQs (0-15).
+ */
+ ioapic = mp_find_ioapic(0);
+ if (ioapic < 0)
+ return;
+
+ intsrc.mpc_type = MP_INTSRC;
+ intsrc.mpc_irqflag = 0; /* Conforming */
+ intsrc.mpc_srcbus = MP_ISA_BUS;
+ intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid;
+
+ /*
+ * Use the default configuration for the IRQs 0-15. Unless
+ * overridden by (MADT) interrupt source override entries.
+ */
+ for (i = 0; i < 16; i++) {
+ int idx;
+
+ for (idx = 0; idx < mp_irq_entries; idx++) {
+ struct mpc_config_intsrc *irq = mp_irqs + idx;
+
+ /* Do we already have a mapping for this ISA IRQ? */
+ if (irq->mpc_srcbus == MP_ISA_BUS && irq->mpc_srcbusirq
== i)
+ break;
+
+ /* Do we already have a mapping for this IOAPIC pin */
+ if ((irq->mpc_dstapic == intsrc.mpc_dstapic) &&
+ (irq->mpc_dstirq == i))
+ break;
+ }
+
+ if (idx != mp_irq_entries) {
+ printk(KERN_DEBUG "ACPI: IRQ%d used by override.\n", i);
+ continue; /* IRQ already used */
+ }
+
+ intsrc.mpc_irqtype = mp_INT;
+ intsrc.mpc_srcbusirq = i; /* Identity mapped */
+ intsrc.mpc_dstirq = i;
+
+ Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, "
+ "%d-%d\n", intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3,
+ (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus,
+ intsrc.mpc_srcbusirq, intsrc.mpc_dstapic,
+ intsrc.mpc_dstirq);
+
+ mp_irqs[mp_irq_entries] = intsrc;
+ if (++mp_irq_entries == MAX_IRQ_SOURCES)
+ panic("Max # of irq sources exceeded!\n");
+ }
+
+ return;
+}
+
+int mp_register_gsi(u32 gsi, int edge_level, int active_high_low)
+{
+ int ioapic = -1;
+ int ioapic_pin = 0;
+ int idx, bit = 0;
+
+ if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
+ return gsi;
+
+#ifdef CONFIG_ACPI_BUS
+ /* Don't set up the ACPI SCI because it's already set up */
+ if (acpi_fadt.sci_int == gsi)
+ return gsi;
+#endif
+
+ ioapic = mp_find_ioapic(gsi);
+ if (ioapic < 0) {
+ printk(KERN_WARNING "No IOAPIC for GSI %u\n", gsi);
+ return gsi;
+ }
+
+ ioapic_pin = gsi - mp_ioapic_routing[ioapic].gsi_start;
+
+ /*
+ * Avoid pin reprogramming. PRTs typically include entries
+ * with redundant pin->gsi mappings (but unique PCI devices);
+ * we only program the IOAPIC on the first.
+ */
+ bit = ioapic_pin % 32;
+ idx = (ioapic_pin < 32) ? 0 : (ioapic_pin / 32);
+ if (idx > 3) {
+ printk(KERN_ERR "Invalid reference to IOAPIC pin "
+ "%d-%d\n", mp_ioapic_routing[ioapic].apic_id,
+ ioapic_pin);
+ return gsi;
+ }
+ if ((1<<bit) & mp_ioapic_routing[ioapic].pin_programmed[idx]) {
+ Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n",
+ mp_ioapic_routing[ioapic].apic_id, ioapic_pin);
+ return gsi;
+ }
+
+ mp_ioapic_routing[ioapic].pin_programmed[idx] |= (1<<bit);
+
+ io_apic_set_pci_routing(ioapic, ioapic_pin, gsi,
+ edge_level == ACPI_EDGE_SENSITIVE ? 0 : 1,
+ active_high_low == ACPI_ACTIVE_HIGH ? 0 : 1);
+ return gsi;
+}
+
+#endif /*CONFIG_X86_IO_APIC*/
+#endif /*CONFIG_ACPI_BOOT*/
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/ptrace.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/ptrace.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,119 @@
+#ifndef _X86_64_PTRACE_H
+#define _X86_64_PTRACE_H
+
+#if defined(__ASSEMBLY__) || defined(__FRAME_OFFSETS)
+#define R15 0
+#define R14 8
+#define R13 16
+#define R12 24
+#define RBP 32
+#define RBX 40
+/* arguments: interrupts/non tracing syscalls only save upto here*/
+#define R11 48
+#define R10 56
+#define R9 64
+#define R8 72
+#define RAX 80
+#define RCX 88
+#define RDX 96
+#define RSI 104
+#define RDI 112
+#define ORIG_RAX 120 /* = ERROR */
+/* end of arguments */
+/* cpu exception frame or undefined in case of fast syscall. */
+#define RIP 128
+#define CS 136
+#define EFLAGS 144
+#define RSP 152
+#define SS 160
+#define ARGOFFSET R11
+#endif /* __ASSEMBLY__ */
+
+/* top of stack page */
+#define FRAME_SIZE 168
+
+#define PTRACE_OLDSETOPTIONS 21
+
+#ifndef __ASSEMBLY__
+
+struct pt_regs {
+ unsigned long r15;
+ unsigned long r14;
+ unsigned long r13;
+ unsigned long r12;
+ unsigned long rbp;
+ unsigned long rbx;
+/* arguments: non interrupts/non tracing syscalls only save upto here*/
+ unsigned long r11;
+ unsigned long r10;
+ unsigned long r9;
+ unsigned long r8;
+ unsigned long rax;
+ unsigned long rcx;
+ unsigned long rdx;
+ unsigned long rsi;
+ unsigned long rdi;
+ unsigned long orig_rax;
+/* end of arguments */
+/* cpu exception frame or undefined */
+ unsigned long rip;
+ unsigned long cs;
+ unsigned long eflags;
+ unsigned long rsp;
+ unsigned long ss;
+/* top of stack page */
+};
+
+#endif
+
+/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */
+#define PTRACE_GETREGS 12
+#define PTRACE_SETREGS 13
+#define PTRACE_GETFPREGS 14
+#define PTRACE_SETFPREGS 15
+#define PTRACE_GETFPXREGS 18
+#define PTRACE_SETFPXREGS 19
+
+/* only useful for access 32bit programs */
+#define PTRACE_GET_THREAD_AREA 25
+#define PTRACE_SET_THREAD_AREA 26
+
+#define PTRACE_ARCH_PRCTL 30 /* arch_prctl for child */
+
+#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
+#define user_mode(regs) (!!((regs)->cs & 3))
+#define instruction_pointer(regs) ((regs)->rip)
+#if defined(CONFIG_SMP) && defined(CONFIG_FRAME_POINTER)
+extern unsigned long profile_pc(struct pt_regs *regs);
+#else
+#define profile_pc(regs) instruction_pointer(regs)
+#endif
+
+void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
+
+enum {
+ EF_CF = 0x00000001,
+ EF_PF = 0x00000004,
+ EF_AF = 0x00000010,
+ EF_ZF = 0x00000040,
+ EF_SF = 0x00000080,
+ EF_TF = 0x00000100,
+ EF_IE = 0x00000200,
+ EF_DF = 0x00000400,
+ EF_OF = 0x00000800,
+ EF_IOPL = 0x00003000,
+ EF_IOPL_RING0 = 0x00000000,
+ EF_IOPL_RING1 = 0x00001000,
+ EF_IOPL_RING2 = 0x00002000,
+ EF_NT = 0x00004000, /* nested task */
+ EF_RF = 0x00010000, /* resume */
+ EF_VM = 0x00020000, /* virtual mode */
+ EF_AC = 0x00040000, /* alignment */
+ EF_VIF = 0x00080000, /* virtual interrupt */
+ EF_VIP = 0x00100000, /* virtual interrupt pending */
+ EF_ID = 0x00200000, /* id */
+};
+
+#endif
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/linux/highmem.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/linux/highmem.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,106 @@
+#ifndef _LINUX_HIGHMEM_H
+#define _LINUX_HIGHMEM_H
+
+#include <linux/config.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+
+#include <asm/cacheflush.h>
+
+#ifdef CONFIG_HIGHMEM
+
+#include <asm/highmem.h>
+
+/* declarations for linux/mm/highmem.c */
+unsigned int nr_free_highpages(void);
+void kmap_flush_unused(void);
+
+#else /* CONFIG_HIGHMEM */
+
+static inline unsigned int nr_free_highpages(void) { return 0; }
+static inline void kmap_flush_unused(void) { }
+
+static inline void *kmap(struct page *page)
+{
+ might_sleep();
+ return page_address(page);
+}
+
+#define kunmap(page) do { (void) (page); } while (0)
+
+#define kmap_atomic(page, idx) page_address(page)
+#define kunmap_atomic(addr, idx) do { } while (0)
+#define kmap_atomic_to_page(ptr) virt_to_page(ptr)
+
+#endif /* CONFIG_HIGHMEM */
+
+/* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */
+static inline void clear_user_highpage(struct page *page, unsigned long vaddr)
+{
+ void *addr = kmap_atomic(page, KM_USER0);
+ clear_user_page(addr, vaddr, page);
+ kunmap_atomic(addr, KM_USER0);
+ /* Make sure this page is cleared on other CPU's too before using it */
+ smp_wmb();
+}
+
+#ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+static inline struct page *
+alloc_zeroed_user_highpage(struct vm_area_struct *vma, unsigned long vaddr)
+{
+ struct page *page = alloc_page_vma(GFP_HIGHUSER, vma, vaddr);
+
+ if (page)
+ clear_user_highpage(page, vaddr);
+
+ return page;
+}
+#endif
+
+static inline void clear_highpage(struct page *page)
+{
+ void *kaddr = kmap_atomic(page, KM_USER0);
+ clear_page(kaddr);
+ kunmap_atomic(kaddr, KM_USER0);
+}
+
+/*
+ * Same but also flushes aliased cache contents to RAM.
+ */
+static inline void memclear_highpage_flush(struct page *page, unsigned int
offset, unsigned int size)
+{
+ void *kaddr;
+
+ BUG_ON(offset + size > PAGE_SIZE);
+
+ kaddr = kmap_atomic(page, KM_USER0);
+ memset((char *)kaddr + offset, 0, size);
+ flush_dcache_page(page);
+ kunmap_atomic(kaddr, KM_USER0);
+}
+
+static inline void copy_user_highpage(struct page *to, struct page *from,
unsigned long vaddr)
+{
+ char *vfrom, *vto;
+
+ vfrom = kmap_atomic(from, KM_USER0);
+ vto = kmap_atomic(to, KM_USER1);
+ copy_user_page(vto, vfrom, vaddr, to);
+ kunmap_atomic(vfrom, KM_USER0);
+ kunmap_atomic(vto, KM_USER1);
+ /* Make sure this page is cleared on other CPU's too before using it */
+ smp_wmb();
+}
+
+static inline void copy_highpage(struct page *to, struct page *from)
+{
+ char *vfrom, *vto;
+
+ vfrom = kmap_atomic(from, KM_USER0);
+ vto = kmap_atomic(to, KM_USER1);
+ copy_page(vto, vfrom);
+ kunmap_atomic(vfrom, KM_USER0);
+ kunmap_atomic(vto, KM_USER1);
+}
+
+#endif /* _LINUX_HIGHMEM_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/balloon/balloon.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/balloon/balloon.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,438 @@
+/******************************************************************************
+ * balloon.c
+ *
+ * Xen balloon driver - enables returning/claiming memory to/from Xen.
+ *
+ * Copyright (c) 2003, B Dragovic
+ * Copyright (c) 2003-2004, M Williamson, K Fraser
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/smp_lock.h>
+#include <linux/pagemap.h>
+#include <linux/bootmem.h>
+#include <linux/highmem.h>
+#include <linux/vmalloc.h>
+#include <asm-xen/xen_proc.h>
+#include <asm-xen/hypervisor.h>
+#include <asm-xen/ctrl_if.h>
+#include <asm-xen/balloon.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+#include <asm/tlb.h>
+#include <linux/list.h>
+
+static struct proc_dir_entry *balloon_pde;
+
+static DECLARE_MUTEX(balloon_mutex);
+spinlock_t balloon_lock = SPIN_LOCK_UNLOCKED;
+
+/* We aim for 'current allocation' == 'target allocation'. */
+static unsigned long current_pages;
+static unsigned long target_pages;
+
+/* We may hit the hard limit in Xen. If we do then we remember it. */
+static unsigned long hard_limit;
+
+/*
+ * Drivers may alter the memory reservation independently, but they must
+ * inform the balloon driver so that we can avoid hitting the hard limit.
+ */
+static unsigned long driver_pages;
+
+/* List of ballooned pages, threaded through the mem_map array. */
+static LIST_HEAD(ballooned_pages);
+static unsigned long balloon_low, balloon_high;
+
+/* Main work function, always executed in process context. */
+static void balloon_process(void *unused);
+static DECLARE_WORK(balloon_worker, balloon_process, NULL);
+static struct timer_list balloon_timer;
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+/* Use the private and mapping fields of struct page as a list. */
+#define PAGE_TO_LIST(p) ( (struct list_head *)&p->private )
+#define LIST_TO_PAGE(l) ( list_entry( ((unsigned long *)l), \
+ struct page, private ) )
+#define UNLIST_PAGE(p) do { list_del(PAGE_TO_LIST(p)); \
+ p->mapping = NULL; \
+ p->private = 0; } while(0)
+#else
+/* There's a dedicated list field in struct page we can use. */
+#define PAGE_TO_LIST(p) ( &p->list )
+#define LIST_TO_PAGE(l) ( list_entry(l, struct page, list) )
+#define UNLIST_PAGE(p) ( list_del(&p->list) )
+#define pte_offset_kernel pte_offset
+#define pud_t pgd_t
+#define pud_offset(d, va) d
+#define pud_none(d) 0
+#define pud_bad(d) 0
+#define subsys_initcall(_fn) __initcall(_fn)
+#define pfn_to_page(_pfn) (mem_map + (_pfn))
+#endif
+
+#define IPRINTK(fmt, args...) \
+ printk(KERN_INFO "xen_mem: " fmt, ##args)
+#define WPRINTK(fmt, args...) \
+ printk(KERN_WARNING "xen_mem: " fmt, ##args)
+
+/* balloon_append: add the given page to the balloon. */
+static void balloon_append(struct page *page)
+{
+ /* Low memory is re-populated first, so highmem pages go at list tail. */
+ if ( PageHighMem(page) )
+ {
+ list_add_tail(PAGE_TO_LIST(page), &ballooned_pages);
+ balloon_high++;
+ }
+ else
+ {
+ list_add(PAGE_TO_LIST(page), &ballooned_pages);
+ balloon_low++;
+ }
+}
+
+/* balloon_retrieve: rescue a page from the balloon, if it is not empty. */
+static struct page *balloon_retrieve(void)
+{
+ struct page *page;
+
+ if ( list_empty(&ballooned_pages) )
+ return NULL;
+
+ page = LIST_TO_PAGE(ballooned_pages.next);
+ UNLIST_PAGE(page);
+
+ if ( PageHighMem(page) )
+ balloon_high--;
+ else
+ balloon_low--;
+
+ return page;
+}
+
+static void balloon_alarm(unsigned long unused)
+{
+ schedule_work(&balloon_worker);
+}
+
+static unsigned long current_target(void)
+{
+ unsigned long target = min(target_pages, hard_limit);
+ if ( target > (current_pages + balloon_low + balloon_high) )
+ target = current_pages + balloon_low + balloon_high;
+ return target;
+}
+
+/*
+ * We avoid multiple worker processes conflicting via the balloon mutex.
+ * We may of course race updates of the target counts (which are protected
+ * by the balloon lock), or with changes to the Xen hard limit, but we will
+ * recover from these in time.
+ */
+static void balloon_process(void *unused)
+{
+ unsigned long *mfn_list, pfn, i, flags;
+ struct page *page;
+ long credit, debt, rc;
+ void *v;
+
+ down(&balloon_mutex);
+
+ retry:
+ mfn_list = NULL;
+
+ if ( (credit = current_target() - current_pages) > 0 )
+ {
+ mfn_list = (unsigned long *)vmalloc(credit * sizeof(*mfn_list));
+ if ( mfn_list == NULL )
+ goto out;
+
+ balloon_lock(flags);
+ rc = HYPERVISOR_dom_mem_op(
+ MEMOP_increase_reservation, mfn_list, credit, 0);
+ balloon_unlock(flags);
+ if ( rc < credit )
+ {
+ /* We hit the Xen hard limit: reprobe. */
+ if ( HYPERVISOR_dom_mem_op(
+ MEMOP_decrease_reservation, mfn_list, rc, 0) != rc )
+ BUG();
+ hard_limit = current_pages + rc - driver_pages;
+ vfree(mfn_list);
+ goto retry;
+ }
+
+ for ( i = 0; i < credit; i++ )
+ {
+ if ( (page = balloon_retrieve()) == NULL )
+ BUG();
+
+ pfn = page - mem_map;
+ if ( phys_to_machine_mapping[pfn] != INVALID_P2M_ENTRY )
+ BUG();
+
+ /* Update P->M and M->P tables. */
+ phys_to_machine_mapping[pfn] = mfn_list[i];
+ xen_machphys_update(mfn_list[i], pfn);
+
+ /* Link back into the page tables if it's not a highmem page. */
+ if ( pfn < max_low_pfn )
+ {
+ HYPERVISOR_update_va_mapping(
+ (unsigned long)__va(pfn << PAGE_SHIFT),
+ __pte_ma((mfn_list[i] << PAGE_SHIFT) |
+ pgprot_val(PAGE_KERNEL)),
+ 0);
+ }
+
+ /* Finally, relinquish the memory back to the system allocator. */
+ ClearPageReserved(page);
+ set_page_count(page, 1);
+ __free_page(page);
+ }
+
+ current_pages += credit;
+ }
+ else if ( credit < 0 )
+ {
+ debt = -credit;
+
+ mfn_list = (unsigned long *)vmalloc(debt * sizeof(*mfn_list));
+ if ( mfn_list == NULL )
+ goto out;
+
+ for ( i = 0; i < debt; i++ )
+ {
+ if ( (page = alloc_page(GFP_HIGHUSER)) == NULL )
+ {
+ debt = i;
+ break;
+ }
+
+ pfn = page - mem_map;
+ mfn_list[i] = phys_to_machine_mapping[pfn];
+
+ if ( !PageHighMem(page) )
+ {
+ v = phys_to_virt(pfn << PAGE_SHIFT);
+ scrub_pages(v, 1);
+ HYPERVISOR_update_va_mapping(
+ (unsigned long)v, __pte_ma(0), 0);
+ }
+#ifdef CONFIG_XEN_SCRUB_PAGES
+ else
+ {
+ v = kmap(page);
+ scrub_pages(v, 1);
+ kunmap(page);
+ }
+#endif
+ }
+
+ /* Ensure that ballooned highmem pages don't have cached mappings. */
+ kmap_flush_unused();
+ flush_tlb_all();
+
+ /* No more mappings: invalidate pages in P2M and add to balloon. */
+ for ( i = 0; i < debt; i++ )
+ {
+ pfn = mfn_to_pfn(mfn_list[i]);
+ phys_to_machine_mapping[pfn] = INVALID_P2M_ENTRY;
+ balloon_append(pfn_to_page(pfn));
+ }
+
+ if ( HYPERVISOR_dom_mem_op(
+ MEMOP_decrease_reservation, mfn_list, debt, 0) != debt )
+ BUG();
+
+ current_pages -= debt;
+ }
+
+ out:
+ if ( mfn_list != NULL )
+ vfree(mfn_list);
+
+ /* Schedule more work if there is some still to be done. */
+ if ( current_target() != current_pages )
+ mod_timer(&balloon_timer, jiffies + HZ);
+
+ up(&balloon_mutex);
+}
+
+/* Resets the Xen limit, sets new target, and kicks off processing. */
+static void set_new_target(unsigned long target)
+{
+ /* No need for lock. Not read-modify-write updates. */
+ hard_limit = ~0UL;
+ target_pages = target;
+ schedule_work(&balloon_worker);
+}
+
+static void balloon_ctrlif_rx(ctrl_msg_t *msg, unsigned long id)
+{
+ switch ( msg->subtype )
+ {
+ case CMSG_MEM_REQUEST_SET:
+ {
+ mem_request_t *req = (mem_request_t *)&msg->msg[0];
+ set_new_target(req->target);
+ req->status = 0;
+ }
+ break;
+
+ default:
+ msg->length = 0;
+ break;
+ }
+
+ ctrl_if_send_response(msg);
+}
+
+static int balloon_write(struct file *file, const char __user *buffer,
+ unsigned long count, void *data)
+{
+ char memstring[64], *endchar;
+ unsigned long long target_bytes;
+
+ if ( !capable(CAP_SYS_ADMIN) )
+ return -EPERM;
+
+ if ( count <= 1 )
+ return -EBADMSG; /* runt */
+ if ( count > sizeof(memstring) )
+ return -EFBIG; /* too long */
+
+ if ( copy_from_user(memstring, buffer, count) )
+ return -EFAULT;
+ memstring[sizeof(memstring)-1] = '\0';
+
+ target_bytes = memparse(memstring, &endchar);
+ set_new_target(target_bytes >> PAGE_SHIFT);
+
+ return count;
+}
+
+static int balloon_read(char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ int len;
+
+#define K(_p) ((_p)<<(PAGE_SHIFT-10))
+ len = sprintf(
+ page,
+ "Current allocation: %8lu kB\n"
+ "Requested target: %8lu kB\n"
+ "Low-mem balloon: %8lu kB\n"
+ "High-mem balloon: %8lu kB\n"
+ "Xen hard limit: ",
+ K(current_pages), K(target_pages), K(balloon_low), K(balloon_high));
+
+ if ( hard_limit != ~0UL )
+ len += sprintf(
+ page + len,
+ "%8lu kB (inc. %8lu kB driver headroom)\n",
+ K(hard_limit), K(driver_pages));
+ else
+ len += sprintf(
+ page + len,
+ " ??? kB\n");
+
+ *eof = 1;
+ return len;
+}
+
+static int __init balloon_init(void)
+{
+ unsigned long pfn;
+ struct page *page;
+
+ IPRINTK("Initialising balloon driver.\n");
+
+ current_pages = min(xen_start_info.nr_pages, max_pfn);
+ target_pages = current_pages;
+ balloon_low = 0;
+ balloon_high = 0;
+ driver_pages = 0UL;
+ hard_limit = ~0UL;
+
+ init_timer(&balloon_timer);
+ balloon_timer.data = 0;
+ balloon_timer.function = balloon_alarm;
+
+ if ( (balloon_pde = create_xen_proc_entry("balloon", 0644)) == NULL )
+ {
+ WPRINTK("Unable to create /proc/xen/balloon.\n");
+ return -1;
+ }
+
+ balloon_pde->read_proc = balloon_read;
+ balloon_pde->write_proc = balloon_write;
+
+ (void)ctrl_if_register_receiver(CMSG_MEM_REQUEST, balloon_ctrlif_rx, 0);
+
+ /* Initialise the balloon with excess memory space. */
+ for ( pfn = xen_start_info.nr_pages; pfn < max_pfn; pfn++ )
+ {
+ page = &mem_map[pfn];
+ if ( !PageReserved(page) )
+ balloon_append(page);
+ }
+
+ return 0;
+}
+
+subsys_initcall(balloon_init);
+
+void balloon_update_driver_allowance(long delta)
+{
+ unsigned long flags;
+ balloon_lock(flags);
+ driver_pages += delta; /* non-atomic update */
+ balloon_unlock(flags);
+}
+
+void balloon_put_pages(unsigned long *mfn_list, unsigned long nr_mfns)
+{
+ unsigned long flags;
+
+ balloon_lock(flags);
+ if ( HYPERVISOR_dom_mem_op(MEMOP_decrease_reservation,
+ mfn_list, nr_mfns, 0) != nr_mfns )
+ BUG();
+ current_pages -= nr_mfns; /* non-atomic update */
+ balloon_unlock(flags);
+
+ schedule_work(&balloon_worker);
+}
+
+EXPORT_SYMBOL(balloon_update_driver_allowance);
+EXPORT_SYMBOL(balloon_put_pages);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/mm/ioremap.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/mm/ioremap.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,466 @@
+/*
+ * arch/x86_64/mm/ioremap.c
+ *
+ * Re-map IO memory to kernel address space so that we can access it.
+ * This is needed for high PCI addresses that aren't mapped in the
+ * 640k-1MB IO memory area on PC's
+ *
+ * (C) Copyright 1995 1996 Linus Torvalds
+ */
+
+#include <linux/vmalloc.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <asm/io.h>
+#include <asm/fixmap.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+
+/*
+ * Reuse arch/xen/i396/mm/ioremap.c. Need to merge later
+ */
+#ifndef CONFIG_XEN_PHYSDEV_ACCESS
+
+void * __ioremap(unsigned long phys_addr, unsigned long size,
+ unsigned long flags)
+{
+ return NULL;
+}
+
+void *ioremap_nocache (unsigned long phys_addr, unsigned long size)
+{
+ return NULL;
+}
+
+void iounmap(volatile void __iomem *addr)
+{
+}
+
+void __init *bt_ioremap(unsigned long phys_addr, unsigned long size)
+{
+ return NULL;
+}
+
+void __init bt_iounmap(void *addr, unsigned long size)
+{
+}
+
+#else
+
+#if defined(__i386__)
+/*
+ * Does @address reside within a non-highmem page that is local to this virtual
+ * machine (i.e., not an I/O page, nor a memory page belonging to another VM).
+ * See the comment that accompanies pte_pfn() in pgtable-2level.h to understand
+ * why this works.
+ */
+static inline int is_local_lowmem(unsigned long address)
+{
+ extern unsigned long max_low_pfn;
+ unsigned long mfn = address >> PAGE_SHIFT;
+ unsigned long pfn = mfn_to_pfn(mfn);
+ return ((pfn < max_low_pfn) && (pfn_to_mfn(pfn) == mfn));
+}
+#elif defined(__x86_64__)
+/*
+ *
+ */
+static inline int is_local_lowmem(unsigned long address)
+{
+ return 0;
+}
+#endif
+
+/*
+ * Generic mapping function (not visible outside):
+ */
+
+/*
+ * Remap an arbitrary physical address space into the kernel virtual
+ * address space. Needed when the kernel wants to access high addresses
+ * directly.
+ *
+ * NOTE! We need to allow non-page-aligned mappings too: we will obviously
+ * have to convert them into an offset in a page-aligned mapping, but the
+ * caller shouldn't need to know that small detail.
+ */
+void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned
long flags)
+{
+ void __iomem * addr;
+ struct vm_struct * area;
+ unsigned long offset, last_addr;
+ domid_t domid = DOMID_IO;
+
+ /* Don't allow wraparound or zero size */
+ last_addr = phys_addr + size - 1;
+ if (!size || last_addr < phys_addr)
+ return NULL;
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ /*
+ * Don't remap the low PCI/ISA area, it's always mapped..
+ */
+ if (phys_addr >= 0x0 && last_addr < 0x100000)
+ return isa_bus_to_virt(phys_addr);
+#endif
+
+ /*
+ * Don't allow anybody to remap normal RAM that we're using..
+ */
+ if (is_local_lowmem(phys_addr)) {
+ char *t_addr, *t_end;
+ struct page *page;
+
+ t_addr = bus_to_virt(phys_addr);
+ t_end = t_addr + (size - 1);
+
+ for(page = virt_to_page(t_addr); page <= virt_to_page(t_end);
page++)
+ if(!PageReserved(page))
+ return NULL;
+
+ domid = DOMID_LOCAL;
+ }
+
+ /*
+ * Mappings have to be page-aligned
+ */
+ offset = phys_addr & ~PAGE_MASK;
+ phys_addr &= PAGE_MASK;
+ size = PAGE_ALIGN(last_addr+1) - phys_addr;
+
+ /*
+ * Ok, go for it..
+ */
+ area = get_vm_area(size, VM_IOREMAP | (flags << 20));
+ if (!area)
+ return NULL;
+ area->phys_addr = phys_addr;
+ addr = (void __iomem *) area->addr;
+ if (direct_remap_area_pages(&init_mm, (unsigned long) addr, phys_addr,
+ size, __pgprot(_PAGE_PRESENT | _PAGE_RW |
+ _PAGE_DIRTY | _PAGE_ACCESSED
+#if defined(__x86_64__)
+ | _PAGE_USER
+#endif
+ | flags), domid)) {
+ vunmap((void __force *) addr);
+ return NULL;
+ }
+ return (void __iomem *) (offset + (char __iomem *)addr);
+}
+
+
+/**
+ * ioremap_nocache - map bus memory into CPU space
+ * @offset: bus address of the memory
+ * @size: size of the resource to map
+ *
+ * ioremap_nocache performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * This version of ioremap ensures that the memory is marked uncachable
+ * on the CPU as well as honouring existing caching rules from things like
+ * the PCI bus. Note that there are other caches and buffers on many
+ * busses. In particular driver authors should read up on PCI writes
+ *
+ * It's useful if some control registers are in such an area and
+ * write combining or read caching is not desirable:
+ *
+ * Must be freed with iounmap.
+ */
+
+void __iomem *ioremap_nocache (unsigned long phys_addr, unsigned long size)
+{
+ unsigned long last_addr;
+ void __iomem *p = __ioremap(phys_addr, size, _PAGE_PCD);
+ if (!p)
+ return p;
+
+ /* Guaranteed to be > phys_addr, as per __ioremap() */
+ last_addr = phys_addr + size - 1;
+
+ if (is_local_lowmem(last_addr)) {
+ struct page *ppage = virt_to_page(bus_to_virt(phys_addr));
+ unsigned long npages;
+
+ phys_addr &= PAGE_MASK;
+
+ /* This might overflow and become zero.. */
+ last_addr = PAGE_ALIGN(last_addr);
+
+ /* .. but that's ok, because modulo-2**n arithmetic will make
+ * the page-aligned "last - first" come out right.
+ */
+ npages = (last_addr - phys_addr) >> PAGE_SHIFT;
+
+ if (change_page_attr(ppage, npages, PAGE_KERNEL_NOCACHE) < 0) {
+ iounmap(p);
+ p = NULL;
+ }
+ global_flush_tlb();
+ }
+
+ return p;
+}
+
+void iounmap(volatile void __iomem *addr)
+{
+ struct vm_struct *p;
+ if ((void __force *) addr <= high_memory)
+ return;
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ if ((unsigned long) addr >= fix_to_virt(FIX_ISAMAP_BEGIN))
+ return;
+#endif
+ p = remove_vm_area((void *) (PAGE_MASK & (unsigned long __force) addr));
+ if (!p) {
+ printk("__iounmap: bad address %p\n", addr);
+ return;
+ }
+
+ if ((p->flags >> 20) && is_local_lowmem(p->phys_addr)) {
+ /* p->size includes the guard page, but cpa doesn't like that */
+ change_page_attr(virt_to_page(bus_to_virt(p->phys_addr)),
+ (p->size - PAGE_SIZE) >> PAGE_SHIFT,
+ PAGE_KERNEL);
+ global_flush_tlb();
+ }
+ kfree(p);
+}
+
+#if defined(__i386__)
+void __init *bt_ioremap(unsigned long phys_addr, unsigned long size)
+{
+ unsigned long offset, last_addr;
+ unsigned int nrpages;
+ enum fixed_addresses idx;
+
+ /* Don't allow wraparound or zero size */
+ last_addr = phys_addr + size - 1;
+ if (!size || last_addr < phys_addr)
+ return NULL;
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ /*
+ * Don't remap the low PCI/ISA area, it's always mapped..
+ */
+ if (phys_addr >= 0x0 && last_addr < 0x100000)
+ return isa_bus_to_virt(phys_addr);
+#endif
+
+ /*
+ * Mappings have to be page-aligned
+ */
+ offset = phys_addr & ~PAGE_MASK;
+ phys_addr &= PAGE_MASK;
+ size = PAGE_ALIGN(last_addr) - phys_addr;
+
+ /*
+ * Mappings have to fit in the FIX_BTMAP area.
+ */
+ nrpages = size >> PAGE_SHIFT;
+ if (nrpages > NR_FIX_BTMAPS)
+ return NULL;
+
+ /*
+ * Ok, go for it..
+ */
+ idx = FIX_BTMAP_BEGIN;
+ while (nrpages > 0) {
+ set_fixmap(idx, phys_addr);
+ phys_addr += PAGE_SIZE;
+ --idx;
+ --nrpages;
+ }
+ return (void*) (offset + fix_to_virt(FIX_BTMAP_BEGIN));
+}
+
+void __init bt_iounmap(void *addr, unsigned long size)
+{
+ unsigned long virt_addr;
+ unsigned long offset;
+ unsigned int nrpages;
+ enum fixed_addresses idx;
+
+ virt_addr = (unsigned long)addr;
+ if (virt_addr < fix_to_virt(FIX_BTMAP_BEGIN))
+ return;
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ if (virt_addr >= fix_to_virt(FIX_ISAMAP_BEGIN))
+ return;
+#endif
+ offset = virt_addr & ~PAGE_MASK;
+ nrpages = PAGE_ALIGN(offset + size - 1) >> PAGE_SHIFT;
+
+ idx = FIX_BTMAP_BEGIN;
+ while (nrpages > 0) {
+ clear_fixmap(idx);
+ --idx;
+ --nrpages;
+ }
+}
+#endif /* defined(__i386__) */
+
+#endif /* CONFIG_XEN_PHYSDEV_ACCESS */
+
+/* These hacky macros avoid phys->machine translations. */
+#define __direct_pte(x) ((pte_t) { (x) } )
+#define __direct_mk_pte(page_nr,pgprot) \
+ __direct_pte(((page_nr) << PAGE_SHIFT) | pgprot_val(pgprot))
+#define direct_mk_pte_phys(physpage, pgprot) \
+ __direct_mk_pte((physpage) >> PAGE_SHIFT, pgprot)
+
+static inline void direct_remap_area_pte(pte_t *pte,
+ unsigned long address,
+ unsigned long size,
+ mmu_update_t **v)
+{
+ unsigned long end;
+
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ if (address >= end)
+ BUG();
+
+ do {
+ (*v)->ptr = virt_to_machine(pte);
+ (*v)++;
+ address += PAGE_SIZE;
+ pte++;
+ } while (address && (address < end));
+}
+
+static inline int direct_remap_area_pmd(struct mm_struct *mm,
+ pmd_t *pmd,
+ unsigned long address,
+ unsigned long size,
+ mmu_update_t **v)
+{
+ unsigned long end;
+
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ if (address >= end)
+ BUG();
+ do {
+ pte_t *pte = (mm == &init_mm) ?
+ pte_alloc_kernel(mm, pmd, address) :
+ pte_alloc_map(mm, pmd, address);
+ if (!pte)
+ return -ENOMEM;
+ direct_remap_area_pte(pte, address, end - address, v);
+ pte_unmap(pte);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+ return 0;
+}
+
+int __direct_remap_area_pages(struct mm_struct *mm,
+ unsigned long address,
+ unsigned long size,
+ mmu_update_t *v)
+{
+ pgd_t * dir;
+ unsigned long end = address + size;
+ int error;
+
+#if defined(__i386__)
+ dir = pgd_offset(mm, address);
+#elif defined (__x86_64)
+ dir = (mm == &init_mm) ?
+ pgd_offset_k(address):
+ pgd_offset(mm, address);
+#endif
+ if (address >= end)
+ BUG();
+ spin_lock(&mm->page_table_lock);
+ do {
+ pud_t *pud;
+ pmd_t *pmd;
+
+ error = -ENOMEM;
+ pud = pud_alloc(mm, dir, address);
+ if (!pud)
+ break;
+ pmd = pmd_alloc(mm, pud, address);
+ if (!pmd)
+ break;
+ error = 0;
+ direct_remap_area_pmd(mm, pmd, address, end - address, &v);
+ address = (address + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+
+ } while (address && (address < end));
+ spin_unlock(&mm->page_table_lock);
+ return error;
+}
+
+
+int direct_remap_area_pages(struct mm_struct *mm,
+ unsigned long address,
+ unsigned long machine_addr,
+ unsigned long size,
+ pgprot_t prot,
+ domid_t domid)
+{
+ int i;
+ unsigned long start_address;
+#define MAX_DIRECTMAP_MMU_QUEUE 130
+ mmu_update_t u[MAX_DIRECTMAP_MMU_QUEUE], *v = u;
+
+ start_address = address;
+
+ flush_cache_all();
+
+ for (i = 0; i < size; i += PAGE_SIZE) {
+ if ((v - u) == MAX_DIRECTMAP_MMU_QUEUE) {
+ /* Fill in the PTE pointers. */
+ __direct_remap_area_pages(mm,
+ start_address,
+ address-start_address,
+ u);
+
+ if (HYPERVISOR_mmu_update(u, v - u, NULL, domid) < 0)
+ return -EFAULT;
+ v = u;
+ start_address = address;
+ }
+
+ /*
+ * Fill in the machine address: PTE ptr is done later by
+ * __direct_remap_area_pages().
+ */
+ v->val = (machine_addr & PAGE_MASK) | pgprot_val(prot);
+
+ machine_addr += PAGE_SIZE;
+ address += PAGE_SIZE;
+ v++;
+ }
+
+ if (v != u) {
+ /* get the ptep's filled in */
+ __direct_remap_area_pages(mm,
+ start_address,
+ address-start_address,
+ u);
+ if (unlikely(HYPERVISOR_mmu_update(u, v - u, NULL, domid) < 0))
+ return -EFAULT;
+ }
+
+ flush_tlb_all();
+
+ return 0;
+}
+
+EXPORT_SYMBOL(direct_remap_area_pages);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/privcmd/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/privcmd/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,2 @@
+
+obj-y := privcmd.o
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/ioport.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/ioport.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,129 @@
+/*
+ * linux/arch/i386/kernel/ioport.c
+ *
+ * This contains the io-permission bitmap code - written by obz, with changes
+ * by Linus.
+ */
+
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/ioport.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/stddef.h>
+#include <linux/slab.h>
+#include <linux/thread_info.h>
+#include <asm-xen/xen-public/physdev.h>
+
+/* Set EXTENT bits starting at BASE in BITMAP to value TURN_ON. */
+static void set_bitmap(unsigned long *bitmap, unsigned int base, unsigned int
extent, int new_value)
+{
+ unsigned long mask;
+ unsigned long *bitmap_base = bitmap + (base / BITS_PER_LONG);
+ unsigned int low_index = base & (BITS_PER_LONG-1);
+ int length = low_index + extent;
+
+ if (low_index != 0) {
+ mask = (~0UL << low_index);
+ if (length < BITS_PER_LONG)
+ mask &= ~(~0UL << length);
+ if (new_value)
+ *bitmap_base++ |= mask;
+ else
+ *bitmap_base++ &= ~mask;
+ length -= BITS_PER_LONG;
+ }
+
+ mask = (new_value ? ~0UL : 0UL);
+ while (length >= BITS_PER_LONG) {
+ *bitmap_base++ = mask;
+ length -= BITS_PER_LONG;
+ }
+
+ if (length > 0) {
+ mask = ~(~0UL << length);
+ if (new_value)
+ *bitmap_base++ |= mask;
+ else
+ *bitmap_base++ &= ~mask;
+ }
+}
+
+
+/*
+ * this changes the io permissions bitmap in the current task.
+ */
+asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
+{
+ struct thread_struct * t = ¤t->thread;
+ unsigned long *bitmap;
+ physdev_op_t op;
+
+ if ((from + num <= from) || (from + num > IO_BITMAP_BITS))
+ return -EINVAL;
+ if (turn_on && !capable(CAP_SYS_RAWIO))
+ return -EPERM;
+
+ /*
+ * If it's the first ioperm() call in this thread's lifetime, set the
+ * IO bitmap up. ioperm() is much less timing critical than clone(),
+ * this is why we delay this operation until now:
+ */
+ if (!t->io_bitmap_ptr) {
+ bitmap = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL);
+ if (!bitmap)
+ return -ENOMEM;
+
+ memset(bitmap, 0xff, IO_BITMAP_BYTES);
+ t->io_bitmap_ptr = bitmap;
+
+ op.cmd = PHYSDEVOP_SET_IOBITMAP;
+ op.u.set_iobitmap.bitmap = (unsigned long)bitmap;
+ op.u.set_iobitmap.nr_ports = IO_BITMAP_BITS;
+ HYPERVISOR_physdev_op(&op);
+ }
+
+ set_bitmap(t->io_bitmap_ptr, from, num, !turn_on);
+
+ return 0;
+}
+
+/*
+ * sys_iopl has to be used when you want to access the IO ports
+ * beyond the 0x3ff range: to get the full 65536 ports bitmapped
+ * you'd need 8kB of bitmaps/process, which is a bit excessive.
+ *
+ * Here we just change the eflags value on the stack: we allow
+ * only the super-user to do it. This depends on the stack-layout
+ * on system-call entry - see also fork() and the signal handling
+ * code.
+ */
+
+asmlinkage long sys_iopl(unsigned int new_io_pl)
+{
+ unsigned int old_io_pl = current->thread.io_pl;
+ physdev_op_t op;
+
+ if (new_io_pl > 3)
+ return -EINVAL;
+
+ /* Need "raw I/O" privileges for direct port access. */
+ if ((new_io_pl > old_io_pl) && !capable(CAP_SYS_RAWIO))
+ return -EPERM;
+
+ /* Maintain OS privileges even if user attempts to relinquish them. */
+ if (new_io_pl == 0)
+ new_io_pl = 1;
+
+ /* Change our version of the privilege levels. */
+ current->thread.io_pl = new_io_pl;
+
+ /* Force the change at ring 0. */
+ op.cmd = PHYSDEVOP_SET_IOPL;
+ op.u.set_iopl.iopl = new_io_pl;
+ HYPERVISOR_physdev_op(&op);
+
+ return 0;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/Kconfig
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/Kconfig Fri Jul 15 13:39:50 2005
@@ -0,0 +1,921 @@
+#
+# For a description of the syntax of this configuration file,
+# see Documentation/kbuild/kconfig-language.txt.
+#
+
+menu "X86 Processor Configuration"
+
+config XENARCH
+ string
+ default i386
+
+config X86
+ bool
+ default y
+ help
+ This is Linux's home port. Linux was originally native to the Intel
+ 386, and runs on all the later x86 processors including the Intel
+ 486, 586, Pentiums, and various instruction-set-compatible chips by
+ AMD, Cyrix, and others.
+
+config MMU
+ bool
+ default y
+
+config SBUS
+ bool
+
+config UID16
+ bool
+ default y
+
+config GENERIC_ISA_DMA
+ bool
+ default y
+
+config GENERIC_IOMAP
+ bool
+ default y
+
+choice
+ prompt "Processor family"
+ default M686
+
+config M386
+ bool "386"
+ ---help---
+ This is the processor type of your CPU. This information is used for
+ optimizing purposes. In order to compile a kernel that can run on
+ all x86 CPU types (albeit not optimally fast), you can specify
+ "386" here.
+
+ The kernel will not necessarily run on earlier architectures than
+ the one you have chosen, e.g. a Pentium optimized kernel will run on
+ a PPro, but not necessarily on a i486.
+
+ Here are the settings recommended for greatest speed:
+ - "386" for the AMD/Cyrix/Intel 386DX/DXL/SL/SLC/SX, Cyrix/TI
+ 486DLC/DLC2, UMC 486SX-S and NexGen Nx586. Only "386" kernels
+ will run on a 386 class machine.
+ - "486" for the AMD/Cyrix/IBM/Intel 486DX/DX2/DX4 or
+ SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S.
+ - "586" for generic Pentium CPUs lacking the TSC
+ (time stamp counter) register.
+ - "Pentium-Classic" for the Intel Pentium.
+ - "Pentium-MMX" for the Intel Pentium MMX.
+ - "Pentium-Pro" for the Intel Pentium Pro.
+ - "Pentium-II" for the Intel Pentium II or pre-Coppermine Celeron.
+ - "Pentium-III" for the Intel Pentium III or Coppermine Celeron.
+ - "Pentium-4" for the Intel Pentium 4 or P4-based Celeron.
+ - "K6" for the AMD K6, K6-II and K6-III (aka K6-3D).
+ - "Athlon" for the AMD K7 family (Athlon/Duron/Thunderbird).
+ - "Crusoe" for the Transmeta Crusoe series.
+ - "Efficeon" for the Transmeta Efficeon series.
+ - "Winchip-C6" for original IDT Winchip.
+ - "Winchip-2" for IDT Winchip 2.
+ - "Winchip-2A" for IDT Winchips with 3dNow! capabilities.
+ - "CyrixIII/VIA C3" for VIA Cyrix III or VIA C3.
+ - "VIA C3-2 for VIA C3-2 "Nehemiah" (model 9 and above).
+
+ If you don't know what to do, choose "386".
+
+config M486
+ bool "486"
+ help
+ Select this for a 486 series processor, either Intel or one of the
+ compatible processors from AMD, Cyrix, IBM, or Intel. Includes DX,
+ DX2, and DX4 variants; also SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or
+ U5S.
+
+config M586
+ bool "586/K5/5x86/6x86/6x86MX"
+ help
+ Select this for an 586 or 686 series processor such as the AMD K5,
+ the Cyrix 5x86, 6x86 and 6x86MX. This choice does not
+ assume the RDTSC (Read Time Stamp Counter) instruction.
+
+config M586TSC
+ bool "Pentium-Classic"
+ help
+ Select this for a Pentium Classic processor with the RDTSC (Read
+ Time Stamp Counter) instruction for benchmarking.
+
+config M586MMX
+ bool "Pentium-MMX"
+ help
+ Select this for a Pentium with the MMX graphics/multimedia
+ extended instructions.
+
+config M686
+ bool "Pentium-Pro"
+ help
+ Select this for Intel Pentium Pro chips. This enables the use of
+ Pentium Pro extended instructions, and disables the init-time guard
+ against the f00f bug found in earlier Pentiums.
+
+config MPENTIUMII
+ bool "Pentium-II/Celeron(pre-Coppermine)"
+ help
+ Select this for Intel chips based on the Pentium-II and
+ pre-Coppermine Celeron core. This option enables an unaligned
+ copy optimization, compiles the kernel with optimization flags
+ tailored for the chip, and applies any applicable Pentium Pro
+ optimizations.
+
+config MPENTIUMIII
+ bool "Pentium-III/Celeron(Coppermine)/Pentium-III Xeon"
+ help
+ Select this for Intel chips based on the Pentium-III and
+ Celeron-Coppermine core. This option enables use of some
+ extended prefetch instructions in addition to the Pentium II
+ extensions.
+
+config MPENTIUMM
+ bool "Pentium M"
+ help
+ Select this for Intel Pentium M (not Pentium-4 M)
+ notebook chips.
+
+config MPENTIUM4
+ bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/Xeon"
+ help
+ Select this for Intel Pentium 4 chips. This includes the
+ Pentium 4, P4-based Celeron and Xeon, and Pentium-4 M
+ (not Pentium M) chips. This option enables compile flags
+ optimized for the chip, uses the correct cache shift, and
+ applies any applicable Pentium III optimizations.
+
+config MK6
+ bool "K6/K6-II/K6-III"
+ help
+ Select this for an AMD K6-family processor. Enables use of
+ some extended instructions, and passes appropriate optimization
+ flags to GCC.
+
+config MK7
+ bool "Athlon/Duron/K7"
+ help
+ Select this for an AMD Athlon K7-family processor. Enables use of
+ some extended instructions, and passes appropriate optimization
+ flags to GCC.
+
+config MK8
+ bool "Opteron/Athlon64/Hammer/K8"
+ help
+ Select this for an AMD Opteron or Athlon64 Hammer-family processor.
Enables
+ use of some extended instructions, and passes appropriate optimization
+ flags to GCC.
+
+config MCRUSOE
+ bool "Crusoe"
+ help
+ Select this for a Transmeta Crusoe processor. Treats the processor
+ like a 586 with TSC, and sets some GCC optimization flags (like a
+ Pentium Pro with no alignment requirements).
+
+config MEFFICEON
+ bool "Efficeon"
+ help
+ Select this for a Transmeta Efficeon processor.
+
+config MWINCHIPC6
+ bool "Winchip-C6"
+ help
+ Select this for an IDT Winchip C6 chip. Linux and GCC
+ treat this chip as a 586TSC with some extended instructions
+ and alignment requirements.
+
+config MWINCHIP2
+ bool "Winchip-2"
+ help
+ Select this for an IDT Winchip-2. Linux and GCC
+ treat this chip as a 586TSC with some extended instructions
+ and alignment requirements.
+
+config MWINCHIP3D
+ bool "Winchip-2A/Winchip-3"
+ help
+ Select this for an IDT Winchip-2A or 3. Linux and GCC
+ treat this chip as a 586TSC with some extended instructions
+ and alignment reqirements. Also enable out of order memory
+ stores for this CPU, which can increase performance of some
+ operations.
+
+config MCYRIXIII
+ bool "CyrixIII/VIA-C3"
+ help
+ Select this for a Cyrix III or C3 chip. Presently Linux and GCC
+ treat this chip as a generic 586. Whilst the CPU is 686 class,
+ it lacks the cmov extension which gcc assumes is present when
+ generating 686 code.
+ Note that Nehemiah (Model 9) and above will not boot with this
+ kernel due to them lacking the 3DNow! instructions used in earlier
+ incarnations of the CPU.
+
+config MVIAC3_2
+ bool "VIA C3-2 (Nehemiah)"
+ help
+ Select this for a VIA C3 "Nehemiah". Selecting this enables usage
+ of SSE and tells gcc to treat the CPU as a 686.
+ Note, this kernel will not boot on older (pre model 9) C3s.
+
+endchoice
+
+config X86_GENERIC
+ bool "Generic x86 support"
+ help
+ Instead of just including optimizations for the selected
+ x86 variant (e.g. PII, Crusoe or Athlon), include some more
+ generic optimizations as well. This will make the kernel
+ perform better on x86 CPUs other than that selected.
+
+ This is really intended for distributors who need more
+ generic optimizations.
+
+#
+# Define implied options from the CPU selection here
+#
+config X86_CMPXCHG
+ bool
+ depends on !M386
+ default y
+
+config X86_XADD
+ bool
+ depends on !M386
+ default y
+
+config X86_L1_CACHE_SHIFT
+ int
+ default "7" if MPENTIUM4 || X86_GENERIC
+ default "4" if X86_ELAN || M486 || M386
+ default "5" if MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCRUSOE ||
MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX
|| M586TSC || M586 || MVIAC3_2
+ default "6" if MK7 || MK8 || MPENTIUMM
+
+config RWSEM_GENERIC_SPINLOCK
+ bool
+ depends on M386
+ default y
+
+config RWSEM_XCHGADD_ALGORITHM
+ bool
+ depends on !M386
+ default y
+
+config GENERIC_CALIBRATE_DELAY
+ bool
+ default y
+
+config X86_PPRO_FENCE
+ bool
+ depends on M686 || M586MMX || M586TSC || M586 || M486 || M386
+ default y
+
+config X86_F00F_BUG
+ bool
+ depends on M586MMX || M586TSC || M586 || M486 || M386
+ default y
+
+config X86_WP_WORKS_OK
+ bool
+ depends on !M386
+ default y
+
+config X86_INVLPG
+ bool
+ depends on !M386
+ default y
+
+config X86_BSWAP
+ bool
+ depends on !M386
+ default y
+
+config X86_POPAD_OK
+ bool
+ depends on !M386
+ default y
+
+config X86_ALIGNMENT_16
+ bool
+ depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII ||
X86_ELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2
+ default y
+
+config X86_GOOD_APIC
+ bool
+ depends on MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII
|| M686 || M586MMX || MK8 || MEFFICEON
+ default y
+
+config X86_INTEL_USERCOPY
+ bool
+ depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII ||
M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON
+ default y
+
+config X86_USE_PPRO_CHECKSUM
+ bool
+ depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || MK7 ||
MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 ||
MVIAC3_2 || MEFFICEON
+ default y
+
+config X86_USE_3DNOW
+ bool
+ depends on MCYRIXIII || MK7
+ default y
+
+config X86_OOSTORE
+ bool
+ depends on (MWINCHIP3D || MWINCHIP2 || MWINCHIPC6) && MTRR
+ default y
+
+config HPET_TIMER
+ bool
+ default n
+#config HPET_TIMER
+# bool "HPET Timer Support"
+# help
+# This enables the use of the HPET for the kernel's internal timer.
+# HPET is the next generation timer replacing legacy 8254s.
+# You can safely choose Y here. However, HPET will only be
+# activated if the platform and the BIOS support this feature.
+# Otherwise the 8254 will be used for timing services.
+#
+# Choose N to continue using the legacy 8254 timer.
+
+config HPET_EMULATE_RTC
+ def_bool HPET_TIMER && RTC=y
+
+config SMP
+ bool "Symmetric multi-processing support"
+ ---help---
+ This enables support for systems with more than one CPU. If you have
+ a system with only one CPU, like most personal computers, say N. If
+ you have a system with more than one CPU, say Y.
+
+ If you say N here, the kernel will run on single and multiprocessor
+ machines, but will use only one CPU of a multiprocessor machine. If
+ you say Y here, the kernel will run on many, but not all,
+ singleprocessor machines. On a singleprocessor machine, the kernel
+ will run faster if you say N here.
+
+ Note that if you say Y here and choose architecture "586" or
+ "Pentium" under "Processor family", the kernel will not work on 486
+ architectures. Similarly, multiprocessor kernels for the "PPro"
+ architecture may not work on all Pentium based boards.
+
+ People using multiprocessor machines who say Y here should also say
+ Y to "Enhanced Real Time Clock Support", below. The "Advanced Power
+ Management" code will be disabled if you say Y here.
+
+ See also the <file:Documentation/smp.txt>,
+ <file:Documentation/i386/IO-APIC.txt>,
+ <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at
+ <http://www.tldp.org/docs.html#howto>.
+
+ If you don't know what to do here, say N.
+
+config SMP_ALTERNATIVES
+ bool "SMP alternatives support (EXPERIMENTAL)"
+ depends on SMP && EXPERIMENTAL
+ help
+ Try to reduce the overhead of running an SMP kernel on a uniprocessor
+ host slightly by replacing certain key instruction sequences
+ according to whether we currently have more than one CPU available.
+ This should provide a noticeable boost to performance when
+ running SMP kernels on UP machines, and have negligible impact
+ when running on an true SMP host.
+
+ If unsure, say N.
+
+config NR_CPUS
+ int "Maximum number of CPUs (2-255)"
+ range 2 255
+ depends on SMP
+ default "32" if X86_NUMAQ || X86_SUMMIT || X86_BIGSMP || X86_ES7000
+ default "8"
+ help
+ This allows you to specify the maximum number of CPUs which this
+ kernel will support. The maximum supported value is 255 and the
+ minimum value which makes sense is 2.
+
+ This is purely to save memory - each supported CPU adds
+ approximately eight kilobytes to the kernel image.
+
+config SCHED_SMT
+ bool "SMT (Hyperthreading) scheduler support"
+ depends on SMP
+ default off
+ help
+ SMT scheduler support improves the CPU scheduler's decision making
+ when dealing with Intel Pentium 4 chips with HyperThreading at a
+ cost of slightly increased overhead in some places. If unsure say
+ N here.
+
+config PREEMPT
+ bool "Preemptible Kernel"
+ help
+ This option reduces the latency of the kernel when reacting to
+ real-time or interactive events by allowing a low priority process to
+ be preempted even if it is in kernel mode executing a system call.
+ This allows applications to run more reliably even when the system is
+ under load.
+
+ Say Y here if you are building a kernel for a desktop, embedded
+ or real-time system. Say N if you are unsure.
+
+config PREEMPT_BKL
+ bool "Preempt The Big Kernel Lock"
+ depends on PREEMPT
+ default y
+ help
+ This option reduces the latency of the kernel by making the
+ big kernel lock preemptible.
+
+ Say Y here if you are building a kernel for a desktop system.
+ Say N if you are unsure.
+
+#config X86_TSC
+# bool
+# depends on (MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON ||
MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII
|| M686 || M586MMX || M586TSC || MK8 || MVIAC3_2) && !X86_NUMAQ
+# default y
+
+#config X86_MCE
+# bool "Machine Check Exception"
+# depends on !X86_VOYAGER
+# ---help---
+# Machine Check Exception support allows the processor to notify the
+# kernel if it detects a problem (e.g. overheating, component failure).
+# The action the kernel takes depends on the severity of the problem,
+# ranging from a warning message on the console, to halting the
machine.
+# Your processor must be a Pentium or newer to support this - check the
+# flags in /proc/cpuinfo for mce. Note that some older Pentium systems
+# have a design flaw which leads to false MCE events - hence MCE is
+# disabled on all P5 processors, unless explicitly enabled with "mce"
+# as a boot argument. Similarly, if MCE is built in and creates a
+# problem on some new non-standard machine, you can boot with "nomce"
+# to disable it. MCE support simply ignores non-MCE processors like
+# the 386 and 486, so nearly everyone can say Y here.
+
+#config X86_MCE_NONFATAL
+# tristate "Check for non-fatal errors on AMD Athlon/Duron / Intel
Pentium 4"
+# depends on X86_MCE
+# help
+# Enabling this feature starts a timer that triggers every 5 seconds
which
+# will look at the machine check registers to see if anything happened.
+# Non-fatal problems automatically get corrected (but still logged).
+# Disable this if you don't want to see these messages.
+# Seeing the messages this option prints out may be indicative of
dying hardware,
+# or out-of-spec (ie, overclocked) hardware.
+# This option only does something on certain CPUs.
+# (AMD Athlon/Duron and Intel Pentium 4)
+
+#config X86_MCE_P4THERMAL
+# bool "check for P4 thermal throttling interrupt."
+# depends on X86_MCE && (X86_UP_APIC || SMP)
+# help
+# Enabling this feature will cause a message to be printed when the P4
+# enters thermal throttling.
+
+config MICROCODE
+ tristate "/dev/cpu/microcode - Intel IA32 CPU microcode support"
+ depends on XEN_PRIVILEGED_GUEST
+ ---help---
+ If you say Y here and also to "/dev file system support" in the
+ 'File systems' section, you will be able to update the microcode on
+ Intel processors in the IA32 family, e.g. Pentium Pro, Pentium II,
+ Pentium III, Pentium 4, Xeon etc. You will obviously need the
+ actual microcode binary data itself which is not shipped with the
+ Linux kernel.
+
+ For latest news and information on obtaining all the required
+ ingredients for this driver, check:
+ <http://www.urbanmyth.org/microcode/>.
+
+ To compile this driver as a module, choose M here: the
+ module will be called microcode.
+
+#config X86_MSR
+# tristate "/dev/cpu/*/msr - Model-specific register support"
+# help
+# This device gives privileged processes access to the x86
+# Model-Specific Registers (MSRs). It is a character device with
+# major 202 and minors 0 to 31 for /dev/cpu/0/msr to /dev/cpu/31/msr.
+# MSR accesses are directed to a specific CPU on multi-processor
+# systems.
+
+config X86_CPUID
+ tristate "/dev/cpu/*/cpuid - CPU information support"
+ help
+ This device gives processes access to the x86 CPUID instruction to
+ be executed on a specific processor. It is a character device
+ with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to
+ /dev/cpu/31/cpuid.
+
+source "drivers/firmware/Kconfig"
+
+choice
+ prompt "High Memory Support"
+ default NOHIGHMEM
+
+config NOHIGHMEM
+ bool "off"
+ ---help---
+ Linux can use up to 64 Gigabytes of physical memory on x86 systems.
+ However, the address space of 32-bit x86 processors is only 4
+ Gigabytes large. That means that, if you have a large amount of
+ physical memory, not all of it can be "permanently mapped" by the
+ kernel. The physical memory that's not permanently mapped is called
+ "high memory".
+
+ If you are compiling a kernel which will never run on a machine with
+ more than 1 Gigabyte total physical RAM, answer "off" here (default
+ choice and suitable for most users). This will result in a "3GB/1GB"
+ split: 3GB are mapped so that each process sees a 3GB virtual memory
+ space and the remaining part of the 4GB virtual memory space is used
+ by the kernel to permanently map as much physical memory as
+ possible.
+
+ If the machine has between 1 and 4 Gigabytes physical RAM, then
+ answer "4GB" here.
+
+ If more than 4 Gigabytes is used then answer "64GB" here. This
+ selection turns Intel PAE (Physical Address Extension) mode on.
+ PAE implements 3-level paging on IA32 processors. PAE is fully
+ supported by Linux, PAE mode is implemented on all recent Intel
+ processors (Pentium Pro and better). NOTE: If you say "64GB" here,
+ then the kernel will not boot on CPUs that don't support PAE!
+
+ The actual amount of total physical memory will either be
+ auto detected or can be forced by using a kernel command line option
+ such as "mem=256M". (Try "man bootparam" or see the documentation of
+ your boot loader (lilo or loadlin) about how to pass options to the
+ kernel at boot time.)
+
+ If unsure, say "off".
+
+config HIGHMEM4G
+ bool "4GB"
+ help
+ Select this if you have a 32-bit processor and between 1 and 4
+ gigabytes of physical RAM.
+
+#config HIGHMEM64G
+# bool "64GB"
+# help
+# Select this if you have a 32-bit processor and more than 4
+# gigabytes of physical RAM.
+
+endchoice
+
+config HIGHMEM
+ bool
+ depends on HIGHMEM64G || HIGHMEM4G
+ default y
+
+config X86_PAE
+ bool
+ depends on HIGHMEM64G
+ default y
+
+# Common NUMA Features
+config NUMA
+ bool "Numa Memory Allocation and Scheduler Support"
+ depends on SMP && HIGHMEM64G && (X86_NUMAQ || X86_GENERICARCH ||
(X86_SUMMIT && ACPI))
+ default n if X86_PC
+ default y if (X86_NUMAQ || X86_SUMMIT)
+
+# Need comments to help the hapless user trying to turn on NUMA support
+comment "NUMA (NUMA-Q) requires SMP, 64GB highmem support"
+ depends on X86_NUMAQ && (!HIGHMEM64G || !SMP)
+
+comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
+ depends on X86_SUMMIT && (!HIGHMEM64G || !ACPI)
+
+config DISCONTIGMEM
+ bool
+ depends on NUMA
+ default y
+
+config HAVE_ARCH_BOOTMEM_NODE
+ bool
+ depends on NUMA
+ default y
+
+#config HIGHPTE
+# bool "Allocate 3rd-level pagetables from highmem"
+# depends on HIGHMEM4G || HIGHMEM64G
+# help
+# The VM uses one page table entry for each page of physical memory.
+# For systems with a lot of RAM, this can be wasteful of precious
+# low memory. Setting this option will put user-space page table
+# entries in high memory.
+
+config MTRR
+ bool
+ depends on XEN_PRIVILEGED_GUEST
+ default y
+
+#config MTRR
+# bool "MTRR (Memory Type Range Register) support"
+# ---help---
+# On Intel P6 family processors (Pentium Pro, Pentium II and later)
+# the Memory Type Range Registers (MTRRs) may be used to control
+# processor access to memory ranges. This is most useful if you have
+# a video (VGA) card on a PCI or AGP bus. Enabling write-combining
+# allows bus write transfers to be combined into a larger transfer
+# before bursting over the PCI/AGP bus. This can increase performance
+# of image write operations 2.5 times or more. Saying Y here creates a
+# /proc/mtrr file which may be used to manipulate your processor's
+# MTRRs. Typically the X server should use this.
+#
+# This code has a reasonably generic interface so that similar
+# control registers on other processors can be easily supported
+# as well:
+#
+# The Cyrix 6x86, 6x86MX and M II processors have Address Range
+# Registers (ARRs) which provide a similar functionality to MTRRs. For
+# these, the ARRs are used to emulate the MTRRs.
+# The AMD K6-2 (stepping 8 and above) and K6-3 processors have two
+# MTRRs. The Centaur C6 (WinChip) has 8 MCRs, allowing
+# write-combining. All of these processors are supported by this code
+# and it makes sense to say Y here if you have one of them.
+#
+# Saying Y here also fixes a problem with buggy SMP BIOSes which only
+# set the MTRRs for the boot CPU and not for the secondary CPUs. This
+# can lead to all sorts of problems, so it's good to say Y here.
+#
+# You can safely say Y even if your machine doesn't have MTRRs, you'll
+# just add about 9 KB to your kernel.
+#
+# See <file:Documentation/mtrr.txt> for more information.
+
+config IRQBALANCE
+ bool "Enable kernel irq balancing"
+ depends on SMP && X86_IO_APIC && !XEN
+ default y
+ help
+ The default yes will allow the kernel to do irq load balancing.
+ Saying no will keep the kernel from doing irq load balancing.
+
+config HAVE_DEC_LOCK
+ bool
+ depends on (SMP || PREEMPT) && X86_CMPXCHG
+ default y
+
+# turning this on wastes a bunch of space.
+# Summit needs it only when NUMA is on
+config BOOT_IOREMAP
+ bool
+ depends on (((X86_SUMMIT || X86_GENERICARCH) && NUMA) || (X86 && EFI))
+ default y
+
+config REGPARM
+ bool "Use register arguments (EXPERIMENTAL)"
+ depends on EXPERIMENTAL
+ default n
+ help
+ Compile the kernel with -mregparm=3. This uses a different ABI
+ and passes the first three arguments of a function call in registers.
+ This will probably break binary only modules.
+
+ This feature is only enabled for gcc-3.0 and later - earlier compilers
+ generate incorrect output with certain kernel constructs when
+ -mregparm=3 is used.
+
+config X86_LOCAL_APIC
+ bool
+ depends on !SMP && X86_UP_APIC
+ default y
+
+config X86_IO_APIC
+ bool
+ depends on !SMP && X86_UP_IOAPIC
+ default y
+
+config HOTPLUG_CPU
+ bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
+ depends on SMP && HOTPLUG && EXPERIMENTAL
+ ---help---
+ Say Y here to experiment with turning CPUs off and on. CPUs
+ can be controlled through /sys/devices/system/cpu.
+
+ Say N.
+
+
+if XEN_PHYSDEV_ACCESS
+
+menu "Bus options (PCI, PCMCIA, EISA, MCA, ISA)"
+
+config X86_VISWS_APIC
+ bool
+ depends on X86_VISWS
+ default y
+
+config X86_LOCAL_APIC
+ bool
+ depends on (X86_VISWS || SMP) && !X86_VOYAGER
+ default y
+
+config X86_UP_APIC
+ bool "Local APIC support on uniprocessors" if !SMP
+ depends on !(X86_VISWS || X86_VOYAGER)
+ ---help---
+ A local APIC (Advanced Programmable Interrupt Controller) is an
+ integrated interrupt controller in the CPU. If you have a single-CPU
+ system which has a processor with a local APIC, you can say Y here to
+ enable and use it. If you say Y here even though your machine doesn't
+ have a local APIC, then the kernel will still run with no slowdown at
+ all. The local APIC supports CPU-generated self-interrupts (timer,
+ performance counters), and the NMI watchdog which detects hard
+ lockups.
+
+ If you have a system with several CPUs, you do not need to say Y
+ here: the local APIC will be used automatically.
+
+config X86_UP_IOAPIC
+ bool "IO-APIC support on uniprocessors"
+ depends on !SMP && X86_UP_APIC
+ help
+ An IO-APIC (I/O Advanced Programmable Interrupt Controller) is an
+ SMP-capable replacement for PC-style interrupt controllers. Most
+ SMP systems and a small number of uniprocessor systems have one.
+ If you have a single-CPU system with an IO-APIC, you can say Y here
+ to use it. If you say Y here even though your machine doesn't have
+ an IO-APIC, then the kernel will still run with no slowdown at all.
+
+ If you have a system with several CPUs, you do not need to say Y
+ here: the IO-APIC will be used automatically.
+
+config X86_IO_APIC
+ bool
+ depends on SMP && !(X86_VISWS || X86_VOYAGER)
+ default y
+
+config PCI
+ bool "PCI support" if !X86_VISWS
+ depends on !X86_VOYAGER
+ default y if X86_VISWS
+ help
+ Find out whether you have a PCI motherboard. PCI is the name of a
+ bus system, i.e. the way the CPU talks to the other stuff inside
+ your box. Other bus systems are ISA, EISA, MicroChannel (MCA) or
+ VESA. If you have PCI, say Y, otherwise N.
+
+ The PCI-HOWTO, available from
+ <http://www.tldp.org/docs.html#howto>, contains valuable
+ information about which PCI hardware does work under Linux and which
+ doesn't.
+
+choice
+ prompt "PCI access mode"
+ depends on PCI && !X86_VISWS
+ default PCI_GOANY
+ ---help---
+ On PCI systems, the BIOS can be used to detect the PCI devices and
+ determine their configuration. However, some old PCI motherboards
+ have BIOS bugs and may crash if this is done. Also, some embedded
+ PCI-based systems don't have any BIOS at all. Linux can also try to
+ detect the PCI hardware directly without using the BIOS.
+
+ With this option, you can specify how Linux should detect the
+ PCI devices. If you choose "BIOS", the BIOS will be used,
+ if you choose "Direct", the BIOS won't be used, and if you
+ choose "MMConfig", then PCI Express MMCONFIG will be used.
+ If you choose "Any", the kernel will try MMCONFIG, then the
+ direct access method and falls back to the BIOS if that doesn't
+ work. If unsure, go with the default, which is "Any".
+
+config PCI_GOBIOS
+ bool "BIOS"
+
+config PCI_GOMMCONFIG
+ bool "MMConfig"
+
+config PCI_GODIRECT
+ bool "Direct"
+
+config PCI_GOANY
+ bool "Any"
+
+endchoice
+
+config PCI_BIOS
+ bool
+ depends on !X86_VISWS && PCI && (PCI_GOBIOS || PCI_GOANY)
+ default y
+
+config PCI_DIRECT
+ bool
+ depends on PCI && ((PCI_GODIRECT || PCI_GOANY) || X86_VISWS)
+ default y
+
+config PCI_MMCONFIG
+ bool
+ depends on PCI && (PCI_GOMMCONFIG || (PCI_GOANY && ACPI))
+ select ACPI_BOOT
+ default y
+
+source "drivers/pci/pcie/Kconfig"
+
+source "drivers/pci/Kconfig"
+
+config ISA
+ bool "ISA support"
+ depends on !(X86_VOYAGER || X86_VISWS)
+ help
+ Find out whether you have ISA slots on your motherboard. ISA is the
+ name of a bus system, i.e. the way the CPU talks to the other stuff
+ inside your box. Other bus systems are PCI, EISA, MicroChannel
+ (MCA) or VESA. ISA is an older system, now being displaced by PCI;
+ newer boards don't support it. If you have ISA, say Y, otherwise N.
+
+config EISA
+ bool "EISA support"
+ depends on ISA
+ ---help---
+ The Extended Industry Standard Architecture (EISA) bus was
+ developed as an open alternative to the IBM MicroChannel bus.
+
+ The EISA bus provided some of the features of the IBM MicroChannel
+ bus while maintaining backward compatibility with cards made for
+ the older ISA bus. The EISA bus saw limited use between 1988 and
+ 1995 when it was made obsolete by the PCI bus.
+
+ Say Y here if you are building a kernel for an EISA-based machine.
+
+ Otherwise, say N.
+
+source "drivers/eisa/Kconfig"
+
+config MCA
+ bool "MCA support"
+ depends on !(X86_VISWS || X86_VOYAGER)
+ help
+ MicroChannel Architecture is found in some IBM PS/2 machines and
+ laptops. It is a bus system similar to PCI or ISA. See
+ <file:Documentation/mca.txt> (and especially the web page given
+ there) before attempting to build an MCA bus kernel.
+
+config MCA
+ depends on X86_VOYAGER
+ default y if X86_VOYAGER
+
+source "drivers/mca/Kconfig"
+
+config SCx200
+ tristate "NatSemi SCx200 support"
+ depends on !X86_VOYAGER
+ help
+ This provides basic support for the National Semiconductor SCx200
+ processor. Right now this is just a driver for the GPIO pins.
+
+ If you don't know what to do here, say N.
+
+ This support is also available as a module. If compiled as a
+ module, it will be called scx200.
+
+source "drivers/pcmcia/Kconfig"
+
+source "drivers/pci/hotplug/Kconfig"
+
+endmenu
+
+endif
+
+source "arch/i386/Kconfig.debug"
+
+#
+# Use the generic interrupt handling code in kernel/irq/:
+#
+config GENERIC_HARDIRQS
+ bool
+ default y
+
+config GENERIC_IRQ_PROBE
+ bool
+ default y
+
+config X86_SMP
+ bool
+ depends on SMP && !X86_VOYAGER
+ default y
+
+#config X86_HT
+# bool
+# depends on SMP && !(X86_VISWS || X86_VOYAGER)
+# default y
+
+config X86_BIOS_REBOOT
+ bool
+ depends on !(X86_VISWS || X86_VOYAGER)
+ default y
+
+config X86_TRAMPOLINE
+ bool
+ depends on X86_SMP || (X86_VOYAGER && SMP)
+ default y
+
+config PC
+ bool
+ depends on X86 && !EMBEDDED
+ default y
+
+endmenu
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/evtchn/evtchn.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/evtchn/evtchn.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,430 @@
+/******************************************************************************
+ * evtchn.c
+ *
+ * Xenolinux driver for receiving and demuxing event-channel signals.
+ *
+ * Copyright (c) 2004, K A Fraser
+ * Multi-process extensions Copyright (c) 2004, Steven Smith
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/errno.h>
+#include <linux/miscdevice.h>
+#include <linux/major.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/poll.h>
+#include <linux/irq.h>
+#include <linux/init.h>
+#define XEN_EVTCHN_MASK_OPS
+#include <asm-xen/evtchn.h>
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
+#include <linux/devfs_fs_kernel.h>
+#define OLD_DEVFS
+#else
+#include <linux/gfp.h>
+#endif
+
+#ifdef OLD_DEVFS
+/* NB. This must be shared amongst drivers if more things go in /dev/xen */
+static devfs_handle_t xen_dev_dir;
+#endif
+
+struct per_user_data {
+ /* Notification ring, accessed via /dev/xen/evtchn. */
+# define EVTCHN_RING_SIZE 2048 /* 2048 16-bit entries */
+# define EVTCHN_RING_MASK(_i) ((_i)&(EVTCHN_RING_SIZE-1))
+ u16 *ring;
+ unsigned int ring_cons, ring_prod, ring_overflow;
+
+ /* Processes wait on this queue when ring is empty. */
+ wait_queue_head_t evtchn_wait;
+ struct fasync_struct *evtchn_async_queue;
+};
+
+/* Who's bound to each port? */
+static struct per_user_data *port_user[NR_EVENT_CHANNELS];
+static spinlock_t port_user_lock;
+
+void evtchn_device_upcall(int port)
+{
+ struct per_user_data *u;
+
+ spin_lock(&port_user_lock);
+
+ mask_evtchn(port);
+ clear_evtchn(port);
+
+ if ( (u = port_user[port]) != NULL )
+ {
+ if ( (u->ring_prod - u->ring_cons) < EVTCHN_RING_SIZE )
+ {
+ u->ring[EVTCHN_RING_MASK(u->ring_prod)] = (u16)port;
+ if ( u->ring_cons == u->ring_prod++ )
+ {
+ wake_up_interruptible(&u->evtchn_wait);
+ kill_fasync(&u->evtchn_async_queue, SIGIO, POLL_IN);
+ }
+ }
+ else
+ {
+ u->ring_overflow = 1;
+ }
+ }
+
+ spin_unlock(&port_user_lock);
+}
+
+static ssize_t evtchn_read(struct file *file, char *buf,
+ size_t count, loff_t *ppos)
+{
+ int rc;
+ unsigned int c, p, bytes1 = 0, bytes2 = 0;
+ DECLARE_WAITQUEUE(wait, current);
+ struct per_user_data *u = file->private_data;
+
+ add_wait_queue(&u->evtchn_wait, &wait);
+
+ count &= ~1; /* even number of bytes */
+
+ if ( count == 0 )
+ {
+ rc = 0;
+ goto out;
+ }
+
+ if ( count > PAGE_SIZE )
+ count = PAGE_SIZE;
+
+ for ( ; ; )
+ {
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ if ( (c = u->ring_cons) != (p = u->ring_prod) )
+ break;
+
+ if ( u->ring_overflow )
+ {
+ rc = -EFBIG;
+ goto out;
+ }
+
+ if ( file->f_flags & O_NONBLOCK )
+ {
+ rc = -EAGAIN;
+ goto out;
+ }
+
+ if ( signal_pending(current) )
+ {
+ rc = -ERESTARTSYS;
+ goto out;
+ }
+
+ schedule();
+ }
+
+ /* Byte lengths of two chunks. Chunk split (if any) is at ring wrap. */
+ if ( ((c ^ p) & EVTCHN_RING_SIZE) != 0 )
+ {
+ bytes1 = (EVTCHN_RING_SIZE - EVTCHN_RING_MASK(c)) * sizeof(u16);
+ bytes2 = EVTCHN_RING_MASK(p) * sizeof(u16);
+ }
+ else
+ {
+ bytes1 = (p - c) * sizeof(u16);
+ bytes2 = 0;
+ }
+
+ /* Truncate chunks according to caller's maximum byte count. */
+ if ( bytes1 > count )
+ {
+ bytes1 = count;
+ bytes2 = 0;
+ }
+ else if ( (bytes1 + bytes2) > count )
+ {
+ bytes2 = count - bytes1;
+ }
+
+ if ( copy_to_user(buf, &u->ring[EVTCHN_RING_MASK(c)], bytes1) ||
+ ((bytes2 != 0) && copy_to_user(&buf[bytes1], &u->ring[0], bytes2)) )
+ {
+ rc = -EFAULT;
+ goto out;
+ }
+
+ u->ring_cons += (bytes1 + bytes2) / sizeof(u16);
+
+ rc = bytes1 + bytes2;
+
+ out:
+ __set_current_state(TASK_RUNNING);
+ remove_wait_queue(&u->evtchn_wait, &wait);
+ return rc;
+}
+
+static ssize_t evtchn_write(struct file *file, const char *buf,
+ size_t count, loff_t *ppos)
+{
+ int rc, i;
+ u16 *kbuf = (u16 *)__get_free_page(GFP_KERNEL);
+ struct per_user_data *u = file->private_data;
+
+ if ( kbuf == NULL )
+ return -ENOMEM;
+
+ count &= ~1; /* even number of bytes */
+
+ if ( count == 0 )
+ {
+ rc = 0;
+ goto out;
+ }
+
+ if ( count > PAGE_SIZE )
+ count = PAGE_SIZE;
+
+ if ( copy_from_user(kbuf, buf, count) != 0 )
+ {
+ rc = -EFAULT;
+ goto out;
+ }
+
+ spin_lock_irq(&port_user_lock);
+ for ( i = 0; i < (count/2); i++ )
+ if ( (kbuf[i] < NR_EVENT_CHANNELS) && (port_user[kbuf[i]] == u) )
+ unmask_evtchn(kbuf[i]);
+ spin_unlock_irq(&port_user_lock);
+
+ rc = count;
+
+ out:
+ free_page((unsigned long)kbuf);
+ return rc;
+}
+
+static int evtchn_ioctl(struct inode *inode, struct file *file,
+ unsigned int cmd, unsigned long arg)
+{
+ int rc = 0;
+ struct per_user_data *u = file->private_data;
+
+ spin_lock_irq(&port_user_lock);
+
+ switch ( cmd )
+ {
+ case EVTCHN_RESET:
+ /* Initialise the ring to empty. Clear errors. */
+ u->ring_cons = u->ring_prod = u->ring_overflow = 0;
+ break;
+
+ case EVTCHN_BIND:
+ if ( arg >= NR_EVENT_CHANNELS )
+ {
+ rc = -EINVAL;
+ }
+ else if ( port_user[arg] != NULL )
+ {
+ rc = -EISCONN;
+ }
+ else
+ {
+ port_user[arg] = u;
+ unmask_evtchn(arg);
+ }
+ break;
+
+ case EVTCHN_UNBIND:
+ if ( arg >= NR_EVENT_CHANNELS )
+ {
+ rc = -EINVAL;
+ }
+ else if ( port_user[arg] != u )
+ {
+ rc = -ENOTCONN;
+ }
+ else
+ {
+ port_user[arg] = NULL;
+ mask_evtchn(arg);
+ }
+ break;
+
+ default:
+ rc = -ENOSYS;
+ break;
+ }
+
+ spin_unlock_irq(&port_user_lock);
+
+ return rc;
+}
+
+static unsigned int evtchn_poll(struct file *file, poll_table *wait)
+{
+ unsigned int mask = POLLOUT | POLLWRNORM;
+ struct per_user_data *u = file->private_data;
+
+ poll_wait(file, &u->evtchn_wait, wait);
+ if ( u->ring_cons != u->ring_prod )
+ mask |= POLLIN | POLLRDNORM;
+ if ( u->ring_overflow )
+ mask = POLLERR;
+ return mask;
+}
+
+static int evtchn_fasync(int fd, struct file *filp, int on)
+{
+ struct per_user_data *u = filp->private_data;
+ return fasync_helper(fd, filp, on, &u->evtchn_async_queue);
+}
+
+static int evtchn_open(struct inode *inode, struct file *filp)
+{
+ struct per_user_data *u;
+
+ if ( (u = kmalloc(sizeof(*u), GFP_KERNEL)) == NULL )
+ return -ENOMEM;
+
+ memset(u, 0, sizeof(*u));
+ init_waitqueue_head(&u->evtchn_wait);
+
+ if ( (u->ring = (u16 *)__get_free_page(GFP_KERNEL)) == NULL )
+ {
+ kfree(u);
+ return -ENOMEM;
+ }
+
+ filp->private_data = u;
+
+ return 0;
+}
+
+static int evtchn_release(struct inode *inode, struct file *filp)
+{
+ int i;
+ struct per_user_data *u = filp->private_data;
+
+ spin_lock_irq(&port_user_lock);
+
+ free_page((unsigned long)u->ring);
+
+ for ( i = 0; i < NR_EVENT_CHANNELS; i++ )
+ {
+ if ( port_user[i] == u )
+ {
+ port_user[i] = NULL;
+ mask_evtchn(i);
+ }
+ }
+
+ spin_unlock_irq(&port_user_lock);
+
+ return 0;
+}
+
+static struct file_operations evtchn_fops = {
+ owner: THIS_MODULE,
+ read: evtchn_read,
+ write: evtchn_write,
+ ioctl: evtchn_ioctl,
+ poll: evtchn_poll,
+ fasync: evtchn_fasync,
+ open: evtchn_open,
+ release: evtchn_release
+};
+
+static struct miscdevice evtchn_miscdev = {
+ .minor = EVTCHN_MINOR,
+ .name = "evtchn",
+ .fops = &evtchn_fops,
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+ .devfs_name = "misc/evtchn",
+#endif
+};
+
+static int __init evtchn_init(void)
+{
+#ifdef OLD_DEVFS
+ devfs_handle_t symlink_handle;
+ int pos;
+ char link_dest[64];
+#endif
+ int err;
+
+ spin_lock_init(&port_user_lock);
+ memset(port_user, 0, sizeof(port_user));
+
+ /* (DEVFS) create '/dev/misc/evtchn'. */
+ err = misc_register(&evtchn_miscdev);
+ if ( err != 0 )
+ {
+ printk(KERN_ALERT "Could not register /dev/misc/evtchn\n");
+ return err;
+ }
+
+#ifdef OLD_DEVFS
+ /* (DEVFS) create directory '/dev/xen'. */
+ xen_dev_dir = devfs_mk_dir(NULL, "xen", NULL);
+
+ /* (DEVFS) &link_dest[pos] == '../misc/evtchn'. */
+ pos = devfs_generate_path(evtchn_miscdev.devfs_handle,
+ &link_dest[3],
+ sizeof(link_dest) - 3);
+ if ( pos >= 0 )
+ strncpy(&link_dest[pos], "../", 3);
+
+ /* (DEVFS) symlink '/dev/xen/evtchn' -> '../misc/evtchn'. */
+ (void)devfs_mk_symlink(xen_dev_dir,
+ "evtchn",
+ DEVFS_FL_DEFAULT,
+ &link_dest[pos],
+ &symlink_handle,
+ NULL);
+
+ /* (DEVFS) automatically destroy the symlink with its destination. */
+ devfs_auto_unregister(evtchn_miscdev.devfs_handle, symlink_handle);
+#endif
+
+ printk("Event-channel device installed.\n");
+
+ return 0;
+}
+
+static void evtchn_cleanup(void)
+{
+ misc_deregister(&evtchn_miscdev);
+}
+
+module_init(evtchn_init);
+module_exit(evtchn_cleanup);
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/mm/highmem.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/mm/highmem.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,461 @@
+/*
+ * High memory handling common code and variables.
+ *
+ * (C) 1999 Andrea Arcangeli, SuSE GmbH, andrea@xxxxxxx
+ * Gerhard Wichert, Siemens AG, Gerhard.Wichert@xxxxxxxxxxxxxx
+ *
+ *
+ * Redesigned the x86 32-bit VM architecture to deal with
+ * 64-bit physical space. With current x86 CPUs this
+ * means up to 64 Gigabytes physical RAM.
+ *
+ * Rewrote high memory support to move the page cache into
+ * high memory. Implemented permanent (schedulable) kmaps
+ * based on Linus' idea.
+ *
+ * Copyright (C) 1999 Ingo Molnar <mingo@xxxxxxxxxx>
+ */
+
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+#include <linux/swap.h>
+#include <linux/slab.h>
+
+/*
+ * Virtual_count is not a pure "count".
+ * 0 means that it is not mapped, and has not been mapped
+ * since a TLB flush - it is usable.
+ * 1 means that there are no users, but it has been mapped
+ * since the last TLB flush - so we can't use it.
+ * n means that there are (n-1) current users of it.
+ */
+static int pkmap_count[LAST_PKMAP];
+static unsigned int last_pkmap_nr;
+static spinlock_cacheline_t kmap_lock_cacheline = {SPIN_LOCK_UNLOCKED};
+#define kmap_lock kmap_lock_cacheline.lock
+
+pte_t * pkmap_page_table;
+
+static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait);
+
+static void flush_all_zero_pkmaps(void)
+{
+ int i;
+
+ flush_cache_all();
+
+ for (i = 0; i < LAST_PKMAP; i++) {
+ struct page *page;
+
+ /*
+ * zero means we don't have anything to do,
+ * >1 means that it is still in use. Only
+ * a count of 1 means that it is free but
+ * needs to be unmapped
+ */
+ if (pkmap_count[i] != 1)
+ continue;
+ pkmap_count[i] = 0;
+
+ /* sanity check */
+ if (pte_none(pkmap_page_table[i]))
+ BUG();
+
+ /*
+ * Don't need an atomic fetch-and-clear op here;
+ * no-one has the page mapped, and cannot get at
+ * its virtual address (and hence PTE) without first
+ * getting the kmap_lock (which is held here).
+ * So no dangers, even with speculative execution.
+ */
+ page = pte_page(pkmap_page_table[i]);
+ pte_clear(&pkmap_page_table[i]);
+
+ page->virtual = NULL;
+ }
+ flush_tlb_all();
+}
+
+static inline unsigned long map_new_virtual(struct page *page, int nonblocking)
+{
+ unsigned long vaddr;
+ int count;
+
+start:
+ count = LAST_PKMAP;
+ /* Find an empty entry */
+ for (;;) {
+ last_pkmap_nr = (last_pkmap_nr + 1) & LAST_PKMAP_MASK;
+ if (!last_pkmap_nr) {
+ flush_all_zero_pkmaps();
+ count = LAST_PKMAP;
+ }
+ if (!pkmap_count[last_pkmap_nr])
+ break; /* Found a usable entry */
+ if (--count)
+ continue;
+
+ if (nonblocking)
+ return 0;
+
+ /*
+ * Sleep for somebody else to unmap their entries
+ */
+ {
+ DECLARE_WAITQUEUE(wait, current);
+
+ current->state = TASK_UNINTERRUPTIBLE;
+ add_wait_queue(&pkmap_map_wait, &wait);
+ spin_unlock(&kmap_lock);
+ schedule();
+ remove_wait_queue(&pkmap_map_wait, &wait);
+ spin_lock(&kmap_lock);
+
+ /* Somebody else might have mapped it while we slept */
+ if (page->virtual)
+ return (unsigned long) page->virtual;
+
+ /* Re-start */
+ goto start;
+ }
+ }
+ vaddr = PKMAP_ADDR(last_pkmap_nr);
+ set_pte(&(pkmap_page_table[last_pkmap_nr]), mk_pte(page, kmap_prot));
+
+ pkmap_count[last_pkmap_nr] = 1;
+ page->virtual = (void *) vaddr;
+
+ return vaddr;
+}
+
+void kmap_flush_unused(void)
+{
+ spin_lock(&kmap_lock);
+ flush_all_zero_pkmaps();
+ spin_unlock(&kmap_lock);
+}
+
+void fastcall *kmap_high(struct page *page, int nonblocking)
+{
+ unsigned long vaddr;
+
+ /*
+ * For highmem pages, we can't trust "virtual" until
+ * after we have the lock.
+ *
+ * We cannot call this from interrupts, as it may block
+ */
+ spin_lock(&kmap_lock);
+ vaddr = (unsigned long) page->virtual;
+ if (!vaddr) {
+ vaddr = map_new_virtual(page, nonblocking);
+ if (!vaddr)
+ goto out;
+ }
+ pkmap_count[PKMAP_NR(vaddr)]++;
+ if (pkmap_count[PKMAP_NR(vaddr)] < 2)
+ BUG();
+ out:
+ spin_unlock(&kmap_lock);
+ return (void*) vaddr;
+}
+
+void fastcall kunmap_high(struct page *page)
+{
+ unsigned long vaddr;
+ unsigned long nr;
+ int need_wakeup;
+
+ spin_lock(&kmap_lock);
+ vaddr = (unsigned long) page->virtual;
+ if (!vaddr)
+ BUG();
+ nr = PKMAP_NR(vaddr);
+
+ /*
+ * A count must never go down to zero
+ * without a TLB flush!
+ */
+ need_wakeup = 0;
+ switch (--pkmap_count[nr]) {
+ case 0:
+ BUG();
+ case 1:
+ /*
+ * Avoid an unnecessary wake_up() function call.
+ * The common case is pkmap_count[] == 1, but
+ * no waiters.
+ * The tasks queued in the wait-queue are guarded
+ * by both the lock in the wait-queue-head and by
+ * the kmap_lock. As the kmap_lock is held here,
+ * no need for the wait-queue-head's lock. Simply
+ * test if the queue is empty.
+ */
+ need_wakeup = waitqueue_active(&pkmap_map_wait);
+ }
+ spin_unlock(&kmap_lock);
+
+ /* do wake-up, if needed, race-free outside of the spin lock */
+ if (need_wakeup)
+ wake_up(&pkmap_map_wait);
+}
+
+#define POOL_SIZE 32
+
+/*
+ * This lock gets no contention at all, normally.
+ */
+static spinlock_t emergency_lock = SPIN_LOCK_UNLOCKED;
+
+int nr_emergency_pages;
+static LIST_HEAD(emergency_pages);
+
+int nr_emergency_bhs;
+static LIST_HEAD(emergency_bhs);
+
+/*
+ * Simple bounce buffer support for highmem pages.
+ * This will be moved to the block layer in 2.5.
+ */
+
+static inline void copy_from_high_bh (struct buffer_head *to,
+ struct buffer_head *from)
+{
+ struct page *p_from;
+ char *vfrom;
+
+ p_from = from->b_page;
+
+ vfrom = kmap_atomic(p_from, KM_USER0);
+ memcpy(to->b_data, vfrom + bh_offset(from), to->b_size);
+ kunmap_atomic(vfrom, KM_USER0);
+}
+
+static inline void copy_to_high_bh_irq (struct buffer_head *to,
+ struct buffer_head *from)
+{
+ struct page *p_to;
+ char *vto;
+ unsigned long flags;
+
+ p_to = to->b_page;
+ __save_flags(flags);
+ __cli();
+ vto = kmap_atomic(p_to, KM_BOUNCE_READ);
+ memcpy(vto + bh_offset(to), from->b_data, to->b_size);
+ kunmap_atomic(vto, KM_BOUNCE_READ);
+ __restore_flags(flags);
+}
+
+static inline void bounce_end_io (struct buffer_head *bh, int uptodate)
+{
+ struct page *page;
+ struct buffer_head *bh_orig = (struct buffer_head *)(bh->b_private);
+ unsigned long flags;
+
+ bh_orig->b_end_io(bh_orig, uptodate);
+
+ page = bh->b_page;
+
+ spin_lock_irqsave(&emergency_lock, flags);
+ if (nr_emergency_pages >= POOL_SIZE)
+ __free_page(page);
+ else {
+ /*
+ * We are abusing page->list to manage
+ * the highmem emergency pool:
+ */
+ list_add(&page->list, &emergency_pages);
+ nr_emergency_pages++;
+ }
+
+ if (nr_emergency_bhs >= POOL_SIZE) {
+#ifdef HIGHMEM_DEBUG
+ /* Don't clobber the constructed slab cache */
+ init_waitqueue_head(&bh->b_wait);
+#endif
+ kmem_cache_free(bh_cachep, bh);
+ } else {
+ /*
+ * Ditto in the bh case, here we abuse b_inode_buffers:
+ */
+ list_add(&bh->b_inode_buffers, &emergency_bhs);
+ nr_emergency_bhs++;
+ }
+ spin_unlock_irqrestore(&emergency_lock, flags);
+}
+
+static __init int init_emergency_pool(void)
+{
+ struct sysinfo i;
+ si_meminfo(&i);
+ si_swapinfo(&i);
+
+ if (!i.totalhigh)
+ return 0;
+
+ spin_lock_irq(&emergency_lock);
+ while (nr_emergency_pages < POOL_SIZE) {
+ struct page * page = alloc_page(GFP_ATOMIC);
+ if (!page) {
+ printk("couldn't refill highmem emergency pages");
+ break;
+ }
+ list_add(&page->list, &emergency_pages);
+ nr_emergency_pages++;
+ }
+ while (nr_emergency_bhs < POOL_SIZE) {
+ struct buffer_head * bh = kmem_cache_alloc(bh_cachep,
SLAB_ATOMIC);
+ if (!bh) {
+ printk("couldn't refill highmem emergency bhs");
+ break;
+ }
+ list_add(&bh->b_inode_buffers, &emergency_bhs);
+ nr_emergency_bhs++;
+ }
+ spin_unlock_irq(&emergency_lock);
+ printk("allocated %d pages and %d bhs reserved for the highmem
bounces\n",
+ nr_emergency_pages, nr_emergency_bhs);
+
+ return 0;
+}
+
+__initcall(init_emergency_pool);
+
+static void bounce_end_io_write (struct buffer_head *bh, int uptodate)
+{
+ bounce_end_io(bh, uptodate);
+}
+
+static void bounce_end_io_read (struct buffer_head *bh, int uptodate)
+{
+ struct buffer_head *bh_orig = (struct buffer_head *)(bh->b_private);
+
+ if (uptodate)
+ copy_to_high_bh_irq(bh_orig, bh);
+ bounce_end_io(bh, uptodate);
+}
+
+struct page *alloc_bounce_page (void)
+{
+ struct list_head *tmp;
+ struct page *page;
+
+ page = alloc_page(GFP_NOHIGHIO);
+ if (page)
+ return page;
+ /*
+ * No luck. First, kick the VM so it doesn't idle around while
+ * we are using up our emergency rations.
+ */
+ wakeup_bdflush();
+
+repeat_alloc:
+ /*
+ * Try to allocate from the emergency pool.
+ */
+ tmp = &emergency_pages;
+ spin_lock_irq(&emergency_lock);
+ if (!list_empty(tmp)) {
+ page = list_entry(tmp->next, struct page, list);
+ list_del(tmp->next);
+ nr_emergency_pages--;
+ }
+ spin_unlock_irq(&emergency_lock);
+ if (page)
+ return page;
+
+ /* we need to wait I/O completion */
+ run_task_queue(&tq_disk);
+
+ yield();
+ goto repeat_alloc;
+}
+
+struct buffer_head *alloc_bounce_bh (void)
+{
+ struct list_head *tmp;
+ struct buffer_head *bh;
+
+ bh = kmem_cache_alloc(bh_cachep, SLAB_NOHIGHIO);
+ if (bh)
+ return bh;
+ /*
+ * No luck. First, kick the VM so it doesn't idle around while
+ * we are using up our emergency rations.
+ */
+ wakeup_bdflush();
+
+repeat_alloc:
+ /*
+ * Try to allocate from the emergency pool.
+ */
+ tmp = &emergency_bhs;
+ spin_lock_irq(&emergency_lock);
+ if (!list_empty(tmp)) {
+ bh = list_entry(tmp->next, struct buffer_head, b_inode_buffers);
+ list_del(tmp->next);
+ nr_emergency_bhs--;
+ }
+ spin_unlock_irq(&emergency_lock);
+ if (bh)
+ return bh;
+
+ /* we need to wait I/O completion */
+ run_task_queue(&tq_disk);
+
+ yield();
+ goto repeat_alloc;
+}
+
+struct buffer_head * create_bounce(int rw, struct buffer_head * bh_orig)
+{
+ struct page *page;
+ struct buffer_head *bh;
+
+ if (!PageHighMem(bh_orig->b_page))
+ return bh_orig;
+
+ bh = alloc_bounce_bh();
+ /*
+ * This is wasteful for 1k buffers, but this is a stopgap measure
+ * and we are being ineffective anyway. This approach simplifies
+ * things immensly. On boxes with more than 4GB RAM this should
+ * not be an issue anyway.
+ */
+ page = alloc_bounce_page();
+
+ set_bh_page(bh, page, 0);
+
+ bh->b_next = NULL;
+ bh->b_blocknr = bh_orig->b_blocknr;
+ bh->b_size = bh_orig->b_size;
+ bh->b_list = -1;
+ bh->b_dev = bh_orig->b_dev;
+ bh->b_count = bh_orig->b_count;
+ bh->b_rdev = bh_orig->b_rdev;
+ bh->b_state = bh_orig->b_state;
+#ifdef HIGHMEM_DEBUG
+ bh->b_flushtime = jiffies;
+ bh->b_next_free = NULL;
+ bh->b_prev_free = NULL;
+ /* bh->b_this_page */
+ bh->b_reqnext = NULL;
+ bh->b_pprev = NULL;
+#endif
+ /* bh->b_page */
+ if (rw == WRITE) {
+ bh->b_end_io = bounce_end_io_write;
+ copy_from_high_bh(bh, bh_orig);
+ } else
+ bh->b_end_io = bounce_end_io_read;
+ bh->b_private = (void *)bh_orig;
+ bh->b_rsector = bh_orig->b_rsector;
+#ifdef HIGHMEM_DEBUG
+ memset(&bh->b_wait, -1, sizeof(bh->b_wait));
+#endif
+
+ return bh;
+}
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/hw_irq.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/hw_irq.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,61 @@
+#ifndef _ASM_HW_IRQ_H
+#define _ASM_HW_IRQ_H
+
+/*
+ * linux/include/asm/hw_irq.h
+ *
+ * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ */
+
+#include <linux/config.h>
+#include <linux/smp.h>
+#include <asm/atomic.h>
+#include <asm/irq.h>
+
+#define SYSCALL_VECTOR 0x80
+
+extern int irq_vector[NR_IRQS];
+
+extern atomic_t irq_err_count;
+extern atomic_t irq_mis_count;
+
+extern char _stext, _etext;
+
+extern unsigned long prof_cpu_mask;
+extern unsigned int * prof_buffer;
+extern unsigned long prof_len;
+extern unsigned long prof_shift;
+
+/*
+ * x86 profiling function, SMP safe. We might want to do this in
+ * assembly totally?
+ */
+static inline void x86_do_profile (unsigned long eip)
+{
+ if (!prof_buffer)
+ return;
+
+ /*
+ * Only measure the CPUs specified by /proc/irq/prof_cpu_mask.
+ * (default is all CPUs.)
+ */
+ if (!((1<<smp_processor_id()) & prof_cpu_mask))
+ return;
+
+ eip -= (unsigned long) &_stext;
+ eip >>= prof_shift;
+ /*
+ * Don't ignore out-of-bounds EIP values silently,
+ * put them into the last histogram slot, so if
+ * present, they will show up as a sharp peak.
+ */
+ if (eip > prof_len-1)
+ eip = prof_len-1;
+ atomic_inc((atomic_t *)&prof_buffer[eip]);
+}
+
+static inline void hw_resend_irq(struct hw_interrupt_type *h,
+ unsigned int i)
+{}
+
+#endif /* _ASM_HW_IRQ_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/console/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/console/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,2 @@
+
+obj-y := console.o
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/kernel/time.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/kernel/time.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,415 @@
+/*
+ * linux/kernel/time.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * This file contains the interface functions for the various
+ * time related system calls: time, stime, gettimeofday, settimeofday,
+ * adjtime
+ */
+/*
+ * Modification history kernel/time.c
+ *
+ * 1993-09-02 Philip Gladstone
+ * Created file with time related functions from sched.c and adjtimex()
+ * 1993-10-08 Torsten Duwe
+ * adjtime interface update and CMOS clock write code
+ * 1995-08-13 Torsten Duwe
+ * kernel PLL updated to 1994-12-13 specs (rfc-1589)
+ * 1999-01-16 Ulrich Windl
+ * Introduced error checking for many cases in adjtimex().
+ * Updated NTP code according to technical memorandum Jan '96
+ * "A Kernel Model for Precision Timekeeping" by Dave Mills
+ * Allow time_constant larger than MAXTC(6) for NTP v4 (MAXTC == 10)
+ * (Even though the technical memorandum forbids it)
+ */
+
+#include <linux/mm.h>
+#include <linux/timex.h>
+#include <linux/smp_lock.h>
+
+#include <asm/uaccess.h>
+
+/*
+ * The timezone where the local system is located. Used as a default by some
+ * programs who obtain this value by using gettimeofday.
+ */
+struct timezone sys_tz;
+
+/* The xtime_lock is not only serializing the xtime read/writes but it's also
+ serializing all accesses to the global NTP variables now. */
+extern rwlock_t xtime_lock;
+
+#if !defined(__alpha__) && !defined(__ia64__)
+
+/*
+ * sys_time() can be implemented in user-level using
+ * sys_gettimeofday(). Is this for backwards compatibility? If so,
+ * why not move it into the appropriate arch directory (for those
+ * architectures that need it).
+ *
+ * XXX This function is NOT 64-bit clean!
+ */
+asmlinkage long sys_time(int * tloc)
+{
+ struct timeval now;
+ int i;
+
+ do_gettimeofday(&now);
+ i = now.tv_sec;
+ if (tloc) {
+ if (put_user(i,tloc))
+ i = -EFAULT;
+ }
+ return i;
+}
+
+#if !defined(CONFIG_XEN)
+
+/*
+ * sys_stime() can be implemented in user-level using
+ * sys_settimeofday(). Is this for backwards compatibility? If so,
+ * why not move it into the appropriate arch directory (for those
+ * architectures that need it).
+ */
+
+asmlinkage long sys_stime(int * tptr)
+{
+ int value;
+
+ if (!capable(CAP_SYS_TIME))
+ return -EPERM;
+ if (get_user(value, tptr))
+ return -EFAULT;
+ write_lock_irq(&xtime_lock);
+ vxtime_lock();
+ xtime.tv_sec = value;
+ xtime.tv_usec = 0;
+ vxtime_unlock();
+ time_adjust = 0; /* stop active adjtime() */
+ time_status |= STA_UNSYNC;
+ time_maxerror = NTP_PHASE_LIMIT;
+ time_esterror = NTP_PHASE_LIMIT;
+ write_unlock_irq(&xtime_lock);
+ return 0;
+}
+
+#endif
+
+#endif
+
+asmlinkage long sys_gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+ if (tv) {
+ struct timeval ktv;
+ do_gettimeofday(&ktv);
+ if (copy_to_user(tv, &ktv, sizeof(ktv)))
+ return -EFAULT;
+ }
+ if (tz) {
+ if (copy_to_user(tz, &sys_tz, sizeof(sys_tz)))
+ return -EFAULT;
+ }
+ return 0;
+}
+
+/*
+ * Adjust the time obtained from the CMOS to be UTC time instead of
+ * local time.
+ *
+ * This is ugly, but preferable to the alternatives. Otherwise we
+ * would either need to write a program to do it in /etc/rc (and risk
+ * confusion if the program gets run more than once; it would also be
+ * hard to make the program warp the clock precisely n hours) or
+ * compile in the timezone information into the kernel. Bad, bad....
+ *
+ * - TYT, 1992-01-01
+ *
+ * The best thing to do is to keep the CMOS clock in universal time (UTC)
+ * as real UNIX machines always do it. This avoids all headaches about
+ * daylight saving times and warping kernel clocks.
+ */
+inline static void warp_clock(void)
+{
+ write_lock_irq(&xtime_lock);
+ vxtime_lock();
+ xtime.tv_sec += sys_tz.tz_minuteswest * 60;
+ vxtime_unlock();
+ write_unlock_irq(&xtime_lock);
+}
+
+/*
+ * In case for some reason the CMOS clock has not already been running
+ * in UTC, but in some local time: The first time we set the timezone,
+ * we will warp the clock so that it is ticking UTC time instead of
+ * local time. Presumably, if someone is setting the timezone then we
+ * are running in an environment where the programs understand about
+ * timezones. This should be done at boot time in the /etc/rc script,
+ * as soon as possible, so that the clock can be set right. Otherwise,
+ * various programs will get confused when the clock gets warped.
+ */
+
+int do_sys_settimeofday(struct timeval *tv, struct timezone *tz)
+{
+ static int firsttime = 1;
+
+ if (!capable(CAP_SYS_TIME))
+ return -EPERM;
+
+ if (tz) {
+ /* SMP safe, global irq locking makes it work. */
+ sys_tz = *tz;
+ if (firsttime) {
+ firsttime = 0;
+ if (!tv)
+ warp_clock();
+ }
+ }
+ if (tv)
+ {
+ /* SMP safe, again the code in arch/foo/time.c should
+ * globally block out interrupts when it runs.
+ */
+ do_settimeofday(tv);
+ }
+ return 0;
+}
+
+asmlinkage long sys_settimeofday(struct timeval *tv, struct timezone *tz)
+{
+ struct timeval new_tv;
+ struct timezone new_tz;
+
+ if (tv) {
+ if (copy_from_user(&new_tv, tv, sizeof(*tv)))
+ return -EFAULT;
+ }
+ if (tz) {
+ if (copy_from_user(&new_tz, tz, sizeof(*tz)))
+ return -EFAULT;
+ }
+
+ return do_sys_settimeofday(tv ? &new_tv : NULL, tz ? &new_tz : NULL);
+}
+
+long pps_offset; /* pps time offset (us) */
+long pps_jitter = MAXTIME; /* time dispersion (jitter) (us) */
+
+long pps_freq; /* frequency offset (scaled ppm) */
+long pps_stabil = MAXFREQ; /* frequency dispersion (scaled ppm) */
+
+long pps_valid = PPS_VALID; /* pps signal watchdog counter */
+
+int pps_shift = PPS_SHIFT; /* interval duration (s) (shift) */
+
+long pps_jitcnt; /* jitter limit exceeded */
+long pps_calcnt; /* calibration intervals */
+long pps_errcnt; /* calibration errors */
+long pps_stbcnt; /* stability limit exceeded */
+
+/* hook for a loadable hardpps kernel module */
+void (*hardpps_ptr)(struct timeval *);
+
+/* adjtimex mainly allows reading (and writing, if superuser) of
+ * kernel time-keeping variables. used by xntpd.
+ */
+int do_adjtimex(struct timex *txc)
+{
+ long ltemp, mtemp, save_adjust;
+ int result;
+
+ /* In order to modify anything, you gotta be super-user! */
+ if (txc->modes && !capable(CAP_SYS_TIME))
+ return -EPERM;
+
+ /* Now we validate the data before disabling interrupts */
+
+ if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT)
+ /* singleshot must not be used with any other mode bits */
+ if (txc->modes != ADJ_OFFSET_SINGLESHOT)
+ return -EINVAL;
+
+ if (txc->modes != ADJ_OFFSET_SINGLESHOT && (txc->modes & ADJ_OFFSET))
+ /* adjustment Offset limited to +- .512 seconds */
+ if (txc->offset <= - MAXPHASE || txc->offset >= MAXPHASE )
+ return -EINVAL;
+
+ /* if the quartz is off by more than 10% something is VERY wrong ! */
+ if (txc->modes & ADJ_TICK)
+ if (txc->tick < 900000/HZ || txc->tick > 1100000/HZ)
+ return -EINVAL;
+
+ write_lock_irq(&xtime_lock);
+ result = time_state; /* mostly `TIME_OK' */
+
+ /* Save for later - semantics of adjtime is to return old value */
+ save_adjust = time_adjust;
+
+#if 0 /* STA_CLOCKERR is never set yet */
+ time_status &= ~STA_CLOCKERR; /* reset STA_CLOCKERR */
+#endif
+ /* If there are input parameters, then process them */
+ if (txc->modes)
+ {
+ if (txc->modes & ADJ_STATUS) /* only set allowed bits */
+ time_status = (txc->status & ~STA_RONLY) |
+ (time_status & STA_RONLY);
+
+ if (txc->modes & ADJ_FREQUENCY) { /* p. 22 */
+ if (txc->freq > MAXFREQ || txc->freq < -MAXFREQ) {
+ result = -EINVAL;
+ goto leave;
+ }
+ time_freq = txc->freq - pps_freq;
+ }
+
+ if (txc->modes & ADJ_MAXERROR) {
+ if (txc->maxerror < 0 || txc->maxerror >= NTP_PHASE_LIMIT) {
+ result = -EINVAL;
+ goto leave;
+ }
+ time_maxerror = txc->maxerror;
+ }
+
+ if (txc->modes & ADJ_ESTERROR) {
+ if (txc->esterror < 0 || txc->esterror >= NTP_PHASE_LIMIT) {
+ result = -EINVAL;
+ goto leave;
+ }
+ time_esterror = txc->esterror;
+ }
+
+ if (txc->modes & ADJ_TIMECONST) { /* p. 24 */
+ if (txc->constant < 0) { /* NTP v4 uses values > 6 */
+ result = -EINVAL;
+ goto leave;
+ }
+ time_constant = txc->constant;
+ }
+
+ if (txc->modes & ADJ_OFFSET) { /* values checked earlier */
+ if (txc->modes == ADJ_OFFSET_SINGLESHOT) {
+ /* adjtime() is independent from ntp_adjtime() */
+ time_adjust = txc->offset;
+ }
+ else if ( time_status & (STA_PLL | STA_PPSTIME) ) {
+ ltemp = (time_status & (STA_PPSTIME | STA_PPSSIGNAL)) ==
+ (STA_PPSTIME | STA_PPSSIGNAL) ?
+ pps_offset : txc->offset;
+
+ /*
+ * Scale the phase adjustment and
+ * clamp to the operating range.
+ */
+ if (ltemp > MAXPHASE)
+ time_offset = MAXPHASE << SHIFT_UPDATE;
+ else if (ltemp < -MAXPHASE)
+ time_offset = -(MAXPHASE << SHIFT_UPDATE);
+ else
+ time_offset = ltemp << SHIFT_UPDATE;
+
+ /*
+ * Select whether the frequency is to be controlled
+ * and in which mode (PLL or FLL). Clamp to the operating
+ * range. Ugly multiply/divide should be replaced someday.
+ */
+
+ if (time_status & STA_FREQHOLD || time_reftime == 0)
+ time_reftime = xtime.tv_sec;
+ mtemp = xtime.tv_sec - time_reftime;
+ time_reftime = xtime.tv_sec;
+ if (time_status & STA_FLL) {
+ if (mtemp >= MINSEC) {
+ ltemp = (time_offset / mtemp) << (SHIFT_USEC -
+ SHIFT_UPDATE);
+ if (ltemp < 0)
+ time_freq -= -ltemp >> SHIFT_KH;
+ else
+ time_freq += ltemp >> SHIFT_KH;
+ } else /* calibration interval too short (p. 12) */
+ result = TIME_ERROR;
+ } else { /* PLL mode */
+ if (mtemp < MAXSEC) {
+ ltemp *= mtemp;
+ if (ltemp < 0)
+ time_freq -= -ltemp >> (time_constant +
+ time_constant +
+ SHIFT_KF - SHIFT_USEC);
+ else
+ time_freq += ltemp >> (time_constant +
+ time_constant +
+ SHIFT_KF - SHIFT_USEC);
+ } else /* calibration interval too long (p. 12) */
+ result = TIME_ERROR;
+ }
+ if (time_freq > time_tolerance)
+ time_freq = time_tolerance;
+ else if (time_freq < -time_tolerance)
+ time_freq = -time_tolerance;
+ } /* STA_PLL || STA_PPSTIME */
+ } /* txc->modes & ADJ_OFFSET */
+ if (txc->modes & ADJ_TICK) {
+ /* if the quartz is off by more than 10% something is
+ VERY wrong ! */
+ if (txc->tick < 900000/HZ || txc->tick > 1100000/HZ) {
+ result = -EINVAL;
+ goto leave;
+ }
+ tick = txc->tick;
+ }
+ } /* txc->modes */
+leave: if ((time_status & (STA_UNSYNC|STA_CLOCKERR)) != 0
+ || ((time_status & (STA_PPSFREQ|STA_PPSTIME)) != 0
+ && (time_status & STA_PPSSIGNAL) == 0)
+ /* p. 24, (b) */
+ || ((time_status & (STA_PPSTIME|STA_PPSJITTER))
+ == (STA_PPSTIME|STA_PPSJITTER))
+ /* p. 24, (c) */
+ || ((time_status & STA_PPSFREQ) != 0
+ && (time_status & (STA_PPSWANDER|STA_PPSERROR)) != 0))
+ /* p. 24, (d) */
+ result = TIME_ERROR;
+
+ if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT)
+ txc->offset = save_adjust;
+ else {
+ if (time_offset < 0)
+ txc->offset = -(-time_offset >> SHIFT_UPDATE);
+ else
+ txc->offset = time_offset >> SHIFT_UPDATE;
+ }
+ txc->freq = time_freq + pps_freq;
+ txc->maxerror = time_maxerror;
+ txc->esterror = time_esterror;
+ txc->status = time_status;
+ txc->constant = time_constant;
+ txc->precision = time_precision;
+ txc->tolerance = time_tolerance;
+ txc->tick = tick;
+ txc->ppsfreq = pps_freq;
+ txc->jitter = pps_jitter >> PPS_AVG;
+ txc->shift = pps_shift;
+ txc->stabil = pps_stabil;
+ txc->jitcnt = pps_jitcnt;
+ txc->calcnt = pps_calcnt;
+ txc->errcnt = pps_errcnt;
+ txc->stbcnt = pps_stbcnt;
+ write_unlock_irq(&xtime_lock);
+ do_gettimeofday(&txc->time);
+ return(result);
+}
+
+asmlinkage long sys_adjtimex(struct timex *txc_p)
+{
+ struct timex txc; /* Local copy of parameter */
+ int ret;
+
+ /* Copy the user data space into the kernel copy
+ * structure. But bear in mind that the structures
+ * may change
+ */
+ if(copy_from_user(&txc, txc_p, sizeof(struct timex)))
+ return -EFAULT;
+ ret = do_adjtimex(&txc);
+ return copy_to_user(txc_p, &txc, sizeof(struct timex)) ? -EFAULT : ret;
+}
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/pal_emul.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/pal_emul.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,283 @@
+/* PAL/SAL call delegation
+ *
+ * Copyright (c) 2004 Li Susie <susie.li@xxxxxxxxx>
+ * Copyright (c) 2005 Yu Ke <ke.yu@xxxxxxxxx>
+ */
+
+#include <asm/vmx_vcpu.h>
+
+static void
+get_pal_parameters (VCPU *vcpu, UINT64 *gr29,
+ UINT64 *gr30, UINT64 *gr31) {
+
+ vmx_vcpu_get_gr(vcpu,29,gr29);
+ vmx_vcpu_get_gr(vcpu,30,gr30);
+ vmx_vcpu_get_gr(vcpu,31,gr31);
+}
+
+static void
+set_pal_result (VCPU *vcpu,struct ia64_pal_retval result) {
+
+ vmx_vcpu_set_gr(vcpu,8, result.status,0);
+ vmx_vcpu_set_gr(vcpu,9, result.v0,0);
+ vmx_vcpu_set_gr(vcpu,10, result.v1,0);
+ vmx_vcpu_set_gr(vcpu,11, result.v2,0);
+}
+
+
+static struct ia64_pal_retval
+pal_cache_flush (VCPU *vcpu) {
+ UINT64 gr28,gr29, gr30, gr31;
+ struct ia64_pal_retval result;
+
+ get_pal_parameters (vcpu, &gr29, &gr30, &gr31);
+ vmx_vcpu_get_gr(vcpu,28,&gr28);
+
+ /* Always call Host Pal in int=1 */
+ gr30 = gr30 &(~(0x2UL));
+
+ /* call Host PAL cache flush */
+ result=ia64_pal_call_static(gr28 ,gr29, gr30,gr31,1); // Clear psr.ic
when call PAL_CACHE_FLUSH
+
+ /* If host PAL call is interrupted, then loop to complete it */
+// while (result.status == 1) {
+// ia64_pal_call_static(gr28 ,gr29, gr30,
+// result.v1,1LL);
+// }
+ while (result.status != 0) {
+ panic("PAL_CACHE_FLUSH ERROR, status %d", result.status);
+ }
+
+ return result;
+}
+
+static struct ia64_pal_retval
+pal_vm_tr_read (VCPU *vcpu ) {
+#warning pal_vm_tr_read: to be implemented
+ struct ia64_pal_retval result;
+
+ result.status= -1; //unimplemented
+
+ return result;
+}
+
+
+static struct ia64_pal_retval
+pal_prefetch_visibility (VCPU *vcpu) {
+ /* Due to current MM virtualization algorithm,
+ * We do not allow guest to change mapping attribute.
+ * Thus we will not support PAL_PREFETCH_VISIBILITY
+ */
+ struct ia64_pal_retval result;
+
+ result.status= -1; //unimplemented
+
+ return result;
+}
+
+static struct ia64_pal_retval
+pal_platform_addr(VCPU *vcpu) {
+ struct ia64_pal_retval result;
+
+ result.status= 0; //success
+
+ return result;
+}
+
+static struct ia64_pal_retval
+pal_halt (VCPU *vcpu) {
+#warning pal_halt: to be implemented
+ //bugbug: to be implement.
+ struct ia64_pal_retval result;
+
+ result.status= -1; //unimplemented
+
+ return result;
+}
+
+
+static struct ia64_pal_retval
+pal_halt_light (VCPU *vcpu) {
+#if 0
+ // GVMM will go back to HVMM and ask HVMM to call yield().
+ vmmdata.p_ctlblk->status = VM_OK;
+ vmmdata.p_ctlblk->ctlcode = ExitVM_YIELD;
+
+ vmm_transition((UINT64)&vmmdata.p_gsa->guest,
+ (UINT64)&vmmdata.p_gsa->host,
+ (UINT64) vmmdata.p_tramp,0,0);
+
+
+ result.status = 0;
+ result.pal_result[0]=0;
+ result.pal_result[1]=0;
+ result.pal_result[2]=0;
+
+ return result;
+#endif
+ struct ia64_pal_retval result;
+
+ result.status= -1; //unimplemented
+
+ return result;
+}
+
+static struct ia64_pal_retval
+pal_cache_read (VCPU *vcpu) {
+ struct ia64_pal_retval result;
+
+ result.status= -1; //unimplemented
+
+ return result;
+}
+
+static struct ia64_pal_retval
+pal_cache_write (VCPU *vcpu) {
+ struct ia64_pal_retval result;
+
+ result.status= -1; //unimplemented
+
+ return result;
+}
+
+static struct ia64_pal_retval
+pal_bus_get_features(VCPU *vcpu){
+
+}
+
+static struct ia64_pal_retval
+pal_cache_summary(VCPU *vcpu){
+
+}
+
+static struct ia64_pal_retval
+pal_cache_init(VCPU *vcpu){
+ struct ia64_pal_retval result;
+ result.status=0;
+ return result;
+}
+
+static struct ia64_pal_retval
+pal_cache_info(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_cache_prot_info(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_cache_shared_info(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_mem_attrib(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_debug_info(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_fixed_addr(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_freq_base(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_freq_ratios(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_halt_info(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_logical_to_physica(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_perf_mon_info(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_proc_get_features(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_ptce_info(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_register_info(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_rse_info(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_test_info(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_vm_summary(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_vm_info(VCPU *vcpu){
+}
+
+static struct ia64_pal_retval
+pal_vm_page_size(VCPU *vcpu){
+}
+
+void
+pal_emul( VCPU *vcpu) {
+ UINT64 gr28;
+ struct ia64_pal_retval result;
+
+
+ vmx_vcpu_get_gr(vcpu,28,&gr28); //bank1
+
+ switch (gr28) {
+ case PAL_CACHE_FLUSH:
+ result = pal_cache_flush (vcpu);
+ break;
+
+ case PAL_PREFETCH_VISIBILITY:
+ result = pal_prefetch_visibility (vcpu);
+ break;
+
+ case PAL_VM_TR_READ:
+ result = pal_vm_tr_read (vcpu);
+ break;
+
+ case PAL_HALT:
+ result = pal_halt (vcpu);
+ break;
+
+ case PAL_HALT_LIGHT:
+ result = pal_halt_light (vcpu);
+ break;
+
+ case PAL_CACHE_READ:
+ result = pal_cache_read (vcpu);
+ break;
+
+ case PAL_CACHE_WRITE:
+ result = pal_cache_write (vcpu);
+ break;
+
+ case PAL_PLATFORM_ADDR:
+ result = pal_platform_addr (vcpu);
+ break;
+
+ default:
+ panic("pal_emul(): guest call unsupported pal" );
+ }
+ set_pal_result (vcpu, result);
+}
+
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/mm/pgtable.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/mm/pgtable.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,525 @@
+/*
+ * linux/arch/i386/mm/pgtable.c
+ */
+
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/smp.h>
+#include <linux/highmem.h>
+#include <linux/slab.h>
+#include <linux/pagemap.h>
+#include <linux/spinlock.h>
+
+#include <asm/system.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/fixmap.h>
+#include <asm/e820.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/io.h>
+#include <asm/mmu_context.h>
+
+#include <asm-xen/foreign_page.h>
+
+void show_mem(void)
+{
+ int total = 0, reserved = 0;
+ int shared = 0, cached = 0;
+ int highmem = 0;
+ struct page *page;
+ pg_data_t *pgdat;
+ unsigned long i;
+
+ printk("Mem-info:\n");
+ show_free_areas();
+ printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
+ for_each_pgdat(pgdat) {
+ for (i = 0; i < pgdat->node_spanned_pages; ++i) {
+ page = pgdat->node_mem_map + i;
+ total++;
+ if (PageHighMem(page))
+ highmem++;
+ if (PageReserved(page))
+ reserved++;
+ else if (PageSwapCache(page))
+ cached++;
+ else if (page_count(page))
+ shared += page_count(page) - 1;
+ }
+ }
+ printk("%d pages of RAM\n", total);
+ printk("%d pages of HIGHMEM\n",highmem);
+ printk("%d reserved pages\n",reserved);
+ printk("%d pages shared\n",shared);
+ printk("%d pages swap cached\n",cached);
+}
+
+/*
+ * Associate a virtual page frame with a given physical page frame
+ * and protection flags for that frame.
+ */
+static void set_pte_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pgd = swapper_pg_dir + pgd_index(vaddr);
+ if (pgd_none(*pgd)) {
+ BUG();
+ return;
+ }
+ pud = pud_offset(pgd, vaddr);
+ if (pud_none(*pud)) {
+ BUG();
+ return;
+ }
+ pmd = pmd_offset(pud, vaddr);
+ if (pmd_none(*pmd)) {
+ BUG();
+ return;
+ }
+ pte = pte_offset_kernel(pmd, vaddr);
+ /* <pfn,flags> stored as-is, to permit clearing entries */
+ set_pte(pte, pfn_pte(pfn, flags));
+
+ /*
+ * It's enough to flush this one mapping.
+ * (PGE mappings get flushed as well)
+ */
+ __flush_tlb_one(vaddr);
+}
+
+/*
+ * Associate a virtual page frame with a given physical page frame
+ * and protection flags for that frame.
+ */
+static void set_pte_pfn_ma(unsigned long vaddr, unsigned long pfn,
+ pgprot_t flags)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pgd = swapper_pg_dir + pgd_index(vaddr);
+ if (pgd_none(*pgd)) {
+ BUG();
+ return;
+ }
+ pud = pud_offset(pgd, vaddr);
+ if (pud_none(*pud)) {
+ BUG();
+ return;
+ }
+ pmd = pmd_offset(pud, vaddr);
+ if (pmd_none(*pmd)) {
+ BUG();
+ return;
+ }
+ pte = pte_offset_kernel(pmd, vaddr);
+ /* <pfn,flags> stored as-is, to permit clearing entries */
+ set_pte(pte, pfn_pte_ma(pfn, flags));
+
+ /*
+ * It's enough to flush this one mapping.
+ * (PGE mappings get flushed as well)
+ */
+ __flush_tlb_one(vaddr);
+}
+
+/*
+ * Associate a large virtual page frame with a given physical page frame
+ * and protection flags for that frame. pfn is for the base of the page,
+ * vaddr is what the page gets mapped to - both must be properly aligned.
+ * The pmd must already be instantiated. Assumes PAE mode.
+ */
+void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ if (vaddr & (PMD_SIZE-1)) { /* vaddr is misaligned */
+ printk ("set_pmd_pfn: vaddr misaligned\n");
+ return; /* BUG(); */
+ }
+ if (pfn & (PTRS_PER_PTE-1)) { /* pfn is misaligned */
+ printk ("set_pmd_pfn: pfn misaligned\n");
+ return; /* BUG(); */
+ }
+ pgd = swapper_pg_dir + pgd_index(vaddr);
+ if (pgd_none(*pgd)) {
+ printk ("set_pmd_pfn: pgd_none\n");
+ return; /* BUG(); */
+ }
+ pud = pud_offset(pgd, vaddr);
+ pmd = pmd_offset(pud, vaddr);
+ set_pmd(pmd, pfn_pmd(pfn, flags));
+ /*
+ * It's enough to flush this one mapping.
+ * (PGE mappings get flushed as well)
+ */
+ __flush_tlb_one(vaddr);
+}
+
+void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t
flags)
+{
+ unsigned long address = __fix_to_virt(idx);
+
+ if (idx >= __end_of_fixed_addresses) {
+ BUG();
+ return;
+ }
+ switch (idx) {
+ case FIX_WP_TEST:
+ case FIX_VSYSCALL:
+#ifdef CONFIG_X86_F00F_BUG
+ case FIX_F00F_IDT:
+#endif
+ set_pte_pfn(address, phys >> PAGE_SHIFT, flags);
+ break;
+ default:
+ set_pte_pfn_ma(address, phys >> PAGE_SHIFT, flags);
+ break;
+ }
+}
+
+pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
+{
+ pte_t *pte = (pte_t
*)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+ if (pte)
+ make_page_readonly(pte);
+ return pte;
+}
+
+struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
+{
+ struct page *pte;
+
+#ifdef CONFIG_HIGHPTE
+ pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT|__GFP_ZERO, 0);
+#else
+ pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
+ if (pte) {
+ SetPageForeign(pte, pte_free);
+ set_page_count(pte, 1);
+ }
+#endif
+
+ return pte;
+}
+
+void pte_free(struct page *pte)
+{
+ unsigned long va = (unsigned long)__va(page_to_pfn(pte)<<PAGE_SHIFT);
+
+ if (!pte_write(*virt_to_ptep(va)))
+ HYPERVISOR_update_va_mapping(
+ va, pfn_pte(page_to_pfn(pte), PAGE_KERNEL), 0);
+
+ ClearPageForeign(pte);
+ set_page_count(pte, 1);
+
+ __free_page(pte);
+}
+
+void pmd_ctor(void *pmd, kmem_cache_t *cache, unsigned long flags)
+{
+ memset(pmd, 0, PTRS_PER_PMD*sizeof(pmd_t));
+}
+
+/*
+ * List of all pgd's needed for non-PAE so it can invalidate entries
+ * in both cached and uncached pgd's; not needed for PAE since the
+ * kernel pmd is shared. If PAE were not to share the pmd a similar
+ * tactic would be needed. This is essentially codepath-based locking
+ * against pageattr.c; it is the unique case in which a valid change
+ * of kernel pagetables can't be lazily synchronized by vmalloc faults.
+ * vmalloc faults work because attached pagetables are never freed.
+ * The locking scheme was chosen on the basis of manfred's
+ * recommendations and having no core impact whatsoever.
+ * -- wli
+ */
+DEFINE_SPINLOCK(pgd_lock);
+struct page *pgd_list;
+
+static inline void pgd_list_add(pgd_t *pgd)
+{
+ struct page *page = virt_to_page(pgd);
+ page->index = (unsigned long)pgd_list;
+ if (pgd_list)
+ pgd_list->private = (unsigned long)&page->index;
+ pgd_list = page;
+ page->private = (unsigned long)&pgd_list;
+}
+
+static inline void pgd_list_del(pgd_t *pgd)
+{
+ struct page *next, **pprev, *page = virt_to_page(pgd);
+ next = (struct page *)page->index;
+ pprev = (struct page **)page->private;
+ *pprev = next;
+ if (next)
+ next->private = (unsigned long)pprev;
+}
+
+void pgd_ctor(void *pgd, kmem_cache_t *cache, unsigned long unused)
+{
+ unsigned long flags;
+
+ if (PTRS_PER_PMD == 1)
+ spin_lock_irqsave(&pgd_lock, flags);
+
+ memcpy((pgd_t *)pgd + USER_PTRS_PER_PGD,
+ swapper_pg_dir + USER_PTRS_PER_PGD,
+ (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+
+ if (PTRS_PER_PMD > 1)
+ return;
+
+ pgd_list_add(pgd);
+ spin_unlock_irqrestore(&pgd_lock, flags);
+ memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t));
+}
+
+/* never called when PTRS_PER_PMD > 1 */
+void pgd_dtor(void *pgd, kmem_cache_t *cache, unsigned long unused)
+{
+ unsigned long flags; /* can be called from interrupt context */
+
+ if (PTRS_PER_PMD > 1)
+ return;
+
+ spin_lock_irqsave(&pgd_lock, flags);
+ pgd_list_del(pgd);
+ spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
+pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+ int i;
+ pgd_t *pgd = kmem_cache_alloc(pgd_cache, GFP_KERNEL);
+
+ if (PTRS_PER_PMD == 1 || !pgd)
+ return pgd;
+
+ for (i = 0; i < USER_PTRS_PER_PGD; ++i) {
+ pmd_t *pmd = kmem_cache_alloc(pmd_cache, GFP_KERNEL);
+ if (!pmd)
+ goto out_oom;
+ set_pgd(&pgd[i], __pgd(1 + __pa(pmd)));
+ }
+ return pgd;
+
+out_oom:
+ for (i--; i >= 0; i--)
+ kmem_cache_free(pmd_cache, (void *)__va(pgd_val(pgd[i])-1));
+ kmem_cache_free(pgd_cache, pgd);
+ return NULL;
+}
+
+void pgd_free(pgd_t *pgd)
+{
+ int i;
+ pte_t *ptep = virt_to_ptep(pgd);
+
+ if (!pte_write(*ptep)) {
+ xen_pgd_unpin(__pa(pgd));
+ HYPERVISOR_update_va_mapping(
+ (unsigned long)pgd,
+ pfn_pte(virt_to_phys(pgd)>>PAGE_SHIFT, PAGE_KERNEL),
+ 0);
+ }
+
+ /* in the PAE case user pgd entries are overwritten before usage */
+ if (PTRS_PER_PMD > 1)
+ for (i = 0; i < USER_PTRS_PER_PGD; ++i)
+ kmem_cache_free(pmd_cache, (void
*)__va(pgd_val(pgd[i])-1));
+ /* in the non-PAE case, clear_page_range() clears user pgd entries */
+ kmem_cache_free(pgd_cache, pgd);
+}
+
+#ifndef CONFIG_XEN_SHADOW_MODE
+void make_lowmem_page_readonly(void *va)
+{
+ pte_t *pte = virt_to_ptep(va);
+ set_pte(pte, pte_wrprotect(*pte));
+}
+
+void make_lowmem_page_writable(void *va)
+{
+ pte_t *pte = virt_to_ptep(va);
+ set_pte(pte, pte_mkwrite(*pte));
+}
+
+void make_page_readonly(void *va)
+{
+ pte_t *pte = virt_to_ptep(va);
+ set_pte(pte, pte_wrprotect(*pte));
+ if ( (unsigned long)va >= (unsigned long)high_memory )
+ {
+ unsigned long phys;
+ phys = machine_to_phys(*(unsigned long *)pte & PAGE_MASK);
+#ifdef CONFIG_HIGHMEM
+ if ( (phys >> PAGE_SHIFT) < highstart_pfn )
+#endif
+ make_lowmem_page_readonly(phys_to_virt(phys));
+ }
+}
+
+void make_page_writable(void *va)
+{
+ pte_t *pte = virt_to_ptep(va);
+ set_pte(pte, pte_mkwrite(*pte));
+ if ( (unsigned long)va >= (unsigned long)high_memory )
+ {
+ unsigned long phys;
+ phys = machine_to_phys(*(unsigned long *)pte & PAGE_MASK);
+#ifdef CONFIG_HIGHMEM
+ if ( (phys >> PAGE_SHIFT) < highstart_pfn )
+#endif
+ make_lowmem_page_writable(phys_to_virt(phys));
+ }
+}
+
+void make_pages_readonly(void *va, unsigned int nr)
+{
+ while ( nr-- != 0 )
+ {
+ make_page_readonly(va);
+ va = (void *)((unsigned long)va + PAGE_SIZE);
+ }
+}
+
+void make_pages_writable(void *va, unsigned int nr)
+{
+ while ( nr-- != 0 )
+ {
+ make_page_writable(va);
+ va = (void *)((unsigned long)va + PAGE_SIZE);
+ }
+}
+#endif /* CONFIG_XEN_SHADOW_MODE */
+
+LIST_HEAD(mm_unpinned);
+DEFINE_SPINLOCK(mm_unpinned_lock);
+
+static inline void mm_walk_set_prot(void *pt, pgprot_t flags)
+{
+ struct page *page = virt_to_page(pt);
+ unsigned long pfn = page_to_pfn(page);
+
+ if (PageHighMem(page))
+ return;
+ HYPERVISOR_update_va_mapping(
+ (unsigned long)__va(pfn << PAGE_SHIFT),
+ pfn_pte(pfn, flags), 0);
+}
+
+static void mm_walk(struct mm_struct *mm, pgprot_t flags)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+ int g,u,m;
+
+ pgd = mm->pgd;
+ for (g = 0; g < USER_PTRS_PER_PGD; g++, pgd++) {
+ if (pgd_none(*pgd))
+ continue;
+ pud = pud_offset(pgd, 0);
+ if (PTRS_PER_PUD > 1) /* not folded */
+ mm_walk_set_prot(pud,flags);
+ for (u = 0; u < PTRS_PER_PUD; u++, pud++) {
+ if (pud_none(*pud))
+ continue;
+ pmd = pmd_offset(pud, 0);
+ if (PTRS_PER_PMD > 1) /* not folded */
+ mm_walk_set_prot(pmd,flags);
+ for (m = 0; m < PTRS_PER_PMD; m++, pmd++) {
+ if (pmd_none(*pmd))
+ continue;
+ pte = pte_offset_kernel(pmd,0);
+ mm_walk_set_prot(pte,flags);
+ }
+ }
+ }
+}
+
+void mm_pin(struct mm_struct *mm)
+{
+ spin_lock(&mm->page_table_lock);
+
+ mm_walk(mm, PAGE_KERNEL_RO);
+ HYPERVISOR_update_va_mapping(
+ (unsigned long)mm->pgd,
+ pfn_pte(virt_to_phys(mm->pgd)>>PAGE_SHIFT, PAGE_KERNEL_RO),
+ UVMF_TLB_FLUSH);
+ xen_pgd_pin(__pa(mm->pgd));
+ mm->context.pinned = 1;
+ spin_lock(&mm_unpinned_lock);
+ list_del(&mm->context.unpinned);
+ spin_unlock(&mm_unpinned_lock);
+
+ spin_unlock(&mm->page_table_lock);
+}
+
+void mm_unpin(struct mm_struct *mm)
+{
+ spin_lock(&mm->page_table_lock);
+
+ xen_pgd_unpin(__pa(mm->pgd));
+ HYPERVISOR_update_va_mapping(
+ (unsigned long)mm->pgd,
+ pfn_pte(virt_to_phys(mm->pgd)>>PAGE_SHIFT, PAGE_KERNEL), 0);
+ mm_walk(mm, PAGE_KERNEL);
+ xen_tlb_flush();
+ mm->context.pinned = 0;
+ spin_lock(&mm_unpinned_lock);
+ list_add(&mm->context.unpinned, &mm_unpinned);
+ spin_unlock(&mm_unpinned_lock);
+
+ spin_unlock(&mm->page_table_lock);
+}
+
+void mm_pin_all(void)
+{
+ while (!list_empty(&mm_unpinned))
+ mm_pin(list_entry(mm_unpinned.next, struct mm_struct,
+ context.unpinned));
+}
+
+void _arch_exit_mmap(struct mm_struct *mm)
+{
+ struct task_struct *tsk = current;
+
+ task_lock(tsk);
+
+ /*
+ * We aggressively remove defunct pgd from cr3. We execute unmap_vmas()
+ * *much* faster this way, as no tlb flushes means bigger wrpt batches.
+ */
+ if ( tsk->active_mm == mm )
+ {
+ tsk->active_mm = &init_mm;
+ atomic_inc(&init_mm.mm_count);
+
+ switch_mm(mm, &init_mm, tsk);
+
+ atomic_dec(&mm->mm_count);
+ BUG_ON(atomic_read(&mm->mm_count) == 0);
+ }
+
+ task_unlock(tsk);
+
+ if ( mm->context.pinned && (atomic_read(&mm->mm_count) == 1) )
+ mm_unpin(mm);
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/synch_bitops.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/synch_bitops.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,2 @@
+
+#include <asm-i386/synch_bitops.h>
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/entry.S
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/entry.S Fri Jul 15
13:39:50 2005
@@ -0,0 +1,1047 @@
+/*
+ * linux/arch/i386/entry.S
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+/*
+ * entry.S contains the system-call and fault low-level handling routines.
+ * This also contains the timer-interrupt handler, as well as all interrupts
+ * and faults that can result in a task-switch.
+ *
+ * NOTE: This code handles signal-recognition, which happens every time
+ * after a timer-interrupt and after each system call.
+ *
+ * I changed all the .align's to 4 (16 byte alignment), as that's faster
+ * on a 486.
+ *
+ * Stack layout in 'ret_from_system_call':
+ * ptrace needs to have all regs on the stack.
+ * if the order here is changed, it needs to be
+ * updated in fork.c:copy_process, signal.c:do_signal,
+ * ptrace.c and ptrace.h
+ *
+ * 0(%esp) - %ebx
+ * 4(%esp) - %ecx
+ * 8(%esp) - %edx
+ * C(%esp) - %esi
+ * 10(%esp) - %edi
+ * 14(%esp) - %ebp
+ * 18(%esp) - %eax
+ * 1C(%esp) - %ds
+ * 20(%esp) - %es
+ * 24(%esp) - orig_eax
+ * 28(%esp) - %eip
+ * 2C(%esp) - %cs
+ * 30(%esp) - %eflags
+ * 34(%esp) - %oldesp
+ * 38(%esp) - %oldss
+ *
+ * "current" is in register %ebx during any slow entries.
+ */
+
+#include <linux/config.h>
+#include <linux/linkage.h>
+#include <asm/thread_info.h>
+#include <asm/errno.h>
+#include <asm/segment.h>
+#include <asm/smp.h>
+#include <asm/page.h>
+#include "irq_vectors.h"
+#include <asm-xen/xen-public/xen.h>
+
+#define nr_syscalls ((syscall_table_size)/4)
+
+EBX = 0x00
+ECX = 0x04
+EDX = 0x08
+ESI = 0x0C
+EDI = 0x10
+EBP = 0x14
+EAX = 0x18
+DS = 0x1C
+ES = 0x20
+ORIG_EAX = 0x24
+EIP = 0x28
+CS = 0x2C
+EVENT_MASK = 0x2E
+EFLAGS = 0x30
+OLDESP = 0x34
+OLDSS = 0x38
+
+CF_MASK = 0x00000001
+TF_MASK = 0x00000100
+IF_MASK = 0x00000200
+DF_MASK = 0x00000400
+NT_MASK = 0x00004000
+VM_MASK = 0x00020000
+
+/* Offsets into shared_info_t. */
+#define evtchn_upcall_pending /* 0 */
+#define evtchn_upcall_mask 1
+
+#define sizeof_vcpu_shift 3
+
+#ifdef CONFIG_SMP
+#define preempt_disable(reg) incl TI_preempt_count(reg)
+#define preempt_enable(reg) decl TI_preempt_count(reg)
+#define XEN_GET_VCPU_INFO(reg) preempt_disable(%ebp) ; \
+ movl TI_cpu(%ebp),reg ; \
+ shl $sizeof_vcpu_shift,reg ; \
+ addl HYPERVISOR_shared_info,reg
+#define XEN_PUT_VCPU_INFO(reg) preempt_enable(%ebp)
+#define XEN_PUT_VCPU_INFO_fixup .byte 0xff,0xff,0xff
+#else
+#define XEN_GET_VCPU_INFO(reg) movl HYPERVISOR_shared_info,reg
+#define XEN_PUT_VCPU_INFO(reg)
+#define XEN_PUT_VCPU_INFO_fixup
+#endif
+
+#define XEN_LOCKED_BLOCK_EVENTS(reg) movb $1,evtchn_upcall_mask(reg)
+#define XEN_LOCKED_UNBLOCK_EVENTS(reg) movb $0,evtchn_upcall_mask(reg)
+#define XEN_BLOCK_EVENTS(reg) XEN_GET_VCPU_INFO(reg) ; \
+ XEN_LOCKED_BLOCK_EVENTS(reg) ; \
+ XEN_PUT_VCPU_INFO(reg)
+#define XEN_UNBLOCK_EVENTS(reg) XEN_GET_VCPU_INFO(reg)
; \
+ XEN_LOCKED_UNBLOCK_EVENTS(reg) ; \
+ XEN_PUT_VCPU_INFO(reg)
+#define XEN_TEST_PENDING(reg) testb $0xFF,evtchn_upcall_pending(reg)
+
+#ifdef CONFIG_PREEMPT
+#define preempt_stop GET_THREAD_INFO(%ebp) ; \
+ XEN_BLOCK_EVENTS(%esi)
+#else
+#define preempt_stop
+#define resume_kernel restore_all
+#endif
+
+#define SAVE_ALL \
+ cld; \
+ pushl %es; \
+ pushl %ds; \
+ pushl %eax; \
+ pushl %ebp; \
+ pushl %edi; \
+ pushl %esi; \
+ pushl %edx; \
+ pushl %ecx; \
+ pushl %ebx; \
+ movl $(__USER_DS), %edx; \
+ movl %edx, %ds; \
+ movl %edx, %es;
+
+#define RESTORE_INT_REGS \
+ popl %ebx; \
+ popl %ecx; \
+ popl %edx; \
+ popl %esi; \
+ popl %edi; \
+ popl %ebp; \
+ popl %eax
+
+#define RESTORE_REGS \
+ RESTORE_INT_REGS; \
+1: popl %ds; \
+2: popl %es; \
+.section .fixup,"ax"; \
+3: movl $0,(%esp); \
+ jmp 1b; \
+4: movl $0,(%esp); \
+ jmp 2b; \
+.previous; \
+.section __ex_table,"a";\
+ .align 4; \
+ .long 1b,3b; \
+ .long 2b,4b; \
+.previous
+
+
+#define RESTORE_ALL \
+ RESTORE_REGS \
+ addl $4, %esp; \
+1: iret; \
+.section .fixup,"ax"; \
+2: movl $(__USER_DS), %edx; \
+ movl %edx, %ds; \
+ movl %edx, %es; \
+ movl $11,%eax; \
+ call do_exit; \
+.previous; \
+.section __ex_table,"a";\
+ .align 4; \
+ .long 1b,2b; \
+.previous
+
+
+ENTRY(ret_from_fork)
+ pushl %eax
+ call schedule_tail
+ GET_THREAD_INFO(%ebp)
+ popl %eax
+ jmp syscall_exit
+
+/*
+ * Return to user mode is not as complex as all this looks,
+ * but we want the default path for a system call return to
+ * go as quickly as possible which is why some of this is
+ * less clear than it otherwise should be.
+ */
+
+ # userspace resumption stub bypassing syscall exit tracing
+ ALIGN
+ret_from_exception:
+ preempt_stop
+ret_from_intr:
+ GET_THREAD_INFO(%ebp)
+ movl EFLAGS(%esp), %eax # mix EFLAGS and CS
+ movb CS(%esp), %al
+ testl $(VM_MASK | 2), %eax
+ jz resume_kernel # returning to kernel or vm86-space
+ENTRY(resume_userspace)
+ XEN_BLOCK_EVENTS(%esi) # make sure we don't miss an interrupt
+ # setting need_resched or sigpending
+ # between sampling and the iret
+ movl TI_flags(%ebp), %ecx
+ andl $_TIF_WORK_MASK, %ecx # is there any work to be done on
+ # int/exception return?
+ jne work_pending
+ jmp restore_all
+
+#ifdef CONFIG_PREEMPT
+ENTRY(resume_kernel)
+ XEN_BLOCK_EVENTS(%esi)
+ cmpl $0,TI_preempt_count(%ebp) # non-zero preempt_count ?
+ jnz restore_all
+need_resched:
+ movl TI_flags(%ebp), %ecx # need_resched set ?
+ testb $_TIF_NEED_RESCHED, %cl
+ jz restore_all
+ testb $0xFF,EVENT_MASK(%esp) # interrupts off (exception path) ?
+ jnz restore_all
+ call preempt_schedule_irq
+ jmp need_resched
+#endif
+
+/* SYSENTER_RETURN points to after the "sysenter" instruction in
+ the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */
+
+ # sysenter call handler stub
+ENTRY(sysenter_entry)
+ movl TSS_sysenter_esp0(%esp),%esp
+sysenter_past_esp:
+ sti
+ pushl $(__USER_DS)
+ pushl %ebp
+ pushfl
+ pushl $(__USER_CS)
+ pushl $SYSENTER_RETURN
+
+/*
+ * Load the potential sixth argument from user stack.
+ * Careful about security.
+ */
+ cmpl $__PAGE_OFFSET-3,%ebp
+ jae syscall_fault
+1: movl (%ebp),%ebp
+.section __ex_table,"a"
+ .align 4
+ .long 1b,syscall_fault
+.previous
+
+ pushl %eax
+ SAVE_ALL
+ GET_THREAD_INFO(%ebp)
+
+ testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
+ jnz syscall_trace_entry
+ cmpl $(nr_syscalls), %eax
+ jae syscall_badsys
+ call *sys_call_table(,%eax,4)
+ movl %eax,EAX(%esp)
+ cli
+ movl TI_flags(%ebp), %ecx
+ testw $_TIF_ALLWORK_MASK, %cx
+ jne syscall_exit_work
+/* if something modifies registers it must also disable sysexit */
+ movl EIP(%esp), %edx
+ movl OLDESP(%esp), %ecx
+ xorl %ebp,%ebp
+ sti
+ sysexit
+
+
+ # system call handler stub
+ENTRY(system_call)
+ pushl %eax # save orig_eax
+ SAVE_ALL
+ GET_THREAD_INFO(%ebp)
+ # system call tracing in operation
+ testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
+ jnz syscall_trace_entry
+ cmpl $(nr_syscalls), %eax
+ jae syscall_badsys
+syscall_call:
+ call *sys_call_table(,%eax,4)
+ movl %eax,EAX(%esp) # store the return value
+syscall_exit:
+ XEN_BLOCK_EVENTS(%esi) # make sure we don't miss an interrupt
+ # setting need_resched or sigpending
+ # between sampling and the iret
+ movl TI_flags(%ebp), %ecx
+ testw $_TIF_ALLWORK_MASK, %cx # current->work
+ jne syscall_exit_work
+restore_all:
+ testl $VM_MASK, EFLAGS(%esp)
+ jnz resume_vm86
+ movb EVENT_MASK(%esp), %al
+ notb %al # %al == ~saved_mask
+ XEN_GET_VCPU_INFO(%esi)
+ andb evtchn_upcall_mask(%esi),%al
+ andb $1,%al # %al == mask & ~saved_mask
+ jnz restore_all_enable_events # != 0 => reenable event delivery
+ XEN_PUT_VCPU_INFO(%esi)
+ RESTORE_ALL
+
+resume_vm86:
+ XEN_UNBLOCK_EVENTS(%esi)
+ RESTORE_REGS
+ movl %eax,(%esp)
+ movl $__HYPERVISOR_switch_vm86,%eax
+ int $0x82
+ ud2
+
+ # perform work that needs to be done immediately before resumption
+ ALIGN
+work_pending:
+ testb $_TIF_NEED_RESCHED, %cl
+ jz work_notifysig
+work_resched:
+ call schedule
+ XEN_BLOCK_EVENTS(%esi) # make sure we don't miss an interrupt
+ # setting need_resched or sigpending
+ # between sampling and the iret
+ movl TI_flags(%ebp), %ecx
+ andl $_TIF_WORK_MASK, %ecx # is there any work to be done other
+ # than syscall tracing?
+ jz restore_all
+ testb $_TIF_NEED_RESCHED, %cl
+ jnz work_resched
+
+work_notifysig: # deal with pending signals and
+ # notify-resume requests
+ testl $VM_MASK, EFLAGS(%esp)
+ movl %esp, %eax
+ jne work_notifysig_v86 # returning to kernel-space or
+ # vm86-space
+ xorl %edx, %edx
+ call do_notify_resume
+ jmp restore_all
+
+ ALIGN
+work_notifysig_v86:
+ pushl %ecx # save ti_flags for do_notify_resume
+ call save_v86_state # %eax contains pt_regs pointer
+ popl %ecx
+ movl %eax, %esp
+ xorl %edx, %edx
+ call do_notify_resume
+ jmp restore_all
+
+ # perform syscall exit tracing
+ ALIGN
+syscall_trace_entry:
+ movl $-ENOSYS,EAX(%esp)
+ movl %esp, %eax
+ xorl %edx,%edx
+ call do_syscall_trace
+ movl ORIG_EAX(%esp), %eax
+ cmpl $(nr_syscalls), %eax
+ jnae syscall_call
+ jmp syscall_exit
+
+ # perform syscall exit tracing
+ ALIGN
+syscall_exit_work:
+ testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP), %cl
+ jz work_pending
+ XEN_UNBLOCK_EVENTS(%esi) # could let do_syscall_trace() call
+ # schedule() instead
+ movl %esp, %eax
+ movl $1, %edx
+ call do_syscall_trace
+ jmp resume_userspace
+
+ ALIGN
+syscall_fault:
+ pushl %eax # save orig_eax
+ SAVE_ALL
+ GET_THREAD_INFO(%ebp)
+ movl $-EFAULT,EAX(%esp)
+ jmp resume_userspace
+
+ ALIGN
+syscall_badsys:
+ movl $-ENOSYS,EAX(%esp)
+ jmp resume_userspace
+
+#if 0 /* XEN */
+/*
+ * Build the entry stubs and pointer table with
+ * some assembler magic.
+ */
+.data
+ENTRY(interrupt)
+.text
+
+vector=0
+ENTRY(irq_entries_start)
+.rept NR_IRQS
+ ALIGN
+1: pushl $vector-256
+ jmp common_interrupt
+.data
+ .long 1b
+.text
+vector=vector+1
+.endr
+
+ ALIGN
+common_interrupt:
+ SAVE_ALL
+ movl %esp,%eax
+ call do_IRQ
+ jmp ret_from_intr
+
+#define BUILD_INTERRUPT(name, nr) \
+ENTRY(name) \
+ pushl $nr-256; \
+ SAVE_ALL \
+ movl %esp,%eax; \
+ call smp_/**/name; \
+ jmp ret_from_intr;
+
+/* The include is where all of the SMP etc. interrupts come from */
+#include "entry_arch.h"
+#endif /* XEN */
+
+ENTRY(divide_error)
+ pushl $0 # no error code
+ pushl $do_divide_error
+ ALIGN
+error_code:
+ pushl %ds
+ pushl %eax
+ xorl %eax, %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ decl %eax # eax = -1
+ pushl %ecx
+ pushl %ebx
+ cld
+ movl %es, %ecx
+ movl ES(%esp), %edi # get the function address
+ movl ORIG_EAX(%esp), %edx # get the error code
+ movl %eax, ORIG_EAX(%esp)
+ movl %ecx, ES(%esp)
+ movl $(__USER_DS), %ecx
+ movl %ecx, %ds
+ movl %ecx, %es
+ movl %esp,%eax # pt_regs pointer
+ call *%edi
+ jmp ret_from_exception
+
+# A note on the "critical region" in our callback handler.
+# We want to avoid stacking callback handlers due to events occurring
+# during handling of the last event. To do this, we keep events disabled
+# until we've done all processing. HOWEVER, we must enable events before
+# popping the stack frame (can't be done atomically) and so it would still
+# be possible to get enough handler activations to overflow the stack.
+# Although unlikely, bugs of that kind are hard to track down, so we'd
+# like to avoid the possibility.
+# So, on entry to the handler we detect whether we interrupted an
+# existing activation in its critical region -- if so, we pop the current
+# activation and restart the handler using the previous one.
+ENTRY(hypervisor_callback)
+ pushl %eax
+ SAVE_ALL
+ movl EIP(%esp),%eax
+ cmpl $scrit,%eax
+ jb 11f
+ cmpl $ecrit,%eax
+ jb critical_region_fixup
+11: push %esp
+ call evtchn_do_upcall
+ add $4,%esp
+ jmp ret_from_intr
+
+ ALIGN
+restore_all_enable_events:
+ XEN_LOCKED_UNBLOCK_EVENTS(%esi)
+scrit: /**** START OF CRITICAL REGION ****/
+ XEN_TEST_PENDING(%esi)
+ jnz 14f # process more events if necessary...
+ XEN_PUT_VCPU_INFO(%esi)
+ RESTORE_ALL
+14: XEN_LOCKED_BLOCK_EVENTS(%esi)
+ XEN_PUT_VCPU_INFO(%esi)
+ jmp 11b
+ecrit: /**** END OF CRITICAL REGION ****/
+# [How we do the fixup]. We want to merge the current stack frame with the
+# just-interrupted frame. How we do this depends on where in the critical
+# region the interrupted handler was executing, and so how many saved
+# registers are in each frame. We do this quickly using the lookup table
+# 'critical_fixup_table'. For each byte offset in the critical region, it
+# provides the number of bytes which have already been popped from the
+# interrupted stack frame.
+critical_region_fixup:
+ addl $critical_fixup_table-scrit,%eax
+ movzbl (%eax),%eax # %eax contains num bytes popped
+ cmpb $0xff,%al # 0xff => vcpu_info critical region
+ jne 15f
+ GET_THREAD_INFO(%ebp)
+ XEN_PUT_VCPU_INFO(%esi) # abort vcpu_info critical region
+ xorl %eax,%eax
+15: mov %esp,%esi
+ add %eax,%esi # %esi points at end of src region
+ mov %esp,%edi
+ add $0x34,%edi # %edi points at end of dst region
+ mov %eax,%ecx
+ shr $2,%ecx # convert words to bytes
+ je 17f # skip loop if nothing to copy
+16: subl $4,%esi # pre-decrementing copy loop
+ subl $4,%edi
+ movl (%esi),%eax
+ movl %eax,(%edi)
+ loop 16b
+17: movl %edi,%esp # final %edi is top of merged stack
+ jmp 11b
+
+critical_fixup_table:
+ .byte 0xff,0xff,0xff # testb $0xff,(%esi) = XEN_TEST_PENDING
+ .byte 0xff,0xff # jnz 14f
+ XEN_PUT_VCPU_INFO_fixup
+ .byte 0x00 # pop %ebx
+ .byte 0x04 # pop %ecx
+ .byte 0x08 # pop %edx
+ .byte 0x0c # pop %esi
+ .byte 0x10 # pop %edi
+ .byte 0x14 # pop %ebp
+ .byte 0x18 # pop %eax
+ .byte 0x1c # pop %ds
+ .byte 0x20 # pop %es
+ .byte 0x24,0x24,0x24 # add $4,%esp
+ .byte 0x28 # iret
+ .byte 0xff,0xff,0xff,0xff # movb $1,1(%esi)
+ XEN_PUT_VCPU_INFO_fixup
+ .byte 0x00,0x00 # jmp 11b
+
+# Hypervisor uses this for application faults while it executes.
+ENTRY(failsafe_callback)
+1: popl %ds
+2: popl %es
+3: popl %fs
+4: popl %gs
+ subl $4,%esp
+ SAVE_ALL
+ jmp ret_from_exception
+.section .fixup,"ax"; \
+6: movl $0,(%esp); \
+ jmp 1b; \
+7: movl $0,(%esp); \
+ jmp 2b; \
+8: movl $0,(%esp); \
+ jmp 3b; \
+9: movl $0,(%esp); \
+ jmp 4b; \
+.previous; \
+.section __ex_table,"a";\
+ .align 4; \
+ .long 1b,6b; \
+ .long 2b,7b; \
+ .long 3b,8b; \
+ .long 4b,9b; \
+.previous
+
+ENTRY(coprocessor_error)
+ pushl $0
+ pushl $do_coprocessor_error
+ jmp error_code
+
+ENTRY(simd_coprocessor_error)
+ pushl $0
+ pushl $do_simd_coprocessor_error
+ jmp error_code
+
+ENTRY(device_not_available)
+ pushl $-1 # mark this as an int
+ SAVE_ALL
+ preempt_stop
+ call math_state_restore
+ jmp ret_from_exception
+
+/*
+ * Debug traps and NMI can happen at the one SYSENTER instruction
+ * that sets up the real kernel stack. Check here, since we can't
+ * allow the wrong stack to be used.
+ *
+ * "TSS_sysenter_esp0+12" is because the NMI/debug handler will have
+ * already pushed 3 words if it hits on the sysenter instruction:
+ * eflags, cs and eip.
+ *
+ * We just load the right stack, and push the three (known) values
+ * by hand onto the new stack - while updating the return eip past
+ * the instruction that would have done it for sysenter.
+ */
+#define FIX_STACK(offset, ok, label) \
+ cmpw $__KERNEL_CS,4(%esp); \
+ jne ok; \
+label: \
+ movl TSS_sysenter_esp0+offset(%esp),%esp; \
+ pushfl; \
+ pushl $__KERNEL_CS; \
+ pushl $sysenter_past_esp
+
+ENTRY(debug)
+ cmpl $sysenter_entry,(%esp)
+ jne debug_stack_correct
+ FIX_STACK(12, debug_stack_correct, debug_esp_fix_insn)
+debug_stack_correct:
+ pushl $-1 # mark this as an int
+ SAVE_ALL
+ xorl %edx,%edx # error code 0
+ movl %esp,%eax # pt_regs pointer
+ call do_debug
+ testl %eax,%eax
+ jnz restore_all
+ jmp ret_from_exception
+
+#if 0 /* XEN */
+/*
+ * NMI is doubly nasty. It can happen _while_ we're handling
+ * a debug fault, and the debug fault hasn't yet been able to
+ * clear up the stack. So we first check whether we got an
+ * NMI on the sysenter entry path, but after that we need to
+ * check whether we got an NMI on the debug path where the debug
+ * fault happened on the sysenter path.
+ */
+ENTRY(nmi)
+ cmpl $sysenter_entry,(%esp)
+ je nmi_stack_fixup
+ pushl %eax
+ movl %esp,%eax
+ /* Do not access memory above the end of our stack page,
+ * it might not exist.
+ */
+ andl $(THREAD_SIZE-1),%eax
+ cmpl $(THREAD_SIZE-20),%eax
+ popl %eax
+ jae nmi_stack_correct
+ cmpl $sysenter_entry,12(%esp)
+ je nmi_debug_stack_check
+nmi_stack_correct:
+ pushl %eax
+ SAVE_ALL
+ xorl %edx,%edx # zero error code
+ movl %esp,%eax # pt_regs pointer
+ call do_nmi
+ RESTORE_ALL
+
+nmi_stack_fixup:
+ FIX_STACK(12,nmi_stack_correct, 1)
+ jmp nmi_stack_correct
+nmi_debug_stack_check:
+ cmpw $__KERNEL_CS,16(%esp)
+ jne nmi_stack_correct
+ cmpl $debug - 1,(%esp)
+ jle nmi_stack_correct
+ cmpl $debug_esp_fix_insn,(%esp)
+ jle nmi_debug_stack_fixup
+nmi_debug_stack_fixup:
+ FIX_STACK(24,nmi_stack_correct, 1)
+ jmp nmi_stack_correct
+#endif /* XEN */
+
+ENTRY(int3)
+ pushl $-1 # mark this as an int
+ SAVE_ALL
+ xorl %edx,%edx # zero error code
+ movl %esp,%eax # pt_regs pointer
+ call do_int3
+ testl %eax,%eax
+ jnz restore_all
+ jmp ret_from_exception
+
+ENTRY(overflow)
+ pushl $0
+ pushl $do_overflow
+ jmp error_code
+
+ENTRY(bounds)
+ pushl $0
+ pushl $do_bounds
+ jmp error_code
+
+ENTRY(invalid_op)
+ pushl $0
+ pushl $do_invalid_op
+ jmp error_code
+
+ENTRY(coprocessor_segment_overrun)
+ pushl $0
+ pushl $do_coprocessor_segment_overrun
+ jmp error_code
+
+ENTRY(invalid_TSS)
+ pushl $do_invalid_TSS
+ jmp error_code
+
+ENTRY(segment_not_present)
+ pushl $do_segment_not_present
+ jmp error_code
+
+ENTRY(stack_segment)
+ pushl $do_stack_segment
+ jmp error_code
+
+ENTRY(general_protection)
+ pushl $do_general_protection
+ jmp error_code
+
+ENTRY(alignment_check)
+ pushl $do_alignment_check
+ jmp error_code
+
+# This handler is special, because it gets an extra value on its stack,
+# which is the linear faulting address.
+# fastcall register usage: %eax = pt_regs, %edx = error code,
+# %ecx = fault address
+ENTRY(page_fault)
+ pushl %ds
+ pushl %eax
+ xorl %eax, %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ decl %eax /* eax = -1 */
+ pushl %ecx
+ pushl %ebx
+ cld
+ movl %es,%edi
+ movl ES(%esp), %ecx /* get the faulting address */
+ movl ORIG_EAX(%esp), %edx /* get the error code */
+ movl %eax, ORIG_EAX(%esp)
+ movl %edi, ES(%esp)
+ movl $(__KERNEL_DS),%eax
+ movl %eax, %ds
+ movl %eax, %es
+ movl %esp,%eax /* pt_regs pointer */
+ call do_page_fault
+ jmp ret_from_exception
+
+#ifdef CONFIG_X86_MCE
+ENTRY(machine_check)
+ pushl $0
+ pushl machine_check_vector
+ jmp error_code
+#endif
+
+ENTRY(fixup_4gb_segment)
+ pushl $do_fixup_4gb_segment
+ jmp error_code
+
+.data
+ENTRY(sys_call_table)
+ .long sys_restart_syscall /* 0 - old "setup()" system call, used
for restarting */
+ .long sys_exit
+ .long sys_fork
+ .long sys_read
+ .long sys_write
+ .long sys_open /* 5 */
+ .long sys_close
+ .long sys_waitpid
+ .long sys_creat
+ .long sys_link
+ .long sys_unlink /* 10 */
+ .long sys_execve
+ .long sys_chdir
+ .long sys_time
+ .long sys_mknod
+ .long sys_chmod /* 15 */
+ .long sys_lchown16
+ .long sys_ni_syscall /* old break syscall holder */
+ .long sys_stat
+ .long sys_lseek
+ .long sys_getpid /* 20 */
+ .long sys_mount
+ .long sys_oldumount
+ .long sys_setuid16
+ .long sys_getuid16
+ .long sys_stime /* 25 */
+ .long sys_ptrace
+ .long sys_alarm
+ .long sys_fstat
+ .long sys_pause
+ .long sys_utime /* 30 */
+ .long sys_ni_syscall /* old stty syscall holder */
+ .long sys_ni_syscall /* old gtty syscall holder */
+ .long sys_access
+ .long sys_nice
+ .long sys_ni_syscall /* 35 - old ftime syscall holder */
+ .long sys_sync
+ .long sys_kill
+ .long sys_rename
+ .long sys_mkdir
+ .long sys_rmdir /* 40 */
+ .long sys_dup
+ .long sys_pipe
+ .long sys_times
+ .long sys_ni_syscall /* old prof syscall holder */
+ .long sys_brk /* 45 */
+ .long sys_setgid16
+ .long sys_getgid16
+ .long sys_signal
+ .long sys_geteuid16
+ .long sys_getegid16 /* 50 */
+ .long sys_acct
+ .long sys_umount /* recycled never used phys() */
+ .long sys_ni_syscall /* old lock syscall holder */
+ .long sys_ioctl
+ .long sys_fcntl /* 55 */
+ .long sys_ni_syscall /* old mpx syscall holder */
+ .long sys_setpgid
+ .long sys_ni_syscall /* old ulimit syscall holder */
+ .long sys_olduname
+ .long sys_umask /* 60 */
+ .long sys_chroot
+ .long sys_ustat
+ .long sys_dup2
+ .long sys_getppid
+ .long sys_getpgrp /* 65 */
+ .long sys_setsid
+ .long sys_sigaction
+ .long sys_sgetmask
+ .long sys_ssetmask
+ .long sys_setreuid16 /* 70 */
+ .long sys_setregid16
+ .long sys_sigsuspend
+ .long sys_sigpending
+ .long sys_sethostname
+ .long sys_setrlimit /* 75 */
+ .long sys_old_getrlimit
+ .long sys_getrusage
+ .long sys_gettimeofday
+ .long sys_settimeofday
+ .long sys_getgroups16 /* 80 */
+ .long sys_setgroups16
+ .long old_select
+ .long sys_symlink
+ .long sys_lstat
+ .long sys_readlink /* 85 */
+ .long sys_uselib
+ .long sys_swapon
+ .long sys_reboot
+ .long old_readdir
+ .long old_mmap /* 90 */
+ .long sys_munmap
+ .long sys_truncate
+ .long sys_ftruncate
+ .long sys_fchmod
+ .long sys_fchown16 /* 95 */
+ .long sys_getpriority
+ .long sys_setpriority
+ .long sys_ni_syscall /* old profil syscall holder */
+ .long sys_statfs
+ .long sys_fstatfs /* 100 */
+ .long sys_ioperm
+ .long sys_socketcall
+ .long sys_syslog
+ .long sys_setitimer
+ .long sys_getitimer /* 105 */
+ .long sys_newstat
+ .long sys_newlstat
+ .long sys_newfstat
+ .long sys_uname
+ .long sys_iopl /* 110 */
+ .long sys_vhangup
+ .long sys_ni_syscall /* old "idle" system call */
+ .long sys_vm86old
+ .long sys_wait4
+ .long sys_swapoff /* 115 */
+ .long sys_sysinfo
+ .long sys_ipc
+ .long sys_fsync
+ .long sys_sigreturn
+ .long sys_clone /* 120 */
+ .long sys_setdomainname
+ .long sys_newuname
+ .long sys_modify_ldt
+ .long sys_adjtimex
+ .long sys_mprotect /* 125 */
+ .long sys_sigprocmask
+ .long sys_ni_syscall /* old "create_module" */
+ .long sys_init_module
+ .long sys_delete_module
+ .long sys_ni_syscall /* 130: old "get_kernel_syms" */
+ .long sys_quotactl
+ .long sys_getpgid
+ .long sys_fchdir
+ .long sys_bdflush
+ .long sys_sysfs /* 135 */
+ .long sys_personality
+ .long sys_ni_syscall /* reserved for afs_syscall */
+ .long sys_setfsuid16
+ .long sys_setfsgid16
+ .long sys_llseek /* 140 */
+ .long sys_getdents
+ .long sys_select
+ .long sys_flock
+ .long sys_msync
+ .long sys_readv /* 145 */
+ .long sys_writev
+ .long sys_getsid
+ .long sys_fdatasync
+ .long sys_sysctl
+ .long sys_mlock /* 150 */
+ .long sys_munlock
+ .long sys_mlockall
+ .long sys_munlockall
+ .long sys_sched_setparam
+ .long sys_sched_getparam /* 155 */
+ .long sys_sched_setscheduler
+ .long sys_sched_getscheduler
+ .long sys_sched_yield
+ .long sys_sched_get_priority_max
+ .long sys_sched_get_priority_min /* 160 */
+ .long sys_sched_rr_get_interval
+ .long sys_nanosleep
+ .long sys_mremap
+ .long sys_setresuid16
+ .long sys_getresuid16 /* 165 */
+ .long sys_vm86
+ .long sys_ni_syscall /* Old sys_query_module */
+ .long sys_poll
+ .long sys_nfsservctl
+ .long sys_setresgid16 /* 170 */
+ .long sys_getresgid16
+ .long sys_prctl
+ .long sys_rt_sigreturn
+ .long sys_rt_sigaction
+ .long sys_rt_sigprocmask /* 175 */
+ .long sys_rt_sigpending
+ .long sys_rt_sigtimedwait
+ .long sys_rt_sigqueueinfo
+ .long sys_rt_sigsuspend
+ .long sys_pread64 /* 180 */
+ .long sys_pwrite64
+ .long sys_chown16
+ .long sys_getcwd
+ .long sys_capget
+ .long sys_capset /* 185 */
+ .long sys_sigaltstack
+ .long sys_sendfile
+ .long sys_ni_syscall /* reserved for streams1 */
+ .long sys_ni_syscall /* reserved for streams2 */
+ .long sys_vfork /* 190 */
+ .long sys_getrlimit
+ .long sys_mmap2
+ .long sys_truncate64
+ .long sys_ftruncate64
+ .long sys_stat64 /* 195 */
+ .long sys_lstat64
+ .long sys_fstat64
+ .long sys_lchown
+ .long sys_getuid
+ .long sys_getgid /* 200 */
+ .long sys_geteuid
+ .long sys_getegid
+ .long sys_setreuid
+ .long sys_setregid
+ .long sys_getgroups /* 205 */
+ .long sys_setgroups
+ .long sys_fchown
+ .long sys_setresuid
+ .long sys_getresuid
+ .long sys_setresgid /* 210 */
+ .long sys_getresgid
+ .long sys_chown
+ .long sys_setuid
+ .long sys_setgid
+ .long sys_setfsuid /* 215 */
+ .long sys_setfsgid
+ .long sys_pivot_root
+ .long sys_mincore
+ .long sys_madvise
+ .long sys_getdents64 /* 220 */
+ .long sys_fcntl64
+ .long sys_ni_syscall /* reserved for TUX */
+ .long sys_ni_syscall
+ .long sys_gettid
+ .long sys_readahead /* 225 */
+ .long sys_setxattr
+ .long sys_lsetxattr
+ .long sys_fsetxattr
+ .long sys_getxattr
+ .long sys_lgetxattr /* 230 */
+ .long sys_fgetxattr
+ .long sys_listxattr
+ .long sys_llistxattr
+ .long sys_flistxattr
+ .long sys_removexattr /* 235 */
+ .long sys_lremovexattr
+ .long sys_fremovexattr
+ .long sys_tkill
+ .long sys_sendfile64
+ .long sys_futex /* 240 */
+ .long sys_sched_setaffinity
+ .long sys_sched_getaffinity
+ .long sys_set_thread_area
+ .long sys_get_thread_area
+ .long sys_io_setup /* 245 */
+ .long sys_io_destroy
+ .long sys_io_getevents
+ .long sys_io_submit
+ .long sys_io_cancel
+ .long sys_fadvise64 /* 250 */
+ .long sys_ni_syscall
+ .long sys_exit_group
+ .long sys_lookup_dcookie
+ .long sys_epoll_create
+ .long sys_epoll_ctl /* 255 */
+ .long sys_epoll_wait
+ .long sys_remap_file_pages
+ .long sys_set_tid_address
+ .long sys_timer_create
+ .long sys_timer_settime /* 260 */
+ .long sys_timer_gettime
+ .long sys_timer_getoverrun
+ .long sys_timer_delete
+ .long sys_clock_settime
+ .long sys_clock_gettime /* 265 */
+ .long sys_clock_getres
+ .long sys_clock_nanosleep
+ .long sys_statfs64
+ .long sys_fstatfs64
+ .long sys_tgkill /* 270 */
+ .long sys_utimes
+ .long sys_fadvise64_64
+ .long sys_ni_syscall /* sys_vserver */
+ .long sys_mbind
+ .long sys_get_mempolicy
+ .long sys_set_mempolicy
+ .long sys_mq_open
+ .long sys_mq_unlink
+ .long sys_mq_timedsend
+ .long sys_mq_timedreceive /* 280 */
+ .long sys_mq_notify
+ .long sys_mq_getsetattr
+ .long sys_ni_syscall /* reserved for kexec */
+ .long sys_waitid
+ .long sys_ni_syscall /* 285 */ /* available */
+ .long sys_add_key
+ .long sys_request_key
+ .long sys_keyctl
+
+syscall_table_size=(.-sys_call_table)
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/kernel/i386_ksyms.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/kernel/i386_ksyms.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,180 @@
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/user.h>
+#include <linux/elfcore.h>
+#include <linux/mca.h>
+#include <linux/sched.h>
+#include <linux/in6.h>
+#include <linux/interrupt.h>
+#include <linux/smp_lock.h>
+#include <linux/pm.h>
+#include <linux/pci.h>
+#include <linux/apm_bios.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/tty.h>
+
+#include <asm/semaphore.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/uaccess.h>
+#include <asm/checksum.h>
+#include <asm/io.h>
+#include <asm/hardirq.h>
+#include <asm/delay.h>
+#include <asm/irq.h>
+#include <asm/mmx.h>
+#include <asm/desc.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+
+extern void dump_thread(struct pt_regs *, struct user *);
+extern spinlock_t rtc_lock;
+
+#if defined(CONFIG_APMXXX) || defined(CONFIG_APM_MODULEXXX)
+extern void machine_real_restart(unsigned char *, int);
+EXPORT_SYMBOL(machine_real_restart);
+extern void default_idle(void);
+EXPORT_SYMBOL(default_idle);
+#endif
+
+#ifdef CONFIG_SMP
+extern void FASTCALL( __write_lock_failed(rwlock_t *rw));
+extern void FASTCALL( __read_lock_failed(rwlock_t *rw));
+#endif
+
+#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) ||
defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE)
+extern struct drive_info_struct drive_info;
+EXPORT_SYMBOL(drive_info);
+#endif
+
+// XXX extern unsigned long get_cmos_time(void);
+
+/* platform dependent support */
+EXPORT_SYMBOL(boot_cpu_data);
+EXPORT_SYMBOL(dump_thread);
+EXPORT_SYMBOL(dump_fpu);
+EXPORT_SYMBOL(dump_extended_fpu);
+EXPORT_SYMBOL(__ioremap);
+EXPORT_SYMBOL(iounmap);
+EXPORT_SYMBOL(enable_irq);
+EXPORT_SYMBOL(disable_irq);
+EXPORT_SYMBOL(disable_irq_nosync);
+EXPORT_SYMBOL(probe_irq_mask);
+EXPORT_SYMBOL(kernel_thread);
+EXPORT_SYMBOL(pm_idle);
+EXPORT_SYMBOL(pm_power_off);
+EXPORT_SYMBOL(apm_info);
+//EXPORT_SYMBOL(gdt);
+EXPORT_SYMBOL(empty_zero_page);
+EXPORT_SYMBOL(phys_to_machine_mapping);
+
+
+#ifdef CONFIG_DEBUG_IOVIRT
+EXPORT_SYMBOL(__io_virt_debug);
+#endif
+
+EXPORT_SYMBOL_NOVERS(__down_failed);
+EXPORT_SYMBOL_NOVERS(__down_failed_interruptible);
+EXPORT_SYMBOL_NOVERS(__down_failed_trylock);
+EXPORT_SYMBOL_NOVERS(__up_wakeup);
+/* Networking helper routines. */
+EXPORT_SYMBOL(csum_partial_copy_generic);
+/* Delay loops */
+EXPORT_SYMBOL(__ndelay);
+EXPORT_SYMBOL(__udelay);
+EXPORT_SYMBOL(__delay);
+EXPORT_SYMBOL(__const_udelay);
+
+EXPORT_SYMBOL_NOVERS(__get_user_1);
+EXPORT_SYMBOL_NOVERS(__get_user_2);
+EXPORT_SYMBOL_NOVERS(__get_user_4);
+
+EXPORT_SYMBOL(strtok);
+EXPORT_SYMBOL(strpbrk);
+EXPORT_SYMBOL(strstr);
+
+EXPORT_SYMBOL(strncpy_from_user);
+EXPORT_SYMBOL(__strncpy_from_user);
+EXPORT_SYMBOL(clear_user);
+EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(__generic_copy_from_user);
+EXPORT_SYMBOL(__generic_copy_to_user);
+EXPORT_SYMBOL(strnlen_user);
+
+
+EXPORT_SYMBOL(pci_alloc_consistent);
+EXPORT_SYMBOL(pci_free_consistent);
+
+#ifdef CONFIG_PCI
+EXPORT_SYMBOL(pcibios_penalize_isa_irq);
+EXPORT_SYMBOL(pci_mem_start);
+#endif
+
+
+#ifdef CONFIG_X86_USE_3DNOW
+EXPORT_SYMBOL(_mmx_memcpy);
+EXPORT_SYMBOL(mmx_clear_page);
+EXPORT_SYMBOL(mmx_copy_page);
+#endif
+
+#ifdef CONFIG_SMP
+EXPORT_SYMBOL(cpu_data);
+EXPORT_SYMBOL(kernel_flag_cacheline);
+EXPORT_SYMBOL(smp_num_cpus);
+EXPORT_SYMBOL(cpu_online_map);
+EXPORT_SYMBOL_NOVERS(__write_lock_failed);
+EXPORT_SYMBOL_NOVERS(__read_lock_failed);
+
+/* Global SMP irq stuff */
+EXPORT_SYMBOL(synchronize_irq);
+EXPORT_SYMBOL(global_irq_holder);
+EXPORT_SYMBOL(__global_cli);
+EXPORT_SYMBOL(__global_sti);
+EXPORT_SYMBOL(__global_save_flags);
+EXPORT_SYMBOL(__global_restore_flags);
+EXPORT_SYMBOL(smp_call_function);
+
+/* TLB flushing */
+EXPORT_SYMBOL(flush_tlb_page);
+
+/* HT support */
+EXPORT_SYMBOL(smp_num_siblings);
+EXPORT_SYMBOL(cpu_sibling_map);
+#endif
+
+#ifdef CONFIG_X86_IO_APIC
+EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
+#endif
+
+#ifdef CONFIG_VT
+EXPORT_SYMBOL(screen_info);
+#endif
+
+EXPORT_SYMBOL(get_wchan);
+
+EXPORT_SYMBOL(rtc_lock);
+
+#undef memcpy
+#undef memset
+extern void * memset(void *,int,__kernel_size_t);
+extern void * memcpy(void *,const void *,__kernel_size_t);
+EXPORT_SYMBOL_NOVERS(memcpy);
+EXPORT_SYMBOL_NOVERS(memset);
+
+#ifdef CONFIG_HAVE_DEC_LOCK
+EXPORT_SYMBOL(atomic_dec_and_lock);
+#endif
+
+#ifdef CONFIG_MULTIQUAD
+EXPORT_SYMBOL(xquad_portio);
+#endif
+
+#include <asm/xen_proc.h>
+EXPORT_SYMBOL(create_xen_proc_entry);
+EXPORT_SYMBOL(remove_xen_proc_entry);
+
+EXPORT_SYMBOL(evtchn_do_upcall);
+EXPORT_SYMBOL(force_evtchn_callback);
+EXPORT_SYMBOL(HYPERVISOR_shared_info);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/system.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/system.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,403 @@
+#ifndef __ASM_SYSTEM_H
+#define __ASM_SYSTEM_H
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <asm/segment.h>
+#include <asm-xen/synch_bitops.h>
+#include <asm-xen/hypervisor.h>
+#include <asm-xen/xen-public/arch-x86_64.h>
+
+#ifdef __KERNEL__
+
+#ifdef CONFIG_SMP
+#define LOCK_PREFIX "lock ; "
+#else
+#define LOCK_PREFIX ""
+#endif
+
+#define __STR(x) #x
+#define STR(x) __STR(x)
+
+#define __SAVE(reg,offset) "movq %%" #reg ",(14-" #offset ")*8(%%rsp)\n\t"
+#define __RESTORE(reg,offset) "movq (14-" #offset ")*8(%%rsp),%%" #reg "\n\t"
+
+/* frame pointer must be last for get_wchan */
+#define SAVE_CONTEXT "pushfq ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popfq\n\t"
+
+#define __EXTRA_CLOBBER \
+ ,"rcx","rbx","rdx","r8","r9","r10","r11","r12","r13","r14","r15"
+
+#define switch_to(prev,next,last) \
+ asm volatile(SAVE_CONTEXT
\
+ "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */
\
+ "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */
\
+ "call __switch_to\n\t"
\
+ ".globl thread_return\n"
\
+ "thread_return:\n\t"
\
+ "movq %%gs:%P[pda_pcurrent],%%rsi\n\t"
\
+ "movq %P[thread_info](%%rsi),%%r8\n\t"
\
+ LOCK "btr %[tif_fork],%P[ti_flags](%%r8)\n\t"
\
+ "movq %%rax,%%rdi\n\t"
\
+ "jc ret_from_fork\n\t"
\
+ RESTORE_CONTEXT
\
+ : "=a" (last)
\
+ : [next] "S" (next), [prev] "D" (prev),
\
+ [threadrsp] "i" (offsetof(struct task_struct,
thread.rsp)), \
+ [ti_flags] "i" (offsetof(struct thread_info, flags)),\
+ [tif_fork] "i" (TIF_FORK), \
+ [thread_info] "i" (offsetof(struct task_struct,
thread_info)), \
+ [pda_pcurrent] "i" (offsetof(struct x8664_pda,
pcurrent)) \
+ : "memory", "cc" __EXTRA_CLOBBER)
+
+
+extern void load_gs_index(unsigned);
+
+/*
+ * Load a segment. Fall back on loading the zero
+ * segment if something goes wrong..
+ */
+#define loadsegment(seg,value) \
+ asm volatile("\n" \
+ "1:\t" \
+ "movl %k0,%%" #seg "\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3:\t" \
+ "movl %1,%%" #seg "\n\t" \
+ "jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n\t" \
+ ".align 8\n\t" \
+ ".quad 1b,3b\n" \
+ ".previous" \
+ : :"r" (value), "r" (0))
+
+#define set_debug(value,register) \
+ __asm__("movq %0,%%db" #register \
+ : /* no output */ \
+ :"r" ((unsigned long) value))
+
+
+#ifdef __KERNEL__
+struct alt_instr {
+ __u8 *instr; /* original instruction */
+ __u8 *replacement;
+ __u8 cpuid; /* cpuid bit set for replacement */
+ __u8 instrlen; /* length of original instruction */
+ __u8 replacementlen; /* length of new instruction, <= instrlen */
+ __u8 pad[5];
+};
+#endif
+
+/*
+ * Alternative instructions for different CPU types or capabilities.
+ *
+ * This allows to use optimized instructions even on generic binary
+ * kernels.
+ *
+ * length of oldinstr must be longer or equal the length of newinstr
+ * It can be padded with nops as needed.
+ *
+ * For non barrier like inlines please define new variants
+ * without volatile and memory clobber.
+ */
+#define alternative(oldinstr, newinstr, feature) \
+ asm volatile ("661:\n\t" oldinstr "\n662:\n" \
+ ".section .altinstructions,\"a\"\n" \
+ " .align 8\n" \
+ " .quad 661b\n" /* label */ \
+ " .quad 663f\n" /* new instruction */ \
+ " .byte %c0\n" /* feature bit */ \
+ " .byte 662b-661b\n" /* sourcelen */ \
+ " .byte 664f-663f\n" /* replacementlen */ \
+ ".previous\n" \
+ ".section .altinstr_replacement,\"ax\"\n" \
+ "663:\n\t" newinstr "\n664:\n" /* replacement */ \
+ ".previous" :: "i" (feature) : "memory")
+
+/*
+ * Alternative inline assembly with input.
+ *
+ * Pecularities:
+ * No memory clobber here.
+ * Argument numbers start with 1.
+ * Best is to use constraints that are fixed size (like (%1) ... "r")
+ * If you use variable sized constraints like "m" or "g" in the
+ * replacement maake sure to pad to the worst case length.
+ */
+#define alternative_input(oldinstr, newinstr, feature, input...) \
+ asm volatile ("661:\n\t" oldinstr "\n662:\n" \
+ ".section .altinstructions,\"a\"\n" \
+ " .align 8\n" \
+ " .quad 661b\n" /* label */ \
+ " .quad 663f\n" /* new instruction */ \
+ " .byte %c0\n" /* feature bit */ \
+ " .byte 662b-661b\n" /* sourcelen */ \
+ " .byte 664f-663f\n" /* replacementlen */ \
+ ".previous\n" \
+ ".section .altinstr_replacement,\"ax\"\n" \
+ "663:\n\t" newinstr "\n664:\n" /* replacement */ \
+ ".previous" :: "i" (feature), ##input)
+
+/*
+ * Clear and set 'TS' bit respectively
+ */
+#define clts() (HYPERVISOR_fpu_taskswitch(0))
+
+static inline unsigned long read_cr0(void)
+{
+ unsigned long cr0;
+ asm volatile("movq %%cr0,%0" : "=r" (cr0));
+ return cr0;
+}
+
+static inline void write_cr0(unsigned long val)
+{
+ asm volatile("movq %0,%%cr0" :: "r" (val));
+}
+
+static inline unsigned long read_cr3(void)
+{
+ unsigned long cr3;
+ asm("movq %%cr3,%0" : "=r" (cr3));
+ return cr3;
+}
+
+static inline unsigned long read_cr4(void)
+{
+ unsigned long cr4;
+ asm("movq %%cr4,%0" : "=r" (cr4));
+ return cr4;
+}
+
+static inline void write_cr4(unsigned long val)
+{
+ asm volatile("movq %0,%%cr4" :: "r" (val));
+}
+
+#define stts() (HYPERVISOR_fpu_taskswitch(1))
+
+#define wbinvd() \
+ __asm__ __volatile__ ("wbinvd": : :"memory");
+
+#endif /* __KERNEL__ */
+
+#define nop() __asm__ __volatile__ ("nop")
+
+#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned
long)(v),(ptr),sizeof(*(ptr))))
+
+#define tas(ptr) (xchg((ptr),1))
+
+#define __xg(x) ((volatile long *)(x))
+
+extern inline void set_64bit(volatile unsigned long *ptr, unsigned long val)
+{
+ *ptr = val;
+}
+
+#define _set_64bit set_64bit
+
+/*
+ * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
+ * Note 2: xchg has side effect, so that attribute volatile is necessary,
+ * but generally the primitive is invalid, *ptr is output argument. --ANK
+ */
+static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int
size)
+{
+ switch (size) {
+ case 1:
+ __asm__ __volatile__("xchgb %b0,%1"
+ :"=q" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ case 2:
+ __asm__ __volatile__("xchgw %w0,%1"
+ :"=r" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ case 4:
+ __asm__ __volatile__("xchgl %k0,%1"
+ :"=r" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ case 8:
+ __asm__ __volatile__("xchgq %0,%1"
+ :"=r" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ }
+ return x;
+}
+
+/*
+ * Atomic compare and exchange. Compare OLD with MEM, if identical,
+ * store NEW in MEM. Return the initial value in MEM. Success is
+ * indicated by comparing RETURN with OLD.
+ */
+
+#define __HAVE_ARCH_CMPXCHG 1
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+ unsigned long new, int size)
+{
+ unsigned long prev;
+ switch (size) {
+ case 1:
+ __asm__ __volatile__(LOCK_PREFIX "cmpxchgb %b1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ case 2:
+ __asm__ __volatile__(LOCK_PREFIX "cmpxchgw %w1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ case 4:
+ __asm__ __volatile__(LOCK_PREFIX "cmpxchgl %k1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ case 8:
+ __asm__ __volatile__(LOCK_PREFIX "cmpxchgq %1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ }
+ return old;
+}
+
+#define cmpxchg(ptr,o,n)\
+ ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
+ (unsigned long)(n),sizeof(*(ptr))))
+
+#ifdef CONFIG_SMP
+#define smp_mb() mb()
+#define smp_rmb() rmb()
+#define smp_wmb() wmb()
+#define smp_read_barrier_depends() do {} while(0)
+#else
+#define smp_mb() barrier()
+#define smp_rmb() barrier()
+#define smp_wmb() barrier()
+#define smp_read_barrier_depends() do {} while(0)
+#endif
+
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+#define mb() asm volatile("mfence":::"memory")
+#define rmb() asm volatile("lfence":::"memory")
+
+#ifdef CONFIG_UNORDERED_IO
+#define wmb() asm volatile("sfence" ::: "memory")
+#else
+#define wmb() asm volatile("" ::: "memory")
+#endif
+#define read_barrier_depends() do {} while(0)
+#define set_mb(var, value) do { xchg(&var, value); } while (0)
+#define set_wmb(var, value) do { var = value; wmb(); } while (0)
+
+#define warn_if_not_ulong(x) do { unsigned long foo; (void) (&(x) == &foo); }
while (0)
+
+
+/*
+ * The use of 'barrier' in the following reflects their use as local-lock
+ * operations. Reentrancy must be prevented (e.g., __cli()) /before/ following
+ * critical operations are executed. All critical operations must complete
+ * /before/ reentrancy is permitted (e.g., __sti()). Alpha architecture also
+ * includes these barriers, for example.
+ */
+
+#define __cli()
\
+do { \
+ vcpu_info_t *_vcpu; \
+ preempt_disable(); \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_data[smp_processor_id()]; \
+ _vcpu->evtchn_upcall_mask = 1; \
+ preempt_enable_no_resched(); \
+ barrier(); \
+} while (0)
+
+#define __sti()
\
+do { \
+ vcpu_info_t *_vcpu; \
+ barrier(); \
+ preempt_disable(); \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_data[smp_processor_id()]; \
+ _vcpu->evtchn_upcall_mask = 0; \
+ barrier(); /* unmask then check (avoid races) */ \
+ if ( unlikely(_vcpu->evtchn_upcall_pending) ) \
+ force_evtchn_callback(); \
+ preempt_enable(); \
+} while (0)
+
+#define __save_flags(x)
\
+do { \
+ vcpu_info_t *_vcpu; \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_data[smp_processor_id()]; \
+ (x) = _vcpu->evtchn_upcall_mask; \
+} while (0)
+
+#define __restore_flags(x) \
+do { \
+ vcpu_info_t *_vcpu; \
+ barrier(); \
+ preempt_disable(); \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_data[smp_processor_id()]; \
+ if ((_vcpu->evtchn_upcall_mask = (x)) == 0) { \
+ barrier(); /* unmask then check (avoid races) */ \
+ if ( unlikely(_vcpu->evtchn_upcall_pending) ) \
+ force_evtchn_callback(); \
+ preempt_enable(); \
+ } else \
+ preempt_enable_no_resched(); \
+} while (0)
+
+#define safe_halt() ((void)0)
+
+#define __save_and_cli(x) \
+do { \
+ vcpu_info_t *_vcpu; \
+ preempt_disable(); \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_data[smp_processor_id()]; \
+ (x) = _vcpu->evtchn_upcall_mask; \
+ _vcpu->evtchn_upcall_mask = 1; \
+ preempt_enable_no_resched(); \
+ barrier(); \
+} while (0)
+
+void cpu_idle_wait(void);
+
+#define local_irq_save(x) __save_and_cli(x)
+#define local_irq_restore(x) __restore_flags(x)
+#define local_save_flags(x) __save_flags(x)
+#define local_irq_disable() __cli()
+#define local_irq_enable() __sti()
+
+#define irqs_disabled() \
+ HYPERVISOR_shared_info->vcpu_data[smp_processor_id()].evtchn_upcall_mask
+
+/*
+ * disable hlt during certain critical i/o operations
+ */
+#define HAVE_DISABLE_HLT
+void disable_hlt(void);
+void enable_hlt(void);
+
+#define HAVE_EAT_KEY
+void eat_key(void);
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/linux/timer.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/linux/timer.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,77 @@
+#ifndef _LINUX_TIMER_H
+#define _LINUX_TIMER_H
+
+#include <linux/config.h>
+#include <linux/list.h>
+
+/*
+ * In Linux 2.4, static timers have been removed from the kernel.
+ * Timers may be dynamically created and destroyed, and should be initialized
+ * by a call to init_timer() upon creation.
+ *
+ * The "data" field enables use of a common timeout function for several
+ * timeouts. You can use this field to distinguish between the different
+ * invocations.
+ */
+struct timer_list {
+ struct list_head list;
+ unsigned long expires;
+ unsigned long data;
+ void (*function)(unsigned long);
+};
+
+extern void add_timer(struct timer_list * timer);
+extern int del_timer(struct timer_list * timer);
+#ifdef CONFIG_NO_IDLE_HZ
+extern struct timer_list *next_timer_event(void);
+#endif
+
+#ifdef CONFIG_SMP
+extern int del_timer_sync(struct timer_list * timer);
+extern void sync_timers(void);
+#else
+#define del_timer_sync(t) del_timer(t)
+#define sync_timers() do { } while (0)
+#endif
+
+/*
+ * mod_timer is a more efficient way to update the expire field of an
+ * active timer (if the timer is inactive it will be activated)
+ * mod_timer(a,b) is equivalent to del_timer(a); a->expires = b; add_timer(a).
+ * If the timer is known to be not pending (ie, in the handler), mod_timer
+ * is less efficient than a->expires = b; add_timer(a).
+ */
+int mod_timer(struct timer_list *timer, unsigned long expires);
+
+extern void it_real_fn(unsigned long);
+
+static inline void init_timer(struct timer_list * timer)
+{
+ timer->list.next = timer->list.prev = NULL;
+}
+
+static inline int timer_pending (const struct timer_list * timer)
+{
+ return timer->list.next != NULL;
+}
+
+/*
+ * These inlines deal with timer wrapping correctly. You are
+ * strongly encouraged to use them
+ * 1. Because people otherwise forget
+ * 2. Because if the timer wrap changes in future you wont have to
+ * alter your driver code.
+ *
+ * time_after(a,b) returns true if the time a is after time b.
+ *
+ * Do this with "<0" and ">=0" to only test the sign of the result. A
+ * good compiler would generate better code (and a really good compiler
+ * wouldn't care). Gcc is currently neither.
+ */
+#define time_after(a,b) ((long)(b) - (long)(a) < 0)
+#define time_before(a,b) time_after(b,a)
+
+#define time_after_eq(a,b) ((long)(a) - (long)(b) >= 0)
+#define time_before_eq(a,b) time_after_eq(b,a)
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/signal.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/signal.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,493 @@
+/*
+ * linux/arch/x86_64/kernel/signal.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs
+ *
+ * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson
+ * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes
+ * 2000-2002 x86-64 support by Andi Kleen
+ *
+ * $Id: signal.c,v 1.18 2001/10/17 22:30:37 ak Exp $
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/errno.h>
+#include <linux/wait.h>
+#include <linux/ptrace.h>
+#include <linux/unistd.h>
+#include <linux/stddef.h>
+#include <linux/personality.h>
+#include <linux/compiler.h>
+#include <asm/ucontext.h>
+#include <asm/uaccess.h>
+#include <asm/i387.h>
+#include <asm/proto.h>
+
+/* #define DEBUG_SIG 1 */
+
+#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
+
+void ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+ sigset_t *set, struct pt_regs * regs);
+void ia32_setup_frame(int sig, struct k_sigaction *ka,
+ sigset_t *set, struct pt_regs * regs);
+
+asmlinkage long
+sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize, struct pt_regs
*regs)
+{
+ sigset_t saveset, newset;
+
+ /* XXX: Don't preclude handling different sized sigset_t's. */
+ if (sigsetsize != sizeof(sigset_t))
+ return -EINVAL;
+
+ if (copy_from_user(&newset, unewset, sizeof(newset)))
+ return -EFAULT;
+ sigdelsetmask(&newset, ~_BLOCKABLE);
+
+ spin_lock_irq(¤t->sighand->siglock);
+ saveset = current->blocked;
+ current->blocked = newset;
+ recalc_sigpending();
+ spin_unlock_irq(¤t->sighand->siglock);
+#ifdef DEBUG_SIG
+ printk("rt_sigsuspend savset(%lx) newset(%lx) regs(%p) rip(%lx)\n",
+ saveset, newset, regs, regs->rip);
+#endif
+ regs->rax = -EINTR;
+ while (1) {
+ current->state = TASK_INTERRUPTIBLE;
+ schedule();
+ if (do_signal(regs, &saveset))
+ return -EINTR;
+ }
+}
+
+asmlinkage long
+sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
+ struct pt_regs *regs)
+{
+ return do_sigaltstack(uss, uoss, regs->rsp);
+}
+
+
+/*
+ * Do a signal return; undo the signal stack.
+ */
+
+struct rt_sigframe
+{
+ char *pretcode;
+ struct ucontext uc;
+ struct siginfo info;
+};
+
+static int
+restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
unsigned long *prax)
+{
+ unsigned int err = 0;
+
+ /* Always make any pending restarted system calls return -EINTR */
+ current_thread_info()->restart_block.fn = do_no_restart_syscall;
+
+#define COPY(x) err |= __get_user(regs->x, &sc->x)
+
+ COPY(rdi); COPY(rsi); COPY(rbp); COPY(rsp); COPY(rbx);
+ COPY(rdx); COPY(rcx); COPY(rip);
+ COPY(r8);
+ COPY(r9);
+ COPY(r10);
+ COPY(r11);
+ COPY(r12);
+ COPY(r13);
+ COPY(r14);
+ COPY(r15);
+
+ {
+ unsigned int tmpflags;
+ err |= __get_user(tmpflags, &sc->eflags);
+ regs->eflags = (regs->eflags & ~0x40DD5) | (tmpflags & 0x40DD5);
+ regs->orig_rax = -1; /* disable syscall checks */
+ }
+
+ {
+ struct _fpstate __user * buf;
+ err |= __get_user(buf, &sc->fpstate);
+
+ if (buf) {
+ if (verify_area(VERIFY_READ, buf, sizeof(*buf)))
+ goto badframe;
+ err |= restore_i387(buf);
+ } else {
+ struct task_struct *me = current;
+ if (used_math()) {
+ clear_fpu(me);
+ clear_used_math();
+ }
+ }
+ }
+
+ err |= __get_user(*prax, &sc->rax);
+ return err;
+
+badframe:
+ return 1;
+}
+
+asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
+{
+ struct rt_sigframe __user *frame;
+ sigset_t set;
+ unsigned long eax;
+
+ frame = (struct rt_sigframe __user *)(regs->rsp - 8);
+ if (verify_area(VERIFY_READ, frame, sizeof(*frame))) {
+ goto badframe;
+ }
+ if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) {
+ goto badframe;
+ }
+
+ sigdelsetmask(&set, ~_BLOCKABLE);
+ spin_lock_irq(¤t->sighand->siglock);
+ current->blocked = set;
+ recalc_sigpending();
+ spin_unlock_irq(¤t->sighand->siglock);
+
+ if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &eax)) {
+ goto badframe;
+ }
+
+#ifdef DEBUG_SIG
+ printk("%d sigreturn rip:%lx rsp:%lx frame:%p
rax:%lx\n",current->pid,regs.rip,regs.rsp,frame,eax);
+#endif
+
+ if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->rsp) == -EFAULT)
+ goto badframe;
+
+ return eax;
+
+badframe:
+ signal_fault(regs,frame,"sigreturn");
+ return 0;
+}
+
+/*
+ * Set up a signal frame.
+ */
+
+static inline int
+setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, unsigned
long mask, struct task_struct *me)
+{
+ int err = 0;
+ unsigned long eflags;
+
+ err |= __put_user(0, &sc->gs);
+ err |= __put_user(0, &sc->fs);
+
+ err |= __put_user(regs->rdi, &sc->rdi);
+ err |= __put_user(regs->rsi, &sc->rsi);
+ err |= __put_user(regs->rbp, &sc->rbp);
+ err |= __put_user(regs->rsp, &sc->rsp);
+ err |= __put_user(regs->rbx, &sc->rbx);
+ err |= __put_user(regs->rdx, &sc->rdx);
+ err |= __put_user(regs->rcx, &sc->rcx);
+ err |= __put_user(regs->rax, &sc->rax);
+ err |= __put_user(regs->r8, &sc->r8);
+ err |= __put_user(regs->r9, &sc->r9);
+ err |= __put_user(regs->r10, &sc->r10);
+ err |= __put_user(regs->r11, &sc->r11);
+ err |= __put_user(regs->r12, &sc->r12);
+ err |= __put_user(regs->r13, &sc->r13);
+ err |= __put_user(regs->r14, &sc->r14);
+ err |= __put_user(regs->r15, &sc->r15);
+ err |= __put_user(me->thread.trap_no, &sc->trapno);
+ err |= __put_user(me->thread.error_code, &sc->err);
+ err |= __put_user(regs->rip, &sc->rip);
+ eflags = regs->eflags;
+ if (current->ptrace & PT_PTRACED) {
+ eflags &= ~TF_MASK;
+ }
+ err |= __put_user(eflags, &sc->eflags);
+ err |= __put_user(mask, &sc->oldmask);
+ err |= __put_user(me->thread.cr2, &sc->cr2);
+
+ return err;
+}
+
+/*
+ * Determine which stack to use..
+ */
+
+static void __user *
+get_stack(struct k_sigaction *ka, struct pt_regs *regs, unsigned long size)
+{
+ unsigned long rsp;
+
+ /* Default to using normal stack - redzone*/
+ rsp = regs->rsp - 128;
+
+ /* This is the X/Open sanctioned signal stack switching. */
+ /* RED-PEN: redzone on that stack? */
+ if (ka->sa.sa_flags & SA_ONSTACK) {
+ if (sas_ss_flags(rsp) == 0)
+ rsp = current->sas_ss_sp + current->sas_ss_size;
+ }
+
+ return (void __user *)round_down(rsp - size, 16);
+}
+
+static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+ sigset_t *set, struct pt_regs * regs)
+{
+ struct rt_sigframe __user *frame;
+ struct _fpstate __user *fp = NULL;
+ int err = 0;
+ struct task_struct *me = current;
+
+ if (used_math()) {
+ fp = get_stack(ka, regs, sizeof(struct _fpstate));
+ frame = (void __user *)round_down((unsigned long)fp -
sizeof(struct rt_sigframe), 16) - 8;
+
+ if (!access_ok(VERIFY_WRITE, fp, sizeof(struct _fpstate))) {
+ goto give_sigsegv;
+ }
+
+ if (save_i387(fp) < 0)
+ err |= -1;
+ } else {
+ frame = get_stack(ka, regs, sizeof(struct rt_sigframe)) - 8;
+ }
+
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) {
+ goto give_sigsegv;
+ }
+
+ if (ka->sa.sa_flags & SA_SIGINFO) {
+ err |= copy_siginfo_to_user(&frame->info, info);
+ if (err) {
+ goto give_sigsegv;
+ }
+ }
+
+ /* Create the ucontext. */
+ err |= __put_user(0, &frame->uc.uc_flags);
+ err |= __put_user(0, &frame->uc.uc_link);
+ err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ err |= __put_user(sas_ss_flags(regs->rsp),
+ &frame->uc.uc_stack.ss_flags);
+ err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, set->sig[0], me);
+ err |= __put_user(fp, &frame->uc.uc_mcontext.fpstate);
+ if (sizeof(*set) == 16) {
+ __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]);
+ __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]);
+ } else {
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+ }
+
+ /* Set up to return from userspace. If provided, use a stub
+ already in userspace. */
+ /* x86-64 should always use SA_RESTORER. */
+ if (ka->sa.sa_flags & SA_RESTORER) {
+ err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
+ } else {
+ /* could use a vstub here */
+ goto give_sigsegv;
+ }
+
+ if (err) {
+ goto give_sigsegv;
+ }
+
+#ifdef DEBUG_SIG
+ printk("%d old rip %lx old rsp %lx old rax %lx\n",
current->pid,regs->rip,regs->rsp,regs->rax);
+#endif
+
+ /* Set up registers for signal handler */
+ {
+ struct exec_domain *ed = current_thread_info()->exec_domain;
+ if (unlikely(ed && ed->signal_invmap && sig < 32))
+ sig = ed->signal_invmap[sig];
+ }
+ regs->rdi = sig;
+ /* In case the signal handler was declared without prototypes */
+ regs->rax = 0;
+
+ /* This also works for non SA_SIGINFO handlers because they expect the
+ next argument after the signal number on the stack. */
+ regs->rsi = (unsigned long)&frame->info;
+ regs->rdx = (unsigned long)&frame->uc;
+ regs->rip = (unsigned long) ka->sa.sa_handler;
+
+ regs->rsp = (unsigned long)frame;
+
+ set_fs(USER_DS);
+ if (regs->eflags & TF_MASK) {
+ if ((current->ptrace & (PT_PTRACED | PT_DTRACE)) == (PT_PTRACED
| PT_DTRACE)) {
+ ptrace_notify(SIGTRAP);
+ } else {
+ regs->eflags &= ~TF_MASK;
+ }
+ }
+
+#ifdef DEBUG_SIG
+ printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n",
+ current->comm, current->pid, frame, regs->rip, frame->pretcode);
+#endif
+
+ return;
+
+give_sigsegv:
+ force_sigsegv(sig, current);
+}
+
+/*
+ * OK, we're invoking a handler
+ */
+
+static void
+handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
+ sigset_t *oldset, struct pt_regs *regs)
+{
+#ifdef DEBUG_SIG
+ printk("handle_signal pid:%d sig:%lu rip:%lx rsp:%lx regs=%p\n",
current->pid, sig,
+ regs->rip, regs->rsp, regs);
+#endif
+
+ /* Are we from a system call? */
+ if ((long)regs->orig_rax >= 0) {
+ /* If so, check system call restarting.. */
+ switch (regs->rax) {
+ case -ERESTART_RESTARTBLOCK:
+ case -ERESTARTNOHAND:
+ regs->rax = -EINTR;
+ break;
+
+ case -ERESTARTSYS:
+ if (!(ka->sa.sa_flags & SA_RESTART)) {
+ regs->rax = -EINTR;
+ break;
+ }
+ /* fallthrough */
+ case -ERESTARTNOINTR:
+ regs->rax = regs->orig_rax;
+ regs->rip -= 2;
+ }
+ }
+
+#ifdef CONFIG_IA32_EMULATION
+ if (test_thread_flag(TIF_IA32)) {
+ if (ka->sa.sa_flags & SA_SIGINFO)
+ ia32_setup_rt_frame(sig, ka, info, oldset, regs);
+ else
+ ia32_setup_frame(sig, ka, oldset, regs);
+ } else
+#endif
+ setup_rt_frame(sig, ka, info, oldset, regs);
+
+ if (!(ka->sa.sa_flags & SA_NODEFER)) {
+ spin_lock_irq(¤t->sighand->siglock);
+ sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask);
+ sigaddset(¤t->blocked,sig);
+ recalc_sigpending();
+ spin_unlock_irq(¤t->sighand->siglock);
+ }
+}
+
+/*
+ * Note that 'init' is a special process: it doesn't get signals it doesn't
+ * want to handle. Thus you cannot kill init even with a SIGKILL even by
+ * mistake.
+ */
+int do_signal(struct pt_regs *regs, sigset_t *oldset)
+{
+ struct k_sigaction ka;
+ siginfo_t info;
+ int signr;
+
+ /*
+ * We want the common case to go fast, which
+ * is why we may in certain cases get here from
+ * kernel mode. Just return without doing anything
+ * if so.
+ */
+ if ((regs->cs & 2) != 2) {
+ return 1;
+ }
+
+ if (try_to_freeze(0))
+ goto no_signal;
+
+ if (!oldset)
+ oldset = ¤t->blocked;
+
+ signr = get_signal_to_deliver(&info, &ka, regs, NULL);
+ if (signr > 0) {
+ /* Reenable any watchpoints before delivering the
+ * signal to user space. The processor register will
+ * have been cleared if the watchpoint triggered
+ * inside the kernel.
+ */
+ if (current->thread.debugreg7) {
+ HYPERVISOR_set_debugreg(7,
+ current->thread.debugreg7);
+ }
+
+ /* Whee! Actually deliver the signal. */
+ handle_signal(signr, &info, &ka, oldset, regs);
+ return 1;
+ }
+
+ no_signal:
+ /* Did we come from a system call? */
+ if ((long)regs->orig_rax >= 0) {
+ /* Restart the system call - no handlers present */
+ long res = regs->rax;
+ if (res == -ERESTARTNOHAND ||
+ res == -ERESTARTSYS ||
+ res == -ERESTARTNOINTR) {
+ regs->rax = regs->orig_rax;
+ regs->rip -= 2;
+ }
+ if (regs->rax == (unsigned long)-ERESTART_RESTARTBLOCK) {
+ regs->rax = __NR_restart_syscall;
+ regs->rip -= 2;
+ }
+ }
+ return 0;
+}
+
+void do_notify_resume(struct pt_regs *regs, sigset_t *oldset, __u32
thread_info_flags)
+{
+#ifdef DEBUG_SIG
+ printk("do_notify_resume flags:%x rip:%lx rsp:%lx caller:%lx
pending:%lx\n",
+ thread_info_flags, regs->rip, regs->rsp,
__builtin_return_address(0),signal_pending(current));
+#endif
+
+ /* Pending single-step? */
+ if (thread_info_flags & _TIF_SINGLESTEP) {
+ regs->eflags |= TF_MASK;
+ clear_thread_flag(TIF_SINGLESTEP);
+ }
+
+ /* deal with pending signal delivery */
+ if (thread_info_flags & _TIF_SIGPENDING)
+ do_signal(regs,oldset);
+}
+
+void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
+{
+ struct task_struct *me = current;
+ if (exception_trace)
+ printk("%s[%d] bad frame in %s frame:%p rip:%lx rsp:%lx
orax:%lx\n",
+
me->comm,me->pid,where,frame,regs->rip,regs->rsp,regs->orig_rax);
+
+ force_sig(SIGSEGV, me);
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/fixmap.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/fixmap.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,168 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ */
+
+#ifndef _ASM_FIXMAP_H
+#define _ASM_FIXMAP_H
+
+#include <linux/config.h>
+
+/* used by vmalloc.c, vsyscall.lds.S.
+ *
+ * Leave one empty page between vmalloc'ed areas and
+ * the start of the fixmap.
+ */
+#define __FIXADDR_TOP (HYPERVISOR_VIRT_START - 2 * PAGE_SIZE)
+
+#ifndef __ASSEMBLY__
+#include <linux/kernel.h>
+#include <asm/acpi.h>
+#include <asm/apicdef.h>
+#include <asm/page.h>
+#include <asm-xen/gnttab.h>
+#ifdef CONFIG_HIGHMEM
+#include <linux/threads.h>
+#include <asm/kmap_types.h>
+#endif
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process. We allocate these special addresses
+ * from the end of virtual memory (0xfffff000) backwards.
+ * Also this lets us do fail-safe vmalloc(), we
+ * can guarantee that these special addresses and
+ * vmalloc()-ed addresses never overlap.
+ *
+ * these 'compile-time allocated' memory buffers are
+ * fixed-size 4k pages. (or larger if used with an increment
+ * highger than 1) use fixmap_set(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ * TLB entries of such buffers will not be flushed across
+ * task switches.
+ */
+enum fixed_addresses {
+ FIX_HOLE,
+ FIX_VSYSCALL,
+#ifdef CONFIG_X86_LOCAL_APIC
+ FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */
+#endif
+#ifdef CONFIG_X86_IO_APIC
+ FIX_IO_APIC_BASE_0,
+ FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS-1,
+#endif
+#ifdef CONFIG_X86_VISWS_APIC
+ FIX_CO_CPU, /* Cobalt timer */
+ FIX_CO_APIC, /* Cobalt APIC Redirection Table */
+ FIX_LI_PCIA, /* Lithium PCI Bridge A */
+ FIX_LI_PCIB, /* Lithium PCI Bridge B */
+#endif
+#ifdef CONFIG_X86_F00F_BUG
+ FIX_F00F_IDT, /* Virtual mapping for IDT */
+#endif
+#ifdef CONFIG_X86_CYCLONE_TIMER
+ FIX_CYCLONE_TIMER, /*cyclone timer register*/
+#endif
+#ifdef CONFIG_HIGHMEM
+ FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */
+ FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
+#endif
+#ifdef CONFIG_ACPI_BOOT
+ FIX_ACPI_BEGIN,
+ FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
+ FIX_ACPI_RSDP_PAGE,
+#endif
+#ifdef CONFIG_PCI_MMCONFIG
+ FIX_PCIE_MCFG,
+#endif
+ FIX_SHARED_INFO,
+ FIX_GNTTAB_BEGIN,
+ FIX_GNTTAB_END = FIX_GNTTAB_BEGIN + NR_GRANT_FRAMES - 1,
+#ifdef CONFIG_XEN_PHYSDEV_ACCESS
+#define NR_FIX_ISAMAPS 256
+ FIX_ISAMAP_END,
+ FIX_ISAMAP_BEGIN = FIX_ISAMAP_END + NR_FIX_ISAMAPS - 1,
+#endif
+ __end_of_permanent_fixed_addresses,
+ /* temporary boot-time mappings, used before ioremap() is functional */
+#define NR_FIX_BTMAPS 16
+ FIX_BTMAP_END = __end_of_permanent_fixed_addresses,
+ FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS - 1,
+ FIX_WP_TEST,
+ __end_of_fixed_addresses
+};
+
+extern void __set_fixmap (enum fixed_addresses idx,
+ unsigned long phys, pgprot_t flags);
+
+#define set_fixmap(idx, phys) \
+ __set_fixmap(idx, phys, PAGE_KERNEL)
+/*
+ * Some hardware wants to get fixmapped without caching.
+ */
+#define set_fixmap_nocache(idx, phys) \
+ __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
+
+#define clear_fixmap(idx) \
+ __set_fixmap(idx, 0, __pgprot(0))
+
+#define FIXADDR_TOP ((unsigned long)__FIXADDR_TOP)
+
+#define __FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT)
+#define __FIXADDR_BOOT_SIZE (__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START (FIXADDR_TOP - __FIXADDR_SIZE)
+#define FIXADDR_BOOT_START (FIXADDR_TOP - __FIXADDR_BOOT_SIZE)
+
+#define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT))
+#define __virt_to_fix(x) ((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
+
+/*
+ * This is the range that is readable by user mode, and things
+ * acting like user mode such as get_user_pages.
+ */
+#define FIXADDR_USER_START (__fix_to_virt(FIX_VSYSCALL))
+#define FIXADDR_USER_END (FIXADDR_USER_START + PAGE_SIZE)
+
+
+extern void __this_fixmap_does_not_exist(void);
+
+/*
+ * 'index to address' translation. If anyone tries to use the idx
+ * directly without tranlation, we catch the bug with a NULL-deference
+ * kernel oops. Illegal ranges of incoming indices are caught too.
+ */
+static __always_inline unsigned long fix_to_virt(const unsigned int idx)
+{
+ /*
+ * this branch gets completely eliminated after inlining,
+ * except when someone tries to use fixaddr indices in an
+ * illegal way. (such as mixing up address types or using
+ * out-of-range indices).
+ *
+ * If it doesn't get removed, the linker will complain
+ * loudly with a reasonably clear error message..
+ */
+ if (idx >= __end_of_fixed_addresses)
+ __this_fixmap_does_not_exist();
+
+ return __fix_to_virt(idx);
+}
+
+static inline unsigned long virt_to_fix(const unsigned long vaddr)
+{
+ BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
+ return __virt_to_fix(vaddr);
+}
+
+#endif /* !__ASSEMBLY__ */
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/pgtable.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/pgtable.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,541 @@
+#ifndef _X86_64_PGTABLE_H
+#define _X86_64_PGTABLE_H
+
+/*
+ * This file contains the functions and defines necessary to modify and use
+ * the x86-64 page table tree.
+ *
+ * x86-64 has a 4 level table setup. Generic linux MM only supports
+ * three levels. The fourth level is currently a single static page that
+ * is shared by everybody and just contains a pointer to the current
+ * three level page setup on the beginning and some kernel mappings at
+ * the end. For more details see Documentation/x86_64/mm.txt
+ */
+#include <asm/processor.h>
+#include <asm/fixmap.h>
+#include <asm/bitops.h>
+#include <linux/threads.h>
+#include <asm/pda.h>
+#include <asm-xen/hypervisor.h>
+extern pud_t level3_user_pgt[512];
+extern pud_t init_level4_pgt[];
+extern pud_t init_level4_user_pgt[];
+extern unsigned long __supported_pte_mask;
+
+#define swapper_pg_dir NULL
+
+extern int nonx_setup(char *str);
+extern void paging_init(void);
+extern void clear_kernel_mapping(unsigned long addr, unsigned long size);
+
+extern unsigned long pgkern_mask;
+
+#define virt_to_ptep(__va) \
+({ \
+ pgd_t *__pgd = pgd_offset_k((unsigned long)(__va)); \
+ pud_t *__pud = pud_offset(__pgd, (unsigned long)(__va)); \
+ pmd_t *__pmd = pmd_offset(__pud, (unsigned long)(__va)); \
+ pte_offset_kernel(__pmd, (unsigned long)(__va)); \
+})
+
+#define arbitrary_virt_to_machine(__va)
\
+({ \
+ pte_t *__pte = virt_to_ptep(__va); \
+ unsigned long __pa = (*(unsigned long *)__pte) & PAGE_MASK; \
+ __pa | ((unsigned long)(__va) & (PAGE_SIZE-1)); \
+})
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)];
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+
+#define PGDIR_SHIFT 39
+#define PTRS_PER_PGD 512
+
+/*
+ * PUDIR_SHIFT determines what a top-level page table entry can map
+ */
+#define PUD_SHIFT 30
+#define PTRS_PER_PUD 512
+
+/*
+ * PMD_SHIFT determines the size of the area a middle-level
+ * page table can map
+ */
+#define PMD_SHIFT 21
+#define PTRS_PER_PMD 512
+
+/*
+ * entries per page directory level
+ */
+#define PTRS_PER_PTE 512
+
+#define pte_ERROR(e) \
+ printk("%s:%d: bad pte %p(%016lx).\n", __FILE__, __LINE__, &(e),
pte_val(e))
+#define pmd_ERROR(e) \
+ printk("%s:%d: bad pmd %p(%016lx).\n", __FILE__, __LINE__, &(e),
pmd_val(e))
+#define pud_ERROR(e) \
+ printk("%s:%d: bad pud %p(%016lx).\n", __FILE__, __LINE__, &(e),
pud_val(e))
+#define pgd_ERROR(e) \
+ printk("%s:%d: bad pgd %p(%016lx).\n", __FILE__, __LINE__, &(e),
pgd_val(e))
+
+#define pgd_none(x) (!pgd_val(x))
+#define pud_none(x) (!pud_val(x))
+
+#define set_pte_batched(pteptr, pteval) \
+ queue_l1_entry_update(pteptr, (pteval))
+
+extern inline int pud_present(pud_t pud) { return !pud_none(pud); }
+
+#ifdef CONFIG_SMP
+#define set_pte(pteptr, pteval) xen_l1_entry_update(pteptr, (pteval).pte)
+
+#else
+#define set_pte(pteptr, pteval) xen_l1_entry_update(pteptr, (pteval.pte))
+#if 0
+static inline void set_pte(pte_t *dst, pte_t val)
+{
+ *dst = val;
+}
+#endif
+#endif
+
+#define set_pmd(pmdptr, pmdval) xen_l2_entry_update(pmdptr, (pmdval))
+#define set_pud(pudptr, pudval) xen_l3_entry_update(pudptr, (pudval))
+#define set_pgd(pgdptr, pgdval) xen_l4_entry_update(pgdptr, (pgdval))
+
+extern inline void pud_clear (pud_t * pud)
+{
+ set_pud(pud, __pud(0));
+}
+
+#define __user_pgd(pgd) ((pgd) + PTRS_PER_PGD)
+
+extern inline void pgd_clear (pgd_t * pgd)
+{
+ set_pgd(pgd, __pgd(0));
+ set_pgd(__user_pgd(pgd), __pgd(0));
+}
+
+#define pud_page(pud) \
+ ((unsigned long) __va(pud_val(pud) & PHYSICAL_PAGE_MASK))
+
+/*
+ * A note on implementation of this atomic 'get-and-clear' operation.
+ * This is actually very simple because Xen Linux can only run on a single
+ * processor. Therefore, we cannot race other processors setting the 'accessed'
+ * or 'dirty' bits on a page-table entry.
+ * Even if pages are shared between domains, that is not a problem because
+ * each domain will have separate page tables, with their own versions of
+ * accessed & dirty state.
+ */
+static inline pte_t ptep_get_and_clear(pte_t *xp)
+{
+ pte_t pte = *xp;
+ if (pte.pte)
+ set_pte(xp, __pte_ma(0));
+ return pte;
+}
+
+#define pte_same(a, b) ((a).pte == (b).pte)
+
+#define PMD_SIZE (1UL << PMD_SHIFT)
+#define PMD_MASK (~(PMD_SIZE-1))
+#define PUD_SIZE (1UL << PUD_SHIFT)
+#define PUD_MASK (~(PUD_SIZE-1))
+#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE-1))
+
+#define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE)
+#define FIRST_USER_PGD_NR 0
+
+#ifndef __ASSEMBLY__
+#define MAXMEM 0x3fffffffffffUL
+#define VMALLOC_START 0xffffc20000000000UL
+#define VMALLOC_END 0xffffe1ffffffffffUL
+#define MODULES_VADDR 0xffffffff88000000UL
+#define MODULES_END 0xfffffffffff00000UL
+#define MODULES_LEN (MODULES_END - MODULES_VADDR)
+
+#define _PAGE_BIT_PRESENT 0
+#define _PAGE_BIT_RW 1
+#define _PAGE_BIT_USER 2
+#define _PAGE_BIT_PWT 3
+#define _PAGE_BIT_PCD 4
+#define _PAGE_BIT_ACCESSED 5
+#define _PAGE_BIT_DIRTY 6
+#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */
+#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
+#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid
check */
+
+#define _PAGE_PRESENT 0x001
+#define _PAGE_RW 0x002
+#define _PAGE_USER 0x004
+#define _PAGE_PWT 0x008
+#define _PAGE_PCD 0x010
+#define _PAGE_ACCESSED 0x020
+#define _PAGE_DIRTY 0x040
+#define _PAGE_PSE 0x080 /* 2MB page */
+#define _PAGE_FILE 0x040 /* set:pagecache, unset:swap */
+#define _PAGE_GLOBAL 0x100 /* Global TLB entry */
+
+#define _PAGE_PROTNONE 0x080 /* If not present */
+#define _PAGE_NX (1UL<<_PAGE_BIT_NX)
+
+#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED
| _PAGE_DIRTY)
+#define _KERNPG_TABLE _PAGE_TABLE
+
+#define _PAGE_CHG_MASK (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+
+#define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
+#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |
_PAGE_ACCESSED | _PAGE_NX)
+#define PAGE_SHARED_EXEC __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |
_PAGE_ACCESSED)
+#define PAGE_COPY_NOEXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED
| _PAGE_NX)
+#define PAGE_COPY PAGE_COPY_NOEXEC
+#define PAGE_COPY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED |
_PAGE_NX)
+#define PAGE_READONLY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER |
_PAGE_ACCESSED)
+#define __PAGE_KERNEL \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX |
_PAGE_USER )
+#define __PAGE_KERNEL_EXEC \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_USER )
+#define __PAGE_KERNEL_NOCACHE \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_PCD | _PAGE_ACCESSED |
_PAGE_NX | _PAGE_USER )
+#define __PAGE_KERNEL_RO \
+ (_PAGE_PRESENT | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX | _PAGE_USER )
+#define __PAGE_KERNEL_VSYSCALL \
+ (_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_USER )
+#define __PAGE_KERNEL_VSYSCALL_NOCACHE \
+ (_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_PCD | _PAGE_USER )
+#define __PAGE_KERNEL_LARGE \
+ (__PAGE_KERNEL | _PAGE_PSE | _PAGE_USER )
+
+
+/*
+ * We don't support GLOBAL page in xenolinux64
+ */
+#define MAKE_GLOBAL(x) __pgprot((x))
+
+#define PAGE_KERNEL MAKE_GLOBAL(__PAGE_KERNEL)
+#define PAGE_KERNEL_EXEC MAKE_GLOBAL(__PAGE_KERNEL_EXEC)
+#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO)
+#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
+#define PAGE_KERNEL_VSYSCALL32 __pgprot(__PAGE_KERNEL_VSYSCALL)
+#define PAGE_KERNEL_VSYSCALL MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL)
+#define PAGE_KERNEL_LARGE MAKE_GLOBAL(__PAGE_KERNEL_LARGE)
+#define PAGE_KERNEL_VSYSCALL_NOCACHE
MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL_NOCACHE)
+
+/* xwr */
+#define __P000 PAGE_NONE
+#define __P001 PAGE_READONLY
+#define __P010 PAGE_COPY
+#define __P011 PAGE_COPY
+#define __P100 PAGE_READONLY_EXEC
+#define __P101 PAGE_READONLY_EXEC
+#define __P110 PAGE_COPY_EXEC
+#define __P111 PAGE_COPY_EXEC
+
+#define __S000 PAGE_NONE
+#define __S001 PAGE_READONLY
+#define __S010 PAGE_SHARED
+#define __S011 PAGE_SHARED
+#define __S100 PAGE_READONLY_EXEC
+#define __S101 PAGE_READONLY_EXEC
+#define __S110 PAGE_SHARED_EXEC
+#define __S111 PAGE_SHARED_EXEC
+
+static inline unsigned long pgd_bad(pgd_t pgd)
+{
+ unsigned long val = pgd_val(pgd);
+ val &= ~PTE_MASK;
+ val &= ~(_PAGE_USER | _PAGE_DIRTY);
+ return val & ~(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED);
+}
+
+static inline unsigned long pud_bad(pud_t pud)
+{
+ unsigned long val = pud_val(pud);
+ val &= ~PTE_MASK;
+ val &= ~(_PAGE_USER | _PAGE_DIRTY);
+ return val & ~(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED);
+}
+
+#define pte_none(x) (!(x).pte)
+#define pte_present(x) ((x).pte & (_PAGE_PRESENT | _PAGE_PROTNONE))
+#define pte_clear(xp) do { set_pte(xp, __pte(0)); } while (0)
+
+#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
+
+/*
+ * We detect special mappings in one of two ways:
+ * 1. If the MFN is an I/O page then Xen will set the m2p entry
+ * to be outside our maximum possible pseudophys range.
+ * 2. If the MFN belongs to a different domain then we will certainly
+ * not have MFN in our p2m table. Conversely, if the page is ours,
+ * then we'll have p2m(m2p(MFN))==MFN.
+ * If we detect a special mapping then it doesn't have a 'struct page'.
+ * We force !pfn_valid() by returning an out-of-range pointer.
+ *
+ * NB. These checks require that, for any MFN that is not in our reservation,
+ * there is no PFN such that p2m(PFN) == MFN. Otherwise we can get confused if
+ * we are foreign-mapping the MFN, and the other domain as m2p(MFN) == PFN.
+ * Yikes! Various places must poke in INVALID_P2M_ENTRY for safety.
+ *
+ * NB2. When deliberately mapping foreign pages into the p2m table, you *must*
+ * use FOREIGN_FRAME(). This will cause pte_pfn() to choke on it, as we
+ * require. In all the cases we care about, the high bit gets shifted out
+ * (e.g., phys_to_machine()) so behaviour there is correct.
+ */
+#define INVALID_P2M_ENTRY (~0U)
+#define FOREIGN_FRAME(_m) ((_m) | (1UL<<((sizeof(unsigned long)*8)-1)))
+#define pte_mfn(_pte) (((_pte).pte & PTE_MASK) >> PAGE_SHIFT)
+#define pte_pfn(_pte) \
+({ \
+ unsigned long mfn = pte_mfn(_pte); \
+ unsigned pfn = mfn_to_pfn(mfn); \
+ if ((pfn >= max_mapnr) || (pfn_to_mfn(pfn) != mfn)) \
+ pfn = max_mapnr; /* special: force !pfn_valid() */ \
+ pfn; \
+})
+
+#define pte_page(x) pfn_to_page(pte_pfn(x))
+
+static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
+{
+ pte_t pte;
+
+ (pte).pte = (pfn_to_mfn(page_nr) << PAGE_SHIFT);
+ (pte).pte |= pgprot_val(pgprot);
+ (pte).pte &= __supported_pte_mask;
+ return pte;
+}
+
+#define pfn_pte_ma(pfn, prot) __pte_ma((((pfn) << PAGE_SHIFT) |
pgprot_val(prot)) & __supported_pte_mask)
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+#define __pte_val(x) ((x).pte)
+
+static inline int pte_user(pte_t pte) { return __pte_val(pte) &
_PAGE_USER; }
+extern inline int pte_read(pte_t pte) { return __pte_val(pte) &
_PAGE_USER; }
+extern inline int pte_exec(pte_t pte) { return __pte_val(pte) &
_PAGE_USER; }
+extern inline int pte_dirty(pte_t pte) { return __pte_val(pte) &
_PAGE_DIRTY; }
+extern inline int pte_young(pte_t pte) { return __pte_val(pte) &
_PAGE_ACCESSED; }
+extern inline int pte_write(pte_t pte) { return __pte_val(pte) &
_PAGE_RW; }
+static inline int pte_file(pte_t pte) { return __pte_val(pte) &
_PAGE_FILE; }
+
+extern inline pte_t pte_rdprotect(pte_t pte) { __pte_val(pte) &=
~_PAGE_USER; return pte; }
+extern inline pte_t pte_exprotect(pte_t pte) { __pte_val(pte) &=
~_PAGE_USER; return pte; }
+extern inline pte_t pte_mkclean(pte_t pte) { __pte_val(pte) &=
~_PAGE_DIRTY; return pte; }
+extern inline pte_t pte_mkold(pte_t pte) { __pte_val(pte) &=
~_PAGE_ACCESSED; return pte; }
+extern inline pte_t pte_wrprotect(pte_t pte) { __pte_val(pte) &= ~_PAGE_RW;
return pte; }
+extern inline pte_t pte_mkread(pte_t pte) { __pte_val(pte) |= _PAGE_USER;
return pte; }
+extern inline pte_t pte_mkexec(pte_t pte) { __pte_val(pte) |= _PAGE_USER;
return pte; }
+extern inline pte_t pte_mkdirty(pte_t pte) { __pte_val(pte) |=
_PAGE_DIRTY; return pte; }
+extern inline pte_t pte_mkyoung(pte_t pte) { __pte_val(pte) |=
_PAGE_ACCESSED; return pte; }
+extern inline pte_t pte_mkwrite(pte_t pte) { __pte_val(pte) |= _PAGE_RW;
return pte; }
+
+static inline int ptep_test_and_clear_dirty(pte_t *ptep)
+{
+ pte_t pte = *ptep;
+ int ret = pte_dirty(pte);
+ if (ret)
+ xen_l1_entry_update(ptep, pte_mkclean(pte).pte);
+ return ret;
+}
+
+static inline int ptep_test_and_clear_young(pte_t *ptep)
+{
+ pte_t pte = *ptep;
+ int ret = pte_young(pte);
+ if (ret)
+ xen_l1_entry_update(ptep, pte_mkold(pte).pte);
+ return ret;
+}
+
+static inline void ptep_set_wrprotect(pte_t *ptep)
+{
+ pte_t pte = *ptep;
+ if (pte_write(pte))
+ set_pte(ptep, pte_wrprotect(pte));
+}
+static inline void ptep_mkdirty(pte_t *ptep)
+{
+ pte_t pte = *ptep;
+ if (!pte_dirty(pte))
+ xen_l1_entry_update(ptep, pte_mkdirty(pte).pte);
+}
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ */
+#define pgprot_noncached(prot) (__pgprot(pgprot_val(prot) | _PAGE_PCD |
_PAGE_PWT))
+
+#define __LARGE_PTE (_PAGE_PSE|_PAGE_PRESENT)
+static inline int pmd_large(pmd_t pte) {
+ return (pmd_val(pte) & __LARGE_PTE) == __LARGE_PTE;
+}
+
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ */
+
+#define page_pte(page) page_pte_prot(page, __pgprot(0))
+
+/*
+ * Level 4 access.
+ * Never use these in the common code.
+ */
+#define pgd_page(pgd) ((unsigned long) __va(pgd_val(pgd) & PTE_MASK))
+#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
+#define pgd_offset(mm, addr) ((mm)->pgd + pgd_index(addr))
+#define pgd_offset_k(address) (pgd_t *)(init_level4_pgt + pgd_index(address))
+#define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT)
+#define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE)
+
+/* PUD - Level3 access */
+/* to find an entry in a page-table-directory. */
+#define pud_index(address) ((address >> PUD_SHIFT) & (PTRS_PER_PUD-1))
+#define pud_offset(pgd, address) ((pud_t *) pgd_page(*(pgd)) +
pud_index(address))
+static inline pud_t *__pud_offset_k(pud_t *pud, unsigned long address)
+{
+ return pud + pud_index(address);
+}
+
+/* Find correct pud via the hidden fourth level page level: */
+
+/* This accesses the reference page table of the boot cpu.
+ Other CPUs get synced lazily via the page fault handler. */
+static inline pud_t *pud_offset_k(unsigned long address)
+{
+ unsigned long addr;
+
+ addr = pud_val(init_level4_pgt[pud_index(address)]);
+ addr &= PHYSICAL_PAGE_MASK; /* machine physical */
+ addr = machine_to_phys(addr);
+ return __pud_offset_k((pud_t *)__va(addr), address);
+}
+
+/* PMD - Level 2 access */
+#define pmd_page_kernel(pmd) ((unsigned long) __va(pmd_val(pmd) & PTE_MASK))
+#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
+
+#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
+#define pmd_offset(dir, address) ((pmd_t *) pud_page(*(dir)) + \
+ pmd_index(address))
+#define pmd_none(x) (!pmd_val(x))
+#define pmd_present(x) (pmd_val(x) & _PAGE_PRESENT)
+#define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0)
+#define pmd_bad(x) ((pmd_val(x) & ~PTE_MASK) != _KERNPG_TABLE )
+#define pfn_pmd(nr,prot) (__pmd(((nr) << PAGE_SHIFT) | pgprot_val(prot)))
+#define pmd_pfn(x) ((pmd_val(x) >> PAGE_SHIFT) & __PHYSICAL_MASK)
+
+#define pte_to_pgoff(pte) ((pte_val(pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
+#define pgoff_to_pte(off) ((pte_t) { ((off) << PAGE_SHIFT) | _PAGE_FILE })
+#define PTE_FILE_MAX_BITS __PHYSICAL_MASK_SHIFT
+
+/* PTE - Level 1 access. */
+
+/* page, protection -> pte */
+#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
+#define mk_pte_huge(entry) (pte_val(entry) |= _PAGE_PRESENT | _PAGE_PSE)
+
+/* physical address -> PTE */
+static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot)
+{
+ pte_t pte;
+ (pte).pte = physpage | pgprot_val(pgprot);
+ return pte;
+}
+
+/* Change flags of a PTE */
+extern inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+ (pte).pte &= _PAGE_CHG_MASK;
+ (pte).pte |= pgprot_val(newprot);
+ (pte).pte &= __supported_pte_mask;
+ return pte;
+}
+
+#define pte_index(address) \
+ ((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_offset_kernel(dir, address) ((pte_t *) pmd_page_kernel(*(dir)) + \
+ pte_index(address))
+
+/* x86-64 always has all page tables mapped. */
+#define pte_offset_map(dir,address) pte_offset_kernel(dir,address)
+#define pte_offset_map_nested(dir,address) pte_offset_kernel(dir,address)
+#define pte_unmap(pte) /* NOP */
+#define pte_unmap_nested(pte) /* NOP */
+
+#define update_mmu_cache(vma,address,pte) do { } while (0)
+
+/* We only update the dirty/accessed state if we set
+ * the dirty bit by hand in the kernel, since the hardware
+ * will do the accessed bit for us, and we don't want to
+ * race with other CPU's that might be updating the dirty
+ * bit at the same time. */
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
+ do { \
+ if (__dirty) { \
+ set_pte(__ptep, __entry); \
+ flush_tlb_page(__vma, __address); \
+ } \
+ } while (0)
+
+/* Encode and de-code a swap entry */
+#define __swp_type(x) (((x).val >> 1) & 0x3f)
+#define __swp_offset(x) ((x).val >> 8)
+#define __swp_entry(type, offset) ((swp_entry_t) { ((type) << 1) |
((offset) << 8) })
+#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
+
+#endif /* !__ASSEMBLY__ */
+
+extern int kern_addr_valid(unsigned long addr);
+
+#define DOMID_LOCAL (0xFFFFU)
+
+int direct_remap_area_pages(struct mm_struct *mm,
+ unsigned long address,
+ unsigned long machine_addr,
+ unsigned long size,
+ pgprot_t prot,
+ domid_t domid);
+int __direct_remap_area_pages(struct mm_struct *mm,
+ unsigned long address,
+ unsigned long size,
+ mmu_update_t *v);
+
+#define io_remap_page_range(vma, vaddr, paddr, size, prot) \
+ remap_pfn_range(vma, vaddr, (paddr) >> PAGE_SHIFT, size, prot)
+
+#define HAVE_ARCH_UNMAPPED_AREA
+
+#define pgtable_cache_init() do { } while (0)
+#define check_pgt_cache() do { } while (0)
+
+#define PAGE_AGP PAGE_KERNEL_NOCACHE
+#define HAVE_PAGE_AGP 1
+
+/* fs/proc/kcore.c */
+#define kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK)
+#define kc_offset_to_vaddr(o) \
+ (((o) & (1UL << (__VIRTUAL_MASK_SHIFT-1))) ? ((o) | (~__VIRTUAL_MASK)) :
(o))
+
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+#define __HAVE_ARCH_PTEP_MKDIRTY
+#define __HAVE_ARCH_PTE_SAME
+#include <asm-generic/pgtable.h>
+
+#endif /* _X86_64_PGTABLE_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/floppy.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/floppy.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,204 @@
+/*
+ * Architecture specific parts of the Floppy driver
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1995
+ *
+ * Modifications for Xen are Copyright (c) 2004, Keir Fraser.
+ */
+#ifndef __ASM_XEN_X86_64_FLOPPY_H
+#define __ASM_XEN_X86_64_FLOPPY_H
+
+#include <linux/vmalloc.h>
+
+
+/*
+ * The DMA channel used by the floppy controller cannot access data at
+ * addresses >= 16MB
+ *
+ * Went back to the 1MB limit, as some people had problems with the floppy
+ * driver otherwise. It doesn't matter much for performance anyway, as most
+ * floppy accesses go through the track buffer.
+ */
+#define _CROSS_64KB(a,s,vdma) \
+(!(vdma) && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
+
+#include <linux/vmalloc.h>
+
+/* XEN: Hit DMA paths on the head. This trick from asm-m68k/floppy.h. */
+#include <asm/dma.h>
+#undef MAX_DMA_ADDRESS
+#define MAX_DMA_ADDRESS 0
+#define CROSS_64KB(a,s) (0)
+
+#define fd_inb(port) inb_p(port)
+#define fd_outb(value,port) outb_p(value,port)
+
+#define fd_request_dma() (0)
+#define fd_free_dma() ((void)0)
+#define fd_enable_irq() enable_irq(FLOPPY_IRQ)
+#define fd_disable_irq() disable_irq(FLOPPY_IRQ)
+#define fd_free_irq() free_irq(FLOPPY_IRQ, NULL)
+#define fd_get_dma_residue() vdma_get_dma_residue(FLOPPY_DMA)
+#define fd_dma_mem_alloc(size) vdma_mem_alloc(size)
+#define fd_dma_mem_free(addr, size) vdma_mem_free(addr, size)
+#define fd_dma_setup(addr, size, mode, io) vdma_dma_setup(addr, size, mode, io)
+
+static int virtual_dma_count;
+static int virtual_dma_residue;
+static char *virtual_dma_addr;
+static int virtual_dma_mode;
+static int doing_pdma;
+
+static irqreturn_t floppy_hardint(int irq, void *dev_id, struct pt_regs * regs)
+{
+ register unsigned char st;
+
+#undef TRACE_FLPY_INT
+
+#ifdef TRACE_FLPY_INT
+ static int calls=0;
+ static int bytes=0;
+ static int dma_wait=0;
+#endif
+ if (!doing_pdma)
+ return floppy_interrupt(irq, dev_id, regs);
+
+#ifdef TRACE_FLPY_INT
+ if(!calls)
+ bytes = virtual_dma_count;
+#endif
+
+ {
+ register int lcount;
+ register char *lptr;
+
+ st = 1;
+ for(lcount=virtual_dma_count, lptr=virtual_dma_addr;
+ lcount; lcount--, lptr++) {
+ st=inb(virtual_dma_port+4) & 0xa0 ;
+ if(st != 0xa0)
+ break;
+ if(virtual_dma_mode)
+ outb_p(*lptr, virtual_dma_port+5);
+ else
+ *lptr = inb_p(virtual_dma_port+5);
+ }
+ virtual_dma_count = lcount;
+ virtual_dma_addr = lptr;
+ st = inb(virtual_dma_port+4);
+ }
+
+#ifdef TRACE_FLPY_INT
+ calls++;
+#endif
+ if(st == 0x20)
+ return IRQ_HANDLED;
+ if(!(st & 0x20)) {
+ virtual_dma_residue += virtual_dma_count;
+ virtual_dma_count=0;
+#ifdef TRACE_FLPY_INT
+ printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n",
+ virtual_dma_count, virtual_dma_residue, calls, bytes,
+ dma_wait);
+ calls = 0;
+ dma_wait=0;
+#endif
+ doing_pdma = 0;
+ floppy_interrupt(irq, dev_id, regs);
+ return IRQ_HANDLED;
+ }
+#ifdef TRACE_FLPY_INT
+ if(!virtual_dma_count)
+ dma_wait++;
+#endif
+ return IRQ_HANDLED;
+}
+
+static void fd_disable_dma(void)
+{
+ doing_pdma = 0;
+ virtual_dma_residue += virtual_dma_count;
+ virtual_dma_count=0;
+}
+
+static int vdma_get_dma_residue(unsigned int dummy)
+{
+ return virtual_dma_count + virtual_dma_residue;
+}
+
+
+static int fd_request_irq(void)
+{
+ return request_irq(FLOPPY_IRQ, floppy_hardint,SA_INTERRUPT,
+ "floppy", NULL);
+}
+
+
+static unsigned long vdma_mem_alloc(unsigned long size)
+{
+ return (unsigned long) vmalloc(size);
+
+}
+
+static void vdma_mem_free(unsigned long addr, unsigned long size)
+{
+ vfree((void *)addr);
+}
+
+static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+ doing_pdma = 1;
+ virtual_dma_port = io;
+ virtual_dma_mode = (mode == DMA_MODE_WRITE);
+ virtual_dma_addr = addr;
+ virtual_dma_count = size;
+ virtual_dma_residue = 0;
+ return 0;
+}
+
+/* XEN: This trick to force 'virtual DMA' is from include/asm-m68k/floppy.h. */
+#define FDC1 xen_floppy_init()
+static int FDC2 = -1;
+
+static int xen_floppy_init(void)
+{
+ use_virtual_dma = 1;
+ can_use_virtual_dma = 1;
+ return 0x340;
+}
+
+/*
+ * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock
+ * is needed to prevent corrupted CMOS RAM in case "insmod floppy"
+ * coincides with another rtc CMOS user. Paul G.
+ */
+#define FLOPPY0_TYPE ({ \
+ unsigned long flags; \
+ unsigned char val; \
+ spin_lock_irqsave(&rtc_lock, flags); \
+ val = (CMOS_READ(0x10) >> 4) & 15; \
+ spin_unlock_irqrestore(&rtc_lock, flags); \
+ val; \
+})
+
+#define FLOPPY1_TYPE ({ \
+ unsigned long flags; \
+ unsigned char val; \
+ spin_lock_irqsave(&rtc_lock, flags); \
+ val = CMOS_READ(0x10) & 15; \
+ spin_unlock_irqrestore(&rtc_lock, flags); \
+ val; \
+})
+
+#define N_FDC 2
+#define N_DRIVE 8
+
+#define FLOPPY_MOTOR_MASK 0xf0
+
+#define EXTRA_FLOPPY_PARAMS
+
+#endif /* __ASM_XEN_X86_64_FLOPPY_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/module.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/module.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,14 @@
+#ifndef _ASM_I386_MODULE_H
+#define _ASM_I386_MODULE_H
+/*
+ * This file contains the i386 architecture specific module code.
+ */
+
+extern int xen_module_init(struct module *mod);
+
+#define module_map(x) vmalloc(x)
+#define module_unmap(x) vfree(x)
+#define module_arch_init(x) xen_module_init(x)
+#define arch_init_modules(x) do { } while (0)
+
+#endif /* _ASM_I386_MODULE_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/mm/ioremap.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/mm/ioremap.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,442 @@
+/*
+ * arch/i386/mm/ioremap.c
+ *
+ * Re-map IO memory to kernel address space so that we can access it.
+ * This is needed for high PCI addresses that aren't mapped in the
+ * 640k-1MB IO memory area on PC's
+ *
+ * (C) Copyright 1995 1996 Linus Torvalds
+ */
+
+#include <linux/vmalloc.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <asm/io.h>
+#include <asm/fixmap.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+
+#ifndef CONFIG_XEN_PHYSDEV_ACCESS
+
+void * __ioremap(unsigned long phys_addr, unsigned long size,
+ unsigned long flags)
+{
+ return NULL;
+}
+
+void *ioremap_nocache (unsigned long phys_addr, unsigned long size)
+{
+ return NULL;
+}
+
+void iounmap(volatile void __iomem *addr)
+{
+}
+
+void __init *bt_ioremap(unsigned long phys_addr, unsigned long size)
+{
+ return NULL;
+}
+
+void __init bt_iounmap(void *addr, unsigned long size)
+{
+}
+
+#else
+
+/*
+ * Does @address reside within a non-highmem page that is local to this virtual
+ * machine (i.e., not an I/O page, nor a memory page belonging to another VM).
+ * See the comment that accompanies pte_pfn() in pgtable-2level.h to understand
+ * why this works.
+ */
+static inline int is_local_lowmem(unsigned long address)
+{
+ extern unsigned long max_low_pfn;
+ unsigned long mfn = address >> PAGE_SHIFT;
+ unsigned long pfn = mfn_to_pfn(mfn);
+ return ((pfn < max_low_pfn) && (pfn_to_mfn(pfn) == mfn));
+}
+
+/*
+ * Generic mapping function (not visible outside):
+ */
+
+/*
+ * Remap an arbitrary physical address space into the kernel virtual
+ * address space. Needed when the kernel wants to access high addresses
+ * directly.
+ *
+ * NOTE! We need to allow non-page-aligned mappings too: we will obviously
+ * have to convert them into an offset in a page-aligned mapping, but the
+ * caller shouldn't need to know that small detail.
+ */
+void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned
long flags)
+{
+ void __iomem * addr;
+ struct vm_struct * area;
+ unsigned long offset, last_addr;
+ domid_t domid = DOMID_IO;
+
+ /* Don't allow wraparound or zero size */
+ last_addr = phys_addr + size - 1;
+ if (!size || last_addr < phys_addr)
+ return NULL;
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ /*
+ * Don't remap the low PCI/ISA area, it's always mapped..
+ */
+ if (phys_addr >= 0x0 && last_addr < 0x100000)
+ return isa_bus_to_virt(phys_addr);
+#endif
+
+ /*
+ * Don't allow anybody to remap normal RAM that we're using..
+ */
+ if (is_local_lowmem(phys_addr)) {
+ char *t_addr, *t_end;
+ struct page *page;
+
+ t_addr = bus_to_virt(phys_addr);
+ t_end = t_addr + (size - 1);
+
+ for(page = virt_to_page(t_addr); page <= virt_to_page(t_end);
page++)
+ if(!PageReserved(page))
+ return NULL;
+
+ domid = DOMID_SELF;
+ }
+
+ /*
+ * Mappings have to be page-aligned
+ */
+ offset = phys_addr & ~PAGE_MASK;
+ phys_addr &= PAGE_MASK;
+ size = PAGE_ALIGN(last_addr+1) - phys_addr;
+
+ /*
+ * Ok, go for it..
+ */
+ area = get_vm_area(size, VM_IOREMAP | (flags << 20));
+ if (!area)
+ return NULL;
+ area->phys_addr = phys_addr;
+ addr = (void __iomem *) area->addr;
+ if (direct_remap_area_pages(&init_mm, (unsigned long) addr, phys_addr,
+ size, __pgprot(_PAGE_PRESENT | _PAGE_RW |
+ _PAGE_DIRTY | _PAGE_ACCESSED
+ | flags), domid)) {
+ vunmap((void __force *) addr);
+ return NULL;
+ }
+ return (void __iomem *) (offset + (char __iomem *)addr);
+}
+
+
+/**
+ * ioremap_nocache - map bus memory into CPU space
+ * @offset: bus address of the memory
+ * @size: size of the resource to map
+ *
+ * ioremap_nocache performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * This version of ioremap ensures that the memory is marked uncachable
+ * on the CPU as well as honouring existing caching rules from things like
+ * the PCI bus. Note that there are other caches and buffers on many
+ * busses. In particular driver authors should read up on PCI writes
+ *
+ * It's useful if some control registers are in such an area and
+ * write combining or read caching is not desirable:
+ *
+ * Must be freed with iounmap.
+ */
+
+void __iomem *ioremap_nocache (unsigned long phys_addr, unsigned long size)
+{
+ unsigned long last_addr;
+ void __iomem *p = __ioremap(phys_addr, size, _PAGE_PCD);
+ if (!p)
+ return p;
+
+ /* Guaranteed to be > phys_addr, as per __ioremap() */
+ last_addr = phys_addr + size - 1;
+
+ if (is_local_lowmem(last_addr)) {
+ struct page *ppage = virt_to_page(bus_to_virt(phys_addr));
+ unsigned long npages;
+
+ phys_addr &= PAGE_MASK;
+
+ /* This might overflow and become zero.. */
+ last_addr = PAGE_ALIGN(last_addr);
+
+ /* .. but that's ok, because modulo-2**n arithmetic will make
+ * the page-aligned "last - first" come out right.
+ */
+ npages = (last_addr - phys_addr) >> PAGE_SHIFT;
+
+ if (change_page_attr(ppage, npages, PAGE_KERNEL_NOCACHE) < 0) {
+ iounmap(p);
+ p = NULL;
+ }
+ global_flush_tlb();
+ }
+
+ return p;
+}
+
+void iounmap(volatile void __iomem *addr)
+{
+ struct vm_struct *p;
+ if ((void __force *) addr <= high_memory)
+ return;
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ if ((unsigned long) addr >= fix_to_virt(FIX_ISAMAP_BEGIN))
+ return;
+#endif
+ p = remove_vm_area((void *) (PAGE_MASK & (unsigned long __force) addr));
+ if (!p) {
+ printk("__iounmap: bad address %p\n", addr);
+ return;
+ }
+
+ if ((p->flags >> 20) && is_local_lowmem(p->phys_addr)) {
+ /* p->size includes the guard page, but cpa doesn't like that */
+ change_page_attr(virt_to_page(bus_to_virt(p->phys_addr)),
+ (p->size - PAGE_SIZE) >> PAGE_SHIFT,
+ PAGE_KERNEL);
+ global_flush_tlb();
+ }
+ kfree(p);
+}
+
+void __init *bt_ioremap(unsigned long phys_addr, unsigned long size)
+{
+ unsigned long offset, last_addr;
+ unsigned int nrpages;
+ enum fixed_addresses idx;
+
+ /* Don't allow wraparound or zero size */
+ last_addr = phys_addr + size - 1;
+ if (!size || last_addr < phys_addr)
+ return NULL;
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ /*
+ * Don't remap the low PCI/ISA area, it's always mapped..
+ */
+ if (phys_addr >= 0x0 && last_addr < 0x100000)
+ return isa_bus_to_virt(phys_addr);
+#endif
+
+ /*
+ * Mappings have to be page-aligned
+ */
+ offset = phys_addr & ~PAGE_MASK;
+ phys_addr &= PAGE_MASK;
+ size = PAGE_ALIGN(last_addr) - phys_addr;
+
+ /*
+ * Mappings have to fit in the FIX_BTMAP area.
+ */
+ nrpages = size >> PAGE_SHIFT;
+ if (nrpages > NR_FIX_BTMAPS)
+ return NULL;
+
+ /*
+ * Ok, go for it..
+ */
+ idx = FIX_BTMAP_BEGIN;
+ while (nrpages > 0) {
+ set_fixmap(idx, phys_addr);
+ phys_addr += PAGE_SIZE;
+ --idx;
+ --nrpages;
+ }
+ return (void*) (offset + fix_to_virt(FIX_BTMAP_BEGIN));
+}
+
+void __init bt_iounmap(void *addr, unsigned long size)
+{
+ unsigned long virt_addr;
+ unsigned long offset;
+ unsigned int nrpages;
+ enum fixed_addresses idx;
+
+ virt_addr = (unsigned long)addr;
+ if (virt_addr < fix_to_virt(FIX_BTMAP_BEGIN))
+ return;
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ if (virt_addr >= fix_to_virt(FIX_ISAMAP_BEGIN))
+ return;
+#endif
+ offset = virt_addr & ~PAGE_MASK;
+ nrpages = PAGE_ALIGN(offset + size - 1) >> PAGE_SHIFT;
+
+ idx = FIX_BTMAP_BEGIN;
+ while (nrpages > 0) {
+ clear_fixmap(idx);
+ --idx;
+ --nrpages;
+ }
+}
+
+#endif /* CONFIG_XEN_PHYSDEV_ACCESS */
+
+/* These hacky macros avoid phys->machine translations. */
+#define __direct_pte(x) ((pte_t) { (x) } )
+#define __direct_mk_pte(page_nr,pgprot) \
+ __direct_pte(((page_nr) << PAGE_SHIFT) | pgprot_val(pgprot))
+#define direct_mk_pte_phys(physpage, pgprot) \
+ __direct_mk_pte((physpage) >> PAGE_SHIFT, pgprot)
+
+static inline void direct_remap_area_pte(pte_t *pte,
+ unsigned long address,
+ unsigned long size,
+ mmu_update_t **v)
+{
+ unsigned long end;
+
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ if (address >= end)
+ BUG();
+
+ do {
+ (*v)->ptr = virt_to_machine(pte);
+ (*v)++;
+ address += PAGE_SIZE;
+ pte++;
+ } while (address && (address < end));
+}
+
+static inline int direct_remap_area_pmd(struct mm_struct *mm,
+ pmd_t *pmd,
+ unsigned long address,
+ unsigned long size,
+ mmu_update_t **v)
+{
+ unsigned long end;
+
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ if (address >= end)
+ BUG();
+ do {
+ pte_t *pte = (mm == &init_mm) ?
+ pte_alloc_kernel(mm, pmd, address) :
+ pte_alloc_map(mm, pmd, address);
+ if (!pte)
+ return -ENOMEM;
+ direct_remap_area_pte(pte, address, end - address, v);
+ pte_unmap(pte);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+ return 0;
+}
+
+int __direct_remap_area_pages(struct mm_struct *mm,
+ unsigned long address,
+ unsigned long size,
+ mmu_update_t *v)
+{
+ pgd_t * dir;
+ unsigned long end = address + size;
+ int error;
+
+ dir = pgd_offset(mm, address);
+ if (address >= end)
+ BUG();
+ spin_lock(&mm->page_table_lock);
+ do {
+ pud_t *pud;
+ pmd_t *pmd;
+
+ error = -ENOMEM;
+ pud = pud_alloc(mm, dir, address);
+ if (!pud)
+ break;
+ pmd = pmd_alloc(mm, pud, address);
+ if (!pmd)
+ break;
+ error = 0;
+ direct_remap_area_pmd(mm, pmd, address, end - address, &v);
+ address = (address + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+
+ } while (address && (address < end));
+ spin_unlock(&mm->page_table_lock);
+ return error;
+}
+
+
+int direct_remap_area_pages(struct mm_struct *mm,
+ unsigned long address,
+ unsigned long machine_addr,
+ unsigned long size,
+ pgprot_t prot,
+ domid_t domid)
+{
+ int i;
+ unsigned long start_address;
+#define MAX_DIRECTMAP_MMU_QUEUE 130
+ mmu_update_t u[MAX_DIRECTMAP_MMU_QUEUE], *v = u;
+
+ start_address = address;
+
+ flush_cache_all();
+
+ for (i = 0; i < size; i += PAGE_SIZE) {
+ if ((v - u) == MAX_DIRECTMAP_MMU_QUEUE) {
+ /* Fill in the PTE pointers. */
+ __direct_remap_area_pages(mm,
+ start_address,
+ address-start_address,
+ u);
+
+ if (HYPERVISOR_mmu_update(u, v - u, NULL, domid) < 0)
+ return -EFAULT;
+ v = u;
+ start_address = address;
+ }
+
+ /*
+ * Fill in the machine address: PTE ptr is done later by
+ * __direct_remap_area_pages().
+ */
+ v->val = (machine_addr & PAGE_MASK) | pgprot_val(prot);
+
+ machine_addr += PAGE_SIZE;
+ address += PAGE_SIZE;
+ v++;
+ }
+
+ if (v != u) {
+ /* get the ptep's filled in */
+ __direct_remap_area_pages(mm,
+ start_address,
+ address-start_address,
+ u);
+ if (unlikely(HYPERVISOR_mmu_update(u, v - u, NULL, domid) < 0))
+ return -EFAULT;
+ }
+
+ flush_tlb_all();
+
+ return 0;
+}
+
+EXPORT_SYMBOL(direct_remap_area_pages);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blktap/blktap.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blktap/blktap.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,253 @@
+/*
+ * blktap.h
+ *
+ * Interfaces for the Xen block tap driver.
+ *
+ * (c) 2004, Andrew Warfield, University of Cambridge
+ *
+ */
+
+#ifndef __BLKTAP_H__
+#define __BLKTAP_H__
+
+#include <linux/version.h>
+#include <linux/blkdev.h>
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <asm-xen/ctrl_if.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <asm/io.h>
+#include <asm/setup.h>
+#include <asm/pgalloc.h>
+#include <asm-xen/hypervisor.h>
+#include <asm-xen/xen-public/io/blkif.h>
+#include <asm-xen/xen-public/io/ring.h>
+
+/* Used to signal to the backend that this is a tap domain. */
+#define BLKTAP_COOKIE 0xbeadfeed
+
+/* -------[ debug / pretty printing ]--------------------------------- */
+
+#define PRINTK(_f, _a...) printk(KERN_ALERT "(file=%s, line=%d) " _f, \
+ __FILE__ , __LINE__ , ## _a )
+#if 0
+#define DPRINTK(_f, _a...) printk(KERN_ALERT "(file=%s, line=%d) " _f, \
+ __FILE__ , __LINE__ , ## _a )
+#else
+#define DPRINTK(_f, _a...) ((void)0)
+#endif
+
+#if 1
+#define ASSERT(_p) \
+ if ( !(_p) ) { printk("Assertion '%s' failed, line %d, file %s", #_p , \
+ __LINE__, __FILE__); *(int*)0=0; }
+#else
+#define ASSERT(_p) ((void)0)
+#endif
+
+#define WPRINTK(fmt, args...) printk(KERN_WARNING "blk_tap: " fmt, ##args)
+
+
+/* -------[ state descriptors ]--------------------------------------- */
+
+#define BLKIF_STATE_CLOSED 0
+#define BLKIF_STATE_DISCONNECTED 1
+#define BLKIF_STATE_CONNECTED 2
+
+/* -------[ connection tracking ]------------------------------------- */
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+#define VMALLOC_VMADDR(x) ((unsigned long)(x))
+#endif
+
+extern spinlock_t blkif_io_lock;
+
+typedef struct blkif_st {
+ /* Unique identifier for this interface. */
+ domid_t domid;
+ unsigned int handle;
+ /* Physical parameters of the comms window. */
+ unsigned long shmem_frame;
+ unsigned int evtchn;
+ int irq;
+ /* Comms information. */
+ blkif_back_ring_t blk_ring;
+
+ enum { DISCONNECTED, DISCONNECTING, CONNECTED } status;
+ /*
+ * DISCONNECT response is deferred until pending requests are ack'ed.
+ * We therefore need to store the id from the original request.
+ */
+ u8 disconnect_rspid;
+ struct blkif_st *hash_next;
+ struct list_head blkdev_list;
+ spinlock_t blk_ring_lock;
+ atomic_t refcnt;
+ struct work_struct work;
+} blkif_t;
+
+blkif_t *blkif_find_by_handle(domid_t domid, unsigned int handle);
+void blkif_disconnect_complete(blkif_t *blkif);
+#define blkif_get(_b) (atomic_inc(&(_b)->refcnt))
+#define blkif_put(_b) \
+ do { \
+ if ( atomic_dec_and_test(&(_b)->refcnt) ) \
+ blkif_disconnect_complete(_b); \
+ } while (0)
+
+
+/* -------[ active request tracking ]--------------------------------- */
+
+typedef struct {
+ blkif_t *blkif;
+ unsigned long id;
+ int nr_pages;
+ unsigned long mach_fas[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ unsigned long virt_fas[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ int next_free;
+} active_req_t;
+
+typedef unsigned int ACTIVE_RING_IDX;
+
+active_req_t *lookup_active_req(ACTIVE_RING_IDX idx);
+
+extern inline unsigned int ID_TO_IDX(unsigned long id)
+{
+ return ( id & 0x0000ffff );
+}
+
+extern inline domid_t ID_TO_DOM(unsigned long id)
+{
+ return (id >> 16);
+}
+
+void active_reqs_init(void);
+
+/* -------[ interposition -> character device interface ]------------- */
+
+/* /dev/xen/blktap resides at device number major=10, minor=200 */
+#define BLKTAP_MINOR 202
+
+/* size of the extra VMA area to map in attached pages. */
+#define BLKTAP_VMA_PAGES BLKIF_RING_SIZE
+
+/* blktap IOCTLs: */
+#define BLKTAP_IOCTL_KICK_FE 1
+#define BLKTAP_IOCTL_KICK_BE 2
+#define BLKTAP_IOCTL_SETMODE 3
+#define BLKTAP_IOCTL_PRINT_IDXS 100
+
+/* blktap switching modes: (Set with BLKTAP_IOCTL_SETMODE) */
+#define BLKTAP_MODE_PASSTHROUGH 0x00000000 /* default */
+#define BLKTAP_MODE_INTERCEPT_FE 0x00000001
+#define BLKTAP_MODE_INTERCEPT_BE 0x00000002
+#define BLKTAP_MODE_COPY_FE 0x00000004
+#define BLKTAP_MODE_COPY_BE 0x00000008
+#define BLKTAP_MODE_COPY_FE_PAGES 0x00000010
+#define BLKTAP_MODE_COPY_BE_PAGES 0x00000020
+
+#define BLKTAP_MODE_INTERPOSE \
+ (BLKTAP_MODE_INTERCEPT_FE | BLKTAP_MODE_INTERCEPT_BE)
+
+#define BLKTAP_MODE_COPY_BOTH \
+ (BLKTAP_MODE_COPY_FE | BLKTAP_MODE_COPY_BE)
+
+#define BLKTAP_MODE_COPY_BOTH_PAGES \
+ (BLKTAP_MODE_COPY_FE_PAGES | BLKTAP_MODE_COPY_BE_PAGES)
+
+static inline int BLKTAP_MODE_VALID(unsigned long arg)
+{
+ return (
+ ( arg == BLKTAP_MODE_PASSTHROUGH ) ||
+ ( arg == BLKTAP_MODE_INTERCEPT_FE ) ||
+ ( arg == BLKTAP_MODE_INTERCEPT_BE ) ||
+ ( arg == BLKTAP_MODE_INTERPOSE ) ||
+ ( (arg & ~BLKTAP_MODE_COPY_FE_PAGES) == BLKTAP_MODE_COPY_FE ) ||
+ ( (arg & ~BLKTAP_MODE_COPY_BE_PAGES) == BLKTAP_MODE_COPY_BE ) ||
+ ( (arg & ~BLKTAP_MODE_COPY_BOTH_PAGES) == BLKTAP_MODE_COPY_BOTH )
+ );
+}
+
+
+
+/* -------[ Mappings to User VMA ]------------------------------------ */
+#define MAX_PENDING_REQS 64
+#define BATCH_PER_DOMAIN 16
+extern struct vm_area_struct *blktap_vma;
+
+/* The following are from blkback.c and should probably be put in a
+ * header and included from there.
+ * The mmap area described here is where attached data pages eill be mapped.
+ */
+
+extern unsigned long mmap_vstart;
+#define MMAP_PAGES_PER_REQUEST \
+ (BLKIF_MAX_SEGMENTS_PER_REQUEST + 1)
+#define MMAP_PAGES \
+ (MAX_PENDING_REQS * MMAP_PAGES_PER_REQUEST)
+#define MMAP_VADDR(_req,_seg) \
+ (mmap_vstart + \
+ ((_req) * MMAP_PAGES_PER_REQUEST * PAGE_SIZE) + \
+ ((_seg) * PAGE_SIZE))
+
+/* immediately before the mmap area, we have a bunch of pages reserved
+ * for shared memory rings.
+ */
+
+#define RING_PAGES 3 /* Ctrl, Front, and Back */
+extern unsigned long rings_vstart;
+
+
+/* -------[ Here be globals ]----------------------------------------- */
+extern unsigned long blktap_mode;
+
+/* Connection to a single backend domain. */
+extern blkif_front_ring_t blktap_be_ring;
+extern unsigned int blktap_be_evtchn;
+extern unsigned int blktap_be_state;
+
+/* User ring status. */
+extern unsigned long blktap_ring_ok;
+
+/* -------[ ...and function prototypes. ]----------------------------- */
+
+/* init function for character device interface. */
+int blktap_init(void);
+
+/* init function for the blkif cache. */
+void __init blkif_interface_init(void);
+void __init blkdev_schedule_init(void);
+void blkif_deschedule(blkif_t *blkif);
+
+/* interfaces to the char driver, passing messages to and from apps. */
+void blktap_kick_user(void);
+
+/* user ring access functions: */
+int blktap_write_fe_ring(blkif_request_t *req);
+int blktap_write_be_ring(blkif_response_t *rsp);
+int blktap_write_ctrl_ring(ctrl_msg_t *msg);
+
+/* fe/be ring access functions: */
+int write_resp_to_fe_ring(blkif_t *blkif, blkif_response_t *rsp);
+int write_req_to_be_ring(blkif_request_t *req);
+
+/* event notification functions */
+void kick_fe_domain(blkif_t *blkif);
+void kick_be_domain(void);
+
+/* Interrupt handlers. */
+irqreturn_t blkif_ptbe_int(int irq, void *dev_id,
+ struct pt_regs *ptregs);
+irqreturn_t blkif_ptfe_int(int irq, void *dev_id, struct pt_regs *regs);
+
+/* Control message receiver. */
+extern void blkif_ctrlif_rx(ctrl_msg_t *msg, unsigned long id);
+
+/* debug */
+void print_fe_ring_idxs(void);
+void print_be_ring_idxs(void);
+
+#define __BLKINT_H__
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blktap/blktap.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blktap/blktap.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,87 @@
+/******************************************************************************
+ * blktap.c
+ *
+ * XenLinux virtual block-device tap.
+ *
+ * Copyright (c) 2004, Andrew Warfield
+ *
+ * Based on the original split block driver:
+ * Copyright (c) 2003-2004, Keir Fraser & Steve Hand
+ * Modifications by Mark A. Williamson are (c) Intel Research Cambridge
+ * Copyright (c) 2004, Christian Limpach
+ *
+ * Note that unlike the split block driver code, this driver has been developed
+ * strictly for Linux 2.6
+ */
+
+#include "blktap.h"
+
+int __init xlblktap_init(void)
+{
+ ctrl_msg_t cmsg;
+ blkif_fe_driver_status_t fe_st;
+ blkif_be_driver_status_t be_st;
+
+ printk(KERN_INFO "Initialising Xen block tap device\n");
+
+ DPRINTK(" tap - Backend connection init:\n");
+
+
+ (void)ctrl_if_register_receiver(CMSG_BLKIF_FE, blkif_ctrlif_rx,
+ CALLBACK_IN_BLOCKING_CONTEXT);
+
+ /* Send a driver-UP notification to the domain controller. */
+ cmsg.type = CMSG_BLKIF_FE;
+ cmsg.subtype = CMSG_BLKIF_FE_DRIVER_STATUS;
+ cmsg.length = sizeof(blkif_fe_driver_status_t);
+ fe_st.status = BLKIF_DRIVER_STATUS_UP;
+ memcpy(cmsg.msg, &fe_st, sizeof(fe_st));
+ ctrl_if_send_message_block(&cmsg, NULL, 0, TASK_UNINTERRUPTIBLE);
+
+ DPRINTK(" tap - Frontend connection init:\n");
+
+ active_reqs_init();
+ blkif_interface_init();
+ blkdev_schedule_init();
+
+ (void)ctrl_if_register_receiver(CMSG_BLKIF_BE, blkif_ctrlif_rx,
+ CALLBACK_IN_BLOCKING_CONTEXT);
+
+ /* Send a driver-UP notification to the domain controller. */
+ cmsg.type = CMSG_BLKIF_BE;
+ cmsg.subtype = CMSG_BLKIF_BE_DRIVER_STATUS;
+ cmsg.length = sizeof(blkif_be_driver_status_t);
+ be_st.status = BLKIF_DRIVER_STATUS_UP;
+ memcpy(cmsg.msg, &be_st, sizeof(be_st));
+ ctrl_if_send_message_block(&cmsg, NULL, 0, TASK_UNINTERRUPTIBLE);
+
+ DPRINTK(" tap - Userland channel init:\n");
+
+ blktap_init();
+
+ DPRINTK("Blkif tap device initialized.\n");
+
+ return 0;
+}
+
+#if 0 /* tap doesn't handle suspend/resume */
+void blkdev_suspend(void)
+{
+}
+
+void blkdev_resume(void)
+{
+ ctrl_msg_t cmsg;
+ blkif_fe_driver_status_t st;
+
+ /* Send a driver-UP notification to the domain controller. */
+ cmsg.type = CMSG_BLKIF_FE;
+ cmsg.subtype = CMSG_BLKIF_FE_DRIVER_STATUS;
+ cmsg.length = sizeof(blkif_fe_driver_status_t);
+ st.status = BLKIF_DRIVER_STATUS_UP;
+ memcpy(cmsg.msg, &st, sizeof(st));
+ ctrl_if_send_message_block(&cmsg, NULL, 0, TASK_UNINTERRUPTIBLE);
+}
+#endif
+
+__initcall(xlblktap_init);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/mach-default/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/mach-default/Makefile Fri Jul
15 13:39:50 2005
@@ -0,0 +1,12 @@
+#
+# Makefile for the linux kernel.
+#
+
+c-obj-y := topology.o
+
+$(patsubst %.o,$(obj)/%.c,$(c-obj-y)):
+ @ln -fsn $(srctree)/arch/i386/mach-default/$(notdir $@) $@
+
+obj-y += $(c-obj-y)
+
+clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-))
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/kernel/smp.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/kernel/smp.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,16 @@
+/* Copyright (C) 2004, Christian Limpach */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/threads.h>
+
+/*
+ * the frequency of the profiling timer can be changed
+ * by writing a multiplier value into /proc/profile.
+ */
+int setup_profiling_timer(unsigned int multiplier)
+{
+ printk("setup_profiling_timer\n");
+
+ return 0;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/pgalloc.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/pgalloc.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,280 @@
+#ifndef _I386_PGALLOC_H
+#define _I386_PGALLOC_H
+
+#include <linux/config.h>
+#include <asm/processor.h>
+#include <asm/fixmap.h>
+#include <asm/hypervisor.h>
+#include <linux/threads.h>
+
+/*
+ * Quick lists are aligned so that least significant bits of array pointer
+ * are all zero when list is empty, and all one when list is full.
+ */
+#define QUICKLIST_ENTRIES 256
+#define QUICKLIST_EMPTY(_l) !((unsigned long)(_l) & ((QUICKLIST_ENTRIES*4)-1))
+#define QUICKLIST_FULL(_l) QUICKLIST_EMPTY((_l)+1)
+#define pgd_quicklist (current_cpu_data.pgd_quick)
+#define pmd_quicklist (current_cpu_data.pmd_quick)
+#define pte_quicklist (current_cpu_data.pte_quick)
+#define pgtable_cache_size (current_cpu_data.pgtable_cache_sz)
+
+#define pmd_populate(mm, pmd, pte) \
+ do { \
+ set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte))); \
+ } while ( 0 )
+
+/*
+ * Allocate and free page tables.
+ */
+
+#if defined (CONFIG_X86_PAE)
+
+#error "no PAE support as yet"
+
+/*
+ * We can't include <linux/slab.h> here, thus these uglinesses.
+ */
+struct kmem_cache_s;
+
+extern struct kmem_cache_s *pae_pgd_cachep;
+extern void *kmem_cache_alloc(struct kmem_cache_s *, int);
+extern void kmem_cache_free(struct kmem_cache_s *, void *);
+
+
+static inline pgd_t *get_pgd_slow(void)
+{
+ int i;
+ pgd_t *pgd = kmem_cache_alloc(pae_pgd_cachep, GFP_KERNEL);
+
+ if (pgd) {
+ for (i = 0; i < USER_PTRS_PER_PGD; i++) {
+ unsigned long pmd = __get_free_page(GFP_KERNEL);
+ if (!pmd)
+ goto out_oom;
+ clear_page(pmd);
+ set_pgd(pgd + i, __pgd(1 + __pa(pmd)));
+ }
+ memcpy(pgd + USER_PTRS_PER_PGD,
+ init_mm.pgd + USER_PTRS_PER_PGD,
+ (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+ }
+ return pgd;
+out_oom:
+ for (i--; i >= 0; i--)
+ free_page((unsigned long)__va(pgd_val(pgd[i])-1));
+ kmem_cache_free(pae_pgd_cachep, pgd);
+ return NULL;
+}
+
+#else
+
+static inline pgd_t *get_pgd_slow(void)
+{
+ pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL);
+
+ if (pgd) {
+ memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
+ memcpy(pgd + USER_PTRS_PER_PGD,
+ init_mm.pgd + USER_PTRS_PER_PGD,
+ (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+ __make_page_readonly(pgd);
+ xen_pgd_pin(__pa(pgd));
+ }
+ return pgd;
+}
+
+#endif /* CONFIG_X86_PAE */
+
+static inline pgd_t *get_pgd_fast(void)
+{
+ unsigned long ret;
+
+ if ( !QUICKLIST_EMPTY(pgd_quicklist) ) {
+ ret = *(--pgd_quicklist);
+ pgtable_cache_size--;
+
+ } else
+ ret = (unsigned long)get_pgd_slow();
+ return (pgd_t *)ret;
+}
+
+static inline void free_pgd_slow(pgd_t *pgd)
+{
+#if defined(CONFIG_X86_PAE)
+#error
+ int i;
+
+ for (i = 0; i < USER_PTRS_PER_PGD; i++)
+ free_page((unsigned long)__va(pgd_val(pgd[i])-1));
+ kmem_cache_free(pae_pgd_cachep, pgd);
+#else
+ xen_pgd_unpin(__pa(pgd));
+ __make_page_writable(pgd);
+ free_page((unsigned long)pgd);
+#endif
+}
+
+static inline void free_pgd_fast(pgd_t *pgd)
+{
+ if ( !QUICKLIST_FULL(pgd_quicklist) ) {
+ *(pgd_quicklist++) = (unsigned long)pgd;
+ pgtable_cache_size++;
+ } else
+ free_pgd_slow(pgd);
+}
+
+static inline pte_t *pte_alloc_one(struct mm_struct *mm, unsigned long address)
+{
+ pte_t *pte;
+
+ pte = (pte_t *) __get_free_page(GFP_KERNEL);
+ if (pte)
+ {
+ clear_page(pte);
+ __make_page_readonly(pte);
+ xen_pte_pin(__pa(pte));
+ }
+ return pte;
+
+}
+
+static inline pte_t *pte_alloc_one_fast(struct mm_struct *mm,
+ unsigned long address)
+{
+ unsigned long ret = 0;
+ if ( !QUICKLIST_EMPTY(pte_quicklist) ) {
+ ret = *(--pte_quicklist);
+ pgtable_cache_size--;
+ }
+ return (pte_t *)ret;
+}
+
+static __inline__ void pte_free_slow(pte_t *pte)
+{
+ xen_pte_unpin(__pa(pte));
+ __make_page_writable(pte);
+ free_page((unsigned long)pte);
+}
+
+static inline void pte_free_fast(pte_t *pte)
+{
+ if ( !QUICKLIST_FULL(pte_quicklist) ) {
+ *(pte_quicklist++) = (unsigned long)pte;
+ pgtable_cache_size++;
+ } else
+ pte_free_slow(pte);
+}
+
+#define pte_free(pte) pte_free_fast(pte)
+#define pgd_free(pgd) free_pgd_fast(pgd)
+#define pgd_alloc(mm) get_pgd_fast()
+
+/*
+ * allocating and freeing a pmd is trivial: the 1-entry pmd is
+ * inside the pgd, so has no extra memory associated with it.
+ * (In the PAE case we free the pmds as part of the pgd.)
+ */
+
+#define pmd_alloc_one_fast(mm, addr) ({ BUG(); ((pmd_t *)1); })
+#define pmd_alloc_one(mm, addr) ({ BUG(); ((pmd_t *)2); })
+#define pmd_free_slow(x) do { } while (0)
+#define pmd_free_fast(x) do { } while (0)
+#define pmd_free(x) do { } while (0)
+#define pgd_populate(mm, pmd, pte) BUG()
+
+extern int do_check_pgt_cache(int, int);
+
+/*
+ * TLB flushing:
+ *
+ * - flush_tlb() flushes the current mm struct TLBs
+ * - flush_tlb_all() flushes all processes TLBs
+ * - flush_tlb_mm(mm) flushes the specified mm context TLB's
+ * - flush_tlb_page(vma, vmaddr) flushes one page
+ * - flush_tlb_range(mm, start, end) flushes a range of pages
+ * - flush_tlb_pgtables(mm, start, end) flushes a range of page tables
+ *
+ * ..but the i386 has somewhat limited tlb flushing capabilities,
+ * and page-granular flushes are available only on i486 and up.
+ */
+
+#ifndef CONFIG_SMP
+
+#define flush_tlb() __flush_tlb()
+#define flush_tlb_all() __flush_tlb_all()
+#define local_flush_tlb() __flush_tlb()
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+ if (mm == current->active_mm) xen_tlb_flush();
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+ unsigned long addr)
+{
+ if (vma->vm_mm == current->active_mm) xen_invlpg(addr);
+}
+
+static inline void flush_tlb_range(struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ if (mm == current->active_mm) xen_tlb_flush();
+}
+
+#else
+#error no kernel SMP support yet...
+#include <asm/smp.h>
+
+#define local_flush_tlb() \
+ __flush_tlb()
+
+extern void flush_tlb_all(void);
+extern void flush_tlb_current_task(void);
+extern void flush_tlb_mm(struct mm_struct *);
+extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
+
+#define flush_tlb() flush_tlb_current_task()
+
+static inline void flush_tlb_range(struct mm_struct * mm, unsigned long start,
unsigned long end)
+{
+ flush_tlb_mm(mm);
+}
+
+#define TLBSTATE_OK 1
+#define TLBSTATE_LAZY 2
+
+struct tlb_state
+{
+ struct mm_struct *active_mm;
+ int state;
+} ____cacheline_aligned;
+extern struct tlb_state cpu_tlbstate[NR_CPUS];
+
+#endif /* CONFIG_SMP */
+
+static inline void flush_tlb_pgtables(struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ /* i386 does not keep any page table caches in TLB */
+}
+
+/*
+ * NB. The 'domid' field should be zero if mapping I/O space (non RAM).
+ * Otherwise it identifies the owner of the memory that is being mapped.
+ */
+extern int direct_remap_area_pages(struct mm_struct *mm,
+ unsigned long address,
+ unsigned long machine_addr,
+ unsigned long size,
+ pgprot_t prot,
+ domid_t domid);
+
+extern int __direct_remap_area_pages(struct mm_struct *mm,
+ unsigned long address,
+ unsigned long size,
+ mmu_update_t *v);
+
+
+
+#endif /* _I386_PGALLOC_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/drivers/netif/backend/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/drivers/netif/backend/Makefile Fri Jul
15 13:39:50 2005
@@ -0,0 +1,4 @@
+O_TARGET := drv.o
+export-objs := interface.o
+obj-y := main.o control.o interface.o
+include $(TOPDIR)/Rules.make
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/page.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/page.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,229 @@
+#ifndef _X86_64_PAGE_H
+#define _X86_64_PAGE_H
+
+#include <linux/config.h>
+/* #include <linux/string.h> */
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+#endif
+#include <asm-xen/xen-public/xen.h>
+#include <asm-xen/foreign_page.h>
+
+#define arch_free_page(_page,_order) \
+({ int foreign = PageForeign(_page); \
+ if (foreign) \
+ (PageForeignDestructor(_page))(_page); \
+ foreign; \
+})
+#define HAVE_ARCH_FREE_PAGE
+
+#ifdef CONFIG_XEN_SCRUB_PAGES
+#define scrub_pages(_p,_n) memset((void *)(_p), 0, (_n) << PAGE_SHIFT)
+#else
+#define scrub_pages(_p,_n) ((void)0)
+#endif
+
+/* PAGE_SHIFT determines the page size */
+#define PAGE_SHIFT 12
+#ifdef __ASSEMBLY__
+#define PAGE_SIZE (0x1 << PAGE_SHIFT)
+#else
+#define PAGE_SIZE (1UL << PAGE_SHIFT)
+#endif
+#define PAGE_MASK (~(PAGE_SIZE-1))
+#define PHYSICAL_PAGE_MASK (~(PAGE_SIZE-1) & (__PHYSICAL_MASK <<
PAGE_SHIFT))
+
+#define THREAD_ORDER 1
+#ifdef __ASSEMBLY__
+#define THREAD_SIZE (1 << (PAGE_SHIFT + THREAD_ORDER))
+#else
+#define THREAD_SIZE (1UL << (PAGE_SHIFT + THREAD_ORDER))
+#endif
+#define CURRENT_MASK (~(THREAD_SIZE-1))
+
+#define LARGE_PAGE_MASK (~(LARGE_PAGE_SIZE-1))
+#define LARGE_PAGE_SIZE (1UL << PMD_SHIFT)
+
+#define HPAGE_SHIFT PMD_SHIFT
+#define HPAGE_SIZE ((1UL) << HPAGE_SHIFT)
+#define HPAGE_MASK (~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT)
+
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+
+void clear_page(void *);
+void copy_page(void *, void *);
+
+#define clear_user_page(page, vaddr, pg) clear_page(page)
+#define copy_user_page(to, from, vaddr, pg) copy_page(to, from)
+
+#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER |
__GFP_ZERO, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+
+/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
+extern u32 *phys_to_machine_mapping;
+#define pfn_to_mfn(_pfn) ((unsigned long) phys_to_machine_mapping[(unsigned
int)(_pfn)])
+#define mfn_to_pfn(_mfn) ((unsigned long) machine_to_phys_mapping[(unsigned
int)(_mfn)])
+static inline unsigned long phys_to_machine(unsigned long phys)
+{
+ unsigned long machine = pfn_to_mfn(phys >> PAGE_SHIFT);
+ machine = (machine << PAGE_SHIFT) | (phys & ~PAGE_MASK);
+ return machine;
+}
+
+static inline unsigned long machine_to_phys(unsigned long machine)
+{
+ unsigned long phys = mfn_to_pfn(machine >> PAGE_SHIFT);
+ phys = (phys << PAGE_SHIFT) | (machine & ~PAGE_MASK);
+ return phys;
+}
+
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef struct { unsigned long pte; } pte_t;
+typedef struct { unsigned long pmd; } pmd_t;
+typedef struct { unsigned long pud; } pud_t;
+typedef struct { unsigned long pgd; } pgd_t;
+#define PTE_MASK PHYSICAL_PAGE_MASK
+
+typedef struct { unsigned long pgprot; } pgprot_t;
+
+#define pte_val(x) (((x).pte & 1) ? machine_to_phys((x).pte) : \
+ (x).pte)
+#define pte_val_ma(x) ((x).pte)
+
+static inline unsigned long pmd_val(pmd_t x)
+{
+ unsigned long ret = x.pmd;
+ if (ret) ret = machine_to_phys(ret);
+ return ret;
+}
+
+static inline unsigned long pud_val(pud_t x)
+{
+ unsigned long ret = x.pud;
+ if (ret) ret = machine_to_phys(ret);
+ return ret;
+}
+
+static inline unsigned long pgd_val(pgd_t x)
+{
+ unsigned long ret = x.pgd;
+ if (ret) ret = machine_to_phys(ret);
+ return ret;
+}
+
+#define pgprot_val(x) ((x).pgprot)
+
+#define __pte_ma(x) ((pte_t) { (x) } )
+
+static inline pte_t __pte(unsigned long x)
+{
+ if (x & 1) x = phys_to_machine(x);
+ return ((pte_t) { (x) });
+}
+
+static inline pmd_t __pmd(unsigned long x)
+{
+ if ((x & 1)) x = phys_to_machine(x);
+ return ((pmd_t) { (x) });
+}
+
+static inline pud_t __pud(unsigned long x)
+{
+ if ((x & 1)) x = phys_to_machine(x);
+ return ((pud_t) { (x) });
+}
+
+static inline pgd_t __pgd(unsigned long x)
+{
+ if ((x & 1)) x = phys_to_machine(x);
+ return ((pgd_t) { (x) });
+}
+
+#define __pgprot(x) ((pgprot_t) { (x) } )
+
+extern unsigned long vm_stack_flags, vm_stack_flags32;
+extern unsigned long vm_data_default_flags, vm_data_default_flags32;
+extern unsigned long vm_force_exec32;
+
+#define __START_KERNEL 0xffffffff80100000UL
+#define __START_KERNEL_map 0xffffffff80000000UL
+#define __PAGE_OFFSET 0xffff880000000000UL
+
+#else
+#define __START_KERNEL 0xffffffff80100000
+#define __START_KERNEL_map 0xffffffff80000000
+#define __PAGE_OFFSET 0xffff880000000000
+#endif /* !__ASSEMBLY__ */
+
+/* to align the pointer to the (next) page boundary */
+#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK)
+
+/* See Documentation/x86_64/mm.txt for a description of the memory map. */
+#define __PHYSICAL_MASK_SHIFT 46
+#define __PHYSICAL_MASK ((1UL << __PHYSICAL_MASK_SHIFT) - 1)
+#define __VIRTUAL_MASK_SHIFT 48
+#define __VIRTUAL_MASK ((1UL << __VIRTUAL_MASK_SHIFT) - 1)
+
+#define KERNEL_TEXT_SIZE (40UL*1024*1024)
+#define KERNEL_TEXT_START 0xffffffff80000000UL
+
+#ifndef __ASSEMBLY__
+
+#include <asm/bug.h>
+
+/* Pure 2^n version of get_order */
+extern __inline__ int get_order(unsigned long size)
+{
+ int order;
+
+ size = (size-1) >> (PAGE_SHIFT-1);
+ order = -1;
+ do {
+ size >>= 1;
+ order++;
+ } while (size);
+ return order;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#define PAGE_OFFSET ((unsigned long)__PAGE_OFFSET)
+
+/* Note: __pa(&symbol_visible_to_c) should be always replaced with __pa_symbol.
+ Otherwise you risk miscompilation. */
+#define __pa(x) (((unsigned
long)(x)>=__START_KERNEL_map)?(unsigned long)(x) - (unsigned
long)__START_KERNEL_map:(unsigned long)(x) - PAGE_OFFSET)
+/* __pa_symbol should be used for C visible symbols.
+ This seems to be the official gcc blessed way to do such arithmetic. */
+#define __pa_symbol(x) \
+ ({unsigned long v; \
+ asm("" : "=r" (v) : "0" (x)); \
+ __pa(v); })
+
+#define __va(x) ((void *)((unsigned
long)(x)+PAGE_OFFSET))
+#ifndef CONFIG_DISCONTIGMEM
+#define pfn_to_page(pfn) (mem_map + (pfn))
+#define page_to_pfn(page) ((unsigned long)((page) - mem_map))
+#define pfn_valid(pfn) ((pfn) < max_mapnr)
+#endif
+
+#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
+#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
+
+/* VIRT <-> MACHINE conversion */
+#define virt_to_machine(_a) (phys_to_machine(__pa(_a)))
+#define machine_to_virt(_m) (__va(machine_to_phys(_m)))
+
+#define VM_DATA_DEFAULT_FLAGS \
+ (((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
+ VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#define __HAVE_ARCH_GATE_AREA 1
+
+#endif /* __KERNEL__ */
+
+#endif /* _X86_64_PAGE_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/mm/init.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/mm/init.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,795 @@
+/*
+ * linux/arch/i386/mm/init.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/swap.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/bootmem.h>
+#include <linux/slab.h>
+#include <linux/proc_fs.h>
+#include <linux/efi.h>
+
+#include <asm/processor.h>
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/dma.h>
+#include <asm/fixmap.h>
+#include <asm/e820.h>
+#include <asm/apic.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/sections.h>
+#include <asm-xen/hypervisor.h>
+
+unsigned int __VMALLOC_RESERVE = 128 << 20;
+
+DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
+unsigned long highstart_pfn, highend_pfn;
+
+static int noinline do_test_wp_bit(void);
+
+/*
+ * Creates a middle page table and puts a pointer to it in the
+ * given global directory entry. This only returns the gd entry
+ * in non-PAE compilation mode, since the middle layer is folded.
+ */
+static pmd_t * __init one_md_table_init(pgd_t *pgd)
+{
+ pud_t *pud;
+ pmd_t *pmd_table;
+
+#ifdef CONFIG_X86_PAE
+ pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE);
+ set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
+ pud = pud_offset(pgd, 0);
+ if (pmd_table != pmd_offset(pud, 0))
+ BUG();
+#else
+ pud = pud_offset(pgd, 0);
+ pmd_table = pmd_offset(pud, 0);
+#endif
+
+ return pmd_table;
+}
+
+/*
+ * Create a page table and place a pointer to it in a middle page
+ * directory entry.
+ */
+static pte_t * __init one_page_table_init(pmd_t *pmd)
+{
+ if (pmd_none(*pmd)) {
+ pte_t *page_table = (pte_t *)
alloc_bootmem_low_pages(PAGE_SIZE);
+ make_page_readonly(page_table);
+ set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
+ if (page_table != pte_offset_kernel(pmd, 0))
+ BUG();
+
+ return page_table;
+ }
+
+ return pte_offset_kernel(pmd, 0);
+}
+
+/*
+ * This function initializes a certain range of kernel virtual memory
+ * with new bootmem page tables, everywhere page tables are missing in
+ * the given range.
+ */
+
+/*
+ * NOTE: The pagetables are allocated contiguous on the physical space
+ * so we can cache the place of the first one and move around without
+ * checking the pgd every time.
+ */
+static void __init page_table_range_init (unsigned long start, unsigned long
end, pgd_t *pgd_base)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ int pgd_idx, pmd_idx;
+ unsigned long vaddr;
+
+ vaddr = start;
+ pgd_idx = pgd_index(vaddr);
+ pmd_idx = pmd_index(vaddr);
+ pgd = pgd_base + pgd_idx;
+
+ for ( ; (pgd_idx < PTRS_PER_PGD_NO_HV) && (vaddr != end); pgd++,
pgd_idx++) {
+ if (pgd_none(*pgd))
+ one_md_table_init(pgd);
+ pud = pud_offset(pgd, vaddr);
+ pmd = pmd_offset(pud, vaddr);
+ for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end); pmd++,
pmd_idx++) {
+ if (pmd_none(*pmd))
+ one_page_table_init(pmd);
+
+ vaddr += PMD_SIZE;
+ }
+ pmd_idx = 0;
+ }
+}
+
+static inline int is_kernel_text(unsigned long addr)
+{
+ if (addr >= PAGE_OFFSET && addr <= (unsigned long)__init_end)
+ return 1;
+ return 0;
+}
+
+/*
+ * This maps the physical memory to kernel virtual address space, a total
+ * of max_low_pfn pages, by creating page tables starting from address
+ * PAGE_OFFSET.
+ */
+static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
+{
+ unsigned long pfn;
+ pgd_t *pgd;
+ pmd_t *pmd;
+ pte_t *pte;
+ int pgd_idx, pmd_idx, pte_ofs;
+
+ unsigned long max_ram_pfn = xen_start_info.nr_pages;
+ if (max_ram_pfn > max_low_pfn)
+ max_ram_pfn = max_low_pfn;
+
+ pgd_idx = pgd_index(PAGE_OFFSET);
+ pgd = pgd_base + pgd_idx;
+ pfn = 0;
+ pmd_idx = pmd_index(PAGE_OFFSET);
+ pte_ofs = pte_index(PAGE_OFFSET);
+
+ for (; pgd_idx < PTRS_PER_PGD_NO_HV; pgd++, pgd_idx++) {
+ pmd = one_md_table_init(pgd);
+ if (pfn >= max_low_pfn)
+ continue;
+ pmd += pmd_idx;
+ for (; pmd_idx < PTRS_PER_PMD && pfn < max_low_pfn; pmd++,
pmd_idx++) {
+ unsigned int address = pfn * PAGE_SIZE + PAGE_OFFSET;
+
+ /* Map with big pages if possible, otherwise create
normal page tables. */
+ if (cpu_has_pse) {
+ unsigned int address2 = (pfn + PTRS_PER_PTE -
1) * PAGE_SIZE + PAGE_OFFSET + PAGE_SIZE-1;
+
+ if (is_kernel_text(address) ||
is_kernel_text(address2))
+ set_pmd(pmd, pfn_pmd(pfn,
PAGE_KERNEL_LARGE_EXEC));
+ else
+ set_pmd(pmd, pfn_pmd(pfn,
PAGE_KERNEL_LARGE));
+ pfn += PTRS_PER_PTE;
+ } else {
+ pte = one_page_table_init(pmd);
+
+ pte += pte_ofs;
+ for (; pte_ofs < PTRS_PER_PTE && pfn <
max_low_pfn; pte++, pfn++, pte_ofs++) {
+ /* XEN: Only map initial RAM
allocation. */
+ if ((pfn >= max_ram_pfn) ||
pte_present(*pte))
+ continue;
+ if (is_kernel_text(address))
+ set_pte(pte,
pfn_pte(pfn, PAGE_KERNEL_EXEC));
+ else
+ set_pte(pte,
pfn_pte(pfn, PAGE_KERNEL));
+ }
+ pte_ofs = 0;
+ }
+ }
+ pmd_idx = 0;
+ }
+}
+
+static inline int page_kills_ppro(unsigned long pagenr)
+{
+ if (pagenr >= 0x70000 && pagenr <= 0x7003F)
+ return 1;
+ return 0;
+}
+
+extern int is_available_memory(efi_memory_desc_t *);
+
+static inline int page_is_ram(unsigned long pagenr)
+{
+ int i;
+ unsigned long addr, end;
+
+ if (efi_enabled) {
+ efi_memory_desc_t *md;
+
+ for (i = 0; i < memmap.nr_map; i++) {
+ md = &memmap.map[i];
+ if (!is_available_memory(md))
+ continue;
+ addr = (md->phys_addr+PAGE_SIZE-1) >> PAGE_SHIFT;
+ end = (md->phys_addr + (md->num_pages <<
EFI_PAGE_SHIFT)) >> PAGE_SHIFT;
+
+ if ((pagenr >= addr) && (pagenr < end))
+ return 1;
+ }
+ return 0;
+ }
+
+ for (i = 0; i < e820.nr_map; i++) {
+
+ if (e820.map[i].type != E820_RAM) /* not usable memory */
+ continue;
+ /*
+ * !!!FIXME!!! Some BIOSen report areas as RAM that
+ * are not. Notably the 640->1Mb area. We need a sanity
+ * check here.
+ */
+ addr = (e820.map[i].addr+PAGE_SIZE-1) >> PAGE_SHIFT;
+ end = (e820.map[i].addr+e820.map[i].size) >> PAGE_SHIFT;
+ if ((pagenr >= addr) && (pagenr < end))
+ return 1;
+ }
+ return 0;
+}
+
+#ifdef CONFIG_HIGHMEM
+pte_t *kmap_pte;
+pgprot_t kmap_prot;
+
+EXPORT_SYMBOL(kmap_prot);
+EXPORT_SYMBOL(kmap_pte);
+
+#define kmap_get_fixmap_pte(vaddr) \
+ pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr), vaddr),
(vaddr)), (vaddr))
+
+void __init kmap_init(void)
+{
+ unsigned long kmap_vstart;
+
+ /* cache the first kmap pte */
+ kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
+ kmap_pte = kmap_get_fixmap_pte(kmap_vstart);
+
+ kmap_prot = PAGE_KERNEL;
+}
+
+void __init permanent_kmaps_init(pgd_t *pgd_base)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+ unsigned long vaddr;
+
+ vaddr = PKMAP_BASE;
+ page_table_range_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base);
+
+ pgd = swapper_pg_dir + pgd_index(vaddr);
+ pud = pud_offset(pgd, vaddr);
+ pmd = pmd_offset(pud, vaddr);
+ pte = pte_offset_kernel(pmd, vaddr);
+ pkmap_page_table = pte;
+}
+
+void __init one_highpage_init(struct page *page, int pfn, int bad_ppro)
+{
+ if (page_is_ram(pfn) && !(bad_ppro && page_kills_ppro(pfn))) {
+ ClearPageReserved(page);
+ set_bit(PG_highmem, &page->flags);
+ set_page_count(page, 1);
+ if (pfn < xen_start_info.nr_pages)
+ __free_page(page);
+ totalhigh_pages++;
+ } else
+ SetPageReserved(page);
+}
+
+#ifndef CONFIG_DISCONTIGMEM
+void __init set_highmem_pages_init(int bad_ppro)
+{
+ int pfn;
+ for (pfn = highstart_pfn; pfn < highend_pfn; pfn++)
+ one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro);
+ totalram_pages += totalhigh_pages;
+}
+#else
+extern void set_highmem_pages_init(int);
+#endif /* !CONFIG_DISCONTIGMEM */
+
+#else
+#define kmap_init() do { } while (0)
+#define permanent_kmaps_init(pgd_base) do { } while (0)
+#define set_highmem_pages_init(bad_ppro) do { } while (0)
+#endif /* CONFIG_HIGHMEM */
+
+unsigned long long __PAGE_KERNEL = _PAGE_KERNEL;
+unsigned long long __PAGE_KERNEL_EXEC = _PAGE_KERNEL_EXEC;
+
+#ifndef CONFIG_DISCONTIGMEM
+#define remap_numa_kva() do {} while (0)
+#else
+extern void __init remap_numa_kva(void);
+#endif
+
+static void __init pagetable_init (void)
+{
+ unsigned long vaddr;
+ pgd_t *pgd_base = swapper_pg_dir;
+ pgd_t *old_pgd = (pgd_t *)xen_start_info.pt_base;
+
+#ifdef CONFIG_X86_PAE
+ int i;
+ /* Init entries of the first-level page table to the zero page */
+ for (i = 0; i < PTRS_PER_PGD; i++)
+ set_pgd(pgd_base + i, __pgd(__pa(empty_zero_page) |
_PAGE_PRESENT));
+#endif
+
+ /* Enable PSE if available */
+ if (cpu_has_pse) {
+ set_in_cr4(X86_CR4_PSE);
+ }
+
+ /* Enable PGE if available */
+ if (cpu_has_pge) {
+ set_in_cr4(X86_CR4_PGE);
+ __PAGE_KERNEL |= _PAGE_GLOBAL;
+ __PAGE_KERNEL_EXEC |= _PAGE_GLOBAL;
+ }
+
+ /*
+ * Switch to proper mm_init page directory. Initialise from the current
+ * page directory, write-protect the new page directory, then switch to
+ * it. We clean up by write-enabling and then freeing the old page dir.
+ */
+ memcpy(pgd_base, old_pgd, PTRS_PER_PGD_NO_HV*sizeof(pgd_t));
+ make_page_readonly(pgd_base);
+ xen_pgd_pin(__pa(pgd_base));
+ load_cr3(pgd_base);
+ xen_pgd_unpin(__pa(old_pgd));
+ make_page_writable(old_pgd);
+ __flush_tlb_all();
+ free_bootmem(__pa(old_pgd), PAGE_SIZE);
+ init_mm.context.pinned = 1;
+
+ kernel_physical_mapping_init(pgd_base);
+ remap_numa_kva();
+
+ /*
+ * Fixed mappings, only the page table structure has to be
+ * created - mappings will be set by set_fixmap():
+ */
+ vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
+ page_table_range_init(vaddr, 0, pgd_base);
+
+ permanent_kmaps_init(pgd_base);
+
+#ifdef CONFIG_X86_PAE
+ /*
+ * Add low memory identity-mappings - SMP needs it when
+ * starting up on an AP from real-mode. In the non-PAE
+ * case we already have these mappings through head.S.
+ * All user-space mappings are explicitly cleared after
+ * SMP startup.
+ */
+ pgd_base[0] = pgd_base[USER_PTRS_PER_PGD];
+#endif
+}
+
+#if defined(CONFIG_PM_DISK) || defined(CONFIG_SOFTWARE_SUSPEND)
+/*
+ * Swap suspend & friends need this for resume because things like the
intel-agp
+ * driver might have split up a kernel 4MB mapping.
+ */
+char __nosavedata swsusp_pg_dir[PAGE_SIZE]
+ __attribute__ ((aligned (PAGE_SIZE)));
+
+static inline void save_pg_dir(void)
+{
+ memcpy(swsusp_pg_dir, swapper_pg_dir, PAGE_SIZE);
+}
+#else
+static inline void save_pg_dir(void)
+{
+}
+#endif
+
+void zap_low_mappings (void)
+{
+ int i;
+
+ save_pg_dir();
+
+ /*
+ * Zap initial low-memory mappings.
+ *
+ * Note that "pgd_clear()" doesn't do it for
+ * us, because pgd_clear() is a no-op on i386.
+ */
+ for (i = 0; i < USER_PTRS_PER_PGD; i++)
+#ifdef CONFIG_X86_PAE
+ set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page)));
+#else
+ set_pgd(swapper_pg_dir+i, __pgd(0));
+#endif
+ flush_tlb_all();
+}
+
+#ifndef CONFIG_DISCONTIGMEM
+void __init zone_sizes_init(void)
+{
+ unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0};
+ unsigned int /*max_dma,*/ high, low;
+
+ /*
+ * XEN: Our notion of "DMA memory" is fake when running over Xen.
+ * We simply put all RAM in the DMA zone so that those drivers which
+ * needlessly specify GFP_DMA do not get starved of RAM unnecessarily.
+ * Those drivers that *do* require lowmem are screwed anyway when
+ * running over Xen!
+ */
+ /*max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;*/
+ low = max_low_pfn;
+ high = highend_pfn;
+
+ /*if (low < max_dma)*/
+ zones_size[ZONE_DMA] = low;
+ /*else*/ {
+ /*zones_size[ZONE_DMA] = max_dma;*/
+ /*zones_size[ZONE_NORMAL] = low - max_dma;*/
+#ifdef CONFIG_HIGHMEM
+ zones_size[ZONE_HIGHMEM] = high - low;
+#endif
+ }
+ free_area_init(zones_size);
+}
+#else
+extern void zone_sizes_init(void);
+#endif /* !CONFIG_DISCONTIGMEM */
+
+static int disable_nx __initdata = 0;
+u64 __supported_pte_mask = ~_PAGE_NX;
+
+/*
+ * noexec = on|off
+ *
+ * Control non executable mappings.
+ *
+ * on Enable
+ * off Disable
+ */
+void __init noexec_setup(const char *str)
+{
+ if (!strncmp(str, "on",2) && cpu_has_nx) {
+ __supported_pte_mask |= _PAGE_NX;
+ disable_nx = 0;
+ } else if (!strncmp(str,"off",3)) {
+ disable_nx = 1;
+ __supported_pte_mask &= ~_PAGE_NX;
+ }
+}
+
+int nx_enabled = 0;
+#ifdef CONFIG_X86_PAE
+
+static void __init set_nx(void)
+{
+ unsigned int v[4], l, h;
+
+ if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
+ cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);
+ if ((v[3] & (1 << 20)) && !disable_nx) {
+ rdmsr(MSR_EFER, l, h);
+ l |= EFER_NX;
+ wrmsr(MSR_EFER, l, h);
+ nx_enabled = 1;
+ __supported_pte_mask |= _PAGE_NX;
+ }
+ }
+}
+
+/*
+ * Enables/disables executability of a given kernel page and
+ * returns the previous setting.
+ */
+int __init set_kernel_exec(unsigned long vaddr, int enable)
+{
+ pte_t *pte;
+ int ret = 1;
+
+ if (!nx_enabled)
+ goto out;
+
+ pte = lookup_address(vaddr);
+ BUG_ON(!pte);
+
+ if (!pte_exec_kernel(*pte))
+ ret = 0;
+
+ if (enable)
+ pte->pte_high &= ~(1 << (_PAGE_BIT_NX - 32));
+ else
+ pte->pte_high |= 1 << (_PAGE_BIT_NX - 32);
+ __flush_tlb_all();
+out:
+ return ret;
+}
+
+#endif
+
+/*
+ * paging_init() sets up the page tables - note that the first 8MB are
+ * already mapped by head.S.
+ *
+ * This routines also unmaps the page at virtual kernel address 0, so
+ * that we can trap those pesky NULL-reference errors in the kernel.
+ */
+void __init paging_init(void)
+{
+#ifdef CONFIG_XEN_PHYSDEV_ACCESS
+ int i;
+#endif
+
+#ifdef CONFIG_X86_PAE
+ set_nx();
+ if (nx_enabled)
+ printk("NX (Execute Disable) protection: active\n");
+#endif
+
+ pagetable_init();
+
+#ifdef CONFIG_X86_PAE
+ /*
+ * We will bail out later - printk doesn't work right now so
+ * the user would just see a hanging kernel.
+ */
+ if (cpu_has_pae)
+ set_in_cr4(X86_CR4_PAE);
+#endif
+ __flush_tlb_all();
+
+ kmap_init();
+ zone_sizes_init();
+
+ /* Switch to the real shared_info page, and clear the dummy page. */
+ set_fixmap(FIX_SHARED_INFO, xen_start_info.shared_info);
+ HYPERVISOR_shared_info = (shared_info_t *)fix_to_virt(FIX_SHARED_INFO);
+ memset(empty_zero_page, 0, sizeof(empty_zero_page));
+
+#ifdef CONFIG_XEN_PHYSDEV_ACCESS
+ /* Setup mapping of lower 1st MB */
+ for (i = 0; i < NR_FIX_ISAMAPS; i++)
+ if (xen_start_info.flags & SIF_PRIVILEGED)
+ set_fixmap(FIX_ISAMAP_BEGIN - i, i * PAGE_SIZE);
+ else
+ __set_fixmap(FIX_ISAMAP_BEGIN - i,
+ virt_to_machine(empty_zero_page),
+ PAGE_KERNEL_RO);
+#endif
+}
+
+/*
+ * Test if the WP bit works in supervisor mode. It isn't supported on 386's
+ * and also on some strange 486's (NexGen etc.). All 586+'s are OK. This
+ * used to involve black magic jumps to work around some nasty CPU bugs,
+ * but fortunately the switch to using exceptions got rid of all that.
+ */
+
+void __init test_wp_bit(void)
+{
+ printk("Checking if this processor honours the WP bit even in
supervisor mode... ");
+
+ /* Any page-aligned address will do, the test is non-destructive */
+ __set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_READONLY);
+ boot_cpu_data.wp_works_ok = do_test_wp_bit();
+ clear_fixmap(FIX_WP_TEST);
+
+ if (!boot_cpu_data.wp_works_ok) {
+ printk("No.\n");
+#ifdef CONFIG_X86_WP_WORKS_OK
+ panic("This kernel doesn't support CPU's with broken WP.
Recompile it for a 386!");
+#endif
+ } else {
+ printk("Ok.\n");
+ }
+}
+
+#ifndef CONFIG_DISCONTIGMEM
+static void __init set_max_mapnr_init(void)
+{
+#ifdef CONFIG_HIGHMEM
+ max_mapnr = num_physpages = highend_pfn;
+#else
+ max_mapnr = num_physpages = max_low_pfn;
+#endif
+}
+#define __free_all_bootmem() free_all_bootmem()
+#else
+#define __free_all_bootmem() free_all_bootmem_node(NODE_DATA(0))
+extern void set_max_mapnr_init(void);
+#endif /* !CONFIG_DISCONTIGMEM */
+
+static struct kcore_list kcore_mem, kcore_vmalloc;
+
+void __init mem_init(void)
+{
+ extern int ppro_with_ram_bug(void);
+ int codesize, reservedpages, datasize, initsize;
+ int tmp;
+ int bad_ppro;
+ unsigned long pfn;
+
+#ifndef CONFIG_DISCONTIGMEM
+ if (!mem_map)
+ BUG();
+#endif
+
+ bad_ppro = ppro_with_ram_bug();
+
+#ifdef CONFIG_HIGHMEM
+ /* check that fixmap and pkmap do not overlap */
+ if (PKMAP_BASE+LAST_PKMAP*PAGE_SIZE >= FIXADDR_START) {
+ printk(KERN_ERR "fixmap and kmap areas overlap - this will
crash\n");
+ printk(KERN_ERR "pkstart: %lxh pkend: %lxh fixstart %lxh\n",
+ PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE,
FIXADDR_START);
+ BUG();
+ }
+#endif
+
+ set_max_mapnr_init();
+
+#ifdef CONFIG_HIGHMEM
+ high_memory = (void *) __va(highstart_pfn * PAGE_SIZE);
+#else
+ high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
+#endif
+ printk("vmalloc area: %lx-%lx, maxmem %lx\n",
+ VMALLOC_START,VMALLOC_END,MAXMEM);
+ BUG_ON(VMALLOC_START > VMALLOC_END);
+
+ /* this will put all low memory onto the freelists */
+ totalram_pages += __free_all_bootmem();
+ /* XEN: init and count low-mem pages outside initial allocation. */
+ for (pfn = xen_start_info.nr_pages; pfn < max_low_pfn; pfn++) {
+ ClearPageReserved(&mem_map[pfn]);
+ set_page_count(&mem_map[pfn], 1);
+ totalram_pages++;
+ }
+
+ reservedpages = 0;
+ for (tmp = 0; tmp < max_low_pfn; tmp++)
+ /*
+ * Only count reserved RAM pages
+ */
+ if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp)))
+ reservedpages++;
+
+ set_highmem_pages_init(bad_ppro);
+
+ codesize = (unsigned long) &_etext - (unsigned long) &_text;
+ datasize = (unsigned long) &_edata - (unsigned long) &_etext;
+ initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
+
+ kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT);
+ kclist_add(&kcore_vmalloc, (void *)VMALLOC_START,
+ VMALLOC_END-VMALLOC_START);
+
+ printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, %dk
reserved, %dk data, %dk init, %ldk highmem)\n",
+ (unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
+ num_physpages << (PAGE_SHIFT-10),
+ codesize >> 10,
+ reservedpages << (PAGE_SHIFT-10),
+ datasize >> 10,
+ initsize >> 10,
+ (unsigned long) (totalhigh_pages << (PAGE_SHIFT-10))
+ );
+
+#ifdef CONFIG_X86_PAE
+ if (!cpu_has_pae)
+ panic("cannot execute a PAE-enabled kernel on a PAE-less CPU!");
+#endif
+ if (boot_cpu_data.wp_works_ok < 0)
+ test_wp_bit();
+
+ /*
+ * Subtle. SMP is doing it's boot stuff late (because it has to
+ * fork idle threads) - but it also needs low mappings for the
+ * protected-mode entry to work. We zap these entries only after
+ * the WP-bit has been tested.
+ */
+#ifndef CONFIG_SMP
+ zap_low_mappings();
+#endif
+}
+
+kmem_cache_t *pgd_cache;
+kmem_cache_t *pmd_cache;
+
+void __init pgtable_cache_init(void)
+{
+ if (PTRS_PER_PMD > 1) {
+ pmd_cache = kmem_cache_create("pmd",
+ PTRS_PER_PMD*sizeof(pmd_t),
+ PTRS_PER_PMD*sizeof(pmd_t),
+ 0,
+ pmd_ctor,
+ NULL);
+ if (!pmd_cache)
+ panic("pgtable_cache_init(): cannot create pmd cache");
+ }
+ pgd_cache = kmem_cache_create("pgd",
+ PTRS_PER_PGD*sizeof(pgd_t),
+ PTRS_PER_PGD*sizeof(pgd_t),
+ 0,
+ pgd_ctor,
+ pgd_dtor);
+ if (!pgd_cache)
+ panic("pgtable_cache_init(): Cannot create pgd cache");
+}
+
+/*
+ * This function cannot be __init, since exceptions don't work in that
+ * section. Put this after the callers, so that it cannot be inlined.
+ */
+static int noinline do_test_wp_bit(void)
+{
+ char tmp_reg;
+ int flag;
+
+ __asm__ __volatile__(
+ " movb %0,%1 \n"
+ "1: movb %1,%0 \n"
+ " xorl %2,%2 \n"
+ "2: \n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4 \n"
+ " .long 1b,2b \n"
+ ".previous \n"
+ :"=m" (*(char *)fix_to_virt(FIX_WP_TEST)),
+ "=q" (tmp_reg),
+ "=r" (flag)
+ :"2" (1)
+ :"memory");
+
+ return flag;
+}
+
+void free_initmem(void)
+{
+ unsigned long addr;
+
+ addr = (unsigned long)(&__init_begin);
+ for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
+ ClearPageReserved(virt_to_page(addr));
+ set_page_count(virt_to_page(addr), 1);
+ memset((void *)addr, 0xcc, PAGE_SIZE);
+ free_page(addr);
+ totalram_pages++;
+ }
+ printk (KERN_INFO "Freeing unused kernel memory: %dk freed\n",
(__init_end - __init_begin) >> 10);
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void free_initrd_mem(unsigned long start, unsigned long end)
+{
+ if (start < end)
+ printk (KERN_INFO "Freeing initrd memory: %ldk freed\n", (end -
start) >> 10);
+ for (; start < end; start += PAGE_SIZE) {
+ ClearPageReserved(virt_to_page(start));
+ set_page_count(virt_to_page(start), 1);
+ free_page(start);
+ totalram_pages++;
+ }
+}
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,68 @@
+#
+# Makefile for the linux kernel.
+#
+XENARCH := $(subst ",,$(CONFIG_XENARCH))
+
+CFLAGS += -Iarch/$(XENARCH)/kernel
+
+extra-y := head.o head64.o init_task.o
+
+obj-y := process.o signal.o entry.o traps.o \
+ ioport.o ldt.o setup.o \
+ x8664_ksyms.o vsyscall.o \
+ setup64.o e820.o irq.o early_printk.o
+c-obj-y := semaphore.o i387.o sys_x86_64.o \
+ ptrace.o quirks.o syscall.o bootflag.o
+
+i386-obj-y := time.o
+obj-y += ../../i386/kernel/timers/
+
+s-obj-y :=
+
+#obj-$(CONFIG_X86_MCE) += mce.o
+#obj-$(CONFIG_MTRR) += ../../i386/kernel/cpu/mtrr/
+obj-$(CONFIG_ACPI_BOOT) += acpi/
+c-obj-$(CONFIG_X86_MSR) += msr.o
+obj-$(CONFIG_MICROCODE) += microcode.o
+obj-$(CONFIG_X86_CPUID) += cpuid.o
+#obj-$(CONFIG_SMP) += smp.o smpboot.o trampoline.o
+obj-$(CONFIG_X86_LOCAL_APIC) += apic.o
+c-obj-$(CONFIG_X86_LOCAL_APIC) += nmi.o
+obj-$(CONFIG_X86_IO_APIC) += io_apic.o mpparse.o
+c-obj-$(CONFIG_X86_IO_APIC) += genapic.o genapic_cluster.o genapic_flat.o
+#obj-$(CONFIG_PM) += suspend.o
+#obj-$(CONFIG_SOFTWARE_SUSPEND) += suspend_asm.o
+#obj-$(CONFIG_CPU_FREQ) += cpufreq/
+#obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
+#obj-$(CONFIG_GART_IOMMU) += pci-gart.o aperture.o
+c-obj-$(CONFIG_DUMMY_IOMMU) += pci-nommu.o pci-dma.o
+#obj-$(CONFIG_SWIOTLB) += swiotlb.o
+obj-$(CONFIG_KPROBES) += kprobes.o
+
+c-obj-$(CONFIG_MODULES) += module.o
+
+#obj-y += topology.o
+c-obj-y += intel_cacheinfo.o
+
+bootflag-y += ../../../i386/kernel/bootflag.o
+cpuid-$(subst m,y,$(CONFIG_X86_CPUID)) += ../../../i386/kernel/cpuid.o
+topology-y += ../../../i386/mach-default/topology.o
+swiotlb-$(CONFIG_SWIOTLB) += ../../../ia64/lib/swiotlb.o
+microcode-$(subst m,y,$(CONFIG_MICROCODE)) += ../../../i386/kernel/microcode.o
+intel_cacheinfo-y += ../../../i386/kernel/cpu/intel_cacheinfo.o
+quirks-y += ../../../i386/kernel/quirks.o
+
+c-link := init_task.o
+s-link := vsyscall.o
+
+$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-obj-m) $(c-link)) $(patsubst
%.o,$(obj)/%.S,$(s-obj-y) $(s-link)):
+ @ln -fsn $(srctree)/arch/x86_64/kernel/$(notdir $@) $@
+
+$(patsubst %.o,$(obj)/%.c,$(i386-obj-y)):
+ @ln -fsn $(srctree)/arch/xen/i386/kernel/$(notdir $@) $@
+
+obj-y += $(c-obj-y) $(s-obj-y) $(i386-obj-y)
+obj-m += $(c-obj-m)
+
+clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-m) $(c-obj-) $(c-link)
$(i386-obj-y))
+clean-files += $(patsubst %.o,%.S,$(s-obj-y) $(s-obj-) $(s-link))
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/signal.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/signal.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,656 @@
+/*
+ * linux/arch/i386/kernel/signal.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson
+ * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/errno.h>
+#include <linux/wait.h>
+#include <linux/unistd.h>
+#include <linux/stddef.h>
+#include <linux/personality.h>
+#include <linux/suspend.h>
+#include <linux/ptrace.h>
+#include <linux/elf.h>
+#include <asm/processor.h>
+#include <asm/ucontext.h>
+#include <asm/uaccess.h>
+#include <asm/i387.h>
+#include "sigframe.h"
+
+#define DEBUG_SIG 0
+
+#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
+
+/*
+ * Atomically swap in the new signal mask, and wait for a signal.
+ */
+asmlinkage int
+sys_sigsuspend(int history0, int history1, old_sigset_t mask)
+{
+ struct pt_regs * regs = (struct pt_regs *) &history0;
+ sigset_t saveset;
+
+ mask &= _BLOCKABLE;
+ spin_lock_irq(¤t->sighand->siglock);
+ saveset = current->blocked;
+ siginitset(¤t->blocked, mask);
+ recalc_sigpending();
+ spin_unlock_irq(¤t->sighand->siglock);
+
+ regs->eax = -EINTR;
+ while (1) {
+ current->state = TASK_INTERRUPTIBLE;
+ schedule();
+ if (do_signal(regs, &saveset))
+ return -EINTR;
+ }
+}
+
+asmlinkage int
+sys_rt_sigsuspend(struct pt_regs regs)
+{
+ sigset_t saveset, newset;
+
+ /* XXX: Don't preclude handling different sized sigset_t's. */
+ if (regs.ecx != sizeof(sigset_t))
+ return -EINVAL;
+
+ if (copy_from_user(&newset, (sigset_t __user *)regs.ebx,
sizeof(newset)))
+ return -EFAULT;
+ sigdelsetmask(&newset, ~_BLOCKABLE);
+
+ spin_lock_irq(¤t->sighand->siglock);
+ saveset = current->blocked;
+ current->blocked = newset;
+ recalc_sigpending();
+ spin_unlock_irq(¤t->sighand->siglock);
+
+ regs.eax = -EINTR;
+ while (1) {
+ current->state = TASK_INTERRUPTIBLE;
+ schedule();
+ if (do_signal(®s, &saveset))
+ return -EINTR;
+ }
+}
+
+asmlinkage int
+sys_sigaction(int sig, const struct old_sigaction __user *act,
+ struct old_sigaction __user *oact)
+{
+ struct k_sigaction new_ka, old_ka;
+ int ret;
+
+ if (act) {
+ old_sigset_t mask;
+ if (verify_area(VERIFY_READ, act, sizeof(*act)) ||
+ __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
+ __get_user(new_ka.sa.sa_restorer, &act->sa_restorer))
+ return -EFAULT;
+ __get_user(new_ka.sa.sa_flags, &act->sa_flags);
+ __get_user(mask, &act->sa_mask);
+ siginitset(&new_ka.sa.sa_mask, mask);
+ }
+
+ ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
+
+ if (!ret && oact) {
+ if (verify_area(VERIFY_WRITE, oact, sizeof(*oact)) ||
+ __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
+ __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer))
+ return -EFAULT;
+ __put_user(old_ka.sa.sa_flags, &oact->sa_flags);
+ __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
+ }
+
+ return ret;
+}
+
+asmlinkage int
+sys_sigaltstack(unsigned long ebx)
+{
+ /* This is needed to make gcc realize it doesn't own the "struct
pt_regs" */
+ struct pt_regs *regs = (struct pt_regs *)&ebx;
+ const stack_t __user *uss = (const stack_t __user *)ebx;
+ stack_t __user *uoss = (stack_t __user *)regs->ecx;
+
+ return do_sigaltstack(uss, uoss, regs->esp);
+}
+
+
+/*
+ * Do a signal return; undo the signal stack.
+ */
+
+static int
+restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int
*peax)
+{
+ unsigned int err = 0;
+
+ /* Always make any pending restarted system calls return -EINTR */
+ current_thread_info()->restart_block.fn = do_no_restart_syscall;
+
+#define COPY(x) err |= __get_user(regs->x, &sc->x)
+
+#define COPY_SEG(seg) \
+ { unsigned short tmp; \
+ err |= __get_user(tmp, &sc->seg); \
+ regs->x##seg = tmp; }
+
+#define COPY_SEG_STRICT(seg) \
+ { unsigned short tmp; \
+ err |= __get_user(tmp, &sc->seg); \
+ regs->x##seg = tmp|3; }
+
+#define GET_SEG(seg) \
+ { unsigned short tmp; \
+ err |= __get_user(tmp, &sc->seg); \
+ loadsegment(seg,tmp); }
+
+#define FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | X86_EFLAGS_DF
| \
+ X86_EFLAGS_TF | X86_EFLAGS_SF | X86_EFLAGS_ZF | \
+ X86_EFLAGS_AF | X86_EFLAGS_PF | X86_EFLAGS_CF)
+
+ GET_SEG(gs);
+ GET_SEG(fs);
+ COPY_SEG(es);
+ COPY_SEG(ds);
+ COPY(edi);
+ COPY(esi);
+ COPY(ebp);
+ COPY(esp);
+ COPY(ebx);
+ COPY(edx);
+ COPY(ecx);
+ COPY(eip);
+ COPY_SEG_STRICT(cs);
+ COPY_SEG_STRICT(ss);
+
+ {
+ unsigned int tmpflags;
+ err |= __get_user(tmpflags, &sc->eflags);
+ regs->eflags = (regs->eflags & ~FIX_EFLAGS) | (tmpflags &
FIX_EFLAGS);
+ regs->orig_eax = -1; /* disable syscall checks */
+ }
+
+ {
+ struct _fpstate __user * buf;
+ err |= __get_user(buf, &sc->fpstate);
+ if (buf) {
+ if (verify_area(VERIFY_READ, buf, sizeof(*buf)))
+ goto badframe;
+ err |= restore_i387(buf);
+ } else {
+ struct task_struct *me = current;
+ if (used_math()) {
+ clear_fpu(me);
+ clear_used_math();
+ }
+ }
+ }
+
+ err |= __get_user(*peax, &sc->eax);
+ return err;
+
+badframe:
+ return 1;
+}
+
+asmlinkage int sys_sigreturn(unsigned long __unused)
+{
+ struct pt_regs *regs = (struct pt_regs *) &__unused;
+ struct sigframe __user *frame = (struct sigframe __user *)(regs->esp -
8);
+ sigset_t set;
+ int eax;
+
+ if (verify_area(VERIFY_READ, frame, sizeof(*frame)))
+ goto badframe;
+ if (__get_user(set.sig[0], &frame->sc.oldmask)
+ || (_NSIG_WORDS > 1
+ && __copy_from_user(&set.sig[1], &frame->extramask,
+ sizeof(frame->extramask))))
+ goto badframe;
+
+ sigdelsetmask(&set, ~_BLOCKABLE);
+ spin_lock_irq(¤t->sighand->siglock);
+ current->blocked = set;
+ recalc_sigpending();
+ spin_unlock_irq(¤t->sighand->siglock);
+
+ if (restore_sigcontext(regs, &frame->sc, &eax))
+ goto badframe;
+ return eax;
+
+badframe:
+ force_sig(SIGSEGV, current);
+ return 0;
+}
+
+asmlinkage int sys_rt_sigreturn(unsigned long __unused)
+{
+ struct pt_regs *regs = (struct pt_regs *) &__unused;
+ struct rt_sigframe __user *frame = (struct rt_sigframe __user
*)(regs->esp - 4);
+ sigset_t set;
+ int eax;
+
+ if (verify_area(VERIFY_READ, frame, sizeof(*frame)))
+ goto badframe;
+ if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+ goto badframe;
+
+ sigdelsetmask(&set, ~_BLOCKABLE);
+ spin_lock_irq(¤t->sighand->siglock);
+ current->blocked = set;
+ recalc_sigpending();
+ spin_unlock_irq(¤t->sighand->siglock);
+
+ if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &eax))
+ goto badframe;
+
+ if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->esp) == -EFAULT)
+ goto badframe;
+
+ return eax;
+
+badframe:
+ force_sig(SIGSEGV, current);
+ return 0;
+}
+
+/*
+ * Set up a signal frame.
+ */
+
+static int
+setup_sigcontext(struct sigcontext __user *sc, struct _fpstate __user *fpstate,
+ struct pt_regs *regs, unsigned long mask)
+{
+ int tmp, err = 0;
+
+ tmp = 0;
+ __asm__("movl %%gs,%0" : "=r"(tmp): "0"(tmp));
+ err |= __put_user(tmp, (unsigned int __user *)&sc->gs);
+ __asm__("movl %%fs,%0" : "=r"(tmp): "0"(tmp));
+ err |= __put_user(tmp, (unsigned int __user *)&sc->fs);
+
+ err |= __put_user(regs->xes, (unsigned int __user *)&sc->es);
+ err |= __put_user(regs->xds, (unsigned int __user *)&sc->ds);
+ err |= __put_user(regs->edi, &sc->edi);
+ err |= __put_user(regs->esi, &sc->esi);
+ err |= __put_user(regs->ebp, &sc->ebp);
+ err |= __put_user(regs->esp, &sc->esp);
+ err |= __put_user(regs->ebx, &sc->ebx);
+ err |= __put_user(regs->edx, &sc->edx);
+ err |= __put_user(regs->ecx, &sc->ecx);
+ err |= __put_user(regs->eax, &sc->eax);
+ err |= __put_user(current->thread.trap_no, &sc->trapno);
+ err |= __put_user(current->thread.error_code, &sc->err);
+ err |= __put_user(regs->eip, &sc->eip);
+ err |= __put_user(regs->xcs, (unsigned int __user *)&sc->cs);
+ err |= __put_user(regs->eflags, &sc->eflags);
+ err |= __put_user(regs->esp, &sc->esp_at_signal);
+ err |= __put_user(regs->xss, (unsigned int __user *)&sc->ss);
+
+ tmp = save_i387(fpstate);
+ if (tmp < 0)
+ err = 1;
+ else
+ err |= __put_user(tmp ? fpstate : NULL, &sc->fpstate);
+
+ /* non-iBCS2 extensions.. */
+ err |= __put_user(mask, &sc->oldmask);
+ err |= __put_user(current->thread.cr2, &sc->cr2);
+
+ return err;
+}
+
+/*
+ * Determine which stack to use..
+ */
+static inline void __user *
+get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size)
+{
+ unsigned long esp;
+
+ /* Default to using normal stack */
+ esp = regs->esp;
+
+ /* This is the X/Open sanctioned signal stack switching. */
+ if (ka->sa.sa_flags & SA_ONSTACK) {
+ if (sas_ss_flags(esp) == 0)
+ esp = current->sas_ss_sp + current->sas_ss_size;
+ }
+
+ /* This is the legacy signal stack switching. */
+ else if ((regs->xss & 0xffff) != __USER_DS &&
+ !(ka->sa.sa_flags & SA_RESTORER) &&
+ ka->sa.sa_restorer) {
+ esp = (unsigned long) ka->sa.sa_restorer;
+ }
+
+ return (void __user *)((esp - frame_size) & -8ul);
+}
+
+/* These symbols are defined with the addresses in the vsyscall page.
+ See vsyscall-sigreturn.S. */
+extern void __user __kernel_sigreturn;
+extern void __user __kernel_rt_sigreturn;
+
+static void setup_frame(int sig, struct k_sigaction *ka,
+ sigset_t *set, struct pt_regs * regs)
+{
+ void __user *restorer;
+ struct sigframe __user *frame;
+ int err = 0;
+ int usig;
+
+ frame = get_sigframe(ka, regs, sizeof(*frame));
+
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ goto give_sigsegv;
+
+ usig = current_thread_info()->exec_domain
+ && current_thread_info()->exec_domain->signal_invmap
+ && sig < 32
+ ? current_thread_info()->exec_domain->signal_invmap[sig]
+ : sig;
+
+ err = __put_user(usig, &frame->sig);
+ if (err)
+ goto give_sigsegv;
+
+ err = setup_sigcontext(&frame->sc, &frame->fpstate, regs, set->sig[0]);
+ if (err)
+ goto give_sigsegv;
+
+ if (_NSIG_WORDS > 1) {
+ err = __copy_to_user(&frame->extramask, &set->sig[1],
+ sizeof(frame->extramask));
+ if (err)
+ goto give_sigsegv;
+ }
+
+ restorer = &__kernel_sigreturn;
+ if (ka->sa.sa_flags & SA_RESTORER)
+ restorer = ka->sa.sa_restorer;
+
+ /* Set up to return from userspace. */
+ err |= __put_user(restorer, &frame->pretcode);
+
+ /*
+ * This is popl %eax ; movl $,%eax ; int $0x80
+ *
+ * WE DO NOT USE IT ANY MORE! It's only left here for historical
+ * reasons and because gdb uses it as a signature to notice
+ * signal handler stack frames.
+ */
+ err |= __put_user(0xb858, (short __user *)(frame->retcode+0));
+ err |= __put_user(__NR_sigreturn, (int __user *)(frame->retcode+2));
+ err |= __put_user(0x80cd, (short __user *)(frame->retcode+6));
+
+ if (err)
+ goto give_sigsegv;
+
+ /* Set up registers for signal handler */
+ regs->esp = (unsigned long) frame;
+ regs->eip = (unsigned long) ka->sa.sa_handler;
+ regs->eax = (unsigned long) sig;
+ regs->edx = (unsigned long) 0;
+ regs->ecx = (unsigned long) 0;
+
+ set_fs(USER_DS);
+ regs->xds = __USER_DS;
+ regs->xes = __USER_DS;
+ regs->xss = __USER_DS;
+ regs->xcs = __USER_CS;
+
+ /*
+ * Clear TF when entering the signal handler, but
+ * notify any tracer that was single-stepping it.
+ * The tracer may want to single-step inside the
+ * handler too.
+ */
+ regs->eflags &= ~TF_MASK;
+ if (test_thread_flag(TIF_SINGLESTEP))
+ ptrace_notify(SIGTRAP);
+
+#if DEBUG_SIG
+ printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n",
+ current->comm, current->pid, frame, regs->eip, frame->pretcode);
+#endif
+
+ return;
+
+give_sigsegv:
+ force_sigsegv(sig, current);
+}
+
+static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+ sigset_t *set, struct pt_regs * regs)
+{
+ void __user *restorer;
+ struct rt_sigframe __user *frame;
+ int err = 0;
+ int usig;
+
+ frame = get_sigframe(ka, regs, sizeof(*frame));
+
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ goto give_sigsegv;
+
+ usig = current_thread_info()->exec_domain
+ && current_thread_info()->exec_domain->signal_invmap
+ && sig < 32
+ ? current_thread_info()->exec_domain->signal_invmap[sig]
+ : sig;
+
+ err |= __put_user(usig, &frame->sig);
+ err |= __put_user(&frame->info, &frame->pinfo);
+ err |= __put_user(&frame->uc, &frame->puc);
+ err |= copy_siginfo_to_user(&frame->info, info);
+ if (err)
+ goto give_sigsegv;
+
+ /* Create the ucontext. */
+ err |= __put_user(0, &frame->uc.uc_flags);
+ err |= __put_user(0, &frame->uc.uc_link);
+ err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ err |= __put_user(sas_ss_flags(regs->esp),
+ &frame->uc.uc_stack.ss_flags);
+ err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate,
+ regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+ if (err)
+ goto give_sigsegv;
+
+ /* Set up to return from userspace. */
+ restorer = &__kernel_rt_sigreturn;
+ if (ka->sa.sa_flags & SA_RESTORER)
+ restorer = ka->sa.sa_restorer;
+ err |= __put_user(restorer, &frame->pretcode);
+
+ /*
+ * This is movl $,%eax ; int $0x80
+ *
+ * WE DO NOT USE IT ANY MORE! It's only left here for historical
+ * reasons and because gdb uses it as a signature to notice
+ * signal handler stack frames.
+ */
+ err |= __put_user(0xb8, (char __user *)(frame->retcode+0));
+ err |= __put_user(__NR_rt_sigreturn, (int __user *)(frame->retcode+1));
+ err |= __put_user(0x80cd, (short __user *)(frame->retcode+5));
+
+ if (err)
+ goto give_sigsegv;
+
+ /* Set up registers for signal handler */
+ regs->esp = (unsigned long) frame;
+ regs->eip = (unsigned long) ka->sa.sa_handler;
+ regs->eax = (unsigned long) usig;
+ regs->edx = (unsigned long) &frame->info;
+ regs->ecx = (unsigned long) &frame->uc;
+
+ set_fs(USER_DS);
+ regs->xds = __USER_DS;
+ regs->xes = __USER_DS;
+ regs->xss = __USER_DS;
+ regs->xcs = __USER_CS;
+
+ /*
+ * Clear TF when entering the signal handler, but
+ * notify any tracer that was single-stepping it.
+ * The tracer may want to single-step inside the
+ * handler too.
+ */
+ regs->eflags &= ~TF_MASK;
+ if (test_thread_flag(TIF_SINGLESTEP))
+ ptrace_notify(SIGTRAP);
+
+#if DEBUG_SIG
+ printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n",
+ current->comm, current->pid, frame, regs->eip, frame->pretcode);
+#endif
+
+ return;
+
+give_sigsegv:
+ force_sigsegv(sig, current);
+}
+
+/*
+ * OK, we're invoking a handler
+ */
+
+static void
+handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
+ sigset_t *oldset, struct pt_regs * regs)
+{
+ /* Are we from a system call? */
+ if (regs->orig_eax >= 0) {
+ /* If so, check system call restarting.. */
+ switch (regs->eax) {
+ case -ERESTART_RESTARTBLOCK:
+ case -ERESTARTNOHAND:
+ regs->eax = -EINTR;
+ break;
+
+ case -ERESTARTSYS:
+ if (!(ka->sa.sa_flags & SA_RESTART)) {
+ regs->eax = -EINTR;
+ break;
+ }
+ /* fallthrough */
+ case -ERESTARTNOINTR:
+ regs->eax = regs->orig_eax;
+ regs->eip -= 2;
+ }
+ }
+
+ /* Set up the stack frame */
+ if (ka->sa.sa_flags & SA_SIGINFO)
+ setup_rt_frame(sig, ka, info, oldset, regs);
+ else
+ setup_frame(sig, ka, oldset, regs);
+
+ if (!(ka->sa.sa_flags & SA_NODEFER)) {
+ spin_lock_irq(¤t->sighand->siglock);
+ sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask);
+ sigaddset(¤t->blocked,sig);
+ recalc_sigpending();
+ spin_unlock_irq(¤t->sighand->siglock);
+ }
+}
+
+/*
+ * Note that 'init' is a special process: it doesn't get signals it doesn't
+ * want to handle. Thus you cannot kill init even with a SIGKILL even by
+ * mistake.
+ */
+int fastcall do_signal(struct pt_regs *regs, sigset_t *oldset)
+{
+ siginfo_t info;
+ int signr;
+ struct k_sigaction ka;
+
+ /*
+ * We want the common case to go fast, which
+ * is why we may in certain cases get here from
+ * kernel mode. Just return without doing anything
+ * if so.
+ */
+ if ((regs->xcs & 2) != 2)
+ return 1;
+
+ if (current->flags & PF_FREEZE) {
+ refrigerator(0);
+ goto no_signal;
+ }
+
+ if (!oldset)
+ oldset = ¤t->blocked;
+
+ signr = get_signal_to_deliver(&info, &ka, regs, NULL);
+ if (signr > 0) {
+ /* Reenable any watchpoints before delivering the
+ * signal to user space. The processor register will
+ * have been cleared if the watchpoint triggered
+ * inside the kernel.
+ */
+ if (unlikely(current->thread.debugreg[7])) {
+ HYPERVISOR_set_debugreg(7,
+ current->thread.debugreg[7]);
+ }
+
+ /* Whee! Actually deliver the signal. */
+ handle_signal(signr, &info, &ka, oldset, regs);
+ return 1;
+ }
+
+ no_signal:
+ /* Did we come from a system call? */
+ if (regs->orig_eax >= 0) {
+ /* Restart the system call - no handlers present */
+ if (regs->eax == -ERESTARTNOHAND ||
+ regs->eax == -ERESTARTSYS ||
+ regs->eax == -ERESTARTNOINTR) {
+ regs->eax = regs->orig_eax;
+ regs->eip -= 2;
+ }
+ if (regs->eax == -ERESTART_RESTARTBLOCK){
+ regs->eax = __NR_restart_syscall;
+ regs->eip -= 2;
+ }
+ }
+ return 0;
+}
+
+/*
+ * notification of userspace execution resumption
+ * - triggered by current->work.notify_resume
+ */
+__attribute__((regparm(3)))
+void do_notify_resume(struct pt_regs *regs, sigset_t *oldset,
+ __u32 thread_info_flags)
+{
+ /* Pending single-step? */
+ if (thread_info_flags & _TIF_SINGLESTEP) {
+ regs->eflags |= TF_MASK;
+ clear_thread_flag(TIF_SINGLESTEP);
+ }
+ /* deal with pending signal delivery */
+ if (thread_info_flags & _TIF_SIGPENDING)
+ do_signal(regs,oldset);
+
+ clear_thread_flag(TIF_IRET);
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/pci-nommu.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/pci-nommu.c Fri Jul
15 13:39:50 2005
@@ -0,0 +1,96 @@
+/* Fallback functions when the main IOMMU code is not compiled in. This
+ code is roughly equivalent to i386. */
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+#include <asm/proto.h>
+#include <asm/processor.h>
+
+int iommu_merge = 0;
+EXPORT_SYMBOL(iommu_merge);
+
+dma_addr_t bad_dma_address;
+EXPORT_SYMBOL(bad_dma_address);
+
+int iommu_bio_merge = 0;
+EXPORT_SYMBOL(iommu_bio_merge);
+
+int iommu_sac_force = 0;
+EXPORT_SYMBOL(iommu_sac_force);
+
+#if 0
+/*
+ * Dummy IO MMU functions
+ */
+
+void *dma_alloc_coherent(struct device *hwdev, size_t size,
+ dma_addr_t *dma_handle, unsigned gfp)
+{
+ void *ret;
+ u64 mask;
+ int order = get_order(size);
+
+ if (hwdev)
+ mask = hwdev->coherent_dma_mask & *hwdev->dma_mask;
+ else
+ mask = 0xffffffff;
+ for (;;) {
+ ret = (void *)__get_free_pages(gfp, order);
+ if (ret == NULL)
+ return NULL;
+ *dma_handle = virt_to_bus(ret);
+ if ((*dma_handle & ~mask) == 0)
+ break;
+ free_pages((unsigned long)ret, order);
+ if (gfp & GFP_DMA)
+ return NULL;
+ gfp |= GFP_DMA;
+ }
+
+ memset(ret, 0, size);
+ return ret;
+}
+EXPORT_SYMBOL(dma_alloc_coherent);
+
+void dma_free_coherent(struct device *hwdev, size_t size,
+ void *vaddr, dma_addr_t dma_handle)
+{
+ free_pages((unsigned long)vaddr, get_order(size));
+}
+EXPORT_SYMBOL(dma_free_coherent);
+#endif
+
+int dma_supported(struct device *hwdev, u64 mask)
+{
+ /*
+ * we fall back to GFP_DMA when the mask isn't all 1s,
+ * so we can't guarantee allocations that must be
+ * within a tighter range than GFP_DMA..
+ * RED-PEN this won't work for pci_map_single. Caller has to
+ * use GFP_DMA in the first place.
+ */
+ if (mask < 0x00ffffff)
+ return 0;
+
+ return 1;
+}
+EXPORT_SYMBOL(dma_supported);
+
+int dma_get_cache_alignment(void)
+{
+ return boot_cpu_data.x86_clflush_size;
+}
+EXPORT_SYMBOL(dma_get_cache_alignment);
+
+static int __init check_ram(void)
+{
+ if (end_pfn >= 0xffffffff>>PAGE_SHIFT) {
+ printk(
+ KERN_ERR "WARNING more than 4GB of memory but IOMMU not
compiled in.\n"
+ KERN_ERR "WARNING 32bit PCI may malfunction.\n");
+ }
+ return 0;
+}
+__initcall(check_ram);
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/desc.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/desc.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,240 @@
+/* Written 2000 by Andi Kleen */
+#ifndef __ARCH_DESC_H
+#define __ARCH_DESC_H
+
+#include <linux/threads.h>
+#include <asm/ldt.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/string.h>
+#include <asm/segment.h>
+#include <asm/mmu.h>
+
+// 8 byte segment descriptor
+struct desc_struct {
+ u16 limit0;
+ u16 base0;
+ unsigned base1 : 8, type : 4, s : 1, dpl : 2, p : 1;
+ unsigned limit : 4, avl : 1, l : 1, d : 1, g : 1, base2 : 8;
+} __attribute__((packed));
+
+struct n_desc_struct {
+ unsigned int a,b;
+};
+
+enum {
+ GATE_INTERRUPT = 0xE,
+ GATE_TRAP = 0xF,
+ GATE_CALL = 0xC,
+};
+
+// 16byte gate
+struct gate_struct {
+ u16 offset_low;
+ u16 segment;
+ unsigned ist : 3, zero0 : 5, type : 5, dpl : 2, p : 1;
+ u16 offset_middle;
+ u32 offset_high;
+ u32 zero1;
+} __attribute__((packed));
+
+#define PTR_LOW(x) ((unsigned long)(x) & 0xFFFF)
+#define PTR_MIDDLE(x) (((unsigned long)(x) >> 16) & 0xFFFF)
+#define PTR_HIGH(x) ((unsigned long)(x) >> 32)
+
+enum {
+ DESC_TSS = 0x9,
+ DESC_LDT = 0x2,
+};
+
+// LDT or TSS descriptor in the GDT. 16 bytes.
+struct ldttss_desc {
+ u16 limit0;
+ u16 base0;
+ unsigned base1 : 8, type : 5, dpl : 2, p : 1;
+ unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8;
+ u32 base3;
+ u32 zero1;
+} __attribute__((packed));
+
+struct desc_ptr {
+ unsigned short size;
+ unsigned long address;
+} __attribute__((packed)) ;
+
+extern struct desc_ptr idt_descr, cpu_gdt_descr[NR_CPUS];
+
+extern struct desc_struct cpu_gdt_table[NR_CPUS][GDT_ENTRIES];
+
+#define get_cpu_gdt_table(_cpu) ((struct desc_struct
*)(cpu_gdt_descr[(_cpu)].address))
+
+#define load_TR_desc() asm volatile("ltr %w0"::"r" (GDT_ENTRY_TSS*8))
+#define load_LDT_desc() asm volatile("lldt %w0"::"r" (GDT_ENTRY_LDT*8))
+
+static inline void clear_LDT(void)
+{
+ int cpu = get_cpu();
+
+ /*
+ * NB. We load the default_ldt for lcall7/27 handling on demand, as
+ * it slows down context switching. Noone uses it anyway.
+ */
+ cpu = cpu; /* XXX avoid compiler warning */
+ xen_set_ldt(0UL, 0);
+ put_cpu();
+}
+
+/*
+ * This is the ldt that every process will get unless we need
+ * something other than this.
+ */
+extern struct desc_struct default_ldt[];
+extern struct gate_struct idt_table[];
+
+static inline void _set_gate(void *adr, unsigned type, unsigned long func,
unsigned dpl, unsigned ist)
+{
+ struct gate_struct s;
+ s.offset_low = PTR_LOW(func);
+ s.segment = __KERNEL_CS;
+ s.ist = ist;
+ s.p = 1;
+ s.dpl = dpl;
+ s.zero0 = 0;
+ s.zero1 = 0;
+ s.type = type;
+ s.offset_middle = PTR_MIDDLE(func);
+ s.offset_high = PTR_HIGH(func);
+ /* does not need to be atomic because it is only done once at setup
time */
+ memcpy(adr, &s, 16);
+}
+
+static inline void set_intr_gate(int nr, void *func)
+{
+ _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 0, 0);
+}
+
+static inline void set_intr_gate_ist(int nr, void *func, unsigned ist)
+{
+ _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 0,
ist);
+}
+
+static inline void set_system_gate(int nr, void *func)
+{
+ _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 3, 0);
+}
+
+static inline void set_tssldt_descriptor(void *ptr, unsigned long tss,
unsigned type,
+ unsigned size)
+{
+ struct ldttss_desc d;
+ memset(&d,0,sizeof(d));
+ d.limit0 = size & 0xFFFF;
+ d.base0 = PTR_LOW(tss);
+ d.base1 = PTR_MIDDLE(tss) & 0xFF;
+ d.type = type;
+ d.p = 1;
+ d.limit1 = (size >> 16) & 0xF;
+ d.base2 = (PTR_MIDDLE(tss) >> 8) & 0xFF;
+ d.base3 = PTR_HIGH(tss);
+ memcpy(ptr, &d, 16);
+}
+
+static inline void set_tss_desc(unsigned cpu, void *addr)
+{
+ set_tssldt_descriptor((struct ldttss_desc
*)&get_cpu_gdt_table(cpu)[GDT_ENTRY_TSS],
+ (unsigned long)addr,
+ DESC_TSS,
+ sizeof(struct tss_struct) - 1);
+}
+
+static inline void set_ldt_desc(unsigned cpu, void *addr, int size)
+{
+ set_tssldt_descriptor((struct ldttss_desc
*)&get_cpu_gdt_table(cpu)[GDT_ENTRY_LDT],
+ (unsigned long)addr,
+ DESC_LDT, size * 8 - 1);
+}
+
+static inline void set_seg_base(unsigned cpu, int entry, void *base)
+{
+ struct desc_struct *d = (struct desc_struct
*)&get_cpu_gdt_table(cpu)[entry];
+ u32 addr = (u32)(u64)base;
+ BUG_ON((u64)base >> 32);
+ d->base0 = addr & 0xffff;
+ d->base1 = (addr >> 16) & 0xff;
+ d->base2 = (addr >> 24) & 0xff;
+}
+
+#define LDT_entry_a(info) \
+ ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
+/* Don't allow setting of the lm bit. It is useless anyways because
+ 64bit system calls require __USER_CS. */
+#define LDT_entry_b(info) \
+ (((info)->base_addr & 0xff000000) | \
+ (((info)->base_addr & 0x00ff0000) >> 16) | \
+ ((info)->limit & 0xf0000) | \
+ (((info)->read_exec_only ^ 1) << 9) | \
+ ((info)->contents << 10) | \
+ (((info)->seg_not_present ^ 1) << 15) | \
+ ((info)->seg_32bit << 22) | \
+ ((info)->limit_in_pages << 23) | \
+ ((info)->useable << 20) | \
+ /* ((info)->lm << 21) | */ \
+ 0x7000)
+
+#define LDT_empty(info) (\
+ (info)->base_addr == 0 && \
+ (info)->limit == 0 && \
+ (info)->contents == 0 && \
+ (info)->read_exec_only == 1 && \
+ (info)->seg_32bit == 0 && \
+ (info)->limit_in_pages == 0 && \
+ (info)->seg_not_present == 1 && \
+ (info)->useable == 0 && \
+ (info)->lm == 0)
+
+#if TLS_SIZE != 24
+# error update this code.
+#endif
+
+static inline void load_TLS(struct thread_struct *t, unsigned int cpu)
+{
+#if 0
+ u64 *gdt = (u64 *)(cpu_gdt_table[cpu] + GDT_ENTRY_TLS_MIN);
+ gdt[0] = t->tls_array[0];
+ gdt[1] = t->tls_array[1];
+ gdt[2] = t->tls_array[2];
+#endif
+#define C(i) \
+
HYPERVISOR_update_descriptor(virt_to_machine(&get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN
+ i]), t->tls_array[i])
+
+ C(0); C(1); C(2);
+#undef C
+}
+
+/*
+ * load one particular LDT into the current CPU
+ */
+extern inline void load_LDT_nolock (mm_context_t *pc, int cpu)
+{
+ void *segments = pc->ldt;
+ int count = pc->size;
+
+ if (likely(!count))
+ segments = NULL;
+
+ xen_set_ldt((unsigned long)segments, count);
+}
+
+static inline void load_LDT(mm_context_t *pc)
+{
+ int cpu = get_cpu();
+ load_LDT_nolock(pc, cpu);
+ put_cpu();
+}
+
+extern struct desc_ptr idt_descr;
+
+#endif /* !__ASSEMBLY__ */
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/mm/fault.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/mm/fault.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,561 @@
+/*
+ * linux/arch/i386/mm/fault.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ */
+
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/tty.h>
+#include <linux/vt_kern.h> /* For unblank_screen() */
+#include <linux/highmem.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/desc.h>
+#include <asm/kdebug.h>
+
+extern void die(const char *,struct pt_regs *,long);
+
+DEFINE_PER_CPU(pgd_t *, cur_pgd);
+
+/*
+ * Unlock any spinlocks which will prevent us from getting the
+ * message out
+ */
+void bust_spinlocks(int yes)
+{
+ int loglevel_save = console_loglevel;
+
+ if (yes) {
+ oops_in_progress = 1;
+ return;
+ }
+#ifdef CONFIG_VT
+ unblank_screen();
+#endif
+ oops_in_progress = 0;
+ /*
+ * OK, the message is on the console. Now we call printk()
+ * without oops_in_progress set so that printk will give klogd
+ * a poke. Hold onto your hats...
+ */
+ console_loglevel = 15; /* NMI oopser may have shut the console
up */
+ printk(" ");
+ console_loglevel = loglevel_save;
+}
+
+/*
+ * Return EIP plus the CS segment base. The segment limit is also
+ * adjusted, clamped to the kernel/user address space (whichever is
+ * appropriate), and returned in *eip_limit.
+ *
+ * The segment is checked, because it might have been changed by another
+ * task between the original faulting instruction and here.
+ *
+ * If CS is no longer a valid code segment, or if EIP is beyond the
+ * limit, or if it is a kernel address when CS is not a kernel segment,
+ * then the returned value will be greater than *eip_limit.
+ *
+ * This is slow, but is very rarely executed.
+ */
+static inline unsigned long get_segment_eip(struct pt_regs *regs,
+ unsigned long *eip_limit)
+{
+ unsigned long eip = regs->eip;
+ unsigned seg = regs->xcs & 0xffff;
+ u32 seg_ar, seg_limit, base, *desc;
+
+ /* The standard kernel/user address space limit. */
+ *eip_limit = (seg & 2) ? USER_DS.seg : KERNEL_DS.seg;
+
+ /* Unlikely, but must come before segment checks. */
+ if (unlikely((regs->eflags & VM_MASK) != 0))
+ return eip + (seg << 4);
+
+ /* By far the most common cases. */
+ if (likely(seg == __USER_CS || seg == __KERNEL_CS))
+ return eip;
+
+ /* Check the segment exists, is within the current LDT/GDT size,
+ that kernel/user (ring 0..3) has the appropriate privilege,
+ that it's a code segment, and get the limit. */
+ __asm__ ("larl %3,%0; lsll %3,%1"
+ : "=&r" (seg_ar), "=r" (seg_limit) : "0" (0), "rm" (seg));
+ if ((~seg_ar & 0x9800) || eip > seg_limit) {
+ *eip_limit = 0;
+ return 1; /* So that returned eip > *eip_limit. */
+ }
+
+ /* Get the GDT/LDT descriptor base.
+ When you look for races in this code remember that
+ LDT and other horrors are only used in user space. */
+ if (seg & (1<<2)) {
+ /* Must lock the LDT while reading it. */
+ down(¤t->mm->context.sem);
+ desc = current->mm->context.ldt;
+ desc = (void *)desc + (seg & ~7);
+ } else {
+ /* Must disable preemption while reading the GDT. */
+ desc = (u32 *)get_cpu_gdt_table(get_cpu());
+ desc = (void *)desc + (seg & ~7);
+ }
+
+ /* Decode the code segment base from the descriptor */
+ base = get_desc_base((unsigned long *)desc);
+
+ if (seg & (1<<2)) {
+ up(¤t->mm->context.sem);
+ } else
+ put_cpu();
+
+ /* Adjust EIP and segment limit, and clamp at the kernel limit.
+ It's legitimate for segments to wrap at 0xffffffff. */
+ seg_limit += base;
+ if (seg_limit < *eip_limit && seg_limit >= base)
+ *eip_limit = seg_limit;
+ return eip + base;
+}
+
+/*
+ * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch.
+ * Check that here and ignore it.
+ */
+static int __is_prefetch(struct pt_regs *regs, unsigned long addr)
+{
+ unsigned long limit;
+ unsigned long instr = get_segment_eip (regs, &limit);
+ int scan_more = 1;
+ int prefetch = 0;
+ int i;
+
+ for (i = 0; scan_more && i < 15; i++) {
+ unsigned char opcode;
+ unsigned char instr_hi;
+ unsigned char instr_lo;
+
+ if (instr > limit)
+ break;
+ if (__get_user(opcode, (unsigned char *) instr))
+ break;
+
+ instr_hi = opcode & 0xf0;
+ instr_lo = opcode & 0x0f;
+ instr++;
+
+ switch (instr_hi) {
+ case 0x20:
+ case 0x30:
+ /* Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes. */
+ scan_more = ((instr_lo & 7) == 0x6);
+ break;
+
+ case 0x60:
+ /* 0x64 thru 0x67 are valid prefixes in all modes. */
+ scan_more = (instr_lo & 0xC) == 0x4;
+ break;
+ case 0xF0:
+ /* 0xF0, 0xF2, and 0xF3 are valid prefixes */
+ scan_more = !instr_lo || (instr_lo>>1) == 1;
+ break;
+ case 0x00:
+ /* Prefetch instruction is 0x0F0D or 0x0F18 */
+ scan_more = 0;
+ if (instr > limit)
+ break;
+ if (__get_user(opcode, (unsigned char *) instr))
+ break;
+ prefetch = (instr_lo == 0xF) &&
+ (opcode == 0x0D || opcode == 0x18);
+ break;
+ default:
+ scan_more = 0;
+ break;
+ }
+ }
+ return prefetch;
+}
+
+static inline int is_prefetch(struct pt_regs *regs, unsigned long addr,
+ unsigned long error_code)
+{
+ if (unlikely(boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
+ boot_cpu_data.x86 >= 6)) {
+ /* Catch an obscure case of prefetch inside an NX page. */
+ if (nx_enabled && (error_code & 16))
+ return 0;
+ return __is_prefetch(regs, addr);
+ }
+ return 0;
+}
+
+fastcall void do_invalid_op(struct pt_regs *, unsigned long);
+
+/*
+ * This routine handles page faults. It determines the address,
+ * and the problem, and then passes it off to one of the appropriate
+ * routines.
+ *
+ * error_code:
+ * bit 0 == 0 means no page found, 1 means protection fault
+ * bit 1 == 0 means read, 1 means write
+ * bit 2 == 0 means kernel, 1 means user-mode
+ */
+fastcall void do_page_fault(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
+{
+ struct task_struct *tsk;
+ struct mm_struct *mm;
+ struct vm_area_struct * vma;
+ unsigned long page;
+ int write;
+ siginfo_t info;
+
+ /* Set the "privileged fault" bit to something sane. */
+ error_code &= 3;
+ error_code |= (regs->xcs & 2) << 1;
+ if (regs->eflags & X86_EFLAGS_VM)
+ error_code |= 4;
+
+ if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
+ SIGSEGV) == NOTIFY_STOP)
+ return;
+#if 0
+ /* It's safe to allow irq's after cr2 has been saved */
+ if (regs->eflags & (X86_EFLAGS_IF|VM_MASK))
+ local_irq_enable();
+#endif
+
+ tsk = current;
+
+ info.si_code = SEGV_MAPERR;
+
+ /*
+ * We fault-in kernel-space virtual memory on-demand. The
+ * 'reference' page table is init_mm.pgd.
+ *
+ * NOTE! We MUST NOT take any locks for this case. We may
+ * be in an interrupt or a critical region, and should
+ * only copy the information from the master page table,
+ * nothing more.
+ *
+ * This verifies that the fault happens in kernel space
+ * (error_code & 4) == 0, and that the fault was not a
+ * protection error (error_code & 1) == 0.
+ */
+ if (unlikely(address >= TASK_SIZE)) {
+ if (!(error_code & 5))
+ goto vmalloc_fault;
+ /*
+ * Don't take the mm semaphore here. If we fixup a prefetch
+ * fault we could otherwise deadlock.
+ */
+ goto bad_area_nosemaphore;
+ }
+
+ mm = tsk->mm;
+
+ /*
+ * If we're in an interrupt, have no user context or are running in an
+ * atomic region then we must not take the fault..
+ */
+ if (in_atomic() || !mm)
+ goto bad_area_nosemaphore;
+
+ /* When running in the kernel we expect faults to occur only to
+ * addresses in user space. All other faults represent errors in the
+ * kernel and should generate an OOPS. Unfortunatly, in the case of an
+ * erroneous fault occuring in a code path which already holds mmap_sem
+ * we will deadlock attempting to validate the fault against the
+ * address space. Luckily the kernel only validly references user
+ * space from well defined areas of code, which are listed in the
+ * exceptions table.
+ *
+ * As the vast majority of faults will be valid we will only perform
+ * the source reference check when there is a possibilty of a deadlock.
+ * Attempt to lock the address space, if we cannot we then validate the
+ * source. If this is invalid we can skip the address space check,
+ * thus avoiding the deadlock.
+ */
+ if (!down_read_trylock(&mm->mmap_sem)) {
+ if ((error_code & 4) == 0 &&
+ !search_exception_tables(regs->eip))
+ goto bad_area_nosemaphore;
+ down_read(&mm->mmap_sem);
+ }
+
+ vma = find_vma(mm, address);
+ if (!vma)
+ goto bad_area;
+ if (vma->vm_start <= address)
+ goto good_area;
+ if (!(vma->vm_flags & VM_GROWSDOWN))
+ goto bad_area;
+ if (error_code & 4) {
+ /*
+ * accessing the stack below %esp is always a bug.
+ * The "+ 32" is there due to some instructions (like
+ * pusha) doing post-decrement on the stack and that
+ * doesn't show up until later..
+ */
+ if (address + 32 < regs->esp)
+ goto bad_area;
+ }
+ if (expand_stack(vma, address))
+ goto bad_area;
+/*
+ * Ok, we have a good vm_area for this memory access, so
+ * we can handle it..
+ */
+good_area:
+ info.si_code = SEGV_ACCERR;
+ write = 0;
+ switch (error_code & 3) {
+ default: /* 3: write, present */
+#ifdef TEST_VERIFY_AREA
+ if (regs->cs == KERNEL_CS)
+ printk("WP fault at %08lx\n", regs->eip);
+#endif
+ /* fall through */
+ case 2: /* write, not present */
+ if (!(vma->vm_flags & VM_WRITE))
+ goto bad_area;
+ write++;
+ break;
+ case 1: /* read, present */
+ goto bad_area;
+ case 0: /* read, not present */
+ if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+ goto bad_area;
+ }
+
+ survive:
+ /*
+ * If for any reason at all we couldn't handle the fault,
+ * make sure we exit gracefully rather than endlessly redo
+ * the fault.
+ */
+ switch (handle_mm_fault(mm, vma, address, write)) {
+ case VM_FAULT_MINOR:
+ tsk->min_flt++;
+ break;
+ case VM_FAULT_MAJOR:
+ tsk->maj_flt++;
+ break;
+ case VM_FAULT_SIGBUS:
+ goto do_sigbus;
+ case VM_FAULT_OOM:
+ goto out_of_memory;
+ default:
+ BUG();
+ }
+
+ /*
+ * Did it hit the DOS screen memory VA from vm86 mode?
+ */
+ if (regs->eflags & VM_MASK) {
+ unsigned long bit = (address - 0xA0000) >> PAGE_SHIFT;
+ if (bit < 32)
+ tsk->thread.screen_bitmap |= 1 << bit;
+ }
+ up_read(&mm->mmap_sem);
+ return;
+
+/*
+ * Something tried to access memory that isn't in our memory map..
+ * Fix it, but check if it's kernel or user first..
+ */
+bad_area:
+ up_read(&mm->mmap_sem);
+
+bad_area_nosemaphore:
+ /* User mode accesses just cause a SIGSEGV */
+ if (error_code & 4) {
+ /*
+ * Valid to do another page fault here because this one came
+ * from user space.
+ */
+ if (is_prefetch(regs, address, error_code))
+ return;
+
+ tsk->thread.cr2 = address;
+ /* Kernel addresses are always protection faults */
+ tsk->thread.error_code = error_code | (address >= TASK_SIZE);
+ tsk->thread.trap_no = 14;
+ info.si_signo = SIGSEGV;
+ info.si_errno = 0;
+ /* info.si_code has been set above */
+ info.si_addr = (void __user *)address;
+ force_sig_info(SIGSEGV, &info, tsk);
+ return;
+ }
+
+#ifdef CONFIG_X86_F00F_BUG
+ /*
+ * Pentium F0 0F C7 C8 bug workaround.
+ */
+ if (boot_cpu_data.f00f_bug) {
+ unsigned long nr;
+
+ nr = (address - idt_descr.address) >> 3;
+
+ if (nr == 6) {
+ do_invalid_op(regs, 0);
+ return;
+ }
+ }
+#endif
+
+no_context:
+ /* Are we prepared to handle this kernel fault? */
+ if (fixup_exception(regs))
+ return;
+
+ /*
+ * Valid to do another page fault here, because if this fault
+ * had been triggered by is_prefetch fixup_exception would have
+ * handled it.
+ */
+ if (is_prefetch(regs, address, error_code))
+ return;
+
+/*
+ * Oops. The kernel tried to access some bad page. We'll have to
+ * terminate things with extreme prejudice.
+ */
+
+ bust_spinlocks(1);
+
+#ifdef CONFIG_X86_PAE
+ if (error_code & 16) {
+ pte_t *pte = lookup_address(address);
+
+ if (pte && pte_present(*pte) && !pte_exec_kernel(*pte))
+ printk(KERN_CRIT "kernel tried to execute NX-protected
page - exploit attempt? (uid: %d)\n", current->uid);
+ }
+#endif
+ if (address < PAGE_SIZE)
+ printk(KERN_ALERT "Unable to handle kernel NULL pointer
dereference");
+ else
+ printk(KERN_ALERT "Unable to handle kernel paging request");
+ printk(" at virtual address %08lx\n",address);
+ printk(KERN_ALERT " printing eip:\n");
+ printk("%08lx\n", regs->eip);
+ page = ((unsigned long *) per_cpu(cur_pgd, smp_processor_id()))
+ [address >> 22];
+ printk(KERN_ALERT "*pde = ma %08lx pa %08lx\n", page,
+ machine_to_phys(page));
+ /*
+ * We must not directly access the pte in the highpte
+ * case, the page table might be allocated in highmem.
+ * And lets rather not kmap-atomic the pte, just in case
+ * it's allocated already.
+ */
+#ifndef CONFIG_HIGHPTE
+ if (page & 1) {
+ page &= PAGE_MASK;
+ address &= 0x003ff000;
+ page = machine_to_phys(page);
+ page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT];
+ printk(KERN_ALERT "*pte = ma %08lx pa %08lx\n", page,
+ machine_to_phys(page));
+ }
+#endif
+ die("Oops", regs, error_code);
+ bust_spinlocks(0);
+ do_exit(SIGKILL);
+
+/*
+ * We ran out of memory, or some other thing happened to us that made
+ * us unable to handle the page fault gracefully.
+ */
+out_of_memory:
+ up_read(&mm->mmap_sem);
+ if (tsk->pid == 1) {
+ yield();
+ down_read(&mm->mmap_sem);
+ goto survive;
+ }
+ printk("VM: killing process %s\n", tsk->comm);
+ if (error_code & 4)
+ do_exit(SIGKILL);
+ goto no_context;
+
+do_sigbus:
+ up_read(&mm->mmap_sem);
+
+ /* Kernel mode? Handle exceptions or die */
+ if (!(error_code & 4))
+ goto no_context;
+
+ /* User space => ok to do another page fault */
+ if (is_prefetch(regs, address, error_code))
+ return;
+
+ tsk->thread.cr2 = address;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = 14;
+ info.si_signo = SIGBUS;
+ info.si_errno = 0;
+ info.si_code = BUS_ADRERR;
+ info.si_addr = (void __user *)address;
+ force_sig_info(SIGBUS, &info, tsk);
+ return;
+
+vmalloc_fault:
+ {
+ /*
+ * Synchronize this task's top level page-table
+ * with the 'reference' page table.
+ *
+ * Do _not_ use "tsk" here. We might be inside
+ * an interrupt in the middle of a task switch..
+ */
+ int index = pgd_index(address);
+ pgd_t *pgd, *pgd_k;
+ pud_t *pud, *pud_k;
+ pmd_t *pmd, *pmd_k;
+ pte_t *pte_k;
+
+ pgd = index + per_cpu(cur_pgd, smp_processor_id());
+ pgd_k = init_mm.pgd + index;
+
+ if (!pgd_present(*pgd_k))
+ goto no_context;
+
+ /*
+ * set_pgd(pgd, *pgd_k); here would be useless on PAE
+ * and redundant with the set_pmd() on non-PAE. As would
+ * set_pud.
+ */
+
+ pud = pud_offset(pgd, address);
+ pud_k = pud_offset(pgd_k, address);
+ if (!pud_present(*pud_k))
+ goto no_context;
+
+ pmd = pmd_offset(pud, address);
+ pmd_k = pmd_offset(pud_k, address);
+ if (!pmd_present(*pmd_k))
+ goto no_context;
+ set_pmd(pmd, *pmd_k);
+
+ pte_k = pte_offset_kernel(pmd_k, address);
+ if (!pte_present(*pte_k))
+ goto no_context;
+ return;
+ }
+}
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/include/linux/mm.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/linux/mm.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,727 @@
+#ifndef _LINUX_MM_H
+#define _LINUX_MM_H
+
+#include <linux/sched.h>
+#include <linux/errno.h>
+
+#ifdef __KERNEL__
+
+#include <linux/config.h>
+#include <linux/string.h>
+#include <linux/list.h>
+#include <linux/mmzone.h>
+#include <linux/swap.h>
+#include <linux/rbtree.h>
+
+extern unsigned long max_mapnr;
+extern unsigned long num_physpages;
+extern unsigned long num_mappedpages;
+extern void * high_memory;
+extern int page_cluster;
+/* The inactive_clean lists are per zone. */
+extern struct list_head active_list;
+extern struct list_head inactive_list;
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/atomic.h>
+
+/*
+ * Linux kernel virtual memory manager primitives.
+ * The idea being to have a "virtual" mm in the same way
+ * we have a virtual fs - giving a cleaner interface to the
+ * mm details, and allowing different kinds of memory mappings
+ * (from shared memory to executable loading to arbitrary
+ * mmap() functions).
+ */
+
+/*
+ * This struct defines a memory VMM memory area. There is one of these
+ * per VM-area/task. A VM area is any part of the process virtual memory
+ * space that has a special rule for the page-fault handlers (ie a shared
+ * library, the executable area etc).
+ */
+struct vm_area_struct {
+ struct mm_struct * vm_mm; /* The address space we belong to. */
+ unsigned long vm_start; /* Our start address within vm_mm. */
+ unsigned long vm_end; /* The first byte after our end address
+ within vm_mm. */
+
+ /* linked list of VM areas per task, sorted by address */
+ struct vm_area_struct *vm_next;
+
+ pgprot_t vm_page_prot; /* Access permissions of this VMA. */
+ unsigned long vm_flags; /* Flags, listed below. */
+
+ rb_node_t vm_rb;
+
+ /*
+ * For areas with an address space and backing store,
+ * one of the address_space->i_mmap{,shared} lists,
+ * for shm areas, the list of attaches, otherwise unused.
+ */
+ struct vm_area_struct *vm_next_share;
+ struct vm_area_struct **vm_pprev_share;
+
+ /* Function pointers to deal with this struct. */
+ struct vm_operations_struct * vm_ops;
+
+ /* Information about our backing store: */
+ unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE
+ units, *not* PAGE_CACHE_SIZE */
+ struct file * vm_file; /* File we map to (can be NULL). */
+ unsigned long vm_raend; /* XXX: put full readahead info here. */
+ void * vm_private_data; /* was vm_pte (shared mem) */
+};
+
+/*
+ * vm_flags..
+ */
+#define VM_READ 0x00000001 /* currently active flags */
+#define VM_WRITE 0x00000002
+#define VM_EXEC 0x00000004
+#define VM_SHARED 0x00000008
+
+#define VM_MAYREAD 0x00000010 /* limits for mprotect() etc */
+#define VM_MAYWRITE 0x00000020
+#define VM_MAYEXEC 0x00000040
+#define VM_MAYSHARE 0x00000080
+
+#define VM_GROWSDOWN 0x00000100 /* general info on the segment */
+#define VM_GROWSUP 0x00000200
+#define VM_SHM 0x00000400 /* shared memory area, don't swap out */
+#define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */
+
+#define VM_EXECUTABLE 0x00001000
+#define VM_LOCKED 0x00002000
+#define VM_IO 0x00004000 /* Memory mapped I/O or similar */
+
+ /* Used by sys_madvise() */
+#define VM_SEQ_READ 0x00008000 /* App will access data sequentially */
+#define VM_RAND_READ 0x00010000 /* App will not benefit from clustered
reads */
+
+#define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */
+#define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */
+#define VM_RESERVED 0x00080000 /* Don't unmap it from swap_out */
+
+#ifndef VM_STACK_FLAGS
+#define VM_STACK_FLAGS 0x00000177
+#endif
+
+#define VM_READHINTMASK (VM_SEQ_READ | VM_RAND_READ)
+#define VM_ClearReadHint(v) (v)->vm_flags &= ~VM_READHINTMASK
+#define VM_NormalReadHint(v) (!((v)->vm_flags & VM_READHINTMASK))
+#define VM_SequentialReadHint(v) ((v)->vm_flags & VM_SEQ_READ)
+#define VM_RandomReadHint(v) ((v)->vm_flags & VM_RAND_READ)
+
+/* read ahead limits */
+extern int vm_min_readahead;
+extern int vm_max_readahead;
+
+/*
+ * mapping from the currently active vm_flags protection bits (the
+ * low four bits) to a page protection mask..
+ */
+extern pgprot_t protection_map[16];
+
+
+/*
+ * These are the virtual MM functions - opening of an area, closing and
+ * unmapping it (needed to keep files on disk up-to-date etc), pointer
+ * to the functions called when a no-page or a wp-page exception occurs.
+ */
+struct vm_operations_struct {
+ void (*open)(struct vm_area_struct * area);
+ void (*close)(struct vm_area_struct * area);
+ struct page * (*nopage)(struct vm_area_struct * area, unsigned long
address, int unused);
+};
+
+/*
+ * Each physical page in the system has a struct page associated with
+ * it to keep track of whatever it is we are using the page for at the
+ * moment. Note that we have no way to track which tasks are using
+ * a page.
+ *
+ * Try to keep the most commonly accessed fields in single cache lines
+ * here (16 bytes or greater). This ordering should be particularly
+ * beneficial on 32-bit processors.
+ *
+ * The first line is data used in page cache lookup, the second line
+ * is used for linear searches (eg. clock algorithm scans).
+ *
+ * TODO: make this structure smaller, it could be as small as 32 bytes.
+ */
+typedef struct page {
+ struct list_head list; /* ->mapping has some page lists. */
+ struct address_space *mapping; /* The inode (or ...) we belong to. */
+ unsigned long index; /* Our offset within mapping. */
+ struct page *next_hash; /* Next page sharing our hash bucket in
+ the pagecache hash table. */
+ atomic_t count; /* Usage count, see below. */
+ unsigned long flags; /* atomic flags, some possibly
+ updated asynchronously */
+ struct list_head lru; /* Pageout list, eg. active_list;
+ protected by pagemap_lru_lock !! */
+ struct page **pprev_hash; /* Complement to *next_hash. */
+ struct buffer_head * buffers; /* Buffer maps us to a disk block. */
+
+ /*
+ * On machines where all RAM is mapped into kernel address space,
+ * we can simply calculate the virtual address. On machines with
+ * highmem some memory is mapped into kernel virtual memory
+ * dynamically, so we need a place to store that address.
+ * Note that this field could be 16 bits on x86 ... ;)
+ *
+ * Architectures with slow multiplication can define
+ * WANT_PAGE_VIRTUAL in asm/page.h
+ */
+#if defined(CONFIG_HIGHMEM) || defined(WANT_PAGE_VIRTUAL)
+ void *virtual; /* Kernel virtual address (NULL if
+ not kmapped, ie. highmem) */
+#endif /* CONFIG_HIGMEM || WANT_PAGE_VIRTUAL */
+} mem_map_t;
+
+/*
+ * Methods to modify the page usage count.
+ *
+ * What counts for a page usage:
+ * - cache mapping (page->mapping)
+ * - disk mapping (page->buffers)
+ * - page mapped in a task's page tables, each mapping
+ * is counted separately
+ *
+ * Also, many kernel routines increase the page count before a critical
+ * routine so they can be sure the page doesn't go away from under them.
+ */
+#define get_page(p) atomic_inc(&(p)->count)
+#define put_page(p) __free_page(p)
+#define put_page_testzero(p) atomic_dec_and_test(&(p)->count)
+#define page_count(p) atomic_read(&(p)->count)
+#define set_page_count(p,v) atomic_set(&(p)->count, v)
+
+static inline struct page *nth_page(struct page *page, int n)
+{
+ return page + n;
+}
+
+/*
+ * Various page->flags bits:
+ *
+ * PG_reserved is set for special pages, which can never be swapped
+ * out. Some of them might not even exist (eg empty_bad_page)...
+ *
+ * Multiple processes may "see" the same page. E.g. for untouched
+ * mappings of /dev/null, all processes see the same page full of
+ * zeroes, and text pages of executables and shared libraries have
+ * only one copy in memory, at most, normally.
+ *
+ * For the non-reserved pages, page->count denotes a reference count.
+ * page->count == 0 means the page is free.
+ * page->count == 1 means the page is used for exactly one purpose
+ * (e.g. a private data page of one process).
+ *
+ * A page may be used for kmalloc() or anyone else who does a
+ * __get_free_page(). In this case the page->count is at least 1, and
+ * all other fields are unused but should be 0 or NULL. The
+ * management of this page is the responsibility of the one who uses
+ * it.
+ *
+ * The other pages (we may call them "process pages") are completely
+ * managed by the Linux memory manager: I/O, buffers, swapping etc.
+ * The following discussion applies only to them.
+ *
+ * A page may belong to an inode's memory mapping. In this case,
+ * page->mapping is the pointer to the inode, and page->index is the
+ * file offset of the page, in units of PAGE_CACHE_SIZE.
+ *
+ * A page may have buffers allocated to it. In this case,
+ * page->buffers is a circular list of these buffer heads. Else,
+ * page->buffers == NULL.
+ *
+ * For pages belonging to inodes, the page->count is the number of
+ * attaches, plus 1 if buffers are allocated to the page, plus one
+ * for the page cache itself.
+ *
+ * All pages belonging to an inode are in these doubly linked lists:
+ * mapping->clean_pages, mapping->dirty_pages and mapping->locked_pages;
+ * using the page->list list_head. These fields are also used for
+ * freelist managemet (when page->count==0).
+ *
+ * There is also a hash table mapping (mapping,index) to the page
+ * in memory if present. The lists for this hash table use the fields
+ * page->next_hash and page->pprev_hash.
+ *
+ * All process pages can do I/O:
+ * - inode pages may need to be read from disk,
+ * - inode pages which have been modified and are MAP_SHARED may need
+ * to be written to disk,
+ * - private pages which have been modified may need to be swapped out
+ * to swap space and (later) to be read back into memory.
+ * During disk I/O, PG_locked is used. This bit is set before I/O
+ * and reset when I/O completes. page_waitqueue(page) is a wait queue of all
+ * tasks waiting for the I/O on this page to complete.
+ * PG_uptodate tells whether the page's contents is valid.
+ * When a read completes, the page becomes uptodate, unless a disk I/O
+ * error happened.
+ *
+ * For choosing which pages to swap out, inode pages carry a
+ * PG_referenced bit, which is set any time the system accesses
+ * that page through the (mapping,index) hash table. This referenced
+ * bit, together with the referenced bit in the page tables, is used
+ * to manipulate page->age and move the page across the active,
+ * inactive_dirty and inactive_clean lists.
+ *
+ * Note that the referenced bit, the page->lru list_head and the
+ * active, inactive_dirty and inactive_clean lists are protected by
+ * the pagemap_lru_lock, and *NOT* by the usual PG_locked bit!
+ *
+ * PG_skip is used on sparc/sparc64 architectures to "skip" certain
+ * parts of the address space.
+ *
+ * PG_error is set to indicate that an I/O error occurred on this page.
+ *
+ * PG_arch_1 is an architecture specific page state bit. The generic
+ * code guarantees that this bit is cleared for a page when it first
+ * is entered into the page cache.
+ *
+ * PG_highmem pages are not permanently mapped into the kernel virtual
+ * address space, they need to be kmapped separately for doing IO on
+ * the pages. The struct page (these bits with information) are always
+ * mapped into kernel address space...
+ */
+#define PG_locked 0 /* Page is locked. Don't touch. */
+#define PG_error 1
+#define PG_referenced 2
+#define PG_uptodate 3
+#define PG_dirty 4
+#define PG_unused 5
+#define PG_lru 6
+#define PG_active 7
+#define PG_slab 8
+#define PG_skip 10
+#define PG_highmem 11
+#define PG_checked 12 /* kill me in 2.5.<early>. */
+#define PG_arch_1 13
+#define PG_reserved 14
+#define PG_launder 15 /* written out by VM pressure.. */
+#define PG_fs_1 16 /* Filesystem specific */
+#define PG_foreign 21 /* Page belongs to foreign allocator */
+
+#ifndef arch_set_page_uptodate
+#define arch_set_page_uptodate(page)
+#endif
+
+/* Make it prettier to test the above... */
+#define UnlockPage(page) unlock_page(page)
+#define Page_Uptodate(page) test_bit(PG_uptodate, &(page)->flags)
+#ifndef SetPageUptodate
+#define SetPageUptodate(page) set_bit(PG_uptodate, &(page)->flags)
+#endif
+#define ClearPageUptodate(page) clear_bit(PG_uptodate, &(page)->flags)
+#define PageDirty(page) test_bit(PG_dirty, &(page)->flags)
+#define SetPageDirty(page) set_bit(PG_dirty, &(page)->flags)
+#define ClearPageDirty(page) clear_bit(PG_dirty, &(page)->flags)
+#define PageLocked(page) test_bit(PG_locked, &(page)->flags)
+#define LockPage(page) set_bit(PG_locked, &(page)->flags)
+#define TryLockPage(page) test_and_set_bit(PG_locked, &(page)->flags)
+#define PageChecked(page) test_bit(PG_checked, &(page)->flags)
+#define SetPageChecked(page) set_bit(PG_checked, &(page)->flags)
+#define ClearPageChecked(page) clear_bit(PG_checked, &(page)->flags)
+#define PageLaunder(page) test_bit(PG_launder, &(page)->flags)
+#define SetPageLaunder(page) set_bit(PG_launder, &(page)->flags)
+#define ClearPageLaunder(page) clear_bit(PG_launder, &(page)->flags)
+#define ClearPageArch1(page) clear_bit(PG_arch_1, &(page)->flags)
+
+/* A foreign page uses a custom destructor rather than the buddy allocator. */
+#ifdef CONFIG_FOREIGN_PAGES
+#define PageForeign(page) test_bit(PG_foreign, &(page)->flags)
+#define SetPageForeign(page, dtor) do { \
+ set_bit(PG_foreign, &(page)->flags); \
+ (page)->mapping = (void *)dtor; \
+} while (0)
+#define ClearPageForeign(page) do { \
+ clear_bit(PG_foreign, &(page)->flags); \
+ (page)->mapping = NULL; \
+} while (0)
+#define PageForeignDestructor(page) \
+ ( (void (*) (struct page *)) (page)->mapping )
+#else
+#define PageForeign(page) 0
+#define PageForeignDestructor(page) void
+#endif
+
+/*
+ * The zone field is never updated after free_area_init_core()
+ * sets it, so none of the operations on it need to be atomic.
+ */
+#define NODE_SHIFT 4
+#define ZONE_SHIFT (BITS_PER_LONG - 8)
+
+struct zone_struct;
+extern struct zone_struct *zone_table[];
+
+static inline zone_t *page_zone(struct page *page)
+{
+ return zone_table[page->flags >> ZONE_SHIFT];
+}
+
+static inline void set_page_zone(struct page *page, unsigned long zone_num)
+{
+ page->flags &= ~(~0UL << ZONE_SHIFT);
+ page->flags |= zone_num << ZONE_SHIFT;
+}
+
+/*
+ * In order to avoid #ifdefs within C code itself, we define
+ * set_page_address to a noop for non-highmem machines, where
+ * the field isn't useful.
+ * The same is true for page_address() in arch-dependent code.
+ */
+#if defined(CONFIG_HIGHMEM) || defined(WANT_PAGE_VIRTUAL)
+
+#define set_page_address(page, address) \
+ do { \
+ (page)->virtual = (address); \
+ } while(0)
+
+#else /* CONFIG_HIGHMEM || WANT_PAGE_VIRTUAL */
+#define set_page_address(page, address) do { } while(0)
+#endif /* CONFIG_HIGHMEM || WANT_PAGE_VIRTUAL */
+
+/*
+ * Permanent address of a page. Obviously must never be
+ * called on a highmem page.
+ */
+#if defined(CONFIG_HIGHMEM) || defined(WANT_PAGE_VIRTUAL)
+
+#define page_address(page) ((page)->virtual)
+
+#else /* CONFIG_HIGHMEM || WANT_PAGE_VIRTUAL */
+
+#define page_address(page) \
+ __va( (((page) - page_zone(page)->zone_mem_map) << PAGE_SHIFT) \
+ + page_zone(page)->zone_start_paddr)
+
+#endif /* CONFIG_HIGHMEM || WANT_PAGE_VIRTUAL */
+
+extern void FASTCALL(set_page_dirty(struct page *));
+
+/*
+ * The first mb is necessary to safely close the critical section opened by the
+ * TryLockPage(), the second mb is necessary to enforce ordering between
+ * the clear_bit and the read of the waitqueue (to avoid SMP races with a
+ * parallel wait_on_page).
+ */
+#define PageError(page) test_bit(PG_error, &(page)->flags)
+#define SetPageError(page) set_bit(PG_error, &(page)->flags)
+#define ClearPageError(page) clear_bit(PG_error, &(page)->flags)
+#define PageReferenced(page) test_bit(PG_referenced, &(page)->flags)
+#define SetPageReferenced(page) set_bit(PG_referenced, &(page)->flags)
+#define ClearPageReferenced(page) clear_bit(PG_referenced, &(page)->flags)
+#define PageTestandClearReferenced(page)
test_and_clear_bit(PG_referenced, &(page)->flags)
+#define PageSlab(page) test_bit(PG_slab, &(page)->flags)
+#define PageSetSlab(page) set_bit(PG_slab, &(page)->flags)
+#define PageClearSlab(page) clear_bit(PG_slab, &(page)->flags)
+#define PageReserved(page) test_bit(PG_reserved, &(page)->flags)
+
+#define PageActive(page) test_bit(PG_active, &(page)->flags)
+#define SetPageActive(page) set_bit(PG_active, &(page)->flags)
+#define ClearPageActive(page) clear_bit(PG_active, &(page)->flags)
+
+#define PageLRU(page) test_bit(PG_lru, &(page)->flags)
+#define TestSetPageLRU(page) test_and_set_bit(PG_lru, &(page)->flags)
+#define TestClearPageLRU(page) test_and_clear_bit(PG_lru, &(page)->flags)
+
+#ifdef CONFIG_HIGHMEM
+#define PageHighMem(page) test_bit(PG_highmem, &(page)->flags)
+#else
+#define PageHighMem(page) 0 /* needed to optimize away at compile
time */
+#endif
+
+#define SetPageReserved(page) set_bit(PG_reserved, &(page)->flags)
+#define ClearPageReserved(page) clear_bit(PG_reserved,
&(page)->flags)
+
+/*
+ * Error return values for the *_nopage functions
+ */
+#define NOPAGE_SIGBUS (NULL)
+#define NOPAGE_OOM ((struct page *) (-1))
+
+/* The array of struct pages */
+extern mem_map_t * mem_map;
+
+/*
+ * There is only one page-allocator function, and two main namespaces to
+ * it. The alloc_page*() variants return 'struct page *' and as such
+ * can allocate highmem pages, the *get*page*() variants return
+ * virtual kernel addresses to the allocated page(s).
+ */
+extern struct page * FASTCALL(_alloc_pages(unsigned int gfp_mask, unsigned int
order));
+extern struct page * FASTCALL(__alloc_pages(unsigned int gfp_mask, unsigned
int order, zonelist_t *zonelist));
+extern struct page * alloc_pages_node(int nid, unsigned int gfp_mask, unsigned
int order);
+
+static inline struct page * alloc_pages(unsigned int gfp_mask, unsigned int
order)
+{
+ /*
+ * Gets optimized away by the compiler.
+ */
+ if (order >= MAX_ORDER)
+ return NULL;
+ return _alloc_pages(gfp_mask, order);
+}
+
+#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
+
+extern unsigned long FASTCALL(__get_free_pages(unsigned int gfp_mask, unsigned
int order));
+extern unsigned long FASTCALL(get_zeroed_page(unsigned int gfp_mask));
+
+#define __get_free_page(gfp_mask) \
+ __get_free_pages((gfp_mask),0)
+
+#define __get_dma_pages(gfp_mask, order) \
+ __get_free_pages((gfp_mask) | GFP_DMA,(order))
+
+/*
+ * The old interface name will be removed in 2.5:
+ */
+#define get_free_page get_zeroed_page
+
+/*
+ * There is only one 'core' page-freeing function.
+ */
+extern void FASTCALL(__free_pages(struct page *page, unsigned int order));
+extern void FASTCALL(free_pages(unsigned long addr, unsigned int order));
+
+#define __free_page(page) __free_pages((page), 0)
+#define free_page(addr) free_pages((addr),0)
+
+extern void show_free_areas(void);
+extern void show_free_areas_node(pg_data_t *pgdat);
+
+extern void clear_page_tables(struct mm_struct *, unsigned long, int);
+
+extern int fail_writepage(struct page *);
+struct page * shmem_nopage(struct vm_area_struct * vma, unsigned long address,
int unused);
+struct file *shmem_file_setup(char * name, loff_t size);
+extern void shmem_lock(struct file * file, int lock);
+extern int shmem_zero_setup(struct vm_area_struct *);
+
+extern void zap_page_range(struct mm_struct *mm, unsigned long address,
unsigned long size);
+extern int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
struct vm_area_struct *vma);
+extern int remap_page_range(unsigned long from, unsigned long to, unsigned
long size, pgprot_t prot);
+extern int zeromap_page_range(unsigned long from, unsigned long size, pgprot_t
prot);
+
+extern int vmtruncate(struct inode * inode, loff_t offset);
+extern pmd_t *FASTCALL(__pmd_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned
long address));
+extern pte_t *FASTCALL(pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned
long address));
+extern int handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma,
unsigned long address, int write_access);
+extern int make_pages_present(unsigned long addr, unsigned long end);
+extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void
*buf, int len, int write);
+extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char
*dst, int len);
+extern int ptrace_writedata(struct task_struct *tsk, char * src, unsigned long
dst, int len);
+extern int ptrace_attach(struct task_struct *tsk);
+extern int ptrace_detach(struct task_struct *, unsigned int);
+extern void ptrace_disable(struct task_struct *);
+extern int ptrace_check_attach(struct task_struct *task, int kill);
+
+int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned
long start,
+ int len, int write, int force, struct page **pages, struct
vm_area_struct **vmas);
+
+/*
+ * On a two-level page table, this ends up being trivial. Thus the
+ * inlining and the symmetry break with pte_alloc() that does all
+ * of this out-of-line.
+ */
+static inline pmd_t *pmd_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long
address)
+{
+ if (pgd_none(*pgd))
+ return __pmd_alloc(mm, pgd, address);
+ return pmd_offset(pgd, address);
+}
+
+extern int pgt_cache_water[2];
+extern int check_pgt_cache(void);
+
+extern void free_area_init(unsigned long * zones_size);
+extern void free_area_init_node(int nid, pg_data_t *pgdat, struct page *pmap,
+ unsigned long * zones_size, unsigned long zone_start_paddr,
+ unsigned long *zholes_size);
+extern void mem_init(void);
+extern void show_mem(void);
+extern void si_meminfo(struct sysinfo * val);
+extern void swapin_readahead(swp_entry_t);
+
+extern struct address_space swapper_space;
+#define PageSwapCache(page) ((page)->mapping == &swapper_space)
+
+static inline int is_page_cache_freeable(struct page * page)
+{
+ return page_count(page) - !!page->buffers == 1;
+}
+
+extern int FASTCALL(can_share_swap_page(struct page *));
+extern int FASTCALL(remove_exclusive_swap_page(struct page *));
+
+extern void __free_pte(pte_t);
+
+/* mmap.c */
+extern void lock_vma_mappings(struct vm_area_struct *);
+extern void unlock_vma_mappings(struct vm_area_struct *);
+extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
+extern void __insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
+extern void build_mmap_rb(struct mm_struct *);
+extern void exit_mmap(struct mm_struct *);
+
+extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned
long, unsigned long, unsigned long);
+
+extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long prot,
+ unsigned long flag, unsigned long pgoff);
+
+static inline unsigned long do_mmap(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long prot,
+ unsigned long flag, unsigned long offset)
+{
+ unsigned long ret = -EINVAL;
+ if ((offset + PAGE_ALIGN(len)) < offset)
+ goto out;
+ if (!(offset & ~PAGE_MASK))
+ ret = do_mmap_pgoff(file, addr, len, prot, flag, offset >>
PAGE_SHIFT);
+out:
+ return ret;
+}
+
+extern int do_munmap(struct mm_struct *, unsigned long, size_t);
+
+extern unsigned long do_brk(unsigned long, unsigned long);
+
+static inline void __vma_unlink(struct mm_struct * mm, struct vm_area_struct *
vma, struct vm_area_struct * prev)
+{
+ prev->vm_next = vma->vm_next;
+ rb_erase(&vma->vm_rb, &mm->mm_rb);
+ if (mm->mmap_cache == vma)
+ mm->mmap_cache = prev;
+}
+
+static inline int can_vma_merge(struct vm_area_struct * vma, unsigned long
vm_flags)
+{
+ if (!vma->vm_file && vma->vm_flags == vm_flags)
+ return 1;
+ else
+ return 0;
+}
+
+struct zone_t;
+/* filemap.c */
+extern void remove_inode_page(struct page *);
+extern unsigned long page_unuse(struct page *);
+extern void truncate_inode_pages(struct address_space *, loff_t);
+
+/* generic vm_area_ops exported for stackable file systems */
+extern int filemap_sync(struct vm_area_struct *, unsigned long, size_t,
unsigned int);
+extern struct page *filemap_nopage(struct vm_area_struct *, unsigned long,
int);
+
+/*
+ * GFP bitmasks..
+ */
+/* Zone modifiers in GFP_ZONEMASK (see linux/mmzone.h - low four bits) */
+#define __GFP_DMA 0x01
+#define __GFP_HIGHMEM 0x02
+
+/* Action modifiers - doesn't change the zoning */
+#define __GFP_WAIT 0x10 /* Can wait and reschedule? */
+#define __GFP_HIGH 0x20 /* Should access emergency pools? */
+#define __GFP_IO 0x40 /* Can start low memory physical IO? */
+#define __GFP_HIGHIO 0x80 /* Can start high mem physical IO? */
+#define __GFP_FS 0x100 /* Can call down to low-level FS? */
+
+#define GFP_NOHIGHIO (__GFP_HIGH | __GFP_WAIT | __GFP_IO)
+#define GFP_NOIO (__GFP_HIGH | __GFP_WAIT)
+#define GFP_NOFS (__GFP_HIGH | __GFP_WAIT | __GFP_IO | __GFP_HIGHIO)
+#define GFP_ATOMIC (__GFP_HIGH)
+#define GFP_USER ( __GFP_WAIT | __GFP_IO | __GFP_HIGHIO |
__GFP_FS)
+#define GFP_HIGHUSER ( __GFP_WAIT | __GFP_IO | __GFP_HIGHIO |
__GFP_FS | __GFP_HIGHMEM)
+#define GFP_KERNEL (__GFP_HIGH | __GFP_WAIT | __GFP_IO | __GFP_HIGHIO |
__GFP_FS)
+#define GFP_NFS (__GFP_HIGH | __GFP_WAIT | __GFP_IO |
__GFP_HIGHIO | __GFP_FS)
+#define GFP_KSWAPD ( __GFP_WAIT | __GFP_IO | __GFP_HIGHIO |
__GFP_FS)
+
+/* Flag - indicates that the buffer will be suitable for DMA. Ignored on some
+ platforms, used as appropriate on others */
+
+#define GFP_DMA __GFP_DMA
+
+static inline unsigned int pf_gfp_mask(unsigned int gfp_mask)
+{
+ /* avoid all memory balancing I/O methods if this task cannot block on
I/O */
+ if (current->flags & PF_NOIO)
+ gfp_mask &= ~(__GFP_IO | __GFP_HIGHIO | __GFP_FS);
+
+ return gfp_mask;
+}
+
+/* vma is the first one with address < vma->vm_end,
+ * and even address < vma->vm_start. Have to extend vma. */
+static inline int expand_stack(struct vm_area_struct * vma, unsigned long
address)
+{
+ unsigned long grow;
+
+ /*
+ * vma->vm_start/vm_end cannot change under us because the caller
+ * is required to hold the mmap_sem in read mode. We need the
+ * page_table_lock lock to serialize against concurrent expand_stacks.
+ */
+ address &= PAGE_MASK;
+ spin_lock(&vma->vm_mm->page_table_lock);
+
+ /* already expanded while we were spinning? */
+ if (vma->vm_start <= address) {
+ spin_unlock(&vma->vm_mm->page_table_lock);
+ return 0;
+ }
+
+ grow = (vma->vm_start - address) >> PAGE_SHIFT;
+ if (vma->vm_end - address > current->rlim[RLIMIT_STACK].rlim_cur ||
+ ((vma->vm_mm->total_vm + grow) << PAGE_SHIFT) >
current->rlim[RLIMIT_AS].rlim_cur) {
+ spin_unlock(&vma->vm_mm->page_table_lock);
+ return -ENOMEM;
+ }
+
+ if ((vma->vm_flags & VM_LOCKED) &&
+ ((vma->vm_mm->locked_vm + grow) << PAGE_SHIFT) >
current->rlim[RLIMIT_MEMLOCK].rlim_cur) {
+ spin_unlock(&vma->vm_mm->page_table_lock);
+ return -ENOMEM;
+ }
+
+
+ vma->vm_start = address;
+ vma->vm_pgoff -= grow;
+ vma->vm_mm->total_vm += grow;
+ if (vma->vm_flags & VM_LOCKED)
+ vma->vm_mm->locked_vm += grow;
+ spin_unlock(&vma->vm_mm->page_table_lock);
+ return 0;
+}
+
+/* Look up the first VMA which satisfies addr < vm_end, NULL if none. */
+extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long
addr);
+extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned
long addr,
+ struct vm_area_struct **pprev);
+
+/* Look up the first VMA which intersects the interval start_addr..end_addr-1,
+ NULL if none. Assume start_addr < end_addr. */
+static inline struct vm_area_struct * find_vma_intersection(struct mm_struct *
mm, unsigned long start_addr, unsigned long end_addr)
+{
+ struct vm_area_struct * vma = find_vma(mm,start_addr);
+
+ if (vma && end_addr <= vma->vm_start)
+ vma = NULL;
+ return vma;
+}
+
+extern struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned
long addr);
+
+extern struct page * vmalloc_to_page(void *addr);
+
+#endif /* __KERNEL__ */
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/pci-dma.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/pci-dma.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,205 @@
+/*
+ * Dynamic DMA mapping support.
+ */
+
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/pci.h>
+#include <linux/module.h>
+#include <asm/io.h>
+#include <asm-xen/balloon.h>
+
+/* Map a set of buffers described by scatterlist in streaming
+ * mode for DMA. This is the scatter-gather version of the
+ * above pci_map_single interface. Here the scatter gather list
+ * elements are each tagged with the appropriate dma address
+ * and length. They are obtained via sg_dma_{address,length}(SG).
+ *
+ * NOTE: An implementation may be able to use a smaller number of
+ * DMA address/length pairs than there are SG table elements.
+ * (for example via virtual mapping capabilities)
+ * The routine returns the number of addr/length pairs actually
+ * used, at most nents.
+ *
+ * Device ownership issues as mentioned above for pci_map_single are
+ * the same here.
+ */
+int dma_map_sg(struct device *hwdev, struct scatterlist *sg,
+ int nents, int direction)
+{
+ int i;
+
+ BUG_ON(direction == DMA_NONE);
+ for (i = 0; i < nents; i++ ) {
+ struct scatterlist *s = &sg[i];
+ BUG_ON(!s->page);
+ s->dma_address = virt_to_bus(page_address(s->page) +s->offset);
+ s->dma_length = s->length;
+ }
+ return nents;
+}
+
+EXPORT_SYMBOL(dma_map_sg);
+
+/* Unmap a set of streaming mode DMA translations.
+ * Again, cpu read rules concerning calls here are the same as for
+ * pci_unmap_single() above.
+ */
+void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
+ int nents, int dir)
+{
+ int i;
+ for (i = 0; i < nents; i++) {
+ struct scatterlist *s = &sg[i];
+ BUG_ON(s->page == NULL);
+ BUG_ON(s->dma_address == 0);
+ dma_unmap_single(dev, s->dma_address, s->dma_length, dir);
+ }
+}
+
+EXPORT_SYMBOL(dma_unmap_sg);
+
+struct dma_coherent_mem {
+ void *virt_base;
+ u32 device_base;
+ int size;
+ int flags;
+ unsigned long *bitmap;
+};
+
+void *dma_alloc_coherent(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, unsigned gfp)
+{
+ void *ret;
+ unsigned int order = get_order(size);
+ unsigned long vstart;
+
+ struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+
+ /* ignore region specifiers */
+ gfp &= ~(__GFP_DMA | __GFP_HIGHMEM);
+
+ if (mem) {
+ int page = bitmap_find_free_region(mem->bitmap, mem->size,
+ order);
+ if (page >= 0) {
+ *dma_handle = mem->device_base + (page << PAGE_SHIFT);
+ ret = mem->virt_base + (page << PAGE_SHIFT);
+ memset(ret, 0, size);
+ return ret;
+ }
+ if (mem->flags & DMA_MEMORY_EXCLUSIVE)
+ return NULL;
+ }
+
+ if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff))
+ gfp |= GFP_DMA;
+
+ vstart = __get_free_pages(gfp, order);
+ ret = (void *)vstart;
+ if (ret == NULL)
+ return ret;
+
+ xen_contig_memory(vstart, order);
+
+ memset(ret, 0, size);
+ *dma_handle = virt_to_bus(ret);
+
+ return ret;
+}
+EXPORT_SYMBOL(dma_alloc_coherent);
+
+void dma_free_coherent(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle)
+{
+ struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+ int order = get_order(size);
+
+ if (mem && vaddr >= mem->virt_base && vaddr < (mem->virt_base +
(mem->size << PAGE_SHIFT))) {
+ int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+
+ bitmap_release_region(mem->bitmap, page, order);
+ } else
+ free_pages((unsigned long)vaddr, order);
+}
+EXPORT_SYMBOL(dma_free_coherent);
+
+#if 0
+int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
+ dma_addr_t device_addr, size_t size, int flags)
+{
+ void __iomem *mem_base;
+ int pages = size >> PAGE_SHIFT;
+ int bitmap_size = (pages + 31)/32;
+
+ if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
+ goto out;
+ if (!size)
+ goto out;
+ if (dev->dma_mem)
+ goto out;
+
+ /* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
+
+ mem_base = ioremap(bus_addr, size);
+ if (!mem_base)
+ goto out;
+
+ dev->dma_mem = kmalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
+ if (!dev->dma_mem)
+ goto out;
+ memset(dev->dma_mem, 0, sizeof(struct dma_coherent_mem));
+ dev->dma_mem->bitmap = kmalloc(bitmap_size, GFP_KERNEL);
+ if (!dev->dma_mem->bitmap)
+ goto free1_out;
+ memset(dev->dma_mem->bitmap, 0, bitmap_size);
+
+ dev->dma_mem->virt_base = mem_base;
+ dev->dma_mem->device_base = device_addr;
+ dev->dma_mem->size = pages;
+ dev->dma_mem->flags = flags;
+
+ if (flags & DMA_MEMORY_MAP)
+ return DMA_MEMORY_MAP;
+
+ return DMA_MEMORY_IO;
+
+ free1_out:
+ kfree(dev->dma_mem->bitmap);
+ out:
+ return 0;
+}
+EXPORT_SYMBOL(dma_declare_coherent_memory);
+
+void dma_release_declared_memory(struct device *dev)
+{
+ struct dma_coherent_mem *mem = dev->dma_mem;
+
+ if(!mem)
+ return;
+ dev->dma_mem = NULL;
+ iounmap(mem->virt_base);
+ kfree(mem->bitmap);
+ kfree(mem);
+}
+EXPORT_SYMBOL(dma_release_declared_memory);
+
+void *dma_mark_declared_memory_occupied(struct device *dev,
+ dma_addr_t device_addr, size_t size)
+{
+ struct dma_coherent_mem *mem = dev->dma_mem;
+ int pages = (size + (device_addr & ~PAGE_MASK) + PAGE_SIZE - 1) >>
PAGE_SHIFT;
+ int pos, err;
+
+ if (!mem)
+ return ERR_PTR(-EINVAL);
+
+ pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
+ err = bitmap_allocate_region(mem->bitmap, pos, get_order(pages));
+ if (err != 0)
+ return ERR_PTR(err);
+ return mem->virt_base + (pos << PAGE_SHIFT);
+}
+EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/head.S
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/head.S Fri Jul 15
13:39:50 2005
@@ -0,0 +1,207 @@
+/*
+ * linux/arch/x86_64/kernel/head.S -- start in 32bit and switch to 64bit
+ *
+ * Copyright (C) 2000 Andrea Arcangeli <andrea@xxxxxxx> SuSE
+ * Copyright (C) 2000 Pavel Machek <pavel@xxxxxxx>
+ * Copyright (C) 2000 Karsten Keil <kkeil@xxxxxxx>
+ * Copyright (C) 2001,2002 Andi Kleen <ak@xxxxxxx>
+ *
+ * $Id: head.S,v 1.49 2002/03/19 17:39:25 ak Exp $
+ *
+ * Jun Nakajima <jun.nakajima@xxxxxxxxx>
+ * Modified for Xen
+ */
+
+
+#include <linux/linkage.h>
+
+.section __xen_guest
+ .ascii
"GUEST_OS=linux,GUEST_VER=2.6,XEN_VER=3.0,VIRT_BASE=0xffffffff80000000"
+ .ascii ",LOADER=generic"
+/* .ascii ",PT_MODE_WRITABLE" */
+ .byte 0
+
+
+#include <linux/threads.h>
+#include <asm/desc.h>
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/msr.h>
+#include <asm/cache.h>
+/* #include <asm/thread_info.h> */
+
+
+/* we are not able to switch in one step to the final KERNEL ADRESS SPACE
+ * because we need identity-mapped pages on setup so define __START_KERNEL to
+ * 0x100000 for this stage
+ *
+ */
+
+ .text
+ .code64
+ENTRY(_start)
+ cld
+ movq init_rsp(%rip),%rsp
+ /* Copy the necessary stuff from xen_start_info structure. */
+ movq $xen_start_info_union,%rdi
+ movq $64,%rcx /* sizeof (union xen_start_info_union) / sizeof
(long) */
+ rep movsq
+
+#ifdef CONFIG_SMP
+ ENTRY(startup_64_smp)
+ cld
+#endif /* CONFIG_SMP */
+
+ /* zero EFLAGS after setting rsp */
+ pushq $0
+ popfq
+ movq initial_code(%rip),%rax
+ jmp *%rax
+
+ /* SMP bootup changes these two */
+ .globl initial_code
+initial_code:
+ .quad x86_64_start_kernel
+ .globl init_rsp
+init_rsp:
+ .quad init_thread_union+THREAD_SIZE-8
+
+ENTRY(early_idt_handler)
+ xorl %eax,%eax
+ movq 8(%rsp),%rsi # get rip
+ movq (%rsp),%rdx
+ leaq early_idt_msg(%rip),%rdi
+1: hlt # generate #GP
+ jmp 1b
+
+early_idt_msg:
+ .asciz "PANIC: early exception rip %lx error %lx cr2 %lx\n"
+
+#if 0
+ENTRY(lgdt_finish)
+ movl $(__USER_DS),%eax # DS/ES contains default USER segment
+ movw %ax,%ds
+ movw %ax,%es
+ movl $(__KERNEL_DS),%eax
+ movw %ax,%ss # after changing gdt.
+ popq %rax # get the retrun address
+ pushq $(__KERNEL_CS)
+ pushq %rax
+ lretq
+#endif
+
+ENTRY(stext)
+ENTRY(_stext)
+
+ /*
+ * This default setting generates an ident mapping at address 0x100000
+ * and a mapping for the kernel that precisely maps virtual address
+ * 0xffffffff80000000 to physical address 0x000000. (always using
+ * 2Mbyte large pages provided by PAE mode)
+ */
+.org 0x1000
+ENTRY(init_level4_pgt)
+ .fill 512,8,0
+
+ /*
+ * We update two pgd entries to make kernel and user pgd consistent
+ * at pgd_populate(). It can be used for kernel modules. So we place
+ * this page here for those cases to avoid memory corruption.
+ * We also use this page to establish the initiali mapping for
+ * vsyscall area.
+ */
+.org 0x2000
+ENTRY(init_level4_user_pgt)
+ .fill 512,8,0
+
+ /*
+ * This is used for vsyscall area mapping as we have a different
+ * level4 page table for user.
+ */
+.org 0x3000
+ENTRY(level3_user_pgt)
+ .fill 512,8,0
+
+.org 0x4000
+ENTRY(cpu_gdt_table)
+/* The TLS descriptors are currently at a different place compared to i386.
+ Hopefully nobody expects them at a fixed place (Wine?) */
+ .quad 0x0000000000000000 /* NULL descriptor */
+ .quad 0x008ffa000000ffff /* __KERNEL_COMPAT32_CS */
+ .quad 0x00affa000000ffff /* __KERNEL_CS */
+ .quad 0x00cff2000000ffff /* __KERNEL_DS */
+
+ .quad 0x00cffa000000ffff /* __USER32_CS */
+ .quad 0x00cff2000000ffff /* __USER_DS, __USER32_DS */
+ .quad 0x00affa000000ffff /* __USER_CS */
+ .quad 0x00cffa000000ffff /* __KERNEL32_CS */
+ .quad 0,0 /* TSS */
+ .quad 0 /* LDT */
+ .quad 0,0,0 /* three TLS descriptors */
+ .quad 0 /* unused now */
+
+gdt_end:
+ /* asm/segment.h:GDT_ENTRIES must match this */
+ /* This should be a multiple of the cache line size */
+ /* GDTs of other CPUs: */
+ .fill (GDT_SIZE * NR_CPUS) - (gdt_end - cpu_gdt_table)
+
+.org 0x5000
+ENTRY(empty_zero_page)
+
+.org 0x6000
+ENTRY(empty_bad_page)
+
+.org 0x7000
+ENTRY(empty_bad_pte_table)
+
+.org 0x8000
+ENTRY(empty_bad_pmd_table)
+
+ .org 0x9000
+#ifdef CONFIG_ACPI_SLEEP
+ENTRY(wakeup_level4_pgt)
+ .quad 0x0000000000102007 /* -> level3_ident_pgt */
+ .fill 255,8,0
+ .quad 0x000000000010a007
+ .fill 254,8,0
+ /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
+ .quad 0x0000000000103007 /* -> level3_kernel_pgt */
+#endif
+
+ .data
+
+ .align 16
+ .globl cpu_gdt_descr
+cpu_gdt_descr:
+ .word gdt_end-cpu_gdt_table
+gdt:
+ .quad cpu_gdt_table
+#ifdef CONFIG_SMP
+ .rept NR_CPUS-1
+ .word 0
+ .quad 0
+ .endr
+#endif
+
+ENTRY(gdt_table32)
+ .quad 0x0000000000000000 /* This one is magic */
+ .quad 0x0000000000000000 /* unused */
+ .quad 0x00af9a000000ffff /* __KERNEL_CS */
+gdt32_end:
+
+/* We need valid kernel segments for data and code in long mode too
+ * IRET will check the segment types kkeil 2000/10/28
+ * Also sysret mandates a special GDT layout
+ */
+
+#if 0
+.align L1_CACHE_BYTES
+#endif
+ .align L1_CACHE_BYTES
+ENTRY(idt_table)
+ .rept 256
+ .quad 0
+ .quad 0
+ .endr
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/kernel/irq.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/kernel/irq.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,1242 @@
+/*
+ * linux/arch/i386/kernel/irq.c
+ *
+ * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
+ *
+ * This file contains the code used by various IRQ handling routines:
+ * asking for different IRQ's should be done through these routines
+ * instead of just grabbing them. Thus setups with different IRQ numbers
+ * shouldn't result in any weird surprises, and installing new handlers
+ * should be easier.
+ */
+
+/*
+ * (mostly architecture independent, will move to kernel/irq.c in 2.5.)
+ *
+ * IRQs are in fact implemented a bit like signal handlers for the kernel.
+ * Naturally it's not a 1:1 relation, but there are similarities.
+ */
+
+#include <linux/config.h>
+#include <linux/ptrace.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/smp_lock.h>
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/irq.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+
+#include <asm/atomic.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/system.h>
+#include <asm/bitops.h>
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+#include <asm/delay.h>
+#include <asm/desc.h>
+#include <asm/irq.h>
+
+
+
+/*
+ * Linux has a controller-independent x86 interrupt architecture.
+ * every controller has a 'controller-template', that is used
+ * by the main code to do the right thing. Each driver-visible
+ * interrupt source is transparently wired to the apropriate
+ * controller. Thus drivers need not be aware of the
+ * interrupt-controller.
+ *
+ * Various interrupt controllers we handle: 8259 PIC, SMP IO-APIC,
+ * PIIX4's internal 8259 PIC and SGI's Visual Workstation Cobalt (IO-)APIC.
+ * (IO-APICs assumed to be messaging to Pentium local-APICs)
+ *
+ * the code is designed to be easily extended with new/different
+ * interrupt controllers, without having to do assembly magic.
+ */
+
+/*
+ * Controller mappings for all interrupt sources:
+ */
+irq_desc_t irq_desc[NR_IRQS] __cacheline_aligned =
+ { [0 ... NR_IRQS-1] = { 0, &no_irq_type, NULL, 0, SPIN_LOCK_UNLOCKED}};
+
+static void register_irq_proc (unsigned int irq);
+
+/*
+ * Special irq handlers.
+ */
+
+void no_action(int cpl, void *dev_id, struct pt_regs *regs) { }
+
+/*
+ * Generic no controller code
+ */
+
+static void enable_none(unsigned int irq) { }
+static unsigned int startup_none(unsigned int irq) { return 0; }
+static void disable_none(unsigned int irq) { }
+static void ack_none(unsigned int irq)
+{
+/*
+ * 'what should we do if we get a hw irq event on an illegal vector'.
+ * each architecture has to answer this themselves, it doesnt deserve
+ * a generic callback i think.
+ */
+#if CONFIG_X86
+ printk("unexpected IRQ trap at vector %02x\n", irq);
+#ifdef CONFIG_X86_LOCAL_APIC
+ /*
+ * Currently unexpected vectors happen only on SMP and APIC.
+ * We _must_ ack these because every local APIC has only N
+ * irq slots per priority level, and a 'hanging, unacked' IRQ
+ * holds up an irq slot - in excessive cases (when multiple
+ * unexpected vectors occur) that might lock up the APIC
+ * completely.
+ */
+ ack_APIC_irq();
+#endif
+#endif
+}
+
+/* startup is the same as "enable", shutdown is same as "disable" */
+#define shutdown_none disable_none
+#define end_none enable_none
+
+struct hw_interrupt_type no_irq_type = {
+ "none",
+ startup_none,
+ shutdown_none,
+ enable_none,
+ disable_none,
+ ack_none,
+ end_none
+};
+
+atomic_t irq_err_count;
+#ifdef CONFIG_X86_IO_APIC
+#ifdef APIC_MISMATCH_DEBUG
+atomic_t irq_mis_count;
+#endif
+#endif
+
+/*
+ * Generic, controller-independent functions:
+ */
+
+int show_interrupts(struct seq_file *p, void *v)
+{
+ int i, j;
+ struct irqaction * action;
+
+ seq_printf(p, " ");
+ for (j=0; j<smp_num_cpus; j++)
+ seq_printf(p, "CPU%d ",j);
+ seq_putc(p,'\n');
+
+ for (i = 0 ; i < NR_IRQS ; i++) {
+ action = irq_desc[i].action;
+ if (!action)
+ continue;
+ seq_printf(p, "%3d: ",i);
+#ifndef CONFIG_SMP
+ seq_printf(p, "%10u ", kstat_irqs(i));
+#else
+ for (j = 0; j < smp_num_cpus; j++)
+ seq_printf(p, "%10u ",
+ kstat.irqs[cpu_logical_map(j)][i]);
+#endif
+ seq_printf(p, " %14s", irq_desc[i].handler->typename);
+ seq_printf(p, " %s", action->name);
+
+ for (action=action->next; action; action = action->next)
+ seq_printf(p, ", %s", action->name);
+ seq_putc(p,'\n');
+ }
+ seq_printf(p, "NMI: ");
+ for (j = 0; j < smp_num_cpus; j++)
+ seq_printf(p, "%10u ",
+ nmi_count(cpu_logical_map(j)));
+ seq_printf(p, "\n");
+#if CONFIG_X86_LOCAL_APIC
+ seq_printf(p, "LOC: ");
+ for (j = 0; j < smp_num_cpus; j++)
+ seq_printf(p, "%10u ",
+ apic_timer_irqs[cpu_logical_map(j)]);
+ seq_printf(p, "\n");
+#endif
+ seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
+#ifdef CONFIG_X86_IO_APIC
+#ifdef APIC_MISMATCH_DEBUG
+ seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));
+#endif
+#endif
+
+ return 0;
+}
+
+
+/*
+ * Global interrupt locks for SMP. Allow interrupts to come in on any
+ * CPU, yet make cli/sti act globally to protect critical regions..
+ */
+
+#ifdef CONFIG_SMP
+unsigned char global_irq_holder = NO_PROC_ID;
+unsigned volatile long global_irq_lock; /* pendantic: long for set_bit --RR */
+
+extern void show_stack(unsigned long* esp);
+
+static void show(char * str)
+{
+ int i;
+ int cpu = smp_processor_id();
+
+ printk("\n%s, CPU %d:\n", str, cpu);
+ printk("irq: %d [",irqs_running());
+ for(i=0;i < smp_num_cpus;i++)
+ printk(" %d",local_irq_count(i));
+ printk(" ]\nbh: %d [",spin_is_locked(&global_bh_lock) ? 1 : 0);
+ for(i=0;i < smp_num_cpus;i++)
+ printk(" %d",local_bh_count(i));
+
+ printk(" ]\nStack dumps:");
+ for(i = 0; i < smp_num_cpus; i++) {
+ unsigned long esp;
+ if (i == cpu)
+ continue;
+ printk("\nCPU %d:",i);
+ esp = init_tss[i].esp0;
+ if (!esp) {
+ /* tss->esp0 is set to NULL in cpu_init(),
+ * it's initialized when the cpu returns to user
+ * space. -- manfreds
+ */
+ printk(" <unknown> ");
+ continue;
+ }
+ esp &= ~(THREAD_SIZE-1);
+ esp += sizeof(struct task_struct);
+ show_stack((void*)esp);
+ }
+ printk("\nCPU %d:",cpu);
+ show_stack(NULL);
+ printk("\n");
+}
+
+#define MAXCOUNT 100000000
+
+/*
+ * I had a lockup scenario where a tight loop doing
+ * spin_unlock()/spin_lock() on CPU#1 was racing with
+ * spin_lock() on CPU#0. CPU#0 should have noticed spin_unlock(), but
+ * apparently the spin_unlock() information did not make it
+ * through to CPU#0 ... nasty, is this by design, do we have to limit
+ * 'memory update oscillation frequency' artificially like here?
+ *
+ * Such 'high frequency update' races can be avoided by careful design, but
+ * some of our major constructs like spinlocks use similar techniques,
+ * it would be nice to clarify this issue. Set this define to 0 if you
+ * want to check whether your system freezes. I suspect the delay done
+ * by SYNC_OTHER_CORES() is in correlation with 'snooping latency', but
+ * i thought that such things are guaranteed by design, since we use
+ * the 'LOCK' prefix.
+ */
+#define SUSPECTED_CPU_OR_CHIPSET_BUG_WORKAROUND 0
+
+#if SUSPECTED_CPU_OR_CHIPSET_BUG_WORKAROUND
+# define SYNC_OTHER_CORES(x) udelay(x+1)
+#else
+/*
+ * We have to allow irqs to arrive between __sti and __cli
+ */
+# define SYNC_OTHER_CORES(x) __asm__ __volatile__ ("nop")
+#endif
+
+static inline void wait_on_irq(int cpu)
+{
+ int count = MAXCOUNT;
+
+ for (;;) {
+
+ /*
+ * Wait until all interrupts are gone. Wait
+ * for bottom half handlers unless we're
+ * already executing in one..
+ */
+ if (!irqs_running())
+ if (local_bh_count(cpu) ||
!spin_is_locked(&global_bh_lock))
+ break;
+
+ /* Duh, we have to loop. Release the lock to avoid deadlocks */
+ clear_bit(0,&global_irq_lock);
+
+ for (;;) {
+ if (!--count) {
+ show("wait_on_irq");
+ count = ~0;
+ }
+ __sti();
+ SYNC_OTHER_CORES(cpu);
+ __cli();
+ if (irqs_running())
+ continue;
+ if (global_irq_lock)
+ continue;
+ if (!local_bh_count(cpu) &&
spin_is_locked(&global_bh_lock))
+ continue;
+ if (!test_and_set_bit(0,&global_irq_lock))
+ break;
+ }
+ }
+}
+
+/*
+ * This is called when we want to synchronize with
+ * interrupts. We may for example tell a device to
+ * stop sending interrupts: but to make sure there
+ * are no interrupts that are executing on another
+ * CPU we need to call this function.
+ */
+void synchronize_irq(void)
+{
+ if (irqs_running()) {
+ /* Stupid approach */
+ cli();
+ sti();
+ }
+}
+
+static inline void get_irqlock(int cpu)
+{
+ if (test_and_set_bit(0,&global_irq_lock)) {
+ /* do we already hold the lock? */
+ if ((unsigned char) cpu == global_irq_holder)
+ return;
+ /* Uhhuh.. Somebody else got it. Wait.. */
+ do {
+ do {
+ rep_nop();
+ } while (test_bit(0,&global_irq_lock));
+ } while (test_and_set_bit(0,&global_irq_lock));
+ }
+ /*
+ * We also to make sure that nobody else is running
+ * in an interrupt context.
+ */
+ wait_on_irq(cpu);
+
+ /*
+ * Ok, finally..
+ */
+ global_irq_holder = cpu;
+}
+
+/*
+ * A global "cli()" while in an interrupt context
+ * turns into just a local cli(). Interrupts
+ * should use spinlocks for the (very unlikely)
+ * case that they ever want to protect against
+ * each other.
+ *
+ * If we already have local interrupts disabled,
+ * this will not turn a local disable into a
+ * global one (problems with spinlocks: this makes
+ * save_flags+cli+sti usable inside a spinlock).
+ */
+void __global_cli(void)
+{
+ unsigned int flags;
+
+ __save_flags(flags);
+ if (!flags) {
+ int cpu = smp_processor_id();
+ __cli();
+ if (!local_irq_count(cpu))
+ get_irqlock(cpu);
+ }
+}
+
+void __global_sti(void)
+{
+ int cpu = smp_processor_id();
+
+ if (!local_irq_count(cpu))
+ release_irqlock(cpu);
+ __sti();
+}
+
+/*
+ * SMP flags value to restore to:
+ * 0 - global cli
+ * 1 - global sti
+ * 2 - local cli
+ * 3 - local sti
+ */
+unsigned long __global_save_flags(void)
+{
+ int retval;
+ int local_enabled;
+ unsigned long flags;
+ int cpu = smp_processor_id();
+
+ __save_flags(flags);
+ local_enabled = !flags;
+ /* default to local */
+ retval = 2 + local_enabled;
+
+ /* check for global flags if we're not in an interrupt */
+ if (!local_irq_count(cpu)) {
+ if (local_enabled)
+ retval = 1;
+ if (global_irq_holder == cpu)
+ retval = 0;
+ }
+ return retval;
+}
+
+void __global_restore_flags(unsigned long flags)
+{
+ switch (flags) {
+ case 0:
+ __global_cli();
+ break;
+ case 1:
+ __global_sti();
+ break;
+ case 2:
+ __cli();
+ break;
+ case 3:
+ __sti();
+ break;
+ default:
+ printk("global_restore_flags: %08lx (%08lx)\n",
+ flags, (&flags)[-1]);
+ }
+}
+
+#endif
+
+/*
+ * This should really return information about whether
+ * we should do bottom half handling etc. Right now we
+ * end up _always_ checking the bottom half, which is a
+ * waste of time and is not what some drivers would
+ * prefer.
+ */
+int handle_IRQ_event(unsigned int irq, struct pt_regs * regs, struct irqaction
* action)
+{
+ int status;
+ int cpu = smp_processor_id();
+
+ irq_enter(cpu, irq);
+
+ status = 1; /* Force the "do bottom halves" bit */
+
+ if (!(action->flags & SA_INTERRUPT))
+ __sti();
+
+ do {
+ status |= action->flags;
+ action->handler(irq, action->dev_id, regs);
+ action = action->next;
+ } while (action);
+ if (status & SA_SAMPLE_RANDOM)
+ add_interrupt_randomness(irq);
+ __cli();
+
+ irq_exit(cpu, irq);
+
+ return status;
+}
+
+/*
+ * Generic enable/disable code: this just calls
+ * down into the PIC-specific version for the actual
+ * hardware disable after having gotten the irq
+ * controller lock.
+ */
+
+/**
+ * disable_irq_nosync - disable an irq without waiting
+ * @irq: Interrupt to disable
+ *
+ * Disable the selected interrupt line. Disables and Enables are
+ * nested.
+ * Unlike disable_irq(), this function does not ensure existing
+ * instances of the IRQ handler have completed before returning.
+ *
+ * This function may be called from IRQ context.
+ */
+
+inline void disable_irq_nosync(unsigned int irq)
+{
+ irq_desc_t *desc = irq_desc + irq;
+ unsigned long flags;
+
+ spin_lock_irqsave(&desc->lock, flags);
+ if (!desc->depth++) {
+ desc->status |= IRQ_DISABLED;
+ desc->handler->disable(irq);
+ }
+ spin_unlock_irqrestore(&desc->lock, flags);
+}
+
+/**
+ * disable_irq - disable an irq and wait for completion
+ * @irq: Interrupt to disable
+ *
+ * Disable the selected interrupt line. Enables and Disables are
+ * nested.
+ * This function waits for any pending IRQ handlers for this interrupt
+ * to complete before returning. If you use this function while
+ * holding a resource the IRQ handler may need you will deadlock.
+ *
+ * This function may be called - with care - from IRQ context.
+ */
+
+void disable_irq(unsigned int irq)
+{
+ disable_irq_nosync(irq);
+
+ if (!local_irq_count(smp_processor_id())) {
+ do {
+ barrier();
+ cpu_relax();
+ } while (irq_desc[irq].status & IRQ_INPROGRESS);
+ }
+}
+
+/**
+ * enable_irq - enable handling of an irq
+ * @irq: Interrupt to enable
+ *
+ * Undoes the effect of one call to disable_irq(). If this
+ * matches the last disable, processing of interrupts on this
+ * IRQ line is re-enabled.
+ *
+ * This function may be called from IRQ context.
+ */
+
+void enable_irq(unsigned int irq)
+{
+ irq_desc_t *desc = irq_desc + irq;
+ unsigned long flags;
+
+ spin_lock_irqsave(&desc->lock, flags);
+ switch (desc->depth) {
+ case 1: {
+ unsigned int status = desc->status & ~IRQ_DISABLED;
+ desc->status = status;
+ if ((status & (IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
+ desc->status = status | IRQ_REPLAY;
+ hw_resend_irq(desc->handler,irq);
+ }
+ desc->handler->enable(irq);
+ /* fall-through */
+ }
+ default:
+ desc->depth--;
+ break;
+ case 0:
+ printk("enable_irq(%u) unbalanced from %p\n", irq,
+ __builtin_return_address(0));
+ }
+ spin_unlock_irqrestore(&desc->lock, flags);
+}
+
+/*
+ * do_IRQ handles all normal device IRQ's (the special
+ * SMP cross-CPU interrupts have their own specific
+ * handlers).
+ */
+asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
+{
+ /*
+ * We ack quickly, we don't want the irq controller
+ * thinking we're snobs just because some other CPU has
+ * disabled global interrupts (we have already done the
+ * INT_ACK cycles, it's too late to try to pretend to the
+ * controller that we aren't taking the interrupt).
+ *
+ * 0 return value means that this irq is already being
+ * handled by some other CPU. (or is disabled)
+ */
+ int irq = regs->orig_eax & 0xff; /* high bits used in ret_from_ code */
+ int cpu = smp_processor_id();
+ irq_desc_t *desc = irq_desc + irq;
+ struct irqaction * action;
+ unsigned int status;
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
+ long esp;
+
+ /* Debugging check for stack overflow: is there less than 1KB free? */
+ __asm__ __volatile__("andl %%esp,%0" : "=r" (esp) : "0" (8191));
+ if (unlikely(esp < (sizeof(struct task_struct) + 1024))) {
+ extern void show_stack(unsigned long *);
+
+ printk("do_IRQ: stack overflow: %ld\n",
+ esp - sizeof(struct task_struct));
+ __asm__ __volatile__("movl %%esp,%0" : "=r" (esp));
+ show_stack((void *)esp);
+ }
+#endif
+
+ kstat.irqs[cpu][irq]++;
+ spin_lock(&desc->lock);
+ desc->handler->ack(irq);
+ /*
+ REPLAY is when Linux resends an IRQ that was dropped earlier
+ WAITING is used by probe to mark irqs that are being tested
+ */
+ status = desc->status & ~(IRQ_REPLAY | IRQ_WAITING);
+ status |= IRQ_PENDING; /* we _want_ to handle it */
+
+ /*
+ * If the IRQ is disabled for whatever reason, we cannot
+ * use the action we have.
+ */
+ action = NULL;
+ if (!(status & (IRQ_DISABLED | IRQ_INPROGRESS))) {
+ action = desc->action;
+ status &= ~IRQ_PENDING; /* we commit to handling */
+ status |= IRQ_INPROGRESS; /* we are handling it */
+ }
+ desc->status = status;
+
+ /*
+ * If there is no IRQ handler or it was disabled, exit early.
+ Since we set PENDING, if another processor is handling
+ a different instance of this same irq, the other processor
+ will take care of it.
+ */
+ if (!action)
+ goto out;
+
+ /*
+ * Edge triggered interrupts need to remember
+ * pending events.
+ * This applies to any hw interrupts that allow a second
+ * instance of the same irq to arrive while we are in do_IRQ
+ * or in the handler. But the code here only handles the _second_
+ * instance of the irq, not the third or fourth. So it is mostly
+ * useful for irq hardware that does not mask cleanly in an
+ * SMP environment.
+ */
+ for (;;) {
+ spin_unlock(&desc->lock);
+ handle_IRQ_event(irq, regs, action);
+ spin_lock(&desc->lock);
+
+ if (!(desc->status & IRQ_PENDING))
+ break;
+ desc->status &= ~IRQ_PENDING;
+ }
+ desc->status &= ~IRQ_INPROGRESS;
+out:
+ /*
+ * The ->end() handler has to deal with interrupts which got
+ * disabled while the handler was running.
+ */
+ desc->handler->end(irq);
+ spin_unlock(&desc->lock);
+
+ if (softirq_pending(cpu))
+ do_softirq();
+ return 1;
+}
+
+/**
+ * request_irq - allocate an interrupt line
+ * @irq: Interrupt line to allocate
+ * @handler: Function to be called when the IRQ occurs
+ * @irqflags: Interrupt type flags
+ * @devname: An ascii name for the claiming device
+ * @dev_id: A cookie passed back to the handler function
+ *
+ * This call allocates interrupt resources and enables the
+ * interrupt line and IRQ handling. From the point this
+ * call is made your handler function may be invoked. Since
+ * your handler function must clear any interrupt the board
+ * raises, you must take care both to initialise your hardware
+ * and to set up the interrupt handler in the right order.
+ *
+ * Dev_id must be globally unique. Normally the address of the
+ * device data structure is used as the cookie. Since the handler
+ * receives this value it makes sense to use it.
+ *
+ * If your interrupt is shared you must pass a non NULL dev_id
+ * as this is required when freeing the interrupt.
+ *
+ * Flags:
+ *
+ * SA_SHIRQ Interrupt is shared
+ *
+ * SA_INTERRUPT Disable local interrupts while processing
+ *
+ * SA_SAMPLE_RANDOM The interrupt can be used for entropy
+ *
+ */
+
+int request_irq(unsigned int irq,
+ void (*handler)(int, void *, struct pt_regs *),
+ unsigned long irqflags,
+ const char * devname,
+ void *dev_id)
+{
+ int retval;
+ struct irqaction * action;
+
+#if 1
+ /*
+ * Sanity-check: shared interrupts should REALLY pass in
+ * a real dev-ID, otherwise we'll have trouble later trying
+ * to figure out which interrupt is which (messes up the
+ * interrupt freeing logic etc).
+ */
+ if (irqflags & SA_SHIRQ) {
+ if (!dev_id)
+ printk("Bad boy: %s (at 0x%x) called us without a
dev_id!\n", devname, (&irq)[-1]);
+ }
+#endif
+
+ if (irq >= NR_IRQS)
+ return -EINVAL;
+ if (!handler)
+ return -EINVAL;
+
+ action = (struct irqaction *)
+ kmalloc(sizeof(struct irqaction), GFP_KERNEL);
+ if (!action)
+ return -ENOMEM;
+
+ action->handler = handler;
+ action->flags = irqflags;
+ action->mask = 0;
+ action->name = devname;
+ action->next = NULL;
+ action->dev_id = dev_id;
+
+ retval = setup_irq(irq, action);
+ if (retval)
+ kfree(action);
+ return retval;
+}
+
+/*
+ * Internal function to unregister an irqaction - typically used to
+ * deallocate special interrupts that are part of the architecture.
+ */
+int teardown_irq(unsigned int irq, struct irqaction * old)
+{
+ irq_desc_t *desc;
+ struct irqaction **p;
+ unsigned long flags;
+
+ if (irq >= NR_IRQS)
+ return -ENOENT;
+
+ desc = irq_desc + irq;
+ spin_lock_irqsave(&desc->lock,flags);
+ p = &desc->action;
+ for (;;) {
+ struct irqaction * action = *p;
+ if (action) {
+ struct irqaction **pp = p;
+ p = &action->next;
+ if (action != old)
+ continue;
+
+ /* Found it - now remove it from the list of entries */
+ *pp = action->next;
+ if (!desc->action) {
+ desc->status |= IRQ_DISABLED;
+ desc->handler->shutdown(irq);
+ }
+ spin_unlock_irqrestore(&desc->lock,flags);
+
+#ifdef CONFIG_SMP
+ /* Wait to make sure it's not being used on another CPU
*/
+ while (desc->status & IRQ_INPROGRESS) {
+ barrier();
+ cpu_relax();
+ }
+#endif
+ return 0;
+ }
+ printk("Trying to free free IRQ%d\n",irq);
+ spin_unlock_irqrestore(&desc->lock,flags);
+ return -ENOENT;
+ }
+}
+
+/**
+ * free_irq - free an interrupt
+ * @irq: Interrupt line to free
+ * @dev_id: Device identity to free
+ *
+ * Remove an interrupt handler. The handler is removed and if the
+ * interrupt line is no longer in use by any driver it is disabled.
+ * On a shared IRQ the caller must ensure the interrupt is disabled
+ * on the card it drives before calling this function. The function
+ * does not return until any executing interrupts for this IRQ
+ * have completed.
+ *
+ * This function may be called from interrupt context.
+ *
+ * Bugs: Attempting to free an irq in a handler for the same irq hangs
+ * the machine.
+ */
+
+void free_irq(unsigned int irq, void *dev_id)
+{
+ irq_desc_t *desc;
+ struct irqaction *action;
+ unsigned long flags;
+
+ if (irq >= NR_IRQS)
+ return;
+
+ desc = irq_desc + irq;
+ spin_lock_irqsave(&desc->lock,flags);
+ for (action = desc->action; action != NULL; action = action->next) {
+ if (action->dev_id != dev_id)
+ continue;
+
+ spin_unlock_irqrestore(&desc->lock,flags);
+
+ if (teardown_irq(irq, action) == 0)
+ kfree(action);
+ return;
+ }
+ printk("Trying to free free IRQ%d\n",irq);
+ spin_unlock_irqrestore(&desc->lock,flags);
+ return;
+}
+
+/*
+ * IRQ autodetection code..
+ *
+ * This depends on the fact that any interrupt that
+ * comes in on to an unassigned handler will get stuck
+ * with "IRQ_WAITING" cleared and the interrupt
+ * disabled.
+ */
+
+static DECLARE_MUTEX(probe_sem);
+
+/**
+ * probe_irq_on - begin an interrupt autodetect
+ *
+ * Commence probing for an interrupt. The interrupts are scanned
+ * and a mask of potential interrupt lines is returned.
+ *
+ */
+
+unsigned long probe_irq_on(void)
+{
+ unsigned int i;
+ irq_desc_t *desc;
+ unsigned long val;
+ unsigned long delay;
+
+ down(&probe_sem);
+ /*
+ * something may have generated an irq long ago and we want to
+ * flush such a longstanding irq before considering it as spurious.
+ */
+ for (i = NR_PIRQS-1; i > 0; i--) {
+ desc = irq_desc + i;
+
+ spin_lock_irq(&desc->lock);
+ if (!irq_desc[i].action)
+ irq_desc[i].handler->startup(i);
+ spin_unlock_irq(&desc->lock);
+ }
+
+ /* Wait for longstanding interrupts to trigger. */
+ for (delay = jiffies + HZ/50; time_after(delay, jiffies); )
+ /* about 20ms delay */ synchronize_irq();
+
+ /*
+ * enable any unassigned irqs
+ * (we must startup again here because if a longstanding irq
+ * happened in the previous stage, it may have masked itself)
+ */
+ for (i = NR_PIRQS-1; i > 0; i--) {
+ desc = irq_desc + i;
+
+ spin_lock_irq(&desc->lock);
+ if (!desc->action) {
+ desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
+ if (desc->handler->startup(i))
+ desc->status |= IRQ_PENDING;
+ }
+ spin_unlock_irq(&desc->lock);
+ }
+
+ /*
+ * Wait for spurious interrupts to trigger
+ */
+ for (delay = jiffies + HZ/10; time_after(delay, jiffies); )
+ /* about 100ms delay */ synchronize_irq();
+
+ /*
+ * Now filter out any obviously spurious interrupts
+ */
+ val = 0;
+ for (i = 0; i < NR_PIRQS; i++) {
+ irq_desc_t *desc = irq_desc + i;
+ unsigned int status;
+
+ spin_lock_irq(&desc->lock);
+ status = desc->status;
+
+ if (status & IRQ_AUTODETECT) {
+ /* It triggered already - consider it spurious. */
+ if (!(status & IRQ_WAITING)) {
+ desc->status = status & ~IRQ_AUTODETECT;
+ desc->handler->shutdown(i);
+ } else
+ if (i < 32)
+ val |= 1 << i;
+ }
+ spin_unlock_irq(&desc->lock);
+ }
+
+ return val;
+}
+
+/*
+ * Return a mask of triggered interrupts (this
+ * can handle only legacy ISA interrupts).
+ */
+
+/**
+ * probe_irq_mask - scan a bitmap of interrupt lines
+ * @val: mask of interrupts to consider
+ *
+ * Scan the ISA bus interrupt lines and return a bitmap of
+ * active interrupts. The interrupt probe logic state is then
+ * returned to its previous value.
+ *
+ * Note: we need to scan all the irq's even though we will
+ * only return ISA irq numbers - just so that we reset them
+ * all to a known state.
+ */
+unsigned int probe_irq_mask(unsigned long val)
+{
+ int i;
+ unsigned int mask;
+
+ mask = 0;
+ for (i = 0; i < NR_PIRQS; i++) {
+ irq_desc_t *desc = irq_desc + i;
+ unsigned int status;
+
+ spin_lock_irq(&desc->lock);
+ status = desc->status;
+
+ if (status & IRQ_AUTODETECT) {
+ if (i < 16 && !(status & IRQ_WAITING))
+ mask |= 1 << i;
+
+ desc->status = status & ~IRQ_AUTODETECT;
+ desc->handler->shutdown(i);
+ }
+ spin_unlock_irq(&desc->lock);
+ }
+ up(&probe_sem);
+
+ return mask & val;
+}
+
+/*
+ * Return the one interrupt that triggered (this can
+ * handle any interrupt source).
+ */
+
+/**
+ * probe_irq_off - end an interrupt autodetect
+ * @val: mask of potential interrupts (unused)
+ *
+ * Scans the unused interrupt lines and returns the line which
+ * appears to have triggered the interrupt. If no interrupt was
+ * found then zero is returned. If more than one interrupt is
+ * found then minus the first candidate is returned to indicate
+ * their is doubt.
+ *
+ * The interrupt probe logic state is returned to its previous
+ * value.
+ *
+ * BUGS: When used in a module (which arguably shouldnt happen)
+ * nothing prevents two IRQ probe callers from overlapping. The
+ * results of this are non-optimal.
+ */
+
+int probe_irq_off(unsigned long val)
+{
+ int i, irq_found, nr_irqs;
+
+ nr_irqs = 0;
+ irq_found = 0;
+ for (i = 0; i < NR_PIRQS; i++) {
+ irq_desc_t *desc = irq_desc + i;
+ unsigned int status;
+
+ spin_lock_irq(&desc->lock);
+ status = desc->status;
+
+ if (status & IRQ_AUTODETECT) {
+ if (!(status & IRQ_WAITING)) {
+ if (!nr_irqs)
+ irq_found = i;
+ nr_irqs++;
+ }
+ desc->status = status & ~IRQ_AUTODETECT;
+ desc->handler->shutdown(i);
+ }
+ spin_unlock_irq(&desc->lock);
+ }
+ up(&probe_sem);
+
+ if (nr_irqs > 1)
+ irq_found = -irq_found;
+ return irq_found;
+}
+
+/* this was setup_x86_irq but it seems pretty generic */
+int setup_irq(unsigned int irq, struct irqaction * new)
+{
+ int shared = 0;
+ unsigned long flags;
+ struct irqaction *old, **p;
+ irq_desc_t *desc = irq_desc + irq;
+
+ /*
+ * Some drivers like serial.c use request_irq() heavily,
+ * so we have to be careful not to interfere with a
+ * running system.
+ */
+ if (new->flags & SA_SAMPLE_RANDOM) {
+ /*
+ * This function might sleep, we want to call it first,
+ * outside of the atomic block.
+ * Yes, this might clear the entropy pool if the wrong
+ * driver is attempted to be loaded, without actually
+ * installing a new handler, but is this really a problem,
+ * only the sysadmin is able to do this.
+ */
+ rand_initialize_irq(irq);
+ }
+
+ /*
+ * The following block of code has to be executed atomically
+ */
+ spin_lock_irqsave(&desc->lock,flags);
+ p = &desc->action;
+ if ((old = *p) != NULL) {
+ /* Can't share interrupts unless both agree to */
+ if (!(old->flags & new->flags & SA_SHIRQ)) {
+ spin_unlock_irqrestore(&desc->lock,flags);
+ return -EBUSY;
+ }
+
+ /* add new interrupt at end of irq queue */
+ do {
+ p = &old->next;
+ old = *p;
+ } while (old);
+ shared = 1;
+ }
+
+ *p = new;
+
+ if (!shared) {
+ desc->depth = 0;
+ desc->status &= ~(IRQ_DISABLED | IRQ_AUTODETECT | IRQ_WAITING |
IRQ_INPROGRESS);
+ desc->handler->startup(irq);
+ }
+ spin_unlock_irqrestore(&desc->lock,flags);
+
+ register_irq_proc(irq);
+ return 0;
+}
+
+static struct proc_dir_entry * root_irq_dir;
+static struct proc_dir_entry * irq_dir [NR_IRQS];
+
+#define HEX_DIGITS 8
+
+static unsigned int parse_hex_value (const char *buffer,
+ unsigned long count, unsigned long *ret)
+{
+ unsigned char hexnum [HEX_DIGITS];
+ unsigned long value;
+ int i;
+
+ if (!count)
+ return -EINVAL;
+ if (count > HEX_DIGITS)
+ count = HEX_DIGITS;
+ if (copy_from_user(hexnum, buffer, count))
+ return -EFAULT;
+
+ /*
+ * Parse the first 8 characters as a hex string, any non-hex char
+ * is end-of-string. '00e1', 'e1', '00E1', 'E1' are all the same.
+ */
+ value = 0;
+
+ for (i = 0; i < count; i++) {
+ unsigned int c = hexnum[i];
+
+ switch (c) {
+ case '0' ... '9': c -= '0'; break;
+ case 'a' ... 'f': c -= 'a'-10; break;
+ case 'A' ... 'F': c -= 'A'-10; break;
+ default:
+ goto out;
+ }
+ value = (value << 4) | c;
+ }
+out:
+ *ret = value;
+ return 0;
+}
+
+#if CONFIG_SMP
+
+static struct proc_dir_entry * smp_affinity_entry [NR_IRQS];
+
+static unsigned long irq_affinity [NR_IRQS] = { [0 ... NR_IRQS-1] = ~0UL };
+static int irq_affinity_read_proc (char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ if (count < HEX_DIGITS+1)
+ return -EINVAL;
+ return sprintf (page, "%08lx\n", irq_affinity[(long)data]);
+}
+
+static int irq_affinity_write_proc (struct file *file, const char *buffer,
+ unsigned long count, void *data)
+{
+ int irq = (long) data, full_count = count, err;
+ unsigned long new_value;
+
+ if (!irq_desc[irq].handler->set_affinity)
+ return -EIO;
+
+ err = parse_hex_value(buffer, count, &new_value);
+
+ /*
+ * Do not allow disabling IRQs completely - it's a too easy
+ * way to make the system unusable accidentally :-) At least
+ * one online CPU still has to be targeted.
+ */
+ if (!(new_value & cpu_online_map))
+ return -EINVAL;
+
+ irq_affinity[irq] = new_value;
+ irq_desc[irq].handler->set_affinity(irq, new_value);
+
+ return full_count;
+}
+
+#endif
+
+static int prof_cpu_mask_read_proc (char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ unsigned long *mask = (unsigned long *) data;
+ if (count < HEX_DIGITS+1)
+ return -EINVAL;
+ return sprintf (page, "%08lx\n", *mask);
+}
+
+static int prof_cpu_mask_write_proc (struct file *file, const char *buffer,
+ unsigned long count, void *data)
+{
+ unsigned long *mask = (unsigned long *) data, full_count = count, err;
+ unsigned long new_value;
+
+ err = parse_hex_value(buffer, count, &new_value);
+ if (err)
+ return err;
+
+ *mask = new_value;
+ return full_count;
+}
+
+#define MAX_NAMELEN 10
+
+static void register_irq_proc (unsigned int irq)
+{
+ char name [MAX_NAMELEN];
+
+ if (!root_irq_dir || (irq_desc[irq].handler == &no_irq_type) ||
+ irq_dir[irq])
+ return;
+
+ memset(name, 0, MAX_NAMELEN);
+ sprintf(name, "%d", irq);
+
+ /* create /proc/irq/1234 */
+ irq_dir[irq] = proc_mkdir(name, root_irq_dir);
+
+#if CONFIG_SMP
+ {
+ struct proc_dir_entry *entry;
+
+ /* create /proc/irq/1234/smp_affinity */
+ entry = create_proc_entry("smp_affinity", 0600, irq_dir[irq]);
+
+ if (entry) {
+ entry->nlink = 1;
+ entry->data = (void *)(long)irq;
+ entry->read_proc = irq_affinity_read_proc;
+ entry->write_proc = irq_affinity_write_proc;
+ }
+
+ smp_affinity_entry[irq] = entry;
+ }
+#endif
+}
+
+unsigned long prof_cpu_mask = -1;
+
+void init_irq_proc (void)
+{
+ struct proc_dir_entry *entry;
+ int i;
+
+ /* create /proc/irq */
+ root_irq_dir = proc_mkdir("irq", 0);
+
+ /* create /proc/irq/prof_cpu_mask */
+ entry = create_proc_entry("prof_cpu_mask", 0600, root_irq_dir);
+
+ if (!entry)
+ return;
+
+ entry->nlink = 1;
+ entry->data = (void *)&prof_cpu_mask;
+ entry->read_proc = prof_cpu_mask_read_proc;
+ entry->write_proc = prof_cpu_mask_write_proc;
+
+ /*
+ * Create entries for all existing IRQs.
+ */
+ for (i = 0; i < NR_IRQS; i++)
+ register_irq_proc(i);
+}
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/foreign_page.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/foreign_page.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,30 @@
+/******************************************************************************
+ * foreign_page.h
+ *
+ * Provide a "foreign" page type, that is owned by a foreign allocator and
+ * not the normal buddy allocator in page_alloc.c
+ *
+ * Copyright (c) 2004, K A Fraser
+ */
+
+#ifndef __ASM_XEN_FOREIGN_PAGE_H__
+#define __ASM_XEN_FOREIGN_PAGE_H__
+
+#define PG_foreign PG_arch_1
+
+#define PageForeign(page) test_bit(PG_foreign, &(page)->flags)
+
+#define SetPageForeign(page, dtor) do { \
+ set_bit(PG_foreign, &(page)->flags); \
+ (page)->mapping = (void *)dtor; \
+} while (0)
+
+#define ClearPageForeign(page) do { \
+ clear_bit(PG_foreign, &(page)->flags); \
+ (page)->mapping = NULL; \
+} while (0)
+
+#define PageForeignDestructor(page) \
+ ( (void (*) (struct page *)) (page)->mapping )
+
+#endif /* __ASM_XEN_FOREIGN_PAGE_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/cpu/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/cpu/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,31 @@
+#
+# Makefile for x86-compatible CPU details and quirks
+#
+
+CFLAGS += -Iarch/i386/kernel/cpu
+
+obj-y := common.o
+c-obj-y += proc.o
+
+c-obj-y += amd.o
+c-obj-y += cyrix.o
+c-obj-y += centaur.o
+c-obj-y += transmeta.o
+c-obj-y += intel.o intel_cacheinfo.o
+c-obj-y += rise.o
+c-obj-y += nexgen.o
+c-obj-y += umc.o
+
+#obj-$(CONFIG_X86_MCE) += ../../../../i386/kernel/cpu/mcheck/
+
+obj-$(CONFIG_MTRR) += mtrr/
+#obj-$(CONFIG_CPU_FREQ) += ../../../../i386/kernel/cpu/cpufreq/
+
+c-link :=
+
+$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)):
+ @ln -fsn $(srctree)/arch/i386/kernel/cpu/$(notdir $@) $@
+
+obj-y += $(c-obj-y)
+
+clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link))
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/vsyscall.S
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/vsyscall.S Fri Jul 15
13:39:50 2005
@@ -0,0 +1,15 @@
+#include <linux/init.h>
+
+__INITDATA
+
+ .globl vsyscall_int80_start, vsyscall_int80_end
+vsyscall_int80_start:
+ .incbin "arch/xen/i386/kernel/vsyscall-int80.so"
+vsyscall_int80_end:
+
+ .globl vsyscall_sysenter_start, vsyscall_sysenter_end
+vsyscall_sysenter_start:
+ .incbin "arch/xen/i386/kernel/vsyscall-sysenter.so"
+vsyscall_sysenter_end:
+
+__FINIT
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/entry.S
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/entry.S Fri Jul 15
13:39:50 2005
@@ -0,0 +1,1047 @@
+/*
+ * linux/arch/x86_64/entry.S
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs
+ * Copyright (C) 2000 Pavel Machek <pavel@xxxxxxx>
+ *
+ * $Id$
+ *
+ * Jun Nakajima <jun.nakajima@xxxxxxxxx>
+ * Asit Mallick <asit.k.mallick@xxxxxxxxx>
+ * Modified for Xen
+ */
+
+/*
+ * entry.S contains the system-call and fault low-level handling routines.
+ *
+ * NOTE: This code handles signal-recognition, which happens every time
+ * after an interrupt and after each system call.
+ *
+ * Normal syscalls and interrupts don't save a full stack frame, this is
+ * only done for syscall tracing, signals or fork/exec et.al.
+ *
+ * A note on terminology:
+ * - top of stack: Architecture defined interrupt frame from SS to RIP
+ * at the top of the kernel process stack.
+ * - partial stack frame: partially saved registers upto R11.
+ * - full stack frame: Like partial stack frame, but all register saved.
+ *
+ * TODO:
+ * - schedule it carefully for the final hardware.
+ */
+
+#define ASSEMBLY 1
+#include <linux/config.h>
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/smp.h>
+#include <asm/cache.h>
+#include <asm/errno.h>
+#include <asm/dwarf2.h>
+#include <asm/calling.h>
+#include <asm/asm_offset.h>
+#include <asm/msr.h>
+#include <asm/unistd.h>
+#include <asm/thread_info.h>
+#include <asm/hw_irq.h>
+#include <asm/errno.h>
+#include <asm-xen/xen-public/arch-x86_64.h>
+
+#include "irq_vectors.h"
+
+#include "xen_entry.S"
+
+ .code64
+
+#ifdef CONFIG_PREEMPT
+#define preempt_stop XEN_BLOCK_EVENTS(%rsi)
+#else
+#define preempt_stop
+#define retint_kernel retint_restore_args
+#endif
+
+/*
+ * C code is not supposed to know about undefined top of stack. Every time
+ * a C function with an pt_regs argument is called from the SYSCALL based
+ * fast path FIXUP_TOP_OF_STACK is needed.
+ * RESTORE_TOP_OF_STACK syncs the syscall state after any possible ptregs
+ * manipulation.
+ */
+
+ /* %rsp:at FRAMEEND */
+ .macro FIXUP_TOP_OF_STACK tmp
+ movq $__USER_CS,CS(%rsp)
+ movq $-1,RCX(%rsp)
+ .endm
+
+ .macro RESTORE_TOP_OF_STACK tmp,offset=0
+ .endm
+
+ .macro FAKE_STACK_FRAME child_rip
+ /* push in order ss, rsp, eflags, cs, rip */
+ xorq %rax, %rax
+ pushq %rax /* ss */
+ CFI_ADJUST_CFA_OFFSET 8
+ pushq %rax /* rsp */
+ CFI_ADJUST_CFA_OFFSET 8
+ CFI_OFFSET rip,0
+ pushq $(1<<9) /* eflags - interrupts on */
+ CFI_ADJUST_CFA_OFFSET 8
+ pushq $__KERNEL_CS /* cs */
+ CFI_ADJUST_CFA_OFFSET 8
+ pushq \child_rip /* rip */
+ CFI_ADJUST_CFA_OFFSET 8
+ CFI_OFFSET rip,0
+ pushq %rax /* orig rax */
+ CFI_ADJUST_CFA_OFFSET 8
+ .endm
+
+ .macro UNFAKE_STACK_FRAME
+ addq $8*6, %rsp
+ CFI_ADJUST_CFA_OFFSET -(6*8)
+ .endm
+
+ .macro CFI_DEFAULT_STACK
+ CFI_ADJUST_CFA_OFFSET (SS)
+ CFI_OFFSET r15,R15-SS
+ CFI_OFFSET r14,R14-SS
+ CFI_OFFSET r13,R13-SS
+ CFI_OFFSET r12,R12-SS
+ CFI_OFFSET rbp,RBP-SS
+ CFI_OFFSET rbx,RBX-SS
+ CFI_OFFSET r11,R11-SS
+ CFI_OFFSET r10,R10-SS
+ CFI_OFFSET r9,R9-SS
+ CFI_OFFSET r8,R8-SS
+ CFI_OFFSET rax,RAX-SS
+ CFI_OFFSET rcx,RCX-SS
+ CFI_OFFSET rdx,RDX-SS
+ CFI_OFFSET rsi,RSI-SS
+ CFI_OFFSET rdi,RDI-SS
+ CFI_OFFSET rsp,RSP-SS
+ CFI_OFFSET rip,RIP-SS
+ .endm
+
+ /*
+ * Must be consistent with the definition in arch_x86_64.h:
+ * struct switch_to_user {
+ * u64 rax, r11, rcx, flags, rip, cs, rflags, rsp, ss;
+ * };
+ * #define VGCF_IN_SYSCALL (1<<8)
+ */
+ .macro SWITCH_TO_USER flag
+ movl $0,%gs:pda_kernel_mode # change to user mode
+ subq $8*4,%rsp # reuse rip, cs, rflags, rsp, ss in
the stack
+ movq %rax,(%rsp)
+ movq %r11,1*8(%rsp)
+ movq %rcx,2*8(%rsp) # we saved %rcx upon exceptions
+ movq $\flag,3*8(%rsp)
+ movq $__HYPERVISOR_switch_to_user,%rax
+ syscall
+ .endm
+
+ .macro SWITCH_TO_KERNEL ssoff,adjust=0
+ btsq $0,%gs:pda_kernel_mode
+ jc 1f
+ orb $1,\ssoff-\adjust+4(%rsp)
+1:
+ .endm
+
+/*
+ * A newly forked process directly context switches into this.
+ */
+/* rdi: prev */
+ENTRY(ret_from_fork)
+ CFI_STARTPROC
+ CFI_DEFAULT_STACK
+ call schedule_tail
+ GET_THREAD_INFO(%rcx)
+ testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),threadinfo_flags(%rcx)
+ jnz rff_trace
+rff_action:
+ RESTORE_REST
+ testl $3,CS-ARGOFFSET(%rsp) # from kernel_thread?
+ je int_ret_from_sys_call
+ testl $_TIF_IA32,threadinfo_flags(%rcx)
+ jnz int_ret_from_sys_call
+ RESTORE_TOP_OF_STACK %rdi,ARGOFFSET
+ jmp ret_from_sys_call
+rff_trace:
+ movq %rsp,%rdi
+ call syscall_trace_leave
+ GET_THREAD_INFO(%rcx)
+ jmp rff_action
+ CFI_ENDPROC
+
+/*
+ * System call entry. Upto 6 arguments in registers are supported.
+ *
+ * SYSCALL does not save anything on the stack and does not change the
+ * stack pointer.
+ */
+
+/*
+ * Register setup:
+ * rax system call number
+ * rdi arg0
+ * rcx return address for syscall/sysret, C arg3
+ * rsi arg1
+ * rdx arg2
+ * r10 arg3 (--> moved to rcx for C)
+ * r8 arg4
+ * r9 arg5
+ * r11 eflags for syscall/sysret, temporary for C
+ * r12-r15,rbp,rbx saved by C code, not touched.
+ *
+ * Interrupts are off on entry.
+ * Only called from user space.
+ *
+ * XXX if we had a free scratch register we could save the RSP into the stack
frame
+ * and report it properly in ps. Unfortunately we haven't.
+ */
+
+ENTRY(system_call)
+ CFI_STARTPROC
+ SAVE_ARGS -8,0
+ movq %rax,ORIG_RAX-ARGOFFSET(%rsp)
+ XEN_UNBLOCK_EVENTS(%r11)
+ GET_THREAD_INFO(%rcx)
+ testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),threadinfo_flags(%rcx)
+ jnz tracesys
+ cmpq $__NR_syscall_max,%rax
+ ja badsys
+ movq %r10,%rcx
+ call *sys_call_table(,%rax,8) # XXX: rip relative
+ movq %rax,RAX-ARGOFFSET(%rsp)
+/*
+ * Syscall return path ending with SYSRET (fast path)
+ * Has incomplete stack frame and undefined top of stack.
+ */
+ .globl ret_from_sys_call
+ret_from_sys_call:
+ movl $_TIF_WORK_MASK,%edi
+ /* edi: flagmask */
+sysret_check:
+ GET_THREAD_INFO(%rcx)
+ XEN_BLOCK_EVENTS(%rsi)
+ movl threadinfo_flags(%rcx),%edx
+ andl %edi,%edx
+ jnz sysret_careful
+ XEN_UNBLOCK_EVENTS(%rsi)
+ RESTORE_ARGS 0,8,0
+ SWITCH_TO_USER VGCF_IN_SYSCALL
+
+ /* Handle reschedules */
+ /* edx: work, edi: workmask */
+sysret_careful:
+ bt $TIF_NEED_RESCHED,%edx
+ jnc sysret_signal
+ XEN_BLOCK_EVENTS(%rsi)
+ pushq %rdi
+ call schedule
+ popq %rdi
+ jmp sysret_check
+
+ /* Handle a signal */
+sysret_signal:
+/* sti */
+ XEN_UNBLOCK_EVENTS(%rsi)
+ testl $(_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SINGLESTEP),%edx
+ jz 1f
+
+ /* Really a signal */
+ /* edx: work flags (arg3) */
+ leaq do_notify_resume(%rip),%rax
+ leaq -ARGOFFSET(%rsp),%rdi # &pt_regs -> arg1
+ xorl %esi,%esi # oldset -> arg2
+ call ptregscall_common
+1: movl $_TIF_NEED_RESCHED,%edi
+ jmp sysret_check
+
+ /* Do syscall tracing */
+tracesys:
+ SAVE_REST
+ movq $-ENOSYS,RAX(%rsp)
+ FIXUP_TOP_OF_STACK %rdi
+ movq %rsp,%rdi
+ call syscall_trace_enter
+ LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed
it */
+ RESTORE_REST
+ cmpq $__NR_syscall_max,%rax
+ ja 1f
+ movq %r10,%rcx /* fixup for C */
+ call *sys_call_table(,%rax,8)
+ movq %rax,RAX-ARGOFFSET(%rsp)
+1: SAVE_REST
+ movq %rsp,%rdi
+ call syscall_trace_leave
+ RESTORE_TOP_OF_STACK %rbx
+ RESTORE_REST
+ jmp ret_from_sys_call
+
+badsys:
+ movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
+ jmp ret_from_sys_call
+
+/*
+ * Syscall return path ending with IRET.
+ * Has correct top of stack, but partial stack frame.
+ */
+ENTRY(int_ret_from_sys_call)
+ XEN_BLOCK_EVENTS(%rsi)
+ testb $3,CS-ARGOFFSET(%rsp)
+ jnz 1f
+ /* Need to set the proper %ss (not NULL) for ring 3 iretq */
+ movl $__KERNEL_DS,SS-ARGOFFSET(%rsp)
+ jmp retint_restore_args # retrun from ring3 kernel
+1:
+ movl $_TIF_ALLWORK_MASK,%edi
+ /* edi: mask to check */
+int_with_check:
+ GET_THREAD_INFO(%rcx)
+ movl threadinfo_flags(%rcx),%edx
+ andl %edi,%edx
+ jnz int_careful
+ jmp retint_restore_args
+
+ /* Either reschedule or signal or syscall exit tracking needed. */
+ /* First do a reschedule test. */
+ /* edx: work, edi: workmask */
+int_careful:
+ bt $TIF_NEED_RESCHED,%edx
+ jnc int_very_careful
+/* sti */
+ XEN_UNBLOCK_EVENTS(%rsi)
+ pushq %rdi
+ call schedule
+ popq %rdi
+ jmp int_with_check
+
+ /* handle signals and tracing -- both require a full stack frame */
+int_very_careful:
+/* sti */
+ XEN_UNBLOCK_EVENTS(%rsi)
+ SAVE_REST
+ /* Check for syscall exit trace */
+ testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP),%edx
+ jz int_signal
+ pushq %rdi
+ leaq 8(%rsp),%rdi # &ptregs -> arg1
+ call syscall_trace_leave
+ popq %rdi
+ btr $TIF_SYSCALL_TRACE,%edi
+ btr $TIF_SYSCALL_AUDIT,%edi
+ btr $TIF_SINGLESTEP,%edi
+ jmp int_restore_rest
+
+int_signal:
+ testl $(_TIF_NOTIFY_RESUME|_TIF_SIGPENDING|_TIF_SINGLESTEP),%edx
+ jz 1f
+ movq %rsp,%rdi # &ptregs -> arg1
+ xorl %esi,%esi # oldset -> arg2
+ call do_notify_resume
+1: movl $_TIF_NEED_RESCHED,%edi
+int_restore_rest:
+ RESTORE_REST
+ jmp int_with_check
+ CFI_ENDPROC
+
+/*
+ * Certain special system calls that need to save a complete full stack frame.
+ */
+
+ .macro PTREGSCALL label,func,arg
+ .globl \label
+\label:
+ leaq \func(%rip),%rax
+ leaq -ARGOFFSET+8(%rsp),\arg /* 8 for return address */
+ jmp ptregscall_common
+ .endm
+
+ PTREGSCALL stub_clone, sys_clone, %r8
+ PTREGSCALL stub_fork, sys_fork, %rdi
+ PTREGSCALL stub_vfork, sys_vfork, %rdi
+ PTREGSCALL stub_rt_sigsuspend, sys_rt_sigsuspend, %rdx
+ PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx
+ PTREGSCALL stub_iopl, sys_iopl, %rsi
+
+ENTRY(ptregscall_common)
+ CFI_STARTPROC
+ popq %r11
+ CFI_ADJUST_CFA_OFFSET -8
+ SAVE_REST
+ movq %r11, %r15
+ FIXUP_TOP_OF_STACK %r11
+ call *%rax
+ RESTORE_TOP_OF_STACK %r11
+ movq %r15, %r11
+ RESTORE_REST
+ pushq %r11
+ CFI_ADJUST_CFA_OFFSET 8
+ ret
+ CFI_ENDPROC
+
+ENTRY(stub_execve)
+ CFI_STARTPROC
+ popq %r11
+ CFI_ADJUST_CFA_OFFSET -8
+ SAVE_REST
+ movq %r11, %r15
+ FIXUP_TOP_OF_STACK %r11
+ call sys_execve
+ GET_THREAD_INFO(%rcx)
+ bt $TIF_IA32,threadinfo_flags(%rcx)
+ jc exec_32bit
+ RESTORE_TOP_OF_STACK %r11
+ movq %r15, %r11
+ RESTORE_REST
+ push %r11
+ ret
+
+exec_32bit:
+ CFI_ADJUST_CFA_OFFSET REST_SKIP
+ movq %rax,RAX(%rsp)
+ RESTORE_REST
+ jmp int_ret_from_sys_call
+ CFI_ENDPROC
+
+/*
+ * sigreturn is special because it needs to restore all registers on return.
+ * This cannot be done with SYSRET, so use the IRET return path instead.
+ */
+ENTRY(stub_rt_sigreturn)
+ CFI_STARTPROC
+ addq $8, %rsp
+ SAVE_REST
+ movq %rsp,%rdi
+ FIXUP_TOP_OF_STACK %r11
+ call sys_rt_sigreturn
+ movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
+ RESTORE_REST
+ jmp int_ret_from_sys_call
+ CFI_ENDPROC
+
+
+/*
+ * Interrupt entry/exit.
+ *
+ * Interrupt entry points save only callee clobbered registers in fast path.
+ *
+ * Entry runs with interrupts off.
+ */
+
+/* 0(%rsp): interrupt number */
+ .macro interrupt func
+ CFI_STARTPROC simple
+ CFI_DEF_CFA rsp,(SS-RDI)
+ CFI_REL_OFFSET rsp,(RSP-ORIG_RAX)
+ CFI_REL_OFFSET rip,(RIP-ORIG_RAX)
+ cld
+#ifdef CONFIG_DEBUG_INFO
+ SAVE_ALL
+ movq %rsp,%rdi
+ /*
+ * Setup a stack frame pointer. This allows gdb to trace
+ * back to the original stack.
+ */
+ movq %rsp,%rbp
+ CFI_DEF_CFA_REGISTER rbp
+#else
+ SAVE_ARGS
+ leaq -ARGOFFSET(%rsp),%rdi # arg1 for handler
+#endif
+#if 0 /* For Xen we don't need to do this */
+ testl $3,CS(%rdi)
+ je 1f
+ swapgs
+#endif
+1: addl $1,%gs:pda_irqcount # RED-PEN should check preempt count
+ movq %gs:pda_irqstackptr,%rax
+ cmoveq %rax,%rsp
+ pushq %rdi # save old stack
+ call \func
+ .endm
+
+retint_check:
+ movl threadinfo_flags(%rcx),%edx
+ andl %edi,%edx
+ jnz retint_careful
+retint_restore_args:
+ movb EVENT_MASK-REST_SKIP(%rsp), %al
+ notb %al # %al == ~saved_mask
+ XEN_GET_VCPU_INFO(%rsi)
+ andb evtchn_upcall_mask(%rsi),%al
+ andb $1,%al # %al == mask & ~saved_mask
+ jnz restore_all_enable_events # != 0 => reenable event delivery
+ XEN_PUT_VCPU_INFO(%rsi)
+
+ RESTORE_ARGS 0,8,0
+ testb $3,8(%rsp) # check CS
+ jnz user_mode
+kernel_mode:
+ orb $3,1*8(%rsp)
+ iretq
+user_mode:
+ SWITCH_TO_USER 0
+
+ /* edi: workmask, edx: work */
+retint_careful:
+ bt $TIF_NEED_RESCHED,%edx
+ jnc retint_signal
+ XEN_UNBLOCK_EVENTS(%rsi)
+/* sti */
+ pushq %rdi
+ call schedule
+ popq %rdi
+ XEN_BLOCK_EVENTS(%rsi)
+ GET_THREAD_INFO(%rcx)
+/* cli */
+ jmp retint_check
+
+retint_signal:
+ testl $(_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SINGLESTEP),%edx
+ jz retint_restore_args
+ XEN_UNBLOCK_EVENTS(%rsi)
+ SAVE_REST
+ movq $-1,ORIG_RAX(%rsp)
+ xorq %rsi,%rsi # oldset
+ movq %rsp,%rdi # &pt_regs
+ call do_notify_resume
+ RESTORE_REST
+ XEN_BLOCK_EVENTS(%rsi)
+ movl $_TIF_NEED_RESCHED,%edi
+ GET_THREAD_INFO(%rcx)
+ jmp retint_check
+
+#ifdef CONFIG_PREEMPT
+ /* Returning to kernel space. Check if we need preemption */
+ /* rcx: threadinfo. interrupts off. */
+ .p2align
+retint_kernel:
+ cmpl $0,threadinfo_preempt_count(%rcx)
+ jnz retint_restore_args
+ bt $TIF_NEED_RESCHED,threadinfo_flags(%rcx)
+ jnc retint_restore_args
+ bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */
+ jc retint_restore_args
+ movl $PREEMPT_ACTIVE,threadinfo_preempt_count(%rcx)
+/* sti */
+ XEN_UNBLOCK_EVENTS(%rsi)
+ call schedule
+ XEN_BLOCK_EVENTS(%rsi)
+/* cli */
+ GET_THREAD_INFO(%rcx)
+ movl $0,threadinfo_preempt_count(%rcx)
+ jmp retint_kernel /* check again */
+#endif
+ CFI_ENDPROC
+
+/*
+ * APIC interrupts.
+ */
+ .macro apicinterrupt num,func
+ pushq $\num-256
+ interrupt \func
+ jmp error_entry
+ CFI_ENDPROC
+ .endm
+
+#ifdef CONFIG_SMP
+ENTRY(reschedule_interrupt)
+ apicinterrupt RESCHEDULE_VECTOR,smp_reschedule_interrupt
+
+ENTRY(invalidate_interrupt)
+ apicinterrupt INVALIDATE_TLB_VECTOR,smp_invalidate_interrupt
+
+ENTRY(call_function_interrupt)
+ apicinterrupt CALL_FUNCTION_VECTOR,smp_call_function_interrupt
+#endif
+
+#ifdef CONFIG_X86_LOCAL_APIC
+ENTRY(apic_timer_interrupt)
+ apicinterrupt LOCAL_TIMER_VECTOR,smp_apic_timer_interrupt
+
+ENTRY(error_interrupt)
+ apicinterrupt ERROR_APIC_VECTOR,smp_error_interrupt
+
+ENTRY(spurious_interrupt)
+ apicinterrupt SPURIOUS_APIC_VECTOR,smp_spurious_interrupt
+#endif
+
+/*
+ * Exception entry points.
+ */
+ .macro zeroentry sym
+ movq (%rsp),%rcx
+ movq 8(%rsp),%r11
+ addq $0x10,%rsp /* skip rcx and r11 */
+ pushq $0 /* push error code/oldrax */
+ pushq %rax /* push real oldrax to the rdi slot */
+ leaq \sym(%rip),%rax
+ jmp error_entry
+ .endm
+
+ .macro errorentry sym
+ movq (%rsp),%rcx
+ movq 8(%rsp),%r11
+ addq $0x10,%rsp /* rsp points to the error code */
+ pushq %rax
+ leaq \sym(%rip),%rax
+ jmp error_entry
+ .endm
+
+ /* error code is on the stack already */
+ /* handle NMI like exceptions that can happen everywhere */
+ .macro paranoidentry sym
+ movq (%rsp),%rcx
+ movq 8(%rsp),%r11
+ addq $0x10,%rsp /* skip rcx and r11 */
+ SAVE_ALL
+ cld
+ movl $1,%ebx
+ movl $MSR_GS_BASE,%ecx
+ rdmsr
+ testl %edx,%edx
+ js 1f
+/* swapgs */
+ xorl %ebx,%ebx
+1: movq %rsp,%rdi
+ movq ORIG_RAX(%rsp),%rsi
+ movq $-1,ORIG_RAX(%rsp)
+ call \sym
+ .endm
+
+/*
+ * Exception entry point. This expects an error code/orig_rax on the stack
+ * and the exception handler in %rax.
+ */
+ENTRY(error_entry)
+ CFI_STARTPROC simple
+ CFI_DEF_CFA rsp,(SS-RDI)
+ CFI_REL_OFFSET rsp,(RSP-RDI)
+ CFI_REL_OFFSET rip,(RIP-RDI)
+ /* rdi slot contains rax, oldrax contains error code */
+ cld
+ subq $14*8,%rsp
+ CFI_ADJUST_CFA_OFFSET (14*8)
+ movq %rsi,13*8(%rsp)
+ CFI_REL_OFFSET rsi,RSI
+ movq 14*8(%rsp),%rsi /* load rax from rdi slot */
+ movq %rdx,12*8(%rsp)
+ CFI_REL_OFFSET rdx,RDX
+ movq %rcx,11*8(%rsp)
+ CFI_REL_OFFSET rcx,RCX
+ movq %rsi,10*8(%rsp) /* store rax */
+ CFI_REL_OFFSET rax,RAX
+ movq %r8, 9*8(%rsp)
+ CFI_REL_OFFSET r8,R8
+ movq %r9, 8*8(%rsp)
+ CFI_REL_OFFSET r9,R9
+ movq %r10,7*8(%rsp)
+ CFI_REL_OFFSET r10,R10
+ movq %r11,6*8(%rsp)
+ CFI_REL_OFFSET r11,R11
+ movq %rbx,5*8(%rsp)
+ CFI_REL_OFFSET rbx,RBX
+ movq %rbp,4*8(%rsp)
+ CFI_REL_OFFSET rbp,RBP
+ movq %r12,3*8(%rsp)
+ CFI_REL_OFFSET r12,R12
+ movq %r13,2*8(%rsp)
+ CFI_REL_OFFSET r13,R13
+ movq %r14,1*8(%rsp)
+ CFI_REL_OFFSET r14,R14
+ movq %r15,(%rsp)
+ CFI_REL_OFFSET r15,R15
+#if 0
+ cmpl $__KERNEL_CS,CS(%rsp)
+ je error_kernelspace
+#endif
+error_call_handler:
+ movq %rdi, RDI(%rsp)
+ movq %rsp,%rdi
+ movq ORIG_RAX(%rsp),%rsi # get error code
+ movq $-1,ORIG_RAX(%rsp)
+ call *%rax
+error_exit:
+ RESTORE_REST
+/* cli */
+ XEN_BLOCK_EVENTS(%rsi)
+ GET_THREAD_INFO(%rcx)
+ testb $3,CS-ARGOFFSET(%rsp)
+ jz retint_kernel
+ movl threadinfo_flags(%rcx),%edx
+ movl $_TIF_WORK_MASK,%edi
+ andl %edi,%edx
+ jnz retint_careful
+ jmp retint_restore_args
+
+error_kernelspace:
+ /*
+ * We need to re-write the logic here because we don't do iretq to
+ * to return to user mode. It's still possible that we get trap/fault
+ * in the kernel (when accessing buffers pointed to by system calls,
+ * for example).
+ *
+ */
+#if 0
+ incl %ebx
+ /* There are two places in the kernel that can potentially fault with
+ usergs. Handle them here. The exception handlers after
+ iret run with kernel gs again, so don't set the user space flag.
+ B stepping K8s sometimes report an truncated RIP for IRET
+ exceptions returning to compat mode. Check for these here too. */
+ leaq iret_label(%rip),%rbp
+ cmpq %rbp,RIP(%rsp)
+ je error_swapgs
+ movl %ebp,%ebp /* zero extend */
+ cmpq %rbp,RIP(%rsp)
+ je error_swapgs
+ cmpq $gs_change,RIP(%rsp)
+ je error_swapgs
+ jmp error_sti
+#endif
+
+ENTRY(hypervisor_callback)
+ zeroentry do_hypervisor_callback
+
+/*
+ * Copied from arch/xen/i386/kernel/entry.S
+ */
+# A note on the "critical region" in our callback handler.
+# We want to avoid stacking callback handlers due to events occurring
+# during handling of the last event. To do this, we keep events disabled
+# until we've done all processing. HOWEVER, we must enable events before
+# popping the stack frame (can't be done atomically) and so it would still
+# be possible to get enough handler activations to overflow the stack.
+# Although unlikely, bugs of that kind are hard to track down, so we'd
+# like to avoid the possibility.
+# So, on entry to the handler we detect whether we interrupted an
+# existing activation in its critical region -- if so, we pop the current
+# activation and restart the handler using the previous one.
+ENTRY(do_hypervisor_callback) # do_hyperviosr_callback(struct *pt_regs)
+# Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
+# see the correct pointer to the pt_regs
+ addq $8, %rsp # we don't return, adjust the stack frame
+11: movb $0, EVENT_MASK(%rsp)
+ call evtchn_do_upcall
+ jmp error_exit
+
+ ALIGN
+restore_all_enable_events:
+ XEN_UNBLOCK_EVENTS(%rsi) # %rsi is already set up...
+
+scrit: /**** START OF CRITICAL REGION ****/
+ XEN_TEST_PENDING(%rsi)
+ jnz 14f # process more events if necessary...
+ XEN_PUT_VCPU_INFO(%rsi)
+ RESTORE_ARGS 0,8,0
+ testb $3,8(%rsp) # check CS
+ jnz crit_user_mode
+ orb $3,1*8(%rsp)
+ iretq
+crit_user_mode:
+ SWITCH_TO_USER 0
+
+14: XEN_LOCKED_BLOCK_EVENTS(%rsi)
+ XEN_PUT_VCPU_INFO(%rsi)
+ SAVE_REST
+ movq %rsp,%rdi # set the argument again
+ jmp 11b
+ecrit: /**** END OF CRITICAL REGION ****/
+# At this point, unlike on x86-32, we don't do the fixup to simplify the
+# code and the stack frame is more complex on x86-64.
+# When the kernel is interrupted in the critical section, the kernel
+# will do IRET in that case, and everything will be restored at that point,
+# i.e. it just resumes from the next instruction interrupted with the same
context.
+
+# Hypervisor uses this for application faults while it executes.
+ENTRY(failsafe_callback)
+ addq $0x10,%rsp /* skip rcx and r11 */
+1: movl (%rsp),%ds
+2: movl 8(%rsp),%es
+3: movl 16(%rsp),%fs
+4: movl 24(%rsp),%gs
+ addq $0x20,%rsp /* skip the above selectors */
+ SAVE_ALL
+ jmp error_exit
+.section .fixup,"ax"; \
+6: movq $0,(%rsp); \
+ jmp 1b; \
+7: movq $0,8(%rsp); \
+ jmp 2b; \
+8: movq $0,16(%rsp); \
+ jmp 3b; \
+9: movq $0,24(%rsp); \
+ jmp 4b; \
+.previous; \
+.section __ex_table,"a";\
+ .align 16; \
+ .quad 1b,6b; \
+ .quad 2b,7b; \
+ .quad 3b,8b; \
+ .quad 4b,9b; \
+.previous
+
+#if 0
+ .section __ex_table,"a"
+ .align 8
+ .quad gs_change,bad_gs
+ .previous
+ .section .fixup,"ax"
+ /* running with kernelgs */
+bad_gs:
+/* swapgs */ /* switch back to user gs */
+ xorl %eax,%eax
+ movl %eax,%gs
+ jmp 2b
+ .previous
+#endif
+
+/*
+ * Create a kernel thread.
+ *
+ * C extern interface:
+ * extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long
flags)
+ *
+ * asm input arguments:
+ * rdi: fn, rsi: arg, rdx: flags
+ */
+ENTRY(kernel_thread)
+ CFI_STARTPROC
+ FAKE_STACK_FRAME $child_rip
+ SAVE_ALL
+
+ # rdi: flags, rsi: usp, rdx: will be &pt_regs
+ movq %rdx,%rdi
+ orq kernel_thread_flags(%rip),%rdi
+ movq $-1, %rsi
+ movq %rsp, %rdx
+
+ xorl %r8d,%r8d
+ xorl %r9d,%r9d
+
+ # clone now
+ call do_fork
+ movq %rax,RAX(%rsp)
+ xorl %edi,%edi
+
+ /*
+ * It isn't worth to check for reschedule here,
+ * so internally to the x86_64 port you can rely on kernel_thread()
+ * not to reschedule the child before returning, this avoids the need
+ * of hacks for example to fork off the per-CPU idle tasks.
+ * [Hopefully no generic code relies on the reschedule -AK]
+ */
+ RESTORE_ALL
+ UNFAKE_STACK_FRAME
+ ret
+ CFI_ENDPROC
+
+
+child_rip:
+ /*
+ * Here we are in the child and the registers are set as they were
+ * at kernel_thread() invocation in the parent.
+ */
+ movq %rdi, %rax
+ movq %rsi, %rdi
+ call *%rax
+ # exit
+ xorq %rdi, %rdi
+ call do_exit
+
+/*
+ * execve(). This function needs to use IRET, not SYSRET, to set up all state
properly.
+ *
+ * C extern interface:
+ * extern long execve(char *name, char **argv, char **envp)
+ *
+ * asm input arguments:
+ * rdi: name, rsi: argv, rdx: envp
+ *
+ * We want to fallback into:
+ * extern long sys_execve(char *name, char **argv,char **envp, struct
pt_regs regs)
+ *
+ * do_sys_execve asm fallback arguments:
+ * rdi: name, rsi: argv, rdx: envp, fake frame on the stack
+ */
+ENTRY(execve)
+ CFI_STARTPROC
+ FAKE_STACK_FRAME $0
+ SAVE_ALL
+ call sys_execve
+ movq %rax, RAX(%rsp)
+ RESTORE_REST
+ testq %rax,%rax
+ jne 1f
+ jmp int_ret_from_sys_call
+1: RESTORE_ARGS
+ UNFAKE_STACK_FRAME
+ ret
+ CFI_ENDPROC
+
+
+ /*
+ * Copy error_entry because of the different stack frame
+ */
+ENTRY(page_fault)
+ movq (%rsp),%rcx
+ movq 8(%rsp),%r11
+ addq $0x10,%rsp # now %rsp points to %cr2
+ pushq %rax
+ leaq do_page_fault(%rip),%rax
+ cld
+ subq $13*8,%rsp
+ movq %rdx,12*8(%rsp) # save %rdx
+ movq 13*8(%rsp),%rdx # load rax
+ movq %rcx,11*8(%rsp)
+ movq %rdx,10*8(%rsp) # store rax
+ movq %rsi,13*8(%rsp) # now save %rsi
+ movq 14*8(%rsp),%rdx # load %cr2, 3rd argument
+ movq %r8, 9*8(%rsp)
+ movq %r9, 8*8(%rsp)
+ movq %r10,7*8(%rsp)
+ movq %r11,6*8(%rsp)
+ movq %rbx,5*8(%rsp)
+ movq %rbp,4*8(%rsp)
+ movq %r12,3*8(%rsp)
+ movq %r13,2*8(%rsp)
+ movq %r14,1*8(%rsp)
+ movq %r15,(%rsp)
+#if 0
+ cmpl $__KERNEL_CS,CS(%rsp)
+ je error_kernelspace
+#endif
+ /*
+ * 1st and 2nd arguments are set by error_call_handler
+ */
+ jmp error_call_handler
+
+ENTRY(coprocessor_error)
+ zeroentry do_coprocessor_error
+
+ENTRY(simd_coprocessor_error)
+ zeroentry do_simd_coprocessor_error
+
+ENTRY(device_not_available)
+ zeroentry math_state_restore
+
+ /* runs on exception stack */
+ENTRY(debug)
+ CFI_STARTPROC
+ pushq $0
+ CFI_ADJUST_CFA_OFFSET 8
+ paranoidentry do_debug
+ /* switch back to process stack to restore the state ptrace touched */
+ movq %rax,%rsp
+ jmp paranoid_exit
+ CFI_ENDPROC
+
+#if 0
+ /* runs on exception stack */
+ENTRY(nmi)
+ CFI_STARTPROC
+ pushq $-1
+ CFI_ADJUST_CFA_OFFSET 8
+ paranoidentry do_nmi
+ /* ebx: no swapgs flag */
+#endif
+paranoid_exit:
+ testl %ebx,%ebx /* swapgs needed? */
+ jnz paranoid_restore
+paranoid_swapgs:
+/* cli
+ swapgs */
+paranoid_restore:
+ RESTORE_ALL 8
+/* iretq */
+paranoid_userspace:
+/* cli */
+ GET_THREAD_INFO(%rcx)
+ movl threadinfo_flags(%rcx),%edx
+ testl $_TIF_NEED_RESCHED,%edx
+ jnz paranoid_resched
+ testl $(_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SINGLESTEP),%edx
+ jnz paranoid_signal
+ jmp paranoid_swapgs
+paranoid_resched:
+/* sti */
+ call schedule
+ jmp paranoid_exit
+paranoid_signal:
+/* sti */
+ xorl %esi,%esi /* oldset */
+ movq %rsp,%rdi /* &pt_regs */
+ call do_notify_resume
+ jmp paranoid_exit
+ CFI_ENDPROC
+
+ENTRY(int3)
+ zeroentry do_int3
+
+ENTRY(overflow)
+ zeroentry do_overflow
+
+ENTRY(bounds)
+ zeroentry do_bounds
+
+ENTRY(invalid_op)
+ zeroentry do_invalid_op
+
+ENTRY(coprocessor_segment_overrun)
+ zeroentry do_coprocessor_segment_overrun
+
+ENTRY(reserved)
+ zeroentry do_reserved
+
+ /* runs on exception stack */
+ENTRY(double_fault)
+ CFI_STARTPROC
+ paranoidentry do_double_fault
+ movq %rax,%rsp
+ jmp paranoid_exit
+ CFI_ENDPROC
+
+ENTRY(invalid_TSS)
+ errorentry do_invalid_TSS
+
+ENTRY(segment_not_present)
+ errorentry do_segment_not_present
+
+ /* runs on exception stack */
+ENTRY(stack_segment)
+ CFI_STARTPROC
+ paranoidentry do_stack_segment
+ movq %rax,%rsp
+ jmp paranoid_exit
+ CFI_ENDPROC
+
+ENTRY(general_protection)
+ errorentry do_general_protection
+
+ENTRY(alignment_check)
+ errorentry do_alignment_check
+
+ENTRY(divide_error)
+ zeroentry do_divide_error
+
+ENTRY(spurious_interrupt_bug)
+ zeroentry do_spurious_interrupt_bug
+
+#ifdef CONFIG_X86_MCE
+ /* runs on exception stack */
+ENTRY(machine_check)
+ CFI_STARTPROC
+ pushq $0
+ CFI_ADJUST_CFA_OFFSET 8
+ paranoidentry do_machine_check
+ jmp paranoid_exit
+ CFI_ENDPROC
+#endif
+
+ENTRY(call_debug)
+ zeroentry do_call_debug
+
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/kernel/fixup.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/kernel/fixup.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,87 @@
+/******************************************************************************
+ * fixup.c
+ *
+ * Binary-rewriting of certain IA32 instructions, on notification by Xen.
+ * Used to avoid repeated slow emulation of common instructions used by the
+ * user-space TLS (Thread-Local Storage) libraries.
+ *
+ * **** NOTE ****
+ * Issues with the binary rewriting have caused it to be removed. Instead
+ * we rely on Xen's emulator to boot the kernel, and then print a banner
+ * message recommending that the user disables /lib/tls.
+ *
+ * Copyright (c) 2004, K A Fraser
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/version.h>
+
+#define DP(_f, _args...) printk(KERN_ALERT " " _f "\n" , ## _args )
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+#define __LINKAGE fastcall
+#else
+#define __LINKAGE asmlinkage
+#endif
+
+__LINKAGE void do_fixup_4gb_segment(struct pt_regs *regs, long error_code)
+{
+ static unsigned long printed = 0;
+ char info[100];
+ int i;
+
+ if ( !test_and_set_bit(0, &printed) )
+ {
+ HYPERVISOR_vm_assist(VMASST_CMD_disable,
+ VMASST_TYPE_4gb_segments_notify);
+
+ sprintf(info, "%s (pid=%d)", current->comm, current->tgid);
+
+ DP("");
+ DP("***************************************************************");
+ DP("***************************************************************");
+ DP("** WARNING: Currently emulating unsupported memory accesses **");
+ DP("** in /lib/tls libraries. The emulation is very **");
+ DP("** slow. To ensure full performance you should **");
+ DP("** execute the following as root: **");
+ DP("** mv /lib/tls /lib/tls.disabled **");
+ DP("** Offending process: %-38.38s **", info);
+ DP("***************************************************************");
+ DP("***************************************************************");
+ DP("");
+
+ for ( i = 5; i > 0; i-- )
+ {
+ printk("Pausing... %d", i);
+ mdelay(1000);
+ printk("\b\b\b\b\b\b\b\b\b\b\b\b");
+ }
+ printk("Continuing...\n\n");
+ }
+}
+
+static int __init fixup_init(void)
+{
+ HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments_notify);
+ return 0;
+}
+__initcall(fixup_init);
diff -r 35b74976f598 -r a83ac0806d6b patches/linux-2.6.11/udp-frag.patch
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/patches/linux-2.6.11/udp-frag.patch Fri Jul 15 13:39:50 2005
@@ -0,0 +1,55 @@
+diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
+--- a/net/ipv4/udp.c
++++ b/net/ipv4/udp.c
+@@ -738,7 +738,7 @@ int udp_ioctl(struct sock *sk, int cmd,
+ unsigned long amount;
+
+ amount = 0;
+- spin_lock_irq(&sk->sk_receive_queue.lock);
++ spin_lock_bh(&sk->sk_receive_queue.lock);
+ skb = skb_peek(&sk->sk_receive_queue);
+ if (skb != NULL) {
+ /*
+@@ -748,7 +748,7 @@ int udp_ioctl(struct sock *sk, int cmd,
+ */
+ amount = skb->len - sizeof(struct udphdr);
+ }
+- spin_unlock_irq(&sk->sk_receive_queue.lock);
++ spin_unlock_bh(&sk->sk_receive_queue.lock);
+ return put_user(amount, (int __user *)arg);
+ }
+
+@@ -848,12 +848,12 @@ csum_copy_err:
+ /* Clear queue. */
+ if (flags&MSG_PEEK) {
+ int clear = 0;
+- spin_lock_irq(&sk->sk_receive_queue.lock);
++ spin_lock_bh(&sk->sk_receive_queue.lock);
+ if (skb == skb_peek(&sk->sk_receive_queue)) {
+ __skb_unlink(skb, &sk->sk_receive_queue);
+ clear = 1;
+ }
+- spin_unlock_irq(&sk->sk_receive_queue.lock);
++ spin_unlock_bh(&sk->sk_receive_queue.lock);
+ if (clear)
+ kfree_skb(skb);
+ }
+@@ -1334,7 +1334,7 @@ unsigned int udp_poll(struct file *file,
+ struct sk_buff_head *rcvq = &sk->sk_receive_queue;
+ struct sk_buff *skb;
+
+- spin_lock_irq(&rcvq->lock);
++ spin_lock_bh(&rcvq->lock);
+ while ((skb = skb_peek(rcvq)) != NULL) {
+ if (udp_checksum_complete(skb)) {
+ UDP_INC_STATS_BH(UDP_MIB_INERRORS);
+@@ -1345,7 +1345,7 @@ unsigned int udp_poll(struct file *file,
+ break;
+ }
+ }
+- spin_unlock_irq(&rcvq->lock);
++ spin_unlock_bh(&rcvq->lock);
+
+ /* nothing to see, move along */
+ if (skb == NULL)
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/console/console.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/console/console.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,811 @@
+/******************************************************************************
+ * console.c
+ *
+ * Virtual console driver.
+ *
+ * Copyright (c) 2002-2004, K A Fraser.
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/config.h>
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/tty.h>
+#include <linux/tty_flip.h>
+#include <linux/serial.h>
+#include <linux/major.h>
+#include <linux/ptrace.h>
+#include <linux/ioport.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/console.h>
+#include <linux/bootmem.h>
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/uaccess.h>
+#include <asm-xen/xen-public/event_channel.h>
+#include <asm-xen/hypervisor.h>
+#include <asm-xen/evtchn.h>
+#include <asm-xen/ctrl_if.h>
+
+/*
+ * Modes:
+ * 'xencons=off' [XC_OFF]: Console is disabled.
+ * 'xencons=tty' [XC_TTY]: Console attached to '/dev/tty[0-9]+'.
+ * 'xencons=ttyS' [XC_SERIAL]: Console attached to '/dev/ttyS[0-9]+'.
+ * [XC_DEFAULT]: DOM0 -> XC_SERIAL ; all others -> XC_TTY.
+ *
+ * NB. In mode XC_TTY, we create dummy consoles for tty2-63. This suppresses
+ * warnings from standard distro startup scripts.
+ */
+static enum { XC_OFF, XC_DEFAULT, XC_TTY, XC_SERIAL } xc_mode = XC_DEFAULT;
+static int xc_num = -1;
+
+static int __init xencons_setup(char *str)
+{
+ char *q;
+ int n;
+
+ if ( !strncmp(str, "ttyS", 4) )
+ xc_mode = XC_SERIAL;
+ else if ( !strncmp(str, "tty", 3) )
+ xc_mode = XC_TTY;
+ else if ( !strncmp(str, "off", 3) )
+ xc_mode = XC_OFF;
+
+ switch ( xc_mode )
+ {
+ case XC_SERIAL:
+ n = simple_strtol( str+4, &q, 10 );
+ if ( q > (str + 4) ) xc_num = n;
+ break;
+ case XC_TTY:
+ n = simple_strtol( str+3, &q, 10 );
+ if ( q > (str + 3) ) xc_num = n;
+ break;
+ default:
+ break;
+ }
+
+ return 1;
+}
+__setup("xencons=", xencons_setup);
+
+/* The kernel and user-land drivers share a common transmit buffer. */
+static unsigned int wbuf_size = 4096;
+#define WBUF_MASK(_i) ((_i)&(wbuf_size-1))
+static char *wbuf;
+static unsigned int wc, wp; /* write_cons, write_prod */
+
+static int __init xencons_bufsz_setup(char *str)
+{
+ unsigned int goal;
+ goal = simple_strtoul(str, NULL, 0);
+ while ( wbuf_size < goal )
+ wbuf_size <<= 1;
+ return 1;
+}
+__setup("xencons_bufsz=", xencons_bufsz_setup);
+
+/* This lock protects accesses to the common transmit buffer. */
+static spinlock_t xencons_lock = SPIN_LOCK_UNLOCKED;
+
+/* Common transmit-kick routine. */
+static void __xencons_tx_flush(void);
+
+/* This task is used to defer sending console data until there is space. */
+static void xencons_tx_flush_task_routine(void *data);
+
+static DECLARE_TQUEUE(xencons_tx_flush_task,
+ xencons_tx_flush_task_routine,
+ NULL);
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+static struct tty_driver *xencons_driver;
+#else
+static struct tty_driver xencons_driver;
+#endif
+
+
+/******************** Kernel console driver ********************************/
+
+static void kcons_write(
+ struct console *c, const char *s, unsigned int count)
+{
+ int i;
+ unsigned long flags;
+
+ spin_lock_irqsave(&xencons_lock, flags);
+
+ for ( i = 0; i < count; i++ )
+ {
+ if ( (wp - wc) >= (wbuf_size - 1) )
+ break;
+ if ( (wbuf[WBUF_MASK(wp++)] = s[i]) == '\n' )
+ wbuf[WBUF_MASK(wp++)] = '\r';
+ }
+
+ __xencons_tx_flush();
+
+ spin_unlock_irqrestore(&xencons_lock, flags);
+}
+
+static void kcons_write_dom0(
+ struct console *c, const char *s, unsigned int count)
+{
+ int rc;
+
+ while ( (count > 0) &&
+ ((rc = HYPERVISOR_console_io(
+ CONSOLEIO_write, count, (char *)s)) > 0) )
+ {
+ count -= rc;
+ s += rc;
+ }
+}
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+static struct tty_driver *kcons_device(struct console *c, int *index)
+{
+ *index = c->index;
+ return xencons_driver;
+}
+#else
+static kdev_t kcons_device(struct console *c)
+{
+ return MKDEV(TTY_MAJOR, (xc_mode == XC_SERIAL) ? 64 : 1);
+}
+#endif
+
+static struct console kcons_info = {
+ device: kcons_device,
+ flags: CON_PRINTBUFFER,
+ index: -1
+};
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+#define __RETCODE 0
+static int __init xen_console_init(void)
+#else
+#define __RETCODE
+void xen_console_init(void)
+#endif
+{
+ if ( xen_start_info.flags & SIF_INITDOMAIN )
+ {
+ if ( xc_mode == XC_DEFAULT )
+ xc_mode = XC_SERIAL;
+ kcons_info.write = kcons_write_dom0;
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+ if ( xc_mode == XC_SERIAL )
+ kcons_info.flags |= CON_ENABLED;
+#endif
+ }
+ else
+ {
+ if ( xc_mode == XC_DEFAULT )
+ xc_mode = XC_TTY;
+ kcons_info.write = kcons_write;
+ }
+
+ switch ( xc_mode )
+ {
+ case XC_SERIAL:
+ strcpy(kcons_info.name, "ttyS");
+ if ( xc_num == -1 ) xc_num = 0;
+ break;
+
+ case XC_TTY:
+ strcpy(kcons_info.name, "tty");
+ if ( xc_num == -1 ) xc_num = 1;
+ break;
+
+ default:
+ return __RETCODE;
+ }
+
+ wbuf = alloc_bootmem(wbuf_size);
+
+ register_console(&kcons_info);
+
+ return __RETCODE;
+}
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+console_initcall(xen_console_init);
+#endif
+
+/*** Useful function for console debugging -- goes straight to Xen. ***/
+asmlinkage int xprintk(const char *fmt, ...)
+{
+ va_list args;
+ int printk_len;
+ static char printk_buf[1024];
+
+ /* Emit the output into the temporary buffer */
+ va_start(args, fmt);
+ printk_len = vsnprintf(printk_buf, sizeof(printk_buf), fmt, args);
+ va_end(args);
+
+ /* Send the processed output directly to Xen. */
+ kcons_write_dom0(NULL, printk_buf, printk_len);
+
+ return 0;
+}
+
+/*** Forcibly flush console data before dying. ***/
+void xencons_force_flush(void)
+{
+ ctrl_msg_t msg;
+ int sz;
+
+ /* Emergency console is synchronous, so there's nothing to flush. */
+ if ( xen_start_info.flags & SIF_INITDOMAIN )
+ return;
+
+ /*
+ * We use dangerous control-interface functions that require a quiescent
+ * system and no interrupts. Try to ensure this with a global cli().
+ */
+ local_irq_disable(); /* XXXsmp */
+
+ /* Spin until console data is flushed through to the domain controller. */
+ while ( (wc != wp) && !ctrl_if_transmitter_empty() )
+ {
+ /* Interrupts are disabled -- we must manually reap responses. */
+ ctrl_if_discard_responses();
+
+ if ( (sz = wp - wc) == 0 )
+ continue;
+ if ( sz > sizeof(msg.msg) )
+ sz = sizeof(msg.msg);
+ if ( sz > (wbuf_size - WBUF_MASK(wc)) )
+ sz = wbuf_size - WBUF_MASK(wc);
+
+ msg.type = CMSG_CONSOLE;
+ msg.subtype = CMSG_CONSOLE_DATA;
+ msg.length = sz;
+ memcpy(msg.msg, &wbuf[WBUF_MASK(wc)], sz);
+
+ if ( ctrl_if_send_message_noblock(&msg, NULL, 0) == 0 )
+ wc += sz;
+ }
+}
+
+
+/******************** User-space console driver (/dev/console) ************/
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+#define DRV(_d) (_d)
+#define TTY_INDEX(_tty) ((_tty)->index)
+#else
+static int xencons_refcount;
+static struct tty_struct *xencons_table[MAX_NR_CONSOLES];
+#define DRV(_d) (&(_d))
+#define TTY_INDEX(_tty) (MINOR((_tty)->device) - xencons_driver.minor_start)
+#endif
+
+static struct termios *xencons_termios[MAX_NR_CONSOLES];
+static struct termios *xencons_termios_locked[MAX_NR_CONSOLES];
+static struct tty_struct *xencons_tty;
+static int xencons_priv_irq;
+static char x_char;
+
+/* Non-privileged receive callback. */
+static void xencons_rx(ctrl_msg_t *msg, unsigned long id)
+{
+ int i;
+ unsigned long flags;
+
+ spin_lock_irqsave(&xencons_lock, flags);
+ if ( xencons_tty != NULL )
+ {
+ for ( i = 0; i < msg->length; i++ )
+ tty_insert_flip_char(xencons_tty, msg->msg[i], 0);
+ tty_flip_buffer_push(xencons_tty);
+ }
+ spin_unlock_irqrestore(&xencons_lock, flags);
+
+ msg->length = 0;
+ ctrl_if_send_response(msg);
+}
+
+/* Privileged and non-privileged transmit worker. */
+static void __xencons_tx_flush(void)
+{
+ int sz, work_done = 0;
+ ctrl_msg_t msg;
+
+ if ( xen_start_info.flags & SIF_INITDOMAIN )
+ {
+ if ( x_char )
+ {
+ kcons_write_dom0(NULL, &x_char, 1);
+ x_char = 0;
+ work_done = 1;
+ }
+
+ while ( wc != wp )
+ {
+ sz = wp - wc;
+ if ( sz > (wbuf_size - WBUF_MASK(wc)) )
+ sz = wbuf_size - WBUF_MASK(wc);
+ kcons_write_dom0(NULL, &wbuf[WBUF_MASK(wc)], sz);
+ wc += sz;
+ work_done = 1;
+ }
+ }
+ else
+ {
+ while ( x_char )
+ {
+ msg.type = CMSG_CONSOLE;
+ msg.subtype = CMSG_CONSOLE_DATA;
+ msg.length = 1;
+ msg.msg[0] = x_char;
+
+ if ( ctrl_if_send_message_noblock(&msg, NULL, 0) == 0 )
+ x_char = 0;
+ else if ( ctrl_if_enqueue_space_callback(&xencons_tx_flush_task) )
+ break;
+
+ work_done = 1;
+ }
+
+ while ( wc != wp )
+ {
+ sz = wp - wc;
+ if ( sz > sizeof(msg.msg) )
+ sz = sizeof(msg.msg);
+ if ( sz > (wbuf_size - WBUF_MASK(wc)) )
+ sz = wbuf_size - WBUF_MASK(wc);
+
+ msg.type = CMSG_CONSOLE;
+ msg.subtype = CMSG_CONSOLE_DATA;
+ msg.length = sz;
+ memcpy(msg.msg, &wbuf[WBUF_MASK(wc)], sz);
+
+ if ( ctrl_if_send_message_noblock(&msg, NULL, 0) == 0 )
+ wc += sz;
+ else if ( ctrl_if_enqueue_space_callback(&xencons_tx_flush_task) )
+ break;
+
+ work_done = 1;
+ }
+ }
+
+ if ( work_done && (xencons_tty != NULL) )
+ {
+ wake_up_interruptible(&xencons_tty->write_wait);
+ if ( (xencons_tty->flags & (1 << TTY_DO_WRITE_WAKEUP)) &&
+ (xencons_tty->ldisc.write_wakeup != NULL) )
+ (xencons_tty->ldisc.write_wakeup)(xencons_tty);
+ }
+}
+
+/* Non-privileged transmit kicker. */
+static void xencons_tx_flush_task_routine(void *data)
+{
+ unsigned long flags;
+ spin_lock_irqsave(&xencons_lock, flags);
+ __xencons_tx_flush();
+ spin_unlock_irqrestore(&xencons_lock, flags);
+}
+
+/* Privileged receive callback and transmit kicker. */
+static irqreturn_t xencons_priv_interrupt(int irq, void *dev_id,
+ struct pt_regs *regs)
+{
+ static char rbuf[16];
+ int i, l;
+ unsigned long flags;
+
+ spin_lock_irqsave(&xencons_lock, flags);
+
+ if ( xencons_tty != NULL )
+ {
+ /* Receive work. */
+ while ( (l = HYPERVISOR_console_io(CONSOLEIO_read, 16, rbuf)) > 0 )
+ for ( i = 0; i < l; i++ )
+ tty_insert_flip_char(xencons_tty, rbuf[i], 0);
+ if ( xencons_tty->flip.count != 0 )
+ tty_flip_buffer_push(xencons_tty);
+ }
+
+ /* Transmit work. */
+ __xencons_tx_flush();
+
+ spin_unlock_irqrestore(&xencons_lock, flags);
+
+ return IRQ_HANDLED;
+}
+
+static int xencons_write_room(struct tty_struct *tty)
+{
+ return wbuf_size - (wp - wc);
+}
+
+static int xencons_chars_in_buffer(struct tty_struct *tty)
+{
+ return wp - wc;
+}
+
+static void xencons_send_xchar(struct tty_struct *tty, char ch)
+{
+ unsigned long flags;
+
+ if ( TTY_INDEX(tty) != 0 )
+ return;
+
+ spin_lock_irqsave(&xencons_lock, flags);
+ x_char = ch;
+ __xencons_tx_flush();
+ spin_unlock_irqrestore(&xencons_lock, flags);
+}
+
+static void xencons_throttle(struct tty_struct *tty)
+{
+ if ( TTY_INDEX(tty) != 0 )
+ return;
+
+ if ( I_IXOFF(tty) )
+ xencons_send_xchar(tty, STOP_CHAR(tty));
+}
+
+static void xencons_unthrottle(struct tty_struct *tty)
+{
+ if ( TTY_INDEX(tty) != 0 )
+ return;
+
+ if ( I_IXOFF(tty) )
+ {
+ if ( x_char != 0 )
+ x_char = 0;
+ else
+ xencons_send_xchar(tty, START_CHAR(tty));
+ }
+}
+
+static void xencons_flush_buffer(struct tty_struct *tty)
+{
+ unsigned long flags;
+
+ if ( TTY_INDEX(tty) != 0 )
+ return;
+
+ spin_lock_irqsave(&xencons_lock, flags);
+ wc = wp = 0;
+ spin_unlock_irqrestore(&xencons_lock, flags);
+}
+
+static inline int __xencons_put_char(int ch)
+{
+ char _ch = (char)ch;
+ if ( (wp - wc) == wbuf_size )
+ return 0;
+ wbuf[WBUF_MASK(wp++)] = _ch;
+ return 1;
+}
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+static int xencons_write(
+ struct tty_struct *tty,
+ const unsigned char *buf,
+ int count)
+{
+ int i;
+ unsigned long flags;
+
+ if ( TTY_INDEX(tty) != 0 )
+ return count;
+
+ spin_lock_irqsave(&xencons_lock, flags);
+
+ for ( i = 0; i < count; i++ )
+ if ( !__xencons_put_char(buf[i]) )
+ break;
+
+ if ( i != 0 )
+ __xencons_tx_flush();
+
+ spin_unlock_irqrestore(&xencons_lock, flags);
+
+ return i;
+}
+#else
+static int xencons_write(
+ struct tty_struct *tty,
+ int from_user,
+ const u_char *buf,
+ int count)
+{
+ int i;
+ unsigned long flags;
+
+ if ( from_user && verify_area(VERIFY_READ, buf, count) )
+ return -EINVAL;
+
+ if ( TTY_INDEX(tty) != 0 )
+ return count;
+
+ spin_lock_irqsave(&xencons_lock, flags);
+
+ for ( i = 0; i < count; i++ )
+ {
+ char ch;
+ if ( from_user )
+ __get_user(ch, buf + i);
+ else
+ ch = buf[i];
+ if ( !__xencons_put_char(ch) )
+ break;
+ }
+
+ if ( i != 0 )
+ __xencons_tx_flush();
+
+ spin_unlock_irqrestore(&xencons_lock, flags);
+
+ return i;
+}
+#endif
+
+static void xencons_put_char(struct tty_struct *tty, u_char ch)
+{
+ unsigned long flags;
+
+ if ( TTY_INDEX(tty) != 0 )
+ return;
+
+ spin_lock_irqsave(&xencons_lock, flags);
+ (void)__xencons_put_char(ch);
+ spin_unlock_irqrestore(&xencons_lock, flags);
+}
+
+static void xencons_flush_chars(struct tty_struct *tty)
+{
+ unsigned long flags;
+
+ if ( TTY_INDEX(tty) != 0 )
+ return;
+
+ spin_lock_irqsave(&xencons_lock, flags);
+ __xencons_tx_flush();
+ spin_unlock_irqrestore(&xencons_lock, flags);
+}
+
+static void xencons_wait_until_sent(struct tty_struct *tty, int timeout)
+{
+ unsigned long orig_jiffies = jiffies;
+
+ if ( TTY_INDEX(tty) != 0 )
+ return;
+
+ while ( DRV(tty->driver)->chars_in_buffer(tty) )
+ {
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(1);
+ if ( signal_pending(current) )
+ break;
+ if ( (timeout != 0) && time_after(jiffies, orig_jiffies + timeout) )
+ break;
+ }
+
+ set_current_state(TASK_RUNNING);
+}
+
+static int xencons_open(struct tty_struct *tty, struct file *filp)
+{
+ unsigned long flags;
+
+ if ( TTY_INDEX(tty) != 0 )
+ return 0;
+
+ spin_lock_irqsave(&xencons_lock, flags);
+ tty->driver_data = NULL;
+ if ( xencons_tty == NULL )
+ xencons_tty = tty;
+ __xencons_tx_flush();
+ spin_unlock_irqrestore(&xencons_lock, flags);
+
+ return 0;
+}
+
+static void xencons_close(struct tty_struct *tty, struct file *filp)
+{
+ unsigned long flags;
+
+ if ( TTY_INDEX(tty) != 0 )
+ return;
+
+ if ( tty->count == 1 )
+ {
+ tty->closing = 1;
+ tty_wait_until_sent(tty, 0);
+ if ( DRV(tty->driver)->flush_buffer != NULL )
+ DRV(tty->driver)->flush_buffer(tty);
+ if ( tty->ldisc.flush_buffer != NULL )
+ tty->ldisc.flush_buffer(tty);
+ tty->closing = 0;
+ spin_lock_irqsave(&xencons_lock, flags);
+ xencons_tty = NULL;
+ spin_unlock_irqrestore(&xencons_lock, flags);
+ }
+}
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+static struct tty_operations xencons_ops = {
+ .open = xencons_open,
+ .close = xencons_close,
+ .write = xencons_write,
+ .write_room = xencons_write_room,
+ .put_char = xencons_put_char,
+ .flush_chars = xencons_flush_chars,
+ .chars_in_buffer = xencons_chars_in_buffer,
+ .send_xchar = xencons_send_xchar,
+ .flush_buffer = xencons_flush_buffer,
+ .throttle = xencons_throttle,
+ .unthrottle = xencons_unthrottle,
+ .wait_until_sent = xencons_wait_until_sent,
+};
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+static const char *xennullcon_startup(void)
+{
+ return NULL;
+}
+
+static int xennullcon_dummy(void)
+{
+ return 0;
+}
+
+#define DUMMY (void *)xennullcon_dummy
+
+/*
+ * The console `switch' structure for the dummy console
+ *
+ * Most of the operations are dummies.
+ */
+
+const struct consw xennull_con = {
+ .owner = THIS_MODULE,
+ .con_startup = xennullcon_startup,
+ .con_init = DUMMY,
+ .con_deinit = DUMMY,
+ .con_clear = DUMMY,
+ .con_putc = DUMMY,
+ .con_putcs = DUMMY,
+ .con_cursor = DUMMY,
+ .con_scroll = DUMMY,
+ .con_bmove = DUMMY,
+ .con_switch = DUMMY,
+ .con_blank = DUMMY,
+ .con_font_set = DUMMY,
+ .con_font_get = DUMMY,
+ .con_font_default = DUMMY,
+ .con_font_copy = DUMMY,
+ .con_set_palette = DUMMY,
+ .con_scrolldelta = DUMMY,
+};
+#endif
+#endif
+
+static int __init xencons_init(void)
+{
+ int rc;
+
+ if ( xc_mode == XC_OFF )
+ return 0;
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+ xencons_driver = alloc_tty_driver((xc_mode == XC_SERIAL) ?
+ 1 : MAX_NR_CONSOLES);
+ if ( xencons_driver == NULL )
+ return -ENOMEM;
+#else
+ memset(&xencons_driver, 0, sizeof(struct tty_driver));
+ xencons_driver.magic = TTY_DRIVER_MAGIC;
+ xencons_driver.refcount = &xencons_refcount;
+ xencons_driver.table = xencons_table;
+ xencons_driver.num = (xc_mode == XC_SERIAL) ? 1 : MAX_NR_CONSOLES;
+#endif
+
+ DRV(xencons_driver)->major = TTY_MAJOR;
+ DRV(xencons_driver)->type = TTY_DRIVER_TYPE_SERIAL;
+ DRV(xencons_driver)->subtype = SERIAL_TYPE_NORMAL;
+ DRV(xencons_driver)->init_termios = tty_std_termios;
+ DRV(xencons_driver)->flags =
+ TTY_DRIVER_REAL_RAW | TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_NO_DEVFS;
+ DRV(xencons_driver)->termios = xencons_termios;
+ DRV(xencons_driver)->termios_locked = xencons_termios_locked;
+
+ if ( xc_mode == XC_SERIAL )
+ {
+ DRV(xencons_driver)->name = "ttyS";
+ DRV(xencons_driver)->minor_start = 64 + xc_num;
+ DRV(xencons_driver)->name_base = 0 + xc_num;
+ }
+ else
+ {
+ DRV(xencons_driver)->name = "tty";
+ DRV(xencons_driver)->minor_start = xc_num;
+ DRV(xencons_driver)->name_base = xc_num;
+ }
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+ tty_set_operations(xencons_driver, &xencons_ops);
+#else
+ xencons_driver.open = xencons_open;
+ xencons_driver.close = xencons_close;
+ xencons_driver.write = xencons_write;
+ xencons_driver.write_room = xencons_write_room;
+ xencons_driver.put_char = xencons_put_char;
+ xencons_driver.flush_chars = xencons_flush_chars;
+ xencons_driver.chars_in_buffer = xencons_chars_in_buffer;
+ xencons_driver.send_xchar = xencons_send_xchar;
+ xencons_driver.flush_buffer = xencons_flush_buffer;
+ xencons_driver.throttle = xencons_throttle;
+ xencons_driver.unthrottle = xencons_unthrottle;
+ xencons_driver.wait_until_sent = xencons_wait_until_sent;
+#endif
+
+ if ( (rc = tty_register_driver(DRV(xencons_driver))) != 0 )
+ {
+ printk("WARNING: Failed to register Xen virtual "
+ "console driver as '%s%d'\n",
+ DRV(xencons_driver)->name, DRV(xencons_driver)->name_base);
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+ put_tty_driver(xencons_driver);
+ xencons_driver = NULL;
+#endif
+ return rc;
+ }
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+ tty_register_device(xencons_driver, 0, NULL);
+#endif
+
+ if ( xen_start_info.flags & SIF_INITDOMAIN )
+ {
+ xencons_priv_irq = bind_virq_to_irq(VIRQ_CONSOLE);
+ (void)request_irq(xencons_priv_irq,
+ xencons_priv_interrupt, 0, "console", NULL);
+ }
+ else
+ {
+ (void)ctrl_if_register_receiver(CMSG_CONSOLE, xencons_rx, 0);
+ }
+
+ printk("Xen virtual console successfully installed as %s%d\n",
+ DRV(xencons_driver)->name,
+ DRV(xencons_driver)->name_base );
+
+ return 0;
+}
+
+module_init(xencons_init);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/ptrace.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/ptrace.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,69 @@
+#ifndef _I386_PTRACE_H
+#define _I386_PTRACE_H
+
+#define EBX 0
+#define ECX 1
+#define EDX 2
+#define ESI 3
+#define EDI 4
+#define EBP 5
+#define EAX 6
+#define DS 7
+#define ES 8
+#define FS 9
+#define GS 10
+#define ORIG_EAX 11
+#define EIP 12
+#define CS 13
+#define EFL 14
+#define UESP 15
+#define SS 16
+#define FRAME_SIZE 17
+
+/* this struct defines the way the registers are stored on the
+ stack during a system call. */
+
+struct pt_regs {
+ long ebx;
+ long ecx;
+ long edx;
+ long esi;
+ long edi;
+ long ebp;
+ long eax;
+ int xds;
+ int xes;
+ long orig_eax;
+ long eip;
+ int xcs;
+ long eflags;
+ long esp;
+ int xss;
+};
+
+/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */
+#define PTRACE_GETREGS 12
+#define PTRACE_SETREGS 13
+#define PTRACE_GETFPREGS 14
+#define PTRACE_SETFPREGS 15
+#define PTRACE_GETFPXREGS 18
+#define PTRACE_SETFPXREGS 19
+
+#define PTRACE_OLDSETOPTIONS 21
+
+#define PTRACE_GET_THREAD_AREA 25
+#define PTRACE_SET_THREAD_AREA 26
+
+#ifdef __KERNEL__
+struct task_struct;
+extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int
error_code);
+#define user_mode(regs) ((VM_MASK & (regs)->eflags) || (2 & (regs)->xcs))
+#define instruction_pointer(regs) ((regs)->eip)
+#if defined(CONFIG_SMP) && defined(CONFIG_FRAME_POINTER)
+extern unsigned long profile_pc(struct pt_regs *regs);
+#else
+#define profile_pc(regs) instruction_pointer(regs)
+#endif
+#endif
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/traps.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/traps.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,975 @@
+/*
+ * linux/arch/x86-64/traps.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000
+ *
+ * $Id: traps.c,v 1.36 2002/03/24 11:09:10 ak Exp $
+ */
+
+/*
+ * 'Traps.c' handles hardware traps and faults after we have saved some
+ * state in 'entry.S'.
+ */
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/timer.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/atomic.h>
+#include <asm/debugreg.h>
+#include <asm/desc.h>
+#include <asm/i387.h>
+#include <asm/kdebug.h>
+#include <asm/processor.h>
+
+#include <asm/smp.h>
+#include <asm/pgalloc.h>
+#include <asm/pda.h>
+#include <asm/proto.h>
+#include <asm/nmi.h>
+
+#include <linux/irq.h>
+
+
+extern struct gate_struct idt_table[256];
+
+asmlinkage void divide_error(void);
+asmlinkage void debug(void);
+asmlinkage void nmi(void);
+asmlinkage void int3(void);
+asmlinkage void overflow(void);
+asmlinkage void bounds(void);
+asmlinkage void invalid_op(void);
+asmlinkage void device_not_available(void);
+asmlinkage void double_fault(void);
+asmlinkage void coprocessor_segment_overrun(void);
+asmlinkage void invalid_TSS(void);
+asmlinkage void segment_not_present(void);
+asmlinkage void stack_segment(void);
+asmlinkage void general_protection(void);
+asmlinkage void page_fault(void);
+asmlinkage void coprocessor_error(void);
+asmlinkage void simd_coprocessor_error(void);
+asmlinkage void reserved(void);
+asmlinkage void alignment_check(void);
+asmlinkage void machine_check(void);
+asmlinkage void spurious_interrupt_bug(void);
+asmlinkage void call_debug(void);
+
+struct notifier_block *die_chain;
+static DEFINE_SPINLOCK(die_notifier_lock);
+
+int register_die_notifier(struct notifier_block *nb)
+{
+ int err = 0;
+ unsigned long flags;
+ spin_lock_irqsave(&die_notifier_lock, flags);
+ err = notifier_chain_register(&die_chain, nb);
+ spin_unlock_irqrestore(&die_notifier_lock, flags);
+ return err;
+}
+
+static inline void conditional_sti(struct pt_regs *regs)
+{
+ if (regs->eflags & X86_EFLAGS_IF)
+ local_irq_enable();
+}
+
+static int kstack_depth_to_print = 10;
+
+#ifdef CONFIG_KALLSYMS
+#include <linux/kallsyms.h>
+int printk_address(unsigned long address)
+{
+ unsigned long offset = 0, symsize;
+ const char *symname;
+ char *modname;
+ char *delim = ":";
+ char namebuf[128];
+
+ symname = kallsyms_lookup(address, &symsize, &offset, &modname,
namebuf);
+ if (!symname)
+ return printk("[<%016lx>]", address);
+ if (!modname)
+ modname = delim = "";
+ return printk("<%016lx>{%s%s%s%s%+ld}",
+ address,delim,modname,delim,symname,offset);
+}
+#else
+int printk_address(unsigned long address)
+{
+ return printk("[<%016lx>]", address);
+}
+#endif
+
+unsigned long *in_exception_stack(int cpu, unsigned long stack)
+{
+ int k;
+ for (k = 0; k < N_EXCEPTION_STACKS; k++) {
+ struct tss_struct *tss = &per_cpu(init_tss, cpu);
+ unsigned long end = tss->ist[k] + EXCEPTION_STKSZ;
+
+ if (stack >= tss->ist[k] && stack <= end)
+ return (unsigned long *)end;
+ }
+ return NULL;
+}
+
+/*
+ * x86-64 can have upto three kernel stacks:
+ * process stack
+ * interrupt stack
+ * severe exception (double fault, nmi, stack fault) hardware stack
+ * Check and process them in order.
+ */
+
+void show_trace(unsigned long *stack)
+{
+ unsigned long addr;
+ unsigned long *irqstack, *irqstack_end, *estack_end;
+ const int cpu = safe_smp_processor_id();
+ int i;
+
+ printk("\nCall Trace:");
+ i = 0;
+
+ estack_end = in_exception_stack(cpu, (unsigned long)stack);
+ if (estack_end) {
+ while (stack < estack_end) {
+ addr = *stack++;
+ if (__kernel_text_address(addr)) {
+ i += printk_address(addr);
+ i += printk(" ");
+ if (i > 50) {
+ printk("\n");
+ i = 0;
+ }
+ }
+ }
+ i += printk(" <EOE> ");
+ i += 7;
+ stack = (unsigned long *) estack_end[-2];
+ }
+
+ irqstack_end = (unsigned long *) (cpu_pda[cpu].irqstackptr);
+ irqstack = (unsigned long *) (cpu_pda[cpu].irqstackptr - IRQSTACKSIZE +
64);
+
+ if (stack >= irqstack && stack < irqstack_end) {
+ printk("<IRQ> ");
+ while (stack < irqstack_end) {
+ addr = *stack++;
+ /*
+ * If the address is either in the text segment of the
+ * kernel, or in the region which contains vmalloc'ed
+ * memory, it *may* be the address of a calling
+ * routine; if so, print it so that someone tracing
+ * down the cause of the crash will be able to figure
+ * out the call path that was taken.
+ */
+ if (__kernel_text_address(addr)) {
+ i += printk_address(addr);
+ i += printk(" ");
+ if (i > 50) {
+ printk("\n ");
+ i = 0;
+ }
+ }
+ }
+ stack = (unsigned long *) (irqstack_end[-1]);
+ printk(" <EOI> ");
+ i += 7;
+ }
+
+ while (((long) stack & (THREAD_SIZE-1)) != 0) {
+ addr = *stack++;
+ if (__kernel_text_address(addr)) {
+ i += printk_address(addr);
+ i += printk(" ");
+ if (i > 50) {
+ printk("\n ");
+ i = 0;
+ }
+ }
+ }
+ printk("\n");
+}
+
+void show_stack(struct task_struct *tsk, unsigned long * rsp)
+{
+ unsigned long *stack;
+ int i;
+ const int cpu = safe_smp_processor_id();
+ unsigned long *irqstack_end = (unsigned long *)
(cpu_pda[cpu].irqstackptr);
+ unsigned long *irqstack = (unsigned long *) (cpu_pda[cpu].irqstackptr -
IRQSTACKSIZE);
+
+ // debugging aid: "show_stack(NULL, NULL);" prints the
+ // back trace for this cpu.
+
+ if (rsp == NULL) {
+ if (tsk)
+ rsp = (unsigned long *)tsk->thread.rsp;
+ else
+ rsp = (unsigned long *)&rsp;
+ }
+
+ stack = rsp;
+ for(i=0; i < kstack_depth_to_print; i++) {
+ if (stack >= irqstack && stack <= irqstack_end) {
+ if (stack == irqstack_end) {
+ stack = (unsigned long *) (irqstack_end[-1]);
+ printk(" <EOI> ");
+ }
+ } else {
+ if (((long) stack & (THREAD_SIZE-1)) == 0)
+ break;
+ }
+ if (i && ((i % 4) == 0))
+ printk("\n ");
+ printk("%016lx ", *stack++);
+ }
+ show_trace((unsigned long *)rsp);
+}
+
+/*
+ * The architecture-independent dump_stack generator
+ */
+void dump_stack(void)
+{
+ unsigned long dummy;
+ show_trace(&dummy);
+}
+
+EXPORT_SYMBOL(dump_stack);
+
+void show_registers(struct pt_regs *regs)
+{
+ int i;
+ int in_kernel = (regs->cs & 3) == 0;
+ unsigned long rsp;
+ const int cpu = safe_smp_processor_id();
+ struct task_struct *cur = cpu_pda[cpu].pcurrent;
+
+ rsp = regs->rsp;
+
+ printk("CPU %d ", cpu);
+ __show_regs(regs);
+ printk("Process %s (pid: %d, threadinfo %p, task %p)\n",
+ cur->comm, cur->pid, cur->thread_info, cur);
+
+ /*
+ * When in-kernel, we also print out the stack and code at the
+ * time of the fault..
+ */
+ if (in_kernel) {
+
+ printk("Stack: ");
+ show_stack(NULL, (unsigned long*)rsp);
+
+ printk("\nCode: ");
+ if(regs->rip < PAGE_OFFSET)
+ goto bad;
+
+ for(i=0;i<20;i++)
+ {
+ unsigned char c;
+ if(__get_user(c, &((unsigned char*)regs->rip)[i])) {
+bad:
+ printk(" Bad RIP value.");
+ break;
+ }
+ printk("%02x ", c);
+ }
+ }
+ printk("\n");
+}
+
+void handle_BUG(struct pt_regs *regs)
+{
+ struct bug_frame f;
+ char tmp;
+
+ if (regs->cs & 3)
+ return;
+ if (__copy_from_user(&f, (struct bug_frame *) regs->rip,
+ sizeof(struct bug_frame)))
+ return;
+ if ((unsigned long)f.filename < __PAGE_OFFSET ||
+ f.ud2[0] != 0x0f || f.ud2[1] != 0x0b)
+ return;
+ if (__get_user(tmp, f.filename))
+ f.filename = "unmapped filename";
+ printk("----------- [cut here ] --------- [please bite here ]
---------\n");
+ printk(KERN_ALERT "Kernel BUG at %.50s:%d\n", f.filename, f.line);
+}
+
+void out_of_line_bug(void)
+{
+ BUG();
+}
+
+static DEFINE_SPINLOCK(die_lock);
+static int die_owner = -1;
+
+void oops_begin(void)
+{
+ int cpu = safe_smp_processor_id();
+ /* racy, but better than risking deadlock. */
+ local_irq_disable();
+ if (!spin_trylock(&die_lock)) {
+ if (cpu == die_owner)
+ /* nested oops. should stop eventually */;
+ else
+ spin_lock(&die_lock);
+ }
+ die_owner = cpu;
+ console_verbose();
+ bust_spinlocks(1);
+}
+
+void oops_end(void)
+{
+ die_owner = -1;
+ bust_spinlocks(0);
+ spin_unlock(&die_lock);
+ local_irq_enable(); /* make sure back scroll still works */
+ if (panic_on_oops)
+ panic("Oops");
+}
+
+void __die(const char * str, struct pt_regs * regs, long err)
+{
+ static int die_counter;
+ printk(KERN_EMERG "%s: %04lx [%u] ", str, err & 0xffff,++die_counter);
+#ifdef CONFIG_PREEMPT
+ printk("PREEMPT ");
+#endif
+#ifdef CONFIG_SMP
+ printk("SMP ");
+#endif
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ printk("DEBUG_PAGEALLOC");
+#endif
+ printk("\n");
+ notify_die(DIE_OOPS, (char *)str, regs, err, 255, SIGSEGV);
+ show_registers(regs);
+ /* Executive summary in case the oops scrolled away */
+ printk(KERN_ALERT "RIP ");
+ printk_address(regs->rip);
+ printk(" RSP <%016lx>\n", regs->rsp);
+}
+
+void die(const char * str, struct pt_regs * regs, long err)
+{
+ oops_begin();
+ handle_BUG(regs);
+ __die(str, regs, err);
+ oops_end();
+ do_exit(SIGSEGV);
+}
+static inline void die_if_kernel(const char * str, struct pt_regs * regs, long
err)
+{
+ if (!(regs->eflags & VM_MASK) && (regs->cs == __KERNEL_CS))
+ die(str, regs, err);
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+void die_nmi(char *str, struct pt_regs *regs)
+{
+ oops_begin();
+ /*
+ * We are in trouble anyway, lets at least try
+ * to get a message out.
+ */
+ printk(str, safe_smp_processor_id());
+ show_registers(regs);
+ if (panic_on_timeout || panic_on_oops)
+ panic("nmi watchdog");
+ printk("console shuts up ...\n");
+ oops_end();
+ do_exit(SIGSEGV);
+}
+#endif
+
+static void do_trap(int trapnr, int signr, char *str,
+ struct pt_regs * regs, long error_code, siginfo_t
*info)
+{
+ conditional_sti(regs);
+
+#ifdef CONFIG_CHECKING
+ {
+ unsigned long gs;
+ struct x8664_pda *pda = cpu_pda + safe_smp_processor_id();
+ rdmsrl(MSR_GS_BASE, gs);
+ if (gs != (unsigned long)pda) {
+ wrmsrl(MSR_GS_BASE, pda);
+ printk("%s: wrong gs %lx expected %p rip %lx\n", str,
gs, pda,
+ regs->rip);
+ }
+ }
+#endif
+
+ if ((regs->cs & 3) != 0) {
+ struct task_struct *tsk = current;
+
+ if (exception_trace && unhandled_signal(tsk, signr))
+ printk(KERN_INFO
+ "%s[%d] trap %s rip:%lx rsp:%lx error:%lx\n",
+ tsk->comm, tsk->pid, str,
+ regs->rip,regs->rsp,error_code);
+
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = trapnr;
+ if (info)
+ force_sig_info(signr, info, tsk);
+ else
+ force_sig(signr, tsk);
+ return;
+ }
+
+
+ /* kernel trap */
+ {
+ const struct exception_table_entry *fixup;
+ fixup = search_exception_tables(regs->rip);
+ if (fixup) {
+ regs->rip = fixup->fixup;
+ } else
+ die(str, regs, error_code);
+ return;
+ }
+}
+
+#define DO_ERROR(trapnr, signr, str, name) \
+asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
+{ \
+ if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
+ == NOTIFY_STOP) \
+ return; \
+ do_trap(trapnr, signr, str, regs, error_code, NULL); \
+}
+
+#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
+asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
+{ \
+ siginfo_t info; \
+ info.si_signo = signr; \
+ info.si_errno = 0; \
+ info.si_code = sicode; \
+ info.si_addr = (void __user *)siaddr; \
+ if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
+ == NOTIFY_STOP) \
+ return; \
+ do_trap(trapnr, signr, str, regs, error_code, &info); \
+}
+
+DO_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->rip)
+DO_ERROR( 4, SIGSEGV, "overflow", overflow)
+DO_ERROR( 5, SIGSEGV, "bounds", bounds)
+DO_ERROR_INFO( 6, SIGILL, "invalid operand", invalid_op, ILL_ILLOPN,
regs->rip)
+DO_ERROR( 7, SIGSEGV, "device not available", device_not_available)
+DO_ERROR( 9, SIGFPE, "coprocessor segment overrun",
coprocessor_segment_overrun)
+DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
+DO_ERROR(11, SIGBUS, "segment not present", segment_not_present)
+DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0)
+DO_ERROR(18, SIGSEGV, "reserved", reserved)
+
+#define DO_ERROR_STACK(trapnr, signr, str, name) \
+asmlinkage void *do_##name(struct pt_regs * regs, long error_code) \
+{ \
+ struct pt_regs *pr = ((struct pt_regs *)(current->thread.rsp0))-1; \
+ if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
+ == NOTIFY_STOP) \
+ return regs; \
+ if (regs->cs & 3) { \
+ memcpy(pr, regs, sizeof(struct pt_regs)); \
+ regs = pr; \
+ } \
+ do_trap(trapnr, signr, str, regs, error_code, NULL); \
+ return regs; \
+}
+
+DO_ERROR_STACK(12, SIGBUS, "stack segment", stack_segment)
+DO_ERROR_STACK( 8, SIGSEGV, "double fault", double_fault)
+
+asmlinkage void do_general_protection(struct pt_regs * regs, long error_code)
+{
+ conditional_sti(regs);
+
+#ifdef CONFIG_CHECKING
+ {
+ unsigned long gs;
+ struct x8664_pda *pda = cpu_pda + safe_smp_processor_id();
+ rdmsrl(MSR_GS_BASE, gs);
+ if (gs != (unsigned long)pda) {
+ wrmsrl(MSR_GS_BASE, pda);
+ oops_in_progress++;
+ printk("general protection handler: wrong gs %lx
expected %p\n", gs, pda);
+ oops_in_progress--;
+ }
+ }
+#endif
+
+ if ((regs->cs & 3)!=0) {
+ struct task_struct *tsk = current;
+
+ if (exception_trace && unhandled_signal(tsk, SIGSEGV))
+ printk(KERN_INFO
+ "%s[%d] general protection rip:%lx rsp:%lx error:%lx\n",
+ tsk->comm, tsk->pid,
+ regs->rip,regs->rsp,error_code);
+
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = 13;
+ force_sig(SIGSEGV, tsk);
+ return;
+ }
+
+ /* kernel gp */
+ {
+ const struct exception_table_entry *fixup;
+ fixup = search_exception_tables(regs->rip);
+ if (fixup) {
+ regs->rip = fixup->fixup;
+ return;
+ }
+ if (notify_die(DIE_GPF, "general protection fault", regs,
+ error_code, 13, SIGSEGV) == NOTIFY_STOP)
+ return;
+ die("general protection fault", regs, error_code);
+ }
+}
+
+static void mem_parity_error(unsigned char reason, struct pt_regs * regs)
+{
+ printk("Uhhuh. NMI received. Dazed and confused, but trying to
continue\n");
+ printk("You probably have a hardware problem with your RAM chips\n");
+
+ /* Clear and disable the memory parity error line. */
+ reason = (reason & 0xf) | 4;
+ outb(reason, 0x61);
+}
+
+static void io_check_error(unsigned char reason, struct pt_regs * regs)
+{
+ printk("NMI: IOCK error (debug interrupt?)\n");
+ show_registers(regs);
+
+ /* Re-enable the IOCK line, wait for a few seconds */
+ reason = (reason & 0xf) | 8;
+ outb(reason, 0x61);
+ mdelay(2000);
+ reason &= ~8;
+ outb(reason, 0x61);
+}
+
+static void unknown_nmi_error(unsigned char reason, struct pt_regs * regs)
+{ printk("Uhhuh. NMI received for unknown reason %02x.\n", reason);
+ printk("Dazed and confused, but trying to continue\n");
+ printk("Do you have a strange power saving mode enabled?\n");
+}
+
+asmlinkage void default_do_nmi(struct pt_regs *regs)
+{
+ unsigned char reason = 0;
+
+ /* Only the BSP gets external NMIs from the system. */
+ if (!smp_processor_id())
+ reason = get_nmi_reason();
+
+ if (!(reason & 0xc0)) {
+ if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 0, SIGINT)
+ == NOTIFY_STOP)
+ return;
+#ifdef CONFIG_X86_LOCAL_APIC
+ /*
+ * Ok, so this is none of the documented NMI sources,
+ * so it must be the NMI watchdog.
+ */
+ if (nmi_watchdog > 0) {
+ nmi_watchdog_tick(regs,reason);
+ return;
+ }
+#endif
+ unknown_nmi_error(reason, regs);
+ return;
+ }
+ if (notify_die(DIE_NMI, "nmi", regs, reason, 0, SIGINT) == NOTIFY_STOP)
+ return;
+
+ /* AK: following checks seem to be broken on modern chipsets. FIXME */
+
+ if (reason & 0x80)
+ mem_parity_error(reason, regs);
+ if (reason & 0x40)
+ io_check_error(reason, regs);
+
+ /*
+ * Reassert NMI in case it became active meanwhile
+ * as it's edge-triggered.
+ */
+ outb(0x8f, 0x70);
+ inb(0x71); /* dummy */
+ outb(0x0f, 0x70);
+ inb(0x71); /* dummy */
+}
+
+asmlinkage void do_int3(struct pt_regs * regs, long error_code)
+{
+ if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) ==
NOTIFY_STOP) {
+ return;
+ }
+ do_trap(3, SIGTRAP, "int3", regs, error_code, NULL);
+ return;
+}
+
+/* runs on IST stack. */
+asmlinkage void *do_debug(struct pt_regs * regs, unsigned long error_code)
+{
+ struct pt_regs *pr;
+ unsigned long condition;
+ struct task_struct *tsk = current;
+ siginfo_t info;
+
+ pr = (struct pt_regs *)(current->thread.rsp0)-1;
+ if (regs->cs & 3) {
+ memcpy(pr, regs, sizeof(struct pt_regs));
+ regs = pr;
+ }
+
+#ifdef CONFIG_CHECKING
+ {
+ /* RED-PEN interaction with debugger - could destroy gs */
+ unsigned long gs;
+ struct x8664_pda *pda = cpu_pda + safe_smp_processor_id();
+ rdmsrl(MSR_GS_BASE, gs);
+ if (gs != (unsigned long)pda) {
+ wrmsrl(MSR_GS_BASE, pda);
+ printk("debug handler: wrong gs %lx expected %p\n", gs,
pda);
+ }
+ }
+#endif
+
+ asm("movq %%db6,%0" : "=r" (condition));
+
+ if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code,
+ SIGTRAP) == NOTIFY_STOP) {
+ return regs;
+ }
+ conditional_sti(regs);
+
+ /* Mask out spurious debug traps due to lazy DR7 setting */
+ if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) {
+ if (!tsk->thread.debugreg7) {
+ goto clear_dr7;
+ }
+ }
+
+ tsk->thread.debugreg6 = condition;
+
+ /* Mask out spurious TF errors due to lazy TF clearing */
+ if ((condition & DR_STEP) &&
+ (notify_die(DIE_DEBUGSTEP, "debugstep", regs, condition,
+ 1, SIGTRAP) != NOTIFY_STOP)) {
+ /*
+ * The TF error should be masked out only if the current
+ * process is not traced and if the TRAP flag has been set
+ * previously by a tracing process (condition detected by
+ * the PT_DTRACE flag); remember that the i386 TRAP flag
+ * can be modified by the process itself in user mode,
+ * allowing programs to debug themselves without the ptrace()
+ * interface.
+ */
+ if ((regs->cs & 3) == 0)
+ goto clear_TF_reenable;
+ if ((tsk->ptrace & (PT_DTRACE|PT_PTRACED)) == PT_DTRACE)
+ goto clear_TF;
+ }
+
+ /* Ok, finally something we can handle */
+ tsk->thread.trap_no = 1;
+ tsk->thread.error_code = error_code;
+ info.si_signo = SIGTRAP;
+ info.si_errno = 0;
+ info.si_code = TRAP_BRKPT;
+ if ((regs->cs & 3) == 0)
+ goto clear_dr7;
+
+ info.si_addr = (void __user *)regs->rip;
+ force_sig_info(SIGTRAP, &info, tsk);
+clear_dr7:
+ asm volatile("movq %0,%%db7"::"r"(0UL));
+ notify_die(DIE_DEBUG, "debug", regs, condition, 1, SIGTRAP);
+ return regs;
+
+clear_TF_reenable:
+ set_tsk_thread_flag(tsk, TIF_SINGLESTEP);
+
+clear_TF:
+ /* RED-PEN could cause spurious errors */
+ if (notify_die(DIE_DEBUG, "debug2", regs, condition, 1, SIGTRAP)
+ != NOTIFY_STOP)
+ regs->eflags &= ~TF_MASK;
+ return regs;
+}
+
+static int kernel_math_error(struct pt_regs *regs, char *str)
+{
+ const struct exception_table_entry *fixup;
+ fixup = search_exception_tables(regs->rip);
+ if (fixup) {
+ regs->rip = fixup->fixup;
+ return 1;
+ }
+ notify_die(DIE_GPF, str, regs, 0, 16, SIGFPE);
+#if 0
+ /* This should be a die, but warn only for now */
+ die(str, regs, 0);
+#else
+ printk(KERN_DEBUG "%s: %s at ", current->comm, str);
+ printk_address(regs->rip);
+ printk("\n");
+#endif
+ return 0;
+}
+
+/*
+ * Note that we play around with the 'TS' bit in an attempt to get
+ * the correct behaviour even in the presence of the asynchronous
+ * IRQ13 behaviour
+ */
+asmlinkage void do_coprocessor_error(struct pt_regs *regs)
+{
+ void __user *rip = (void __user *)(regs->rip);
+ struct task_struct * task;
+ siginfo_t info;
+ unsigned short cwd, swd;
+
+ conditional_sti(regs);
+ if ((regs->cs & 3) == 0 &&
+ kernel_math_error(regs, "kernel x87 math error"))
+ return;
+
+ /*
+ * Save the info for the exception handler and clear the error.
+ */
+ task = current;
+ save_init_fpu(task);
+ task->thread.trap_no = 16;
+ task->thread.error_code = 0;
+ info.si_signo = SIGFPE;
+ info.si_errno = 0;
+ info.si_code = __SI_FAULT;
+ info.si_addr = rip;
+ /*
+ * (~cwd & swd) will mask out exceptions that are not set to unmasked
+ * status. 0x3f is the exception bits in these regs, 0x200 is the
+ * C1 reg you need in case of a stack fault, 0x040 is the stack
+ * fault bit. We should only be taking one exception at a time,
+ * so if this combination doesn't produce any single exception,
+ * then we have a bad program that isn't synchronizing its FPU usage
+ * and it will suffer the consequences since we won't be able to
+ * fully reproduce the context of the exception
+ */
+ cwd = get_fpu_cwd(task);
+ swd = get_fpu_swd(task);
+ switch (((~cwd) & swd & 0x3f) | (swd & 0x240)) {
+ case 0x000:
+ default:
+ break;
+ case 0x001: /* Invalid Op */
+ case 0x041: /* Stack Fault */
+ case 0x241: /* Stack Fault | Direction */
+ info.si_code = FPE_FLTINV;
+ break;
+ case 0x002: /* Denormalize */
+ case 0x010: /* Underflow */
+ info.si_code = FPE_FLTUND;
+ break;
+ case 0x004: /* Zero Divide */
+ info.si_code = FPE_FLTDIV;
+ break;
+ case 0x008: /* Overflow */
+ info.si_code = FPE_FLTOVF;
+ break;
+ case 0x020: /* Precision */
+ info.si_code = FPE_FLTRES;
+ break;
+ }
+ force_sig_info(SIGFPE, &info, task);
+}
+
+asmlinkage void bad_intr(void)
+{
+ printk("bad interrupt");
+}
+
+asmlinkage void do_simd_coprocessor_error(struct pt_regs *regs)
+{
+ void __user *rip = (void __user *)(regs->rip);
+ struct task_struct * task;
+ siginfo_t info;
+ unsigned short mxcsr;
+
+ conditional_sti(regs);
+ if ((regs->cs & 3) == 0 &&
+ kernel_math_error(regs, "simd math error"))
+ return;
+
+ /*
+ * Save the info for the exception handler and clear the error.
+ */
+ task = current;
+ save_init_fpu(task);
+ task->thread.trap_no = 19;
+ task->thread.error_code = 0;
+ info.si_signo = SIGFPE;
+ info.si_errno = 0;
+ info.si_code = __SI_FAULT;
+ info.si_addr = rip;
+ /*
+ * The SIMD FPU exceptions are handled a little differently, as there
+ * is only a single status/control register. Thus, to determine which
+ * unmasked exception was caught we must mask the exception mask bits
+ * at 0x1f80, and then use these to mask the exception bits at 0x3f.
+ */
+ mxcsr = get_fpu_mxcsr(task);
+ switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) {
+ case 0x000:
+ default:
+ break;
+ case 0x001: /* Invalid Op */
+ info.si_code = FPE_FLTINV;
+ break;
+ case 0x002: /* Denormalize */
+ case 0x010: /* Underflow */
+ info.si_code = FPE_FLTUND;
+ break;
+ case 0x004: /* Zero Divide */
+ info.si_code = FPE_FLTDIV;
+ break;
+ case 0x008: /* Overflow */
+ info.si_code = FPE_FLTOVF;
+ break;
+ case 0x020: /* Precision */
+ info.si_code = FPE_FLTRES;
+ break;
+ }
+ force_sig_info(SIGFPE, &info, task);
+}
+
+asmlinkage void do_spurious_interrupt_bug(struct pt_regs * regs)
+{
+}
+
+#if 0
+asmlinkage void __attribute__((weak)) smp_thermal_interrupt(void)
+{
+}
+#endif
+
+/*
+ * 'math_state_restore()' saves the current math information in the
+ * old math state array, and gets the new ones from the current task
+ *
+ * Careful.. There are problems with IBM-designed IRQ13 behaviour.
+ * Don't touch unless you *really* know how it works.
+ */
+asmlinkage void math_state_restore(void)
+{
+ struct task_struct *me = current;
+
+ /* clts(); */ /* 'clts' is done for us by Xen during virtual trap. */
+
+ if (!used_math())
+ init_fpu(me);
+ restore_fpu_checking(&me->thread.i387.fxsave);
+ me->thread_info->status |= TS_USEDFPU;
+}
+
+void do_call_debug(struct pt_regs *regs)
+{
+ notify_die(DIE_CALL, "debug call", regs, 0, 255, SIGINT);
+}
+
+
+static trap_info_t trap_table[] = {
+ { 0, 0, (__KERNEL_CS|0x3), (unsigned long)divide_error
},
+ { 1, 0, (__KERNEL_CS|0x3), (unsigned long)debug
},
+ { 3, 3, (__KERNEL_CS|0x3), (unsigned long)int3
},
+ { 4, 3, (__KERNEL_CS|0x3), (unsigned long)overflow
},
+ { 5, 3, (__KERNEL_CS|0x3), (unsigned long)bounds
},
+ { 6, 0, (__KERNEL_CS|0x3), (unsigned long)invalid_op
},
+ { 7, 0, (__KERNEL_CS|0x3), (unsigned long)device_not_available
},
+ { 9, 0, (__KERNEL_CS|0x3), (unsigned
long)coprocessor_segment_overrun},
+ { 10, 0, (__KERNEL_CS|0x3), (unsigned long)invalid_TSS
},
+ { 11, 0, (__KERNEL_CS|0x3), (unsigned long)segment_not_present
},
+ { 12, 0, (__KERNEL_CS|0x3), (unsigned long)stack_segment
},
+ { 13, 0, (__KERNEL_CS|0x3), (unsigned long)general_protection
},
+ { 14, 0, (__KERNEL_CS|0x3), (unsigned long)page_fault
},
+ { 15, 0, (__KERNEL_CS|0x3), (unsigned long)spurious_interrupt_bug
},
+ { 16, 0, (__KERNEL_CS|0x3), (unsigned long)coprocessor_error
},
+ { 17, 0, (__KERNEL_CS|0x3), (unsigned long)alignment_check
},
+#ifdef CONFIG_X86_MCE
+ { 18, 0, (__KERNEL_CS|0x3), (unsigned long)machine_check
},
+#endif
+ { 19, 0, (__KERNEL_CS|0x3), (unsigned long)simd_coprocessor_error
},
+ { SYSCALL_VECTOR, 3, (__KERNEL_CS|0x3), (unsigned long)system_call },
+#ifdef CONFIG_IA32_EMULATION
+ { IA32_SYSCALL_VECTOR, 3, (__KERNEL_CS|0x3), (unsigned
long)ia32_syscall},
+#endif
+ { 0, 0, 0, 0 }
+};
+
+void __init trap_init(void)
+{
+ int ret;
+
+ ret = HYPERVISOR_set_trap_table(trap_table);
+
+ if (ret)
+ printk("HYPERVISOR_set_trap_table faild: error %d\n",
+ ret);
+
+#ifdef CONFIG_IA32_EMULATION
+ set_system_gate(IA32_SYSCALL_VECTOR, ia32_syscall);
+#endif
+
+ /*
+ * Should be a barrier for any external CPU state.
+ */
+ cpu_init();
+}
+
+
+/* Actual parsing is done early in setup.c. */
+static int __init oops_dummy(char *s)
+{
+ panic_on_oops = 1;
+ return -1;
+}
+__setup("oops=", oops_dummy);
+
+static int __init kstack_setup(char *s)
+{
+ kstack_depth_to_print = simple_strtoul(s,NULL,0);
+ return 0;
+}
+__setup("kstack=", kstack_setup);
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/mach-xen/smpboot_hooks.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/mach-xen/smpboot_hooks.h
Fri Jul 15 13:39:50 2005
@@ -0,0 +1,55 @@
+/* two abstractions specific to kernel/smpboot.c, mainly to cater to visws
+ * which needs to alter them. */
+
+static inline void smpboot_clear_io_apic_irqs(void)
+{
+#ifdef CONFIG_X86_IO_APIC
+ io_apic_irqs = 0;
+#endif
+}
+
+static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
+{
+#if 1
+ printk("smpboot_setup_warm_reset_vector\n");
+#else
+ CMOS_WRITE(0xa, 0xf);
+ local_flush_tlb();
+ Dprintk("1.\n");
+ *((volatile unsigned short *) TRAMPOLINE_HIGH) = start_eip >> 4;
+ Dprintk("2.\n");
+ *((volatile unsigned short *) TRAMPOLINE_LOW) = start_eip & 0xf;
+ Dprintk("3.\n");
+#endif
+}
+
+static inline void smpboot_restore_warm_reset_vector(void)
+{
+ /*
+ * Install writable page 0 entry to set BIOS data area.
+ */
+ local_flush_tlb();
+
+ /*
+ * Paranoid: Set warm reset code and vector here back
+ * to default values.
+ */
+ CMOS_WRITE(0, 0xf);
+
+ *((volatile long *) phys_to_virt(0x467)) = 0;
+}
+
+static inline void smpboot_setup_io_apic(void)
+{
+#ifdef CONFIG_X86_IO_APIC
+ /*
+ * Here we can be sure that there is an IO-APIC in the system. Let's
+ * go and set it up:
+ */
+ if (!skip_ioapic_setup && nr_ioapics)
+ setup_IO_APIC();
+#endif
+}
+
+
+#define smp_found_config (HYPERVISOR_shared_info->n_vcpu > 1)
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/hypercall.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/hypercall.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,564 @@
+/******************************************************************************
+ * hypercall.h
+ *
+ * Linux-specific hypervisor handling.
+ *
+ * Copyright (c) 2002-2004, K A Fraser
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __HYPERCALL_H__
+#define __HYPERCALL_H__
+#include <asm-xen/xen-public/xen.h>
+
+/*
+ * Assembler stubs for hyper-calls.
+ */
+
+static inline int
+HYPERVISOR_set_trap_table(
+ trap_info_t *table)
+{
+ int ret;
+ unsigned long ignore;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ignore)
+ : "0" (__HYPERVISOR_set_trap_table), "1" (table)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_mmu_update(
+ mmu_update_t *req, int count, int *success_count, domid_t domid)
+{
+ int ret;
+ unsigned long ign1, ign2, ign3, ign4;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3), "=S" (ign4)
+ : "0" (__HYPERVISOR_mmu_update), "1" (req), "2" (count),
+ "3" (success_count), "4" (domid)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_mmuext_op(
+ struct mmuext_op *op, int count, int *success_count, domid_t domid)
+{
+ int ret;
+ unsigned long ign1, ign2, ign3, ign4;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3), "=S" (ign4)
+ : "0" (__HYPERVISOR_mmuext_op), "1" (op), "2" (count),
+ "3" (success_count), "4" (domid)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_set_gdt(
+ unsigned long *frame_list, int entries)
+{
+ int ret;
+ unsigned long ign1, ign2;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2)
+ : "0" (__HYPERVISOR_set_gdt), "1" (frame_list), "2" (entries)
+ : "memory" );
+
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_stack_switch(
+ unsigned long ss, unsigned long esp)
+{
+ int ret;
+ unsigned long ign1, ign2;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2)
+ : "0" (__HYPERVISOR_stack_switch), "1" (ss), "2" (esp)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_set_callbacks(
+ unsigned long event_selector, unsigned long event_address,
+ unsigned long failsafe_selector, unsigned long failsafe_address)
+{
+ int ret;
+ unsigned long ign1, ign2, ign3, ign4;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3), "=S" (ign4)
+ : "0" (__HYPERVISOR_set_callbacks), "1" (event_selector),
+ "2" (event_address), "3" (failsafe_selector), "4" (failsafe_address)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_fpu_taskswitch(
+ int set)
+{
+ int ret;
+ unsigned long ign;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign)
+ : "0" (__HYPERVISOR_fpu_taskswitch), "1" (set)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_yield(
+ void)
+{
+ int ret;
+ unsigned long ign;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign)
+ : "0" (__HYPERVISOR_sched_op), "1" (SCHEDOP_yield)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_block(
+ void)
+{
+ int ret;
+ unsigned long ign1;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1)
+ : "0" (__HYPERVISOR_sched_op), "1" (SCHEDOP_block)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_shutdown(
+ void)
+{
+ int ret;
+ unsigned long ign1;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1)
+ : "0" (__HYPERVISOR_sched_op),
+ "1" (SCHEDOP_shutdown | (SHUTDOWN_poweroff << SCHEDOP_reasonshift))
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_reboot(
+ void)
+{
+ int ret;
+ unsigned long ign1;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1)
+ : "0" (__HYPERVISOR_sched_op),
+ "1" (SCHEDOP_shutdown | (SHUTDOWN_reboot << SCHEDOP_reasonshift))
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_suspend(
+ unsigned long srec)
+{
+ int ret;
+ unsigned long ign1, ign2;
+
+ /* NB. On suspend, control software expects a suspend record in %esi. */
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=S" (ign2)
+ : "0" (__HYPERVISOR_sched_op),
+ "b" (SCHEDOP_shutdown | (SHUTDOWN_suspend << SCHEDOP_reasonshift)),
+ "S" (srec) : "memory");
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_crash(
+ void)
+{
+ int ret;
+ unsigned long ign1;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1)
+ : "0" (__HYPERVISOR_sched_op),
+ "1" (SCHEDOP_shutdown | (SHUTDOWN_crash << SCHEDOP_reasonshift))
+ : "memory" );
+
+ return ret;
+}
+
+static inline long
+HYPERVISOR_set_timer_op(
+ u64 timeout)
+{
+ int ret;
+ unsigned long timeout_hi = (unsigned long)(timeout>>32);
+ unsigned long timeout_lo = (unsigned long)timeout;
+ unsigned long ign1, ign2;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2)
+ : "0" (__HYPERVISOR_set_timer_op), "b" (timeout_lo), "c" (timeout_hi)
+ : "memory");
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_dom0_op(
+ dom0_op_t *dom0_op)
+{
+ int ret;
+ unsigned long ign1;
+
+ dom0_op->interface_version = DOM0_INTERFACE_VERSION;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1)
+ : "0" (__HYPERVISOR_dom0_op), "1" (dom0_op)
+ : "memory");
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_set_debugreg(
+ int reg, unsigned long value)
+{
+ int ret;
+ unsigned long ign1, ign2;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2)
+ : "0" (__HYPERVISOR_set_debugreg), "1" (reg), "2" (value)
+ : "memory" );
+
+ return ret;
+}
+
+static inline unsigned long
+HYPERVISOR_get_debugreg(
+ int reg)
+{
+ unsigned long ret;
+ unsigned long ign;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign)
+ : "0" (__HYPERVISOR_get_debugreg), "1" (reg)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_update_descriptor(
+ unsigned long ma, unsigned long word1, unsigned long word2)
+{
+ int ret;
+ unsigned long ign1, ign2, ign3;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3)
+ : "0" (__HYPERVISOR_update_descriptor), "1" (ma), "2" (word1),
+ "3" (word2)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_dom_mem_op(
+ unsigned int op, unsigned long *extent_list,
+ unsigned long nr_extents, unsigned int extent_order)
+{
+ int ret;
+ unsigned long ign1, ign2, ign3, ign4, ign5;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3), "=S" (ign4),
+ "=D" (ign5)
+ : "0" (__HYPERVISOR_dom_mem_op), "1" (op), "2" (extent_list),
+ "3" (nr_extents), "4" (extent_order), "5" (DOMID_SELF)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_multicall(
+ void *call_list, int nr_calls)
+{
+ int ret;
+ unsigned long ign1, ign2;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2)
+ : "0" (__HYPERVISOR_multicall), "1" (call_list), "2" (nr_calls)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_update_va_mapping(
+ unsigned long va, pte_t new_val, unsigned long flags)
+{
+ int ret;
+ unsigned long ign1, ign2, ign3, ign4;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3), "=S" (ign4)
+ : "0" (__HYPERVISOR_update_va_mapping),
+ "1" (va), "2" ((new_val).pte_low),
+#ifdef CONFIG_X86_PAE
+ "3" ((new_val).pte_high),
+#else
+ "3" (0),
+#endif
+ "4" (flags)
+ : "memory" );
+
+ if ( unlikely(ret < 0) )
+ {
+ printk(KERN_ALERT "Failed update VA mapping: %08lx, %08lx, %08lx\n",
+ va, (new_val).pte_low, flags);
+ BUG();
+ }
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_event_channel_op(
+ void *op)
+{
+ int ret;
+ unsigned long ignore;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ignore)
+ : "0" (__HYPERVISOR_event_channel_op), "1" (op)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_xen_version(
+ int cmd)
+{
+ int ret;
+ unsigned long ignore;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ignore)
+ : "0" (__HYPERVISOR_xen_version), "1" (cmd)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_console_io(
+ int cmd, int count, char *str)
+{
+ int ret;
+ unsigned long ign1, ign2, ign3;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3)
+ : "0" (__HYPERVISOR_console_io), "1" (cmd), "2" (count), "3" (str)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_physdev_op(
+ void *physdev_op)
+{
+ int ret;
+ unsigned long ign;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign)
+ : "0" (__HYPERVISOR_physdev_op), "1" (physdev_op)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_grant_table_op(
+ unsigned int cmd, void *uop, unsigned int count)
+{
+ int ret;
+ unsigned long ign1, ign2, ign3;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3)
+ : "0" (__HYPERVISOR_grant_table_op), "1" (cmd), "2" (uop), "3" (count)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_update_va_mapping_otherdomain(
+ unsigned long va, pte_t new_val, unsigned long flags, domid_t domid)
+{
+ int ret;
+ unsigned long ign1, ign2, ign3, ign4, ign5;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3),
+ "=S" (ign4), "=D" (ign5)
+ : "0" (__HYPERVISOR_update_va_mapping_otherdomain),
+ "1" (va), "2" ((new_val).pte_low),
+#ifdef CONFIG_X86_PAE
+ "3" ((new_val).pte_high),
+#else
+ "3" (0),
+#endif
+ "4" (flags), "5" (domid) :
+ "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_vm_assist(
+ unsigned int cmd, unsigned int type)
+{
+ int ret;
+ unsigned long ign1, ign2;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2)
+ : "0" (__HYPERVISOR_vm_assist), "1" (cmd), "2" (type)
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_boot_vcpu(
+ unsigned long vcpu, vcpu_guest_context_t *ctxt)
+{
+ int ret;
+ unsigned long ign1, ign2;
+
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1), "=c" (ign2)
+ : "0" (__HYPERVISOR_boot_vcpu), "1" (vcpu), "2" (ctxt)
+ : "memory");
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_vcpu_down(
+ int vcpu)
+{
+ int ret;
+ unsigned long ign1;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1)
+ : "0" (__HYPERVISOR_sched_op),
+ "1" (SCHEDOP_vcpu_down | (vcpu << SCHEDOP_vcpushift))
+ : "memory" );
+
+ return ret;
+}
+
+static inline int
+HYPERVISOR_vcpu_up(
+ int vcpu)
+{
+ int ret;
+ unsigned long ign1;
+ __asm__ __volatile__ (
+ TRAP_INSTR
+ : "=a" (ret), "=b" (ign1)
+ : "0" (__HYPERVISOR_sched_op),
+ "1" (SCHEDOP_vcpu_up | (vcpu << SCHEDOP_vcpushift))
+ : "memory" );
+
+ return ret;
+}
+#endif /* __HYPERCALL_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/evtchn.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/evtchn.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,106 @@
+/******************************************************************************
+ * evtchn.h
+ *
+ * Communication via Xen event channels.
+ * Also definitions for the device that demuxes notifications to userspace.
+ *
+ * Copyright (c) 2004, K A Fraser
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __ASM_EVTCHN_H__
+#define __ASM_EVTCHN_H__
+
+#include <linux/config.h>
+#include <asm-xen/hypervisor.h>
+#include <asm/ptrace.h>
+#include <asm-xen/synch_bitops.h>
+#include <asm-xen/xen-public/event_channel.h>
+#include <linux/smp.h>
+
+/*
+ * LOW-LEVEL DEFINITIONS
+ */
+
+/* Entry point for notifications into Linux subsystems. */
+asmlinkage void evtchn_do_upcall(struct pt_regs *regs);
+
+/* Entry point for notifications into the userland character device. */
+void evtchn_device_upcall(int port);
+
+static inline void mask_evtchn(int port)
+{
+ shared_info_t *s = HYPERVISOR_shared_info;
+ synch_set_bit(port, &s->evtchn_mask[0]);
+}
+
+static inline void unmask_evtchn(int port)
+{
+ shared_info_t *s = HYPERVISOR_shared_info;
+ vcpu_info_t *vcpu_info = &s->vcpu_data[smp_processor_id()];
+
+ synch_clear_bit(port, &s->evtchn_mask[0]);
+
+ /*
+ * The following is basically the equivalent of 'hw_resend_irq'. Just like
+ * a real IO-APIC we 'lose the interrupt edge' if the channel is masked.
+ */
+ if ( synch_test_bit (port, &s->evtchn_pending[0]) &&
+ !synch_test_and_set_bit(port>>5, &vcpu_info->evtchn_pending_sel) )
+ {
+ vcpu_info->evtchn_upcall_pending = 1;
+ if ( !vcpu_info->evtchn_upcall_mask )
+ force_evtchn_callback();
+ }
+}
+
+static inline void clear_evtchn(int port)
+{
+ shared_info_t *s = HYPERVISOR_shared_info;
+ synch_clear_bit(port, &s->evtchn_pending[0]);
+}
+
+static inline int notify_via_evtchn(int port)
+{
+ evtchn_op_t op;
+ op.cmd = EVTCHNOP_send;
+ op.u.send.local_port = port;
+ return HYPERVISOR_event_channel_op(&op);
+}
+
+/*
+ * CHARACTER-DEVICE DEFINITIONS
+ */
+
+/* /dev/xen/evtchn resides at device number major=10, minor=201 */
+#define EVTCHN_MINOR 201
+
+/* /dev/xen/evtchn ioctls: */
+/* EVTCHN_RESET: Clear and reinit the event buffer. Clear error condition. */
+#define EVTCHN_RESET _IO('E', 1)
+/* EVTCHN_BIND: Bind to teh specified event-channel port. */
+#define EVTCHN_BIND _IO('E', 2)
+/* EVTCHN_UNBIND: Unbind from the specified event-channel port. */
+#define EVTCHN_UNBIND _IO('E', 3)
+
+#endif /* __ASM_EVTCHN_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/head64.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/head64.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,132 @@
+/*
+ * linux/arch/x86_64/kernel/head64.c -- prepare to run common code
+ *
+ * Copyright (C) 2000 Andrea Arcangeli <andrea@xxxxxxx> SuSE
+ *
+ * $Id: head64.c,v 1.22 2001/07/06 14:28:20 ak Exp $
+ *
+ * Jun Nakajima <jun.nakajima@xxxxxxxxx>
+ * Modified for Xen.
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/percpu.h>
+
+#include <asm/processor.h>
+#include <asm/proto.h>
+#include <asm/smp.h>
+#include <asm/bootsetup.h>
+#include <asm/setup.h>
+#include <asm/desc.h>
+
+unsigned long start_pfn;
+
+/* Don't add a printk in there. printk relies on the PDA which is not
initialized
+ yet. */
+#if 0
+static void __init clear_bss(void)
+{
+ extern char __bss_start[], __bss_end[];
+ memset(__bss_start, 0,
+ (unsigned long) __bss_end - (unsigned long) __bss_start);
+}
+#endif
+
+extern char x86_boot_params[2048];
+
+#define NEW_CL_POINTER 0x228 /* Relative to real mode data */
+#define OLD_CL_MAGIC_ADDR 0x90020
+#define OLD_CL_MAGIC 0xA33F
+#define OLD_CL_BASE_ADDR 0x90000
+#define OLD_CL_OFFSET 0x90022
+
+extern char saved_command_line[];
+
+#if 0
+static void __init copy_bootdata(char *real_mode_data)
+{
+ int new_data;
+ char * command_line;
+
+ memcpy(x86_boot_params, real_mode_data, 2048);
+ new_data = *(int *) (x86_boot_params + NEW_CL_POINTER);
+ if (!new_data) {
+ if (OLD_CL_MAGIC != * (u16 *) OLD_CL_MAGIC_ADDR) {
+ printk("so old bootloader that it does not support
commandline?!\n");
+ return;
+ }
+ new_data = OLD_CL_BASE_ADDR + * (u16 *) OLD_CL_OFFSET;
+ printk("old bootloader convention, maybe loadlin?\n");
+ }
+ command_line = (char *) ((u64)(new_data));
+ memcpy(saved_command_line, command_line, COMMAND_LINE_SIZE);
+ printk("Bootdata ok (command line is %s)\n", saved_command_line);
+}
+#endif
+
+static void __init setup_boot_cpu_data(void)
+{
+ int dummy, eax;
+
+ /* get vendor info */
+ cpuid(0, &boot_cpu_data.cpuid_level,
+ (int *)&boot_cpu_data.x86_vendor_id[0],
+ (int *)&boot_cpu_data.x86_vendor_id[8],
+ (int *)&boot_cpu_data.x86_vendor_id[4]);
+
+ /* get cpu type */
+ cpuid(1, &eax, &dummy, &dummy,
+ (unsigned int *) &boot_cpu_data.x86_capability);
+ boot_cpu_data.x86 = (eax >> 8) & 0xf;
+ boot_cpu_data.x86_model = (eax >> 4) & 0xf;
+ boot_cpu_data.x86_mask = eax & 0xf;
+}
+
+extern char _end[];
+
+void __init x86_64_start_kernel(char * real_mode_data)
+{
+ int i;
+
+ phys_to_machine_mapping = (u32 *)xen_start_info.mfn_list;
+ start_pfn = (__pa(xen_start_info.pt_base) >> PAGE_SHIFT) +
xen_start_info.nr_pt_frames;
+
+ for (i = 0; i < 256; i++)
+ set_intr_gate(i, early_idt_handler);
+#if 0
+ asm volatile("lidt %0" :: "m" (idt_descr));
+#endif
+ pda_init(0);
+ /* copy_bootdata(real_mode_data); */
+#ifdef CONFIG_SMP
+ cpu_set(0, cpu_online_map);
+#endif
+ /* default console: */
+ if (!strstr(saved_command_line, "console="))
+ strcat(saved_command_line, " console=tty0");
+#if 0
+ s = strstr(saved_command_line, "earlyprintk=");
+ if (s != NULL)
+ setup_early_printk(s);
+#endif
+
+#ifdef CONFIG_DISCONTIGMEM
+ s = strstr(saved_command_line, "numa=");
+ if (s != NULL)
+ numa_setup(s+5);
+#endif
+#ifdef CONFIG_X86_IO_APIC
+ if (strstr(saved_command_line, "disableapic"))
+ disable_apic = 1;
+#endif
+ /* You need early console to see that */
+ if (__pa_symbol(&_end) >= KERNEL_TEXT_SIZE)
+ panic("Kernel too big for kernel mapping\n");
+
+ setup_boot_cpu_data();
+ start_kernel();
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/setup_arch_post.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++
b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/setup_arch_post.h
Fri Jul 15 13:39:50 2005
@@ -0,0 +1,47 @@
+/**
+ * machine_specific_memory_setup - Hook for machine specific memory setup.
+ *
+ * Description:
+ * This is included late in kernel/setup.c so that it can make
+ * use of all of the static functions.
+ **/
+
+static char * __init machine_specific_memory_setup(void)
+{
+ char *who;
+ unsigned long start_pfn, max_pfn;
+
+ who = "Xen";
+
+ start_pfn = 0;
+ max_pfn = xen_start_info.nr_pages;
+
+ e820.nr_map = 0;
+ add_memory_region(PFN_PHYS(start_pfn), PFN_PHYS(max_pfn) -
PFN_PHYS(start_pfn), E820_RAM);
+
+ return who;
+}
+
+void __init machine_specific_modify_cpu_capabilities(struct cpuinfo_x86 *c)
+{
+ clear_bit(X86_FEATURE_VME, c->x86_capability);
+ clear_bit(X86_FEATURE_DE, c->x86_capability);
+ clear_bit(X86_FEATURE_PSE, c->x86_capability);
+ clear_bit(X86_FEATURE_PGE, c->x86_capability);
+ clear_bit(X86_FEATURE_SEP, c->x86_capability);
+ if (!(xen_start_info.flags & SIF_PRIVILEGED))
+ clear_bit(X86_FEATURE_MTRR, c->x86_capability);
+}
+
+extern void hypervisor_callback(void);
+extern void failsafe_callback(void);
+
+static void __init machine_specific_arch_setup(void)
+{
+ HYPERVISOR_set_callbacks(
+ (unsigned long) hypervisor_callback,
+ (unsigned long) failsafe_callback,
+ (unsigned long) system_call);
+
+ machine_specific_modify_cpu_capabilities(&boot_cpu_data);
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/acpi/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/acpi/Makefile Fri Jul
15 13:39:50 2005
@@ -0,0 +1,13 @@
+obj-$(CONFIG_ACPI_BOOT) := boot.o
+c-obj-$(CONFIG_X86_IO_APIC) += earlyquirk.o
+c-obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup.o
+
+c-link :=
+
+$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)):
+ @ln -fsn $(srctree)/arch/i386/kernel/acpi/$(notdir $@) $@
+
+obj-y += $(c-obj-y) $(s-obj-y)
+
+clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link))
+clean-files += $(patsubst %.o,%.S,$(s-obj-y) $(s-obj-) $(s-link))
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/ldt.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/ldt.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,263 @@
+/*
+ * linux/arch/x86_64/kernel/ldt.c
+ *
+ * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds
+ * Copyright (C) 1999 Ingo Molnar <mingo@xxxxxxxxxx>
+ * Copyright (C) 2002 Andi Kleen
+ *
+ * This handles calls from both 32bit and 64bit mode.
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/ldt.h>
+#include <asm/desc.h>
+#include <asm/proto.h>
+#include <asm/pgalloc.h>
+
+#ifdef CONFIG_SMP /* avoids "defined but not used" warnig */
+static void flush_ldt(void *null)
+{
+ if (current->active_mm)
+ load_LDT(¤t->active_mm->context);
+}
+#endif
+
+static int alloc_ldt(mm_context_t *pc, unsigned mincount, int reload)
+{
+ void *oldldt;
+ void *newldt;
+ unsigned oldsize;
+
+ if (mincount <= (unsigned)pc->size)
+ return 0;
+ oldsize = pc->size;
+ mincount = (mincount+511)&(~511);
+ if (mincount*LDT_ENTRY_SIZE > PAGE_SIZE)
+ newldt = vmalloc(mincount*LDT_ENTRY_SIZE);
+ else
+ newldt = kmalloc(mincount*LDT_ENTRY_SIZE, GFP_KERNEL);
+
+ if (!newldt)
+ return -ENOMEM;
+
+ if (oldsize)
+ memcpy(newldt, pc->ldt, oldsize*LDT_ENTRY_SIZE);
+ oldldt = pc->ldt;
+ memset(newldt+oldsize*LDT_ENTRY_SIZE, 0,
(mincount-oldsize)*LDT_ENTRY_SIZE);
+ wmb();
+ pc->ldt = newldt;
+ wmb();
+ pc->size = mincount;
+ wmb();
+ if (reload) {
+#ifdef CONFIG_SMP
+ cpumask_t mask;
+ preempt_disable();
+#endif
+ make_pages_readonly(pc->ldt, (pc->size * LDT_ENTRY_SIZE) /
+ PAGE_SIZE);
+ load_LDT(pc);
+#ifdef CONFIG_SMP
+ mask = cpumask_of_cpu(smp_processor_id());
+ if (!cpus_equal(current->mm->cpu_vm_mask, mask))
+ smp_call_function(flush_ldt, NULL, 1, 1);
+ preempt_enable();
+#endif
+ }
+ if (oldsize) {
+ make_pages_writable(oldldt, (oldsize * LDT_ENTRY_SIZE) /
+ PAGE_SIZE);
+ if (oldsize*LDT_ENTRY_SIZE > PAGE_SIZE)
+ vfree(oldldt);
+ else
+ kfree(oldldt);
+ }
+ return 0;
+}
+
+static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
+{
+ int err = alloc_ldt(new, old->size, 0);
+ if (err < 0)
+ return err;
+ memcpy(new->ldt, old->ldt, old->size*LDT_ENTRY_SIZE);
+ make_pages_readonly(new->ldt, (new->size * LDT_ENTRY_SIZE) /
+ PAGE_SIZE);
+ return 0;
+}
+
+/*
+ * we do not have to muck with descriptors here, that is
+ * done in switch_mm() as needed.
+ */
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+ struct mm_struct * old_mm;
+ int retval = 0;
+
+ init_MUTEX(&mm->context.sem);
+ mm->context.size = 0;
+ old_mm = current->mm;
+ if (old_mm && old_mm->context.size > 0) {
+ down(&old_mm->context.sem);
+ retval = copy_ldt(&mm->context, &old_mm->context);
+ up(&old_mm->context.sem);
+ }
+ return retval;
+}
+
+/*
+ *
+ * Don't touch the LDT register - we're already in the next thread.
+ */
+void destroy_context(struct mm_struct *mm)
+{
+ if (mm->context.size) {
+ if (mm == current->active_mm)
+ clear_LDT();
+ make_pages_writable(mm->context.ldt,
+ (mm->context.size * LDT_ENTRY_SIZE) /
+ PAGE_SIZE);
+ if (mm->context.size*LDT_ENTRY_SIZE > PAGE_SIZE)
+ vfree(mm->context.ldt);
+ else
+ kfree(mm->context.ldt);
+ mm->context.size = 0;
+ }
+}
+
+static int read_ldt(void __user * ptr, unsigned long bytecount)
+{
+ int err;
+ unsigned long size;
+ struct mm_struct * mm = current->mm;
+
+ if (!mm->context.size)
+ return 0;
+ if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES)
+ bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES;
+
+ down(&mm->context.sem);
+ size = mm->context.size*LDT_ENTRY_SIZE;
+ if (size > bytecount)
+ size = bytecount;
+
+ err = 0;
+ if (copy_to_user(ptr, mm->context.ldt, size))
+ err = -EFAULT;
+ up(&mm->context.sem);
+ if (err < 0)
+ goto error_return;
+ if (size != bytecount) {
+ /* zero-fill the rest */
+ if (clear_user(ptr+size, bytecount-size) != 0) {
+ err = -EFAULT;
+ goto error_return;
+ }
+ }
+ return bytecount;
+error_return:
+ return err;
+}
+
+static int read_default_ldt(void __user * ptr, unsigned long bytecount)
+{
+ /* Arbitrary number */
+ /* x86-64 default LDT is all zeros */
+ if (bytecount > 128)
+ bytecount = 128;
+ if (clear_user(ptr, bytecount))
+ return -EFAULT;
+ return bytecount;
+}
+
+static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode)
+{
+ struct task_struct *me = current;
+ struct mm_struct * mm = me->mm;
+ __u32 entry_1, entry_2, *lp;
+ unsigned long mach_lp;
+ int error;
+ struct user_desc ldt_info;
+
+ error = -EINVAL;
+ if (bytecount != sizeof(ldt_info))
+ goto out;
+ error = -EFAULT;
+ if (copy_from_user(&ldt_info, ptr, bytecount))
+ goto out;
+
+ error = -EINVAL;
+ if (ldt_info.entry_number >= LDT_ENTRIES)
+ goto out;
+ if (ldt_info.contents == 3) {
+ if (oldmode)
+ goto out;
+ if (ldt_info.seg_not_present == 0)
+ goto out;
+ }
+
+ down(&mm->context.sem);
+ if (ldt_info.entry_number >= (unsigned)mm->context.size) {
+ error = alloc_ldt(¤t->mm->context,
ldt_info.entry_number+1, 1);
+ if (error < 0)
+ goto out_unlock;
+ }
+
+ lp = (__u32 *) ((ldt_info.entry_number << 3) + (char *)
mm->context.ldt);
+ mach_lp = arbitrary_virt_to_machine(lp);
+
+ /* Allow LDTs to be cleared by the user. */
+ if (ldt_info.base_addr == 0 && ldt_info.limit == 0) {
+ if (oldmode || LDT_empty(&ldt_info)) {
+ entry_1 = 0;
+ entry_2 = 0;
+ goto install;
+ }
+ }
+
+ entry_1 = LDT_entry_a(&ldt_info);
+ entry_2 = LDT_entry_b(&ldt_info);
+ if (oldmode)
+ entry_2 &= ~(1 << 20);
+
+ /* Install the new entry ... */
+install:
+ error = HYPERVISOR_update_descriptor(mach_lp, (unsigned long)((entry_1
| (unsigned long) entry_2 << 32)));
+
+out_unlock:
+ up(&mm->context.sem);
+out:
+ return error;
+}
+
+asmlinkage int sys_modify_ldt(int func, void __user *ptr, unsigned long
bytecount)
+{
+ int ret = -ENOSYS;
+
+ switch (func) {
+ case 0:
+ ret = read_ldt(ptr, bytecount);
+ break;
+ case 1:
+ ret = write_ldt(ptr, bytecount, 1);
+ break;
+ case 2:
+ ret = read_default_ldt(ptr, bytecount);
+ break;
+ case 0x11:
+ ret = write_ldt(ptr, bytecount, 0);
+ break;
+ }
+ return ret;
+}
diff -r 35b74976f598 -r a83ac0806d6b linux-2.6.11-xen-sparse/include/linux/gfp.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/linux/gfp.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,138 @@
+#ifndef __LINUX_GFP_H
+#define __LINUX_GFP_H
+
+#include <linux/mmzone.h>
+#include <linux/stddef.h>
+#include <linux/linkage.h>
+#include <linux/config.h>
+
+struct vm_area_struct;
+
+/*
+ * GFP bitmasks..
+ */
+/* Zone modifiers in GFP_ZONEMASK (see linux/mmzone.h - low two bits) */
+#define __GFP_DMA 0x01
+#define __GFP_HIGHMEM 0x02
+
+/*
+ * Action modifiers - doesn't change the zoning
+ *
+ * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt
+ * _might_ fail. This depends upon the particular VM implementation.
+ *
+ * __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
+ * cannot handle allocation failures.
+ *
+ * __GFP_NORETRY: The VM implementation must not retry indefinitely.
+ */
+#define __GFP_WAIT 0x10 /* Can wait and reschedule? */
+#define __GFP_HIGH 0x20 /* Should access emergency pools? */
+#define __GFP_IO 0x40 /* Can start physical IO? */
+#define __GFP_FS 0x80 /* Can call down to low-level FS? */
+#define __GFP_COLD 0x100 /* Cache-cold page required */
+#define __GFP_NOWARN 0x200 /* Suppress page allocation failure warning */
+#define __GFP_REPEAT 0x400 /* Retry the allocation. Might fail */
+#define __GFP_NOFAIL 0x800 /* Retry for ever. Cannot fail */
+#define __GFP_NORETRY 0x1000 /* Do not retry. Might fail */
+#define __GFP_NO_GROW 0x2000 /* Slab internal usage */
+#define __GFP_COMP 0x4000 /* Add compound page metadata */
+#define __GFP_ZERO 0x8000 /* Return zeroed page on success */
+
+#define __GFP_BITS_SHIFT 16 /* Room for 16 __GFP_FOO bits */
+#define __GFP_BITS_MASK ((1 << __GFP_BITS_SHIFT) - 1)
+
+/* if you forget to add the bitmask here kernel will crash, period */
+#define GFP_LEVEL_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS| \
+ __GFP_COLD|__GFP_NOWARN|__GFP_REPEAT| \
+ __GFP_NOFAIL|__GFP_NORETRY|__GFP_NO_GROW|__GFP_COMP)
+
+#define GFP_ATOMIC (__GFP_HIGH)
+#define GFP_NOIO (__GFP_WAIT)
+#define GFP_NOFS (__GFP_WAIT | __GFP_IO)
+#define GFP_KERNEL (__GFP_WAIT | __GFP_IO | __GFP_FS)
+#define GFP_USER (__GFP_WAIT | __GFP_IO | __GFP_FS)
+#define GFP_HIGHUSER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HIGHMEM)
+
+/* Flag - indicates that the buffer will be suitable for DMA. Ignored on some
+ platforms, used as appropriate on others */
+
+#define GFP_DMA __GFP_DMA
+
+
+/*
+ * There is only one page-allocator function, and two main namespaces to
+ * it. The alloc_page*() variants return 'struct page *' and as such
+ * can allocate highmem pages, the *get*page*() variants return
+ * virtual kernel addresses to the allocated page(s).
+ */
+
+/*
+ * We get the zone list from the current node and the gfp_mask.
+ * This zone list contains a maximum of MAXNODES*MAX_NR_ZONES zones.
+ *
+ * For the normal case of non-DISCONTIGMEM systems the NODE_DATA() gets
+ * optimized to &contig_page_data at compile-time.
+ */
+
+/*
+ * If arch_free_page returns non-zero then the generic free_page code can
+ * immediately bail: the arch-specific function has done all the work.
+ */
+#ifndef HAVE_ARCH_FREE_PAGE
+#define arch_free_page(page, order) 0
+#endif
+
+extern struct page *
+FASTCALL(__alloc_pages(unsigned int, unsigned int, struct zonelist *));
+
+static inline struct page *alloc_pages_node(int nid, unsigned int gfp_mask,
+ unsigned int order)
+{
+ if (unlikely(order >= MAX_ORDER))
+ return NULL;
+
+ return __alloc_pages(gfp_mask, order,
+ NODE_DATA(nid)->node_zonelists + (gfp_mask & GFP_ZONEMASK));
+}
+
+#ifdef CONFIG_NUMA
+extern struct page *alloc_pages_current(unsigned gfp_mask, unsigned order);
+
+static inline struct page *
+alloc_pages(unsigned int gfp_mask, unsigned int order)
+{
+ if (unlikely(order >= MAX_ORDER))
+ return NULL;
+
+ return alloc_pages_current(gfp_mask, order);
+}
+extern struct page *alloc_page_vma(unsigned gfp_mask,
+ struct vm_area_struct *vma, unsigned long addr);
+#else
+#define alloc_pages(gfp_mask, order) \
+ alloc_pages_node(numa_node_id(), gfp_mask, order)
+#define alloc_page_vma(gfp_mask, vma, addr) alloc_pages(gfp_mask, 0)
+#endif
+#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
+
+extern unsigned long FASTCALL(__get_free_pages(unsigned int gfp_mask, unsigned
int order));
+extern unsigned long FASTCALL(get_zeroed_page(unsigned int gfp_mask));
+
+#define __get_free_page(gfp_mask) \
+ __get_free_pages((gfp_mask),0)
+
+#define __get_dma_pages(gfp_mask, order) \
+ __get_free_pages((gfp_mask) | GFP_DMA,(order))
+
+extern void FASTCALL(__free_pages(struct page *page, unsigned int order));
+extern void FASTCALL(free_pages(unsigned long addr, unsigned int order));
+extern void FASTCALL(free_hot_page(struct page *page));
+extern void FASTCALL(free_cold_page(struct page *page));
+
+#define __free_page(page) __free_pages((page), 0)
+#define free_page(addr) free_pages((addr),0)
+
+void page_alloc_init(void);
+
+#endif /* __LINUX_GFP_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/kernel/entry.S
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/kernel/entry.S Fri Jul 15 13:39:50 2005
@@ -0,0 +1,779 @@
+/*
+ * linux/arch/i386/entry.S
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+/*
+ * entry.S contains the system-call and fault low-level handling routines.
+ * This also contains the timer-interrupt handler, as well as all interrupts
+ * and faults that can result in a task-switch.
+ *
+ * NOTE: This code handles signal-recognition, which happens every time
+ * after a timer-interrupt and after each system call.
+ *
+ * I changed all the .align's to 4 (16 byte alignment), as that's faster
+ * on a 486.
+ *
+ * Stack layout in 'ret_to_user':
+ * ptrace needs to have all regs on the stack.
+ * if the order here is changed, it needs to be
+ * updated in fork.c:copy_process, signal.c:do_signal,
+ * ptrace.c and ptrace.h
+ *
+ * 0(%esp) - %ebx
+ * 4(%esp) - %ecx
+ * 8(%esp) - %edx
+ * C(%esp) - %esi
+ * 10(%esp) - %edi
+ * 14(%esp) - %ebp
+ * 18(%esp) - %eax
+ * 1C(%esp) - %ds
+ * 20(%esp) - %es
+ * 24(%esp) - orig_eax
+ * 28(%esp) - %eip
+ * 2C(%esp) - %cs
+ * 30(%esp) - %eflags
+ * 34(%esp) - %oldesp
+ * 38(%esp) - %oldss
+ *
+ * "current" is in register %ebx during any slow entries.
+ */
+
+#include <linux/config.h>
+#include <linux/sys.h>
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/smp.h>
+
+EBX = 0x00
+ECX = 0x04
+EDX = 0x08
+ESI = 0x0C
+EDI = 0x10
+EBP = 0x14
+EAX = 0x18
+DS = 0x1C
+ES = 0x20
+ORIG_EAX = 0x24
+EIP = 0x28
+CS = 0x2C
+EFLAGS = 0x30
+OLDESP = 0x34
+OLDSS = 0x38
+
+CF_MASK = 0x00000001
+TF_MASK = 0x00000100
+IF_MASK = 0x00000200
+DF_MASK = 0x00000400
+NT_MASK = 0x00004000
+
+/* Offsets into task_struct. */
+state = 0
+flags = 4
+sigpending = 8
+addr_limit = 12
+exec_domain = 16
+need_resched = 20
+tsk_ptrace = 24
+processor = 52
+
+/* Offsets into shared_info_t. */
+#define evtchn_upcall_pending /* 0 */
+#define evtchn_upcall_mask 1
+
+ENOSYS = 38
+
+
+#define SAVE_ALL \
+ cld; \
+ pushl %es; \
+ pushl %ds; \
+ pushl %eax; \
+ pushl %ebp; \
+ pushl %edi; \
+ pushl %esi; \
+ pushl %edx; \
+ pushl %ecx; \
+ pushl %ebx; \
+ movl $(__KERNEL_DS),%edx; \
+ movl %edx,%ds; \
+ movl %edx,%es;
+
+#define RESTORE_ALL \
+ popl %ebx; \
+ popl %ecx; \
+ popl %edx; \
+ popl %esi; \
+ popl %edi; \
+ popl %ebp; \
+ popl %eax; \
+1: popl %ds; \
+2: popl %es; \
+ addl $4,%esp; \
+3: iret; \
+.section .fixup,"ax"; \
+4: movl $0,(%esp); \
+ jmp 1b; \
+5: movl $0,(%esp); \
+ jmp 2b; \
+6: pushl %ss; \
+ popl %ds; \
+ pushl %ss; \
+ popl %es; \
+ pushl $11; \
+ call do_exit; \
+.previous; \
+.section __ex_table,"a";\
+ .align 4; \
+ .long 1b,4b; \
+ .long 2b,5b; \
+ .long 3b,6b; \
+.previous
+
+#define GET_CURRENT(reg) \
+ movl $-8192, reg; \
+ andl %esp, reg
+
+ENTRY(lcall7)
+ pushfl # We get a different stack layout with call
+ pushl %eax # gates, which has to be cleaned up later..
+ SAVE_ALL
+ movl EIP(%esp),%eax # due to call gates, this is eflags, not eip..
+ movl CS(%esp),%edx # this is eip..
+ movl EFLAGS(%esp),%ecx # and this is cs..
+ movl %eax,EFLAGS(%esp) #
+ andl $~(NT_MASK|TF_MASK|DF_MASK), %eax
+ pushl %eax
+ popfl
+ movl %edx,EIP(%esp) # Now we move them to their "normal" places
+ movl %ecx,CS(%esp) #
+ movl %esp,%ebx
+ pushl %ebx
+ andl $-8192,%ebx # GET_CURRENT
+ movl exec_domain(%ebx),%edx # Get the execution domain
+ movl 4(%edx),%edx # Get the lcall7 handler for the domain
+ pushl $0x7
+ call *%edx
+ addl $4, %esp
+ popl %eax
+ jmp ret_to_user
+
+ENTRY(lcall27)
+ pushfl # We get a different stack layout with call
+ pushl %eax # gates, which has to be cleaned up later..
+ SAVE_ALL
+ movl EIP(%esp),%eax # due to call gates, this is eflags, not eip..
+ movl CS(%esp),%edx # this is eip..
+ movl EFLAGS(%esp),%ecx # and this is cs..
+ movl %eax,EFLAGS(%esp) #
+ andl $~(NT_MASK|TF_MASK|DF_MASK), %eax
+ pushl %eax
+ popfl
+ movl %edx,EIP(%esp) # Now we move them to their "normal" places
+ movl %ecx,CS(%esp) #
+ movl %esp,%ebx
+ pushl %ebx
+ andl $-8192,%ebx # GET_CURRENT
+ movl exec_domain(%ebx),%edx # Get the execution domain
+ movl 4(%edx),%edx # Get the lcall7 handler for the domain
+ pushl $0x27
+ call *%edx
+ addl $4, %esp
+ popl %eax
+ jmp ret_to_user
+
+ENTRY(ret_from_fork)
+ pushl %ebx
+ call SYMBOL_NAME(schedule_tail)
+ addl $4, %esp
+ GET_CURRENT(%ebx)
+ testb $0x02,tsk_ptrace(%ebx) # PT_TRACESYS
+ jne tracesys_exit
+ jmp ret_to_user
+
+/*
+ * Return to user mode is not as complex as all this looks,
+ * but we want the default path for a system call return to
+ * go as quickly as possible which is why some of this is
+ * less clear than it otherwise should be.
+ */
+ENTRY(system_call)
+ pushl %eax # save orig_eax
+ SAVE_ALL
+ GET_CURRENT(%ebx)
+ testb $0x02,tsk_ptrace(%ebx) # PT_TRACESYS
+ jne tracesys
+ cmpl $(NR_syscalls),%eax
+ jae badsys
+ call *SYMBOL_NAME(sys_call_table)(,%eax,4)
+ movl %eax,EAX(%esp) # save the return value
+ret_to_user:
+ movl SYMBOL_NAME(HYPERVISOR_shared_info),%esi
+ movb $1,evtchn_upcall_mask(%esi) # make tests atomic
+ret_to_user_nocli:
+ cmpl $0,need_resched(%ebx)
+ jne reschedule
+ cmpl $0,sigpending(%ebx)
+ je safesti # ensure need_resched updates are seen
+/*signal_return:*/
+ movb $0,evtchn_upcall_mask(%esi) # reenable event callbacks
+ movl %esp,%eax
+ xorl %edx,%edx
+ call SYMBOL_NAME(do_signal)
+ jmp safesti
+
+ ALIGN
+restore_all:
+ RESTORE_ALL
+
+ ALIGN
+tracesys:
+ movl $-ENOSYS,EAX(%esp)
+ call SYMBOL_NAME(syscall_trace)
+ movl ORIG_EAX(%esp),%eax
+ cmpl $(NR_syscalls),%eax
+ jae tracesys_exit
+ call *SYMBOL_NAME(sys_call_table)(,%eax,4)
+ movl %eax,EAX(%esp) # save the return value
+tracesys_exit:
+ call SYMBOL_NAME(syscall_trace)
+ jmp ret_to_user
+badsys:
+ movl $-ENOSYS,EAX(%esp)
+ jmp ret_to_user
+
+ ALIGN
+ENTRY(ret_from_intr)
+ GET_CURRENT(%ebx)
+ret_from_exception:
+ movb CS(%esp),%al
+ testl $2,%eax
+ jne ret_to_user
+ jmp restore_all
+
+ ALIGN
+reschedule:
+ movb $0,evtchn_upcall_mask(%esi) # reenable event callbacks
+ call SYMBOL_NAME(schedule) # test
+ jmp ret_to_user
+
+ENTRY(divide_error)
+ pushl $0 # no error code
+ pushl $ SYMBOL_NAME(do_divide_error)
+ ALIGN
+error_code:
+ pushl %ds
+ pushl %eax
+ xorl %eax,%eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ decl %eax # eax = -1
+ pushl %ecx
+ pushl %ebx
+ GET_CURRENT(%ebx)
+ cld
+ movl %es,%ecx
+ movl ORIG_EAX(%esp), %esi # get the error code
+ movl ES(%esp), %edi # get the function address
+ movl %eax, ORIG_EAX(%esp)
+ movl %ecx, ES(%esp)
+ movl %esp,%edx
+ pushl %esi # push the error code
+ pushl %edx # push the pt_regs pointer
+ movl $(__KERNEL_DS),%edx
+ movl %edx,%ds
+ movl %edx,%es
+ call *%edi
+ addl $8,%esp
+ jmp ret_from_exception
+
+# A note on the "critical region" in our callback handler.
+# We want to avoid stacking callback handlers due to events occurring
+# during handling of the last event. To do this, we keep events disabled
+# until we've done all processing. HOWEVER, we must enable events before
+# popping the stack frame (can't be done atomically) and so it would still
+# be possible to get enough handler activations to overflow the stack.
+# Although unlikely, bugs of that kind are hard to track down, so we'd
+# like to avoid the possibility.
+# So, on entry to the handler we detect whether we interrupted an
+# existing activation in its critical region -- if so, we pop the current
+# activation and restart the handler using the previous one.
+ENTRY(hypervisor_callback)
+ pushl %eax
+ SAVE_ALL
+ GET_CURRENT(%ebx)
+ movl EIP(%esp),%eax
+ cmpl $scrit,%eax
+ jb 11f
+ cmpl $ecrit,%eax
+ jb critical_region_fixup
+11: push %esp
+ call evtchn_do_upcall
+ add $4,%esp
+ movl SYMBOL_NAME(HYPERVISOR_shared_info),%esi
+ movb CS(%esp),%cl
+ test $2,%cl # slow return to ring 2 or 3
+ jne ret_to_user_nocli
+safesti:movb $0,evtchn_upcall_mask(%esi) # reenable event callbacks
+scrit: /**** START OF CRITICAL REGION ****/
+ testb $0xFF,evtchn_upcall_pending(%esi)
+ jnz 14f # process more events if necessary...
+ RESTORE_ALL
+14: movb $1,evtchn_upcall_mask(%esi)
+ jmp 11b
+ecrit: /**** END OF CRITICAL REGION ****/
+# [How we do the fixup]. We want to merge the current stack frame with the
+# just-interrupted frame. How we do this depends on where in the critical
+# region the interrupted handler was executing, and so how many saved
+# registers are in each frame. We do this quickly using the lookup table
+# 'critical_fixup_table'. For each byte offset in the critical region, it
+# provides the number of bytes which have already been popped from the
+# interrupted stack frame.
+critical_region_fixup:
+ addl $critical_fixup_table-scrit,%eax
+ movzbl (%eax),%eax # %eax contains num bytes popped
+ mov %esp,%esi
+ add %eax,%esi # %esi points at end of src region
+ mov %esp,%edi
+ add $0x34,%edi # %edi points at end of dst region
+ mov %eax,%ecx
+ shr $2,%ecx # convert words to bytes
+ je 16f # skip loop if nothing to copy
+15: subl $4,%esi # pre-decrementing copy loop
+ subl $4,%edi
+ movl (%esi),%eax
+ movl %eax,(%edi)
+ loop 15b
+16: movl %edi,%esp # final %edi is top of merged stack
+ jmp 11b
+
+critical_fixup_table:
+ .byte 0x00,0x00,0x00 # testb $0xFF,(%esi)
+ .byte 0x00,0x00 # jnz 14f
+ .byte 0x00 # pop %ebx
+ .byte 0x04 # pop %ecx
+ .byte 0x08 # pop %edx
+ .byte 0x0c # pop %esi
+ .byte 0x10 # pop %edi
+ .byte 0x14 # pop %ebp
+ .byte 0x18 # pop %eax
+ .byte 0x1c # pop %ds
+ .byte 0x20 # pop %es
+ .byte 0x24,0x24,0x24 # add $4,%esp
+ .byte 0x28 # iret
+ .byte 0x00,0x00,0x00,0x00 # movb $1,4(%esi)
+ .byte 0x00,0x00 # jmp 11b
+
+# Hypervisor uses this for application faults while it executes.
+ENTRY(failsafe_callback)
+1: popl %ds
+2: popl %es
+3: popl %fs
+4: popl %gs
+5: iret
+.section .fixup,"ax"; \
+6: movl $0,(%esp); \
+ jmp 1b; \
+7: movl $0,(%esp); \
+ jmp 2b; \
+8: movl $0,(%esp); \
+ jmp 3b; \
+9: movl $0,(%esp); \
+ jmp 4b; \
+10: pushl %ss; \
+ popl %ds; \
+ pushl %ss; \
+ popl %es; \
+ pushl $11; \
+ call do_exit; \
+.previous; \
+.section __ex_table,"a";\
+ .align 4; \
+ .long 1b,6b; \
+ .long 2b,7b; \
+ .long 3b,8b; \
+ .long 4b,9b; \
+ .long 5b,10b; \
+.previous
+
+ENTRY(coprocessor_error)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_coprocessor_error)
+ jmp error_code
+
+ENTRY(simd_coprocessor_error)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_simd_coprocessor_error)
+ jmp error_code
+
+ENTRY(device_not_available)
+ pushl $-1 # mark this as an int
+ SAVE_ALL
+ GET_CURRENT(%ebx)
+ call SYMBOL_NAME(math_state_restore)
+ jmp ret_from_exception
+
+ENTRY(debug)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_debug)
+ jmp error_code
+
+ENTRY(int3)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_int3)
+ jmp error_code
+
+ENTRY(overflow)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_overflow)
+ jmp error_code
+
+ENTRY(bounds)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_bounds)
+ jmp error_code
+
+ENTRY(invalid_op)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_invalid_op)
+ jmp error_code
+
+ENTRY(coprocessor_segment_overrun)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_coprocessor_segment_overrun)
+ jmp error_code
+
+ENTRY(double_fault)
+ pushl $ SYMBOL_NAME(do_double_fault)
+ jmp error_code
+
+ENTRY(invalid_TSS)
+ pushl $ SYMBOL_NAME(do_invalid_TSS)
+ jmp error_code
+
+ENTRY(segment_not_present)
+ pushl $ SYMBOL_NAME(do_segment_not_present)
+ jmp error_code
+
+ENTRY(stack_segment)
+ pushl $ SYMBOL_NAME(do_stack_segment)
+ jmp error_code
+
+ENTRY(general_protection)
+ pushl $ SYMBOL_NAME(do_general_protection)
+ jmp error_code
+
+ENTRY(alignment_check)
+ pushl $ SYMBOL_NAME(do_alignment_check)
+ jmp error_code
+
+# This handler is special, because it gets an extra value on its stack,
+# which is the linear faulting address.
+#define PAGE_FAULT_STUB(_name1, _name2) \
+ENTRY(_name1) \
+ pushl %ds ; \
+ pushl %eax ; \
+ xorl %eax,%eax ; \
+ pushl %ebp ; \
+ pushl %edi ; \
+ pushl %esi ; \
+ pushl %edx ; \
+ decl %eax /* eax = -1 */ ; \
+ pushl %ecx ; \
+ pushl %ebx ; \
+ GET_CURRENT(%ebx) ; \
+ cld ; \
+ movl %es,%ecx ; \
+ movl ORIG_EAX(%esp), %esi /* get the error code */ ; \
+ movl ES(%esp), %edi /* get the faulting address */ ; \
+ movl %eax, ORIG_EAX(%esp) ; \
+ movl %ecx, ES(%esp) ; \
+ movl %esp,%edx ; \
+ pushl %edi /* push the faulting address */ ; \
+ pushl %esi /* push the error code */ ; \
+ pushl %edx /* push the pt_regs pointer */ ; \
+ movl $(__KERNEL_DS),%edx ; \
+ movl %edx,%ds ; \
+ movl %edx,%es ; \
+ call SYMBOL_NAME(_name2) ; \
+ addl $12,%esp ; \
+ jmp ret_from_exception ;
+PAGE_FAULT_STUB(page_fault, do_page_fault)
+
+ENTRY(machine_check)
+ pushl $0
+ pushl $ SYMBOL_NAME(do_machine_check)
+ jmp error_code
+
+ENTRY(fixup_4gb_segment)
+ pushl $ SYMBOL_NAME(do_fixup_4gb_segment)
+ jmp error_code
+
+.data
+ENTRY(sys_call_table)
+ .long SYMBOL_NAME(sys_ni_syscall) /* 0 - old "setup()" system
call*/
+ .long SYMBOL_NAME(sys_exit)
+ .long SYMBOL_NAME(sys_fork)
+ .long SYMBOL_NAME(sys_read)
+ .long SYMBOL_NAME(sys_write)
+ .long SYMBOL_NAME(sys_open) /* 5 */
+ .long SYMBOL_NAME(sys_close)
+ .long SYMBOL_NAME(sys_waitpid)
+ .long SYMBOL_NAME(sys_creat)
+ .long SYMBOL_NAME(sys_link)
+ .long SYMBOL_NAME(sys_unlink) /* 10 */
+ .long SYMBOL_NAME(sys_execve)
+ .long SYMBOL_NAME(sys_chdir)
+ .long SYMBOL_NAME(sys_time)
+ .long SYMBOL_NAME(sys_mknod)
+ .long SYMBOL_NAME(sys_chmod) /* 15 */
+ .long SYMBOL_NAME(sys_lchown16)
+ .long SYMBOL_NAME(sys_ni_syscall) /* old
break syscall holder */
+ .long SYMBOL_NAME(sys_stat)
+ .long SYMBOL_NAME(sys_lseek)
+ .long SYMBOL_NAME(sys_getpid) /* 20 */
+ .long SYMBOL_NAME(sys_mount)
+ .long SYMBOL_NAME(sys_oldumount)
+ .long SYMBOL_NAME(sys_setuid16)
+ .long SYMBOL_NAME(sys_getuid16)
+ .long SYMBOL_NAME(sys_stime) /* 25 */
+ .long SYMBOL_NAME(sys_ptrace)
+ .long SYMBOL_NAME(sys_alarm)
+ .long SYMBOL_NAME(sys_fstat)
+ .long SYMBOL_NAME(sys_pause)
+ .long SYMBOL_NAME(sys_utime) /* 30 */
+ .long SYMBOL_NAME(sys_ni_syscall) /* old
stty syscall holder */
+ .long SYMBOL_NAME(sys_ni_syscall) /* old
gtty syscall holder */
+ .long SYMBOL_NAME(sys_access)
+ .long SYMBOL_NAME(sys_nice)
+ .long SYMBOL_NAME(sys_ni_syscall) /* 35 */ /* old
ftime syscall holder */
+ .long SYMBOL_NAME(sys_sync)
+ .long SYMBOL_NAME(sys_kill)
+ .long SYMBOL_NAME(sys_rename)
+ .long SYMBOL_NAME(sys_mkdir)
+ .long SYMBOL_NAME(sys_rmdir) /* 40 */
+ .long SYMBOL_NAME(sys_dup)
+ .long SYMBOL_NAME(sys_pipe)
+ .long SYMBOL_NAME(sys_times)
+ .long SYMBOL_NAME(sys_ni_syscall) /* old
prof syscall holder */
+ .long SYMBOL_NAME(sys_brk) /* 45 */
+ .long SYMBOL_NAME(sys_setgid16)
+ .long SYMBOL_NAME(sys_getgid16)
+ .long SYMBOL_NAME(sys_signal)
+ .long SYMBOL_NAME(sys_geteuid16)
+ .long SYMBOL_NAME(sys_getegid16) /* 50 */
+ .long SYMBOL_NAME(sys_acct)
+ .long SYMBOL_NAME(sys_umount) /*
recycled never used phys() */
+ .long SYMBOL_NAME(sys_ni_syscall) /* old
lock syscall holder */
+ .long SYMBOL_NAME(sys_ioctl)
+ .long SYMBOL_NAME(sys_fcntl) /* 55 */
+ .long SYMBOL_NAME(sys_ni_syscall) /* old
mpx syscall holder */
+ .long SYMBOL_NAME(sys_setpgid)
+ .long SYMBOL_NAME(sys_ni_syscall) /* old
ulimit syscall holder */
+ .long SYMBOL_NAME(sys_olduname)
+ .long SYMBOL_NAME(sys_umask) /* 60 */
+ .long SYMBOL_NAME(sys_chroot)
+ .long SYMBOL_NAME(sys_ustat)
+ .long SYMBOL_NAME(sys_dup2)
+ .long SYMBOL_NAME(sys_getppid)
+ .long SYMBOL_NAME(sys_getpgrp) /* 65 */
+ .long SYMBOL_NAME(sys_setsid)
+ .long SYMBOL_NAME(sys_sigaction)
+ .long SYMBOL_NAME(sys_sgetmask)
+ .long SYMBOL_NAME(sys_ssetmask)
+ .long SYMBOL_NAME(sys_setreuid16) /* 70 */
+ .long SYMBOL_NAME(sys_setregid16)
+ .long SYMBOL_NAME(sys_sigsuspend)
+ .long SYMBOL_NAME(sys_sigpending)
+ .long SYMBOL_NAME(sys_sethostname)
+ .long SYMBOL_NAME(sys_setrlimit) /* 75 */
+ .long SYMBOL_NAME(sys_old_getrlimit)
+ .long SYMBOL_NAME(sys_getrusage)
+ .long SYMBOL_NAME(sys_gettimeofday)
+ .long SYMBOL_NAME(sys_settimeofday)
+ .long SYMBOL_NAME(sys_getgroups16) /* 80 */
+ .long SYMBOL_NAME(sys_setgroups16)
+ .long SYMBOL_NAME(old_select)
+ .long SYMBOL_NAME(sys_symlink)
+ .long SYMBOL_NAME(sys_lstat)
+ .long SYMBOL_NAME(sys_readlink) /* 85 */
+ .long SYMBOL_NAME(sys_uselib)
+ .long SYMBOL_NAME(sys_swapon)
+ .long SYMBOL_NAME(sys_reboot)
+ .long SYMBOL_NAME(old_readdir)
+ .long SYMBOL_NAME(old_mmap) /* 90 */
+ .long SYMBOL_NAME(sys_munmap)
+ .long SYMBOL_NAME(sys_truncate)
+ .long SYMBOL_NAME(sys_ftruncate)
+ .long SYMBOL_NAME(sys_fchmod)
+ .long SYMBOL_NAME(sys_fchown16) /* 95 */
+ .long SYMBOL_NAME(sys_getpriority)
+ .long SYMBOL_NAME(sys_setpriority)
+ .long SYMBOL_NAME(sys_ni_syscall) /* old
profil syscall holder */
+ .long SYMBOL_NAME(sys_statfs)
+ .long SYMBOL_NAME(sys_fstatfs) /* 100 */
+ .long SYMBOL_NAME(sys_ioperm)
+ .long SYMBOL_NAME(sys_socketcall)
+ .long SYMBOL_NAME(sys_syslog)
+ .long SYMBOL_NAME(sys_setitimer)
+ .long SYMBOL_NAME(sys_getitimer) /* 105 */
+ .long SYMBOL_NAME(sys_newstat)
+ .long SYMBOL_NAME(sys_newlstat)
+ .long SYMBOL_NAME(sys_newfstat)
+ .long SYMBOL_NAME(sys_uname)
+ .long SYMBOL_NAME(sys_iopl) /* 110 */
+ .long SYMBOL_NAME(sys_vhangup)
+ .long SYMBOL_NAME(sys_ni_syscall) /* old "idle" system call */
+ .long SYMBOL_NAME(sys_ni_syscall) /* was VM86 */
+ .long SYMBOL_NAME(sys_wait4)
+ .long SYMBOL_NAME(sys_swapoff) /* 115 */
+ .long SYMBOL_NAME(sys_sysinfo)
+ .long SYMBOL_NAME(sys_ipc)
+ .long SYMBOL_NAME(sys_fsync)
+ .long SYMBOL_NAME(sys_sigreturn)
+ .long SYMBOL_NAME(sys_clone) /* 120 */
+ .long SYMBOL_NAME(sys_setdomainname)
+ .long SYMBOL_NAME(sys_newuname)
+ .long SYMBOL_NAME(sys_modify_ldt)
+ .long SYMBOL_NAME(sys_adjtimex)
+ .long SYMBOL_NAME(sys_mprotect) /* 125 */
+ .long SYMBOL_NAME(sys_sigprocmask)
+ .long SYMBOL_NAME(sys_create_module)
+ .long SYMBOL_NAME(sys_init_module)
+ .long SYMBOL_NAME(sys_delete_module)
+ .long SYMBOL_NAME(sys_get_kernel_syms) /* 130 */
+ .long SYMBOL_NAME(sys_quotactl)
+ .long SYMBOL_NAME(sys_getpgid)
+ .long SYMBOL_NAME(sys_fchdir)
+ .long SYMBOL_NAME(sys_bdflush)
+ .long SYMBOL_NAME(sys_sysfs) /* 135 */
+ .long SYMBOL_NAME(sys_personality)
+ .long SYMBOL_NAME(sys_ni_syscall) /* for afs_syscall */
+ .long SYMBOL_NAME(sys_setfsuid16)
+ .long SYMBOL_NAME(sys_setfsgid16)
+ .long SYMBOL_NAME(sys_llseek) /* 140 */
+ .long SYMBOL_NAME(sys_getdents)
+ .long SYMBOL_NAME(sys_select)
+ .long SYMBOL_NAME(sys_flock)
+ .long SYMBOL_NAME(sys_msync)
+ .long SYMBOL_NAME(sys_readv) /* 145 */
+ .long SYMBOL_NAME(sys_writev)
+ .long SYMBOL_NAME(sys_getsid)
+ .long SYMBOL_NAME(sys_fdatasync)
+ .long SYMBOL_NAME(sys_sysctl)
+ .long SYMBOL_NAME(sys_mlock) /* 150 */
+ .long SYMBOL_NAME(sys_munlock)
+ .long SYMBOL_NAME(sys_mlockall)
+ .long SYMBOL_NAME(sys_munlockall)
+ .long SYMBOL_NAME(sys_sched_setparam)
+ .long SYMBOL_NAME(sys_sched_getparam) /* 155 */
+ .long SYMBOL_NAME(sys_sched_setscheduler)
+ .long SYMBOL_NAME(sys_sched_getscheduler)
+ .long SYMBOL_NAME(sys_sched_yield)
+ .long SYMBOL_NAME(sys_sched_get_priority_max)
+ .long SYMBOL_NAME(sys_sched_get_priority_min) /* 160 */
+ .long SYMBOL_NAME(sys_sched_rr_get_interval)
+ .long SYMBOL_NAME(sys_nanosleep)
+ .long SYMBOL_NAME(sys_mremap)
+ .long SYMBOL_NAME(sys_setresuid16)
+ .long SYMBOL_NAME(sys_getresuid16) /* 165 */
+ .long SYMBOL_NAME(sys_ni_syscall) /* was VM86 */
+ .long SYMBOL_NAME(sys_query_module)
+ .long SYMBOL_NAME(sys_poll)
+ .long SYMBOL_NAME(sys_nfsservctl)
+ .long SYMBOL_NAME(sys_setresgid16) /* 170 */
+ .long SYMBOL_NAME(sys_getresgid16)
+ .long SYMBOL_NAME(sys_prctl)
+ .long SYMBOL_NAME(sys_rt_sigreturn)
+ .long SYMBOL_NAME(sys_rt_sigaction)
+ .long SYMBOL_NAME(sys_rt_sigprocmask) /* 175 */
+ .long SYMBOL_NAME(sys_rt_sigpending)
+ .long SYMBOL_NAME(sys_rt_sigtimedwait)
+ .long SYMBOL_NAME(sys_rt_sigqueueinfo)
+ .long SYMBOL_NAME(sys_rt_sigsuspend)
+ .long SYMBOL_NAME(sys_pread) /* 180 */
+ .long SYMBOL_NAME(sys_pwrite)
+ .long SYMBOL_NAME(sys_chown16)
+ .long SYMBOL_NAME(sys_getcwd)
+ .long SYMBOL_NAME(sys_capget)
+ .long SYMBOL_NAME(sys_capset) /* 185 */
+ .long SYMBOL_NAME(sys_sigaltstack)
+ .long SYMBOL_NAME(sys_sendfile)
+ .long SYMBOL_NAME(sys_ni_syscall) /* streams1 */
+ .long SYMBOL_NAME(sys_ni_syscall) /* streams2 */
+ .long SYMBOL_NAME(sys_vfork) /* 190 */
+ .long SYMBOL_NAME(sys_getrlimit)
+ .long SYMBOL_NAME(sys_mmap2)
+ .long SYMBOL_NAME(sys_truncate64)
+ .long SYMBOL_NAME(sys_ftruncate64)
+ .long SYMBOL_NAME(sys_stat64) /* 195 */
+ .long SYMBOL_NAME(sys_lstat64)
+ .long SYMBOL_NAME(sys_fstat64)
+ .long SYMBOL_NAME(sys_lchown)
+ .long SYMBOL_NAME(sys_getuid)
+ .long SYMBOL_NAME(sys_getgid) /* 200 */
+ .long SYMBOL_NAME(sys_geteuid)
+ .long SYMBOL_NAME(sys_getegid)
+ .long SYMBOL_NAME(sys_setreuid)
+ .long SYMBOL_NAME(sys_setregid)
+ .long SYMBOL_NAME(sys_getgroups) /* 205 */
+ .long SYMBOL_NAME(sys_setgroups)
+ .long SYMBOL_NAME(sys_fchown)
+ .long SYMBOL_NAME(sys_setresuid)
+ .long SYMBOL_NAME(sys_getresuid)
+ .long SYMBOL_NAME(sys_setresgid) /* 210 */
+ .long SYMBOL_NAME(sys_getresgid)
+ .long SYMBOL_NAME(sys_chown)
+ .long SYMBOL_NAME(sys_setuid)
+ .long SYMBOL_NAME(sys_setgid)
+ .long SYMBOL_NAME(sys_setfsuid) /* 215 */
+ .long SYMBOL_NAME(sys_setfsgid)
+ .long SYMBOL_NAME(sys_pivot_root)
+ .long SYMBOL_NAME(sys_mincore)
+ .long SYMBOL_NAME(sys_madvise)
+ .long SYMBOL_NAME(sys_getdents64) /* 220 */
+ .long SYMBOL_NAME(sys_fcntl64)
+ .long SYMBOL_NAME(sys_ni_syscall) /* reserved for TUX */
+ .long SYMBOL_NAME(sys_ni_syscall) /* Reserved for Security */
+ .long SYMBOL_NAME(sys_gettid)
+ .long SYMBOL_NAME(sys_readahead) /* 225 */
+ .long SYMBOL_NAME(sys_setxattr)
+ .long SYMBOL_NAME(sys_lsetxattr)
+ .long SYMBOL_NAME(sys_fsetxattr)
+ .long SYMBOL_NAME(sys_getxattr)
+ .long SYMBOL_NAME(sys_lgetxattr) /* 230 */
+ .long SYMBOL_NAME(sys_fgetxattr)
+ .long SYMBOL_NAME(sys_listxattr)
+ .long SYMBOL_NAME(sys_llistxattr)
+ .long SYMBOL_NAME(sys_flistxattr)
+ .long SYMBOL_NAME(sys_removexattr) /* 235 */
+ .long SYMBOL_NAME(sys_lremovexattr)
+ .long SYMBOL_NAME(sys_fremovexattr)
+ .long SYMBOL_NAME(sys_tkill)
+ .long SYMBOL_NAME(sys_sendfile64)
+ .long SYMBOL_NAME(sys_ni_syscall) /* 240 reserved for futex */
+ .long SYMBOL_NAME(sys_ni_syscall) /* reserved for
sched_setaffinity */
+ .long SYMBOL_NAME(sys_ni_syscall) /* reserved for
sched_getaffinity */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_set_thread_area */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_get_thread_area */
+ .long SYMBOL_NAME(sys_ni_syscall) /* 245 sys_io_setup */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_io_destroy */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_io_getevents */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_io_submit */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_io_cancel */
+ .long SYMBOL_NAME(sys_ni_syscall) /* 250 sys_alloc_hugepages */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_free_hugepages */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_exit_group */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_lookup_dcookie */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_epoll_create */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_epoll_ctl 255 */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_epoll_wait */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_remap_file_pages */
+ .long SYMBOL_NAME(sys_ni_syscall) /* sys_set_tid_address */
+
+ .rept NR_syscalls-(.-sys_call_table)/4
+ .long SYMBOL_NAME(sys_ni_syscall)
+ .endr
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/e820.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/e820.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,533 @@
+/*
+ * Handle the memory map.
+ * The functions here do the job until bootmem takes over.
+ * $Id: e820.c,v 1.4 2002/09/19 19:25:32 ak Exp $
+ */
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/ioport.h>
+#include <linux/string.h>
+#include <asm/page.h>
+#include <asm/e820.h>
+#include <asm/proto.h>
+#include <asm/bootsetup.h>
+
+/*
+ * PFN of last memory page.
+ */
+unsigned long end_pfn;
+unsigned long end_user_pfn = MAXMEM>>PAGE_SHIFT;
+unsigned long end_pfn_map;
+
+/*
+ * Add a memory region to the kernel e820 map.
+ */
+void __init add_memory_region(unsigned long start, unsigned long size, int
type)
+{
+ int x = e820.nr_map;
+
+ if (x == E820MAX) {
+ printk(KERN_ERR "Ooops! Too many entries in the memory map!\n");
+ return;
+ }
+
+ e820.map[x].addr = start;
+ e820.map[x].size = size;
+ e820.map[x].type = type;
+ e820.nr_map++;
+}
+
+#if 0
+extern char _end[];
+
+/*
+ * end_pfn only includes RAM, while end_pfn_map includes all e820 entries.
+ * The direct mapping extends to end_pfn_map, so that we can directly access
+ * apertures, ACPI and other tables without having to play with fixmaps.
+ */
+
+/*
+ * Last pfn which the user wants to use.
+ */
+
+extern struct resource code_resource, data_resource;
+
+/* Check for some hardcoded bad areas that early boot is not allowed to touch
*/
+static inline int bad_addr(unsigned long *addrp, unsigned long size)
+{
+ unsigned long addr = *addrp, last = addr + size;
+
+ /* various gunk below that needed for SMP startup */
+ if (addr < 0x8000) {
+ *addrp = 0x8000;
+ return 1;
+ }
+
+ /* direct mapping tables of the kernel */
+ if (last >= table_start<<PAGE_SHIFT && addr < table_end<<PAGE_SHIFT) {
+ *addrp = table_end << PAGE_SHIFT;
+ return 1;
+ }
+
+ /* initrd */
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (LOADER_TYPE && INITRD_START && last >= INITRD_START &&
+ addr < INITRD_START+INITRD_SIZE) {
+ *addrp = INITRD_START + INITRD_SIZE;
+ return 1;
+ }
+#endif
+ /* kernel code + 640k memory hole (later should not be needed, but
+ be paranoid for now) */
+ if (last >= 640*1024 && addr < __pa_symbol(&_end)) {
+ *addrp = __pa_symbol(&_end);
+ return 1;
+ }
+ /* XXX ramdisk image here? */
+ return 0;
+}
+
+int __init e820_mapped(unsigned long start, unsigned long end, unsigned type)
+{
+ int i;
+ for (i = 0; i < e820.nr_map; i++) {
+ struct e820entry *ei = &e820.map[i];
+ if (type && ei->type != type)
+ continue;
+ if (ei->addr >= end || ei->addr + ei->size < start)
+ continue;
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * Find a free area in a specific range.
+ */
+unsigned long __init find_e820_area(unsigned long start, unsigned long end,
unsigned size)
+{
+ int i;
+ for (i = 0; i < e820.nr_map; i++) {
+ struct e820entry *ei = &e820.map[i];
+ unsigned long addr = ei->addr, last;
+ if (ei->type != E820_RAM)
+ continue;
+ if (addr < start)
+ addr = start;
+ if (addr > ei->addr + ei->size)
+ continue;
+ while (bad_addr(&addr, size) && addr+size < ei->addr + ei->size)
+ ;
+ last = addr + size;
+ if (last > ei->addr + ei->size)
+ continue;
+ if (last > end)
+ continue;
+ return addr;
+ }
+ return -1UL;
+}
+
+/*
+ * Free bootmem based on the e820 table for a node.
+ */
+void __init e820_bootmem_free(pg_data_t *pgdat, unsigned long start,unsigned
long end)
+{
+ int i;
+ for (i = 0; i < e820.nr_map; i++) {
+ struct e820entry *ei = &e820.map[i];
+ unsigned long last, addr;
+
+ if (ei->type != E820_RAM ||
+ ei->addr+ei->size <= start ||
+ ei->addr > end)
+ continue;
+
+ addr = round_up(ei->addr, PAGE_SIZE);
+ if (addr < start)
+ addr = start;
+
+ last = round_down(ei->addr + ei->size, PAGE_SIZE);
+ if (last >= end)
+ last = end;
+
+ if (last > addr && last-addr >= PAGE_SIZE)
+ free_bootmem_node(pgdat, addr, last-addr);
+ }
+}
+
+/*
+ * Find the highest page frame number we have available
+ */
+unsigned long __init e820_end_of_ram(void)
+{
+ int i;
+ unsigned long end_pfn = 0;
+
+ for (i = 0; i < e820.nr_map; i++) {
+ struct e820entry *ei = &e820.map[i];
+ unsigned long start, end;
+
+ start = round_up(ei->addr, PAGE_SIZE);
+ end = round_down(ei->addr + ei->size, PAGE_SIZE);
+ if (start >= end)
+ continue;
+ if (ei->type == E820_RAM) {
+ if (end > end_pfn<<PAGE_SHIFT)
+ end_pfn = end>>PAGE_SHIFT;
+ } else {
+ if (end > end_pfn_map<<PAGE_SHIFT)
+ end_pfn_map = end>>PAGE_SHIFT;
+ }
+ }
+
+ if (end_pfn > end_pfn_map)
+ end_pfn_map = end_pfn;
+ if (end_pfn_map > MAXMEM>>PAGE_SHIFT)
+ end_pfn_map = MAXMEM>>PAGE_SHIFT;
+ if (end_pfn > end_user_pfn)
+ end_pfn = end_user_pfn;
+ if (end_pfn > end_pfn_map)
+ end_pfn = end_pfn_map;
+
+ return end_pfn;
+}
+
+/*
+ * Mark e820 reserved areas as busy for the resource manager.
+ */
+void __init e820_reserve_resources(void)
+{
+ int i;
+ for (i = 0; i < e820.nr_map; i++) {
+ struct resource *res;
+ if (e820.map[i].addr + e820.map[i].size > 0x100000000ULL)
+ continue;
+ res = alloc_bootmem_low(sizeof(struct resource));
+ switch (e820.map[i].type) {
+ case E820_RAM: res->name = "System RAM"; break;
+ case E820_ACPI: res->name = "ACPI Tables"; break;
+ case E820_NVS: res->name = "ACPI Non-volatile Storage"; break;
+ default: res->name = "reserved";
+ }
+ res->start = e820.map[i].addr;
+ res->end = res->start + e820.map[i].size - 1;
+ res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+ request_resource(&iomem_resource, res);
+ if (e820.map[i].type == E820_RAM) {
+ /*
+ * We don't know which RAM region contains kernel data,
+ * so we try it repeatedly and let the resource manager
+ * test it.
+ */
+ request_resource(res, &code_resource);
+ request_resource(res, &data_resource);
+ }
+ }
+}
+
+
+void __init e820_print_map(char *who)
+{
+ int i;
+
+ for (i = 0; i < e820.nr_map; i++) {
+ printk(" %s: %016Lx - %016Lx ", who,
+ (unsigned long long) e820.map[i].addr,
+ (unsigned long long) (e820.map[i].addr +
e820.map[i].size));
+ switch (e820.map[i].type) {
+ case E820_RAM: printk("(usable)\n");
+ break;
+ case E820_RESERVED:
+ printk("(reserved)\n");
+ break;
+ case E820_ACPI:
+ printk("(ACPI data)\n");
+ break;
+ case E820_NVS:
+ printk("(ACPI NVS)\n");
+ break;
+ default: printk("type %u\n", e820.map[i].type);
+ break;
+ }
+ }
+}
+
+/*
+ * Sanitize the BIOS e820 map.
+ *
+ * Some e820 responses include overlapping entries. The following
+ * replaces the original e820 map with a new one, removing overlaps.
+ *
+ */
+static int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map)
+{
+ struct change_member {
+ struct e820entry *pbios; /* pointer to original bios entry */
+ unsigned long long addr; /* address for this change point */
+ };
+ static struct change_member change_point_list[2*E820MAX] __initdata;
+ static struct change_member *change_point[2*E820MAX] __initdata;
+ static struct e820entry *overlap_list[E820MAX] __initdata;
+ static struct e820entry new_bios[E820MAX] __initdata;
+ struct change_member *change_tmp;
+ unsigned long current_type, last_type;
+ unsigned long long last_addr;
+ int chgidx, still_changing;
+ int overlap_entries;
+ int new_bios_entry;
+ int old_nr, new_nr;
+ int i;
+
+ /*
+ Visually we're performing the following (1,2,3,4 = memory
types)...
+
+ Sample memory map (w/overlaps):
+ ____22__________________
+ ______________________4_
+ ____1111________________
+ _44_____________________
+ 11111111________________
+ ____________________33__
+ ___________44___________
+ __________33333_________
+ ______________22________
+ ___________________2222_
+ _________111111111______
+ _____________________11_
+ _________________4______
+
+ Sanitized equivalent (no overlap):
+ 1_______________________
+ _44_____________________
+ ___1____________________
+ ____22__________________
+ ______11________________
+ _________1______________
+ __________3_____________
+ ___________44___________
+ _____________33_________
+ _______________2________
+ ________________1_______
+ _________________4______
+ ___________________2____
+ ____________________33__
+ ______________________4_
+ */
+
+ /* if there's only one memory region, don't bother */
+ if (*pnr_map < 2)
+ return -1;
+
+ old_nr = *pnr_map;
+
+ /* bail out if we find any unreasonable addresses in bios map */
+ for (i=0; i<old_nr; i++)
+ if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr)
+ return -1;
+
+ /* create pointers for initial change-point information (for sorting) */
+ for (i=0; i < 2*old_nr; i++)
+ change_point[i] = &change_point_list[i];
+
+ /* record all known change-points (starting and ending addresses) */
+ chgidx = 0;
+ for (i=0; i < old_nr; i++) {
+ change_point[chgidx]->addr = biosmap[i].addr;
+ change_point[chgidx++]->pbios = &biosmap[i];
+ change_point[chgidx]->addr = biosmap[i].addr + biosmap[i].size;
+ change_point[chgidx++]->pbios = &biosmap[i];
+ }
+
+ /* sort change-point list by memory addresses (low -> high) */
+ still_changing = 1;
+ while (still_changing) {
+ still_changing = 0;
+ for (i=1; i < 2*old_nr; i++) {
+ /* if <current_addr> > <last_addr>, swap */
+ /* or, if current=<start_addr> & last=<end_addr>, swap
*/
+ if ((change_point[i]->addr < change_point[i-1]->addr) ||
+ ((change_point[i]->addr ==
change_point[i-1]->addr) &&
+ (change_point[i]->addr ==
change_point[i]->pbios->addr) &&
+ (change_point[i-1]->addr !=
change_point[i-1]->pbios->addr))
+ )
+ {
+ change_tmp = change_point[i];
+ change_point[i] = change_point[i-1];
+ change_point[i-1] = change_tmp;
+ still_changing=1;
+ }
+ }
+ }
+
+ /* create a new bios memory map, removing overlaps */
+ overlap_entries=0; /* number of entries in the overlap table */
+ new_bios_entry=0; /* index for creating new bios map entries */
+ last_type = 0; /* start with undefined memory type */
+ last_addr = 0; /* start with 0 as last starting address */
+ /* loop through change-points, determining affect on the new bios map */
+ for (chgidx=0; chgidx < 2*old_nr; chgidx++)
+ {
+ /* keep track of all overlapping bios entries */
+ if (change_point[chgidx]->addr ==
change_point[chgidx]->pbios->addr)
+ {
+ /* add map entry to overlap list (> 1 entry implies an
overlap) */
+
overlap_list[overlap_entries++]=change_point[chgidx]->pbios;
+ }
+ else
+ {
+ /* remove entry from list (order independent, so swap
with last) */
+ for (i=0; i<overlap_entries; i++)
+ {
+ if (overlap_list[i] ==
change_point[chgidx]->pbios)
+ overlap_list[i] =
overlap_list[overlap_entries-1];
+ }
+ overlap_entries--;
+ }
+ /* if there are overlapping entries, decide which "type" to use
*/
+ /* (larger value takes precedence -- 1=usable,
2,3,4,4+=unusable) */
+ current_type = 0;
+ for (i=0; i<overlap_entries; i++)
+ if (overlap_list[i]->type > current_type)
+ current_type = overlap_list[i]->type;
+ /* continue building up new bios map based on this information
*/
+ if (current_type != last_type) {
+ if (last_type != 0) {
+ new_bios[new_bios_entry].size =
+ change_point[chgidx]->addr - last_addr;
+ /* move forward only if the new size was
non-zero */
+ if (new_bios[new_bios_entry].size != 0)
+ if (++new_bios_entry >= E820MAX)
+ break; /* no more space left
for new bios entries */
+ }
+ if (current_type != 0) {
+ new_bios[new_bios_entry].addr =
change_point[chgidx]->addr;
+ new_bios[new_bios_entry].type = current_type;
+ last_addr=change_point[chgidx]->addr;
+ }
+ last_type = current_type;
+ }
+ }
+ new_nr = new_bios_entry; /* retain count for new bios entries */
+
+ /* copy new bios mapping into original location */
+ memcpy(biosmap, new_bios, new_nr*sizeof(struct e820entry));
+ *pnr_map = new_nr;
+
+ return 0;
+}
+
+/*
+ * Copy the BIOS e820 map into a safe place.
+ *
+ * Sanity-check it while we're at it..
+ *
+ * If we're lucky and live on a modern system, the setup code
+ * will have given us a memory map that we can use to properly
+ * set up memory. If we aren't, we'll fake a memory map.
+ *
+ * We check to see that the memory map contains at least 2 elements
+ * before we'll use it, because the detection code in setup.S may
+ * not be perfect and most every PC known to man has two memory
+ * regions: one from 0 to 640k, and one from 1mb up. (The IBM
+ * thinkpad 560x, for example, does not cooperate with the memory
+ * detection code.)
+ */
+static int __init copy_e820_map(struct e820entry * biosmap, int nr_map)
+{
+ /* Only one memory region (or negative)? Ignore it */
+ if (nr_map < 2)
+ return -1;
+
+ do {
+ unsigned long start = biosmap->addr;
+ unsigned long size = biosmap->size;
+ unsigned long end = start + size;
+ unsigned long type = biosmap->type;
+
+ /* Overflow in 64 bits? Ignore the memory map. */
+ if (start > end)
+ return -1;
+
+ /*
+ * Some BIOSes claim RAM in the 640k - 1M region.
+ * Not right. Fix it up.
+ *
+ * This should be removed on Hammer which is supposed to not
+ * have non e820 covered ISA mappings there, but I had some
strange
+ * problems so it stays for now. -AK
+ */
+ if (type == E820_RAM) {
+ if (start < 0x100000ULL && end > 0xA0000ULL) {
+ if (start < 0xA0000ULL)
+ add_memory_region(start,
0xA0000ULL-start, type);
+ if (end <= 0x100000ULL)
+ continue;
+ start = 0x100000ULL;
+ size = end - start;
+ }
+ }
+
+ add_memory_region(start, size, type);
+ } while (biosmap++,--nr_map);
+ return 0;
+}
+
+void __init setup_memory_region(void)
+{
+ char *who = "BIOS-e820";
+
+ /*
+ * Try to copy the BIOS-supplied E820-map.
+ *
+ * Otherwise fake a memory map; one section from 0k->640k,
+ * the next section from 1mb->appropriate_mem_k
+ */
+ sanitize_e820_map(E820_MAP, &E820_MAP_NR);
+ if (copy_e820_map(E820_MAP, E820_MAP_NR) < 0) {
+ unsigned long mem_size;
+
+ /* compare results from other methods and take the greater */
+ if (ALT_MEM_K < EXT_MEM_K) {
+ mem_size = EXT_MEM_K;
+ who = "BIOS-88";
+ } else {
+ mem_size = ALT_MEM_K;
+ who = "BIOS-e801";
+ }
+
+ e820.nr_map = 0;
+ add_memory_region(0, LOWMEMSIZE(), E820_RAM);
+ add_memory_region(HIGH_MEMORY, mem_size << 10, E820_RAM);
+ }
+ printk(KERN_INFO "BIOS-provided physical RAM map:\n");
+ e820_print_map(who);
+}
+#endif
+
+extern unsigned long xen_override_max_pfn;
+
+void __init parse_memopt(char *p, char **from)
+{
+ /*
+ * mem=XXX[kKmM] limits kernel memory to XXX+1MB
+ *
+ * It would be more logical to count from 0 instead of from
+ * HIGH_MEMORY, but we keep that for now for i386 compatibility.
+ *
+ * No support for custom mapping like i386. The reason is
+ * that we need to read the e820 map anyways to handle the
+ * ACPI mappings in the direct map. Also on x86-64 there
+ * should be always a good e820 map. This is only an upper
+ * limit, you cannot force usage of memory not in e820.
+ *
+ * -AK
+ */
+ end_user_pfn = memparse(p, from) + HIGH_MEMORY;
+ end_user_pfn >>= PAGE_SHIFT;
+ xen_override_max_pfn = (unsigned long) end_user_pfn;
+}
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/hypervisor.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/hypervisor.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,187 @@
+/******************************************************************************
+ * hypervisor.h
+ *
+ * Linux-specific hypervisor handling.
+ *
+ * Copyright (c) 2002-2004, K A Fraser
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __HYPERVISOR_H__
+#define __HYPERVISOR_H__
+
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/version.h>
+#include <asm-xen/xen-public/xen.h>
+#include <asm-xen/xen-public/dom0_ops.h>
+#include <asm-xen/xen-public/io/domain_controller.h>
+#include <asm/ptrace.h>
+#include <asm/page.h>
+#if defined(__i386__)
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+#include <asm-generic/pgtable-nopmd.h>
+#endif
+#endif
+
+/* arch/xen/i386/kernel/setup.c */
+union xen_start_info_union
+{
+ start_info_t xen_start_info;
+ char padding[2048];
+};
+extern union xen_start_info_union xen_start_info_union;
+#define xen_start_info (xen_start_info_union.xen_start_info)
+
+/* arch/xen/kernel/evtchn.c */
+/* Force a proper event-channel callback from Xen. */
+void force_evtchn_callback(void);
+
+/* arch/xen/kernel/process.c */
+void xen_cpu_idle (void);
+
+/* arch/xen/i386/kernel/hypervisor.c */
+void do_hypervisor_callback(struct pt_regs *regs);
+
+/* arch/xen/i386/kernel/head.S */
+void lgdt_finish(void);
+
+/* arch/xen/i386/mm/hypervisor.c */
+/*
+ * NB. ptr values should be PHYSICAL, not MACHINE. 'vals' should be already
+ * be MACHINE addresses.
+ */
+
+void xen_pt_switch(unsigned long ptr);
+void xen_new_user_pt(unsigned long ptr); /* x86_64 only */
+void xen_load_gs(unsigned int selector); /* x86_64 only */
+void xen_tlb_flush(void);
+void xen_invlpg(unsigned long ptr);
+
+#ifndef CONFIG_XEN_SHADOW_MODE
+void xen_l1_entry_update(pte_t *ptr, unsigned long val);
+void xen_l2_entry_update(pmd_t *ptr, pmd_t val);
+#ifdef __x86_64__
+void xen_l3_entry_update(pud_t *ptr, pud_t val); /* x86_64 only */
+#endif
+void xen_l4_entry_update(pgd_t *ptr, pgd_t val); /* x86_64 only */
+void xen_pgd_pin(unsigned long ptr);
+void xen_pgd_unpin(unsigned long ptr);
+void xen_pud_pin(unsigned long ptr); /* x86_64 only */
+void xen_pud_unpin(unsigned long ptr); /* x86_64 only */
+void xen_pmd_pin(unsigned long ptr); /* x86_64 only */
+void xen_pmd_unpin(unsigned long ptr); /* x86_64 only */
+void xen_pte_pin(unsigned long ptr);
+void xen_pte_unpin(unsigned long ptr);
+#else
+#define xen_l1_entry_update(_p, _v) set_pte((_p), (pte_t){(_v)})
+#define xen_l2_entry_update(_p, _v) set_pgd((_p), (pgd_t){(_v)})
+#define xen_pgd_pin(_p) ((void)0)
+#define xen_pgd_unpin(_p) ((void)0)
+#define xen_pte_pin(_p) ((void)0)
+#define xen_pte_unpin(_p) ((void)0)
+#endif
+
+void xen_set_ldt(unsigned long ptr, unsigned long bytes);
+void xen_machphys_update(unsigned long mfn, unsigned long pfn);
+
+#ifdef CONFIG_SMP
+#include <linux/cpumask.h>
+void xen_tlb_flush_all(void);
+void xen_invlpg_all(unsigned long ptr);
+void xen_tlb_flush_mask(cpumask_t *mask);
+void xen_invlpg_mask(cpumask_t *mask, unsigned long ptr);
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
+/*
+** XXX SMH: 2.4 doesn't have percpu.h (or support SMP guests) so just
+** include sufficient #defines to allow the below to build.
+*/
+#define DEFINE_PER_CPU(type, name) \
+ __typeof__(type) per_cpu__##name
+
+#define per_cpu(var, cpu) (*((void)cpu, &per_cpu__##var))
+#define __get_cpu_var(var) per_cpu__##var
+#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name
+
+#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
+#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
+#endif /* linux < 2.6.0 */
+
+void xen_contig_memory(unsigned long vstart, unsigned int order);
+
+#ifdef CONFIG_XEN_PHYSDEV_ACCESS
+/* Allocate a contiguous empty region of low memory. Return virtual start. */
+unsigned long allocate_empty_lowmem_region(unsigned long pages);
+#endif
+
+#include <asm/hypercall.h>
+
+static inline void
+MULTI_update_va_mapping(
+ multicall_entry_t *mcl, unsigned long va,
+ pte_t new_val, unsigned long flags)
+{
+ mcl->op = __HYPERVISOR_update_va_mapping;
+ mcl->args[0] = va;
+#if defined(CONFIG_X86_64)
+ mcl->args[1] = new_val.pte;
+ mcl->args[2] = flags;
+#elif defined(CONFIG_X86_PAE)
+ mcl->args[1] = new_val.pte_low;
+ mcl->args[2] = new_val.pte_high;
+ mcl->args[3] = flags;
+#else
+ mcl->args[1] = new_val.pte_low;
+ mcl->args[2] = 0;
+ mcl->args[3] = flags;
+#endif
+}
+
+static inline void
+MULTI_update_va_mapping_otherdomain(
+ multicall_entry_t *mcl, unsigned long va,
+ pte_t new_val, unsigned long flags, domid_t domid)
+{
+ mcl->op = __HYPERVISOR_update_va_mapping_otherdomain;
+ mcl->args[0] = va;
+#if defined(CONFIG_X86_64)
+ mcl->args[1] = new_val.pte;
+ mcl->args[2] = flags;
+ mcl->args[3] = domid;
+#elif defined(CONFIG_X86_PAE)
+ mcl->args[1] = new_val.pte_low;
+ mcl->args[2] = new_val.pte_high;
+ mcl->args[3] = flags;
+ mcl->args[4] = domid;
+#else
+ mcl->args[1] = new_val.pte_low;
+ mcl->args[2] = 0;
+ mcl->args[3] = flags;
+ mcl->args[4] = domid;
+#endif
+}
+
+#endif /* __HYPERVISOR_H__ */
diff -r 35b74976f598 -r a83ac0806d6b linux-2.6.11-xen-sparse/mm/page_alloc.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/mm/page_alloc.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,2157 @@
+/*
+ * linux/mm/page_alloc.c
+ *
+ * Manages the free list, the system allocates free pages here.
+ * Note that kmalloc() lives in slab.c
+ *
+ * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
+ * Swap reorganised 29.12.95, Stephen Tweedie
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ * Reshaped it to be a zoned allocator, Ingo Molnar, Red Hat, 1999
+ * Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
+ * Zone balancing, Kanoj Sarcar, SGI, Jan 2000
+ * Per cpu hot/cold page lists, bulk allocation, Martin J. Bligh, Sept 2002
+ * (lots of bits borrowed from Ingo Molnar & Andrew Morton)
+ */
+
+#include <linux/config.h>
+#include <linux/stddef.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/interrupt.h>
+#include <linux/pagemap.h>
+#include <linux/bootmem.h>
+#include <linux/compiler.h>
+#include <linux/module.h>
+#include <linux/suspend.h>
+#include <linux/pagevec.h>
+#include <linux/blkdev.h>
+#include <linux/slab.h>
+#include <linux/notifier.h>
+#include <linux/topology.h>
+#include <linux/sysctl.h>
+#include <linux/cpu.h>
+#include <linux/nodemask.h>
+#include <linux/vmalloc.h>
+
+#include <asm/tlbflush.h>
+#include "internal.h"
+
+/* MCD - HACK: Find somewhere to initialize this EARLY, or make this
initializer cleaner */
+nodemask_t node_online_map = { { [0] = 1UL } };
+nodemask_t node_possible_map = NODE_MASK_ALL;
+struct pglist_data *pgdat_list;
+unsigned long totalram_pages;
+unsigned long totalhigh_pages;
+long nr_swap_pages;
+/*
+ * results with 256, 32 in the lowmem_reserve sysctl:
+ * 1G machine -> (16M dma, 800M-16M normal, 1G-800M high)
+ * 1G machine -> (16M dma, 784M normal, 224M high)
+ * NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA
+ * HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL
+ * HIGHMEM allocation will (224M+784M)/256 of ram reserved in ZONE_DMA
+ */
+int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { 256, 32 };
+
+EXPORT_SYMBOL(totalram_pages);
+EXPORT_SYMBOL(nr_swap_pages);
+
+/*
+ * Used by page_zone() to look up the address of the struct zone whose
+ * id is encoded in the upper bits of page->flags
+ */
+struct zone *zone_table[1 << (ZONES_SHIFT + NODES_SHIFT)];
+EXPORT_SYMBOL(zone_table);
+
+static char *zone_names[MAX_NR_ZONES] = { "DMA", "Normal", "HighMem" };
+int min_free_kbytes = 1024;
+
+unsigned long __initdata nr_kernel_pages;
+unsigned long __initdata nr_all_pages;
+
+/*
+ * Temporary debugging check for pages not lying within a given zone.
+ */
+static int bad_range(struct zone *zone, struct page *page)
+{
+ if (page_to_pfn(page) >= zone->zone_start_pfn + zone->spanned_pages)
+ return 1;
+ if (page_to_pfn(page) < zone->zone_start_pfn)
+ return 1;
+#ifdef CONFIG_HOLES_IN_ZONE
+ if (!pfn_valid(page_to_pfn(page)))
+ return 1;
+#endif
+ if (zone != page_zone(page))
+ return 1;
+ return 0;
+}
+
+static void bad_page(const char *function, struct page *page)
+{
+ printk(KERN_EMERG "Bad page state at %s (in process '%s', page %p)\n",
+ function, current->comm, page);
+ printk(KERN_EMERG "flags:0x%0*lx mapping:%p mapcount:%d count:%d\n",
+ (int)(2*sizeof(page_flags_t)), (unsigned long)page->flags,
+ page->mapping, page_mapcount(page), page_count(page));
+ printk(KERN_EMERG "Backtrace:\n");
+ dump_stack();
+ printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n");
+ page->flags &= ~(1 << PG_private |
+ 1 << PG_locked |
+ 1 << PG_lru |
+ 1 << PG_active |
+ 1 << PG_dirty |
+ 1 << PG_swapcache |
+ 1 << PG_writeback);
+ set_page_count(page, 0);
+ reset_page_mapcount(page);
+ page->mapping = NULL;
+ tainted |= TAINT_BAD_PAGE;
+}
+
+#ifndef CONFIG_HUGETLB_PAGE
+#define prep_compound_page(page, order) do { } while (0)
+#define destroy_compound_page(page, order) do { } while (0)
+#else
+/*
+ * Higher-order pages are called "compound pages". They are structured thusly:
+ *
+ * The first PAGE_SIZE page is called the "head page".
+ *
+ * The remaining PAGE_SIZE pages are called "tail pages".
+ *
+ * All pages have PG_compound set. All pages have their ->private pointing at
+ * the head page (even the head page has this).
+ *
+ * The first tail page's ->mapping, if non-zero, holds the address of the
+ * compound page's put_page() function.
+ *
+ * The order of the allocation is stored in the first tail page's ->index
+ * This is only for debug at present. This usage means that zero-order pages
+ * may not be compound.
+ */
+static void prep_compound_page(struct page *page, unsigned long order)
+{
+ int i;
+ int nr_pages = 1 << order;
+
+ page[1].mapping = NULL;
+ page[1].index = order;
+ for (i = 0; i < nr_pages; i++) {
+ struct page *p = page + i;
+
+ SetPageCompound(p);
+ p->private = (unsigned long)page;
+ }
+}
+
+static void destroy_compound_page(struct page *page, unsigned long order)
+{
+ int i;
+ int nr_pages = 1 << order;
+
+ if (!PageCompound(page))
+ return;
+
+ if (page[1].index != order)
+ bad_page(__FUNCTION__, page);
+
+ for (i = 0; i < nr_pages; i++) {
+ struct page *p = page + i;
+
+ if (!PageCompound(p))
+ bad_page(__FUNCTION__, page);
+ if (p->private != (unsigned long)page)
+ bad_page(__FUNCTION__, page);
+ ClearPageCompound(p);
+ }
+}
+#endif /* CONFIG_HUGETLB_PAGE */
+
+/*
+ * function for dealing with page's order in buddy system.
+ * zone->lock is already acquired when we use these.
+ * So, we don't need atomic page->flags operations here.
+ */
+static inline unsigned long page_order(struct page *page) {
+ return page->private;
+}
+
+static inline void set_page_order(struct page *page, int order) {
+ page->private = order;
+ __SetPagePrivate(page);
+}
+
+static inline void rmv_page_order(struct page *page)
+{
+ __ClearPagePrivate(page);
+ page->private = 0;
+}
+
+/*
+ * This function checks whether a page is free && is the buddy
+ * we can do coalesce a page and its buddy if
+ * (a) the buddy is free &&
+ * (b) the buddy is on the buddy system &&
+ * (c) a page and its buddy have the same order.
+ * for recording page's order, we use page->private and PG_private.
+ *
+ */
+static inline int page_is_buddy(struct page *page, int order)
+{
+ if (PagePrivate(page) &&
+ (page_order(page) == order) &&
+ !PageReserved(page) &&
+ page_count(page) == 0)
+ return 1;
+ return 0;
+}
+
+/*
+ * Freeing function for a buddy system allocator.
+ *
+ * The concept of a buddy system is to maintain direct-mapped table
+ * (containing bit values) for memory blocks of various "orders".
+ * The bottom level table contains the map for the smallest allocatable
+ * units of memory (here, pages), and each level above it describes
+ * pairs of units from the levels below, hence, "buddies".
+ * At a high level, all that happens here is marking the table entry
+ * at the bottom level available, and propagating the changes upward
+ * as necessary, plus some accounting needed to play nicely with other
+ * parts of the VM system.
+ * At each level, we keep a list of pages, which are heads of continuous
+ * free pages of length of (1 << order) and marked with PG_Private.Page's
+ * order is recorded in page->private field.
+ * So when we are allocating or freeing one, we can derive the state of the
+ * other. That is, if we allocate a small block, and both were
+ * free, the remainder of the region must be split into blocks.
+ * If a block is freed, and its buddy is also free, then this
+ * triggers coalescing into a block of larger size.
+ *
+ * -- wli
+ */
+
+static inline void __free_pages_bulk (struct page *page, struct page *base,
+ struct zone *zone, unsigned int order)
+{
+ unsigned long page_idx;
+ struct page *coalesced;
+ int order_size = 1 << order;
+
+ if (unlikely(order))
+ destroy_compound_page(page, order);
+
+ page_idx = page - base;
+
+ BUG_ON(page_idx & (order_size - 1));
+ BUG_ON(bad_range(zone, page));
+
+ zone->free_pages += order_size;
+ while (order < MAX_ORDER-1) {
+ struct free_area *area;
+ struct page *buddy;
+ int buddy_idx;
+
+ buddy_idx = (page_idx ^ (1 << order));
+ buddy = base + buddy_idx;
+ if (bad_range(zone, buddy))
+ break;
+ if (!page_is_buddy(buddy, order))
+ break;
+ /* Move the buddy up one level. */
+ list_del(&buddy->lru);
+ area = zone->free_area + order;
+ area->nr_free--;
+ rmv_page_order(buddy);
+ page_idx &= buddy_idx;
+ order++;
+ }
+ coalesced = base + page_idx;
+ set_page_order(coalesced, order);
+ list_add(&coalesced->lru, &zone->free_area[order].free_list);
+ zone->free_area[order].nr_free++;
+}
+
+static inline void free_pages_check(const char *function, struct page *page)
+{
+ if ( page_mapped(page) ||
+ page->mapping != NULL ||
+ page_count(page) != 0 ||
+ (page->flags & (
+ 1 << PG_lru |
+ 1 << PG_private |
+ 1 << PG_locked |
+ 1 << PG_active |
+ 1 << PG_reclaim |
+ 1 << PG_slab |
+ 1 << PG_swapcache |
+ 1 << PG_writeback )))
+ bad_page(function, page);
+ if (PageDirty(page))
+ ClearPageDirty(page);
+}
+
+/*
+ * Frees a list of pages.
+ * Assumes all pages on list are in same zone, and of same order.
+ * count is the number of pages to free, or 0 for all on the list.
+ *
+ * If the zone was previously in an "all pages pinned" state then look to
+ * see if this freeing clears that state.
+ *
+ * And clear the zone's pages_scanned counter, to hold off the "all pages are
+ * pinned" detection logic.
+ */
+static int
+free_pages_bulk(struct zone *zone, int count,
+ struct list_head *list, unsigned int order)
+{
+ unsigned long flags;
+ struct page *base, *page = NULL;
+ int ret = 0;
+
+ base = zone->zone_mem_map;
+ spin_lock_irqsave(&zone->lock, flags);
+ zone->all_unreclaimable = 0;
+ zone->pages_scanned = 0;
+ while (!list_empty(list) && count--) {
+ page = list_entry(list->prev, struct page, lru);
+ /* have to delete it as __free_pages_bulk list manipulates */
+ list_del(&page->lru);
+ __free_pages_bulk(page, base, zone, order);
+ ret++;
+ }
+ spin_unlock_irqrestore(&zone->lock, flags);
+ return ret;
+}
+
+void __free_pages_ok(struct page *page, unsigned int order)
+{
+ LIST_HEAD(list);
+ int i;
+
+ if (arch_free_page(page, order))
+ return;
+
+ mod_page_state(pgfree, 1 << order);
+
+#ifndef CONFIG_MMU
+ if (order > 0)
+ for (i = 1 ; i < (1 << order) ; ++i)
+ __put_page(page + i);
+#endif
+
+ for (i = 0 ; i < (1 << order) ; ++i)
+ free_pages_check(__FUNCTION__, page + i);
+ list_add(&page->lru, &list);
+ kernel_map_pages(page, 1<<order, 0);
+ free_pages_bulk(page_zone(page), 1, &list, order);
+}
+
+
+/*
+ * The order of subdivision here is critical for the IO subsystem.
+ * Please do not alter this order without good reasons and regression
+ * testing. Specifically, as large blocks of memory are subdivided,
+ * the order in which smaller blocks are delivered depends on the order
+ * they're subdivided in this function. This is the primary factor
+ * influencing the order in which pages are delivered to the IO
+ * subsystem according to empirical testing, and this is also justified
+ * by considering the behavior of a buddy system containing a single
+ * large block of memory acted on by a series of small allocations.
+ * This behavior is a critical factor in sglist merging's success.
+ *
+ * -- wli
+ */
+static inline struct page *
+expand(struct zone *zone, struct page *page,
+ int low, int high, struct free_area *area)
+{
+ unsigned long size = 1 << high;
+
+ while (high > low) {
+ area--;
+ high--;
+ size >>= 1;
+ BUG_ON(bad_range(zone, &page[size]));
+ list_add(&page[size].lru, &area->free_list);
+ area->nr_free++;
+ set_page_order(&page[size], high);
+ }
+ return page;
+}
+
+void set_page_refs(struct page *page, int order)
+{
+#ifdef CONFIG_MMU
+ set_page_count(page, 1);
+#else
+ int i;
+
+ /*
+ * We need to reference all the pages for this order, otherwise if
+ * anyone accesses one of the pages with (get/put) it will be freed.
+ * - eg: access_process_vm()
+ */
+ for (i = 0; i < (1 << order); i++)
+ set_page_count(page + i, 1);
+#endif /* CONFIG_MMU */
+}
+
+/*
+ * This page is about to be returned from the page allocator
+ */
+static void prep_new_page(struct page *page, int order)
+{
+ if (page->mapping || page_mapped(page) ||
+ (page->flags & (
+ 1 << PG_private |
+ 1 << PG_locked |
+ 1 << PG_lru |
+ 1 << PG_active |
+ 1 << PG_dirty |
+ 1 << PG_reclaim |
+ 1 << PG_swapcache |
+ 1 << PG_writeback )))
+ bad_page(__FUNCTION__, page);
+
+ page->flags &= ~(1 << PG_uptodate | 1 << PG_error |
+ 1 << PG_referenced | 1 << PG_arch_1 |
+ 1 << PG_checked | 1 << PG_mappedtodisk);
+ page->private = 0;
+ set_page_refs(page, order);
+ kernel_map_pages(page, 1 << order, 1);
+}
+
+/*
+ * Do the hard work of removing an element from the buddy allocator.
+ * Call me with the zone->lock already held.
+ */
+static struct page *__rmqueue(struct zone *zone, unsigned int order)
+{
+ struct free_area * area;
+ unsigned int current_order;
+ struct page *page;
+
+ for (current_order = order; current_order < MAX_ORDER; ++current_order)
{
+ area = zone->free_area + current_order;
+ if (list_empty(&area->free_list))
+ continue;
+
+ page = list_entry(area->free_list.next, struct page, lru);
+ list_del(&page->lru);
+ rmv_page_order(page);
+ area->nr_free--;
+ zone->free_pages -= 1UL << order;
+ return expand(zone, page, order, current_order, area);
+ }
+
+ return NULL;
+}
+
+/*
+ * Obtain a specified number of elements from the buddy allocator, all under
+ * a single hold of the lock, for efficiency. Add them to the supplied list.
+ * Returns the number of new pages which were placed at *list.
+ */
+static int rmqueue_bulk(struct zone *zone, unsigned int order,
+ unsigned long count, struct list_head *list)
+{
+ unsigned long flags;
+ int i;
+ int allocated = 0;
+ struct page *page;
+
+ spin_lock_irqsave(&zone->lock, flags);
+ for (i = 0; i < count; ++i) {
+ page = __rmqueue(zone, order);
+ if (page == NULL)
+ break;
+ allocated++;
+ list_add_tail(&page->lru, list);
+ }
+ spin_unlock_irqrestore(&zone->lock, flags);
+ return allocated;
+}
+
+#if defined(CONFIG_PM) || defined(CONFIG_HOTPLUG_CPU)
+static void __drain_pages(unsigned int cpu)
+{
+ struct zone *zone;
+ int i;
+
+ for_each_zone(zone) {
+ struct per_cpu_pageset *pset;
+
+ pset = &zone->pageset[cpu];
+ for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
+ struct per_cpu_pages *pcp;
+
+ pcp = &pset->pcp[i];
+ pcp->count -= free_pages_bulk(zone, pcp->count,
+ &pcp->list, 0);
+ }
+ }
+}
+#endif /* CONFIG_PM || CONFIG_HOTPLUG_CPU */
+
+#ifdef CONFIG_PM
+
+void mark_free_pages(struct zone *zone)
+{
+ unsigned long zone_pfn, flags;
+ int order;
+ struct list_head *curr;
+
+ if (!zone->spanned_pages)
+ return;
+
+ spin_lock_irqsave(&zone->lock, flags);
+ for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
+ ClearPageNosaveFree(pfn_to_page(zone_pfn +
zone->zone_start_pfn));
+
+ for (order = MAX_ORDER - 1; order >= 0; --order)
+ list_for_each(curr, &zone->free_area[order].free_list) {
+ unsigned long start_pfn, i;
+
+ start_pfn = page_to_pfn(list_entry(curr, struct page,
lru));
+
+ for (i=0; i < (1<<order); i++)
+ SetPageNosaveFree(pfn_to_page(start_pfn+i));
+ }
+ spin_unlock_irqrestore(&zone->lock, flags);
+}
+
+/*
+ * Spill all of this CPU's per-cpu pages back into the buddy allocator.
+ */
+void drain_local_pages(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __drain_pages(smp_processor_id());
+ local_irq_restore(flags);
+}
+#endif /* CONFIG_PM */
+
+static void zone_statistics(struct zonelist *zonelist, struct zone *z)
+{
+#ifdef CONFIG_NUMA
+ unsigned long flags;
+ int cpu;
+ pg_data_t *pg = z->zone_pgdat;
+ pg_data_t *orig = zonelist->zones[0]->zone_pgdat;
+ struct per_cpu_pageset *p;
+
+ local_irq_save(flags);
+ cpu = smp_processor_id();
+ p = &z->pageset[cpu];
+ if (pg == orig) {
+ z->pageset[cpu].numa_hit++;
+ } else {
+ p->numa_miss++;
+ zonelist->zones[0]->pageset[cpu].numa_foreign++;
+ }
+ if (pg == NODE_DATA(numa_node_id()))
+ p->local_node++;
+ else
+ p->other_node++;
+ local_irq_restore(flags);
+#endif
+}
+
+/*
+ * Free a 0-order page
+ */
+static void FASTCALL(free_hot_cold_page(struct page *page, int cold));
+static void fastcall free_hot_cold_page(struct page *page, int cold)
+{
+ struct zone *zone = page_zone(page);
+ struct per_cpu_pages *pcp;
+ unsigned long flags;
+
+ if (arch_free_page(page, 0))
+ return;
+
+ kernel_map_pages(page, 1, 0);
+ inc_page_state(pgfree);
+ if (PageAnon(page))
+ page->mapping = NULL;
+ free_pages_check(__FUNCTION__, page);
+ pcp = &zone->pageset[get_cpu()].pcp[cold];
+ local_irq_save(flags);
+ if (pcp->count >= pcp->high)
+ pcp->count -= free_pages_bulk(zone, pcp->batch, &pcp->list, 0);
+ list_add(&page->lru, &pcp->list);
+ pcp->count++;
+ local_irq_restore(flags);
+ put_cpu();
+}
+
+void fastcall free_hot_page(struct page *page)
+{
+ free_hot_cold_page(page, 0);
+}
+
+void fastcall free_cold_page(struct page *page)
+{
+ free_hot_cold_page(page, 1);
+}
+
+static inline void prep_zero_page(struct page *page, int order, int gfp_flags)
+{
+ int i;
+
+ BUG_ON((gfp_flags & (__GFP_WAIT | __GFP_HIGHMEM)) == __GFP_HIGHMEM);
+ for(i = 0; i < (1 << order); i++)
+ clear_highpage(page + i);
+}
+
+/*
+ * Really, prep_compound_page() should be called from __rmqueue_bulk(). But
+ * we cheat by calling it from here, in the order > 0 path. Saves a branch
+ * or two.
+ */
+static struct page *
+buffered_rmqueue(struct zone *zone, int order, int gfp_flags)
+{
+ unsigned long flags;
+ struct page *page = NULL;
+ int cold = !!(gfp_flags & __GFP_COLD);
+
+ if (order == 0) {
+ struct per_cpu_pages *pcp;
+
+ pcp = &zone->pageset[get_cpu()].pcp[cold];
+ local_irq_save(flags);
+ if (pcp->count <= pcp->low)
+ pcp->count += rmqueue_bulk(zone, 0,
+ pcp->batch, &pcp->list);
+ if (pcp->count) {
+ page = list_entry(pcp->list.next, struct page, lru);
+ list_del(&page->lru);
+ pcp->count--;
+ }
+ local_irq_restore(flags);
+ put_cpu();
+ }
+
+ if (page == NULL) {
+ spin_lock_irqsave(&zone->lock, flags);
+ page = __rmqueue(zone, order);
+ spin_unlock_irqrestore(&zone->lock, flags);
+ }
+
+ if (page != NULL) {
+ BUG_ON(bad_range(zone, page));
+ mod_page_state_zone(zone, pgalloc, 1 << order);
+ prep_new_page(page, order);
+
+ if (gfp_flags & __GFP_ZERO)
+ prep_zero_page(page, order, gfp_flags);
+
+ if (order && (gfp_flags & __GFP_COMP))
+ prep_compound_page(page, order);
+ }
+ return page;
+}
+
+/*
+ * Return 1 if free pages are above 'mark'. This takes into account the order
+ * of the allocation.
+ */
+int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+ int classzone_idx, int can_try_harder, int gfp_high)
+{
+ /* free_pages my go negative - that's OK */
+ long min = mark, free_pages = z->free_pages - (1 << order) + 1;
+ int o;
+
+ if (gfp_high)
+ min -= min / 2;
+ if (can_try_harder)
+ min -= min / 4;
+
+ if (free_pages <= min + z->lowmem_reserve[classzone_idx])
+ return 0;
+ for (o = 0; o < order; o++) {
+ /* At the next order, this order's pages become unavailable */
+ free_pages -= z->free_area[o].nr_free << o;
+
+ /* Require fewer higher order pages to be free */
+ min >>= 1;
+
+ if (free_pages <= min)
+ return 0;
+ }
+ return 1;
+}
+
+/*
+ * This is the 'heart' of the zoned buddy allocator.
+ */
+struct page * fastcall
+__alloc_pages(unsigned int gfp_mask, unsigned int order,
+ struct zonelist *zonelist)
+{
+ const int wait = gfp_mask & __GFP_WAIT;
+ struct zone **zones, *z;
+ struct page *page;
+ struct reclaim_state reclaim_state;
+ struct task_struct *p = current;
+ int i;
+ int classzone_idx;
+ int do_retry;
+ int can_try_harder;
+ int did_some_progress;
+
+ might_sleep_if(wait);
+
+ /*
+ * The caller may dip into page reserves a bit more if the caller
+ * cannot run direct reclaim, or is the caller has realtime scheduling
+ * policy
+ */
+ can_try_harder = (unlikely(rt_task(p)) && !in_interrupt()) || !wait;
+
+ zones = zonelist->zones; /* the list of zones suitable for gfp_mask */
+
+ if (unlikely(zones[0] == NULL)) {
+ /* Should this ever happen?? */
+ return NULL;
+ }
+
+ classzone_idx = zone_idx(zones[0]);
+
+ restart:
+ /* Go through the zonelist once, looking for a zone with enough free */
+ for (i = 0; (z = zones[i]) != NULL; i++) {
+
+ if (!zone_watermark_ok(z, order, z->pages_low,
+ classzone_idx, 0, 0))
+ continue;
+
+ page = buffered_rmqueue(z, order, gfp_mask);
+ if (page)
+ goto got_pg;
+ }
+
+ for (i = 0; (z = zones[i]) != NULL; i++)
+ wakeup_kswapd(z, order);
+
+ /*
+ * Go through the zonelist again. Let __GFP_HIGH and allocations
+ * coming from realtime tasks to go deeper into reserves
+ */
+ for (i = 0; (z = zones[i]) != NULL; i++) {
+ if (!zone_watermark_ok(z, order, z->pages_min,
+ classzone_idx, can_try_harder,
+ gfp_mask & __GFP_HIGH))
+ continue;
+
+ page = buffered_rmqueue(z, order, gfp_mask);
+ if (page)
+ goto got_pg;
+ }
+
+ /* This allocation should allow future memory freeing. */
+ if (((p->flags & PF_MEMALLOC) ||
unlikely(test_thread_flag(TIF_MEMDIE))) && !in_interrupt()) {
+ /* go through the zonelist yet again, ignoring mins */
+ for (i = 0; (z = zones[i]) != NULL; i++) {
+ page = buffered_rmqueue(z, order, gfp_mask);
+ if (page)
+ goto got_pg;
+ }
+ goto nopage;
+ }
+
+ /* Atomic allocations - we can't balance anything */
+ if (!wait)
+ goto nopage;
+
+rebalance:
+ cond_resched();
+
+ /* We now go into synchronous reclaim */
+ p->flags |= PF_MEMALLOC;
+ reclaim_state.reclaimed_slab = 0;
+ p->reclaim_state = &reclaim_state;
+
+ did_some_progress = try_to_free_pages(zones, gfp_mask, order);
+
+ p->reclaim_state = NULL;
+ p->flags &= ~PF_MEMALLOC;
+
+ cond_resched();
+
+ if (likely(did_some_progress)) {
+ /*
+ * Go through the zonelist yet one more time, keep
+ * very high watermark here, this is only to catch
+ * a parallel oom killing, we must fail if we're still
+ * under heavy pressure.
+ */
+ for (i = 0; (z = zones[i]) != NULL; i++) {
+ if (!zone_watermark_ok(z, order, z->pages_min,
+ classzone_idx, can_try_harder,
+ gfp_mask & __GFP_HIGH))
+ continue;
+
+ page = buffered_rmqueue(z, order, gfp_mask);
+ if (page)
+ goto got_pg;
+ }
+ } else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
+ /*
+ * Go through the zonelist yet one more time, keep
+ * very high watermark here, this is only to catch
+ * a parallel oom killing, we must fail if we're still
+ * under heavy pressure.
+ */
+ for (i = 0; (z = zones[i]) != NULL; i++) {
+ if (!zone_watermark_ok(z, order, z->pages_high,
+ classzone_idx, 0, 0))
+ continue;
+
+ page = buffered_rmqueue(z, order, gfp_mask);
+ if (page)
+ goto got_pg;
+ }
+
+ out_of_memory(gfp_mask);
+ goto restart;
+ }
+
+ /*
+ * Don't let big-order allocations loop unless the caller explicitly
+ * requests that. Wait for some write requests to complete then retry.
+ *
+ * In this implementation, __GFP_REPEAT means __GFP_NOFAIL for order
+ * <= 3, but that may not be true in other implementations.
+ */
+ do_retry = 0;
+ if (!(gfp_mask & __GFP_NORETRY)) {
+ if ((order <= 3) || (gfp_mask & __GFP_REPEAT))
+ do_retry = 1;
+ if (gfp_mask & __GFP_NOFAIL)
+ do_retry = 1;
+ }
+ if (do_retry) {
+ blk_congestion_wait(WRITE, HZ/50);
+ goto rebalance;
+ }
+
+nopage:
+ if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
+ printk(KERN_WARNING "%s: page allocation failure."
+ " order:%d, mode:0x%x\n",
+ p->comm, order, gfp_mask);
+ dump_stack();
+ }
+ return NULL;
+got_pg:
+ zone_statistics(zonelist, z);
+ return page;
+}
+
+EXPORT_SYMBOL(__alloc_pages);
+
+/*
+ * Common helper functions.
+ */
+fastcall unsigned long __get_free_pages(unsigned int gfp_mask, unsigned int
order)
+{
+ struct page * page;
+ page = alloc_pages(gfp_mask, order);
+ if (!page)
+ return 0;
+ return (unsigned long) page_address(page);
+}
+
+EXPORT_SYMBOL(__get_free_pages);
+
+fastcall unsigned long get_zeroed_page(unsigned int gfp_mask)
+{
+ struct page * page;
+
+ /*
+ * get_zeroed_page() returns a 32-bit address, which cannot represent
+ * a highmem page
+ */
+ BUG_ON(gfp_mask & __GFP_HIGHMEM);
+
+ page = alloc_pages(gfp_mask | __GFP_ZERO, 0);
+ if (page)
+ return (unsigned long) page_address(page);
+ return 0;
+}
+
+EXPORT_SYMBOL(get_zeroed_page);
+
+void __pagevec_free(struct pagevec *pvec)
+{
+ int i = pagevec_count(pvec);
+
+ while (--i >= 0)
+ free_hot_cold_page(pvec->pages[i], pvec->cold);
+}
+
+fastcall void __free_pages(struct page *page, unsigned int order)
+{
+ if (!PageReserved(page) && put_page_testzero(page)) {
+ if (order == 0)
+ free_hot_page(page);
+ else
+ __free_pages_ok(page, order);
+ }
+}
+
+EXPORT_SYMBOL(__free_pages);
+
+fastcall void free_pages(unsigned long addr, unsigned int order)
+{
+ if (addr != 0) {
+ BUG_ON(!virt_addr_valid((void *)addr));
+ __free_pages(virt_to_page((void *)addr), order);
+ }
+}
+
+EXPORT_SYMBOL(free_pages);
+
+/*
+ * Total amount of free (allocatable) RAM:
+ */
+unsigned int nr_free_pages(void)
+{
+ unsigned int sum = 0;
+ struct zone *zone;
+
+ for_each_zone(zone)
+ sum += zone->free_pages;
+
+ return sum;
+}
+
+EXPORT_SYMBOL(nr_free_pages);
+
+#ifdef CONFIG_NUMA
+unsigned int nr_free_pages_pgdat(pg_data_t *pgdat)
+{
+ unsigned int i, sum = 0;
+
+ for (i = 0; i < MAX_NR_ZONES; i++)
+ sum += pgdat->node_zones[i].free_pages;
+
+ return sum;
+}
+#endif
+
+static unsigned int nr_free_zone_pages(int offset)
+{
+ pg_data_t *pgdat;
+ unsigned int sum = 0;
+
+ for_each_pgdat(pgdat) {
+ struct zonelist *zonelist = pgdat->node_zonelists + offset;
+ struct zone **zonep = zonelist->zones;
+ struct zone *zone;
+
+ for (zone = *zonep++; zone; zone = *zonep++) {
+ unsigned long size = zone->present_pages;
+ unsigned long high = zone->pages_high;
+ if (size > high)
+ sum += size - high;
+ }
+ }
+
+ return sum;
+}
+
+/*
+ * Amount of free RAM allocatable within ZONE_DMA and ZONE_NORMAL
+ */
+unsigned int nr_free_buffer_pages(void)
+{
+ return nr_free_zone_pages(GFP_USER & GFP_ZONEMASK);
+}
+
+/*
+ * Amount of free RAM allocatable within all zones
+ */
+unsigned int nr_free_pagecache_pages(void)
+{
+ return nr_free_zone_pages(GFP_HIGHUSER & GFP_ZONEMASK);
+}
+
+#ifdef CONFIG_HIGHMEM
+unsigned int nr_free_highpages (void)
+{
+ pg_data_t *pgdat;
+ unsigned int pages = 0;
+
+ for_each_pgdat(pgdat)
+ pages += pgdat->node_zones[ZONE_HIGHMEM].free_pages;
+
+ return pages;
+}
+#endif
+
+#ifdef CONFIG_NUMA
+static void show_node(struct zone *zone)
+{
+ printk("Node %d ", zone->zone_pgdat->node_id);
+}
+#else
+#define show_node(zone) do { } while (0)
+#endif
+
+/*
+ * Accumulate the page_state information across all CPUs.
+ * The result is unavoidably approximate - it can change
+ * during and after execution of this function.
+ */
+static DEFINE_PER_CPU(struct page_state, page_states) = {0};
+
+atomic_t nr_pagecache = ATOMIC_INIT(0);
+EXPORT_SYMBOL(nr_pagecache);
+#ifdef CONFIG_SMP
+DEFINE_PER_CPU(long, nr_pagecache_local) = 0;
+#endif
+
+void __get_page_state(struct page_state *ret, int nr)
+{
+ int cpu = 0;
+
+ memset(ret, 0, sizeof(*ret));
+
+ cpu = first_cpu(cpu_online_map);
+ while (cpu < NR_CPUS) {
+ unsigned long *in, *out, off;
+
+ in = (unsigned long *)&per_cpu(page_states, cpu);
+
+ cpu = next_cpu(cpu, cpu_online_map);
+
+ if (cpu < NR_CPUS)
+ prefetch(&per_cpu(page_states, cpu));
+
+ out = (unsigned long *)ret;
+ for (off = 0; off < nr; off++)
+ *out++ += *in++;
+ }
+}
+
+void get_page_state(struct page_state *ret)
+{
+ int nr;
+
+ nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
+ nr /= sizeof(unsigned long);
+
+ __get_page_state(ret, nr + 1);
+}
+
+void get_full_page_state(struct page_state *ret)
+{
+ __get_page_state(ret, sizeof(*ret) / sizeof(unsigned long));
+}
+
+unsigned long __read_page_state(unsigned offset)
+{
+ unsigned long ret = 0;
+ int cpu;
+
+ for_each_online_cpu(cpu) {
+ unsigned long in;
+
+ in = (unsigned long)&per_cpu(page_states, cpu) + offset;
+ ret += *((unsigned long *)in);
+ }
+ return ret;
+}
+
+void __mod_page_state(unsigned offset, unsigned long delta)
+{
+ unsigned long flags;
+ void* ptr;
+
+ local_irq_save(flags);
+ ptr = &__get_cpu_var(page_states);
+ *(unsigned long*)(ptr + offset) += delta;
+ local_irq_restore(flags);
+}
+
+EXPORT_SYMBOL(__mod_page_state);
+
+void __get_zone_counts(unsigned long *active, unsigned long *inactive,
+ unsigned long *free, struct pglist_data *pgdat)
+{
+ struct zone *zones = pgdat->node_zones;
+ int i;
+
+ *active = 0;
+ *inactive = 0;
+ *free = 0;
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ *active += zones[i].nr_active;
+ *inactive += zones[i].nr_inactive;
+ *free += zones[i].free_pages;
+ }
+}
+
+void get_zone_counts(unsigned long *active,
+ unsigned long *inactive, unsigned long *free)
+{
+ struct pglist_data *pgdat;
+
+ *active = 0;
+ *inactive = 0;
+ *free = 0;
+ for_each_pgdat(pgdat) {
+ unsigned long l, m, n;
+ __get_zone_counts(&l, &m, &n, pgdat);
+ *active += l;
+ *inactive += m;
+ *free += n;
+ }
+}
+
+void si_meminfo(struct sysinfo *val)
+{
+ val->totalram = totalram_pages;
+ val->sharedram = 0;
+ val->freeram = nr_free_pages();
+ val->bufferram = nr_blockdev_pages();
+#ifdef CONFIG_HIGHMEM
+ val->totalhigh = totalhigh_pages;
+ val->freehigh = nr_free_highpages();
+#else
+ val->totalhigh = 0;
+ val->freehigh = 0;
+#endif
+ val->mem_unit = PAGE_SIZE;
+}
+
+EXPORT_SYMBOL(si_meminfo);
+
+#ifdef CONFIG_NUMA
+void si_meminfo_node(struct sysinfo *val, int nid)
+{
+ pg_data_t *pgdat = NODE_DATA(nid);
+
+ val->totalram = pgdat->node_present_pages;
+ val->freeram = nr_free_pages_pgdat(pgdat);
+ val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].present_pages;
+ val->freehigh = pgdat->node_zones[ZONE_HIGHMEM].free_pages;
+ val->mem_unit = PAGE_SIZE;
+}
+#endif
+
+#define K(x) ((x) << (PAGE_SHIFT-10))
+
+/*
+ * Show free area list (used inside shift_scroll-lock stuff)
+ * We also calculate the percentage fragmentation. We do this by counting the
+ * memory on each free list with the exception of the first item on the list.
+ */
+void show_free_areas(void)
+{
+ struct page_state ps;
+ int cpu, temperature;
+ unsigned long active;
+ unsigned long inactive;
+ unsigned long free;
+ struct zone *zone;
+
+ for_each_zone(zone) {
+ show_node(zone);
+ printk("%s per-cpu:", zone->name);
+
+ if (!zone->present_pages) {
+ printk(" empty\n");
+ continue;
+ } else
+ printk("\n");
+
+ for (cpu = 0; cpu < NR_CPUS; ++cpu) {
+ struct per_cpu_pageset *pageset;
+
+ if (!cpu_possible(cpu))
+ continue;
+
+ pageset = zone->pageset + cpu;
+
+ for (temperature = 0; temperature < 2; temperature++)
+ printk("cpu %d %s: low %d, high %d, batch %d\n",
+ cpu,
+ temperature ? "cold" : "hot",
+ pageset->pcp[temperature].low,
+ pageset->pcp[temperature].high,
+ pageset->pcp[temperature].batch);
+ }
+ }
+
+ get_page_state(&ps);
+ get_zone_counts(&active, &inactive, &free);
+
+ printk("\nFree pages: %11ukB (%ukB HighMem)\n",
+ K(nr_free_pages()),
+ K(nr_free_highpages()));
+
+ printk("Active:%lu inactive:%lu dirty:%lu writeback:%lu "
+ "unstable:%lu free:%u slab:%lu mapped:%lu pagetables:%lu\n",
+ active,
+ inactive,
+ ps.nr_dirty,
+ ps.nr_writeback,
+ ps.nr_unstable,
+ nr_free_pages(),
+ ps.nr_slab,
+ ps.nr_mapped,
+ ps.nr_page_table_pages);
+
+ for_each_zone(zone) {
+ int i;
+
+ show_node(zone);
+ printk("%s"
+ " free:%lukB"
+ " min:%lukB"
+ " low:%lukB"
+ " high:%lukB"
+ " active:%lukB"
+ " inactive:%lukB"
+ " present:%lukB"
+ " pages_scanned:%lu"
+ " all_unreclaimable? %s"
+ "\n",
+ zone->name,
+ K(zone->free_pages),
+ K(zone->pages_min),
+ K(zone->pages_low),
+ K(zone->pages_high),
+ K(zone->nr_active),
+ K(zone->nr_inactive),
+ K(zone->present_pages),
+ zone->pages_scanned,
+ (zone->all_unreclaimable ? "yes" : "no")
+ );
+ printk("lowmem_reserve[]:");
+ for (i = 0; i < MAX_NR_ZONES; i++)
+ printk(" %lu", zone->lowmem_reserve[i]);
+ printk("\n");
+ }
+
+ for_each_zone(zone) {
+ unsigned long nr, flags, order, total = 0;
+
+ show_node(zone);
+ printk("%s: ", zone->name);
+ if (!zone->present_pages) {
+ printk("empty\n");
+ continue;
+ }
+
+ spin_lock_irqsave(&zone->lock, flags);
+ for (order = 0; order < MAX_ORDER; order++) {
+ nr = zone->free_area[order].nr_free;
+ total += nr << order;
+ printk("%lu*%lukB ", nr, K(1UL) << order);
+ }
+ spin_unlock_irqrestore(&zone->lock, flags);
+ printk("= %lukB\n", K(total));
+ }
+
+ show_swap_cache_info();
+}
+
+/*
+ * Builds allocation fallback zone lists.
+ */
+static int __init build_zonelists_node(pg_data_t *pgdat, struct zonelist
*zonelist, int j, int k)
+{
+ switch (k) {
+ struct zone *zone;
+ default:
+ BUG();
+ case ZONE_HIGHMEM:
+ zone = pgdat->node_zones + ZONE_HIGHMEM;
+ if (zone->present_pages) {
+#ifndef CONFIG_HIGHMEM
+ BUG();
+#endif
+ zonelist->zones[j++] = zone;
+ }
+ case ZONE_NORMAL:
+ zone = pgdat->node_zones + ZONE_NORMAL;
+ if (zone->present_pages)
+ zonelist->zones[j++] = zone;
+ case ZONE_DMA:
+ zone = pgdat->node_zones + ZONE_DMA;
+ if (zone->present_pages)
+ zonelist->zones[j++] = zone;
+ }
+
+ return j;
+}
+
+#ifdef CONFIG_NUMA
+#define MAX_NODE_LOAD (num_online_nodes())
+static int __initdata node_load[MAX_NUMNODES];
+/**
+ * find_next_best_node - find the next node that should appear in a given
+ * node's fallback list
+ * @node: node whose fallback list we're appending
+ * @used_node_mask: nodemask_t of already used nodes
+ *
+ * We use a number of factors to determine which is the next node that should
+ * appear on a given node's fallback list. The node should not have appeared
+ * already in @node's fallback list, and it should be the next closest node
+ * according to the distance array (which contains arbitrary distance values
+ * from each node to each node in the system), and should also prefer nodes
+ * with no CPUs, since presumably they'll have very little allocation pressure
+ * on them otherwise.
+ * It returns -1 if no node is found.
+ */
+static int __init find_next_best_node(int node, nodemask_t *used_node_mask)
+{
+ int i, n, val;
+ int min_val = INT_MAX;
+ int best_node = -1;
+
+ for_each_online_node(i) {
+ cpumask_t tmp;
+
+ /* Start from local node */
+ n = (node+i) % num_online_nodes();
+
+ /* Don't want a node to appear more than once */
+ if (node_isset(n, *used_node_mask))
+ continue;
+
+ /* Use the local node if we haven't already */
+ if (!node_isset(node, *used_node_mask)) {
+ best_node = node;
+ break;
+ }
+
+ /* Use the distance array to find the distance */
+ val = node_distance(node, n);
+
+ /* Give preference to headless and unused nodes */
+ tmp = node_to_cpumask(n);
+ if (!cpus_empty(tmp))
+ val += PENALTY_FOR_NODE_WITH_CPUS;
+
+ /* Slight preference for less loaded node */
+ val *= (MAX_NODE_LOAD*MAX_NUMNODES);
+ val += node_load[n];
+
+ if (val < min_val) {
+ min_val = val;
+ best_node = n;
+ }
+ }
+
+ if (best_node >= 0)
+ node_set(best_node, *used_node_mask);
+
+ return best_node;
+}
+
+static void __init build_zonelists(pg_data_t *pgdat)
+{
+ int i, j, k, node, local_node;
+ int prev_node, load;
+ struct zonelist *zonelist;
+ nodemask_t used_mask;
+
+ /* initialize zonelists */
+ for (i = 0; i < GFP_ZONETYPES; i++) {
+ zonelist = pgdat->node_zonelists + i;
+ memset(zonelist, 0, sizeof(*zonelist));
+ zonelist->zones[0] = NULL;
+ }
+
+ /* NUMA-aware ordering of nodes */
+ local_node = pgdat->node_id;
+ load = num_online_nodes();
+ prev_node = local_node;
+ nodes_clear(used_mask);
+ while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
+ /*
+ * We don't want to pressure a particular node.
+ * So adding penalty to the first node in same
+ * distance group to make it round-robin.
+ */
+ if (node_distance(local_node, node) !=
+ node_distance(local_node, prev_node))
+ node_load[node] += load;
+ prev_node = node;
+ load--;
+ for (i = 0; i < GFP_ZONETYPES; i++) {
+ zonelist = pgdat->node_zonelists + i;
+ for (j = 0; zonelist->zones[j] != NULL; j++);
+
+ k = ZONE_NORMAL;
+ if (i & __GFP_HIGHMEM)
+ k = ZONE_HIGHMEM;
+ if (i & __GFP_DMA)
+ k = ZONE_DMA;
+
+ j = build_zonelists_node(NODE_DATA(node), zonelist, j,
k);
+ zonelist->zones[j] = NULL;
+ }
+ }
+}
+
+#else /* CONFIG_NUMA */
+
+static void __init build_zonelists(pg_data_t *pgdat)
+{
+ int i, j, k, node, local_node;
+
+ local_node = pgdat->node_id;
+ for (i = 0; i < GFP_ZONETYPES; i++) {
+ struct zonelist *zonelist;
+
+ zonelist = pgdat->node_zonelists + i;
+ memset(zonelist, 0, sizeof(*zonelist));
+
+ j = 0;
+ k = ZONE_NORMAL;
+ if (i & __GFP_HIGHMEM)
+ k = ZONE_HIGHMEM;
+ if (i & __GFP_DMA)
+ k = ZONE_DMA;
+
+ j = build_zonelists_node(pgdat, zonelist, j, k);
+ /*
+ * Now we build the zonelist so that it contains the zones
+ * of all the other nodes.
+ * We don't want to pressure a particular node, so when
+ * building the zones for node N, we make sure that the
+ * zones coming right after the local ones are those from
+ * node N+1 (modulo N)
+ */
+ for (node = local_node + 1; node < MAX_NUMNODES; node++) {
+ if (!node_online(node))
+ continue;
+ j = build_zonelists_node(NODE_DATA(node), zonelist, j,
k);
+ }
+ for (node = 0; node < local_node; node++) {
+ if (!node_online(node))
+ continue;
+ j = build_zonelists_node(NODE_DATA(node), zonelist, j,
k);
+ }
+
+ zonelist->zones[j] = NULL;
+ }
+}
+
+#endif /* CONFIG_NUMA */
+
+void __init build_all_zonelists(void)
+{
+ int i;
+
+ for_each_online_node(i)
+ build_zonelists(NODE_DATA(i));
+ printk("Built %i zonelists\n", num_online_nodes());
+}
+
+/*
+ * Helper functions to size the waitqueue hash table.
+ * Essentially these want to choose hash table sizes sufficiently
+ * large so that collisions trying to wait on pages are rare.
+ * But in fact, the number of active page waitqueues on typical
+ * systems is ridiculously low, less than 200. So this is even
+ * conservative, even though it seems large.
+ *
+ * The constant PAGES_PER_WAITQUEUE specifies the ratio of pages to
+ * waitqueues, i.e. the size of the waitq table given the number of pages.
+ */
+#define PAGES_PER_WAITQUEUE 256
+
+static inline unsigned long wait_table_size(unsigned long pages)
+{
+ unsigned long size = 1;
+
+ pages /= PAGES_PER_WAITQUEUE;
+
+ while (size < pages)
+ size <<= 1;
+
+ /*
+ * Once we have dozens or even hundreds of threads sleeping
+ * on IO we've got bigger problems than wait queue collision.
+ * Limit the size of the wait table to a reasonable size.
+ */
+ size = min(size, 4096UL);
+
+ return max(size, 4UL);
+}
+
+/*
+ * This is an integer logarithm so that shifts can be used later
+ * to extract the more random high bits from the multiplicative
+ * hash function before the remainder is taken.
+ */
+static inline unsigned long wait_table_bits(unsigned long size)
+{
+ return ffz(~size);
+}
+
+#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))
+
+static void __init calculate_zone_totalpages(struct pglist_data *pgdat,
+ unsigned long *zones_size, unsigned long *zholes_size)
+{
+ unsigned long realtotalpages, totalpages = 0;
+ int i;
+
+ for (i = 0; i < MAX_NR_ZONES; i++)
+ totalpages += zones_size[i];
+ pgdat->node_spanned_pages = totalpages;
+
+ realtotalpages = totalpages;
+ if (zholes_size)
+ for (i = 0; i < MAX_NR_ZONES; i++)
+ realtotalpages -= zholes_size[i];
+ pgdat->node_present_pages = realtotalpages;
+ printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id,
realtotalpages);
+}
+
+
+/*
+ * Initially all pages are reserved - free ones are freed
+ * up by free_all_bootmem() once the early boot process is
+ * done. Non-atomic initialization, single-pass.
+ */
+void __init memmap_init_zone(unsigned long size, int nid, unsigned long zone,
+ unsigned long start_pfn)
+{
+ struct page *start = pfn_to_page(start_pfn);
+ struct page *page;
+
+ for (page = start; page < (start + size); page++) {
+ set_page_zone(page, NODEZONE(nid, zone));
+ set_page_count(page, 0);
+ reset_page_mapcount(page);
+ SetPageReserved(page);
+ INIT_LIST_HEAD(&page->lru);
+#ifdef WANT_PAGE_VIRTUAL
+ /* The shift won't overflow because ZONE_NORMAL is below 4G. */
+ if (!is_highmem_idx(zone))
+ set_page_address(page, __va(start_pfn << PAGE_SHIFT));
+#endif
+ start_pfn++;
+ }
+}
+
+void zone_init_free_lists(struct pglist_data *pgdat, struct zone *zone,
+ unsigned long size)
+{
+ int order;
+ for (order = 0; order < MAX_ORDER ; order++) {
+ INIT_LIST_HEAD(&zone->free_area[order].free_list);
+ zone->free_area[order].nr_free = 0;
+ }
+}
+
+#ifndef __HAVE_ARCH_MEMMAP_INIT
+#define memmap_init(size, nid, zone, start_pfn) \
+ memmap_init_zone((size), (nid), (zone), (start_pfn))
+#endif
+
+/*
+ * Set up the zone data structures:
+ * - mark all pages reserved
+ * - mark all memory queues empty
+ * - clear the memory bitmaps
+ */
+static void __init free_area_init_core(struct pglist_data *pgdat,
+ unsigned long *zones_size, unsigned long *zholes_size)
+{
+ unsigned long i, j;
+ const unsigned long zone_required_alignment = 1UL << (MAX_ORDER-1);
+ int cpu, nid = pgdat->node_id;
+ unsigned long zone_start_pfn = pgdat->node_start_pfn;
+
+ pgdat->nr_zones = 0;
+ init_waitqueue_head(&pgdat->kswapd_wait);
+ pgdat->kswapd_max_order = 0;
+
+ for (j = 0; j < MAX_NR_ZONES; j++) {
+ struct zone *zone = pgdat->node_zones + j;
+ unsigned long size, realsize;
+ unsigned long batch;
+
+ zone_table[NODEZONE(nid, j)] = zone;
+ realsize = size = zones_size[j];
+ if (zholes_size)
+ realsize -= zholes_size[j];
+
+ if (j == ZONE_DMA || j == ZONE_NORMAL)
+ nr_kernel_pages += realsize;
+ nr_all_pages += realsize;
+
+ zone->spanned_pages = size;
+ zone->present_pages = realsize;
+ zone->name = zone_names[j];
+ spin_lock_init(&zone->lock);
+ spin_lock_init(&zone->lru_lock);
+ zone->zone_pgdat = pgdat;
+ zone->free_pages = 0;
+
+ zone->temp_priority = zone->prev_priority = DEF_PRIORITY;
+
+ /*
+ * The per-cpu-pages pools are set to around 1000th of the
+ * size of the zone. But no more than 1/4 of a meg - there's
+ * no point in going beyond the size of L2 cache.
+ *
+ * OK, so we don't know how big the cache is. So guess.
+ */
+ batch = zone->present_pages / 1024;
+ if (batch * PAGE_SIZE > 256 * 1024)
+ batch = (256 * 1024) / PAGE_SIZE;
+ batch /= 4; /* We effectively *= 4 below */
+ if (batch < 1)
+ batch = 1;
+
+ for (cpu = 0; cpu < NR_CPUS; cpu++) {
+ struct per_cpu_pages *pcp;
+
+ pcp = &zone->pageset[cpu].pcp[0]; /* hot */
+ pcp->count = 0;
+ pcp->low = 2 * batch;
+ pcp->high = 6 * batch;
+ pcp->batch = 1 * batch;
+ INIT_LIST_HEAD(&pcp->list);
+
+ pcp = &zone->pageset[cpu].pcp[1]; /* cold */
+ pcp->count = 0;
+ pcp->low = 0;
+ pcp->high = 2 * batch;
+ pcp->batch = 1 * batch;
+ INIT_LIST_HEAD(&pcp->list);
+ }
+ printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%lu\n",
+ zone_names[j], realsize, batch);
+ INIT_LIST_HEAD(&zone->active_list);
+ INIT_LIST_HEAD(&zone->inactive_list);
+ zone->nr_scan_active = 0;
+ zone->nr_scan_inactive = 0;
+ zone->nr_active = 0;
+ zone->nr_inactive = 0;
+ if (!size)
+ continue;
+
+ /*
+ * The per-page waitqueue mechanism uses hashed waitqueues
+ * per zone.
+ */
+ zone->wait_table_size = wait_table_size(size);
+ zone->wait_table_bits =
+ wait_table_bits(zone->wait_table_size);
+ zone->wait_table = (wait_queue_head_t *)
+ alloc_bootmem_node(pgdat, zone->wait_table_size
+ * sizeof(wait_queue_head_t));
+
+ for(i = 0; i < zone->wait_table_size; ++i)
+ init_waitqueue_head(zone->wait_table + i);
+
+ pgdat->nr_zones = j+1;
+
+ zone->zone_mem_map = pfn_to_page(zone_start_pfn);
+ zone->zone_start_pfn = zone_start_pfn;
+
+ if ((zone_start_pfn) & (zone_required_alignment-1))
+ printk(KERN_CRIT "BUG: wrong zone alignment, it will
crash\n");
+
+ memmap_init(size, nid, j, zone_start_pfn);
+
+ zone_start_pfn += size;
+
+ zone_init_free_lists(pgdat, zone, zone->spanned_pages);
+ }
+}
+
+void __init node_alloc_mem_map(struct pglist_data *pgdat)
+{
+ unsigned long size;
+
+ size = (pgdat->node_spanned_pages + 1) * sizeof(struct page);
+ pgdat->node_mem_map = alloc_bootmem_node(pgdat, size);
+#ifndef CONFIG_DISCONTIGMEM
+ mem_map = contig_page_data.node_mem_map;
+#endif
+}
+
+void __init free_area_init_node(int nid, struct pglist_data *pgdat,
+ unsigned long *zones_size, unsigned long node_start_pfn,
+ unsigned long *zholes_size)
+{
+ pgdat->node_id = nid;
+ pgdat->node_start_pfn = node_start_pfn;
+ calculate_zone_totalpages(pgdat, zones_size, zholes_size);
+
+ if (!pfn_to_page(node_start_pfn))
+ node_alloc_mem_map(pgdat);
+
+ free_area_init_core(pgdat, zones_size, zholes_size);
+}
+
+#ifndef CONFIG_DISCONTIGMEM
+static bootmem_data_t contig_bootmem_data;
+struct pglist_data contig_page_data = { .bdata = &contig_bootmem_data };
+
+EXPORT_SYMBOL(contig_page_data);
+
+void __init free_area_init(unsigned long *zones_size)
+{
+ free_area_init_node(0, &contig_page_data, zones_size,
+ __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
+}
+#endif
+
+#ifdef CONFIG_PROC_FS
+
+#include <linux/seq_file.h>
+
+static void *frag_start(struct seq_file *m, loff_t *pos)
+{
+ pg_data_t *pgdat;
+ loff_t node = *pos;
+
+ for (pgdat = pgdat_list; pgdat && node; pgdat = pgdat->pgdat_next)
+ --node;
+
+ return pgdat;
+}
+
+static void *frag_next(struct seq_file *m, void *arg, loff_t *pos)
+{
+ pg_data_t *pgdat = (pg_data_t *)arg;
+
+ (*pos)++;
+ return pgdat->pgdat_next;
+}
+
+static void frag_stop(struct seq_file *m, void *arg)
+{
+}
+
+/*
+ * This walks the free areas for each zone.
+ */
+static int frag_show(struct seq_file *m, void *arg)
+{
+ pg_data_t *pgdat = (pg_data_t *)arg;
+ struct zone *zone;
+ struct zone *node_zones = pgdat->node_zones;
+ unsigned long flags;
+ int order;
+
+ for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
+ if (!zone->present_pages)
+ continue;
+
+ spin_lock_irqsave(&zone->lock, flags);
+ seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
+ for (order = 0; order < MAX_ORDER; ++order)
+ seq_printf(m, "%6lu ", zone->free_area[order].nr_free);
+ spin_unlock_irqrestore(&zone->lock, flags);
+ seq_putc(m, '\n');
+ }
+ return 0;
+}
+
+struct seq_operations fragmentation_op = {
+ .start = frag_start,
+ .next = frag_next,
+ .stop = frag_stop,
+ .show = frag_show,
+};
+
+static char *vmstat_text[] = {
+ "nr_dirty",
+ "nr_writeback",
+ "nr_unstable",
+ "nr_page_table_pages",
+ "nr_mapped",
+ "nr_slab",
+
+ "pgpgin",
+ "pgpgout",
+ "pswpin",
+ "pswpout",
+ "pgalloc_high",
+
+ "pgalloc_normal",
+ "pgalloc_dma",
+ "pgfree",
+ "pgactivate",
+ "pgdeactivate",
+
+ "pgfault",
+ "pgmajfault",
+ "pgrefill_high",
+ "pgrefill_normal",
+ "pgrefill_dma",
+
+ "pgsteal_high",
+ "pgsteal_normal",
+ "pgsteal_dma",
+ "pgscan_kswapd_high",
+ "pgscan_kswapd_normal",
+
+ "pgscan_kswapd_dma",
+ "pgscan_direct_high",
+ "pgscan_direct_normal",
+ "pgscan_direct_dma",
+ "pginodesteal",
+
+ "slabs_scanned",
+ "kswapd_steal",
+ "kswapd_inodesteal",
+ "pageoutrun",
+ "allocstall",
+
+ "pgrotated",
+};
+
+static void *vmstat_start(struct seq_file *m, loff_t *pos)
+{
+ struct page_state *ps;
+
+ if (*pos >= ARRAY_SIZE(vmstat_text))
+ return NULL;
+
+ ps = kmalloc(sizeof(*ps), GFP_KERNEL);
+ m->private = ps;
+ if (!ps)
+ return ERR_PTR(-ENOMEM);
+ get_full_page_state(ps);
+ ps->pgpgin /= 2; /* sectors -> kbytes */
+ ps->pgpgout /= 2;
+ return (unsigned long *)ps + *pos;
+}
+
+static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos)
+{
+ (*pos)++;
+ if (*pos >= ARRAY_SIZE(vmstat_text))
+ return NULL;
+ return (unsigned long *)m->private + *pos;
+}
+
+static int vmstat_show(struct seq_file *m, void *arg)
+{
+ unsigned long *l = arg;
+ unsigned long off = l - (unsigned long *)m->private;
+
+ seq_printf(m, "%s %lu\n", vmstat_text[off], *l);
+ return 0;
+}
+
+static void vmstat_stop(struct seq_file *m, void *arg)
+{
+ kfree(m->private);
+ m->private = NULL;
+}
+
+struct seq_operations vmstat_op = {
+ .start = vmstat_start,
+ .next = vmstat_next,
+ .stop = vmstat_stop,
+ .show = vmstat_show,
+};
+
+#endif /* CONFIG_PROC_FS */
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int page_alloc_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ int cpu = (unsigned long)hcpu;
+ long *count;
+ unsigned long *src, *dest;
+
+ if (action == CPU_DEAD) {
+ int i;
+
+ /* Drain local pagecache count. */
+ count = &per_cpu(nr_pagecache_local, cpu);
+ atomic_add(*count, &nr_pagecache);
+ *count = 0;
+ local_irq_disable();
+ __drain_pages(cpu);
+
+ /* Add dead cpu's page_states to our own. */
+ dest = (unsigned long *)&__get_cpu_var(page_states);
+ src = (unsigned long *)&per_cpu(page_states, cpu);
+
+ for (i = 0; i < sizeof(struct page_state)/sizeof(unsigned long);
+ i++) {
+ dest[i] += src[i];
+ src[i] = 0;
+ }
+
+ local_irq_enable();
+ }
+ return NOTIFY_OK;
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+void __init page_alloc_init(void)
+{
+ hotcpu_notifier(page_alloc_cpu_notify, 0);
+}
+
+/*
+ * setup_per_zone_lowmem_reserve - called whenever
+ * sysctl_lower_zone_reserve_ratio changes. Ensures that each zone
+ * has a correct pages reserved value, so an adequate number of
+ * pages are left in the zone after a successful __alloc_pages().
+ */
+static void setup_per_zone_lowmem_reserve(void)
+{
+ struct pglist_data *pgdat;
+ int j, idx;
+
+ for_each_pgdat(pgdat) {
+ for (j = 0; j < MAX_NR_ZONES; j++) {
+ struct zone * zone = pgdat->node_zones + j;
+ unsigned long present_pages = zone->present_pages;
+
+ zone->lowmem_reserve[j] = 0;
+
+ for (idx = j-1; idx >= 0; idx--) {
+ struct zone * lower_zone = pgdat->node_zones +
idx;
+
+ lower_zone->lowmem_reserve[j] = present_pages /
sysctl_lowmem_reserve_ratio[idx];
+ present_pages += lower_zone->present_pages;
+ }
+ }
+ }
+}
+
+/*
+ * setup_per_zone_pages_min - called when min_free_kbytes changes. Ensures
+ * that the pages_{min,low,high} values for each zone are set correctly
+ * with respect to min_free_kbytes.
+ */
+static void setup_per_zone_pages_min(void)
+{
+ unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
+ unsigned long lowmem_pages = 0;
+ struct zone *zone;
+ unsigned long flags;
+
+ /* Calculate total number of !ZONE_HIGHMEM pages */
+ for_each_zone(zone) {
+ if (!is_highmem(zone))
+ lowmem_pages += zone->present_pages;
+ }
+
+ for_each_zone(zone) {
+ spin_lock_irqsave(&zone->lru_lock, flags);
+ if (is_highmem(zone)) {
+ /*
+ * Often, highmem doesn't need to reserve any pages.
+ * But the pages_min/low/high values are also used for
+ * batching up page reclaim activity so we need a
+ * decent value here.
+ */
+ int min_pages;
+
+ min_pages = zone->present_pages / 1024;
+ if (min_pages < SWAP_CLUSTER_MAX)
+ min_pages = SWAP_CLUSTER_MAX;
+ if (min_pages > 128)
+ min_pages = 128;
+ zone->pages_min = min_pages;
+ } else {
+ /* if it's a lowmem zone, reserve a number of pages
+ * proportionate to the zone's size.
+ */
+ zone->pages_min = (pages_min * zone->present_pages) /
+ lowmem_pages;
+ }
+
+ /*
+ * When interpreting these watermarks, just keep in mind that:
+ * zone->pages_min == (zone->pages_min * 4) / 4;
+ */
+ zone->pages_low = (zone->pages_min * 5) / 4;
+ zone->pages_high = (zone->pages_min * 6) / 4;
+ spin_unlock_irqrestore(&zone->lru_lock, flags);
+ }
+}
+
+/*
+ * Initialise min_free_kbytes.
+ *
+ * For small machines we want it small (128k min). For large machines
+ * we want it large (64MB max). But it is not linear, because network
+ * bandwidth does not increase linearly with machine size. We use
+ *
+ * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
+ * min_free_kbytes = sqrt(lowmem_kbytes * 16)
+ *
+ * which yields
+ *
+ * 16MB: 512k
+ * 32MB: 724k
+ * 64MB: 1024k
+ * 128MB: 1448k
+ * 256MB: 2048k
+ * 512MB: 2896k
+ * 1024MB: 4096k
+ * 2048MB: 5792k
+ * 4096MB: 8192k
+ * 8192MB: 11584k
+ * 16384MB: 16384k
+ */
+static int __init init_per_zone_pages_min(void)
+{
+ unsigned long lowmem_kbytes;
+
+ lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10);
+
+ min_free_kbytes = int_sqrt(lowmem_kbytes * 16);
+ if (min_free_kbytes < 128)
+ min_free_kbytes = 128;
+ if (min_free_kbytes > 65536)
+ min_free_kbytes = 65536;
+ setup_per_zone_pages_min();
+ setup_per_zone_lowmem_reserve();
+ return 0;
+}
+module_init(init_per_zone_pages_min)
+
+/*
+ * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
+ * that we can call two helper functions whenever min_free_kbytes
+ * changes.
+ */
+int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
+ struct file *file, void __user *buffer, size_t *length, loff_t
*ppos)
+{
+ proc_dointvec(table, write, file, buffer, length, ppos);
+ setup_per_zone_pages_min();
+ return 0;
+}
+
+/*
+ * lowmem_reserve_ratio_sysctl_handler - just a wrapper around
+ * proc_dointvec() so that we can call setup_per_zone_lowmem_reserve()
+ * whenever sysctl_lowmem_reserve_ratio changes.
+ *
+ * The reserve ratio obviously has absolutely no relation with the
+ * pages_min watermarks. The lowmem reserve ratio can only make sense
+ * if in function of the boot time zone sizes.
+ */
+int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
+ struct file *file, void __user *buffer, size_t *length, loff_t
*ppos)
+{
+ proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+ setup_per_zone_lowmem_reserve();
+ return 0;
+}
+
+__initdata int hashdist = HASHDIST_DEFAULT;
+
+#ifdef CONFIG_NUMA
+static int __init set_hashdist(char *str)
+{
+ if (!str)
+ return 0;
+ hashdist = simple_strtoul(str, &str, 0);
+ return 1;
+}
+__setup("hashdist=", set_hashdist);
+#endif
+
+/*
+ * allocate a large system hash table from bootmem
+ * - it is assumed that the hash table must contain an exact power-of-2
+ * quantity of entries
+ * - limit is the number of hash buckets, not the total allocation size
+ */
+void *__init alloc_large_system_hash(const char *tablename,
+ unsigned long bucketsize,
+ unsigned long numentries,
+ int scale,
+ int flags,
+ unsigned int *_hash_shift,
+ unsigned int *_hash_mask,
+ unsigned long limit)
+{
+ unsigned long long max = limit;
+ unsigned long log2qty, size;
+ void *table = NULL;
+
+ /* allow the kernel cmdline to have a say */
+ if (!numentries) {
+ /* round applicable memory size up to nearest megabyte */
+ numentries = (flags & HASH_HIGHMEM) ? nr_all_pages :
nr_kernel_pages;
+ numentries += (1UL << (20 - PAGE_SHIFT)) - 1;
+ numentries >>= 20 - PAGE_SHIFT;
+ numentries <<= 20 - PAGE_SHIFT;
+
+ /* limit to 1 bucket per 2^scale bytes of low memory */
+ if (scale > PAGE_SHIFT)
+ numentries >>= (scale - PAGE_SHIFT);
+ else
+ numentries <<= (PAGE_SHIFT - scale);
+ }
+ /* rounded up to nearest power of 2 in size */
+ numentries = 1UL << (long_log2(numentries) + 1);
+
+ /* limit allocation size to 1/16 total memory by default */
+ if (max == 0) {
+ max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4;
+ do_div(max, bucketsize);
+ }
+
+ if (numentries > max)
+ numentries = max;
+
+ log2qty = long_log2(numentries);
+
+ do {
+ size = bucketsize << log2qty;
+ if (flags & HASH_EARLY)
+ table = alloc_bootmem(size);
+ else if (hashdist)
+ table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
+ else {
+ unsigned long order;
+ for (order = 0; ((1UL << order) << PAGE_SHIFT) < size;
order++)
+ ;
+ table = (void*) __get_free_pages(GFP_ATOMIC, order);
+ }
+ } while (!table && size > PAGE_SIZE && --log2qty);
+
+ if (!table)
+ panic("Failed to allocate %s hash table\n", tablename);
+
+ printk("%s hash table entries: %d (order: %d, %lu bytes)\n",
+ tablename,
+ (1U << log2qty),
+ long_log2(size) - PAGE_SHIFT,
+ size);
+
+ if (_hash_shift)
+ *_hash_shift = log2qty;
+ if (_hash_mask)
+ *_hash_mask = (1 << log2qty) - 1;
+
+ return table;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/vmlinux.lds
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/vmlinux.lds Fri Jul 15 13:39:50 2005
@@ -0,0 +1,75 @@
+/* ld script to make i386 Linux kernel
+ * Written by Martin Mares <mj@xxxxxxxxxxxxxxxxxxxxxxxx>;
+ */
+OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
+OUTPUT_ARCH(i386)
+ENTRY(_start)
+SECTIONS
+{
+ . = 0xC0000000 + 0x100000;
+ _text = .; /* Text and read-only data */
+ .text : {
+ *(.text)
+ *(.fixup)
+ *(.gnu.warning)
+ } = 0x9090
+
+ _etext = .; /* End of text section */
+
+ .rodata : { *(.rodata) *(.rodata.*) }
+ .kstrtab : { *(.kstrtab) }
+
+ . = ALIGN(16); /* Exception table */
+ __start___ex_table = .;
+ __ex_table : { *(__ex_table) }
+ __stop___ex_table = .;
+
+ __start___ksymtab = .; /* Kernel symbol table */
+ __ksymtab : { *(__ksymtab) }
+ __stop___ksymtab = .;
+
+ .data : { /* Data */
+ *(.data)
+ CONSTRUCTORS
+ }
+
+ _edata = .; /* End of data section */
+
+ . = ALIGN(8192); /* init_task */
+ .data.init_task : { *(.data.init_task) }
+
+ . = ALIGN(4096); /* Init code and data */
+ __init_begin = .;
+ .text.init : { *(.text.init) }
+ .data.init : { *(.data.init) }
+ . = ALIGN(16);
+ __setup_start = .;
+ .setup.init : { *(.setup.init) }
+ __setup_end = .;
+ __initcall_start = .;
+ .initcall.init : { *(.initcall.init) }
+ __initcall_end = .;
+ . = ALIGN(4096);
+ __init_end = .;
+
+ . = ALIGN(4096);
+ .data.page_aligned : { *(.data.idt) }
+
+ . = ALIGN(32);
+ .data.cacheline_aligned : { *(.data.cacheline_aligned) }
+
+ __bss_start = .; /* BSS */
+ .bss : {
+ *(.bss)
+ }
+ _end = . ;
+
+ /* Stabs debugging sections. */
+ .stab 0 : { *(.stab) }
+ .stabstr 0 : { *(.stabstr) }
+ .stab.excl 0 : { *(.stab.excl) }
+ .stab.exclstr 0 : { *(.stab.exclstr) }
+ .stab.index 0 : { *(.stab.index) }
+ .stab.indexstr 0 : { *(.stab.indexstr) }
+ .comment 0 : { *(.comment) }
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/mm/fault.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/mm/fault.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,592 @@
+/*
+ * linux/arch/x86-64/mm/fault.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ * Copyright (C) 2001,2002 Andi Kleen, SuSE Labs.
+ */
+
+#include <linux/config.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/tty.h>
+#include <linux/vt_kern.h> /* For unblank_screen() */
+#include <linux/compiler.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/kprobes.h>
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+#include <asm/smp.h>
+#include <asm/tlbflush.h>
+#include <asm/proto.h>
+#include <asm/kdebug.h>
+#include <asm-generic/sections.h>
+#include <asm/kdebug.h>
+
+DEFINE_PER_CPU(pgd_t *, cur_pgd);
+
+void bust_spinlocks(int yes)
+{
+ int loglevel_save = console_loglevel;
+ if (yes) {
+ oops_in_progress = 1;
+ } else {
+#ifdef CONFIG_VT
+ unblank_screen();
+#endif
+ oops_in_progress = 0;
+ /*
+ * OK, the message is on the console. Now we call printk()
+ * without oops_in_progress set so that printk will give klogd
+ * a poke. Hold onto your hats...
+ */
+ console_loglevel = 15; /* NMI oopser may have shut the
console up */
+ printk(" ");
+ console_loglevel = loglevel_save;
+ }
+}
+
+/* Sometimes the CPU reports invalid exceptions on prefetch.
+ Check that here and ignore.
+ Opcode checker based on code by Richard Brunner */
+static noinline int is_prefetch(struct pt_regs *regs, unsigned long addr,
+ unsigned long error_code)
+{
+ unsigned char *instr = (unsigned char *)(regs->rip);
+ int scan_more = 1;
+ int prefetch = 0;
+ unsigned char *max_instr = instr + 15;
+
+ /* If it was a exec fault ignore */
+ if (error_code & (1<<4))
+ return 0;
+
+ /* Code segments in LDT could have a non zero base. Don't check
+ when that's possible */
+ if (regs->cs & (1<<2))
+ return 0;
+
+ if ((regs->cs & 3) != 0 && regs->rip >= TASK_SIZE)
+ return 0;
+
+ while (scan_more && instr < max_instr) {
+ unsigned char opcode;
+ unsigned char instr_hi;
+ unsigned char instr_lo;
+
+ if (__get_user(opcode, instr))
+ break;
+
+ instr_hi = opcode & 0xf0;
+ instr_lo = opcode & 0x0f;
+ instr++;
+
+ switch (instr_hi) {
+ case 0x20:
+ case 0x30:
+ /* Values 0x26,0x2E,0x36,0x3E are valid x86
+ prefixes. In long mode, the CPU will signal
+ invalid opcode if some of these prefixes are
+ present so we will never get here anyway */
+ scan_more = ((instr_lo & 7) == 0x6);
+ break;
+
+ case 0x40:
+ /* In AMD64 long mode, 0x40 to 0x4F are valid REX
prefixes
+ Need to figure out under what instruction mode the
+ instruction was issued ... */
+ /* Could check the LDT for lm, but for now it's good
+ enough to assume that long mode only uses well known
+ segments or kernel. */
+ scan_more = ((regs->cs & 3) == 0) || (regs->cs ==
__USER_CS);
+ break;
+
+ case 0x60:
+ /* 0x64 thru 0x67 are valid prefixes in all modes. */
+ scan_more = (instr_lo & 0xC) == 0x4;
+ break;
+ case 0xF0:
+ /* 0xF0, 0xF2, and 0xF3 are valid prefixes in all
modes. */
+ scan_more = !instr_lo || (instr_lo>>1) == 1;
+ break;
+ case 0x00:
+ /* Prefetch instruction is 0x0F0D or 0x0F18 */
+ scan_more = 0;
+ if (__get_user(opcode, instr))
+ break;
+ prefetch = (instr_lo == 0xF) &&
+ (opcode == 0x0D || opcode == 0x18);
+ break;
+ default:
+ scan_more = 0;
+ break;
+ }
+ }
+ return prefetch;
+}
+
+static int bad_address(void *p)
+{
+ unsigned long dummy;
+ return __get_user(dummy, (unsigned long *)p);
+}
+
+void dump_pagetable(unsigned long address)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pgd = (pgd_t *)per_cpu(cur_pgd, smp_processor_id());
+ pgd += pgd_index(address);
+
+ printk("PGD %lx ", pgd_val(*pgd));
+ if (bad_address(pgd)) goto bad;
+ if (!pgd_present(*pgd)) goto ret;
+
+ pud = __pud_offset_k((pud_t *)pgd_page(*pgd), address);
+ if (bad_address(pud)) goto bad;
+ printk("PUD %lx ", pud_val(*pud));
+ if (!pud_present(*pud)) goto ret;
+
+ pmd = pmd_offset(pud, address);
+ if (bad_address(pmd)) goto bad;
+ printk("PMD %lx ", pmd_val(*pmd));
+ if (!pmd_present(*pmd)) goto ret;
+
+ pte = pte_offset_kernel(pmd, address);
+ if (bad_address(pte)) goto bad;
+ printk("PTE %lx", pte_val(*pte));
+ret:
+ printk("\n");
+ return;
+bad:
+ printk("BAD\n");
+}
+
+static const char errata93_warning[] =
+KERN_ERR "******* Your BIOS seems to not contain a fix for K8 errata #93\n"
+KERN_ERR "******* Working around it, but it may cause SEGVs or burn power.\n"
+KERN_ERR "******* Please consider a BIOS update.\n"
+KERN_ERR "******* Disabling USB legacy in the BIOS may also help.\n";
+
+/* Workaround for K8 erratum #93 & buggy BIOS.
+ BIOS SMM functions are required to use a specific workaround
+ to avoid corruption of the 64bit RIP register on C stepping K8.
+ A lot of BIOS that didn't get tested properly miss this.
+ The OS sees this as a page fault with the upper 32bits of RIP cleared.
+ Try to work around it here.
+ Note we only handle faults in kernel here. */
+
+static int is_errata93(struct pt_regs *regs, unsigned long address)
+{
+ static int warned;
+ if (address != regs->rip)
+ return 0;
+ if ((address >> 32) != 0)
+ return 0;
+ address |= 0xffffffffUL << 32;
+ if ((address >= (u64)_stext && address <= (u64)_etext) ||
+ (address >= MODULES_VADDR && address <= MODULES_END)) {
+ if (!warned) {
+ printk(errata93_warning);
+ warned = 1;
+ }
+ regs->rip = address;
+ return 1;
+ }
+ return 0;
+}
+
+int unhandled_signal(struct task_struct *tsk, int sig)
+{
+ if (tsk->pid == 1)
+ return 1;
+ /* Warn for strace, but not for gdb */
+ if (!test_ti_thread_flag(tsk->thread_info, TIF_SYSCALL_TRACE) &&
+ (tsk->ptrace & PT_PTRACED))
+ return 0;
+ return (tsk->sighand->action[sig-1].sa.sa_handler == SIG_IGN) ||
+ (tsk->sighand->action[sig-1].sa.sa_handler == SIG_DFL);
+}
+
+static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
+ unsigned long error_code)
+{
+ oops_begin();
+ printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
+ current->comm, address);
+ dump_pagetable(address);
+ __die("Bad pagetable", regs, error_code);
+ oops_end();
+ do_exit(SIGKILL);
+}
+
+/*
+ * Handle a fault on the vmalloc or module mapping area
+ */
+static int vmalloc_fault(unsigned long address)
+{
+ pgd_t *pgd, *pgd_ref;
+ pud_t *pud, *pud_ref;
+ pmd_t *pmd, *pmd_ref;
+ pte_t *pte, *pte_ref;
+
+ /* Copy kernel mappings over when needed. This can also
+ happen within a race in page table update. In the later
+ case just flush. */
+
+ pgd = pgd_offset(current->mm ?: &init_mm, address);
+ pgd_ref = pgd_offset_k(address);
+ if (pgd_none(*pgd_ref))
+ return -1;
+ if (pgd_none(*pgd))
+ set_pgd(pgd, *pgd_ref);
+
+ /* Below here mismatches are bugs because these lower tables
+ are shared */
+
+ pud = pud_offset(pgd, address);
+ pud_ref = pud_offset(pgd_ref, address);
+ if (pud_none(*pud_ref))
+ return -1;
+ if (pud_none(*pud) || pud_page(*pud) != pud_page(*pud_ref))
+ BUG();
+ pmd = pmd_offset(pud, address);
+ pmd_ref = pmd_offset(pud_ref, address);
+ if (pmd_none(*pmd_ref))
+ return -1;
+ if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref))
+ BUG();
+ pte_ref = pte_offset_kernel(pmd_ref, address);
+ if (!pte_present(*pte_ref))
+ return -1;
+ pte = pte_offset_kernel(pmd, address);
+ if (!pte_present(*pte) || pte_page(*pte) != pte_page(*pte_ref))
+ BUG();
+ __flush_tlb_all();
+ return 0;
+}
+
+int page_fault_trace = 0;
+int exception_trace = 1;
+
+
+#define MEM_VERBOSE 1
+
+#ifdef MEM_VERBOSE
+#define MEM_LOG(_f, _a...) \
+ printk("fault.c:[%d]-> " _f "\n", \
+ __LINE__ , ## _a )
+#else
+#define MEM_LOG(_f, _a...) ((void)0)
+#endif
+
+/*
+ * This routine handles page faults. It determines the address,
+ * and the problem, and then passes it off to one of the appropriate
+ * routines.
+ *
+ * error_code:
+ * bit 0 == 0 means no page found, 1 means protection fault
+ * bit 1 == 0 means read, 1 means write
+ * bit 2 == 0 means kernel, 1 means user-mode
+ * bit 3 == 1 means fault was an instruction fetch
+ */
+asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
+{
+ struct task_struct *tsk;
+ struct mm_struct *mm;
+ struct vm_area_struct * vma;
+ const struct exception_table_entry *fixup;
+ int write;
+ siginfo_t info;
+
+ if (!user_mode(regs))
+ error_code &= ~4; /* means kernel */
+
+#ifdef CONFIG_CHECKING
+ {
+ unsigned long gs;
+ struct x8664_pda *pda = cpu_pda + stack_smp_processor_id();
+ rdmsrl(MSR_GS_BASE, gs);
+ if (gs != (unsigned long)pda) {
+ wrmsrl(MSR_GS_BASE, pda);
+ printk("page_fault: wrong gs %lx expected %p\n", gs,
pda);
+ }
+ }
+#endif
+ if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
+ SIGSEGV) == NOTIFY_STOP)
+ return;
+
+ if (likely(regs->eflags & X86_EFLAGS_IF))
+ local_irq_enable();
+
+ if (unlikely(page_fault_trace))
+ printk("pagefault rip:%lx rsp:%lx cs:%lu ss:%lu address %lx
error %lx\n",
+
regs->rip,regs->rsp,regs->cs,regs->ss,address,error_code);
+
+ tsk = current;
+ mm = tsk->mm;
+ info.si_code = SEGV_MAPERR;
+
+
+ /*
+ * We fault-in kernel-space virtual memory on-demand. The
+ * 'reference' page table is init_mm.pgd.
+ *
+ * NOTE! We MUST NOT take any locks for this case. We may
+ * be in an interrupt or a critical region, and should
+ * only copy the information from the master page table,
+ * nothing more.
+ *
+ * This verifies that the fault happens in kernel space
+ * (error_code & 4) == 0, and that the fault was not a
+ * protection error (error_code & 1) == 0.
+ */
+ if (unlikely(address >= TASK_SIZE)) {
+ if (!(error_code & 5)) {
+ if (vmalloc_fault(address) < 0)
+ goto bad_area_nosemaphore;
+ return;
+ }
+ /*
+ * Don't take the mm semaphore here. If we fixup a prefetch
+ * fault we could otherwise deadlock.
+ */
+ goto bad_area_nosemaphore;
+ }
+
+ if (unlikely(error_code & (1 << 3)))
+ pgtable_bad(address, regs, error_code);
+
+ /*
+ * If we're in an interrupt or have no user
+ * context, we must not take the fault..
+ */
+ if (unlikely(in_atomic() || !mm))
+ goto bad_area_nosemaphore;
+
+ again:
+ /* When running in the kernel we expect faults to occur only to
+ * addresses in user space. All other faults represent errors in the
+ * kernel and should generate an OOPS. Unfortunatly, in the case of an
+ * erroneous fault occuring in a code path which already holds mmap_sem
+ * we will deadlock attempting to validate the fault against the
+ * address space. Luckily the kernel only validly references user
+ * space from well defined areas of code, which are listed in the
+ * exceptions table.
+ *
+ * As the vast majority of faults will be valid we will only perform
+ * the source reference check when there is a possibilty of a deadlock.
+ * Attempt to lock the address space, if we cannot we then validate the
+ * source. If this is invalid we can skip the address space check,
+ * thus avoiding the deadlock.
+ */
+ if (!down_read_trylock(&mm->mmap_sem)) {
+ if ((error_code & 4) == 0 &&
+ !search_exception_tables(regs->rip))
+ goto bad_area_nosemaphore;
+ down_read(&mm->mmap_sem);
+ }
+
+ vma = find_vma(mm, address);
+ if (!vma)
+ goto bad_area;
+ if (likely(vma->vm_start <= address))
+ goto good_area;
+ if (!(vma->vm_flags & VM_GROWSDOWN))
+ goto bad_area;
+ if (error_code & 4) {
+ // XXX: align red zone size with ABI
+ if (address + 128 < regs->rsp)
+ goto bad_area;
+ }
+ if (expand_stack(vma, address))
+ goto bad_area;
+/*
+ * Ok, we have a good vm_area for this memory access, so
+ * we can handle it..
+ */
+good_area:
+ info.si_code = SEGV_ACCERR;
+ write = 0;
+ switch (error_code & 3) {
+ default: /* 3: write, present */
+ /* fall through */
+ case 2: /* write, not present */
+ if (!(vma->vm_flags & VM_WRITE))
+ goto bad_area;
+ write++;
+ break;
+ case 1: /* read, present */
+ goto bad_area;
+ case 0: /* read, not present */
+ if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+ goto bad_area;
+ }
+
+ /*
+ * If for any reason at all we couldn't handle the fault,
+ * make sure we exit gracefully rather than endlessly redo
+ * the fault.
+ */
+ switch (handle_mm_fault(mm, vma, address, write)) {
+ case 1:
+ tsk->min_flt++;
+ break;
+ case 2:
+ tsk->maj_flt++;
+ break;
+ case 0:
+ goto do_sigbus;
+ default:
+ goto out_of_memory;
+ }
+
+ up_read(&mm->mmap_sem);
+ return;
+
+/*
+ * Something tried to access memory that isn't in our memory map..
+ * Fix it, but check if it's kernel or user first..
+ */
+bad_area:
+ up_read(&mm->mmap_sem);
+
+bad_area_nosemaphore:
+
+#ifdef CONFIG_IA32_EMULATION
+ /* 32bit vsyscall. map on demand. */
+ if (test_thread_flag(TIF_IA32) &&
+ address >= VSYSCALL32_BASE && address < VSYSCALL32_END) {
+ if (map_syscall32(mm, address) < 0)
+ goto out_of_memory2;
+ return;
+ }
+#endif
+
+ /* User mode accesses just cause a SIGSEGV */
+ if (error_code & 4) {
+ if (is_prefetch(regs, address, error_code))
+ return;
+
+ /* Work around K8 erratum #100 K8 in compat mode
+ occasionally jumps to illegal addresses >4GB. We
+ catch this here in the page fault handler because
+ these addresses are not reachable. Just detect this
+ case and return. Any code segment in LDT is
+ compatibility mode. */
+ if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) &&
+ (address >> 32))
+ return;
+
+ if (exception_trace && unhandled_signal(tsk, SIGSEGV)) {
+ printk(
+ "%s%s[%d]: segfault at %016lx rip %016lx rsp %016lx
error %lx\n",
+ tsk->pid > 1 ? KERN_INFO : KERN_EMERG,
+ tsk->comm, tsk->pid, address, regs->rip,
+ regs->rsp, error_code);
+ }
+
+ tsk->thread.cr2 = address;
+ /* Kernel addresses are always protection faults */
+ tsk->thread.error_code = error_code | (address >= TASK_SIZE);
+ tsk->thread.trap_no = 14;
+ info.si_signo = SIGSEGV;
+ info.si_errno = 0;
+ /* info.si_code has been set above */
+ info.si_addr = (void __user *)address;
+ force_sig_info(SIGSEGV, &info, tsk);
+ return;
+ }
+
+no_context:
+
+ /* Are we prepared to handle this kernel fault? */
+ fixup = search_exception_tables(regs->rip);
+ if (fixup) {
+ regs->rip = fixup->fixup;
+ return;
+ }
+
+ /*
+ * Hall of shame of CPU/BIOS bugs.
+ */
+
+ if (is_prefetch(regs, address, error_code))
+ return;
+
+ if (is_errata93(regs, address))
+ return;
+
+/*
+ * Oops. The kernel tried to access some bad page. We'll have to
+ * terminate things with extreme prejudice.
+ */
+
+ oops_begin();
+
+ if (address < PAGE_SIZE)
+ printk(KERN_ALERT "Unable to handle kernel NULL pointer
dereference");
+ else
+ printk(KERN_ALERT "Unable to handle kernel paging request");
+ printk(" at %016lx RIP: \n" KERN_ALERT,address);
+ printk_address(regs->rip);
+ printk("\n");
+ dump_pagetable(address);
+ __die("Oops", regs, error_code);
+ /* Executive summary in case the body of the oops scrolled away */
+ printk(KERN_EMERG "CR2: %016lx\n", address);
+ oops_end();
+ do_exit(SIGKILL);
+
+/*
+ * We ran out of memory, or some other thing happened to us that made
+ * us unable to handle the page fault gracefully.
+ */
+out_of_memory:
+ up_read(&mm->mmap_sem);
+out_of_memory2:
+ if (current->pid == 1) {
+ yield();
+ goto again;
+ }
+ printk("VM: killing process %s\n", tsk->comm);
+ if (error_code & 4)
+ do_exit(SIGKILL);
+ goto no_context;
+
+do_sigbus:
+ up_read(&mm->mmap_sem);
+
+ /* Kernel mode? Handle exceptions or die */
+ if (!(error_code & 4))
+ goto no_context;
+
+ tsk->thread.cr2 = address;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = 14;
+ info.si_signo = SIGBUS;
+ info.si_errno = 0;
+ info.si_code = BUS_ADRERR;
+ info.si_addr = (void __user *)address;
+ force_sig_info(SIGBUS, &info, tsk);
+ return;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/fixmap.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/fixmap.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,114 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ */
+
+#ifndef _ASM_FIXMAP_H
+#define _ASM_FIXMAP_H
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <asm/apicdef.h>
+#include <asm-xen/gnttab.h>
+#include <asm/page.h>
+#include <asm/vsyscall.h>
+#include <asm/vsyscall32.h>
+#include <asm/acpi.h>
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process.
+ *
+ * these 'compile-time allocated' memory buffers are
+ * fixed-size 4k pages. (or larger if used with an increment
+ * highger than 1) use fixmap_set(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ * TLB entries of such buffers will not be flushed across
+ * task switches.
+ */
+
+enum fixed_addresses {
+ VSYSCALL_LAST_PAGE,
+ VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE +
((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1,
+ VSYSCALL_HPET,
+ FIX_HPET_BASE,
+#ifdef CONFIG_X86_LOCAL_APIC
+ FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */
+#endif
+#ifdef CONFIG_X86_IO_APIC
+ FIX_IO_APIC_BASE_0,
+ FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS-1,
+#endif
+#ifdef CONFIG_ACPI_BOOT
+ FIX_ACPI_BEGIN,
+ FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
+ FIX_ACPI_RSDP_PAGE,
+#endif
+ FIX_SHARED_INFO,
+ FIX_GNTTAB_BEGIN,
+ FIX_GNTTAB_END = FIX_GNTTAB_BEGIN + NR_GRANT_FRAMES - 1,
+#ifdef CONFIG_XEN_PHYSDEV_ACCESS
+#define NR_FIX_ISAMAPS 256
+ FIX_ISAMAP_END,
+ FIX_ISAMAP_BEGIN = FIX_ISAMAP_END + NR_FIX_ISAMAPS - 1,
+#endif
+ __end_of_fixed_addresses
+};
+
+extern void __set_fixmap (enum fixed_addresses idx,
+ unsigned long phys, pgprot_t flags);
+
+#define set_fixmap(idx, phys) \
+ __set_fixmap(idx, phys, PAGE_KERNEL)
+/*
+ * Some hardware wants to get fixmapped without caching.
+ */
+#define set_fixmap_nocache(idx, phys) \
+ __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
+
+#define clear_fixmap(idx) \
+ __set_fixmap(idx, 0, __pgprot(0))
+
+#define FIXADDR_TOP (VSYSCALL_END-PAGE_SIZE)
+#define FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE)
+
+/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */
+#define FIXADDR_USER_START ((unsigned long)VSYSCALL32_VSYSCALL)
+#define FIXADDR_USER_END (FIXADDR_USER_START + PAGE_SIZE)
+
+#define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT))
+
+extern void __this_fixmap_does_not_exist(void);
+
+/*
+ * 'index to address' translation. If anyone tries to use the idx
+ * directly without translation, we catch the bug with a NULL-deference
+ * kernel oops. Illegal ranges of incoming indices are caught too.
+ */
+extern inline unsigned long fix_to_virt(const unsigned int idx)
+{
+ /*
+ * this branch gets completely eliminated after inlining,
+ * except when someone tries to use fixaddr indices in an
+ * illegal way. (such as mixing up address types or using
+ * out-of-range indices).
+ *
+ * If it doesn't get removed, the linker will complain
+ * loudly with a reasonably clear error message..
+ */
+ if (idx >= __end_of_fixed_addresses)
+ __this_fixmap_does_not_exist();
+
+ return __fix_to_virt(idx);
+}
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/drivers/evtchn/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/drivers/evtchn/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,3 @@
+O_TARGET := drv.o
+obj-y := evtchn.o
+include $(TOPDIR)/Rules.make
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/gnttab.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/gnttab.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,72 @@
+/******************************************************************************
+ * gnttab.h
+ *
+ * Two sets of functionality:
+ * 1. Granting foreign access to our memory reservation.
+ * 2. Accessing others' memory reservations via grant references.
+ * (i.e., mechanisms for both sender and recipient of grant references)
+ *
+ * Copyright (c) 2004, K A Fraser
+ * Copyright (c) 2005, Christopher Clark
+ */
+
+#ifndef __ASM_GNTTAB_H__
+#define __ASM_GNTTAB_H__
+
+#include <linux/config.h>
+#include <asm-xen/hypervisor.h>
+#include <asm-xen/xen-public/grant_table.h>
+
+/* NR_GRANT_FRAMES must be less than or equal to that configured in Xen */
+#define NR_GRANT_FRAMES 4
+#define NR_GRANT_ENTRIES (NR_GRANT_FRAMES * PAGE_SIZE / sizeof(grant_entry_t))
+
+int
+gnttab_grant_foreign_access(
+ domid_t domid, unsigned long frame, int readonly);
+
+void
+gnttab_end_foreign_access(
+ grant_ref_t ref, int readonly);
+
+int
+gnttab_grant_foreign_transfer(
+ domid_t domid, unsigned long pfn);
+
+unsigned long
+gnttab_end_foreign_transfer(
+ grant_ref_t ref);
+
+int
+gnttab_query_foreign_access(
+ grant_ref_t ref );
+
+/*
+ * operations on reserved batches of grant references
+ */
+int
+gnttab_alloc_grant_references(
+ u16 count, grant_ref_t *pprivate_head, grant_ref_t *private_terminal );
+
+void
+gnttab_free_grant_references(
+ u16 count, grant_ref_t private_head );
+
+int
+gnttab_claim_grant_reference( grant_ref_t *pprivate_head, grant_ref_t terminal
+);
+
+void
+gnttab_release_grant_reference(
+ grant_ref_t *private_head, grant_ref_t release );
+
+void
+gnttab_grant_foreign_access_ref(
+ grant_ref_t ref, domid_t domid, unsigned long frame, int readonly);
+
+void
+gnttab_grant_foreign_transfer_ref(
+ grant_ref_t, domid_t domid, unsigned long pfn);
+
+
+#endif /* __ASM_GNTTAB_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blkfront/blkfront.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blkfront/blkfront.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,1491 @@
+/******************************************************************************
+ * blkfront.c
+ *
+ * XenLinux virtual block-device driver.
+ *
+ * Copyright (c) 2003-2004, Keir Fraser & Steve Hand
+ * Modifications by Mark A. Williamson are (c) Intel Research Cambridge
+ * Copyright (c) 2004, Christian Limpach
+ * Copyright (c) 2004, Andrew Warfield
+ * Copyright (c) 2005, Christopher Clark
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#if 1
+#define ASSERT(_p) \
+ if ( !(_p) ) { printk("Assertion '%s' failed, line %d, file %s", #_p , \
+ __LINE__, __FILE__); *(int*)0=0; }
+#else
+#define ASSERT(_p)
+#endif
+
+#include <linux/version.h>
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+#include "block.h"
+#else
+#include "common.h"
+#include <linux/blk.h>
+#include <linux/tqueue.h>
+#endif
+
+#include <linux/cdrom.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <scsi/scsi.h>
+#include <asm-xen/ctrl_if.h>
+#include <asm-xen/evtchn.h>
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+#include <asm-xen/xen-public/grant_table.h>
+#include <asm-xen/gnttab.h>
+#endif
+
+typedef unsigned char byte; /* from linux/ide.h */
+
+/* Control whether runtime update of vbds is enabled. */
+#define ENABLE_VBD_UPDATE 1
+
+#if ENABLE_VBD_UPDATE
+static void vbd_update(void);
+#else
+static void vbd_update(void){};
+#endif
+
+#define BLKIF_STATE_CLOSED 0
+#define BLKIF_STATE_DISCONNECTED 1
+#define BLKIF_STATE_CONNECTED 2
+
+static int blkif_handle = 0;
+static unsigned int blkif_state = BLKIF_STATE_CLOSED;
+static unsigned int blkif_evtchn = 0;
+static unsigned int blkif_irq = 0;
+
+static int blkif_control_rsp_valid;
+static blkif_response_t blkif_control_rsp;
+
+static blkif_front_ring_t blk_ring;
+
+#define BLK_RING_SIZE __RING_SIZE((blkif_sring_t *)0, PAGE_SIZE)
+
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+static domid_t rdomid = 0;
+static grant_ref_t gref_head, gref_terminal;
+#define MAXIMUM_OUTSTANDING_BLOCK_REQS \
+ (BLKIF_MAX_SEGMENTS_PER_REQUEST * BLKIF_RING_SIZE)
+#define GRANTREF_INVALID (1<<15)
+#endif
+
+static struct blk_shadow {
+ blkif_request_t req;
+ unsigned long request;
+ unsigned long frame[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+} blk_shadow[BLK_RING_SIZE];
+unsigned long blk_shadow_free;
+
+static int recovery = 0; /* Recovery in progress: protected by blkif_io_lock */
+
+static void kick_pending_request_queues(void);
+
+int __init xlblk_init(void);
+
+static void blkif_completion(struct blk_shadow *s);
+
+static inline int GET_ID_FROM_FREELIST(void)
+{
+ unsigned long free = blk_shadow_free;
+ BUG_ON(free > BLK_RING_SIZE);
+ blk_shadow_free = blk_shadow[free].req.id;
+ blk_shadow[free].req.id = 0x0fffffee; /* debug */
+ return free;
+}
+
+static inline void ADD_ID_TO_FREELIST(unsigned long id)
+{
+ blk_shadow[id].req.id = blk_shadow_free;
+ blk_shadow[id].request = 0;
+ blk_shadow_free = id;
+}
+
+
+/************************ COMMON CODE (inlined) ************************/
+
+/* Kernel-specific definitions used in the common code */
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+#define DISABLE_SCATTERGATHER()
+#else
+static int sg_operation = -1;
+#define DISABLE_SCATTERGATHER() (sg_operation = -1)
+#endif
+
+static inline void pickle_request(struct blk_shadow *s, blkif_request_t *r)
+{
+#ifndef CONFIG_XEN_BLKDEV_GRANT
+ int i;
+#endif
+
+ s->req = *r;
+
+#ifndef CONFIG_XEN_BLKDEV_GRANT
+ for ( i = 0; i < r->nr_segments; i++ )
+ s->req.frame_and_sects[i] = machine_to_phys(r->frame_and_sects[i]);
+#endif
+}
+
+static inline void unpickle_request(blkif_request_t *r, struct blk_shadow *s)
+{
+#ifndef CONFIG_XEN_BLKDEV_GRANT
+ int i;
+#endif
+
+ *r = s->req;
+
+#ifndef CONFIG_XEN_BLKDEV_GRANT
+ for ( i = 0; i < s->req.nr_segments; i++ )
+ r->frame_and_sects[i] = phys_to_machine(s->req.frame_and_sects[i]);
+#endif
+}
+
+
+static inline void flush_requests(void)
+{
+ DISABLE_SCATTERGATHER();
+ RING_PUSH_REQUESTS(&blk_ring);
+ notify_via_evtchn(blkif_evtchn);
+}
+
+
+/************************** KERNEL VERSION 2.6 **************************/
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+
+module_init(xlblk_init);
+
+#if ENABLE_VBD_UPDATE
+static void update_vbds_task(void *unused)
+{
+ xlvbd_update_vbds();
+}
+
+static void vbd_update(void)
+{
+ static DECLARE_WORK(update_tq, update_vbds_task, NULL);
+ schedule_work(&update_tq);
+}
+#endif /* ENABLE_VBD_UPDATE */
+
+static struct xlbd_disk_info *head_waiting = NULL;
+static void kick_pending_request_queues(void)
+{
+ struct xlbd_disk_info *di;
+ while ( ((di = head_waiting) != NULL) && !RING_FULL(&blk_ring) )
+ {
+ head_waiting = di->next_waiting;
+ di->next_waiting = NULL;
+ /* Re-enable calldowns. */
+ blk_start_queue(di->rq);
+ /* Kick things off immediately. */
+ do_blkif_request(di->rq);
+ }
+}
+
+int blkif_open(struct inode *inode, struct file *filep)
+{
+ struct gendisk *gd = inode->i_bdev->bd_disk;
+ struct xlbd_disk_info *di = (struct xlbd_disk_info *)gd->private_data;
+
+ /* Update of usage count is protected by per-device semaphore. */
+ di->mi->usage++;
+
+ return 0;
+}
+
+
+int blkif_release(struct inode *inode, struct file *filep)
+{
+ struct gendisk *gd = inode->i_bdev->bd_disk;
+ struct xlbd_disk_info *di = (struct xlbd_disk_info *)gd->private_data;
+
+ /*
+ * When usage drops to zero it may allow more VBD updates to occur.
+ * Update of usage count is protected by a per-device semaphore.
+ */
+ if ( --di->mi->usage == 0 )
+ vbd_update();
+
+ return 0;
+}
+
+
+int blkif_ioctl(struct inode *inode, struct file *filep,
+ unsigned command, unsigned long argument)
+{
+ int i;
+
+ DPRINTK_IOCTL("command: 0x%x, argument: 0x%lx, dev: 0x%04x\n",
+ command, (long)argument, inode->i_rdev);
+
+ switch ( command )
+ {
+ case HDIO_GETGEO:
+ /* return ENOSYS to use defaults */
+ return -ENOSYS;
+
+ case CDROMMULTISESSION:
+ DPRINTK("FIXME: support multisession CDs later\n");
+ for ( i = 0; i < sizeof(struct cdrom_multisession); i++ )
+ if ( put_user(0, (byte *)(argument + i)) ) return -EFAULT;
+ return 0;
+
+ default:
+ /*printk(KERN_ALERT "ioctl %08x not supported by Xen blkdev\n",
+ command);*/
+ return -EINVAL; /* same return as native Linux */
+ }
+
+ return 0;
+}
+
+
+/*
+ * blkif_queue_request
+ *
+ * request block io
+ *
+ * id: for guest use only.
+ * operation: BLKIF_OP_{READ,WRITE,PROBE}
+ * buffer: buffer to read/write into. this should be a
+ * virtual address in the guest os.
+ */
+static int blkif_queue_request(struct request *req)
+{
+ struct xlbd_disk_info *di = req->rq_disk->private_data;
+ unsigned long buffer_ma;
+ blkif_request_t *ring_req;
+ struct bio *bio;
+ struct bio_vec *bvec;
+ int idx;
+ unsigned long id;
+ unsigned int fsect, lsect;
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ int ref;
+#endif
+
+ if ( unlikely(blkif_state != BLKIF_STATE_CONNECTED) )
+ return 1;
+
+ /* Fill out a communications ring structure. */
+ ring_req = RING_GET_REQUEST(&blk_ring, blk_ring.req_prod_pvt);
+ id = GET_ID_FROM_FREELIST();
+ blk_shadow[id].request = (unsigned long)req;
+
+ ring_req->id = id;
+ ring_req->operation = rq_data_dir(req) ? BLKIF_OP_WRITE :
+ BLKIF_OP_READ;
+ ring_req->sector_number = (blkif_sector_t)req->sector;
+ ring_req->device = di->xd_device;
+
+ ring_req->nr_segments = 0;
+ rq_for_each_bio(bio, req)
+ {
+ bio_for_each_segment(bvec, bio, idx)
+ {
+ if ( ring_req->nr_segments == BLKIF_MAX_SEGMENTS_PER_REQUEST )
+ BUG();
+ buffer_ma = page_to_phys(bvec->bv_page);
+ fsect = bvec->bv_offset >> 9;
+ lsect = fsect + (bvec->bv_len >> 9) - 1;
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ /* install a grant reference. */
+ ref = gnttab_claim_grant_reference(&gref_head, gref_terminal);
+ ASSERT( ref != -ENOSPC );
+
+ gnttab_grant_foreign_access_ref(
+ ref,
+ rdomid,
+ buffer_ma >> PAGE_SHIFT,
+ rq_data_dir(req) );
+
+ blk_shadow[id].frame[ring_req->nr_segments] =
+ buffer_ma >> PAGE_SHIFT;
+
+ ring_req->frame_and_sects[ring_req->nr_segments++] =
+ (((u32) ref) << 16) | (fsect << 3) | lsect;
+
+#else
+ ring_req->frame_and_sects[ring_req->nr_segments++] =
+ buffer_ma | (fsect << 3) | lsect;
+#endif
+ }
+ }
+
+ blk_ring.req_prod_pvt++;
+
+ /* Keep a private copy so we can reissue requests when recovering. */
+ pickle_request(&blk_shadow[id], ring_req);
+
+ return 0;
+}
+
+
+/*
+ * do_blkif_request
+ * read a block; request is in a request queue
+ */
+void do_blkif_request(request_queue_t *rq)
+{
+ struct xlbd_disk_info *di;
+ struct request *req;
+ int queued;
+
+ DPRINTK("Entered do_blkif_request\n");
+
+ queued = 0;
+
+ while ( (req = elv_next_request(rq)) != NULL )
+ {
+ if ( !blk_fs_request(req) )
+ {
+ end_request(req, 0);
+ continue;
+ }
+
+ if ( RING_FULL(&blk_ring) )
+ goto wait;
+
+ DPRINTK("do_blk_req %p: cmd %p, sec %lx, (%u/%li) buffer:%p [%s]\n",
+ req, req->cmd, req->sector, req->current_nr_sectors,
+ req->nr_sectors, req->buffer,
+ rq_data_dir(req) ? "write" : "read");
+
+ blkdev_dequeue_request(req);
+ if ( blkif_queue_request(req) )
+ {
+ wait:
+ di = req->rq_disk->private_data;
+ if ( di->next_waiting == NULL )
+ {
+ di->next_waiting = head_waiting;
+ head_waiting = di;
+ /* Avoid pointless unplugs. */
+ blk_stop_queue(rq);
+ }
+ break;
+ }
+
+ queued++;
+ }
+
+ if ( queued != 0 )
+ flush_requests();
+}
+
+
+static irqreturn_t blkif_int(int irq, void *dev_id, struct pt_regs *ptregs)
+{
+ struct request *req;
+ blkif_response_t *bret;
+ RING_IDX i, rp;
+ unsigned long flags;
+
+ spin_lock_irqsave(&blkif_io_lock, flags);
+
+ if ( unlikely(blkif_state == BLKIF_STATE_CLOSED) ||
+ unlikely(recovery) )
+ {
+ spin_unlock_irqrestore(&blkif_io_lock, flags);
+ return IRQ_HANDLED;
+ }
+
+ rp = blk_ring.sring->rsp_prod;
+ rmb(); /* Ensure we see queued responses up to 'rp'. */
+
+ for ( i = blk_ring.rsp_cons; i != rp; i++ )
+ {
+ unsigned long id;
+
+ bret = RING_GET_RESPONSE(&blk_ring, i);
+ id = bret->id;
+ req = (struct request *)blk_shadow[id].request;
+
+ blkif_completion(&blk_shadow[id]);
+
+ ADD_ID_TO_FREELIST(id);
+
+ switch ( bret->operation )
+ {
+ case BLKIF_OP_READ:
+ case BLKIF_OP_WRITE:
+ if ( unlikely(bret->status != BLKIF_RSP_OKAY) )
+ DPRINTK("Bad return from blkdev data request: %x\n",
+ bret->status);
+
+ if ( unlikely(end_that_request_first
+ (req,
+ (bret->status == BLKIF_RSP_OKAY),
+ req->hard_nr_sectors)) )
+ BUG();
+ end_that_request_last(req);
+
+ break;
+ case BLKIF_OP_PROBE:
+ memcpy(&blkif_control_rsp, bret, sizeof(*bret));
+ blkif_control_rsp_valid = 1;
+ break;
+ default:
+ BUG();
+ }
+ }
+
+ blk_ring.rsp_cons = i;
+
+ kick_pending_request_queues();
+
+ spin_unlock_irqrestore(&blkif_io_lock, flags);
+
+ return IRQ_HANDLED;
+}
+
+#else
+/************************** KERNEL VERSION 2.4 **************************/
+
+static kdev_t sg_dev;
+static unsigned long sg_next_sect;
+
+/*
+ * Request queues with outstanding work, but ring is currently full.
+ * We need no special lock here, as we always access this with the
+ * blkif_io_lock held. We only need a small maximum list.
+ */
+#define MAX_PENDING 8
+static request_queue_t *pending_queues[MAX_PENDING];
+static int nr_pending;
+
+
+#define blkif_io_lock io_request_lock
+
+/*============================================================================*/
+#if ENABLE_VBD_UPDATE
+
+/*
+ * blkif_update_int/update-vbds_task - handle VBD update events.
+ * Schedule a task for keventd to run, which will update the VBDs and perform
+ * the corresponding updates to our view of VBD state.
+ */
+static void update_vbds_task(void *unused)
+{
+ xlvbd_update_vbds();
+}
+
+static void vbd_update(void)
+{
+ static struct tq_struct update_tq;
+ update_tq.routine = update_vbds_task;
+ schedule_task(&update_tq);
+}
+
+#endif /* ENABLE_VBD_UPDATE */
+/*============================================================================*/
+
+static void kick_pending_request_queues(void)
+{
+ /* We kick pending request queues if the ring is reasonably empty. */
+ if ( (nr_pending != 0) &&
+ (RING_PENDING_REQUESTS(&blk_ring) < (BLK_RING_SIZE >> 1)) )
+ {
+ /* Attempt to drain the queue, but bail if the ring becomes full. */
+ while ( (nr_pending != 0) && !RING_FULL(&blk_ring) )
+ do_blkif_request(pending_queues[--nr_pending]);
+ }
+}
+
+int blkif_open(struct inode *inode, struct file *filep)
+{
+ short xldev = inode->i_rdev;
+ struct gendisk *gd = get_gendisk(xldev);
+ xl_disk_t *disk = xldev_to_xldisk(inode->i_rdev);
+ short minor = MINOR(xldev);
+
+ if ( gd->part[minor].nr_sects == 0 )
+ {
+ /*
+ * Device either doesn't exist, or has zero capacity; we use a few
+ * cheesy heuristics to return the relevant error code
+ */
+ if ( (gd->sizes[minor >> gd->minor_shift] != 0) ||
+ ((minor & (gd->max_p - 1)) != 0) )
+ {
+ /*
+ * We have a real device, but no such partition, or we just have a
+ * partition number so guess this is the problem.
+ */
+ return -ENXIO; /* no such device or address */
+ }
+ else if ( gd->flags[minor >> gd->minor_shift] & GENHD_FL_REMOVABLE )
+ {
+ /* This is a removable device => assume that media is missing. */
+ return -ENOMEDIUM; /* media not present (this is a guess) */
+ }
+ else
+ {
+ /* Just go for the general 'no such device' error. */
+ return -ENODEV; /* no such device */
+ }
+ }
+
+ /* Update of usage count is protected by per-device semaphore. */
+ disk->usage++;
+
+ return 0;
+}
+
+
+int blkif_release(struct inode *inode, struct file *filep)
+{
+ xl_disk_t *disk = xldev_to_xldisk(inode->i_rdev);
+
+ /*
+ * When usage drops to zero it may allow more VBD updates to occur.
+ * Update of usage count is protected by a per-device semaphore.
+ */
+ if ( --disk->usage == 0 ) {
+ vbd_update();
+ }
+
+ return 0;
+}
+
+
+int blkif_ioctl(struct inode *inode, struct file *filep,
+ unsigned command, unsigned long argument)
+{
+ kdev_t dev = inode->i_rdev;
+ struct hd_geometry *geo = (struct hd_geometry *)argument;
+ struct gendisk *gd;
+ struct hd_struct *part;
+ int i;
+ unsigned short cylinders;
+ byte heads, sectors;
+
+ /* NB. No need to check permissions. That is done for us. */
+
+ DPRINTK_IOCTL("command: 0x%x, argument: 0x%lx, dev: 0x%04x\n",
+ command, (long) argument, dev);
+
+ gd = get_gendisk(dev);
+ part = &gd->part[MINOR(dev)];
+
+ switch ( command )
+ {
+ case BLKGETSIZE:
+ DPRINTK_IOCTL(" BLKGETSIZE: %x %lx\n", BLKGETSIZE, part->nr_sects);
+ return put_user(part->nr_sects, (unsigned long *) argument);
+
+ case BLKGETSIZE64:
+ DPRINTK_IOCTL(" BLKGETSIZE64: %x %llx\n", BLKGETSIZE64,
+ (u64)part->nr_sects * 512);
+ return put_user((u64)part->nr_sects * 512, (u64 *) argument);
+
+ case BLKRRPART: /* re-read partition table */
+ DPRINTK_IOCTL(" BLKRRPART: %x\n", BLKRRPART);
+ return blkif_revalidate(dev);
+
+ case BLKSSZGET:
+ return hardsect_size[MAJOR(dev)][MINOR(dev)];
+
+ case BLKBSZGET: /* get block size */
+ DPRINTK_IOCTL(" BLKBSZGET: %x\n", BLKBSZGET);
+ break;
+
+ case BLKBSZSET: /* set block size */
+ DPRINTK_IOCTL(" BLKBSZSET: %x\n", BLKBSZSET);
+ break;
+
+ case BLKRASET: /* set read-ahead */
+ DPRINTK_IOCTL(" BLKRASET: %x\n", BLKRASET);
+ break;
+
+ case BLKRAGET: /* get read-ahead */
+ DPRINTK_IOCTL(" BLKRAFET: %x\n", BLKRAGET);
+ break;
+
+ case HDIO_GETGEO:
+ DPRINTK_IOCTL(" HDIO_GETGEO: %x\n", HDIO_GETGEO);
+ if (!argument) return -EINVAL;
+
+ /* We don't have real geometry info, but let's at least return
+ values consistent with the size of the device */
+
+ heads = 0xff;
+ sectors = 0x3f;
+ cylinders = part->nr_sects / (heads * sectors);
+
+ if (put_user(0x00, (unsigned long *) &geo->start)) return -EFAULT;
+ if (put_user(heads, (byte *)&geo->heads)) return -EFAULT;
+ if (put_user(sectors, (byte *)&geo->sectors)) return -EFAULT;
+ if (put_user(cylinders, (unsigned short *)&geo->cylinders)) return
-EFAULT;
+
+ return 0;
+
+ case HDIO_GETGEO_BIG:
+ DPRINTK_IOCTL(" HDIO_GETGEO_BIG: %x\n", HDIO_GETGEO_BIG);
+ if (!argument) return -EINVAL;
+
+ /* We don't have real geometry info, but let's at least return
+ values consistent with the size of the device */
+
+ heads = 0xff;
+ sectors = 0x3f;
+ cylinders = part->nr_sects / (heads * sectors);
+
+ if (put_user(0x00, (unsigned long *) &geo->start)) return -EFAULT;
+ if (put_user(heads, (byte *)&geo->heads)) return -EFAULT;
+ if (put_user(sectors, (byte *)&geo->sectors)) return -EFAULT;
+ if (put_user(cylinders, (unsigned int *) &geo->cylinders)) return
-EFAULT;
+
+ return 0;
+
+ case CDROMMULTISESSION:
+ DPRINTK("FIXME: support multisession CDs later\n");
+ for ( i = 0; i < sizeof(struct cdrom_multisession); i++ )
+ if ( put_user(0, (byte *)(argument + i)) ) return -EFAULT;
+ return 0;
+
+ case SCSI_IOCTL_GET_BUS_NUMBER:
+ DPRINTK("FIXME: SCSI_IOCTL_GET_BUS_NUMBER ioctl in XL blkif");
+ return -ENOSYS;
+
+ default:
+ WPRINTK("ioctl %08x not supported by XL blkif\n", command);
+ return -ENOSYS;
+ }
+
+ return 0;
+}
+
+
+
+/* check media change: should probably do something here in some cases :-) */
+int blkif_check(kdev_t dev)
+{
+ DPRINTK("blkif_check\n");
+ return 0;
+}
+
+int blkif_revalidate(kdev_t dev)
+{
+ struct block_device *bd;
+ struct gendisk *gd;
+ xl_disk_t *disk;
+ unsigned long capacity;
+ int i, rc = 0;
+
+ if ( (bd = bdget(dev)) == NULL )
+ return -EINVAL;
+
+ /*
+ * Update of partition info, and check of usage count, is protected
+ * by the per-block-device semaphore.
+ */
+ down(&bd->bd_sem);
+
+ if ( ((gd = get_gendisk(dev)) == NULL) ||
+ ((disk = xldev_to_xldisk(dev)) == NULL) ||
+ ((capacity = gd->part[MINOR(dev)].nr_sects) == 0) )
+ {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ if ( disk->usage > 1 )
+ {
+ rc = -EBUSY;
+ goto out;
+ }
+
+ /* Only reread partition table if VBDs aren't mapped to partitions. */
+ if ( !(gd->flags[MINOR(dev) >> gd->minor_shift] & GENHD_FL_VIRT_PARTNS) )
+ {
+ for ( i = gd->max_p - 1; i >= 0; i-- )
+ {
+ invalidate_device(dev+i, 1);
+ gd->part[MINOR(dev+i)].start_sect = 0;
+ gd->part[MINOR(dev+i)].nr_sects = 0;
+ gd->sizes[MINOR(dev+i)] = 0;
+ }
+
+ grok_partitions(gd, MINOR(dev)>>gd->minor_shift, gd->max_p, capacity);
+ }
+
+ out:
+ up(&bd->bd_sem);
+ bdput(bd);
+ return rc;
+}
+
+
+/*
+ * blkif_queue_request
+ *
+ * request block io
+ *
+ * id: for guest use only.
+ * operation: BLKIF_OP_{READ,WRITE,PROBE}
+ * buffer: buffer to read/write into. this should be a
+ * virtual address in the guest os.
+ */
+static int blkif_queue_request(unsigned long id,
+ int operation,
+ char * buffer,
+ unsigned long sector_number,
+ unsigned short nr_sectors,
+ kdev_t device)
+{
+ unsigned long buffer_ma = virt_to_bus(buffer);
+ unsigned long xid;
+ struct gendisk *gd;
+ blkif_request_t *req;
+ struct buffer_head *bh;
+ unsigned int fsect, lsect;
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ int ref;
+#endif
+
+ fsect = (buffer_ma & ~PAGE_MASK) >> 9;
+ lsect = fsect + nr_sectors - 1;
+
+ /* Buffer must be sector-aligned. Extent mustn't cross a page boundary. */
+ if ( unlikely((buffer_ma & ((1<<9)-1)) != 0) )
+ BUG();
+ if ( lsect > 7 )
+ BUG();
+
+ buffer_ma &= PAGE_MASK;
+
+ if ( unlikely(blkif_state != BLKIF_STATE_CONNECTED) )
+ return 1;
+
+ switch ( operation )
+ {
+
+ case BLKIF_OP_READ:
+ case BLKIF_OP_WRITE:
+ gd = get_gendisk(device);
+
+ /*
+ * Update the sector_number we'll pass down as appropriate; note that
+ * we could sanity check that resulting sector will be in this
+ * partition, but this will happen in driver backend anyhow.
+ */
+ sector_number += gd->part[MINOR(device)].start_sect;
+
+ /*
+ * If this unit doesn't consist of virtual partitions then we clear
+ * the partn bits from the device number.
+ */
+ if ( !(gd->flags[MINOR(device)>>gd->minor_shift] &
+ GENHD_FL_VIRT_PARTNS) )
+ device &= ~(gd->max_p - 1);
+
+ if ( (sg_operation == operation) &&
+ (sg_dev == device) &&
+ (sg_next_sect == sector_number) )
+ {
+ req = RING_GET_REQUEST(&blk_ring,
+ blk_ring.req_prod_pvt - 1);
+ bh = (struct buffer_head *)id;
+
+ bh->b_reqnext = (struct buffer_head *)blk_shadow[req->id].request;
+ blk_shadow[req->id].request = (unsigned long)id;
+
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ /* install a grant reference. */
+ ref = gnttab_claim_grant_reference(&gref_head, gref_terminal);
+ ASSERT( ref != -ENOSPC );
+
+ gnttab_grant_foreign_access_ref(
+ ref,
+ rdomid,
+ buffer_ma >> PAGE_SHIFT,
+ ( operation == BLKIF_OP_WRITE ? 1 : 0 ) );
+
+ blk_shadow[req->id].frame[req->nr_segments] =
+ buffer_ma >> PAGE_SHIFT;
+
+ req->frame_and_sects[req->nr_segments] =
+ (((u32) ref ) << 16) | (fsect << 3) | lsect;
+#else
+ req->frame_and_sects[req->nr_segments] =
+ buffer_ma | (fsect << 3) | lsect;
+#endif
+ if ( ++req->nr_segments < BLKIF_MAX_SEGMENTS_PER_REQUEST )
+ sg_next_sect += nr_sectors;
+ else
+ DISABLE_SCATTERGATHER();
+
+ /* Update the copy of the request in the recovery ring. */
+ pickle_request(&blk_shadow[req->id], req );
+
+ return 0;
+ }
+ else if ( RING_FULL(&blk_ring) )
+ {
+ return 1;
+ }
+ else
+ {
+ sg_operation = operation;
+ sg_dev = device;
+ sg_next_sect = sector_number + nr_sectors;
+ }
+ break;
+
+ default:
+ panic("unknown op %d\n", operation);
+ }
+
+ /* Fill out a communications ring structure. */
+ req = RING_GET_REQUEST(&blk_ring, blk_ring.req_prod_pvt);
+
+ xid = GET_ID_FROM_FREELIST();
+ blk_shadow[xid].request = (unsigned long)id;
+
+ req->id = xid;
+ req->operation = operation;
+ req->sector_number = (blkif_sector_t)sector_number;
+ req->device = device;
+ req->nr_segments = 1;
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ /* install a grant reference. */
+ ref = gnttab_claim_grant_reference(&gref_head, gref_terminal);
+ ASSERT( ref != -ENOSPC );
+
+ gnttab_grant_foreign_access_ref(
+ ref,
+ rdomid,
+ buffer_ma >> PAGE_SHIFT,
+ ( operation == BLKIF_OP_WRITE ? 1 : 0 ) );
+
+ blk_shadow[xid].frame[0] = buffer_ma >> PAGE_SHIFT;
+
+ req->frame_and_sects[0] = (((u32) ref)<<16) | (fsect<<3) | lsect;
+#else
+ req->frame_and_sects[0] = buffer_ma | (fsect<<3) | lsect;
+#endif
+
+ /* Keep a private copy so we can reissue requests when recovering. */
+ pickle_request(&blk_shadow[xid], req);
+
+ blk_ring.req_prod_pvt++;
+
+ return 0;
+}
+
+
+/*
+ * do_blkif_request
+ * read a block; request is in a request queue
+ */
+void do_blkif_request(request_queue_t *rq)
+{
+ struct request *req;
+ struct buffer_head *bh, *next_bh;
+ int rw, nsect, full, queued = 0;
+
+ DPRINTK("Entered do_blkif_request\n");
+
+ while ( !rq->plugged && !list_empty(&rq->queue_head))
+ {
+ if ( (req = blkdev_entry_next_request(&rq->queue_head)) == NULL )
+ goto out;
+
+ DPRINTK("do_blkif_request %p: cmd %i, sec %lx, (%li/%li) bh:%p\n",
+ req, req->cmd, req->sector,
+ req->current_nr_sectors, req->nr_sectors, req->bh);
+
+ rw = req->cmd;
+ if ( rw == READA )
+ rw = READ;
+ if ( unlikely((rw != READ) && (rw != WRITE)) )
+ panic("XenoLinux Virtual Block Device: bad cmd: %d\n", rw);
+
+ req->errors = 0;
+
+ bh = req->bh;
+ while ( bh != NULL )
+ {
+ next_bh = bh->b_reqnext;
+ bh->b_reqnext = NULL;
+
+ full = blkif_queue_request(
+ (unsigned long)bh,
+ (rw == READ) ? BLKIF_OP_READ : BLKIF_OP_WRITE,
+ bh->b_data, bh->b_rsector, bh->b_size>>9, bh->b_rdev);
+
+ if ( full )
+ {
+ bh->b_reqnext = next_bh;
+ pending_queues[nr_pending++] = rq;
+ if ( unlikely(nr_pending >= MAX_PENDING) )
+ BUG();
+ goto out;
+ }
+
+ queued++;
+
+ /* Dequeue the buffer head from the request. */
+ nsect = bh->b_size >> 9;
+ bh = req->bh = next_bh;
+
+ if ( bh != NULL )
+ {
+ /* There's another buffer head to do. Update the request. */
+ req->hard_sector += nsect;
+ req->hard_nr_sectors -= nsect;
+ req->sector = req->hard_sector;
+ req->nr_sectors = req->hard_nr_sectors;
+ req->current_nr_sectors = bh->b_size >> 9;
+ req->buffer = bh->b_data;
+ }
+ else
+ {
+ /* That was the last buffer head. Finalise the request. */
+ if ( unlikely(end_that_request_first(req, 1, "XenBlk")) )
+ BUG();
+ blkdev_dequeue_request(req);
+ end_that_request_last(req);
+ }
+ }
+ }
+
+ out:
+ if ( queued != 0 )
+ flush_requests();
+}
+
+
+static void blkif_int(int irq, void *dev_id, struct pt_regs *ptregs)
+{
+ RING_IDX i, rp;
+ unsigned long flags;
+ struct buffer_head *bh, *next_bh;
+
+ spin_lock_irqsave(&io_request_lock, flags);
+
+ if ( unlikely(blkif_state == BLKIF_STATE_CLOSED || recovery) )
+ {
+ spin_unlock_irqrestore(&io_request_lock, flags);
+ return;
+ }
+
+ rp = blk_ring.sring->rsp_prod;
+ rmb(); /* Ensure we see queued responses up to 'rp'. */
+
+ for ( i = blk_ring.rsp_cons; i != rp; i++ )
+ {
+ unsigned long id;
+ blkif_response_t *bret;
+
+ bret = RING_GET_RESPONSE(&blk_ring, i);
+ id = bret->id;
+ bh = (struct buffer_head *)blk_shadow[id].request;
+
+ blkif_completion(&blk_shadow[id]);
+
+ ADD_ID_TO_FREELIST(id);
+
+ switch ( bret->operation )
+ {
+ case BLKIF_OP_READ:
+ case BLKIF_OP_WRITE:
+ if ( unlikely(bret->status != BLKIF_RSP_OKAY) )
+ DPRINTK("Bad return from blkdev data request: %lx\n",
+ bret->status);
+ for ( ; bh != NULL; bh = next_bh )
+ {
+ next_bh = bh->b_reqnext;
+ bh->b_reqnext = NULL;
+ bh->b_end_io(bh, bret->status == BLKIF_RSP_OKAY);
+ }
+
+ break;
+ case BLKIF_OP_PROBE:
+ memcpy(&blkif_control_rsp, bret, sizeof(*bret));
+ blkif_control_rsp_valid = 1;
+ break;
+ default:
+ BUG();
+ }
+
+ }
+ blk_ring.rsp_cons = i;
+
+ kick_pending_request_queues();
+
+ spin_unlock_irqrestore(&io_request_lock, flags);
+}
+
+#endif
+
+/***************************** COMMON CODE *******************************/
+
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+void blkif_control_probe_send(blkif_request_t *req, blkif_response_t *rsp,
+ unsigned long address)
+{
+ int ref = gnttab_claim_grant_reference(&gref_head, gref_terminal);
+ ASSERT( ref != -ENOSPC );
+
+ gnttab_grant_foreign_access_ref( ref, rdomid, address >> PAGE_SHIFT, 0 );
+
+ req->frame_and_sects[0] = (((u32) ref) << 16) | 7;
+
+ blkif_control_send(req, rsp);
+}
+#endif
+
+void blkif_control_send(blkif_request_t *req, blkif_response_t *rsp)
+{
+ unsigned long flags, id;
+ blkif_request_t *req_d;
+
+ retry:
+ while ( RING_FULL(&blk_ring) )
+ {
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(1);
+ }
+
+ spin_lock_irqsave(&blkif_io_lock, flags);
+ if ( RING_FULL(&blk_ring) )
+ {
+ spin_unlock_irqrestore(&blkif_io_lock, flags);
+ goto retry;
+ }
+
+ DISABLE_SCATTERGATHER();
+ req_d = RING_GET_REQUEST(&blk_ring, blk_ring.req_prod_pvt);
+ *req_d = *req;
+
+ id = GET_ID_FROM_FREELIST();
+ req_d->id = id;
+ blk_shadow[id].request = (unsigned long)req;
+
+ pickle_request(&blk_shadow[id], req);
+
+ blk_ring.req_prod_pvt++;
+ flush_requests();
+
+ spin_unlock_irqrestore(&blkif_io_lock, flags);
+
+ while ( !blkif_control_rsp_valid )
+ {
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(1);
+ }
+
+ memcpy(rsp, &blkif_control_rsp, sizeof(*rsp));
+ blkif_control_rsp_valid = 0;
+}
+
+
+/* Send a driver status notification to the domain controller. */
+static void send_driver_status(int ok)
+{
+ ctrl_msg_t cmsg = {
+ .type = CMSG_BLKIF_FE,
+ .subtype = CMSG_BLKIF_FE_DRIVER_STATUS,
+ .length = sizeof(blkif_fe_driver_status_t),
+ };
+ blkif_fe_driver_status_t *msg = (void*)cmsg.msg;
+
+ msg->status = (ok ? BLKIF_DRIVER_STATUS_UP : BLKIF_DRIVER_STATUS_DOWN);
+
+ ctrl_if_send_message_block(&cmsg, NULL, 0, TASK_UNINTERRUPTIBLE);
+}
+
+/* Tell the controller to bring up the interface. */
+static void blkif_send_interface_connect(void)
+{
+ ctrl_msg_t cmsg = {
+ .type = CMSG_BLKIF_FE,
+ .subtype = CMSG_BLKIF_FE_INTERFACE_CONNECT,
+ .length = sizeof(blkif_fe_interface_connect_t),
+ };
+ blkif_fe_interface_connect_t *msg = (void*)cmsg.msg;
+
+ msg->handle = 0;
+ msg->shmem_frame = (virt_to_machine(blk_ring.sring) >> PAGE_SHIFT);
+
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ msg->shmem_ref = gnttab_claim_grant_reference( &gref_head, gref_terminal
);
+ ASSERT( msg->shmem_ref != -ENOSPC );
+ gnttab_grant_foreign_access_ref ( msg->shmem_ref , rdomid,
msg->shmem_frame, 0 );
+#endif
+
+ ctrl_if_send_message_block(&cmsg, NULL, 0, TASK_UNINTERRUPTIBLE);
+}
+
+static void blkif_free(void)
+{
+ /* Prevent new requests being issued until we fix things up. */
+ spin_lock_irq(&blkif_io_lock);
+ recovery = 1;
+ blkif_state = BLKIF_STATE_DISCONNECTED;
+ spin_unlock_irq(&blkif_io_lock);
+
+ /* Free resources associated with old device channel. */
+ if ( blk_ring.sring != NULL )
+ {
+ free_page((unsigned long)blk_ring.sring);
+ blk_ring.sring = NULL;
+ }
+ free_irq(blkif_irq, NULL);
+ blkif_irq = 0;
+
+ unbind_evtchn_from_irq(blkif_evtchn);
+ blkif_evtchn = 0;
+}
+
+static void blkif_close(void)
+{
+}
+
+/* Move from CLOSED to DISCONNECTED state. */
+static void blkif_disconnect(void)
+{
+ blkif_sring_t *sring;
+
+ if ( blk_ring.sring != NULL )
+ free_page((unsigned long)blk_ring.sring);
+
+ sring = (blkif_sring_t *)__get_free_page(GFP_KERNEL);
+ SHARED_RING_INIT(sring);
+ FRONT_RING_INIT(&blk_ring, sring, PAGE_SIZE);
+ blkif_state = BLKIF_STATE_DISCONNECTED;
+ blkif_send_interface_connect();
+}
+
+static void blkif_reset(void)
+{
+ blkif_free();
+ blkif_disconnect();
+}
+
+static void blkif_recover(void)
+{
+ int i;
+ blkif_request_t *req;
+ struct blk_shadow *copy;
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ int j;
+#endif
+
+ /* Stage 1: Make a safe copy of the shadow state. */
+ copy = (struct blk_shadow *)kmalloc(sizeof(blk_shadow), GFP_KERNEL);
+ BUG_ON(copy == NULL);
+ memcpy(copy, blk_shadow, sizeof(blk_shadow));
+
+ /* Stage 2: Set up free list. */
+ memset(&blk_shadow, 0, sizeof(blk_shadow));
+ for ( i = 0; i < BLK_RING_SIZE; i++ )
+ blk_shadow[i].req.id = i+1;
+ blk_shadow_free = blk_ring.req_prod_pvt;
+ blk_shadow[BLK_RING_SIZE-1].req.id = 0x0fffffff;
+
+ /* Stage 3: Find pending requests and requeue them. */
+ for ( i = 0; i < BLK_RING_SIZE; i++ )
+ {
+ /* Not in use? */
+ if ( copy[i].request == 0 )
+ continue;
+
+ /* Grab a request slot and unpickle shadow state into it. */
+ req = RING_GET_REQUEST(
+ &blk_ring, blk_ring.req_prod_pvt);
+ unpickle_request(req, ©[i]);
+
+ /* We get a new request id, and must reset the shadow state. */
+ req->id = GET_ID_FROM_FREELIST();
+ memcpy(&blk_shadow[req->id], ©[i], sizeof(copy[i]));
+
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ /* Rewrite any grant references invalidated by suspend/resume. */
+ for ( j = 0; j < req->nr_segments; j++ )
+ {
+ if ( req->frame_and_sects[j] & GRANTREF_INVALID )
+ gnttab_grant_foreign_access_ref(
+ blkif_gref_from_fas(req->frame_and_sects[j]),
+ rdomid,
+ blk_shadow[req->id].frame[j],
+ rq_data_dir((struct request *)
+ blk_shadow[req->id].request));
+ req->frame_and_sects[j] &= ~GRANTREF_INVALID;
+ }
+ blk_shadow[req->id].req = *req;
+#endif
+
+ blk_ring.req_prod_pvt++;
+ }
+
+ kfree(copy);
+
+ recovery = 0;
+
+ /* blk_ring->req_prod will be set when we flush_requests().*/
+ wmb();
+
+ /* Kicks things back into life. */
+ flush_requests();
+
+ /* Now safe to left other people use the interface. */
+ blkif_state = BLKIF_STATE_CONNECTED;
+}
+
+static void blkif_connect(blkif_fe_interface_status_t *status)
+{
+ int err = 0;
+
+ blkif_evtchn = status->evtchn;
+ blkif_irq = bind_evtchn_to_irq(blkif_evtchn);
+
+ err = request_irq(blkif_irq, blkif_int, SA_SAMPLE_RANDOM, "blkif", NULL);
+ if ( err )
+ {
+ WPRINTK("request_irq failed (err=%d)\n", err);
+ return;
+ }
+
+ if ( recovery )
+ {
+ blkif_recover();
+ }
+ else
+ {
+ /* Transition to connected in case we need to do
+ * a partition probe on a whole disk. */
+ blkif_state = BLKIF_STATE_CONNECTED;
+
+ /* Probe for discs attached to the interface. */
+ xlvbd_init();
+ }
+
+ /* Kick pending requests. */
+ spin_lock_irq(&blkif_io_lock);
+ kick_pending_request_queues();
+ spin_unlock_irq(&blkif_io_lock);
+}
+
+static void unexpected(blkif_fe_interface_status_t *status)
+{
+ DPRINTK(" Unexpected blkif status %u in state %u\n",
+ status->status, blkif_state);
+}
+
+static void blkif_status(blkif_fe_interface_status_t *status)
+{
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ rdomid = status->domid; /* need to set rdomid early */
+#endif
+
+ if ( status->handle != blkif_handle )
+ {
+ WPRINTK(" Invalid blkif: handle=%u\n", status->handle);
+ unexpected(status);
+ return;
+ }
+
+ switch ( status->status )
+ {
+ case BLKIF_INTERFACE_STATUS_CLOSED:
+ switch ( blkif_state )
+ {
+ case BLKIF_STATE_CLOSED:
+ unexpected(status);
+ break;
+ case BLKIF_STATE_DISCONNECTED:
+ case BLKIF_STATE_CONNECTED:
+ unexpected(status);
+ blkif_close();
+ break;
+ }
+ break;
+
+ case BLKIF_INTERFACE_STATUS_DISCONNECTED:
+ switch ( blkif_state )
+ {
+ case BLKIF_STATE_CLOSED:
+ blkif_disconnect();
+ break;
+ case BLKIF_STATE_DISCONNECTED:
+ case BLKIF_STATE_CONNECTED:
+ /* unexpected(status); */ /* occurs during suspend/resume */
+ blkif_reset();
+ break;
+ }
+ break;
+
+ case BLKIF_INTERFACE_STATUS_CONNECTED:
+ switch ( blkif_state )
+ {
+ case BLKIF_STATE_CLOSED:
+ unexpected(status);
+ blkif_disconnect();
+ blkif_connect(status);
+ break;
+ case BLKIF_STATE_DISCONNECTED:
+ blkif_connect(status);
+ break;
+ case BLKIF_STATE_CONNECTED:
+ unexpected(status);
+ blkif_connect(status);
+ break;
+ }
+ break;
+
+ case BLKIF_INTERFACE_STATUS_CHANGED:
+ switch ( blkif_state )
+ {
+ case BLKIF_STATE_CLOSED:
+ case BLKIF_STATE_DISCONNECTED:
+ unexpected(status);
+ break;
+ case BLKIF_STATE_CONNECTED:
+ vbd_update();
+ break;
+ }
+ break;
+
+ default:
+ WPRINTK(" Invalid blkif status: %d\n", status->status);
+ break;
+ }
+}
+
+
+static void blkif_ctrlif_rx(ctrl_msg_t *msg, unsigned long id)
+{
+ switch ( msg->subtype )
+ {
+ case CMSG_BLKIF_FE_INTERFACE_STATUS:
+ blkif_status((blkif_fe_interface_status_t *)
+ &msg->msg[0]);
+ break;
+ default:
+ msg->length = 0;
+ break;
+ }
+
+ ctrl_if_send_response(msg);
+}
+
+int wait_for_blkif(void)
+{
+ int err = 0;
+ int i;
+ send_driver_status(1);
+
+ /*
+ * We should read 'nr_interfaces' from response message and wait
+ * for notifications before proceeding. For now we assume that we
+ * will be notified of exactly one interface.
+ */
+ for ( i=0; (blkif_state != BLKIF_STATE_CONNECTED) && (i < 10*HZ); i++ )
+ {
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(1);
+ }
+
+ if ( blkif_state != BLKIF_STATE_CONNECTED )
+ {
+ WPRINTK("Timeout connecting to device!\n");
+ err = -ENOSYS;
+ }
+ return err;
+}
+
+int __init xlblk_init(void)
+{
+ int i;
+
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ if ( 0 > gnttab_alloc_grant_references( MAXIMUM_OUTSTANDING_BLOCK_REQS,
+ &gref_head, &gref_terminal ))
+ return 1;
+ printk(KERN_ALERT "Blkif frontend is using grant tables.\n");
+#endif
+
+ if ( (xen_start_info.flags & SIF_INITDOMAIN) ||
+ (xen_start_info.flags & SIF_BLK_BE_DOMAIN) )
+ return 0;
+
+ IPRINTK("Initialising virtual block device driver\n");
+
+ blk_shadow_free = 0;
+ memset(blk_shadow, 0, sizeof(blk_shadow));
+ for ( i = 0; i < BLK_RING_SIZE; i++ )
+ blk_shadow[i].req.id = i+1;
+ blk_shadow[BLK_RING_SIZE-1].req.id = 0x0fffffff;
+
+ (void)ctrl_if_register_receiver(CMSG_BLKIF_FE, blkif_ctrlif_rx,
+ CALLBACK_IN_BLOCKING_CONTEXT);
+
+ wait_for_blkif();
+
+ return 0;
+}
+
+void blkdev_suspend(void)
+{
+}
+
+void blkdev_resume(void)
+{
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ int i, j;
+ for ( i = 0; i < BLK_RING_SIZE; i++ )
+ for ( j = 0; j < BLKIF_MAX_SEGMENTS_PER_REQUEST; j++ )
+ blk_shadow[i].req.frame_and_sects[j] |= GRANTREF_INVALID;
+#endif
+ send_driver_status(1);
+}
+
+static void blkif_completion(struct blk_shadow *s)
+{
+ int i;
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ for ( i = 0; i < s->req.nr_segments; i++ )
+ gnttab_release_grant_reference(
+ &gref_head, blkif_gref_from_fas(s->req.frame_and_sects[i]));
+#else
+ /* This is a hack to get the dirty logging bits set */
+ if ( s->req.operation == BLKIF_OP_READ )
+ {
+ for ( i = 0; i < s->req.nr_segments; i++ )
+ {
+ unsigned long pfn = s->req.frame_and_sects[i] >> PAGE_SHIFT;
+ unsigned long mfn = phys_to_machine_mapping[pfn];
+ xen_machphys_update(mfn, pfn);
+ }
+ }
+#endif
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/smp.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/smp.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,102 @@
+#ifndef __ASM_SMP_H
+#define __ASM_SMP_H
+
+/*
+ * We need the APIC definitions automatically as part of 'smp.h'
+ */
+#ifndef __ASSEMBLY__
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <linux/ptrace.h>
+#endif
+
+#ifdef CONFIG_X86_LOCAL_APIC
+#ifndef __ASSEMBLY__
+#include <asm/bitops.h>
+#include <asm/mpspec.h>
+#ifdef CONFIG_X86_IO_APIC
+#include <asm/io_apic.h>
+#endif
+#include <asm/apic.h>
+#endif
+#endif
+
+#ifdef CONFIG_SMP
+#ifndef __ASSEMBLY__
+
+/*
+ * Private routines/data
+ */
+
+extern void smp_alloc_memory(void);
+extern unsigned long phys_cpu_present_map;
+extern unsigned long cpu_online_map;
+extern volatile unsigned long smp_invalidate_needed;
+extern int pic_mode;
+extern int smp_num_siblings;
+extern int cpu_sibling_map[];
+
+extern void smp_flush_tlb(void);
+extern void smp_message_irq(int cpl, void *dev_id, struct pt_regs *regs);
+extern void fastcall smp_send_reschedule(int cpu);
+extern void smp_invalidate_rcv(void); /* Process an NMI */
+extern void (*mtrr_hook) (void);
+extern void zap_low_mappings (void);
+
+/*
+ * On x86 all CPUs are mapped 1:1 to the APIC space.
+ * This simplifies scheduling and IPI sending and
+ * compresses data structures.
+ */
+static inline int cpu_logical_map(int cpu)
+{
+ return cpu;
+}
+static inline int cpu_number_map(int cpu)
+{
+ return cpu;
+}
+
+/*
+ * Some lowlevel functions might want to know about
+ * the real APIC ID <-> CPU # mapping.
+ */
+#define MAX_APICID 256
+extern volatile int cpu_to_physical_apicid[NR_CPUS];
+extern volatile int physical_apicid_to_cpu[MAX_APICID];
+extern volatile int cpu_to_logical_apicid[NR_CPUS];
+extern volatile int logical_apicid_to_cpu[MAX_APICID];
+
+/*
+ * General functions that each host system must provide.
+ */
+
+extern void smp_boot_cpus(void);
+extern void smp_store_cpu_info(int id); /* Store per CPU info
(like the initial udelay numbers */
+
+/*
+ * This function is needed by all SMP systems. It must _always_ be valid
+ * from the initial startup. We map APIC_BASE very early in page_setup(),
+ * so this is correct in the x86 case.
+ */
+
+#define smp_processor_id() (current->processor)
+
+#endif /* !__ASSEMBLY__ */
+
+#define NO_PROC_ID 0xFF /* No processor magic marker */
+
+/*
+ * This magic constant controls our willingness to transfer
+ * a process across CPUs. Such a transfer incurs misses on the L1
+ * cache, and on a P6 or P5 with multiple L2 caches L2 hits. My
+ * gut feeling is this will vary by board in value. For a board
+ * with separate L2 cache it probably depends also on the RSS, and
+ * for a board with shared L2 cache it ought to decay fast as other
+ * processes are run.
+ */
+
+#define PROC_CHANGE_PENALTY 15 /* Schedule penalty */
+
+#endif
+#endif
diff -r 35b74976f598 -r a83ac0806d6b xen/arch/ia64/vmx_support.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/xen/arch/ia64/vmx_support.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,159 @@
+
+/* -*- Mode:C; c-basic-offset:4; tab-width:4; indent-tabs-mode:nil -*- */
+/*
+ * vmx_support.c: vmx specific support interface.
+ * Copyright (c) 2005, Intel Corporation.
+ * Kun Tian (Kevin Tian) (Kevin.tian@xxxxxxxxx)
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ */
+#include <xen/config.h>
+#include <xen/sched.h>
+#include <public/io/ioreq.h>
+#include <asm/vmx.h>
+#include <asm/vmx_vcpu.h>
+
+/*
+ * I/O emulation should be atomic from domain point of view. However,
+ * when emulation code is waiting for I/O completion by do_block,
+ * other events like DM interrupt, VBD, etc. may come and unblock
+ * current exection flow. So we have to prepare for re-block if unblocked
+ * by non I/O completion event.
+ */
+void vmx_wait_io(void)
+{
+ struct vcpu *v = current;
+ struct domain *d = v->domain;
+ extern void do_block();
+
+ do {
+ if (!test_bit(IOPACKET_PORT,
+ &d->shared_info->evtchn_pending[0]))
+ do_block();
+
+ /* Unblocked when some event is coming. Clear pending indication
+ * immediately if deciding to go for io assist
+ */
+ if (test_and_clear_bit(IOPACKET_PORT,
+ &d->shared_info->evtchn_pending[0])) {
+ clear_bit(IOPACKET_PORT>>5, &v->vcpu_info->evtchn_pending_sel);
+ clear_bit(0, &v->vcpu_info->evtchn_upcall_pending);
+ vmx_io_assist(v);
+ }
+
+
+ if (test_bit(ARCH_VMX_IO_WAIT, &v->arch.arch_vmx.flags)) {
+ /*
+ * Latest event is not I/O completion, so clear corresponding
+ * selector and pending indication, to allow real event coming
+ */
+ clear_bit(0, &v->vcpu_info->evtchn_upcall_pending);
+
+ /* Here atually one window is leaved before selector is cleared.
+ * However this window only delay the indication to coming event,
+ * nothing losed. Next loop will check I/O channel to fix this
+ * window.
+ */
+ clear_bit(IOPACKET_PORT>>5, &v->vcpu_info->evtchn_pending_sel);
+ }
+ else
+ break;
+ } while (test_bit(ARCH_VMX_IO_WAIT, &v->arch.arch_vmx.flags));
+}
+
+/*
+ * Only place to call vmx_io_assist is mmio/legacy_io emulation.
+ * Since I/O emulation is synchronous, it shouldn't be called in
+ * other places. This is not like x86, since IA-64 implements a
+ * per-vp stack without continuation.
+ */
+void vmx_io_assist(struct vcpu *v)
+{
+ vcpu_iodata_t *vio;
+ ioreq_t *p;
+
+ /*
+ * This shared page contains I/O request between emulation code
+ * and device model.
+ */
+ vio = (vcpu_iodata_t *)v->arch.arch_vmx.vmx_platform.shared_page_va;
+ if (!vio)
+ panic("Corruption: bad shared page: %lx\n", (unsigned long)vio);
+
+ p = &vio->vp_ioreq;
+
+ if (p->state == STATE_IORESP_HOOK)
+ panic("Not supported: No hook available for DM request\n");
+
+ if (test_bit(ARCH_VMX_IO_WAIT, &v->arch.arch_vmx.flags)) {
+ if (p->state != STATE_IORESP_READY) {
+ /* Can't do_block here, for the same reason as other places to
+ * use vmx_wait_io. Simple return is safe since vmx_wait_io will
+ * try to block again
+ */
+ return;
+ } else
+ p->state = STATE_INVALID;
+
+ clear_bit(ARCH_VMX_IO_WAIT, &v->arch.arch_vmx.flags);
+ } else
+ return; /* Spurous event? */
+}
+
+/*
+ * VMX domainN has two types of interrupt source: lsapic model within
+ * HV, and device model within domain 0 (service OS). There're another
+ * pending array in share page, manipulated by device model directly.
+ * To conform to VT-i spec, we have to sync pending bits in shared page
+ * into VPD. This has to be done before checking pending interrupt at
+ * resume to guest. For domain 0, all the interrupt sources come from
+ * HV, which then doesn't require this assist.
+ */
+void vmx_intr_assist(struct vcpu *v)
+{
+ vcpu_iodata_t *vio;
+ struct domain *d = v->domain;
+ extern void vmx_vcpu_pend_batch_interrupt(VCPU *vcpu,
+ unsigned long *pend_irr);
+
+ /* I/O emulation is atomic, so it's impossible to see execution flow
+ * out of vmx_wait_io, when guest is still waiting for response.
+ */
+ if (test_bit(ARCH_VMX_IO_WAIT, &v->arch.arch_vmx.flags))
+ panic("!!!Bad resume to guest before I/O emulation is done.\n");
+
+ /* Clear indicator specific to interrupt delivered from DM */
+ if (test_and_clear_bit(IOPACKET_PORT,
+ &d->shared_info->evtchn_pending[0])) {
+ if (!d->shared_info->evtchn_pending[IOPACKET_PORT >> 5])
+ clear_bit(IOPACKET_PORT>>5, &v->vcpu_info->evtchn_pending_sel);
+
+ if (!v->vcpu_info->evtchn_pending_sel)
+ clear_bit(0, &v->vcpu_info->evtchn_upcall_pending);
+ }
+
+ /* Even without event pending, we still need to sync pending bits
+ * between DM and vlsapic. The reason is that interrupt delivery
+ * shares same event channel as I/O emulation, with corresponding
+ * indicator possibly cleared when vmx_wait_io().
+ */
+ vio = (vcpu_iodata_t *)v->arch.arch_vmx.vmx_platform.shared_page_va;
+ if (!vio)
+ panic("Corruption: bad shared page: %lx\n", (unsigned long)vio);
+
+ vmx_vcpu_pend_batch_interrupt(v, &vio->vp_intr[0]);
+ memset(&vio->vp_intr[0], 0, sizeof(vio->vp_intr));
+ return;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/drivers/blkif/frontend/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/drivers/blkif/frontend/Makefile Fri Jul
15 13:39:50 2005
@@ -0,0 +1,3 @@
+O_TARGET := drv.o
+obj-y := blkfront.o vbd.o
+include $(TOPDIR)/Rules.make
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/setup.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/setup.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,66 @@
+/*
+ * Just a place holder. We don't want to have to test x86 before
+ * we include stuff
+ */
+
+#ifndef _i386_SETUP_H
+#define _i386_SETUP_H
+
+#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT)
+#define PFN_DOWN(x) ((x) >> PAGE_SHIFT)
+#define PFN_PHYS(x) ((x) << PAGE_SHIFT)
+
+/*
+ * Reserved space for vmalloc and iomap - defined in asm/page.h
+ */
+#define MAXMEM_PFN PFN_DOWN(MAXMEM)
+#define MAX_NONPAE_PFN (1 << 20)
+
+#define PARAM_SIZE 2048
+#define COMMAND_LINE_SIZE 256
+
+#define OLD_CL_MAGIC_ADDR 0x90020
+#define OLD_CL_MAGIC 0xA33F
+#define OLD_CL_BASE_ADDR 0x90000
+#define OLD_CL_OFFSET 0x90022
+#define NEW_CL_POINTER 0x228 /* Relative to real mode data */
+
+#ifndef __ASSEMBLY__
+/*
+ * This is set up by the setup-routine at boot-time
+ */
+extern unsigned char boot_params[PARAM_SIZE];
+
+#define PARAM (boot_params)
+#define SCREEN_INFO (*(struct screen_info *) (PARAM+0))
+#define EXT_MEM_K (*(unsigned short *) (PARAM+2))
+#define ALT_MEM_K (*(unsigned long *) (PARAM+0x1e0))
+#define E820_MAP_NR (*(char*) (PARAM+E820NR))
+#define E820_MAP ((struct e820entry *) (PARAM+E820MAP))
+#define APM_BIOS_INFO (*(struct apm_bios_info *) (PARAM+0x40))
+#define IST_INFO (*(struct ist_info *) (PARAM+0x60))
+#define DRIVE_INFO (*(struct drive_info_struct *) (PARAM+0x80))
+#define SYS_DESC_TABLE (*(struct sys_desc_table_struct*)(PARAM+0xa0))
+#define EFI_SYSTAB ((efi_system_table_t *) *((unsigned long *)(PARAM+0x1c4)))
+#define EFI_MEMDESC_SIZE (*((unsigned long *) (PARAM+0x1c8)))
+#define EFI_MEMDESC_VERSION (*((unsigned long *) (PARAM+0x1cc)))
+#define EFI_MEMMAP ((efi_memory_desc_t *) *((unsigned long *)(PARAM+0x1d0)))
+#define EFI_MEMMAP_SIZE (*((unsigned long *) (PARAM+0x1d4)))
+#define MOUNT_ROOT_RDONLY (*(unsigned short *) (PARAM+0x1F2))
+#define RAMDISK_FLAGS (*(unsigned short *) (PARAM+0x1F8))
+#define VIDEO_MODE (*(unsigned short *) (PARAM+0x1FA))
+#define ORIG_ROOT_DEV (*(unsigned short *) (PARAM+0x1FC))
+#define AUX_DEVICE_INFO (*(unsigned char *) (PARAM+0x1FF))
+#define LOADER_TYPE (*(unsigned char *) (PARAM+0x210))
+#define KERNEL_START (*(unsigned long *) (PARAM+0x214))
+#define INITRD_START (__pa(xen_start_info.mod_start))
+#define INITRD_SIZE (xen_start_info.mod_len)
+#define EDID_INFO (*(struct edid_info *) (PARAM+0x440))
+#define EDD_NR (*(unsigned char *) (PARAM+EDDNR))
+#define EDD_MBR_SIG_NR (*(unsigned char *) (PARAM+EDD_MBR_SIG_NR_BUF))
+#define EDD_MBR_SIGNATURE ((unsigned int *) (PARAM+EDD_MBR_SIG_BUF))
+#define EDD_BUF ((struct edd_info *) (PARAM+EDDBUF))
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _i386_SETUP_H */
diff -r 35b74976f598 -r a83ac0806d6b
patches/linux-2.6.11/i386-cpu-hotplug-updated-for-mm.patch
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/patches/linux-2.6.11/i386-cpu-hotplug-updated-for-mm.patch Fri Jul
15 13:39:50 2005
@@ -0,0 +1,656 @@
+
+From: Zwane Mwaikambo <zwane@xxxxxxxxxxxxx>
+
+Find attached the i386 cpu hotplug patch updated for Ingo's latest round of
+goodies. In order to avoid dumping cpu hotplug code into kernel/irq/* i
+dropped the cpu_online check in do_IRQ() by modifying fixup_irqs(). The
+difference being that on cpu offline, fixup_irqs() is called before we
+clear the cpu from cpu_online_map and a long delay in order to ensure that
+we never have any queued external interrupts on the APICs. Due to my usual
+test victims being in boxes a continent away this hasn't been tested, but
+i'll cover bug reports (nudge, Nathan! ;)
+
+1) Add CONFIG_HOTPLUG_CPU
+2) disable local APIC timer on dead cpus.
+3) Disable preempt around irq balancing to prevent CPUs going down.
+4) Print irq stats for all possible cpus.
+5) Debugging check for interrupts on offline cpus.
+6) Hacky fixup_irqs() to redirect irqs when cpus go off/online.
+7) play_dead() for offline cpus to spin inside.
+8) Handle offline cpus set in flush_tlb_others().
+9) Grab lock earlier in smp_call_function() to prevent CPUs going down.
+10) Implement __cpu_disable() and __cpu_die().
+11) Enable local interrupts in cpu_enable() after fixup_irqs()
+12) Don't fiddle with NMI on dead cpu, but leave intact on other cpus.
+13) Program IRQ affinity whilst cpu is still in cpu_online_map on offline.
+
+Signed-off-by: Zwane Mwaikambo <zwane@xxxxxxxxxxxxx>
+DESC
+ppc64: fix hotplug cpu
+EDESC
+From: Zwane Mwaikambo <zwane@xxxxxxxxxxx>
+
+I seem to have broken this when I moved the clearing of the dying cpu to
+arch specific code.
+
+Signed-off-by: Zwane Mwaikambo <zwane@xxxxxxxxxxx>
+Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
+---
+
+ 25-akpm/arch/i386/Kconfig | 9 ++
+ 25-akpm/arch/i386/kernel/apic.c | 3
+ 25-akpm/arch/i386/kernel/io_apic.c | 2
+ 25-akpm/arch/i386/kernel/irq.c | 66 +++++++++++++++++----
+ 25-akpm/arch/i386/kernel/msr.c | 2
+ 25-akpm/arch/i386/kernel/process.c | 35 +++++++++++
+ 25-akpm/arch/i386/kernel/smp.c | 25 +++++---
+ 25-akpm/arch/i386/kernel/smpboot.c | 98
++++++++++++++++++++++++++++++--
+ 25-akpm/arch/i386/kernel/traps.c | 8 ++
+ 25-akpm/arch/ia64/kernel/smpboot.c | 3
+ 25-akpm/arch/ppc64/kernel/pSeries_smp.c | 5 +
+ 25-akpm/arch/s390/kernel/smp.c | 4 -
+ 25-akpm/include/asm-i386/cpu.h | 2
+ 25-akpm/include/asm-i386/irq.h | 4 +
+ 25-akpm/include/asm-i386/smp.h | 3
+ 25-akpm/kernel/cpu.c | 14 +---
+ arch/ppc64/kernel/smp.c | 0
+ 17 files changed, 242 insertions(+), 41 deletions(-)
+
+diff -puN arch/i386/Kconfig~i386-cpu-hotplug-updated-for-mm arch/i386/Kconfig
+--- 25/arch/i386/Kconfig~i386-cpu-hotplug-updated-for-mm 2005-02-23
02:20:06.000000000 -0800
++++ 25-akpm/arch/i386/Kconfig 2005-02-23 02:20:06.000000000 -0800
+@@ -1205,6 +1205,15 @@ config SCx200
+ This support is also available as a module. If compiled as a
+ module, it will be called scx200.
+
++config HOTPLUG_CPU
++ bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
++ depends on SMP && HOTPLUG && EXPERIMENTAL
++ ---help---
++ Say Y here to experiment with turning CPUs off and on. CPUs
++ can be controlled through /sys/devices/system/cpu.
++
++ Say N.
++
+ source "drivers/pcmcia/Kconfig"
+
+ source "drivers/pci/hotplug/Kconfig"
+diff -puN arch/i386/kernel/apic.c~i386-cpu-hotplug-updated-for-mm
arch/i386/kernel/apic.c
+--- 25/arch/i386/kernel/apic.c~i386-cpu-hotplug-updated-for-mm 2005-02-23
02:20:06.000000000 -0800
++++ 25-akpm/arch/i386/kernel/apic.c 2005-02-23 02:20:06.000000000 -0800
+@@ -26,6 +26,7 @@
+ #include <linux/mc146818rtc.h>
+ #include <linux/kernel_stat.h>
+ #include <linux/sysdev.h>
++#include <linux/cpu.h>
+
+ #include <asm/atomic.h>
+ #include <asm/smp.h>
+@@ -1048,7 +1049,7 @@ void __init setup_secondary_APIC_clock(v
+ setup_APIC_timer(calibration_result);
+ }
+
+-void __init disable_APIC_timer(void)
++void __devinit disable_APIC_timer(void)
+ {
+ if (using_apic_timer) {
+ unsigned long v;
+diff -puN arch/i386/kernel/io_apic.c~i386-cpu-hotplug-updated-for-mm
arch/i386/kernel/io_apic.c
+--- 25/arch/i386/kernel/io_apic.c~i386-cpu-hotplug-updated-for-mm
2005-02-23 02:20:06.000000000 -0800
++++ 25-akpm/arch/i386/kernel/io_apic.c 2005-02-23 02:20:06.000000000 -0800
+@@ -576,9 +576,11 @@ static int balanced_irq(void *unused)
+ try_to_freeze(PF_FREEZE);
+ if (time_after(jiffies,
+ prev_balance_time+balanced_irq_interval)) {
++ preempt_disable();
+ do_irq_balance();
+ prev_balance_time = jiffies;
+ time_remaining = balanced_irq_interval;
++ preempt_enable();
+ }
+ }
+ return 0;
+diff -puN arch/i386/kernel/irq.c~i386-cpu-hotplug-updated-for-mm
arch/i386/kernel/irq.c
+--- 25/arch/i386/kernel/irq.c~i386-cpu-hotplug-updated-for-mm 2005-02-23
02:20:06.000000000 -0800
++++ 25-akpm/arch/i386/kernel/irq.c 2005-02-23 02:20:06.000000000 -0800
+@@ -15,6 +15,9 @@
+ #include <linux/seq_file.h>
+ #include <linux/interrupt.h>
+ #include <linux/kernel_stat.h>
++#include <linux/notifier.h>
++#include <linux/cpu.h>
++#include <linux/delay.h>
+
+ #ifndef CONFIG_X86_LOCAL_APIC
+ /*
+@@ -209,9 +212,8 @@ int show_interrupts(struct seq_file *p,
+
+ if (i == 0) {
+ seq_printf(p, " ");
+- for (j=0; j<NR_CPUS; j++)
+- if (cpu_online(j))
+- seq_printf(p, "CPU%d ",j);
++ for_each_cpu(j)
++ seq_printf(p, "CPU%d ",j);
+ seq_putc(p, '\n');
+ }
+
+@@ -224,9 +226,8 @@ int show_interrupts(struct seq_file *p,
+ #ifndef CONFIG_SMP
+ seq_printf(p, "%10u ", kstat_irqs(i));
+ #else
+- for (j = 0; j < NR_CPUS; j++)
+- if (cpu_online(j))
+- seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
++ for_each_cpu(j)
++ seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+ #endif
+ seq_printf(p, " %14s", irq_desc[i].handler->typename);
+ seq_printf(p, " %s", action->name);
+@@ -239,16 +240,13 @@ skip:
+ spin_unlock_irqrestore(&irq_desc[i].lock, flags);
+ } else if (i == NR_IRQS) {
+ seq_printf(p, "NMI: ");
+- for (j = 0; j < NR_CPUS; j++)
+- if (cpu_online(j))
+- seq_printf(p, "%10u ", nmi_count(j));
++ for_each_cpu(j)
++ seq_printf(p, "%10u ", nmi_count(j));
+ seq_putc(p, '\n');
+ #ifdef CONFIG_X86_LOCAL_APIC
+ seq_printf(p, "LOC: ");
+- for (j = 0; j < NR_CPUS; j++)
+- if (cpu_online(j))
+- seq_printf(p, "%10u ",
+- irq_stat[j].apic_timer_irqs);
++ for_each_cpu(j)
++ seq_printf(p, "%10u ", irq_stat[j].apic_timer_irqs);
+ seq_putc(p, '\n');
+ #endif
+ seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
+@@ -258,3 +256,45 @@ skip:
+ }
+ return 0;
+ }
++
++#ifdef CONFIG_HOTPLUG_CPU
++#include <mach_apic.h>
++
++void fixup_irqs(cpumask_t map)
++{
++ unsigned int irq;
++ static int warned;
++
++ for (irq = 0; irq < NR_IRQS; irq++) {
++ cpumask_t mask;
++ if (irq == 2)
++ continue;
++
++ cpus_and(mask, irq_affinity[irq], map);
++ if (any_online_cpu(mask) == NR_CPUS) {
++ printk("Breaking affinity for irq %i\n", irq);
++ mask = map;
++ }
++ if (irq_desc[irq].handler->set_affinity)
++ irq_desc[irq].handler->set_affinity(irq, mask);
++ else if (irq_desc[irq].action && !(warned++))
++ printk("Cannot set affinity for irq %i\n", irq);
++ }
++
++#if 0
++ barrier();
++ /* Ingo Molnar says: "after the IO-APIC masks have been redirected
++ [note the nop - the interrupt-enable boundary on x86 is two
++ instructions from sti] - to flush out pending hardirqs and
++ IPIs. After this point nothing is supposed to reach this CPU." */
++ __asm__ __volatile__("sti; nop; cli");
++ barrier();
++#else
++ /* That doesn't seem sufficient. Give it 1ms. */
++ local_irq_enable();
++ mdelay(1);
++ local_irq_disable();
++#endif
++}
++#endif
++
+diff -puN arch/i386/kernel/msr.c~i386-cpu-hotplug-updated-for-mm
arch/i386/kernel/msr.c
+--- 25/arch/i386/kernel/msr.c~i386-cpu-hotplug-updated-for-mm 2005-02-23
02:20:06.000000000 -0800
++++ 25-akpm/arch/i386/kernel/msr.c 2005-02-23 02:20:06.000000000 -0800
+@@ -260,7 +260,7 @@ static struct file_operations msr_fops =
+ .open = msr_open,
+ };
+
+-static int msr_class_simple_device_add(int i)
++static int __devinit msr_class_simple_device_add(int i)
+ {
+ int err = 0;
+ struct class_device *class_err;
+diff -puN arch/i386/kernel/process.c~i386-cpu-hotplug-updated-for-mm
arch/i386/kernel/process.c
+--- 25/arch/i386/kernel/process.c~i386-cpu-hotplug-updated-for-mm
2005-02-23 02:20:06.000000000 -0800
++++ 25-akpm/arch/i386/kernel/process.c 2005-02-23 02:20:06.000000000 -0800
+@@ -13,6 +13,7 @@
+
+ #include <stdarg.h>
+
++#include <linux/cpu.h>
+ #include <linux/errno.h>
+ #include <linux/sched.h>
+ #include <linux/fs.h>
+@@ -55,6 +56,9 @@
+ #include <linux/irq.h>
+ #include <linux/err.h>
+
++#include <asm/tlbflush.h>
++#include <asm/cpu.h>
++
+ asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
+
+ int hlt_counter;
+@@ -139,6 +143,34 @@ static void poll_idle (void)
+ }
+ }
+
++#ifdef CONFIG_HOTPLUG_CPU
++#include <asm/nmi.h>
++/* We don't actually take CPU down, just spin without interrupts. */
++static inline void play_dead(void)
++{
++ /* Ack it */
++ __get_cpu_var(cpu_state) = CPU_DEAD;
++
++ /* We shouldn't have to disable interrupts while dead, but
++ * some interrupts just don't seem to go away, and this makes
++ * it "work" for testing purposes. */
++ /* Death loop */
++ while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE)
++ cpu_relax();
++
++ local_irq_disable();
++ __flush_tlb_all();
++ cpu_set(smp_processor_id(), cpu_online_map);
++ enable_APIC_timer();
++ local_irq_enable();
++}
++#else
++static inline void play_dead(void)
++{
++ BUG();
++}
++#endif /* CONFIG_HOTPLUG_CPU */
++
+ /*
+ * The idle thread. There's no useful work to be
+ * done, so just try to conserve power and have a
+@@ -162,6 +194,9 @@ void cpu_idle (void)
+ if (!idle)
+ idle = default_idle;
+
++ if (cpu_is_offline(cpu))
++ play_dead();
++
+ irq_stat[cpu].idle_timestamp = jiffies;
+ idle();
+ }
+diff -puN arch/i386/kernel/smpboot.c~i386-cpu-hotplug-updated-for-mm
arch/i386/kernel/smpboot.c
+--- 25/arch/i386/kernel/smpboot.c~i386-cpu-hotplug-updated-for-mm
2005-02-23 02:20:06.000000000 -0800
++++ 25-akpm/arch/i386/kernel/smpboot.c 2005-02-23 02:20:06.000000000 -0800
+@@ -44,6 +44,9 @@
+ #include <linux/smp_lock.h>
+ #include <linux/irq.h>
+ #include <linux/bootmem.h>
++#include <linux/notifier.h>
++#include <linux/cpu.h>
++#include <linux/percpu.h>
+
+ #include <linux/delay.h>
+ #include <linux/mc146818rtc.h>
+@@ -89,6 +92,9 @@ extern unsigned char trampoline_end [];
+ static unsigned char *trampoline_base;
+ static int trampoline_exec;
+
++/* State of each CPU. */
++DEFINE_PER_CPU(int, cpu_state) = { 0 };
++
+ /*
+ * Currently trivial. Write the real->protected mode
+ * bootstrap into the page concerned. The caller
+@@ -1095,6 +1101,9 @@ static void __init smp_boot_cpus(unsigne
+ who understands all this stuff should rewrite it properly. --RR 15/Jul/02
*/
+ void __init smp_prepare_cpus(unsigned int max_cpus)
+ {
++ smp_commenced_mask = cpumask_of_cpu(0);
++ cpu_callin_map = cpumask_of_cpu(0);
++ mb();
+ smp_boot_cpus(max_cpus);
+ }
+
+@@ -1104,20 +1113,99 @@ void __devinit smp_prepare_boot_cpu(void
+ cpu_set(smp_processor_id(), cpu_callout_map);
+ }
+
+-int __devinit __cpu_up(unsigned int cpu)
++#ifdef CONFIG_HOTPLUG_CPU
++
++/* must be called with the cpucontrol mutex held */
++static int __devinit cpu_enable(unsigned int cpu)
+ {
+- /* This only works at boot for x86. See "rewrite" above. */
+- if (cpu_isset(cpu, smp_commenced_mask)) {
+- local_irq_enable();
+- return -ENOSYS;
++ /* get the target out of its holding state */
++ per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
++ wmb();
++
++ /* wait for the processor to ack it. timeout? */
++ while (!cpu_online(cpu))
++ cpu_relax();
++
++ fixup_irqs(cpu_online_map);
++ /* counter the disable in fixup_irqs() */
++ local_irq_enable();
++ return 0;
++}
++
++int __cpu_disable(void)
++{
++ cpumask_t map = cpu_online_map;
++ int cpu = smp_processor_id();
++
++ /*
++ * Perhaps use cpufreq to drop frequency, but that could go
++ * into generic code.
++ *
++ * We won't take down the boot processor on i386 due to some
++ * interrupts only being able to be serviced by the BSP.
++ * Especially so if we're not using an IOAPIC -zwane
++ */
++ if (cpu == 0)
++ return -EBUSY;
++
++ /* We enable the timer again on the exit path of the death loop */
++ disable_APIC_timer();
++ /* Allow any queued timer interrupts to get serviced */
++ local_irq_enable();
++ mdelay(1);
++ local_irq_disable();
++
++ cpu_clear(cpu, map);
++ fixup_irqs(map);
++ /* It's now safe to remove this processor from the online map */
++ cpu_clear(cpu, cpu_online_map);
++ return 0;
++}
++
++void __cpu_die(unsigned int cpu)
++{
++ /* We don't do anything here: idle task is faking death itself. */
++ unsigned int i;
++
++ for (i = 0; i < 10; i++) {
++ /* They ack this in play_dead by setting CPU_DEAD */
++ if (per_cpu(cpu_state, cpu) == CPU_DEAD)
++ return;
++ current->state = TASK_UNINTERRUPTIBLE;
++ schedule_timeout(HZ/10);
+ }
++ printk(KERN_ERR "CPU %u didn't die...\n", cpu);
++}
++#else /* ... !CONFIG_HOTPLUG_CPU */
++int __cpu_disable(void)
++{
++ return -ENOSYS;
++}
+
++void __cpu_die(unsigned int cpu)
++{
++ /* We said "no" in __cpu_disable */
++ BUG();
++}
++#endif /* CONFIG_HOTPLUG_CPU */
++
++int __devinit __cpu_up(unsigned int cpu)
++{
+ /* In case one didn't come up */
+ if (!cpu_isset(cpu, cpu_callin_map)) {
++ printk(KERN_DEBUG "skipping cpu%d, didn't come online\n", cpu);
+ local_irq_enable();
+ return -EIO;
+ }
+
++#ifdef CONFIG_HOTPLUG_CPU
++ /* Already up, and in cpu_quiescent now? */
++ if (cpu_isset(cpu, smp_commenced_mask)) {
++ cpu_enable(cpu);
++ return 0;
++ }
++#endif
++
+ local_irq_enable();
+ /* Unleash the CPU! */
+ cpu_set(cpu, smp_commenced_mask);
+diff -puN arch/i386/kernel/smp.c~i386-cpu-hotplug-updated-for-mm
arch/i386/kernel/smp.c
+--- 25/arch/i386/kernel/smp.c~i386-cpu-hotplug-updated-for-mm 2005-02-23
02:20:06.000000000 -0800
++++ 25-akpm/arch/i386/kernel/smp.c 2005-02-23 02:20:06.000000000 -0800
+@@ -19,6 +19,7 @@
+ #include <linux/mc146818rtc.h>
+ #include <linux/cache.h>
+ #include <linux/interrupt.h>
++#include <linux/cpu.h>
+
+ #include <asm/mtrr.h>
+ #include <asm/tlbflush.h>
+@@ -163,7 +164,7 @@ void send_IPI_mask_bitmask(cpumask_t cpu
+ unsigned long flags;
+
+ local_irq_save(flags);
+-
++ WARN_ON(mask & ~cpus_addr(cpu_online_map)[0]);
+ /*
+ * Wait for idle.
+ */
+@@ -345,21 +346,21 @@ out:
+ static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
+ unsigned long va)
+ {
+- cpumask_t tmp;
+ /*
+ * A couple of (to be removed) sanity checks:
+ *
+- * - we do not send IPIs to not-yet booted CPUs.
+ * - current CPU must not be in mask
+ * - mask must exist :)
+ */
+ BUG_ON(cpus_empty(cpumask));
+-
+- cpus_and(tmp, cpumask, cpu_online_map);
+- BUG_ON(!cpus_equal(cpumask, tmp));
+ BUG_ON(cpu_isset(smp_processor_id(), cpumask));
+ BUG_ON(!mm);
+
++ /* If a CPU which we ran on has gone down, OK. */
++ cpus_and(cpumask, cpumask, cpu_online_map);
++ if (cpus_empty(cpumask))
++ return;
++
+ /*
+ * i'm not happy about this global shared spinlock in the
+ * MM hot path, but we'll see how contended it is.
+@@ -484,6 +485,7 @@ void smp_send_nmi_allbutself(void)
+ */
+ void smp_send_reschedule(int cpu)
+ {
++ WARN_ON(cpu_is_offline(cpu));
+ send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR);
+ }
+
+@@ -524,10 +526,16 @@ int smp_call_function (void (*func) (voi
+ */
+ {
+ struct call_data_struct data;
+- int cpus = num_online_cpus()-1;
++ int cpus;
+
+- if (!cpus)
++ /* Holding any lock stops cpus from going down. */
++ spin_lock(&call_lock);
++ cpus = num_online_cpus()-1;
++
++ if (!cpus) {
++ spin_unlock(&call_lock);
+ return 0;
++ }
+
+ /* Can deadlock when called with interrupts disabled */
+ WARN_ON(irqs_disabled());
+@@ -539,7 +547,6 @@ int smp_call_function (void (*func) (voi
+ if (wait)
+ atomic_set(&data.finished, 0);
+
+- spin_lock(&call_lock);
+ call_data = &data;
+ mb();
+
+diff -puN arch/i386/kernel/traps.c~i386-cpu-hotplug-updated-for-mm
arch/i386/kernel/traps.c
+--- 25/arch/i386/kernel/traps.c~i386-cpu-hotplug-updated-for-mm
2005-02-23 02:20:06.000000000 -0800
++++ 25-akpm/arch/i386/kernel/traps.c 2005-02-23 02:20:06.000000000 -0800
+@@ -669,6 +669,14 @@ fastcall void do_nmi(struct pt_regs * re
+ nmi_enter();
+
+ cpu = smp_processor_id();
++
++#ifdef CONFIG_HOTPLUG_CPU
++ if (!cpu_online(cpu)) {
++ nmi_exit();
++ return;
++ }
++#endif
++
+ ++nmi_count(cpu);
+
+ if (!nmi_callback(regs, cpu))
+diff -puN arch/ia64/kernel/smpboot.c~i386-cpu-hotplug-updated-for-mm
arch/ia64/kernel/smpboot.c
+--- 25/arch/ia64/kernel/smpboot.c~i386-cpu-hotplug-updated-for-mm
2005-02-23 02:20:06.000000000 -0800
++++ 25-akpm/arch/ia64/kernel/smpboot.c 2005-02-23 02:20:06.000000000 -0800
+@@ -590,9 +590,10 @@ int __cpu_disable(void)
+ if (cpu == 0)
+ return -EBUSY;
+
++ cpu_clear(cpu, cpu_online_map);
+ fixup_irqs();
+ local_flush_tlb_all();
+- printk ("Disabled cpu %u\n", smp_processor_id());
++ printk("Disabled cpu %u\n", cpu);
+ return 0;
+ }
+
+diff -puN arch/ppc64/kernel/smp.c~i386-cpu-hotplug-updated-for-mm
arch/ppc64/kernel/smp.c
+diff -puN arch/s390/kernel/smp.c~i386-cpu-hotplug-updated-for-mm
arch/s390/kernel/smp.c
+--- 25/arch/s390/kernel/smp.c~i386-cpu-hotplug-updated-for-mm 2005-02-23
02:20:06.000000000 -0800
++++ 25-akpm/arch/s390/kernel/smp.c 2005-02-23 02:20:06.000000000 -0800
+@@ -679,12 +679,14 @@ __cpu_disable(void)
+ {
+ unsigned long flags;
+ ec_creg_mask_parms cr_parms;
++ int cpu = smp_processor_id();
+
+ spin_lock_irqsave(&smp_reserve_lock, flags);
+- if (smp_cpu_reserved[smp_processor_id()] != 0) {
++ if (smp_cpu_reserved[cpu] != 0) {
+ spin_unlock_irqrestore(&smp_reserve_lock, flags);
+ return -EBUSY;
+ }
++ cpu_clear(cpu, cpu_online_map);
+
+ #ifdef CONFIG_PFAULT
+ /* Disable pfault pseudo page faults on this cpu. */
+diff -puN include/asm-i386/cpu.h~i386-cpu-hotplug-updated-for-mm
include/asm-i386/cpu.h
+--- 25/include/asm-i386/cpu.h~i386-cpu-hotplug-updated-for-mm 2005-02-23
02:20:06.000000000 -0800
++++ 25-akpm/include/asm-i386/cpu.h 2005-02-23 02:20:06.000000000 -0800
+@@ -5,6 +5,7 @@
+ #include <linux/cpu.h>
+ #include <linux/topology.h>
+ #include <linux/nodemask.h>
++#include <linux/percpu.h>
+
+ #include <asm/node.h>
+
+@@ -17,4 +18,5 @@ extern int arch_register_cpu(int num);
+ extern void arch_unregister_cpu(int);
+ #endif
+
++DECLARE_PER_CPU(int, cpu_state);
+ #endif /* _ASM_I386_CPU_H_ */
+diff -puN include/asm-i386/irq.h~i386-cpu-hotplug-updated-for-mm
include/asm-i386/irq.h
+--- 25/include/asm-i386/irq.h~i386-cpu-hotplug-updated-for-mm 2005-02-23
02:20:06.000000000 -0800
++++ 25-akpm/include/asm-i386/irq.h 2005-02-23 02:20:06.000000000 -0800
+@@ -38,4 +38,8 @@ extern void release_vm86_irqs(struct tas
+ extern int irqbalance_disable(char *str);
+ #endif
+
++#ifdef CONFIG_HOTPLUG_CPU
++extern void fixup_irqs(cpumask_t map);
++#endif
++
+ #endif /* _ASM_IRQ_H */
+diff -puN include/asm-i386/smp.h~i386-cpu-hotplug-updated-for-mm
include/asm-i386/smp.h
+--- 25/include/asm-i386/smp.h~i386-cpu-hotplug-updated-for-mm 2005-02-23
02:20:06.000000000 -0800
++++ 25-akpm/include/asm-i386/smp.h 2005-02-23 02:20:06.000000000 -0800
+@@ -85,6 +85,9 @@ static __inline int logical_smp_processo
+ }
+
+ #endif
++
++extern int __cpu_disable(void);
++extern void __cpu_die(unsigned int cpu);
+ #endif /* !__ASSEMBLY__ */
+
+ #define NO_PROC_ID 0xFF /* No processor magic marker */
+diff -puN kernel/cpu.c~i386-cpu-hotplug-updated-for-mm kernel/cpu.c
+--- 25/kernel/cpu.c~i386-cpu-hotplug-updated-for-mm 2005-02-23
02:20:06.000000000 -0800
++++ 25-akpm/kernel/cpu.c 2005-02-23 02:20:06.000000000 -0800
+@@ -63,19 +63,15 @@ static int take_cpu_down(void *unused)
+ {
+ int err;
+
+- /* Take offline: makes arch_cpu_down somewhat easier. */
+- cpu_clear(smp_processor_id(), cpu_online_map);
+-
+ /* Ensure this CPU doesn't handle any more interrupts. */
+ err = __cpu_disable();
+ if (err < 0)
+- cpu_set(smp_processor_id(), cpu_online_map);
+- else
+- /* Force idle task to run as soon as we yield: it should
+- immediately notice cpu is offline and die quickly. */
+- sched_idle_next();
++ return err;
+
+- return err;
++ /* Force idle task to run as soon as we yield: it should
++ immediately notice cpu is offline and die quickly. */
++ sched_idle_next();
++ return 0;
+ }
+
+ int cpu_down(unsigned int cpu)
+diff -puN arch/ppc64/kernel/pSeries_smp.c~i386-cpu-hotplug-updated-for-mm
arch/ppc64/kernel/pSeries_smp.c
+--- 25/arch/ppc64/kernel/pSeries_smp.c~i386-cpu-hotplug-updated-for-mm
2005-02-23 02:20:08.000000000 -0800
++++ 25-akpm/arch/ppc64/kernel/pSeries_smp.c 2005-02-23 02:20:08.000000000
-0800
+@@ -86,10 +86,13 @@ static int query_cpu_stopped(unsigned in
+
+ int pSeries_cpu_disable(void)
+ {
++ int cpu = smp_processor_id();
++
++ cpu_clear(cpu, cpu_online_map);
+ systemcfg->processorCount--;
+
+ /*fix boot_cpuid here*/
+- if (smp_processor_id() == boot_cpuid)
++ if (cpu == boot_cpuid)
+ boot_cpuid = any_online_cpu(cpu_online_map);
+
+ /* FIXME: abstract this to not be platform specific later on */
+_
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/mach_time.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/mach_time.h
Fri Jul 15 13:39:50 2005
@@ -0,0 +1,122 @@
+/*
+ * include/asm-i386/mach-default/mach_time.h
+ *
+ * Machine specific set RTC function for generic.
+ * Split out from time.c by Osamu Tomita <tomita@xxxxxxxxxxx>
+ */
+#ifndef _MACH_TIME_H
+#define _MACH_TIME_H
+
+#include <linux/mc146818rtc.h>
+
+/* for check timing call set_rtc_mmss() 500ms */
+/* used in arch/i386/time.c::do_timer_interrupt() */
+#define USEC_AFTER 500000
+#define USEC_BEFORE 500000
+
+/*
+ * In order to set the CMOS clock precisely, set_rtc_mmss has to be
+ * called 500 ms after the second nowtime has started, because when
+ * nowtime is written into the registers of the CMOS clock, it will
+ * jump to the next second precisely 500 ms later. Check the Motorola
+ * MC146818A or Dallas DS12887 data sheet for details.
+ *
+ * BUG: This routine does not handle hour overflow properly; it just
+ * sets the minutes. Usually you'll only notice that after reboot!
+ */
+static inline int mach_set_rtc_mmss(unsigned long nowtime)
+{
+ int retval = 0;
+ int real_seconds, real_minutes, cmos_minutes;
+ unsigned char save_control, save_freq_select;
+
+ save_control = CMOS_READ(RTC_CONTROL); /* tell the clock it's being set
*/
+ CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL);
+
+ save_freq_select = CMOS_READ(RTC_FREQ_SELECT); /* stop and reset
prescaler */
+ CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT);
+
+ cmos_minutes = CMOS_READ(RTC_MINUTES);
+ if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
+ BCD_TO_BIN(cmos_minutes);
+
+ /*
+ * since we're only adjusting minutes and seconds,
+ * don't interfere with hour overflow. This avoids
+ * messing with unknown time zones but requires your
+ * RTC not to be off by more than 15 minutes
+ */
+ real_seconds = nowtime % 60;
+ real_minutes = nowtime / 60;
+ if (((abs(real_minutes - cmos_minutes) + 15)/30) & 1)
+ real_minutes += 30; /* correct for half hour time
zone */
+ real_minutes %= 60;
+
+ if (abs(real_minutes - cmos_minutes) < 30) {
+ if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
+ BIN_TO_BCD(real_seconds);
+ BIN_TO_BCD(real_minutes);
+ }
+ CMOS_WRITE(real_seconds,RTC_SECONDS);
+ CMOS_WRITE(real_minutes,RTC_MINUTES);
+ } else {
+ printk(KERN_WARNING
+ "set_rtc_mmss: can't update from %d to %d\n",
+ cmos_minutes, real_minutes);
+ retval = -1;
+ }
+
+ /* The following flags have to be released exactly in this order,
+ * otherwise the DS12887 (popular MC146818A clone with integrated
+ * battery and quartz) will not reset the oscillator and will not
+ * update precisely 500 ms later. You won't find this mentioned in
+ * the Dallas Semiconductor data sheets, but who believes data
+ * sheets anyway ... -- Markus Kuhn
+ */
+ CMOS_WRITE(save_control, RTC_CONTROL);
+ CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
+
+ return retval;
+}
+
+static inline unsigned long mach_get_cmos_time(void)
+{
+ unsigned int year, mon, day, hour, min, sec;
+ int i;
+
+ /* The Linux interpretation of the CMOS clock register contents:
+ * When the Update-In-Progress (UIP) flag goes from 1 to 0, the
+ * RTC registers show the second which has precisely just started.
+ * Let's hope other operating systems interpret the RTC the same way.
+ */
+ /* read RTC exactly on falling edge of update flag */
+ for (i = 0 ; i < 1000000 ; i++) /* may take up to 1 second... */
+ if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP)
+ break;
+ for (i = 0 ; i < 1000000 ; i++) /* must try at least 2.228 ms */
+ if (!(CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP))
+ break;
+ do { /* Isn't this overkill ? UIP above should guarantee consistency */
+ sec = CMOS_READ(RTC_SECONDS);
+ min = CMOS_READ(RTC_MINUTES);
+ hour = CMOS_READ(RTC_HOURS);
+ day = CMOS_READ(RTC_DAY_OF_MONTH);
+ mon = CMOS_READ(RTC_MONTH);
+ year = CMOS_READ(RTC_YEAR);
+ } while (sec != CMOS_READ(RTC_SECONDS));
+ if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
+ {
+ BCD_TO_BIN(sec);
+ BCD_TO_BIN(min);
+ BCD_TO_BIN(hour);
+ BCD_TO_BIN(day);
+ BCD_TO_BIN(mon);
+ BCD_TO_BIN(year);
+ }
+ if ((year += 1900) < 1970)
+ year += 100;
+
+ return mktime(year, mon, day, hour, min, sec);
+}
+
+#endif /* !_MACH_TIME_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/ctrl_if.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/ctrl_if.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,160 @@
+/******************************************************************************
+ * ctrl_if.h
+ *
+ * Management functions for special interface to the domain controller.
+ *
+ * Copyright (c) 2004, K A Fraser
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __ASM_XEN__CTRL_IF_H__
+#define __ASM_XEN__CTRL_IF_H__
+
+#include <asm-xen/hypervisor.h>
+#include <asm-xen/queues.h>
+
+typedef control_msg_t ctrl_msg_t;
+
+/*
+ * Callback function type. Called for asynchronous processing of received
+ * request messages, and responses to previously-transmitted request messages.
+ * The parameters are (@msg, @id).
+ * @msg: Original request/response message (not a copy). The message can be
+ * modified in-place by the handler (e.g., a response callback can
+ * turn a request message into a response message in place). The message
+ * is no longer accessible after the callback handler returns -- if the
+ * message is required to persist for longer then it must be copied.
+ * @id: (Response callbacks only) The 'id' that was specified when the
+ * original request message was queued for transmission.
+ */
+typedef void (*ctrl_msg_handler_t)(ctrl_msg_t *, unsigned long);
+
+/*
+ * Send @msg to the domain controller. Execute @hnd when a response is
+ * received, passing the response message and the specified @id. This
+ * operation will not block: it will return -EAGAIN if there is no space.
+ * Notes:
+ * 1. The @msg is copied if it is transmitted and so can be freed after this
+ * function returns.
+ * 2. If @hnd is NULL then no callback is executed.
+ */
+int
+ctrl_if_send_message_noblock(
+ ctrl_msg_t *msg,
+ ctrl_msg_handler_t hnd,
+ unsigned long id);
+
+/*
+ * Send @msg to the domain controller. Execute @hnd when a response is
+ * received, passing the response message and the specified @id. This
+ * operation will block until the message is sent, or a signal is received
+ * for the calling process (unless @wait_state is TASK_UNINTERRUPTIBLE).
+ * Notes:
+ * 1. The @msg is copied if it is transmitted and so can be freed after this
+ * function returns.
+ * 2. If @hnd is NULL then no callback is executed.
+ */
+int
+ctrl_if_send_message_block(
+ ctrl_msg_t *msg,
+ ctrl_msg_handler_t hnd,
+ unsigned long id,
+ long wait_state);
+
+/*
+ * Send @msg to the domain controller. Block until the response is received,
+ * and then copy it into the provided buffer, @rmsg.
+ */
+int
+ctrl_if_send_message_and_get_response(
+ ctrl_msg_t *msg,
+ ctrl_msg_t *rmsg,
+ long wait_state);
+
+/*
+ * Request a callback when there is /possibly/ space to immediately send a
+ * message to the domain controller. This function returns 0 if there is
+ * already space to trasnmit a message --- in this case the callback task /may/
+ * still be executed. If this function returns 1 then the callback /will/ be
+ * executed when space becomes available.
+ */
+int
+ctrl_if_enqueue_space_callback(
+ struct tq_struct *task);
+
+/*
+ * Send a response (@msg) to a message from the domain controller. This will
+ * never block.
+ * Notes:
+ * 1. The @msg is copied and so can be freed after this function returns.
+ * 2. The @msg may be the original request message, modified in-place.
+ */
+void
+ctrl_if_send_response(
+ ctrl_msg_t *msg);
+
+/*
+ * Register a receiver for typed messages from the domain controller. The
+ * handler (@hnd) is called for every received message of specified @type.
+ * Returns TRUE (non-zero) if the handler was successfully registered.
+ * If CALLBACK_IN_BLOCKING CONTEXT is specified in @flags then callbacks will
+ * occur in a context in which it is safe to yield (i.e., process context).
+ */
+#define CALLBACK_IN_BLOCKING_CONTEXT 1
+int ctrl_if_register_receiver(
+ u8 type,
+ ctrl_msg_handler_t hnd,
+ unsigned int flags);
+
+/*
+ * Unregister a receiver for typed messages from the domain controller. The
+ * handler (@hnd) will not be executed after this function returns.
+ */
+void
+ctrl_if_unregister_receiver(
+ u8 type, ctrl_msg_handler_t hnd);
+
+/* Suspend/resume notifications. */
+void ctrl_if_suspend(void);
+void ctrl_if_resume(void);
+
+/* Start-of-day setup. */
+void ctrl_if_init(void);
+
+/*
+ * Returns TRUE if there are no outstanding message requests at the domain
+ * controller. This can be used to ensure that messages have really flushed
+ * through when it is not possible to use the response-callback interface.
+ * WARNING: If other subsystems are using the control interface then this
+ * function might never return TRUE!
+ */
+int ctrl_if_transmitter_empty(void); /* !! DANGEROUS FUNCTION !! */
+
+/*
+ * Manually discard response messages from the domain controller.
+ * WARNING: This is usually done automatically -- this function should only
+ * be called when normal interrupt mechanisms are disabled!
+ */
+void ctrl_if_discard_responses(void); /* !! DANGEROUS FUNCTION !! */
+
+#endif /* __ASM_XEN__CONTROL_IF_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/Kconfig.drivers
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/Kconfig.drivers Fri Jul 15 13:39:50 2005
@@ -0,0 +1,94 @@
+# arch/xen/Kconfig.drivers
+
+menu "Device Drivers"
+
+source "drivers/base/Kconfig"
+
+if XEN_PHYSDEV_ACCESS
+source "drivers/mtd/Kconfig"
+source "drivers/parport/Kconfig"
+source "drivers/pnp/Kconfig"
+endif
+
+source "drivers/block/Kconfig"
+
+if XEN_PHYSDEV_ACCESS
+source "drivers/ide/Kconfig"
+endif
+
+source "drivers/scsi/Kconfig"
+
+if XEN_PHYSDEV_ACCESS
+source "drivers/cdrom/Kconfig"
+endif
+
+source "drivers/md/Kconfig"
+
+if XEN_PHYSDEV_ACCESS
+source "drivers/message/fusion/Kconfig"
+source "drivers/ieee1394/Kconfig"
+source "drivers/message/i2o/Kconfig"
+endif
+
+source "net/Kconfig"
+
+if XEN_PHYSDEV_ACCESS
+source "drivers/isdn/Kconfig"
+source "drivers/telephony/Kconfig"
+source "drivers/input/Kconfig"
+source "drivers/char/Kconfig"
+source "drivers/i2c/Kconfig"
+source "drivers/w1/Kconfig"
+source "drivers/misc/Kconfig"
+source "drivers/media/Kconfig"
+source "drivers/video/Kconfig"
+source "sound/Kconfig"
+source "drivers/usb/Kconfig"
+source "drivers/mmc/Kconfig"
+source "drivers/infiniband/Kconfig"
+endif
+
+if !XEN_PHYSDEV_ACCESS
+
+menu "Character devices"
+
+config UNIX98_PTYS
+ bool
+ default y
+
+config LEGACY_PTYS
+ bool "Legacy (BSD) PTY support"
+ default y
+ ---help---
+ A pseudo terminal (PTY) is a software device consisting of two
+ halves: a master and a slave. The slave device behaves identical to
+ a physical terminal; the master device is used by a process to
+ read data from and write data to the slave, thereby emulating a
+ terminal. Typical programs for the master side are telnet servers
+ and xterms.
+
+ Linux has traditionally used the BSD-like names /dev/ptyxx
+ for masters and /dev/ttyxx for slaves of pseudo
+ terminals. This scheme has a number of problems, including
+ security. This option enables these legacy devices; on most
+ systems, it is safe to say N.
+
+
+config LEGACY_PTY_COUNT
+ int "Maximum number of legacy PTY in use"
+ depends on LEGACY_PTYS
+ range 1 256
+ default "256"
+ ---help---
+ The maximum number of legacy PTYs that can be used at any one time.
+ The default is 256, and should be more than enough. Embedded
+ systems may want to reduce this to save memory.
+
+ When not in use, each legacy PTY occupies 12 bytes on 32-bit
+ architectures and 24 bytes on 64-bit architectures.
+
+endmenu
+
+endif
+
+endmenu
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/vga.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/vga.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,20 @@
+/*
+ * Access to VGA videoram
+ *
+ * (c) 1998 Martin Mares <mj@xxxxxx>
+ */
+
+#ifndef _LINUX_ASM_VGA_H_
+#define _LINUX_ASM_VGA_H_
+
+/*
+ * On the PC, we can just recalculate addresses and then
+ * access the videoram directly without any black magic.
+ */
+
+#define VGA_MAP_MEM(x) (unsigned long)isa_bus_to_virt(x)
+
+#define vga_readb(x) (*(x))
+#define vga_writeb(x,y) (*(y) = (x))
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/timers/timer_tsc.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/timers/timer_tsc.c Fri Jul
15 13:39:50 2005
@@ -0,0 +1,379 @@
+/*
+ * This code largely moved from arch/i386/kernel/time.c.
+ * See comments there for proper credits.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <linux/timex.h>
+#include <linux/errno.h>
+#include <linux/cpufreq.h>
+#include <linux/string.h>
+#include <linux/jiffies.h>
+
+#include <asm/timer.h>
+#include <asm/io.h>
+/* processor.h for distable_tsc flag */
+#include <asm/processor.h>
+
+#include "io_ports.h"
+#include "mach_timer.h"
+
+#include <asm/hpet.h>
+
+#ifdef CONFIG_HPET_TIMER
+static unsigned long hpet_usec_quotient;
+static unsigned long hpet_last;
+static struct timer_opts timer_tsc;
+#endif
+
+static inline void cpufreq_delayed_get(void);
+
+int tsc_disable __initdata = 0;
+
+extern spinlock_t i8253_lock;
+
+static int use_tsc;
+
+static unsigned long long monotonic_base;
+static u32 monotonic_offset;
+static seqlock_t monotonic_lock = SEQLOCK_UNLOCKED;
+
+/* convert from cycles(64bits) => nanoseconds (64bits)
+ * basic equation:
+ * ns = cycles / (freq / ns_per_sec)
+ * ns = cycles * (ns_per_sec / freq)
+ * ns = cycles * (10^9 / (cpu_mhz * 10^6))
+ * ns = cycles * (10^3 / cpu_mhz)
+ *
+ * Then we use scaling math (suggested by george@xxxxxxxxxx) to get:
+ * ns = cycles * (10^3 * SC / cpu_mhz) / SC
+ * ns = cycles * cyc2ns_scale / SC
+ *
+ * And since SC is a constant power of two, we can convert the div
+ * into a shift.
+ * -johnstul@xxxxxxxxxx "math is hard, lets go shopping!"
+ */
+static unsigned long cyc2ns_scale;
+#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
+
+static inline void set_cyc2ns_scale(unsigned long cpu_mhz)
+{
+ cyc2ns_scale = (1000 << CYC2NS_SCALE_FACTOR)/cpu_mhz;
+}
+
+static inline unsigned long long cycles_2_ns(unsigned long long cyc)
+{
+ return (cyc * cyc2ns_scale) >> CYC2NS_SCALE_FACTOR;
+}
+
+/* Cached *multiplier* to convert TSC counts to microseconds.
+ * (see the equation below).
+ * Equal to 2^32 * (1 / (clocks per usec) ).
+ * Initialized in time_init.
+ */
+static unsigned long fast_gettimeoffset_quotient;
+
+extern u32 shadow_tsc_stamp;
+extern u64 shadow_system_time;
+
+static unsigned long get_offset_tsc(void)
+{
+ register unsigned long eax, edx;
+
+ /* Read the Time Stamp Counter */
+
+ rdtsc(eax,edx);
+
+ /* .. relative to previous jiffy (32 bits is enough) */
+ eax -= shadow_tsc_stamp;
+
+ /*
+ * Time offset = (tsc_low delta) * fast_gettimeoffset_quotient
+ * = (tsc_low delta) * (usecs_per_clock)
+ * = (tsc_low delta) * (usecs_per_jiffy / clocks_per_jiffy)
+ *
+ * Using a mull instead of a divl saves up to 31 clock cycles
+ * in the critical path.
+ */
+
+ __asm__("mull %2"
+ :"=a" (eax), "=d" (edx)
+ :"rm" (fast_gettimeoffset_quotient),
+ "0" (eax));
+
+ /* our adjusted time offset in microseconds */
+ return edx;
+}
+
+static unsigned long long monotonic_clock_tsc(void)
+{
+ unsigned long long last_offset, this_offset, base;
+ unsigned seq;
+
+ /* atomically read monotonic base & last_offset */
+ do {
+ seq = read_seqbegin(&monotonic_lock);
+ last_offset = monotonic_offset;
+ base = monotonic_base;
+ } while (read_seqretry(&monotonic_lock, seq));
+
+ /* Read the Time Stamp Counter */
+ rdtscll(this_offset);
+
+ /* return the value in ns */
+ return base + cycles_2_ns(this_offset - last_offset);
+}
+
+/*
+ * Scheduler clock - returns current time in nanosec units.
+ */
+unsigned long long sched_clock(void)
+{
+ unsigned long long this_offset;
+
+ /*
+ * In the NUMA case we dont use the TSC as they are not
+ * synchronized across all CPUs.
+ */
+#ifndef CONFIG_NUMA
+ if (!use_tsc)
+#endif
+ /* no locking but a rare wrong value is not a big deal */
+ return jiffies_64 * (1000000000 / HZ);
+
+ /* Read the Time Stamp Counter */
+ rdtscll(this_offset);
+
+ /* return the value in ns */
+ return cycles_2_ns(this_offset);
+}
+
+
+static void mark_offset_tsc(void)
+{
+
+ /* update the monotonic base value */
+ write_seqlock(&monotonic_lock);
+ monotonic_base = shadow_system_time;
+ monotonic_offset = shadow_tsc_stamp;
+ write_sequnlock(&monotonic_lock);
+}
+
+static void delay_tsc(unsigned long loops)
+{
+ unsigned long bclock, now;
+
+ rdtscl(bclock);
+ do
+ {
+ rep_nop();
+ rdtscl(now);
+ } while ((now-bclock) < loops);
+}
+
+#ifdef CONFIG_HPET_TIMER
+static void mark_offset_tsc_hpet(void)
+{
+ unsigned long long this_offset, last_offset;
+ unsigned long offset, temp, hpet_current;
+
+ write_seqlock(&monotonic_lock);
+ last_offset = ((unsigned long long)last_tsc_high<<32)|last_tsc_low;
+ /*
+ * It is important that these two operations happen almost at
+ * the same time. We do the RDTSC stuff first, since it's
+ * faster. To avoid any inconsistencies, we need interrupts
+ * disabled locally.
+ */
+ /*
+ * Interrupts are just disabled locally since the timer irq
+ * has the SA_INTERRUPT flag set. -arca
+ */
+ /* read Pentium cycle counter */
+
+ hpet_current = hpet_readl(HPET_COUNTER);
+ rdtsc(last_tsc_low, last_tsc_high);
+
+ /* lost tick compensation */
+ offset = hpet_readl(HPET_T0_CMP) - hpet_tick;
+ if (unlikely(((offset - hpet_last) > hpet_tick) && (hpet_last != 0))) {
+ int lost_ticks = (offset - hpet_last) / hpet_tick;
+ jiffies_64 += lost_ticks;
+ }
+ hpet_last = hpet_current;
+
+ /* update the monotonic base value */
+ this_offset = ((unsigned long long)last_tsc_high<<32)|last_tsc_low;
+ monotonic_base += cycles_2_ns(this_offset - last_offset);
+ write_sequnlock(&monotonic_lock);
+
+ /* calculate delay_at_last_interrupt */
+ /*
+ * Time offset = (hpet delta) * ( usecs per HPET clock )
+ * = (hpet delta) * ( usecs per tick / HPET clocks per tick)
+ * = (hpet delta) * ( hpet_usec_quotient ) / (2^32)
+ * Where,
+ * hpet_usec_quotient = (2^32 * usecs per tick)/HPET clocks per tick
+ */
+ delay_at_last_interrupt = hpet_current - offset;
+ ASM_MUL64_REG(temp, delay_at_last_interrupt,
+ hpet_usec_quotient, delay_at_last_interrupt);
+}
+#endif
+
+
+#ifdef CONFIG_CPU_FREQ
+#include <linux/workqueue.h>
+
+static unsigned int cpufreq_delayed_issched = 0;
+static unsigned int cpufreq_init = 0;
+static struct work_struct cpufreq_delayed_get_work;
+
+static void handle_cpufreq_delayed_get(void *v)
+{
+ unsigned int cpu;
+ for_each_online_cpu(cpu) {
+ cpufreq_get(cpu);
+ }
+ cpufreq_delayed_issched = 0;
+}
+
+/* if we notice lost ticks, schedule a call to cpufreq_get() as it tries
+ * to verify the CPU frequency the timing core thinks the CPU is running
+ * at is still correct.
+ */
+static inline void cpufreq_delayed_get(void)
+{
+ if (cpufreq_init && !cpufreq_delayed_issched) {
+ cpufreq_delayed_issched = 1;
+ printk(KERN_DEBUG "Losing some ticks... checking if CPU
frequency changed.\n");
+ schedule_work(&cpufreq_delayed_get_work);
+ }
+}
+
+/* If the CPU frequency is scaled, TSC-based delays will need a different
+ * loops_per_jiffy value to function properly.
+ */
+
+static unsigned int ref_freq = 0;
+static unsigned long loops_per_jiffy_ref = 0;
+
+#ifndef CONFIG_SMP
+static unsigned long fast_gettimeoffset_ref = 0;
+static unsigned long cpu_khz_ref = 0;
+#endif
+
+static int
+time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
+ void *data)
+{
+ struct cpufreq_freqs *freq = data;
+
+ if (val != CPUFREQ_RESUMECHANGE)
+ write_seqlock_irq(&xtime_lock);
+ if (!ref_freq) {
+ ref_freq = freq->old;
+ loops_per_jiffy_ref = cpu_data[freq->cpu].loops_per_jiffy;
+#ifndef CONFIG_SMP
+ fast_gettimeoffset_ref = fast_gettimeoffset_quotient;
+ cpu_khz_ref = cpu_khz;
+#endif
+ }
+
+ if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) ||
+ (val == CPUFREQ_POSTCHANGE && freq->old > freq->new) ||
+ (val == CPUFREQ_RESUMECHANGE)) {
+ if (!(freq->flags & CPUFREQ_CONST_LOOPS))
+ cpu_data[freq->cpu].loops_per_jiffy =
cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);
+#ifndef CONFIG_SMP
+ if (cpu_khz)
+ cpu_khz = cpufreq_scale(cpu_khz_ref, ref_freq,
freq->new);
+ if (use_tsc) {
+ if (!(freq->flags & CPUFREQ_CONST_LOOPS)) {
+ fast_gettimeoffset_quotient =
cpufreq_scale(fast_gettimeoffset_ref, freq->new, ref_freq);
+ set_cyc2ns_scale(cpu_khz/1000);
+ }
+ }
+#endif
+ }
+
+ if (val != CPUFREQ_RESUMECHANGE)
+ write_sequnlock_irq(&xtime_lock);
+
+ return 0;
+}
+
+static struct notifier_block time_cpufreq_notifier_block = {
+ .notifier_call = time_cpufreq_notifier
+};
+
+
+static int __init cpufreq_tsc(void)
+{
+ int ret;
+ INIT_WORK(&cpufreq_delayed_get_work, handle_cpufreq_delayed_get, NULL);
+ ret = cpufreq_register_notifier(&time_cpufreq_notifier_block,
+ CPUFREQ_TRANSITION_NOTIFIER);
+ if (!ret)
+ cpufreq_init = 1;
+ return ret;
+}
+core_initcall(cpufreq_tsc);
+
+#else /* CONFIG_CPU_FREQ */
+static inline void cpufreq_delayed_get(void) { return; }
+#endif
+
+
+static int init_tsc(char* override)
+{
+ u64 __cpu_khz;
+
+ __cpu_khz = HYPERVISOR_shared_info->cpu_freq;
+ do_div(__cpu_khz, 1000);
+ cpu_khz = (u32)__cpu_khz;
+ printk(KERN_INFO "Xen reported: %lu.%03lu MHz processor.\n",
+ cpu_khz / 1000, cpu_khz % 1000);
+
+ /* (10^6 * 2^32) / cpu_hz = (10^3 * 2^32) / cpu_khz =
+ (2^32 * 1 / (clocks/us)) */
+ {
+ unsigned long eax=0, edx=1000;
+ __asm__("divl %2"
+ :"=a" (fast_gettimeoffset_quotient), "=d" (edx)
+ :"r" (cpu_khz),
+ "0" (eax), "1" (edx));
+ }
+
+ set_cyc2ns_scale(cpu_khz/1000);
+
+ use_tsc = 1;
+
+ return 0;
+}
+
+static int __init tsc_setup(char *str)
+{
+ printk(KERN_WARNING "notsc: cannot disable TSC in Xen/Linux.\n");
+ return 1;
+}
+__setup("notsc", tsc_setup);
+
+
+
+/************************************************************/
+
+/* tsc timer_opts struct */
+struct timer_opts timer_tsc = {
+ .name = "tsc",
+ .mark_offset = mark_offset_tsc,
+ .get_offset = get_offset_tsc,
+ .monotonic_clock = monotonic_clock_tsc,
+ .delay = delay_tsc,
+};
+
+struct init_timer_opts timer_tsc_init = {
+ .init = init_tsc,
+ .opts = &timer_tsc,
+};
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/kernel/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/kernel/Makefile Fri Jul 15 13:39:50 2005
@@ -0,0 +1,20 @@
+
+.S.o:
+ $(CC) $(AFLAGS) -traditional -c $< -o $*.o
+
+all: kernel.o head.o init_task.o
+
+O_TARGET := kernel.o
+
+export-objs := i386_ksyms.o gnttab.o skbuff.o ctrl_if.o
+
+obj-y := process.o semaphore.o signal.o entry.o traps.o irq.o \
+ ptrace.o ioport.o ldt.o setup.o time.o sys_i386.o \
+ i386_ksyms.o i387.o evtchn.o ctrl_if.o pci-dma.o \
+ reboot.o fixup.o gnttab.o skbuff.o
+
+ifdef CONFIG_PCI
+obj-y += pci-i386.o pci-pc.o
+endif
+
+include $(TOPDIR)/Rules.make
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/queues.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/queues.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,81 @@
+
+/*
+ * Oh dear. Task queues were removed from Linux 2.6 and replaced by work
+ * queues. Unfortunately the semantics is not the same. With task queues we
+ * can defer work until a particular event occurs -- this is not
+ * straightforwardly done with work queues (queued work is performed asap, or
+ * after some fixed timeout). Conversely, work queues are a (slightly) neater
+ * way of deferring work to a process context than using task queues in 2.4.
+ *
+ * This is a bit of a needless reimplementation -- should have just pulled
+ * the code from 2.4, but I tried leveraging work queues to simplify things.
+ * They didn't help. :-(
+ */
+
+#ifndef __QUEUES_H__
+#define __QUEUES_H__
+
+#include <linux/version.h>
+#include <linux/list.h>
+#include <linux/workqueue.h>
+
+struct tq_struct {
+ void (*fn)(void *);
+ void *arg;
+ struct list_head list;
+ unsigned long pending;
+};
+#define INIT_TQUEUE(_name, _fn, _arg) \
+ do { \
+ INIT_LIST_HEAD(&(_name)->list); \
+ (_name)->pending = 0; \
+ (_name)->fn = (_fn); (_name)->arg = (_arg); \
+ } while ( 0 )
+#define DECLARE_TQUEUE(_name, _fn, _arg) \
+ struct tq_struct _name = { (_fn), (_arg), LIST_HEAD_INIT((_name).list), 0 }
+
+typedef struct {
+ struct list_head list;
+ spinlock_t lock;
+} task_queue;
+#define DECLARE_TASK_QUEUE(_name) \
+ task_queue _name = { LIST_HEAD_INIT((_name).list), SPIN_LOCK_UNLOCKED }
+
+static inline int queue_task(struct tq_struct *tqe, task_queue *tql)
+{
+ unsigned long flags;
+ if ( test_and_set_bit(0, &tqe->pending) )
+ return 0;
+ spin_lock_irqsave(&tql->lock, flags);
+ list_add_tail(&tqe->list, &tql->list);
+ spin_unlock_irqrestore(&tql->lock, flags);
+ return 1;
+}
+
+static inline void run_task_queue(task_queue *tql)
+{
+ struct list_head head, *ent;
+ struct tq_struct *tqe;
+ unsigned long flags;
+ void (*fn)(void *);
+ void *arg;
+
+ spin_lock_irqsave(&tql->lock, flags);
+ list_add(&head, &tql->list);
+ list_del_init(&tql->list);
+ spin_unlock_irqrestore(&tql->lock, flags);
+
+ while ( !list_empty(&head) )
+ {
+ ent = head.next;
+ list_del_init(ent);
+ tqe = list_entry(ent, struct tq_struct, list);
+ fn = tqe->fn;
+ arg = tqe->arg;
+ wmb();
+ tqe->pending = 0;
+ fn(arg);
+ }
+}
+
+#endif /* __QUEUES_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/mm/highmem.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/mm/highmem.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,100 @@
+#include <linux/highmem.h>
+
+void *kmap(struct page *page)
+{
+ might_sleep();
+ if (!PageHighMem(page))
+ return page_address(page);
+ return kmap_high(page);
+}
+
+void kunmap(struct page *page)
+{
+ if (in_interrupt())
+ BUG();
+ if (!PageHighMem(page))
+ return;
+ kunmap_high(page);
+}
+
+/*
+ * kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because
+ * no global lock is needed and because the kmap code must perform a global TLB
+ * invalidation when the kmap pool wraps.
+ *
+ * However when holding an atomic kmap is is not legal to sleep, so atomic
+ * kmaps are appropriate for short, tight code paths only.
+ */
+static void *__kmap_atomic(struct page *page, enum km_type type, pgprot_t prot)
+{
+ enum fixed_addresses idx;
+ unsigned long vaddr;
+
+ /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+ inc_preempt_count();
+ if (!PageHighMem(page))
+ return page_address(page);
+
+ idx = type + KM_TYPE_NR*smp_processor_id();
+ vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+#ifdef CONFIG_DEBUG_HIGHMEM
+ if (!pte_none(*(kmap_pte-idx)))
+ BUG();
+#endif
+ set_pte(kmap_pte-idx, mk_pte(page, prot));
+ __flush_tlb_one(vaddr);
+
+ return (void*) vaddr;
+}
+
+void *kmap_atomic(struct page *page, enum km_type type)
+{
+ return __kmap_atomic(page, type, kmap_prot);
+}
+
+/* Same as kmap_atomic but with PAGE_KERNEL_RO page protection. */
+void *kmap_atomic_pte(struct page *page, enum km_type type)
+{
+ return __kmap_atomic(page, type, PAGE_KERNEL_RO);
+}
+
+void kunmap_atomic(void *kvaddr, enum km_type type)
+{
+#ifdef CONFIG_DEBUG_HIGHMEM
+ unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
+ enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
+
+ if (vaddr < FIXADDR_START) { // FIXME
+ dec_preempt_count();
+ preempt_check_resched();
+ return;
+ }
+
+ if (vaddr != __fix_to_virt(FIX_KMAP_BEGIN+idx))
+ BUG();
+
+ /*
+ * force other mappings to Oops if they'll try to access
+ * this pte without first remap it
+ */
+ pte_clear(kmap_pte-idx);
+ __flush_tlb_one(vaddr);
+#endif
+
+ dec_preempt_count();
+ preempt_check_resched();
+}
+
+struct page *kmap_atomic_to_page(void *ptr)
+{
+ unsigned long idx, vaddr = (unsigned long)ptr;
+ pte_t *pte;
+
+ if (vaddr < FIXADDR_START)
+ return virt_to_page(ptr);
+
+ idx = virt_to_fix(vaddr);
+ pte = kmap_pte - (idx - FIX_KMAP_BEGIN);
+ return pte_page(*pte);
+}
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/xenbus/xenbus_comms.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/xenbus/xenbus_comms.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,208 @@
+/******************************************************************************
+ * xenbus_comms.c
+ *
+ * Low level code to talks to Xen Store: ringbuffer and event channel.
+ *
+ * Copyright (C) 2005 Rusty Russell, IBM Corporation
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+//#define DEBUG
+
+#include <asm-xen/hypervisor.h>
+#include <asm-xen/evtchn.h>
+#include <linux/wait.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/err.h>
+#include "xenbus_comms.h"
+
+#define RINGBUF_DATASIZE ((PAGE_SIZE / 2) - sizeof(struct ringbuf_head))
+struct ringbuf_head
+{
+ u32 write; /* Next place to write to */
+ u32 read; /* Next place to read from */
+ u8 flags;
+ char buf[0];
+} __attribute__((packed));
+
+DECLARE_WAIT_QUEUE_HEAD(xb_waitq);
+
+static irqreturn_t wake_waiting(int irq, void *unused, struct pt_regs *regs)
+{
+ wake_up(&xb_waitq);
+ return IRQ_HANDLED;
+}
+
+static int check_buffer(const struct ringbuf_head *h)
+{
+ return (h->write < RINGBUF_DATASIZE && h->read < RINGBUF_DATASIZE);
+}
+
+/* We can't fill last byte: would look like empty buffer. */
+static void *get_output_chunk(const struct ringbuf_head *h,
+ void *buf, u32 *len)
+{
+ u32 read_mark;
+
+ if (h->read == 0)
+ read_mark = RINGBUF_DATASIZE - 1;
+ else
+ read_mark = h->read - 1;
+
+ /* Here to the end of buffer, unless they haven't read some out. */
+ *len = RINGBUF_DATASIZE - h->write;
+ if (read_mark >= h->write)
+ *len = read_mark - h->write;
+ return buf + h->write;
+}
+
+static const void *get_input_chunk(const struct ringbuf_head *h,
+ const void *buf, u32 *len)
+{
+ /* Here to the end of buffer, unless they haven't written some. */
+ *len = RINGBUF_DATASIZE - h->read;
+ if (h->write >= h->read)
+ *len = h->write - h->read;
+ return buf + h->read;
+}
+
+static void update_output_chunk(struct ringbuf_head *h, u32 len)
+{
+ h->write += len;
+ if (h->write == RINGBUF_DATASIZE)
+ h->write = 0;
+}
+
+static void update_input_chunk(struct ringbuf_head *h, u32 len)
+{
+ h->read += len;
+ if (h->read == RINGBUF_DATASIZE)
+ h->read = 0;
+}
+
+static int output_avail(struct ringbuf_head *out)
+{
+ unsigned int avail;
+
+ get_output_chunk(out, out->buf, &avail);
+ return avail != 0;
+}
+
+int xb_write(struct ringbuf_head *out, const void *data, unsigned len)
+{
+ struct ringbuf_head h;
+
+ do {
+ void *dst;
+ unsigned int avail;
+
+ wait_event(xb_waitq, output_avail(out));
+
+ /* Read, then check: not that we don't trust store.
+ * Hell, some of my best friends are daemons. But,
+ * in this post-911 world... */
+ h = *out;
+ mb();
+ if (!check_buffer(&h)) {
+ set_current_state(TASK_RUNNING);
+ return -EIO; /* ETERRORIST! */
+ }
+
+ dst = get_output_chunk(&h, out->buf, &avail);
+ if (avail > len)
+ avail = len;
+ memcpy(dst, data, avail);
+ data += avail;
+ len -= avail;
+ update_output_chunk(out, avail);
+ notify_via_evtchn(xen_start_info.store_evtchn);
+ } while (len != 0);
+
+ return 0;
+}
+
+int xs_input_avail(struct ringbuf_head *in)
+{
+ unsigned int avail;
+
+ get_input_chunk(in, in->buf, &avail);
+ return avail != 0;
+}
+
+int xb_read(struct ringbuf_head *in, void *data, unsigned len)
+{
+ struct ringbuf_head h;
+ int was_full;
+
+ while (len != 0) {
+ unsigned int avail;
+ const char *src;
+
+ wait_event(xb_waitq, xs_input_avail(in));
+ h = *in;
+ mb();
+ if (!check_buffer(&h)) {
+ set_current_state(TASK_RUNNING);
+ return -EIO;
+ }
+
+ src = get_input_chunk(&h, in->buf, &avail);
+ if (avail > len)
+ avail = len;
+ was_full = !output_avail(&h);
+
+ memcpy(data, src, avail);
+ data += avail;
+ len -= avail;
+ update_input_chunk(in, avail);
+ pr_debug("Finished read of %i bytes (%i to go)\n", avail, len);
+ /* If it was full, tell them we've taken some. */
+ if (was_full)
+ notify_via_evtchn(xen_start_info.store_evtchn);
+ }
+
+ /* If we left something, wake watch thread to deal with it. */
+ if (xs_input_avail(in))
+ wake_up(&xb_waitq);
+
+ return 0;
+}
+
+/* Set up interrpt handler off store event channel. */
+int xb_init_comms(void **in, void **out)
+{
+ int err, irq;
+
+ irq = bind_evtchn_to_irq(xen_start_info.store_evtchn);
+
+ err = request_irq(irq, wake_waiting, SA_SHIRQ, "xenbus", &xb_waitq);
+ if (err) {
+ printk(KERN_ERR "XENBUS request irq failed %i\n", err);
+ unbind_evtchn_from_irq(xen_start_info.store_evtchn);
+ return err;
+ }
+
+ *out = (void *)xen_start_info.store_page;
+ *in = (void *)xen_start_info.store_page + PAGE_SIZE/2;
+ return 0;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/xenbus/xenbus_comms.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/xenbus/xenbus_comms.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,14 @@
+/* Private include for xenbus communications. */
+#ifndef _XENBUS_COMMS_H
+#define _XENBUS_COMMS_H
+int xs_init(void);
+int xb_init_comms(void **in, void **out);
+
+/* Low level routines. */
+struct ringbuf_head;
+int xb_write(struct ringbuf_head *out, const void *data, unsigned len);
+int xb_read(struct ringbuf_head *in, void *data, unsigned len);
+int xs_input_avail(struct ringbuf_head *in);
+extern wait_queue_head_t xb_waitq;
+
+#endif /* _XENBUS_COMMS_H */
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/net/core/skbuff.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/net/core/skbuff.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,1309 @@
+/*
+ * Routines having to do with the 'struct sk_buff' memory handlers.
+ *
+ * Authors: Alan Cox <iiitac@xxxxxxxxxxxxxx>
+ * Florian La Roche <rzsfl@xxxxxxxxxxxx>
+ *
+ * Version: $Id: skbuff.c,v 1.90 2001/11/07 05:56:19 davem Exp $
+ *
+ * Fixes:
+ * Alan Cox : Fixed the worst of the load balancer
bugs.
+ * Dave Platt : Interrupt stacking fix.
+ * Richard Kooijman : Timestamp fixes.
+ * Alan Cox : Changed buffer format.
+ * Alan Cox : destructor hook for AF_UNIX etc.
+ * Linus Torvalds : Better skb_clone.
+ * Alan Cox : Added skb_copy.
+ * Alan Cox : Added all the changed routines Linus
+ * only put in the headers
+ * Ray VanTassle : Fixed --skb->lock in free
+ * Alan Cox : skb_copy copy arp field
+ * Andi Kleen : slabified it.
+ *
+ * NOTE:
+ * The __skb_ routines should be called with interrupts
+ * disabled, or you better be *real* sure that the operation is atomic
+ * with respect to whatever list is being frobbed (e.g. via lock_sock()
+ * or via disabling bottom half handlers, etc).
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+/*
+ * The functions in this file will not compile correctly with gcc 2.4.x
+ */
+
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/in.h>
+#include <linux/inet.h>
+#include <linux/slab.h>
+#include <linux/netdevice.h>
+#include <linux/string.h>
+#include <linux/skbuff.h>
+#include <linux/cache.h>
+#include <linux/rtnetlink.h>
+#include <linux/init.h>
+#include <linux/highmem.h>
+
+#include <net/protocol.h>
+#include <net/dst.h>
+#include <net/sock.h>
+#include <net/checksum.h>
+
+#include <asm/uaccess.h>
+#include <asm/system.h>
+
+int sysctl_hot_list_len = 128;
+
+static kmem_cache_t *skbuff_head_cache;
+
+static union {
+ struct sk_buff_head list;
+ char pad[SMP_CACHE_BYTES];
+} skb_head_pool[NR_CPUS];
+
+/*
+ * Keep out-of-line to prevent kernel bloat.
+ * __builtin_return_address is not used because it is not always
+ * reliable.
+ */
+
+/**
+ * skb_over_panic - private function
+ * @skb: buffer
+ * @sz: size
+ * @here: address
+ *
+ * Out of line support code for skb_put(). Not user callable.
+ */
+
+void skb_over_panic(struct sk_buff *skb, int sz, void *here)
+{
+ printk("skput:over: %p:%d put:%d dev:%s",
+ here, skb->len, sz, skb->dev ? skb->dev->name : "<NULL>");
+ BUG();
+}
+
+/**
+ * skb_under_panic - private function
+ * @skb: buffer
+ * @sz: size
+ * @here: address
+ *
+ * Out of line support code for skb_push(). Not user callable.
+ */
+
+
+void skb_under_panic(struct sk_buff *skb, int sz, void *here)
+{
+ printk("skput:under: %p:%d put:%d dev:%s",
+ here, skb->len, sz, skb->dev ? skb->dev->name : "<NULL>");
+ BUG();
+}
+
+static __inline__ struct sk_buff *skb_head_from_pool(void)
+{
+ struct sk_buff_head *list = &skb_head_pool[smp_processor_id()].list;
+
+ if (skb_queue_len(list)) {
+ struct sk_buff *skb;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ skb = __skb_dequeue(list);
+ local_irq_restore(flags);
+ return skb;
+ }
+ return NULL;
+}
+
+static __inline__ void skb_head_to_pool(struct sk_buff *skb)
+{
+ struct sk_buff_head *list = &skb_head_pool[smp_processor_id()].list;
+
+ if (skb_queue_len(list) < sysctl_hot_list_len) {
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __skb_queue_head(list, skb);
+ local_irq_restore(flags);
+
+ return;
+ }
+ kmem_cache_free(skbuff_head_cache, skb);
+}
+
+
+/* Allocate a new skbuff. We do this ourselves so we can fill in a few
+ * 'private' fields and also do memory statistics to find all the
+ * [BEEP] leaks.
+ *
+ */
+
+/**
+ * alloc_skb - allocate a network buffer
+ * @size: size to allocate
+ * @gfp_mask: allocation mask
+ *
+ * Allocate a new &sk_buff. The returned buffer has no headroom and a
+ * tail room of size bytes. The object has a reference count of one.
+ * The return is the buffer. On a failure the return is %NULL.
+ *
+ * Buffers may only be allocated from interrupts using a @gfp_mask of
+ * %GFP_ATOMIC.
+ */
+
+struct sk_buff *alloc_skb(unsigned int size,int gfp_mask)
+{
+ struct sk_buff *skb;
+ u8 *data;
+
+ if (in_interrupt() && (gfp_mask & __GFP_WAIT)) {
+ static int count = 0;
+ if (++count < 5) {
+ printk(KERN_ERR "alloc_skb called nonatomically "
+ "from interrupt %p\n", NET_CALLER(size));
+ BUG();
+ }
+ gfp_mask &= ~__GFP_WAIT;
+ }
+
+ /* Get the HEAD */
+ skb = skb_head_from_pool();
+ if (skb == NULL) {
+ skb = kmem_cache_alloc(skbuff_head_cache, gfp_mask &
~__GFP_DMA);
+ if (skb == NULL)
+ goto nohead;
+ }
+
+ /* Get the DATA. Size must match skb_add_mtu(). */
+ size = SKB_DATA_ALIGN(size);
+ data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
+ if (data == NULL)
+ goto nodata;
+
+ /* XXX: does not include slab overhead */
+ skb->truesize = size + sizeof(struct sk_buff);
+
+ /* Load the data pointers. */
+ skb->head = data;
+ skb->data = data;
+ skb->tail = data;
+ skb->end = data + size;
+
+ /* Set up other state */
+ skb->len = 0;
+ skb->cloned = 0;
+ skb->data_len = 0;
+
+ atomic_set(&skb->users, 1);
+ atomic_set(&(skb_shinfo(skb)->dataref), 1);
+ skb_shinfo(skb)->nr_frags = 0;
+ skb_shinfo(skb)->frag_list = NULL;
+ return skb;
+
+nodata:
+ skb_head_to_pool(skb);
+nohead:
+ return NULL;
+}
+
+/**
+ * alloc_skb_from_cache - allocate a network buffer
+ * @cp: kmem_cache from which to allocate the data area
+ * (object size must be big enough for @size bytes + skb overheads)
+ * @size: size to allocate
+ * @gfp_mask: allocation mask
+ *
+ * Allocate a new &sk_buff. The returned buffer has no headroom and a
+ * tail room of size bytes. The object has a reference count of one.
+ * The return is the buffer. On a failure the return is %NULL.
+ *
+ * Buffers may only be allocated from interrupts using a @gfp_mask of
+ * %GFP_ATOMIC.
+ */
+
+struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp,
+ unsigned int size, int gfp_mask)
+{
+ struct sk_buff *skb;
+ u8 *data;
+
+ if (in_interrupt() && (gfp_mask & __GFP_WAIT)) {
+ static int count = 0;
+ if (++count < 5) {
+ printk(KERN_ERR "alloc_skb called nonatomically "
+ "from interrupt %p\n", NET_CALLER(size));
+ BUG();
+ }
+ gfp_mask &= ~__GFP_WAIT;
+ }
+
+ /* Get the HEAD */
+ skb = skb_head_from_pool();
+ if (skb == NULL) {
+ skb = kmem_cache_alloc(skbuff_head_cache, gfp_mask &
~__GFP_DMA);
+ if (skb == NULL)
+ goto nohead;
+ }
+
+ /* Get the DATA. */
+ size = SKB_DATA_ALIGN(size);
+ data = kmem_cache_alloc(cp, gfp_mask);
+ if (data == NULL)
+ goto nodata;
+
+ /* XXX: does not include slab overhead */
+ skb->truesize = size + sizeof(struct sk_buff);
+
+ /* Load the data pointers. */
+ skb->head = data;
+ skb->data = data;
+ skb->tail = data;
+ skb->end = data + size;
+
+ /* Set up other state */
+ skb->len = 0;
+ skb->cloned = 0;
+ skb->data_len = 0;
+
+ atomic_set(&skb->users, 1);
+ atomic_set(&(skb_shinfo(skb)->dataref), 1);
+ skb_shinfo(skb)->nr_frags = 0;
+ skb_shinfo(skb)->frag_list = NULL;
+ return skb;
+
+nodata:
+ skb_head_to_pool(skb);
+nohead:
+ return NULL;
+}
+
+
+/*
+ * Slab constructor for a skb head.
+ */
+static inline void skb_headerinit(void *p, kmem_cache_t *cache,
+ unsigned long flags)
+{
+ struct sk_buff *skb = p;
+
+ skb->next = NULL;
+ skb->prev = NULL;
+ skb->list = NULL;
+ skb->sk = NULL;
+ skb->stamp.tv_sec=0; /* No idea about time */
+ skb->dev = NULL;
+ skb->real_dev = NULL;
+ skb->dst = NULL;
+ memset(skb->cb, 0, sizeof(skb->cb));
+ skb->pkt_type = PACKET_HOST; /* Default type */
+ skb->ip_summed = 0;
+ skb->priority = 0;
+ skb->security = 0; /* By default packets are insecure */
+ skb->destructor = NULL;
+
+#ifdef CONFIG_NETFILTER
+ skb->nfmark = skb->nfcache = 0;
+ skb->nfct = NULL;
+#ifdef CONFIG_NETFILTER_DEBUG
+ skb->nf_debug = 0;
+#endif
+#endif
+#ifdef CONFIG_NET_SCHED
+ skb->tc_index = 0;
+#endif
+}
+
+static void skb_drop_fraglist(struct sk_buff *skb)
+{
+ struct sk_buff *list = skb_shinfo(skb)->frag_list;
+
+ skb_shinfo(skb)->frag_list = NULL;
+
+ do {
+ struct sk_buff *this = list;
+ list = list->next;
+ kfree_skb(this);
+ } while (list);
+}
+
+static void skb_clone_fraglist(struct sk_buff *skb)
+{
+ struct sk_buff *list;
+
+ for (list = skb_shinfo(skb)->frag_list; list; list=list->next)
+ skb_get(list);
+}
+
+static void skb_release_data(struct sk_buff *skb)
+{
+ if (!skb->cloned ||
+ atomic_dec_and_test(&(skb_shinfo(skb)->dataref))) {
+ if (skb_shinfo(skb)->nr_frags) {
+ int i;
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
+ put_page(skb_shinfo(skb)->frags[i].page);
+ }
+
+ if (skb_shinfo(skb)->frag_list)
+ skb_drop_fraglist(skb);
+
+ kfree(skb->head);
+ }
+}
+
+/*
+ * Free an skbuff by memory without cleaning the state.
+ */
+void kfree_skbmem(struct sk_buff *skb)
+{
+ skb_release_data(skb);
+ skb_head_to_pool(skb);
+}
+
+/**
+ * __kfree_skb - private function
+ * @skb: buffer
+ *
+ * Free an sk_buff. Release anything attached to the buffer.
+ * Clean the state. This is an internal helper function. Users should
+ * always call kfree_skb
+ */
+
+void __kfree_skb(struct sk_buff *skb)
+{
+ if (skb->list) {
+ printk(KERN_WARNING "Warning: kfree_skb passed an skb still "
+ "on a list (from %p).\n", NET_CALLER(skb));
+ BUG();
+ }
+
+ dst_release(skb->dst);
+ if(skb->destructor) {
+ if (in_irq()) {
+ printk(KERN_WARNING "Warning: kfree_skb on hard IRQ
%p\n",
+ NET_CALLER(skb));
+ }
+ skb->destructor(skb);
+ }
+#ifdef CONFIG_NETFILTER
+ nf_conntrack_put(skb->nfct);
+#endif
+ skb_headerinit(skb, NULL, 0); /* clean state */
+ kfree_skbmem(skb);
+}
+
+/**
+ * skb_clone - duplicate an sk_buff
+ * @skb: buffer to clone
+ * @gfp_mask: allocation priority
+ *
+ * Duplicate an &sk_buff. The new one is not owned by a socket. Both
+ * copies share the same packet data but not structure. The new
+ * buffer has a reference count of 1. If the allocation fails the
+ * function returns %NULL otherwise the new buffer is returned.
+ *
+ * If this function is called from an interrupt gfp_mask() must be
+ * %GFP_ATOMIC.
+ */
+
+struct sk_buff *skb_clone(struct sk_buff *skb, int gfp_mask)
+{
+ struct sk_buff *n;
+
+ n = skb_head_from_pool();
+ if (!n) {
+ n = kmem_cache_alloc(skbuff_head_cache, gfp_mask);
+ if (!n)
+ return NULL;
+ }
+
+#define C(x) n->x = skb->x
+
+ n->next = n->prev = NULL;
+ n->list = NULL;
+ n->sk = NULL;
+ C(stamp);
+ C(dev);
+ C(real_dev);
+ C(h);
+ C(nh);
+ C(mac);
+ C(dst);
+ dst_clone(n->dst);
+ memcpy(n->cb, skb->cb, sizeof(skb->cb));
+ C(len);
+ C(data_len);
+ C(csum);
+ n->cloned = 1;
+ C(pkt_type);
+ C(ip_summed);
+ C(priority);
+ atomic_set(&n->users, 1);
+ C(protocol);
+ C(security);
+ C(truesize);
+ C(head);
+ C(data);
+ C(tail);
+ C(end);
+ n->destructor = NULL;
+#ifdef CONFIG_NETFILTER
+ C(nfmark);
+ C(nfcache);
+ C(nfct);
+#ifdef CONFIG_NETFILTER_DEBUG
+ C(nf_debug);
+#endif
+#endif /*CONFIG_NETFILTER*/
+#if defined(CONFIG_HIPPI)
+ C(private);
+#endif
+#ifdef CONFIG_NET_SCHED
+ C(tc_index);
+#endif
+
+ atomic_inc(&(skb_shinfo(skb)->dataref));
+ skb->cloned = 1;
+#ifdef CONFIG_NETFILTER
+ nf_conntrack_get(skb->nfct);
+#endif
+ return n;
+}
+
+static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
+{
+ /*
+ * Shift between the two data areas in bytes
+ */
+ unsigned long offset = new->data - old->data;
+
+ new->list=NULL;
+ new->sk=NULL;
+ new->dev=old->dev;
+ new->real_dev=old->real_dev;
+ new->priority=old->priority;
+ new->protocol=old->protocol;
+ new->dst=dst_clone(old->dst);
+ new->h.raw=old->h.raw+offset;
+ new->nh.raw=old->nh.raw+offset;
+ new->mac.raw=old->mac.raw+offset;
+ memcpy(new->cb, old->cb, sizeof(old->cb));
+ atomic_set(&new->users, 1);
+ new->pkt_type=old->pkt_type;
+ new->stamp=old->stamp;
+ new->destructor = NULL;
+ new->security=old->security;
+#ifdef CONFIG_NETFILTER
+ new->nfmark=old->nfmark;
+ new->nfcache=old->nfcache;
+ new->nfct=old->nfct;
+ nf_conntrack_get(new->nfct);
+#ifdef CONFIG_NETFILTER_DEBUG
+ new->nf_debug=old->nf_debug;
+#endif
+#endif
+#ifdef CONFIG_NET_SCHED
+ new->tc_index = old->tc_index;
+#endif
+}
+
+/**
+ * skb_copy - create private copy of an sk_buff
+ * @skb: buffer to copy
+ * @gfp_mask: allocation priority
+ *
+ * Make a copy of both an &sk_buff and its data. This is used when the
+ * caller wishes to modify the data and needs a private copy of the
+ * data to alter. Returns %NULL on failure or the pointer to the buffer
+ * on success. The returned buffer has a reference count of 1.
+ *
+ * As by-product this function converts non-linear &sk_buff to linear
+ * one, so that &sk_buff becomes completely private and caller is allowed
+ * to modify all the data of returned buffer. This means that this
+ * function is not recommended for use in circumstances when only
+ * header is going to be modified. Use pskb_copy() instead.
+ */
+
+struct sk_buff *skb_copy(const struct sk_buff *skb, int gfp_mask)
+{
+ struct sk_buff *n;
+ int headerlen = skb->data-skb->head;
+
+ /*
+ * Allocate the copy buffer
+ */
+ n=alloc_skb(skb->end - skb->head + skb->data_len, gfp_mask);
+ if(n==NULL)
+ return NULL;
+
+ /* Set the data pointer */
+ skb_reserve(n,headerlen);
+ /* Set the tail pointer and length */
+ skb_put(n,skb->len);
+ n->csum = skb->csum;
+ n->ip_summed = skb->ip_summed;
+
+ if (skb_copy_bits(skb, -headerlen, n->head, headerlen+skb->len))
+ BUG();
+
+ copy_skb_header(n, skb);
+
+ return n;
+}
+
+/* Keep head the same: replace data */
+int skb_linearize(struct sk_buff *skb, int gfp_mask)
+{
+ unsigned int size;
+ u8 *data;
+ long offset;
+ int headerlen = skb->data - skb->head;
+ int expand = (skb->tail+skb->data_len) - skb->end;
+
+ if (skb_shared(skb))
+ BUG();
+
+ if (expand <= 0)
+ expand = 0;
+
+ size = (skb->end - skb->head + expand);
+ size = SKB_DATA_ALIGN(size);
+ data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
+ if (data == NULL)
+ return -ENOMEM;
+
+ /* Copy entire thing */
+ if (skb_copy_bits(skb, -headerlen, data, headerlen+skb->len))
+ BUG();
+
+ /* Offset between the two in bytes */
+ offset = data - skb->head;
+
+ /* Free old data. */
+ skb_release_data(skb);
+
+ skb->head = data;
+ skb->end = data + size;
+
+ /* Set up new pointers */
+ skb->h.raw += offset;
+ skb->nh.raw += offset;
+ skb->mac.raw += offset;
+ skb->tail += offset;
+ skb->data += offset;
+
+ /* Set up shinfo */
+ atomic_set(&(skb_shinfo(skb)->dataref), 1);
+ skb_shinfo(skb)->nr_frags = 0;
+ skb_shinfo(skb)->frag_list = NULL;
+
+ /* We are no longer a clone, even if we were. */
+ skb->cloned = 0;
+
+ skb->tail += skb->data_len;
+ skb->data_len = 0;
+ return 0;
+}
+
+
+/**
+ * pskb_copy - create copy of an sk_buff with private head.
+ * @skb: buffer to copy
+ * @gfp_mask: allocation priority
+ *
+ * Make a copy of both an &sk_buff and part of its data, located
+ * in header. Fragmented data remain shared. This is used when
+ * the caller wishes to modify only header of &sk_buff and needs
+ * private copy of the header to alter. Returns %NULL on failure
+ * or the pointer to the buffer on success.
+ * The returned buffer has a reference count of 1.
+ */
+
+struct sk_buff *pskb_copy(struct sk_buff *skb, int gfp_mask)
+{
+ struct sk_buff *n;
+
+ /*
+ * Allocate the copy buffer
+ */
+ n=alloc_skb(skb->end - skb->head, gfp_mask);
+ if(n==NULL)
+ return NULL;
+
+ /* Set the data pointer */
+ skb_reserve(n,skb->data-skb->head);
+ /* Set the tail pointer and length */
+ skb_put(n,skb_headlen(skb));
+ /* Copy the bytes */
+ memcpy(n->data, skb->data, n->len);
+ n->csum = skb->csum;
+ n->ip_summed = skb->ip_summed;
+
+ n->data_len = skb->data_len;
+ n->len = skb->len;
+
+ if (skb_shinfo(skb)->nr_frags) {
+ int i;
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i];
+ get_page(skb_shinfo(n)->frags[i].page);
+ }
+ skb_shinfo(n)->nr_frags = i;
+ }
+
+ if (skb_shinfo(skb)->frag_list) {
+ skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list;
+ skb_clone_fraglist(n);
+ }
+
+ copy_skb_header(n, skb);
+
+ return n;
+}
+
+/**
+ * pskb_expand_head - reallocate header of &sk_buff
+ * @skb: buffer to reallocate
+ * @nhead: room to add at head
+ * @ntail: room to add at tail
+ * @gfp_mask: allocation priority
+ *
+ * Expands (or creates identical copy, if &nhead and &ntail are zero)
+ * header of skb. &sk_buff itself is not changed. &sk_buff MUST have
+ * reference count of 1. Returns zero in the case of success or error,
+ * if expansion failed. In the last case, &sk_buff is not changed.
+ *
+ * All the pointers pointing into skb header may change and must be
+ * reloaded after call to this function.
+ */
+
+int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, int gfp_mask)
+{
+ int i;
+ u8 *data;
+ int size = nhead + (skb->end - skb->head) + ntail;
+ long off;
+
+ if (skb_shared(skb))
+ BUG();
+
+ size = SKB_DATA_ALIGN(size);
+
+ data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
+ if (data == NULL)
+ goto nodata;
+
+ /* Copy only real data... and, alas, header. This should be
+ * optimized for the cases when header is void. */
+ memcpy(data+nhead, skb->head, skb->tail-skb->head);
+ memcpy(data+size, skb->end, sizeof(struct skb_shared_info));
+
+ for (i=0; i<skb_shinfo(skb)->nr_frags; i++)
+ get_page(skb_shinfo(skb)->frags[i].page);
+
+ if (skb_shinfo(skb)->frag_list)
+ skb_clone_fraglist(skb);
+
+ skb_release_data(skb);
+
+ off = (data+nhead) - skb->head;
+
+ skb->head = data;
+ skb->end = data+size;
+
+ skb->data += off;
+ skb->tail += off;
+ skb->mac.raw += off;
+ skb->h.raw += off;
+ skb->nh.raw += off;
+ skb->cloned = 0;
+ atomic_set(&skb_shinfo(skb)->dataref, 1);
+ return 0;
+
+nodata:
+ return -ENOMEM;
+}
+
+/* Make private copy of skb with writable head and some headroom */
+
+struct sk_buff *
+skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom)
+{
+ struct sk_buff *skb2;
+ int delta = headroom - skb_headroom(skb);
+
+ if (delta <= 0)
+ return pskb_copy(skb, GFP_ATOMIC);
+
+ skb2 = skb_clone(skb, GFP_ATOMIC);
+ if (skb2 == NULL ||
+ !pskb_expand_head(skb2, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC))
+ return skb2;
+
+ kfree_skb(skb2);
+ return NULL;
+}
+
+
+/**
+ * skb_copy_expand - copy and expand sk_buff
+ * @skb: buffer to copy
+ * @newheadroom: new free bytes at head
+ * @newtailroom: new free bytes at tail
+ * @gfp_mask: allocation priority
+ *
+ * Make a copy of both an &sk_buff and its data and while doing so
+ * allocate additional space.
+ *
+ * This is used when the caller wishes to modify the data and needs a
+ * private copy of the data to alter as well as more space for new fields.
+ * Returns %NULL on failure or the pointer to the buffer
+ * on success. The returned buffer has a reference count of 1.
+ *
+ * You must pass %GFP_ATOMIC as the allocation priority if this function
+ * is called from an interrupt.
+ */
+
+
+struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
+ int newheadroom,
+ int newtailroom,
+ int gfp_mask)
+{
+ struct sk_buff *n;
+
+ /*
+ * Allocate the copy buffer
+ */
+
+ n=alloc_skb(newheadroom + skb->len + newtailroom,
+ gfp_mask);
+ if(n==NULL)
+ return NULL;
+
+ skb_reserve(n,newheadroom);
+
+ /* Set the tail pointer and length */
+ skb_put(n,skb->len);
+
+ /* Copy the data only. */
+ if (skb_copy_bits(skb, 0, n->data, skb->len))
+ BUG();
+
+ copy_skb_header(n, skb);
+ return n;
+}
+
+/**
+ * skb_pad - zero pad the tail of an skb
+ * @skb: buffer to pad
+ * @pad: space to pad
+ *
+ * Ensure that a buffer is followed by a padding area that is zero
+ * filled. Used by network drivers which may DMA or transfer data
+ * beyond the buffer end onto the wire.
+ *
+ * May return NULL in out of memory cases.
+ */
+
+struct sk_buff *skb_pad(struct sk_buff *skb, int pad)
+{
+ struct sk_buff *nskb;
+
+ /* If the skbuff is non linear tailroom is always zero.. */
+ if(skb_tailroom(skb) >= pad)
+ {
+ memset(skb->data+skb->len, 0, pad);
+ return skb;
+ }
+
+ nskb = skb_copy_expand(skb, skb_headroom(skb), skb_tailroom(skb) + pad,
GFP_ATOMIC);
+ kfree_skb(skb);
+ if(nskb)
+ memset(nskb->data+nskb->len, 0, pad);
+ return nskb;
+}
+
+/* Trims skb to length len. It can change skb pointers, if "realloc" is 1.
+ * If realloc==0 and trimming is impossible without change of data,
+ * it is BUG().
+ */
+
+int ___pskb_trim(struct sk_buff *skb, unsigned int len, int realloc)
+{
+ int offset = skb_headlen(skb);
+ int nfrags = skb_shinfo(skb)->nr_frags;
+ int i;
+
+ for (i=0; i<nfrags; i++) {
+ int end = offset + skb_shinfo(skb)->frags[i].size;
+ if (end > len) {
+ if (skb_cloned(skb)) {
+ if (!realloc)
+ BUG();
+ if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ return -ENOMEM;
+ }
+ if (len <= offset) {
+ put_page(skb_shinfo(skb)->frags[i].page);
+ skb_shinfo(skb)->nr_frags--;
+ } else {
+ skb_shinfo(skb)->frags[i].size = len-offset;
+ }
+ }
+ offset = end;
+ }
+
+ if (offset < len) {
+ skb->data_len -= skb->len - len;
+ skb->len = len;
+ } else {
+ if (len <= skb_headlen(skb)) {
+ skb->len = len;
+ skb->data_len = 0;
+ skb->tail = skb->data + len;
+ if (skb_shinfo(skb)->frag_list && !skb_cloned(skb))
+ skb_drop_fraglist(skb);
+ } else {
+ skb->data_len -= skb->len - len;
+ skb->len = len;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * __pskb_pull_tail - advance tail of skb header
+ * @skb: buffer to reallocate
+ * @delta: number of bytes to advance tail
+ *
+ * The function makes a sense only on a fragmented &sk_buff,
+ * it expands header moving its tail forward and copying necessary
+ * data from fragmented part.
+ *
+ * &sk_buff MUST have reference count of 1.
+ *
+ * Returns %NULL (and &sk_buff does not change) if pull failed
+ * or value of new tail of skb in the case of success.
+ *
+ * All the pointers pointing into skb header may change and must be
+ * reloaded after call to this function.
+ */
+
+/* Moves tail of skb head forward, copying data from fragmented part,
+ * when it is necessary.
+ * 1. It may fail due to malloc failure.
+ * 2. It may change skb pointers.
+ *
+ * It is pretty complicated. Luckily, it is called only in exceptional cases.
+ */
+unsigned char * __pskb_pull_tail(struct sk_buff *skb, int delta)
+{
+ int i, k, eat;
+
+ /* If skb has not enough free space at tail, get new one
+ * plus 128 bytes for future expansions. If we have enough
+ * room at tail, reallocate without expansion only if skb is cloned.
+ */
+ eat = (skb->tail+delta) - skb->end;
+
+ if (eat > 0 || skb_cloned(skb)) {
+ if (pskb_expand_head(skb, 0, eat>0 ? eat+128 : 0, GFP_ATOMIC))
+ return NULL;
+ }
+
+ if (skb_copy_bits(skb, skb_headlen(skb), skb->tail, delta))
+ BUG();
+
+ /* Optimization: no fragments, no reasons to preestimate
+ * size of pulled pages. Superb.
+ */
+ if (skb_shinfo(skb)->frag_list == NULL)
+ goto pull_pages;
+
+ /* Estimate size of pulled pages. */
+ eat = delta;
+ for (i=0; i<skb_shinfo(skb)->nr_frags; i++) {
+ if (skb_shinfo(skb)->frags[i].size >= eat)
+ goto pull_pages;
+ eat -= skb_shinfo(skb)->frags[i].size;
+ }
+
+ /* If we need update frag list, we are in troubles.
+ * Certainly, it possible to add an offset to skb data,
+ * but taking into account that pulling is expected to
+ * be very rare operation, it is worth to fight against
+ * further bloating skb head and crucify ourselves here instead.
+ * Pure masohism, indeed. 8)8)
+ */
+ if (eat) {
+ struct sk_buff *list = skb_shinfo(skb)->frag_list;
+ struct sk_buff *clone = NULL;
+ struct sk_buff *insp = NULL;
+
+ do {
+ if (list == NULL)
+ BUG();
+
+ if (list->len <= eat) {
+ /* Eaten as whole. */
+ eat -= list->len;
+ list = list->next;
+ insp = list;
+ } else {
+ /* Eaten partially. */
+
+ if (skb_shared(list)) {
+ /* Sucks! We need to fork list. :-( */
+ clone = skb_clone(list, GFP_ATOMIC);
+ if (clone == NULL)
+ return NULL;
+ insp = list->next;
+ list = clone;
+ } else {
+ /* This may be pulled without
+ * problems. */
+ insp = list;
+ }
+ if (pskb_pull(list, eat) == NULL) {
+ if (clone)
+ kfree_skb(clone);
+ return NULL;
+ }
+ break;
+ }
+ } while (eat);
+
+ /* Free pulled out fragments. */
+ while ((list = skb_shinfo(skb)->frag_list) != insp) {
+ skb_shinfo(skb)->frag_list = list->next;
+ kfree_skb(list);
+ }
+ /* And insert new clone at head. */
+ if (clone) {
+ clone->next = list;
+ skb_shinfo(skb)->frag_list = clone;
+ }
+ }
+ /* Success! Now we may commit changes to skb data. */
+
+pull_pages:
+ eat = delta;
+ k = 0;
+ for (i=0; i<skb_shinfo(skb)->nr_frags; i++) {
+ if (skb_shinfo(skb)->frags[i].size <= eat) {
+ put_page(skb_shinfo(skb)->frags[i].page);
+ eat -= skb_shinfo(skb)->frags[i].size;
+ } else {
+ skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i];
+ if (eat) {
+ skb_shinfo(skb)->frags[k].page_offset += eat;
+ skb_shinfo(skb)->frags[k].size -= eat;
+ eat = 0;
+ }
+ k++;
+ }
+ }
+ skb_shinfo(skb)->nr_frags = k;
+
+ skb->tail += delta;
+ skb->data_len -= delta;
+
+ return skb->tail;
+}
+
+/* Copy some data bits from skb to kernel buffer. */
+
+int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len)
+{
+ int i, copy;
+ int start = skb->len - skb->data_len;
+
+ if (offset > (int)skb->len-len)
+ goto fault;
+
+ /* Copy header. */
+ if ((copy = start-offset) > 0) {
+ if (copy > len)
+ copy = len;
+ memcpy(to, skb->data + offset, copy);
+ if ((len -= copy) == 0)
+ return 0;
+ offset += copy;
+ to += copy;
+ }
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ int end;
+
+ BUG_TRAP(start <= offset+len);
+
+ end = start + skb_shinfo(skb)->frags[i].size;
+ if ((copy = end-offset) > 0) {
+ u8 *vaddr;
+
+ if (copy > len)
+ copy = len;
+
+ vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]);
+ memcpy(to, vaddr+skb_shinfo(skb)->frags[i].page_offset+
+ offset-start, copy);
+ kunmap_skb_frag(vaddr);
+
+ if ((len -= copy) == 0)
+ return 0;
+ offset += copy;
+ to += copy;
+ }
+ start = end;
+ }
+
+ if (skb_shinfo(skb)->frag_list) {
+ struct sk_buff *list;
+
+ for (list = skb_shinfo(skb)->frag_list; list; list=list->next) {
+ int end;
+
+ BUG_TRAP(start <= offset+len);
+
+ end = start + list->len;
+ if ((copy = end-offset) > 0) {
+ if (copy > len)
+ copy = len;
+ if (skb_copy_bits(list, offset-start, to, copy))
+ goto fault;
+ if ((len -= copy) == 0)
+ return 0;
+ offset += copy;
+ to += copy;
+ }
+ start = end;
+ }
+ }
+ if (len == 0)
+ return 0;
+
+fault:
+ return -EFAULT;
+}
+
+/* Checksum skb data. */
+
+unsigned int skb_checksum(const struct sk_buff *skb, int offset, int len,
unsigned int csum)
+{
+ int i, copy;
+ int start = skb->len - skb->data_len;
+ int pos = 0;
+
+ /* Checksum header. */
+ if ((copy = start-offset) > 0) {
+ if (copy > len)
+ copy = len;
+ csum = csum_partial(skb->data+offset, copy, csum);
+ if ((len -= copy) == 0)
+ return csum;
+ offset += copy;
+ pos = copy;
+ }
+
+ for (i=0; i<skb_shinfo(skb)->nr_frags; i++) {
+ int end;
+
+ BUG_TRAP(start <= offset+len);
+
+ end = start + skb_shinfo(skb)->frags[i].size;
+ if ((copy = end-offset) > 0) {
+ unsigned int csum2;
+ u8 *vaddr;
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+ if (copy > len)
+ copy = len;
+ vaddr = kmap_skb_frag(frag);
+ csum2 = csum_partial(vaddr + frag->page_offset +
+ offset-start, copy, 0);
+ kunmap_skb_frag(vaddr);
+ csum = csum_block_add(csum, csum2, pos);
+ if (!(len -= copy))
+ return csum;
+ offset += copy;
+ pos += copy;
+ }
+ start = end;
+ }
+
+ if (skb_shinfo(skb)->frag_list) {
+ struct sk_buff *list;
+
+ for (list = skb_shinfo(skb)->frag_list; list; list=list->next) {
+ int end;
+
+ BUG_TRAP(start <= offset+len);
+
+ end = start + list->len;
+ if ((copy = end-offset) > 0) {
+ unsigned int csum2;
+ if (copy > len)
+ copy = len;
+ csum2 = skb_checksum(list, offset-start, copy,
0);
+ csum = csum_block_add(csum, csum2, pos);
+ if ((len -= copy) == 0)
+ return csum;
+ offset += copy;
+ pos += copy;
+ }
+ start = end;
+ }
+ }
+ if (len == 0)
+ return csum;
+
+ BUG();
+ return csum;
+}
+
+/* Both of above in one bottle. */
+
+unsigned int skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8
*to, int len, unsigned int csum)
+{
+ int i, copy;
+ int start = skb->len - skb->data_len;
+ int pos = 0;
+
+ /* Copy header. */
+ if ((copy = start-offset) > 0) {
+ if (copy > len)
+ copy = len;
+ csum = csum_partial_copy_nocheck(skb->data+offset, to, copy,
csum);
+ if ((len -= copy) == 0)
+ return csum;
+ offset += copy;
+ to += copy;
+ pos = copy;
+ }
+
+ for (i=0; i<skb_shinfo(skb)->nr_frags; i++) {
+ int end;
+
+ BUG_TRAP(start <= offset+len);
+
+ end = start + skb_shinfo(skb)->frags[i].size;
+ if ((copy = end-offset) > 0) {
+ unsigned int csum2;
+ u8 *vaddr;
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+ if (copy > len)
+ copy = len;
+ vaddr = kmap_skb_frag(frag);
+ csum2 = csum_partial_copy_nocheck(vaddr +
frag->page_offset +
+ offset-start, to, copy,
0);
+ kunmap_skb_frag(vaddr);
+ csum = csum_block_add(csum, csum2, pos);
+ if (!(len -= copy))
+ return csum;
+ offset += copy;
+ to += copy;
+ pos += copy;
+ }
+ start = end;
+ }
+
+ if (skb_shinfo(skb)->frag_list) {
+ struct sk_buff *list;
+
+ for (list = skb_shinfo(skb)->frag_list; list; list=list->next) {
+ unsigned int csum2;
+ int end;
+
+ BUG_TRAP(start <= offset+len);
+
+ end = start + list->len;
+ if ((copy = end-offset) > 0) {
+ if (copy > len)
+ copy = len;
+ csum2 = skb_copy_and_csum_bits(list,
offset-start, to, copy, 0);
+ csum = csum_block_add(csum, csum2, pos);
+ if ((len -= copy) == 0)
+ return csum;
+ offset += copy;
+ to += copy;
+ pos += copy;
+ }
+ start = end;
+ }
+ }
+ if (len == 0)
+ return csum;
+
+ BUG();
+ return csum;
+}
+
+void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to)
+{
+ unsigned int csum;
+ long csstart;
+
+ if (skb->ip_summed == CHECKSUM_HW)
+ csstart = skb->h.raw - skb->data;
+ else
+ csstart = skb->len - skb->data_len;
+
+ if (csstart > skb->len - skb->data_len)
+ BUG();
+
+ memcpy(to, skb->data, csstart);
+
+ csum = 0;
+ if (csstart != skb->len)
+ csum = skb_copy_and_csum_bits(skb, csstart, to+csstart,
+ skb->len-csstart, 0);
+
+ if (skb->ip_summed == CHECKSUM_HW) {
+ long csstuff = csstart + skb->csum;
+
+ *((unsigned short *)(to + csstuff)) = csum_fold(csum);
+ }
+}
+
+#if 0
+/*
+ * Tune the memory allocator for a new MTU size.
+ */
+void skb_add_mtu(int mtu)
+{
+ /* Must match allocation in alloc_skb */
+ mtu = SKB_DATA_ALIGN(mtu) + sizeof(struct skb_shared_info);
+
+ kmem_add_cache_size(mtu);
+}
+#endif
+
+void __init skb_init(void)
+{
+ int i;
+
+ skbuff_head_cache = kmem_cache_create("skbuff_head_cache",
+ sizeof(struct sk_buff),
+ 0,
+ SLAB_HWCACHE_ALIGN,
+ skb_headerinit, NULL);
+ if (!skbuff_head_cache)
+ panic("cannot create skbuff cache");
+
+ for (i=0; i<NR_CPUS; i++)
+ skb_queue_head_init(&skb_head_pool[i].list);
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/floppy.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/floppy.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,147 @@
+/*
+ * Architecture specific parts of the Floppy driver
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1995
+ *
+ * Modifications for Xen are Copyright (c) 2004, Keir Fraser.
+ */
+#ifndef __ASM_XEN_I386_FLOPPY_H
+#define __ASM_XEN_I386_FLOPPY_H
+
+#include <linux/vmalloc.h>
+
+/* XEN: Hit DMA paths on the head. This trick from asm-m68k/floppy.h. */
+#include <asm/dma.h>
+#undef MAX_DMA_ADDRESS
+#define MAX_DMA_ADDRESS 0
+#define CROSS_64KB(a,s) (0)
+
+#define fd_inb(port) inb_p(port)
+#define fd_outb(value,port) outb_p(value,port)
+
+#define fd_request_dma() (0)
+#define fd_free_dma() ((void)0)
+#define fd_enable_irq() enable_irq(FLOPPY_IRQ)
+#define fd_disable_irq() disable_irq(FLOPPY_IRQ)
+#define fd_free_irq() free_irq(FLOPPY_IRQ, NULL)
+#define fd_get_dma_residue() (virtual_dma_count + virtual_dma_residue)
+#define fd_dma_setup(addr, size, mode, io) vdma_dma_setup(addr, size, mode, io)
+/*
+ * Do not use vmalloc/vfree: floppy_release_irq_and_dma() gets called from
+ * softirq context via motor_off_callback. A generic bug we happen to trigger.
+ */
+#define fd_dma_mem_alloc(size) __get_free_pages(GFP_KERNEL, get_order(size))
+#define fd_dma_mem_free(addr, size) free_pages(addr, get_order(size))
+
+static int virtual_dma_count;
+static int virtual_dma_residue;
+static char *virtual_dma_addr;
+static int virtual_dma_mode;
+static int doing_pdma;
+
+static irqreturn_t floppy_hardint(int irq, void *dev_id, struct pt_regs * regs)
+{
+ register unsigned char st;
+ register int lcount;
+ register char *lptr;
+
+ if (!doing_pdma)
+ return floppy_interrupt(irq, dev_id, regs);
+
+ st = 1;
+ for(lcount=virtual_dma_count, lptr=virtual_dma_addr;
+ lcount; lcount--, lptr++) {
+ st=inb(virtual_dma_port+4) & 0xa0 ;
+ if(st != 0xa0)
+ break;
+ if(virtual_dma_mode)
+ outb_p(*lptr, virtual_dma_port+5);
+ else
+ *lptr = inb_p(virtual_dma_port+5);
+ }
+ virtual_dma_count = lcount;
+ virtual_dma_addr = lptr;
+ st = inb(virtual_dma_port+4);
+
+ if(st == 0x20)
+ return IRQ_HANDLED;
+ if(!(st & 0x20)) {
+ virtual_dma_residue += virtual_dma_count;
+ virtual_dma_count=0;
+ doing_pdma = 0;
+ floppy_interrupt(irq, dev_id, regs);
+ return IRQ_HANDLED;
+ }
+ return IRQ_HANDLED;
+}
+
+static void fd_disable_dma(void)
+{
+ doing_pdma = 0;
+ virtual_dma_residue += virtual_dma_count;
+ virtual_dma_count=0;
+}
+
+static int fd_request_irq(void)
+{
+ return request_irq(FLOPPY_IRQ, floppy_hardint,SA_INTERRUPT,
+ "floppy", NULL);
+}
+
+static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+ doing_pdma = 1;
+ virtual_dma_port = io;
+ virtual_dma_mode = (mode == DMA_MODE_WRITE);
+ virtual_dma_addr = addr;
+ virtual_dma_count = size;
+ virtual_dma_residue = 0;
+ return 0;
+}
+
+/* XEN: This trick to force 'virtual DMA' is from include/asm-m68k/floppy.h. */
+#define FDC1 xen_floppy_init()
+static int FDC2 = -1;
+
+static int xen_floppy_init(void)
+{
+ use_virtual_dma = 1;
+ can_use_virtual_dma = 1;
+ return 0x3f0;
+}
+
+/*
+ * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock
+ * is needed to prevent corrupted CMOS RAM in case "insmod floppy"
+ * coincides with another rtc CMOS user. Paul G.
+ */
+#define FLOPPY0_TYPE ({ \
+ unsigned long flags; \
+ unsigned char val; \
+ spin_lock_irqsave(&rtc_lock, flags); \
+ val = (CMOS_READ(0x10) >> 4) & 15; \
+ spin_unlock_irqrestore(&rtc_lock, flags); \
+ val; \
+})
+
+#define FLOPPY1_TYPE ({ \
+ unsigned long flags; \
+ unsigned char val; \
+ spin_lock_irqsave(&rtc_lock, flags); \
+ val = CMOS_READ(0x10) & 15; \
+ spin_unlock_irqrestore(&rtc_lock, flags); \
+ val; \
+})
+
+#define N_FDC 2
+#define N_DRIVE 8
+
+#define FLOPPY_MOTOR_MASK 0xf0
+
+#define EXTRA_FLOPPY_PARAMS
+
+#endif /* __ASM_XEN_I386_FLOPPY_H */
diff -r 35b74976f598 -r a83ac0806d6b linux-2.6.11-xen-sparse/kernel/irq/manage.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/kernel/irq/manage.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,392 @@
+/*
+ * linux/kernel/irq/manage.c
+ *
+ * Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar
+ *
+ * This file contains driver APIs to the irq subsystem.
+ */
+
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/interrupt.h>
+
+#include "internals.h"
+
+#ifdef CONFIG_SMP
+
+cpumask_t irq_affinity[NR_IRQS] = { [0 ... NR_IRQS-1] = CPU_MASK_ALL };
+
+/**
+ * synchronize_irq - wait for pending IRQ handlers (on other CPUs)
+ *
+ * This function waits for any pending IRQ handlers for this interrupt
+ * to complete before returning. If you use this function while
+ * holding a resource the IRQ handler may need you will deadlock.
+ *
+ * This function may be called - with care - from IRQ context.
+ */
+void synchronize_irq(unsigned int irq)
+{
+ struct irq_desc *desc = irq_desc + irq;
+
+ while (desc->status & IRQ_INPROGRESS)
+ cpu_relax();
+}
+
+EXPORT_SYMBOL(synchronize_irq);
+
+#endif
+
+/**
+ * disable_irq_nosync - disable an irq without waiting
+ * @irq: Interrupt to disable
+ *
+ * Disable the selected interrupt line. Disables and Enables are
+ * nested.
+ * Unlike disable_irq(), this function does not ensure existing
+ * instances of the IRQ handler have completed before returning.
+ *
+ * This function may be called from IRQ context.
+ */
+void disable_irq_nosync(unsigned int irq)
+{
+ irq_desc_t *desc = irq_desc + irq;
+ unsigned long flags;
+
+ spin_lock_irqsave(&desc->lock, flags);
+ if (!desc->depth++) {
+ desc->status |= IRQ_DISABLED;
+ desc->handler->disable(irq);
+ }
+ spin_unlock_irqrestore(&desc->lock, flags);
+}
+
+EXPORT_SYMBOL(disable_irq_nosync);
+
+/**
+ * disable_irq - disable an irq and wait for completion
+ * @irq: Interrupt to disable
+ *
+ * Disable the selected interrupt line. Enables and Disables are
+ * nested.
+ * This function waits for any pending IRQ handlers for this interrupt
+ * to complete before returning. If you use this function while
+ * holding a resource the IRQ handler may need you will deadlock.
+ *
+ * This function may be called - with care - from IRQ context.
+ */
+void disable_irq(unsigned int irq)
+{
+ irq_desc_t *desc = irq_desc + irq;
+
+ disable_irq_nosync(irq);
+ if (desc->action)
+ synchronize_irq(irq);
+}
+
+EXPORT_SYMBOL(disable_irq);
+
+/**
+ * enable_irq - enable handling of an irq
+ * @irq: Interrupt to enable
+ *
+ * Undoes the effect of one call to disable_irq(). If this
+ * matches the last disable, processing of interrupts on this
+ * IRQ line is re-enabled.
+ *
+ * This function may be called from IRQ context.
+ */
+void enable_irq(unsigned int irq)
+{
+ irq_desc_t *desc = irq_desc + irq;
+ unsigned long flags;
+
+ spin_lock_irqsave(&desc->lock, flags);
+ switch (desc->depth) {
+ case 0:
+ WARN_ON(1);
+ break;
+ case 1: {
+ unsigned int status = desc->status & ~IRQ_DISABLED;
+
+ desc->status = status;
+ if ((status & (IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
+ desc->status = status | IRQ_REPLAY;
+ hw_resend_irq(desc->handler,irq);
+ }
+ desc->handler->enable(irq);
+ /* fall-through */
+ }
+ default:
+ desc->depth--;
+ }
+ spin_unlock_irqrestore(&desc->lock, flags);
+}
+
+EXPORT_SYMBOL(enable_irq);
+
+/*
+ * Internal function that tells the architecture code whether a
+ * particular irq has been exclusively allocated or is available
+ * for driver use.
+ */
+int can_request_irq(unsigned int irq, unsigned long irqflags)
+{
+ struct irqaction *action;
+
+ if (irq >= NR_IRQS)
+ return 0;
+
+ action = irq_desc[irq].action;
+ if (action)
+ if (irqflags & action->flags & SA_SHIRQ)
+ action = NULL;
+
+ return !action;
+}
+
+/**
+ * setup_irq - register an irqaction structure
+ * @irq: Interrupt to register
+ * @irqaction: The irqaction structure to be registered
+ *
+ * Normally called by request_irq, this function can be used
+ * directly to allocate special interrupts that are part of the
+ * architecture.
+ */
+int setup_irq(unsigned int irq, struct irqaction * new)
+{
+ struct irq_desc *desc = irq_desc + irq;
+ struct irqaction *old, **p;
+ unsigned long flags;
+ int shared = 0;
+
+ if (desc->handler == &no_irq_type)
+ return -ENOSYS;
+ /*
+ * Some drivers like serial.c use request_irq() heavily,
+ * so we have to be careful not to interfere with a
+ * running system.
+ */
+ if (new->flags & SA_SAMPLE_RANDOM) {
+ /*
+ * This function might sleep, we want to call it first,
+ * outside of the atomic block.
+ * Yes, this might clear the entropy pool if the wrong
+ * driver is attempted to be loaded, without actually
+ * installing a new handler, but is this really a problem,
+ * only the sysadmin is able to do this.
+ */
+ rand_initialize_irq(irq);
+ }
+
+ /*
+ * The following block of code has to be executed atomically
+ */
+ spin_lock_irqsave(&desc->lock,flags);
+ p = &desc->action;
+ if ((old = *p) != NULL) {
+ /* Can't share interrupts unless both agree to */
+ if (!(old->flags & new->flags & SA_SHIRQ)) {
+ spin_unlock_irqrestore(&desc->lock,flags);
+ return -EBUSY;
+ }
+
+ /* add new interrupt at end of irq queue */
+ do {
+ p = &old->next;
+ old = *p;
+ } while (old);
+ shared = 1;
+ }
+
+ *p = new;
+
+ if (!shared) {
+ desc->depth = 0;
+ desc->status &= ~(IRQ_DISABLED | IRQ_AUTODETECT |
+ IRQ_WAITING | IRQ_INPROGRESS);
+ if (desc->handler->startup)
+ desc->handler->startup(irq);
+ else
+ desc->handler->enable(irq);
+ }
+ spin_unlock_irqrestore(&desc->lock,flags);
+
+ new->irq = irq;
+ register_irq_proc(irq);
+ new->dir = NULL;
+ register_handler_proc(irq, new);
+
+ return 0;
+}
+
+/*
+ * teardown_irq - unregister an irqaction
+ * @irq: Interrupt line being freed
+ * @old: Pointer to the irqaction that is to be unregistered
+ *
+ * This function is called by free_irq and does the actual
+ * business of unregistering the handler. It exists as a
+ * seperate function to enable handlers to be unregistered
+ * for irqactions that have been allocated statically at
+ * boot time.
+ *
+ * This function must not be called from interrupt context.
+ */
+int teardown_irq(unsigned int irq, struct irqaction * old)
+{
+ struct irq_desc *desc;
+ struct irqaction **p;
+ unsigned long flags;
+
+ if (irq >= NR_IRQS)
+ return -ENOENT;
+
+ desc = irq_desc + irq;
+ spin_lock_irqsave(&desc->lock,flags);
+ p = &desc->action;
+ for (;;) {
+ struct irqaction * action = *p;
+
+ if (action) {
+ struct irqaction **pp = p;
+
+ p = &action->next;
+ if (action != old)
+ continue;
+
+ /* Found it - now remove it from the list of entries */
+ *pp = action->next;
+ if (!desc->action) {
+ desc->status |= IRQ_DISABLED;
+ if (desc->handler->shutdown)
+ desc->handler->shutdown(irq);
+ else
+ desc->handler->disable(irq);
+ }
+ spin_unlock_irqrestore(&desc->lock,flags);
+ unregister_handler_proc(irq, action);
+
+ /* Make sure it's not being used on another CPU */
+ synchronize_irq(irq);
+ return 0;
+ }
+ printk(KERN_ERR "Trying to teardown free IRQ%d\n",irq);
+ spin_unlock_irqrestore(&desc->lock,flags);
+ return -ENOENT;
+ }
+}
+
+/**
+ * free_irq - free an interrupt
+ * @irq: Interrupt line to free
+ * @dev_id: Device identity to free
+ *
+ * Remove an interrupt handler. The handler is removed and if the
+ * interrupt line is no longer in use by any driver it is disabled.
+ * On a shared IRQ the caller must ensure the interrupt is disabled
+ * on the card it drives before calling this function. The function
+ * does not return until any executing interrupts for this IRQ
+ * have completed.
+ *
+ * This function must not be called from interrupt context.
+ */
+void free_irq(unsigned int irq, void *dev_id)
+{
+ struct irq_desc *desc;
+ struct irqaction *action;
+ unsigned long flags;
+
+ if (irq >= NR_IRQS)
+ return;
+
+ desc = irq_desc + irq;
+ spin_lock_irqsave(&desc->lock,flags);
+ for (action = desc->action; action != NULL; action = action->next) {
+ if (action->dev_id != dev_id)
+ continue;
+
+ spin_unlock_irqrestore(&desc->lock,flags);
+
+ if (teardown_irq(irq, action) == 0)
+ kfree(action);
+ return;
+ }
+ printk(KERN_ERR "Trying to free free IRQ%d\n",irq);
+ spin_unlock_irqrestore(&desc->lock,flags);
+ return;
+}
+
+EXPORT_SYMBOL(free_irq);
+
+/**
+ * request_irq - allocate an interrupt line
+ * @irq: Interrupt line to allocate
+ * @handler: Function to be called when the IRQ occurs
+ * @irqflags: Interrupt type flags
+ * @devname: An ascii name for the claiming device
+ * @dev_id: A cookie passed back to the handler function
+ *
+ * This call allocates interrupt resources and enables the
+ * interrupt line and IRQ handling. From the point this
+ * call is made your handler function may be invoked. Since
+ * your handler function must clear any interrupt the board
+ * raises, you must take care both to initialise your hardware
+ * and to set up the interrupt handler in the right order.
+ *
+ * Dev_id must be globally unique. Normally the address of the
+ * device data structure is used as the cookie. Since the handler
+ * receives this value it makes sense to use it.
+ *
+ * If your interrupt is shared you must pass a non NULL dev_id
+ * as this is required when freeing the interrupt.
+ *
+ * Flags:
+ *
+ * SA_SHIRQ Interrupt is shared
+ * SA_INTERRUPT Disable local interrupts while processing
+ * SA_SAMPLE_RANDOM The interrupt can be used for entropy
+ *
+ */
+int request_irq(unsigned int irq,
+ irqreturn_t (*handler)(int, void *, struct pt_regs *),
+ unsigned long irqflags, const char * devname, void *dev_id)
+{
+ struct irqaction * action;
+ int retval;
+
+ /*
+ * Sanity-check: shared interrupts must pass in a real dev-ID,
+ * otherwise we'll have trouble later trying to figure out
+ * which interrupt is which (messes up the interrupt freeing
+ * logic etc).
+ */
+ if ((irqflags & SA_SHIRQ) && !dev_id)
+ return -EINVAL;
+ if (irq >= NR_IRQS)
+ return -EINVAL;
+ if (!handler)
+ return -EINVAL;
+
+ action = kmalloc(sizeof(struct irqaction), GFP_ATOMIC);
+ if (!action)
+ return -ENOMEM;
+
+ action->handler = handler;
+ action->flags = irqflags;
+ cpus_clear(action->mask);
+ action->name = devname;
+ action->next = NULL;
+ action->dev_id = dev_id;
+
+ retval = setup_irq(irq, action);
+ if (retval)
+ kfree(action);
+
+ return retval;
+}
+
+EXPORT_SYMBOL(request_irq);
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/linux-public/privcmd.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/linux-public/privcmd.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,90 @@
+/******************************************************************************
+ * privcmd.h
+ *
+ * Interface to /proc/xen/privcmd.
+ *
+ * Copyright (c) 2003-2004, K A Fraser
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __PRIVCMD_H__
+#define __PRIVCMD_H__
+
+typedef struct privcmd_hypercall
+{
+ unsigned long op;
+ unsigned long arg[5];
+} privcmd_hypercall_t;
+
+typedef struct privcmd_mmap_entry {
+ unsigned long va;
+ unsigned long mfn;
+ unsigned long npages;
+} privcmd_mmap_entry_t;
+
+typedef struct privcmd_mmap {
+ int num;
+ domid_t dom; /* target domain */
+ privcmd_mmap_entry_t *entry;
+} privcmd_mmap_t;
+
+typedef struct privcmd_mmapbatch {
+ int num; /* number of pages to populate */
+ domid_t dom; /* target domain */
+ unsigned long addr; /* virtual address */
+ unsigned long *arr; /* array of mfns - top nibble set on err */
+} privcmd_mmapbatch_t;
+
+typedef struct privcmd_blkmsg
+{
+ unsigned long op;
+ void *buf;
+ int buf_size;
+} privcmd_blkmsg_t;
+
+/*
+ * @cmd: IOCTL_PRIVCMD_HYPERCALL
+ * @arg: &privcmd_hypercall_t
+ * Return: Value returned from execution of the specified hypercall.
+ */
+#define IOCTL_PRIVCMD_HYPERCALL \
+ _IOC(_IOC_NONE, 'P', 0, sizeof(privcmd_hypercall_t))
+
+/*
+ * @cmd: IOCTL_PRIVCMD_INITDOMAIN_EVTCHN
+ * @arg: n/a
+ * Return: Port associated with domain-controller end of control event channel
+ * for the initial domain.
+ */
+#define IOCTL_PRIVCMD_INITDOMAIN_EVTCHN \
+ _IOC(_IOC_NONE, 'P', 1, 0)
+#define IOCTL_PRIVCMD_MMAP \
+ _IOC(_IOC_NONE, 'P', 2, sizeof(privcmd_mmap_t))
+#define IOCTL_PRIVCMD_MMAPBATCH \
+ _IOC(_IOC_NONE, 'P', 3, sizeof(privcmd_mmapbatch_t))
+#define IOCTL_PRIVCMD_GET_MACH2PHYS_START_MFN \
+ _IOC(_IOC_READ, 'P', 4, sizeof(unsigned long))
+#define IOCTL_PRIVCMD_INITDOMAIN_STORE \
+ _IOC(_IOC_READ, 'P', 5, 0)
+
+#endif /* __PRIVCMD_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/kernel/reboot.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/kernel/reboot.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,269 @@
+
+#define __KERNEL_SYSCALLS__
+static int errno;
+#include <linux/errno.h>
+#include <linux/version.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/unistd.h>
+#include <linux/module.h>
+#include <linux/reboot.h>
+#include <linux/sysrq.h>
+#include <asm/irq.h>
+#include <asm/mmu_context.h>
+#include <asm-xen/ctrl_if.h>
+#include <asm-xen/hypervisor.h>
+#include <asm-xen/xen-public/dom0_ops.h>
+#include <asm-xen/linux-public/suspend.h>
+#include <asm-xen/queues.h>
+
+void machine_restart(char * __unused)
+{
+ /* We really want to get pending console data out before we die. */
+ extern void xencons_force_flush(void);
+ xencons_force_flush();
+ HYPERVISOR_reboot();
+}
+
+void machine_halt(void)
+{
+ machine_power_off();
+}
+
+void machine_power_off(void)
+{
+ /* We really want to get pending console data out before we die. */
+ extern void xencons_force_flush(void);
+ xencons_force_flush();
+ HYPERVISOR_shutdown();
+}
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+int reboot_thru_bios = 0; /* for dmi_scan.c */
+EXPORT_SYMBOL(machine_restart);
+EXPORT_SYMBOL(machine_halt);
+EXPORT_SYMBOL(machine_power_off);
+#endif
+
+
+/******************************************************************************
+ * Stop/pickle callback handling.
+ */
+
+/* Ignore multiple shutdown requests. */
+static int shutting_down = -1;
+
+static void __do_suspend(void)
+{
+ int i, j;
+ suspend_record_t *suspend_record;
+
+ /* Hmmm... a cleaner interface to suspend/resume blkdevs would be nice. */
+ /* XXX SMH: yes it would :-( */
+#ifdef CONFIG_XEN_BLKDEV_FRONTEND
+ extern void blkdev_suspend(void);
+ extern void blkdev_resume(void);
+#else
+#define blkdev_suspend() do{}while(0)
+#define blkdev_resume() do{}while(0)
+#endif
+
+#ifdef CONFIG_XEN_NETDEV_FRONTEND
+ extern void netif_suspend(void);
+ extern void netif_resume(void);
+#else
+#define netif_suspend() do{}while(0)
+#define netif_resume() do{}while(0)
+#endif
+
+#ifdef CONFIG_XEN_USB_FRONTEND
+ extern void usbif_resume();
+#else
+#define usbif_resume() do{}while(0)
+#endif
+
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ extern int gnttab_suspend(void);
+ extern int gnttab_resume(void);
+#else
+#define gnttab_suspend() do{}while(0)
+#define gnttab_resume() do{}while(0)
+#endif
+
+ extern void time_suspend(void);
+ extern void time_resume(void);
+ extern unsigned long max_pfn;
+ extern unsigned int *pfn_to_mfn_frame_list;
+
+ suspend_record = (suspend_record_t *)__get_free_page(GFP_KERNEL);
+ if ( suspend_record == NULL )
+ goto out;
+
+ suspend_record->nr_pfns = max_pfn; /* final number of pfns */
+
+ __cli();
+
+#ifdef __i386__
+ mm_pin_all();
+ kmem_cache_shrink(pgd_cache);
+#endif
+
+ netif_suspend();
+
+ blkdev_suspend();
+
+ time_suspend();
+
+ ctrl_if_suspend();
+
+ irq_suspend();
+
+ gnttab_suspend();
+
+ HYPERVISOR_shared_info = (shared_info_t *)empty_zero_page;
+ clear_fixmap(FIX_SHARED_INFO);
+
+ memcpy(&suspend_record->resume_info, &xen_start_info,
+ sizeof(xen_start_info));
+
+ HYPERVISOR_suspend(virt_to_machine(suspend_record) >> PAGE_SHIFT);
+
+ shutting_down = -1;
+
+ memcpy(&xen_start_info, &suspend_record->resume_info,
+ sizeof(xen_start_info));
+
+ set_fixmap(FIX_SHARED_INFO, xen_start_info.shared_info);
+
+ HYPERVISOR_shared_info = (shared_info_t *)fix_to_virt(FIX_SHARED_INFO);
+
+ memset(empty_zero_page, 0, PAGE_SIZE);
+
+ for ( i=0, j=0; i < max_pfn; i+=(PAGE_SIZE/sizeof(unsigned long)), j++ )
+ {
+ pfn_to_mfn_frame_list[j] =
+ virt_to_machine(&phys_to_machine_mapping[i]) >> PAGE_SHIFT;
+ }
+ HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list =
+ virt_to_machine(pfn_to_mfn_frame_list) >> PAGE_SHIFT;
+
+ gnttab_resume();
+
+ irq_resume();
+
+ ctrl_if_resume();
+
+ time_resume();
+
+ blkdev_resume();
+
+ netif_resume();
+
+ usbif_resume();
+
+ __sti();
+
+ out:
+ if ( suspend_record != NULL )
+ free_page((unsigned long)suspend_record);
+}
+
+static int shutdown_process(void *__unused)
+{
+ static char *envp[] = { "HOME=/", "TERM=linux",
+ "PATH=/sbin:/usr/sbin:/bin:/usr/bin", NULL };
+ static char *restart_argv[] = { "/sbin/shutdown", "-r", "now", NULL };
+ static char *poweroff_argv[] = { "/sbin/halt", "-p", NULL };
+
+ extern asmlinkage long sys_reboot(int magic1, int magic2,
+ unsigned int cmd, void *arg);
+
+ daemonize(
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+ "shutdown"
+#endif
+ );
+
+ switch ( shutting_down )
+ {
+ case CMSG_SHUTDOWN_POWEROFF:
+ if ( execve("/sbin/halt", poweroff_argv, envp) < 0 )
+ {
+ sys_reboot(LINUX_REBOOT_MAGIC1,
+ LINUX_REBOOT_MAGIC2,
+ LINUX_REBOOT_CMD_POWER_OFF,
+ NULL);
+ }
+ break;
+
+ case CMSG_SHUTDOWN_REBOOT:
+ if ( execve("/sbin/shutdown", restart_argv, envp) < 0 )
+ {
+ sys_reboot(LINUX_REBOOT_MAGIC1,
+ LINUX_REBOOT_MAGIC2,
+ LINUX_REBOOT_CMD_RESTART,
+ NULL);
+ }
+ break;
+ }
+
+ shutting_down = -1; /* could try again */
+
+ return 0;
+}
+
+static void __shutdown_handler(void *unused)
+{
+ int err;
+
+ if ( shutting_down != CMSG_SHUTDOWN_SUSPEND )
+ {
+ err = kernel_thread(shutdown_process, NULL, CLONE_FS | CLONE_FILES);
+ if ( err < 0 )
+ printk(KERN_ALERT "Error creating shutdown process!\n");
+ }
+ else
+ {
+ __do_suspend();
+ }
+}
+
+static void shutdown_handler(ctrl_msg_t *msg, unsigned long id)
+{
+ static DECLARE_WORK(shutdown_work, __shutdown_handler, NULL);
+
+ if ( msg->subtype == CMSG_SHUTDOWN_SYSRQ )
+ {
+ int sysrq = ((shutdown_sysrq_t *)&msg->msg[0])->key;
+
+#ifdef CONFIG_MAGIC_SYSRQ
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+ handle_sysrq(sysrq, NULL, NULL);
+#else
+ handle_sysrq(sysrq, NULL, NULL, NULL);
+#endif
+#endif
+ }
+ else if ( (shutting_down == -1) &&
+ ((msg->subtype == CMSG_SHUTDOWN_POWEROFF) ||
+ (msg->subtype == CMSG_SHUTDOWN_REBOOT) ||
+ (msg->subtype == CMSG_SHUTDOWN_SUSPEND)) )
+ {
+ shutting_down = msg->subtype;
+ schedule_work(&shutdown_work);
+ }
+ else
+ {
+ printk("Ignore spurious shutdown request\n");
+ }
+
+ ctrl_if_send_response(msg);
+}
+
+static int __init setup_shutdown_event(void)
+{
+ ctrl_if_register_receiver(CMSG_SHUTDOWN, shutdown_handler, 0);
+ return 0;
+}
+
+__initcall(setup_shutdown_event);
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/mm/memory.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/mm/memory.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,1534 @@
+/*
+ * linux/mm/memory.c
+ *
+ * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
+ */
+
+/*
+ * demand-loading started 01.12.91 - seems it is high on the list of
+ * things wanted, and it should be easy to implement. - Linus
+ */
+
+/*
+ * Ok, demand-loading was easy, shared pages a little bit tricker. Shared
+ * pages started 02.12.91, seems to work. - Linus.
+ *
+ * Tested sharing by executing about 30 /bin/sh: under the old kernel it
+ * would have taken more than the 6M I have free, but it worked well as
+ * far as I could see.
+ *
+ * Also corrected some "invalidate()"s - I wasn't doing enough of them.
+ */
+
+/*
+ * Real VM (paging to/from disk) started 18.12.91. Much more work and
+ * thought has to go into this. Oh, well..
+ * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why.
+ * Found it. Everything seems to work now.
+ * 20.12.91 - Ok, making the swap-device changeable like the root.
+ */
+
+/*
+ * 05.04.94 - Multi-page memory management added for v1.1.
+ * Idea by Alex Bligh (alex@xxxxxxxxxxxxxxx)
+ *
+ * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG
+ * (Gerhard.Wichert@xxxxxxxxxxxxxx)
+ */
+
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/smp_lock.h>
+#include <linux/swapctl.h>
+#include <linux/iobuf.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/module.h>
+
+#include <asm/pgalloc.h>
+#include <asm/uaccess.h>
+#include <asm/tlb.h>
+
+unsigned long max_mapnr;
+unsigned long num_physpages;
+unsigned long num_mappedpages;
+void * high_memory;
+struct page *highmem_start_page;
+
+/*
+ * We special-case the C-O-W ZERO_PAGE, because it's such
+ * a common occurrence (no need to read the page to know
+ * that it's zero - better for the cache and memory subsystem).
+ */
+static inline void copy_cow_page(struct page * from, struct page * to,
unsigned long address)
+{
+ if (from == ZERO_PAGE(address)) {
+ clear_user_highpage(to, address);
+ return;
+ }
+ copy_user_highpage(to, from, address);
+}
+
+mem_map_t * mem_map;
+
+/*
+ * Called by TLB shootdown
+ */
+void __free_pte(pte_t pte)
+{
+ struct page *page = pte_page(pte);
+ if ((!VALID_PAGE(page)) || PageReserved(page))
+ return;
+ if (pte_dirty(pte))
+ set_page_dirty(page);
+ free_page_and_swap_cache(page);
+}
+
+
+/*
+ * Note: this doesn't free the actual pages themselves. That
+ * has been handled earlier when unmapping all the memory regions.
+ */
+static inline void free_one_pmd(pmd_t * dir)
+{
+ pte_t * pte;
+
+ if (pmd_none(*dir))
+ return;
+ if (pmd_bad(*dir)) {
+ pmd_ERROR(*dir);
+ pmd_clear(dir);
+ return;
+ }
+ pte = pte_offset(dir, 0);
+ pmd_clear(dir);
+ pte_free(pte);
+}
+
+static inline void free_one_pgd(pgd_t * dir)
+{
+ int j;
+ pmd_t * pmd;
+
+ if (pgd_none(*dir))
+ return;
+ if (pgd_bad(*dir)) {
+ pgd_ERROR(*dir);
+ pgd_clear(dir);
+ return;
+ }
+ pmd = pmd_offset(dir, 0);
+ pgd_clear(dir);
+ for (j = 0; j < PTRS_PER_PMD ; j++) {
+ prefetchw(pmd+j+(PREFETCH_STRIDE/16));
+ free_one_pmd(pmd+j);
+ }
+ pmd_free(pmd);
+}
+
+/* Low and high watermarks for page table cache.
+ The system should try to have pgt_water[0] <= cache elements <= pgt_water[1]
+ */
+int pgt_cache_water[2] = { 25, 50 };
+
+/* Returns the number of pages freed */
+int check_pgt_cache(void)
+{
+ return do_check_pgt_cache(pgt_cache_water[0], pgt_cache_water[1]);
+}
+
+
+/*
+ * This function clears all user-level page tables of a process - this
+ * is needed by execve(), so that old pages aren't in the way.
+ */
+void clear_page_tables(struct mm_struct *mm, unsigned long first, int nr)
+{
+ pgd_t * page_dir = mm->pgd;
+
+ spin_lock(&mm->page_table_lock);
+ page_dir += first;
+ do {
+ free_one_pgd(page_dir);
+ page_dir++;
+ } while (--nr);
+ spin_unlock(&mm->page_table_lock);
+
+ /* keep the page table cache within bounds */
+ check_pgt_cache();
+}
+
+#define PTE_TABLE_MASK ((PTRS_PER_PTE-1) * sizeof(pte_t))
+#define PMD_TABLE_MASK ((PTRS_PER_PMD-1) * sizeof(pmd_t))
+
+/*
+ * copy one vm_area from one task to the other. Assumes the page tables
+ * already present in the new task to be cleared in the whole range
+ * covered by this vma.
+ *
+ * 08Jan98 Merged into one routine from several inline routines to reduce
+ * variable count and make things faster. -jj
+ *
+ * dst->page_table_lock is held on entry and exit,
+ * but may be dropped within pmd_alloc() and pte_alloc().
+ */
+int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
+ struct vm_area_struct *vma)
+{
+ pgd_t * src_pgd, * dst_pgd;
+ unsigned long address = vma->vm_start;
+ unsigned long end = vma->vm_end;
+ unsigned long cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) ==
VM_MAYWRITE;
+
+ src_pgd = pgd_offset(src, address)-1;
+ dst_pgd = pgd_offset(dst, address)-1;
+
+ for (;;) {
+ pmd_t * src_pmd, * dst_pmd;
+
+ src_pgd++; dst_pgd++;
+
+ /* copy_pmd_range */
+
+ if (pgd_none(*src_pgd))
+ goto skip_copy_pmd_range;
+ if (pgd_bad(*src_pgd)) {
+ pgd_ERROR(*src_pgd);
+ pgd_clear(src_pgd);
+skip_copy_pmd_range: address = (address + PGDIR_SIZE) & PGDIR_MASK;
+ if (!address || (address >= end))
+ goto out;
+ continue;
+ }
+
+ src_pmd = pmd_offset(src_pgd, address);
+ dst_pmd = pmd_alloc(dst, dst_pgd, address);
+ if (!dst_pmd)
+ goto nomem;
+
+ do {
+ pte_t * src_pte, * dst_pte;
+
+ /* copy_pte_range */
+
+ if (pmd_none(*src_pmd))
+ goto skip_copy_pte_range;
+ if (pmd_bad(*src_pmd)) {
+ pmd_ERROR(*src_pmd);
+ pmd_clear(src_pmd);
+skip_copy_pte_range: address = (address + PMD_SIZE) & PMD_MASK;
+ if (address >= end)
+ goto out;
+ goto cont_copy_pmd_range;
+ }
+
+ src_pte = pte_offset(src_pmd, address);
+ dst_pte = pte_alloc(dst, dst_pmd, address);
+ if (!dst_pte)
+ goto nomem;
+
+ spin_lock(&src->page_table_lock);
+ do {
+ pte_t pte = *src_pte;
+ struct page *ptepage;
+
+ /* copy_one_pte */
+
+ if (pte_none(pte))
+ goto cont_copy_pte_range_noset;
+ if (!pte_present(pte)) {
+ swap_duplicate(pte_to_swp_entry(pte));
+ goto cont_copy_pte_range;
+ }
+ ptepage = pte_page(pte);
+ if ((!VALID_PAGE(ptepage)) ||
+ PageReserved(ptepage))
+ goto cont_copy_pte_range;
+
+ /* If it's a COW mapping, write protect it both
in the parent and the child */
+ if (cow && pte_write(pte)) {
+ ptep_set_wrprotect(src_pte);
+ pte = *src_pte;
+ }
+
+ /* If it's a shared mapping, mark it clean in
the child */
+ if (vma->vm_flags & VM_SHARED)
+ pte = pte_mkclean(pte);
+ pte = pte_mkold(pte);
+ get_page(ptepage);
+ dst->rss++;
+
+cont_copy_pte_range: set_pte(dst_pte, pte);
+cont_copy_pte_range_noset: address += PAGE_SIZE;
+ if (address >= end)
+ goto out_unlock;
+ src_pte++;
+ dst_pte++;
+ } while ((unsigned long)src_pte & PTE_TABLE_MASK);
+ spin_unlock(&src->page_table_lock);
+
+cont_copy_pmd_range: src_pmd++;
+ dst_pmd++;
+ } while ((unsigned long)src_pmd & PMD_TABLE_MASK);
+ }
+out_unlock:
+ spin_unlock(&src->page_table_lock);
+out:
+ return 0;
+nomem:
+ return -ENOMEM;
+}
+
+/*
+ * Return indicates whether a page was freed so caller can adjust rss
+ */
+static inline void forget_pte(pte_t page)
+{
+ if (!pte_none(page)) {
+ printk("forget_pte: old mapping existed!\n");
+ BUG();
+ }
+}
+
+static inline int zap_pte_range(mmu_gather_t *tlb, pmd_t * pmd, unsigned long
address, unsigned long size)
+{
+ unsigned long offset;
+ pte_t * ptep;
+ int freed = 0;
+
+ if (pmd_none(*pmd))
+ return 0;
+ if (pmd_bad(*pmd)) {
+ pmd_ERROR(*pmd);
+ pmd_clear(pmd);
+ return 0;
+ }
+ ptep = pte_offset(pmd, address);
+ offset = address & ~PMD_MASK;
+ if (offset + size > PMD_SIZE)
+ size = PMD_SIZE - offset;
+ size &= PAGE_MASK;
+ for (offset=0; offset < size; ptep++, offset += PAGE_SIZE) {
+ pte_t pte = *ptep;
+ if (pte_none(pte))
+ continue;
+ if (pte_present(pte)) {
+ struct page *page = pte_page(pte);
+ if (VALID_PAGE(page) && !PageReserved(page))
+ freed ++;
+ /* This will eventually call __free_pte on the pte. */
+ tlb_remove_page(tlb, ptep, address + offset);
+ } else {
+ free_swap_and_cache(pte_to_swp_entry(pte));
+ pte_clear(ptep);
+ }
+ }
+
+ return freed;
+}
+
+static inline int zap_pmd_range(mmu_gather_t *tlb, pgd_t * dir, unsigned long
address, unsigned long size)
+{
+ pmd_t * pmd;
+ unsigned long end;
+ int freed;
+
+ if (pgd_none(*dir))
+ return 0;
+ if (pgd_bad(*dir)) {
+ pgd_ERROR(*dir);
+ pgd_clear(dir);
+ return 0;
+ }
+ pmd = pmd_offset(dir, address);
+ end = address + size;
+ if (end > ((address + PGDIR_SIZE) & PGDIR_MASK))
+ end = ((address + PGDIR_SIZE) & PGDIR_MASK);
+ freed = 0;
+ do {
+ freed += zap_pte_range(tlb, pmd, address, end - address);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address < end);
+ return freed;
+}
+
+/*
+ * remove user pages in a given range.
+ */
+void zap_page_range(struct mm_struct *mm, unsigned long address, unsigned long
size)
+{
+ mmu_gather_t *tlb;
+ pgd_t * dir;
+ unsigned long start = address, end = address + size;
+ int freed = 0;
+
+ dir = pgd_offset(mm, address);
+
+ /*
+ * This is a long-lived spinlock. That's fine.
+ * There's no contention, because the page table
+ * lock only protects against kswapd anyway, and
+ * even if kswapd happened to be looking at this
+ * process we _want_ it to get stuck.
+ */
+ if (address >= end)
+ BUG();
+ spin_lock(&mm->page_table_lock);
+ flush_cache_range(mm, address, end);
+ tlb = tlb_gather_mmu(mm);
+
+ do {
+ freed += zap_pmd_range(tlb, dir, address, end - address);
+ address = (address + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+ } while (address && (address < end));
+
+ /* this will flush any remaining tlb entries */
+ tlb_finish_mmu(tlb, start, end);
+
+ /*
+ * Update rss for the mm_struct (not necessarily current->mm)
+ * Notice that rss is an unsigned long.
+ */
+ if (mm->rss > freed)
+ mm->rss -= freed;
+ else
+ mm->rss = 0;
+ spin_unlock(&mm->page_table_lock);
+}
+
+/*
+ * Do a quick page-table lookup for a single page.
+ */
+static struct page * follow_page(struct mm_struct *mm, unsigned long address,
int write)
+{
+ pgd_t *pgd;
+ pmd_t *pmd;
+ pte_t *ptep, pte;
+
+ pgd = pgd_offset(mm, address);
+ if (pgd_none(*pgd) || pgd_bad(*pgd))
+ goto out;
+
+ pmd = pmd_offset(pgd, address);
+ if (pmd_none(*pmd) || pmd_bad(*pmd))
+ goto out;
+
+ ptep = pte_offset(pmd, address);
+ if (!ptep)
+ goto out;
+
+ pte = *ptep;
+ if (pte_present(pte)) {
+ if (!write ||
+ (pte_write(pte) && pte_dirty(pte)))
+ return pte_page(pte);
+ }
+
+out:
+ return 0;
+}
+
+/*
+ * Given a physical address, is there a useful struct page pointing to
+ * it? This may become more complex in the future if we start dealing
+ * with IO-aperture pages in kiobufs.
+ */
+
+static inline struct page * get_page_map(struct page *page)
+{
+ if (!VALID_PAGE(page))
+ return 0;
+ return page;
+}
+
+/*
+ * Please read Documentation/cachetlb.txt before using this function,
+ * accessing foreign memory spaces can cause cache coherency problems.
+ *
+ * Accessing a VM_IO area is even more dangerous, therefore the function
+ * fails if pages is != NULL and a VM_IO area is found.
+ */
+int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned
long start,
+ int len, int write, int force, struct page **pages, struct
vm_area_struct **vmas)
+{
+ int i;
+ unsigned int flags;
+
+ /*
+ * Require read or write permissions.
+ * If 'force' is set, we only require the "MAY" flags.
+ */
+ flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
+ flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
+ i = 0;
+
+ do {
+ struct vm_area_struct * vma;
+
+ vma = find_extend_vma(mm, start);
+
+ if ( !vma || (pages && vma->vm_flags & VM_IO) || !(flags &
vma->vm_flags) )
+ return i ? : -EFAULT;
+
+ spin_lock(&mm->page_table_lock);
+ do {
+ struct page *map;
+ while (!(map = follow_page(mm, start, write))) {
+ spin_unlock(&mm->page_table_lock);
+ switch (handle_mm_fault(mm, vma, start, write))
{
+ case 1:
+ tsk->min_flt++;
+ break;
+ case 2:
+ tsk->maj_flt++;
+ break;
+ case 0:
+ if (i) return i;
+ return -EFAULT;
+ default:
+ if (i) return i;
+ return -ENOMEM;
+ }
+ spin_lock(&mm->page_table_lock);
+ }
+ if (pages) {
+ pages[i] = get_page_map(map);
+ /* FIXME: call the correct function,
+ * depending on the type of the found page
+ */
+ if (!pages[i] || PageReserved(pages[i])) {
+ if (pages[i] != ZERO_PAGE(start))
+ goto bad_page;
+ } else
+ page_cache_get(pages[i]);
+ }
+ if (vmas)
+ vmas[i] = vma;
+ i++;
+ start += PAGE_SIZE;
+ len--;
+ } while(len && start < vma->vm_end);
+ spin_unlock(&mm->page_table_lock);
+ } while(len);
+out:
+ return i;
+
+ /*
+ * We found an invalid page in the VMA. Release all we have
+ * so far and fail.
+ */
+bad_page:
+ spin_unlock(&mm->page_table_lock);
+ while (i--)
+ page_cache_release(pages[i]);
+ i = -EFAULT;
+ goto out;
+}
+
+EXPORT_SYMBOL(get_user_pages);
+
+/*
+ * Force in an entire range of pages from the current process's user VA,
+ * and pin them in physical memory.
+ */
+#define dprintk(x...)
+
+int map_user_kiobuf(int rw, struct kiobuf *iobuf, unsigned long va, size_t len)
+{
+ int pgcount, err;
+ struct mm_struct * mm;
+
+ /* Make sure the iobuf is not already mapped somewhere. */
+ if (iobuf->nr_pages)
+ return -EINVAL;
+
+ mm = current->mm;
+ dprintk ("map_user_kiobuf: begin\n");
+
+ pgcount = (va + len + PAGE_SIZE - 1)/PAGE_SIZE - va/PAGE_SIZE;
+ /* mapping 0 bytes is not permitted */
+ if (!pgcount) BUG();
+ err = expand_kiobuf(iobuf, pgcount);
+ if (err)
+ return err;
+
+ iobuf->locked = 0;
+ iobuf->offset = va & (PAGE_SIZE-1);
+ iobuf->length = len;
+
+ /* Try to fault in all of the necessary pages */
+ down_read(&mm->mmap_sem);
+ /* rw==READ means read from disk, write into memory area */
+ err = get_user_pages(current, mm, va, pgcount,
+ (rw==READ), 0, iobuf->maplist, NULL);
+ up_read(&mm->mmap_sem);
+ if (err < 0) {
+ unmap_kiobuf(iobuf);
+ dprintk ("map_user_kiobuf: end %d\n", err);
+ return err;
+ }
+ iobuf->nr_pages = err;
+ while (pgcount--) {
+ /* FIXME: flush superflous for rw==READ,
+ * probably wrong function for rw==WRITE
+ */
+ flush_dcache_page(iobuf->maplist[pgcount]);
+ }
+ dprintk ("map_user_kiobuf: end OK\n");
+ return 0;
+}
+
+/*
+ * Mark all of the pages in a kiobuf as dirty
+ *
+ * We need to be able to deal with short reads from disk: if an IO error
+ * occurs, the number of bytes read into memory may be less than the
+ * size of the kiobuf, so we have to stop marking pages dirty once the
+ * requested byte count has been reached.
+ *
+ * Must be called from process context - set_page_dirty() takes VFS locks.
+ */
+
+void mark_dirty_kiobuf(struct kiobuf *iobuf, int bytes)
+{
+ int index, offset, remaining;
+ struct page *page;
+
+ index = iobuf->offset >> PAGE_SHIFT;
+ offset = iobuf->offset & ~PAGE_MASK;
+ remaining = bytes;
+ if (remaining > iobuf->length)
+ remaining = iobuf->length;
+
+ while (remaining > 0 && index < iobuf->nr_pages) {
+ page = iobuf->maplist[index];
+
+ if (!PageReserved(page))
+ set_page_dirty(page);
+
+ remaining -= (PAGE_SIZE - offset);
+ offset = 0;
+ index++;
+ }
+}
+
+/*
+ * Unmap all of the pages referenced by a kiobuf. We release the pages,
+ * and unlock them if they were locked.
+ */
+
+void unmap_kiobuf (struct kiobuf *iobuf)
+{
+ int i;
+ struct page *map;
+
+ for (i = 0; i < iobuf->nr_pages; i++) {
+ map = iobuf->maplist[i];
+ if (map) {
+ if (iobuf->locked)
+ UnlockPage(map);
+ /* FIXME: cache flush missing for rw==READ
+ * FIXME: call the correct reference counting function
+ */
+ page_cache_release(map);
+ }
+ }
+
+ iobuf->nr_pages = 0;
+ iobuf->locked = 0;
+}
+
+
+/*
+ * Lock down all of the pages of a kiovec for IO.
+ *
+ * If any page is mapped twice in the kiovec, we return the error -EINVAL.
+ *
+ * The optional wait parameter causes the lock call to block until all
+ * pages can be locked if set. If wait==0, the lock operation is
+ * aborted if any locked pages are found and -EAGAIN is returned.
+ */
+
+int lock_kiovec(int nr, struct kiobuf *iovec[], int wait)
+{
+ struct kiobuf *iobuf;
+ int i, j;
+ struct page *page, **ppage;
+ int doublepage = 0;
+ int repeat = 0;
+
+ repeat:
+
+ for (i = 0; i < nr; i++) {
+ iobuf = iovec[i];
+
+ if (iobuf->locked)
+ continue;
+
+ ppage = iobuf->maplist;
+ for (j = 0; j < iobuf->nr_pages; ppage++, j++) {
+ page = *ppage;
+ if (!page)
+ continue;
+
+ if (TryLockPage(page)) {
+ while (j--) {
+ struct page *tmp = *--ppage;
+ if (tmp)
+ UnlockPage(tmp);
+ }
+ goto retry;
+ }
+ }
+ iobuf->locked = 1;
+ }
+
+ return 0;
+
+ retry:
+
+ /*
+ * We couldn't lock one of the pages. Undo the locking so far,
+ * wait on the page we got to, and try again.
+ */
+
+ unlock_kiovec(nr, iovec);
+ if (!wait)
+ return -EAGAIN;
+
+ /*
+ * Did the release also unlock the page we got stuck on?
+ */
+ if (!PageLocked(page)) {
+ /*
+ * If so, we may well have the page mapped twice
+ * in the IO address range. Bad news. Of
+ * course, it _might_ just be a coincidence,
+ * but if it happens more than once, chances
+ * are we have a double-mapped page.
+ */
+ if (++doublepage >= 3)
+ return -EINVAL;
+
+ /* Try again... */
+ wait_on_page(page);
+ }
+
+ if (++repeat < 16)
+ goto repeat;
+ return -EAGAIN;
+}
+
+/*
+ * Unlock all of the pages of a kiovec after IO.
+ */
+
+int unlock_kiovec(int nr, struct kiobuf *iovec[])
+{
+ struct kiobuf *iobuf;
+ int i, j;
+ struct page *page, **ppage;
+
+ for (i = 0; i < nr; i++) {
+ iobuf = iovec[i];
+
+ if (!iobuf->locked)
+ continue;
+ iobuf->locked = 0;
+
+ ppage = iobuf->maplist;
+ for (j = 0; j < iobuf->nr_pages; ppage++, j++) {
+ page = *ppage;
+ if (!page)
+ continue;
+ UnlockPage(page);
+ }
+ }
+ return 0;
+}
+
+static inline void zeromap_pte_range(pte_t * pte, unsigned long address,
+ unsigned long size, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ do {
+ pte_t zero_pte = pte_wrprotect(mk_pte(ZERO_PAGE(address),
prot));
+ pte_t oldpage = ptep_get_and_clear(pte);
+ set_pte(pte, zero_pte);
+ forget_pte(oldpage);
+ address += PAGE_SIZE;
+ pte++;
+ } while (address && (address < end));
+}
+
+static inline int zeromap_pmd_range(struct mm_struct *mm, pmd_t * pmd,
unsigned long address,
+ unsigned long size, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ do {
+ pte_t * pte = pte_alloc(mm, pmd, address);
+ if (!pte)
+ return -ENOMEM;
+ zeromap_pte_range(pte, address, end - address, prot);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+ return 0;
+}
+
+int zeromap_page_range(unsigned long address, unsigned long size, pgprot_t
prot)
+{
+ int error = 0;
+ pgd_t * dir;
+ unsigned long beg = address;
+ unsigned long end = address + size;
+ struct mm_struct *mm = current->mm;
+
+ dir = pgd_offset(mm, address);
+ flush_cache_range(mm, beg, end);
+ if (address >= end)
+ BUG();
+
+ spin_lock(&mm->page_table_lock);
+ do {
+ pmd_t *pmd = pmd_alloc(mm, dir, address);
+ error = -ENOMEM;
+ if (!pmd)
+ break;
+ error = zeromap_pmd_range(mm, pmd, address, end - address,
prot);
+ if (error)
+ break;
+ address = (address + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+ } while (address && (address < end));
+ spin_unlock(&mm->page_table_lock);
+ flush_tlb_range(mm, beg, end);
+ return error;
+}
+
+/*
+ * maps a range of physical memory into the requested pages. the old
+ * mappings are removed. any references to nonexistent pages results
+ * in null mappings (currently treated as "copy-on-access")
+ */
+static inline void remap_pte_range(pte_t * pte, unsigned long address,
unsigned long size,
+ unsigned long phys_addr, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ do {
+ struct page *page;
+ pte_t oldpage;
+ oldpage = ptep_get_and_clear(pte);
+
+ page = virt_to_page(__va(phys_addr));
+ if ((!VALID_PAGE(page)) || PageReserved(page))
+ set_pte(pte, mk_pte_phys(phys_addr, prot));
+ forget_pte(oldpage);
+ address += PAGE_SIZE;
+ phys_addr += PAGE_SIZE;
+ pte++;
+ } while (address && (address < end));
+}
+
+static inline int remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned
long address, unsigned long size,
+ unsigned long phys_addr, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ phys_addr -= address;
+ do {
+ pte_t * pte = pte_alloc(mm, pmd, address);
+ if (!pte)
+ return -ENOMEM;
+ remap_pte_range(pte, address, end - address, address +
phys_addr, prot);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+ return 0;
+}
+
+/* Note: this is only safe if the mm semaphore is held when called. */
+int remap_page_range(unsigned long from, unsigned long phys_addr, unsigned
long size, pgprot_t prot)
+{
+ int error = 0;
+ pgd_t * dir;
+ unsigned long beg = from;
+ unsigned long end = from + size;
+ struct mm_struct *mm = current->mm;
+
+ phys_addr -= from;
+ dir = pgd_offset(mm, from);
+ flush_cache_range(mm, beg, end);
+ if (from >= end)
+ BUG();
+
+ spin_lock(&mm->page_table_lock);
+ do {
+ pmd_t *pmd = pmd_alloc(mm, dir, from);
+ error = -ENOMEM;
+ if (!pmd)
+ break;
+ error = remap_pmd_range(mm, pmd, from, end - from, phys_addr +
from, prot);
+ if (error)
+ break;
+ from = (from + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+ } while (from && (from < end));
+ spin_unlock(&mm->page_table_lock);
+ flush_tlb_range(mm, beg, end);
+ return error;
+}
+
+/*
+ * Establish a new mapping:
+ * - flush the old one
+ * - update the page tables
+ * - inform the TLB about the new one
+ *
+ * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock
+ */
+static inline void establish_pte(struct vm_area_struct * vma, unsigned long
address, pte_t *page_table, pte_t entry)
+{
+#ifdef CONFIG_XEN
+ if ( likely(vma->vm_mm == current->mm) ) {
+ HYPERVISOR_update_va_mapping(address, entry,
UVMF_INVLPG|UVMF_LOCAL);
+ } else {
+ set_pte(page_table, entry);
+ flush_tlb_page(vma, address);
+ }
+#else
+ set_pte(page_table, entry);
+ flush_tlb_page(vma, address);
+#endif
+ update_mmu_cache(vma, address, entry);
+}
+
+/*
+ * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock
+ */
+static inline void break_cow(struct vm_area_struct * vma, struct page *
new_page, unsigned long address,
+ pte_t *page_table)
+{
+ flush_page_to_ram(new_page);
+ flush_cache_page(vma, address);
+ establish_pte(vma, address, page_table,
pte_mkwrite(pte_mkdirty(mk_pte(new_page, vma->vm_page_prot))));
+}
+
+/*
+ * This routine handles present pages, when users try to write
+ * to a shared page. It is done by copying the page to a new address
+ * and decrementing the shared-page counter for the old page.
+ *
+ * Goto-purists beware: the only reason for goto's here is that it results
+ * in better assembly code.. The "default" path will see no jumps at all.
+ *
+ * Note that this routine assumes that the protection checks have been
+ * done by the caller (the low-level page fault routine in most cases).
+ * Thus we can safely just mark it writable once we've done any necessary
+ * COW.
+ *
+ * We also mark the page dirty at this point even though the page will
+ * change only once the write actually happens. This avoids a few races,
+ * and potentially makes it more efficient.
+ *
+ * We hold the mm semaphore and the page_table_lock on entry and exit
+ * with the page_table_lock released.
+ */
+static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
+ unsigned long address, pte_t *page_table, pte_t pte)
+{
+ struct page *old_page, *new_page;
+
+ old_page = pte_page(pte);
+ if (!VALID_PAGE(old_page))
+ goto bad_wp_page;
+
+ if (!TryLockPage(old_page)) {
+ int reuse = can_share_swap_page(old_page);
+ unlock_page(old_page);
+ if (reuse) {
+ flush_cache_page(vma, address);
+ establish_pte(vma, address, page_table,
pte_mkyoung(pte_mkdirty(pte_mkwrite(pte))));
+ spin_unlock(&mm->page_table_lock);
+ return 1; /* Minor fault */
+ }
+ }
+
+ /*
+ * Ok, we need to copy. Oh, well..
+ */
+ page_cache_get(old_page);
+ spin_unlock(&mm->page_table_lock);
+
+ new_page = alloc_page(GFP_HIGHUSER);
+ if (!new_page)
+ goto no_mem;
+ copy_cow_page(old_page,new_page,address);
+
+ /*
+ * Re-check the pte - we dropped the lock
+ */
+ spin_lock(&mm->page_table_lock);
+ if (pte_same(*page_table, pte)) {
+ if (PageReserved(old_page))
+ ++mm->rss;
+ break_cow(vma, new_page, address, page_table);
+ if (vm_anon_lru)
+ lru_cache_add(new_page);
+
+ /* Free the old page.. */
+ new_page = old_page;
+ }
+ spin_unlock(&mm->page_table_lock);
+ page_cache_release(new_page);
+ page_cache_release(old_page);
+ return 1; /* Minor fault */
+
+bad_wp_page:
+ spin_unlock(&mm->page_table_lock);
+ printk("do_wp_page: bogus page at address %08lx (page
0x%lx)\n",address,(unsigned long)old_page);
+ return -1;
+no_mem:
+ page_cache_release(old_page);
+ return -1;
+}
+
+static void vmtruncate_list(struct vm_area_struct *mpnt, unsigned long pgoff)
+{
+ do {
+ struct mm_struct *mm = mpnt->vm_mm;
+ unsigned long start = mpnt->vm_start;
+ unsigned long end = mpnt->vm_end;
+ unsigned long len = end - start;
+ unsigned long diff;
+
+ /* mapping wholly truncated? */
+ if (mpnt->vm_pgoff >= pgoff) {
+ zap_page_range(mm, start, len);
+ continue;
+ }
+
+ /* mapping wholly unaffected? */
+ len = len >> PAGE_SHIFT;
+ diff = pgoff - mpnt->vm_pgoff;
+ if (diff >= len)
+ continue;
+
+ /* Ok, partially affected.. */
+ start += diff << PAGE_SHIFT;
+ len = (len - diff) << PAGE_SHIFT;
+ zap_page_range(mm, start, len);
+ } while ((mpnt = mpnt->vm_next_share) != NULL);
+}
+
+/*
+ * Handle all mappings that got truncated by a "truncate()"
+ * system call.
+ *
+ * NOTE! We have to be ready to update the memory sharing
+ * between the file and the memory map for a potential last
+ * incomplete page. Ugly, but necessary.
+ */
+int vmtruncate(struct inode * inode, loff_t offset)
+{
+ unsigned long pgoff;
+ struct address_space *mapping = inode->i_mapping;
+ unsigned long limit;
+
+ if (inode->i_size < offset)
+ goto do_expand;
+ inode->i_size = offset;
+ spin_lock(&mapping->i_shared_lock);
+ if (!mapping->i_mmap && !mapping->i_mmap_shared)
+ goto out_unlock;
+
+ pgoff = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ if (mapping->i_mmap != NULL)
+ vmtruncate_list(mapping->i_mmap, pgoff);
+ if (mapping->i_mmap_shared != NULL)
+ vmtruncate_list(mapping->i_mmap_shared, pgoff);
+
+out_unlock:
+ spin_unlock(&mapping->i_shared_lock);
+ truncate_inode_pages(mapping, offset);
+ goto out_truncate;
+
+do_expand:
+ limit = current->rlim[RLIMIT_FSIZE].rlim_cur;
+ if (limit != RLIM_INFINITY && offset > limit)
+ goto out_sig;
+ if (offset > inode->i_sb->s_maxbytes)
+ goto out;
+ inode->i_size = offset;
+
+out_truncate:
+ if (inode->i_op && inode->i_op->truncate) {
+ lock_kernel();
+ inode->i_op->truncate(inode);
+ unlock_kernel();
+ }
+ return 0;
+out_sig:
+ send_sig(SIGXFSZ, current, 0);
+out:
+ return -EFBIG;
+}
+
+/*
+ * Primitive swap readahead code. We simply read an aligned block of
+ * (1 << page_cluster) entries in the swap area. This method is chosen
+ * because it doesn't cost us any seek time. We also make sure to queue
+ * the 'original' request together with the readahead ones...
+ */
+void swapin_readahead(swp_entry_t entry)
+{
+ int i, num;
+ struct page *new_page;
+ unsigned long offset;
+
+ /*
+ * Get the number of handles we should do readahead io to.
+ */
+ num = valid_swaphandles(entry, &offset);
+ for (i = 0; i < num; offset++, i++) {
+ /* Ok, do the async read-ahead now */
+ new_page = read_swap_cache_async(SWP_ENTRY(SWP_TYPE(entry),
offset));
+ if (!new_page)
+ break;
+ page_cache_release(new_page);
+ }
+ return;
+}
+
+/*
+ * We hold the mm semaphore and the page_table_lock on entry and
+ * should release the pagetable lock on exit..
+ */
+static int do_swap_page(struct mm_struct * mm,
+ struct vm_area_struct * vma, unsigned long address,
+ pte_t * page_table, pte_t orig_pte, int write_access)
+{
+ struct page *page;
+ swp_entry_t entry = pte_to_swp_entry(orig_pte);
+ pte_t pte;
+ int ret = 1;
+
+ spin_unlock(&mm->page_table_lock);
+ page = lookup_swap_cache(entry);
+ if (!page) {
+ swapin_readahead(entry);
+ page = read_swap_cache_async(entry);
+ if (!page) {
+ /*
+ * Back out if somebody else faulted in this pte while
+ * we released the page table lock.
+ */
+ int retval;
+ spin_lock(&mm->page_table_lock);
+ retval = pte_same(*page_table, orig_pte) ? -1 : 1;
+ spin_unlock(&mm->page_table_lock);
+ return retval;
+ }
+
+ /* Had to read the page from swap area: Major fault */
+ ret = 2;
+ }
+
+ mark_page_accessed(page);
+
+ lock_page(page);
+
+ /*
+ * Back out if somebody else faulted in this pte while we
+ * released the page table lock.
+ */
+ spin_lock(&mm->page_table_lock);
+ if (!pte_same(*page_table, orig_pte)) {
+ spin_unlock(&mm->page_table_lock);
+ unlock_page(page);
+ page_cache_release(page);
+ return 1;
+ }
+
+ /* The page isn't present yet, go ahead with the fault. */
+
+ swap_free(entry);
+ if (vm_swap_full())
+ remove_exclusive_swap_page(page);
+
+ mm->rss++;
+ pte = mk_pte(page, vma->vm_page_prot);
+ if (write_access && can_share_swap_page(page))
+ pte = pte_mkdirty(pte_mkwrite(pte));
+ unlock_page(page);
+
+ flush_page_to_ram(page);
+ flush_icache_page(vma, page);
+#ifdef CONFIG_XEN
+ if ( likely(vma->vm_mm == current->mm) )
+ HYPERVISOR_update_va_mapping(address, pte, 0);
+ else
+ set_pte(page_table, pte);
+#else
+ set_pte(page_table, pte);
+#endif
+
+ /* No need to invalidate - it was non-present before */
+ update_mmu_cache(vma, address, pte);
+ spin_unlock(&mm->page_table_lock);
+ return ret;
+}
+
+/*
+ * We are called with the MM semaphore and page_table_lock
+ * spinlock held to protect against concurrent faults in
+ * multithreaded programs.
+ */
+static int do_anonymous_page(struct mm_struct * mm, struct vm_area_struct *
vma, pte_t *page_table, int write_access, unsigned long addr)
+{
+ pte_t entry;
+
+ /* Read-only mapping of ZERO_PAGE. */
+ entry = pte_wrprotect(mk_pte(ZERO_PAGE(addr), vma->vm_page_prot));
+
+ /* ..except if it's a write access */
+ if (write_access) {
+ struct page *page;
+
+ /* Allocate our own private page. */
+ spin_unlock(&mm->page_table_lock);
+
+ page = alloc_page(GFP_HIGHUSER);
+ if (!page)
+ goto no_mem;
+ clear_user_highpage(page, addr);
+
+ spin_lock(&mm->page_table_lock);
+ if (!pte_none(*page_table)) {
+ page_cache_release(page);
+ spin_unlock(&mm->page_table_lock);
+ return 1;
+ }
+ mm->rss++;
+ flush_page_to_ram(page);
+ entry = pte_mkwrite(pte_mkdirty(mk_pte(page,
vma->vm_page_prot)));
+ if (vm_anon_lru)
+ lru_cache_add(page);
+ mark_page_accessed(page);
+ }
+
+#ifdef CONFIG_XEN
+ if ( likely(vma->vm_mm == current->mm) )
+ HYPERVISOR_update_va_mapping(addr, entry, 0);
+ else
+ set_pte(page_table, entry);
+#else
+ set_pte(page_table, entry);
+#endif
+
+ /* No need to invalidate - it was non-present before */
+ update_mmu_cache(vma, addr, entry);
+ spin_unlock(&mm->page_table_lock);
+ return 1; /* Minor fault */
+
+no_mem:
+ return -1;
+}
+
+/*
+ * do_no_page() tries to create a new page mapping. It aggressively
+ * tries to share with existing pages, but makes a separate copy if
+ * the "write_access" parameter is true in order to avoid the next
+ * page fault.
+ *
+ * As this is called only for pages that do not currently exist, we
+ * do not need to flush old virtual caches or the TLB.
+ *
+ * This is called with the MM semaphore held and the page table
+ * spinlock held. Exit with the spinlock released.
+ */
+static int do_no_page(struct mm_struct * mm, struct vm_area_struct * vma,
+ unsigned long address, int write_access, pte_t *page_table)
+{
+ struct page * new_page;
+ pte_t entry;
+
+ if (!vma->vm_ops || !vma->vm_ops->nopage)
+ return do_anonymous_page(mm, vma, page_table, write_access,
address);
+ spin_unlock(&mm->page_table_lock);
+
+ new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, 0);
+
+ if (new_page == NULL) /* no page was available -- SIGBUS */
+ return 0;
+ if (new_page == NOPAGE_OOM)
+ return -1;
+
+ /*
+ * Should we do an early C-O-W break?
+ */
+ if (write_access && !(vma->vm_flags & VM_SHARED)) {
+ struct page * page = alloc_page(GFP_HIGHUSER);
+ if (!page) {
+ page_cache_release(new_page);
+ return -1;
+ }
+ copy_user_highpage(page, new_page, address);
+ page_cache_release(new_page);
+ if (vm_anon_lru)
+ lru_cache_add(page);
+ new_page = page;
+ }
+
+ spin_lock(&mm->page_table_lock);
+ /*
+ * This silly early PAGE_DIRTY setting removes a race
+ * due to the bad i386 page protection. But it's valid
+ * for other architectures too.
+ *
+ * Note that if write_access is true, we either now have
+ * an exclusive copy of the page, or this is a shared mapping,
+ * so we can make it writable and dirty to avoid having to
+ * handle that later.
+ */
+ /* Only go through if we didn't race with anybody else... */
+ if (pte_none(*page_table)) {
+ if (!PageReserved(new_page))
+ ++mm->rss;
+ flush_page_to_ram(new_page);
+ flush_icache_page(vma, new_page);
+ entry = mk_pte(new_page, vma->vm_page_prot);
+ if (write_access)
+ entry = pte_mkwrite(pte_mkdirty(entry));
+#ifdef CONFIG_XEN
+ if ( likely(vma->vm_mm == current->mm) )
+ HYPERVISOR_update_va_mapping(address, entry, 0);
+ else
+ set_pte(page_table, entry);
+#else
+ set_pte(page_table, entry);
+#endif
+ } else {
+ /* One of our sibling threads was faster, back out. */
+ page_cache_release(new_page);
+ spin_unlock(&mm->page_table_lock);
+ return 1;
+ }
+
+ /* no need to invalidate: a not-present page shouldn't be cached */
+ update_mmu_cache(vma, address, entry);
+ spin_unlock(&mm->page_table_lock);
+ return 2; /* Major fault */
+}
+
+/*
+ * These routines also need to handle stuff like marking pages dirty
+ * and/or accessed for architectures that don't do it in hardware (most
+ * RISC architectures). The early dirtying is also good on the i386.
+ *
+ * There is also a hook called "update_mmu_cache()" that architectures
+ * with external mmu caches can use to update those (ie the Sparc or
+ * PowerPC hashed page tables that act as extended TLBs).
+ *
+ * Note the "page_table_lock". It is to protect against kswapd removing
+ * pages from under us. Note that kswapd only ever _removes_ pages, never
+ * adds them. As such, once we have noticed that the page is not present,
+ * we can drop the lock early.
+ *
+ * The adding of pages is protected by the MM semaphore (which we hold),
+ * so we don't need to worry about a page being suddenly been added into
+ * our VM.
+ *
+ * We enter with the pagetable spinlock held, we are supposed to
+ * release it when done.
+ */
+static inline int handle_pte_fault(struct mm_struct *mm,
+ struct vm_area_struct * vma, unsigned long address,
+ int write_access, pte_t * pte)
+{
+ pte_t entry;
+
+ entry = *pte;
+ if (!pte_present(entry)) {
+ /*
+ * If it truly wasn't present, we know that kswapd
+ * and the PTE updates will not touch it later. So
+ * drop the lock.
+ */
+ if (pte_none(entry))
+ return do_no_page(mm, vma, address, write_access, pte);
+ return do_swap_page(mm, vma, address, pte, entry, write_access);
+ }
+
+ if (write_access) {
+ if (!pte_write(entry))
+ return do_wp_page(mm, vma, address, pte, entry);
+
+ entry = pte_mkdirty(entry);
+ }
+ entry = pte_mkyoung(entry);
+ establish_pte(vma, address, pte, entry);
+ spin_unlock(&mm->page_table_lock);
+ return 1;
+}
+
+/*
+ * By the time we get here, we already hold the mm semaphore
+ */
+int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
+ unsigned long address, int write_access)
+{
+ pgd_t *pgd;
+ pmd_t *pmd;
+
+ current->state = TASK_RUNNING;
+ pgd = pgd_offset(mm, address);
+
+ /*
+ * We need the page table lock to synchronize with kswapd
+ * and the SMP-safe atomic PTE updates.
+ */
+ spin_lock(&mm->page_table_lock);
+ pmd = pmd_alloc(mm, pgd, address);
+
+ if (pmd) {
+ pte_t * pte = pte_alloc(mm, pmd, address);
+ if (pte)
+ return handle_pte_fault(mm, vma, address, write_access,
pte);
+ }
+ spin_unlock(&mm->page_table_lock);
+ return -1;
+}
+
+/*
+ * Allocate page middle directory.
+ *
+ * We've already handled the fast-path in-line, and we own the
+ * page table lock.
+ *
+ * On a two-level page table, this ends up actually being entirely
+ * optimized away.
+ */
+pmd_t fastcall *__pmd_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long
address)
+{
+ pmd_t *new;
+
+ /* "fast" allocation can happen without dropping the lock.. */
+ new = pmd_alloc_one_fast(mm, address);
+ if (!new) {
+ spin_unlock(&mm->page_table_lock);
+ new = pmd_alloc_one(mm, address);
+ spin_lock(&mm->page_table_lock);
+ if (!new)
+ return NULL;
+
+ /*
+ * Because we dropped the lock, we should re-check the
+ * entry, as somebody else could have populated it..
+ */
+ if (!pgd_none(*pgd)) {
+ pmd_free(new);
+ check_pgt_cache();
+ goto out;
+ }
+ }
+ pgd_populate(mm, pgd, new);
+out:
+ return pmd_offset(pgd, address);
+}
+
+/*
+ * Allocate the page table directory.
+ *
+ * We've already handled the fast-path in-line, and we own the
+ * page table lock.
+ */
+pte_t fastcall *pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long
address)
+{
+ if (pmd_none(*pmd)) {
+ pte_t *new;
+
+ /* "fast" allocation can happen without dropping the lock.. */
+ new = pte_alloc_one_fast(mm, address);
+ if (!new) {
+ spin_unlock(&mm->page_table_lock);
+ new = pte_alloc_one(mm, address);
+ spin_lock(&mm->page_table_lock);
+ if (!new)
+ return NULL;
+
+ /*
+ * Because we dropped the lock, we should re-check the
+ * entry, as somebody else could have populated it..
+ */
+ if (!pmd_none(*pmd)) {
+ pte_free(new);
+ check_pgt_cache();
+ goto out;
+ }
+ }
+ pmd_populate(mm, pmd, new);
+ }
+out:
+ return pte_offset(pmd, address);
+}
+
+int make_pages_present(unsigned long addr, unsigned long end)
+{
+ int ret, len, write;
+ struct vm_area_struct * vma;
+
+ vma = find_vma(current->mm, addr);
+ write = (vma->vm_flags & VM_WRITE) != 0;
+ if (addr >= end)
+ BUG();
+ if (end > vma->vm_end)
+ BUG();
+ len = (end+PAGE_SIZE-1)/PAGE_SIZE-addr/PAGE_SIZE;
+ ret = get_user_pages(current, current->mm, addr,
+ len, write, 0, NULL, NULL);
+ return ret == len ? 0 : -1;
+}
+
+struct page * vmalloc_to_page(void * vmalloc_addr)
+{
+ unsigned long addr = (unsigned long) vmalloc_addr;
+ struct page *page = NULL;
+ pmd_t *pmd;
+ pte_t *pte;
+ pgd_t *pgd;
+
+ pgd = pgd_offset_k(addr);
+ if (!pgd_none(*pgd)) {
+ pmd = pmd_offset(pgd, addr);
+ if (!pmd_none(*pmd)) {
+ pte = pte_offset(pmd, addr);
+ if (pte_present(*pte)) {
+ page = pte_page(*pte);
+ }
+ }
+ }
+ return page;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/segment.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/segment.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,96 @@
+#ifndef _ASM_SEGMENT_H
+#define _ASM_SEGMENT_H
+
+/*
+ * The layout of the per-CPU GDT under Linux:
+ *
+ * 0 - null
+ * 1 - reserved
+ * 2 - reserved
+ * 3 - reserved
+ *
+ * 4 - unused <==== new cacheline
+ * 5 - unused
+ *
+ * ------- start of TLS (Thread-Local Storage) segments:
+ *
+ * 6 - TLS segment #1 [ glibc's TLS segment ]
+ * 7 - TLS segment #2 [ Wine's %fs Win32 segment ]
+ * 8 - TLS segment #3
+ * 9 - reserved
+ * 10 - reserved
+ * 11 - reserved
+ *
+ * ------- start of kernel segments:
+ *
+ * 12 - kernel code segment <==== new cacheline
+ * 13 - kernel data segment
+ * 14 - default user CS
+ * 15 - default user DS
+ * 16 - TSS
+ * 17 - LDT
+ * 18 - PNPBIOS support (16->32 gate)
+ * 19 - PNPBIOS support
+ * 20 - PNPBIOS support
+ * 21 - PNPBIOS support
+ * 22 - PNPBIOS support
+ * 23 - APM BIOS support
+ * 24 - APM BIOS support
+ * 25 - APM BIOS support
+ *
+ * 26 - unused
+ * 27 - unused
+ * 28 - unused
+ * 29 - unused
+ * 30 - unused
+ * 31 - TSS for double fault handler
+ */
+#define GDT_ENTRY_TLS_ENTRIES 3
+#define GDT_ENTRY_TLS_MIN 6
+#define GDT_ENTRY_TLS_MAX (GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1)
+
+#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8)
+
+#define GDT_ENTRY_DEFAULT_USER_CS 14
+#define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS * 8 + 3)
+
+#define GDT_ENTRY_DEFAULT_USER_DS 15
+#define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS * 8 + 3)
+
+#define GDT_ENTRY_KERNEL_BASE 12
+
+#define GDT_ENTRY_KERNEL_CS (GDT_ENTRY_KERNEL_BASE + 0)
+#define __KERNEL_CS (GDT_ENTRY_KERNEL_CS * 8 + 1)
+
+#define GDT_ENTRY_KERNEL_DS (GDT_ENTRY_KERNEL_BASE + 1)
+#define __KERNEL_DS (GDT_ENTRY_KERNEL_DS * 8 + 1)
+
+#define GDT_ENTRY_TSS (GDT_ENTRY_KERNEL_BASE + 4)
+#define GDT_ENTRY_LDT (GDT_ENTRY_KERNEL_BASE + 5)
+
+#define GDT_ENTRY_PNPBIOS_BASE (GDT_ENTRY_KERNEL_BASE + 6)
+#define GDT_ENTRY_APMBIOS_BASE (GDT_ENTRY_KERNEL_BASE + 11)
+
+#define GDT_ENTRY_DOUBLEFAULT_TSS 31
+
+/*
+ * The GDT has 32 entries
+ */
+#define GDT_ENTRIES 32
+
+#define GDT_SIZE (GDT_ENTRIES * 8)
+
+/* Simple and small GDT entries for booting only */
+
+#define __BOOT_CS FLAT_KERNEL_CS
+
+#define __BOOT_DS FLAT_KERNEL_DS
+
+/*
+ * The interrupt descriptor table has room for 256 idt's,
+ * the global descriptor table is dependent on the number
+ * of tasks we can have..
+ */
+#define IDT_ENTRIES 256
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/io.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/io.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,425 @@
+#ifndef _ASM_IO_H
+#define _ASM_IO_H
+
+#include <linux/config.h>
+#include <linux/string.h>
+#include <linux/compiler.h>
+
+/*
+ * This file contains the definitions for the x86 IO instructions
+ * inb/inw/inl/outb/outw/outl and the "string versions" of the same
+ * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
+ * versions of the single-IO instructions (inb_p/inw_p/..).
+ *
+ * This file is not meant to be obfuscating: it's just complicated
+ * to (a) handle it all in a way that makes gcc able to optimize it
+ * as well as possible and (b) trying to avoid writing the same thing
+ * over and over again with slight variations and possibly making a
+ * mistake somewhere.
+ */
+
+/*
+ * Thanks to James van Artsdalen for a better timing-fix than
+ * the two short jumps: using outb's to a nonexistent port seems
+ * to guarantee better timings even on fast machines.
+ *
+ * On the other hand, I'd like to be sure of a non-existent port:
+ * I feel a bit unsafe about using 0x80 (should be safe, though)
+ *
+ * Linus
+ */
+
+ /*
+ * Bit simplified and optimized by Jan Hubicka
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
+ *
+ * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
+ * isa_read[wl] and isa_write[wl] fixed
+ * - Arnaldo Carvalho de Melo <acme@xxxxxxxxxxxxxxxx>
+ */
+
+#define IO_SPACE_LIMIT 0xffff
+
+#define XQUAD_PORTIO_BASE 0xfe400000
+#define XQUAD_PORTIO_QUAD 0x40000 /* 256k per quad. */
+
+#ifdef __KERNEL__
+
+#include <asm-generic/iomap.h>
+
+#include <linux/vmalloc.h>
+#include <asm/fixmap.h>
+
+/**
+ * virt_to_phys - map virtual addresses to physical
+ * @address: address to remap
+ *
+ * The returned physical address is the physical (CPU) mapping for
+ * the memory address given. It is only valid to use this function on
+ * addresses directly mapped or allocated via kmalloc.
+ *
+ * This function does not give bus mappings for DMA transfers. In
+ * almost all conceivable cases a device driver should not be using
+ * this function
+ */
+
+static inline unsigned long virt_to_phys(volatile void * address)
+{
+ return __pa(address);
+}
+
+/**
+ * phys_to_virt - map physical address to virtual
+ * @address: address to remap
+ *
+ * The returned virtual address is a current CPU mapping for
+ * the memory address given. It is only valid to use this function on
+ * addresses that have a kernel mapping
+ *
+ * This function does not handle bus mappings for DMA transfers. In
+ * almost all conceivable cases a device driver should not be using
+ * this function
+ */
+
+static inline void * phys_to_virt(unsigned long address)
+{
+ return __va(address);
+}
+
+/*
+ * Change "struct page" to physical address.
+ */
+#define page_to_pseudophys(page) ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
+#define page_to_phys(page) (phys_to_machine(page_to_pseudophys(page)))
+
+#define bio_to_pseudophys(bio) (page_to_pseudophys(bio_page((bio))) + \
+ (unsigned long) bio_offset((bio)))
+#define bvec_to_pseudophys(bv) (page_to_pseudophys((bv)->bv_page) + \
+ (unsigned long) (bv)->bv_offset)
+
+#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \
+ (((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) && \
+ ((bvec_to_pseudophys((vec1)) + (vec1)->bv_len) == \
+ bvec_to_pseudophys((vec2))))
+
+extern void __iomem * __ioremap(unsigned long offset, unsigned long size,
unsigned long flags);
+
+/**
+ * ioremap - map bus memory into CPU space
+ * @offset: bus address of the memory
+ * @size: size of the resource to map
+ *
+ * ioremap performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ */
+
+static inline void __iomem * ioremap(unsigned long offset, unsigned long size)
+{
+ return __ioremap(offset, size, 0);
+}
+
+extern void __iomem * ioremap_nocache(unsigned long offset, unsigned long
size);
+extern void iounmap(volatile void __iomem *addr);
+
+/*
+ * bt_ioremap() and bt_iounmap() are for temporary early boot-time
+ * mappings, before the real ioremap() is functional.
+ * A boot-time mapping is currently limited to at most 16 pages.
+ */
+extern void *bt_ioremap(unsigned long offset, unsigned long size);
+extern void bt_iounmap(void *addr, unsigned long size);
+
+/*
+ * ISA I/O bus memory addresses are 1:1 with the physical address.
+ */
+#define isa_virt_to_bus(_x) isa_virt_to_bus_is_UNSUPPORTED->x
+#define isa_page_to_bus(_x) isa_page_to_bus_is_UNSUPPORTED->x
+#ifdef CONFIG_XEN_PHYSDEV_ACCESS
+#define isa_bus_to_virt(_x) (void *)(__fix_to_virt(FIX_ISAMAP_BEGIN) + (_x))
+#else
+#define isa_bus_to_virt(_x) isa_bus_to_virt_needs_PRIVILEGED_BUILD
+#endif
+
+/*
+ * However PCI ones are not necessarily 1:1 and therefore these interfaces
+ * are forbidden in portable PCI drivers.
+ *
+ * Allow them on x86 for legacy drivers, though.
+ */
+#define virt_to_bus(_x) phys_to_machine(__pa(_x))
+#define bus_to_virt(_x) __va(machine_to_phys(_x))
+
+/*
+ * readX/writeX() are used to access memory mapped devices. On some
+ * architectures the memory mapped IO stuff needs to be accessed
+ * differently. On the x86 architecture, we just read/write the
+ * memory location directly.
+ */
+
+static inline unsigned char readb(const volatile void __iomem *addr)
+{
+ return *(volatile unsigned char __force *) addr;
+}
+static inline unsigned short readw(const volatile void __iomem *addr)
+{
+ return *(volatile unsigned short __force *) addr;
+}
+static inline unsigned int readl(const volatile void __iomem *addr)
+{
+ return *(volatile unsigned int __force *) addr;
+}
+#define readb_relaxed(addr) readb(addr)
+#define readw_relaxed(addr) readw(addr)
+#define readl_relaxed(addr) readl(addr)
+#define __raw_readb readb
+#define __raw_readw readw
+#define __raw_readl readl
+
+static inline void writeb(unsigned char b, volatile void __iomem *addr)
+{
+ *(volatile unsigned char __force *) addr = b;
+}
+static inline void writew(unsigned short b, volatile void __iomem *addr)
+{
+ *(volatile unsigned short __force *) addr = b;
+}
+static inline void writel(unsigned int b, volatile void __iomem *addr)
+{
+ *(volatile unsigned int __force *) addr = b;
+}
+#define __raw_writeb writeb
+#define __raw_writew writew
+#define __raw_writel writel
+
+#define mmiowb()
+
+static inline void memset_io(volatile void __iomem *addr, unsigned char val,
int count)
+{
+ memset((void __force *) addr, val, count);
+}
+static inline void memcpy_fromio(void *dst, const volatile void __iomem *src,
int count)
+{
+ __memcpy(dst, (void __force *) src, count);
+}
+static inline void memcpy_toio(volatile void __iomem *dst, const void *src,
int count)
+{
+ __memcpy((void __force *) dst, src, count);
+}
+
+/*
+ * ISA space is 'always mapped' on a typical x86 system, no need to
+ * explicitly ioremap() it. The fact that the ISA IO space is mapped
+ * to PAGE_OFFSET is pure coincidence - it does not mean ISA values
+ * are physical addresses. The following constant pointer can be
+ * used as the IO-area pointer (it can be iounmapped as well, so the
+ * analogy with PCI is quite large):
+ */
+#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
+
+#define isa_readb(a) readb(__ISA_IO_base + (a))
+#define isa_readw(a) readw(__ISA_IO_base + (a))
+#define isa_readl(a) readl(__ISA_IO_base + (a))
+#define isa_writeb(b,a) writeb(b,__ISA_IO_base + (a))
+#define isa_writew(w,a) writew(w,__ISA_IO_base + (a))
+#define isa_writel(l,a) writel(l,__ISA_IO_base + (a))
+#define isa_memset_io(a,b,c) memset_io(__ISA_IO_base + (a),(b),(c))
+#define isa_memcpy_fromio(a,b,c) memcpy_fromio((a),__ISA_IO_base +
(b),(c))
+#define isa_memcpy_toio(a,b,c) memcpy_toio(__ISA_IO_base + (a),(b),(c))
+
+
+/*
+ * Again, i386 does not require mem IO specific function.
+ */
+
+#define eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void
__force *)(b),(c),(d))
+#define isa_eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void
__force *)(__ISA_IO_base + (b)),(c),(d))
+
+/**
+ * check_signature - find BIOS signatures
+ * @io_addr: mmio address to check
+ * @signature: signature block
+ * @length: length of signature
+ *
+ * Perform a signature comparison with the mmio address io_addr. This
+ * address should have been obtained by ioremap.
+ * Returns 1 on a match.
+ */
+
+static inline int check_signature(volatile void __iomem * io_addr,
+ const unsigned char *signature, int length)
+{
+ int retval = 0;
+ do {
+ if (readb(io_addr) != *signature)
+ goto out;
+ io_addr++;
+ signature++;
+ length--;
+ } while (length);
+ retval = 1;
+out:
+ return retval;
+}
+
+/*
+ * Cache management
+ *
+ * This needed for two cases
+ * 1. Out of order aware processors
+ * 2. Accidentally out of order processors (PPro errata #51)
+ */
+
+#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+
+static inline void flush_write_buffers(void)
+{
+ __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory");
+}
+
+#define dma_cache_inv(_start,_size) flush_write_buffers()
+#define dma_cache_wback(_start,_size) flush_write_buffers()
+#define dma_cache_wback_inv(_start,_size) flush_write_buffers()
+
+#else
+
+/* Nothing to do */
+
+#define dma_cache_inv(_start,_size) do { } while (0)
+#define dma_cache_wback(_start,_size) do { } while (0)
+#define dma_cache_wback_inv(_start,_size) do { } while (0)
+#define flush_write_buffers()
+
+#endif
+
+#endif /* __KERNEL__ */
+
+#ifdef SLOW_IO_BY_JUMPING
+#define __SLOW_DOWN_IO "jmp 1f; 1: jmp 1f; 1:"
+#elif defined(__UNSAFE_IO__)
+#define __SLOW_DOWN_IO "outb %%al,$0x80;"
+#else
+#define __SLOW_DOWN_IO "\n1: outb %%al,$0x80\n" \
+ "2:\n" \
+ ".section __ex_table,\"a\"\n\t" \
+ ".align 4\n\t" \
+ ".long 1b,2b\n" \
+ ".previous"
+#endif
+
+static inline void slow_down_io(void) {
+ __asm__ __volatile__(
+ __SLOW_DOWN_IO
+#ifdef REALLY_SLOW_IO
+ __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO
+#endif
+ : : );
+}
+
+#ifdef CONFIG_X86_NUMAQ
+extern void *xquad_portio; /* Where the IO area was mapped */
+#define XQUAD_PORT_ADDR(port, quad) (xquad_portio + (XQUAD_PORTIO_QUAD*quad) +
port)
+#define __BUILDIO(bwl,bw,type) \
+static inline void out##bwl##_quad(unsigned type value, int port, int quad) { \
+ if (xquad_portio) \
+ write##bwl(value, XQUAD_PORT_ADDR(port, quad)); \
+ else \
+ out##bwl##_local(value, port); \
+} \
+static inline void out##bwl(unsigned type value, int port) { \
+ out##bwl##_quad(value, port, 0); \
+} \
+static inline unsigned type in##bwl##_quad(int port, int quad) { \
+ if (xquad_portio) \
+ return read##bwl(XQUAD_PORT_ADDR(port, quad)); \
+ else \
+ return in##bwl##_local(port); \
+} \
+static inline unsigned type in##bwl(int port) { \
+ return in##bwl##_quad(port, 0); \
+}
+#else
+#define __BUILDIO(bwl,bw,type) \
+static inline void out##bwl(unsigned type value, int port) { \
+ out##bwl##_local(value, port); \
+} \
+static inline unsigned type in##bwl(int port) { \
+ return in##bwl##_local(port); \
+}
+#endif
+
+
+#if __UNSAFE_IO__
+#define ____BUILDIO(bwl,bw,type) \
+static inline void out##bwl##_local(unsigned type value, int port) { \
+ __asm__ __volatile__("out" #bwl " %" #bw "0, %w1" : : "a"(value),
"Nd"(port)); \
+} \
+static inline unsigned type in##bwl##_local(int port) { \
+ unsigned type value; \
+ __asm__ __volatile__("in" #bwl " %w1, %" #bw "0" : "=a"(value) :
"Nd"(port)); \
+ return value; \
+}
+#else
+#define ____BUILDIO(bwl,bw,type) \
+static inline void out##bwl##_local(unsigned type value, int port) { \
+ __asm__ __volatile__("1: out" #bwl " %" #bw "0, %w1\n" \
+ "2:\n" \
+ ".section __ex_table,\"a\"\n\t" \
+ ".align 4\n\t" \
+ ".long 1b,2b\n" \
+ ".previous" : : "a"(value), "Nd"(port)); \
+} \
+static inline unsigned type in##bwl##_local(int port) { \
+ unsigned type value; \
+ __asm__ __volatile__("1:in" #bwl " %w1, %" #bw "0\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: mov" #bwl " $~0,%" #bw "0\n\t" \
+ "jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n\t" \
+ ".align 4\n\t" \
+ ".long 1b,3b\n" \
+ ".previous" : "=a"(value) : "Nd"(port)); \
+ return value; \
+}
+#endif
+
+#define BUILDIO(bwl,bw,type) \
+____BUILDIO(bwl,bw,type) \
+static inline void out##bwl##_local_p(unsigned type value, int port) { \
+ out##bwl##_local(value, port); \
+ slow_down_io(); \
+} \
+static inline unsigned type in##bwl##_local_p(int port) { \
+ unsigned type value = in##bwl##_local(port); \
+ slow_down_io(); \
+ return value; \
+} \
+__BUILDIO(bwl,bw,type) \
+static inline void out##bwl##_p(unsigned type value, int port) { \
+ out##bwl(value, port); \
+ slow_down_io(); \
+} \
+static inline unsigned type in##bwl##_p(int port) { \
+ unsigned type value = in##bwl(port); \
+ slow_down_io(); \
+ return value; \
+} \
+static inline void outs##bwl(int port, const void *addr, unsigned long count)
{ \
+ __asm__ __volatile__("rep; outs" #bwl : "+S"(addr), "+c"(count) :
"d"(port)); \
+} \
+static inline void ins##bwl(int port, void *addr, unsigned long count) { \
+ __asm__ __volatile__("rep; ins" #bwl : "+D"(addr), "+c"(count) :
"d"(port)); \
+}
+
+BUILDIO(b,b,char)
+BUILDIO(w,w,short)
+BUILDIO(l,,int)
+
+/* We will be supplying our own /dev/mem implementation */
+#define ARCH_HAS_DEV_MEM
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/setup64.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/setup64.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,344 @@
+/*
+ * X86-64 specific CPU setup.
+ * Copyright (C) 1995 Linus Torvalds
+ * Copyright 2001, 2002, 2003 SuSE Labs / Andi Kleen.
+ * See setup.c for older changelog.
+ * $Id: setup64.c,v 1.12 2002/03/21 10:09:17 ak Exp $
+ *
+ * Jun Nakajima <jun.nakajima@xxxxxxxxx>
+ * Modified for Xen
+ *
+ */
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/bootmem.h>
+#include <linux/bitops.h>
+#include <asm/pda.h>
+#include <asm/pgtable.h>
+#include <asm/processor.h>
+#include <asm/desc.h>
+#include <asm/atomic.h>
+#include <asm/mmu_context.h>
+#include <asm/smp.h>
+#include <asm/i387.h>
+#include <asm/percpu.h>
+#include <asm/mtrr.h>
+#include <asm/proto.h>
+#include <asm/mman.h>
+#include <asm/numa.h>
+
+#include <asm-xen/hypervisor.h>
+
+char x86_boot_params[2048] __initdata = {0,};
+
+cpumask_t cpu_initialized __initdata = CPU_MASK_NONE;
+
+struct x8664_pda cpu_pda[NR_CPUS] __cacheline_aligned;
+
+extern struct task_struct init_task;
+
+extern unsigned char __per_cpu_start[], __per_cpu_end[];
+
+extern struct desc_ptr cpu_gdt_descr[];
+struct desc_ptr idt_descr = { 256 * 16, (unsigned long) idt_table };
+
+char boot_cpu_stack[IRQSTACKSIZE]
__attribute__((section(".bss.page_aligned")));
+
+unsigned long __supported_pte_mask = ~0UL;
+static int do_not_nx __initdata = 0;
+
+/* noexec=on|off
+Control non executable mappings for 64bit processes.
+
+on Enable(default)
+off Disable
+*/
+int __init nonx_setup(char *str)
+{
+ if (!strncmp(str, "on", 2)) {
+ __supported_pte_mask |= _PAGE_NX;
+ do_not_nx = 0;
+ } else if (!strncmp(str, "off", 3)) {
+ do_not_nx = 1;
+ __supported_pte_mask &= ~_PAGE_NX;
+ }
+ return 0;
+}
+__setup("noexec=", nonx_setup); /* parsed early actually */
+
+int force_personality32 = READ_IMPLIES_EXEC;
+
+/* noexec32=on|off
+Control non executable heap for 32bit processes.
+To control the stack too use noexec=off
+
+on PROT_READ does not imply PROT_EXEC for 32bit processes
+off PROT_READ implies PROT_EXEC (default)
+*/
+static int __init nonx32_setup(char *str)
+{
+ if (!strcmp(str, "on"))
+ force_personality32 &= ~READ_IMPLIES_EXEC;
+ else if (!strcmp(str, "off"))
+ force_personality32 |= READ_IMPLIES_EXEC;
+ return 0;
+}
+__setup("noexec32=", nonx32_setup);
+
+/*
+ * Great future plan:
+ * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data.
+ * Always point %gs to its beginning
+ */
+void __init setup_per_cpu_areas(void)
+{
+ int i;
+ unsigned long size;
+
+ /* Copy section for each CPU (we discard the original) */
+ size = ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES);
+#ifdef CONFIG_MODULES
+ if (size < PERCPU_ENOUGH_ROOM)
+ size = PERCPU_ENOUGH_ROOM;
+#endif
+
+ for (i = 0; i < NR_CPUS; i++) {
+ unsigned char *ptr;
+
+ if (!NODE_DATA(cpu_to_node(i))) {
+ printk("cpu with no node %d, num_online_nodes %d\n",
+ i, num_online_nodes());
+ ptr = alloc_bootmem(size);
+ } else {
+ ptr = alloc_bootmem_node(NODE_DATA(cpu_to_node(i)),
size);
+ }
+ if (!ptr)
+ panic("Cannot allocate cpu data for CPU %d\n", i);
+ cpu_pda[i].data_offset = ptr - __per_cpu_start;
+ memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
+ }
+}
+
+void pda_init(int cpu)
+{
+ pgd_t *old_level4 = (pgd_t *)xen_start_info.pt_base;
+ struct x8664_pda *pda = &cpu_pda[cpu];
+
+ /* Setup up data that may be needed in __get_free_pages early */
+ asm volatile("movl %0,%%fs ; movl %0,%%gs" :: "r" (0));
+ HYPERVISOR_set_segment_base(SEGBASE_GS_KERNEL,
+ (unsigned long)(cpu_pda + cpu));
+
+ pda->me = pda;
+ pda->cpunumber = cpu;
+ pda->irqcount = -1;
+ pda->kernelstack =
+ (unsigned long)stack_thread_info() - PDA_STACKOFFSET +
THREAD_SIZE;
+ pda->active_mm = &init_mm;
+ pda->mmu_state = 0;
+ pda->kernel_mode = 1;
+
+ if (cpu == 0) {
+ memcpy((void *)init_level4_pgt,
+ (void *) xen_start_info.pt_base, PAGE_SIZE);
+ /* others are initialized in smpboot.c */
+ pda->pcurrent = &init_task;
+ pda->irqstackptr = boot_cpu_stack;
+ make_page_readonly(init_level4_pgt);
+ make_page_readonly(init_level4_user_pgt);
+ make_page_readonly(level3_user_pgt); /* for vsyscall stuff */
+ xen_pgd_pin(__pa_symbol(init_level4_user_pgt));
+ xen_pud_pin(__pa_symbol(level3_user_pgt));
+ set_pgd((pgd_t *)(init_level4_user_pgt + 511),
+ mk_kernel_pgd(__pa_symbol(level3_user_pgt)));
+ } else {
+ pda->irqstackptr = (char *)
+ __get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER);
+ if (!pda->irqstackptr)
+ panic("cannot allocate irqstack for cpu %d", cpu);
+ }
+
+ xen_pt_switch(__pa(init_level4_pgt));
+ xen_new_user_pt(__pa(init_level4_user_pgt));
+
+ if (cpu == 0) {
+ xen_pgd_unpin(__pa(old_level4));
+#if 0
+ early_printk("__pa: %x, <machine_phys> old_level 4 %x\n",
+ __pa(xen_start_info.pt_base),
+ pfn_to_mfn(__pa(old_level4) >> PAGE_SHIFT));
+#endif
+// make_page_writable(old_level4);
+// free_bootmem(__pa(old_level4), PAGE_SIZE);
+ }
+
+ pda->irqstackptr += IRQSTACKSIZE-64;
+}
+
+char boot_exception_stacks[N_EXCEPTION_STACKS * EXCEPTION_STKSZ]
+__attribute__((section(".bss.page_aligned")));
+
+/* May not be marked __init: used by software suspend */
+void syscall_init(void)
+{
+#ifdef CONFIG_IA32_EMULATION
+ syscall32_cpu_init ();
+#endif
+}
+
+void __init check_efer(void)
+{
+ unsigned long efer;
+
+ /* rdmsrl(MSR_EFER, efer); */
+
+ /*
+ * At this point, Xen does not like the bit 63.
+ * So NX is not supported. Come back later.
+ */
+ efer = 0;
+
+ if (!(efer & EFER_NX) || do_not_nx) {
+ __supported_pte_mask &= ~_PAGE_NX;
+ }
+}
+
+void __init cpu_gdt_init(struct desc_ptr *gdt_descr)
+{
+ unsigned long frames[16];
+ unsigned long va;
+ int f;
+
+ for (va = gdt_descr->address, f = 0;
+ va < gdt_descr->address + gdt_descr->size;
+ va += PAGE_SIZE, f++) {
+ frames[f] = virt_to_machine(va) >> PAGE_SHIFT;
+ make_page_readonly((void *)va);
+ }
+ if (HYPERVISOR_set_gdt(frames, gdt_descr->size /
+ sizeof (struct desc_struct)))
+ BUG();
+}
+
+
+/*
+ * cpu_init() initializes state that is per-CPU. Some data is already
+ * initialized (naturally) in the bootstrap process, such as the GDT
+ * and IDT. We reload them nevertheless, this function acts as a
+ * 'CPU state barrier', nothing should get across.
+ * A lot of state is already set up in PDA init.
+ */
+void __init cpu_init (void)
+{
+#ifdef CONFIG_SMP
+ int cpu = stack_smp_processor_id();
+#else
+ int cpu = smp_processor_id();
+#endif
+ struct tss_struct *t = &per_cpu(init_tss, cpu);
+ unsigned long v;
+ char *estacks = NULL;
+ struct task_struct *me;
+ int i;
+
+ /* CPU 0 is initialised in head64.c */
+ if (cpu != 0) {
+ pda_init(cpu);
+ } else
+ estacks = boot_exception_stacks;
+
+ me = current;
+
+ if (test_and_set_bit(cpu, &cpu_initialized))
+ panic("CPU#%d already initialized!\n", cpu);
+
+ printk("Initializing CPU#%d\n", cpu);
+
+#if 0
+ clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
+#endif
+ /*
+ * Initialize the per-CPU GDT with the boot GDT,
+ * and set up the GDT descriptor:
+ */
+ if (cpu) {
+ memcpy(cpu_gdt_table[cpu], cpu_gdt_table[0], GDT_SIZE);
+ }
+
+ cpu_gdt_descr[cpu].size = GDT_SIZE;
+ cpu_gdt_descr[cpu].address = (unsigned long)cpu_gdt_table[cpu];
+#if 0
+ asm volatile("lgdt %0" :: "m" (cpu_gdt_descr[cpu]));
+ asm volatile("lidt %0" :: "m" (idt_descr));
+#endif
+ cpu_gdt_init(&cpu_gdt_descr[cpu]);
+
+#if 0
+ memcpy(me->thread.tls_array, cpu_gdt_table[cpu], GDT_ENTRY_TLS_ENTRIES
* 8);
+
+#endif
+ memcpy(me->thread.tls_array, &get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN],
+ GDT_ENTRY_TLS_ENTRIES * 8);
+
+ /*
+ * Delete NT
+ */
+
+ asm volatile("pushfq ; popq %%rax ; btr $14,%%rax ; pushq %%rax ;
popfq" ::: "eax");
+
+ if (cpu == 0)
+ early_identify_cpu(&boot_cpu_data);
+
+ syscall_init();
+
+ barrier();
+ check_efer();
+
+ /*
+ * set up and load the per-CPU TSS
+ */
+ for (v = 0; v < N_EXCEPTION_STACKS; v++) {
+ if (cpu) {
+ estacks = (char *)__get_free_pages(GFP_ATOMIC,
+ EXCEPTION_STACK_ORDER);
+ if (!estacks)
+ panic("Cannot allocate exception stack %ld
%d\n",
+ v, cpu);
+ }
+ estacks += EXCEPTION_STKSZ;
+ t->ist[v] = (unsigned long)estacks;
+ }
+
+ t->io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+ /*
+ * <= is required because the CPU will access up to
+ * 8 bits beyond the end of the IO permission bitmap.
+ */
+ for (i = 0; i <= IO_BITMAP_LONGS; i++)
+ t->io_bitmap[i] = ~0UL;
+
+ atomic_inc(&init_mm.mm_count);
+ me->active_mm = &init_mm;
+ if (me->mm)
+ BUG();
+ enter_lazy_tlb(&init_mm, me);
+
+ load_LDT(&init_mm.context);
+
+ /*
+ * Clear all 6 debug registers:
+ */
+#define CD(register) HYPERVISOR_set_debugreg(register, 0)
+
+ CD(0); CD(1); CD(2); CD(3); /* no db4 and db5 */; CD(6); CD(7);
+
+#undef CD
+ fpu_init();
+
+#ifdef CONFIG_NUMA
+ numa_add_cpu(cpu);
+#endif
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/kernel/setup.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/kernel/setup.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,1213 @@
+/*
+ * linux/arch/i386/kernel/setup.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ */
+
+/*
+ * This file handles the architecture-dependent parts of initialization
+ */
+
+#define __KERNEL_SYSCALLS__
+static int errno;
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/a.out.h>
+#include <linux/tty.h>
+#include <linux/ioport.h>
+#include <linux/delay.h>
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/apm_bios.h>
+#ifdef CONFIG_BLK_DEV_RAM
+#include <linux/blk.h>
+#endif
+#include <linux/highmem.h>
+#include <linux/bootmem.h>
+#include <linux/seq_file.h>
+#include <linux/reboot.h>
+#include <asm/processor.h>
+#include <linux/console.h>
+#include <linux/module.h>
+#include <asm/mtrr.h>
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/msr.h>
+#include <asm/desc.h>
+#include <asm/dma.h>
+#include <asm/mpspec.h>
+#include <asm/mmu_context.h>
+#include <asm/ctrl_if.h>
+#include <asm/hypervisor.h>
+#include <asm-xen/xen-public/physdev.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/tqueue.h>
+#include <net/pkt_sched.h> /* dev_(de)activate */
+
+/*
+ * Point at the empty zero page to start with. We map the real shared_info
+ * page as soon as fixmap is up and running.
+ */
+shared_info_t *HYPERVISOR_shared_info = (shared_info_t *)empty_zero_page;
+
+unsigned int *phys_to_machine_mapping, *pfn_to_mfn_frame_list;
+
+/*
+ * Machine setup..
+ */
+
+char ignore_irq13; /* set if exception 16 works */
+struct cpuinfo_x86 boot_cpu_data = { 0, 0, 0, 0, -1, 1, 0, 0, -1 };
+
+unsigned long mmu_cr4_features;
+
+unsigned char * vgacon_mmap;
+
+/*
+ * Bus types ..
+ */
+#ifdef CONFIG_EISA
+int EISA_bus;
+#endif
+int MCA_bus;
+
+/* for MCA, but anyone else can use it if they want */
+unsigned int machine_id;
+unsigned int machine_submodel_id;
+unsigned int BIOS_revision;
+unsigned int mca_pentium_flag;
+
+/* For PCI or other memory-mapped resources */
+unsigned long pci_mem_start = 0x10000000;
+
+/*
+ * Setup options
+ */
+struct drive_info_struct { char dummy[32]; } drive_info;
+struct screen_info screen_info;
+struct apm_info apm_info;
+struct sys_desc_table_struct {
+ unsigned short length;
+ unsigned char table[0];
+};
+
+unsigned char aux_device_present;
+
+extern int root_mountflags;
+extern char _text, _etext, _edata, _end;
+
+extern int blk_nohighio;
+
+int enable_acpi_smp_table;
+
+/* Raw start-of-day parameters from the hypervisor. */
+union xen_start_info_union xen_start_info_union;
+
+#define COMMAND_LINE_SIZE MAX_GUEST_CMDLINE
+static char command_line[COMMAND_LINE_SIZE];
+char saved_command_line[COMMAND_LINE_SIZE];
+
+/* parse_mem_cmdline()
+ * returns the value of the mem= boot param converted to pages or 0
+ */
+static int __init parse_mem_cmdline (char ** cmdline_p)
+{
+ char c = ' ', *to = command_line, *from = saved_command_line;
+ int len = 0;
+ unsigned long long bytes;
+ int mem_param = 0;
+
+ /* Save unparsed command line copy for /proc/cmdline */
+ memcpy(saved_command_line, xen_start_info.cmd_line, COMMAND_LINE_SIZE);
+ saved_command_line[COMMAND_LINE_SIZE-1] = '\0';
+
+ for (;;) {
+ /*
+ * "mem=nopentium" disables the 4MB page tables.
+ * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM
+ * to <mem>, overriding the bios size.
+ * "mem=XXX[KkmM]@XXX[KkmM]" defines a memory region from
+ * <start> to <start>+<mem>, overriding the bios size.
+ */
+ if (c == ' ' && !memcmp(from, "mem=", 4)) {
+ if (to != command_line)
+ to--;
+ if (!memcmp(from+4, "nopentium", 9)) {
+ from += 9+4;
+ } else if (!memcmp(from+4, "exactmap", 8)) {
+ from += 8+4;
+ } else {
+ bytes = memparse(from+4, &from);
+ mem_param = bytes>>PAGE_SHIFT;
+ if (*from == '@')
+ (void)memparse(from+1, &from);
+ }
+ }
+
+ c = *(from++);
+ if (!c)
+ break;
+ if (COMMAND_LINE_SIZE <= ++len)
+ break;
+ *(to++) = c;
+ }
+ *to = '\0';
+ *cmdline_p = command_line;
+
+ return mem_param;
+}
+
+/*
+ * Every exception-fixup table is sorted (i.e., kernel main table, and every
+ * module table. Some elements may be out of order if they reference text.init,
+ * for example.
+ */
+static void sort_exception_table(struct exception_table_entry *start,
+ struct exception_table_entry *end)
+{
+ struct exception_table_entry *p, *q, tmp;
+
+ for ( p = start; p < end; p++ )
+ {
+ for ( q = p-1; q > start; q-- )
+ if ( p->insn > q->insn )
+ break;
+ if ( ++q != p )
+ {
+ tmp = *p;
+ memmove(q+1, q, (p-q)*sizeof(*p));
+ *q = tmp;
+ }
+ }
+}
+
+int xen_module_init(struct module *mod)
+{
+ sort_exception_table(mod->ex_table_start, mod->ex_table_end);
+ return 0;
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+ int i,j;
+ unsigned long bootmap_size, start_pfn, lmax_low_pfn;
+ int mem_param; /* user specified memory size in pages */
+ int boot_pfn; /* low pages available for bootmem */
+ physdev_op_t op;
+
+ extern void hypervisor_callback(void);
+ extern void failsafe_callback(void);
+
+ extern unsigned long cpu0_pte_quicklist[];
+ extern unsigned long cpu0_pgd_quicklist[];
+
+ extern const struct exception_table_entry __start___ex_table[];
+ extern const struct exception_table_entry __stop___ex_table[];
+
+ extern char _stext;
+
+ /* Force a quick death if the kernel panics. */
+ extern int panic_timeout;
+ if ( panic_timeout == 0 )
+ panic_timeout = 1;
+
+ /* Ensure that the kernel exception-fixup table is sorted. */
+ sort_exception_table(__start___ex_table, __stop___ex_table);
+
+#ifndef CONFIG_HIGHIO
+ blk_nohighio = 1;
+#endif
+
+ HYPERVISOR_vm_assist(
+ VMASST_CMD_enable, VMASST_TYPE_4gb_segments);
+ HYPERVISOR_vm_assist(
+ VMASST_CMD_enable, VMASST_TYPE_writable_pagetables);
+
+ HYPERVISOR_set_callbacks(
+ __KERNEL_CS, (unsigned long)hypervisor_callback,
+ __KERNEL_CS, (unsigned long)failsafe_callback);
+
+ boot_cpu_data.pgd_quick = cpu0_pgd_quicklist;
+ boot_cpu_data.pte_quick = cpu0_pte_quicklist;
+
+ /* This must be initialized to UNNAMED_MAJOR for ipconfig to work
+ properly. Setting ROOT_DEV to default to /dev/ram0 breaks initrd. */
+ ROOT_DEV = MKDEV(UNNAMED_MAJOR,0);
+ memset(&drive_info, 0, sizeof(drive_info));
+ memset(&screen_info, 0, sizeof(screen_info));
+
+ /* This is drawn from a dump from vgacon:startup in standard Linux. */
+ screen_info.orig_video_mode = 3;
+ screen_info.orig_video_isVGA = 1;
+ screen_info.orig_video_lines = 25;
+ screen_info.orig_video_cols = 80;
+ screen_info.orig_video_ega_bx = 3;
+ screen_info.orig_video_points = 16;
+
+ memset(&apm_info.bios, 0, sizeof(apm_info.bios));
+ aux_device_present = 0;
+#ifdef CONFIG_BLK_DEV_RAM
+ rd_image_start = 0;
+ rd_prompt = 0;
+ rd_doload = 0;
+#endif
+
+ root_mountflags &= ~MS_RDONLY;
+ init_mm.start_code = (unsigned long) &_text;
+ init_mm.end_code = (unsigned long) &_etext;
+ init_mm.end_data = (unsigned long) &_edata;
+ init_mm.brk = (unsigned long) &_end;
+
+ /* The mem= kernel command line param overrides the detected amount
+ * of memory. For xenolinux, if this override is larger than detected
+ * memory, then boot using only detected memory and make provisions to
+ * use all of the override value. The hypervisor can give this
+ * domain more memory later on and it will be added to the free
+ * lists at that time. See claim_new_pages() in
+ * arch/xen/drivers/balloon/balloon.c
+ */
+ mem_param = parse_mem_cmdline(cmdline_p);
+ if (mem_param < xen_start_info.nr_pages)
+ mem_param = xen_start_info.nr_pages;
+
+#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT)
+#define PFN_DOWN(x) ((x) >> PAGE_SHIFT)
+#define PFN_PHYS(x) ((x) << PAGE_SHIFT)
+
+/*
+ * 128MB for vmalloc(), iomap(), kmap(), and fixaddr mappings.
+ */
+#define VMALLOC_RESERVE (unsigned long)(128 << 20)
+#define MAXMEM (unsigned
long)(HYPERVISOR_VIRT_START-PAGE_OFFSET-VMALLOC_RESERVE)
+#define MAXMEM_PFN PFN_DOWN(MAXMEM)
+#define MAX_NONPAE_PFN (1 << 20)
+
+ /*
+ * Determine low and high memory ranges:
+ */
+ lmax_low_pfn = max_pfn = mem_param;
+ if (lmax_low_pfn > MAXMEM_PFN) {
+ lmax_low_pfn = MAXMEM_PFN;
+#ifndef CONFIG_HIGHMEM
+ /* Maximum memory usable is what is directly addressable */
+ printk(KERN_WARNING "Warning only %ldMB will be used.\n",
+ MAXMEM>>20);
+ if (max_pfn > MAX_NONPAE_PFN)
+ printk(KERN_WARNING "Use a PAE enabled kernel.\n");
+ else
+ printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
+ max_pfn = lmax_low_pfn;
+#else /* !CONFIG_HIGHMEM */
+#ifndef CONFIG_X86_PAE
+ if (max_pfn > MAX_NONPAE_PFN) {
+ max_pfn = MAX_NONPAE_PFN;
+ printk(KERN_WARNING "Warning only 4GB will be used.\n");
+ printk(KERN_WARNING "Use a PAE enabled kernel.\n");
+ }
+#endif /* !CONFIG_X86_PAE */
+#endif /* !CONFIG_HIGHMEM */
+ }
+
+#ifdef CONFIG_HIGHMEM
+ highstart_pfn = highend_pfn = max_pfn;
+ if (max_pfn > MAXMEM_PFN) {
+ highstart_pfn = MAXMEM_PFN;
+ printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
+ pages_to_mb(highend_pfn - highstart_pfn));
+ }
+#endif
+
+ phys_to_machine_mapping = (unsigned int *)xen_start_info.mfn_list;
+ cur_pgd = init_mm.pgd = (pgd_t *)xen_start_info.pt_base;
+
+ start_pfn = (__pa(xen_start_info.pt_base) >> PAGE_SHIFT) +
+ xen_start_info.nr_pt_frames;
+
+ /*
+ * Initialize the boot-time allocator, and free up all RAM. Then reserve
+ * space for OS image, initrd, phys->machine table, bootstrap page table,
+ * and the bootmem bitmap.
+ * NB. There is definitely enough room for the bootmem bitmap in the
+ * bootstrap page table. We are guaranteed to get >=512kB unused 'padding'
+ * for our own use after all bootstrap elements
+ * (see asm-xen/xen-public/xen.h).
+ */
+ boot_pfn = min((int)xen_start_info.nr_pages,lmax_low_pfn);
+ bootmap_size = init_bootmem(start_pfn,boot_pfn);
+ free_bootmem(0, PFN_PHYS(boot_pfn));
+ reserve_bootmem(__pa(&_stext),
+ PFN_PHYS(start_pfn) + bootmap_size + PAGE_SIZE-1 -
+ __pa(&_stext));
+
+ /* init_bootmem() set the global max_low_pfn to boot_pfn. Now max_low_pfn
+ * can be set to the override value.
+ */
+ max_low_pfn = lmax_low_pfn;
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ if ( xen_start_info.mod_start != 0 )
+ {
+ if ( (__pa(xen_start_info.mod_start) + xen_start_info.mod_len) <=
+ (max_low_pfn << PAGE_SHIFT) )
+ {
+ initrd_start = xen_start_info.mod_start;
+ initrd_end = initrd_start + xen_start_info.mod_len;
+ initrd_below_start_ok = 1;
+ }
+ else
+ {
+ printk(KERN_ERR "initrd extends beyond end of memory "
+ "(0x%08lx > 0x%08lx)\ndisabling initrd\n",
+ __pa(xen_start_info.mod_start) + xen_start_info.mod_len,
+ max_low_pfn << PAGE_SHIFT);
+ initrd_start = 0;
+ }
+ }
+#endif
+
+ paging_init();
+
+ /* Make sure we have a correctly sized P->M table. */
+ if ( max_pfn != xen_start_info.nr_pages )
+ {
+ phys_to_machine_mapping = alloc_bootmem_low_pages(
+ max_pfn * sizeof(unsigned long));
+ if ( max_pfn > xen_start_info.nr_pages )
+ {
+ memset(phys_to_machine_mapping, ~0,
+ max_pfn * sizeof(unsigned long));
+ memcpy(phys_to_machine_mapping,
+ (unsigned long *)xen_start_info.mfn_list,
+ xen_start_info.nr_pages * sizeof(unsigned long));
+ }
+ else
+ {
+ memcpy(phys_to_machine_mapping,
+ (unsigned long *)xen_start_info.mfn_list,
+ max_pfn * sizeof(unsigned long));
+ if (HYPERVISOR_dom_mem_op(
+ MEMOP_decrease_reservation,
+ (unsigned long *)xen_start_info.mfn_list + max_pfn,
+ xen_start_info.nr_pages - max_pfn, 0) !=
+ (xen_start_info.nr_pages - max_pfn))
+ BUG();
+ }
+ free_bootmem(__pa(xen_start_info.mfn_list),
+ PFN_PHYS(PFN_UP(xen_start_info.nr_pages *
+ sizeof(unsigned long))));
+ }
+
+ pfn_to_mfn_frame_list = alloc_bootmem_low_pages(PAGE_SIZE);
+ for ( i=0, j=0; i < max_pfn; i+=(PAGE_SIZE/sizeof(unsigned long)), j++ )
+ {
+ pfn_to_mfn_frame_list[j] =
+ virt_to_machine(&phys_to_machine_mapping[i]) >> PAGE_SHIFT;
+ }
+ HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list =
+ virt_to_machine(pfn_to_mfn_frame_list) >> PAGE_SHIFT;
+
+ op.cmd = PHYSDEVOP_SET_IOPL;
+ op.u.set_iopl.iopl = current->thread.io_pl = 1;
+ HYPERVISOR_physdev_op(&op);
+
+ if (xen_start_info.flags & SIF_INITDOMAIN )
+ {
+ if( !(xen_start_info.flags & SIF_PRIVILEGED) )
+ panic("Xen granted us console access but not privileged status");
+
+#if defined(CONFIG_VT)
+#if defined(CONFIG_VGA_CONSOLE)
+ conswitchp = &vga_con;
+#elif defined(CONFIG_DUMMY_CONSOLE)
+ conswitchp = &dummy_con;
+#endif
+#endif
+ }
+}
+
+static int cachesize_override __initdata = -1;
+static int __init cachesize_setup(char *str)
+{
+ get_option (&str, &cachesize_override);
+ return 1;
+}
+__setup("cachesize=", cachesize_setup);
+
+static int __init highio_setup(char *str)
+{
+ printk("i386: disabling HIGHMEM block I/O\n");
+ blk_nohighio = 1;
+ return 1;
+}
+__setup("nohighio", highio_setup);
+
+static int __init get_model_name(struct cpuinfo_x86 *c)
+{
+ unsigned int *v;
+ char *p, *q;
+
+ if (cpuid_eax(0x80000000) < 0x80000004)
+ return 0;
+
+ v = (unsigned int *) c->x86_model_id;
+ cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]);
+ cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]);
+ cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
+ c->x86_model_id[48] = 0;
+
+ /* Intel chips right-justify this string for some dumb reason;
+ undo that brain damage */
+ p = q = &c->x86_model_id[0];
+ while ( *p == ' ' )
+ p++;
+ if ( p != q ) {
+ while ( *p )
+ *q++ = *p++;
+ while ( q <= &c->x86_model_id[48] )
+ *q++ = '\0'; /* Zero-pad the rest */
+ }
+
+ return 1;
+}
+
+
+static void __init display_cacheinfo(struct cpuinfo_x86 *c)
+{
+ unsigned int n, dummy, ecx, edx, l2size;
+
+ n = cpuid_eax(0x80000000);
+
+ if (n >= 0x80000005) {
+ cpuid(0x80000005, &dummy, &dummy, &ecx, &edx);
+ printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache %dK
(%d bytes/line)\n",
+ edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
+ c->x86_cache_size=(ecx>>24)+(edx>>24);
+ }
+
+ if (n < 0x80000006) /* Some chips just has a large L1. */
+ return;
+
+ ecx = cpuid_ecx(0x80000006);
+ l2size = ecx >> 16;
+
+ /* AMD errata T13 (order #21922) */
+ if ((c->x86_vendor == X86_VENDOR_AMD) && (c->x86 == 6)) {
+ if (c->x86_model == 3 && c->x86_mask == 0) /* Duron Rev A0 */
+ l2size = 64;
+ if (c->x86_model == 4 &&
+ (c->x86_mask==0 || c->x86_mask==1)) /* Tbird rev A1/A2 */
+ l2size = 256;
+ }
+
+ /* Intel PIII Tualatin. This comes in two flavours.
+ * One has 256kb of cache, the other 512. We have no way
+ * to determine which, so we use a boottime override
+ * for the 512kb model, and assume 256 otherwise.
+ */
+ if ((c->x86_vendor == X86_VENDOR_INTEL) && (c->x86 == 6) &&
+ (c->x86_model == 11) && (l2size == 0))
+ l2size = 256;
+
+ if (c->x86_vendor == X86_VENDOR_CENTAUR) {
+ /* VIA C3 CPUs (670-68F) need further shifting. */
+ if ((c->x86 == 6) &&
+ ((c->x86_model == 7) || (c->x86_model == 8))) {
+ l2size >>= 8;
+ }
+
+ /* VIA also screwed up Nehemiah stepping 1, and made
+ it return '65KB' instead of '64KB'
+ - Note, it seems this may only be in engineering samples. */
+ if ((c->x86==6) && (c->x86_model==9) &&
+ (c->x86_mask==1) && (l2size==65))
+ l2size -= 1;
+ }
+
+ /* Allow user to override all this if necessary. */
+ if (cachesize_override != -1)
+ l2size = cachesize_override;
+
+ if ( l2size == 0 )
+ return; /* Again, no L2 cache is possible */
+
+ c->x86_cache_size = l2size;
+
+ printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
+ l2size, ecx & 0xFF);
+}
+
+static void __init init_c3(struct cpuinfo_x86 *c)
+{
+ /* Test for Centaur Extended Feature Flags presence */
+ if (cpuid_eax(0xC0000000) >= 0xC0000001) {
+ /* store Centaur Extended Feature Flags as
+ * word 5 of the CPU capability bit array
+ */
+ c->x86_capability[5] = cpuid_edx(0xC0000001);
+ }
+
+ switch (c->x86_model) {
+ case 9: /* Nehemiah */
+ default:
+ get_model_name(c);
+ display_cacheinfo(c);
+ break;
+ }
+}
+
+static void __init init_centaur(struct cpuinfo_x86 *c)
+{
+ /* Bit 31 in normal CPUID used for nonstandard 3DNow ID;
+ 3DNow is IDd by bit 31 in extended CPUID (1*3231) anyway */
+ clear_bit(0*32+31, &c->x86_capability);
+
+ switch (c->x86) {
+ case 6:
+ init_c3(c);
+ break;
+ default:
+ panic("Unsupported Centaur CPU (%i)\n", c->x86);
+ }
+}
+
+static int __init init_amd(struct cpuinfo_x86 *c)
+{
+ int r;
+
+ /* Bit 31 in normal CPUID used for nonstandard 3DNow ID;
+ 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */
+ clear_bit(0*32+31, &c->x86_capability);
+
+ r = get_model_name(c);
+
+ switch(c->x86)
+ {
+ case 5: /* We don't like AMD K6 */
+ panic("Unsupported AMD processor\n");
+ case 6: /* An Athlon/Duron. We can trust the BIOS probably */
+ break;
+ }
+
+ display_cacheinfo(c);
+ return r;
+}
+
+
+static void __init init_intel(struct cpuinfo_x86 *c)
+{
+ char *p = NULL;
+ unsigned int l1i = 0, l1d = 0, l2 = 0, l3 = 0; /* Cache sizes */
+
+ if (c->cpuid_level > 1) {
+ /* supports eax=2 call */
+ int i, j, n;
+ int regs[4];
+ unsigned char *dp = (unsigned char *)regs;
+
+ /* Number of times to iterate */
+ n = cpuid_eax(2) & 0xFF;
+
+ for ( i = 0 ; i < n ; i++ ) {
+ cpuid(2, ®s[0], ®s[1], ®s[2], ®s[3]);
+
+ /* If bit 31 is set, this is an unknown format */
+ for ( j = 0 ; j < 3 ; j++ ) {
+ if ( regs[j] < 0 ) regs[j] = 0;
+ }
+
+ /* Byte 0 is level count, not a descriptor */
+ for ( j = 1 ; j < 16 ; j++ ) {
+ unsigned char des = dp[j];
+ unsigned char dl, dh;
+ unsigned int cs;
+
+ dh = des >> 4;
+ dl = des & 0x0F;
+
+ /* Black magic... */
+
+ switch ( dh )
+ {
+ case 0:
+ switch ( dl ) {
+ case 6:
+ /* L1 I cache */
+ l1i += 8;
+ break;
+ case 8:
+ /* L1 I cache */
+ l1i += 16;
+ break;
+ case 10:
+ /* L1 D cache */
+ l1d += 8;
+ break;
+ case 12:
+ /* L1 D cache */
+ l1d += 16;
+ break;
+ default:;
+ /* TLB, or unknown */
+ }
+ break;
+ case 2:
+ if ( dl ) {
+ /* L3 cache */
+ cs = (dl-1) << 9;
+ l3 += cs;
+ }
+ break;
+ case 4:
+ if ( c->x86 > 6 && dl ) {
+ /* P4 family */
+ /* L3 cache */
+ cs = 128 << (dl-1);
+ l3 += cs;
+ break;
+ }
+ /* else same as 8 - fall through */
+ case 8:
+ if ( dl ) {
+ /* L2 cache */
+ cs = 128 << (dl-1);
+ l2 += cs;
+ }
+ break;
+ case 6:
+ if (dl > 5) {
+ /* L1 D cache */
+ cs = 8<<(dl-6);
+ l1d += cs;
+ }
+ break;
+ case 7:
+ if ( dl >= 8 )
+ {
+ /* L2 cache */
+ cs = 64<<(dl-8);
+ l2 += cs;
+ } else {
+ /* L0 I cache, count as L1 */
+ cs = dl ? (16 << (dl-1)) : 12;
+ l1i += cs;
+ }
+ break;
+ default:
+ /* TLB, or something else we don't know about */
+ break;
+ }
+ }
+ }
+ if ( l1i || l1d )
+ printk(KERN_INFO "CPU: L1 I cache: %dK, L1 D cache: %dK\n",
+ l1i, l1d);
+ if ( l2 )
+ printk(KERN_INFO "CPU: L2 cache: %dK\n", l2);
+ if ( l3 )
+ printk(KERN_INFO "CPU: L3 cache: %dK\n", l3);
+
+ /*
+ * This assumes the L3 cache is shared; it typically lives in
+ * the northbridge. The L1 caches are included by the L2
+ * cache, and so should not be included for the purpose of
+ * SMP switching weights.
+ */
+ c->x86_cache_size = l2 ? l2 : (l1i+l1d);
+ }
+
+ /* SEP CPUID bug: Pentium Pro reports SEP but doesn't have it */
+ if ( c->x86 == 6 && c->x86_model < 3 && c->x86_mask < 3 )
+ clear_bit(X86_FEATURE_SEP, &c->x86_capability);
+
+ /* Names for the Pentium II/Celeron processors
+ detectable only by also checking the cache size.
+ Dixon is NOT a Celeron. */
+ if (c->x86 == 6) {
+ switch (c->x86_model) {
+ case 5:
+ if (l2 == 0)
+ p = "Celeron (Covington)";
+ if (l2 == 256)
+ p = "Mobile Pentium II (Dixon)";
+ break;
+
+ case 6:
+ if (l2 == 128)
+ p = "Celeron (Mendocino)";
+ break;
+
+ case 8:
+ if (l2 == 128)
+ p = "Celeron (Coppermine)";
+ break;
+ }
+ }
+
+ if ( p )
+ strcpy(c->x86_model_id, p);
+}
+
+void __init get_cpu_vendor(struct cpuinfo_x86 *c)
+{
+ char *v = c->x86_vendor_id;
+
+ if (!strcmp(v, "GenuineIntel"))
+ c->x86_vendor = X86_VENDOR_INTEL;
+ else if (!strcmp(v, "AuthenticAMD"))
+ c->x86_vendor = X86_VENDOR_AMD;
+ else if (!strcmp(v, "CentaurHauls"))
+ c->x86_vendor = X86_VENDOR_CENTAUR;
+ else
+ c->x86_vendor = X86_VENDOR_UNKNOWN;
+}
+
+struct cpu_model_info {
+ int vendor;
+ int family;
+ char *model_names[16];
+};
+
+/* Naming convention should be: <Name> [(<Codename>)] */
+/* This table only is used unless init_<vendor>() below doesn't set it; */
+/* in particular, if CPUID levels 0x80000002..4 are supported, this isn't used
*/
+static struct cpu_model_info cpu_models[] __initdata = {
+ { X86_VENDOR_INTEL, 6,
+ { "Pentium Pro A-step", "Pentium Pro", NULL, "Pentium II (Klamath)",
+ NULL, "Pentium II (Deschutes)", "Mobile Pentium II",
+ "Pentium III (Katmai)", "Pentium III (Coppermine)", NULL,
+ "Pentium III (Cascades)", NULL, NULL, NULL, NULL }},
+ { X86_VENDOR_AMD, 6, /* Is this this really necessary?? */
+ { "Athlon", "Athlon",
+ "Athlon", NULL, "Athlon", NULL,
+ NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL }}
+};
+
+/* Look up CPU names by table lookup. */
+static char __init *table_lookup_model(struct cpuinfo_x86 *c)
+{
+ struct cpu_model_info *info = cpu_models;
+ int i;
+
+ if ( c->x86_model >= 16 )
+ return NULL; /* Range check */
+
+ for ( i = 0 ; i < sizeof(cpu_models)/sizeof(struct cpu_model_info) ; i++ )
{
+ if ( info->vendor == c->x86_vendor &&
+ info->family == c->x86 ) {
+ return info->model_names[c->x86_model];
+ }
+ info++;
+ }
+ return NULL; /* Not found */
+}
+
+
+
+/* Standard macro to see if a specific flag is changeable */
+static inline int flag_is_changeable_p(u32 flag)
+{
+ u32 f1, f2;
+
+ asm("pushfl\n\t"
+ "pushfl\n\t"
+ "popl %0\n\t"
+ "movl %0,%1\n\t"
+ "xorl %2,%0\n\t"
+ "pushl %0\n\t"
+ "popfl\n\t"
+ "pushfl\n\t"
+ "popl %0\n\t"
+ "popfl\n\t"
+ : "=&r" (f1), "=&r" (f2)
+ : "ir" (flag));
+
+ return ((f1^f2) & flag) != 0;
+}
+
+
+/* Probe for the CPUID instruction */
+static int __init have_cpuid_p(void)
+{
+ return flag_is_changeable_p(X86_EFLAGS_ID);
+}
+
+
+
+#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
+unsigned char eddnr;
+struct edd_info edd[EDDMAXNR];
+unsigned int edd_disk80_sig;
+/**
+ * copy_edd() - Copy the BIOS EDD information
+ * from empty_zero_page into a safe place.
+ *
+ */
+static inline void copy_edd(void)
+{
+ eddnr = EDD_NR;
+ memcpy(edd, EDD_BUF, sizeof(edd));
+ edd_disk80_sig = DISK80_SIGNATURE_BUFFER;
+}
+#else
+static inline void copy_edd(void) {}
+#endif
+
+/*
+ * This does the hard work of actually picking apart the CPU stuff...
+ */
+void __init identify_cpu(struct cpuinfo_x86 *c)
+{
+ int junk, i;
+ u32 xlvl, tfms;
+
+ c->loops_per_jiffy = loops_per_jiffy;
+ c->x86_cache_size = -1;
+ c->x86_vendor = X86_VENDOR_UNKNOWN;
+ c->cpuid_level = -1; /* CPUID not detected */
+ c->x86_model = c->x86_mask = 0; /* So far unknown... */
+ c->x86_vendor_id[0] = '\0'; /* Unset */
+ c->x86_model_id[0] = '\0'; /* Unset */
+ memset(&c->x86_capability, 0, sizeof c->x86_capability);
+ c->hard_math = 1;
+
+ if ( !have_cpuid_p() ) {
+ panic("Processor must support CPUID\n");
+ } else {
+ /* CPU does have CPUID */
+
+ /* Get vendor name */
+ cpuid(0x00000000, &c->cpuid_level,
+ (int *)&c->x86_vendor_id[0],
+ (int *)&c->x86_vendor_id[8],
+ (int *)&c->x86_vendor_id[4]);
+
+ get_cpu_vendor(c);
+ /* Initialize the standard set of capabilities */
+ /* Note that the vendor-specific code below might override */
+
+ /* Intel-defined flags: level 0x00000001 */
+ if ( c->cpuid_level >= 0x00000001 ) {
+ u32 capability, excap;
+ cpuid(0x00000001, &tfms, &junk, &excap, &capability);
+ c->x86_capability[0] = capability;
+ c->x86_capability[4] = excap;
+ c->x86 = (tfms >> 8) & 15;
+ c->x86_model = (tfms >> 4) & 15;
+ if (c->x86 == 0xf) {
+ c->x86 += (tfms >> 20) & 0xff;
+ c->x86_model += ((tfms >> 16) & 0xF) << 4;
+ }
+ c->x86_mask = tfms & 15;
+ } else {
+ /* Have CPUID level 0 only - unheard of */
+ c->x86 = 4;
+ }
+
+ /* AMD-defined flags: level 0x80000001 */
+ xlvl = cpuid_eax(0x80000000);
+ if ( (xlvl & 0xffff0000) == 0x80000000 ) {
+ if ( xlvl >= 0x80000001 )
+ c->x86_capability[1] = cpuid_edx(0x80000001);
+ if ( xlvl >= 0x80000004 )
+ get_model_name(c); /* Default name */
+ }
+
+ /* Transmeta-defined flags: level 0x80860001 */
+ xlvl = cpuid_eax(0x80860000);
+ if ( (xlvl & 0xffff0000) == 0x80860000 ) {
+ if ( xlvl >= 0x80860001 )
+ c->x86_capability[2] = cpuid_edx(0x80860001);
+ }
+ }
+
+ printk(KERN_DEBUG "CPU: Before vendor init, caps: %08x %08x %08x, vendor =
%d\n",
+ c->x86_capability[0],
+ c->x86_capability[1],
+ c->x86_capability[2],
+ c->x86_vendor);
+
+ /*
+ * Vendor-specific initialization. In this section we
+ * canonicalize the feature flags, meaning if there are
+ * features a certain CPU supports which CPUID doesn't
+ * tell us, CPUID claiming incorrect flags, or other bugs,
+ * we handle them here.
+ *
+ * At the end of this section, c->x86_capability better
+ * indicate the features this CPU genuinely supports!
+ */
+ switch ( c->x86_vendor ) {
+ case X86_VENDOR_AMD:
+ init_amd(c);
+ break;
+
+ case X86_VENDOR_INTEL:
+ init_intel(c);
+ break;
+
+ case X86_VENDOR_CENTAUR:
+ init_centaur(c);
+ break;
+
+ default:
+ printk("Unsupported CPU vendor (%d) -- please report!\n",
+ c->x86_vendor);
+ }
+
+ printk(KERN_DEBUG "CPU: After vendor init, caps: %08x %08x %08x %08x\n",
+ c->x86_capability[0],
+ c->x86_capability[1],
+ c->x86_capability[2],
+ c->x86_capability[3]);
+
+
+ /* If the model name is still unset, do table lookup. */
+ if ( !c->x86_model_id[0] ) {
+ char *p;
+ p = table_lookup_model(c);
+ if ( p )
+ strcpy(c->x86_model_id, p);
+ else
+ /* Last resort... */
+ sprintf(c->x86_model_id, "%02x/%02x",
+ c->x86_vendor, c->x86_model);
+ }
+
+ /* Now the feature flags better reflect actual CPU features! */
+
+ printk(KERN_DEBUG "CPU: After generic, caps: %08x %08x %08x %08x\n",
+ c->x86_capability[0],
+ c->x86_capability[1],
+ c->x86_capability[2],
+ c->x86_capability[3]);
+
+ /*
+ * On SMP, boot_cpu_data holds the common feature set between
+ * all CPUs; so make sure that we indicate which features are
+ * common between the CPUs. The first time this routine gets
+ * executed, c == &boot_cpu_data.
+ */
+ if ( c != &boot_cpu_data ) {
+ /* AND the already accumulated flags with these */
+ for ( i = 0 ; i < NCAPINTS ; i++ )
+ boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
+ }
+
+ printk(KERN_DEBUG "CPU: Common caps: %08x %08x %08x %08x\n",
+ boot_cpu_data.x86_capability[0],
+ boot_cpu_data.x86_capability[1],
+ boot_cpu_data.x86_capability[2],
+ boot_cpu_data.x86_capability[3]);
+}
+
+
+/* These need to match <asm/processor.h> */
+static char *cpu_vendor_names[] __initdata = {
+ "Intel", "Cyrix", "AMD", "UMC", "NexGen", "Centaur", "Rise", "Transmeta" };
+
+
+void __init print_cpu_info(struct cpuinfo_x86 *c)
+{
+ char *vendor = NULL;
+
+ if (c->x86_vendor < sizeof(cpu_vendor_names)/sizeof(char *))
+ vendor = cpu_vendor_names[c->x86_vendor];
+ else if (c->cpuid_level >= 0)
+ vendor = c->x86_vendor_id;
+
+ if (vendor && strncmp(c->x86_model_id, vendor, strlen(vendor)))
+ printk("%s ", vendor);
+
+ if (!c->x86_model_id[0])
+ printk("%d86", c->x86);
+ else
+ printk("%s", c->x86_model_id);
+
+ if (c->x86_mask || c->cpuid_level >= 0)
+ printk(" stepping %02x\n", c->x86_mask);
+ else
+ printk("\n");
+}
+
+/*
+ * Get CPU information for use by the procfs.
+ */
+static int show_cpuinfo(struct seq_file *m, void *v)
+{
+ /*
+ * These flag bits must match the definitions in <asm/cpufeature.h>.
+ * NULL means this bit is undefined or reserved; either way it doesn't
+ * have meaning as far as Linux is concerned. Note that it's important
+ * to realize there is a difference between this table and CPUID -- if
+ * applications want to get the raw CPUID data, they should access
+ * /dev/cpu/<cpu_nr>/cpuid instead.
+ */
+ static char *x86_cap_flags[] = {
+ /* Intel-defined */
+ "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce",
+ "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov",
+ "pat", "pse36", "pn", "clflush", NULL, "dts", "acpi", "mmx",
+ "fxsr", "sse", "sse2", "ss", "ht", "tm", "ia64", "pbe",
+
+ /* AMD-defined */
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, "mp", NULL, NULL, "mmxext", NULL,
+ NULL, NULL, NULL, NULL, NULL, "lm", "3dnowext", "3dnow",
+
+ /* Transmeta-defined */
+ "recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+
+ /* Other (Linux-defined) */
+ "cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr",
+ NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+
+ /* Intel-defined (#2) */
+ "pni", NULL, NULL, "monitor", "ds_cpl", NULL, NULL, "tm2",
+ "est", NULL, "cid", NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+
+ /* VIA/Cyrix/Centaur-defined */
+ NULL, NULL, "xstore", NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+
+ };
+ struct cpuinfo_x86 *c = v;
+ int i, n = c - cpu_data;
+ int fpu_exception;
+
+#ifdef CONFIG_SMP
+ if (!(cpu_online_map & (1<<n)))
+ return 0;
+#endif
+ seq_printf(m, "processor\t: %d\n"
+ "vendor_id\t: %s\n"
+ "cpu family\t: %d\n"
+ "model\t\t: %d\n"
+ "model name\t: %s\n",
+ n,
+ c->x86_vendor_id[0] ? c->x86_vendor_id : "unknown",
+ c->x86,
+ c->x86_model,
+ c->x86_model_id[0] ? c->x86_model_id : "unknown");
+
+ if (c->x86_mask || c->cpuid_level >= 0)
+ seq_printf(m, "stepping\t: %d\n", c->x86_mask);
+ else
+ seq_printf(m, "stepping\t: unknown\n");
+
+ if ( test_bit(X86_FEATURE_TSC, &c->x86_capability) ) {
+ seq_printf(m, "cpu MHz\t\t: %lu.%03lu\n",
+ cpu_khz / 1000, (cpu_khz % 1000));
+ }
+
+ /* Cache size */
+ if (c->x86_cache_size >= 0)
+ seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size);
+
+ /* We use exception 16 if we have hardware math and we've either seen
it or the CPU claims it is internal */
+ fpu_exception = c->hard_math && (ignore_irq13 || cpu_has_fpu);
+ seq_printf(m, "fdiv_bug\t: %s\n"
+ "hlt_bug\t\t: %s\n"
+ "f00f_bug\t: %s\n"
+ "coma_bug\t: %s\n"
+ "fpu\t\t: %s\n"
+ "fpu_exception\t: %s\n"
+ "cpuid level\t: %d\n"
+ "wp\t\t: %s\n"
+ "flags\t\t:",
+ c->fdiv_bug ? "yes" : "no",
+ c->hlt_works_ok ? "no" : "yes",
+ c->f00f_bug ? "yes" : "no",
+ c->coma_bug ? "yes" : "no",
+ c->hard_math ? "yes" : "no",
+ fpu_exception ? "yes" : "no",
+ c->cpuid_level,
+ c->wp_works_ok ? "yes" : "no");
+
+ for ( i = 0 ; i < 32*NCAPINTS ; i++ )
+ if ( test_bit(i, &c->x86_capability) &&
+ x86_cap_flags[i] != NULL )
+ seq_printf(m, " %s", x86_cap_flags[i]);
+
+ seq_printf(m, "\nbogomips\t: %lu.%02lu\n\n",
+ c->loops_per_jiffy/(500000/HZ),
+ (c->loops_per_jiffy/(5000/HZ)) % 100);
+ return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+ return *pos < NR_CPUS ? cpu_data + *pos : NULL;
+}
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ ++*pos;
+ return c_start(m, pos);
+}
+static void c_stop(struct seq_file *m, void *v)
+{
+}
+struct seq_operations cpuinfo_op = {
+ start: c_start,
+ next: c_next,
+ stop: c_stop,
+ show: show_cpuinfo,
+};
+
+unsigned long cpu_initialized __initdata = 0;
+
+/*
+ * cpu_init() initializes state that is per-CPU. Some data is already
+ * initialized (naturally) in the bootstrap process, such as the GDT
+ * and IDT. We reload them nevertheless, this function acts as a
+ * 'CPU state barrier', nothing should get across.
+ */
+void __init cpu_init (void)
+{
+ int nr = smp_processor_id();
+
+ if (test_and_set_bit(nr, &cpu_initialized)) {
+ printk(KERN_WARNING "CPU#%d already initialized!\n", nr);
+ for (;;) __sti();
+ }
+ printk(KERN_INFO "Initializing CPU#%d\n", nr);
+
+ /*
+ * set up and load the per-CPU TSS and LDT
+ */
+ atomic_inc(&init_mm.mm_count);
+ current->active_mm = &init_mm;
+ if(current->mm)
+ BUG();
+ enter_lazy_tlb(&init_mm, current, nr);
+
+ HYPERVISOR_stack_switch(__KERNEL_DS, current->thread.esp0);
+
+ load_LDT(&init_mm.context);
+
+ /* Force FPU initialization. */
+ current->flags &= ~PF_USEDFPU;
+ current->used_math = 0;
+ stts();
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/queues.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/queues.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,20 @@
+
+/* Work-queue emulation over task queues. Pretty simple. */
+
+#ifndef __QUEUES_H__
+#define __QUEUES_H__
+
+#include <linux/version.h>
+#include <linux/list.h>
+#include <linux/tqueue.h>
+
+#define DECLARE_TQUEUE(_name, _fn, _arg) \
+ struct tq_struct _name = { LIST_HEAD_INIT((_name).list), 0, _fn, _arg }
+#define DECLARE_WORK(_name, _fn, _arg) DECLARE_TQUEUE(_name, _fn, _arg)
+
+#define work_struct tq_struct
+#define INIT_WORK(_work, _fn, _arg) INIT_TQUEUE(_work, _fn, _arg)
+
+#define schedule_work(_w) schedule_task(_w)
+
+#endif /* __QUEUES_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/pda.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/pda.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,85 @@
+#ifndef X86_64_PDA_H
+#define X86_64_PDA_H
+
+#ifndef __ASSEMBLY__
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <linux/cache.h>
+
+/* Per processor datastructure. %gs points to it while the kernel runs */
+struct x8664_pda {
+ struct task_struct *pcurrent; /* Current process */
+ unsigned long data_offset; /* Per cpu data offset from linker
address */
+ struct x8664_pda *me; /* Pointer to itself */
+ unsigned long kernelstack; /* top of kernel stack for current */
+ unsigned long oldrsp; /* user rsp for system call */
+ unsigned long irqrsp; /* Old rsp for interrupts. */
+ int irqcount; /* Irq nesting counter. Starts with -1 */
+ int cpunumber; /* Logical CPU number */
+ char *irqstackptr; /* top of irqstack */
+ unsigned int __softirq_pending;
+ unsigned int __nmi_count; /* number of NMI on this CPUs */
+ unsigned long idle_timestamp;
+ struct mm_struct *active_mm;
+ int mmu_state;
+ unsigned apic_timer_irqs;
+ int kernel_mode; /* kernel or user mode */
+} ____cacheline_aligned;
+
+
+#define IRQSTACK_ORDER 2
+#define IRQSTACKSIZE (PAGE_SIZE << IRQSTACK_ORDER)
+
+extern struct x8664_pda cpu_pda[];
+
+/*
+ * There is no fast way to get the base address of the PDA, all the accesses
+ * have to mention %fs/%gs. So it needs to be done this Torvaldian way.
+ */
+#define sizeof_field(type,field) (sizeof(((type *)0)->field))
+#define typeof_field(type,field) typeof(((type *)0)->field)
+
+extern void __bad_pda_field(void);
+
+#define pda_offset(field) offsetof(struct x8664_pda, field)
+
+#define pda_to_op(op,field,val) do { \
+ switch (sizeof_field(struct x8664_pda, field)) { \
+case 2: \
+asm volatile(op "w %0,%%gs:%P1"::"r" (val),"i"(pda_offset(field)):"memory");
break; \
+case 4: \
+asm volatile(op "l %0,%%gs:%P1"::"r" (val),"i"(pda_offset(field)):"memory");
break; \
+case 8: \
+asm volatile(op "q %0,%%gs:%P1"::"r" (val),"i"(pda_offset(field)):"memory");
break; \
+ default: __bad_pda_field(); \
+ } \
+ } while (0)
+
+/*
+ * AK: PDA read accesses should be neither volatile nor have an memory clobber.
+ * Unfortunately removing them causes all hell to break lose currently.
+ */
+#define pda_from_op(op,field) ({ \
+ typedef typeof_field(struct x8664_pda, field) T__; T__ ret__; \
+ switch (sizeof_field(struct x8664_pda, field)) { \
+case 2: \
+asm volatile(op "w %%gs:%P1,%0":"=r" (ret__):"i"(pda_offset(field)):"memory");
break;\
+case 4: \
+asm volatile(op "l %%gs:%P1,%0":"=r" (ret__):"i"(pda_offset(field)):"memory");
break;\
+case 8: \
+asm volatile(op "q %%gs:%P1,%0":"=r" (ret__):"i"(pda_offset(field)):"memory");
break;\
+ default: __bad_pda_field(); \
+ } \
+ ret__; })
+
+
+#define read_pda(field) pda_from_op("mov",field)
+#define write_pda(field,val) pda_to_op("mov",field,val)
+#define add_pda(field,val) pda_to_op("add",field,val)
+#define sub_pda(field,val) pda_to_op("sub",field,val)
+
+#endif
+
+#define PDA_STACKOFFSET (5*8)
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/ioport.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/ioport.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,63 @@
+/*
+ * linux/arch/x86_64/kernel/ioport.c
+ *
+ * This contains the io-permission bitmap code - written by obz, with changes
+ * by Linus.
+ */
+
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/ioport.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/stddef.h>
+#include <linux/slab.h>
+#include <linux/thread_info.h>
+#include <asm-xen/xen-public/physdev.h>
+
+/*
+ * sys_iopl has to be used when you want to access the IO ports
+ * beyond the 0x3ff range: to get the full 65536 ports bitmapped
+ * you'd need 8kB of bitmaps/process, which is a bit excessive.
+ *
+ */
+
+// asmlinkage long sys_iopl(unsigned int level, struct pt_regs *regs)
+asmlinkage long sys_iopl(unsigned int new_io_pl)
+{
+ unsigned int old_io_pl = current->thread.io_pl;
+ physdev_op_t op;
+
+
+ if (new_io_pl > 3)
+ return -EINVAL;
+
+ /* Need "raw I/O" privileges for direct port access. */
+ if ((new_io_pl > old_io_pl) && !capable(CAP_SYS_RAWIO))
+ return -EPERM;
+
+ /* Maintain OS privileges even if user attempts to relinquish them. */
+ if (new_io_pl == 0)
+ new_io_pl = 1;
+
+ /* Change our version of the privilege levels. */
+ current->thread.io_pl = new_io_pl;
+
+ /* Force the change at ring 0. */
+ op.cmd = PHYSDEVOP_SET_IOPL;
+ op.u.set_iopl.iopl = new_io_pl;
+ HYPERVISOR_physdev_op(&op);
+
+ return 0;
+}
+
+/*
+ * this changes the io permissions bitmap in the current task.
+ */
+asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
+{
+ return turn_on ? sys_iopl(3) : 0;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/balloon/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/balloon/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,2 @@
+
+obj-y += balloon.o
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/mm/ioremap.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/mm/ioremap.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,266 @@
+/*
+ * arch/xen/mm/ioremap.c
+ *
+ * Re-map IO memory to kernel address space so that we can access it.
+ *
+ * (C) Copyright 1995 1996 Linus Torvalds
+ *
+ * Modifications for Xenolinux (c) 2003-2004 Keir Fraser
+ */
+
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/vmalloc.h>
+#include <asm/io.h>
+#include <asm/pgalloc.h>
+#include <asm/uaccess.h>
+#include <asm/tlb.h>
+#include <asm/mmu.h>
+
+#if defined(CONFIG_XEN_PRIVILEGED_GUEST)
+
+/* These hacky macros avoid phys->machine translations. */
+#define __direct_pte(x) ((pte_t) { (x) } )
+#define __direct_mk_pte(page_nr,pgprot) \
+ __direct_pte(((page_nr) << PAGE_SHIFT) | pgprot_val(pgprot))
+#define direct_mk_pte_phys(physpage, pgprot) \
+ __direct_mk_pte((physpage) >> PAGE_SHIFT, pgprot)
+
+static inline void direct_remap_area_pte(pte_t *pte,
+ unsigned long address,
+ unsigned long size,
+ mmu_update_t **v)
+{
+ unsigned long end;
+
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ if (address >= end)
+ BUG();
+
+ do {
+ (*v)->ptr = virt_to_machine(pte);
+ (*v)++;
+ address += PAGE_SIZE;
+ pte++;
+ } while (address && (address < end));
+}
+
+static inline int direct_remap_area_pmd(struct mm_struct *mm,
+ pmd_t *pmd,
+ unsigned long address,
+ unsigned long size,
+ mmu_update_t **v)
+{
+ unsigned long end;
+
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ if (address >= end)
+ BUG();
+ do {
+ pte_t *pte = pte_alloc(mm, pmd, address);
+ if (!pte)
+ return -ENOMEM;
+ direct_remap_area_pte(pte, address, end - address, v);
+
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+ return 0;
+}
+
+int __direct_remap_area_pages(struct mm_struct *mm,
+ unsigned long address,
+ unsigned long size,
+ mmu_update_t *v)
+{
+ pgd_t * dir;
+ unsigned long end = address + size;
+
+ dir = pgd_offset(mm, address);
+ flush_cache_all();
+ if (address >= end)
+ BUG();
+ spin_lock(&mm->page_table_lock);
+ do {
+ pmd_t *pmd = pmd_alloc(mm, dir, address);
+ if (!pmd)
+ return -ENOMEM;
+ direct_remap_area_pmd(mm, pmd, address, end - address, &v);
+ address = (address + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+
+ } while (address && (address < end));
+ spin_unlock(&mm->page_table_lock);
+ flush_tlb_all();
+ return 0;
+}
+
+
+int direct_remap_area_pages(struct mm_struct *mm,
+ unsigned long address,
+ unsigned long machine_addr,
+ unsigned long size,
+ pgprot_t prot,
+ domid_t domid)
+{
+ int i;
+ unsigned long start_address;
+#define MAX_DIRECTMAP_MMU_QUEUE 130
+ mmu_update_t u[MAX_DIRECTMAP_MMU_QUEUE], *v = u;
+
+ start_address = address;
+
+ for( i = 0; i < size; i += PAGE_SIZE )
+ {
+ if ( (v - u) == MAX_DIRECTMAP_MMU_QUEUE )
+ {
+ /* Fill in the PTE pointers. */
+ __direct_remap_area_pages( mm,
+ start_address,
+ address-start_address,
+ u);
+
+ if ( HYPERVISOR_mmu_update(u, v - u, NULL, domid) < 0 )
+ return -EFAULT;
+ v = u;
+ start_address = address;
+ }
+
+ /*
+ * Fill in the machine address: PTE ptr is done later by
+ * __direct_remap_area_pages().
+ */
+ v->val = (machine_addr & PAGE_MASK) | pgprot_val(prot);
+
+ machine_addr += PAGE_SIZE;
+ address += PAGE_SIZE;
+ v++;
+ }
+
+ if ( v != u )
+ {
+ /* get the ptep's filled in */
+ __direct_remap_area_pages(mm,
+ start_address,
+ address-start_address,
+ u);
+ if ( unlikely(HYPERVISOR_mmu_update(u, v - u, NULL, domid) < 0) )
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
+
+#endif /* CONFIG_XEN_PRIVILEGED_GUEST */
+
+
+/*
+ * Remap an arbitrary machine address space into the kernel virtual
+ * address space. Needed when a privileged instance of Xenolinux wants
+ * to access space outside its world directly.
+ *
+ * NOTE! We need to allow non-page-aligned mappings too: we will obviously
+ * have to convert them into an offset in a page-aligned mapping, but the
+ * caller shouldn't need to know that small detail.
+ */
+void * __ioremap(unsigned long machine_addr,
+ unsigned long size,
+ unsigned long flags)
+{
+#if defined(CONFIG_XEN_PRIVILEGED_GUEST)
+ void * addr;
+ struct vm_struct * area;
+ unsigned long offset, last_addr;
+ pgprot_t prot;
+
+ /* Don't allow wraparound or zero size */
+ last_addr = machine_addr + size - 1;
+ if (!size || last_addr < machine_addr)
+ return NULL;
+
+ /* Mappings have to be page-aligned */
+ offset = machine_addr & ~PAGE_MASK;
+ machine_addr &= PAGE_MASK;
+ size = PAGE_ALIGN(last_addr+1) - machine_addr;
+
+ /* Ok, go for it */
+ area = get_vm_area(size, VM_IOREMAP);
+ if (!area)
+ return NULL;
+ addr = area->addr;
+ prot = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY |
+ _PAGE_ACCESSED | flags);
+ if (direct_remap_area_pages(&init_mm, VMALLOC_VMADDR(addr),
+ machine_addr, size, prot, 0)) {
+ vfree(addr);
+ return NULL;
+ }
+ return (void *) (offset + (char *)addr);
+#else
+ return NULL;
+#endif
+}
+
+void iounmap(void *addr)
+{
+ vfree((void *)((unsigned long)addr & PAGE_MASK));
+}
+
+/* implementation of boot time ioremap for purpose of provising access
+to the vga console for privileged domains. Unlike boot time ioremap on
+other architectures, ours is permanent and not reclaimed when then vmalloc
+infrastructure is started */
+
+void __init *bt_ioremap(unsigned long machine_addr, unsigned long size)
+{
+ unsigned long offset, last_addr;
+ unsigned int nrpages;
+ enum fixed_addresses idx;
+
+ /* Don't allow wraparound or zero size */
+ last_addr = machine_addr + size - 1;
+ if (!size || last_addr < machine_addr)
+ return NULL;
+
+ /*
+ * Mappings have to be page-aligned
+ */
+ offset = machine_addr & ~PAGE_MASK;
+ machine_addr &= PAGE_MASK;
+ size = PAGE_ALIGN(last_addr) - machine_addr;
+
+ /*
+ * Mappings have to fit in the FIX_BTMAP area.
+ */
+ nrpages = size >> PAGE_SHIFT;
+ if (nrpages > NR_FIX_BTMAPS)
+ return NULL;
+
+ /*
+ * Ok, go for it..
+ */
+ idx = FIX_BTMAP_BEGIN;
+ while (nrpages > 0) {
+ __set_fixmap(idx, machine_addr, PAGE_KERNEL);
+ machine_addr += PAGE_SIZE;
+ --idx;
+ --nrpages;
+ }
+
+ flush_tlb_all();
+
+ return (void*) (offset + fix_to_virt(FIX_BTMAP_BEGIN));
+}
+
+
+#if 0 /* We don't support these functions. They shouldn't be required. */
+void __init bt_iounmap(void *addr, unsigned long size) {}
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/cpu/common.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/cpu/common.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,642 @@
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <asm/semaphore.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/msr.h>
+#include <asm/io.h>
+#include <asm/mmu_context.h>
+#ifdef CONFIG_X86_LOCAL_APIC
+#include <asm/mpspec.h>
+#include <asm/apic.h>
+#include <mach_apic.h>
+#endif
+#include <asm-xen/hypervisor.h>
+
+#include "cpu.h"
+
+DEFINE_PER_CPU(struct desc_struct, cpu_gdt_table[GDT_ENTRIES]);
+EXPORT_PER_CPU_SYMBOL(cpu_gdt_table);
+
+static int cachesize_override __initdata = -1;
+static int disable_x86_fxsr __initdata = 0;
+static int disable_x86_serial_nr __initdata = 1;
+
+struct cpu_dev * cpu_devs[X86_VENDOR_NUM] = {};
+
+extern void mcheck_init(struct cpuinfo_x86 *c);
+
+extern void machine_specific_modify_cpu_capabilities(struct cpuinfo_x86 *c);
+
+extern int disable_pse;
+
+static void default_init(struct cpuinfo_x86 * c)
+{
+ /* Not much we can do here... */
+ /* Check if at least it has cpuid */
+ if (c->cpuid_level == -1) {
+ /* No cpuid. It must be an ancient CPU */
+ if (c->x86 == 4)
+ strcpy(c->x86_model_id, "486");
+ else if (c->x86 == 3)
+ strcpy(c->x86_model_id, "386");
+ }
+}
+
+static struct cpu_dev default_cpu = {
+ .c_init = default_init,
+};
+static struct cpu_dev * this_cpu = &default_cpu;
+
+static int __init cachesize_setup(char *str)
+{
+ get_option (&str, &cachesize_override);
+ return 1;
+}
+__setup("cachesize=", cachesize_setup);
+
+int __init get_model_name(struct cpuinfo_x86 *c)
+{
+ unsigned int *v;
+ char *p, *q;
+
+ if (cpuid_eax(0x80000000) < 0x80000004)
+ return 0;
+
+ v = (unsigned int *) c->x86_model_id;
+ cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]);
+ cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]);
+ cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
+ c->x86_model_id[48] = 0;
+
+ /* Intel chips right-justify this string for some dumb reason;
+ undo that brain damage */
+ p = q = &c->x86_model_id[0];
+ while ( *p == ' ' )
+ p++;
+ if ( p != q ) {
+ while ( *p )
+ *q++ = *p++;
+ while ( q <= &c->x86_model_id[48] )
+ *q++ = '\0'; /* Zero-pad the rest */
+ }
+
+ return 1;
+}
+
+
+void __init display_cacheinfo(struct cpuinfo_x86 *c)
+{
+ unsigned int n, dummy, ecx, edx, l2size;
+
+ n = cpuid_eax(0x80000000);
+
+ if (n >= 0x80000005) {
+ cpuid(0x80000005, &dummy, &dummy, &ecx, &edx);
+ printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache
%dK (%d bytes/line)\n",
+ edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
+ c->x86_cache_size=(ecx>>24)+(edx>>24);
+ }
+
+ if (n < 0x80000006) /* Some chips just has a large L1. */
+ return;
+
+ ecx = cpuid_ecx(0x80000006);
+ l2size = ecx >> 16;
+
+ /* do processor-specific cache resizing */
+ if (this_cpu->c_size_cache)
+ l2size = this_cpu->c_size_cache(c,l2size);
+
+ /* Allow user to override all this if necessary. */
+ if (cachesize_override != -1)
+ l2size = cachesize_override;
+
+ if ( l2size == 0 )
+ return; /* Again, no L2 cache is possible */
+
+ c->x86_cache_size = l2size;
+
+ printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
+ l2size, ecx & 0xFF);
+}
+
+/* Naming convention should be: <Name> [(<Codename>)] */
+/* This table only is used unless init_<vendor>() below doesn't set it; */
+/* in particular, if CPUID levels 0x80000002..4 are supported, this isn't used
*/
+
+/* Look up CPU names by table lookup. */
+static char __init *table_lookup_model(struct cpuinfo_x86 *c)
+{
+ struct cpu_model_info *info;
+
+ if ( c->x86_model >= 16 )
+ return NULL; /* Range check */
+
+ if (!this_cpu)
+ return NULL;
+
+ info = this_cpu->c_models;
+
+ while (info && info->family) {
+ if (info->family == c->x86)
+ return info->model_names[c->x86_model];
+ info++;
+ }
+ return NULL; /* Not found */
+}
+
+
+void __init get_cpu_vendor(struct cpuinfo_x86 *c, int early)
+{
+ char *v = c->x86_vendor_id;
+ int i;
+
+ for (i = 0; i < X86_VENDOR_NUM; i++) {
+ if (cpu_devs[i]) {
+ if (!strcmp(v,cpu_devs[i]->c_ident[0]) ||
+ (cpu_devs[i]->c_ident[1] &&
+ !strcmp(v,cpu_devs[i]->c_ident[1]))) {
+ c->x86_vendor = i;
+ if (!early)
+ this_cpu = cpu_devs[i];
+ break;
+ }
+ }
+ }
+}
+
+
+static int __init x86_fxsr_setup(char * s)
+{
+ disable_x86_fxsr = 1;
+ return 1;
+}
+__setup("nofxsr", x86_fxsr_setup);
+
+
+/* Standard macro to see if a specific flag is changeable */
+static inline int flag_is_changeable_p(u32 flag)
+{
+ u32 f1, f2;
+
+ asm("pushfl\n\t"
+ "pushfl\n\t"
+ "popl %0\n\t"
+ "movl %0,%1\n\t"
+ "xorl %2,%0\n\t"
+ "pushl %0\n\t"
+ "popfl\n\t"
+ "pushfl\n\t"
+ "popl %0\n\t"
+ "popfl\n\t"
+ : "=&r" (f1), "=&r" (f2)
+ : "ir" (flag));
+
+ return ((f1^f2) & flag) != 0;
+}
+
+
+/* Probe for the CPUID instruction */
+int __init have_cpuid_p(void)
+{
+ return flag_is_changeable_p(X86_EFLAGS_ID);
+}
+
+/* Do minimum CPU detection early.
+ Fields really needed: vendor, cpuid_level, family, model, mask, cache
alignment.
+ The others are not touched to avoid unwanted side effects. */
+void __init early_cpu_detect(void)
+{
+ struct cpuinfo_x86 *c = &boot_cpu_data;
+
+ c->x86_cache_alignment = 32;
+
+ if (!have_cpuid_p())
+ return;
+
+ /* Get vendor name */
+ cpuid(0x00000000, &c->cpuid_level,
+ (int *)&c->x86_vendor_id[0],
+ (int *)&c->x86_vendor_id[8],
+ (int *)&c->x86_vendor_id[4]);
+
+ get_cpu_vendor(c, 1);
+
+ c->x86 = 4;
+ if (c->cpuid_level >= 0x00000001) {
+ u32 junk, tfms, cap0, misc;
+ cpuid(0x00000001, &tfms, &misc, &junk, &cap0);
+ c->x86 = (tfms >> 8) & 15;
+ c->x86_model = (tfms >> 4) & 15;
+ if (c->x86 == 0xf) {
+ c->x86 += (tfms >> 20) & 0xff;
+ c->x86_model += ((tfms >> 16) & 0xF) << 4;
+ }
+ c->x86_mask = tfms & 15;
+ if (cap0 & (1<<19))
+ c->x86_cache_alignment = ((misc >> 8) & 0xff) * 8;
+ }
+
+ early_intel_workaround(c);
+}
+
+void __init generic_identify(struct cpuinfo_x86 * c)
+{
+ u32 tfms, xlvl;
+ int junk;
+
+ if (have_cpuid_p()) {
+ /* Get vendor name */
+ cpuid(0x00000000, &c->cpuid_level,
+ (int *)&c->x86_vendor_id[0],
+ (int *)&c->x86_vendor_id[8],
+ (int *)&c->x86_vendor_id[4]);
+
+ get_cpu_vendor(c, 0);
+ /* Initialize the standard set of capabilities */
+ /* Note that the vendor-specific code below might override */
+
+ /* Intel-defined flags: level 0x00000001 */
+ if ( c->cpuid_level >= 0x00000001 ) {
+ u32 capability, excap;
+ cpuid(0x00000001, &tfms, &junk, &excap, &capability);
+ c->x86_capability[0] = capability;
+ c->x86_capability[4] = excap;
+ c->x86 = (tfms >> 8) & 15;
+ c->x86_model = (tfms >> 4) & 15;
+ if (c->x86 == 0xf) {
+ c->x86 += (tfms >> 20) & 0xff;
+ c->x86_model += ((tfms >> 16) & 0xF) << 4;
+ }
+ c->x86_mask = tfms & 15;
+ } else {
+ /* Have CPUID level 0 only - unheard of */
+ c->x86 = 4;
+ }
+
+ /* AMD-defined flags: level 0x80000001 */
+ xlvl = cpuid_eax(0x80000000);
+ if ( (xlvl & 0xffff0000) == 0x80000000 ) {
+ if ( xlvl >= 0x80000001 ) {
+ c->x86_capability[1] = cpuid_edx(0x80000001);
+ c->x86_capability[6] = cpuid_ecx(0x80000001);
+ }
+ if ( xlvl >= 0x80000004 )
+ get_model_name(c); /* Default name */
+ }
+ }
+}
+
+static void __init squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
+{
+ if (cpu_has(c, X86_FEATURE_PN) && disable_x86_serial_nr ) {
+ /* Disable processor serial number */
+ unsigned long lo,hi;
+ rdmsr(MSR_IA32_BBL_CR_CTL,lo,hi);
+ lo |= 0x200000;
+ wrmsr(MSR_IA32_BBL_CR_CTL,lo,hi);
+ printk(KERN_NOTICE "CPU serial number disabled.\n");
+ clear_bit(X86_FEATURE_PN, c->x86_capability);
+
+ /* Disabling the serial number may affect the cpuid level */
+ c->cpuid_level = cpuid_eax(0);
+ }
+}
+
+static int __init x86_serial_nr_setup(char *s)
+{
+ disable_x86_serial_nr = 0;
+ return 1;
+}
+__setup("serialnumber", x86_serial_nr_setup);
+
+
+
+/*
+ * This does the hard work of actually picking apart the CPU stuff...
+ */
+void __init identify_cpu(struct cpuinfo_x86 *c)
+{
+ int i;
+
+ c->loops_per_jiffy = loops_per_jiffy;
+ c->x86_cache_size = -1;
+ c->x86_vendor = X86_VENDOR_UNKNOWN;
+ c->cpuid_level = -1; /* CPUID not detected */
+ c->x86_model = c->x86_mask = 0; /* So far unknown... */
+ c->x86_vendor_id[0] = '\0'; /* Unset */
+ c->x86_model_id[0] = '\0'; /* Unset */
+ c->x86_num_cores = 1;
+ memset(&c->x86_capability, 0, sizeof c->x86_capability);
+
+ if (!have_cpuid_p()) {
+ /* First of all, decide if this is a 486 or higher */
+ /* It's a 486 if we can modify the AC flag */
+ if ( flag_is_changeable_p(X86_EFLAGS_AC) )
+ c->x86 = 4;
+ else
+ c->x86 = 3;
+ }
+
+ generic_identify(c);
+
+ printk(KERN_DEBUG "CPU: After generic identify, caps:");
+ for (i = 0; i < NCAPINTS; i++)
+ printk(" %08lx", c->x86_capability[i]);
+ printk("\n");
+
+ if (this_cpu->c_identify) {
+ this_cpu->c_identify(c);
+
+ printk(KERN_DEBUG "CPU: After vendor identify, caps:");
+ for (i = 0; i < NCAPINTS; i++)
+ printk(" %08lx", c->x86_capability[i]);
+ printk("\n");
+ }
+
+ /*
+ * Vendor-specific initialization. In this section we
+ * canonicalize the feature flags, meaning if there are
+ * features a certain CPU supports which CPUID doesn't
+ * tell us, CPUID claiming incorrect flags, or other bugs,
+ * we handle them here.
+ *
+ * At the end of this section, c->x86_capability better
+ * indicate the features this CPU genuinely supports!
+ */
+ if (this_cpu->c_init)
+ this_cpu->c_init(c);
+
+ /* Disable the PN if appropriate */
+ squash_the_stupid_serial_number(c);
+
+ /*
+ * The vendor-specific functions might have changed features. Now
+ * we do "generic changes."
+ */
+
+ /* TSC disabled? */
+ if ( tsc_disable )
+ clear_bit(X86_FEATURE_TSC, c->x86_capability);
+
+ /* FXSR disabled? */
+ if (disable_x86_fxsr) {
+ clear_bit(X86_FEATURE_FXSR, c->x86_capability);
+ clear_bit(X86_FEATURE_XMM, c->x86_capability);
+ }
+
+ if (disable_pse)
+ clear_bit(X86_FEATURE_PSE, c->x86_capability);
+
+ /* If the model name is still unset, do table lookup. */
+ if ( !c->x86_model_id[0] ) {
+ char *p;
+ p = table_lookup_model(c);
+ if ( p )
+ strcpy(c->x86_model_id, p);
+ else
+ /* Last resort... */
+ sprintf(c->x86_model_id, "%02x/%02x",
+ c->x86_vendor, c->x86_model);
+ }
+
+ machine_specific_modify_cpu_capabilities(c);
+
+ /* Now the feature flags better reflect actual CPU features! */
+
+ printk(KERN_DEBUG "CPU: After all inits, caps:");
+ for (i = 0; i < NCAPINTS; i++)
+ printk(" %08lx", c->x86_capability[i]);
+ printk("\n");
+
+ /*
+ * On SMP, boot_cpu_data holds the common feature set between
+ * all CPUs; so make sure that we indicate which features are
+ * common between the CPUs. The first time this routine gets
+ * executed, c == &boot_cpu_data.
+ */
+ if ( c != &boot_cpu_data ) {
+ /* AND the already accumulated flags with these */
+ for ( i = 0 ; i < NCAPINTS ; i++ )
+ boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
+ }
+
+ /* Init Machine Check Exception if available. */
+#ifdef CONFIG_X86_MCE
+ mcheck_init(c);
+#endif
+}
+/*
+ * Perform early boot up checks for a valid TSC. See
arch/i386/kernel/time.c
+ */
+
+void __init dodgy_tsc(void)
+{
+ if (( boot_cpu_data.x86_vendor == X86_VENDOR_CYRIX ) ||
+ ( boot_cpu_data.x86_vendor == X86_VENDOR_NSC ))
+ cpu_devs[X86_VENDOR_CYRIX]->c_init(&boot_cpu_data);
+}
+
+#ifdef CONFIG_X86_HT
+void __init detect_ht(struct cpuinfo_x86 *c)
+{
+ u32 eax, ebx, ecx, edx;
+ int index_lsb, index_msb, tmp;
+ int cpu = smp_processor_id();
+
+ if (!cpu_has(c, X86_FEATURE_HT))
+ return;
+
+ cpuid(1, &eax, &ebx, &ecx, &edx);
+ smp_num_siblings = (ebx & 0xff0000) >> 16;
+
+ if (smp_num_siblings == 1) {
+ printk(KERN_INFO "CPU: Hyper-Threading is disabled\n");
+ } else if (smp_num_siblings > 1 ) {
+ index_lsb = 0;
+ index_msb = 31;
+
+ if (smp_num_siblings > NR_CPUS) {
+ printk(KERN_WARNING "CPU: Unsupported number of the
siblings %d", smp_num_siblings);
+ smp_num_siblings = 1;
+ return;
+ }
+ tmp = smp_num_siblings;
+ while ((tmp & 1) == 0) {
+ tmp >>=1 ;
+ index_lsb++;
+ }
+ tmp = smp_num_siblings;
+ while ((tmp & 0x80000000 ) == 0) {
+ tmp <<=1 ;
+ index_msb--;
+ }
+ if (index_lsb != index_msb )
+ index_msb++;
+ phys_proc_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb);
+
+ printk(KERN_INFO "CPU: Physical Processor ID: %d\n",
+ phys_proc_id[cpu]);
+ }
+}
+#endif
+
+void __init print_cpu_info(struct cpuinfo_x86 *c)
+{
+ char *vendor = NULL;
+
+ if (c->x86_vendor < X86_VENDOR_NUM)
+ vendor = this_cpu->c_vendor;
+ else if (c->cpuid_level >= 0)
+ vendor = c->x86_vendor_id;
+
+ if (vendor && strncmp(c->x86_model_id, vendor, strlen(vendor)))
+ printk("%s ", vendor);
+
+ if (!c->x86_model_id[0])
+ printk("%d86", c->x86);
+ else
+ printk("%s", c->x86_model_id);
+
+ if (c->x86_mask || c->cpuid_level >= 0)
+ printk(" stepping %02x\n", c->x86_mask);
+ else
+ printk("\n");
+}
+
+cpumask_t cpu_initialized __initdata = CPU_MASK_NONE;
+
+/* This is hacky. :)
+ * We're emulating future behavior.
+ * In the future, the cpu-specific init functions will be called implicitly
+ * via the magic of initcalls.
+ * They will insert themselves into the cpu_devs structure.
+ * Then, when cpu_init() is called, we can just iterate over that array.
+ */
+
+extern int intel_cpu_init(void);
+extern int cyrix_init_cpu(void);
+extern int nsc_init_cpu(void);
+extern int amd_init_cpu(void);
+extern int centaur_init_cpu(void);
+extern int transmeta_init_cpu(void);
+extern int rise_init_cpu(void);
+extern int nexgen_init_cpu(void);
+extern int umc_init_cpu(void);
+void early_cpu_detect(void);
+
+void __init early_cpu_init(void)
+{
+ intel_cpu_init();
+ cyrix_init_cpu();
+ nsc_init_cpu();
+ amd_init_cpu();
+ centaur_init_cpu();
+ transmeta_init_cpu();
+ rise_init_cpu();
+ nexgen_init_cpu();
+ umc_init_cpu();
+ early_cpu_detect();
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ /* pse is not compatible with on-the-fly unmapping,
+ * disable it even if the cpus claim to support it.
+ */
+ clear_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability);
+ disable_pse = 1;
+#endif
+}
+
+void __init cpu_gdt_init(struct Xgt_desc_struct *gdt_descr)
+{
+ unsigned long frames[16];
+ unsigned long va;
+ int f;
+
+ for (va = gdt_descr->address, f = 0;
+ va < gdt_descr->address + gdt_descr->size;
+ va += PAGE_SIZE, f++) {
+ frames[f] = virt_to_machine(va) >> PAGE_SHIFT;
+ make_page_readonly((void *)va);
+ }
+ if (HYPERVISOR_set_gdt(frames, gdt_descr->size / 8))
+ BUG();
+ lgdt_finish();
+}
+
+/*
+ * cpu_init() initializes state that is per-CPU. Some data is already
+ * initialized (naturally) in the bootstrap process, such as the GDT
+ * and IDT. We reload them nevertheless, this function acts as a
+ * 'CPU state barrier', nothing should get across.
+ */
+void __init cpu_init (void)
+{
+ int cpu = smp_processor_id();
+ struct tss_struct * t = &per_cpu(init_tss, cpu);
+ struct thread_struct *thread = ¤t->thread;
+
+ if (cpu_test_and_set(cpu, cpu_initialized)) {
+ printk(KERN_WARNING "CPU#%d already initialized!\n", cpu);
+ for (;;) local_irq_enable();
+ }
+ printk(KERN_INFO "Initializing CPU#%d\n", cpu);
+
+ if (cpu_has_vme || cpu_has_de)
+ clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
+ if (tsc_disable && cpu_has_tsc) {
+ printk(KERN_NOTICE "Disabling TSC...\n");
+ /**** FIX-HPA: DOES THIS REALLY BELONG HERE? ****/
+ clear_bit(X86_FEATURE_TSC, boot_cpu_data.x86_capability);
+ set_in_cr4(X86_CR4_TSD);
+ }
+
+ /*
+ * Set up the per-thread TLS descriptor cache:
+ */
+ memcpy(thread->tls_array, &get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN],
+ GDT_ENTRY_TLS_ENTRIES * 8);
+
+ cpu_gdt_init(&cpu_gdt_descr[cpu]);
+
+ /*
+ * Delete NT
+ */
+ __asm__("pushfl ; andl $0xffffbfff,(%esp) ; popfl");
+
+ /*
+ * Set up and load the per-CPU TSS and LDT
+ */
+ atomic_inc(&init_mm.mm_count);
+ current->active_mm = &init_mm;
+ if (current->mm)
+ BUG();
+ enter_lazy_tlb(&init_mm, current);
+
+ load_esp0(t, thread);
+
+ load_LDT(&init_mm.context);
+
+ /* Clear %fs and %gs. */
+ asm volatile ("xorl %eax, %eax; movl %eax, %fs; movl %eax, %gs");
+
+ /* Clear all 6 debug registers: */
+
+#define CD(register) HYPERVISOR_set_debugreg(register, 0)
+
+ CD(0); CD(1); CD(2); CD(3); /* no db4 and db5 */; CD(6); CD(7);
+
+#undef CD
+
+ /*
+ * Force FPU initialization:
+ */
+ current_thread_info()->status = 0;
+ clear_used_math();
+ mxcsr_feature_mask_init();
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/pgalloc.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/pgalloc.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,171 @@
+#ifndef _X86_64_PGALLOC_H
+#define _X86_64_PGALLOC_H
+
+#include <asm/processor.h>
+#include <asm/fixmap.h>
+#include <asm/pda.h>
+#include <linux/threads.h>
+#include <linux/mm.h>
+#include <asm/io.h> /* for phys_to_virt and page_to_pseudophys */
+
+void make_page_readonly(void *va);
+void make_page_writable(void *va);
+void make_pages_readonly(void *va, unsigned int nr);
+void make_pages_writable(void *va, unsigned int nr);
+
+#define __user_pgd(pgd) ((pgd) + PTRS_PER_PGD)
+
+static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t
*pte)
+{
+ set_pmd(pmd, __pmd(_PAGE_TABLE | __pa(pte)));
+}
+
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page
*pte)
+{
+ set_pmd(pmd, __pmd(_PAGE_TABLE | (page_to_pfn(pte) << PAGE_SHIFT)));
+}
+
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+ set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd)));
+}
+
+/*
+ * We need to use the batch mode here, but pgd_pupulate() won't be
+ * be called frequently.
+ */
+static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
+{
+ set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud)));
+ set_pgd(__user_pgd(pgd), __pgd(_PAGE_TABLE | __pa(pud)));
+}
+
+extern __inline__ pmd_t *get_pmd(void)
+{
+ pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL);
+ if (!pmd)
+ return NULL;
+ make_page_readonly(pmd);
+ xen_pmd_pin(__pa(pmd));
+ return pmd;
+}
+
+extern __inline__ void pmd_free(pmd_t *pmd)
+{
+ BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+ xen_pmd_unpin(__pa(pmd));
+ make_page_writable(pmd);
+ free_page((unsigned long)pmd);
+}
+
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+ pmd_t *pmd = (pmd_t *) get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+ if (!pmd)
+ return NULL;
+ make_page_readonly(pmd);
+ xen_pmd_pin(__pa(pmd));
+ return pmd;
+}
+
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+ pud_t *pud = (pud_t *) get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+ if (!pud)
+ return NULL;
+ make_page_readonly(pud);
+ xen_pud_pin(__pa(pud));
+ return pud;
+}
+
+static inline void pud_free(pud_t *pud)
+{
+ BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
+ xen_pud_unpin(__pa(pud));
+ make_page_writable(pud);
+ free_page((unsigned long)pud);
+}
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+ /*
+ * We allocate two contiguous pages for kernel and user.
+ */
+ unsigned boundary;
+ pgd_t *pgd = (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_REPEAT, 1);
+
+ if (!pgd)
+ return NULL;
+ /*
+ * Copy kernel pointers in from init.
+ * Could keep a freelist or slab cache of those because the kernel
+ * part never changes.
+ */
+ boundary = pgd_index(__PAGE_OFFSET);
+ memset(pgd, 0, boundary * sizeof(pgd_t));
+ memcpy(pgd + boundary,
+ init_level4_pgt + boundary,
+ (PTRS_PER_PGD - boundary) * sizeof(pgd_t));
+
+ memset(__user_pgd(pgd), 0, PAGE_SIZE); /* clean up user pgd */
+ make_pages_readonly(pgd, 2);
+
+ xen_pgd_pin(__pa(pgd)); /* kernel */
+ xen_pgd_pin(__pa(__user_pgd(pgd))); /* user */
+ /*
+ * Set level3_user_pgt for vsyscall area
+ */
+ set_pgd(__user_pgd(pgd) + pgd_index(VSYSCALL_START),
+ mk_kernel_pgd(__pa_symbol(level3_user_pgt)));
+ return pgd;
+}
+
+static inline void pgd_free(pgd_t *pgd)
+{
+ BUG_ON((unsigned long)pgd & (PAGE_SIZE-1));
+ xen_pgd_unpin(__pa(pgd));
+ xen_pgd_unpin(__pa(__user_pgd(pgd)));
+ make_pages_writable(pgd, 2);
+ free_pages((unsigned long)pgd, 1);
+}
+
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long
address)
+{
+ pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+ if (!pte)
+ return NULL;
+ make_page_readonly(pte);
+ xen_pte_pin(__pa(pte));
+ return pte;
+}
+
+static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long
address)
+{
+ pte_t *pte = (void *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+ if (!pte)
+ return NULL;
+ make_page_readonly(pte);
+ xen_pte_pin(__pa(pte));
+ return virt_to_page((unsigned long)pte);
+}
+
+/* Should really implement gc for free page table pages. This could be
+ done with a reference count in struct page. */
+
+extern __inline__ void pte_free_kernel(pte_t *pte)
+{
+ BUG_ON((unsigned long)pte & (PAGE_SIZE-1));
+ xen_pte_unpin(__pa(pte));
+ make_page_writable(pte);
+ free_page((unsigned long)pte);
+}
+
+extern void pte_free(struct page *pte);
+
+//#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte))
+
+#define __pte_free_tlb(tlb,x) pte_free((x))
+#define __pmd_free_tlb(tlb,x) pmd_free((x))
+#define __pud_free_tlb(tlb,x) pud_free((x))
+
+#endif /* _X86_64_PGALLOC_H */
diff -r 35b74976f598 -r a83ac0806d6b patches/linux-2.6.11/x86_64-linux.patch
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/patches/linux-2.6.11/x86_64-linux.patch Fri Jul 15 13:39:50 2005
@@ -0,0 +1,68 @@
+diff -urN linux-2.6.10-orig/include/asm-x86_64/hw_irq.h
linux-2.6.10/include/asm-x86_64/hw_irq.h
+--- linux-2.6.10-orig/include/asm-x86_64/hw_irq.h 2005-01-06
00:34:38.000000000 -0500
++++ linux-2.6.10/include/asm-x86_64/hw_irq.h 2005-02-25 17:45:37.181518088
-0500
+@@ -48,6 +48,7 @@
+ *
+ * Vectors 0xf0-0xf9 are free (reserved for future Linux use).
+ */
++#ifndef CONFIG_XEN
+ #define SPURIOUS_APIC_VECTOR 0xff
+ #define ERROR_APIC_VECTOR 0xfe
+ #define INVALIDATE_TLB_VECTOR 0xfd
+@@ -57,7 +58,7 @@
+ #define KDB_VECTOR 0xf9
+
+ #define THERMAL_APIC_VECTOR 0xf0
+-
++#endif
+
+ /*
+ * Local APIC timer IRQ vector is on a different priority level,
+diff -urN linux-2.6.10-orig/include/asm-x86_64/irq.h
linux-2.6.10/include/asm-x86_64/irq.h
+--- linux-2.6.10-orig/include/asm-x86_64/irq.h 2005-01-06 00:34:38.000000000
-0500
++++ linux-2.6.10/include/asm-x86_64/irq.h 2005-02-25 17:45:37.181518088
-0500
+@@ -10,6 +10,9 @@
+ * <tomsoft@xxxxxxxxxxxxxxxxxxxxxxxxx>
+ */
+
++#ifdef CONFIG_XEN
++#include "irq_vectors.h"
++#endif
+ #define TIMER_IRQ 0
+
+ /*
+@@ -22,6 +25,7 @@
+ * the usable vector space is 0x20-0xff (224 vectors)
+ */
+
++#ifndef CONFIG_XEN
+ /*
+ * The maximum number of vectors supported by x86_64 processors
+ * is limited to 256. For processors other than x86_64, NR_VECTORS
+@@ -38,6 +42,7 @@
+ #define NR_IRQS 224
+ #define NR_IRQ_VECTORS 1024
+ #endif
++#endif
+
+ static __inline__ int irq_canonicalize(int irq)
+ {
+diff -urN linux-2.6.10-orig/include/asm-x86_64/posix_types.h
linux-2.6.10/include/asm-x86_64/posix_types.h
+--- linux-2.6.10-orig/include/asm-x86_64/posix_types.h 2004-10-18
17:55:29.000000000 -0400
++++ linux-2.6.10/include/asm-x86_64/posix_types.h 2005-02-25
17:45:37.183517784 -0500
+@@ -6,7 +6,7 @@
+ * be a little careful about namespace pollution etc. Also, we cannot
+ * assume GCC is being used.
+ */
+-
++#ifndef __ASSEMBLY__
+ typedef unsigned long __kernel_ino_t;
+ typedef unsigned int __kernel_mode_t;
+ typedef unsigned long __kernel_nlink_t;
+@@ -115,5 +115,5 @@
+ }
+
+ #endif /* defined(__KERNEL__) */
+-
++#endif
+ #endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/xor.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/xor.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,879 @@
+/*
+ * include/asm-i386/xor.h
+ *
+ * Optimized RAID-5 checksumming functions for MMX and SSE.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * You should have received a copy of the GNU General Public License
+ * (for example /usr/src/linux/COPYING); if not, write to the Free
+ * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/*
+ * High-speed RAID5 checksumming functions utilizing MMX instructions.
+ * Copyright (C) 1998 Ingo Molnar.
+ */
+
+#define FPU_SAVE \
+ do { \
+ if (!(current->flags & PF_USEDFPU)) \
+ clts(); \
+ __asm__ __volatile__ ("fsave %0; fwait": "=m"(fpu_save[0])); \
+ } while (0)
+
+#define FPU_RESTORE \
+ do { \
+ __asm__ __volatile__ ("frstor %0": : "m"(fpu_save[0])); \
+ if (!(current->flags & PF_USEDFPU)) \
+ stts(); \
+ } while (0)
+
+#define LD(x,y) " movq 8*("#x")(%1), %%mm"#y" ;\n"
+#define ST(x,y) " movq %%mm"#y", 8*("#x")(%1) ;\n"
+#define XO1(x,y) " pxor 8*("#x")(%2), %%mm"#y" ;\n"
+#define XO2(x,y) " pxor 8*("#x")(%3), %%mm"#y" ;\n"
+#define XO3(x,y) " pxor 8*("#x")(%4), %%mm"#y" ;\n"
+#define XO4(x,y) " pxor 8*("#x")(%5), %%mm"#y" ;\n"
+
+
+static void
+xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+ unsigned long lines = bytes >> 7;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ XO1(i,0) \
+ ST(i,0) \
+ XO1(i+1,1) \
+ ST(i+1,1) \
+ XO1(i+2,2) \
+ ST(i+2,2) \
+ XO1(i+3,3) \
+ ST(i+3,3)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $128, %1 ;\n"
+ " addl $128, %2 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2)
+ :
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static void
+xor_pII_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3)
+{
+ unsigned long lines = bytes >> 7;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ XO2(i,0) \
+ ST(i,0) \
+ XO2(i+1,1) \
+ ST(i+1,1) \
+ XO2(i+2,2) \
+ ST(i+2,2) \
+ XO2(i+3,3) \
+ ST(i+3,3)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $128, %1 ;\n"
+ " addl $128, %2 ;\n"
+ " addl $128, %3 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3)
+ :
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static void
+xor_pII_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4)
+{
+ unsigned long lines = bytes >> 7;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ XO3(i,0) \
+ ST(i,0) \
+ XO3(i+1,1) \
+ ST(i+1,1) \
+ XO3(i+2,2) \
+ ST(i+2,2) \
+ XO3(i+3,3) \
+ ST(i+3,3)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $128, %1 ;\n"
+ " addl $128, %2 ;\n"
+ " addl $128, %3 ;\n"
+ " addl $128, %4 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
+ :
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+
+static void
+xor_pII_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+ unsigned long lines = bytes >> 7;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ /* need to save/restore p4/p5 manually otherwise gcc's 10 argument
+ limit gets exceeded (+ counts as two arguments) */
+ __asm__ __volatile__ (
+ " pushl %4\n"
+ " pushl %5\n"
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ XO3(i,0) \
+ XO3(i+1,1) \
+ XO3(i+2,2) \
+ XO3(i+3,3) \
+ XO4(i,0) \
+ ST(i,0) \
+ XO4(i+1,1) \
+ ST(i+1,1) \
+ XO4(i+2,2) \
+ ST(i+2,2) \
+ XO4(i+3,3) \
+ ST(i+3,3)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $128, %1 ;\n"
+ " addl $128, %2 ;\n"
+ " addl $128, %3 ;\n"
+ " addl $128, %4 ;\n"
+ " addl $128, %5 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ " popl %5\n"
+ " popl %4\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3)
+ : "r" (p4), "r" (p5)
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+#undef LD
+#undef XO1
+#undef XO2
+#undef XO3
+#undef XO4
+#undef ST
+#undef BLOCK
+
+static void
+xor_p5_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+ unsigned long lines = bytes >> 6;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+ " .align 32 ;\n"
+ " 1: ;\n"
+ " movq (%1), %%mm0 ;\n"
+ " movq 8(%1), %%mm1 ;\n"
+ " pxor (%2), %%mm0 ;\n"
+ " movq 16(%1), %%mm2 ;\n"
+ " movq %%mm0, (%1) ;\n"
+ " pxor 8(%2), %%mm1 ;\n"
+ " movq 24(%1), %%mm3 ;\n"
+ " movq %%mm1, 8(%1) ;\n"
+ " pxor 16(%2), %%mm2 ;\n"
+ " movq 32(%1), %%mm4 ;\n"
+ " movq %%mm2, 16(%1) ;\n"
+ " pxor 24(%2), %%mm3 ;\n"
+ " movq 40(%1), %%mm5 ;\n"
+ " movq %%mm3, 24(%1) ;\n"
+ " pxor 32(%2), %%mm4 ;\n"
+ " movq 48(%1), %%mm6 ;\n"
+ " movq %%mm4, 32(%1) ;\n"
+ " pxor 40(%2), %%mm5 ;\n"
+ " movq 56(%1), %%mm7 ;\n"
+ " movq %%mm5, 40(%1) ;\n"
+ " pxor 48(%2), %%mm6 ;\n"
+ " pxor 56(%2), %%mm7 ;\n"
+ " movq %%mm6, 48(%1) ;\n"
+ " movq %%mm7, 56(%1) ;\n"
+
+ " addl $64, %1 ;\n"
+ " addl $64, %2 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2)
+ :
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static void
+xor_p5_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3)
+{
+ unsigned long lines = bytes >> 6;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+ " .align 32,0x90 ;\n"
+ " 1: ;\n"
+ " movq (%1), %%mm0 ;\n"
+ " movq 8(%1), %%mm1 ;\n"
+ " pxor (%2), %%mm0 ;\n"
+ " movq 16(%1), %%mm2 ;\n"
+ " pxor 8(%2), %%mm1 ;\n"
+ " pxor (%3), %%mm0 ;\n"
+ " pxor 16(%2), %%mm2 ;\n"
+ " movq %%mm0, (%1) ;\n"
+ " pxor 8(%3), %%mm1 ;\n"
+ " pxor 16(%3), %%mm2 ;\n"
+ " movq 24(%1), %%mm3 ;\n"
+ " movq %%mm1, 8(%1) ;\n"
+ " movq 32(%1), %%mm4 ;\n"
+ " movq 40(%1), %%mm5 ;\n"
+ " pxor 24(%2), %%mm3 ;\n"
+ " movq %%mm2, 16(%1) ;\n"
+ " pxor 32(%2), %%mm4 ;\n"
+ " pxor 24(%3), %%mm3 ;\n"
+ " pxor 40(%2), %%mm5 ;\n"
+ " movq %%mm3, 24(%1) ;\n"
+ " pxor 32(%3), %%mm4 ;\n"
+ " pxor 40(%3), %%mm5 ;\n"
+ " movq 48(%1), %%mm6 ;\n"
+ " movq %%mm4, 32(%1) ;\n"
+ " movq 56(%1), %%mm7 ;\n"
+ " pxor 48(%2), %%mm6 ;\n"
+ " movq %%mm5, 40(%1) ;\n"
+ " pxor 56(%2), %%mm7 ;\n"
+ " pxor 48(%3), %%mm6 ;\n"
+ " pxor 56(%3), %%mm7 ;\n"
+ " movq %%mm6, 48(%1) ;\n"
+ " movq %%mm7, 56(%1) ;\n"
+
+ " addl $64, %1 ;\n"
+ " addl $64, %2 ;\n"
+ " addl $64, %3 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3)
+ :
+ : "memory" );
+
+ FPU_RESTORE;
+}
+
+static void
+xor_p5_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4)
+{
+ unsigned long lines = bytes >> 6;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ __asm__ __volatile__ (
+ " .align 32,0x90 ;\n"
+ " 1: ;\n"
+ " movq (%1), %%mm0 ;\n"
+ " movq 8(%1), %%mm1 ;\n"
+ " pxor (%2), %%mm0 ;\n"
+ " movq 16(%1), %%mm2 ;\n"
+ " pxor 8(%2), %%mm1 ;\n"
+ " pxor (%3), %%mm0 ;\n"
+ " pxor 16(%2), %%mm2 ;\n"
+ " pxor 8(%3), %%mm1 ;\n"
+ " pxor (%4), %%mm0 ;\n"
+ " movq 24(%1), %%mm3 ;\n"
+ " pxor 16(%3), %%mm2 ;\n"
+ " pxor 8(%4), %%mm1 ;\n"
+ " movq %%mm0, (%1) ;\n"
+ " movq 32(%1), %%mm4 ;\n"
+ " pxor 24(%2), %%mm3 ;\n"
+ " pxor 16(%4), %%mm2 ;\n"
+ " movq %%mm1, 8(%1) ;\n"
+ " movq 40(%1), %%mm5 ;\n"
+ " pxor 32(%2), %%mm4 ;\n"
+ " pxor 24(%3), %%mm3 ;\n"
+ " movq %%mm2, 16(%1) ;\n"
+ " pxor 40(%2), %%mm5 ;\n"
+ " pxor 32(%3), %%mm4 ;\n"
+ " pxor 24(%4), %%mm3 ;\n"
+ " movq %%mm3, 24(%1) ;\n"
+ " movq 56(%1), %%mm7 ;\n"
+ " movq 48(%1), %%mm6 ;\n"
+ " pxor 40(%3), %%mm5 ;\n"
+ " pxor 32(%4), %%mm4 ;\n"
+ " pxor 48(%2), %%mm6 ;\n"
+ " movq %%mm4, 32(%1) ;\n"
+ " pxor 56(%2), %%mm7 ;\n"
+ " pxor 40(%4), %%mm5 ;\n"
+ " pxor 48(%3), %%mm6 ;\n"
+ " pxor 56(%3), %%mm7 ;\n"
+ " movq %%mm5, 40(%1) ;\n"
+ " pxor 48(%4), %%mm6 ;\n"
+ " pxor 56(%4), %%mm7 ;\n"
+ " movq %%mm6, 48(%1) ;\n"
+ " movq %%mm7, 56(%1) ;\n"
+
+ " addl $64, %1 ;\n"
+ " addl $64, %2 ;\n"
+ " addl $64, %3 ;\n"
+ " addl $64, %4 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
+ :
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static void
+xor_p5_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+ unsigned long lines = bytes >> 6;
+ char fpu_save[108];
+
+ FPU_SAVE;
+
+ /* need to save p4/p5 manually to not exceed gcc's 10 argument limit */
+ __asm__ __volatile__ (
+ " pushl %4\n"
+ " pushl %5\n"
+ " .align 32,0x90 ;\n"
+ " 1: ;\n"
+ " movq (%1), %%mm0 ;\n"
+ " movq 8(%1), %%mm1 ;\n"
+ " pxor (%2), %%mm0 ;\n"
+ " pxor 8(%2), %%mm1 ;\n"
+ " movq 16(%1), %%mm2 ;\n"
+ " pxor (%3), %%mm0 ;\n"
+ " pxor 8(%3), %%mm1 ;\n"
+ " pxor 16(%2), %%mm2 ;\n"
+ " pxor (%4), %%mm0 ;\n"
+ " pxor 8(%4), %%mm1 ;\n"
+ " pxor 16(%3), %%mm2 ;\n"
+ " movq 24(%1), %%mm3 ;\n"
+ " pxor (%5), %%mm0 ;\n"
+ " pxor 8(%5), %%mm1 ;\n"
+ " movq %%mm0, (%1) ;\n"
+ " pxor 16(%4), %%mm2 ;\n"
+ " pxor 24(%2), %%mm3 ;\n"
+ " movq %%mm1, 8(%1) ;\n"
+ " pxor 16(%5), %%mm2 ;\n"
+ " pxor 24(%3), %%mm3 ;\n"
+ " movq 32(%1), %%mm4 ;\n"
+ " movq %%mm2, 16(%1) ;\n"
+ " pxor 24(%4), %%mm3 ;\n"
+ " pxor 32(%2), %%mm4 ;\n"
+ " movq 40(%1), %%mm5 ;\n"
+ " pxor 24(%5), %%mm3 ;\n"
+ " pxor 32(%3), %%mm4 ;\n"
+ " pxor 40(%2), %%mm5 ;\n"
+ " movq %%mm3, 24(%1) ;\n"
+ " pxor 32(%4), %%mm4 ;\n"
+ " pxor 40(%3), %%mm5 ;\n"
+ " movq 48(%1), %%mm6 ;\n"
+ " movq 56(%1), %%mm7 ;\n"
+ " pxor 32(%5), %%mm4 ;\n"
+ " pxor 40(%4), %%mm5 ;\n"
+ " pxor 48(%2), %%mm6 ;\n"
+ " pxor 56(%2), %%mm7 ;\n"
+ " movq %%mm4, 32(%1) ;\n"
+ " pxor 48(%3), %%mm6 ;\n"
+ " pxor 56(%3), %%mm7 ;\n"
+ " pxor 40(%5), %%mm5 ;\n"
+ " pxor 48(%4), %%mm6 ;\n"
+ " pxor 56(%4), %%mm7 ;\n"
+ " movq %%mm5, 40(%1) ;\n"
+ " pxor 48(%5), %%mm6 ;\n"
+ " pxor 56(%5), %%mm7 ;\n"
+ " movq %%mm6, 48(%1) ;\n"
+ " movq %%mm7, 56(%1) ;\n"
+
+ " addl $64, %1 ;\n"
+ " addl $64, %2 ;\n"
+ " addl $64, %3 ;\n"
+ " addl $64, %4 ;\n"
+ " addl $64, %5 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ " popl %5\n"
+ " popl %4\n"
+ : "+g" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3)
+ : "r" (p4), "r" (p5)
+ : "memory");
+
+ FPU_RESTORE;
+}
+
+static struct xor_block_template xor_block_pII_mmx = {
+ name: "pII_mmx",
+ do_2: xor_pII_mmx_2,
+ do_3: xor_pII_mmx_3,
+ do_4: xor_pII_mmx_4,
+ do_5: xor_pII_mmx_5,
+};
+
+static struct xor_block_template xor_block_p5_mmx = {
+ name: "p5_mmx",
+ do_2: xor_p5_mmx_2,
+ do_3: xor_p5_mmx_3,
+ do_4: xor_p5_mmx_4,
+ do_5: xor_p5_mmx_5,
+};
+
+#undef FPU_SAVE
+#undef FPU_RESTORE
+
+/*
+ * Cache avoiding checksumming functions utilizing KNI instructions
+ * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
+ */
+
+#define XMMS_SAVE \
+ if (!(current->flags & PF_USEDFPU)) \
+ clts(); \
+ __asm__ __volatile__ ( \
+ "movups %%xmm0,(%1) ;\n\t" \
+ "movups %%xmm1,0x10(%1) ;\n\t" \
+ "movups %%xmm2,0x20(%1) ;\n\t" \
+ "movups %%xmm3,0x30(%1) ;\n\t" \
+ : "=&r" (cr0) \
+ : "r" (xmm_save) \
+ : "memory")
+
+#define XMMS_RESTORE \
+ __asm__ __volatile__ ( \
+ "sfence ;\n\t" \
+ "movups (%1),%%xmm0 ;\n\t" \
+ "movups 0x10(%1),%%xmm1 ;\n\t" \
+ "movups 0x20(%1),%%xmm2 ;\n\t" \
+ "movups 0x30(%1),%%xmm3 ;\n\t" \
+ : \
+ : "r" (cr0), "r" (xmm_save) \
+ : "memory"); \
+ if (!(current->flags & PF_USEDFPU)) \
+ stts()
+
+#define ALIGN16 __attribute__((aligned(16)))
+
+#define OFFS(x) "16*("#x")"
+#define PF_OFFS(x) "256+16*("#x")"
+#define PF0(x) " prefetchnta "PF_OFFS(x)"(%1)
;\n"
+#define LD(x,y) " movaps "OFFS(x)"(%1), %%xmm"#y"
;\n"
+#define ST(x,y) " movaps %%xmm"#y", "OFFS(x)"(%1)
;\n"
+#define PF1(x) " prefetchnta "PF_OFFS(x)"(%2) ;\n"
+#define PF2(x) " prefetchnta "PF_OFFS(x)"(%3) ;\n"
+#define PF3(x) " prefetchnta "PF_OFFS(x)"(%4) ;\n"
+#define PF4(x) " prefetchnta "PF_OFFS(x)"(%5) ;\n"
+#define PF5(x) " prefetchnta "PF_OFFS(x)"(%6) ;\n"
+#define XO1(x,y) " xorps "OFFS(x)"(%2), %%xmm"#y" ;\n"
+#define XO2(x,y) " xorps "OFFS(x)"(%3), %%xmm"#y" ;\n"
+#define XO3(x,y) " xorps "OFFS(x)"(%4), %%xmm"#y" ;\n"
+#define XO4(x,y) " xorps "OFFS(x)"(%5), %%xmm"#y" ;\n"
+#define XO5(x,y) " xorps "OFFS(x)"(%6), %%xmm"#y" ;\n"
+
+
+static void
+xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+ unsigned long lines = bytes >> 8;
+ char xmm_save[16*4] ALIGN16;
+ int cr0;
+
+ XMMS_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ LD(i,0) \
+ LD(i+1,1) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $256, %1 ;\n"
+ " addl $256, %2 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2)
+ :
+ : "memory");
+
+ XMMS_RESTORE;
+}
+
+static void
+xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3)
+{
+ unsigned long lines = bytes >> 8;
+ char xmm_save[16*4] ALIGN16;
+ int cr0;
+
+ XMMS_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF2(i) \
+ PF2(i+2) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $256, %1 ;\n"
+ " addl $256, %2 ;\n"
+ " addl $256, %3 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r"(p2), "+r"(p3)
+ :
+ : "memory" );
+
+ XMMS_RESTORE;
+}
+
+static void
+xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4)
+{
+ unsigned long lines = bytes >> 8;
+ char xmm_save[16*4] ALIGN16;
+ int cr0;
+
+ XMMS_SAVE;
+
+ __asm__ __volatile__ (
+#undef BLOCK
+#define BLOCK(i) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF2(i) \
+ PF2(i+2) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ PF3(i) \
+ PF3(i+2) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ XO3(i,0) \
+ XO3(i+1,1) \
+ XO3(i+2,2) \
+ XO3(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $256, %1 ;\n"
+ " addl $256, %2 ;\n"
+ " addl $256, %3 ;\n"
+ " addl $256, %4 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
+ :
+ : "memory" );
+
+ XMMS_RESTORE;
+}
+
+static void
+xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+ unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+ unsigned long lines = bytes >> 8;
+ char xmm_save[16*4] ALIGN16;
+ int cr0;
+
+ XMMS_SAVE;
+
+ /* need to save p4/p5 manually to not exceed gcc's 10 argument limit */
+ __asm__ __volatile__ (
+ " pushl %4\n"
+ " pushl %5\n"
+#undef BLOCK
+#define BLOCK(i) \
+ PF1(i) \
+ PF1(i+2) \
+ LD(i,0) \
+ LD(i+1,1) \
+ LD(i+2,2) \
+ LD(i+3,3) \
+ PF2(i) \
+ PF2(i+2) \
+ XO1(i,0) \
+ XO1(i+1,1) \
+ XO1(i+2,2) \
+ XO1(i+3,3) \
+ PF3(i) \
+ PF3(i+2) \
+ XO2(i,0) \
+ XO2(i+1,1) \
+ XO2(i+2,2) \
+ XO2(i+3,3) \
+ PF4(i) \
+ PF4(i+2) \
+ PF0(i+4) \
+ PF0(i+6) \
+ XO3(i,0) \
+ XO3(i+1,1) \
+ XO3(i+2,2) \
+ XO3(i+3,3) \
+ XO4(i,0) \
+ XO4(i+1,1) \
+ XO4(i+2,2) \
+ XO4(i+3,3) \
+ ST(i,0) \
+ ST(i+1,1) \
+ ST(i+2,2) \
+ ST(i+3,3) \
+
+
+ PF0(0)
+ PF0(2)
+
+ " .align 32 ;\n"
+ " 1: ;\n"
+
+ BLOCK(0)
+ BLOCK(4)
+ BLOCK(8)
+ BLOCK(12)
+
+ " addl $256, %1 ;\n"
+ " addl $256, %2 ;\n"
+ " addl $256, %3 ;\n"
+ " addl $256, %4 ;\n"
+ " addl $256, %5 ;\n"
+ " decl %0 ;\n"
+ " jnz 1b ;\n"
+ " popl %5\n"
+ " popl %4\n"
+ : "+r" (lines),
+ "+r" (p1), "+r" (p2), "+r" (p3)
+ : "r" (p4), "r" (p5)
+ : "memory");
+
+ XMMS_RESTORE;
+}
+
+static struct xor_block_template xor_block_pIII_sse = {
+ name: "pIII_sse",
+ do_2: xor_sse_2,
+ do_3: xor_sse_3,
+ do_4: xor_sse_4,
+ do_5: xor_sse_5,
+};
+
+/* Also try the generic routines. */
+#include <asm-generic/xor.h>
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES \
+ do { \
+ xor_speed(&xor_block_8regs); \
+ xor_speed(&xor_block_32regs); \
+ if (cpu_has_xmm) \
+ xor_speed(&xor_block_pIII_sse); \
+ if (md_cpu_has_mmx()) { \
+ xor_speed(&xor_block_pII_mmx); \
+ xor_speed(&xor_block_p5_mmx); \
+ } \
+ } while (0)
+
+/* We force the use of the SSE xor block because it can write around L2.
+ We may also be able to load into the L1 only depending on how the cpu
+ deals with a load to a line that is being prefetched. */
+#define XOR_SELECT_TEMPLATE(FASTEST) \
+ (cpu_has_xmm ? &xor_block_pIII_sse : FASTEST)
diff -r 35b74976f598 -r a83ac0806d6b patches/linux-2.6.11/net-csum.patch
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/patches/linux-2.6.11/net-csum.patch Fri Jul 15 13:39:50 2005
@@ -0,0 +1,22 @@
+diff -ur linux-2.6.11/net/ipv4/netfilter/ip_conntrack_proto_tcp.c
linux-2.6.11-csum/net/ipv4/netfilter/ip_conntrack_proto_tcp.c
+--- linux-2.6.11/net/ipv4/netfilter/ip_conntrack_proto_tcp.c 2005-05-27
11:47:48 +01:00
++++ linux-2.6.11-csum/net/ipv4/netfilter/ip_conntrack_proto_tcp.c
2005-05-27 11:48:07 +01:00
+@@ -803,6 +803,7 @@
+ */
+ /* FIXME: Source route IP option packets --RR */
+ if (hooknum == NF_IP_PRE_ROUTING
++ && skb->ip_summed != CHECKSUM_UNNECESSARY
+ && csum_tcpudp_magic(iph->saddr, iph->daddr, tcplen, IPPROTO_TCP,
+ skb->ip_summed == CHECKSUM_HW ? skb->csum
+ : skb_checksum(skb, iph->ihl*4, tcplen, 0))) {
+diff -ur linux-2.6.11/net/ipv4/netfilter/ip_conntrack_proto_udp.c
linux-2.6.11-csum/net/ipv4/netfilter/ip_conntrack_proto_udp.c
+--- linux-2.6.11/net/ipv4/netfilter/ip_conntrack_proto_udp.c 2005-05-27
11:47:48 +01:00
++++ linux-2.6.11-csum/net/ipv4/netfilter/ip_conntrack_proto_udp.c
2005-05-27 11:48:07 +01:00
+@@ -120,6 +120,7 @@
+ * and moreover root might send raw packets.
+ * FIXME: Source route IP option packets --RR */
+ if (hooknum == NF_IP_PRE_ROUTING
++ && skb->ip_summed != CHECKSUM_UNNECESSARY
+ && csum_tcpudp_magic(iph->saddr, iph->daddr, udplen, IPPROTO_UDP,
+ skb->ip_summed == CHECKSUM_HW ? skb->csum
+ : skb_checksum(skb, iph->ihl*4, udplen, 0))) {
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/linux/skbuff.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/linux/skbuff.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,1184 @@
+/*
+ * Definitions for the 'struct sk_buff' memory handlers.
+ *
+ * Authors:
+ * Alan Cox, <gw4pts@xxxxxxxxxxxxxxx>
+ * Florian La Roche, <rzsfl@xxxxxxxxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_SKBUFF_H
+#define _LINUX_SKBUFF_H
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <linux/time.h>
+#include <linux/cache.h>
+
+#include <asm/atomic.h>
+#include <asm/types.h>
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/poll.h>
+#include <linux/net.h>
+#include <net/checksum.h>
+
+#define HAVE_ALLOC_SKB /* For the drivers to know */
+#define HAVE_ALIGNABLE_SKB /* Ditto 8) */
+#define SLAB_SKB /* Slabified skbuffs */
+
+#define CHECKSUM_NONE 0
+#define CHECKSUM_HW 1
+#define CHECKSUM_UNNECESSARY 2
+
+#define SKB_DATA_ALIGN(X) (((X) + (SMP_CACHE_BYTES - 1)) & \
+ ~(SMP_CACHE_BYTES - 1))
+#define SKB_MAX_ORDER(X, ORDER) (((PAGE_SIZE << (ORDER)) - (X) - \
+ sizeof(struct skb_shared_info)) & \
+ ~(SMP_CACHE_BYTES - 1))
+#define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X), 0))
+#define SKB_MAX_ALLOC (SKB_MAX_ORDER(0, 2))
+
+/* A. Checksumming of received packets by device.
+ *
+ * NONE: device failed to checksum this packet.
+ * skb->csum is undefined.
+ *
+ * UNNECESSARY: device parsed packet and wouldbe verified checksum.
+ * skb->csum is undefined.
+ * It is bad option, but, unfortunately, many of vendors do this.
+ * Apparently with secret goal to sell you new device, when you
+ * will add new protocol to your host. F.e. IPv6. 8)
+ *
+ * HW: the most generic way. Device supplied checksum of _all_
+ * the packet as seen by netif_rx in skb->csum.
+ * NOTE: Even if device supports only some protocols, but
+ * is able to produce some skb->csum, it MUST use HW,
+ * not UNNECESSARY.
+ *
+ * B. Checksumming on output.
+ *
+ * NONE: skb is checksummed by protocol or csum is not required.
+ *
+ * HW: device is required to csum packet as seen by hard_start_xmit
+ * from skb->h.raw to the end and to record the checksum
+ * at skb->h.raw+skb->csum.
+ *
+ * Device must show its capabilities in dev->features, set
+ * at device setup time.
+ * NETIF_F_HW_CSUM - it is clever device, it is able to checksum
+ * everything.
+ * NETIF_F_NO_CSUM - loopback or reliable single hop media.
+ * NETIF_F_IP_CSUM - device is dumb. It is able to csum only
+ * TCP/UDP over IPv4. Sigh. Vendors like this
+ * way by an unknown reason. Though, see comment above
+ * about CHECKSUM_UNNECESSARY. 8)
+ *
+ * Any questions? No questions, good. --ANK
+ */
+
+#ifdef __i386__
+#define NET_CALLER(arg) (*(((void **)&arg) - 1))
+#else
+#define NET_CALLER(arg) __builtin_return_address(0)
+#endif
+
+struct net_device;
+
+#ifdef CONFIG_NETFILTER
+struct nf_conntrack {
+ atomic_t use;
+ void (*destroy)(struct nf_conntrack *);
+};
+
+#ifdef CONFIG_BRIDGE_NETFILTER
+struct nf_bridge_info {
+ atomic_t use;
+ struct net_device *physindev;
+ struct net_device *physoutdev;
+#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
+ struct net_device *netoutdev;
+#endif
+ unsigned int mask;
+ unsigned long data[32 / sizeof(unsigned long)];
+};
+#endif
+
+#endif
+
+struct sk_buff_head {
+ /* These two members must be first. */
+ struct sk_buff *next;
+ struct sk_buff *prev;
+
+ __u32 qlen;
+ spinlock_t lock;
+};
+
+struct sk_buff;
+
+/* To allow 64K frame to be packed as single skb without frag_list */
+#define MAX_SKB_FRAGS (65536/PAGE_SIZE + 2)
+
+typedef struct skb_frag_struct skb_frag_t;
+
+struct skb_frag_struct {
+ struct page *page;
+ __u16 page_offset;
+ __u16 size;
+};
+
+/* This data is invariant across clones and lives at
+ * the end of the header data, ie. at skb->end.
+ */
+struct skb_shared_info {
+ atomic_t dataref;
+ unsigned int nr_frags;
+ unsigned short tso_size;
+ unsigned short tso_segs;
+ struct sk_buff *frag_list;
+ skb_frag_t frags[MAX_SKB_FRAGS];
+};
+
+/**
+ * struct sk_buff - socket buffer
+ * @next: Next buffer in list
+ * @prev: Previous buffer in list
+ * @list: List we are on
+ * @sk: Socket we are owned by
+ * @stamp: Time we arrived
+ * @dev: Device we arrived on/are leaving by
+ * @input_dev: Device we arrived on
+ * @real_dev: The real device we are using
+ * @h: Transport layer header
+ * @nh: Network layer header
+ * @mac: Link layer header
+ * @dst: FIXME: Describe this field
+ * @cb: Control buffer. Free for use by every layer. Put private vars here
+ * @len: Length of actual data
+ * @data_len: Data length
+ * @mac_len: Length of link layer header
+ * @csum: Checksum
+ * @__unused: Dead field, may be reused
+ * @cloned: Head may be cloned (check refcnt to be sure)
+ * @proto_csum_valid: Protocol csum validated since arriving at localhost
+ * @proto_csum_blank: Protocol csum must be added before leaving localhost
+ * @pkt_type: Packet class
+ * @ip_summed: Driver fed us an IP checksum
+ * @priority: Packet queueing priority
+ * @users: User count - see {datagram,tcp}.c
+ * @protocol: Packet protocol from driver
+ * @security: Security level of packet
+ * @truesize: Buffer size
+ * @head: Head of buffer
+ * @data: Data head pointer
+ * @tail: Tail pointer
+ * @end: End pointer
+ * @destructor: Destruct function
+ * @nfmark: Can be used for communication between hooks
+ * @nfcache: Cache info
+ * @nfct: Associated connection, if any
+ * @nfctinfo: Relationship of this skb to the connection
+ * @nf_debug: Netfilter debugging
+ * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c
+ * @private: Data which is private to the HIPPI implementation
+ * @tc_index: Traffic control index
+ */
+
+struct sk_buff {
+ /* These two members must be first. */
+ struct sk_buff *next;
+ struct sk_buff *prev;
+
+ struct sk_buff_head *list;
+ struct sock *sk;
+ struct timeval stamp;
+ struct net_device *dev;
+ struct net_device *input_dev;
+ struct net_device *real_dev;
+
+ union {
+ struct tcphdr *th;
+ struct udphdr *uh;
+ struct icmphdr *icmph;
+ struct igmphdr *igmph;
+ struct iphdr *ipiph;
+ struct ipv6hdr *ipv6h;
+ unsigned char *raw;
+ } h;
+
+ union {
+ struct iphdr *iph;
+ struct ipv6hdr *ipv6h;
+ struct arphdr *arph;
+ unsigned char *raw;
+ } nh;
+
+ union {
+ unsigned char *raw;
+ } mac;
+
+ struct dst_entry *dst;
+ struct sec_path *sp;
+
+ /*
+ * This is the control buffer. It is free to use for every
+ * layer. Please put your private variables there. If you
+ * want to keep them across layers you have to do a skb_clone()
+ * first. This is owned by whoever has the skb queued ATM.
+ */
+ char cb[40];
+
+ unsigned int len,
+ data_len,
+ mac_len,
+ csum;
+ unsigned char local_df,
+ cloned:1,
+ proto_csum_valid:1,
+ proto_csum_blank:1,
+ pkt_type,
+ ip_summed;
+ __u32 priority;
+ unsigned short protocol,
+ security;
+
+ void (*destructor)(struct sk_buff *skb);
+#ifdef CONFIG_NETFILTER
+ unsigned long nfmark;
+ __u32 nfcache;
+ __u32 nfctinfo;
+ struct nf_conntrack *nfct;
+#ifdef CONFIG_NETFILTER_DEBUG
+ unsigned int nf_debug;
+#endif
+#ifdef CONFIG_BRIDGE_NETFILTER
+ struct nf_bridge_info *nf_bridge;
+#endif
+#endif /* CONFIG_NETFILTER */
+#if defined(CONFIG_HIPPI)
+ union {
+ __u32 ifield;
+ } private;
+#endif
+#ifdef CONFIG_NET_SCHED
+ __u32 tc_index; /* traffic control index */
+#ifdef CONFIG_NET_CLS_ACT
+ __u32 tc_verd; /* traffic control verdict */
+ __u32 tc_classid; /* traffic control classid */
+#endif
+
+#endif
+
+
+ /* These elements must be at the end, see alloc_skb() for details. */
+ unsigned int truesize;
+ atomic_t users;
+ unsigned char *head,
+ *data,
+ *tail,
+ *end;
+};
+
+#ifdef __KERNEL__
+/*
+ * Handling routines are only of interest to the kernel
+ */
+#include <linux/slab.h>
+
+#include <asm/system.h>
+
+extern void __kfree_skb(struct sk_buff *skb);
+extern struct sk_buff *alloc_skb(unsigned int size, int priority);
+extern struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp,
+ unsigned int size, int priority);
+extern void kfree_skbmem(struct sk_buff *skb);
+extern struct sk_buff *skb_clone(struct sk_buff *skb, int priority);
+extern struct sk_buff *skb_copy(const struct sk_buff *skb, int priority);
+extern struct sk_buff *pskb_copy(struct sk_buff *skb, int gfp_mask);
+extern int pskb_expand_head(struct sk_buff *skb,
+ int nhead, int ntail, int gfp_mask);
+extern struct sk_buff *skb_realloc_headroom(struct sk_buff *skb,
+ unsigned int headroom);
+extern struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
+ int newheadroom, int newtailroom,
+ int priority);
+extern struct sk_buff * skb_pad(struct sk_buff *skb, int pad);
+#define dev_kfree_skb(a) kfree_skb(a)
+extern void skb_over_panic(struct sk_buff *skb, int len,
+ void *here);
+extern void skb_under_panic(struct sk_buff *skb, int len,
+ void *here);
+
+/* Internal */
+#define skb_shinfo(SKB) ((struct skb_shared_info *)((SKB)->end))
+
+/**
+ * skb_queue_empty - check if a queue is empty
+ * @list: queue head
+ *
+ * Returns true if the queue is empty, false otherwise.
+ */
+static inline int skb_queue_empty(const struct sk_buff_head *list)
+{
+ return list->next == (struct sk_buff *)list;
+}
+
+/**
+ * skb_get - reference buffer
+ * @skb: buffer to reference
+ *
+ * Makes another reference to a socket buffer and returns a pointer
+ * to the buffer.
+ */
+static inline struct sk_buff *skb_get(struct sk_buff *skb)
+{
+ atomic_inc(&skb->users);
+ return skb;
+}
+
+/*
+ * If users == 1, we are the only owner and are can avoid redundant
+ * atomic change.
+ */
+
+/**
+ * kfree_skb - free an sk_buff
+ * @skb: buffer to free
+ *
+ * Drop a reference to the buffer and free it if the usage count has
+ * hit zero.
+ */
+static inline void kfree_skb(struct sk_buff *skb)
+{
+ if (likely(atomic_read(&skb->users) == 1))
+ smp_rmb();
+ else if (likely(!atomic_dec_and_test(&skb->users)))
+ return;
+ __kfree_skb(skb);
+}
+
+/**
+ * skb_cloned - is the buffer a clone
+ * @skb: buffer to check
+ *
+ * Returns true if the buffer was generated with skb_clone() and is
+ * one of multiple shared copies of the buffer. Cloned buffers are
+ * shared data so must not be written to under normal circumstances.
+ */
+static inline int skb_cloned(const struct sk_buff *skb)
+{
+ return skb->cloned && atomic_read(&skb_shinfo(skb)->dataref) != 1;
+}
+
+/**
+ * skb_shared - is the buffer shared
+ * @skb: buffer to check
+ *
+ * Returns true if more than one person has a reference to this
+ * buffer.
+ */
+static inline int skb_shared(const struct sk_buff *skb)
+{
+ return atomic_read(&skb->users) != 1;
+}
+
+/**
+ * skb_share_check - check if buffer is shared and if so clone it
+ * @skb: buffer to check
+ * @pri: priority for memory allocation
+ *
+ * If the buffer is shared the buffer is cloned and the old copy
+ * drops a reference. A new clone with a single reference is returned.
+ * If the buffer is not shared the original buffer is returned. When
+ * being called from interrupt status or with spinlocks held pri must
+ * be GFP_ATOMIC.
+ *
+ * NULL is returned on a memory allocation failure.
+ */
+static inline struct sk_buff *skb_share_check(struct sk_buff *skb, int pri)
+{
+ might_sleep_if(pri & __GFP_WAIT);
+ if (skb_shared(skb)) {
+ struct sk_buff *nskb = skb_clone(skb, pri);
+ kfree_skb(skb);
+ skb = nskb;
+ }
+ return skb;
+}
+
+/*
+ * Copy shared buffers into a new sk_buff. We effectively do COW on
+ * packets to handle cases where we have a local reader and forward
+ * and a couple of other messy ones. The normal one is tcpdumping
+ * a packet thats being forwarded.
+ */
+
+/**
+ * skb_unshare - make a copy of a shared buffer
+ * @skb: buffer to check
+ * @pri: priority for memory allocation
+ *
+ * If the socket buffer is a clone then this function creates a new
+ * copy of the data, drops a reference count on the old copy and returns
+ * the new copy with the reference count at 1. If the buffer is not a clone
+ * the original buffer is returned. When called with a spinlock held or
+ * from interrupt state @pri must be %GFP_ATOMIC
+ *
+ * %NULL is returned on a memory allocation failure.
+ */
+static inline struct sk_buff *skb_unshare(struct sk_buff *skb, int pri)
+{
+ might_sleep_if(pri & __GFP_WAIT);
+ if (skb_cloned(skb)) {
+ struct sk_buff *nskb = skb_copy(skb, pri);
+ kfree_skb(skb); /* Free our shared copy */
+ skb = nskb;
+ }
+ return skb;
+}
+
+/**
+ * skb_peek
+ * @list_: list to peek at
+ *
+ * Peek an &sk_buff. Unlike most other operations you _MUST_
+ * be careful with this one. A peek leaves the buffer on the
+ * list and someone else may run off with it. You must hold
+ * the appropriate locks or have a private queue to do this.
+ *
+ * Returns %NULL for an empty list or a pointer to the head element.
+ * The reference count is not incremented and the reference is therefore
+ * volatile. Use with caution.
+ */
+static inline struct sk_buff *skb_peek(struct sk_buff_head *list_)
+{
+ struct sk_buff *list = ((struct sk_buff *)list_)->next;
+ if (list == (struct sk_buff *)list_)
+ list = NULL;
+ return list;
+}
+
+/**
+ * skb_peek_tail
+ * @list_: list to peek at
+ *
+ * Peek an &sk_buff. Unlike most other operations you _MUST_
+ * be careful with this one. A peek leaves the buffer on the
+ * list and someone else may run off with it. You must hold
+ * the appropriate locks or have a private queue to do this.
+ *
+ * Returns %NULL for an empty list or a pointer to the tail element.
+ * The reference count is not incremented and the reference is therefore
+ * volatile. Use with caution.
+ */
+static inline struct sk_buff *skb_peek_tail(struct sk_buff_head *list_)
+{
+ struct sk_buff *list = ((struct sk_buff *)list_)->prev;
+ if (list == (struct sk_buff *)list_)
+ list = NULL;
+ return list;
+}
+
+/**
+ * skb_queue_len - get queue length
+ * @list_: list to measure
+ *
+ * Return the length of an &sk_buff queue.
+ */
+static inline __u32 skb_queue_len(const struct sk_buff_head *list_)
+{
+ return list_->qlen;
+}
+
+static inline void skb_queue_head_init(struct sk_buff_head *list)
+{
+ spin_lock_init(&list->lock);
+ list->prev = list->next = (struct sk_buff *)list;
+ list->qlen = 0;
+}
+
+/*
+ * Insert an sk_buff at the start of a list.
+ *
+ * The "__skb_xxxx()" functions are the non-atomic ones that
+ * can only be called with interrupts disabled.
+ */
+
+/**
+ * __skb_queue_head - queue a buffer at the list head
+ * @list: list to use
+ * @newsk: buffer to queue
+ *
+ * Queue a buffer at the start of a list. This function takes no locks
+ * and you must therefore hold required locks before calling it.
+ *
+ * A buffer cannot be placed on two lists at the same time.
+ */
+extern void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk);
+static inline void __skb_queue_head(struct sk_buff_head *list,
+ struct sk_buff *newsk)
+{
+ struct sk_buff *prev, *next;
+
+ newsk->list = list;
+ list->qlen++;
+ prev = (struct sk_buff *)list;
+ next = prev->next;
+ newsk->next = next;
+ newsk->prev = prev;
+ next->prev = prev->next = newsk;
+}
+
+/**
+ * __skb_queue_tail - queue a buffer at the list tail
+ * @list: list to use
+ * @newsk: buffer to queue
+ *
+ * Queue a buffer at the end of a list. This function takes no locks
+ * and you must therefore hold required locks before calling it.
+ *
+ * A buffer cannot be placed on two lists at the same time.
+ */
+extern void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk);
+static inline void __skb_queue_tail(struct sk_buff_head *list,
+ struct sk_buff *newsk)
+{
+ struct sk_buff *prev, *next;
+
+ newsk->list = list;
+ list->qlen++;
+ next = (struct sk_buff *)list;
+ prev = next->prev;
+ newsk->next = next;
+ newsk->prev = prev;
+ next->prev = prev->next = newsk;
+}
+
+
+/**
+ * __skb_dequeue - remove from the head of the queue
+ * @list: list to dequeue from
+ *
+ * Remove the head of the list. This function does not take any locks
+ * so must be used with appropriate locks held only. The head item is
+ * returned or %NULL if the list is empty.
+ */
+extern struct sk_buff *skb_dequeue(struct sk_buff_head *list);
+static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list)
+{
+ struct sk_buff *next, *prev, *result;
+
+ prev = (struct sk_buff *) list;
+ next = prev->next;
+ result = NULL;
+ if (next != prev) {
+ result = next;
+ next = next->next;
+ list->qlen--;
+ next->prev = prev;
+ prev->next = next;
+ result->next = result->prev = NULL;
+ result->list = NULL;
+ }
+ return result;
+}
+
+
+/*
+ * Insert a packet on a list.
+ */
+extern void skb_insert(struct sk_buff *old, struct sk_buff *newsk);
+static inline void __skb_insert(struct sk_buff *newsk,
+ struct sk_buff *prev, struct sk_buff *next,
+ struct sk_buff_head *list)
+{
+ newsk->next = next;
+ newsk->prev = prev;
+ next->prev = prev->next = newsk;
+ newsk->list = list;
+ list->qlen++;
+}
+
+/*
+ * Place a packet after a given packet in a list.
+ */
+extern void skb_append(struct sk_buff *old, struct sk_buff *newsk);
+static inline void __skb_append(struct sk_buff *old, struct sk_buff *newsk)
+{
+ __skb_insert(newsk, old, old->next, old->list);
+}
+
+/*
+ * remove sk_buff from list. _Must_ be called atomically, and with
+ * the list known..
+ */
+extern void skb_unlink(struct sk_buff *skb);
+static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
+{
+ struct sk_buff *next, *prev;
+
+ list->qlen--;
+ next = skb->next;
+ prev = skb->prev;
+ skb->next = skb->prev = NULL;
+ skb->list = NULL;
+ next->prev = prev;
+ prev->next = next;
+}
+
+
+/* XXX: more streamlined implementation */
+
+/**
+ * __skb_dequeue_tail - remove from the tail of the queue
+ * @list: list to dequeue from
+ *
+ * Remove the tail of the list. This function does not take any locks
+ * so must be used with appropriate locks held only. The tail item is
+ * returned or %NULL if the list is empty.
+ */
+extern struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list);
+static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list)
+{
+ struct sk_buff *skb = skb_peek_tail(list);
+ if (skb)
+ __skb_unlink(skb, list);
+ return skb;
+}
+
+
+static inline int skb_is_nonlinear(const struct sk_buff *skb)
+{
+ return skb->data_len;
+}
+
+static inline unsigned int skb_headlen(const struct sk_buff *skb)
+{
+ return skb->len - skb->data_len;
+}
+
+static inline int skb_pagelen(const struct sk_buff *skb)
+{
+ int i, len = 0;
+
+ for (i = (int)skb_shinfo(skb)->nr_frags - 1; i >= 0; i--)
+ len += skb_shinfo(skb)->frags[i].size;
+ return len + skb_headlen(skb);
+}
+
+static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
+ struct page *page, int off, int size)
+{
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+ frag->page = page;
+ frag->page_offset = off;
+ frag->size = size;
+ skb_shinfo(skb)->nr_frags = i + 1;
+}
+
+#define SKB_PAGE_ASSERT(skb) BUG_ON(skb_shinfo(skb)->nr_frags)
+#define SKB_FRAG_ASSERT(skb) BUG_ON(skb_shinfo(skb)->frag_list)
+#define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb))
+
+/*
+ * Add data to an sk_buff
+ */
+static inline unsigned char *__skb_put(struct sk_buff *skb, unsigned int len)
+{
+ unsigned char *tmp = skb->tail;
+ SKB_LINEAR_ASSERT(skb);
+ skb->tail += len;
+ skb->len += len;
+ return tmp;
+}
+
+/**
+ * skb_put - add data to a buffer
+ * @skb: buffer to use
+ * @len: amount of data to add
+ *
+ * This function extends the used data area of the buffer. If this would
+ * exceed the total buffer size the kernel will panic. A pointer to the
+ * first byte of the extra data is returned.
+ */
+static inline unsigned char *skb_put(struct sk_buff *skb, unsigned int len)
+{
+ unsigned char *tmp = skb->tail;
+ SKB_LINEAR_ASSERT(skb);
+ skb->tail += len;
+ skb->len += len;
+ if (unlikely(skb->tail>skb->end))
+ skb_over_panic(skb, len, current_text_addr());
+ return tmp;
+}
+
+static inline unsigned char *__skb_push(struct sk_buff *skb, unsigned int len)
+{
+ skb->data -= len;
+ skb->len += len;
+ return skb->data;
+}
+
+/**
+ * skb_push - add data to the start of a buffer
+ * @skb: buffer to use
+ * @len: amount of data to add
+ *
+ * This function extends the used data area of the buffer at the buffer
+ * start. If this would exceed the total buffer headroom the kernel will
+ * panic. A pointer to the first byte of the extra data is returned.
+ */
+static inline unsigned char *skb_push(struct sk_buff *skb, unsigned int len)
+{
+ skb->data -= len;
+ skb->len += len;
+ if (unlikely(skb->data<skb->head))
+ skb_under_panic(skb, len, current_text_addr());
+ return skb->data;
+}
+
+static inline unsigned char *__skb_pull(struct sk_buff *skb, unsigned int len)
+{
+ skb->len -= len;
+ BUG_ON(skb->len < skb->data_len);
+ return skb->data += len;
+}
+
+/**
+ * skb_pull - remove data from the start of a buffer
+ * @skb: buffer to use
+ * @len: amount of data to remove
+ *
+ * This function removes data from the start of a buffer, returning
+ * the memory to the headroom. A pointer to the next data in the buffer
+ * is returned. Once the data has been pulled future pushes will overwrite
+ * the old data.
+ */
+static inline unsigned char *skb_pull(struct sk_buff *skb, unsigned int len)
+{
+ return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len);
+}
+
+extern unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta);
+
+static inline unsigned char *__pskb_pull(struct sk_buff *skb, unsigned int len)
+{
+ if (len > skb_headlen(skb) &&
+ !__pskb_pull_tail(skb, len-skb_headlen(skb)))
+ return NULL;
+ skb->len -= len;
+ return skb->data += len;
+}
+
+static inline unsigned char *pskb_pull(struct sk_buff *skb, unsigned int len)
+{
+ return unlikely(len > skb->len) ? NULL : __pskb_pull(skb, len);
+}
+
+static inline int pskb_may_pull(struct sk_buff *skb, unsigned int len)
+{
+ if (likely(len <= skb_headlen(skb)))
+ return 1;
+ if (unlikely(len > skb->len))
+ return 0;
+ return __pskb_pull_tail(skb, len-skb_headlen(skb)) != NULL;
+}
+
+/**
+ * skb_headroom - bytes at buffer head
+ * @skb: buffer to check
+ *
+ * Return the number of bytes of free space at the head of an &sk_buff.
+ */
+static inline int skb_headroom(const struct sk_buff *skb)
+{
+ return skb->data - skb->head;
+}
+
+/**
+ * skb_tailroom - bytes at buffer end
+ * @skb: buffer to check
+ *
+ * Return the number of bytes of free space at the tail of an sk_buff
+ */
+static inline int skb_tailroom(const struct sk_buff *skb)
+{
+ return skb_is_nonlinear(skb) ? 0 : skb->end - skb->tail;
+}
+
+/**
+ * skb_reserve - adjust headroom
+ * @skb: buffer to alter
+ * @len: bytes to move
+ *
+ * Increase the headroom of an empty &sk_buff by reducing the tail
+ * room. This is only allowed for an empty buffer.
+ */
+static inline void skb_reserve(struct sk_buff *skb, unsigned int len)
+{
+ skb->data += len;
+ skb->tail += len;
+}
+
+/*
+ * CPUs often take a performance hit when accessing unaligned memory
+ * locations. The actual performance hit varies, it can be small if the
+ * hardware handles it or large if we have to take an exception and fix it
+ * in software.
+ *
+ * Since an ethernet header is 14 bytes network drivers often end up with
+ * the IP header at an unaligned offset. The IP header can be aligned by
+ * shifting the start of the packet by 2 bytes. Drivers should do this
+ * with:
+ *
+ * skb_reserve(NET_IP_ALIGN);
+ *
+ * The downside to this alignment of the IP header is that the DMA is now
+ * unaligned. On some architectures the cost of an unaligned DMA is high
+ * and this cost outweighs the gains made by aligning the IP header.
+ *
+ * Since this trade off varies between architectures, we allow NET_IP_ALIGN
+ * to be overridden.
+ */
+#ifndef NET_IP_ALIGN
+#define NET_IP_ALIGN 2
+#endif
+
+extern int ___pskb_trim(struct sk_buff *skb, unsigned int len, int realloc);
+
+static inline void __skb_trim(struct sk_buff *skb, unsigned int len)
+{
+ if (!skb->data_len) {
+ skb->len = len;
+ skb->tail = skb->data + len;
+ } else
+ ___pskb_trim(skb, len, 0);
+}
+
+/**
+ * skb_trim - remove end from a buffer
+ * @skb: buffer to alter
+ * @len: new length
+ *
+ * Cut the length of a buffer down by removing data from the tail. If
+ * the buffer is already under the length specified it is not modified.
+ */
+static inline void skb_trim(struct sk_buff *skb, unsigned int len)
+{
+ if (skb->len > len)
+ __skb_trim(skb, len);
+}
+
+
+static inline int __pskb_trim(struct sk_buff *skb, unsigned int len)
+{
+ if (!skb->data_len) {
+ skb->len = len;
+ skb->tail = skb->data+len;
+ return 0;
+ }
+ return ___pskb_trim(skb, len, 1);
+}
+
+static inline int pskb_trim(struct sk_buff *skb, unsigned int len)
+{
+ return (len < skb->len) ? __pskb_trim(skb, len) : 0;
+}
+
+/**
+ * skb_orphan - orphan a buffer
+ * @skb: buffer to orphan
+ *
+ * If a buffer currently has an owner then we call the owner's
+ * destructor function and make the @skb unowned. The buffer continues
+ * to exist but is no longer charged to its former owner.
+ */
+static inline void skb_orphan(struct sk_buff *skb)
+{
+ if (skb->destructor)
+ skb->destructor(skb);
+ skb->destructor = NULL;
+ skb->sk = NULL;
+}
+
+/**
+ * __skb_queue_purge - empty a list
+ * @list: list to empty
+ *
+ * Delete all buffers on an &sk_buff list. Each buffer is removed from
+ * the list and one reference dropped. This function does not take the
+ * list lock and the caller must hold the relevant locks to use it.
+ */
+extern void skb_queue_purge(struct sk_buff_head *list);
+static inline void __skb_queue_purge(struct sk_buff_head *list)
+{
+ struct sk_buff *skb;
+ while ((skb = __skb_dequeue(list)) != NULL)
+ kfree_skb(skb);
+}
+
+/**
+ * __dev_alloc_skb - allocate an skbuff for sending
+ * @length: length to allocate
+ * @gfp_mask: get_free_pages mask, passed to alloc_skb
+ *
+ * Allocate a new &sk_buff and assign it a usage count of one. The
+ * buffer has unspecified headroom built in. Users should allocate
+ * the headroom they think they need without accounting for the
+ * built in space. The built in space is used for optimisations.
+ *
+ * %NULL is returned in there is no free memory.
+ */
+#ifndef CONFIG_HAVE_ARCH_DEV_ALLOC_SKB
+static inline struct sk_buff *__dev_alloc_skb(unsigned int length,
+ int gfp_mask)
+{
+ struct sk_buff *skb = alloc_skb(length + 16, gfp_mask);
+ if (likely(skb))
+ skb_reserve(skb, 16);
+ return skb;
+}
+#else
+extern struct sk_buff *__dev_alloc_skb(unsigned int length, int gfp_mask);
+#endif
+
+/**
+ * dev_alloc_skb - allocate an skbuff for sending
+ * @length: length to allocate
+ *
+ * Allocate a new &sk_buff and assign it a usage count of one. The
+ * buffer has unspecified headroom built in. Users should allocate
+ * the headroom they think they need without accounting for the
+ * built in space. The built in space is used for optimisations.
+ *
+ * %NULL is returned in there is no free memory. Although this function
+ * allocates memory it can be called from an interrupt.
+ */
+static inline struct sk_buff *dev_alloc_skb(unsigned int length)
+{
+ return __dev_alloc_skb(length, GFP_ATOMIC);
+}
+
+/**
+ * skb_cow - copy header of skb when it is required
+ * @skb: buffer to cow
+ * @headroom: needed headroom
+ *
+ * If the skb passed lacks sufficient headroom or its data part
+ * is shared, data is reallocated. If reallocation fails, an error
+ * is returned and original skb is not changed.
+ *
+ * The result is skb with writable area skb->head...skb->tail
+ * and at least @headroom of space at head.
+ */
+static inline int skb_cow(struct sk_buff *skb, unsigned int headroom)
+{
+ int delta = (headroom > 16 ? headroom : 16) - skb_headroom(skb);
+
+ if (delta < 0)
+ delta = 0;
+
+ if (delta || skb_cloned(skb))
+ return pskb_expand_head(skb, (delta + 15) & ~15, 0, GFP_ATOMIC);
+ return 0;
+}
+
+/**
+ * skb_padto - pad an skbuff up to a minimal size
+ * @skb: buffer to pad
+ * @len: minimal length
+ *
+ * Pads up a buffer to ensure the trailing bytes exist and are
+ * blanked. If the buffer already contains sufficient data it
+ * is untouched. Returns the buffer, which may be a replacement
+ * for the original, or NULL for out of memory - in which case
+ * the original buffer is still freed.
+ */
+
+static inline struct sk_buff *skb_padto(struct sk_buff *skb, unsigned int len)
+{
+ unsigned int size = skb->len;
+ if (likely(size >= len))
+ return skb;
+ return skb_pad(skb, len-size);
+}
+
+static inline int skb_add_data(struct sk_buff *skb,
+ char __user *from, int copy)
+{
+ const int off = skb->len;
+
+ if (skb->ip_summed == CHECKSUM_NONE) {
+ int err = 0;
+ unsigned int csum = csum_and_copy_from_user(from,
+ skb_put(skb, copy),
+ copy, 0, &err);
+ if (!err) {
+ skb->csum = csum_block_add(skb->csum, csum, off);
+ return 0;
+ }
+ } else if (!copy_from_user(skb_put(skb, copy), from, copy))
+ return 0;
+
+ __skb_trim(skb, off);
+ return -EFAULT;
+}
+
+static inline int skb_can_coalesce(struct sk_buff *skb, int i,
+ struct page *page, int off)
+{
+ if (i) {
+ struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1];
+
+ return page == frag->page &&
+ off == frag->page_offset + frag->size;
+ }
+ return 0;
+}
+
+/**
+ * skb_linearize - convert paged skb to linear one
+ * @skb: buffer to linarize
+ * @gfp: allocation mode
+ *
+ * If there is no free memory -ENOMEM is returned, otherwise zero
+ * is returned and the old skb data released.
+ */
+extern int __skb_linearize(struct sk_buff *skb, int gfp);
+static inline int skb_linearize(struct sk_buff *skb, int gfp)
+{
+ return __skb_linearize(skb, gfp);
+}
+
+static inline void *kmap_skb_frag(const skb_frag_t *frag)
+{
+#ifdef CONFIG_HIGHMEM
+ BUG_ON(in_irq());
+
+ local_bh_disable();
+#endif
+ return kmap_atomic(frag->page, KM_SKB_DATA_SOFTIRQ);
+}
+
+static inline void kunmap_skb_frag(void *vaddr)
+{
+ kunmap_atomic(vaddr, KM_SKB_DATA_SOFTIRQ);
+#ifdef CONFIG_HIGHMEM
+ local_bh_enable();
+#endif
+}
+
+#define skb_queue_walk(queue, skb) \
+ for (skb = (queue)->next;
\
+ prefetch(skb->next), (skb != (struct sk_buff *)(queue));
\
+ skb = skb->next)
+
+
+extern struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags,
+ int noblock, int *err);
+extern unsigned int datagram_poll(struct file *file, struct socket *sock,
+ struct poll_table_struct *wait);
+extern int skb_copy_datagram_iovec(const struct sk_buff *from,
+ int offset, struct iovec *to,
+ int size);
+extern int skb_copy_and_csum_datagram_iovec(const
+ struct sk_buff *skb,
+ int hlen,
+ struct iovec *iov);
+extern void skb_free_datagram(struct sock *sk, struct sk_buff *skb);
+extern unsigned int skb_checksum(const struct sk_buff *skb, int offset,
+ int len, unsigned int csum);
+extern int skb_copy_bits(const struct sk_buff *skb, int offset,
+ void *to, int len);
+extern unsigned int skb_copy_and_csum_bits(const struct sk_buff *skb,
+ int offset, u8 *to, int len,
+ unsigned int csum);
+extern void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to);
+extern void skb_split(struct sk_buff *skb,
+ struct sk_buff *skb1, const u32 len);
+
+static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
+ int len, void *buffer)
+{
+ int hlen = skb_headlen(skb);
+
+ if (offset + len <= hlen)
+ return skb->data + offset;
+
+ if (skb_copy_bits(skb, offset, buffer, len) < 0)
+ return NULL;
+
+ return buffer;
+}
+
+extern void skb_init(void);
+extern void skb_add_mtu(int mtu);
+
+struct skb_iter {
+ /* Iteration functions set these */
+ unsigned char *data;
+ unsigned int len;
+
+ /* Private to iteration */
+ unsigned int nextfrag;
+ struct sk_buff *fraglist;
+};
+
+/* Keep iterating until skb_iter_next returns false. */
+extern void skb_iter_first(const struct sk_buff *skb, struct skb_iter *i);
+extern int skb_iter_next(const struct sk_buff *skb, struct skb_iter *i);
+/* Call this if aborting loop before !skb_iter_next */
+extern void skb_iter_abort(const struct sk_buff *skb, struct skb_iter *i);
+
+#ifdef CONFIG_NETFILTER
+static inline void nf_conntrack_put(struct nf_conntrack *nfct)
+{
+ if (nfct && atomic_dec_and_test(&nfct->use))
+ nfct->destroy(nfct);
+}
+static inline void nf_conntrack_get(struct nf_conntrack *nfct)
+{
+ if (nfct)
+ atomic_inc(&nfct->use);
+}
+static inline void nf_reset(struct sk_buff *skb)
+{
+ nf_conntrack_put(skb->nfct);
+ skb->nfct = NULL;
+#ifdef CONFIG_NETFILTER_DEBUG
+ skb->nf_debug = 0;
+#endif
+}
+static inline void nf_reset_debug(struct sk_buff *skb)
+{
+#ifdef CONFIG_NETFILTER_DEBUG
+ skb->nf_debug = 0;
+#endif
+}
+
+#ifdef CONFIG_BRIDGE_NETFILTER
+static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge)
+{
+ if (nf_bridge && atomic_dec_and_test(&nf_bridge->use))
+ kfree(nf_bridge);
+}
+static inline void nf_bridge_get(struct nf_bridge_info *nf_bridge)
+{
+ if (nf_bridge)
+ atomic_inc(&nf_bridge->use);
+}
+#endif /* CONFIG_BRIDGE_NETFILTER */
+#else /* CONFIG_NETFILTER */
+static inline void nf_reset(struct sk_buff *skb) {}
+#endif /* CONFIG_NETFILTER */
+
+#endif /* __KERNEL__ */
+#endif /* _LINUX_SKBUFF_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/timer.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/timer.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,64 @@
+#ifndef _ASMi386_TIMER_H
+#define _ASMi386_TIMER_H
+#include <linux/init.h>
+
+/**
+ * struct timer_ops - used to define a timer source
+ *
+ * @name: name of the timer.
+ * @init: Probes and initializes the timer. Takes clock= override
+ * string as an argument. Returns 0 on success, anything else
+ * on failure.
+ * @mark_offset: called by the timer interrupt.
+ * @get_offset: called by gettimeofday(). Returns the number of microseconds
+ * since the last timer interupt.
+ * @monotonic_clock: returns the number of nanoseconds since the init of the
+ * timer.
+ * @delay: delays this many clock cycles.
+ */
+struct timer_opts {
+ char* name;
+ void (*mark_offset)(void);
+ unsigned long (*get_offset)(void);
+ unsigned long long (*monotonic_clock)(void);
+ void (*delay)(unsigned long);
+};
+
+struct init_timer_opts {
+ int (*init)(char *override);
+ struct timer_opts *opts;
+};
+
+#define TICK_SIZE (tick_nsec / 1000)
+
+extern struct timer_opts* __init select_timer(void);
+extern void clock_fallback(void);
+void setup_pit_timer(void);
+
+/* Modifiers for buggy PIT handling */
+
+extern int pit_latch_buggy;
+
+extern struct timer_opts *cur_timer;
+extern int timer_ack;
+
+/* list of externed timers */
+extern struct timer_opts timer_none;
+extern struct timer_opts timer_pit;
+extern struct init_timer_opts timer_pit_init;
+extern struct init_timer_opts timer_tsc_init;
+#ifdef CONFIG_X86_CYCLONE_TIMER
+extern struct init_timer_opts timer_cyclone_init;
+#endif
+
+extern unsigned long calibrate_tsc(void);
+extern void init_cpu_khz(void);
+#ifdef CONFIG_HPET_TIMER
+extern struct init_timer_opts timer_hpet_init;
+extern unsigned long calibrate_tsc_hpet(unsigned long *tsc_hpet_quotient_ptr);
+#endif
+
+#ifdef CONFIG_X86_PM_TIMER
+extern struct init_timer_opts timer_pmtmr_init;
+#endif
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/pgtable-2level.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/pgtable-2level.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,106 @@
+#ifndef _I386_PGTABLE_2LEVEL_H
+#define _I386_PGTABLE_2LEVEL_H
+
+#include <asm-generic/pgtable-nopmd.h>
+
+#define pte_ERROR(e) \
+ printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low)
+#define pgd_ERROR(e) \
+ printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+/*
+ * Certain architectures need to do special things when PTEs
+ * within a page table are directly modified. Thus, the following
+ * hook is made available.
+ */
+#define set_pte(pteptr, pteval) (*(pteptr) = pteval)
+#define set_pte_atomic(pteptr, pteval) set_pte(pteptr,pteval)
+
+#ifndef CONFIG_XEN_SHADOW_MODE
+#define set_pmd(pmdptr, pmdval) xen_l2_entry_update((pmdptr), (pmdval))
+#else
+#define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval))
+#endif
+
+#define ptep_get_and_clear(xp) __pte_ma(xchg(&(xp)->pte_low, 0))
+#define pte_same(a, b) ((a).pte_low == (b).pte_low)
+/*
+ * We detect special mappings in one of two ways:
+ * 1. If the MFN is an I/O page then Xen will set the m2p entry
+ * to be outside our maximum possible pseudophys range.
+ * 2. If the MFN belongs to a different domain then we will certainly
+ * not have MFN in our p2m table. Conversely, if the page is ours,
+ * then we'll have p2m(m2p(MFN))==MFN.
+ * If we detect a special mapping then it doesn't have a 'struct page'.
+ * We force !pfn_valid() by returning an out-of-range pointer.
+ *
+ * NB. These checks require that, for any MFN that is not in our reservation,
+ * there is no PFN such that p2m(PFN) == MFN. Otherwise we can get confused if
+ * we are foreign-mapping the MFN, and the other domain as m2p(MFN) == PFN.
+ * Yikes! Various places must poke in INVALID_P2M_ENTRY for safety.
+ *
+ * NB2. When deliberately mapping foreign pages into the p2m table, you *must*
+ * use FOREIGN_FRAME(). This will cause pte_pfn() to choke on it, as we
+ * require. In all the cases we care about, the high bit gets shifted out
+ * (e.g., phys_to_machine()) so behaviour there is correct.
+ */
+#define INVALID_P2M_ENTRY (~0U)
+#define FOREIGN_FRAME(_m) ((_m) | (1UL<<((sizeof(unsigned long)*8)-1)))
+#define pte_mfn(_pte) ((_pte).pte_low >> PAGE_SHIFT)
+#define pte_pfn(_pte) \
+({ \
+ unsigned long mfn = pte_mfn(_pte); \
+ unsigned long pfn = mfn_to_pfn(mfn); \
+ if ((pfn >= max_mapnr) || (pfn_to_mfn(pfn) != mfn)) \
+ pfn = max_mapnr; /* special: force !pfn_valid() */ \
+ pfn; \
+})
+
+#define pte_page(_pte) pfn_to_page(pte_pfn(_pte))
+
+#define pte_none(x) (!(x).pte_low)
+#define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
+#define pfn_pte_ma(pfn, prot) __pte_ma(((pfn) << PAGE_SHIFT) |
pgprot_val(prot))
+#define pfn_pmd(pfn, prot) __pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
+
+#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
+
+#define pmd_page_kernel(pmd) \
+((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
+
+/*
+ * All present user pages are user-executable:
+ */
+static inline int pte_exec(pte_t pte)
+{
+ return pte_user(pte);
+}
+
+/*
+ * All present pages are kernel-executable:
+ */
+static inline int pte_exec_kernel(pte_t pte)
+{
+ return 1;
+}
+
+/*
+ * Bits 0, 6 and 7 are taken, split up the 29 bits of offset
+ * into this range:
+ */
+#define PTE_FILE_MAX_BITS 29
+
+#define pte_to_pgoff(pte) \
+ ((((pte).pte_low >> 1) & 0x1f ) + (((pte).pte_low >> 8) << 5 ))
+
+#define pgoff_to_pte(off) \
+ ((pte_t) { (((off) & 0x1f) << 1) + (((off) >> 5) << 8) + _PAGE_FILE })
+
+/* Encode and de-code a swap entry */
+#define __swp_type(x) (((x).val >> 1) & 0x1f)
+#define __swp_offset(x) ((x).val >> 8)
+#define __swp_entry(type, offset) ((swp_entry_t) { ((type) << 1) |
((offset) << 8) })
+#define __pte_to_swp_entry(pte) ((swp_entry_t) { (pte).pte_low
})
+#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
+
+#endif /* _I386_PGTABLE_2LEVEL_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/drivers/blkif/backend/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/drivers/blkif/backend/Makefile Fri Jul
15 13:39:50 2005
@@ -0,0 +1,3 @@
+O_TARGET := drv.o
+obj-y := main.o control.o interface.o vbd.o
+include $(TOPDIR)/Rules.make
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/asm-offsets.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/asm-offsets.c Fri Jul
15 13:39:50 2005
@@ -0,0 +1,70 @@
+/*
+ * Generate definitions needed by assembly language modules.
+ * This code generates raw asm output which is post-processed to extract
+ * and format the required data.
+ */
+
+#include <linux/sched.h>
+#include <linux/stddef.h>
+#include <linux/errno.h>
+#include <linux/hardirq.h>
+#include <linux/suspend.h>
+#include <asm/pda.h>
+#include <asm/processor.h>
+#include <asm/segment.h>
+#include <asm/thread_info.h>
+#include <asm/ia32.h>
+
+#define DEFINE(sym, val) \
+ asm volatile("\n->" #sym " %0 " #val : : "i" (val))
+
+#define BLANK() asm volatile("\n->" : : )
+
+int main(void)
+{
+#define ENTRY(entry) DEFINE(tsk_ ## entry, offsetof(struct task_struct, entry))
+ ENTRY(state);
+ ENTRY(flags);
+ ENTRY(thread);
+ ENTRY(pid);
+ BLANK();
+#undef ENTRY
+#define ENTRY(entry) DEFINE(threadinfo_ ## entry, offsetof(struct thread_info,
entry))
+ ENTRY(flags);
+ ENTRY(addr_limit);
+ ENTRY(preempt_count);
+ BLANK();
+#undef ENTRY
+#define ENTRY(entry) DEFINE(pda_ ## entry, offsetof(struct x8664_pda, entry))
+ ENTRY(kernelstack);
+ ENTRY(oldrsp);
+ ENTRY(pcurrent);
+ ENTRY(irqrsp);
+ ENTRY(irqcount);
+ ENTRY(cpunumber);
+ ENTRY(irqstackptr);
+ ENTRY(kernel_mode);
+ BLANK();
+#undef ENTRY
+#ifdef CONFIG_IA32_EMULATION
+#define ENTRY(entry) DEFINE(IA32_SIGCONTEXT_ ## entry, offsetof(struct
sigcontext_ia32, entry))
+ ENTRY(eax);
+ ENTRY(ebx);
+ ENTRY(ecx);
+ ENTRY(edx);
+ ENTRY(esi);
+ ENTRY(edi);
+ ENTRY(ebp);
+ ENTRY(esp);
+ ENTRY(eip);
+ BLANK();
+#undef ENTRY
+ DEFINE(IA32_RT_SIGFRAME_sigcontext,
+ offsetof (struct rt_sigframe32, uc.uc_mcontext));
+ BLANK();
+#endif
+ DEFINE(SIZEOF_PBE, sizeof(struct pbe));
+ DEFINE(pbe_address, offsetof(struct pbe, address));
+ DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address));
+ return 0;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/system.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/system.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,424 @@
+#ifndef __ASM_SYSTEM_H
+#define __ASM_SYSTEM_H
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/bitops.h>
+#include <asm/synch_bitops.h>
+#include <asm/segment.h>
+#include <asm/hypervisor.h>
+#include <asm/evtchn.h>
+
+#ifdef __KERNEL__
+
+struct task_struct;
+extern void FASTCALL(__switch_to(struct task_struct *prev,
+ struct task_struct *next));
+
+#define prepare_to_switch() \
+do { \
+ struct thread_struct *__t = ¤t->thread; \
+ __asm__ __volatile__ ( "movl %%fs,%0" : "=m" (*(int *)&__t->fs) ); \
+ __asm__ __volatile__ ( "movl %%gs,%0" : "=m" (*(int *)&__t->gs) ); \
+} while (0)
+#define switch_to(prev,next,last) do { \
+ asm volatile("pushl %%esi\n\t" \
+ "pushl %%edi\n\t" \
+ "pushl %%ebp\n\t" \
+ "movl %%esp,%0\n\t" /* save ESP */ \
+ "movl %3,%%esp\n\t" /* restore ESP */ \
+ "movl $1f,%1\n\t" /* save EIP */ \
+ "pushl %4\n\t" /* restore EIP */ \
+ "jmp __switch_to\n" \
+ "1:\t" \
+ "popl %%ebp\n\t" \
+ "popl %%edi\n\t" \
+ "popl %%esi\n\t" \
+ :"=m" (prev->thread.esp),"=m" (prev->thread.eip), \
+ "=b" (last) \
+ :"m" (next->thread.esp),"m" (next->thread.eip), \
+ "a" (prev), "d" (next), \
+ "b" (prev)); \
+} while (0)
+
+#define _set_base(addr,base) do { unsigned long __pr; \
+__asm__ __volatile__ ("movw %%dx,%1\n\t" \
+ "rorl $16,%%edx\n\t" \
+ "movb %%dl,%2\n\t" \
+ "movb %%dh,%3" \
+ :"=&d" (__pr) \
+ :"m" (*((addr)+2)), \
+ "m" (*((addr)+4)), \
+ "m" (*((addr)+7)), \
+ "0" (base) \
+ ); } while(0)
+
+#define _set_limit(addr,limit) do { unsigned long __lr; \
+__asm__ __volatile__ ("movw %%dx,%1\n\t" \
+ "rorl $16,%%edx\n\t" \
+ "movb %2,%%dh\n\t" \
+ "andb $0xf0,%%dh\n\t" \
+ "orb %%dh,%%dl\n\t" \
+ "movb %%dl,%2" \
+ :"=&d" (__lr) \
+ :"m" (*(addr)), \
+ "m" (*((addr)+6)), \
+ "0" (limit) \
+ ); } while(0)
+
+#define set_base(ldt,base) _set_base( ((char *)&(ldt)) , (base) )
+#define set_limit(ldt,limit) _set_limit( ((char *)&(ldt)) , ((limit)-1)>>12 )
+
+static inline unsigned long _get_base(char * addr)
+{
+ unsigned long __base;
+ __asm__("movb %3,%%dh\n\t"
+ "movb %2,%%dl\n\t"
+ "shll $16,%%edx\n\t"
+ "movw %1,%%dx"
+ :"=&d" (__base)
+ :"m" (*((addr)+2)),
+ "m" (*((addr)+4)),
+ "m" (*((addr)+7)));
+ return __base;
+}
+
+#define get_base(ldt) _get_base( ((char *)&(ldt)) )
+
+/*
+ * Load a segment. Fall back on loading the zero
+ * segment if something goes wrong..
+ */
+#define loadsegment(seg,value) \
+ asm volatile("\n" \
+ "1:\t" \
+ "movl %0,%%" #seg "\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3:\t" \
+ "pushl $0\n\t" \
+ "popl %%" #seg "\n\t" \
+ "jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n\t" \
+ ".align 4\n\t" \
+ ".long 1b,3b\n" \
+ ".previous" \
+ : :"m" (*(unsigned int *)&(value)))
+
+/* NB. 'clts' is done for us by Xen during virtual trap. */
+#define clts() ((void)0)
+#define stts() (HYPERVISOR_fpu_taskswitch(1))
+
+#endif /* __KERNEL__ */
+
+/**
+ * __ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ *
+ * Taken from 2.6 for Xen.
+ */
+static inline unsigned long __ffs(unsigned long word)
+{
+ __asm__("bsfl %1,%0"
+ :"=r" (word)
+ :"rm" (word));
+ return word;
+}
+
+static inline unsigned long get_limit(unsigned long segment)
+{
+ unsigned long __limit;
+ __asm__("lsll %1,%0"
+ :"=r" (__limit):"r" (segment));
+ return __limit+1;
+}
+
+#define nop() __asm__ __volatile__ ("nop")
+
+#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned
long)(v),(ptr),sizeof(*(ptr))))
+
+#define tas(ptr) (xchg((ptr),1))
+
+struct __xchg_dummy { unsigned long a[100]; };
+#define __xg(x) ((struct __xchg_dummy *)(x))
+
+
+/*
+ * The semantics of XCHGCMP8B are a bit strange, this is why
+ * there is a loop and the loading of %%eax and %%edx has to
+ * be inside. This inlines well in most cases, the cached
+ * cost is around ~38 cycles. (in the future we might want
+ * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that
+ * might have an implicit FPU-save as a cost, so it's not
+ * clear which path to go.)
+ *
+ * chmxchg8b must be used with the lock prefix here to allow
+ * the instruction to be executed atomically, see page 3-102
+ * of the instruction set reference 24319102.pdf. We need
+ * the reader side to see the coherent 64bit value.
+ */
+static inline void __set_64bit (unsigned long long * ptr,
+ unsigned int low, unsigned int high)
+{
+ __asm__ __volatile__ (
+ "\n1:\t"
+ "movl (%0), %%eax\n\t"
+ "movl 4(%0), %%edx\n\t"
+ "lock cmpxchg8b (%0)\n\t"
+ "jnz 1b"
+ : /* no outputs */
+ : "D"(ptr),
+ "b"(low),
+ "c"(high)
+ : "ax","dx","memory");
+}
+
+static inline void __set_64bit_constant (unsigned long long *ptr,
+ unsigned long long value)
+{
+ __set_64bit(ptr,(unsigned int)(value), (unsigned int)((value)>>32ULL));
+}
+#define ll_low(x) *(((unsigned int*)&(x))+0)
+#define ll_high(x) *(((unsigned int*)&(x))+1)
+
+static inline void __set_64bit_var (unsigned long long *ptr,
+ unsigned long long value)
+{
+ __set_64bit(ptr,ll_low(value), ll_high(value));
+}
+
+#define set_64bit(ptr,value) \
+(__builtin_constant_p(value) ? \
+ __set_64bit_constant(ptr, value) : \
+ __set_64bit_var(ptr, value) )
+
+#define _set_64bit(ptr,value) \
+(__builtin_constant_p(value) ? \
+ __set_64bit(ptr, (unsigned int)(value), (unsigned int)((value)>>32ULL) ) : \
+ __set_64bit(ptr, ll_low(value), ll_high(value)) )
+
+/*
+ * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
+ * Note 2: xchg has side effect, so that attribute volatile is necessary,
+ * but generally the primitive is invalid, *ptr is output argument. --ANK
+ */
+static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int
size)
+{
+ switch (size) {
+ case 1:
+ __asm__ __volatile__("xchgb %b0,%1"
+ :"=q" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ case 2:
+ __asm__ __volatile__("xchgw %w0,%1"
+ :"=r" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ case 4:
+ __asm__ __volatile__("xchgl %0,%1"
+ :"=r" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ }
+ return x;
+}
+
+/*
+ * Atomic compare and exchange. Compare OLD with MEM, if identical,
+ * store NEW in MEM. Return the initial value in MEM. Success is
+ * indicated by comparing RETURN with OLD.
+ */
+
+#ifdef CONFIG_X86_CMPXCHG
+#define __HAVE_ARCH_CMPXCHG 1
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+ unsigned long new, int size)
+{
+ unsigned long prev;
+ switch (size) {
+ case 1:
+ __asm__ __volatile__("lock cmpxchgb %b1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ case 2:
+ __asm__ __volatile__("lock cmpxchgw %w1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ case 4:
+ __asm__ __volatile__("lock cmpxchgl %1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ }
+ return old;
+}
+
+#define cmpxchg(ptr,o,n)\
+ ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
+ (unsigned long)(n),sizeof(*(ptr))))
+
+#else
+/* Compiling for a 386 proper. Is it worth implementing via cli/sti? */
+#endif
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ *
+ * For now, "wmb()" doesn't actually do anything, as all
+ * Intel CPU's follow what Intel calls a *Processor Order*,
+ * in which all writes are seen in the program order even
+ * outside the CPU.
+ *
+ * I expect future Intel CPU's to have a weaker ordering,
+ * but I'd also expect them to finally get their act together
+ * and add some real memory barriers if so.
+ *
+ * Some non intel clones support out of order store. wmb() ceases to be a
+ * nop for these.
+ */
+
+#define mb() __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory")
+#define rmb() mb()
+
+#ifdef CONFIG_X86_OOSTORE
+#define wmb() __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory")
+#else
+#define wmb() __asm__ __volatile__ ("": : :"memory")
+#endif
+
+#ifdef CONFIG_SMP
+#define smp_mb() mb()
+#define smp_rmb() rmb()
+#define smp_wmb() wmb()
+#define set_mb(var, value) do { xchg(&var, value); } while (0)
+#else
+#define smp_mb() barrier()
+#define smp_rmb() barrier()
+#define smp_wmb() barrier()
+#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#endif
+
+#define set_wmb(var, value) do { var = value; wmb(); } while (0)
+
+#define safe_halt() ((void)0)
+
+/*
+ * The use of 'barrier' in the following reflects their use as local-lock
+ * operations. Reentrancy must be prevented (e.g., __cli()) /before/ following
+ * critical operations are executed. All critical operatiosn must complete
+ * /before/ reentrancy is permitted (e.g., __sti()). Alpha architecture also
+ * includes these barriers, for example.
+ */
+
+#define __cli() \
+do { \
+ HYPERVISOR_shared_info->vcpu_data[0].evtchn_upcall_mask = 1; \
+ barrier(); \
+} while (0)
+
+#define __sti() \
+do { \
+ shared_info_t *_shared = HYPERVISOR_shared_info; \
+ barrier(); \
+ _shared->vcpu_data[0].evtchn_upcall_mask = 0; \
+ barrier(); /* unmask then check (avoid races) */ \
+ if ( unlikely(_shared->vcpu_data[0].evtchn_upcall_pending) ) \
+ force_evtchn_callback(); \
+} while (0)
+
+#define __save_flags(x) \
+do { \
+ (x) = HYPERVISOR_shared_info->vcpu_data[0].evtchn_upcall_mask; \
+} while (0)
+
+#define __restore_flags(x) \
+do { \
+ shared_info_t *_shared = HYPERVISOR_shared_info; \
+ barrier(); \
+ if ( (_shared->vcpu_data[0].evtchn_upcall_mask = x) == 0 ) { \
+ barrier(); /* unmask then check (avoid races) */ \
+ if ( unlikely(_shared->vcpu_data[0].evtchn_upcall_pending) ) \
+ force_evtchn_callback(); \
+ } \
+} while (0)
+
+#define __save_and_cli(x) \
+do { \
+ (x) = HYPERVISOR_shared_info->vcpu_data[0].evtchn_upcall_mask; \
+ HYPERVISOR_shared_info->vcpu_data[0].evtchn_upcall_mask = 1; \
+ barrier(); \
+} while (0)
+
+#define __save_and_sti(x) \
+do { \
+ shared_info_t *_shared = HYPERVISOR_shared_info; \
+ barrier(); \
+ (x) = _shared->vcpu_data[0].evtchn_upcall_mask; \
+ _shared->vcpu_data[0].evtchn_upcall_mask = 0; \
+ barrier(); /* unmask then check (avoid races) */ \
+ if ( unlikely(_shared->vcpu_data[0].evtchn_upcall_pending) ) \
+ force_evtchn_callback(); \
+} while (0)
+
+#define local_irq_save(x) __save_and_cli(x)
+#define local_irq_set(x) __save_and_sti(x)
+#define local_irq_restore(x) __restore_flags(x)
+#define local_irq_disable() __cli()
+#define local_irq_enable() __sti()
+
+
+#ifdef CONFIG_SMP
+#error no SMP
+extern void __global_cli(void);
+extern void __global_sti(void);
+extern unsigned long __global_save_flags(void);
+extern void __global_restore_flags(unsigned long);
+#define cli() __global_cli()
+#define sti() __global_sti()
+#define save_flags(x) ((x)=__global_save_flags())
+#define restore_flags(x) __global_restore_flags(x)
+#define save_and_cli(x) do { save_flags(x); cli(); } while(0);
+#define save_and_sti(x) do { save_flags(x); sti(); } while(0);
+
+#else
+
+#define cli() __cli()
+#define sti() __sti()
+#define save_flags(x) __save_flags(x)
+#define restore_flags(x) __restore_flags(x)
+#define save_and_cli(x) __save_and_cli(x)
+#define save_and_sti(x) __save_and_sti(x)
+
+#endif
+
+/*
+ * disable hlt during certain critical i/o operations
+ */
+#define HAVE_DISABLE_HLT
+void disable_hlt(void);
+void enable_hlt(void);
+
+extern unsigned long dmi_broken;
+extern int is_sony_vaio_laptop;
+
+#define BROKEN_ACPI_Sx 0x0001
+#define BROKEN_INIT_AFTER_S1 0x0002
+#define BROKEN_PNP_BIOS 0x0004
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/ia32/ia32entry.S
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/ia32/ia32entry.S Fri Jul 15
13:39:50 2005
@@ -0,0 +1,629 @@
+/*
+ * Compatibility mode system call entry point for x86-64.
+ *
+ * Copyright 2000-2002 Andi Kleen, SuSE Labs.
+ */
+
+#include <asm/dwarf2.h>
+#include <asm/calling.h>
+#include <asm/offset.h>
+#include <asm/current.h>
+#include <asm/errno.h>
+#include <asm/ia32_unistd.h>
+#include <asm/thread_info.h>
+#include <asm/segment.h>
+#include <asm/vsyscall32.h>
+#include <linux/linkage.h>
+
+#define __XEN_X86_64 1
+
+ .macro IA32_ARG_FIXUP noebp=0
+ movl %edi,%r8d
+ .if \noebp
+ .else
+ movl %ebp,%r9d
+ .endif
+ xchg %ecx,%esi
+ movl %ebx,%edi
+ movl %edx,%edx /* zero extension */
+ .endm
+
+ /* clobbers %eax */
+ .macro CLEAR_RREGS
+ xorl %eax,%eax
+ movq %rax,R11(%rsp)
+ movq %rax,R10(%rsp)
+ movq %rax,R9(%rsp)
+ movq %rax,R8(%rsp)
+ .endm
+
+#if defined (__XEN_X86_64)
+#include "../kernel/xen_entry.S"
+
+#define __swapgs
+#define __cli
+#define __sti
+#else
+/*
+ * Use the native instructions
+ */
+#define __swapgs swapgs
+#define __cli cli
+#define __sti sti
+#endif
+
+/*
+ * 32bit SYSENTER instruction entry.
+ *
+ * Arguments:
+ * %eax System call number.
+ * %ebx Arg1
+ * %ecx Arg2
+ * %edx Arg3
+ * %esi Arg4
+ * %edi Arg5
+ * %ebp user stack
+ * 0(%ebp) Arg6
+ *
+ * Interrupts off.
+ *
+ * This is purely a fast path. For anything complicated we use the int 0x80
+ * path below. Set up a complete hardware stack frame to share code
+ * with the int 0x80 path.
+ */
+ENTRY(ia32_sysenter_target)
+ CFI_STARTPROC
+ __swapgs
+ movq %gs:pda_kernelstack, %rsp
+ addq $(PDA_STACKOFFSET),%rsp
+ XEN_UNBLOCK_EVENTS(%r11)
+ __sti
+ movl %ebp,%ebp /* zero extension */
+ pushq $__USER32_DS
+ pushq %rbp
+ pushfq
+ movl $VSYSCALL32_SYSEXIT, %r10d
+ pushq $__USER32_CS
+ movl %eax, %eax
+ pushq %r10
+ pushq %rax
+ cld
+ SAVE_ARGS 0,0,1
+ /* no need to do an access_ok check here because rbp has been
+ 32bit zero extended */
+1: movl (%rbp),%r9d
+ .section __ex_table,"a"
+ .quad 1b,ia32_badarg
+ .previous
+ GET_THREAD_INFO(%r10)
+ testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),threadinfo_flags(%r10)
+ jnz sysenter_tracesys
+sysenter_do_call:
+ cmpl $(IA32_NR_syscalls),%eax
+ jae ia32_badsys
+ IA32_ARG_FIXUP 1
+ call *ia32_sys_call_table(,%rax,8)
+ movq %rax,RAX-ARGOFFSET(%rsp)
+ GET_THREAD_INFO(%r10)
+ XEN_BLOCK_EVENTS(%r11)
+ __cli
+ testl $_TIF_ALLWORK_MASK,threadinfo_flags(%r10)
+ jnz int_ret_from_sys_call
+ /* clear IF, that popfq doesn't enable interrupts early */
+ andl $~0x200,EFLAGS-R11(%rsp)
+ RESTORE_ARGS 1,24,1,1,1,1
+ popfq
+ popq %rcx /* User %esp */
+ movl $VSYSCALL32_SYSEXIT,%edx /* User %eip */
+ __swapgs
+ XEN_UNBLOCK_EVENTS(%r11)
+ __sti /* sti only takes effect after the next instruction */
+ /* sysexit */
+ .byte 0xf, 0x35 /* TBD */
+
+sysenter_tracesys:
+ SAVE_REST
+ CLEAR_RREGS
+ movq $-ENOSYS,RAX(%rsp) /* really needed? */
+ movq %rsp,%rdi /* &pt_regs -> arg1 */
+ call syscall_trace_enter
+ LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed
it */
+ RESTORE_REST
+ movl %ebp, %ebp
+ /* no need to do an access_ok check here because rbp has been
+ 32bit zero extended */
+1: movl (%rbp),%r9d
+ .section __ex_table,"a"
+ .quad 1b,ia32_badarg
+ .previous
+ jmp sysenter_do_call
+ CFI_ENDPROC
+
+/*
+ * 32bit SYSCALL instruction entry.
+ *
+ * Arguments:
+ * %eax System call number.
+ * %ebx Arg1
+ * %ecx return EIP
+ * %edx Arg3
+ * %esi Arg4
+ * %edi Arg5
+ * %ebp Arg2 [note: not saved in the stack frame, should not be touched]
+ * %esp user stack
+ * 0(%esp) Arg6
+ *
+ * Interrupts off.
+ *
+ * This is purely a fast path. For anything complicated we use the int 0x80
+ * path below. Set up a complete hardware stack frame to share code
+ * with the int 0x80 path.
+ */
+ENTRY(ia32_cstar_target)
+ CFI_STARTPROC
+ __swapgs
+ movl %esp,%r8d
+ movq %gs:pda_kernelstack,%rsp
+ XEN_UNBLOCK_EVENTS(%r11)
+ __sti
+ SAVE_ARGS 8,1,1
+ movl %eax,%eax /* zero extension */
+ movq %rax,ORIG_RAX-ARGOFFSET(%rsp)
+ movq %rcx,RIP-ARGOFFSET(%rsp)
+ movq %rbp,RCX-ARGOFFSET(%rsp) /* this lies slightly to ptrace */
+ movl %ebp,%ecx
+ movq $__USER32_CS,CS-ARGOFFSET(%rsp)
+ movq $__USER32_DS,SS-ARGOFFSET(%rsp)
+ movq %r11,EFLAGS-ARGOFFSET(%rsp)
+ movq %r8,RSP-ARGOFFSET(%rsp)
+ /* no need to do an access_ok check here because r8 has been
+ 32bit zero extended */
+ /* hardware stack frame is complete now */
+1: movl (%r8),%r9d
+ .section __ex_table,"a"
+ .quad 1b,ia32_badarg
+ .previous
+ GET_THREAD_INFO(%r10)
+ testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),threadinfo_flags(%r10)
+ jnz cstar_tracesys
+cstar_do_call:
+ cmpl $IA32_NR_syscalls,%eax
+ jae ia32_badsys
+ IA32_ARG_FIXUP 1
+ call *ia32_sys_call_table(,%rax,8)
+ movq %rax,RAX-ARGOFFSET(%rsp)
+ GET_THREAD_INFO(%r10)
+ XEN_BLOCK_EVENTS(%r11)
+ __cli
+ testl $_TIF_ALLWORK_MASK,threadinfo_flags(%r10)
+ jnz int_ret_from_sys_call
+ RESTORE_ARGS 1,-ARG_SKIP,1,1,1
+ movl RIP-ARGOFFSET(%rsp),%ecx
+ movl EFLAGS-ARGOFFSET(%rsp),%r11d
+ movl RSP-ARGOFFSET(%rsp),%esp
+ __swapgs
+ sysretl /* TBD */
+
+cstar_tracesys:
+ SAVE_REST
+ CLEAR_RREGS
+ movq $-ENOSYS,RAX(%rsp) /* really needed? */
+ movq %rsp,%rdi /* &pt_regs -> arg1 */
+ call syscall_trace_enter
+ LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed
it */
+ RESTORE_REST
+ movl RSP-ARGOFFSET(%rsp), %r8d
+ /* no need to do an access_ok check here because r8 has been
+ 32bit zero extended */
+1: movl (%r8),%r9d
+ .section __ex_table,"a"
+ .quad 1b,ia32_badarg
+ .previous
+ jmp cstar_do_call
+
+ia32_badarg:
+ movq $-EFAULT,%rax
+ jmp ia32_sysret
+ CFI_ENDPROC
+
+/*
+ * Emulated IA32 system calls via int 0x80.
+ *
+ * Arguments:
+ * %eax System call number.
+ * %ebx Arg1
+ * %ecx Arg2
+ * %edx Arg3
+ * %esi Arg4
+ * %edi Arg5
+ * %ebp Arg6 [note: not saved in the stack frame, should not be touched]
+ *
+ * Notes:
+ * Uses the same stack frame as the x86-64 version.
+ * All registers except %eax must be saved (but ptrace may violate that)
+ * Arguments are zero extended. For system calls that want sign extension and
+ * take long arguments a wrapper is needed. Most calls can just be called
+ * directly.
+ * Assumes it is only called from user space and entered with interrupts off.
+ */
+
+ENTRY(ia32_syscall)
+ CFI_STARTPROC
+ __swapgs
+ XEN_UNBLOCK_EVENTS(%r11)
+ __sti
+ movq (%rsp),%rcx
+ movq 8(%rsp),%r11
+ addq $0x10,%rsp /* skip rcx and r11 */
+ movl %eax,%eax
+ pushq %rax
+ cld
+/* 1: jmp 1b */
+ /* note the registers are not zero extended to the sf.
+ this could be a problem. */
+ SAVE_ARGS 0,0,1
+ GET_THREAD_INFO(%r10)
+ testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),threadinfo_flags(%r10)
+ jnz ia32_tracesys
+ia32_do_syscall:
+ cmpl $(IA32_NR_syscalls),%eax
+ jae ia32_badsys
+ IA32_ARG_FIXUP
+ call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
+ia32_sysret:
+ movq %rax,RAX-ARGOFFSET(%rsp)
+ jmp int_ret_from_sys_call
+
+ia32_tracesys:
+ SAVE_REST
+ movq $-ENOSYS,RAX(%rsp) /* really needed? */
+ movq %rsp,%rdi /* &pt_regs -> arg1 */
+ call syscall_trace_enter
+ LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed
it */
+ RESTORE_REST
+ jmp ia32_do_syscall
+
+ia32_badsys:
+ movq $0,ORIG_RAX-ARGOFFSET(%rsp)
+ movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
+ jmp int_ret_from_sys_call
+
+ni_syscall:
+ movq %rax,%rdi
+ jmp sys32_ni_syscall
+
+quiet_ni_syscall:
+ movq $-ENOSYS,%rax
+ ret
+ CFI_ENDPROC
+
+ .macro PTREGSCALL label, func, arg
+ .globl \label
+\label:
+ leaq \func(%rip),%rax
+ leaq -ARGOFFSET+8(%rsp),\arg /* 8 for return address */
+ jmp ia32_ptregs_common
+ .endm
+
+ PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn, %rdi
+ PTREGSCALL stub32_sigreturn, sys32_sigreturn, %rdi
+ PTREGSCALL stub32_sigaltstack, sys32_sigaltstack, %rdx
+ PTREGSCALL stub32_sigsuspend, sys32_sigsuspend, %rcx
+ PTREGSCALL stub32_execve, sys32_execve, %rcx
+ PTREGSCALL stub32_fork, sys_fork, %rdi
+ PTREGSCALL stub32_clone, sys32_clone, %rdx
+ PTREGSCALL stub32_vfork, sys_vfork, %rdi
+ PTREGSCALL stub32_iopl, sys_iopl, %rsi
+ PTREGSCALL stub32_rt_sigsuspend, sys_rt_sigsuspend, %rdx
+
+ENTRY(ia32_ptregs_common)
+ CFI_STARTPROC
+ popq %r11
+ SAVE_REST
+ call *%rax
+ RESTORE_REST
+ jmp ia32_sysret /* misbalances the return cache */
+ CFI_ENDPROC
+
+ .data
+ .align 8
+ .globl ia32_sys_call_table
+ia32_sys_call_table:
+ .quad sys_restart_syscall
+ .quad sys_exit
+ .quad stub32_fork
+ .quad sys_read
+ .quad sys_write
+ .quad sys32_open /* 5 */
+ .quad sys_close
+ .quad sys32_waitpid
+ .quad sys_creat
+ .quad sys_link
+ .quad sys_unlink /* 10 */
+ .quad stub32_execve
+ .quad sys_chdir
+ .quad compat_sys_time
+ .quad sys_mknod
+ .quad sys_chmod /* 15 */
+ .quad sys_lchown16
+ .quad quiet_ni_syscall /* old break syscall holder */
+ .quad sys_stat
+ .quad sys32_lseek
+ .quad sys_getpid /* 20 */
+ .quad compat_sys_mount /* mount */
+ .quad sys_oldumount /* old_umount */
+ .quad sys_setuid16
+ .quad sys_getuid16
+ .quad compat_sys_stime /* stime */ /* 25 */
+ .quad sys32_ptrace /* ptrace */
+ .quad sys_alarm
+ .quad sys_fstat /* (old)fstat */
+ .quad sys_pause
+ .quad compat_sys_utime /* 30 */
+ .quad quiet_ni_syscall /* old stty syscall holder */
+ .quad quiet_ni_syscall /* old gtty syscall holder */
+ .quad sys_access
+ .quad sys_nice
+ .quad quiet_ni_syscall /* 35 */ /* old ftime syscall holder */
+ .quad sys_sync
+ .quad sys32_kill
+ .quad sys_rename
+ .quad sys_mkdir
+ .quad sys_rmdir /* 40 */
+ .quad sys_dup
+ .quad sys32_pipe
+ .quad compat_sys_times
+ .quad quiet_ni_syscall /* old prof syscall holder */
+ .quad sys_brk /* 45 */
+ .quad sys_setgid16
+ .quad sys_getgid16
+ .quad sys_signal
+ .quad sys_geteuid16
+ .quad sys_getegid16 /* 50 */
+ .quad sys_acct
+ .quad sys_umount /* new_umount */
+ .quad quiet_ni_syscall /* old lock syscall holder */
+ .quad compat_sys_ioctl
+ .quad compat_sys_fcntl64 /* 55 */
+ .quad quiet_ni_syscall /* old mpx syscall holder */
+ .quad sys_setpgid
+ .quad quiet_ni_syscall /* old ulimit syscall holder */
+ .quad sys32_olduname
+ .quad sys_umask /* 60 */
+ .quad sys_chroot
+ .quad sys32_ustat
+ .quad sys_dup2
+ .quad sys_getppid
+ .quad sys_getpgrp /* 65 */
+ .quad sys_setsid
+ .quad sys32_sigaction
+ .quad sys_sgetmask
+ .quad sys_ssetmask
+ .quad sys_setreuid16 /* 70 */
+ .quad sys_setregid16
+ .quad stub32_sigsuspend
+ .quad compat_sys_sigpending
+ .quad sys_sethostname
+ .quad compat_sys_setrlimit /* 75 */
+ .quad compat_sys_old_getrlimit /* old_getrlimit */
+ .quad compat_sys_getrusage
+ .quad sys32_gettimeofday
+ .quad sys32_settimeofday
+ .quad sys_getgroups16 /* 80 */
+ .quad sys_setgroups16
+ .quad sys32_old_select
+ .quad sys_symlink
+ .quad sys_lstat
+ .quad sys_readlink /* 85 */
+#ifdef CONFIG_IA32_AOUT
+ .quad sys_uselib
+#else
+ .quad quiet_ni_syscall
+#endif
+ .quad sys_swapon
+ .quad sys_reboot
+ .quad compat_sys_old_readdir
+ .quad sys32_mmap /* 90 */
+ .quad sys_munmap
+ .quad sys_truncate
+ .quad sys_ftruncate
+ .quad sys_fchmod
+ .quad sys_fchown16 /* 95 */
+ .quad sys_getpriority
+ .quad sys_setpriority
+ .quad quiet_ni_syscall /* old profil syscall holder */
+ .quad compat_sys_statfs
+ .quad compat_sys_fstatfs /* 100 */
+ .quad sys_ioperm
+ .quad compat_sys_socketcall
+ .quad sys_syslog
+ .quad compat_sys_setitimer
+ .quad compat_sys_getitimer /* 105 */
+ .quad compat_sys_newstat
+ .quad compat_sys_newlstat
+ .quad compat_sys_newfstat
+ .quad sys32_uname
+ .quad stub32_iopl /* 110 */
+ .quad sys_vhangup
+ .quad quiet_ni_syscall /* old "idle" system call */
+ .quad sys32_vm86_warning /* vm86old */
+ .quad compat_sys_wait4
+ .quad sys_swapoff /* 115 */
+ .quad sys32_sysinfo
+ .quad sys32_ipc
+ .quad sys_fsync
+ .quad stub32_sigreturn
+ .quad stub32_clone /* 120 */
+ .quad sys_setdomainname
+ .quad sys_uname
+ .quad sys_modify_ldt
+ .quad sys32_adjtimex
+ .quad sys32_mprotect /* 125 */
+ .quad compat_sys_sigprocmask
+ .quad quiet_ni_syscall /* create_module */
+ .quad sys_init_module
+ .quad sys_delete_module
+ .quad quiet_ni_syscall /* 130 get_kernel_syms */
+ .quad sys_quotactl
+ .quad sys_getpgid
+ .quad sys_fchdir
+ .quad quiet_ni_syscall /* bdflush */
+ .quad sys_sysfs /* 135 */
+ .quad sys_personality
+ .quad quiet_ni_syscall /* for afs_syscall */
+ .quad sys_setfsuid16
+ .quad sys_setfsgid16
+ .quad sys_llseek /* 140 */
+ .quad compat_sys_getdents
+ .quad compat_sys_select
+ .quad sys_flock
+ .quad sys_msync
+ .quad compat_sys_readv /* 145 */
+ .quad compat_sys_writev
+ .quad sys_getsid
+ .quad sys_fdatasync
+ .quad sys32_sysctl /* sysctl */
+ .quad sys_mlock /* 150 */
+ .quad sys_munlock
+ .quad sys_mlockall
+ .quad sys_munlockall
+ .quad sys_sched_setparam
+ .quad sys_sched_getparam /* 155 */
+ .quad sys_sched_setscheduler
+ .quad sys_sched_getscheduler
+ .quad sys_sched_yield
+ .quad sys_sched_get_priority_max
+ .quad sys_sched_get_priority_min /* 160 */
+ .quad sys_sched_rr_get_interval
+ .quad compat_sys_nanosleep
+ .quad sys_mremap
+ .quad sys_setresuid16
+ .quad sys_getresuid16 /* 165 */
+ .quad sys32_vm86_warning /* vm86 */
+ .quad quiet_ni_syscall /* query_module */
+ .quad sys_poll
+ .quad compat_sys_nfsservctl
+ .quad sys_setresgid16 /* 170 */
+ .quad sys_getresgid16
+ .quad sys_prctl
+ .quad stub32_rt_sigreturn
+ .quad sys32_rt_sigaction
+ .quad sys32_rt_sigprocmask /* 175 */
+ .quad sys32_rt_sigpending
+ .quad compat_sys_rt_sigtimedwait
+ .quad sys32_rt_sigqueueinfo
+ .quad stub32_rt_sigsuspend
+ .quad sys32_pread /* 180 */
+ .quad sys32_pwrite
+ .quad sys_chown16
+ .quad sys_getcwd
+ .quad sys_capget
+ .quad sys_capset
+ .quad stub32_sigaltstack
+ .quad sys32_sendfile
+ .quad quiet_ni_syscall /* streams1 */
+ .quad quiet_ni_syscall /* streams2 */
+ .quad stub32_vfork /* 190 */
+ .quad compat_sys_getrlimit
+ .quad sys32_mmap2
+ .quad sys32_truncate64
+ .quad sys32_ftruncate64
+ .quad sys32_stat64 /* 195 */
+ .quad sys32_lstat64
+ .quad sys32_fstat64
+ .quad sys_lchown
+ .quad sys_getuid
+ .quad sys_getgid /* 200 */
+ .quad sys_geteuid
+ .quad sys_getegid
+ .quad sys_setreuid
+ .quad sys_setregid
+ .quad sys_getgroups /* 205 */
+ .quad sys_setgroups
+ .quad sys_fchown
+ .quad sys_setresuid
+ .quad sys_getresuid
+ .quad sys_setresgid /* 210 */
+ .quad sys_getresgid
+ .quad sys_chown
+ .quad sys_setuid
+ .quad sys_setgid
+ .quad sys_setfsuid /* 215 */
+ .quad sys_setfsgid
+ .quad sys_pivot_root
+ .quad sys_mincore
+ .quad sys_madvise
+ .quad compat_sys_getdents64 /* 220 getdents64 */
+ .quad compat_sys_fcntl64
+ .quad quiet_ni_syscall /* tux */
+ .quad quiet_ni_syscall /* security */
+ .quad sys_gettid
+ .quad sys_readahead /* 225 */
+ .quad sys_setxattr
+ .quad sys_lsetxattr
+ .quad sys_fsetxattr
+ .quad sys_getxattr
+ .quad sys_lgetxattr /* 230 */
+ .quad sys_fgetxattr
+ .quad sys_listxattr
+ .quad sys_llistxattr
+ .quad sys_flistxattr
+ .quad sys_removexattr /* 235 */
+ .quad sys_lremovexattr
+ .quad sys_fremovexattr
+ .quad sys_tkill
+ .quad sys_sendfile64
+ .quad compat_sys_futex /* 240 */
+ .quad compat_sys_sched_setaffinity
+ .quad compat_sys_sched_getaffinity
+ .quad sys32_set_thread_area
+ .quad sys32_get_thread_area
+ .quad compat_sys_io_setup /* 245 */
+ .quad sys_io_destroy
+ .quad compat_sys_io_getevents
+ .quad compat_sys_io_submit
+ .quad sys_io_cancel
+ .quad sys_fadvise64 /* 250 */
+ .quad quiet_ni_syscall /* free_huge_pages */
+ .quad sys_exit_group
+ .quad sys32_lookup_dcookie
+ .quad sys_epoll_create
+ .quad sys_epoll_ctl /* 255 */
+ .quad sys_epoll_wait
+ .quad sys_remap_file_pages
+ .quad sys_set_tid_address
+ .quad sys32_timer_create
+ .quad compat_sys_timer_settime /* 260 */
+ .quad compat_sys_timer_gettime
+ .quad sys_timer_getoverrun
+ .quad sys_timer_delete
+ .quad compat_sys_clock_settime
+ .quad compat_sys_clock_gettime /* 265 */
+ .quad compat_sys_clock_getres
+ .quad compat_sys_clock_nanosleep
+ .quad compat_sys_statfs64
+ .quad compat_sys_fstatfs64
+ .quad sys_tgkill /* 270 */
+ .quad compat_sys_utimes
+ .quad sys32_fadvise64_64
+ .quad quiet_ni_syscall /* sys_vserver */
+ .quad sys_mbind
+ .quad compat_sys_get_mempolicy /* 275 */
+ .quad sys_set_mempolicy
+ .quad compat_sys_mq_open
+ .quad sys_mq_unlink
+ .quad compat_sys_mq_timedsend
+ .quad compat_sys_mq_timedreceive /* 280 */
+ .quad compat_sys_mq_notify
+ .quad compat_sys_mq_getsetattr
+ .quad quiet_ni_syscall /* reserved for kexec */
+ .quad sys32_waitid
+ .quad quiet_ni_syscall /* sys_altroot */
+ .quad sys_add_key
+ .quad sys_request_key
+ .quad sys_keyctl
+ /* don't forget to change IA32_NR_syscalls */
+ia32_syscall_end:
+ .rept IA32_NR_syscalls-(ia32_syscall_end-ia32_sys_call_table)/8
+ .quad ni_syscall
+ .endr
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blktap/blktap_controlmsg.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blktap/blktap_controlmsg.c Fri Jul
15 13:39:50 2005
@@ -0,0 +1,540 @@
+/******************************************************************************
+ * blktap_controlmsg.c
+ *
+ * XenLinux virtual block-device tap.
+ * Control interfaces to the frontend and backend drivers.
+ *
+ * Copyright (c) 2004, Andrew Warfield
+ *
+ */
+
+#include "blktap.h"
+
+static char *blkif_state_name[] = {
+ [BLKIF_STATE_CLOSED] = "closed",
+ [BLKIF_STATE_DISCONNECTED] = "disconnected",
+ [BLKIF_STATE_CONNECTED] = "connected",
+};
+
+static char * blkif_status_name[] = {
+ [BLKIF_INTERFACE_STATUS_CLOSED] = "closed",
+ [BLKIF_INTERFACE_STATUS_DISCONNECTED] = "disconnected",
+ [BLKIF_INTERFACE_STATUS_CONNECTED] = "connected",
+ [BLKIF_INTERFACE_STATUS_CHANGED] = "changed",
+};
+
+static unsigned blktap_be_irq;
+unsigned int blktap_be_state = BLKIF_STATE_CLOSED;
+unsigned int blktap_be_evtchn;
+
+/*-----[ Control Messages to/from Frontend VMs ]--------------------------*/
+
+#define BLKIF_HASHSZ 1024
+#define BLKIF_HASH(_d,_h) (((int)(_d)^(int)(_h))&(BLKIF_HASHSZ-1))
+
+static kmem_cache_t *blkif_cachep;
+static blkif_t *blkif_hash[BLKIF_HASHSZ];
+
+blkif_t *blkif_find_by_handle(domid_t domid, unsigned int handle)
+{
+ blkif_t *blkif = blkif_hash[BLKIF_HASH(domid, handle)];
+ while ( (blkif != NULL) &&
+ ((blkif->domid != domid) || (blkif->handle != handle)) )
+ blkif = blkif->hash_next;
+ return blkif;
+}
+
+static void __blkif_disconnect_complete(void *arg)
+{
+ blkif_t *blkif = (blkif_t *)arg;
+ ctrl_msg_t cmsg;
+ blkif_be_disconnect_t disc;
+
+ /*
+ * These can't be done in blkif_disconnect() because at that point there
+ * may be outstanding requests at the disc whose asynchronous responses
+ * must still be notified to the remote driver.
+ */
+ unbind_evtchn_from_irq(blkif->evtchn);
+ vfree(blkif->blk_ring.sring);
+
+ /* Construct the deferred response message. */
+ cmsg.type = CMSG_BLKIF_BE;
+ cmsg.subtype = CMSG_BLKIF_BE_DISCONNECT;
+ cmsg.id = blkif->disconnect_rspid;
+ cmsg.length = sizeof(blkif_be_disconnect_t);
+ disc.domid = blkif->domid;
+ disc.blkif_handle = blkif->handle;
+ disc.status = BLKIF_BE_STATUS_OKAY;
+ memcpy(cmsg.msg, &disc, sizeof(disc));
+
+ /*
+ * Make sure message is constructed /before/ status change, because
+ * after the status change the 'blkif' structure could be deallocated at
+ * any time. Also make sure we send the response /after/ status change,
+ * as otherwise a subsequent CONNECT request could spuriously fail if
+ * another CPU doesn't see the status change yet.
+ */
+ mb();
+ if ( blkif->status != DISCONNECTING )
+ BUG();
+ blkif->status = DISCONNECTED;
+ mb();
+
+ /* Send the successful response. */
+ ctrl_if_send_response(&cmsg);
+}
+
+void blkif_disconnect_complete(blkif_t *blkif)
+{
+ INIT_WORK(&blkif->work, __blkif_disconnect_complete, (void *)blkif);
+ schedule_work(&blkif->work);
+}
+
+void blkif_ptfe_create(blkif_be_create_t *create)
+{
+ blkif_t *blkif, **pblkif;
+ domid_t domid = create->domid;
+ unsigned int handle = create->blkif_handle;
+
+
+ /* May want to store info on the connecting domain here. */
+
+ DPRINTK("PT got BE_CREATE\n");
+
+ if ( (blkif = kmem_cache_alloc(blkif_cachep, GFP_KERNEL)) == NULL )
+ {
+ WPRINTK("Could not create blkif: out of memory\n");
+ create->status = BLKIF_BE_STATUS_OUT_OF_MEMORY;
+ return;
+ }
+
+ /* blkif struct init code from blkback.c */
+ memset(blkif, 0, sizeof(*blkif));
+ blkif->domid = domid;
+ blkif->handle = handle;
+ blkif->status = DISCONNECTED;
+ spin_lock_init(&blkif->blk_ring_lock);
+ atomic_set(&blkif->refcnt, 0);
+
+ pblkif = &blkif_hash[BLKIF_HASH(domid, handle)];
+ while ( *pblkif != NULL )
+ {
+ if ( ((*pblkif)->domid == domid) && ((*pblkif)->handle == handle) )
+ {
+ WPRINTK("Could not create blkif: already exists\n");
+ create->status = BLKIF_BE_STATUS_INTERFACE_EXISTS;
+ kmem_cache_free(blkif_cachep, blkif);
+ return;
+ }
+ pblkif = &(*pblkif)->hash_next;
+ }
+
+ blkif->hash_next = *pblkif;
+ *pblkif = blkif;
+
+ create->status = BLKIF_BE_STATUS_OKAY;
+}
+
+
+void blkif_ptfe_destroy(blkif_be_destroy_t *destroy)
+{
+ /* Clear anything that we initialized above. */
+
+ domid_t domid = destroy->domid;
+ unsigned int handle = destroy->blkif_handle;
+ blkif_t **pblkif, *blkif;
+
+ DPRINTK("PT got BE_DESTROY\n");
+
+ pblkif = &blkif_hash[BLKIF_HASH(domid, handle)];
+ while ( (blkif = *pblkif) != NULL )
+ {
+ if ( (blkif->domid == domid) && (blkif->handle == handle) )
+ {
+ if ( blkif->status != DISCONNECTED )
+ goto still_connected;
+ goto destroy;
+ }
+ pblkif = &blkif->hash_next;
+ }
+
+ destroy->status = BLKIF_BE_STATUS_INTERFACE_NOT_FOUND;
+ return;
+
+ still_connected:
+ destroy->status = BLKIF_BE_STATUS_INTERFACE_CONNECTED;
+ return;
+
+ destroy:
+ *pblkif = blkif->hash_next;
+ kmem_cache_free(blkif_cachep, blkif);
+ destroy->status = BLKIF_BE_STATUS_OKAY;
+}
+
+void blkif_ptfe_connect(blkif_be_connect_t *connect)
+{
+ domid_t domid = connect->domid;
+ unsigned int handle = connect->blkif_handle;
+ unsigned int evtchn = connect->evtchn;
+ unsigned long shmem_frame = connect->shmem_frame;
+ struct vm_struct *vma;
+ pgprot_t prot;
+ int error;
+ blkif_t *blkif;
+ blkif_sring_t *sring;
+
+ DPRINTK("PT got BE_CONNECT\n");
+
+ blkif = blkif_find_by_handle(domid, handle);
+ if ( unlikely(blkif == NULL) )
+ {
+ WPRINTK("blkif_connect attempted for non-existent blkif (%u,%u)\n",
+ connect->domid, connect->blkif_handle);
+ connect->status = BLKIF_BE_STATUS_INTERFACE_NOT_FOUND;
+ return;
+ }
+
+ if ( (vma = get_vm_area(PAGE_SIZE, VM_IOREMAP)) == NULL )
+ {
+ connect->status = BLKIF_BE_STATUS_OUT_OF_MEMORY;
+ return;
+ }
+
+ prot = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED);
+ error = direct_remap_area_pages(&init_mm, VMALLOC_VMADDR(vma->addr),
+ shmem_frame<<PAGE_SHIFT, PAGE_SIZE,
+ prot, domid);
+ if ( error != 0 )
+ {
+ WPRINTK("BE_CONNECT: error! (%d)\n", error);
+ if ( error == -ENOMEM )
+ connect->status = BLKIF_BE_STATUS_OUT_OF_MEMORY;
+ else if ( error == -EFAULT ) {
+ connect->status = BLKIF_BE_STATUS_MAPPING_ERROR;
+ WPRINTK("BE_CONNECT: MAPPING error!\n");
+ }
+ else
+ connect->status = BLKIF_BE_STATUS_ERROR;
+ vfree(vma->addr);
+ return;
+ }
+
+ if ( blkif->status != DISCONNECTED )
+ {
+ connect->status = BLKIF_BE_STATUS_INTERFACE_CONNECTED;
+ vfree(vma->addr);
+ return;
+ }
+
+ sring = (blkif_sring_t *)vma->addr;
+ SHARED_RING_INIT(sring);
+ BACK_RING_INIT(&blkif->blk_ring, sring, PAGE_SIZE);
+
+ blkif->evtchn = evtchn;
+ blkif->irq = bind_evtchn_to_irq(evtchn);
+ blkif->shmem_frame = shmem_frame;
+ blkif->status = CONNECTED;
+ blkif_get(blkif);
+
+ request_irq(blkif->irq, blkif_ptfe_int, 0, "blkif-pt-backend", blkif);
+
+ connect->status = BLKIF_BE_STATUS_OKAY;
+}
+
+int blkif_ptfe_disconnect(blkif_be_disconnect_t *disconnect, u8 rsp_id)
+{
+ domid_t domid = disconnect->domid;
+ unsigned int handle = disconnect->blkif_handle;
+ blkif_t *blkif;
+
+ DPRINTK("PT got BE_DISCONNECT\n");
+
+ blkif = blkif_find_by_handle(domid, handle);
+ if ( unlikely(blkif == NULL) )
+ {
+ WPRINTK("blkif_disconnect attempted for non-existent blkif"
+ " (%u,%u)\n", disconnect->domid, disconnect->blkif_handle);
+ disconnect->status = BLKIF_BE_STATUS_INTERFACE_NOT_FOUND;
+ return 1; /* Caller will send response error message. */
+ }
+
+ if ( blkif->status == CONNECTED )
+ {
+ blkif->status = DISCONNECTING;
+ blkif->disconnect_rspid = rsp_id;
+ wmb(); /* Let other CPUs see the status change. */
+ free_irq(blkif->irq, blkif);
+ blkif_deschedule(blkif);
+ blkif_put(blkif);
+ return 0; /* Caller should not send response message. */
+ }
+
+ disconnect->status = BLKIF_BE_STATUS_OKAY;
+ return 1;
+}
+
+/*-----[ Control Messages to/from Backend VM ]----------------------------*/
+
+/* Tell the controller to bring up the interface. */
+static void blkif_ptbe_send_interface_connect(void)
+{
+ ctrl_msg_t cmsg = {
+ .type = CMSG_BLKIF_FE,
+ .subtype = CMSG_BLKIF_FE_INTERFACE_CONNECT,
+ .length = sizeof(blkif_fe_interface_connect_t),
+ };
+ blkif_fe_interface_connect_t *msg = (void*)cmsg.msg;
+ msg->handle = 0;
+ msg->shmem_frame = virt_to_machine(blktap_be_ring.sring) >> PAGE_SHIFT;
+
+ ctrl_if_send_message_block(&cmsg, NULL, 0, TASK_UNINTERRUPTIBLE);
+}
+
+static void blkif_ptbe_close(void)
+{
+}
+
+/* Move from CLOSED to DISCONNECTED state. */
+static void blkif_ptbe_disconnect(void)
+{
+ blkif_sring_t *sring;
+
+ sring = (blkif_sring_t *)__get_free_page(GFP_KERNEL);
+ SHARED_RING_INIT(sring);
+ FRONT_RING_INIT(&blktap_be_ring, sring, PAGE_SIZE);
+ blktap_be_state = BLKIF_STATE_DISCONNECTED;
+ DPRINTK("Blkif-Passthrough-BE is now DISCONNECTED.\n");
+ blkif_ptbe_send_interface_connect();
+}
+
+static void blkif_ptbe_connect(blkif_fe_interface_status_t *status)
+{
+ int err = 0;
+
+ blktap_be_evtchn = status->evtchn;
+ blktap_be_irq = bind_evtchn_to_irq(blktap_be_evtchn);
+
+ err = request_irq(blktap_be_irq, blkif_ptbe_int,
+ SA_SAMPLE_RANDOM, "blkif", NULL);
+ if ( err ) {
+ WPRINTK("blkfront request_irq failed (%d)\n", err);
+ return;
+ } else {
+ /* transtion to connected in case we need to do a
+ a partion probe on a whole disk */
+ blktap_be_state = BLKIF_STATE_CONNECTED;
+ }
+}
+
+static void unexpected(blkif_fe_interface_status_t *status)
+{
+ WPRINTK(" TAP: Unexpected blkif status %s in state %s\n",
+ blkif_status_name[status->status],
+ blkif_state_name[blktap_be_state]);
+}
+
+static void blkif_ptbe_status(
+ blkif_fe_interface_status_t *status)
+{
+ if ( status->handle != 0 )
+ {
+ DPRINTK("Status change on unsupported blkif %d\n",
+ status->handle);
+ return;
+ }
+
+ DPRINTK("ptbe_status: got %s\n", blkif_status_name[status->status]);
+
+ switch ( status->status )
+ {
+ case BLKIF_INTERFACE_STATUS_CLOSED:
+ switch ( blktap_be_state )
+ {
+ case BLKIF_STATE_CLOSED:
+ unexpected(status);
+ break;
+ case BLKIF_STATE_DISCONNECTED:
+ case BLKIF_STATE_CONNECTED:
+ unexpected(status);
+ blkif_ptbe_close();
+ break;
+ }
+ break;
+
+ case BLKIF_INTERFACE_STATUS_DISCONNECTED:
+ switch ( blktap_be_state )
+ {
+ case BLKIF_STATE_CLOSED:
+ blkif_ptbe_disconnect();
+ break;
+ case BLKIF_STATE_DISCONNECTED:
+ case BLKIF_STATE_CONNECTED:
+ printk(KERN_ALERT "*** add recovery code to the tap driver.
***\n");
+ unexpected(status);
+ break;
+ }
+ break;
+
+ case BLKIF_INTERFACE_STATUS_CONNECTED:
+ switch ( blktap_be_state )
+ {
+ case BLKIF_STATE_CLOSED:
+ unexpected(status);
+ blkif_ptbe_disconnect();
+ blkif_ptbe_connect(status);
+ break;
+ case BLKIF_STATE_DISCONNECTED:
+ blkif_ptbe_connect(status);
+ break;
+ case BLKIF_STATE_CONNECTED:
+ unexpected(status);
+ blkif_ptbe_connect(status);
+ break;
+ }
+ break;
+
+ case BLKIF_INTERFACE_STATUS_CHANGED:
+ switch ( blktap_be_state )
+ {
+ case BLKIF_STATE_CLOSED:
+ case BLKIF_STATE_DISCONNECTED:
+ unexpected(status);
+ break;
+ case BLKIF_STATE_CONNECTED:
+ /* vbd_update(); */
+ /* tap doesn't really get state changes... */
+ unexpected(status);
+ break;
+ }
+ break;
+
+ default:
+ DPRINTK("Status change to unknown value %d\n", status->status);
+ break;
+ }
+}
+
+/*-----[ All control messages enter here: ]-------------------------------*/
+
+void blkif_ctrlif_rx(ctrl_msg_t *msg, unsigned long id)
+{
+ switch ( msg->type )
+ {
+ case CMSG_BLKIF_FE:
+
+ switch ( msg->subtype )
+ {
+ case CMSG_BLKIF_FE_INTERFACE_STATUS:
+ blkif_ptbe_status((blkif_fe_interface_status_t *) &msg->msg[0]);
+ break;
+
+ default:
+ goto parse_error;
+ }
+
+ break;
+
+ case CMSG_BLKIF_BE:
+
+ /* send a copy of the message to user if wanted */
+
+ if ( (blktap_mode & BLKTAP_MODE_INTERCEPT_FE) ||
+ (blktap_mode & BLKTAP_MODE_COPY_FE) ) {
+
+ blktap_write_ctrl_ring(msg);
+ blktap_kick_user();
+ }
+
+ switch ( msg->subtype )
+ {
+ case CMSG_BLKIF_BE_CREATE:
+ blkif_ptfe_create((blkif_be_create_t *)&msg->msg[0]);
+ break;
+ case CMSG_BLKIF_BE_DESTROY:
+ blkif_ptfe_destroy((blkif_be_destroy_t *)&msg->msg[0]);
+ break;
+ case CMSG_BLKIF_BE_CONNECT:
+ blkif_ptfe_connect((blkif_be_connect_t *)&msg->msg[0]);
+ break;
+ case CMSG_BLKIF_BE_DISCONNECT:
+ if ( !blkif_ptfe_disconnect((blkif_be_disconnect_t *)&msg->msg[0],
+ msg->id) )
+ return;
+ break;
+
+ /* We just ignore anything to do with vbds for now. */
+
+ case CMSG_BLKIF_BE_VBD_CREATE:
+ DPRINTK("PT got VBD_CREATE\n");
+ ((blkif_be_vbd_create_t *)&msg->msg[0])->status
+ = BLKIF_BE_STATUS_OKAY;
+ break;
+ case CMSG_BLKIF_BE_VBD_DESTROY:
+ DPRINTK("PT got VBD_DESTROY\n");
+ ((blkif_be_vbd_destroy_t *)&msg->msg[0])->status
+ = BLKIF_BE_STATUS_OKAY;
+ break;
+ default:
+ goto parse_error;
+ }
+
+ break;
+ }
+
+ ctrl_if_send_response(msg);
+ return;
+
+ parse_error:
+ msg->length = 0;
+ ctrl_if_send_response(msg);
+}
+
+/*-----[ Initialization ]-------------------------------------------------*/
+
+void __init blkif_interface_init(void)
+{
+ blkif_cachep = kmem_cache_create("blkif_cache", sizeof(blkif_t),
+ 0, 0, NULL, NULL);
+ memset(blkif_hash, 0, sizeof(blkif_hash));
+
+ blktap_be_ring.sring = NULL;
+}
+
+
+
+/* Debug : print the current ring indices. */
+
+void print_fe_ring_idxs(void)
+{
+ int i;
+ blkif_t *blkif;
+
+ WPRINTK("FE Rings: \n---------\n");
+ for ( i = 0; i < BLKIF_HASHSZ; i++) {
+ blkif = blkif_hash[i];
+ while (blkif != NULL) {
+ if (blkif->status == DISCONNECTED) {
+ WPRINTK("(%2d,%2d) DISCONNECTED\n",
+ blkif->domid, blkif->handle);
+ } else if (blkif->status == DISCONNECTING) {
+ WPRINTK("(%2d,%2d) DISCONNECTING\n",
+ blkif->domid, blkif->handle);
+ } else if (blkif->blk_ring.sring == NULL) {
+ WPRINTK("(%2d,%2d) CONNECTED, but null sring!\n",
+ blkif->domid, blkif->handle);
+ } else {
+ blkif_get(blkif);
+ WPRINTK("(%2d,%2d): req_cons: %2d, rsp_prod_prv: %2d "
+ "| req_prod: %2d, rsp_prod: %2d\n",
+ blkif->domid, blkif->handle,
+ blkif->blk_ring.req_cons,
+ blkif->blk_ring.rsp_prod_pvt,
+ blkif->blk_ring.sring->req_prod,
+ blkif->blk_ring.sring->rsp_prod);
+ blkif_put(blkif);
+ }
+ blkif = blkif->hash_next;
+ }
+ }
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/Kconfig
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/Kconfig Fri Jul 15 13:39:50 2005
@@ -0,0 +1,455 @@
+#
+# For a description of the syntax of this configuration file,
+# see Documentation/kbuild/kconfig-language.txt.
+#
+# Note: ISA is disabled and will hopefully never be enabled.
+# If you managed to buy an ISA x86-64 box you'll have to fix all the
+# ISA drivers you need yourself.
+#
+
+menu "X86_64 processor configuration"
+
+config XENARCH
+ string
+ default x86_64
+
+config X86_64
+ bool
+ default y
+ help
+ Port to the x86-64 architecture. x86-64 is a 64-bit extension to the
+ classical 32-bit x86 architecture. For details see
+ <http://www.x86-64.org/>.
+
+config X86
+ bool
+ default y
+
+config 64BIT
+ def_bool y
+
+config MMU
+ bool
+ default y
+
+config ISA
+ bool
+
+config SBUS
+ bool
+
+config RWSEM_GENERIC_SPINLOCK
+ bool
+ default y
+
+config RWSEM_XCHGADD_ALGORITHM
+ bool
+
+config GENERIC_CALIBRATE_DELAY
+ bool
+ default y
+
+config X86_CMPXCHG
+ bool
+ default y
+
+config EARLY_PRINTK
+ bool "Early Printk"
+ default n
+ help
+ Write kernel log output directly into the VGA buffer or to a serial
+ port.
+
+ This is useful for kernel debugging when your machine crashes very
+ early before the console code is initialized. For normal operation
+ it is not recommended because it looks ugly and doesn't cooperate
+ with klogd/syslogd or the X server. You should normally N here,
+ unless you want to debug such a crash.
+
+config HPET_TIMER
+ bool
+ default n
+ help
+ Use the IA-PC HPET (High Precision Event Timer) to manage
+ time in preference to the PIT and RTC, if a HPET is
+ present. The HPET provides a stable time base on SMP
+ systems, unlike the RTC, but it is more expensive to access,
+ as it is off-chip. You can find the HPET spec at
+ <http://www.intel.com/labs/platcomp/hpet/hpetspec.htm>.
+
+ If unsure, say Y.
+
+config HPET_EMULATE_RTC
+ bool "Provide RTC interrupt"
+ depends on HPET_TIMER && RTC=y
+
+config GENERIC_ISA_DMA
+ bool
+ default y
+
+config GENERIC_IOMAP
+ bool
+ default y
+
+#source "init/Kconfig"
+
+
+menu "Processor type and features"
+
+choice
+ prompt "Processor family"
+ default MK8
+
+#config MK8
+# bool "AMD-Opteron/Athlon64"
+# help
+# Optimize for AMD Opteron/Athlon64/Hammer/K8 CPUs.
+
+config MPSC
+ bool "Intel x86-64"
+ help
+ Optimize for Intel IA32 with 64bit extension CPUs
+ (Prescott/Nocona/Potomac)
+
+config GENERIC_CPU
+ bool "Generic-x86-64"
+ help
+ Generic x86-64 CPU.
+
+endchoice
+
+#
+# Define implied options from the CPU selection here
+#
+config X86_L1_CACHE_BYTES
+ int
+ default "128" if GENERIC_CPU || MPSC
+ default "64" if MK8
+
+config X86_L1_CACHE_SHIFT
+ int
+ default "7" if GENERIC_CPU || MPSC
+ default "6" if MK8
+
+config X86_TSC
+ bool
+ default n
+
+config X86_GOOD_APIC
+ bool
+ default y
+
+config X86_IO_APIC
+ bool
+ default XEN_PRIVILEGED_GUEST
+
+config X86_LOCAL_APIC
+ bool
+ default XEN_PRIVILEGED_GUEST
+
+config MICROCODE
+ tristate "/dev/cpu/microcode - Intel CPU microcode support"
+ ---help---
+ If you say Y here the 'File systems' section, you will be
+ able to update the microcode on Intel processors. You will
+ obviously need the actual microcode binary data itself which is
+ not shipped with the Linux kernel.
+
+ For latest news and information on obtaining all the required
+ ingredients for this driver, check:
+ <http://www.urbanmyth.org/microcode/>.
+
+ To compile this driver as a module, choose M here: the
+ module will be called microcode.
+ If you use modprobe or kmod you may also want to add the line
+ 'alias char-major-10-184 microcode' to your /etc/modules.conf file.
+
+config X86_MSR
+ tristate "/dev/cpu/*/msr - Model-specific register support"
+ help
+ This device gives privileged processes access to the x86
+ Model-Specific Registers (MSRs). It is a character device with
+ major 202 and minors 0 to 31 for /dev/cpu/0/msr to /dev/cpu/31/msr.
+ MSR accesses are directed to a specific CPU on multi-processor
+ systems.
+
+config X86_CPUID
+ tristate "/dev/cpu/*/cpuid - CPU information support"
+ help
+ This device gives processes access to the x86 CPUID instruction to
+ be executed on a specific processor. It is a character device
+ with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to
+ /dev/cpu/31/cpuid.
+
+# disable it for opteron optimized builds because it pulls in ACPI_BOOT
+config X86_HT
+ bool
+ depends on SMP && !MK8
+ default y
+
+config MATH_EMULATION
+ bool
+
+config MCA
+ bool
+
+config EISA
+ bool
+
+config MTRR
+ bool "MTRR (Memory Type Range Register) support"
+ ---help---
+ On Intel P6 family processors (Pentium Pro, Pentium II and later)
+ the Memory Type Range Registers (MTRRs) may be used to control
+ processor access to memory ranges. This is most useful if you have
+ a video (VGA) card on a PCI or AGP bus. Enabling write-combining
+ allows bus write transfers to be combined into a larger transfer
+ before bursting over the PCI/AGP bus. This can increase performance
+ of image write operations 2.5 times or more. Saying Y here creates a
+ /proc/mtrr file which may be used to manipulate your processor's
+ MTRRs. Typically the X server should use this.
+
+ This code has a reasonably generic interface so that similar
+ control registers on other processors can be easily supported
+ as well.
+
+ Saying Y here also fixes a problem with buggy SMP BIOSes which only
+ set the MTRRs for the boot CPU and not for the secondary CPUs. This
+ can lead to all sorts of problems, so it's good to say Y here.
+
+ Just say Y here, all x86-64 machines support MTRRs.
+
+ See <file:Documentation/mtrr.txt> for more information.
+
+config SMP
+ bool "Symmetric multi-processing support"
+ ---help---
+ This enables support for systems with more than one CPU. If you have
+ a system with only one CPU, like most personal computers, say N. If
+ you have a system with more than one CPU, say Y.
+
+ If you say N here, the kernel will run on single and multiprocessor
+ machines, but will use only one CPU of a multiprocessor machine. If
+ you say Y here, the kernel will run on many, but not all,
+ singleprocessor machines. On a singleprocessor machine, the kernel
+ will run faster if you say N here.
+
+ If you don't know what to do here, say N.
+
+config PREEMPT
+ bool "Preemptible Kernel"
+ ---help---
+ This option reduces the latency of the kernel when reacting to
+ real-time or interactive events by allowing a low priority process to
+ be preempted even if it is in kernel mode executing a system call.
+ This allows applications to run more reliably even when the system is
+ under load. On contrary it may also break your drivers and add
+ priority inheritance problems to your system. Don't select it if
+ you rely on a stable system or have slightly obscure hardware.
+ It's also not very well tested on x86-64 currently.
+ You have been warned.
+
+ Say Y here if you are feeling brave and building a kernel for a
+ desktop, embedded or real-time system. Say N if you are unsure.
+
+config SCHED_SMT
+ bool "SMT (Hyperthreading) scheduler support"
+ depends on SMP
+ default off
+ help
+ SMT scheduler support improves the CPU scheduler's decision making
+ when dealing with Intel Pentium 4 chips with HyperThreading at a
+ cost of slightly increased overhead in some places. If unsure say
+ N here.
+
+config K8_NUMA
+ bool "K8 NUMA support"
+ select NUMA
+ depends on SMP
+ help
+ Enable NUMA (Non Unified Memory Architecture) support for
+ AMD Opteron Multiprocessor systems. The kernel will try to allocate
+ memory used by a CPU on the local memory controller of the CPU
+ and add some more NUMA awareness to the kernel.
+ This code is recommended on all multiprocessor Opteron systems
+ and normally doesn't hurt on others.
+
+config NUMA_EMU
+ bool "NUMA emulation support"
+ select NUMA
+ depends on SMP
+ help
+ Enable NUMA emulation. A flat machine will be split
+ into virtual nodes when booted with "numa=fake=N", where N is the
+ number of nodes. This is only useful for debugging.
+
+config DISCONTIGMEM
+ bool
+ depends on NUMA
+ default y
+
+config NUMA
+ bool
+ default n
+
+config HAVE_DEC_LOCK
+ bool
+ depends on SMP
+ default y
+
+# actually 64 maximum, but you need to fix the APIC code first
+# to use clustered mode or whatever your big iron needs
+config NR_CPUS
+ int "Maximum number of CPUs (2-8)"
+ range 2 8
+ depends on SMP
+ default "8"
+ help
+ This allows you to specify the maximum number of CPUs which this
+ kernel will support. The maximum supported value is 32 and the
+ minimum value which makes sense is 2.
+
+ This is purely to save memory - each supported CPU requires
+ memory in the static kernel configuration.
+
+config GART_IOMMU
+ bool "IOMMU support"
+ depends on PCI
+ help
+ Support the K8 IOMMU. Needed to run systems with more than 4GB of
memory
+ properly with 32-bit PCI devices that do not support DAC (Double
Address
+ Cycle). The IOMMU can be turned off at runtime with the iommu=off
parameter.
+ Normally the kernel will take the right choice by itself.
+ If unsure, say Y.
+
+# need this always enabled with GART_IOMMU for the VIA workaround
+config SWIOTLB
+ bool
+ depends on GART_IOMMU
+ default y
+
+config DUMMY_IOMMU
+ bool
+ depends on !GART_IOMMU && !SWIOTLB
+ default y
+ help
+ Don't use IOMMU code. This will cause problems when you have more
than 4GB
+ of memory and any 32-bit devices. Don't turn on unless you know what
you
+ are doing.
+
+config X86_MCE
+ bool "Machine check support" if EMBEDDED
+ default n
+ help
+ Include a machine check error handler to report hardware errors.
+ This version will require the mcelog utility to decode some
+ machine check error logs. See
+ ftp://ftp.x86-64.org/pub/linux/tools/mcelog
+
+endmenu
+
+#
+# Use the generic interrupt handling code in kernel/irq/:
+#
+config GENERIC_HARDIRQS
+ bool
+ default y
+
+config GENERIC_IRQ_PROBE
+ bool
+ default y
+
+menu "Power management options"
+
+source kernel/power/Kconfig
+
+source "arch/x86_64/kernel/cpufreq/Kconfig"
+
+endmenu
+
+menu "Bus options (PCI etc.)"
+
+config PCI
+ bool "PCI support"
+
+# x86-64 doesn't support PCI BIOS access from long mode so always go direct.
+config PCI_DIRECT
+ bool
+ depends on PCI
+ default y
+
+config PCI_MMCONFIG
+ bool "Support mmconfig PCI config space access"
+ depends on PCI
+ select ACPI_BOOT
+
+config UNORDERED_IO
+ bool "Unordered IO mapping access"
+ depends on EXPERIMENTAL
+ help
+ Use unordered stores to access IO memory mappings in device drivers.
+ Still very experimental. When a driver works on IA64/ppc64/pa-risc it
should
+ work with this option, but it makes the drivers behave differently
+ from i386. Requires that the driver writer used memory barriers
+ properly.
+
+#source "drivers/pci/Kconfig"
+
+#source "drivers/pcmcia/Kconfig"
+
+#source "drivers/pci/hotplug/Kconfig"
+
+endmenu
+
+
+menu "Executable file formats / Emulations"
+
+# source "fs/Kconfig.binfmt"
+
+config IA32_EMULATION
+ bool "IA32 Emulation"
+ help
+ Include code to run 32-bit programs under a 64-bit kernel. You should
likely
+ turn this on, unless you're 100% sure that you don't have any 32-bit
programs
+ left.
+
+config IA32_AOUT
+ bool "IA32 a.out support"
+ depends on IA32_EMULATION
+ help
+ Support old a.out binaries in the 32bit emulation.
+
+config COMPAT
+ bool
+ depends on IA32_EMULATION
+ default y
+
+config SYSVIPC_COMPAT
+ bool
+ depends on COMPAT && SYSVIPC
+ default y
+
+config UID16
+ bool
+ depends on IA32_EMULATION
+ default y
+
+endmenu
+
+# source drivers/Kconfig
+
+# source "drivers/firmware/Kconfig"
+
+# source fs/Kconfig
+
+#source "arch/x86_64/oprofile/Kconfig"
+
+#source "arch/x86_64/Kconfig.debug"
+
+# source "security/Kconfig"
+
+# source "crypto/Kconfig"
+
+# source "lib/Kconfig"
+
+endmenu
diff -r 35b74976f598 -r a83ac0806d6b patches/linux-2.6.11/agpgart.patch
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/patches/linux-2.6.11/agpgart.patch Fri Jul 15 13:39:50 2005
@@ -0,0 +1,437 @@
+--- linux-2.6.11/drivers/char/agp/agp.h 2005-03-02 07:38:07 +00:00
++++ linux-2.6.11-agp/drivers/char/agp/agp.h 2005-03-22 11:14:02 +00:00
+@@ -272,6 +272,8 @@
+ #define AGP_GENERIC_SIZES_ENTRIES 11
+ extern struct aper_size_info_16 agp3_generic_sizes[];
+
++#define virt_to_gart(x) (phys_to_gart(virt_to_phys(x)))
++#define gart_to_virt(x) (phys_to_virt(gart_to_phys(x)))
+
+ extern int agp_off;
+ extern int agp_try_unsupported_boot;
+--- linux-2.6.11/drivers/char/agp/ali-agp.c 2005-03-02 07:38:13 +00:00
++++ linux-2.6.11-agp/drivers/char/agp/ali-agp.c 2005-03-22 11:14:56
+00:00
+@@ -150,7 +150,7 @@
+ pci_read_config_dword(agp_bridge->dev, ALI_CACHE_FLUSH_CTRL, &temp);
+ pci_write_config_dword(agp_bridge->dev, ALI_CACHE_FLUSH_CTRL,
+ (((temp & ALI_CACHE_FLUSH_ADDR_MASK) |
+- virt_to_phys(addr)) | ALI_CACHE_FLUSH_EN ));
++ virt_to_gart(addr)) | ALI_CACHE_FLUSH_EN ));
+ return addr;
+ }
+
+@@ -174,7 +174,7 @@
+ pci_read_config_dword(agp_bridge->dev, ALI_CACHE_FLUSH_CTRL, &temp);
+ pci_write_config_dword(agp_bridge->dev, ALI_CACHE_FLUSH_CTRL,
+ (((temp & ALI_CACHE_FLUSH_ADDR_MASK) |
+- virt_to_phys(addr)) | ALI_CACHE_FLUSH_EN));
++ virt_to_gart(addr)) | ALI_CACHE_FLUSH_EN));
+ agp_generic_destroy_page(addr);
+ }
+
+--- linux-2.6.11/drivers/char/agp/amd-k7-agp.c 2005-03-02 07:38:33 +00:00
++++ linux-2.6.11-agp/drivers/char/agp/amd-k7-agp.c 2005-03-22 11:14:56
+00:00
+@@ -43,7 +43,7 @@
+
+ SetPageReserved(virt_to_page(page_map->real));
+ global_cache_flush();
+- page_map->remapped = ioremap_nocache(virt_to_phys(page_map->real),
++ page_map->remapped = ioremap_nocache(virt_to_gart(page_map->real),
+ PAGE_SIZE);
+ if (page_map->remapped == NULL) {
+ ClearPageReserved(virt_to_page(page_map->real));
+@@ -154,7 +154,7 @@
+
+ agp_bridge->gatt_table_real = (u32 *)page_dir.real;
+ agp_bridge->gatt_table = (u32 __iomem *)page_dir.remapped;
+- agp_bridge->gatt_bus_addr = virt_to_phys(page_dir.real);
++ agp_bridge->gatt_bus_addr = virt_to_gart(page_dir.real);
+
+ /* Get the address for the gart region.
+ * This is a bus address even on the alpha, b/c its
+@@ -167,7 +167,7 @@
+
+ /* Calculate the agp offset */
+ for (i = 0; i < value->num_entries / 1024; i++, addr += 0x00400000) {
+- writel(virt_to_phys(amd_irongate_private.gatt_pages[i]->real) |
1,
++ writel(virt_to_gart(amd_irongate_private.gatt_pages[i]->real) |
1,
+ page_dir.remapped+GET_PAGE_DIR_OFF(addr));
+ readl(page_dir.remapped+GET_PAGE_DIR_OFF(addr)); /* PCI
Posting. */
+ }
+--- linux-2.6.11/drivers/char/agp/amd64-agp.c 2005-03-02 07:38:13 +00:00
++++ linux-2.6.11-agp/drivers/char/agp/amd64-agp.c 2005-03-22 11:14:56
+00:00
+@@ -218,7 +218,7 @@
+
+ static int amd_8151_configure(void)
+ {
+- unsigned long gatt_bus = virt_to_phys(agp_bridge->gatt_table_real);
++ unsigned long gatt_bus = virt_to_gart(agp_bridge->gatt_table_real);
+
+ /* Configure AGP regs in each x86-64 host bridge. */
+ for_each_nb() {
+@@ -590,7 +590,7 @@
+ {
+ struct agp_bridge_data *bridge = pci_get_drvdata(pdev);
+
+- release_mem_region(virt_to_phys(bridge->gatt_table_real),
++ release_mem_region(virt_to_gart(bridge->gatt_table_real),
+
amd64_aperture_sizes[bridge->aperture_size_idx].size);
+ agp_remove_bridge(bridge);
+ agp_put_bridge(bridge);
+--- linux-2.6.11/drivers/char/agp/ati-agp.c 2005-03-02 07:38:13 +00:00
++++ linux-2.6.11-agp/drivers/char/agp/ati-agp.c 2005-03-22 11:14:56
+00:00
+@@ -61,7 +61,7 @@
+
+ SetPageReserved(virt_to_page(page_map->real));
+ err = map_page_into_agp(virt_to_page(page_map->real));
+- page_map->remapped = ioremap_nocache(virt_to_phys(page_map->real),
++ page_map->remapped = ioremap_nocache(virt_to_gart(page_map->real),
+ PAGE_SIZE);
+ if (page_map->remapped == NULL || err) {
+ ClearPageReserved(virt_to_page(page_map->real));
+--- linux-2.6.11/drivers/char/agp/backend.c 2005-03-02 07:38:13 +00:00
++++ linux-2.6.11-agp/drivers/char/agp/backend.c 2005-03-22 11:14:56
+00:00
+@@ -142,7 +142,7 @@
+ return -ENOMEM;
+ }
+
+- bridge->scratch_page_real = virt_to_phys(addr);
++ bridge->scratch_page_real = virt_to_gart(addr);
+ bridge->scratch_page =
+ bridge->driver->mask_memory(bridge->scratch_page_real, 0);
+ }
+@@ -186,7 +186,7 @@
+ err_out:
+ if (bridge->driver->needs_scratch_page)
+ bridge->driver->agp_destroy_page(
+- phys_to_virt(bridge->scratch_page_real));
++ gart_to_virt(bridge->scratch_page_real));
+ if (got_gatt)
+ bridge->driver->free_gatt_table();
+ if (got_keylist) {
+@@ -211,7 +211,7 @@
+ if (bridge->driver->agp_destroy_page &&
+ bridge->driver->needs_scratch_page)
+ bridge->driver->agp_destroy_page(
+- phys_to_virt(bridge->scratch_page_real));
++ gart_to_virt(bridge->scratch_page_real));
+ }
+
+ /* XXX Kludge alert: agpgart isn't ready for multiple bridges yet */
+--- linux-2.6.11/drivers/char/agp/efficeon-agp.c 2005-03-02 07:37:30
+00:00
++++ linux-2.6.11-agp/drivers/char/agp/efficeon-agp.c 2005-03-22 11:15:17
+00:00
+@@ -219,7 +219,7 @@
+
+ efficeon_private.l1_table[index] = page;
+
+- value = __pa(page) | pati | present | index;
++ value = virt_to_gart(page) | pati | present | index;
+
+ pci_write_config_dword(agp_bridge->dev,
+ EFFICEON_ATTPAGE, value);
+--- linux-2.6.11/drivers/char/agp/generic.c 2005-03-02 07:37:55 +00:00
++++ linux-2.6.11-agp/drivers/char/agp/generic.c 2005-03-22 11:17:37
+00:00
+@@ -151,7 +151,7 @@
+ }
+ if (curr->page_count != 0) {
+ for (i = 0; i < curr->page_count; i++) {
+-
agp_bridge->driver->agp_destroy_page(phys_to_virt(curr->memory[i]));
++
agp_bridge->driver->agp_destroy_page(gart_to_virt(curr->memory[i]));
+ }
+ }
+ agp_free_key(curr->key);
+@@ -204,7 +204,7 @@
+ agp_free_memory(new);
+ return NULL;
+ }
+- new->memory[i] = virt_to_phys(addr);
++ new->memory[i] = virt_to_gart(addr);
+ new->page_count++;
+ }
+
+@@ -697,8 +697,7 @@
+ break;
+ }
+
+- table = (char *) __get_free_pages(GFP_KERNEL,
+- page_order);
++ table = alloc_gatt_pages(page_order);
+
+ if (table == NULL) {
+ i++;
+@@ -729,7 +728,7 @@
+ size = ((struct aper_size_info_fixed *) temp)->size;
+ page_order = ((struct aper_size_info_fixed *) temp)->page_order;
+ num_entries = ((struct aper_size_info_fixed *)
temp)->num_entries;
+- table = (char *) __get_free_pages(GFP_KERNEL, page_order);
++ table = alloc_gatt_pages(page_order);
+ }
+
+ if (table == NULL)
+@@ -744,7 +743,7 @@
+ agp_gatt_table = (void *)table;
+
+ agp_bridge->driver->cache_flush();
+- agp_bridge->gatt_table = ioremap_nocache(virt_to_phys(table),
++ agp_bridge->gatt_table = ioremap_nocache(virt_to_gart(table),
+ (PAGE_SIZE * (1 << page_order)));
+ agp_bridge->driver->cache_flush();
+
+@@ -752,11 +751,11 @@
+ for (page = virt_to_page(table); page <=
virt_to_page(table_end); page++)
+ ClearPageReserved(page);
+
+- free_pages((unsigned long) table, page_order);
++ free_gatt_pages(table, page_order);
+
+ return -ENOMEM;
+ }
+- agp_bridge->gatt_bus_addr = virt_to_phys(agp_bridge->gatt_table_real);
++ agp_bridge->gatt_bus_addr = virt_to_gart(agp_bridge->gatt_table_real);
+
+ /* AK: bogus, should encode addresses > 4GB */
+ for (i = 0; i < num_entries; i++) {
+@@ -810,7 +809,7 @@
+ for (page = virt_to_page(table); page <= virt_to_page(table_end);
page++)
+ ClearPageReserved(page);
+
+- free_pages((unsigned long) agp_bridge->gatt_table_real, page_order);
++ free_gatt_pages(agp_bridge->gatt_table_real, page_order);
+
+ agp_gatt_table = NULL;
+ agp_bridge->gatt_table = NULL;
+--- linux-2.6.11/drivers/char/agp/hp-agp.c 2005-03-02 07:38:19 +00:00
++++ linux-2.6.11-agp/drivers/char/agp/hp-agp.c 2005-03-22 11:14:56 +00:00
+@@ -110,7 +110,7 @@
+ hp->gart_size = HP_ZX1_GART_SIZE;
+ hp->gatt_entries = hp->gart_size / hp->io_page_size;
+
+- hp->io_pdir = phys_to_virt(readq(hp->ioc_regs+HP_ZX1_PDIR_BASE));
++ hp->io_pdir = gart_to_virt(readq(hp->ioc_regs+HP_ZX1_PDIR_BASE));
+ hp->gatt = &hp->io_pdir[HP_ZX1_IOVA_TO_PDIR(hp->gart_base)];
+
+ if (hp->gatt[0] != HP_ZX1_SBA_IOMMU_COOKIE) {
+@@ -248,7 +248,7 @@
+ agp_bridge->mode =
readl(hp->lba_regs+hp->lba_cap_offset+PCI_AGP_STATUS);
+
+ if (hp->io_pdir_owner) {
+- writel(virt_to_phys(hp->io_pdir),
hp->ioc_regs+HP_ZX1_PDIR_BASE);
++ writel(virt_to_gart(hp->io_pdir),
hp->ioc_regs+HP_ZX1_PDIR_BASE);
+ readl(hp->ioc_regs+HP_ZX1_PDIR_BASE);
+ writel(hp->io_tlb_ps, hp->ioc_regs+HP_ZX1_TCNFG);
+ readl(hp->ioc_regs+HP_ZX1_TCNFG);
+--- linux-2.6.11/drivers/char/agp/i460-agp.c 2005-03-02 07:38:10 +00:00
++++ linux-2.6.11-agp/drivers/char/agp/i460-agp.c 2005-03-22 11:14:56
+00:00
+@@ -371,7 +371,7 @@
+ }
+ memset(lp->alloced_map, 0, map_size);
+
+- lp->paddr = virt_to_phys(lpage);
++ lp->paddr = virt_to_gart(lpage);
+ lp->refcount = 0;
+ atomic_add(I460_KPAGES_PER_IOPAGE, &agp_bridge->current_memory_agp);
+ return 0;
+@@ -382,7 +382,7 @@
+ kfree(lp->alloced_map);
+ lp->alloced_map = NULL;
+
+- free_pages((unsigned long) phys_to_virt(lp->paddr), I460_IO_PAGE_SHIFT
- PAGE_SHIFT);
++ free_pages((unsigned long) gart_to_virt(lp->paddr), I460_IO_PAGE_SHIFT
- PAGE_SHIFT);
+ atomic_sub(I460_KPAGES_PER_IOPAGE, &agp_bridge->current_memory_agp);
+ }
+
+--- linux-2.6.11/drivers/char/agp/intel-agp.c 2005-03-02 07:38:09 +00:00
++++ linux-2.6.11-agp/drivers/char/agp/intel-agp.c 2005-03-22 11:14:56
+00:00
+@@ -285,7 +285,7 @@
+ if (new == NULL)
+ return NULL;
+
+- new->memory[0] = virt_to_phys(addr);
++ new->memory[0] = virt_to_gart(addr);
+ if (pg_count == 4) {
+ /* kludge to get 4 physical pages for ARGB cursor */
+ new->memory[1] = new->memory[0] + PAGE_SIZE;
+@@ -328,10 +328,10 @@
+ agp_free_key(curr->key);
+ if(curr->type == AGP_PHYS_MEMORY) {
+ if (curr->page_count == 4)
+- i8xx_destroy_pages(phys_to_virt(curr->memory[0]));
++ i8xx_destroy_pages(gart_to_virt(curr->memory[0]));
+ else
+ agp_bridge->driver->agp_destroy_page(
+- phys_to_virt(curr->memory[0]));
++ gart_to_virt(curr->memory[0]));
+ vfree(curr->memory);
+ }
+ kfree(curr);
+--- linux-2.6.11/drivers/char/agp/intel-mch-agp.c 2005-03-02 07:37:48
+00:00
++++ linux-2.6.11-agp/drivers/char/agp/intel-mch-agp.c 2005-03-22 11:14:56
+00:00
+@@ -51,7 +51,7 @@
+ if (new == NULL)
+ return NULL;
+
+- new->memory[0] = virt_to_phys(addr);
++ new->memory[0] = virt_to_gart(addr);
+ new->page_count = 1;
+ new->num_scratch_pages = 1;
+ new->type = AGP_PHYS_MEMORY;
+@@ -63,7 +63,7 @@
+ {
+ agp_free_key(curr->key);
+ if(curr->type == AGP_PHYS_MEMORY) {
+-
agp_bridge->driver->agp_destroy_page(phys_to_virt(curr->memory[0]));
++
agp_bridge->driver->agp_destroy_page(gart_to_virt(curr->memory[0]));
+ vfree(curr->memory);
+ }
+ kfree(curr);
+--- linux-2.6.11/drivers/char/agp/sworks-agp.c 2005-03-02 07:38:37 +00:00
++++ linux-2.6.11-agp/drivers/char/agp/sworks-agp.c 2005-03-22 11:14:56
+00:00
+@@ -51,7 +51,7 @@
+ }
+ SetPageReserved(virt_to_page(page_map->real));
+ global_cache_flush();
+- page_map->remapped = ioremap_nocache(virt_to_phys(page_map->real),
++ page_map->remapped = ioremap_nocache(virt_to_gart(page_map->real),
+ PAGE_SIZE);
+ if (page_map->remapped == NULL) {
+ ClearPageReserved(virt_to_page(page_map->real));
+@@ -162,7 +162,7 @@
+ /* Create a fake scratch directory */
+ for(i = 0; i < 1024; i++) {
+ writel(agp_bridge->scratch_page,
serverworks_private.scratch_dir.remapped+i);
+- writel(virt_to_phys(serverworks_private.scratch_dir.real) | 1,
page_dir.remapped+i);
++ writel(virt_to_gart(serverworks_private.scratch_dir.real) | 1,
page_dir.remapped+i);
+ }
+
+ retval = serverworks_create_gatt_pages(value->num_entries / 1024);
+@@ -174,7 +174,7 @@
+
+ agp_bridge->gatt_table_real = (u32 *)page_dir.real;
+ agp_bridge->gatt_table = (u32 __iomem *)page_dir.remapped;
+- agp_bridge->gatt_bus_addr = virt_to_phys(page_dir.real);
++ agp_bridge->gatt_bus_addr = virt_to_gart(page_dir.real);
+
+ /* Get the address for the gart region.
+ * This is a bus address even on the alpha, b/c its
+@@ -187,7 +187,7 @@
+ /* Calculate the agp offset */
+
+ for(i = 0; i < value->num_entries / 1024; i++)
+- writel(virt_to_phys(serverworks_private.gatt_pages[i]->real)|1,
page_dir.remapped+i);
++ writel(virt_to_gart(serverworks_private.gatt_pages[i]->real)|1,
page_dir.remapped+i);
+
+ return 0;
+ }
+--- linux-2.6.11/drivers/char/agp/uninorth-agp.c 2005-03-02 07:38:09
+00:00
++++ linux-2.6.11-agp/drivers/char/agp/uninorth-agp.c 2005-03-22 11:14:56
+00:00
+@@ -200,7 +200,7 @@
+
+ agp_bridge->gatt_table_real = (u32 *) table;
+ agp_bridge->gatt_table = (u32 *)table;
+- agp_bridge->gatt_bus_addr = virt_to_phys(table);
++ agp_bridge->gatt_bus_addr = virt_to_gart(table);
+
+ for (i = 0; i < num_entries; i++) {
+ agp_bridge->gatt_table[i] =
+--- linux-2.6.11/include/asm-alpha/agp.h 2005-03-02 07:37:39 +00:00
++++ linux-2.6.11-agp/include/asm-alpha/agp.h 2005-03-22 11:18:34 +00:00
+@@ -10,4 +10,14 @@
+ #define flush_agp_mappings()
+ #define flush_agp_cache() mb()
+
++/* Convert a physical address to an address suitable for the GART. */
++#define phys_to_gart(x) (x)
++#define gart_to_phys(x) (x)
++
++/* GATT allocation. Returns/accepts GATT kernel virtual address. */
++#define alloc_gatt_pages(order) \
++ ((char *)__get_free_pages(GFP_KERNEL, (order)))
++#define free_gatt_pages(table, order) \
++ free_pages((unsigned long)(table), (order))
++
+ #endif
+--- linux-2.6.11/include/asm-i386/agp.h 2005-03-02 07:37:31 +00:00
++++ linux-2.6.11-agp/include/asm-i386/agp.h 2005-03-22 11:18:39 +00:00
+@@ -21,4 +21,14 @@
+ worth it. Would need a page for it. */
+ #define flush_agp_cache() asm volatile("wbinvd":::"memory")
+
++/* Convert a physical address to an address suitable for the GART. */
++#define phys_to_gart(x) (x)
++#define gart_to_phys(x) (x)
++
++/* GATT allocation. Returns/accepts GATT kernel virtual address. */
++#define alloc_gatt_pages(order) \
++ ((char *)__get_free_pages(GFP_KERNEL, (order)))
++#define free_gatt_pages(table, order) \
++ free_pages((unsigned long)(table), (order))
++
+ #endif
+--- linux-2.6.11/include/asm-ia64/agp.h 2005-03-02 07:38:09 +00:00
++++ linux-2.6.11-agp/include/asm-ia64/agp.h 2005-03-22 11:18:45 +00:00
+@@ -18,4 +18,14 @@
+ #define flush_agp_mappings() /* nothing */
+ #define flush_agp_cache() mb()
+
++/* Convert a physical address to an address suitable for the GART. */
++#define phys_to_gart(x) (x)
++#define gart_to_phys(x) (x)
++
++/* GATT allocation. Returns/accepts GATT kernel virtual address. */
++#define alloc_gatt_pages(order) \
++ ((char *)__get_free_pages(GFP_KERNEL, (order)))
++#define free_gatt_pages(table, order) \
++ free_pages((unsigned long)(table), (order))
++
+ #endif /* _ASM_IA64_AGP_H */
+--- linux-2.6.11/include/asm-ppc/agp.h 2005-03-02 07:38:08 +00:00
++++ linux-2.6.11-agp/include/asm-ppc/agp.h 2005-03-22 11:18:52 +00:00
+@@ -10,4 +10,14 @@
+ #define flush_agp_mappings()
+ #define flush_agp_cache() mb()
+
++/* Convert a physical address to an address suitable for the GART. */
++#define phys_to_gart(x) (x)
++#define gart_to_phys(x) (x)
++
++/* GATT allocation. Returns/accepts GATT kernel virtual address. */
++#define alloc_gatt_pages(order) \
++ ((char *)__get_free_pages(GFP_KERNEL, (order)))
++#define free_gatt_pages(table, order) \
++ free_pages((unsigned long)(table), (order))
++
+ #endif
+--- linux-2.6.11/include/asm-sparc64/agp.h 2005-03-02 07:37:48 +00:00
++++ linux-2.6.11-agp/include/asm-sparc64/agp.h 2005-03-22 11:18:59 +00:00
+@@ -8,4 +8,14 @@
+ #define flush_agp_mappings()
+ #define flush_agp_cache() mb()
+
++/* Convert a physical address to an address suitable for the GART. */
++#define phys_to_gart(x) (x)
++#define gart_to_phys(x) (x)
++
++/* GATT allocation. Returns/accepts GATT kernel virtual address. */
++#define alloc_gatt_pages(order) \
++ ((char *)__get_free_pages(GFP_KERNEL, (order)))
++#define free_gatt_pages(table, order) \
++ free_pages((unsigned long)(table), (order))
++
+ #endif
+--- linux-2.6.11/include/asm-x86_64/agp.h 2005-03-02 07:37:30 +00:00
++++ linux-2.6.11-agp/include/asm-x86_64/agp.h 2005-03-22 11:18:22 +00:00
+@@ -19,4 +19,14 @@
+ worth it. Would need a page for it. */
+ #define flush_agp_cache() asm volatile("wbinvd":::"memory")
+
++/* Convert a physical address to an address suitable for the GART. */
++#define phys_to_gart(x) (x)
++#define gart_to_phys(x) (x)
++
++/* GATT allocation. Returns/accepts GATT kernel virtual address. */
++#define alloc_gatt_pages(order) \
++ ((char *)__get_free_pages(GFP_KERNEL, (order)))
++#define free_gatt_pages(table, order) \
++ free_pages((unsigned long)(table), (order))
++
+ #endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/kernel/skbuff.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/kernel/skbuff.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,47 @@
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/version.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/init.h>
+#include <asm/io.h>
+#include <asm/page.h>
+
+EXPORT_SYMBOL(__dev_alloc_skb);
+
+/* Referenced in netback.c. */
+/*static*/ kmem_cache_t *skbuff_cachep;
+
+/* Size must be cacheline-aligned (alloc_skb uses SKB_DATA_ALIGN). */
+#define XEN_SKB_SIZE \
+ ((PAGE_SIZE - sizeof(struct skb_shared_info)) & ~(SMP_CACHE_BYTES - 1))
+
+struct sk_buff *__dev_alloc_skb(unsigned int length, int gfp_mask)
+{
+ struct sk_buff *skb;
+ skb = alloc_skb_from_cache(skbuff_cachep, length + 16, gfp_mask);
+ if ( likely(skb != NULL) )
+ skb_reserve(skb, 16);
+ return skb;
+}
+
+static void skbuff_ctor(void *buf, kmem_cache_t *cachep, unsigned long unused)
+{
+ scrub_pages(buf, 1);
+}
+
+static int __init skbuff_init(void)
+{
+ skbuff_cachep = kmem_cache_create(
+ "xen-skb", PAGE_SIZE, PAGE_SIZE, 0, skbuff_ctor, NULL);
+ return 0;
+}
+__initcall(skbuff_init);
diff -r 35b74976f598 -r a83ac0806d6b linux-2.6.11-xen-sparse/include/linux/mm.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/linux/mm.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,865 @@
+#ifndef _LINUX_MM_H
+#define _LINUX_MM_H
+
+#include <linux/sched.h>
+#include <linux/errno.h>
+
+#ifdef __KERNEL__
+
+#include <linux/config.h>
+#include <linux/gfp.h>
+#include <linux/list.h>
+#include <linux/mmzone.h>
+#include <linux/rbtree.h>
+#include <linux/prio_tree.h>
+#include <linux/fs.h>
+
+struct mempolicy;
+struct anon_vma;
+
+#ifndef CONFIG_DISCONTIGMEM /* Don't use mapnrs, do it properly */
+extern unsigned long max_mapnr;
+#endif
+
+extern unsigned long num_physpages;
+extern void * high_memory;
+extern unsigned long vmalloc_earlyreserve;
+extern int page_cluster;
+
+#ifdef CONFIG_SYSCTL
+extern int sysctl_legacy_va_layout;
+#else
+#define sysctl_legacy_va_layout 0
+#endif
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/processor.h>
+#include <asm/atomic.h>
+
+#ifndef MM_VM_SIZE
+#define MM_VM_SIZE(mm) ((TASK_SIZE + PGDIR_SIZE - 1) & PGDIR_MASK)
+#endif
+
+#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
+
+/*
+ * Linux kernel virtual memory manager primitives.
+ * The idea being to have a "virtual" mm in the same way
+ * we have a virtual fs - giving a cleaner interface to the
+ * mm details, and allowing different kinds of memory mappings
+ * (from shared memory to executable loading to arbitrary
+ * mmap() functions).
+ */
+
+/*
+ * This struct defines a memory VMM memory area. There is one of these
+ * per VM-area/task. A VM area is any part of the process virtual memory
+ * space that has a special rule for the page-fault handlers (ie a shared
+ * library, the executable area etc).
+ */
+struct vm_area_struct {
+ struct mm_struct * vm_mm; /* The address space we belong to. */
+ unsigned long vm_start; /* Our start address within vm_mm. */
+ unsigned long vm_end; /* The first byte after our end address
+ within vm_mm. */
+
+ /* linked list of VM areas per task, sorted by address */
+ struct vm_area_struct *vm_next;
+
+ pgprot_t vm_page_prot; /* Access permissions of this VMA. */
+ unsigned long vm_flags; /* Flags, listed below. */
+
+ struct rb_node vm_rb;
+
+ /*
+ * For areas with an address space and backing store,
+ * linkage into the address_space->i_mmap prio tree, or
+ * linkage to the list of like vmas hanging off its node, or
+ * linkage of vma in the address_space->i_mmap_nonlinear list.
+ */
+ union {
+ struct {
+ struct list_head list;
+ void *parent; /* aligns with prio_tree_node parent */
+ struct vm_area_struct *head;
+ } vm_set;
+
+ struct raw_prio_tree_node prio_tree_node;
+ } shared;
+
+ /*
+ * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
+ * list, after a COW of one of the file pages. A MAP_SHARED vma
+ * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack
+ * or brk vma (with NULL file) can only be in an anon_vma list.
+ */
+ struct list_head anon_vma_node; /* Serialized by anon_vma->lock */
+ struct anon_vma *anon_vma; /* Serialized by page_table_lock */
+
+ /* Function pointers to deal with this struct. */
+ struct vm_operations_struct * vm_ops;
+
+ /* Information about our backing store: */
+ unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE
+ units, *not* PAGE_CACHE_SIZE */
+ struct file * vm_file; /* File we map to (can be NULL). */
+ void * vm_private_data; /* was vm_pte (shared mem) */
+ unsigned long vm_truncate_count;/* truncate_count or restart_addr */
+
+#ifndef CONFIG_MMU
+ atomic_t vm_usage; /* refcount (VMAs shared if !MMU) */
+#endif
+#ifdef CONFIG_NUMA
+ struct mempolicy *vm_policy; /* NUMA policy for the VMA */
+#endif
+};
+
+/*
+ * This struct defines the per-mm list of VMAs for uClinux. If CONFIG_MMU is
+ * disabled, then there's a single shared list of VMAs maintained by the
+ * system, and mm's subscribe to these individually
+ */
+struct vm_list_struct {
+ struct vm_list_struct *next;
+ struct vm_area_struct *vma;
+};
+
+#ifndef CONFIG_MMU
+extern struct rb_root nommu_vma_tree;
+extern struct rw_semaphore nommu_vma_sem;
+
+extern unsigned int kobjsize(const void *objp);
+#endif
+
+/*
+ * vm_flags..
+ */
+#define VM_READ 0x00000001 /* currently active flags */
+#define VM_WRITE 0x00000002
+#define VM_EXEC 0x00000004
+#define VM_SHARED 0x00000008
+
+#define VM_MAYREAD 0x00000010 /* limits for mprotect() etc */
+#define VM_MAYWRITE 0x00000020
+#define VM_MAYEXEC 0x00000040
+#define VM_MAYSHARE 0x00000080
+
+#define VM_GROWSDOWN 0x00000100 /* general info on the segment */
+#define VM_GROWSUP 0x00000200
+#define VM_SHM 0x00000400 /* shared memory area, don't swap out */
+#define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */
+
+#define VM_EXECUTABLE 0x00001000
+#define VM_LOCKED 0x00002000
+#define VM_IO 0x00004000 /* Memory mapped I/O or similar */
+
+ /* Used by sys_madvise() */
+#define VM_SEQ_READ 0x00008000 /* App will access data sequentially */
+#define VM_RAND_READ 0x00010000 /* App will not benefit from clustered
reads */
+
+#define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */
+#define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */
+#define VM_RESERVED 0x00080000 /* Don't unmap it from swap_out */
+#define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */
+#define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */
+#define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */
+#define VM_FOREIGN 0x01000000 /* Has pages belonging to another VM */
+
+#ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */
+#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
+#endif
+
+#ifdef CONFIG_STACK_GROWSUP
+#define VM_STACK_FLAGS (VM_GROWSUP | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
+#else
+#define VM_STACK_FLAGS (VM_GROWSDOWN | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
+#endif
+
+#define VM_READHINTMASK (VM_SEQ_READ | VM_RAND_READ)
+#define VM_ClearReadHint(v) (v)->vm_flags &= ~VM_READHINTMASK
+#define VM_NormalReadHint(v) (!((v)->vm_flags & VM_READHINTMASK))
+#define VM_SequentialReadHint(v) ((v)->vm_flags & VM_SEQ_READ)
+#define VM_RandomReadHint(v) ((v)->vm_flags & VM_RAND_READ)
+
+/*
+ * mapping from the currently active vm_flags protection bits (the
+ * low four bits) to a page protection mask..
+ */
+extern pgprot_t protection_map[16];
+
+
+/*
+ * These are the virtual MM functions - opening of an area, closing and
+ * unmapping it (needed to keep files on disk up-to-date etc), pointer
+ * to the functions called when a no-page or a wp-page exception occurs.
+ */
+struct vm_operations_struct {
+ void (*open)(struct vm_area_struct * area);
+ void (*close)(struct vm_area_struct * area);
+ struct page * (*nopage)(struct vm_area_struct * area, unsigned long
address, int *type);
+ int (*populate)(struct vm_area_struct * area, unsigned long address,
unsigned long len, pgprot_t prot, unsigned long pgoff, int nonblock);
+#ifdef CONFIG_NUMA
+ int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new);
+ struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
+ unsigned long addr);
+#endif
+};
+
+struct mmu_gather;
+struct inode;
+
+#ifdef ARCH_HAS_ATOMIC_UNSIGNED
+typedef unsigned page_flags_t;
+#else
+typedef unsigned long page_flags_t;
+#endif
+
+/*
+ * Each physical page in the system has a struct page associated with
+ * it to keep track of whatever it is we are using the page for at the
+ * moment. Note that we have no way to track which tasks are using
+ * a page.
+ */
+struct page {
+ page_flags_t flags; /* Atomic flags, some possibly
+ * updated asynchronously */
+ atomic_t _count; /* Usage count, see below. */
+ atomic_t _mapcount; /* Count of ptes mapped in mms,
+ * to show when page is mapped
+ * & limit reverse map searches.
+ */
+ unsigned long private; /* Mapping-private opaque data:
+ * usually used for buffer_heads
+ * if PagePrivate set; used for
+ * swp_entry_t if PageSwapCache
+ * When page is free, this indicates
+ * order in the buddy system.
+ */
+ struct address_space *mapping; /* If low bit clear, points to
+ * inode address_space, or NULL.
+ * If page mapped as anonymous
+ * memory, low bit is set, and
+ * it points to anon_vma object:
+ * see PAGE_MAPPING_ANON below.
+ */
+ pgoff_t index; /* Our offset within mapping. */
+ struct list_head lru; /* Pageout list, eg. active_list
+ * protected by zone->lru_lock !
+ */
+ /*
+ * On machines where all RAM is mapped into kernel address space,
+ * we can simply calculate the virtual address. On machines with
+ * highmem some memory is mapped into kernel virtual memory
+ * dynamically, so we need a place to store that address.
+ * Note that this field could be 16 bits on x86 ... ;)
+ *
+ * Architectures with slow multiplication can define
+ * WANT_PAGE_VIRTUAL in asm/page.h
+ */
+#if defined(WANT_PAGE_VIRTUAL)
+ void *virtual; /* Kernel virtual address (NULL if
+ not kmapped, ie. highmem) */
+#endif /* WANT_PAGE_VIRTUAL */
+};
+
+/*
+ * FIXME: take this include out, include page-flags.h in
+ * files which need it (119 of them)
+ */
+#include <linux/page-flags.h>
+
+/*
+ * Methods to modify the page usage count.
+ *
+ * What counts for a page usage:
+ * - cache mapping (page->mapping)
+ * - private data (page->private)
+ * - page mapped in a task's page tables, each mapping
+ * is counted separately
+ *
+ * Also, many kernel routines increase the page count before a critical
+ * routine so they can be sure the page doesn't go away from under them.
+ *
+ * Since 2.6.6 (approx), a free page has ->_count = -1. This is so that we
+ * can use atomic_add_negative(-1, page->_count) to detect when the page
+ * becomes free and so that we can also use atomic_inc_and_test to atomically
+ * detect when we just tried to grab a ref on a page which some other CPU has
+ * already deemed to be freeable.
+ *
+ * NO code should make assumptions about this internal detail! Use the
provided
+ * macros which retain the old rules: page_count(page) == 0 is a free page.
+ */
+
+/*
+ * Drop a ref, return true if the logical refcount fell to zero (the page has
+ * no users)
+ */
+#define put_page_testzero(p) \
+ ({ \
+ BUG_ON(page_count(p) == 0); \
+ atomic_add_negative(-1, &(p)->_count); \
+ })
+
+/*
+ * Grab a ref, return true if the page previously had a logical refcount of
+ * zero. ie: returns true if we just grabbed an already-deemed-to-be-free page
+ */
+#define get_page_testone(p) atomic_inc_and_test(&(p)->_count)
+
+#define set_page_count(p,v) atomic_set(&(p)->_count, v - 1)
+#define __put_page(p) atomic_dec(&(p)->_count)
+
+extern void FASTCALL(__page_cache_release(struct page *));
+
+#ifdef CONFIG_HUGETLB_PAGE
+
+static inline int page_count(struct page *p)
+{
+ if (PageCompound(p))
+ p = (struct page *)p->private;
+ return atomic_read(&(p)->_count) + 1;
+}
+
+static inline void get_page(struct page *page)
+{
+ if (unlikely(PageCompound(page)))
+ page = (struct page *)page->private;
+ atomic_inc(&page->_count);
+}
+
+void put_page(struct page *page);
+
+#else /* CONFIG_HUGETLB_PAGE */
+
+#define page_count(p) (atomic_read(&(p)->_count) + 1)
+
+static inline void get_page(struct page *page)
+{
+ atomic_inc(&page->_count);
+}
+
+static inline void put_page(struct page *page)
+{
+ if (!PageReserved(page) && put_page_testzero(page))
+ __page_cache_release(page);
+}
+
+#endif /* CONFIG_HUGETLB_PAGE */
+
+/*
+ * Multiple processes may "see" the same page. E.g. for untouched
+ * mappings of /dev/null, all processes see the same page full of
+ * zeroes, and text pages of executables and shared libraries have
+ * only one copy in memory, at most, normally.
+ *
+ * For the non-reserved pages, page_count(page) denotes a reference count.
+ * page_count() == 0 means the page is free.
+ * page_count() == 1 means the page is used for exactly one purpose
+ * (e.g. a private data page of one process).
+ *
+ * A page may be used for kmalloc() or anyone else who does a
+ * __get_free_page(). In this case the page_count() is at least 1, and
+ * all other fields are unused but should be 0 or NULL. The
+ * management of this page is the responsibility of the one who uses
+ * it.
+ *
+ * The other pages (we may call them "process pages") are completely
+ * managed by the Linux memory manager: I/O, buffers, swapping etc.
+ * The following discussion applies only to them.
+ *
+ * A page may belong to an inode's memory mapping. In this case,
+ * page->mapping is the pointer to the inode, and page->index is the
+ * file offset of the page, in units of PAGE_CACHE_SIZE.
+ *
+ * A page contains an opaque `private' member, which belongs to the
+ * page's address_space. Usually, this is the address of a circular
+ * list of the page's disk buffers.
+ *
+ * For pages belonging to inodes, the page_count() is the number of
+ * attaches, plus 1 if `private' contains something, plus one for
+ * the page cache itself.
+ *
+ * All pages belonging to an inode are in these doubly linked lists:
+ * mapping->clean_pages, mapping->dirty_pages and mapping->locked_pages;
+ * using the page->list list_head. These fields are also used for
+ * freelist managemet (when page_count()==0).
+ *
+ * There is also a per-mapping radix tree mapping index to the page
+ * in memory if present. The tree is rooted at mapping->root.
+ *
+ * All process pages can do I/O:
+ * - inode pages may need to be read from disk,
+ * - inode pages which have been modified and are MAP_SHARED may need
+ * to be written to disk,
+ * - private pages which have been modified may need to be swapped out
+ * to swap space and (later) to be read back into memory.
+ */
+
+/*
+ * The zone field is never updated after free_area_init_core()
+ * sets it, so none of the operations on it need to be atomic.
+ * We'll have up to (MAX_NUMNODES * MAX_NR_ZONES) zones total,
+ * so we use (MAX_NODES_SHIFT + MAX_ZONES_SHIFT) here to get enough bits.
+ */
+#define NODEZONE_SHIFT (sizeof(page_flags_t)*8 - MAX_NODES_SHIFT -
MAX_ZONES_SHIFT)
+#define NODEZONE(node, zone) ((node << ZONES_SHIFT) | zone)
+
+static inline unsigned long page_zonenum(struct page *page)
+{
+ return (page->flags >> NODEZONE_SHIFT) & (~(~0UL << ZONES_SHIFT));
+}
+static inline unsigned long page_to_nid(struct page *page)
+{
+ return (page->flags >> (NODEZONE_SHIFT + ZONES_SHIFT));
+}
+
+struct zone;
+extern struct zone *zone_table[];
+
+static inline struct zone *page_zone(struct page *page)
+{
+ return zone_table[page->flags >> NODEZONE_SHIFT];
+}
+
+static inline void set_page_zone(struct page *page, unsigned long nodezone_num)
+{
+ page->flags &= ~(~0UL << NODEZONE_SHIFT);
+ page->flags |= nodezone_num << NODEZONE_SHIFT;
+}
+
+#ifndef CONFIG_DISCONTIGMEM
+/* The array of struct pages - for discontigmem use pgdat->lmem_map */
+extern struct page *mem_map;
+#endif
+
+static inline void *lowmem_page_address(struct page *page)
+{
+ return __va(page_to_pfn(page) << PAGE_SHIFT);
+}
+
+#if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL)
+#define HASHED_PAGE_VIRTUAL
+#endif
+
+#if defined(WANT_PAGE_VIRTUAL)
+#define page_address(page) ((page)->virtual)
+#define set_page_address(page, address) \
+ do { \
+ (page)->virtual = (address); \
+ } while(0)
+#define page_address_init() do { } while(0)
+#endif
+
+#if defined(HASHED_PAGE_VIRTUAL)
+void *page_address(struct page *page);
+void set_page_address(struct page *page, void *virtual);
+void page_address_init(void);
+#endif
+
+#if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL)
+#define page_address(page) lowmem_page_address(page)
+#define set_page_address(page, address) do { } while(0)
+#define page_address_init() do { } while(0)
+#endif
+
+/*
+ * On an anonymous page mapped into a user virtual memory area,
+ * page->mapping points to its anon_vma, not to a struct address_space;
+ * with the PAGE_MAPPING_ANON bit set to distinguish it.
+ *
+ * Please note that, confusingly, "page_mapping" refers to the inode
+ * address_space which maps the page from disk; whereas "page_mapped"
+ * refers to user virtual address space into which the page is mapped.
+ */
+#define PAGE_MAPPING_ANON 1
+
+extern struct address_space swapper_space;
+static inline struct address_space *page_mapping(struct page *page)
+{
+ struct address_space *mapping = page->mapping;
+
+ if (unlikely(PageSwapCache(page)))
+ mapping = &swapper_space;
+ else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
+ mapping = NULL;
+ return mapping;
+}
+
+static inline int PageAnon(struct page *page)
+{
+ return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
+}
+
+/*
+ * Return the pagecache index of the passed page. Regular pagecache pages
+ * use ->index whereas swapcache pages use ->private
+ */
+static inline pgoff_t page_index(struct page *page)
+{
+ if (unlikely(PageSwapCache(page)))
+ return page->private;
+ return page->index;
+}
+
+/*
+ * The atomic page->_mapcount, like _count, starts from -1:
+ * so that transitions both from it and to it can be tracked,
+ * using atomic_inc_and_test and atomic_add_negative(-1).
+ */
+static inline void reset_page_mapcount(struct page *page)
+{
+ atomic_set(&(page)->_mapcount, -1);
+}
+
+static inline int page_mapcount(struct page *page)
+{
+ return atomic_read(&(page)->_mapcount) + 1;
+}
+
+/*
+ * Return true if this page is mapped into pagetables.
+ */
+static inline int page_mapped(struct page *page)
+{
+ return atomic_read(&(page)->_mapcount) >= 0;
+}
+
+/*
+ * Error return values for the *_nopage functions
+ */
+#define NOPAGE_SIGBUS (NULL)
+#define NOPAGE_OOM ((struct page *) (-1))
+
+/*
+ * Different kinds of faults, as returned by handle_mm_fault().
+ * Used to decide whether a process gets delivered SIGBUS or
+ * just gets major/minor fault counters bumped up.
+ */
+#define VM_FAULT_OOM (-1)
+#define VM_FAULT_SIGBUS 0
+#define VM_FAULT_MINOR 1
+#define VM_FAULT_MAJOR 2
+
+#define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK)
+
+extern void show_free_areas(void);
+
+#ifdef CONFIG_SHMEM
+struct page *shmem_nopage(struct vm_area_struct *vma,
+ unsigned long address, int *type);
+int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new);
+struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
+ unsigned long addr);
+int shmem_lock(struct file *file, int lock, struct user_struct *user);
+#else
+#define shmem_nopage filemap_nopage
+#define shmem_lock(a, b, c) ({0;}) /* always in memory, no need to lock */
+#define shmem_set_policy(a, b) (0)
+#define shmem_get_policy(a, b) (NULL)
+#endif
+struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags);
+
+int shmem_zero_setup(struct vm_area_struct *);
+
+static inline int can_do_mlock(void)
+{
+ if (capable(CAP_IPC_LOCK))
+ return 1;
+ if (current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur != 0)
+ return 1;
+ return 0;
+}
+extern int user_shm_lock(size_t, struct user_struct *);
+extern void user_shm_unlock(size_t, struct user_struct *);
+
+/*
+ * Parameter block passed down to zap_pte_range in exceptional cases.
+ */
+struct zap_details {
+ struct vm_area_struct *nonlinear_vma; /* Check page->index if set */
+ struct address_space *check_mapping; /* Check page->mapping if set */
+ pgoff_t first_index; /* Lowest page->index to unmap
*/
+ pgoff_t last_index; /* Highest page->index to unmap
*/
+ spinlock_t *i_mmap_lock; /* For unmap_mapping_range: */
+ unsigned long break_addr; /* Where unmap_vmas stopped */
+ unsigned long truncate_count; /* Compare vm_truncate_count */
+};
+
+void zap_page_range(struct vm_area_struct *vma, unsigned long address,
+ unsigned long size, struct zap_details *);
+int unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm,
+ struct vm_area_struct *start_vma, unsigned long start_addr,
+ unsigned long end_addr, unsigned long *nr_accounted,
+ struct zap_details *);
+void clear_page_range(struct mmu_gather *tlb, unsigned long addr, unsigned
long end);
+int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
+ struct vm_area_struct *vma);
+int zeromap_page_range(struct vm_area_struct *vma, unsigned long from,
+ unsigned long size, pgprot_t prot);
+void unmap_mapping_range(struct address_space *mapping,
+ loff_t const holebegin, loff_t const holelen, int even_cows);
+
+static inline void unmap_shared_mapping_range(struct address_space *mapping,
+ loff_t const holebegin, loff_t const holelen)
+{
+ unmap_mapping_range(mapping, holebegin, holelen, 0);
+}
+
+extern int vmtruncate(struct inode * inode, loff_t offset);
+extern pud_t *FASTCALL(__pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned
long address));
+extern pmd_t *FASTCALL(__pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned
long address));
+extern pte_t *FASTCALL(pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd,
unsigned long address));
+extern pte_t *FASTCALL(pte_alloc_map(struct mm_struct *mm, pmd_t *pmd,
unsigned long address));
+extern int install_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, struct page *page, pgprot_t prot);
+extern int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, unsigned long pgoff, pgprot_t prot);
+extern int handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma,
unsigned long address, int write_access);
+extern int make_pages_present(unsigned long addr, unsigned long end);
+extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void
*buf, int len, int write);
+void install_arg_page(struct vm_area_struct *, struct page *, unsigned long);
+
+int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned
long start,
+ int len, int write, int force, struct page **pages, struct
vm_area_struct **vmas);
+
+int __set_page_dirty_buffers(struct page *page);
+int __set_page_dirty_nobuffers(struct page *page);
+int redirty_page_for_writepage(struct writeback_control *wbc,
+ struct page *page);
+int FASTCALL(set_page_dirty(struct page *page));
+int set_page_dirty_lock(struct page *page);
+int clear_page_dirty_for_io(struct page *page);
+
+extern unsigned long do_mremap(unsigned long addr,
+ unsigned long old_len, unsigned long new_len,
+ unsigned long flags, unsigned long new_addr);
+
+/*
+ * Prototype to add a shrinker callback for ageable caches.
+ *
+ * These functions are passed a count `nr_to_scan' and a gfpmask. They should
+ * scan `nr_to_scan' objects, attempting to free them.
+ *
+ * The callback must the number of objects which remain in the cache.
+ *
+ * The callback will be passes nr_to_scan == 0 when the VM is querying the
+ * cache size, so a fastpath for that case is appropriate.
+ */
+typedef int (*shrinker_t)(int nr_to_scan, unsigned int gfp_mask);
+
+/*
+ * Add an aging callback. The int is the number of 'seeks' it takes
+ * to recreate one of the objects that these functions age.
+ */
+
+#define DEFAULT_SEEKS 2
+struct shrinker;
+extern struct shrinker *set_shrinker(int, shrinker_t);
+extern void remove_shrinker(struct shrinker *shrinker);
+
+/*
+ * On a two-level or three-level page table, this ends up being trivial. Thus
+ * the inlining and the symmetry break with pte_alloc_map() that does all
+ * of this out-of-line.
+ */
+/*
+ * The following ifdef needed to get the 4level-fixup.h header to work.
+ * Remove it when 4level-fixup.h has been removed.
+ */
+#ifdef CONFIG_MMU
+#ifndef __ARCH_HAS_4LEVEL_HACK
+static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long
address)
+{
+ if (pgd_none(*pgd))
+ return __pud_alloc(mm, pgd, address);
+ return pud_offset(pgd, address);
+}
+
+static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long
address)
+{
+ if (pud_none(*pud))
+ return __pmd_alloc(mm, pud, address);
+ return pmd_offset(pud, address);
+}
+#endif
+#endif /* CONFIG_MMU */
+
+extern void free_area_init(unsigned long * zones_size);
+extern void free_area_init_node(int nid, pg_data_t *pgdat,
+ unsigned long * zones_size, unsigned long zone_start_pfn,
+ unsigned long *zholes_size);
+extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long);
+extern void mem_init(void);
+extern void show_mem(void);
+extern void si_meminfo(struct sysinfo * val);
+extern void si_meminfo_node(struct sysinfo *val, int nid);
+
+/* prio_tree.c */
+void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old);
+void vma_prio_tree_insert(struct vm_area_struct *, struct prio_tree_root *);
+void vma_prio_tree_remove(struct vm_area_struct *, struct prio_tree_root *);
+struct vm_area_struct *vma_prio_tree_next(struct vm_area_struct *vma,
+ struct prio_tree_iter *iter);
+
+#define vma_prio_tree_foreach(vma, iter, root, begin, end) \
+ for (prio_tree_iter_init(iter, root, begin, end), vma = NULL; \
+ (vma = vma_prio_tree_next(vma, iter)); )
+
+static inline void vma_nonlinear_insert(struct vm_area_struct *vma,
+ struct list_head *list)
+{
+ vma->shared.vm_set.parent = NULL;
+ list_add_tail(&vma->shared.vm_set.list, list);
+}
+
+/* mmap.c */
+extern int __vm_enough_memory(long pages, int cap_sys_admin);
+extern void vma_adjust(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert);
+extern struct vm_area_struct *vma_merge(struct mm_struct *,
+ struct vm_area_struct *prev, unsigned long addr, unsigned long end,
+ unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t,
+ struct mempolicy *);
+extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *);
+extern int split_vma(struct mm_struct *,
+ struct vm_area_struct *, unsigned long addr, int new_below);
+extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
+extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *,
+ struct rb_node **, struct rb_node *);
+extern struct vm_area_struct *copy_vma(struct vm_area_struct **,
+ unsigned long addr, unsigned long len, pgoff_t pgoff);
+extern void exit_mmap(struct mm_struct *);
+
+extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned
long, unsigned long, unsigned long);
+
+extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long prot,
+ unsigned long flag, unsigned long pgoff);
+
+static inline unsigned long do_mmap(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long prot,
+ unsigned long flag, unsigned long offset)
+{
+ unsigned long ret = -EINVAL;
+ if ((offset + PAGE_ALIGN(len)) < offset)
+ goto out;
+ if (!(offset & ~PAGE_MASK))
+ ret = do_mmap_pgoff(file, addr, len, prot, flag, offset >>
PAGE_SHIFT);
+out:
+ return ret;
+}
+
+extern int do_munmap(struct mm_struct *, unsigned long, size_t);
+
+extern unsigned long do_brk(unsigned long, unsigned long);
+
+/* filemap.c */
+extern unsigned long page_unuse(struct page *);
+extern void truncate_inode_pages(struct address_space *, loff_t);
+
+/* generic vm_area_ops exported for stackable file systems */
+extern struct page *filemap_nopage(struct vm_area_struct *, unsigned long, int
*);
+extern int filemap_populate(struct vm_area_struct *, unsigned long,
+ unsigned long, pgprot_t, unsigned long, int);
+
+/* mm/page-writeback.c */
+int write_one_page(struct page *page, int wait);
+
+/* readahead.c */
+#define VM_MAX_READAHEAD 128 /* kbytes */
+#define VM_MIN_READAHEAD 16 /* kbytes (includes current page) */
+#define VM_MAX_CACHE_HIT 256 /* max pages in a row in cache before
+ * turning readahead off */
+
+int do_page_cache_readahead(struct address_space *mapping, struct file *filp,
+ unsigned long offset, unsigned long nr_to_read);
+int force_page_cache_readahead(struct address_space *mapping, struct file
*filp,
+ unsigned long offset, unsigned long nr_to_read);
+unsigned long page_cache_readahead(struct address_space *mapping,
+ struct file_ra_state *ra,
+ struct file *filp,
+ unsigned long offset,
+ unsigned long size);
+void handle_ra_miss(struct address_space *mapping,
+ struct file_ra_state *ra, pgoff_t offset);
+unsigned long max_sane_readahead(unsigned long nr);
+
+/* Do stack extension */
+extern int expand_stack(struct vm_area_struct * vma, unsigned long address);
+
+/* Look up the first VMA which satisfies addr < vm_end, NULL if none. */
+extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long
addr);
+extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned
long addr,
+ struct vm_area_struct **pprev);
+
+/* Look up the first VMA which intersects the interval start_addr..end_addr-1,
+ NULL if none. Assume start_addr < end_addr. */
+static inline struct vm_area_struct * find_vma_intersection(struct mm_struct *
mm, unsigned long start_addr, unsigned long end_addr)
+{
+ struct vm_area_struct * vma = find_vma(mm,start_addr);
+
+ if (vma && end_addr <= vma->vm_start)
+ vma = NULL;
+ return vma;
+}
+
+static inline unsigned long vma_pages(struct vm_area_struct *vma)
+{
+ return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+}
+
+extern struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned
long addr);
+
+extern struct page * vmalloc_to_page(void *addr);
+extern unsigned long vmalloc_to_pfn(void *addr);
+extern struct page * follow_page(struct mm_struct *mm, unsigned long address,
+ int write);
+extern int check_user_page_readable(struct mm_struct *mm, unsigned long
address);
+int remap_pfn_range(struct vm_area_struct *, unsigned long,
+ unsigned long, unsigned long, pgprot_t);
+/* Allow arch override for mapping of device and I/O (non-RAM) pages. */
+#ifndef io_remap_pfn_range
+#define io_remap_pfn_range remap_pfn_range
+#endif
+
+#ifdef CONFIG_PROC_FS
+void __vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
+#else
+static inline void __vm_stat_account(struct mm_struct *mm,
+ unsigned long flags, struct file *file, long pages)
+{
+}
+#endif /* CONFIG_PROC_FS */
+
+static inline void vm_stat_account(struct vm_area_struct *vma)
+{
+ __vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file,
+ vma_pages(vma));
+}
+
+static inline void vm_stat_unaccount(struct vm_area_struct *vma)
+{
+ __vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file,
+ -vma_pages(vma));
+}
+
+/* update per process rss and vm hiwater data */
+extern void update_mem_hiwater(void);
+
+#ifndef CONFIG_DEBUG_PAGEALLOC
+static inline void
+kernel_map_pages(struct page *page, int numpages, int enable)
+{
+}
+#endif
+
+extern struct vm_area_struct *get_gate_vma(struct task_struct *tsk);
+#ifdef __HAVE_ARCH_GATE_AREA
+int in_gate_area_no_task(unsigned long addr);
+int in_gate_area(struct task_struct *task, unsigned long addr);
+#else
+int in_gate_area_no_task(unsigned long addr);
+#define in_gate_area(task, addr) ({(void)task; in_gate_area_no_task(addr);})
+#endif /* __HAVE_ARCH_GATE_AREA */
+
+#endif /* __KERNEL__ */
+#endif /* _LINUX_MM_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/xenbus/xenbus_probe.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/xenbus/xenbus_probe.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,858 @@
+/******************************************************************************
+ * Talks to Xen Store to figure out what devices we have.
+ * Currently experiment code, but when I grow up I'll be a bus driver!
+ *
+ * Copyright (C) 2005 Rusty Russell, IBM Corporation
+ * Copyright (C) 2005 Mike Wray, Hewlett-Packard
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+#include <asm-xen/hypervisor.h>
+#include <asm-xen/xenbus.h>
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/fcntl.h>
+#include <stdarg.h>
+#include "xenbus_comms.h"
+
+/* Directory inside a domain containing devices. */
+#define XENBUS_DEVICE_DIR "device"
+
+/* Directory inside a domain containing backends. */
+#define XENBUS_BACKEND_DIR "backend"
+
+/* Name of field containing device id. */
+#define XENBUS_DEVICE_ID "id"
+
+/* Name of field containing device type. */
+#define XENBUS_DEVICE_TYPE "type"
+
+//#define DEBUG
+
+#ifdef DEBUG
+#define dprintf(_fmt, _args...) \
+printk(KERN_INFO __stringify(KBUILD_MODNAME) " [DBG] %s" _fmt,
__FUNCTION__, ##_args)
+#else
+#define dprintf(_fmt, _args...) do { } while(0)
+#endif
+
+static int xs_init_done = 0;
+
+/* Return the path to dir with /name appended.
+ * If name is null or empty returns a copy of dir.
+ */
+char *xenbus_path(const char *dir, const char *name)
+{
+ char *ret;
+ int len;
+
+ len = strlen(dir) + 1;
+ if (name)
+ len += strlen(name) + 1;
+ ret = kmalloc(len, GFP_KERNEL);
+ if (ret == NULL)
+ return NULL;
+ strcpy(ret, dir);
+ if (name) {
+ strcat(ret, "/");
+ strcat(ret, name);
+ }
+ return ret;
+}
+
+#define streq(a, b) (strcmp((a), (b)) == 0)
+
+char *xenbus_read(const char *dir, const char *name, unsigned int *data_n)
+{
+ int err = 0;
+ char *data = NULL;
+ char *path = xenbus_path(dir, name);
+ int n = 0;
+
+ if (!path) {
+ err = -ENOMEM;
+ goto out;
+ }
+ data = xs_read(path, &n);
+ if (IS_ERR(data)) {
+ err = PTR_ERR(data);
+ if (err == -EISDIR)
+ err = -ENOENT;
+ } else if (n == 0) {
+ err = -ENOENT;
+ kfree(data);
+ }
+ kfree(path);
+ out:
+ if (data_n)
+ *data_n = n;
+ return (err ? ERR_PTR(err) : data);
+}
+
+int xenbus_write(const char *dir, const char *name, const char *data, int
data_n)
+{
+ int err = 0;
+ char *path = xenbus_path(dir, name);
+
+ if (!path)
+ return -ENOMEM;
+ err = xs_write(path, data, data_n, O_CREAT);
+ kfree(path);
+ return err;
+}
+
+int xenbus_read_string(const char *dir, const char *name, char **val)
+{
+ int err = 0;
+
+ *val = xenbus_read(dir, name, NULL);
+ if (IS_ERR(*val)) {
+ err = PTR_ERR(*val);
+ *val = NULL;
+ }
+ return err;
+}
+
+int xenbus_write_string(const char *dir, const char *name, const char *val)
+{
+ return xenbus_write(dir, name, val, strlen(val));
+}
+
+int xenbus_read_ulong(const char *dir, const char *name, unsigned long *val)
+{
+ int err = 0;
+ char *data = NULL, *end = NULL;
+ unsigned int data_n = 0;
+
+ data = xenbus_read(dir, name, &data_n);
+ if (IS_ERR(data)) {
+ err = PTR_ERR(data);
+ goto out;
+ }
+ if (data_n <= 1) {
+ err = -ENOENT;
+ goto free_data;
+ }
+ *val = simple_strtoul(data, &end, 10);
+ if (end != data + data_n) {
+ printk("XENBUS: Path %s/%s, bad parse of '%s' as ulong\n",
+ dir, name, data);
+ err = -EINVAL;
+ }
+ free_data:
+ kfree(data);
+ out:
+ if (err)
+ *val = 0;
+ return err;
+}
+
+int xenbus_write_ulong(const char *dir, const char *name, unsigned long val)
+{
+ char data[32] = {};
+
+ snprintf(data, sizeof(data), "%lu", val);
+ return xenbus_write(dir, name, data, strlen(data));
+}
+
+int xenbus_read_long(const char *dir, const char *name, long *val)
+{
+ int err = 0;
+ char *data = NULL, *end = NULL;
+ unsigned int data_n = 0;
+
+ data = xenbus_read(dir, name, &data_n);
+ if (IS_ERR(data)) {
+ err = PTR_ERR(data);
+ goto out;
+ }
+ if (data_n <= 1) {
+ err = -ENOENT;
+ goto free_data;
+ }
+ *val = simple_strtol(data, &end, 10);
+ if (end != data + data_n) {
+ printk("XENBUS: Path %s/%s, bad parse of '%s' as long\n",
+ dir, name, data);
+ err = -EINVAL;
+ }
+ free_data:
+ kfree(data);
+ out:
+ if (err)
+ *val = 0;
+ return err;
+}
+
+int xenbus_write_long(const char *dir, const char *name, long val)
+{
+ char data[32] = {};
+
+ snprintf(data, sizeof(data), "%li", val);
+ return xenbus_write(dir, name, data, strlen(data));
+}
+
+/* Number of characters in string form of a MAC address. */
+#define MAC_LENGTH 17
+
+/** Convert a mac address from a string of the form
+ * XX:XX:XX:XX:XX:XX to numerical form (an array of 6 unsigned chars).
+ * Each X denotes a hex digit: 0..9, a..f, A..F.
+ * Also supports using '-' as the separator instead of ':'.
+ */
+static int mac_aton(const char *macstr, unsigned int n, unsigned char mac[6])
+{
+ int err = -EINVAL;
+ int i, j;
+ const char *p;
+ char sep = 0;
+
+ if (!macstr || n != MAC_LENGTH)
+ goto exit;
+ for (i = 0, p = macstr; i < 6; i++) {
+ unsigned char d = 0;
+ if (i) {
+ if (!sep && (*p == ':' || *p == '-'))
+ sep = *p;
+ if (sep && *p == sep)
+ p++;
+ else
+ goto exit;
+ }
+ for (j = 0; j < 2; j++, p++) {
+ if (j)
+ d <<= 4;
+ if (isdigit(*p))
+ d += *p - '0';
+ else if (isxdigit(*p))
+ d += toupper(*p) - 'A' + 10;
+ else
+ goto exit;
+ }
+ mac[i] = d;
+ }
+ err = 0;
+ exit:
+ return err;
+}
+
+int xenbus_read_mac(const char *dir, const char *name, unsigned char mac[6])
+{
+ int err = 0;
+ char *data = 0;
+ unsigned int data_n = 0;
+
+ data = xenbus_read(dir, name, &data_n);
+ if (IS_ERR(data)) {
+ err = PTR_ERR(data);
+ goto out;
+ }
+ if (data_n <= 1) {
+ err = -ENOENT;
+ goto free_data;
+ }
+ err = mac_aton(data, data_n, mac);
+ if (err) {
+ printk("XENBUS: Path %s/%s, bad parse of '%s' as mac\n",
+ dir, name, data);
+ err = -EINVAL;
+ }
+ free_data:
+ kfree(data);
+ out:
+ if (err)
+ memset(mac, 0, sizeof(mac));
+ return err;
+}
+
+int xenbus_write_mac(const char *dir, const char *name, const unsigned char
mac[6])
+{
+ char buf[MAC_LENGTH] = {};
+ int buf_n = sizeof(buf);
+
+ snprintf(buf, buf_n, "%02x:%02x:%02x:%02x:%02x:%02x",
+ mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
+ return xenbus_write(dir, name, buf, buf_n);
+}
+
+/* Read event channel information from xenstore.
+ *
+ * Event channel xenstore fields:
+ * dom1 - backend domain id (int)
+ * port1 - backend port (int)
+ * dom2 - frontend domain id (int)
+ * port2 - frontend port (int)
+ */
+int xenbus_read_evtchn(const char *dir, const char *name, struct xenbus_evtchn
*evtchn)
+{
+ int err = 0;
+ char *evtchn_path = xenbus_path(dir, name);
+
+ if (!evtchn_path) {
+ err = -ENOMEM;
+ goto out;
+ }
+ err = xenbus_read_ulong(evtchn_path, "dom1", &evtchn->dom1);
+ if (err)
+ goto free_evtchn_path;
+ err = xenbus_read_ulong(evtchn_path, "port1", &evtchn->port1);
+ if (err)
+ goto free_evtchn_path;
+ err = xenbus_read_ulong(evtchn_path, "dom2", &evtchn->dom2);
+ if (err)
+ goto free_evtchn_path;
+ err = xenbus_read_ulong(evtchn_path, "port2", &evtchn->port2);
+
+ free_evtchn_path:
+ kfree(evtchn_path);
+ out:
+ if (err)
+ *evtchn = (struct xenbus_evtchn){};
+ return err;
+}
+
+/* Write a message to 'dir'.
+ * The data is 'val' followed by parameter names and values,
+ * terminated by NULL.
+ */
+int xenbus_message(const char *dir, const char *val, ...)
+{
+ static const char *mid_name = "@mid";
+ va_list args;
+ int err = 0;
+ char *mid_path = NULL;
+ char *msg_path = NULL;
+ char mid_str[32] = {};
+ long mid = 0;
+ int i;
+
+ va_start(args, val);
+ mid_path = xenbus_path(dir, mid_name);
+ if (!mid_path) {
+ err = -ENOMEM;
+ goto out;
+ }
+ err = xenbus_read_long(dir, mid_name, &mid);
+ if (err != -ENOENT)
+ goto out;
+ mid++;
+ err = xenbus_write_long(dir, mid_name, mid);
+ if (err)
+ goto out;
+ sprintf(mid_str, "%li", mid);
+ msg_path = xenbus_path(dir, mid_str);
+ if (!mid_path) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ for (i = 0; i < 16; i++) {
+ char *k, *v;
+ k = va_arg(args, char *);
+ if (!k)
+ break;
+ v = va_arg(args, char *);
+ if (!v)
+ break;
+ err = xenbus_write_string(msg_path, k, v);
+ if (err)
+ goto out;
+ }
+ err = xenbus_write_string(msg_path, NULL, val);
+
+ out:
+ kfree(msg_path);
+ kfree(mid_path);
+ va_end(args);
+ return err;
+}
+
+/* If something in array of ids matches this device, return it. */
+static const struct xenbus_device_id *
+match_device(const struct xenbus_device_id *arr, struct xenbus_device *dev)
+{
+ for (; !streq(arr->devicetype, ""); arr++) {
+ if (!streq(arr->devicetype, dev->devicetype))
+ continue;
+
+ if (streq(arr->subtype, "") ||
+ streq(arr->subtype, dev->subtype)) {
+ return arr;
+ }
+ }
+ return NULL;
+}
+
+static int xenbus_match(struct device *_dev, struct device_driver *_drv)
+{
+ struct xenbus_driver *drv = to_xenbus_driver(_drv);
+
+ if (!drv->ids)
+ return 0;
+
+ return match_device(drv->ids, to_xenbus_device(_dev)) != NULL;
+}
+
+/* Bus type for frontend drivers. */
+static struct bus_type xenbus_type = {
+ .name = "xenbus",
+ .match = xenbus_match,
+};
+
+
+/* Bus type for backend drivers. */
+static struct bus_type xenback_type = {
+ .name = "xenback",
+ .match = xenbus_match,
+};
+
+struct xenbus_for_dev {
+ int (*fn)(struct xenbus_device *, void *);
+ void *data;
+};
+
+static int for_dev(struct device *_dev, void *_data)
+{
+ struct xenbus_device *dev = to_xenbus_device(_dev);
+ struct xenbus_for_dev *data = _data;
+ dev = to_xenbus_device(_dev);
+ return data->fn(dev, data->data);
+}
+
+int xenbus_for_each_dev(struct xenbus_device * start, void * data,
+ int (*fn)(struct xenbus_device *, void *))
+{
+ struct xenbus_for_dev for_data = {
+ .fn = fn,
+ .data = data,
+ };
+ if (!fn)
+ return -EINVAL;
+ printk("%s> data=%p fn=%p for_data=%p\n", __FUNCTION__,
+ data, fn, &for_data);
+ return bus_for_each_dev(&xenbus_type,
+ (start ? &start->dev : NULL),
+ &for_data, for_dev);
+}
+
+struct xenbus_for_drv {
+ int (*fn)(struct xenbus_driver *, void *);
+ void *data;
+};
+
+static int for_drv(struct device_driver *_drv, void *_data)
+{
+ struct xenbus_driver *drv = to_xenbus_driver(_drv);
+ struct xenbus_for_drv *data = _data;
+ return data->fn(drv, data->data);
+}
+
+int xenbus_for_each_drv(struct xenbus_driver * start, void * data,
+ int (*fn)(struct xenbus_driver *, void *))
+{
+ struct xenbus_for_drv for_data = {
+ .fn = fn,
+ .data = data,
+ };
+ if (!fn)
+ return -EINVAL;
+ return bus_for_each_drv(&xenbus_type,
+ (start ? &start->driver: NULL),
+ &for_data, for_drv);
+}
+
+static int xenbus_dev_probe(struct device *_dev)
+{
+ struct xenbus_device *dev = to_xenbus_device(_dev);
+ struct xenbus_driver *drv = to_xenbus_driver(_dev->driver);
+ const struct xenbus_device_id *id;
+
+ if (!drv->probe)
+ return -ENODEV;
+
+ id = match_device(drv->ids, dev);
+ if (!id)
+ return -ENODEV;
+ return drv->probe(dev, id);
+}
+
+static int xenbus_dev_remove(struct device *_dev)
+{
+ struct xenbus_device *dev = to_xenbus_device(_dev);
+ struct xenbus_driver *drv = to_xenbus_driver(_dev->driver);
+
+ if (!drv->remove)
+ return 0;
+ return drv->remove(dev);
+}
+
+int xenbus_register_driver(struct xenbus_driver *drv)
+{
+ int err = 0;
+
+ printk("%s> frontend driver %p %s\n", __FUNCTION__,
+ drv, drv->name);
+ drv->driver.name = drv->name;
+ drv->driver.bus = &xenbus_type;
+ drv->driver.owner = drv->owner;
+ drv->driver.probe = xenbus_dev_probe;
+ drv->driver.remove = xenbus_dev_remove;
+
+ err = driver_register(&drv->driver);
+ if (err == 0 && xs_init_done && drv->connect) {
+ printk("%s> connecting driver %p %s\n", __FUNCTION__,
+ drv, drv->name);
+ drv->connect(drv);
+ }
+ return err;
+}
+
+void xenbus_unregister_driver(struct xenbus_driver *drv)
+{
+ driver_unregister(&drv->driver);
+}
+
+static int xenbus_probe_device(const char *dir, const char *name)
+{
+ int err;
+ struct xenbus_device *xendev;
+ unsigned int xendev_n;
+ long id;
+ char *nodename, *devicetype;
+ unsigned int devicetype_n;
+
+ dprintf("> dir=%s name=%s\n", dir, name);
+ nodename = xenbus_path(dir, name);
+ if (!nodename)
+ return -ENOMEM;
+
+ devicetype = xenbus_read(nodename, XENBUS_DEVICE_TYPE, &devicetype_n);
+ if (IS_ERR(devicetype)) {
+ err = PTR_ERR(devicetype);
+ goto free_nodename;
+ }
+
+ err = xenbus_read_long(nodename, XENBUS_DEVICE_ID, &id);
+ if (err == -ENOENT)
+ id = 0;
+ else if (err != 0)
+ goto free_devicetype;
+
+ dprintf("> devicetype='%s' name='%s' id=%ld\n", devicetype, name, id);
+ /* FIXME: This could be a rescan. Don't re-register existing devices. */
+
+ /* Add space for the strings. */
+ xendev_n = sizeof(*xendev) + strlen(nodename) + strlen(devicetype) + 2;
+ xendev = kmalloc(xendev_n, GFP_KERNEL);
+ if (!xendev) {
+ err = -ENOMEM;
+ goto free_devicetype;
+ }
+ memset(xendev, 0, xendev_n);
+
+ snprintf(xendev->dev.bus_id, BUS_ID_SIZE, "%s-%s", devicetype, name);
+ xendev->dev.bus = &xenbus_type;
+
+ xendev->id = id;
+
+ /* Copy the strings into the extra space. */
+ xendev->nodename = (char *)(xendev + 1);
+ strcpy(xendev->nodename, nodename);
+ xendev->devicetype = xendev->nodename + strlen(xendev->nodename) + 1;
+ strcpy(xendev->devicetype, devicetype);
+
+ /* Register with generic device framework. */
+ printk("XENBUS: Registering device %s\n", xendev->dev.bus_id);
+ err = device_register(&xendev->dev);
+ if (err) {
+ printk("XENBUS: Registering device %s: error %i\n",
+ xendev->dev.bus_id, err);
+ kfree(xendev);
+ }
+
+free_devicetype:
+ kfree(devicetype);
+free_nodename:
+ kfree(nodename);
+ dprintf("< err=%i\n", err);
+ return err;
+}
+
+static int xenbus_probe_device_type(const char *dirpath, const char *typename)
+{
+ int err = 0;
+ char **dir;
+ char *path;
+ unsigned int dir_n = 0;
+ int i;
+
+ dprintf("> dirpath=%s typename=%s\n", dirpath, typename);
+ path = xenbus_path(dirpath, typename);
+ if (!path)
+ return -ENOMEM;
+
+ dir = xs_directory(path, &dir_n);
+ if (IS_ERR(dir)) {
+ err = PTR_ERR(dir);
+ goto out;
+ }
+
+ for (i = 0; i < dir_n; i++) {
+ err = xenbus_probe_device(path, dir[i]);
+ if (err)
+ break;
+ }
+ kfree(dir);
+out:
+ kfree(path);
+ dprintf("< err=%i\n", err);
+ return err;
+}
+
+static int xenbus_probe_devices(const char *path)
+{
+ int err = 0;
+ char **dir;
+ unsigned int i, dir_n;
+
+ dprintf("> path=%s\n", path);
+ down(&xs_lock);
+ dir = xs_directory(path, &dir_n);
+ if (IS_ERR(dir)) {
+ err = PTR_ERR(dir);
+ goto unlock;
+ }
+ for (i = 0; i < dir_n; i++) {
+ err = xenbus_probe_device_type(path, dir[i]);
+ if (err)
+ break;
+ }
+ kfree(dir);
+unlock:
+ up(&xs_lock);
+ dprintf("< err=%i\n", err);
+ return err;
+}
+
+
+static int xenbus_probe_backend(const char *dir, const char *name)
+{
+ int err = 0;
+ struct xenbus_device *xendev = NULL;
+ unsigned int xendev_n = 0;
+ char *nodename = NULL, *devicetype = NULL;
+ unsigned int devicetype_n = 0;
+
+ dprintf("> dir=%s name=%s\n", dir, name);
+ nodename = xenbus_path(dir, name);
+ if (!nodename)
+ return -ENOMEM;
+
+ devicetype = xenbus_read(nodename, XENBUS_DEVICE_TYPE, &devicetype_n);
+ if (IS_ERR(devicetype)) {
+ err = PTR_ERR(devicetype);
+ goto free_nodename;
+ }
+
+ dprintf("> devicetype='%s'\n", devicetype);
+ /* FIXME: This could be a rescan. Don't re-register existing devices. */
+
+ /* Add space for the strings. */
+ xendev_n = sizeof(*xendev) + strlen(nodename) + strlen(devicetype) + 2;
+ xendev = kmalloc(xendev_n, GFP_KERNEL);
+ if (!xendev) {
+ err = -ENOMEM;
+ goto free_devicetype;
+ }
+ memset(xendev, 0, xendev_n);
+
+ snprintf(xendev->dev.bus_id, BUS_ID_SIZE, "%s", devicetype);
+ xendev->dev.bus = &xenback_type;
+
+ /* Copy the strings into the extra space. */
+ xendev->nodename = (char *)(xendev + 1);
+ strcpy(xendev->nodename, nodename);
+ xendev->devicetype = xendev->nodename + strlen(xendev->nodename) + 1;
+ strcpy(xendev->devicetype, devicetype);
+
+ /* Register with generic device framework. */
+ printk("XENBUS: Registering backend %s\n", xendev->dev.bus_id);
+ err = device_register(&xendev->dev);
+ if (err) {
+ printk("XENBUS: Registering device %s: error %i\n",
+ xendev->dev.bus_id, err);
+ kfree(xendev);
+ }
+
+free_devicetype:
+ kfree(devicetype);
+free_nodename:
+ kfree(nodename);
+ dprintf("< err=%i\n", err);
+ return err;
+}
+
+static int xenbus_probe_backends(const char *path)
+{
+ int err = 0;
+ char **dir;
+ unsigned int i, dir_n;
+
+ dprintf("> path=%s\n", path);
+ down(&xs_lock);
+ dir = xs_directory(path, &dir_n);
+ if (IS_ERR(dir)) {
+ err = PTR_ERR(dir);
+ goto unlock;
+ }
+ for (i = 0; i < dir_n; i++) {
+ err = xenbus_probe_backend(path, dir[i]);
+ if (err)
+ break;
+ }
+ kfree(dir);
+unlock:
+ up(&xs_lock);
+ dprintf("< err=%i\n", err);
+ return err;
+}
+
+int xenbus_register_backend(struct xenbus_driver *drv)
+{
+ int err = 0;
+
+ printk("%s> backend driver %p %s\n", __FUNCTION__,
+ drv, drv->name);
+ drv->driver.name = drv->name;
+ drv->driver.bus = &xenback_type;
+ drv->driver.owner = drv->owner;
+ drv->driver.probe = xenbus_dev_probe;
+ drv->driver.remove = xenbus_dev_remove;
+
+ err = driver_register(&drv->driver);
+ if (err == 0 && xs_init_done && drv->connect) {
+ printk("%s> connecting driver %p %s\n", __FUNCTION__,
+ drv, drv->name);
+ drv->connect(drv);
+ }
+ return err;
+}
+
+void xenbus_unregister_backend(struct xenbus_driver *drv)
+{
+ driver_unregister(&drv->driver);
+}
+
+int xenbus_for_each_backend(struct xenbus_driver * start, void * data,
+ int (*fn)(struct xenbus_driver *, void *))
+{
+ struct xenbus_for_drv for_data = {
+ .fn = fn,
+ .data = data,
+ };
+ if (!fn)
+ return -EINVAL;
+ return bus_for_each_drv(&xenback_type,
+ (start ? &start->driver: NULL),
+ &for_data, for_drv);
+}
+
+static void test_callback(struct xenbus_watch *w, const char *node)
+{
+ printk("test_callback: got watch hit for %s\n", node);
+}
+
+static void test_watch(void)
+{
+ static int init_done = 0;
+ static struct xenbus_watch watch = { .node = "/",
+ .priority = 0,
+ .callback = test_callback };
+
+ if (init_done)
+ return;
+ printk("registering watch %lX = %i\n",
+ (long)&watch,
+ register_xenbus_watch(&watch));
+ init_done = 1;
+}
+
+static int xenbus_driver_connect(struct xenbus_driver *drv, void *data)
+{
+ printk("%s> driver %p %s\n", __FUNCTION__, drv, drv->name);
+ if (drv->connect) {
+ printk("%s> connecting driver %p %s\n", __FUNCTION__,
+ drv, drv->name);
+ drv->connect(drv);
+ }
+ printk("%s< driver %p %s\n", __FUNCTION__, drv, drv->name);
+ return 0;
+}
+
+int do_xenbus_connect(void *unused)
+{
+ int err = 0;
+
+ printk("%s> xs_init_done=%d\n", __FUNCTION__, xs_init_done);
+ if (xs_init_done)
+ goto exit;
+ /* Initialize xenstore comms unless already done. */
+ printk("store_evtchn = %i\n", xen_start_info.store_evtchn);
+ err = xs_init();
+ if (err) {
+ printk("XENBUS: Error initializing xenstore comms:"
+ " %i\n", err);
+ goto exit;
+ }
+ xs_init_done = 1;
+
+ /* Notify drivers that xenstore has connected. */
+ test_watch();
+ printk("%s> connect drivers...\n", __FUNCTION__);
+ xenbus_for_each_drv(NULL, NULL, xenbus_driver_connect);
+ printk("%s> connect backends...\n", __FUNCTION__);
+ xenbus_for_each_backend(NULL, NULL, xenbus_driver_connect);
+
+ /* Enumerate devices and backends in xenstore. */
+ xenbus_probe_devices(XENBUS_DEVICE_DIR);
+ xenbus_probe_backends(XENBUS_BACKEND_DIR);
+
+exit:
+ printk("%s< err=%d\n", __FUNCTION__, err);
+ return err;
+}
+
+static int __init xenbus_probe_init(void)
+{
+ bus_register(&xenbus_type);
+ bus_register(&xenback_type);
+
+ if (!xen_start_info.store_evtchn)
+ return 0;
+
+ do_xenbus_connect(NULL);
+ return 0;
+}
+
+postcore_initcall(xenbus_probe_init);
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/mm/page_alloc.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/mm/page_alloc.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,972 @@
+/*
+ * linux/mm/page_alloc.c
+ *
+ * Manages the free list, the system allocates free pages here.
+ * Note that kmalloc() lives in slab.c
+ *
+ * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
+ * Swap reorganised 29.12.95, Stephen Tweedie
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ * Reshaped it to be a zoned allocator, Ingo Molnar, Red Hat, 1999
+ * Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
+ * Zone balancing, Kanoj Sarcar, SGI, Jan 2000
+ */
+
+#include <linux/config.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/swapctl.h>
+#include <linux/interrupt.h>
+#include <linux/pagemap.h>
+#include <linux/bootmem.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+
+int nr_swap_pages;
+int nr_active_pages;
+int nr_inactive_pages;
+LIST_HEAD(inactive_list);
+LIST_HEAD(active_list);
+pg_data_t *pgdat_list;
+
+/*
+ *
+ * The zone_table array is used to look up the address of the
+ * struct zone corresponding to a given zone number (ZONE_DMA,
+ * ZONE_NORMAL, or ZONE_HIGHMEM).
+ */
+zone_t *zone_table[MAX_NR_ZONES*MAX_NR_NODES];
+EXPORT_SYMBOL(zone_table);
+
+static char *zone_names[MAX_NR_ZONES] = { "DMA", "Normal", "HighMem" };
+static int zone_balance_ratio[MAX_NR_ZONES] __initdata = { 128, 128, 128, };
+static int zone_balance_min[MAX_NR_ZONES] __initdata = { 20 , 20, 20, };
+static int zone_balance_max[MAX_NR_ZONES] __initdata = { 255 , 255, 255, };
+static int lower_zone_reserve_ratio[MAX_NR_ZONES-1] = { 256, 32 };
+
+int vm_gfp_debug = 0;
+
+static void FASTCALL(__free_pages_ok (struct page *page, unsigned int order));
+
+static spinlock_t free_pages_ok_no_irq_lock = SPIN_LOCK_UNLOCKED;
+struct page * free_pages_ok_no_irq_head;
+
+static void do_free_pages_ok_no_irq(void * arg)
+{
+ struct page * page, * __page;
+
+ spin_lock_irq(&free_pages_ok_no_irq_lock);
+
+ page = free_pages_ok_no_irq_head;
+ free_pages_ok_no_irq_head = NULL;
+
+ spin_unlock_irq(&free_pages_ok_no_irq_lock);
+
+ while (page) {
+ __page = page;
+ page = page->next_hash;
+ __free_pages_ok(__page, __page->index);
+ }
+}
+
+static struct tq_struct free_pages_ok_no_irq_task = {
+ .routine = do_free_pages_ok_no_irq,
+};
+
+
+/*
+ * Temporary debugging check.
+ */
+#define BAD_RANGE(zone, page) \
+( \
+ (((page) - mem_map) >= ((zone)->zone_start_mapnr+(zone)->size)) \
+ || (((page) - mem_map) < (zone)->zone_start_mapnr) \
+ || ((zone) != page_zone(page)) \
+)
+
+/*
+ * Freeing function for a buddy system allocator.
+ * Contrary to prior comments, this is *NOT* hairy, and there
+ * is no reason for anyone not to understand it.
+ *
+ * The concept of a buddy system is to maintain direct-mapped tables
+ * (containing bit values) for memory blocks of various "orders".
+ * The bottom level table contains the map for the smallest allocatable
+ * units of memory (here, pages), and each level above it describes
+ * pairs of units from the levels below, hence, "buddies".
+ * At a high level, all that happens here is marking the table entry
+ * at the bottom level available, and propagating the changes upward
+ * as necessary, plus some accounting needed to play nicely with other
+ * parts of the VM system.
+ * At each level, we keep one bit for each pair of blocks, which
+ * is set to 1 iff only one of the pair is allocated. So when we
+ * are allocating or freeing one, we can derive the state of the
+ * other. That is, if we allocate a small block, and both were
+ * free, the remainder of the region must be split into blocks.
+ * If a block is freed, and its buddy is also free, then this
+ * triggers coalescing into a block of larger size.
+ *
+ * -- wli
+ */
+
+static void fastcall __free_pages_ok (struct page *page, unsigned int order)
+{
+ unsigned long index, page_idx, mask, flags;
+ free_area_t *area;
+ struct page *base;
+ zone_t *zone;
+
+ if (PageForeign(page))
+ return (PageForeignDestructor(page))(page);
+
+ /*
+ * Yes, think what happens when other parts of the kernel take
+ * a reference to a page in order to pin it for io. -ben
+ */
+ if (PageLRU(page)) {
+ if (unlikely(in_interrupt())) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&free_pages_ok_no_irq_lock, flags);
+ page->next_hash = free_pages_ok_no_irq_head;
+ free_pages_ok_no_irq_head = page;
+ page->index = order;
+
+ spin_unlock_irqrestore(&free_pages_ok_no_irq_lock,
flags);
+
+ schedule_task(&free_pages_ok_no_irq_task);
+ return;
+ }
+
+ lru_cache_del(page);
+ }
+
+ if (page->buffers)
+ BUG();
+ if (page->mapping)
+ BUG();
+ if (!VALID_PAGE(page))
+ BUG();
+ if (PageLocked(page))
+ BUG();
+ if (PageActive(page))
+ BUG();
+ ClearPageReferenced(page);
+ ClearPageDirty(page);
+
+ if (current->flags & PF_FREE_PAGES)
+ goto local_freelist;
+ back_local_freelist:
+
+ zone = page_zone(page);
+
+ mask = (~0UL) << order;
+ base = zone->zone_mem_map;
+ page_idx = page - base;
+ if (page_idx & ~mask)
+ BUG();
+ index = page_idx >> (1 + order);
+
+ area = zone->free_area + order;
+
+ spin_lock_irqsave(&zone->lock, flags);
+
+ zone->free_pages -= mask;
+
+ while (mask + (1 << (MAX_ORDER-1))) {
+ struct page *buddy1, *buddy2;
+
+ if (area >= zone->free_area + MAX_ORDER)
+ BUG();
+ if (!__test_and_change_bit(index, area->map))
+ /*
+ * the buddy page is still allocated.
+ */
+ break;
+ /*
+ * Move the buddy up one level.
+ * This code is taking advantage of the identity:
+ * -mask = 1+~mask
+ */
+ buddy1 = base + (page_idx ^ -mask);
+ buddy2 = base + page_idx;
+ if (BAD_RANGE(zone,buddy1))
+ BUG();
+ if (BAD_RANGE(zone,buddy2))
+ BUG();
+
+ list_del(&buddy1->list);
+ mask <<= 1;
+ area++;
+ index >>= 1;
+ page_idx &= mask;
+ }
+ list_add(&(base + page_idx)->list, &area->free_list);
+
+ spin_unlock_irqrestore(&zone->lock, flags);
+ return;
+
+ local_freelist:
+ if (current->nr_local_pages)
+ goto back_local_freelist;
+ if (in_interrupt())
+ goto back_local_freelist;
+
+ list_add(&page->list, ¤t->local_pages);
+ page->index = order;
+ current->nr_local_pages++;
+}
+
+#define MARK_USED(index, order, area) \
+ __change_bit((index) >> (1+(order)), (area)->map)
+
+static inline struct page * expand (zone_t *zone, struct page *page,
+ unsigned long index, int low, int high, free_area_t * area)
+{
+ unsigned long size = 1 << high;
+
+ while (high > low) {
+ if (BAD_RANGE(zone,page))
+ BUG();
+ area--;
+ high--;
+ size >>= 1;
+ list_add(&(page)->list, &(area)->free_list);
+ MARK_USED(index, high, area);
+ index += size;
+ page += size;
+ }
+ if (BAD_RANGE(zone,page))
+ BUG();
+ return page;
+}
+
+static FASTCALL(struct page * rmqueue(zone_t *zone, unsigned int order));
+static struct page * fastcall rmqueue(zone_t *zone, unsigned int order)
+{
+ free_area_t * area = zone->free_area + order;
+ unsigned int curr_order = order;
+ struct list_head *head, *curr;
+ unsigned long flags;
+ struct page *page;
+
+ spin_lock_irqsave(&zone->lock, flags);
+ do {
+ head = &area->free_list;
+ curr = head->next;
+
+ if (curr != head) {
+ unsigned int index;
+
+ page = list_entry(curr, struct page, list);
+ if (BAD_RANGE(zone,page))
+ BUG();
+ list_del(curr);
+ index = page - zone->zone_mem_map;
+ if (curr_order != MAX_ORDER-1)
+ MARK_USED(index, curr_order, area);
+ zone->free_pages -= 1UL << order;
+
+ page = expand(zone, page, index, order, curr_order,
area);
+ spin_unlock_irqrestore(&zone->lock, flags);
+
+ set_page_count(page, 1);
+ if (BAD_RANGE(zone,page))
+ BUG();
+ if (PageLRU(page))
+ BUG();
+ if (PageActive(page))
+ BUG();
+ return page;
+ }
+ curr_order++;
+ area++;
+ } while (curr_order < MAX_ORDER);
+ spin_unlock_irqrestore(&zone->lock, flags);
+
+ return NULL;
+}
+
+#ifndef CONFIG_DISCONTIGMEM
+struct page * fastcall _alloc_pages(unsigned int gfp_mask, unsigned int order)
+{
+ return __alloc_pages(gfp_mask, order,
+ contig_page_data.node_zonelists+(gfp_mask & GFP_ZONEMASK));
+}
+#endif
+
+static struct page * FASTCALL(balance_classzone(zone_t *, unsigned int,
unsigned int, int *));
+static struct page * fastcall balance_classzone(zone_t * classzone, unsigned
int gfp_mask, unsigned int order, int * freed)
+{
+ struct page * page = NULL;
+ int __freed;
+
+ if (in_interrupt())
+ BUG();
+
+ current->allocation_order = order;
+ current->flags |= PF_MEMALLOC | PF_FREE_PAGES;
+
+ __freed = try_to_free_pages_zone(classzone, gfp_mask);
+
+ current->flags &= ~(PF_MEMALLOC | PF_FREE_PAGES);
+
+ if (current->nr_local_pages) {
+ struct list_head * entry, * local_pages;
+ struct page * tmp;
+ int nr_pages;
+
+ local_pages = ¤t->local_pages;
+
+ if (likely(__freed)) {
+ /* pick from the last inserted so we're lifo */
+ entry = local_pages->next;
+ do {
+ tmp = list_entry(entry, struct page, list);
+ if (tmp->index == order &&
memclass(page_zone(tmp), classzone)) {
+ list_del(entry);
+ current->nr_local_pages--;
+ set_page_count(tmp, 1);
+ page = tmp;
+
+ if (page->buffers)
+ BUG();
+ if (page->mapping)
+ BUG();
+ if (!VALID_PAGE(page))
+ BUG();
+ if (PageLocked(page))
+ BUG();
+ if (PageLRU(page))
+ BUG();
+ if (PageActive(page))
+ BUG();
+ if (PageDirty(page))
+ BUG();
+
+ break;
+ }
+ } while ((entry = entry->next) != local_pages);
+ }
+
+ nr_pages = current->nr_local_pages;
+ /* free in reverse order so that the global order will be lifo
*/
+ while ((entry = local_pages->prev) != local_pages) {
+ list_del(entry);
+ tmp = list_entry(entry, struct page, list);
+ __free_pages_ok(tmp, tmp->index);
+ if (!nr_pages--)
+ BUG();
+ }
+ current->nr_local_pages = 0;
+ }
+
+ *freed = __freed;
+ return page;
+}
+
+static inline unsigned long zone_free_pages(zone_t * zone, unsigned int order)
+{
+ long free = zone->free_pages - (1UL << order);
+ return free >= 0 ? free : 0;
+}
+
+/*
+ * This is the 'heart' of the zoned buddy allocator:
+ */
+struct page * fastcall __alloc_pages(unsigned int gfp_mask, unsigned int
order, zonelist_t *zonelist)
+{
+ zone_t **zone, * classzone;
+ struct page * page;
+ int freed, class_idx;
+
+ zone = zonelist->zones;
+ classzone = *zone;
+ class_idx = zone_idx(classzone);
+
+ for (;;) {
+ zone_t *z = *(zone++);
+ if (!z)
+ break;
+
+ if (zone_free_pages(z, order) > z->watermarks[class_idx].low) {
+ page = rmqueue(z, order);
+ if (page)
+ return page;
+ }
+ }
+
+ classzone->need_balance = 1;
+ mb();
+ if (waitqueue_active(&kswapd_wait))
+ wake_up_interruptible(&kswapd_wait);
+
+ zone = zonelist->zones;
+ for (;;) {
+ unsigned long min;
+ zone_t *z = *(zone++);
+ if (!z)
+ break;
+
+ min = z->watermarks[class_idx].min;
+ if (!(gfp_mask & __GFP_WAIT))
+ min >>= 2;
+ if (zone_free_pages(z, order) > min) {
+ page = rmqueue(z, order);
+ if (page)
+ return page;
+ }
+ }
+
+ /* here we're in the low on memory slow path */
+
+ if ((current->flags & PF_MEMALLOC) &&
+ (!in_interrupt() || (current->flags & PF_MEMDIE))) {
+ zone = zonelist->zones;
+ for (;;) {
+ zone_t *z = *(zone++);
+ if (!z)
+ break;
+
+ page = rmqueue(z, order);
+ if (page)
+ return page;
+ }
+ return NULL;
+ }
+
+ /* Atomic allocations - we can't balance anything */
+ if (!(gfp_mask & __GFP_WAIT))
+ goto out;
+
+ rebalance:
+ page = balance_classzone(classzone, gfp_mask, order, &freed);
+ if (page)
+ return page;
+
+ zone = zonelist->zones;
+ if (likely(freed)) {
+ for (;;) {
+ zone_t *z = *(zone++);
+ if (!z)
+ break;
+
+ if (zone_free_pages(z, order) >
z->watermarks[class_idx].min) {
+ page = rmqueue(z, order);
+ if (page)
+ return page;
+ }
+ }
+ goto rebalance;
+ } else {
+ /*
+ * Check that no other task is been killed meanwhile,
+ * in such a case we can succeed the allocation.
+ */
+ for (;;) {
+ zone_t *z = *(zone++);
+ if (!z)
+ break;
+
+ if (zone_free_pages(z, order) >
z->watermarks[class_idx].high) {
+ page = rmqueue(z, order);
+ if (page)
+ return page;
+ }
+ }
+ }
+
+ out:
+ printk(KERN_NOTICE "__alloc_pages: %u-order allocation failed
(gfp=0x%x/%i)\n",
+ order, gfp_mask, !!(current->flags & PF_MEMALLOC));
+ if (unlikely(vm_gfp_debug))
+ dump_stack();
+ return NULL;
+}
+
+/*
+ * Common helper functions.
+ */
+fastcall unsigned long __get_free_pages(unsigned int gfp_mask, unsigned int
order)
+{
+ struct page * page;
+
+ page = alloc_pages(gfp_mask, order);
+ if (!page)
+ return 0;
+ return (unsigned long) page_address(page);
+}
+
+fastcall unsigned long get_zeroed_page(unsigned int gfp_mask)
+{
+ struct page * page;
+
+ page = alloc_pages(gfp_mask, 0);
+ if (page) {
+ void *address = page_address(page);
+ clear_page(address);
+ return (unsigned long) address;
+ }
+ return 0;
+}
+
+fastcall void __free_pages(struct page *page, unsigned int order)
+{
+ if (!PageReserved(page) && put_page_testzero(page))
+ __free_pages_ok(page, order);
+}
+
+fastcall void free_pages(unsigned long addr, unsigned int order)
+{
+ if (addr != 0)
+ __free_pages(virt_to_page(addr), order);
+}
+
+/*
+ * Total amount of free (allocatable) RAM:
+ */
+unsigned int nr_free_pages (void)
+{
+ unsigned int sum = 0;
+ zone_t *zone;
+
+ for_each_zone(zone)
+ sum += zone->free_pages;
+
+ return sum;
+}
+
+/*
+ * Amount of free RAM allocatable as buffer memory:
+ */
+unsigned int nr_free_buffer_pages (void)
+{
+ pg_data_t *pgdat;
+ unsigned int sum = 0;
+ zonelist_t *zonelist;
+ zone_t **zonep, *zone;
+
+ for_each_pgdat(pgdat) {
+ int class_idx;
+ zonelist = pgdat->node_zonelists + (GFP_USER & GFP_ZONEMASK);
+ zonep = zonelist->zones;
+ zone = *zonep;
+ class_idx = zone_idx(zone);
+
+ sum += zone->nr_cache_pages;
+ for (; zone; zone = *zonep++) {
+ int free = zone->free_pages -
zone->watermarks[class_idx].high;
+ if (free <= 0)
+ continue;
+ sum += free;
+ }
+ }
+
+ return sum;
+}
+
+#if CONFIG_HIGHMEM
+unsigned int nr_free_highpages (void)
+{
+ pg_data_t *pgdat;
+ unsigned int pages = 0;
+
+ for_each_pgdat(pgdat)
+ pages += pgdat->node_zones[ZONE_HIGHMEM].free_pages;
+
+ return pages;
+}
+
+unsigned int freeable_lowmem(void)
+{
+ unsigned int pages = 0;
+ pg_data_t *pgdat;
+
+ for_each_pgdat(pgdat) {
+ pages += pgdat->node_zones[ZONE_DMA].free_pages;
+ pages += pgdat->node_zones[ZONE_DMA].nr_active_pages;
+ pages += pgdat->node_zones[ZONE_DMA].nr_inactive_pages;
+ pages += pgdat->node_zones[ZONE_NORMAL].free_pages;
+ pages += pgdat->node_zones[ZONE_NORMAL].nr_active_pages;
+ pages += pgdat->node_zones[ZONE_NORMAL].nr_inactive_pages;
+ }
+
+ return pages;
+}
+#endif
+
+#define K(x) ((x) << (PAGE_SHIFT-10))
+
+/*
+ * Show free area list (used inside shift_scroll-lock stuff)
+ * We also calculate the percentage fragmentation. We do this by counting the
+ * memory on each free list with the exception of the first item on the list.
+ */
+void show_free_areas_core(pg_data_t *pgdat)
+{
+ unsigned int order;
+ unsigned type;
+ pg_data_t *tmpdat = pgdat;
+
+ printk("Free pages: %6dkB (%6dkB HighMem)\n",
+ K(nr_free_pages()),
+ K(nr_free_highpages()));
+
+ while (tmpdat) {
+ zone_t *zone;
+ for (zone = tmpdat->node_zones;
+ zone < tmpdat->node_zones + MAX_NR_ZONES;
zone++)
+ printk("Zone:%s freepages:%6lukB\n",
+ zone->name,
+ K(zone->free_pages));
+
+ tmpdat = tmpdat->node_next;
+ }
+
+ printk("( Active: %d, inactive: %d, free: %d )\n",
+ nr_active_pages,
+ nr_inactive_pages,
+ nr_free_pages());
+
+ for (type = 0; type < MAX_NR_ZONES; type++) {
+ struct list_head *head, *curr;
+ zone_t *zone = pgdat->node_zones + type;
+ unsigned long nr, total, flags;
+
+ total = 0;
+ if (zone->size) {
+ spin_lock_irqsave(&zone->lock, flags);
+ for (order = 0; order < MAX_ORDER; order++) {
+ head = &(zone->free_area + order)->free_list;
+ curr = head;
+ nr = 0;
+ for (;;) {
+ if ((curr = curr->next) == head)
+ break;
+ nr++;
+ }
+ total += nr * (1 << order);
+ printk("%lu*%lukB ", nr, K(1UL) << order);
+ }
+ spin_unlock_irqrestore(&zone->lock, flags);
+ }
+ printk("= %lukB)\n", K(total));
+ }
+
+#ifdef SWAP_CACHE_INFO
+ show_swap_cache_info();
+#endif
+}
+
+void show_free_areas(void)
+{
+ show_free_areas_core(pgdat_list);
+}
+
+/*
+ * Builds allocation fallback zone lists.
+ */
+static inline void build_zonelists(pg_data_t *pgdat)
+{
+ int i, j, k;
+
+ for (i = 0; i <= GFP_ZONEMASK; i++) {
+ zonelist_t *zonelist;
+ zone_t *zone;
+
+ zonelist = pgdat->node_zonelists + i;
+ memset(zonelist, 0, sizeof(*zonelist));
+
+ j = 0;
+ k = ZONE_NORMAL;
+ if (i & __GFP_HIGHMEM)
+ k = ZONE_HIGHMEM;
+ if (i & __GFP_DMA)
+ k = ZONE_DMA;
+
+ switch (k) {
+ default:
+ BUG();
+ /*
+ * fallthrough:
+ */
+ case ZONE_HIGHMEM:
+ zone = pgdat->node_zones + ZONE_HIGHMEM;
+ if (zone->size) {
+#ifndef CONFIG_HIGHMEM
+ BUG();
+#endif
+ zonelist->zones[j++] = zone;
+ }
+ case ZONE_NORMAL:
+ zone = pgdat->node_zones + ZONE_NORMAL;
+ if (zone->size)
+ zonelist->zones[j++] = zone;
+ case ZONE_DMA:
+ zone = pgdat->node_zones + ZONE_DMA;
+ if (zone->size)
+ zonelist->zones[j++] = zone;
+ }
+ zonelist->zones[j++] = NULL;
+ }
+}
+
+/*
+ * Helper functions to size the waitqueue hash table.
+ * Essentially these want to choose hash table sizes sufficiently
+ * large so that collisions trying to wait on pages are rare.
+ * But in fact, the number of active page waitqueues on typical
+ * systems is ridiculously low, less than 200. So this is even
+ * conservative, even though it seems large.
+ *
+ * The constant PAGES_PER_WAITQUEUE specifies the ratio of pages to
+ * waitqueues, i.e. the size of the waitq table given the number of pages.
+ */
+#define PAGES_PER_WAITQUEUE 256
+
+static inline unsigned long wait_table_size(unsigned long pages)
+{
+ unsigned long size = 1;
+
+ pages /= PAGES_PER_WAITQUEUE;
+
+ while (size < pages)
+ size <<= 1;
+
+ /*
+ * Once we have dozens or even hundreds of threads sleeping
+ * on IO we've got bigger problems than wait queue collision.
+ * Limit the size of the wait table to a reasonable size.
+ */
+ size = min(size, 4096UL);
+
+ return size;
+}
+
+/*
+ * This is an integer logarithm so that shifts can be used later
+ * to extract the more random high bits from the multiplicative
+ * hash function before the remainder is taken.
+ */
+static inline unsigned long wait_table_bits(unsigned long size)
+{
+ return ffz(~size);
+}
+
+#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))
+
+/*
+ * Set up the zone data structures:
+ * - mark all pages reserved
+ * - mark all memory queues empty
+ * - clear the memory bitmaps
+ */
+void __init free_area_init_core(int nid, pg_data_t *pgdat, struct page **gmap,
+ unsigned long *zones_size, unsigned long zone_start_paddr,
+ unsigned long *zholes_size, struct page *lmem_map)
+{
+ unsigned long i, j;
+ unsigned long map_size;
+ unsigned long totalpages, offset, realtotalpages;
+ const unsigned long zone_required_alignment = 1UL << (MAX_ORDER-1);
+
+ if (zone_start_paddr & ~PAGE_MASK)
+ BUG();
+
+ totalpages = 0;
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ unsigned long size = zones_size[i];
+ totalpages += size;
+ }
+ realtotalpages = totalpages;
+ if (zholes_size)
+ for (i = 0; i < MAX_NR_ZONES; i++)
+ realtotalpages -= zholes_size[i];
+
+ printk("On node %d totalpages: %lu\n", nid, realtotalpages);
+
+ /*
+ * Some architectures (with lots of mem and discontinous memory
+ * maps) have to search for a good mem_map area:
+ * For discontigmem, the conceptual mem map array starts from
+ * PAGE_OFFSET, we need to align the actual array onto a mem map
+ * boundary, so that MAP_NR works.
+ */
+ map_size = (totalpages + 1)*sizeof(struct page);
+ if (lmem_map == (struct page *)0) {
+ lmem_map = (struct page *) alloc_bootmem_node(pgdat, map_size);
+ lmem_map = (struct page *)(PAGE_OFFSET +
+ MAP_ALIGN((unsigned long)lmem_map - PAGE_OFFSET));
+ }
+ *gmap = pgdat->node_mem_map = lmem_map;
+ pgdat->node_size = totalpages;
+ pgdat->node_start_paddr = zone_start_paddr;
+ pgdat->node_start_mapnr = (lmem_map - mem_map);
+ pgdat->nr_zones = 0;
+
+ offset = lmem_map - mem_map;
+ for (j = 0; j < MAX_NR_ZONES; j++) {
+ zone_t *zone = pgdat->node_zones + j;
+ unsigned long mask;
+ unsigned long size, realsize;
+ int idx;
+
+ zone_table[nid * MAX_NR_ZONES + j] = zone;
+ realsize = size = zones_size[j];
+ if (zholes_size)
+ realsize -= zholes_size[j];
+
+ printk("zone(%lu): %lu pages.\n", j, size);
+ zone->size = size;
+ zone->realsize = realsize;
+ zone->name = zone_names[j];
+ zone->lock = SPIN_LOCK_UNLOCKED;
+ zone->zone_pgdat = pgdat;
+ zone->free_pages = 0;
+ zone->need_balance = 0;
+ zone->nr_active_pages = zone->nr_inactive_pages = 0;
+
+
+ if (!size)
+ continue;
+
+ /*
+ * The per-page waitqueue mechanism uses hashed waitqueues
+ * per zone.
+ */
+ zone->wait_table_size = wait_table_size(size);
+ zone->wait_table_shift =
+ BITS_PER_LONG - wait_table_bits(zone->wait_table_size);
+ zone->wait_table = (wait_queue_head_t *)
+ alloc_bootmem_node(pgdat, zone->wait_table_size
+ * sizeof(wait_queue_head_t));
+
+ for(i = 0; i < zone->wait_table_size; ++i)
+ init_waitqueue_head(zone->wait_table + i);
+
+ pgdat->nr_zones = j+1;
+
+ mask = (realsize / zone_balance_ratio[j]);
+ if (mask < zone_balance_min[j])
+ mask = zone_balance_min[j];
+ else if (mask > zone_balance_max[j])
+ mask = zone_balance_max[j];
+ zone->watermarks[j].min = mask;
+ zone->watermarks[j].low = mask*2;
+ zone->watermarks[j].high = mask*3;
+ /* now set the watermarks of the lower zones in the "j"
classzone */
+ for (idx = j-1; idx >= 0; idx--) {
+ zone_t * lower_zone = pgdat->node_zones + idx;
+ unsigned long lower_zone_reserve;
+ if (!lower_zone->size)
+ continue;
+
+ mask = lower_zone->watermarks[idx].min;
+ lower_zone->watermarks[j].min = mask;
+ lower_zone->watermarks[j].low = mask*2;
+ lower_zone->watermarks[j].high = mask*3;
+
+ /* now the brainer part */
+ lower_zone_reserve = realsize /
lower_zone_reserve_ratio[idx];
+ lower_zone->watermarks[j].min += lower_zone_reserve;
+ lower_zone->watermarks[j].low += lower_zone_reserve;
+ lower_zone->watermarks[j].high += lower_zone_reserve;
+
+ realsize += lower_zone->realsize;
+ }
+
+ zone->zone_mem_map = mem_map + offset;
+ zone->zone_start_mapnr = offset;
+ zone->zone_start_paddr = zone_start_paddr;
+
+ if ((zone_start_paddr >> PAGE_SHIFT) &
(zone_required_alignment-1))
+ printk("BUG: wrong zone alignment, it will crash\n");
+
+ /*
+ * Initially all pages are reserved - free ones are freed
+ * up by free_all_bootmem() once the early boot process is
+ * done. Non-atomic initialization, single-pass.
+ */
+ for (i = 0; i < size; i++) {
+ struct page *page = mem_map + offset + i;
+ set_page_zone(page, nid * MAX_NR_ZONES + j);
+ set_page_count(page, 0);
+ SetPageReserved(page);
+ INIT_LIST_HEAD(&page->list);
+ if (j != ZONE_HIGHMEM)
+ set_page_address(page, __va(zone_start_paddr));
+ zone_start_paddr += PAGE_SIZE;
+ }
+
+ offset += size;
+ for (i = 0; ; i++) {
+ unsigned long bitmap_size;
+
+ INIT_LIST_HEAD(&zone->free_area[i].free_list);
+ if (i == MAX_ORDER-1) {
+ zone->free_area[i].map = NULL;
+ break;
+ }
+
+ /*
+ * Page buddy system uses "index >> (i+1)",
+ * where "index" is at most "size-1".
+ *
+ * The extra "+3" is to round down to byte
+ * size (8 bits per byte assumption). Thus
+ * we get "(size-1) >> (i+4)" as the last byte
+ * we can access.
+ *
+ * The "+1" is because we want to round the
+ * byte allocation up rather than down. So
+ * we should have had a "+7" before we shifted
+ * down by three. Also, we have to add one as
+ * we actually _use_ the last bit (it's [0,n]
+ * inclusive, not [0,n[).
+ *
+ * So we actually had +7+1 before we shift
+ * down by 3. But (n+8) >> 3 == (n >> 3) + 1
+ * (modulo overflows, which we do not have).
+ *
+ * Finally, we LONG_ALIGN because all bitmap
+ * operations are on longs.
+ */
+ bitmap_size = (size-1) >> (i+4);
+ bitmap_size = LONG_ALIGN(bitmap_size+1);
+ zone->free_area[i].map =
+ (unsigned long *) alloc_bootmem_node(pgdat,
bitmap_size);
+ }
+ }
+ build_zonelists(pgdat);
+}
+
+void __init free_area_init(unsigned long *zones_size)
+{
+ free_area_init_core(0, &contig_page_data, &mem_map, zones_size, 0, 0,
0);
+}
+
+static int __init setup_mem_frac(char *str)
+{
+ int j = 0;
+
+ while (get_option(&str, &zone_balance_ratio[j++]) == 2);
+ printk("setup_mem_frac: ");
+ for (j = 0; j < MAX_NR_ZONES; j++) printk("%d ",
zone_balance_ratio[j]);
+ printk("\n");
+ return 1;
+}
+
+__setup("memfrac=", setup_mem_frac);
+
+static int __init setup_lower_zone_reserve(char *str)
+{
+ int j = 0;
+
+ while (get_option(&str, &lower_zone_reserve_ratio[j++]) == 2);
+ printk("setup_lower_zone_reserve: ");
+ for (j = 0; j < MAX_NR_ZONES-1; j++) printk("%d ",
lower_zone_reserve_ratio[j]);
+ printk("\n");
+ return 1;
+}
+
+__setup("lower_zone_reserve=", setup_lower_zone_reserve);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/mach_timer.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/mach_timer.h
Fri Jul 15 13:39:50 2005
@@ -0,0 +1,48 @@
+/*
+ * include/asm-i386/mach-default/mach_timer.h
+ *
+ * Machine specific calibrate_tsc() for generic.
+ * Split out from timer_tsc.c by Osamu Tomita <tomita@xxxxxxxxxxx>
+ */
+/* ------ Calibrate the TSC -------
+ * Return 2^32 * (1 / (TSC clocks per usec)) for do_fast_gettimeoffset().
+ * Too much 64-bit arithmetic here to do this cleanly in C, and for
+ * accuracy's sake we want to keep the overhead on the CTC speaker (channel 2)
+ * output busy loop as low as possible. We avoid reading the CTC registers
+ * directly because of the awkward 8-bit access mechanism of the 82C54
+ * device.
+ */
+#ifndef _MACH_TIMER_H
+#define _MACH_TIMER_H
+
+#define CALIBRATE_LATCH (5 * LATCH)
+
+static inline void mach_prepare_counter(void)
+{
+ /* Set the Gate high, disable speaker */
+ outb((inb(0x61) & ~0x02) | 0x01, 0x61);
+
+ /*
+ * Now let's take care of CTC channel 2
+ *
+ * Set the Gate high, program CTC channel 2 for mode 0,
+ * (interrupt on terminal count mode), binary count,
+ * load 5 * LATCH count, (LSB and MSB) to begin countdown.
+ *
+ * Some devices need a delay here.
+ */
+ outb(0xb0, 0x43); /* binary, mode 0, LSB/MSB, Ch
2 */
+ outb_p(CALIBRATE_LATCH & 0xff, 0x42); /* LSB of count */
+ outb_p(CALIBRATE_LATCH >> 8, 0x42); /* MSB of count */
+}
+
+static inline void mach_countup(unsigned long *count_p)
+{
+ unsigned long count = 0;
+ do {
+ count++;
+ } while ((inb_p(0x61) & 0x20) == 0);
+ *count_p = count;
+}
+
+#endif /* !_MACH_TIMER_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/microcode.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/microcode.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,163 @@
+/*
+ * Intel CPU Microcode Update Driver for Linux
+ *
+ * Copyright (C) 2000-2004 Tigran Aivazian
+ *
+ * This driver allows to upgrade microcode on Intel processors
+ * belonging to IA-32 family - PentiumPro, Pentium II,
+ * Pentium III, Xeon, Pentium 4, etc.
+ *
+ * Reference: Section 8.10 of Volume III, Intel Pentium 4 Manual,
+ * Order Number 245472 or free download from:
+ *
+ * http://developer.intel.com/design/pentium4/manuals/245472.htm
+ *
+ * For more information, go to http://www.urbanmyth.org/microcode
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+//#define DEBUG /* pr_debug */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/miscdevice.h>
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/syscalls.h>
+
+#include <asm/msr.h>
+#include <asm/uaccess.h>
+#include <asm/processor.h>
+
+MODULE_DESCRIPTION("Intel CPU (IA-32) Microcode Update Driver");
+MODULE_AUTHOR("Tigran Aivazian <tigran@xxxxxxxxxxx>");
+MODULE_LICENSE("GPL");
+
+#define MICROCODE_VERSION "1.14-xen"
+
+#define DEFAULT_UCODE_DATASIZE (2000) /* 2000 bytes */
+#define MC_HEADER_SIZE (sizeof (microcode_header_t)) /* 48 bytes */
+#define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE) /*
2048 bytes */
+
+/* no concurrent ->write()s are allowed on /dev/cpu/microcode */
+static DECLARE_MUTEX(microcode_sem);
+
+static void __user *user_buffer; /* user area microcode data buffer */
+static unsigned int user_buffer_size; /* it's size */
+
+static int microcode_open (struct inode *unused1, struct file *unused2)
+{
+ return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
+}
+
+
+static int do_microcode_update (void)
+{
+ int err;
+ dom0_op_t op;
+
+ err = sys_mlock((unsigned long)user_buffer, user_buffer_size);
+ if (err != 0)
+ return err;
+
+ op.cmd = DOM0_MICROCODE;
+ op.u.microcode.data = user_buffer;
+ op.u.microcode.length = user_buffer_size;
+ err = HYPERVISOR_dom0_op(&op);
+
+ (void)sys_munlock((unsigned long)user_buffer, user_buffer_size);
+
+ return err;
+}
+
+static ssize_t microcode_write (struct file *file, const char __user *buf,
size_t len, loff_t *ppos)
+{
+ ssize_t ret;
+
+ if (len < DEFAULT_UCODE_TOTALSIZE) {
+ printk(KERN_ERR "microcode: not enough data\n");
+ return -EINVAL;
+ }
+
+ if ((len >> PAGE_SHIFT) > num_physpages) {
+ printk(KERN_ERR "microcode: too much data (max %ld pages)\n",
num_physpages);
+ return -EINVAL;
+ }
+
+ down(µcode_sem);
+
+ user_buffer = (void __user *) buf;
+ user_buffer_size = (int) len;
+
+ ret = do_microcode_update();
+ if (!ret)
+ ret = (ssize_t)len;
+
+ up(µcode_sem);
+
+ return ret;
+}
+
+static int microcode_ioctl (struct inode *inode, struct file *file,
+ unsigned int cmd, unsigned long arg)
+{
+ switch (cmd) {
+ /*
+ * XXX: will be removed after microcode_ctl
+ * is updated to ignore failure of this ioctl()
+ */
+ case MICROCODE_IOCFREE:
+ return 0;
+ default:
+ return -EINVAL;
+ }
+ return -EINVAL;
+}
+
+static struct file_operations microcode_fops = {
+ .owner = THIS_MODULE,
+ .write = microcode_write,
+ .ioctl = microcode_ioctl,
+ .open = microcode_open,
+};
+
+static struct miscdevice microcode_dev = {
+ .minor = MICROCODE_MINOR,
+ .name = "microcode",
+ .devfs_name = "cpu/microcode",
+ .fops = µcode_fops,
+};
+
+static int __init microcode_init (void)
+{
+ int error;
+
+ error = misc_register(µcode_dev);
+ if (error) {
+ printk(KERN_ERR
+ "microcode: can't misc_register on minor=%d\n",
+ MICROCODE_MINOR);
+ return error;
+ }
+
+ printk(KERN_INFO
+ "IA-32 Microcode Update Driver: v" MICROCODE_VERSION "
<tigran@xxxxxxxxxxx>\n");
+ return 0;
+}
+
+static void __exit microcode_exit (void)
+{
+ misc_deregister(µcode_dev);
+ printk(KERN_INFO "IA-32 Microcode Update Driver v" MICROCODE_VERSION "
unregistered\n");
+}
+
+module_init(microcode_init)
+module_exit(microcode_exit)
+MODULE_ALIAS_MISCDEV(MICROCODE_MINOR);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/highmem.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/highmem.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,82 @@
+/*
+ * highmem.h: virtual kernel memory mappings for high memory
+ *
+ * Used in CONFIG_HIGHMEM systems for memory pages which
+ * are not addressable by direct kernel virtual addresses.
+ *
+ * Copyright (C) 1999 Gerhard Wichert, Siemens AG
+ * Gerhard.Wichert@xxxxxxxxxxxxxx
+ *
+ *
+ * Redesigned the x86 32-bit VM architecture to deal with
+ * up to 16 Terabyte physical memory. With current x86 CPUs
+ * we now support up to 64 Gigabytes physical RAM.
+ *
+ * Copyright (C) 1999 Ingo Molnar <mingo@xxxxxxxxxx>
+ */
+
+#ifndef _ASM_HIGHMEM_H
+#define _ASM_HIGHMEM_H
+
+#ifdef __KERNEL__
+
+#include <linux/config.h>
+#include <linux/interrupt.h>
+#include <linux/threads.h>
+#include <asm/kmap_types.h>
+#include <asm/tlbflush.h>
+
+/* declarations for highmem.c */
+extern unsigned long highstart_pfn, highend_pfn;
+
+extern pte_t *kmap_pte;
+extern pgprot_t kmap_prot;
+extern pte_t *pkmap_page_table;
+
+extern void kmap_init(void);
+
+/*
+ * Right now we initialize only a single pte table. It can be extended
+ * easily, subsequent pte tables have to be allocated in one physical
+ * chunk of RAM.
+ */
+#ifdef CONFIG_X86_PAE
+#define LAST_PKMAP 512
+#else
+#define LAST_PKMAP 1024
+#endif
+/*
+ * Ordering is:
+ *
+ * FIXADDR_TOP
+ * fixed_addresses
+ * FIXADDR_START
+ * temp fixed addresses
+ * FIXADDR_BOOT_START
+ * Persistent kmap area
+ * PKMAP_BASE
+ * VMALLOC_END
+ * Vmalloc area
+ * VMALLOC_START
+ * high_memory
+ */
+#define PKMAP_BASE ( (FIXADDR_BOOT_START - PAGE_SIZE*(LAST_PKMAP + 1)) &
PMD_MASK )
+#define LAST_PKMAP_MASK (LAST_PKMAP-1)
+#define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT)
+#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT))
+
+extern void * FASTCALL(kmap_high(struct page *page));
+extern void FASTCALL(kunmap_high(struct page *page));
+
+void *kmap(struct page *page);
+void kunmap(struct page *page);
+void *kmap_atomic(struct page *page, enum km_type type);
+void *kmap_atomic_pte(struct page *page, enum km_type type);
+void kunmap_atomic(void *kvaddr, enum km_type type);
+struct page *kmap_atomic_to_page(void *ptr);
+
+#define flush_cache_kmaps() do { } while (0)
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_HIGHMEM_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/smp.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/smp.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,411 @@
+/*
+ * Intel SMP support routines.
+ *
+ * (c) 1995 Alan Cox, Building #3 <alan@xxxxxxxxxx>
+ * (c) 1998-99, 2000 Ingo Molnar <mingo@xxxxxxxxxx>
+ * (c) 2002,2003 Andi Kleen, SuSE Labs.
+ *
+ * This code is released under the GNU General Public License version 2 or
+ * later.
+ */
+
+#include <linux/init.h>
+
+#include <linux/mm.h>
+#include <linux/irq.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/smp_lock.h>
+#include <linux/smp.h>
+#include <linux/kernel_stat.h>
+#include <linux/mc146818rtc.h>
+#include <linux/interrupt.h>
+
+#include <asm/mtrr.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/mach_apic.h>
+#include <asm/proto.h>
+
+/*
+ * Smarter SMP flushing macros.
+ * c/o Linus Torvalds.
+ *
+ * These mean you can really definitely utterly forget about
+ * writing to user space from interrupts. (Its not allowed anyway).
+ *
+ * Optimizations Manfred Spraul <manfred@xxxxxxxxxxxxxxxx>
+ */
+
+static cpumask_t flush_cpumask;
+static struct mm_struct * flush_mm;
+static unsigned long flush_va;
+static DEFINE_SPINLOCK(tlbstate_lock);
+#define FLUSH_ALL 0xffffffff
+
+/*
+ * We cannot call mmdrop() because we are in interrupt context,
+ * instead update mm->cpu_vm_mask.
+ */
+static inline void leave_mm (unsigned long cpu)
+{
+ if (read_pda(mmu_state) == TLBSTATE_OK)
+ BUG();
+ clear_bit(cpu, &read_pda(active_mm)->cpu_vm_mask);
+ __flush_tlb();
+}
+
+/*
+ *
+ * The flush IPI assumes that a thread switch happens in this order:
+ * [cpu0: the cpu that switches]
+ * 1) switch_mm() either 1a) or 1b)
+ * 1a) thread switch to a different mm
+ * 1a1) clear_bit(cpu, &old_mm->cpu_vm_mask);
+ * Stop ipi delivery for the old mm. This is not synchronized with
+ * the other cpus, but smp_invalidate_interrupt ignore flush ipis
+ * for the wrong mm, and in the worst case we perform a superfluous
+ * tlb flush.
+ * 1a2) set cpu mmu_state to TLBSTATE_OK
+ * Now the smp_invalidate_interrupt won't call leave_mm if cpu0
+ * was in lazy tlb mode.
+ * 1a3) update cpu active_mm
+ * Now cpu0 accepts tlb flushes for the new mm.
+ * 1a4) set_bit(cpu, &new_mm->cpu_vm_mask);
+ * Now the other cpus will send tlb flush ipis.
+ * 1a4) change cr3.
+ * 1b) thread switch without mm change
+ * cpu active_mm is correct, cpu0 already handles
+ * flush ipis.
+ * 1b1) set cpu mmu_state to TLBSTATE_OK
+ * 1b2) test_and_set the cpu bit in cpu_vm_mask.
+ * Atomically set the bit [other cpus will start sending flush ipis],
+ * and test the bit.
+ * 1b3) if the bit was 0: leave_mm was called, flush the tlb.
+ * 2) switch %%esp, ie current
+ *
+ * The interrupt must handle 2 special cases:
+ * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm.
+ * - the cpu performs speculative tlb reads, i.e. even if the cpu only
+ * runs in kernel space, the cpu could load tlb entries for user space
+ * pages.
+ *
+ * The good news is that cpu mmu_state is local to each cpu, no
+ * write/read ordering problems.
+ */
+
+/*
+ * TLB flush IPI:
+ *
+ * 1) Flush the tlb entries if the cpu uses the mm that's being flushed.
+ * 2) Leave the mm if we are in the lazy tlb mode.
+ */
+
+asmlinkage void smp_invalidate_interrupt (void)
+{
+ unsigned long cpu;
+
+ cpu = get_cpu();
+
+ if (!cpu_isset(cpu, flush_cpumask))
+ goto out;
+ /*
+ * This was a BUG() but until someone can quote me the
+ * line from the intel manual that guarantees an IPI to
+ * multiple CPUs is retried _only_ on the erroring CPUs
+ * its staying as a return
+ *
+ * BUG();
+ */
+
+ if (flush_mm == read_pda(active_mm)) {
+ if (read_pda(mmu_state) == TLBSTATE_OK) {
+ if (flush_va == FLUSH_ALL)
+ local_flush_tlb();
+ else
+ __flush_tlb_one(flush_va);
+ } else
+ leave_mm(cpu);
+ }
+ ack_APIC_irq();
+ cpu_clear(cpu, flush_cpumask);
+
+out:
+ put_cpu_no_resched();
+}
+
+static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
+ unsigned long va)
+{
+ cpumask_t tmp;
+ /*
+ * A couple of (to be removed) sanity checks:
+ *
+ * - we do not send IPIs to not-yet booted CPUs.
+ * - current CPU must not be in mask
+ * - mask must exist :)
+ */
+ BUG_ON(cpus_empty(cpumask));
+ cpus_and(tmp, cpumask, cpu_online_map);
+ BUG_ON(!cpus_equal(tmp, cpumask));
+ BUG_ON(cpu_isset(smp_processor_id(), cpumask));
+ if (!mm)
+ BUG();
+
+ /*
+ * I'm not happy about this global shared spinlock in the
+ * MM hot path, but we'll see how contended it is.
+ * Temporarily this turns IRQs off, so that lockups are
+ * detected by the NMI watchdog.
+ */
+ spin_lock(&tlbstate_lock);
+
+ flush_mm = mm;
+ flush_va = va;
+ cpus_or(flush_cpumask, cpumask, flush_cpumask);
+
+ /*
+ * We have to send the IPI only to
+ * CPUs affected.
+ */
+ send_IPI_mask(cpumask, INVALIDATE_TLB_VECTOR);
+
+ while (!cpus_empty(flush_cpumask))
+ mb(); /* nothing. lockup detection does not belong here */;
+
+ flush_mm = NULL;
+ flush_va = 0;
+ spin_unlock(&tlbstate_lock);
+}
+
+void flush_tlb_current_task(void)
+{
+ struct mm_struct *mm = current->mm;
+ cpumask_t cpu_mask;
+
+ preempt_disable();
+ cpu_mask = mm->cpu_vm_mask;
+ cpu_clear(smp_processor_id(), cpu_mask);
+
+ local_flush_tlb();
+ if (!cpus_empty(cpu_mask))
+ flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
+ preempt_enable();
+}
+
+void flush_tlb_mm (struct mm_struct * mm)
+{
+ cpumask_t cpu_mask;
+
+ preempt_disable();
+ cpu_mask = mm->cpu_vm_mask;
+ cpu_clear(smp_processor_id(), cpu_mask);
+
+ if (current->active_mm == mm) {
+ if (current->mm)
+ local_flush_tlb();
+ else
+ leave_mm(smp_processor_id());
+ }
+ if (!cpus_empty(cpu_mask))
+ flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
+
+ preempt_enable();
+}
+
+void flush_tlb_page(struct vm_area_struct * vma, unsigned long va)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ cpumask_t cpu_mask;
+
+ preempt_disable();
+ cpu_mask = mm->cpu_vm_mask;
+ cpu_clear(smp_processor_id(), cpu_mask);
+
+ if (current->active_mm == mm) {
+ if(current->mm)
+ __flush_tlb_one(va);
+ else
+ leave_mm(smp_processor_id());
+ }
+
+ if (!cpus_empty(cpu_mask))
+ flush_tlb_others(cpu_mask, mm, va);
+
+ preempt_enable();
+}
+
+static void do_flush_tlb_all(void* info)
+{
+ unsigned long cpu = smp_processor_id();
+
+ __flush_tlb_all();
+ if (read_pda(mmu_state) == TLBSTATE_LAZY)
+ leave_mm(cpu);
+}
+
+void flush_tlb_all(void)
+{
+ on_each_cpu(do_flush_tlb_all, NULL, 1, 1);
+}
+
+void smp_kdb_stop(void)
+{
+ send_IPI_allbutself(KDB_VECTOR);
+}
+
+/*
+ * this function sends a 'reschedule' IPI to another CPU.
+ * it goes straight through and wastes no time serializing
+ * anything. Worst case is that we lose a reschedule ...
+ */
+
+void smp_send_reschedule(int cpu)
+{
+ send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR);
+}
+
+/*
+ * Structure and data for smp_call_function(). This is designed to minimise
+ * static memory requirements. It also looks cleaner.
+ */
+static DEFINE_SPINLOCK(call_lock);
+
+struct call_data_struct {
+ void (*func) (void *info);
+ void *info;
+ atomic_t started;
+ atomic_t finished;
+ int wait;
+};
+
+static struct call_data_struct * call_data;
+
+/*
+ * this function sends a 'generic call function' IPI to all other CPUs
+ * in the system.
+ */
+static void __smp_call_function (void (*func) (void *info), void *info,
+ int nonatomic, int wait)
+{
+ struct call_data_struct data;
+ int cpus = num_online_cpus()-1;
+
+ if (!cpus)
+ return;
+
+ data.func = func;
+ data.info = info;
+ atomic_set(&data.started, 0);
+ data.wait = wait;
+ if (wait)
+ atomic_set(&data.finished, 0);
+
+ call_data = &data;
+ wmb();
+ /* Send a message to all other CPUs and wait for them to respond */
+ send_IPI_allbutself(CALL_FUNCTION_VECTOR);
+
+ /* Wait for response */
+ while (atomic_read(&data.started) != cpus)
+ cpu_relax();
+
+ if (!wait)
+ return;
+
+ while (atomic_read(&data.finished) != cpus)
+ cpu_relax();
+}
+
+/*
+ * smp_call_function - run a function on all other CPUs.
+ * @func: The function to run. This must be fast and non-blocking.
+ * @info: An arbitrary pointer to pass to the function.
+ * @nonatomic: currently unused.
+ * @wait: If true, wait (atomically) until function has completed on other
+ * CPUs.
+ *
+ * Returns 0 on success, else a negative status code. Does not return until
+ * remote CPUs are nearly ready to execute func or are or have executed.
+ *
+ * You must not call this function with disabled interrupts or from a
+ * hardware interrupt handler or from a bottom half handler.
+ * Actually there are a few legal cases, like panic.
+ */
+int smp_call_function (void (*func) (void *info), void *info, int nonatomic,
+ int wait)
+{
+ spin_lock(&call_lock);
+ __smp_call_function(func,info,nonatomic,wait);
+ spin_unlock(&call_lock);
+ return 0;
+}
+
+void smp_stop_cpu(void)
+{
+ /*
+ * Remove this CPU:
+ */
+ cpu_clear(smp_processor_id(), cpu_online_map);
+ local_irq_disable();
+ disable_local_APIC();
+ local_irq_enable();
+}
+
+static void smp_really_stop_cpu(void *dummy)
+{
+ smp_stop_cpu();
+ for (;;)
+ asm("hlt");
+}
+
+void smp_send_stop(void)
+{
+ int nolock = 0;
+ if (reboot_force)
+ return;
+ /* Don't deadlock on the call lock in panic */
+ if (!spin_trylock(&call_lock)) {
+ /* ignore locking because we have paniced anyways */
+ nolock = 1;
+ }
+ __smp_call_function(smp_really_stop_cpu, NULL, 0, 0);
+ if (!nolock)
+ spin_unlock(&call_lock);
+ smp_stop_cpu();
+}
+
+/*
+ * Reschedule call back. Nothing to do,
+ * all the work is done automatically when
+ * we return from the interrupt.
+ */
+asmlinkage void smp_reschedule_interrupt(void)
+{
+ ack_APIC_irq();
+}
+
+asmlinkage void smp_call_function_interrupt(void)
+{
+ void (*func) (void *info) = call_data->func;
+ void *info = call_data->info;
+ int wait = call_data->wait;
+
+ ack_APIC_irq();
+ /*
+ * Notify initiating CPU that I've grabbed the data and am
+ * about to execute the function
+ */
+ mb();
+ atomic_inc(&call_data->started);
+ /*
+ * At this point the info structure may be out of scope unless wait==1
+ */
+ irq_enter();
+ (*func)(info);
+ irq_exit();
+ if (wait) {
+ mb();
+ atomic_inc(&call_data->finished);
+ }
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/usbback/usbback.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/usbback/usbback.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,1066 @@
+/******************************************************************************
+ * arch/xen/drivers/usbif/backend/main.c
+ *
+ * Backend for the Xen virtual USB driver - provides an abstraction of a
+ * USB host controller to the corresponding frontend driver.
+ *
+ * by Mark Williamson
+ * Copyright (c) 2004 Intel Research Cambridge
+ * Copyright (c) 2004, 2005 Mark Williamson
+ *
+ * Based on arch/xen/drivers/blkif/backend/main.c
+ * Copyright (c) 2003-2004, Keir Fraser & Steve Hand
+ */
+
+#include "common.h"
+
+
+#include <linux/list.h>
+#include <linux/usb.h>
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/tqueue.h>
+
+/*
+ * This is rather arbitrary.
+ */
+#define MAX_PENDING_REQS 4
+#define BATCH_PER_DOMAIN 1
+
+static unsigned long mmap_vstart;
+
+/* Needs to be sufficiently large that we can map the (large) buffers
+ * the USB mass storage driver wants. */
+#define MMAP_PAGES_PER_REQUEST \
+ (128)
+#define MMAP_PAGES \
+ (MAX_PENDING_REQS * MMAP_PAGES_PER_REQUEST)
+
+#define MMAP_VADDR(_req,_seg) \
+ (mmap_vstart + \
+ ((_req) * MMAP_PAGES_PER_REQUEST * PAGE_SIZE) + \
+ ((_seg) * PAGE_SIZE))
+
+
+static spinlock_t owned_ports_lock;
+LIST_HEAD(owned_ports);
+
+/* A list of these structures is used to track ownership of physical USB
+ * ports. */
+typedef struct
+{
+ usbif_priv_t *usbif_priv;
+ char path[16];
+ int guest_port;
+ int enabled;
+ struct list_head list;
+ unsigned long guest_address; /* The USB device address that has been
+ * assigned by the guest. */
+ int dev_present; /* Is there a device present? */
+ struct usb_device * dev;
+ unsigned long ifaces; /* What interfaces are present on this device? */
+} owned_port_t;
+
+
+/*
+ * Each outstanding request that we've passed to the lower device layers has a
+ * 'pending_req' allocated to it. The request is complete, the specified
+ * domain has a response queued for it, with the saved 'id' passed back.
+ */
+typedef struct {
+ usbif_priv_t *usbif_priv;
+ unsigned long id;
+ int nr_pages;
+ unsigned short operation;
+ int status;
+} pending_req_t;
+
+/*
+ * We can't allocate pending_req's in order, since they may complete out of
+ * order. We therefore maintain an allocation ring. This ring also indicates
+ * when enough work has been passed down -- at that point the allocation ring
+ * will be empty.
+ */
+static pending_req_t pending_reqs[MAX_PENDING_REQS];
+static unsigned char pending_ring[MAX_PENDING_REQS];
+static spinlock_t pend_prod_lock;
+
+/* NB. We use a different index type to differentiate from shared usb rings. */
+typedef unsigned int PEND_RING_IDX;
+#define MASK_PEND_IDX(_i) ((_i)&(MAX_PENDING_REQS-1))
+static PEND_RING_IDX pending_prod, pending_cons;
+#define NR_PENDING_REQS (MAX_PENDING_REQS - pending_prod + pending_cons)
+
+static int do_usb_io_op(usbif_priv_t *usbif, int max_to_do);
+static void make_response(usbif_priv_t *usbif, unsigned long id,
+ unsigned short op, int st, int inband,
+ unsigned long actual_length);
+static void dispatch_usb_probe(usbif_priv_t *up, unsigned long id, unsigned
long port);
+static void dispatch_usb_io(usbif_priv_t *up, usbif_request_t *req);
+static void dispatch_usb_reset(usbif_priv_t *up, unsigned long portid);
+static owned_port_t *usbif_find_port(char *);
+
+/******************************************************************
+ * PRIVATE DEBUG FUNCTIONS
+ */
+
+#undef DEBUG
+#ifdef DEBUG
+
+static void dump_port(owned_port_t *p)
+{
+ printk(KERN_DEBUG "owned_port_t @ %p\n"
+ " usbif_priv @ %p\n"
+ " path: %s\n"
+ " guest_port: %d\n"
+ " guest_address: %ld\n"
+ " dev_present: %d\n"
+ " dev @ %p\n"
+ " ifaces: 0x%lx\n",
+ p, p->usbif_priv, p->path, p->guest_port, p->guest_address,
+ p->dev_present, p->dev, p->ifaces);
+}
+
+
+static void dump_request(usbif_request_t *req)
+{
+ printk(KERN_DEBUG "id = 0x%lx\n"
+ "devnum %d\n"
+ "endpoint 0x%x\n"
+ "direction %d\n"
+ "speed %d\n"
+ "pipe_type 0x%x\n"
+ "transfer_buffer 0x%lx\n"
+ "length 0x%lx\n"
+ "transfer_flags 0x%lx\n"
+ "setup = { 0x%x, 0x%x, 0x%x, 0x%x, 0x%x, 0x%x, 0x%x, 0x%x }\n"
+ "iso_schedule = 0x%lx\n"
+ "num_iso %ld\n",
+ req->id, req->devnum, req->endpoint, req->direction, req->speed,
+ req->pipe_type, req->transfer_buffer, req->length,
+ req->transfer_flags, req->setup[0], req->setup[1], req->setup[2],
+ req->setup[3], req->setup[4], req->setup[5], req->setup[6],
+ req->setup[7], req->iso_schedule, req->num_iso);
+}
+
+static void dump_urb(struct urb *urb)
+{
+ printk(KERN_DEBUG "dumping urb @ %p\n", urb);
+
+#define DUMP_URB_FIELD(name, format) \
+ printk(KERN_DEBUG " " # name " " format "\n", urb-> name)
+
+ DUMP_URB_FIELD(pipe, "0x%x");
+ DUMP_URB_FIELD(status, "%d");
+ DUMP_URB_FIELD(transfer_flags, "0x%x");
+ DUMP_URB_FIELD(transfer_buffer, "%p");
+ DUMP_URB_FIELD(transfer_buffer_length, "%d");
+ DUMP_URB_FIELD(actual_length, "%d");
+}
+
+static void dump_response(usbif_response_t *resp)
+{
+ printk(KERN_DEBUG "usbback: Sending response:\n"
+ " id = 0x%x\n"
+ " op = %d\n"
+ " status = %d\n"
+ " data = %d\n"
+ " length = %d\n",
+ resp->id, resp->op, resp->status, resp->data, resp->length);
+}
+
+#else /* DEBUG */
+
+#define dump_port(blah) ((void)0)
+#define dump_request(blah) ((void)0)
+#define dump_urb(blah) ((void)0)
+#define dump_response(blah) ((void)0)
+
+#endif /* DEBUG */
+
+/******************************************************************
+ * MEMORY MANAGEMENT
+ */
+
+static void fast_flush_area(int idx, int nr_pages)
+{
+ multicall_entry_t mcl[MMAP_PAGES_PER_REQUEST];
+ int i;
+
+ for ( i = 0; i < nr_pages; i++ )
+ {
+ MULTI_update_va_mapping(mcl+i, MMAP_VADDR(idx, i),
+ __pte(0), 0);
+ }
+
+ mcl[nr_pages-1].args[2] = UVMF_TLB_FLUSH|UVMF_ALL;
+ if ( unlikely(HYPERVISOR_multicall(mcl, nr_pages) != 0) )
+ BUG();
+}
+
+
+/******************************************************************
+ * USB INTERFACE SCHEDULER LIST MAINTENANCE
+ */
+
+static struct list_head usbio_schedule_list;
+static spinlock_t usbio_schedule_list_lock;
+
+static int __on_usbif_list(usbif_priv_t *up)
+{
+ return up->usbif_list.next != NULL;
+}
+
+void remove_from_usbif_list(usbif_priv_t *up)
+{
+ unsigned long flags;
+ if ( !__on_usbif_list(up) ) return;
+ spin_lock_irqsave(&usbio_schedule_list_lock, flags);
+ if ( __on_usbif_list(up) )
+ {
+ list_del(&up->usbif_list);
+ up->usbif_list.next = NULL;
+ usbif_put(up);
+ }
+ spin_unlock_irqrestore(&usbio_schedule_list_lock, flags);
+}
+
+static void add_to_usbif_list_tail(usbif_priv_t *up)
+{
+ unsigned long flags;
+ if ( __on_usbif_list(up) ) return;
+ spin_lock_irqsave(&usbio_schedule_list_lock, flags);
+ if ( !__on_usbif_list(up) && (up->status == CONNECTED) )
+ {
+ list_add_tail(&up->usbif_list, &usbio_schedule_list);
+ usbif_get(up);
+ }
+ spin_unlock_irqrestore(&usbio_schedule_list_lock, flags);
+}
+
+void free_pending(int pending_idx)
+{
+ unsigned long flags;
+
+ /* Free the pending request. */
+ spin_lock_irqsave(&pend_prod_lock, flags);
+ pending_ring[MASK_PEND_IDX(pending_prod++)] = pending_idx;
+ spin_unlock_irqrestore(&pend_prod_lock, flags);
+}
+
+/******************************************************************
+ * COMPLETION CALLBACK -- Called as urb->complete()
+ */
+
+static void maybe_trigger_usbio_schedule(void);
+
+static void __end_usb_io_op(struct urb *purb)
+{
+ pending_req_t *pending_req;
+ int pending_idx;
+
+ pending_req = purb->context;
+
+ pending_idx = pending_req - pending_reqs;
+
+ ASSERT(purb->actual_length <= purb->transfer_buffer_length);
+ ASSERT(purb->actual_length <= pending_req->nr_pages * PAGE_SIZE);
+
+ /* An error fails the entire request. */
+ if ( purb->status )
+ {
+ printk(KERN_WARNING "URB @ %p failed. Status %d\n", purb,
purb->status);
+ }
+
+ if ( usb_pipetype(purb->pipe) == 0 )
+ {
+ int i;
+ usbif_iso_t *sched = (usbif_iso_t *)MMAP_VADDR(pending_idx,
pending_req->nr_pages - 1);
+
+ /* If we're dealing with an iso pipe, we need to copy back the
schedule. */
+ for ( i = 0; i < purb->number_of_packets; i++ )
+ {
+ sched[i].length = purb->iso_frame_desc[i].actual_length;
+ ASSERT(sched[i].buffer_offset ==
+ purb->iso_frame_desc[i].offset);
+ sched[i].status = purb->iso_frame_desc[i].status;
+ }
+ }
+
+ fast_flush_area(pending_req - pending_reqs, pending_req->nr_pages);
+
+ kfree(purb->setup_packet);
+
+ make_response(pending_req->usbif_priv, pending_req->id,
+ pending_req->operation, pending_req->status, 0,
purb->actual_length);
+ usbif_put(pending_req->usbif_priv);
+
+ usb_free_urb(purb);
+
+ free_pending(pending_idx);
+
+ rmb();
+
+ /* Check for anything still waiting in the rings, having freed a
request... */
+ maybe_trigger_usbio_schedule();
+}
+
+/******************************************************************
+ * SCHEDULER FUNCTIONS
+ */
+
+static DECLARE_WAIT_QUEUE_HEAD(usbio_schedule_wait);
+
+static int usbio_schedule(void *arg)
+{
+ DECLARE_WAITQUEUE(wq, current);
+
+ usbif_priv_t *up;
+ struct list_head *ent;
+
+ daemonize();
+
+ for ( ; ; )
+ {
+ /* Wait for work to do. */
+ add_wait_queue(&usbio_schedule_wait, &wq);
+ set_current_state(TASK_INTERRUPTIBLE);
+ if ( (NR_PENDING_REQS == MAX_PENDING_REQS) ||
+ list_empty(&usbio_schedule_list) )
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ remove_wait_queue(&usbio_schedule_wait, &wq);
+
+ /* Queue up a batch of requests. */
+ while ( (NR_PENDING_REQS < MAX_PENDING_REQS) &&
+ !list_empty(&usbio_schedule_list) )
+ {
+ ent = usbio_schedule_list.next;
+ up = list_entry(ent, usbif_priv_t, usbif_list);
+ usbif_get(up);
+ remove_from_usbif_list(up);
+ if ( do_usb_io_op(up, BATCH_PER_DOMAIN) )
+ add_to_usbif_list_tail(up);
+ usbif_put(up);
+ }
+ }
+}
+
+static void maybe_trigger_usbio_schedule(void)
+{
+ /*
+ * Needed so that two processes, who together make the following predicate
+ * true, don't both read stale values and evaluate the predicate
+ * incorrectly. Incredibly unlikely to stall the scheduler on x86, but...
+ */
+ smp_mb();
+
+ if ( !list_empty(&usbio_schedule_list) )
+ wake_up(&usbio_schedule_wait);
+}
+
+
+/******************************************************************************
+ * NOTIFICATION FROM GUEST OS.
+ */
+
+irqreturn_t usbif_be_int(int irq, void *dev_id, struct pt_regs *regs)
+{
+ usbif_priv_t *up = dev_id;
+
+ smp_mb();
+
+ add_to_usbif_list_tail(up);
+
+ /* Will in fact /always/ trigger an io schedule in this case. */
+ maybe_trigger_usbio_schedule();
+
+ return IRQ_HANDLED;
+}
+
+
+
+/******************************************************************
+ * DOWNWARD CALLS -- These interface with the usb-device layer proper.
+ */
+
+static int do_usb_io_op(usbif_priv_t *up, int max_to_do)
+{
+ usbif_back_ring_t *usb_ring = &up->usb_ring;
+ usbif_request_t *req;
+ RING_IDX i, rp;
+ int more_to_do = 0;
+
+ rp = usb_ring->sring->req_prod;
+ rmb(); /* Ensure we see queued requests up to 'rp'. */
+
+ /* Take items off the comms ring, taking care not to overflow. */
+ for ( i = usb_ring->req_cons;
+ (i != rp) && !RING_REQUEST_CONS_OVERFLOW(usb_ring, i);
+ i++ )
+ {
+ if ( (max_to_do-- == 0) || (NR_PENDING_REQS == MAX_PENDING_REQS) )
+ {
+ more_to_do = 1;
+ break;
+ }
+
+ req = RING_GET_REQUEST(usb_ring, i);
+
+ switch ( req->operation )
+ {
+ case USBIF_OP_PROBE:
+ dispatch_usb_probe(up, req->id, req->port);
+ break;
+
+ case USBIF_OP_IO:
+ /* Assemble an appropriate URB. */
+ dispatch_usb_io(up, req);
+ break;
+
+ case USBIF_OP_RESET:
+ dispatch_usb_reset(up, req->port);
+ break;
+
+ default:
+ DPRINTK("error: unknown USB io operation [%d]\n",
+ req->operation);
+ make_response(up, req->id, req->operation, -EINVAL, 0, 0);
+ break;
+ }
+ }
+
+ usb_ring->req_cons = i;
+
+ return more_to_do;
+}
+
+static owned_port_t *find_guest_port(usbif_priv_t *up, int port)
+{
+ unsigned long flags;
+ struct list_head *l;
+
+ spin_lock_irqsave(&owned_ports_lock, flags);
+ list_for_each(l, &owned_ports)
+ {
+ owned_port_t *p = list_entry(l, owned_port_t, list);
+ if(p->usbif_priv == up && p->guest_port == port)
+ {
+ spin_unlock_irqrestore(&owned_ports_lock, flags);
+ return p;
+ }
+ }
+ spin_unlock_irqrestore(&owned_ports_lock, flags);
+
+ return NULL;
+}
+
+static void dispatch_usb_reset(usbif_priv_t *up, unsigned long portid)
+{
+ owned_port_t *port = find_guest_port(up, portid);
+ int ret = 0;
+
+
+ /* Allowing the guest to actually reset the device causes more problems
+ * than it's worth. We just fake it out in software but we will do a real
+ * reset when the interface is destroyed. */
+
+ dump_port(port);
+
+ port->guest_address = 0;
+ /* If there's an attached device then the port is now enabled. */
+ if ( port->dev_present )
+ port->enabled = 1;
+ else
+ port->enabled = 0;
+
+ make_response(up, 0, USBIF_OP_RESET, ret, 0, 0);
+}
+
+static void dispatch_usb_probe(usbif_priv_t *up, unsigned long id, unsigned
long portid)
+{
+ owned_port_t *port = find_guest_port(up, portid);
+ int ret;
+
+ if ( port != NULL )
+ ret = port->dev_present;
+ else
+ {
+ ret = -EINVAL;
+ printk(KERN_INFO "dispatch_usb_probe(): invalid port probe request "
+ "(port %ld)\n", portid);
+ }
+
+ /* Probe result is sent back in-band. Probes don't have an associated id
+ * right now... */
+ make_response(up, id, USBIF_OP_PROBE, ret, portid, 0);
+}
+
+/**
+ * check_iso_schedule - safety check the isochronous schedule for an URB
+ * @purb : the URB in question
+ */
+static int check_iso_schedule(struct urb *purb)
+{
+ int i;
+ unsigned long total_length = 0;
+
+ for ( i = 0; i < purb->number_of_packets; i++ )
+ {
+ struct usb_iso_packet_descriptor *desc = &purb->iso_frame_desc[i];
+
+ if ( desc->offset >= purb->transfer_buffer_length
+ || ( desc->offset + desc->length) > purb->transfer_buffer_length )
+ return -EINVAL;
+
+ total_length += desc->length;
+
+ if ( total_length > purb->transfer_buffer_length )
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+owned_port_t *find_port_for_request(usbif_priv_t *up, usbif_request_t *req);
+
+static void dispatch_usb_io(usbif_priv_t *up, usbif_request_t *req)
+{
+ unsigned long buffer_mach;
+ int i = 0, offset = 0,
+ pending_idx = pending_ring[MASK_PEND_IDX(pending_cons)];
+ pending_req_t *pending_req;
+ unsigned long remap_prot;
+ multicall_entry_t mcl[MMAP_PAGES_PER_REQUEST];
+ struct urb *purb = NULL;
+ owned_port_t *port;
+ unsigned char *setup;
+
+ dump_request(req);
+
+ if ( NR_PENDING_REQS == MAX_PENDING_REQS )
+ {
+ printk(KERN_WARNING "usbback: Max requests already queued. "
+ "Giving up!\n");
+
+ return;
+ }
+
+ port = find_port_for_request(up, req);
+
+ if ( port == NULL )
+ {
+ printk(KERN_WARNING "No such device! (%d)\n", req->devnum);
+ dump_request(req);
+
+ make_response(up, req->id, req->operation, -ENODEV, 0, 0);
+ return;
+ }
+ else if ( !port->dev_present )
+ {
+ /* In normal operation, we'll only get here if a device is unplugged
+ * and the frontend hasn't noticed yet. */
+ make_response(up, req->id, req->operation, -ENODEV, 0, 0);
+ return;
+ }
+
+
+ setup = kmalloc(8, GFP_KERNEL);
+
+ if ( setup == NULL )
+ goto no_mem;
+
+ /* Copy request out for safety. */
+ memcpy(setup, req->setup, 8);
+
+ if( setup[0] == 0x0 && setup[1] == 0x5)
+ {
+ /* To virtualise the USB address space, we need to intercept
+ * set_address messages and emulate. From the USB specification:
+ * bmRequestType = 0x0;
+ * Brequest = SET_ADDRESS (i.e. 0x5)
+ * wValue = device address
+ * wIndex = 0
+ * wLength = 0
+ * data = None
+ */
+ /* Store into the guest transfer buffer using cpu_to_le16 */
+ port->guest_address = le16_to_cpu(*(u16 *)(setup + 2));
+ /* Make a successful response. That was easy! */
+
+ make_response(up, req->id, req->operation, 0, 0, 0);
+
+ kfree(setup);
+ return;
+ }
+ else if ( setup[0] == 0x0 && setup[1] == 0x9 )
+ {
+ /* The host kernel needs to know what device configuration is in use
+ * because various error checks get confused otherwise. We just do
+ * configuration settings here, under controlled conditions.
+ */
+
+ /* Ignore configuration setting and hope that the host kernel
+ did it right. */
+ /* usb_set_configuration(port->dev, setup[2]); */
+
+ make_response(up, req->id, req->operation, 0, 0, 0);
+
+ kfree(setup);
+ return;
+ }
+ else if ( setup[0] == 0x1 && setup[1] == 0xB )
+ {
+ /* The host kernel needs to know what device interface is in use
+ * because various error checks get confused otherwise. We just do
+ * configuration settings here, under controlled conditions.
+ */
+ usb_set_interface(port->dev, (setup[4] | setup[5] << 8),
+ (setup[2] | setup[3] << 8) );
+
+ make_response(up, req->id, req->operation, 0, 0, 0);
+
+ kfree(setup);
+ return;
+ }
+
+ if ( ( req->transfer_buffer - (req->transfer_buffer & PAGE_MASK)
+ + req->length )
+ > MMAP_PAGES_PER_REQUEST * PAGE_SIZE )
+ {
+ printk(KERN_WARNING "usbback: request of %lu bytes too large\n",
+ req->length);
+ make_response(up, req->id, req->operation, -EINVAL, 0, 0);
+ kfree(setup);
+ return;
+ }
+
+ buffer_mach = req->transfer_buffer;
+
+ if( buffer_mach == 0 )
+ goto no_remap;
+
+ ASSERT((req->length >> PAGE_SHIFT) <= MMAP_PAGES_PER_REQUEST);
+ ASSERT(buffer_mach);
+
+ /* Always map writeable for now. */
+ remap_prot = _KERNPG_TABLE;
+
+ for ( i = 0, offset = 0; offset < req->length;
+ i++, offset += PAGE_SIZE )
+ {
+ MULTI_update_va_mapping_otherdomain(
+ mcl+i, MMAP_VADDR(pending_idx, i),
+ pfn_pte_ma(buffer_mach >> PAGE_SHIFT, remap_prot),
+ 0, up->domid);
+
+ phys_to_machine_mapping[__pa(MMAP_VADDR(pending_idx, i))>>PAGE_SHIFT] =
+ FOREIGN_FRAME((buffer_mach + offset) >> PAGE_SHIFT);
+
+ ASSERT(virt_to_machine(MMAP_VADDR(pending_idx, i))
+ == buffer_mach + i << PAGE_SHIFT);
+ }
+
+ if ( req->pipe_type == 0 && req->num_iso > 0 ) /* Maybe schedule ISO... */
+ {
+ /* Map in ISO schedule, if necessary. */
+ MULTI_update_va_mapping_otherdomain(
+ mcl+i, MMAP_VADDR(pending_idx, i),
+ pfn_pte_ma(req->iso_schedule >> PAGE_SHIFT, remap_prot),
+ 0, up->domid);
+
+ phys_to_machine_mapping[__pa(MMAP_VADDR(pending_idx, i))>>PAGE_SHIFT] =
+ FOREIGN_FRAME(req->iso_schedule >> PAGE_SHIFT);
+
+ i++;
+ }
+
+ if ( unlikely(HYPERVISOR_multicall(mcl, i) != 0) )
+ BUG();
+
+ {
+ int j;
+ for ( j = 0; j < i; j++ )
+ {
+ if ( unlikely(mcl[j].result != 0) )
+ {
+ printk(KERN_WARNING
+ "invalid buffer %d -- could not remap it\n", j);
+ fast_flush_area(pending_idx, i);
+ goto bad_descriptor;
+ }
+ }
+ }
+
+ no_remap:
+
+ ASSERT(i <= MMAP_PAGES_PER_REQUEST);
+ ASSERT(i * PAGE_SIZE >= req->length);
+
+ /* We have to do this because some things might complete out of order. */
+ pending_req = &pending_reqs[pending_idx];
+ pending_req->usbif_priv= up;
+ pending_req->id = req->id;
+ pending_req->operation = req->operation;
+ pending_req->nr_pages = i;
+
+ pending_cons++;
+
+ usbif_get(up);
+
+ /* Fill out an actual request for the USB layer. */
+ purb = usb_alloc_urb(req->num_iso);
+
+ if ( purb == NULL )
+ {
+ usbif_put(up);
+ free_pending(pending_idx);
+ goto no_mem;
+ }
+
+ purb->dev = port->dev;
+ purb->context = pending_req;
+ purb->transfer_buffer =
+ (void *)(MMAP_VADDR(pending_idx, 0) + (buffer_mach & ~PAGE_MASK));
+ if(buffer_mach == 0)
+ purb->transfer_buffer = NULL;
+ purb->complete = __end_usb_io_op;
+ purb->transfer_buffer_length = req->length;
+ purb->transfer_flags = req->transfer_flags;
+
+ purb->pipe = 0;
+ purb->pipe |= req->direction << 7;
+ purb->pipe |= port->dev->devnum << 8;
+ purb->pipe |= req->speed << 26;
+ purb->pipe |= req->pipe_type << 30;
+ purb->pipe |= req->endpoint << 15;
+
+ purb->number_of_packets = req->num_iso;
+
+ if ( purb->number_of_packets * sizeof(usbif_iso_t) > PAGE_SIZE )
+ goto urb_error;
+
+ /* Make sure there's always some kind of timeout. */
+ purb->timeout = ( req->timeout > 0 ) ? (req->timeout * HZ) / 1000
+ : 1000;
+
+ purb->setup_packet = setup;
+
+ if ( req->pipe_type == 0 ) /* ISO */
+ {
+ int j;
+ usbif_iso_t *iso_sched = (usbif_iso_t *)MMAP_VADDR(pending_idx, i - 1);
+
+ /* If we're dealing with an iso pipe, we need to copy in a schedule. */
+ for ( j = 0; j < purb->number_of_packets; j++ )
+ {
+ purb->iso_frame_desc[j].length = iso_sched[j].length;
+ purb->iso_frame_desc[j].offset = iso_sched[j].buffer_offset;
+ iso_sched[j].status = 0;
+ }
+ }
+
+ if ( check_iso_schedule(purb) != 0 )
+ goto urb_error;
+
+ if ( usb_submit_urb(purb) != 0 )
+ goto urb_error;
+
+ return;
+
+ urb_error:
+ dump_urb(purb);
+ usbif_put(up);
+ free_pending(pending_idx);
+
+ bad_descriptor:
+ kfree ( setup );
+ if ( purb != NULL )
+ usb_free_urb(purb);
+ make_response(up, req->id, req->operation, -EINVAL, 0, 0);
+ return;
+
+ no_mem:
+ if ( setup != NULL )
+ kfree(setup);
+ make_response(up, req->id, req->operation, -ENOMEM, 0, 0);
+ return;
+}
+
+
+
+/******************************************************************
+ * MISCELLANEOUS SETUP / TEARDOWN / DEBUGGING
+ */
+
+
+static void make_response(usbif_priv_t *up, unsigned long id,
+ unsigned short op, int st, int inband,
+ unsigned long length)
+{
+ usbif_response_t *resp;
+ unsigned long flags;
+ usbif_back_ring_t *usb_ring = &up->usb_ring;
+
+ /* Place on the response ring for the relevant domain. */
+ spin_lock_irqsave(&up->usb_ring_lock, flags);
+ resp = RING_GET_RESPONSE(usb_ring, usb_ring->rsp_prod_pvt);
+ resp->id = id;
+ resp->operation = op;
+ resp->status = st;
+ resp->data = inband;
+ resp->length = length;
+ wmb(); /* Ensure other side can see the response fields. */
+
+ dump_response(resp);
+
+ usb_ring->rsp_prod_pvt++;
+ RING_PUSH_RESPONSES(usb_ring);
+ spin_unlock_irqrestore(&up->usb_ring_lock, flags);
+
+ /* Kick the relevant domain. */
+ notify_via_evtchn(up->evtchn);
+}
+
+/**
+ * usbif_claim_port - claim devices on a port on behalf of guest
+ *
+ * Once completed, this will ensure that any device attached to that
+ * port is claimed by this driver for use by the guest.
+ */
+int usbif_claim_port(usbif_be_claim_port_t *msg)
+{
+ owned_port_t *o_p;
+
+ /* Sanity... */
+ if ( usbif_find_port(msg->path) != NULL )
+ {
+ printk(KERN_WARNING "usbback: Attempted to claim USB port "
+ "we already own!\n");
+ return -EINVAL;
+ }
+
+ /* No need for a slab cache - this should be infrequent. */
+ o_p = kmalloc(sizeof(owned_port_t), GFP_KERNEL);
+
+ if ( o_p == NULL )
+ return -ENOMEM;
+
+ o_p->enabled = 0;
+ o_p->usbif_priv = usbif_find(msg->domid);
+ o_p->guest_port = msg->usbif_port;
+ o_p->dev_present = 0;
+ o_p->guest_address = 0; /* Default address. */
+
+ strcpy(o_p->path, msg->path);
+
+ spin_lock_irq(&owned_ports_lock);
+
+ list_add(&o_p->list, &owned_ports);
+
+ spin_unlock_irq(&owned_ports_lock);
+
+ printk(KERN_INFO "usbback: Claimed USB port (%s) for %d.%d\n", o_p->path,
+ msg->domid, msg->usbif_port);
+
+ /* Force a reprobe for unclaimed devices. */
+ usb_scan_devices();
+
+ return 0;
+}
+
+owned_port_t *find_port_for_request(usbif_priv_t *up, usbif_request_t *req)
+{
+ unsigned long flags;
+ struct list_head *port;
+
+ /* I'm assuming this is not called from IRQ context - correct? I think
+ * it's probably only called in response to control messages or plug events
+ * in the USB hub kernel thread, so should be OK. */
+ spin_lock_irqsave(&owned_ports_lock, flags);
+ list_for_each(port, &owned_ports)
+ {
+ owned_port_t *p = list_entry(port, owned_port_t, list);
+ if(p->usbif_priv == up && p->guest_address == req->devnum &&
p->enabled )
+ {
+ dump_port(p);
+
+ spin_unlock_irqrestore(&owned_ports_lock, flags);
+ return p;
+ }
+ }
+ spin_unlock_irqrestore(&owned_ports_lock, flags);
+
+ return NULL;
+}
+
+owned_port_t *__usbif_find_port(char *path)
+{
+ struct list_head *port;
+
+ list_for_each(port, &owned_ports)
+ {
+ owned_port_t *p = list_entry(port, owned_port_t, list);
+ if(!strcmp(path, p->path))
+ {
+ return p;
+ }
+ }
+
+ return NULL;
+}
+
+owned_port_t *usbif_find_port(char *path)
+{
+ owned_port_t *ret;
+ unsigned long flags;
+
+ spin_lock_irqsave(&owned_ports_lock, flags);
+ ret = __usbif_find_port(path);
+ spin_unlock_irqrestore(&owned_ports_lock, flags);
+
+ return ret;
+}
+
+
+static void *probe(struct usb_device *dev, unsigned iface,
+ const struct usb_device_id *id)
+{
+ owned_port_t *p;
+
+ /* We don't care what the device is - if we own the port, we want it. We
+ * don't deal with device-specifics in this driver, so we don't care what
+ * the device actually is ;-) */
+ if ( ( p = usbif_find_port(dev->devpath) ) != NULL )
+ {
+ printk(KERN_INFO "usbback: claimed device attached to owned port\n");
+
+ p->dev_present = 1;
+ p->dev = dev;
+ set_bit(iface, &p->ifaces);
+
+ return p->usbif_priv;
+ }
+ else
+ printk(KERN_INFO "usbback: hotplug for non-owned port (%s),
ignoring\n",
+ dev->devpath);
+
+
+ return NULL;
+}
+
+static void disconnect(struct usb_device *dev, void *usbif)
+{
+ /* Note the device is removed so we can tell the guest when it probes. */
+ owned_port_t *port = usbif_find_port(dev->devpath);
+ port->dev_present = 0;
+ port->dev = NULL;
+ port->ifaces = 0;
+}
+
+
+struct usb_driver driver =
+{
+ .owner = THIS_MODULE,
+ .name = "Xen USB Backend",
+ .probe = probe,
+ .disconnect = disconnect,
+ .id_table = NULL,
+};
+
+/* __usbif_release_port - internal mechanics for releasing a port */
+void __usbif_release_port(owned_port_t *p)
+{
+ int i;
+
+ for ( i = 0; p->ifaces != 0; i++)
+ if ( p->ifaces & 1 << i )
+ {
+ usb_driver_release_interface(&driver, usb_ifnum_to_if(p->dev, i));
+ clear_bit(i, &p->ifaces);
+ }
+ list_del(&p->list);
+
+ /* Reset the real device. We don't simulate disconnect / probe for other
+ * drivers in this kernel because we assume the device is completely under
+ * the control of ourselves (i.e. the guest!). This should ensure that the
+ * device is in a sane state for the next customer ;-) */
+
+ /* MAW NB: we're not resetting the real device here. This looks perfectly
+ * valid to me but it causes memory corruption. We seem to get away with
not
+ * resetting for now, although it'd be nice to have this tracked down. */
+/* if ( p->dev != NULL) */
+/* usb_reset_device(p->dev); */
+
+ kfree(p);
+}
+
+
+/**
+ * usbif_release_port - stop claiming devices on a port on behalf of guest
+ */
+void usbif_release_port(usbif_be_release_port_t *msg)
+{
+ owned_port_t *p;
+
+ spin_lock_irq(&owned_ports_lock);
+ p = __usbif_find_port(msg->path);
+ __usbif_release_port(p);
+ spin_unlock_irq(&owned_ports_lock);
+}
+
+void usbif_release_ports(usbif_priv_t *up)
+{
+ struct list_head *port, *tmp;
+ unsigned long flags;
+
+ spin_lock_irqsave(&owned_ports_lock, flags);
+ list_for_each_safe(port, tmp, &owned_ports)
+ {
+ owned_port_t *p = list_entry(port, owned_port_t, list);
+ if ( p->usbif_priv == up )
+ __usbif_release_port(p);
+ }
+ spin_unlock_irqrestore(&owned_ports_lock, flags);
+}
+
+static int __init usbif_init(void)
+{
+ int i;
+
+ if ( !(xen_start_info.flags & SIF_INITDOMAIN) &&
+ !(xen_start_info.flags & SIF_USB_BE_DOMAIN) )
+ return 0;
+
+ if ( (mmap_vstart = allocate_empty_lowmem_region(MMAP_PAGES)) == 0 )
+ BUG();
+
+ pending_cons = 0;
+ pending_prod = MAX_PENDING_REQS;
+ memset(pending_reqs, 0, sizeof(pending_reqs));
+ for ( i = 0; i < MAX_PENDING_REQS; i++ )
+ pending_ring[i] = i;
+
+ spin_lock_init(&pend_prod_lock);
+
+ spin_lock_init(&owned_ports_lock);
+ INIT_LIST_HEAD(&owned_ports);
+
+ spin_lock_init(&usbio_schedule_list_lock);
+ INIT_LIST_HEAD(&usbio_schedule_list);
+
+ if ( kernel_thread(usbio_schedule, 0, CLONE_FS | CLONE_FILES) < 0 )
+ BUG();
+
+ usbif_interface_init();
+
+ usbif_ctrlif_init();
+
+ usb_register(&driver);
+
+ printk(KERN_INFO "Xen USB Backend Initialised");
+
+ return 0;
+}
+
+__initcall(usbif_init);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/xen_entry.S
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/xen_entry.S Fri Jul
15 13:39:50 2005
@@ -0,0 +1,38 @@
+/*
+ * Copied from arch/xen/i386/kernel/entry.S
+ */
+/* Offsets into shared_info_t. */
+#define evtchn_upcall_pending 0
+#define evtchn_upcall_mask 1
+
+#define sizeof_vcpu_shift 3
+
+#ifdef CONFIG_SMP
+#define preempt_disable(reg) incl threadinfo_preempt_count(reg)
+#define preempt_enable(reg) decl threadinfo_preempt_count(reg)
+#define XEN_GET_VCPU_INFO(reg) preempt_disable(%rbp) ; \
+ movq %gs:pda_cpunumber,reg ; \
+ shl $sizeof_vcpu_shift,reg ; \
+ addq HYPERVISOR_shared_info,reg
+#define XEN_PUT_VCPU_INFO(reg) preempt_enable(%rbp) ; \
+#define XEN_PUT_VCPU_INFO_fixup .byte 0xff,0xff,0xff
+#else
+#define XEN_GET_VCPU_INFO(reg) movq HYPERVISOR_shared_info,reg
+#define XEN_PUT_VCPU_INFO(reg)
+#define XEN_PUT_VCPU_INFO_fixup
+#endif
+
+#define XEN_LOCKED_BLOCK_EVENTS(reg) movb $1,evtchn_upcall_mask(reg)
+#define XEN_LOCKED_UNBLOCK_EVENTS(reg) movb $0,evtchn_upcall_mask(reg)
+#define XEN_BLOCK_EVENTS(reg) XEN_GET_VCPU_INFO(reg) ; \
+ XEN_LOCKED_BLOCK_EVENTS(reg) ; \
+ XEN_PUT_VCPU_INFO(reg)
+#define XEN_UNBLOCK_EVENTS(reg) XEN_GET_VCPU_INFO(reg)
; \
+ XEN_LOCKED_UNBLOCK_EVENTS(reg) ; \
+ XEN_PUT_VCPU_INFO(reg)
+#define XEN_TEST_PENDING(reg) testb $0xFF,evtchn_upcall_pending(reg)
+
+EVENT_MASK = (CS+4)
+VGCF_IN_SYSCALL = (1<<8)
+
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/netfront/Kconfig
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/netfront/Kconfig Fri Jul 15
13:39:50 2005
@@ -0,0 +1,6 @@
+
+config XENNET
+ tristate "Xen network driver"
+ depends on NETDEVICES && ARCH_XEN
+ help
+ Network driver for Xen
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/evtchn/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/evtchn/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,2 @@
+
+obj-y := evtchn.o
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/mmu_context.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/mmu_context.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,59 @@
+#ifndef __I386_MMU_CONTEXT_H
+#define __I386_MMU_CONTEXT_H
+
+#include <linux/config.h>
+#include <asm/desc.h>
+#include <asm/atomic.h>
+#include <asm/pgalloc.h>
+
+/*
+ * hooks to add arch specific data into the mm struct.
+ * Note that destroy_context is called even if init_new_context
+ * fails.
+ */
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
+void destroy_context(struct mm_struct *mm);
+
+#ifdef CONFIG_SMP
+
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct
*tsk, unsigned cpu)
+{
+ if(cpu_tlbstate[cpu].state == TLBSTATE_OK)
+ cpu_tlbstate[cpu].state = TLBSTATE_LAZY;
+}
+#else
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct
*tsk, unsigned cpu)
+{
+}
+#endif
+
+extern pgd_t *cur_pgd;
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk, unsigned cpu)
+{
+ struct mmuext_op _op[2], *op = _op;
+ if (prev != next) {
+ /* stop flush ipis for the previous mm */
+ clear_bit(cpu, &prev->cpu_vm_mask);
+ /* Re-load page tables */
+ cur_pgd = next->pgd;
+ op->cmd = MMUEXT_NEW_BASEPTR;
+ op->mfn = pfn_to_mfn(__pa(next->pgd) >> PAGE_SHIFT);
+ op++;
+ /* load_LDT, if either the previous or next thread
+ * has a non-default LDT.
+ */
+ if (next->context.size+prev->context.size) {
+ op->cmd = MMUEXT_SET_LDT;
+ op->linear_addr = (unsigned long)next->context.ldt;
+ op->nr_ents = next->context.size;
+ op++;
+ }
+ BUG_ON(HYPERVISOR_mmuext_op(_op, op-_op, NULL, DOMID_SELF));
+ }
+}
+
+#define activate_mm(prev, next) \
+ switch_mm((prev),(next),NULL,smp_processor_id())
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/privcmd/privcmd.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/privcmd/privcmd.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,259 @@
+/******************************************************************************
+ * privcmd.c
+ *
+ * Interface to privileged domain-0 commands.
+ *
+ * Copyright (c) 2002-2004, K A Fraser, B Dragovic
+ */
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/smp_lock.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/seq_file.h>
+
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+#include <asm/tlb.h>
+#include <asm-xen/linux-public/privcmd.h>
+#include <asm-xen/xen-public/dom0_ops.h>
+#include <asm-xen/xen_proc.h>
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
+#define pud_t pgd_t
+#define pud_offset(d, va) d
+#endif
+
+static struct proc_dir_entry *privcmd_intf;
+
+static int privcmd_ioctl(struct inode *inode, struct file *file,
+ unsigned int cmd, unsigned long data)
+{
+ int ret = -ENOSYS;
+
+ switch ( cmd )
+ {
+ case IOCTL_PRIVCMD_HYPERCALL:
+ {
+ privcmd_hypercall_t hypercall;
+
+ if ( copy_from_user(&hypercall, (void *)data, sizeof(hypercall)) )
+ return -EFAULT;
+
+#if defined(__i386__)
+ __asm__ __volatile__ (
+ "pushl %%ebx; pushl %%ecx; pushl %%edx; pushl %%esi; pushl %%edi; "
+ "movl 4(%%eax),%%ebx ;"
+ "movl 8(%%eax),%%ecx ;"
+ "movl 12(%%eax),%%edx ;"
+ "movl 16(%%eax),%%esi ;"
+ "movl 20(%%eax),%%edi ;"
+ "movl (%%eax),%%eax ;"
+ TRAP_INSTR "; "
+ "popl %%edi; popl %%esi; popl %%edx; popl %%ecx; popl %%ebx"
+ : "=a" (ret) : "0" (&hypercall) : "memory" );
+#elif defined (__x86_64__)
+ __asm__ __volatile__ (
+ "movq %5,%%r10; movq %6,%%r8;" TRAP_INSTR
+ : "=a" (ret)
+ : "a" ((unsigned long)hypercall.op),
+ "D" ((unsigned long)hypercall.arg[0]),
+ "S" ((unsigned long)hypercall.arg[1]),
+ "d" ((unsigned long)hypercall.arg[2]),
+ "g" ((unsigned long)hypercall.arg[3]),
+ "g" ((unsigned long)hypercall.arg[4])
+ : "r11","rcx","r8","r10","memory");
+#endif
+ }
+ break;
+
+ case IOCTL_PRIVCMD_INITDOMAIN_EVTCHN:
+ {
+ extern int initdom_ctrlif_domcontroller_port;
+ ret = initdom_ctrlif_domcontroller_port;
+ }
+ break;
+
+#if defined(CONFIG_XEN_PRIVILEGED_GUEST)
+ case IOCTL_PRIVCMD_MMAP:
+ {
+#define PRIVCMD_MMAP_SZ 32
+ privcmd_mmap_t mmapcmd;
+ privcmd_mmap_entry_t msg[PRIVCMD_MMAP_SZ], *p;
+ int i, rc;
+
+ if ( copy_from_user(&mmapcmd, (void *)data, sizeof(mmapcmd)) )
+ return -EFAULT;
+
+ p = mmapcmd.entry;
+
+ for (i=0; i<mmapcmd.num; i+=PRIVCMD_MMAP_SZ, p+=PRIVCMD_MMAP_SZ)
+ {
+ int j, n = ((mmapcmd.num-i)>PRIVCMD_MMAP_SZ)?
+ PRIVCMD_MMAP_SZ:(mmapcmd.num-i);
+
+
+ if ( copy_from_user(&msg, p, n*sizeof(privcmd_mmap_entry_t)) )
+ return -EFAULT;
+
+ for ( j = 0; j < n; j++ )
+ {
+ struct vm_area_struct *vma =
+ find_vma( current->mm, msg[j].va );
+
+ if ( !vma )
+ return -EINVAL;
+
+ if ( msg[j].va > PAGE_OFFSET )
+ return -EINVAL;
+
+ if ( (msg[j].va + (msg[j].npages<<PAGE_SHIFT)) > vma->vm_end )
+ return -EINVAL;
+
+ if ( (rc = direct_remap_area_pages(vma->vm_mm,
+ msg[j].va&PAGE_MASK,
+ msg[j].mfn<<PAGE_SHIFT,
+ msg[j].npages<<PAGE_SHIFT,
+ vma->vm_page_prot,
+ mmapcmd.dom)) < 0 )
+ return rc;
+ }
+ }
+ ret = 0;
+ }
+ break;
+
+ case IOCTL_PRIVCMD_MMAPBATCH:
+ {
+ mmu_update_t u;
+ privcmd_mmapbatch_t m;
+ struct vm_area_struct *vma = NULL;
+ unsigned long *p, addr;
+ unsigned long mfn;
+ int i;
+
+ if ( copy_from_user(&m, (void *)data, sizeof(m)) )
+ { ret = -EFAULT; goto batch_err; }
+
+ vma = find_vma( current->mm, m.addr );
+
+ if ( !vma )
+ { ret = -EINVAL; goto batch_err; }
+
+ if ( m.addr > PAGE_OFFSET )
+ { ret = -EFAULT; goto batch_err; }
+
+ if ( (m.addr + (m.num<<PAGE_SHIFT)) > vma->vm_end )
+ { ret = -EFAULT; goto batch_err; }
+
+ p = m.arr;
+ addr = m.addr;
+ for ( i = 0; i < m.num; i++, addr += PAGE_SIZE, p++ )
+ {
+ if ( get_user(mfn, p) )
+ return -EFAULT;
+
+ u.val = (mfn << PAGE_SHIFT) | pgprot_val(vma->vm_page_prot);
+
+ __direct_remap_area_pages(vma->vm_mm,
+ addr,
+ PAGE_SIZE,
+ &u);
+
+ if ( unlikely(HYPERVISOR_mmu_update(&u, 1, NULL, m.dom) < 0) )
+ put_user(0xF0000000 | mfn, p);
+ }
+
+ ret = 0;
+ break;
+
+ batch_err:
+ printk("batch_err ret=%d vma=%p addr=%lx num=%d arr=%p %lx-%lx\n",
+ ret, vma, m.addr, m.num, m.arr,
+ vma ? vma->vm_start : 0, vma ? vma->vm_end : 0);
+ break;
+ }
+ break;
+#endif
+
+ case IOCTL_PRIVCMD_GET_MACH2PHYS_START_MFN:
+ {
+ unsigned long m2pv = (unsigned long)machine_to_phys_mapping;
+ pgd_t *pgd = pgd_offset_k(m2pv);
+ pud_t *pud = pud_offset(pgd, m2pv);
+ pmd_t *pmd = pmd_offset(pud, m2pv);
+ unsigned long m2p_start_mfn = (*(unsigned long *)pmd) >> PAGE_SHIFT;
+ ret = put_user(m2p_start_mfn, (unsigned long *)data) ? -EFAULT: 0;
+ }
+ break;
+
+ case IOCTL_PRIVCMD_INITDOMAIN_STORE:
+ {
+ extern int do_xenbus_probe(void*);
+
+ if (xen_start_info.store_evtchn != 0) {
+ ret = -EINVAL;
+ break;
+ }
+
+ /* Allocate page. */
+ xen_start_info.store_page = get_zeroed_page(GFP_KERNEL);
+ if (!xen_start_info.store_page) {
+ ret = -ENOMEM;
+ break;
+ }
+
+ /* We don't refcnt properly, so set reserved on page.
+ * (this allocation is permanent) */
+ SetPageReserved(virt_to_page(xen_start_info.store_page));
+
+ /* Initial connect. Setup channel and page. */
+ xen_start_info.store_evtchn = data;
+ ret = pfn_to_mfn(virt_to_phys((void *)xen_start_info.store_page) >>
+ PAGE_SHIFT);
+
+ /* We'll return then this will wait for daemon to answer */
+ // kthread_run(do_xenbus_probe, NULL, "xenbus_probe");
+ }
+ break;
+
+ default:
+ ret = -EINVAL;
+ break;
+ }
+ return ret;
+}
+
+static int privcmd_mmap(struct file * file, struct vm_area_struct * vma)
+{
+ /* DONTCOPY is essential for Xen as copy_page_range is broken. */
+ vma->vm_flags |= VM_RESERVED | VM_IO | VM_DONTCOPY;
+
+ return 0;
+}
+
+static struct file_operations privcmd_file_ops = {
+ ioctl : privcmd_ioctl,
+ mmap: privcmd_mmap
+};
+
+
+static int __init privcmd_init(void)
+{
+ privcmd_intf = create_xen_proc_entry("privcmd", 0400);
+ if ( privcmd_intf != NULL )
+ privcmd_intf->proc_fops = &privcmd_file_ops;
+
+ return 0;
+}
+
+__initcall(privcmd_init);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/dma-mapping.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/dma-mapping.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,136 @@
+#ifndef _X8664_DMA_MAPPING_H
+#define _X8664_DMA_MAPPING_H 1
+
+/*
+ * IOMMU interface. See Documentation/DMA-mapping.txt and DMA-API.txt for
+ * documentation.
+ */
+
+#include <linux/config.h>
+
+#include <asm/scatterlist.h>
+#include <asm/io.h>
+#include <asm/swiotlb.h>
+
+extern dma_addr_t bad_dma_address;
+#define dma_mapping_error(x) \
+ (swiotlb ? swiotlb_dma_mapping_error(x) : ((x) == bad_dma_address))
+
+void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t
*dma_handle,
+ unsigned gfp);
+void dma_free_coherent(struct device *dev, size_t size, void *vaddr,
+ dma_addr_t dma_handle);
+
+#ifdef CONFIG_GART_IOMMU
+
+extern dma_addr_t dma_map_single(struct device *hwdev, void *ptr, size_t size,
+ int direction);
+extern void dma_unmap_single(struct device *dev, dma_addr_t addr,size_t size,
+ int direction);
+
+#else
+
+/* No IOMMU */
+
+static inline dma_addr_t dma_map_single(struct device *hwdev, void *ptr,
+ size_t size, int direction)
+{
+ dma_addr_t addr;
+
+ if (direction == DMA_NONE)
+ out_of_line_bug();
+ addr = virt_to_machine(ptr);
+
+ if ((addr+size) & ~*hwdev->dma_mask)
+ out_of_line_bug();
+ return addr;
+}
+
+static inline void dma_unmap_single(struct device *hwdev, dma_addr_t dma_addr,
+ size_t size, int direction)
+{
+ if (direction == DMA_NONE)
+ out_of_line_bug();
+ /* Nothing to do */
+}
+#endif
+
+#define dma_map_page(dev,page,offset,size,dir) \
+ dma_map_single((dev), page_address(page)+(offset), (size), (dir))
+
+static inline void dma_sync_single_for_cpu(struct device *hwdev,
+ dma_addr_t dma_handle,
+ size_t size, int direction)
+{
+ if (direction == DMA_NONE)
+ out_of_line_bug();
+
+ if (swiotlb)
+ return
swiotlb_sync_single_for_cpu(hwdev,dma_handle,size,direction);
+
+ flush_write_buffers();
+}
+
+static inline void dma_sync_single_for_device(struct device *hwdev,
+ dma_addr_t dma_handle,
+ size_t size, int direction)
+{
+ if (direction == DMA_NONE)
+ out_of_line_bug();
+
+ if (swiotlb)
+ return
swiotlb_sync_single_for_device(hwdev,dma_handle,size,direction);
+
+ flush_write_buffers();
+}
+
+static inline void dma_sync_sg_for_cpu(struct device *hwdev,
+ struct scatterlist *sg,
+ int nelems, int direction)
+{
+ if (direction == DMA_NONE)
+ out_of_line_bug();
+
+ if (swiotlb)
+ return swiotlb_sync_sg_for_cpu(hwdev,sg,nelems,direction);
+
+ flush_write_buffers();
+}
+
+static inline void dma_sync_sg_for_device(struct device *hwdev,
+ struct scatterlist *sg,
+ int nelems, int direction)
+{
+ if (direction == DMA_NONE)
+ out_of_line_bug();
+
+ if (swiotlb)
+ return swiotlb_sync_sg_for_device(hwdev,sg,nelems,direction);
+
+ flush_write_buffers();
+}
+
+extern int dma_map_sg(struct device *hwdev, struct scatterlist *sg,
+ int nents, int direction);
+extern void dma_unmap_sg(struct device *hwdev, struct scatterlist *sg,
+ int nents, int direction);
+
+#define dma_unmap_page dma_unmap_single
+
+extern int dma_supported(struct device *hwdev, u64 mask);
+extern int dma_get_cache_alignment(void);
+#define dma_is_consistent(h) 1
+
+static inline int dma_set_mask(struct device *dev, u64 mask)
+{
+ if (!dev->dma_mask || !dma_supported(dev, mask))
+ return -EIO;
+ *dev->dma_mask = mask;
+ return 0;
+}
+
+static inline void dma_cache_sync(void *vaddr, size_t size, enum
dma_data_direction dir)
+{
+ flush_write_buffers();
+}
+#endif
diff -r 35b74976f598 -r a83ac0806d6b linux-2.6.11-xen-sparse/net/core/dev.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/net/core/dev.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,3389 @@
+/*
+ * NET3 Protocol independent device support routines.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Derived from the non IP parts of dev.c 1.0.19
+ * Authors: Ross Biro, <bir7@xxxxxxxxxxxxxxxxxxx>
+ * Fred N. van Kempen, <waltje@xxxxxxxxxxxxxxxxxxx>
+ * Mark Evans, <evansmp@xxxxxxxxxxxxxxxxx>
+ *
+ * Additional Authors:
+ * Florian la Roche <rzsfl@xxxxxxxxxxxx>
+ * Alan Cox <gw4pts@xxxxxxxxxxxxxxx>
+ * David Hinds <dahinds@xxxxxxxxxxxxxxxxxxxxx>
+ * Alexey Kuznetsov <kuznet@xxxxxxxxxxxxx>
+ * Adam Sulmicki <adam@xxxxxxxxxxxx>
+ * Pekka Riikonen <priikone@xxxxxxxxxxxxxxxx>
+ *
+ * Changes:
+ * D.J. Barrow : Fixed bug where dev->refcnt gets set
+ * to 2 if register_netdev gets called
+ * before net_dev_init & also removed a
+ * few lines of code in the process.
+ * Alan Cox : device private ioctl copies fields back.
+ * Alan Cox : Transmit queue code does relevant
+ * stunts to keep the queue safe.
+ * Alan Cox : Fixed double lock.
+ * Alan Cox : Fixed promisc NULL pointer trap
+ * ???????? : Support the full private ioctl range
+ * Alan Cox : Moved ioctl permission check into
+ * drivers
+ * Tim Kordas : SIOCADDMULTI/SIOCDELMULTI
+ * Alan Cox : 100 backlog just doesn't cut it when
+ * you start doing multicast video 8)
+ * Alan Cox : Rewrote net_bh and list manager.
+ * Alan Cox : Fix ETH_P_ALL echoback lengths.
+ * Alan Cox : Took out transmit every packet pass
+ * Saved a few bytes in the ioctl handler
+ * Alan Cox : Network driver sets packet type before
+ * calling netif_rx. Saves a function
+ * call a packet.
+ * Alan Cox : Hashed net_bh()
+ * Richard Kooijman: Timestamp fixes.
+ * Alan Cox : Wrong field in SIOCGIFDSTADDR
+ * Alan Cox : Device lock protection.
+ * Alan Cox : Fixed nasty side effect of device close
+ * changes.
+ * Rudi Cilibrasi : Pass the right thing to
+ * set_mac_address()
+ * Dave Miller : 32bit quantity for the device lock to
+ * make it work out on a Sparc.
+ * Bjorn Ekwall : Added KERNELD hack.
+ * Alan Cox : Cleaned up the backlog initialise.
+ * Craig Metz : SIOCGIFCONF fix if space for under
+ * 1 device.
+ * Thomas Bogendoerfer : Return ENODEV for dev_open, if there
+ * is no device open function.
+ * Andi Kleen : Fix error reporting for SIOCGIFCONF
+ * Michael Chastain : Fix signed/unsigned for SIOCGIFCONF
+ * Cyrus Durgin : Cleaned for KMOD
+ * Adam Sulmicki : Bug Fix : Network Device Unload
+ * A network device unload needs to purge
+ * the backlog queue.
+ * Paul Rusty Russell : SIOCSIFNAME
+ * Pekka Riikonen : Netdev boot-time settings code
+ * Andrew Morton : Make unregister_netdevice wait
+ * indefinitely on dev->refcnt
+ * J Hadi Salim : - Backlog queue sampling
+ * - netif_rx() feedback
+ */
+
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <linux/bitops.h>
+#include <linux/config.h>
+#include <linux/cpu.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/if_ether.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/notifier.h>
+#include <linux/skbuff.h>
+#include <net/sock.h>
+#include <linux/rtnetlink.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/stat.h>
+#include <linux/if_bridge.h>
+#include <linux/divert.h>
+#include <net/dst.h>
+#include <net/pkt_sched.h>
+#include <net/checksum.h>
+#include <linux/highmem.h>
+#include <linux/init.h>
+#include <linux/kmod.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/netpoll.h>
+#include <linux/rcupdate.h>
+#include <linux/delay.h>
+#ifdef CONFIG_NET_RADIO
+#include <linux/wireless.h> /* Note : will define WIRELESS_EXT */
+#include <net/iw_handler.h>
+#endif /* CONFIG_NET_RADIO */
+#include <asm/current.h>
+
+#include <net/ip.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+
+
+/* This define, if set, will randomly drop a packet when congestion
+ * is more than moderate. It helps fairness in the multi-interface
+ * case when one of them is a hog, but it kills performance for the
+ * single interface case so it is off now by default.
+ */
+#undef RAND_LIE
+
+/* Setting this will sample the queue lengths and thus congestion
+ * via a timer instead of as each packet is received.
+ */
+#undef OFFLINE_SAMPLE
+
+/*
+ * The list of packet types we will receive (as opposed to discard)
+ * and the routines to invoke.
+ *
+ * Why 16. Because with 16 the only overlap we get on a hash of the
+ * low nibble of the protocol value is RARP/SNAP/X.25.
+ *
+ * NOTE: That is no longer true with the addition of VLAN tags. Not
+ * sure which should go first, but I bet it won't make much
+ * difference if we are running VLANs. The good news is that
+ * this protocol won't be in the list unless compiled in, so
+ * the average user (w/out VLANs) will not be adversly affected.
+ * --BLG
+ *
+ * 0800 IP
+ * 8100 802.1Q VLAN
+ * 0001 802.3
+ * 0002 AX.25
+ * 0004 802.2
+ * 8035 RARP
+ * 0005 SNAP
+ * 0805 X.25
+ * 0806 ARP
+ * 8137 IPX
+ * 0009 Localtalk
+ * 86DD IPv6
+ */
+
+static DEFINE_SPINLOCK(ptype_lock);
+static struct list_head ptype_base[16]; /* 16 way hashed list */
+static struct list_head ptype_all; /* Taps */
+
+#ifdef OFFLINE_SAMPLE
+static void sample_queue(unsigned long dummy);
+static struct timer_list samp_timer = TIMER_INITIALIZER(sample_queue, 0, 0);
+#endif
+
+/*
+ * The @dev_base list is protected by @dev_base_lock and the rtln
+ * semaphore.
+ *
+ * Pure readers hold dev_base_lock for reading.
+ *
+ * Writers must hold the rtnl semaphore while they loop through the
+ * dev_base list, and hold dev_base_lock for writing when they do the
+ * actual updates. This allows pure readers to access the list even
+ * while a writer is preparing to update it.
+ *
+ * To put it another way, dev_base_lock is held for writing only to
+ * protect against pure readers; the rtnl semaphore provides the
+ * protection against other writers.
+ *
+ * See, for example usages, register_netdevice() and
+ * unregister_netdevice(), which must be called with the rtnl
+ * semaphore held.
+ */
+struct net_device *dev_base;
+static struct net_device **dev_tail = &dev_base;
+DEFINE_RWLOCK(dev_base_lock);
+
+EXPORT_SYMBOL(dev_base);
+EXPORT_SYMBOL(dev_base_lock);
+
+#define NETDEV_HASHBITS 8
+static struct hlist_head dev_name_head[1<<NETDEV_HASHBITS];
+static struct hlist_head dev_index_head[1<<NETDEV_HASHBITS];
+
+static inline struct hlist_head *dev_name_hash(const char *name)
+{
+ unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
+ return &dev_name_head[hash & ((1<<NETDEV_HASHBITS)-1)];
+}
+
+static inline struct hlist_head *dev_index_hash(int ifindex)
+{
+ return &dev_index_head[ifindex & ((1<<NETDEV_HASHBITS)-1)];
+}
+
+/*
+ * Our notifier list
+ */
+
+static struct notifier_block *netdev_chain;
+
+/*
+ * Device drivers call our routines to queue packets here. We empty the
+ * queue in the local softnet handler.
+ */
+DEFINE_PER_CPU(struct softnet_data, softnet_data) = { 0, };
+
+#ifdef CONFIG_SYSFS
+extern int netdev_sysfs_init(void);
+extern int netdev_register_sysfs(struct net_device *);
+extern void netdev_unregister_sysfs(struct net_device *);
+#else
+#define netdev_sysfs_init() (0)
+#define netdev_register_sysfs(dev) (0)
+#define netdev_unregister_sysfs(dev) do { } while(0)
+#endif
+
+
+/*******************************************************************************
+
+ Protocol management and registration routines
+
+*******************************************************************************/
+
+/*
+ * For efficiency
+ */
+
+int netdev_nit;
+
+/*
+ * Add a protocol ID to the list. Now that the input handler is
+ * smarter we can dispense with all the messy stuff that used to be
+ * here.
+ *
+ * BEWARE!!! Protocol handlers, mangling input packets,
+ * MUST BE last in hash buckets and checking protocol handlers
+ * MUST start from promiscuous ptype_all chain in net_bh.
+ * It is true now, do not change it.
+ * Explanation follows: if protocol handler, mangling packet, will
+ * be the first on list, it is not able to sense, that packet
+ * is cloned and should be copied-on-write, so that it will
+ * change it and subsequent readers will get broken packet.
+ * --ANK (980803)
+ */
+
+/**
+ * dev_add_pack - add packet handler
+ * @pt: packet type declaration
+ *
+ * Add a protocol handler to the networking stack. The passed &packet_type
+ * is linked into kernel lists and may not be freed until it has been
+ * removed from the kernel lists.
+ *
+ * This call does not sleep therefore it can not
+ * guarantee all CPU's that are in middle of receiving packets
+ * will see the new packet type (until the next received packet).
+ */
+
+void dev_add_pack(struct packet_type *pt)
+{
+ int hash;
+
+ spin_lock_bh(&ptype_lock);
+ if (pt->type == htons(ETH_P_ALL)) {
+ netdev_nit++;
+ list_add_rcu(&pt->list, &ptype_all);
+ } else {
+ hash = ntohs(pt->type) & 15;
+ list_add_rcu(&pt->list, &ptype_base[hash]);
+ }
+ spin_unlock_bh(&ptype_lock);
+}
+
+extern void linkwatch_run_queue(void);
+
+
+
+/**
+ * __dev_remove_pack - remove packet handler
+ * @pt: packet type declaration
+ *
+ * Remove a protocol handler that was previously added to the kernel
+ * protocol handlers by dev_add_pack(). The passed &packet_type is removed
+ * from the kernel lists and can be freed or reused once this function
+ * returns.
+ *
+ * The packet type might still be in use by receivers
+ * and must not be freed until after all the CPU's have gone
+ * through a quiescent state.
+ */
+void __dev_remove_pack(struct packet_type *pt)
+{
+ struct list_head *head;
+ struct packet_type *pt1;
+
+ spin_lock_bh(&ptype_lock);
+
+ if (pt->type == htons(ETH_P_ALL)) {
+ netdev_nit--;
+ head = &ptype_all;
+ } else
+ head = &ptype_base[ntohs(pt->type) & 15];
+
+ list_for_each_entry(pt1, head, list) {
+ if (pt == pt1) {
+ list_del_rcu(&pt->list);
+ goto out;
+ }
+ }
+
+ printk(KERN_WARNING "dev_remove_pack: %p not found.\n", pt);
+out:
+ spin_unlock_bh(&ptype_lock);
+}
+/**
+ * dev_remove_pack - remove packet handler
+ * @pt: packet type declaration
+ *
+ * Remove a protocol handler that was previously added to the kernel
+ * protocol handlers by dev_add_pack(). The passed &packet_type is removed
+ * from the kernel lists and can be freed or reused once this function
+ * returns.
+ *
+ * This call sleeps to guarantee that no CPU is looking at the packet
+ * type after return.
+ */
+void dev_remove_pack(struct packet_type *pt)
+{
+ __dev_remove_pack(pt);
+
+ synchronize_net();
+}
+
+/******************************************************************************
+
+ Device Boot-time Settings Routines
+
+*******************************************************************************/
+
+/* Boot time configuration table */
+static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX];
+
+/**
+ * netdev_boot_setup_add - add new setup entry
+ * @name: name of the device
+ * @map: configured settings for the device
+ *
+ * Adds new setup entry to the dev_boot_setup list. The function
+ * returns 0 on error and 1 on success. This is a generic routine to
+ * all netdevices.
+ */
+static int netdev_boot_setup_add(char *name, struct ifmap *map)
+{
+ struct netdev_boot_setup *s;
+ int i;
+
+ s = dev_boot_setup;
+ for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
+ if (s[i].name[0] == '\0' || s[i].name[0] == ' ') {
+ memset(s[i].name, 0, sizeof(s[i].name));
+ strcpy(s[i].name, name);
+ memcpy(&s[i].map, map, sizeof(s[i].map));
+ break;
+ }
+ }
+
+ return i >= NETDEV_BOOT_SETUP_MAX ? 0 : 1;
+}
+
+/**
+ * netdev_boot_setup_check - check boot time settings
+ * @dev: the netdevice
+ *
+ * Check boot time settings for the device.
+ * The found settings are set for the device to be used
+ * later in the device probing.
+ * Returns 0 if no settings found, 1 if they are.
+ */
+int netdev_boot_setup_check(struct net_device *dev)
+{
+ struct netdev_boot_setup *s = dev_boot_setup;
+ int i;
+
+ for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
+ if (s[i].name[0] != '\0' && s[i].name[0] != ' ' &&
+ !strncmp(dev->name, s[i].name, strlen(s[i].name))) {
+ dev->irq = s[i].map.irq;
+ dev->base_addr = s[i].map.base_addr;
+ dev->mem_start = s[i].map.mem_start;
+ dev->mem_end = s[i].map.mem_end;
+ return 1;
+ }
+ }
+ return 0;
+}
+
+
+/**
+ * netdev_boot_base - get address from boot time settings
+ * @prefix: prefix for network device
+ * @unit: id for network device
+ *
+ * Check boot time settings for the base address of device.
+ * The found settings are set for the device to be used
+ * later in the device probing.
+ * Returns 0 if no settings found.
+ */
+unsigned long netdev_boot_base(const char *prefix, int unit)
+{
+ const struct netdev_boot_setup *s = dev_boot_setup;
+ char name[IFNAMSIZ];
+ int i;
+
+ sprintf(name, "%s%d", prefix, unit);
+
+ /*
+ * If device already registered then return base of 1
+ * to indicate not to probe for this interface
+ */
+ if (__dev_get_by_name(name))
+ return 1;
+
+ for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++)
+ if (!strcmp(name, s[i].name))
+ return s[i].map.base_addr;
+ return 0;
+}
+
+/*
+ * Saves at boot time configured settings for any netdevice.
+ */
+int __init netdev_boot_setup(char *str)
+{
+ int ints[5];
+ struct ifmap map;
+
+ str = get_options(str, ARRAY_SIZE(ints), ints);
+ if (!str || !*str)
+ return 0;
+
+ /* Save settings */
+ memset(&map, 0, sizeof(map));
+ if (ints[0] > 0)
+ map.irq = ints[1];
+ if (ints[0] > 1)
+ map.base_addr = ints[2];
+ if (ints[0] > 2)
+ map.mem_start = ints[3];
+ if (ints[0] > 3)
+ map.mem_end = ints[4];
+
+ /* Add new entry to the list */
+ return netdev_boot_setup_add(str, &map);
+}
+
+__setup("netdev=", netdev_boot_setup);
+
+/*******************************************************************************
+
+ Device Interface Subroutines
+
+*******************************************************************************/
+
+/**
+ * __dev_get_by_name - find a device by its name
+ * @name: name to find
+ *
+ * Find an interface by name. Must be called under RTNL semaphore
+ * or @dev_base_lock. If the name is found a pointer to the device
+ * is returned. If the name is not found then %NULL is returned. The
+ * reference counters are not incremented so the caller must be
+ * careful with locks.
+ */
+
+struct net_device *__dev_get_by_name(const char *name)
+{
+ struct hlist_node *p;
+
+ hlist_for_each(p, dev_name_hash(name)) {
+ struct net_device *dev
+ = hlist_entry(p, struct net_device, name_hlist);
+ if (!strncmp(dev->name, name, IFNAMSIZ))
+ return dev;
+ }
+ return NULL;
+}
+
+/**
+ * dev_get_by_name - find a device by its name
+ * @name: name to find
+ *
+ * Find an interface by name. This can be called from any
+ * context and does its own locking. The returned handle has
+ * the usage count incremented and the caller must use dev_put() to
+ * release it when it is no longer needed. %NULL is returned if no
+ * matching device is found.
+ */
+
+struct net_device *dev_get_by_name(const char *name)
+{
+ struct net_device *dev;
+
+ read_lock(&dev_base_lock);
+ dev = __dev_get_by_name(name);
+ if (dev)
+ dev_hold(dev);
+ read_unlock(&dev_base_lock);
+ return dev;
+}
+
+/**
+ * __dev_get_by_index - find a device by its ifindex
+ * @ifindex: index of device
+ *
+ * Search for an interface by index. Returns %NULL if the device
+ * is not found or a pointer to the device. The device has not
+ * had its reference counter increased so the caller must be careful
+ * about locking. The caller must hold either the RTNL semaphore
+ * or @dev_base_lock.
+ */
+
+struct net_device *__dev_get_by_index(int ifindex)
+{
+ struct hlist_node *p;
+
+ hlist_for_each(p, dev_index_hash(ifindex)) {
+ struct net_device *dev
+ = hlist_entry(p, struct net_device, index_hlist);
+ if (dev->ifindex == ifindex)
+ return dev;
+ }
+ return NULL;
+}
+
+
+/**
+ * dev_get_by_index - find a device by its ifindex
+ * @ifindex: index of device
+ *
+ * Search for an interface by index. Returns NULL if the device
+ * is not found or a pointer to the device. The device returned has
+ * had a reference added and the pointer is safe until the user calls
+ * dev_put to indicate they have finished with it.
+ */
+
+struct net_device *dev_get_by_index(int ifindex)
+{
+ struct net_device *dev;
+
+ read_lock(&dev_base_lock);
+ dev = __dev_get_by_index(ifindex);
+ if (dev)
+ dev_hold(dev);
+ read_unlock(&dev_base_lock);
+ return dev;
+}
+
+/**
+ * dev_getbyhwaddr - find a device by its hardware address
+ * @type: media type of device
+ * @ha: hardware address
+ *
+ * Search for an interface by MAC address. Returns NULL if the device
+ * is not found or a pointer to the device. The caller must hold the
+ * rtnl semaphore. The returned device has not had its ref count increased
+ * and the caller must therefore be careful about locking
+ *
+ * BUGS:
+ * If the API was consistent this would be __dev_get_by_hwaddr
+ */
+
+struct net_device *dev_getbyhwaddr(unsigned short type, char *ha)
+{
+ struct net_device *dev;
+
+ ASSERT_RTNL();
+
+ for (dev = dev_base; dev; dev = dev->next)
+ if (dev->type == type &&
+ !memcmp(dev->dev_addr, ha, dev->addr_len))
+ break;
+ return dev;
+}
+
+struct net_device *dev_getfirstbyhwtype(unsigned short type)
+{
+ struct net_device *dev;
+
+ rtnl_lock();
+ for (dev = dev_base; dev; dev = dev->next) {
+ if (dev->type == type) {
+ dev_hold(dev);
+ break;
+ }
+ }
+ rtnl_unlock();
+ return dev;
+}
+
+EXPORT_SYMBOL(dev_getfirstbyhwtype);
+
+/**
+ * dev_get_by_flags - find any device with given flags
+ * @if_flags: IFF_* values
+ * @mask: bitmask of bits in if_flags to check
+ *
+ * Search for any interface with the given flags. Returns NULL if a device
+ * is not found or a pointer to the device. The device returned has
+ * had a reference added and the pointer is safe until the user calls
+ * dev_put to indicate they have finished with it.
+ */
+
+struct net_device * dev_get_by_flags(unsigned short if_flags, unsigned short
mask)
+{
+ struct net_device *dev;
+
+ read_lock(&dev_base_lock);
+ for (dev = dev_base; dev != NULL; dev = dev->next) {
+ if (((dev->flags ^ if_flags) & mask) == 0) {
+ dev_hold(dev);
+ break;
+ }
+ }
+ read_unlock(&dev_base_lock);
+ return dev;
+}
+
+/**
+ * dev_valid_name - check if name is okay for network device
+ * @name: name string
+ *
+ * Network device names need to be valid file names to
+ * to allow sysfs to work
+ */
+static int dev_valid_name(const char *name)
+{
+ return !(*name == '\0'
+ || !strcmp(name, ".")
+ || !strcmp(name, "..")
+ || strchr(name, '/'));
+}
+
+/**
+ * dev_alloc_name - allocate a name for a device
+ * @dev: device
+ * @name: name format string
+ *
+ * Passed a format string - eg "lt%d" it will try and find a suitable
+ * id. Not efficient for many devices, not called a lot. The caller
+ * must hold the dev_base or rtnl lock while allocating the name and
+ * adding the device in order to avoid duplicates. Returns the number
+ * of the unit assigned or a negative errno code.
+ */
+
+int dev_alloc_name(struct net_device *dev, const char *name)
+{
+ int i = 0;
+ char buf[IFNAMSIZ];
+ const char *p;
+ const int max_netdevices = 8*PAGE_SIZE;
+ long *inuse;
+ struct net_device *d;
+
+ p = strnchr(name, IFNAMSIZ-1, '%');
+ if (p) {
+ /*
+ * Verify the string as this thing may have come from
+ * the user. There must be either one "%d" and no other "%"
+ * characters.
+ */
+ if (p[1] != 'd' || strchr(p + 2, '%'))
+ return -EINVAL;
+
+ /* Use one page as a bit array of possible slots */
+ inuse = (long *) get_zeroed_page(GFP_ATOMIC);
+ if (!inuse)
+ return -ENOMEM;
+
+ for (d = dev_base; d; d = d->next) {
+ if (!sscanf(d->name, name, &i))
+ continue;
+ if (i < 0 || i >= max_netdevices)
+ continue;
+
+ /* avoid cases where sscanf is not exact inverse of
printf */
+ snprintf(buf, sizeof(buf), name, i);
+ if (!strncmp(buf, d->name, IFNAMSIZ))
+ set_bit(i, inuse);
+ }
+
+ i = find_first_zero_bit(inuse, max_netdevices);
+ free_page((unsigned long) inuse);
+ }
+
+ snprintf(buf, sizeof(buf), name, i);
+ if (!__dev_get_by_name(buf)) {
+ strlcpy(dev->name, buf, IFNAMSIZ);
+ return i;
+ }
+
+ /* It is possible to run out of possible slots
+ * when the name is long and there isn't enough space left
+ * for the digits, or if all bits are used.
+ */
+ return -ENFILE;
+}
+
+
+/**
+ * dev_change_name - change name of a device
+ * @dev: device
+ * @newname: name (or format string) must be at least IFNAMSIZ
+ *
+ * Change name of a device, can pass format strings "eth%d".
+ * for wildcarding.
+ */
+int dev_change_name(struct net_device *dev, char *newname)
+{
+ int err = 0;
+
+ ASSERT_RTNL();
+
+ if (dev->flags & IFF_UP)
+ return -EBUSY;
+
+ if (!dev_valid_name(newname))
+ return -EINVAL;
+
+ if (strchr(newname, '%')) {
+ err = dev_alloc_name(dev, newname);
+ if (err < 0)
+ return err;
+ strcpy(newname, dev->name);
+ }
+ else if (__dev_get_by_name(newname))
+ return -EEXIST;
+ else
+ strlcpy(dev->name, newname, IFNAMSIZ);
+
+ err = class_device_rename(&dev->class_dev, dev->name);
+ if (!err) {
+ hlist_del(&dev->name_hlist);
+ hlist_add_head(&dev->name_hlist, dev_name_hash(dev->name));
+ notifier_call_chain(&netdev_chain, NETDEV_CHANGENAME, dev);
+ }
+
+ return err;
+}
+
+/**
+ * netdev_state_change - device changes state
+ * @dev: device to cause notification
+ *
+ * Called to indicate a device has changed state. This function calls
+ * the notifier chains for netdev_chain and sends a NEWLINK message
+ * to the routing socket.
+ */
+void netdev_state_change(struct net_device *dev)
+{
+ if (dev->flags & IFF_UP) {
+ notifier_call_chain(&netdev_chain, NETDEV_CHANGE, dev);
+ rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
+ }
+}
+
+/**
+ * dev_load - load a network module
+ * @name: name of interface
+ *
+ * If a network interface is not present and the process has suitable
+ * privileges this function loads the module. If module loading is not
+ * available in this kernel then it becomes a nop.
+ */
+
+void dev_load(const char *name)
+{
+ struct net_device *dev;
+
+ read_lock(&dev_base_lock);
+ dev = __dev_get_by_name(name);
+ read_unlock(&dev_base_lock);
+
+ if (!dev && capable(CAP_SYS_MODULE))
+ request_module("%s", name);
+}
+
+static int default_rebuild_header(struct sk_buff *skb)
+{
+ printk(KERN_DEBUG "%s: default_rebuild_header called -- BUG!\n",
+ skb->dev ? skb->dev->name : "NULL!!!");
+ kfree_skb(skb);
+ return 1;
+}
+
+
+/**
+ * dev_open - prepare an interface for use.
+ * @dev: device to open
+ *
+ * Takes a device from down to up state. The device's private open
+ * function is invoked and then the multicast lists are loaded. Finally
+ * the device is moved into the up state and a %NETDEV_UP message is
+ * sent to the netdev notifier chain.
+ *
+ * Calling this function on an active interface is a nop. On a failure
+ * a negative errno code is returned.
+ */
+int dev_open(struct net_device *dev)
+{
+ int ret = 0;
+
+ /*
+ * Is it already up?
+ */
+
+ if (dev->flags & IFF_UP)
+ return 0;
+
+ /*
+ * Is it even present?
+ */
+ if (!netif_device_present(dev))
+ return -ENODEV;
+
+ /*
+ * Call device private open method
+ */
+ set_bit(__LINK_STATE_START, &dev->state);
+ if (dev->open) {
+ ret = dev->open(dev);
+ if (ret)
+ clear_bit(__LINK_STATE_START, &dev->state);
+ }
+
+ /*
+ * If it went open OK then:
+ */
+
+ if (!ret) {
+ /*
+ * Set the flags.
+ */
+ dev->flags |= IFF_UP;
+
+ /*
+ * Initialize multicasting status
+ */
+ dev_mc_upload(dev);
+
+ /*
+ * Wakeup transmit queue engine
+ */
+ dev_activate(dev);
+
+ /*
+ * ... and announce new interface.
+ */
+ notifier_call_chain(&netdev_chain, NETDEV_UP, dev);
+ }
+ return ret;
+}
+
+/**
+ * dev_close - shutdown an interface.
+ * @dev: device to shutdown
+ *
+ * This function moves an active device into down state. A
+ * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device
+ * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier
+ * chain.
+ */
+int dev_close(struct net_device *dev)
+{
+ if (!(dev->flags & IFF_UP))
+ return 0;
+
+ /*
+ * Tell people we are going down, so that they can
+ * prepare to death, when device is still operating.
+ */
+ notifier_call_chain(&netdev_chain, NETDEV_GOING_DOWN, dev);
+
+ dev_deactivate(dev);
+
+ clear_bit(__LINK_STATE_START, &dev->state);
+
+ /* Synchronize to scheduled poll. We cannot touch poll list,
+ * it can be even on different cpu. So just clear netif_running(),
+ * and wait when poll really will happen. Actually, the best place
+ * for this is inside dev->stop() after device stopped its irq
+ * engine, but this requires more changes in devices. */
+
+ smp_mb__after_clear_bit(); /* Commit netif_running(). */
+ while (test_bit(__LINK_STATE_RX_SCHED, &dev->state)) {
+ /* No hurry. */
+ current->state = TASK_INTERRUPTIBLE;
+ schedule_timeout(1);
+ }
+
+ /*
+ * Call the device specific close. This cannot fail.
+ * Only if device is UP
+ *
+ * We allow it to be called even after a DETACH hot-plug
+ * event.
+ */
+ if (dev->stop)
+ dev->stop(dev);
+
+ /*
+ * Device is now down.
+ */
+
+ dev->flags &= ~IFF_UP;
+
+ /*
+ * Tell people we are down
+ */
+ notifier_call_chain(&netdev_chain, NETDEV_DOWN, dev);
+
+ return 0;
+}
+
+
+/*
+ * Device change register/unregister. These are not inline or static
+ * as we export them to the world.
+ */
+
+/**
+ * register_netdevice_notifier - register a network notifier block
+ * @nb: notifier
+ *
+ * Register a notifier to be called when network device events occur.
+ * The notifier passed is linked into the kernel structures and must
+ * not be reused until it has been unregistered. A negative errno code
+ * is returned on a failure.
+ *
+ * When registered all registration and up events are replayed
+ * to the new notifier to allow device to have a race free
+ * view of the network device list.
+ */
+
+int register_netdevice_notifier(struct notifier_block *nb)
+{
+ struct net_device *dev;
+ int err;
+
+ rtnl_lock();
+ err = notifier_chain_register(&netdev_chain, nb);
+ if (!err) {
+ for (dev = dev_base; dev; dev = dev->next) {
+ nb->notifier_call(nb, NETDEV_REGISTER, dev);
+
+ if (dev->flags & IFF_UP)
+ nb->notifier_call(nb, NETDEV_UP, dev);
+ }
+ }
+ rtnl_unlock();
+ return err;
+}
+
+/**
+ * unregister_netdevice_notifier - unregister a network notifier block
+ * @nb: notifier
+ *
+ * Unregister a notifier previously registered by
+ * register_netdevice_notifier(). The notifier is unlinked into the
+ * kernel structures and may then be reused. A negative errno code
+ * is returned on a failure.
+ */
+
+int unregister_netdevice_notifier(struct notifier_block *nb)
+{
+ return notifier_chain_unregister(&netdev_chain, nb);
+}
+
+/**
+ * call_netdevice_notifiers - call all network notifier blocks
+ * @val: value passed unmodified to notifier function
+ * @v: pointer passed unmodified to notifier function
+ *
+ * Call all network notifier blocks. Parameters and return value
+ * are as for notifier_call_chain().
+ */
+
+int call_netdevice_notifiers(unsigned long val, void *v)
+{
+ return notifier_call_chain(&netdev_chain, val, v);
+}
+
+/* When > 0 there are consumers of rx skb time stamps */
+static atomic_t netstamp_needed = ATOMIC_INIT(0);
+
+void net_enable_timestamp(void)
+{
+ atomic_inc(&netstamp_needed);
+}
+
+void net_disable_timestamp(void)
+{
+ atomic_dec(&netstamp_needed);
+}
+
+static inline void net_timestamp(struct timeval *stamp)
+{
+ if (atomic_read(&netstamp_needed))
+ do_gettimeofday(stamp);
+ else {
+ stamp->tv_sec = 0;
+ stamp->tv_usec = 0;
+ }
+}
+
+/*
+ * Support routine. Sends outgoing frames to any network
+ * taps currently in use.
+ */
+
+void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct packet_type *ptype;
+ net_timestamp(&skb->stamp);
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ptype, &ptype_all, list) {
+ /* Never send packets back to the socket
+ * they originated from - MvS (miquels@xxxxxxxxxxxxxx)
+ */
+ if ((ptype->dev == dev || !ptype->dev) &&
+ (ptype->af_packet_priv == NULL ||
+ (struct sock *)ptype->af_packet_priv != skb->sk)) {
+ struct sk_buff *skb2= skb_clone(skb, GFP_ATOMIC);
+ if (!skb2)
+ break;
+
+ /* skb->nh should be correctly
+ set by sender, so that the second statement is
+ just protection against buggy protocols.
+ */
+ skb2->mac.raw = skb2->data;
+
+ if (skb2->nh.raw < skb2->data ||
+ skb2->nh.raw > skb2->tail) {
+ if (net_ratelimit())
+ printk(KERN_CRIT "protocol %04x is "
+ "buggy, dev %s\n",
+ skb2->protocol, dev->name);
+ skb2->nh.raw = skb2->data;
+ }
+
+ skb2->h.raw = skb2->nh.raw;
+ skb2->pkt_type = PACKET_OUTGOING;
+ ptype->func(skb2, skb->dev, ptype);
+ }
+ }
+ rcu_read_unlock();
+}
+
+/*
+ * Invalidate hardware checksum when packet is to be mangled, and
+ * complete checksum manually on outgoing path.
+ */
+int skb_checksum_help(struct sk_buff *skb, int inward)
+{
+ unsigned int csum;
+ int ret = 0, offset = skb->h.raw - skb->data;
+
+ if (inward) {
+ skb->ip_summed = CHECKSUM_NONE;
+ goto out;
+ }
+
+ if (skb_cloned(skb)) {
+ ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+ if (ret)
+ goto out;
+ }
+
+ if (offset > (int)skb->len)
+ BUG();
+ csum = skb_checksum(skb, offset, skb->len-offset, 0);
+
+ offset = skb->tail - skb->h.raw;
+ if (offset <= 0)
+ BUG();
+ if (skb->csum + 2 > offset)
+ BUG();
+
+ *(u16*)(skb->h.raw + skb->csum) = csum_fold(csum);
+ skb->ip_summed = CHECKSUM_NONE;
+out:
+ return ret;
+}
+
+#ifdef CONFIG_HIGHMEM
+/* Actually, we should eliminate this check as soon as we know, that:
+ * 1. IOMMU is present and allows to map all the memory.
+ * 2. No high memory really exists on this machine.
+ */
+
+static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
+{
+ int i;
+
+ if (dev->features & NETIF_F_HIGHDMA)
+ return 0;
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
+ if (PageHighMem(skb_shinfo(skb)->frags[i].page))
+ return 1;
+
+ return 0;
+}
+#else
+#define illegal_highdma(dev, skb) (0)
+#endif
+
+extern void skb_release_data(struct sk_buff *);
+
+/* Keep head the same: replace data */
+int __skb_linearize(struct sk_buff *skb, int gfp_mask)
+{
+ unsigned int size;
+ u8 *data;
+ long offset;
+ struct skb_shared_info *ninfo;
+ int headerlen = skb->data - skb->head;
+ int expand = (skb->tail + skb->data_len) - skb->end;
+
+ if (skb_shared(skb))
+ BUG();
+
+ if (expand <= 0)
+ expand = 0;
+
+ size = skb->end - skb->head + expand;
+ size = SKB_DATA_ALIGN(size);
+ data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
+ if (!data)
+ return -ENOMEM;
+
+ /* Copy entire thing */
+ if (skb_copy_bits(skb, -headerlen, data, headerlen + skb->len))
+ BUG();
+
+ /* Set up shinfo */
+ ninfo = (struct skb_shared_info*)(data + size);
+ atomic_set(&ninfo->dataref, 1);
+ ninfo->tso_size = skb_shinfo(skb)->tso_size;
+ ninfo->tso_segs = skb_shinfo(skb)->tso_segs;
+ ninfo->nr_frags = 0;
+ ninfo->frag_list = NULL;
+
+ /* Offset between the two in bytes */
+ offset = data - skb->head;
+
+ /* Free old data. */
+ skb_release_data(skb);
+
+ skb->head = data;
+ skb->end = data + size;
+
+ /* Set up new pointers */
+ skb->h.raw += offset;
+ skb->nh.raw += offset;
+ skb->mac.raw += offset;
+ skb->tail += offset;
+ skb->data += offset;
+
+ /* We are no longer a clone, even if we were. */
+ skb->cloned = 0;
+
+ skb->tail += skb->data_len;
+ skb->data_len = 0;
+ return 0;
+}
+
+#define HARD_TX_LOCK(dev, cpu) { \
+ if ((dev->features & NETIF_F_LLTX) == 0) { \
+ spin_lock(&dev->xmit_lock); \
+ dev->xmit_lock_owner = cpu; \
+ } \
+}
+
+#define HARD_TX_UNLOCK(dev) { \
+ if ((dev->features & NETIF_F_LLTX) == 0) { \
+ dev->xmit_lock_owner = -1; \
+ spin_unlock(&dev->xmit_lock); \
+ } \
+}
+
+/**
+ * dev_queue_xmit - transmit a buffer
+ * @skb: buffer to transmit
+ *
+ * Queue a buffer for transmission to a network device. The caller must
+ * have set the device and priority and built the buffer before calling
+ * this function. The function can be called from an interrupt.
+ *
+ * A negative errno code is returned on a failure. A success does not
+ * guarantee the frame will be transmitted as it may be dropped due
+ * to congestion or traffic shaping.
+ */
+
+int dev_queue_xmit(struct sk_buff *skb)
+{
+ struct net_device *dev = skb->dev;
+ struct Qdisc *q;
+ int rc = -ENOMEM;
+
+ if (skb_shinfo(skb)->frag_list &&
+ !(dev->features & NETIF_F_FRAGLIST) &&
+ __skb_linearize(skb, GFP_ATOMIC))
+ goto out_kfree_skb;
+
+ /* Fragmented skb is linearized if device does not support SG,
+ * or if at least one of fragments is in highmem and device
+ * does not support DMA from it.
+ */
+ if (skb_shinfo(skb)->nr_frags &&
+ (!(dev->features & NETIF_F_SG) || illegal_highdma(dev, skb)) &&
+ __skb_linearize(skb, GFP_ATOMIC))
+ goto out_kfree_skb;
+
+ /* If a checksum-deferred packet is forwarded to a device that needs a
+ * checksum, correct the pointers and force checksumming.
+ */
+ if (skb->proto_csum_blank) {
+ if (skb->protocol != htons(ETH_P_IP))
+ goto out_kfree_skb;
+ skb->h.raw = (unsigned char *)skb->nh.iph + 4*skb->nh.iph->ihl;
+ if (skb->h.raw >= skb->tail)
+ goto out_kfree_skb;
+ switch (skb->nh.iph->protocol) {
+ case IPPROTO_TCP:
+ skb->csum = offsetof(struct tcphdr, check);
+ break;
+ case IPPROTO_UDP:
+ skb->csum = offsetof(struct udphdr, check);
+ break;
+ default:
+ goto out_kfree_skb;
+ }
+ if ((skb->h.raw + skb->csum + 2) > skb->tail)
+ goto out_kfree_skb;
+ skb->ip_summed = CHECKSUM_HW;
+ }
+
+ /* If packet is not checksummed and device does not support
+ * checksumming for this protocol, complete checksumming here.
+ */
+ if (skb->ip_summed == CHECKSUM_HW &&
+ (!(dev->features & (NETIF_F_HW_CSUM | NETIF_F_NO_CSUM)) &&
+ (!(dev->features & NETIF_F_IP_CSUM) ||
+ skb->protocol != htons(ETH_P_IP))))
+ if (skb_checksum_help(skb, 0))
+ goto out_kfree_skb;
+
+ /* Disable soft irqs for various locks below. Also
+ * stops preemption for RCU.
+ */
+ local_bh_disable();
+
+ /* Updates of qdisc are serialized by queue_lock.
+ * The struct Qdisc which is pointed to by qdisc is now a
+ * rcu structure - it may be accessed without acquiring
+ * a lock (but the structure may be stale.) The freeing of the
+ * qdisc will be deferred until it's known that there are no
+ * more references to it.
+ *
+ * If the qdisc has an enqueue function, we still need to
+ * hold the queue_lock before calling it, since queue_lock
+ * also serializes access to the device queue.
+ */
+
+ q = rcu_dereference(dev->qdisc);
+#ifdef CONFIG_NET_CLS_ACT
+ skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS);
+#endif
+ if (q->enqueue) {
+ /* Grab device queue */
+ spin_lock(&dev->queue_lock);
+
+ rc = q->enqueue(skb, q);
+
+ qdisc_run(dev);
+
+ spin_unlock(&dev->queue_lock);
+ rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc;
+ goto out;
+ }
+
+ /* The device has no queue. Common case for software devices:
+ loopback, all the sorts of tunnels...
+
+ Really, it is unlikely that xmit_lock protection is necessary here.
+ (f.e. loopback and IP tunnels are clean ignoring statistics
+ counters.)
+ However, it is possible, that they rely on protection
+ made by us here.
+
+ Check this and shot the lock. It is not prone from deadlocks.
+ Either shot noqueue qdisc, it is even simpler 8)
+ */
+ if (dev->flags & IFF_UP) {
+ int cpu = smp_processor_id(); /* ok because BHs are off */
+
+ if (dev->xmit_lock_owner != cpu) {
+
+ HARD_TX_LOCK(dev, cpu);
+
+ if (!netif_queue_stopped(dev)) {
+ if (netdev_nit)
+ dev_queue_xmit_nit(skb, dev);
+
+ rc = 0;
+ if (!dev->hard_start_xmit(skb, dev)) {
+ HARD_TX_UNLOCK(dev);
+ goto out;
+ }
+ }
+ HARD_TX_UNLOCK(dev);
+ if (net_ratelimit())
+ printk(KERN_CRIT "Virtual device %s asks to "
+ "queue packet!\n", dev->name);
+ } else {
+ /* Recursion is detected! It is possible,
+ * unfortunately */
+ if (net_ratelimit())
+ printk(KERN_CRIT "Dead loop on virtual device "
+ "%s, fix it urgently!\n", dev->name);
+ }
+ }
+
+ rc = -ENETDOWN;
+ local_bh_enable();
+
+out_kfree_skb:
+ kfree_skb(skb);
+ return rc;
+out:
+ local_bh_enable();
+ return rc;
+}
+
+
+/*=======================================================================
+ Receiver routines
+ =======================================================================*/
+
+int netdev_max_backlog = 300;
+int weight_p = 64; /* old backlog weight */
+/* These numbers are selected based on intuition and some
+ * experimentatiom, if you have more scientific way of doing this
+ * please go ahead and fix things.
+ */
+int no_cong_thresh = 10;
+int no_cong = 20;
+int lo_cong = 100;
+int mod_cong = 290;
+
+DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };
+
+
+static void get_sample_stats(int cpu)
+{
+#ifdef RAND_LIE
+ unsigned long rd;
+ int rq;
+#endif
+ struct softnet_data *sd = &per_cpu(softnet_data, cpu);
+ int blog = sd->input_pkt_queue.qlen;
+ int avg_blog = sd->avg_blog;
+
+ avg_blog = (avg_blog >> 1) + (blog >> 1);
+
+ if (avg_blog > mod_cong) {
+ /* Above moderate congestion levels. */
+ sd->cng_level = NET_RX_CN_HIGH;
+#ifdef RAND_LIE
+ rd = net_random();
+ rq = rd % netdev_max_backlog;
+ if (rq < avg_blog) /* unlucky bastard */
+ sd->cng_level = NET_RX_DROP;
+#endif
+ } else if (avg_blog > lo_cong) {
+ sd->cng_level = NET_RX_CN_MOD;
+#ifdef RAND_LIE
+ rd = net_random();
+ rq = rd % netdev_max_backlog;
+ if (rq < avg_blog) /* unlucky bastard */
+ sd->cng_level = NET_RX_CN_HIGH;
+#endif
+ } else if (avg_blog > no_cong)
+ sd->cng_level = NET_RX_CN_LOW;
+ else /* no congestion */
+ sd->cng_level = NET_RX_SUCCESS;
+
+ sd->avg_blog = avg_blog;
+}
+
+#ifdef OFFLINE_SAMPLE
+static void sample_queue(unsigned long dummy)
+{
+/* 10 ms 0r 1ms -- i don't care -- JHS */
+ int next_tick = 1;
+ int cpu = smp_processor_id();
+
+ get_sample_stats(cpu);
+ next_tick += jiffies;
+ mod_timer(&samp_timer, next_tick);
+}
+#endif
+
+
+/**
+ * netif_rx - post buffer to the network code
+ * @skb: buffer to post
+ *
+ * This function receives a packet from a device driver and queues it for
+ * the upper (protocol) levels to process. It always succeeds. The buffer
+ * may be dropped during processing for congestion control or by the
+ * protocol layers.
+ *
+ * return values:
+ * NET_RX_SUCCESS (no congestion)
+ * NET_RX_CN_LOW (low congestion)
+ * NET_RX_CN_MOD (moderate congestion)
+ * NET_RX_CN_HIGH (high congestion)
+ * NET_RX_DROP (packet was dropped)
+ *
+ */
+
+int netif_rx(struct sk_buff *skb)
+{
+ int this_cpu;
+ struct softnet_data *queue;
+ unsigned long flags;
+
+#ifdef CONFIG_NETPOLL
+ if (skb->dev->netpoll_rx && netpoll_rx(skb)) {
+ kfree_skb(skb);
+ return NET_RX_DROP;
+ }
+#endif
+
+ if (!skb->stamp.tv_sec)
+ net_timestamp(&skb->stamp);
+
+ /*
+ * The code is rearranged so that the path is the most
+ * short when CPU is congested, but is still operating.
+ */
+ local_irq_save(flags);
+ this_cpu = smp_processor_id();
+ queue = &__get_cpu_var(softnet_data);
+
+ __get_cpu_var(netdev_rx_stat).total++;
+ if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
+ if (queue->input_pkt_queue.qlen) {
+ if (queue->throttle)
+ goto drop;
+
+enqueue:
+ dev_hold(skb->dev);
+ __skb_queue_tail(&queue->input_pkt_queue, skb);
+#ifndef OFFLINE_SAMPLE
+ get_sample_stats(this_cpu);
+#endif
+ local_irq_restore(flags);
+ return queue->cng_level;
+ }
+
+ if (queue->throttle)
+ queue->throttle = 0;
+
+ netif_rx_schedule(&queue->backlog_dev);
+ goto enqueue;
+ }
+
+ if (!queue->throttle) {
+ queue->throttle = 1;
+ __get_cpu_var(netdev_rx_stat).throttled++;
+ }
+
+drop:
+ __get_cpu_var(netdev_rx_stat).dropped++;
+ local_irq_restore(flags);
+
+ kfree_skb(skb);
+ return NET_RX_DROP;
+}
+
+int netif_rx_ni(struct sk_buff *skb)
+{
+ int err;
+
+ preempt_disable();
+ err = netif_rx(skb);
+ if (local_softirq_pending())
+ do_softirq();
+ preempt_enable();
+
+ return err;
+}
+
+EXPORT_SYMBOL(netif_rx_ni);
+
+static __inline__ void skb_bond(struct sk_buff *skb)
+{
+ struct net_device *dev = skb->dev;
+
+ if (dev->master) {
+ skb->real_dev = skb->dev;
+ skb->dev = dev->master;
+ }
+}
+
+static void net_tx_action(struct softirq_action *h)
+{
+ struct softnet_data *sd = &__get_cpu_var(softnet_data);
+
+ if (sd->completion_queue) {
+ struct sk_buff *clist;
+
+ local_irq_disable();
+ clist = sd->completion_queue;
+ sd->completion_queue = NULL;
+ local_irq_enable();
+
+ while (clist) {
+ struct sk_buff *skb = clist;
+ clist = clist->next;
+
+ BUG_TRAP(!atomic_read(&skb->users));
+ __kfree_skb(skb);
+ }
+ }
+
+ if (sd->output_queue) {
+ struct net_device *head;
+
+ local_irq_disable();
+ head = sd->output_queue;
+ sd->output_queue = NULL;
+ local_irq_enable();
+
+ while (head) {
+ struct net_device *dev = head;
+ head = head->next_sched;
+
+ smp_mb__before_clear_bit();
+ clear_bit(__LINK_STATE_SCHED, &dev->state);
+
+ if (spin_trylock(&dev->queue_lock)) {
+ qdisc_run(dev);
+ spin_unlock(&dev->queue_lock);
+ } else {
+ netif_schedule(dev);
+ }
+ }
+ }
+}
+
+static __inline__ int deliver_skb(struct sk_buff *skb,
+ struct packet_type *pt_prev)
+{
+ atomic_inc(&skb->users);
+ return pt_prev->func(skb, skb->dev, pt_prev);
+}
+
+#if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE)
+int (*br_handle_frame_hook)(struct net_bridge_port *p, struct sk_buff **pskb);
+
+static __inline__ int handle_bridge(struct sk_buff **pskb,
+ struct packet_type **pt_prev, int *ret)
+{
+ struct net_bridge_port *port;
+
+ if ((*pskb)->pkt_type == PACKET_LOOPBACK ||
+ (port = rcu_dereference((*pskb)->dev->br_port)) == NULL)
+ return 0;
+
+ if (*pt_prev) {
+ *ret = deliver_skb(*pskb, *pt_prev);
+ *pt_prev = NULL;
+ }
+
+ return br_handle_frame_hook(port, pskb);
+}
+#else
+#define handle_bridge(skb, pt_prev, ret) (0)
+#endif
+
+#ifdef CONFIG_NET_CLS_ACT
+/* TODO: Maybe we should just force sch_ingress to be compiled in
+ * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions
+ * a compare and 2 stores extra right now if we dont have it on
+ * but have CONFIG_NET_CLS_ACT
+ * NOTE: This doesnt stop any functionality; if you dont have
+ * the ingress scheduler, you just cant add policies on ingress.
+ *
+ */
+static int ing_filter(struct sk_buff *skb)
+{
+ struct Qdisc *q;
+ struct net_device *dev = skb->dev;
+ int result = TC_ACT_OK;
+
+ if (dev->qdisc_ingress) {
+ __u32 ttl = (__u32) G_TC_RTTL(skb->tc_verd);
+ if (MAX_RED_LOOP < ttl++) {
+ printk("Redir loop detected Dropping packet (%s->%s)\n",
+
skb->input_dev?skb->input_dev->name:"??",skb->dev->name);
+ return TC_ACT_SHOT;
+ }
+
+ skb->tc_verd = SET_TC_RTTL(skb->tc_verd,ttl);
+
+ skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_INGRESS);
+ if (NULL == skb->input_dev) {
+ skb->input_dev = skb->dev;
+ printk("ing_filter: fixed %s out
%s\n",skb->input_dev->name,skb->dev->name);
+ }
+ spin_lock(&dev->ingress_lock);
+ if ((q = dev->qdisc_ingress) != NULL)
+ result = q->enqueue(skb, q);
+ spin_unlock(&dev->ingress_lock);
+
+ }
+
+ return result;
+}
+#endif
+
+int netif_receive_skb(struct sk_buff *skb)
+{
+ struct packet_type *ptype, *pt_prev;
+ int ret = NET_RX_DROP;
+ unsigned short type;
+
+#ifdef CONFIG_NETPOLL
+ if (skb->dev->netpoll_rx && skb->dev->poll && netpoll_rx(skb)) {
+ kfree_skb(skb);
+ return NET_RX_DROP;
+ }
+#endif
+
+ if (!skb->stamp.tv_sec)
+ net_timestamp(&skb->stamp);
+
+ skb_bond(skb);
+
+ __get_cpu_var(netdev_rx_stat).total++;
+
+ skb->h.raw = skb->nh.raw = skb->data;
+ skb->mac_len = skb->nh.raw - skb->mac.raw;
+
+ pt_prev = NULL;
+
+ rcu_read_lock();
+
+#ifdef CONFIG_NET_CLS_ACT
+ if (skb->tc_verd & TC_NCLS) {
+ skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
+ goto ncls;
+ }
+#endif
+
+ switch (skb->ip_summed) {
+ case CHECKSUM_UNNECESSARY:
+ skb->proto_csum_valid = 1;
+ break;
+ case CHECKSUM_HW:
+ /* XXX Implement me. */
+ default:
+ skb->proto_csum_valid = 0;
+ break;
+ }
+
+ list_for_each_entry_rcu(ptype, &ptype_all, list) {
+ if (!ptype->dev || ptype->dev == skb->dev) {
+ if (pt_prev)
+ ret = deliver_skb(skb, pt_prev);
+ pt_prev = ptype;
+ }
+ }
+
+#ifdef CONFIG_NET_CLS_ACT
+ if (pt_prev) {
+ ret = deliver_skb(skb, pt_prev);
+ pt_prev = NULL; /* noone else should process this after*/
+ } else {
+ skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
+ }
+
+ ret = ing_filter(skb);
+
+ if (ret == TC_ACT_SHOT || (ret == TC_ACT_STOLEN)) {
+ kfree_skb(skb);
+ goto out;
+ }
+
+ skb->tc_verd = 0;
+ncls:
+#endif
+
+ handle_diverter(skb);
+
+ if (handle_bridge(&skb, &pt_prev, &ret))
+ goto out;
+
+ type = skb->protocol;
+ list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type)&15], list) {
+ if (ptype->type == type &&
+ (!ptype->dev || ptype->dev == skb->dev)) {
+ if (pt_prev)
+ ret = deliver_skb(skb, pt_prev);
+ pt_prev = ptype;
+ }
+ }
+
+ if (pt_prev) {
+ ret = pt_prev->func(skb, skb->dev, pt_prev);
+ } else {
+ kfree_skb(skb);
+ /* Jamal, now you will not able to escape explaining
+ * me how you were going to use this. :-)
+ */
+ ret = NET_RX_DROP;
+ }
+
+out:
+ rcu_read_unlock();
+ return ret;
+}
+
+static int process_backlog(struct net_device *backlog_dev, int *budget)
+{
+ int work = 0;
+ int quota = min(backlog_dev->quota, *budget);
+ struct softnet_data *queue = &__get_cpu_var(softnet_data);
+ unsigned long start_time = jiffies;
+
+ for (;;) {
+ struct sk_buff *skb;
+ struct net_device *dev;
+
+ local_irq_disable();
+ skb = __skb_dequeue(&queue->input_pkt_queue);
+ if (!skb)
+ goto job_done;
+ local_irq_enable();
+
+ dev = skb->dev;
+
+ netif_receive_skb(skb);
+
+ dev_put(dev);
+
+ work++;
+
+ if (work >= quota || jiffies - start_time > 1)
+ break;
+
+ }
+
+ backlog_dev->quota -= work;
+ *budget -= work;
+ return -1;
+
+job_done:
+ backlog_dev->quota -= work;
+ *budget -= work;
+
+ list_del(&backlog_dev->poll_list);
+ smp_mb__before_clear_bit();
+ netif_poll_enable(backlog_dev);
+
+ if (queue->throttle)
+ queue->throttle = 0;
+ local_irq_enable();
+ return 0;
+}
+
+static void net_rx_action(struct softirq_action *h)
+{
+ struct softnet_data *queue = &__get_cpu_var(softnet_data);
+ unsigned long start_time = jiffies;
+ int budget = netdev_max_backlog;
+
+
+ local_irq_disable();
+
+ while (!list_empty(&queue->poll_list)) {
+ struct net_device *dev;
+
+ if (budget <= 0 || jiffies - start_time > 1)
+ goto softnet_break;
+
+ local_irq_enable();
+
+ dev = list_entry(queue->poll_list.next,
+ struct net_device, poll_list);
+
+ if (dev->quota <= 0 || dev->poll(dev, &budget)) {
+ local_irq_disable();
+ list_del(&dev->poll_list);
+ list_add_tail(&dev->poll_list, &queue->poll_list);
+ if (dev->quota < 0)
+ dev->quota += dev->weight;
+ else
+ dev->quota = dev->weight;
+ } else {
+ dev_put(dev);
+ local_irq_disable();
+ }
+ }
+out:
+ local_irq_enable();
+ return;
+
+softnet_break:
+ __get_cpu_var(netdev_rx_stat).time_squeeze++;
+ __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ goto out;
+}
+
+static gifconf_func_t * gifconf_list [NPROTO];
+
+/**
+ * register_gifconf - register a SIOCGIF handler
+ * @family: Address family
+ * @gifconf: Function handler
+ *
+ * Register protocol dependent address dumping routines. The handler
+ * that is passed must not be freed or reused until it has been replaced
+ * by another handler.
+ */
+int register_gifconf(unsigned int family, gifconf_func_t * gifconf)
+{
+ if (family >= NPROTO)
+ return -EINVAL;
+ gifconf_list[family] = gifconf;
+ return 0;
+}
+
+
+/*
+ * Map an interface index to its name (SIOCGIFNAME)
+ */
+
+/*
+ * We need this ioctl for efficient implementation of the
+ * if_indextoname() function required by the IPv6 API. Without
+ * it, we would have to search all the interfaces to find a
+ * match. --pb
+ */
+
+static int dev_ifname(struct ifreq __user *arg)
+{
+ struct net_device *dev;
+ struct ifreq ifr;
+
+ /*
+ * Fetch the caller's info block.
+ */
+
+ if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
+ return -EFAULT;
+
+ read_lock(&dev_base_lock);
+ dev = __dev_get_by_index(ifr.ifr_ifindex);
+ if (!dev) {
+ read_unlock(&dev_base_lock);
+ return -ENODEV;
+ }
+
+ strcpy(ifr.ifr_name, dev->name);
+ read_unlock(&dev_base_lock);
+
+ if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
+ return -EFAULT;
+ return 0;
+}
+
+/*
+ * Perform a SIOCGIFCONF call. This structure will change
+ * size eventually, and there is nothing I can do about it.
+ * Thus we will need a 'compatibility mode'.
+ */
+
+static int dev_ifconf(char __user *arg)
+{
+ struct ifconf ifc;
+ struct net_device *dev;
+ char __user *pos;
+ int len;
+ int total;
+ int i;
+
+ /*
+ * Fetch the caller's info block.
+ */
+
+ if (copy_from_user(&ifc, arg, sizeof(struct ifconf)))
+ return -EFAULT;
+
+ pos = ifc.ifc_buf;
+ len = ifc.ifc_len;
+
+ /*
+ * Loop over the interfaces, and write an info block for each.
+ */
+
+ total = 0;
+ for (dev = dev_base; dev; dev = dev->next) {
+ for (i = 0; i < NPROTO; i++) {
+ if (gifconf_list[i]) {
+ int done;
+ if (!pos)
+ done = gifconf_list[i](dev, NULL, 0);
+ else
+ done = gifconf_list[i](dev, pos + total,
+ len - total);
+ if (done < 0)
+ return -EFAULT;
+ total += done;
+ }
+ }
+ }
+
+ /*
+ * All done. Write the updated control block back to the caller.
+ */
+ ifc.ifc_len = total;
+
+ /*
+ * Both BSD and Solaris return 0 here, so we do too.
+ */
+ return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0;
+}
+
+#ifdef CONFIG_PROC_FS
+/*
+ * This is invoked by the /proc filesystem handler to display a device
+ * in detail.
+ */
+static __inline__ struct net_device *dev_get_idx(loff_t pos)
+{
+ struct net_device *dev;
+ loff_t i;
+
+ for (i = 0, dev = dev_base; dev && i < pos; ++i, dev = dev->next);
+
+ return i == pos ? dev : NULL;
+}
+
+void *dev_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ read_lock(&dev_base_lock);
+ return *pos ? dev_get_idx(*pos - 1) : SEQ_START_TOKEN;
+}
+
+void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ ++*pos;
+ return v == SEQ_START_TOKEN ? dev_base : ((struct net_device *)v)->next;
+}
+
+void dev_seq_stop(struct seq_file *seq, void *v)
+{
+ read_unlock(&dev_base_lock);
+}
+
+static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
+{
+ if (dev->get_stats) {
+ struct net_device_stats *stats = dev->get_stats(dev);
+
+ seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
+ "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
+ dev->name, stats->rx_bytes, stats->rx_packets,
+ stats->rx_errors,
+ stats->rx_dropped + stats->rx_missed_errors,
+ stats->rx_fifo_errors,
+ stats->rx_length_errors + stats->rx_over_errors +
+ stats->rx_crc_errors + stats->rx_frame_errors,
+ stats->rx_compressed, stats->multicast,
+ stats->tx_bytes, stats->tx_packets,
+ stats->tx_errors, stats->tx_dropped,
+ stats->tx_fifo_errors, stats->collisions,
+ stats->tx_carrier_errors +
+ stats->tx_aborted_errors +
+ stats->tx_window_errors +
+ stats->tx_heartbeat_errors,
+ stats->tx_compressed);
+ } else
+ seq_printf(seq, "%6s: No statistics available.\n", dev->name);
+}
+
+/*
+ * Called from the PROCfs module. This now uses the new arbitrary sized
+ * /proc/net interface to create /proc/net/dev
+ */
+static int dev_seq_show(struct seq_file *seq, void *v)
+{
+ if (v == SEQ_START_TOKEN)
+ seq_puts(seq, "Inter-| Receive "
+ " | Transmit\n"
+ " face |bytes packets errs drop fifo frame "
+ "compressed multicast|bytes packets errs "
+ "drop fifo colls carrier compressed\n");
+ else
+ dev_seq_printf_stats(seq, v);
+ return 0;
+}
+
+static struct netif_rx_stats *softnet_get_online(loff_t *pos)
+{
+ struct netif_rx_stats *rc = NULL;
+
+ while (*pos < NR_CPUS)
+ if (cpu_online(*pos)) {
+ rc = &per_cpu(netdev_rx_stat, *pos);
+ break;
+ } else
+ ++*pos;
+ return rc;
+}
+
+static void *softnet_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ return softnet_get_online(pos);
+}
+
+static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ ++*pos;
+ return softnet_get_online(pos);
+}
+
+static void softnet_seq_stop(struct seq_file *seq, void *v)
+{
+}
+
+static int softnet_seq_show(struct seq_file *seq, void *v)
+{
+ struct netif_rx_stats *s = v;
+
+ seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
+ s->total, s->dropped, s->time_squeeze, s->throttled,
+ s->fastroute_hit, s->fastroute_success, s->fastroute_defer,
+ s->fastroute_deferred_out,
+#if 0
+ s->fastroute_latency_reduction
+#else
+ s->cpu_collision
+#endif
+ );
+ return 0;
+}
+
+static struct seq_operations dev_seq_ops = {
+ .start = dev_seq_start,
+ .next = dev_seq_next,
+ .stop = dev_seq_stop,
+ .show = dev_seq_show,
+};
+
+static int dev_seq_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &dev_seq_ops);
+}
+
+static struct file_operations dev_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = dev_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static struct seq_operations softnet_seq_ops = {
+ .start = softnet_seq_start,
+ .next = softnet_seq_next,
+ .stop = softnet_seq_stop,
+ .show = softnet_seq_show,
+};
+
+static int softnet_seq_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &softnet_seq_ops);
+}
+
+static struct file_operations softnet_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = softnet_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+#ifdef WIRELESS_EXT
+extern int wireless_proc_init(void);
+#else
+#define wireless_proc_init() 0
+#endif
+
+static int __init dev_proc_init(void)
+{
+ int rc = -ENOMEM;
+
+ if (!proc_net_fops_create("dev", S_IRUGO, &dev_seq_fops))
+ goto out;
+ if (!proc_net_fops_create("softnet_stat", S_IRUGO, &softnet_seq_fops))
+ goto out_dev;
+ if (wireless_proc_init())
+ goto out_softnet;
+ rc = 0;
+out:
+ return rc;
+out_softnet:
+ proc_net_remove("softnet_stat");
+out_dev:
+ proc_net_remove("dev");
+ goto out;
+}
+#else
+#define dev_proc_init() 0
+#endif /* CONFIG_PROC_FS */
+
+
+/**
+ * netdev_set_master - set up master/slave pair
+ * @slave: slave device
+ * @master: new master device
+ *
+ * Changes the master device of the slave. Pass %NULL to break the
+ * bonding. The caller must hold the RTNL semaphore. On a failure
+ * a negative errno code is returned. On success the reference counts
+ * are adjusted, %RTM_NEWLINK is sent to the routing socket and the
+ * function returns zero.
+ */
+int netdev_set_master(struct net_device *slave, struct net_device *master)
+{
+ struct net_device *old = slave->master;
+
+ ASSERT_RTNL();
+
+ if (master) {
+ if (old)
+ return -EBUSY;
+ dev_hold(master);
+ }
+
+ slave->master = master;
+
+ synchronize_net();
+
+ if (old)
+ dev_put(old);
+
+ if (master)
+ slave->flags |= IFF_SLAVE;
+ else
+ slave->flags &= ~IFF_SLAVE;
+
+ rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE);
+ return 0;
+}
+
+/**
+ * dev_set_promiscuity - update promiscuity count on a device
+ * @dev: device
+ * @inc: modifier
+ *
+ * Add or remove promsicuity from a device. While the count in the device
+ * remains above zero the interface remains promiscuous. Once it hits zero
+ * the device reverts back to normal filtering operation. A negative inc
+ * value is used to drop promiscuity on the device.
+ */
+void dev_set_promiscuity(struct net_device *dev, int inc)
+{
+ unsigned short old_flags = dev->flags;
+
+ dev->flags |= IFF_PROMISC;
+ if ((dev->promiscuity += inc) == 0)
+ dev->flags &= ~IFF_PROMISC;
+ if (dev->flags ^ old_flags) {
+ dev_mc_upload(dev);
+ printk(KERN_INFO "device %s %s promiscuous mode\n",
+ dev->name, (dev->flags & IFF_PROMISC) ? "entered" :
+ "left");
+ }
+}
+
+/**
+ * dev_set_allmulti - update allmulti count on a device
+ * @dev: device
+ * @inc: modifier
+ *
+ * Add or remove reception of all multicast frames to a device. While the
+ * count in the device remains above zero the interface remains listening
+ * to all interfaces. Once it hits zero the device reverts back to normal
+ * filtering operation. A negative @inc value is used to drop the counter
+ * when releasing a resource needing all multicasts.
+ */
+
+void dev_set_allmulti(struct net_device *dev, int inc)
+{
+ unsigned short old_flags = dev->flags;
+
+ dev->flags |= IFF_ALLMULTI;
+ if ((dev->allmulti += inc) == 0)
+ dev->flags &= ~IFF_ALLMULTI;
+ if (dev->flags ^ old_flags)
+ dev_mc_upload(dev);
+}
+
+unsigned dev_get_flags(const struct net_device *dev)
+{
+ unsigned flags;
+
+ flags = (dev->flags & ~(IFF_PROMISC |
+ IFF_ALLMULTI |
+ IFF_RUNNING)) |
+ (dev->gflags & (IFF_PROMISC |
+ IFF_ALLMULTI));
+
+ if (netif_running(dev) && netif_carrier_ok(dev))
+ flags |= IFF_RUNNING;
+
+ return flags;
+}
+
+int dev_change_flags(struct net_device *dev, unsigned flags)
+{
+ int ret;
+ int old_flags = dev->flags;
+
+ /*
+ * Set the flags on our device.
+ */
+
+ dev->flags = (flags & (IFF_DEBUG | IFF_NOTRAILERS | IFF_NOARP |
+ IFF_DYNAMIC | IFF_MULTICAST | IFF_PORTSEL |
+ IFF_AUTOMEDIA)) |
+ (dev->flags & (IFF_UP | IFF_VOLATILE | IFF_PROMISC |
+ IFF_ALLMULTI));
+
+ /*
+ * Load in the correct multicast list now the flags have changed.
+ */
+
+ dev_mc_upload(dev);
+
+ /*
+ * Have we downed the interface. We handle IFF_UP ourselves
+ * according to user attempts to set it, rather than blindly
+ * setting it.
+ */
+
+ ret = 0;
+ if ((old_flags ^ flags) & IFF_UP) { /* Bit is different ? */
+ ret = ((old_flags & IFF_UP) ? dev_close : dev_open)(dev);
+
+ if (!ret)
+ dev_mc_upload(dev);
+ }
+
+ if (dev->flags & IFF_UP &&
+ ((old_flags ^ dev->flags) &~ (IFF_UP | IFF_PROMISC | IFF_ALLMULTI |
+ IFF_VOLATILE)))
+ notifier_call_chain(&netdev_chain, NETDEV_CHANGE, dev);
+
+ if ((flags ^ dev->gflags) & IFF_PROMISC) {
+ int inc = (flags & IFF_PROMISC) ? +1 : -1;
+ dev->gflags ^= IFF_PROMISC;
+ dev_set_promiscuity(dev, inc);
+ }
+
+ /* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI
+ is important. Some (broken) drivers set IFF_PROMISC, when
+ IFF_ALLMULTI is requested not asking us and not reporting.
+ */
+ if ((flags ^ dev->gflags) & IFF_ALLMULTI) {
+ int inc = (flags & IFF_ALLMULTI) ? +1 : -1;
+ dev->gflags ^= IFF_ALLMULTI;
+ dev_set_allmulti(dev, inc);
+ }
+
+ if (old_flags ^ dev->flags)
+ rtmsg_ifinfo(RTM_NEWLINK, dev, old_flags ^ dev->flags);
+
+ return ret;
+}
+
+int dev_set_mtu(struct net_device *dev, int new_mtu)
+{
+ int err;
+
+ if (new_mtu == dev->mtu)
+ return 0;
+
+ /* MTU must be positive. */
+ if (new_mtu < 0)
+ return -EINVAL;
+
+ if (!netif_device_present(dev))
+ return -ENODEV;
+
+ err = 0;
+ if (dev->change_mtu)
+ err = dev->change_mtu(dev, new_mtu);
+ else
+ dev->mtu = new_mtu;
+ if (!err && dev->flags & IFF_UP)
+ notifier_call_chain(&netdev_chain,
+ NETDEV_CHANGEMTU, dev);
+ return err;
+}
+
+
+/*
+ * Perform the SIOCxIFxxx calls.
+ */
+static int dev_ifsioc(struct ifreq *ifr, unsigned int cmd)
+{
+ int err;
+ struct net_device *dev = __dev_get_by_name(ifr->ifr_name);
+
+ if (!dev)
+ return -ENODEV;
+
+ switch (cmd) {
+ case SIOCGIFFLAGS: /* Get interface flags */
+ ifr->ifr_flags = dev_get_flags(dev);
+ return 0;
+
+ case SIOCSIFFLAGS: /* Set interface flags */
+ return dev_change_flags(dev, ifr->ifr_flags);
+
+ case SIOCGIFMETRIC: /* Get the metric on the interface
+ (currently unused) */
+ ifr->ifr_metric = 0;
+ return 0;
+
+ case SIOCSIFMETRIC: /* Set the metric on the interface
+ (currently unused) */
+ return -EOPNOTSUPP;
+
+ case SIOCGIFMTU: /* Get the MTU of a device */
+ ifr->ifr_mtu = dev->mtu;
+ return 0;
+
+ case SIOCSIFMTU: /* Set the MTU of a device */
+ return dev_set_mtu(dev, ifr->ifr_mtu);
+
+ case SIOCGIFHWADDR:
+ if (!dev->addr_len)
+ memset(ifr->ifr_hwaddr.sa_data, 0, sizeof
ifr->ifr_hwaddr.sa_data);
+ else
+ memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
+ min(sizeof ifr->ifr_hwaddr.sa_data,
(size_t) dev->addr_len));
+ ifr->ifr_hwaddr.sa_family = dev->type;
+ return 0;
+
+ case SIOCSIFHWADDR:
+ if (!dev->set_mac_address)
+ return -EOPNOTSUPP;
+ if (ifr->ifr_hwaddr.sa_family != dev->type)
+ return -EINVAL;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ err = dev->set_mac_address(dev, &ifr->ifr_hwaddr);
+ if (!err)
+ notifier_call_chain(&netdev_chain,
+ NETDEV_CHANGEADDR, dev);
+ return err;
+
+ case SIOCSIFHWBROADCAST:
+ if (ifr->ifr_hwaddr.sa_family != dev->type)
+ return -EINVAL;
+ memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
+ min(sizeof ifr->ifr_hwaddr.sa_data, (size_t)
dev->addr_len));
+ notifier_call_chain(&netdev_chain,
+ NETDEV_CHANGEADDR, dev);
+ return 0;
+
+ case SIOCGIFMAP:
+ ifr->ifr_map.mem_start = dev->mem_start;
+ ifr->ifr_map.mem_end = dev->mem_end;
+ ifr->ifr_map.base_addr = dev->base_addr;
+ ifr->ifr_map.irq = dev->irq;
+ ifr->ifr_map.dma = dev->dma;
+ ifr->ifr_map.port = dev->if_port;
+ return 0;
+
+ case SIOCSIFMAP:
+ if (dev->set_config) {
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return dev->set_config(dev, &ifr->ifr_map);
+ }
+ return -EOPNOTSUPP;
+
+ case SIOCADDMULTI:
+ if (!dev->set_multicast_list ||
+ ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+ return -EINVAL;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data,
+ dev->addr_len, 1);
+
+ case SIOCDELMULTI:
+ if (!dev->set_multicast_list ||
+ ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+ return -EINVAL;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data,
+ dev->addr_len, 1);
+
+ case SIOCGIFINDEX:
+ ifr->ifr_ifindex = dev->ifindex;
+ return 0;
+
+ case SIOCGIFTXQLEN:
+ ifr->ifr_qlen = dev->tx_queue_len;
+ return 0;
+
+ case SIOCSIFTXQLEN:
+ if (ifr->ifr_qlen < 0)
+ return -EINVAL;
+ dev->tx_queue_len = ifr->ifr_qlen;
+ return 0;
+
+ case SIOCSIFNAME:
+ ifr->ifr_newname[IFNAMSIZ-1] = '\0';
+ return dev_change_name(dev, ifr->ifr_newname);
+
+ /*
+ * Unknown or private ioctl
+ */
+
+ default:
+ if ((cmd >= SIOCDEVPRIVATE &&
+ cmd <= SIOCDEVPRIVATE + 15) ||
+ cmd == SIOCBONDENSLAVE ||
+ cmd == SIOCBONDRELEASE ||
+ cmd == SIOCBONDSETHWADDR ||
+ cmd == SIOCBONDSLAVEINFOQUERY ||
+ cmd == SIOCBONDINFOQUERY ||
+ cmd == SIOCBONDCHANGEACTIVE ||
+ cmd == SIOCGMIIPHY ||
+ cmd == SIOCGMIIREG ||
+ cmd == SIOCSMIIREG ||
+ cmd == SIOCBRADDIF ||
+ cmd == SIOCBRDELIF ||
+ cmd == SIOCWANDEV) {
+ err = -EOPNOTSUPP;
+ if (dev->do_ioctl) {
+ if (netif_device_present(dev))
+ err = dev->do_ioctl(dev, ifr,
+ cmd);
+ else
+ err = -ENODEV;
+ }
+ } else
+ err = -EINVAL;
+
+ }
+ return err;
+}
+
+/*
+ * This function handles all "interface"-type I/O control requests. The
actual
+ * 'doing' part of this is dev_ifsioc above.
+ */
+
+/**
+ * dev_ioctl - network device ioctl
+ * @cmd: command to issue
+ * @arg: pointer to a struct ifreq in user space
+ *
+ * Issue ioctl functions to devices. This is normally called by the
+ * user space syscall interfaces but can sometimes be useful for
+ * other purposes. The return value is the return from the syscall if
+ * positive or a negative errno code on error.
+ */
+
+int dev_ioctl(unsigned int cmd, void __user *arg)
+{
+ struct ifreq ifr;
+ int ret;
+ char *colon;
+
+ /* One special case: SIOCGIFCONF takes ifconf argument
+ and requires shared lock, because it sleeps writing
+ to user space.
+ */
+
+ if (cmd == SIOCGIFCONF) {
+ rtnl_shlock();
+ ret = dev_ifconf((char __user *) arg);
+ rtnl_shunlock();
+ return ret;
+ }
+ if (cmd == SIOCGIFNAME)
+ return dev_ifname((struct ifreq __user *)arg);
+
+ if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
+ return -EFAULT;
+
+ ifr.ifr_name[IFNAMSIZ-1] = 0;
+
+ colon = strchr(ifr.ifr_name, ':');
+ if (colon)
+ *colon = 0;
+
+ /*
+ * See which interface the caller is talking about.
+ */
+
+ switch (cmd) {
+ /*
+ * These ioctl calls:
+ * - can be done by all.
+ * - atomic and do not require locking.
+ * - return a value
+ */
+ case SIOCGIFFLAGS:
+ case SIOCGIFMETRIC:
+ case SIOCGIFMTU:
+ case SIOCGIFHWADDR:
+ case SIOCGIFSLAVE:
+ case SIOCGIFMAP:
+ case SIOCGIFINDEX:
+ case SIOCGIFTXQLEN:
+ dev_load(ifr.ifr_name);
+ read_lock(&dev_base_lock);
+ ret = dev_ifsioc(&ifr, cmd);
+ read_unlock(&dev_base_lock);
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
+
+ case SIOCETHTOOL:
+ dev_load(ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ethtool(&ifr);
+ rtnl_unlock();
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
+
+ /*
+ * These ioctl calls:
+ * - require superuser power.
+ * - require strict serialization.
+ * - return a value
+ */
+ case SIOCGMIIPHY:
+ case SIOCGMIIREG:
+ case SIOCSIFNAME:
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ dev_load(ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ifsioc(&ifr, cmd);
+ rtnl_unlock();
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
+
+ /*
+ * These ioctl calls:
+ * - require superuser power.
+ * - require strict serialization.
+ * - do not return a value
+ */
+ case SIOCSIFFLAGS:
+ case SIOCSIFMETRIC:
+ case SIOCSIFMTU:
+ case SIOCSIFMAP:
+ case SIOCSIFHWADDR:
+ case SIOCSIFSLAVE:
+ case SIOCADDMULTI:
+ case SIOCDELMULTI:
+ case SIOCSIFHWBROADCAST:
+ case SIOCSIFTXQLEN:
+ case SIOCSMIIREG:
+ case SIOCBONDENSLAVE:
+ case SIOCBONDRELEASE:
+ case SIOCBONDSETHWADDR:
+ case SIOCBONDSLAVEINFOQUERY:
+ case SIOCBONDINFOQUERY:
+ case SIOCBONDCHANGEACTIVE:
+ case SIOCBRADDIF:
+ case SIOCBRDELIF:
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ dev_load(ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ifsioc(&ifr, cmd);
+ rtnl_unlock();
+ return ret;
+
+ case SIOCGIFMEM:
+ /* Get the per device memory space. We can add this but
+ * currently do not support it */
+ case SIOCSIFMEM:
+ /* Set the per device memory buffer space.
+ * Not applicable in our case */
+ case SIOCSIFLINK:
+ return -EINVAL;
+
+ /*
+ * Unknown or private ioctl.
+ */
+ default:
+ if (cmd == SIOCWANDEV ||
+ (cmd >= SIOCDEVPRIVATE &&
+ cmd <= SIOCDEVPRIVATE + 15)) {
+ dev_load(ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ifsioc(&ifr, cmd);
+ rtnl_unlock();
+ if (!ret && copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ return ret;
+ }
+#ifdef WIRELESS_EXT
+ /* Take care of Wireless Extensions */
+ if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) {
+ /* If command is `set a parameter', or
+ * `get the encoding parameters', check if
+ * the user has the right to do it */
+ if (IW_IS_SET(cmd) || cmd == SIOCGIWENCODE) {
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ }
+ dev_load(ifr.ifr_name);
+ rtnl_lock();
+ /* Follow me in net/core/wireless.c */
+ ret = wireless_process_ioctl(&ifr, cmd);
+ rtnl_unlock();
+ if (IW_IS_GET(cmd) &&
+ copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ return ret;
+ }
+#endif /* WIRELESS_EXT */
+ return -EINVAL;
+ }
+}
+
+
+/**
+ * dev_new_index - allocate an ifindex
+ *
+ * Returns a suitable unique value for a new device interface
+ * number. The caller must hold the rtnl semaphore or the
+ * dev_base_lock to be sure it remains unique.
+ */
+static int dev_new_index(void)
+{
+ static int ifindex;
+ for (;;) {
+ if (++ifindex <= 0)
+ ifindex = 1;
+ if (!__dev_get_by_index(ifindex))
+ return ifindex;
+ }
+}
+
+static int dev_boot_phase = 1;
+
+/* Delayed registration/unregisteration */
+static DEFINE_SPINLOCK(net_todo_list_lock);
+static struct list_head net_todo_list = LIST_HEAD_INIT(net_todo_list);
+
+static inline void net_set_todo(struct net_device *dev)
+{
+ spin_lock(&net_todo_list_lock);
+ list_add_tail(&dev->todo_list, &net_todo_list);
+ spin_unlock(&net_todo_list_lock);
+}
+
+/**
+ * register_netdevice - register a network device
+ * @dev: device to register
+ *
+ * Take a completed network device structure and add it to the kernel
+ * interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier
+ * chain. 0 is returned on success. A negative errno code is returned
+ * on a failure to set up the device, or if the name is a duplicate.
+ *
+ * Callers must hold the rtnl semaphore. You may want
+ * register_netdev() instead of this.
+ *
+ * BUGS:
+ * The locking appears insufficient to guarantee two parallel registers
+ * will not get the same name.
+ */
+
+int register_netdevice(struct net_device *dev)
+{
+ struct hlist_head *head;
+ struct hlist_node *p;
+ int ret;
+
+ BUG_ON(dev_boot_phase);
+ ASSERT_RTNL();
+
+ /* When net_device's are persistent, this will be fatal. */
+ BUG_ON(dev->reg_state != NETREG_UNINITIALIZED);
+
+ spin_lock_init(&dev->queue_lock);
+ spin_lock_init(&dev->xmit_lock);
+ dev->xmit_lock_owner = -1;
+#ifdef CONFIG_NET_CLS_ACT
+ spin_lock_init(&dev->ingress_lock);
+#endif
+
+ ret = alloc_divert_blk(dev);
+ if (ret)
+ goto out;
+
+ dev->iflink = -1;
+
+ /* Init, if this function is available */
+ if (dev->init) {
+ ret = dev->init(dev);
+ if (ret) {
+ if (ret > 0)
+ ret = -EIO;
+ goto out_err;
+ }
+ }
+
+ if (!dev_valid_name(dev->name)) {
+ ret = -EINVAL;
+ goto out_err;
+ }
+
+ dev->ifindex = dev_new_index();
+ if (dev->iflink == -1)
+ dev->iflink = dev->ifindex;
+
+ /* Check for existence of name */
+ head = dev_name_hash(dev->name);
+ hlist_for_each(p, head) {
+ struct net_device *d
+ = hlist_entry(p, struct net_device, name_hlist);
+ if (!strncmp(d->name, dev->name, IFNAMSIZ)) {
+ ret = -EEXIST;
+ goto out_err;
+ }
+ }
+
+ /* Fix illegal SG+CSUM combinations. */
+ if ((dev->features & NETIF_F_SG) &&
+ !(dev->features & (NETIF_F_IP_CSUM |
+ NETIF_F_NO_CSUM |
+ NETIF_F_HW_CSUM))) {
+ printk("%s: Dropping NETIF_F_SG since no checksum feature.\n",
+ dev->name);
+ dev->features &= ~NETIF_F_SG;
+ }
+
+ /* TSO requires that SG is present as well. */
+ if ((dev->features & NETIF_F_TSO) &&
+ !(dev->features & NETIF_F_SG)) {
+ printk("%s: Dropping NETIF_F_TSO since no SG feature.\n",
+ dev->name);
+ dev->features &= ~NETIF_F_TSO;
+ }
+
+ /*
+ * nil rebuild_header routine,
+ * that should be never called and used as just bug trap.
+ */
+
+ if (!dev->rebuild_header)
+ dev->rebuild_header = default_rebuild_header;
+
+ /*
+ * Default initial state at registry is that the
+ * device is present.
+ */
+
+ set_bit(__LINK_STATE_PRESENT, &dev->state);
+
+ dev->next = NULL;
+ dev_init_scheduler(dev);
+ write_lock_bh(&dev_base_lock);
+ *dev_tail = dev;
+ dev_tail = &dev->next;
+ hlist_add_head(&dev->name_hlist, head);
+ hlist_add_head(&dev->index_hlist, dev_index_hash(dev->ifindex));
+ dev_hold(dev);
+ dev->reg_state = NETREG_REGISTERING;
+ write_unlock_bh(&dev_base_lock);
+
+ /* Notify protocols, that a new device appeared. */
+ notifier_call_chain(&netdev_chain, NETDEV_REGISTER, dev);
+
+ /* Finish registration after unlock */
+ net_set_todo(dev);
+ ret = 0;
+
+out:
+ return ret;
+out_err:
+ free_divert_blk(dev);
+ goto out;
+}
+
+/**
+ * register_netdev - register a network device
+ * @dev: device to register
+ *
+ * Take a completed network device structure and add it to the kernel
+ * interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier
+ * chain. 0 is returned on success. A negative errno code is returned
+ * on a failure to set up the device, or if the name is a duplicate.
+ *
+ * This is a wrapper around register_netdev that takes the rtnl semaphore
+ * and expands the device name if you passed a format string to
+ * alloc_netdev.
+ */
+int register_netdev(struct net_device *dev)
+{
+ int err;
+
+ rtnl_lock();
+
+ /*
+ * If the name is a format string the caller wants us to do a
+ * name allocation.
+ */
+ if (strchr(dev->name, '%')) {
+ err = dev_alloc_name(dev, dev->name);
+ if (err < 0)
+ goto out;
+ }
+
+ /*
+ * Back compatibility hook. Kill this one in 2.5
+ */
+ if (dev->name[0] == 0 || dev->name[0] == ' ') {
+ err = dev_alloc_name(dev, "eth%d");
+ if (err < 0)
+ goto out;
+ }
+
+ err = register_netdevice(dev);
+out:
+ rtnl_unlock();
+ return err;
+}
+EXPORT_SYMBOL(register_netdev);
+
+/*
+ * netdev_wait_allrefs - wait until all references are gone.
+ *
+ * This is called when unregistering network devices.
+ *
+ * Any protocol or device that holds a reference should register
+ * for netdevice notification, and cleanup and put back the
+ * reference if they receive an UNREGISTER event.
+ * We can get stuck here if buggy protocols don't correctly
+ * call dev_put.
+ */
+static void netdev_wait_allrefs(struct net_device *dev)
+{
+ unsigned long rebroadcast_time, warning_time;
+
+ rebroadcast_time = warning_time = jiffies;
+ while (atomic_read(&dev->refcnt) != 0) {
+ if (time_after(jiffies, rebroadcast_time + 1 * HZ)) {
+ rtnl_shlock();
+
+ /* Rebroadcast unregister notification */
+ notifier_call_chain(&netdev_chain,
+ NETDEV_UNREGISTER, dev);
+
+ if (test_bit(__LINK_STATE_LINKWATCH_PENDING,
+ &dev->state)) {
+ /* We must not have linkwatch events
+ * pending on unregister. If this
+ * happens, we simply run the queue
+ * unscheduled, resulting in a noop
+ * for this device.
+ */
+ linkwatch_run_queue();
+ }
+
+ rtnl_shunlock();
+
+ rebroadcast_time = jiffies;
+ }
+
+ msleep(250);
+
+ if (time_after(jiffies, warning_time + 10 * HZ)) {
+ printk(KERN_EMERG "unregister_netdevice: "
+ "waiting for %s to become free. Usage "
+ "count = %d\n",
+ dev->name, atomic_read(&dev->refcnt));
+ warning_time = jiffies;
+ }
+ }
+}
+
+/* The sequence is:
+ *
+ * rtnl_lock();
+ * ...
+ * register_netdevice(x1);
+ * register_netdevice(x2);
+ * ...
+ * unregister_netdevice(y1);
+ * unregister_netdevice(y2);
+ * ...
+ * rtnl_unlock();
+ * free_netdev(y1);
+ * free_netdev(y2);
+ *
+ * We are invoked by rtnl_unlock() after it drops the semaphore.
+ * This allows us to deal with problems:
+ * 1) We can create/delete sysfs objects which invoke hotplug
+ * without deadlocking with linkwatch via keventd.
+ * 2) Since we run with the RTNL semaphore not held, we can sleep
+ * safely in order to wait for the netdev refcnt to drop to zero.
+ */
+static DECLARE_MUTEX(net_todo_run_mutex);
+void netdev_run_todo(void)
+{
+ struct list_head list = LIST_HEAD_INIT(list);
+ int err;
+
+
+ /* Need to guard against multiple cpu's getting out of order. */
+ down(&net_todo_run_mutex);
+
+ /* Not safe to do outside the semaphore. We must not return
+ * until all unregister events invoked by the local processor
+ * have been completed (either by this todo run, or one on
+ * another cpu).
+ */
+ if (list_empty(&net_todo_list))
+ goto out;
+
+ /* Snapshot list, allow later requests */
+ spin_lock(&net_todo_list_lock);
+ list_splice_init(&net_todo_list, &list);
+ spin_unlock(&net_todo_list_lock);
+
+ while (!list_empty(&list)) {
+ struct net_device *dev
+ = list_entry(list.next, struct net_device, todo_list);
+ list_del(&dev->todo_list);
+
+ switch(dev->reg_state) {
+ case NETREG_REGISTERING:
+ err = netdev_register_sysfs(dev);
+ if (err)
+ printk(KERN_ERR "%s: failed sysfs registration
(%d)\n",
+ dev->name, err);
+ dev->reg_state = NETREG_REGISTERED;
+ break;
+
+ case NETREG_UNREGISTERING:
+ netdev_unregister_sysfs(dev);
+ dev->reg_state = NETREG_UNREGISTERED;
+
+ netdev_wait_allrefs(dev);
+
+ /* paranoia */
+ BUG_ON(atomic_read(&dev->refcnt));
+ BUG_TRAP(!dev->ip_ptr);
+ BUG_TRAP(!dev->ip6_ptr);
+ BUG_TRAP(!dev->dn_ptr);
+
+
+ /* It must be the very last action,
+ * after this 'dev' may point to freed up memory.
+ */
+ if (dev->destructor)
+ dev->destructor(dev);
+ break;
+
+ default:
+ printk(KERN_ERR "network todo '%s' but state %d\n",
+ dev->name, dev->reg_state);
+ break;
+ }
+ }
+
+out:
+ up(&net_todo_run_mutex);
+}
+
+/**
+ * alloc_netdev - allocate network device
+ * @sizeof_priv: size of private data to allocate space for
+ * @name: device name format string
+ * @setup: callback to initialize device
+ *
+ * Allocates a struct net_device with private data area for driver use
+ * and performs basic initialization.
+ */
+struct net_device *alloc_netdev(int sizeof_priv, const char *name,
+ void (*setup)(struct net_device *))
+{
+ void *p;
+ struct net_device *dev;
+ int alloc_size;
+
+ /* ensure 32-byte alignment of both the device and private area */
+ alloc_size = (sizeof(*dev) + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST;
+ alloc_size += sizeof_priv + NETDEV_ALIGN_CONST;
+
+ p = kmalloc(alloc_size, GFP_KERNEL);
+ if (!p) {
+ printk(KERN_ERR "alloc_dev: Unable to allocate device.\n");
+ return NULL;
+ }
+ memset(p, 0, alloc_size);
+
+ dev = (struct net_device *)
+ (((long)p + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST);
+ dev->padded = (char *)dev - (char *)p;
+
+ if (sizeof_priv)
+ dev->priv = netdev_priv(dev);
+
+ setup(dev);
+ strcpy(dev->name, name);
+ return dev;
+}
+EXPORT_SYMBOL(alloc_netdev);
+
+/**
+ * free_netdev - free network device
+ * @dev: device
+ *
+ * This function does the last stage of destroying an allocated device
+ * interface. The reference to the device object is released.
+ * If this is the last reference then it will be freed.
+ */
+void free_netdev(struct net_device *dev)
+{
+#ifdef CONFIG_SYSFS
+ /* Compatiablity with error handling in drivers */
+ if (dev->reg_state == NETREG_UNINITIALIZED) {
+ kfree((char *)dev - dev->padded);
+ return;
+ }
+
+ BUG_ON(dev->reg_state != NETREG_UNREGISTERED);
+ dev->reg_state = NETREG_RELEASED;
+
+ /* will free via class release */
+ class_device_put(&dev->class_dev);
+#else
+ kfree((char *)dev - dev->padded);
+#endif
+}
+
+/* Synchronize with packet receive processing. */
+void synchronize_net(void)
+{
+ might_sleep();
+ synchronize_kernel();
+}
+
+/**
+ * unregister_netdevice - remove device from the kernel
+ * @dev: device
+ *
+ * This function shuts down a device interface and removes it
+ * from the kernel tables. On success 0 is returned, on a failure
+ * a negative errno code is returned.
+ *
+ * Callers must hold the rtnl semaphore. You may want
+ * unregister_netdev() instead of this.
+ */
+
+int unregister_netdevice(struct net_device *dev)
+{
+ struct net_device *d, **dp;
+
+ BUG_ON(dev_boot_phase);
+ ASSERT_RTNL();
+
+ /* Some devices call without registering for initialization unwind. */
+ if (dev->reg_state == NETREG_UNINITIALIZED) {
+ printk(KERN_DEBUG "unregister_netdevice: device %s/%p never "
+ "was registered\n", dev->name, dev);
+ return -ENODEV;
+ }
+
+ BUG_ON(dev->reg_state != NETREG_REGISTERED);
+
+ /* If device is running, close it first. */
+ if (dev->flags & IFF_UP)
+ dev_close(dev);
+
+ /* And unlink it from device chain. */
+ for (dp = &dev_base; (d = *dp) != NULL; dp = &d->next) {
+ if (d == dev) {
+ write_lock_bh(&dev_base_lock);
+ hlist_del(&dev->name_hlist);
+ hlist_del(&dev->index_hlist);
+ if (dev_tail == &dev->next)
+ dev_tail = dp;
+ *dp = d->next;
+ write_unlock_bh(&dev_base_lock);
+ break;
+ }
+ }
+ if (!d) {
+ printk(KERN_ERR "unregister net_device: '%s' not found\n",
+ dev->name);
+ return -ENODEV;
+ }
+
+ dev->reg_state = NETREG_UNREGISTERING;
+
+ synchronize_net();
+
+ /* Shutdown queueing discipline. */
+ dev_shutdown(dev);
+
+
+ /* Notify protocols, that we are about to destroy
+ this device. They should clean all the things.
+ */
+ notifier_call_chain(&netdev_chain, NETDEV_UNREGISTER, dev);
+
+ /*
+ * Flush the multicast chain
+ */
+ dev_mc_discard(dev);
+
+ if (dev->uninit)
+ dev->uninit(dev);
+
+ /* Notifier chain MUST detach us from master device. */
+ BUG_TRAP(!dev->master);
+
+ free_divert_blk(dev);
+
+ /* Finish processing unregister after unlock */
+ net_set_todo(dev);
+
+ synchronize_net();
+
+ dev_put(dev);
+ return 0;
+}
+
+/**
+ * unregister_netdev - remove device from the kernel
+ * @dev: device
+ *
+ * This function shuts down a device interface and removes it
+ * from the kernel tables. On success 0 is returned, on a failure
+ * a negative errno code is returned.
+ *
+ * This is just a wrapper for unregister_netdevice that takes
+ * the rtnl semaphore. In general you want to use this and not
+ * unregister_netdevice.
+ */
+void unregister_netdev(struct net_device *dev)
+{
+ rtnl_lock();
+ unregister_netdevice(dev);
+ rtnl_unlock();
+}
+
+EXPORT_SYMBOL(unregister_netdev);
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int dev_cpu_callback(struct notifier_block *nfb,
+ unsigned long action,
+ void *ocpu)
+{
+ struct sk_buff **list_skb;
+ struct net_device **list_net;
+ struct sk_buff *skb;
+ unsigned int cpu, oldcpu = (unsigned long)ocpu;
+ struct softnet_data *sd, *oldsd;
+
+ if (action != CPU_DEAD)
+ return NOTIFY_OK;
+
+ local_irq_disable();
+ cpu = smp_processor_id();
+ sd = &per_cpu(softnet_data, cpu);
+ oldsd = &per_cpu(softnet_data, oldcpu);
+
+ /* Find end of our completion_queue. */
+ list_skb = &sd->completion_queue;
+ while (*list_skb)
+ list_skb = &(*list_skb)->next;
+ /* Append completion queue from offline CPU. */
+ *list_skb = oldsd->completion_queue;
+ oldsd->completion_queue = NULL;
+
+ /* Find end of our output_queue. */
+ list_net = &sd->output_queue;
+ while (*list_net)
+ list_net = &(*list_net)->next_sched;
+ /* Append output queue from offline CPU. */
+ *list_net = oldsd->output_queue;
+ oldsd->output_queue = NULL;
+
+ raise_softirq_irqoff(NET_TX_SOFTIRQ);
+ local_irq_enable();
+
+ /* Process offline CPU's input_pkt_queue */
+ while ((skb = __skb_dequeue(&oldsd->input_pkt_queue)))
+ netif_rx(skb);
+
+ return NOTIFY_OK;
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+
+/*
+ * Initialize the DEV module. At boot time this walks the device list and
+ * unhooks any devices that fail to initialise (normally hardware not
+ * present) and leaves us with a valid list of present and active devices.
+ *
+ */
+
+/*
+ * This is called single threaded during boot, so no need
+ * to take the rtnl semaphore.
+ */
+static int __init net_dev_init(void)
+{
+ int i, rc = -ENOMEM;
+
+ BUG_ON(!dev_boot_phase);
+
+ net_random_init();
+
+ if (dev_proc_init())
+ goto out;
+
+ if (netdev_sysfs_init())
+ goto out;
+
+ INIT_LIST_HEAD(&ptype_all);
+ for (i = 0; i < 16; i++)
+ INIT_LIST_HEAD(&ptype_base[i]);
+
+ for (i = 0; i < ARRAY_SIZE(dev_name_head); i++)
+ INIT_HLIST_HEAD(&dev_name_head[i]);
+
+ for (i = 0; i < ARRAY_SIZE(dev_index_head); i++)
+ INIT_HLIST_HEAD(&dev_index_head[i]);
+
+ /*
+ * Initialise the packet receive queues.
+ */
+
+ for (i = 0; i < NR_CPUS; i++) {
+ struct softnet_data *queue;
+
+ queue = &per_cpu(softnet_data, i);
+ skb_queue_head_init(&queue->input_pkt_queue);
+ queue->throttle = 0;
+ queue->cng_level = 0;
+ queue->avg_blog = 10; /* arbitrary non-zero */
+ queue->completion_queue = NULL;
+ INIT_LIST_HEAD(&queue->poll_list);
+ set_bit(__LINK_STATE_START, &queue->backlog_dev.state);
+ queue->backlog_dev.weight = weight_p;
+ queue->backlog_dev.poll = process_backlog;
+ atomic_set(&queue->backlog_dev.refcnt, 1);
+ }
+
+#ifdef OFFLINE_SAMPLE
+ samp_timer.expires = jiffies + (10 * HZ);
+ add_timer(&samp_timer);
+#endif
+
+ dev_boot_phase = 0;
+
+ open_softirq(NET_TX_SOFTIRQ, net_tx_action, NULL);
+ open_softirq(NET_RX_SOFTIRQ, net_rx_action, NULL);
+
+ hotcpu_notifier(dev_cpu_callback, 0);
+ dst_init();
+ dev_mcast_init();
+ rc = 0;
+out:
+ return rc;
+}
+
+subsys_initcall(net_dev_init);
+
+EXPORT_SYMBOL(__dev_get_by_index);
+EXPORT_SYMBOL(__dev_get_by_name);
+EXPORT_SYMBOL(__dev_remove_pack);
+EXPORT_SYMBOL(__skb_linearize);
+EXPORT_SYMBOL(dev_add_pack);
+EXPORT_SYMBOL(dev_alloc_name);
+EXPORT_SYMBOL(dev_close);
+EXPORT_SYMBOL(dev_get_by_flags);
+EXPORT_SYMBOL(dev_get_by_index);
+EXPORT_SYMBOL(dev_get_by_name);
+EXPORT_SYMBOL(dev_ioctl);
+EXPORT_SYMBOL(dev_open);
+EXPORT_SYMBOL(dev_queue_xmit);
+EXPORT_SYMBOL(dev_remove_pack);
+EXPORT_SYMBOL(dev_set_allmulti);
+EXPORT_SYMBOL(dev_set_promiscuity);
+EXPORT_SYMBOL(dev_change_flags);
+EXPORT_SYMBOL(dev_set_mtu);
+EXPORT_SYMBOL(free_netdev);
+EXPORT_SYMBOL(netdev_boot_setup_check);
+EXPORT_SYMBOL(netdev_set_master);
+EXPORT_SYMBOL(netdev_state_change);
+EXPORT_SYMBOL(netif_receive_skb);
+EXPORT_SYMBOL(netif_rx);
+EXPORT_SYMBOL(register_gifconf);
+EXPORT_SYMBOL(register_netdevice);
+EXPORT_SYMBOL(register_netdevice_notifier);
+EXPORT_SYMBOL(skb_checksum_help);
+EXPORT_SYMBOL(synchronize_net);
+EXPORT_SYMBOL(unregister_netdevice);
+EXPORT_SYMBOL(unregister_netdevice_notifier);
+EXPORT_SYMBOL(net_enable_timestamp);
+EXPORT_SYMBOL(net_disable_timestamp);
+
+#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)
+EXPORT_SYMBOL(br_handle_frame_hook);
+#endif
+
+#ifdef CONFIG_KMOD
+EXPORT_SYMBOL(dev_load);
+#endif
+
+EXPORT_PER_CPU_SYMBOL(softnet_data);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/param.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/param.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,23 @@
+#ifndef _ASMi386_PARAM_H
+#define _ASMi386_PARAM_H
+
+#ifdef __KERNEL__
+# define HZ 100 /* Internal kernel timer frequency */
+# define USER_HZ 100 /* .. some user interfaces are in
"ticks" */
+# define CLOCKS_PER_SEC (USER_HZ) /* like times() */
+#endif
+
+#ifndef HZ
+#define HZ 100
+#endif
+
+#define EXEC_PAGESIZE 4096
+
+#ifndef NOGROUP
+#define NOGROUP (-1)
+#endif
+
+#define MAXHOSTNAMELEN 64 /* max length of hostname */
+#define COMMAND_LINE_SIZE 256
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/usbfront/usbfront.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/usbfront/usbfront.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,1738 @@
+/*
+ * Xen Virtual USB Frontend Driver
+ *
+ * This file contains the first version of the Xen virtual USB hub
+ * that I've managed not to delete by mistake (3rd time lucky!).
+ *
+ * Based on Linux's uhci.c, original copyright notices are displayed
+ * below. Portions also (c) 2004 Intel Research Cambridge
+ * and (c) 2004, 2005 Mark Williamson
+ *
+ * Contact <mark.williamson@xxxxxxxxxxxx> or
+ * <xen-devel@xxxxxxxxxxxxxxxxxxxxx> regarding this code.
+ *
+ * Still to be (maybe) implemented:
+ * - migration / backend restart support?
+ * - support for building / using as a module
+ */
+
+/*
+ * Universal Host Controller Interface driver for USB.
+ *
+ * Maintainer: Johannes Erdfelt <johannes@xxxxxxxxxxx>
+ *
+ * (C) Copyright 1999 Linus Torvalds
+ * (C) Copyright 1999-2002 Johannes Erdfelt, johannes@xxxxxxxxxxx
+ * (C) Copyright 1999 Randy Dunlap
+ * (C) Copyright 1999 Georg Acher, acher@xxxxxxxxx
+ * (C) Copyright 1999 Deti Fliegl, deti@xxxxxxxxx
+ * (C) Copyright 1999 Thomas Sailer, sailer@xxxxxxxxxxxxxx
+ * (C) Copyright 1999 Roman Weissgaerber, weissg@xxxxxxxxx
+ * (C) Copyright 2000 Yggdrasil Computing, Inc. (port of new PCI interface
+ * support from usb-ohci.c by Adam Richter, adam@xxxxxxxxxxxxx).
+ * (C) Copyright 1999 Gregory P. Smith (from usb-ohci.c)
+ *
+ * Intel documents this fairly well, and as far as I know there
+ * are no royalties or anything like that, but even so there are
+ * people who decided that they want to do the same thing in a
+ * completely different way.
+ *
+ * WARNING! The USB documentation is downright evil. Most of it
+ * is just crap, written by a committee. You're better off ignoring
+ * most of it, the important stuff is:
+ * - the low-level protocol (fairly simple but lots of small details)
+ * - working around the horridness of the rest
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/smp_lock.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#ifdef CONFIG_USB_DEBUG
+#define DEBUG
+#else
+#undef DEBUG
+#endif
+#include <linux/usb.h>
+
+#include <asm/irq.h>
+#include <asm/system.h>
+
+#include "xhci.h"
+
+#include "../../../../../drivers/usb/hcd.h"
+
+#include <asm-xen/xen-public/io/usbif.h>
+#include <asm/ctrl_if.h>
+#include <asm/xen-public/io/domain_controller.h>
+
+/*
+ * Version Information
+ */
+#define DRIVER_VERSION "v1.0"
+#define DRIVER_AUTHOR "Linus 'Frodo Rabbit' Torvalds, Johannes Erdfelt, " \
+ "Randy Dunlap, Georg Acher, Deti Fliegl, " \
+ "Thomas Sailer, Roman Weissgaerber, Mark Williamson"
+#define DRIVER_DESC "Xen Virtual USB Host Controller Interface"
+
+/*
+ * debug = 0, no debugging messages
+ * debug = 1, dump failed URB's except for stalls
+ * debug = 2, dump all failed URB's (including stalls)
+ */
+#ifdef DEBUG
+static int debug = 1;
+#else
+static int debug = 0;
+#endif
+MODULE_PARM(debug, "i");
+MODULE_PARM_DESC(debug, "Debug level");
+static char *errbuf;
+#define ERRBUF_LEN (PAGE_SIZE * 8)
+
+static int rh_submit_urb(struct urb *urb);
+static int rh_unlink_urb(struct urb *urb);
+static int xhci_unlink_urb(struct urb *urb);
+static void xhci_call_completion(struct urb *urb);
+static void xhci_drain_ring(void);
+static void xhci_transfer_result(struct xhci *xhci, struct urb *urb);
+static void xhci_finish_completion(void);
+
+#define MAX_URB_LOOP 2048 /* Maximum number of linked URB's */
+
+static kmem_cache_t *xhci_up_cachep; /* urb_priv cache */
+static struct xhci *xhci; /* XHCI structure for the interface */
+
+/******************************************************************************
+ * DEBUGGING
+ */
+
+#ifdef DEBUG
+
+static void dump_urb(struct urb *urb)
+{
+ printk(KERN_DEBUG "dumping urb @ %p\n"
+ " hcpriv = %p\n"
+ " next = %p\n"
+ " dev = %p\n"
+ " pipe = 0x%lx\n"
+ " status = %d\n"
+ " transfer_flags = 0x%lx\n"
+ " transfer_buffer = %p\n"
+ " transfer_buffer_length = %d\n"
+ " actual_length = %d\n"
+ " bandwidth = %d\n"
+ " setup_packet = %p\n",
+ urb, urb->hcpriv, urb->next, urb->dev, urb->pipe, urb->status,
+ urb->transfer_flags, urb->transfer_buffer,
+ urb->transfer_buffer_length, urb->actual_length, urb->bandwidth,
+ urb->setup_packet);
+ if ( urb->setup_packet != NULL )
+ printk(KERN_DEBUG
+ "setup = { 0x%x, 0x%x, 0x%x, 0x%x, 0x%x, 0x%x, 0x%x, 0x%x }\n",
+ urb->setup_packet[0], urb->setup_packet[1],
+ urb->setup_packet[2], urb->setup_packet[3],
+ urb->setup_packet[4], urb->setup_packet[5],
+ urb->setup_packet[6], urb->setup_packet[7]);
+ printk(KERN_DEBUG "complete = %p\n"
+ "interval = %d\n", urb->complete, urb->interval);
+
+}
+
+static void xhci_show_resp(usbif_response_t *r)
+{
+ printk(KERN_DEBUG "dumping response @ %p\n"
+ " id=0x%lx\n"
+ " op=0x%x\n"
+ " data=0x%x\n"
+ " status=0x%x\n"
+ " length=0x%lx\n",
+ r->id, r->operation, r->data, r->status, r->length);
+}
+
+#define DPRINK(...) printk(KERN_DEBUG __VA_ARGS__)
+
+#else /* DEBUG */
+
+#define dump_urb(blah) ((void)0)
+#define xhci_show_resp(blah) ((void)0)
+#define DPRINTK(blah,...) ((void)0)
+
+#endif /* DEBUG */
+
+/******************************************************************************
+ * RING REQUEST HANDLING
+ */
+
+#define RING_PLUGGED(_hc) ( RING_FULL(&_hc->usb_ring) || _hc->recovery )
+
+/**
+ * xhci_construct_isoc - add isochronous information to a request
+ */
+static int xhci_construct_isoc(usbif_request_t *req, struct urb *urb)
+{
+ usbif_iso_t *schedule;
+ int i;
+ struct urb_priv *urb_priv = urb->hcpriv;
+
+ req->num_iso = urb->number_of_packets;
+ schedule = (usbif_iso_t *)__get_free_page(GFP_KERNEL);
+
+ if ( schedule == NULL )
+ return -ENOMEM;
+
+ for ( i = 0; i < req->num_iso; i++ )
+ {
+ schedule[i].buffer_offset = urb->iso_frame_desc[i].offset;
+ schedule[i].length = urb->iso_frame_desc[i].length;
+ }
+
+ urb_priv->schedule = schedule;
+ req->iso_schedule = virt_to_machine(schedule);
+
+ return 0;
+}
+
+/**
+ * xhci_queue_req - construct and queue request for an URB
+ */
+static int xhci_queue_req(struct urb *urb)
+{
+ unsigned long flags;
+ usbif_request_t *req;
+ usbif_front_ring_t *usb_ring = &xhci->usb_ring;
+
+#if DEBUG
+ printk(KERN_DEBUG
+ "usbif = %p, req_prod = %d (@ 0x%lx), resp_prod = %d, resp_cons
= %d\n",
+ usbif, usbif->req_prod, virt_to_machine(&usbif->req_prod),
+ usbif->resp_prod, xhci->usb_resp_cons);
+#endif
+
+ spin_lock_irqsave(&xhci->ring_lock, flags);
+
+ if ( RING_PLUGGED(xhci) )
+ {
+ printk(KERN_WARNING
+ "xhci_queue_req(): USB ring plugged, not queuing
request\n");
+ spin_unlock_irqrestore(&xhci->ring_lock, flags);
+ return -ENOBUFS;
+ }
+
+ /* Stick something in the shared communications ring. */
+ req = RING_GET_REQUEST(usb_ring, usb_ring->req_prod_pvt);
+
+ req->operation = USBIF_OP_IO;
+ req->port = 0; /* We don't care what the port is. */
+ req->id = (unsigned long) urb->hcpriv;
+ req->transfer_buffer = virt_to_machine(urb->transfer_buffer);
+ req->devnum = usb_pipedevice(urb->pipe);
+ req->direction = usb_pipein(urb->pipe);
+ req->speed = usb_pipeslow(urb->pipe);
+ req->pipe_type = usb_pipetype(urb->pipe);
+ req->length = urb->transfer_buffer_length;
+ req->transfer_flags = urb->transfer_flags;
+ req->endpoint = usb_pipeendpoint(urb->pipe);
+ req->speed = usb_pipeslow(urb->pipe);
+ req->timeout = urb->timeout * (1000 / HZ);
+
+ if ( usb_pipetype(urb->pipe) == 0 ) /* ISO */
+ {
+ int ret = xhci_construct_isoc(req, urb);
+ if ( ret != 0 )
+ return ret;
+ }
+
+ if(urb->setup_packet != NULL)
+ memcpy(req->setup, urb->setup_packet, 8);
+ else
+ memset(req->setup, 0, 8);
+
+ usb_ring->req_prod_pvt++;
+ RING_PUSH_REQUESTS(usb_ring);
+
+ spin_unlock_irqrestore(&xhci->ring_lock, flags);
+
+ notify_via_evtchn(xhci->evtchn);
+
+ DPRINTK("Queued request for an URB.\n");
+ dump_urb(urb);
+
+ return -EINPROGRESS;
+}
+
+/**
+ * xhci_queue_probe - queue a probe request for a particular port
+ */
+static inline usbif_request_t *xhci_queue_probe(usbif_vdev_t port)
+{
+ usbif_request_t *req;
+ usbif_front_ring_t *usb_ring = &xhci->usb_ring;
+
+#if DEBUG
+ printk(KERN_DEBUG
+ "queuing probe: req_prod = %d (@ 0x%lx), resp_prod = %d, "
+ "resp_cons = %d\n", usbif->req_prod,
+ virt_to_machine(&usbif->req_prod),
+ usbif->resp_prod, xhci->usb_resp_cons);
+#endif
+
+ /* This is always called from the timer interrupt. */
+ spin_lock(&xhci->ring_lock);
+
+ if ( RING_PLUGGED(xhci) )
+ {
+ printk(KERN_WARNING
+ "xhci_queue_probe(): ring full, not queuing request\n");
+ spin_unlock(&xhci->ring_lock);
+ return NULL;
+ }
+
+ /* Stick something in the shared communications ring. */
+ req = RING_GET_REQUEST(usb_ring, usb_ring->req_prod_pvt);
+
+ memset(req, 0, sizeof(*req));
+
+ req->operation = USBIF_OP_PROBE;
+ req->port = port;
+
+ usb_ring->req_prod_pvt++;
+ RING_PUSH_REQUESTS(usb_ring);
+
+ spin_unlock(&xhci->ring_lock);
+
+ notify_via_evtchn(xhci->evtchn);
+
+ return req;
+}
+
+/**
+ * xhci_port_reset - queue a reset request for a particular port
+ */
+static int xhci_port_reset(usbif_vdev_t port)
+{
+ usbif_request_t *req;
+ usbif_front_ring_t *usb_ring = &xhci->usb_ring;
+
+ /* Only ever happens from process context (hub thread). */
+ spin_lock_irq(&xhci->ring_lock);
+
+ if ( RING_PLUGGED(xhci) )
+ {
+ printk(KERN_WARNING
+ "xhci_port_reset(): ring plugged, not queuing
request\n");
+ spin_unlock_irq(&xhci->ring_lock);
+ return -ENOBUFS;
+ }
+
+ /* We only reset one port at a time, so we only need one variable per
+ * hub. */
+ xhci->awaiting_reset = 1;
+
+ /* Stick something in the shared communications ring. */
+ req = RING_GET_REQUEST(usb_ring, usb_ring->req_prod_pvt);
+
+ memset(req, 0, sizeof(*req));
+
+ req->operation = USBIF_OP_RESET;
+ req->port = port;
+
+ usb_ring->req_prod_pvt++;
+ RING_PUSH_REQUESTS(usb_ring);
+
+ spin_unlock_irq(&xhci->ring_lock);
+
+ notify_via_evtchn(xhci->evtchn);
+
+ while ( xhci->awaiting_reset > 0 )
+ {
+ mdelay(1);
+ xhci_drain_ring();
+ }
+
+ xhci->rh.ports[port].pe = 1;
+ xhci->rh.ports[port].pe_chg = 1;
+
+ return xhci->awaiting_reset;
+}
+
+
+/******************************************************************************
+ * RING RESPONSE HANDLING
+ */
+
+static void receive_usb_reset(usbif_response_t *resp)
+{
+ xhci->awaiting_reset = resp->status;
+ rmb();
+
+}
+
+static void receive_usb_probe(usbif_response_t *resp)
+{
+ spin_lock(&xhci->rh.port_state_lock);
+
+ if ( resp->status >= 0 )
+ {
+ if ( resp->status == 1 )
+ {
+ /* If theres a device there and there wasn't one before there must
+ * have been a connection status change. */
+ if( xhci->rh.ports[resp->data].cs == 0 )
+ {
+ xhci->rh.ports[resp->data].cs = 1;
+ xhci->rh.ports[resp->data].cs_chg = 1;
+ }
+ }
+ else if ( resp->status == 0 )
+ {
+ if(xhci->rh.ports[resp->data].cs == 1 )
+ {
+ xhci->rh.ports[resp->data].cs = 0;
+ xhci->rh.ports[resp->data].cs_chg = 1;
+ xhci->rh.ports[resp->data].pe = 0;
+ /* According to USB Spec v2.0, 11.24.2.7.2.2, we don't need
+ * to set pe_chg since an error has not occurred. */
+ }
+ }
+ else
+ printk(KERN_WARNING "receive_usb_probe(): unexpected status %d "
+ "for port %d\n", resp->status, resp->data);
+ }
+ else if ( resp->status < 0)
+ printk(KERN_WARNING "receive_usb_probe(): got error status %d\n",
+ resp->status);
+
+ spin_unlock(&xhci->rh.port_state_lock);
+}
+
+static void receive_usb_io(usbif_response_t *resp)
+{
+ struct urb_priv *urbp = (struct urb_priv *)resp->id;
+ struct urb *urb = urbp->urb;
+
+ urb->actual_length = resp->length;
+ urbp->in_progress = 0;
+
+ if( usb_pipetype(urb->pipe) == 0 ) /* ISO */
+ {
+ int i;
+
+ /* Copy ISO schedule results back in. */
+ for ( i = 0; i < urb->number_of_packets; i++ )
+ {
+ urb->iso_frame_desc[i].status
+ = urbp->schedule[i].status;
+ urb->iso_frame_desc[i].actual_length
+ = urbp->schedule[i].length;
+ }
+ free_page((unsigned long)urbp->schedule);
+ }
+
+ /* Only set status if it's not been changed since submission. It might
+ * have been changed if the URB has been unlinked asynchronously, for
+ * instance. */
+ if ( urb->status == -EINPROGRESS )
+ urbp->status = urb->status = resp->status;
+}
+
+/**
+ * xhci_drain_ring - drain responses from the ring, calling handlers
+ *
+ * This may be called from interrupt context when an event is received from the
+ * backend domain, or sometimes in process context whilst waiting for a port
+ * reset or URB completion.
+ */
+static void xhci_drain_ring(void)
+{
+ struct list_head *tmp, *head;
+ usbif_front_ring_t *usb_ring = &xhci->usb_ring;
+ usbif_response_t *resp;
+ RING_IDX i, rp;
+
+ /* Walk the ring here to get responses, updating URBs to show what
+ * completed. */
+
+ rp = usb_ring->sring->rsp_prod;
+ rmb(); /* Ensure we see queued requests up to 'rp'. */
+
+ /* Take items off the comms ring, taking care not to overflow. */
+ for ( i = usb_ring->rsp_cons; i != rp; i++ )
+ {
+ resp = RING_GET_RESPONSE(usb_ring, i);
+
+ /* May need to deal with batching and with putting a ceiling on
+ the number dispatched for performance and anti-dos reasons */
+
+ xhci_show_resp(resp);
+
+ switch ( resp->operation )
+ {
+ case USBIF_OP_PROBE:
+ receive_usb_probe(resp);
+ break;
+
+ case USBIF_OP_IO:
+ receive_usb_io(resp);
+ break;
+
+ case USBIF_OP_RESET:
+ receive_usb_reset(resp);
+ break;
+
+ default:
+ printk(KERN_WARNING
+ "error: unknown USB io operation response [%d]\n",
+ resp->operation);
+ break;
+ }
+ }
+
+ usb_ring->rsp_cons = i;
+
+ /* Walk the list of pending URB's to see which ones completed and do
+ * callbacks, etc. */
+ spin_lock(&xhci->urb_list_lock);
+ head = &xhci->urb_list;
+ tmp = head->next;
+ while (tmp != head) {
+ struct urb *urb = list_entry(tmp, struct urb, urb_list);
+
+ tmp = tmp->next;
+
+ /* Checks the status and does all of the magic necessary */
+ xhci_transfer_result(xhci, urb);
+ }
+ spin_unlock(&xhci->urb_list_lock);
+
+ xhci_finish_completion();
+}
+
+
+static void xhci_interrupt(int irq, void *__xhci, struct pt_regs *regs)
+{
+ xhci_drain_ring();
+}
+
+/******************************************************************************
+ * HOST CONTROLLER FUNCTIONALITY
+ */
+
+/**
+ * no-op implementation of private device alloc / free routines
+ */
+static int xhci_do_nothing_dev(struct usb_device *dev)
+{
+ return 0;
+}
+
+static inline void xhci_add_complete(struct urb *urb)
+{
+ struct urb_priv *urbp = (struct urb_priv *)urb->hcpriv;
+ unsigned long flags;
+
+ spin_lock_irqsave(&xhci->complete_list_lock, flags);
+ list_add_tail(&urbp->complete_list, &xhci->complete_list);
+ spin_unlock_irqrestore(&xhci->complete_list_lock, flags);
+}
+
+/* When this returns, the owner of the URB may free its
+ * storage.
+ *
+ * We spin and wait for the URB to complete before returning.
+ *
+ * Call with urb->lock acquired.
+ */
+static void xhci_delete_urb(struct urb *urb)
+{
+ struct urb_priv *urbp;
+
+ urbp = urb->hcpriv;
+
+ /* If there's no urb_priv structure for this URB then it can't have
+ * been submitted at all. */
+ if ( urbp == NULL )
+ return;
+
+ /* For now we just spin until the URB completes. It shouldn't take too
+ * long and we don't expect to have to do this very often. */
+ while ( urb->status == -EINPROGRESS )
+ {
+ xhci_drain_ring();
+ mdelay(1);
+ }
+
+ /* Now we know that further transfers to the buffer won't
+ * occur, so we can safely return. */
+}
+
+static struct urb_priv *xhci_alloc_urb_priv(struct urb *urb)
+{
+ struct urb_priv *urbp;
+
+ urbp = kmem_cache_alloc(xhci_up_cachep, SLAB_ATOMIC);
+ if (!urbp) {
+ err("xhci_alloc_urb_priv: couldn't allocate memory for
urb_priv\n");
+ return NULL;
+ }
+
+ memset((void *)urbp, 0, sizeof(*urbp));
+
+ urbp->inserttime = jiffies;
+ urbp->urb = urb;
+ urbp->dev = urb->dev;
+
+ INIT_LIST_HEAD(&urbp->complete_list);
+
+ urb->hcpriv = urbp;
+
+ return urbp;
+}
+
+/*
+ * MUST be called with urb->lock acquired
+ */
+/* When is this called? Do we need to stop the transfer (as we
+ * currently do)? */
+static void xhci_destroy_urb_priv(struct urb *urb)
+{
+ struct urb_priv *urbp;
+
+ urbp = (struct urb_priv *)urb->hcpriv;
+ if (!urbp)
+ return;
+
+ if (!list_empty(&urb->urb_list))
+ warn("xhci_destroy_urb_priv: urb %p still on xhci->urb_list", urb);
+
+ if (!list_empty(&urbp->complete_list))
+ warn("xhci_destroy_urb_priv: urb %p still on xhci->complete_list",
urb);
+
+ kmem_cache_free(xhci_up_cachep, urb->hcpriv);
+
+ urb->hcpriv = NULL;
+}
+
+/**
+ * Try to find URBs in progress on the same pipe to the same device.
+ *
+ * MUST be called with xhci->urb_list_lock acquired
+ */
+static struct urb *xhci_find_urb_ep(struct xhci *xhci, struct urb *urb)
+{
+ struct list_head *tmp, *head;
+
+ /* We don't match Isoc transfers since they are special */
+ if (usb_pipeisoc(urb->pipe))
+ return NULL;
+
+ head = &xhci->urb_list;
+ tmp = head->next;
+ while (tmp != head) {
+ struct urb *u = list_entry(tmp, struct urb, urb_list);
+
+ tmp = tmp->next;
+
+ if (u->dev == urb->dev && u->pipe == urb->pipe &&
+ u->status == -EINPROGRESS)
+ return u;
+ }
+
+ return NULL;
+}
+
+static int xhci_submit_urb(struct urb *urb)
+{
+ int ret = -EINVAL;
+ unsigned long flags;
+ struct urb *eurb;
+ int bustime;
+
+ DPRINTK("URB submitted to XHCI driver.\n");
+ dump_urb(urb);
+
+ if (!urb)
+ return -EINVAL;
+
+ if (!urb->dev || !urb->dev->bus || !urb->dev->bus->hcpriv) {
+ warn("xhci_submit_urb: urb %p belongs to disconnected device or
bus?", urb);
+ return -ENODEV;
+ }
+
+ if ( urb->dev->devpath == NULL )
+ BUG();
+
+ usb_inc_dev_use(urb->dev);
+
+ spin_lock_irqsave(&xhci->urb_list_lock, flags);
+ spin_lock(&urb->lock);
+
+ if (urb->status == -EINPROGRESS || urb->status == -ECONNRESET ||
+ urb->status == -ECONNABORTED) {
+ dbg("xhci_submit_urb: urb not available to submit (status =
%d)", urb->status);
+ /* Since we can have problems on the out path */
+ spin_unlock(&urb->lock);
+ spin_unlock_irqrestore(&xhci->urb_list_lock, flags);
+ usb_dec_dev_use(urb->dev);
+
+ return ret;
+ }
+
+ INIT_LIST_HEAD(&urb->urb_list);
+ if (!xhci_alloc_urb_priv(urb)) {
+ ret = -ENOMEM;
+
+ goto out;
+ }
+
+ ( (struct urb_priv *)urb->hcpriv )->in_progress = 1;
+
+ eurb = xhci_find_urb_ep(xhci, urb);
+ if (eurb && !(urb->transfer_flags & USB_QUEUE_BULK)) {
+ ret = -ENXIO;
+
+ goto out;
+ }
+
+ /* Short circuit the virtual root hub */
+ if (urb->dev == xhci->rh.dev) {
+ ret = rh_submit_urb(urb);
+
+ goto out;
+ }
+
+ switch (usb_pipetype(urb->pipe)) {
+ case PIPE_CONTROL:
+ case PIPE_BULK:
+ ret = xhci_queue_req(urb);
+ break;
+
+ case PIPE_INTERRUPT:
+ if (urb->bandwidth == 0) { /* not yet checked/allocated */
+ bustime = usb_check_bandwidth(urb->dev, urb);
+ if (bustime < 0)
+ ret = bustime;
+ else {
+ ret = xhci_queue_req(urb);
+ if (ret == -EINPROGRESS)
+ usb_claim_bandwidth(urb->dev, urb,
+ bustime, 0);
+ }
+ } else /* bandwidth is already set */
+ ret = xhci_queue_req(urb);
+ break;
+
+ case PIPE_ISOCHRONOUS:
+ if (urb->bandwidth == 0) { /* not yet checked/allocated */
+ if (urb->number_of_packets <= 0) {
+ ret = -EINVAL;
+ break;
+ }
+ bustime = usb_check_bandwidth(urb->dev, urb);
+ if (bustime < 0) {
+ ret = bustime;
+ break;
+ }
+
+ ret = xhci_queue_req(urb);
+ if (ret == -EINPROGRESS)
+ usb_claim_bandwidth(urb->dev, urb, bustime, 1);
+ } else /* bandwidth is already set */
+ ret = xhci_queue_req(urb);
+ break;
+ }
+out:
+ urb->status = ret;
+
+ if (ret == -EINPROGRESS) {
+ /* We use _tail to make find_urb_ep more efficient */
+ list_add_tail(&urb->urb_list, &xhci->urb_list);
+
+ spin_unlock(&urb->lock);
+ spin_unlock_irqrestore(&xhci->urb_list_lock, flags);
+
+ return 0;
+ }
+
+ xhci_delete_urb(urb);
+
+ spin_unlock(&urb->lock);
+ spin_unlock_irqrestore(&xhci->urb_list_lock, flags);
+
+ /* Only call completion if it was successful */
+ if (!ret)
+ xhci_call_completion(urb);
+
+ return ret;
+}
+
+/*
+ * Return the result of a transfer
+ *
+ * MUST be called with urb_list_lock acquired
+ */
+static void xhci_transfer_result(struct xhci *xhci, struct urb *urb)
+{
+ int ret = 0;
+ unsigned long flags;
+ struct urb_priv *urbp;
+
+ /* The root hub is special */
+ if (urb->dev == xhci->rh.dev)
+ return;
+
+ spin_lock_irqsave(&urb->lock, flags);
+
+ urbp = (struct urb_priv *)urb->hcpriv;
+
+ if ( ( (struct urb_priv *)urb->hcpriv )->in_progress )
+ ret = -EINPROGRESS;
+
+ if (urb->actual_length < urb->transfer_buffer_length) {
+ if (urb->transfer_flags & USB_DISABLE_SPD) {
+ ret = -EREMOTEIO;
+ }
+ }
+
+ if (urb->status == -EPIPE)
+ {
+ ret = urb->status;
+ /* endpoint has stalled - mark it halted */
+ usb_endpoint_halt(urb->dev, usb_pipeendpoint(urb->pipe),
+ usb_pipeout(urb->pipe));
+ }
+
+ if ((debug == 1 && ret != 0 && ret != -EPIPE) ||
+ (ret != 0 && debug > 1)) {
+ /* Some debugging code */
+ dbg("xhci_result_interrupt/bulk() failed with status %x",
+ status);
+ }
+
+ if (ret == -EINPROGRESS)
+ goto out;
+
+ switch (usb_pipetype(urb->pipe)) {
+ case PIPE_CONTROL:
+ case PIPE_BULK:
+ case PIPE_ISOCHRONOUS:
+ /* Release bandwidth for Interrupt or Isoc. transfers */
+ /* Spinlock needed ? */
+ if (urb->bandwidth)
+ usb_release_bandwidth(urb->dev, urb, 1);
+ xhci_delete_urb(urb);
+ break;
+ case PIPE_INTERRUPT:
+ /* Interrupts are an exception */
+ if (urb->interval)
+ goto out_complete;
+
+ /* Release bandwidth for Interrupt or Isoc. transfers */
+ /* Spinlock needed ? */
+ if (urb->bandwidth)
+ usb_release_bandwidth(urb->dev, urb, 0);
+ xhci_delete_urb(urb);
+ break;
+ default:
+ info("xhci_transfer_result: unknown pipe type %d for urb %p\n",
+ usb_pipetype(urb->pipe), urb);
+ }
+
+ /* Remove it from xhci->urb_list */
+ list_del_init(&urb->urb_list);
+
+out_complete:
+ xhci_add_complete(urb);
+
+out:
+ spin_unlock_irqrestore(&urb->lock, flags);
+}
+
+static int xhci_unlink_urb(struct urb *urb)
+{
+ unsigned long flags;
+ struct urb_priv *urbp = urb->hcpriv;
+
+ if (!urb)
+ return -EINVAL;
+
+ if (!urb->dev || !urb->dev->bus || !urb->dev->bus->hcpriv)
+ return -ENODEV;
+
+ spin_lock_irqsave(&xhci->urb_list_lock, flags);
+ spin_lock(&urb->lock);
+
+ /* Release bandwidth for Interrupt or Isoc. transfers */
+ /* Spinlock needed ? */
+ if (urb->bandwidth) {
+ switch (usb_pipetype(urb->pipe)) {
+ case PIPE_INTERRUPT:
+ usb_release_bandwidth(urb->dev, urb, 0);
+ break;
+ case PIPE_ISOCHRONOUS:
+ usb_release_bandwidth(urb->dev, urb, 1);
+ break;
+ default:
+ break;
+ }
+ }
+
+ if (urb->status != -EINPROGRESS) {
+ spin_unlock(&urb->lock);
+ spin_unlock_irqrestore(&xhci->urb_list_lock, flags);
+ return 0;
+ }
+
+ list_del_init(&urb->urb_list);
+
+ /* Short circuit the virtual root hub */
+ if (urb->dev == xhci->rh.dev) {
+ rh_unlink_urb(urb);
+
+ spin_unlock(&urb->lock);
+ spin_unlock_irqrestore(&xhci->urb_list_lock, flags);
+
+ xhci_call_completion(urb);
+ } else {
+ if (urb->transfer_flags & USB_ASYNC_UNLINK) {
+ /* We currently don't currently attempt to cancel URBs
+ * that have been queued in the ring. We handle async
+ * unlinked URBs when they complete. */
+ urbp->status = urb->status = -ECONNABORTED;
+ spin_unlock(&urb->lock);
+ spin_unlock_irqrestore(&xhci->urb_list_lock, flags);
+ } else {
+ urb->status = -ENOENT;
+
+ spin_unlock(&urb->lock);
+ spin_unlock_irqrestore(&xhci->urb_list_lock, flags);
+
+ if (in_interrupt()) { /* wait at least 1 frame */
+ static int errorcount = 10;
+
+ if (errorcount--)
+ dbg("xhci_unlink_urb called from
interrupt for urb %p", urb);
+ udelay(1000);
+ } else
+ schedule_timeout(1+1*HZ/1000);
+
+ xhci_delete_urb(urb);
+
+ xhci_call_completion(urb);
+ }
+ }
+
+ return 0;
+}
+
+static void xhci_call_completion(struct urb *urb)
+{
+ struct urb_priv *urbp;
+ struct usb_device *dev = urb->dev;
+ int is_ring = 0, killed, resubmit_interrupt, status;
+ struct urb *nurb;
+ unsigned long flags;
+
+ spin_lock_irqsave(&urb->lock, flags);
+
+ urbp = (struct urb_priv *)urb->hcpriv;
+ if (!urbp || !urb->dev) {
+ spin_unlock_irqrestore(&urb->lock, flags);
+ return;
+ }
+
+ killed = (urb->status == -ENOENT || urb->status == -ECONNABORTED ||
+ urb->status == -ECONNRESET);
+ resubmit_interrupt = (usb_pipetype(urb->pipe) == PIPE_INTERRUPT &&
+ urb->interval);
+
+ nurb = urb->next;
+ if (nurb && !killed) {
+ int count = 0;
+
+ while (nurb && nurb != urb && count < MAX_URB_LOOP) {
+ if (nurb->status == -ENOENT ||
+ nurb->status == -ECONNABORTED ||
+ nurb->status == -ECONNRESET) {
+ killed = 1;
+ break;
+ }
+
+ nurb = nurb->next;
+ count++;
+ }
+
+ if (count == MAX_URB_LOOP)
+ err("xhci_call_completion: too many linked URB's, loop?
(first loop)");
+
+ /* Check to see if chain is a ring */
+ is_ring = (nurb == urb);
+ }
+
+ status = urbp->status;
+ if (!resubmit_interrupt || killed)
+ /* We don't need urb_priv anymore */
+ xhci_destroy_urb_priv(urb);
+
+ if (!killed)
+ urb->status = status;
+
+ spin_unlock_irqrestore(&urb->lock, flags);
+
+ if (urb->complete)
+ urb->complete(urb);
+
+ if (resubmit_interrupt)
+ /* Recheck the status. The completion handler may have */
+ /* unlinked the resubmitting interrupt URB */
+ killed = (urb->status == -ENOENT ||
+ urb->status == -ECONNABORTED ||
+ urb->status == -ECONNRESET);
+
+ if (resubmit_interrupt && !killed) {
+ if ( urb->dev != xhci->rh.dev )
+ xhci_queue_req(urb); /* XXX What if this fails? */
+ /* Don't need to resubmit URBs for the virtual root dev. */
+ } else {
+ if (is_ring && !killed) {
+ urb->dev = dev;
+ xhci_submit_urb(urb);
+ } else {
+ /* We decrement the usage count after we're done */
+ /* with everything */
+ usb_dec_dev_use(dev);
+ }
+ }
+}
+
+static void xhci_finish_completion(void)
+{
+ struct list_head *tmp, *head;
+ unsigned long flags;
+
+ spin_lock_irqsave(&xhci->complete_list_lock, flags);
+ head = &xhci->complete_list;
+ tmp = head->next;
+ while (tmp != head) {
+ struct urb_priv *urbp = list_entry(tmp, struct urb_priv,
+ complete_list);
+ struct urb *urb = urbp->urb;
+
+ list_del_init(&urbp->complete_list);
+ spin_unlock_irqrestore(&xhci->complete_list_lock, flags);
+
+ xhci_call_completion(urb);
+
+ spin_lock_irqsave(&xhci->complete_list_lock, flags);
+ head = &xhci->complete_list;
+ tmp = head->next;
+ }
+ spin_unlock_irqrestore(&xhci->complete_list_lock, flags);
+}
+
+static struct usb_operations xhci_device_operations = {
+ .allocate = xhci_do_nothing_dev,
+ .deallocate = xhci_do_nothing_dev,
+ /* It doesn't look like any drivers actually care what the frame number
+ * is at the moment! If necessary, we could approximate the current
+ * frame nubmer by passing it from the backend in response messages. */
+ .get_frame_number = NULL,
+ .submit_urb = xhci_submit_urb,
+ .unlink_urb = xhci_unlink_urb
+};
+
+/******************************************************************************
+ * VIRTUAL ROOT HUB EMULATION
+ */
+
+static __u8 root_hub_dev_des[] =
+{
+ 0x12, /* __u8 bLength; */
+ 0x01, /* __u8 bDescriptorType; Device */
+ 0x00, /* __u16 bcdUSB; v1.0 */
+ 0x01,
+ 0x09, /* __u8 bDeviceClass; HUB_CLASSCODE */
+ 0x00, /* __u8 bDeviceSubClass; */
+ 0x00, /* __u8 bDeviceProtocol; */
+ 0x08, /* __u8 bMaxPacketSize0; 8 Bytes */
+ 0x00, /* __u16 idVendor; */
+ 0x00,
+ 0x00, /* __u16 idProduct; */
+ 0x00,
+ 0x00, /* __u16 bcdDevice; */
+ 0x00,
+ 0x00, /* __u8 iManufacturer; */
+ 0x02, /* __u8 iProduct; */
+ 0x01, /* __u8 iSerialNumber; */
+ 0x01 /* __u8 bNumConfigurations; */
+};
+
+
+/* Configuration descriptor */
+static __u8 root_hub_config_des[] =
+{
+ 0x09, /* __u8 bLength; */
+ 0x02, /* __u8 bDescriptorType; Configuration */
+ 0x19, /* __u16 wTotalLength; */
+ 0x00,
+ 0x01, /* __u8 bNumInterfaces; */
+ 0x01, /* __u8 bConfigurationValue; */
+ 0x00, /* __u8 iConfiguration; */
+ 0x40, /* __u8 bmAttributes;
+ Bit 7: Bus-powered, 6: Self-powered,
+ Bit 5 Remote-wakeup, 4..0: resvd */
+ 0x00, /* __u8 MaxPower; */
+
+ /* interface */
+ 0x09, /* __u8 if_bLength; */
+ 0x04, /* __u8 if_bDescriptorType; Interface */
+ 0x00, /* __u8 if_bInterfaceNumber; */
+ 0x00, /* __u8 if_bAlternateSetting; */
+ 0x01, /* __u8 if_bNumEndpoints; */
+ 0x09, /* __u8 if_bInterfaceClass; HUB_CLASSCODE */
+ 0x00, /* __u8 if_bInterfaceSubClass; */
+ 0x00, /* __u8 if_bInterfaceProtocol; */
+ 0x00, /* __u8 if_iInterface; */
+
+ /* endpoint */
+ 0x07, /* __u8 ep_bLength; */
+ 0x05, /* __u8 ep_bDescriptorType; Endpoint */
+ 0x81, /* __u8 ep_bEndpointAddress; IN Endpoint 1 */
+ 0x03, /* __u8 ep_bmAttributes; Interrupt */
+ 0x08, /* __u16 ep_wMaxPacketSize; 8 Bytes */
+ 0x00,
+ 0xff /* __u8 ep_bInterval; 255 ms */
+};
+
+static __u8 root_hub_hub_des[] =
+{
+ 0x09, /* __u8 bLength; */
+ 0x29, /* __u8 bDescriptorType; Hub-descriptor */
+ 0x02, /* __u8 bNbrPorts; */
+ 0x00, /* __u16 wHubCharacteristics; */
+ 0x00,
+ 0x01, /* __u8 bPwrOn2pwrGood; 2ms */
+ 0x00, /* __u8 bHubContrCurrent; 0 mA */
+ 0x00, /* __u8 DeviceRemovable; *** 7 Ports max ***
*/
+ 0xff /* __u8 PortPwrCtrlMask; *** 7 ports max ***
*/
+};
+
+/* prepare Interrupt pipe transaction data; HUB INTERRUPT ENDPOINT */
+static int rh_send_irq(struct urb *urb)
+{
+ struct urb_priv *urbp = (struct urb_priv *)urb->hcpriv;
+ xhci_port_t *ports = xhci->rh.ports;
+ unsigned long flags;
+ int i, len = 1;
+ __u16 data = 0;
+
+ spin_lock_irqsave(&urb->lock, flags);
+ for (i = 0; i < xhci->rh.numports; i++) {
+ /* Set a bit if anything at all has changed on the port, as per
+ * USB spec 11.12 */
+ data |= (ports[i].cs_chg || ports[i].pe_chg )
+ ? (1 << (i + 1))
+ : 0;
+
+ len = (i + 1) / 8 + 1;
+ }
+
+ *(__u16 *) urb->transfer_buffer = cpu_to_le16(data);
+ urb->actual_length = len;
+ urbp->status = 0;
+
+ spin_unlock_irqrestore(&urb->lock, flags);
+
+ if ((data > 0) && (xhci->rh.send != 0)) {
+ dbg("root-hub INT complete: data: %x", data);
+ xhci_call_completion(urb);
+ }
+
+ return 0;
+}
+
+/* Virtual Root Hub INTs are polled by this timer every "interval" ms */
+static int rh_init_int_timer(struct urb *urb);
+
+static void rh_int_timer_do(unsigned long ptr)
+{
+ struct urb *urb = (struct urb *)ptr;
+ struct list_head list, *tmp, *head;
+ unsigned long flags;
+ int i;
+
+ for ( i = 0; i < xhci->rh.numports; i++)
+ xhci_queue_probe(i);
+
+ if (xhci->rh.send)
+ rh_send_irq(urb);
+
+ INIT_LIST_HEAD(&list);
+
+ spin_lock_irqsave(&xhci->urb_list_lock, flags);
+ head = &xhci->urb_list;
+ tmp = head->next;
+ while (tmp != head) {
+ struct urb *u = list_entry(tmp, struct urb, urb_list);
+ struct urb_priv *up = (struct urb_priv *)u->hcpriv;
+
+ tmp = tmp->next;
+
+ spin_lock(&u->lock);
+
+ /* Check if the URB timed out */
+ if (u->timeout && time_after_eq(jiffies,
+ up->inserttime + u->timeout)) {
+ list_del(&u->urb_list);
+ list_add_tail(&u->urb_list, &list);
+ }
+
+ spin_unlock(&u->lock);
+ }
+ spin_unlock_irqrestore(&xhci->urb_list_lock, flags);
+
+ head = &list;
+ tmp = head->next;
+ while (tmp != head) {
+ struct urb *u = list_entry(tmp, struct urb, urb_list);
+
+ tmp = tmp->next;
+
+ u->transfer_flags |= USB_ASYNC_UNLINK | USB_TIMEOUT_KILLED;
+ xhci_unlink_urb(u);
+ }
+
+ rh_init_int_timer(urb);
+}
+
+/* Root Hub INTs are polled by this timer */
+static int rh_init_int_timer(struct urb *urb)
+{
+ xhci->rh.interval = urb->interval;
+ init_timer(&xhci->rh.rh_int_timer);
+ xhci->rh.rh_int_timer.function = rh_int_timer_do;
+ xhci->rh.rh_int_timer.data = (unsigned long)urb;
+ xhci->rh.rh_int_timer.expires = jiffies
+ + (HZ * (urb->interval < 30 ? 30 : urb->interval)) / 1000;
+ add_timer(&xhci->rh.rh_int_timer);
+
+ return 0;
+}
+
+#define OK(x) len = (x); break
+
+/* Root Hub Control Pipe */
+static int rh_submit_urb(struct urb *urb)
+{
+ unsigned int pipe = urb->pipe;
+ struct usb_ctrlrequest *cmd =
+ (struct usb_ctrlrequest *)urb->setup_packet;
+ void *data = urb->transfer_buffer;
+ int leni = urb->transfer_buffer_length;
+ int len = 0;
+ xhci_port_t *status;
+ int stat = 0;
+ int i;
+ int retstatus;
+ unsigned long flags;
+
+ __u16 cstatus;
+ __u16 bmRType_bReq;
+ __u16 wValue;
+ __u16 wIndex;
+ __u16 wLength;
+
+ if (usb_pipetype(pipe) == PIPE_INTERRUPT) {
+ xhci->rh.urb = urb;
+ xhci->rh.send = 1;
+ xhci->rh.interval = urb->interval;
+ rh_init_int_timer(urb);
+
+ return -EINPROGRESS;
+ }
+
+ bmRType_bReq = cmd->bRequestType | cmd->bRequest << 8;
+ wValue = le16_to_cpu(cmd->wValue);
+ wIndex = le16_to_cpu(cmd->wIndex);
+ wLength = le16_to_cpu(cmd->wLength);
+
+ for (i = 0; i < 8; i++)
+ xhci->rh.c_p_r[i] = 0;
+
+ status = &xhci->rh.ports[wIndex - 1];
+
+ spin_lock_irqsave(&xhci->rh.port_state_lock, flags);
+
+ switch (bmRType_bReq) {
+ /* Request Destination:
+ without flags: Device,
+ RH_INTERFACE: interface,
+ RH_ENDPOINT: endpoint,
+ RH_CLASS means HUB here,
+ RH_OTHER | RH_CLASS almost ever means HUB_PORT here
+ */
+
+ case RH_GET_STATUS:
+ *(__u16 *)data = cpu_to_le16(1);
+ OK(2);
+ case RH_GET_STATUS | RH_INTERFACE:
+ *(__u16 *)data = cpu_to_le16(0);
+ OK(2);
+ case RH_GET_STATUS | RH_ENDPOINT:
+ *(__u16 *)data = cpu_to_le16(0);
+ OK(2);
+ case RH_GET_STATUS | RH_CLASS:
+ *(__u32 *)data = cpu_to_le32(0);
+ OK(4); /* hub power */
+ case RH_GET_STATUS | RH_OTHER | RH_CLASS:
+ cstatus = (status->cs_chg) |
+ (status->pe_chg << 1) |
+ (xhci->rh.c_p_r[wIndex - 1] << 4);
+ retstatus = (status->cs) |
+ (status->pe << 1) |
+ (status->susp << 2) |
+ (1 << 8) | /* power on */
+ (status->lsda << 9);
+ *(__u16 *)data = cpu_to_le16(retstatus);
+ *(__u16 *)(data + 2) = cpu_to_le16(cstatus);
+ OK(4);
+ case RH_CLEAR_FEATURE | RH_ENDPOINT:
+ switch (wValue) {
+ case RH_ENDPOINT_STALL:
+ OK(0);
+ }
+ break;
+ case RH_CLEAR_FEATURE | RH_CLASS:
+ switch (wValue) {
+ case RH_C_HUB_OVER_CURRENT:
+ OK(0); /* hub power over current */
+ }
+ break;
+ case RH_CLEAR_FEATURE | RH_OTHER | RH_CLASS:
+ switch (wValue) {
+ case RH_PORT_ENABLE:
+ status->pe = 0;
+ OK(0);
+ case RH_PORT_SUSPEND:
+ status->susp = 0;
+ OK(0);
+ case RH_PORT_POWER:
+ OK(0); /* port power */
+ case RH_C_PORT_CONNECTION:
+ status->cs_chg = 0;
+ OK(0);
+ case RH_C_PORT_ENABLE:
+ status->pe_chg = 0;
+ OK(0);
+ case RH_C_PORT_SUSPEND:
+ /*** WR_RH_PORTSTAT(RH_PS_PSSC); */
+ OK(0);
+ case RH_C_PORT_OVER_CURRENT:
+ OK(0); /* port power over current */
+ case RH_C_PORT_RESET:
+ xhci->rh.c_p_r[wIndex - 1] = 0;
+ OK(0);
+ }
+ break;
+ case RH_SET_FEATURE | RH_OTHER | RH_CLASS:
+ switch (wValue) {
+ case RH_PORT_SUSPEND:
+ status->susp = 1;
+ OK(0);
+ case RH_PORT_RESET:
+ {
+ int ret;
+ xhci->rh.c_p_r[wIndex - 1] = 1;
+ status->pr = 0;
+ status->pe = 1;
+ ret = xhci_port_reset(wIndex - 1);
+ /* XXX MAW: should probably cancel queued transfers
during reset... *\/ */
+ if ( ret == 0 ) { OK(0); }
+ else { return ret; }
+ }
+ break;
+ case RH_PORT_POWER:
+ OK(0); /* port power ** */
+ case RH_PORT_ENABLE:
+ status->pe = 1;
+ OK(0);
+ }
+ break;
+ case RH_SET_ADDRESS:
+ xhci->rh.devnum = wValue;
+ OK(0);
+ case RH_GET_DESCRIPTOR:
+ switch ((wValue & 0xff00) >> 8) {
+ case 0x01: /* device descriptor */
+ len = min_t(unsigned int, leni,
+ min_t(unsigned int,
+ sizeof(root_hub_dev_des), wLength));
+ memcpy(data, root_hub_dev_des, len);
+ OK(len);
+ case 0x02: /* configuration descriptor */
+ len = min_t(unsigned int, leni,
+ min_t(unsigned int,
+ sizeof(root_hub_config_des), wLength));
+ memcpy (data, root_hub_config_des, len);
+ OK(len);
+ case 0x03: /* string descriptors */
+ len = usb_root_hub_string (wValue & 0xff,
+ 0, "XHCI-alt",
+ data, wLength);
+ if (len > 0) {
+ OK(min_t(int, leni, len));
+ } else
+ stat = -EPIPE;
+ }
+ break;
+ case RH_GET_DESCRIPTOR | RH_CLASS:
+ root_hub_hub_des[2] = xhci->rh.numports;
+ len = min_t(unsigned int, leni,
+ min_t(unsigned int, sizeof(root_hub_hub_des),
wLength));
+ memcpy(data, root_hub_hub_des, len);
+ OK(len);
+ case RH_GET_CONFIGURATION:
+ *(__u8 *)data = 0x01;
+ OK(1);
+ case RH_SET_CONFIGURATION:
+ OK(0);
+ case RH_GET_INTERFACE | RH_INTERFACE:
+ *(__u8 *)data = 0x00;
+ OK(1);
+ case RH_SET_INTERFACE | RH_INTERFACE:
+ OK(0);
+ default:
+ stat = -EPIPE;
+ }
+
+ spin_unlock_irqrestore(&xhci->rh.port_state_lock, flags);
+
+ urb->actual_length = len;
+
+ return stat;
+}
+
+/*
+ * MUST be called with urb->lock acquired
+ */
+static int rh_unlink_urb(struct urb *urb)
+{
+ if (xhci->rh.urb == urb) {
+ urb->status = -ENOENT;
+ xhci->rh.send = 0;
+ xhci->rh.urb = NULL;
+ del_timer(&xhci->rh.rh_int_timer);
+ }
+ return 0;
+}
+
+/******************************************************************************
+ * CONTROL PLANE FUNCTIONALITY
+ */
+
+/**
+ * alloc_xhci - initialise a new virtual root hub for a new USB device channel
+ */
+static int alloc_xhci(void)
+{
+ int retval;
+ struct usb_bus *bus;
+
+ retval = -EBUSY;
+
+ xhci = kmalloc(sizeof(*xhci), GFP_KERNEL);
+ if (!xhci) {
+ err("couldn't allocate xhci structure");
+ retval = -ENOMEM;
+ goto err_alloc_xhci;
+ }
+
+ xhci->state = USBIF_STATE_CLOSED;
+
+ spin_lock_init(&xhci->urb_list_lock);
+ INIT_LIST_HEAD(&xhci->urb_list);
+
+ spin_lock_init(&xhci->complete_list_lock);
+ INIT_LIST_HEAD(&xhci->complete_list);
+
+ spin_lock_init(&xhci->frame_list_lock);
+
+ bus = usb_alloc_bus(&xhci_device_operations);
+
+ if (!bus) {
+ err("unable to allocate bus");
+ goto err_alloc_bus;
+ }
+
+ xhci->bus = bus;
+ bus->bus_name = "XHCI";
+ bus->hcpriv = xhci;
+
+ usb_register_bus(xhci->bus);
+
+ /* Initialize the root hub */
+
+ xhci->rh.numports = 0;
+
+ xhci->bus->root_hub = xhci->rh.dev = usb_alloc_dev(NULL, xhci->bus);
+ if (!xhci->rh.dev) {
+ err("unable to allocate root hub");
+ goto err_alloc_root_hub;
+ }
+
+ xhci->state = 0;
+
+ return 0;
+
+/*
+ * error exits:
+ */
+err_alloc_root_hub:
+ usb_deregister_bus(xhci->bus);
+ usb_free_bus(xhci->bus);
+ xhci->bus = NULL;
+
+err_alloc_bus:
+ kfree(xhci);
+
+err_alloc_xhci:
+ return retval;
+}
+
+/**
+ * usbif_status_change - deal with an incoming USB_INTERFACE_STATUS_ message
+ */
+static void usbif_status_change(usbif_fe_interface_status_changed_t *status)
+{
+ ctrl_msg_t cmsg;
+ usbif_fe_interface_connect_t up;
+ long rc;
+ usbif_sring_t *sring;
+
+ switch ( status->status )
+ {
+ case USBIF_INTERFACE_STATUS_DESTROYED:
+ printk(KERN_WARNING "Unexpected usbif-DESTROYED message in state %d\n",
+ xhci->state);
+ break;
+
+ case USBIF_INTERFACE_STATUS_DISCONNECTED:
+ if ( xhci->state != USBIF_STATE_CLOSED )
+ {
+ printk(KERN_WARNING "Unexpected usbif-DISCONNECTED message"
+ " in state %d\n", xhci->state);
+ break;
+ /* Not bothering to do recovery here for now. Keep things
+ * simple. */
+
+ spin_lock_irq(&xhci->ring_lock);
+
+ /* Clean up resources. */
+ free_page((unsigned long)xhci->usb_ring.sring);
+ free_irq(xhci->irq, xhci);
+ unbind_evtchn_from_irq(xhci->evtchn);
+
+ /* Plug the ring. */
+ xhci->recovery = 1;
+ wmb();
+
+ spin_unlock_irq(&xhci->ring_lock);
+ }
+
+ /* Move from CLOSED to DISCONNECTED state. */
+ sring = (usbif_sring_t *)__get_free_page(GFP_KERNEL);
+ SHARED_RING_INIT(sring);
+ FRONT_RING_INIT(&xhci->usb_ring, sring, PAGE_SIZE);
+ xhci->state = USBIF_STATE_DISCONNECTED;
+
+ /* Construct an interface-CONNECT message for the domain controller. */
+ cmsg.type = CMSG_USBIF_FE;
+ cmsg.subtype = CMSG_USBIF_FE_INTERFACE_CONNECT;
+ cmsg.length = sizeof(usbif_fe_interface_connect_t);
+ up.shmem_frame = virt_to_machine(sring) >> PAGE_SHIFT;
+ memcpy(cmsg.msg, &up, sizeof(up));
+
+ /* Tell the controller to bring up the interface. */
+ ctrl_if_send_message_block(&cmsg, NULL, 0, TASK_UNINTERRUPTIBLE);
+ break;
+
+ case USBIF_INTERFACE_STATUS_CONNECTED:
+ if ( xhci->state == USBIF_STATE_CLOSED )
+ {
+ printk(KERN_WARNING "Unexpected usbif-CONNECTED message"
+ " in state %d\n", xhci->state);
+ break;
+ }
+
+ xhci->evtchn = status->evtchn;
+ xhci->irq = bind_evtchn_to_irq(xhci->evtchn);
+ xhci->bandwidth = status->bandwidth;
+ xhci->rh.numports = status->num_ports;
+
+ xhci->rh.ports = kmalloc (sizeof(xhci_port_t) * xhci->rh.numports,
GFP_KERNEL);
+
+ if ( xhci->rh.ports == NULL )
+ goto alloc_ports_nomem;
+
+ memset(xhci->rh.ports, 0, sizeof(xhci_port_t) * xhci->rh.numports);
+
+ usb_connect(xhci->rh.dev);
+
+ if (usb_new_device(xhci->rh.dev) != 0) {
+ err("unable to start root hub");
+ }
+
+ /* Allocate the appropriate USB bandwidth here... Need to
+ * somehow know what the total available is thought to be so we
+ * can calculate the reservation correctly. */
+ usb_claim_bandwidth(xhci->rh.dev, xhci->rh.urb,
+ 1000 - xhci->bandwidth, 0);
+
+ if ( (rc = request_irq(xhci->irq, xhci_interrupt,
+ SA_SAMPLE_RANDOM, "usbif", xhci)) )
+ printk(KERN_ALERT"usbfront request_irq failed (%ld)\n",rc);
+
+ DPRINTK(KERN_INFO __FILE__
+ ": USB XHCI: SHM at %p (0x%lx), EVTCHN %d IRQ %d\n",
+ xhci->usb_ring.sring, virt_to_machine(xhci->usbif),
+ xhci->evtchn, xhci->irq);
+
+ xhci->state = USBIF_STATE_CONNECTED;
+
+ break;
+
+ default:
+ printk(KERN_WARNING "Status change to unknown value %d\n",
+ status->status);
+ break;
+ }
+
+ return;
+
+ alloc_ports_nomem:
+ printk(KERN_WARNING "Failed to allocate port memory, XHCI failed to
connect.\n");
+ return;
+}
+
+/**
+ * usbif_ctrlif_rx - demux control messages by subtype
+ */
+static void usbif_ctrlif_rx(ctrl_msg_t *msg, unsigned long id)
+{
+ switch ( msg->subtype )
+ {
+ case CMSG_USBIF_FE_INTERFACE_STATUS_CHANGED:
+ usbif_status_change((usbif_fe_interface_status_changed_t *)
+ &msg->msg[0]);
+ break;
+
+ /* New interface...? */
+ default:
+ msg->length = 0;
+ break;
+ }
+
+ ctrl_if_send_response(msg);
+}
+
+static void send_driver_up(void)
+{
+ control_msg_t cmsg;
+ usbif_fe_interface_status_changed_t st;
+
+ /* Send a driver-UP notification to the domain controller. */
+ cmsg.type = CMSG_USBIF_FE;
+ cmsg.subtype = CMSG_USBIF_FE_DRIVER_STATUS_CHANGED;
+ cmsg.length = sizeof(usbif_fe_driver_status_changed_t);
+ st.status = USBIF_DRIVER_STATUS_UP;
+ memcpy(cmsg.msg, &st, sizeof(st));
+ ctrl_if_send_message_block(&cmsg, NULL, 0, TASK_UNINTERRUPTIBLE);
+}
+
+void usbif_resume(void)
+{
+ int i;
+
+ /* Fake disconnection on all virtual USB ports (suspending / migrating
+ * will destroy hard state associated will the USB devices anyhow). */
+ /* No need to lock here. */
+ for ( i = 0; i < xhci->rh.numports; i++ )
+ {
+ xhci->rh.ports[i].cs = 0;
+ xhci->rh.ports[i].cs_chg = 1;
+ xhci->rh.ports[i].pe = 0;
+ }
+
+ send_driver_up();
+}
+
+static int __init xhci_hcd_init(void)
+{
+ int retval = -ENOMEM, i;
+
+ if ( (xen_start_info.flags & SIF_INITDOMAIN)
+ || (xen_start_info.flags & SIF_USB_BE_DOMAIN) )
+ return 0;
+
+ info(DRIVER_DESC " " DRIVER_VERSION);
+
+ if (debug) {
+ errbuf = kmalloc(ERRBUF_LEN, GFP_KERNEL);
+ if (!errbuf)
+ goto errbuf_failed;
+ }
+
+ xhci_up_cachep = kmem_cache_create("xhci_urb_priv",
+ sizeof(struct urb_priv), 0, 0, NULL, NULL);
+ if (!xhci_up_cachep)
+ goto up_failed;
+
+ /* Let the domain controller know we're here. For now we wait until
+ * connection, as for the block and net drivers. This is only strictly
+ * necessary if we're going to boot off a USB device. */
+ printk(KERN_INFO "Initialising Xen virtual USB hub\n");
+
+ (void)ctrl_if_register_receiver(CMSG_USBIF_FE, usbif_ctrlif_rx,
+ CALLBACK_IN_BLOCKING_CONTEXT);
+
+ alloc_xhci();
+
+ send_driver_up();
+
+ /*
+ * We should read 'nr_interfaces' from response message and wait
+ * for notifications before proceeding. For now we assume that we
+ * will be notified of exactly one interface.
+ */
+ for ( i=0; (xhci->state != USBIF_STATE_CONNECTED) && (i < 10*HZ); i++ )
+ {
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(1);
+ }
+
+ if (xhci->state != USBIF_STATE_CONNECTED)
+ printk(KERN_WARNING "Timeout connecting USB frontend driver!\n");
+
+ return 0;
+
+up_failed:
+ if (errbuf)
+ kfree(errbuf);
+
+errbuf_failed:
+ return retval;
+}
+
+module_init(xhci_hcd_init);
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/traps.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/traps.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,982 @@
+/*
+ * linux/arch/i386/traps.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000
+ */
+
+/*
+ * 'Traps.c' handles hardware traps and faults after we have saved some
+ * state in 'asm.s'.
+ */
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/timer.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#include <linux/highmem.h>
+#include <linux/kallsyms.h>
+#include <linux/ptrace.h>
+#include <linux/utsname.h>
+#include <linux/kprobes.h>
+
+#ifdef CONFIG_EISA
+#include <linux/ioport.h>
+#include <linux/eisa.h>
+#endif
+
+#ifdef CONFIG_MCA
+#include <linux/mca.h>
+#endif
+
+#include <asm/processor.h>
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/atomic.h>
+#include <asm/debugreg.h>
+#include <asm/desc.h>
+#include <asm/i387.h>
+#include <asm/nmi.h>
+
+#include <asm/smp.h>
+#include <asm/arch_hooks.h>
+#include <asm/kdebug.h>
+
+#include <linux/irq.h>
+#include <linux/module.h>
+
+#include "mach_traps.h"
+
+asmlinkage int system_call(void);
+
+/* Do we ignore FPU interrupts ? */
+char ignore_fpu_irq = 0;
+
+/*
+ * The IDT has to be page-aligned to simplify the Pentium
+ * F0 0F bug workaround.. We have a special link segment
+ * for this.
+ */
+struct desc_struct idt_table[256] __attribute__((__section__(".data.idt"))) =
{ {0, 0}, };
+
+asmlinkage void divide_error(void);
+asmlinkage void debug(void);
+asmlinkage void nmi(void);
+asmlinkage void int3(void);
+asmlinkage void overflow(void);
+asmlinkage void bounds(void);
+asmlinkage void invalid_op(void);
+asmlinkage void device_not_available(void);
+asmlinkage void coprocessor_segment_overrun(void);
+asmlinkage void invalid_TSS(void);
+asmlinkage void segment_not_present(void);
+asmlinkage void stack_segment(void);
+asmlinkage void general_protection(void);
+asmlinkage void page_fault(void);
+asmlinkage void coprocessor_error(void);
+asmlinkage void simd_coprocessor_error(void);
+asmlinkage void alignment_check(void);
+asmlinkage void fixup_4gb_segment(void);
+asmlinkage void machine_check(void);
+
+static int kstack_depth_to_print = 24;
+struct notifier_block *i386die_chain;
+static DEFINE_SPINLOCK(die_notifier_lock);
+
+int register_die_notifier(struct notifier_block *nb)
+{
+ int err = 0;
+ unsigned long flags;
+ spin_lock_irqsave(&die_notifier_lock, flags);
+ err = notifier_chain_register(&i386die_chain, nb);
+ spin_unlock_irqrestore(&die_notifier_lock, flags);
+ return err;
+}
+
+static inline int valid_stack_ptr(struct thread_info *tinfo, void *p)
+{
+ return p > (void *)tinfo &&
+ p < (void *)tinfo + THREAD_SIZE - 3;
+}
+
+static inline unsigned long print_context_stack(struct thread_info *tinfo,
+ unsigned long *stack, unsigned long ebp)
+{
+ unsigned long addr;
+
+#ifdef CONFIG_FRAME_POINTER
+ while (valid_stack_ptr(tinfo, (void *)ebp)) {
+ addr = *(unsigned long *)(ebp + 4);
+ printk(" [<%08lx>] ", addr);
+ print_symbol("%s", addr);
+ printk("\n");
+ ebp = *(unsigned long *)ebp;
+ }
+#else
+ while (valid_stack_ptr(tinfo, stack)) {
+ addr = *stack++;
+ if (__kernel_text_address(addr)) {
+ printk(" [<%08lx>]", addr);
+ print_symbol(" %s", addr);
+ printk("\n");
+ }
+ }
+#endif
+ return ebp;
+}
+
+void show_trace(struct task_struct *task, unsigned long * stack)
+{
+ unsigned long ebp;
+
+ if (!task)
+ task = current;
+
+ if (task == current) {
+ /* Grab ebp right from our regs */
+ asm ("movl %%ebp, %0" : "=r" (ebp) : );
+ } else {
+ /* ebp is the last reg pushed by switch_to */
+ ebp = *(unsigned long *) task->thread.esp;
+ }
+
+ while (1) {
+ struct thread_info *context;
+ context = (struct thread_info *)
+ ((unsigned long)stack & (~(THREAD_SIZE - 1)));
+ ebp = print_context_stack(context, stack, ebp);
+ stack = (unsigned long*)context->previous_esp;
+ if (!stack)
+ break;
+ printk(" =======================\n");
+ }
+}
+
+void show_stack(struct task_struct *task, unsigned long *esp)
+{
+ unsigned long *stack;
+ int i;
+
+ if (esp == NULL) {
+ if (task)
+ esp = (unsigned long*)task->thread.esp;
+ else
+ esp = (unsigned long *)&esp;
+ }
+
+ stack = esp;
+ for(i = 0; i < kstack_depth_to_print; i++) {
+ if (kstack_end(stack))
+ break;
+ if (i && ((i % 8) == 0))
+ printk("\n ");
+ printk("%08lx ", *stack++);
+ }
+ printk("\nCall Trace:\n");
+ show_trace(task, esp);
+}
+
+/*
+ * The architecture-independent dump_stack generator
+ */
+void dump_stack(void)
+{
+ unsigned long stack;
+
+ show_trace(current, &stack);
+}
+
+EXPORT_SYMBOL(dump_stack);
+
+void show_registers(struct pt_regs *regs)
+{
+ int i;
+ int in_kernel = 1;
+ unsigned long esp;
+ unsigned short ss;
+
+ esp = (unsigned long) (®s->esp);
+ ss = __KERNEL_DS;
+ if (regs->xcs & 2) {
+ in_kernel = 0;
+ esp = regs->esp;
+ ss = regs->xss & 0xffff;
+ }
+ print_modules();
+ printk("CPU: %d\nEIP: %04x:[<%08lx>] %s VLI\nEFLAGS: %08lx"
+ " (%s) \n",
+ smp_processor_id(), 0xffff & regs->xcs, regs->eip,
+ print_tainted(), regs->eflags, system_utsname.release);
+ print_symbol("EIP is at %s\n", regs->eip);
+ printk("eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n",
+ regs->eax, regs->ebx, regs->ecx, regs->edx);
+ printk("esi: %08lx edi: %08lx ebp: %08lx esp: %08lx\n",
+ regs->esi, regs->edi, regs->ebp, esp);
+ printk("ds: %04x es: %04x ss: %04x\n",
+ regs->xds & 0xffff, regs->xes & 0xffff, ss);
+ printk("Process %s (pid: %d, threadinfo=%p task=%p)",
+ current->comm, current->pid, current_thread_info(), current);
+ /*
+ * When in-kernel, we also print out the stack and code at the
+ * time of the fault..
+ */
+ if (in_kernel) {
+ u8 *eip;
+
+ printk("\nStack: ");
+ show_stack(NULL, (unsigned long*)esp);
+
+ printk("Code: ");
+
+ eip = (u8 *)regs->eip - 43;
+ for (i = 0; i < 64; i++, eip++) {
+ unsigned char c;
+
+ if (eip < (u8 *)PAGE_OFFSET || __get_user(c, eip)) {
+ printk(" Bad EIP value.");
+ break;
+ }
+ if (eip == (u8 *)regs->eip)
+ printk("<%02x> ", c);
+ else
+ printk("%02x ", c);
+ }
+ }
+ printk("\n");
+}
+
+static void handle_BUG(struct pt_regs *regs)
+{
+ unsigned short ud2;
+ unsigned short line;
+ char *file;
+ char c;
+ unsigned long eip;
+
+ if (regs->xcs & 2)
+ goto no_bug; /* Not in kernel */
+
+ eip = regs->eip;
+
+ if (eip < PAGE_OFFSET)
+ goto no_bug;
+ if (__get_user(ud2, (unsigned short *)eip))
+ goto no_bug;
+ if (ud2 != 0x0b0f)
+ goto no_bug;
+ if (__get_user(line, (unsigned short *)(eip + 2)))
+ goto bug;
+ if (__get_user(file, (char **)(eip + 4)) ||
+ (unsigned long)file < PAGE_OFFSET || __get_user(c, file))
+ file = "<bad filename>";
+
+ printk("------------[ cut here ]------------\n");
+ printk(KERN_ALERT "kernel BUG at %s:%d!\n", file, line);
+
+no_bug:
+ return;
+
+ /* Here we know it was a BUG but file-n-line is unavailable */
+bug:
+ printk("Kernel BUG\n");
+}
+
+void die(const char * str, struct pt_regs * regs, long err)
+{
+ static struct {
+ spinlock_t lock;
+ u32 lock_owner;
+ int lock_owner_depth;
+ } die = {
+ .lock = SPIN_LOCK_UNLOCKED,
+ .lock_owner = -1,
+ .lock_owner_depth = 0
+ };
+ static int die_counter;
+
+ if (die.lock_owner != _smp_processor_id()) {
+ console_verbose();
+ spin_lock_irq(&die.lock);
+ die.lock_owner = smp_processor_id();
+ die.lock_owner_depth = 0;
+ bust_spinlocks(1);
+ }
+
+ if (++die.lock_owner_depth < 3) {
+ int nl = 0;
+ handle_BUG(regs);
+ printk(KERN_ALERT "%s: %04lx [#%d]\n", str, err & 0xffff,
++die_counter);
+#ifdef CONFIG_PREEMPT
+ printk("PREEMPT ");
+ nl = 1;
+#endif
+#ifdef CONFIG_SMP
+ printk("SMP ");
+ nl = 1;
+#endif
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ printk("DEBUG_PAGEALLOC");
+ nl = 1;
+#endif
+ if (nl)
+ printk("\n");
+ notify_die(DIE_OOPS, (char *)str, regs, err, 255, SIGSEGV);
+ show_registers(regs);
+ } else
+ printk(KERN_ERR "Recursive die() failure, output suppressed\n");
+
+ bust_spinlocks(0);
+ die.lock_owner = -1;
+ spin_unlock_irq(&die.lock);
+ if (in_interrupt())
+ panic("Fatal exception in interrupt");
+
+ if (panic_on_oops) {
+ printk(KERN_EMERG "Fatal exception: panic in 5 seconds\n");
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ schedule_timeout(5 * HZ);
+ panic("Fatal exception");
+ }
+ do_exit(SIGSEGV);
+}
+
+static inline void die_if_kernel(const char * str, struct pt_regs * regs, long
err)
+{
+ if (!(regs->eflags & VM_MASK) && !(2 & regs->xcs))
+ die(str, regs, err);
+}
+
+static void do_trap(int trapnr, int signr, char *str, int vm86,
+ struct pt_regs * regs, long error_code, siginfo_t
*info)
+{
+ if (regs->eflags & VM_MASK) {
+ if (vm86)
+ goto vm86_trap;
+ goto trap_signal;
+ }
+
+ if (!(regs->xcs & 2))
+ goto kernel_trap;
+
+ trap_signal: {
+ struct task_struct *tsk = current;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = trapnr;
+ if (info)
+ force_sig_info(signr, info, tsk);
+ else
+ force_sig(signr, tsk);
+ return;
+ }
+
+ kernel_trap: {
+ if (!fixup_exception(regs))
+ die(str, regs, error_code);
+ return;
+ }
+
+ vm86_trap: {
+ int ret = handle_vm86_trap((struct kernel_vm86_regs *) regs,
error_code, trapnr);
+ if (ret) goto trap_signal;
+ return;
+ }
+}
+
+#define DO_ERROR(trapnr, signr, str, name) \
+fastcall void do_##name(struct pt_regs * regs, long error_code) \
+{ \
+ if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
+ == NOTIFY_STOP) \
+ return; \
+ do_trap(trapnr, signr, str, 0, regs, error_code, NULL); \
+}
+
+#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
+fastcall void do_##name(struct pt_regs * regs, long error_code) \
+{ \
+ siginfo_t info; \
+ info.si_signo = signr; \
+ info.si_errno = 0; \
+ info.si_code = sicode; \
+ info.si_addr = (void __user *)siaddr; \
+ if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
+ == NOTIFY_STOP) \
+ return; \
+ do_trap(trapnr, signr, str, 0, regs, error_code, &info); \
+}
+
+#define DO_VM86_ERROR(trapnr, signr, str, name) \
+fastcall void do_##name(struct pt_regs * regs, long error_code) \
+{ \
+ if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
+ == NOTIFY_STOP) \
+ return; \
+ do_trap(trapnr, signr, str, 1, regs, error_code, NULL); \
+}
+
+#define DO_VM86_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
+fastcall void do_##name(struct pt_regs * regs, long error_code) \
+{ \
+ siginfo_t info; \
+ info.si_signo = signr; \
+ info.si_errno = 0; \
+ info.si_code = sicode; \
+ info.si_addr = (void __user *)siaddr; \
+ if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
+ == NOTIFY_STOP) \
+ return; \
+ do_trap(trapnr, signr, str, 1, regs, error_code, &info); \
+}
+
+DO_VM86_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV,
regs->eip)
+#ifndef CONFIG_KPROBES
+DO_VM86_ERROR( 3, SIGTRAP, "int3", int3)
+#endif
+DO_VM86_ERROR( 4, SIGSEGV, "overflow", overflow)
+DO_VM86_ERROR( 5, SIGSEGV, "bounds", bounds)
+DO_ERROR_INFO( 6, SIGILL, "invalid operand", invalid_op, ILL_ILLOPN,
regs->eip)
+DO_VM86_ERROR( 7, SIGSEGV, "device not available", device_not_available)
+DO_ERROR( 9, SIGFPE, "coprocessor segment overrun",
coprocessor_segment_overrun)
+DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
+DO_ERROR(11, SIGBUS, "segment not present", segment_not_present)
+DO_ERROR(12, SIGBUS, "stack segment", stack_segment)
+DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0)
+#ifdef CONFIG_X86_MCE
+DO_ERROR(18, SIGBUS, "machine check", machine_check)
+#endif
+
+fastcall void do_general_protection(struct pt_regs * regs, long error_code)
+{
+ /*
+ * If we trapped on an LDT access then ensure that the default_ldt is
+ * loaded, if nothing else. We load default_ldt lazily because LDT
+ * switching costs time and many applications don't need it.
+ */
+ if (unlikely((error_code & 6) == 4)) {
+ unsigned long ldt;
+ __asm__ __volatile__ ("sldt %0" : "=r" (ldt));
+ if (ldt == 0) {
+ xen_set_ldt((unsigned long)&default_ldt[0], 5);
+ return;
+ }
+ }
+
+ if (regs->eflags & VM_MASK)
+ goto gp_in_vm86;
+
+ if (!(regs->xcs & 2))
+ goto gp_in_kernel;
+
+ current->thread.error_code = error_code;
+ current->thread.trap_no = 13;
+ force_sig(SIGSEGV, current);
+ return;
+
+gp_in_vm86:
+ local_irq_enable();
+ handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
+ return;
+
+gp_in_kernel:
+ if (!fixup_exception(regs)) {
+ if (notify_die(DIE_GPF, "general protection fault", regs,
+ error_code, 13, SIGSEGV) == NOTIFY_STOP)
+ return;
+ die("general protection fault", regs, error_code);
+ }
+}
+
+static void mem_parity_error(unsigned char reason, struct pt_regs * regs)
+{
+ printk("Uhhuh. NMI received. Dazed and confused, but trying to
continue\n");
+ printk("You probably have a hardware problem with your RAM chips\n");
+
+ /* Clear and disable the memory parity error line. */
+ clear_mem_error(reason);
+}
+
+static void io_check_error(unsigned char reason, struct pt_regs * regs)
+{
+ unsigned long i;
+
+ printk("NMI: IOCK error (debug interrupt?)\n");
+ show_registers(regs);
+
+ /* Re-enable the IOCK line, wait for a few seconds */
+ reason = (reason & 0xf) | 8;
+ outb(reason, 0x61);
+ i = 2000;
+ while (--i) udelay(1000);
+ reason &= ~8;
+ outb(reason, 0x61);
+}
+
+static void unknown_nmi_error(unsigned char reason, struct pt_regs * regs)
+{
+#ifdef CONFIG_MCA
+ /* Might actually be able to figure out what the guilty party
+ * is. */
+ if( MCA_bus ) {
+ mca_handle_nmi();
+ return;
+ }
+#endif
+ printk("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
+ reason, smp_processor_id());
+ printk("Dazed and confused, but trying to continue\n");
+ printk("Do you have a strange power saving mode enabled?\n");
+}
+
+static DEFINE_SPINLOCK(nmi_print_lock);
+
+void die_nmi (struct pt_regs *regs, const char *msg)
+{
+ spin_lock(&nmi_print_lock);
+ /*
+ * We are in trouble anyway, lets at least try
+ * to get a message out.
+ */
+ bust_spinlocks(1);
+ printk(msg);
+ printk(" on CPU%d, eip %08lx, registers:\n",
+ smp_processor_id(), regs->eip);
+ show_registers(regs);
+ printk("console shuts up ...\n");
+ console_silent();
+ spin_unlock(&nmi_print_lock);
+ bust_spinlocks(0);
+ do_exit(SIGSEGV);
+}
+
+static void default_do_nmi(struct pt_regs * regs)
+{
+ unsigned char reason = 0;
+
+ /* Only the BSP gets external NMIs from the system. */
+ if (!smp_processor_id())
+ reason = get_nmi_reason();
+
+ if (!(reason & 0xc0)) {
+ if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 0, SIGINT)
+ == NOTIFY_STOP)
+ return;
+#ifdef CONFIG_X86_LOCAL_APIC
+ /*
+ * Ok, so this is none of the documented NMI sources,
+ * so it must be the NMI watchdog.
+ */
+ if (nmi_watchdog) {
+ nmi_watchdog_tick(regs);
+ return;
+ }
+#endif
+ unknown_nmi_error(reason, regs);
+ return;
+ }
+ if (notify_die(DIE_NMI, "nmi", regs, reason, 0, SIGINT) == NOTIFY_STOP)
+ return;
+ if (reason & 0x80)
+ mem_parity_error(reason, regs);
+ if (reason & 0x40)
+ io_check_error(reason, regs);
+ /*
+ * Reassert NMI in case it became active meanwhile
+ * as it's edge-triggered.
+ */
+ reassert_nmi();
+}
+
+static int dummy_nmi_callback(struct pt_regs * regs, int cpu)
+{
+ return 0;
+}
+
+static nmi_callback_t nmi_callback = dummy_nmi_callback;
+
+fastcall void do_nmi(struct pt_regs * regs, long error_code)
+{
+ int cpu;
+
+ nmi_enter();
+
+ cpu = smp_processor_id();
+
+#ifdef CONFIG_HOTPLUG_CPU
+ if (!cpu_online(cpu)) {
+ nmi_exit();
+ return;
+ }
+#endif
+
+ ++nmi_count(cpu);
+
+ if (!nmi_callback(regs, cpu))
+ default_do_nmi(regs);
+
+ nmi_exit();
+}
+
+void set_nmi_callback(nmi_callback_t callback)
+{
+ nmi_callback = callback;
+}
+
+void unset_nmi_callback(void)
+{
+ nmi_callback = dummy_nmi_callback;
+}
+
+#ifdef CONFIG_KPROBES
+fastcall int do_int3(struct pt_regs *regs, long error_code)
+{
+ if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP)
+ == NOTIFY_STOP)
+ return 1;
+ /* This is an interrupt gate, because kprobes wants interrupts
+ disabled. Normal trap handlers don't. */
+ restore_interrupts(regs);
+ do_trap(3, SIGTRAP, "int3", 1, regs, error_code, NULL);
+ return 0;
+}
+#endif
+
+/*
+ * Our handling of the processor debug registers is non-trivial.
+ * We do not clear them on entry and exit from the kernel. Therefore
+ * it is possible to get a watchpoint trap here from inside the kernel.
+ * However, the code in ./ptrace.c has ensured that the user can
+ * only set watchpoints on userspace addresses. Therefore the in-kernel
+ * watchpoint trap can only occur in code which is reading/writing
+ * from user space. Such code must not hold kernel locks (since it
+ * can equally take a page fault), therefore it is safe to call
+ * force_sig_info even though that claims and releases locks.
+ *
+ * Code in ./signal.c ensures that the debug control register
+ * is restored before we deliver any signal, and therefore that
+ * user code runs with the correct debug control register even though
+ * we clear it here.
+ *
+ * Being careful here means that we don't have to be as careful in a
+ * lot of more complicated places (task switching can be a bit lazy
+ * about restoring all the debug state, and ptrace doesn't have to
+ * find every occurrence of the TF bit that could be saved away even
+ * by user code)
+ */
+fastcall void do_debug(struct pt_regs * regs, long error_code)
+{
+ unsigned int condition;
+ struct task_struct *tsk = current;
+
+ condition = HYPERVISOR_get_debugreg(6);
+
+ if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code,
+ SIGTRAP) == NOTIFY_STOP)
+ return;
+#if 0
+ /* It's safe to allow irq's after DR6 has been saved */
+ if (regs->eflags & X86_EFLAGS_IF)
+ local_irq_enable();
+#endif
+
+ /* Mask out spurious debug traps due to lazy DR7 setting */
+ if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) {
+ if (!tsk->thread.debugreg[7])
+ goto clear_dr7;
+ }
+
+ if (regs->eflags & VM_MASK)
+ goto debug_vm86;
+
+ /* Save debug status register where ptrace can see it */
+ tsk->thread.debugreg[6] = condition;
+
+ /*
+ * Single-stepping through TF: make sure we ignore any events in
+ * kernel space (but re-enable TF when returning to user mode).
+ * And if the event was due to a debugger (PT_DTRACE), clear the
+ * TF flag so that register information is correct.
+ */
+ if (condition & DR_STEP) {
+ /*
+ * We already checked v86 mode above, so we can
+ * check for kernel mode by just checking the CPL
+ * of CS.
+ */
+ if ((regs->xcs & 2) == 0)
+ goto clear_TF_reenable;
+
+ if (likely(tsk->ptrace & PT_DTRACE)) {
+ tsk->ptrace &= ~PT_DTRACE;
+ regs->eflags &= ~TF_MASK;
+ }
+ }
+
+ /* Ok, finally something we can handle */
+ send_sigtrap(tsk, regs, error_code);
+
+ /* Disable additional traps. They'll be re-enabled when
+ * the signal is delivered.
+ */
+clear_dr7:
+ HYPERVISOR_set_debugreg(7, 0);
+ return;
+
+debug_vm86:
+ handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1);
+ return;
+
+clear_TF_reenable:
+ set_tsk_thread_flag(tsk, TIF_SINGLESTEP);
+ regs->eflags &= ~TF_MASK;
+ return;
+}
+
+/*
+ * Note that we play around with the 'TS' bit in an attempt to get
+ * the correct behaviour even in the presence of the asynchronous
+ * IRQ13 behaviour
+ */
+void math_error(void __user *eip)
+{
+ struct task_struct * task;
+ siginfo_t info;
+ unsigned short cwd, swd;
+
+ /*
+ * Save the info for the exception handler and clear the error.
+ */
+ task = current;
+ save_init_fpu(task);
+ task->thread.trap_no = 16;
+ task->thread.error_code = 0;
+ info.si_signo = SIGFPE;
+ info.si_errno = 0;
+ info.si_code = __SI_FAULT;
+ info.si_addr = eip;
+ /*
+ * (~cwd & swd) will mask out exceptions that are not set to unmasked
+ * status. 0x3f is the exception bits in these regs, 0x200 is the
+ * C1 reg you need in case of a stack fault, 0x040 is the stack
+ * fault bit. We should only be taking one exception at a time,
+ * so if this combination doesn't produce any single exception,
+ * then we have a bad program that isn't syncronizing its FPU usage
+ * and it will suffer the consequences since we won't be able to
+ * fully reproduce the context of the exception
+ */
+ cwd = get_fpu_cwd(task);
+ swd = get_fpu_swd(task);
+ switch (((~cwd) & swd & 0x3f) | (swd & 0x240)) {
+ case 0x000:
+ default:
+ break;
+ case 0x001: /* Invalid Op */
+ case 0x041: /* Stack Fault */
+ case 0x241: /* Stack Fault | Direction */
+ info.si_code = FPE_FLTINV;
+ /* Should we clear the SF or let user space do it ????
*/
+ break;
+ case 0x002: /* Denormalize */
+ case 0x010: /* Underflow */
+ info.si_code = FPE_FLTUND;
+ break;
+ case 0x004: /* Zero Divide */
+ info.si_code = FPE_FLTDIV;
+ break;
+ case 0x008: /* Overflow */
+ info.si_code = FPE_FLTOVF;
+ break;
+ case 0x020: /* Precision */
+ info.si_code = FPE_FLTRES;
+ break;
+ }
+ force_sig_info(SIGFPE, &info, task);
+}
+
+fastcall void do_coprocessor_error(struct pt_regs * regs, long error_code)
+{
+ ignore_fpu_irq = 1;
+ math_error((void __user *)regs->eip);
+}
+
+void simd_math_error(void __user *eip)
+{
+ struct task_struct * task;
+ siginfo_t info;
+ unsigned short mxcsr;
+
+ /*
+ * Save the info for the exception handler and clear the error.
+ */
+ task = current;
+ save_init_fpu(task);
+ task->thread.trap_no = 19;
+ task->thread.error_code = 0;
+ info.si_signo = SIGFPE;
+ info.si_errno = 0;
+ info.si_code = __SI_FAULT;
+ info.si_addr = eip;
+ /*
+ * The SIMD FPU exceptions are handled a little differently, as there
+ * is only a single status/control register. Thus, to determine which
+ * unmasked exception was caught we must mask the exception mask bits
+ * at 0x1f80, and then use these to mask the exception bits at 0x3f.
+ */
+ mxcsr = get_fpu_mxcsr(task);
+ switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) {
+ case 0x000:
+ default:
+ break;
+ case 0x001: /* Invalid Op */
+ info.si_code = FPE_FLTINV;
+ break;
+ case 0x002: /* Denormalize */
+ case 0x010: /* Underflow */
+ info.si_code = FPE_FLTUND;
+ break;
+ case 0x004: /* Zero Divide */
+ info.si_code = FPE_FLTDIV;
+ break;
+ case 0x008: /* Overflow */
+ info.si_code = FPE_FLTOVF;
+ break;
+ case 0x020: /* Precision */
+ info.si_code = FPE_FLTRES;
+ break;
+ }
+ force_sig_info(SIGFPE, &info, task);
+}
+
+fastcall void do_simd_coprocessor_error(struct pt_regs * regs,
+ long error_code)
+{
+ if (cpu_has_xmm) {
+ /* Handle SIMD FPU exceptions on PIII+ processors. */
+ ignore_fpu_irq = 1;
+ simd_math_error((void __user *)regs->eip);
+ } else {
+ /*
+ * Handle strange cache flush from user space exception
+ * in all other cases. This is undocumented behaviour.
+ */
+ if (regs->eflags & VM_MASK) {
+ handle_vm86_fault((struct kernel_vm86_regs *)regs,
+ error_code);
+ return;
+ }
+ die_if_kernel("cache flush denied", regs, error_code);
+ current->thread.trap_no = 19;
+ current->thread.error_code = error_code;
+ force_sig(SIGSEGV, current);
+ }
+}
+
+/*
+ * 'math_state_restore()' saves the current math information in the
+ * old math state array, and gets the new ones from the current task
+ *
+ * Careful.. There are problems with IBM-designed IRQ13 behaviour.
+ * Don't touch unless you *really* know how it works.
+ *
+ * Must be called with kernel preemption disabled (in this case,
+ * local interrupts are disabled at the call-site in entry.S).
+ */
+asmlinkage void math_state_restore(struct pt_regs regs)
+{
+ struct thread_info *thread = current_thread_info();
+ struct task_struct *tsk = thread->task;
+
+ /* NB. 'clts' is done for us by Xen during virtual trap. */
+ if (!tsk_used_math(tsk))
+ init_fpu(tsk);
+ restore_fpu(tsk);
+ thread->status |= TS_USEDFPU; /* So we fnsave on switch_to() */
+}
+
+#ifndef CONFIG_MATH_EMULATION
+
+asmlinkage void math_emulate(long arg)
+{
+ printk("math-emulation not enabled and no coprocessor found.\n");
+ printk("killing %s.\n",current->comm);
+ force_sig(SIGFPE,current);
+ schedule();
+}
+
+#endif /* CONFIG_MATH_EMULATION */
+
+#ifdef CONFIG_X86_F00F_BUG
+void __init trap_init_f00f_bug(void)
+{
+ __set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO);
+
+ /*
+ * Update the IDT descriptor and reload the IDT so that
+ * it uses the read-only mapped virtual address.
+ */
+ idt_descr.address = fix_to_virt(FIX_F00F_IDT);
+ __asm__ __volatile__("lidt %0" : : "m" (idt_descr));
+}
+#endif
+
+
+/* NB. All these are "trap gates" (i.e. events_mask isn't cleared). */
+static trap_info_t trap_table[] = {
+ { 0, 0, __KERNEL_CS, (unsigned long)divide_error },
+ { 1, 0, __KERNEL_CS, (unsigned long)debug },
+ { 3, 3, __KERNEL_CS, (unsigned long)int3 },
+ { 4, 3, __KERNEL_CS, (unsigned long)overflow },
+ { 5, 3, __KERNEL_CS, (unsigned long)bounds },
+ { 6, 0, __KERNEL_CS, (unsigned long)invalid_op },
+ { 7, 0, __KERNEL_CS, (unsigned long)device_not_available },
+ { 9, 0, __KERNEL_CS, (unsigned long)coprocessor_segment_overrun },
+ { 10, 0, __KERNEL_CS, (unsigned long)invalid_TSS },
+ { 11, 0, __KERNEL_CS, (unsigned long)segment_not_present },
+ { 12, 0, __KERNEL_CS, (unsigned long)stack_segment },
+ { 13, 0, __KERNEL_CS, (unsigned long)general_protection },
+ { 14, 0, __KERNEL_CS, (unsigned long)page_fault },
+ { 15, 0, __KERNEL_CS, (unsigned long)fixup_4gb_segment },
+ { 16, 0, __KERNEL_CS, (unsigned long)coprocessor_error },
+ { 17, 0, __KERNEL_CS, (unsigned long)alignment_check },
+#ifdef CONFIG_X86_MCE
+ { 18, 0, __KERNEL_CS, (unsigned long)machine_check },
+#endif
+ { 19, 0, __KERNEL_CS, (unsigned long)simd_coprocessor_error },
+ { SYSCALL_VECTOR, 3, __KERNEL_CS, (unsigned long)system_call },
+ { 0, 0, 0, 0 }
+};
+
+void __init trap_init(void)
+{
+ HYPERVISOR_set_trap_table(trap_table);
+
+ /*
+ * default LDT is a single-entry callgate to lcall7 for iBCS
+ * and a callgate to lcall27 for Solaris/x86 binaries
+ */
+ make_lowmem_page_readonly(&default_ldt[0]);
+
+ /*
+ * Should be a barrier for any external CPU state.
+ */
+ cpu_init();
+}
+
+void smp_trap_init(trap_info_t *trap_ctxt)
+{
+ trap_info_t *t = trap_table;
+
+ for (t = trap_table; t->address; t++) {
+ trap_ctxt[t->vector].flags = t->flags;
+ trap_ctxt[t->vector].cs = t->cs;
+ trap_ctxt[t->vector].address = t->address;
+ }
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/time.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/time.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,801 @@
+/*
+ * linux/arch/i386/kernel/time.c
+ *
+ * Copyright (C) 1991, 1992, 1995 Linus Torvalds
+ *
+ * This file contains the PC-specific time handling details:
+ * reading the RTC at bootup, etc..
+ * 1994-07-02 Alan Modra
+ * fixed set_rtc_mmss, fixed time.year for >= 2000, new mktime
+ * 1995-03-26 Markus Kuhn
+ * fixed 500 ms bug at call to set_rtc_mmss, fixed DS12887
+ * precision CMOS clock update
+ * 1996-05-03 Ingo Molnar
+ * fixed time warps in do_[slow|fast]_gettimeoffset()
+ * 1997-09-10 Updated NTP code according to technical memorandum Jan '96
+ * "A Kernel Model for Precision Timekeeping" by Dave Mills
+ * 1998-09-05 (Various)
+ * More robust do_fast_gettimeoffset() algorithm implemented
+ * (works with APM, Cyrix 6x86MX and Centaur C6),
+ * monotonic gettimeofday() with fast_get_timeoffset(),
+ * drift-proof precision TSC calibration on boot
+ * (C. Scott Ananian <cananian@xxxxxxxxxxxxxxxxxxxx>, Andrew D.
+ * Balsa <andrebalsa@xxxxxxxxxx>, Philip Gladstone <philip@xxxxxxxxxx>;
+ * ported from 2.0.35 Jumbo-9 by Michael Krause <m.krause@xxxxxxxxxxxxx>).
+ * 1998-12-16 Andrea Arcangeli
+ * Fixed Jumbo-9 code in 2.1.131: do_gettimeofday was missing 1 jiffy
+ * because was not accounting lost_ticks.
+ * 1998-12-24 Copyright (C) 1998 Andrea Arcangeli
+ * Fixed a xtime SMP race (we need the xtime_lock rw spinlock to
+ * serialize accesses to xtime/lost_ticks).
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/param.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/time.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+#include <linux/sysdev.h>
+#include <linux/bcd.h>
+#include <linux/efi.h>
+#include <linux/mca.h>
+#include <linux/sysctl.h>
+#include <linux/percpu.h>
+
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/irq.h>
+#include <asm/msr.h>
+#include <asm/delay.h>
+#include <asm/mpspec.h>
+#include <asm/uaccess.h>
+#include <asm/processor.h>
+#include <asm/timer.h>
+
+#include "mach_time.h"
+
+#include <linux/timex.h>
+#include <linux/config.h>
+
+#include <asm/hpet.h>
+
+#include <asm/arch_hooks.h>
+
+#include "io_ports.h"
+
+extern spinlock_t i8259A_lock;
+int pit_latch_buggy; /* extern */
+
+u64 jiffies_64 = INITIAL_JIFFIES;
+
+EXPORT_SYMBOL(jiffies_64);
+
+#if defined(__x86_64__)
+unsigned long vxtime_hz = PIT_TICK_RATE;
+struct vxtime_data __vxtime __section_vxtime; /* for vsyscalls */
+volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
+unsigned long __wall_jiffies __section_wall_jiffies = INITIAL_JIFFIES;
+struct timespec __xtime __section_xtime;
+struct timezone __sys_tz __section_sys_tz;
+#endif
+
+#if defined(__x86_64__)
+unsigned int cpu_khz; /* Detected as we calibrate the TSC */
+#else
+unsigned long cpu_khz; /* Detected as we calibrate the TSC */
+#endif
+
+extern unsigned long wall_jiffies;
+
+DEFINE_SPINLOCK(rtc_lock);
+
+DEFINE_SPINLOCK(i8253_lock);
+EXPORT_SYMBOL(i8253_lock);
+
+extern struct init_timer_opts timer_tsc_init;
+extern struct timer_opts timer_tsc;
+struct timer_opts *cur_timer = &timer_tsc;
+
+/* These are peridically updated in shared_info, and then copied here. */
+u32 shadow_tsc_stamp;
+u64 shadow_system_time;
+static u32 shadow_time_version;
+static struct timeval shadow_tv;
+
+/*
+ * We use this to ensure that gettimeofday() is monotonically increasing. We
+ * only break this guarantee if the wall clock jumps backwards "a long way".
+ */
+static struct timeval last_seen_tv = {0,0};
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+/* Periodically propagate synchronised time base to the RTC and to Xen. */
+static long last_rtc_update, last_update_to_xen;
+#endif
+
+/* Periodically take synchronised time base from Xen, if we need it. */
+static long last_update_from_xen; /* UTC seconds when last read Xen clock. */
+
+/* Keep track of last time we did processing/updating of jiffies and xtime. */
+static u64 processed_system_time; /* System time (ns) at last processing. */
+static DEFINE_PER_CPU(u64, processed_system_time);
+
+#define NS_PER_TICK (1000000000ULL/HZ)
+
+#define HANDLE_USEC_UNDERFLOW(_tv) do { \
+ while ((_tv).tv_usec < 0) { \
+ (_tv).tv_usec += USEC_PER_SEC; \
+ (_tv).tv_sec--; \
+ } \
+} while (0)
+#define HANDLE_USEC_OVERFLOW(_tv) do { \
+ while ((_tv).tv_usec >= USEC_PER_SEC) { \
+ (_tv).tv_usec -= USEC_PER_SEC; \
+ (_tv).tv_sec++; \
+ } \
+} while (0)
+static inline void __normalize_time(time_t *sec, s64 *nsec)
+{
+ while (*nsec >= NSEC_PER_SEC) {
+ (*nsec) -= NSEC_PER_SEC;
+ (*sec)++;
+ }
+ while (*nsec < 0) {
+ (*nsec) += NSEC_PER_SEC;
+ (*sec)--;
+ }
+}
+
+/* Does this guest OS track Xen time, or set its wall clock independently? */
+static int independent_wallclock = 0;
+static int __init __independent_wallclock(char *str)
+{
+ independent_wallclock = 1;
+ return 1;
+}
+__setup("independent_wallclock", __independent_wallclock);
+#define INDEPENDENT_WALLCLOCK() \
+ (independent_wallclock || (xen_start_info.flags & SIF_INITDOMAIN))
+
+/*
+ * Reads a consistent set of time-base values from Xen, into a shadow data
+ * area. Must be called with the xtime_lock held for writing.
+ */
+static void __get_time_values_from_xen(void)
+{
+ shared_info_t *s = HYPERVISOR_shared_info;
+
+ do {
+ shadow_time_version = s->time_version2;
+ rmb();
+ shadow_tv.tv_sec = s->wc_sec;
+ shadow_tv.tv_usec = s->wc_usec;
+ shadow_tsc_stamp = (u32)s->tsc_timestamp;
+ shadow_system_time = s->system_time;
+ rmb();
+ }
+ while (shadow_time_version != s->time_version1);
+
+ cur_timer->mark_offset();
+}
+
+#define TIME_VALUES_UP_TO_DATE \
+ ({ rmb(); (shadow_time_version == HYPERVISOR_shared_info->time_version2); })
+
+/*
+ * This version of gettimeofday has microsecond resolution
+ * and better than microsecond precision on fast x86 machines with TSC.
+ */
+void do_gettimeofday(struct timeval *tv)
+{
+ unsigned long seq;
+ unsigned long usec, sec;
+ unsigned long max_ntp_tick;
+ unsigned long flags;
+ s64 nsec;
+
+ do {
+ unsigned long lost;
+
+ seq = read_seqbegin(&xtime_lock);
+
+ usec = cur_timer->get_offset();
+ lost = jiffies - wall_jiffies;
+
+ /*
+ * If time_adjust is negative then NTP is slowing the clock
+ * so make sure not to go into next possible interval.
+ * Better to lose some accuracy than have time go backwards..
+ */
+ if (unlikely(time_adjust < 0)) {
+ max_ntp_tick = (USEC_PER_SEC / HZ) - tickadj;
+ usec = min(usec, max_ntp_tick);
+
+ if (lost)
+ usec += lost * max_ntp_tick;
+ }
+ else if (unlikely(lost))
+ usec += lost * (USEC_PER_SEC / HZ);
+
+ sec = xtime.tv_sec;
+ usec += (xtime.tv_nsec / NSEC_PER_USEC);
+
+ nsec = shadow_system_time - processed_system_time;
+ __normalize_time(&sec, &nsec);
+ usec += (long)nsec / NSEC_PER_USEC;
+
+ if (unlikely(!TIME_VALUES_UP_TO_DATE)) {
+ /*
+ * We may have blocked for a long time,
+ * rendering our calculations invalid
+ * (e.g. the time delta may have
+ * overflowed). Detect that and recalculate
+ * with fresh values.
+ */
+ write_seqlock_irqsave(&xtime_lock, flags);
+ __get_time_values_from_xen();
+ write_sequnlock_irqrestore(&xtime_lock, flags);
+ continue;
+ }
+ } while (read_seqretry(&xtime_lock, seq));
+
+ while (usec >= USEC_PER_SEC) {
+ usec -= USEC_PER_SEC;
+ sec++;
+ }
+
+ /* Ensure that time-of-day is monotonically increasing. */
+ if ((sec < last_seen_tv.tv_sec) ||
+ ((sec == last_seen_tv.tv_sec) && (usec < last_seen_tv.tv_usec))) {
+ sec = last_seen_tv.tv_sec;
+ usec = last_seen_tv.tv_usec;
+ } else {
+ last_seen_tv.tv_sec = sec;
+ last_seen_tv.tv_usec = usec;
+ }
+
+ tv->tv_sec = sec;
+ tv->tv_usec = usec;
+}
+
+EXPORT_SYMBOL(do_gettimeofday);
+
+int do_settimeofday(struct timespec *tv)
+{
+ time_t wtm_sec, sec = tv->tv_sec;
+ long wtm_nsec;
+ s64 nsec;
+ struct timespec xentime;
+
+ if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
+ return -EINVAL;
+
+ if (!INDEPENDENT_WALLCLOCK())
+ return 0; /* Silent failure? */
+
+ write_seqlock_irq(&xtime_lock);
+
+ /*
+ * Ensure we don't get blocked for a long time so that our time delta
+ * overflows. If that were to happen then our shadow time values would
+ * be stale, so we can retry with fresh ones.
+ */
+ again:
+ nsec = (s64)tv->tv_nsec -
+ ((s64)cur_timer->get_offset() * (s64)NSEC_PER_USEC);
+ if (unlikely(!TIME_VALUES_UP_TO_DATE)) {
+ __get_time_values_from_xen();
+ goto again;
+ }
+
+ __normalize_time(&sec, &nsec);
+ set_normalized_timespec(&xentime, sec, nsec);
+
+ /*
+ * This is revolting. We need to set "xtime" correctly. However, the
+ * value in this location is the value at the most recent update of
+ * wall time. Discover what correction gettimeofday() would have
+ * made, and then undo it!
+ */
+ nsec -= (jiffies - wall_jiffies) * TICK_NSEC;
+
+ nsec -= (shadow_system_time - processed_system_time);
+
+ __normalize_time(&sec, &nsec);
+ wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
+ wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);
+
+ set_normalized_timespec(&xtime, sec, nsec);
+ set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
+
+ time_adjust = 0; /* stop active adjtime() */
+ time_status |= STA_UNSYNC;
+ time_maxerror = NTP_PHASE_LIMIT;
+ time_esterror = NTP_PHASE_LIMIT;
+
+ /* Reset all our running time counts. They make no sense now. */
+ last_seen_tv.tv_sec = 0;
+ last_update_from_xen = 0;
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ if (xen_start_info.flags & SIF_INITDOMAIN) {
+ dom0_op_t op;
+ last_rtc_update = last_update_to_xen = 0;
+ op.cmd = DOM0_SETTIME;
+ op.u.settime.secs = xentime.tv_sec;
+ op.u.settime.usecs = xentime.tv_nsec / NSEC_PER_USEC;
+ op.u.settime.system_time = shadow_system_time;
+ write_sequnlock_irq(&xtime_lock);
+ HYPERVISOR_dom0_op(&op);
+ } else
+#endif
+ write_sequnlock_irq(&xtime_lock);
+
+ clock_was_set();
+ return 0;
+}
+
+EXPORT_SYMBOL(do_settimeofday);
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+static int set_rtc_mmss(unsigned long nowtime)
+{
+ int retval;
+
+ /* gets recalled with irq locally disabled */
+ spin_lock(&rtc_lock);
+ if (efi_enabled)
+ retval = efi_set_rtc_mmss(nowtime);
+ else
+ retval = mach_set_rtc_mmss(nowtime);
+ spin_unlock(&rtc_lock);
+
+ return retval;
+}
+#endif
+
+/* monotonic_clock(): returns # of nanoseconds passed since time_init()
+ * Note: This function is required to return accurate
+ * time even in the absence of multiple timer ticks.
+ */
+unsigned long long monotonic_clock(void)
+{
+ return cur_timer->monotonic_clock();
+}
+EXPORT_SYMBOL(monotonic_clock);
+
+#if defined(CONFIG_SMP) && defined(CONFIG_FRAME_POINTER)
+unsigned long profile_pc(struct pt_regs *regs)
+{
+ unsigned long pc = instruction_pointer(regs);
+
+ if (in_lock_functions(pc))
+ return *(unsigned long *)(regs->ebp + 4);
+
+ return pc;
+}
+EXPORT_SYMBOL(profile_pc);
+#endif
+
+/*
+ * timer_interrupt() needs to keep up the real-time clock,
+ * as well as call the "do_timer()" routine every clocktick
+ */
+static inline void do_timer_interrupt(int irq, void *dev_id,
+ struct pt_regs *regs)
+{
+ time_t wtm_sec, sec;
+ s64 delta, delta_cpu, nsec;
+ long sec_diff, wtm_nsec;
+ int cpu = smp_processor_id();
+
+ do {
+ __get_time_values_from_xen();
+
+ delta = delta_cpu = (s64)shadow_system_time +
+ ((s64)cur_timer->get_offset() * (s64)NSEC_PER_USEC);
+ delta -= processed_system_time;
+ delta_cpu -= per_cpu(processed_system_time, cpu);
+ }
+ while (!TIME_VALUES_UP_TO_DATE);
+
+ if (unlikely(delta < 0) || unlikely(delta_cpu < 0)) {
+ printk("Timer ISR/%d: Time went backwards: "
+ "delta=%lld cpu_delta=%lld shadow=%lld "
+ "off=%lld processed=%lld cpu_processed=%lld\n",
+ cpu, delta, delta_cpu, shadow_system_time,
+ ((s64)cur_timer->get_offset() * (s64)NSEC_PER_USEC),
+ processed_system_time,
+ per_cpu(processed_system_time, cpu));
+ for (cpu = 0; cpu < num_online_cpus(); cpu++)
+ printk(" %d: %lld\n", cpu,
+ per_cpu(processed_system_time, cpu));
+ return;
+ }
+
+ /* System-wide jiffy work. */
+ while (delta >= NS_PER_TICK) {
+ delta -= NS_PER_TICK;
+ processed_system_time += NS_PER_TICK;
+ do_timer(regs);
+ }
+
+ /* Local CPU jiffy work. */
+ while (delta_cpu >= NS_PER_TICK) {
+ delta_cpu -= NS_PER_TICK;
+ per_cpu(processed_system_time, cpu) += NS_PER_TICK;
+ update_process_times(user_mode(regs));
+ profile_tick(CPU_PROFILING, regs);
+ }
+
+ if (cpu != 0)
+ return;
+
+ /*
+ * Take synchronised time from Xen once a minute if we're not
+ * synchronised ourselves, and we haven't chosen to keep an independent
+ * time base.
+ */
+ if (!INDEPENDENT_WALLCLOCK() &&
+ ((time_status & STA_UNSYNC) != 0) &&
+ (xtime.tv_sec > (last_update_from_xen + 60))) {
+ /* Adjust shadow for jiffies that haven't updated xtime yet. */
+ shadow_tv.tv_usec -=
+ (jiffies - wall_jiffies) * (USEC_PER_SEC / HZ);
+ HANDLE_USEC_UNDERFLOW(shadow_tv);
+
+ /*
+ * Reset our running time counts if they are invalidated by
+ * a warp backwards of more than 500ms.
+ */
+ sec_diff = xtime.tv_sec - shadow_tv.tv_sec;
+ if (unlikely(abs(sec_diff) > 1) ||
+ unlikely(((sec_diff * USEC_PER_SEC) +
+ (xtime.tv_nsec / NSEC_PER_USEC) -
+ shadow_tv.tv_usec) > 500000)) {
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ last_rtc_update = last_update_to_xen = 0;
+#endif
+ last_seen_tv.tv_sec = 0;
+ }
+
+ /* Update our unsynchronised xtime appropriately. */
+ sec = shadow_tv.tv_sec;
+ nsec = shadow_tv.tv_usec * NSEC_PER_USEC;
+
+ __normalize_time(&sec, &nsec);
+ wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
+ wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);
+
+ set_normalized_timespec(&xtime, sec, nsec);
+ set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
+
+ last_update_from_xen = sec;
+ }
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ if (!(xen_start_info.flags & SIF_INITDOMAIN))
+ return;
+
+ /* Send synchronised time to Xen approximately every minute. */
+ if (((time_status & STA_UNSYNC) == 0) &&
+ (xtime.tv_sec > (last_update_to_xen + 60))) {
+ dom0_op_t op;
+ struct timeval tv;
+
+ tv.tv_sec = xtime.tv_sec;
+ tv.tv_usec = xtime.tv_nsec / NSEC_PER_USEC;
+ tv.tv_usec += (jiffies - wall_jiffies) * (USEC_PER_SEC/HZ);
+ HANDLE_USEC_OVERFLOW(tv);
+
+ op.cmd = DOM0_SETTIME;
+ op.u.settime.secs = tv.tv_sec;
+ op.u.settime.usecs = tv.tv_usec;
+ op.u.settime.system_time = shadow_system_time;
+ HYPERVISOR_dom0_op(&op);
+
+ last_update_to_xen = xtime.tv_sec;
+ }
+
+ /*
+ * If we have an externally synchronized Linux clock, then update
+ * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be
+ * called as close as possible to 500 ms before the new second starts.
+ */
+ if ((time_status & STA_UNSYNC) == 0 &&
+ xtime.tv_sec > last_rtc_update + 660 &&
+ (xtime.tv_nsec / 1000)
+ >= USEC_AFTER - ((unsigned) TICK_SIZE) / 2 &&
+ (xtime.tv_nsec / 1000)
+ <= USEC_BEFORE + ((unsigned) TICK_SIZE) / 2) {
+ /* horrible...FIXME */
+ if (efi_enabled) {
+ if (efi_set_rtc_mmss(xtime.tv_sec) == 0)
+ last_rtc_update = xtime.tv_sec;
+ else
+ last_rtc_update = xtime.tv_sec - 600;
+ } else if (set_rtc_mmss(xtime.tv_sec) == 0)
+ last_rtc_update = xtime.tv_sec;
+ else
+ last_rtc_update = xtime.tv_sec - 600; /* do it again in
60 s */
+ }
+#endif
+}
+
+/*
+ * This is the same as the above, except we _also_ save the current
+ * Time Stamp Counter value at the time of the timer interrupt, so that
+ * we later on can estimate the time of day more exactly.
+ */
+irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+{
+ /*
+ * Here we are in the timer irq handler. We just have irqs locally
+ * disabled but we don't know if the timer_bh is running on the other
+ * CPU. We need to avoid to SMP race with it. NOTE: we don' t need
+ * the irq version of write_lock because as just said we have irq
+ * locally disabled. -arca
+ */
+ write_seqlock(&xtime_lock);
+ do_timer_interrupt(irq, NULL, regs);
+ write_sequnlock(&xtime_lock);
+ return IRQ_HANDLED;
+}
+
+/* not static: needed by APM */
+unsigned long get_cmos_time(void)
+{
+ unsigned long retval;
+
+ spin_lock(&rtc_lock);
+
+ if (efi_enabled)
+ retval = efi_get_time();
+ else
+ retval = mach_get_cmos_time();
+
+ spin_unlock(&rtc_lock);
+
+ return retval;
+}
+
+static long clock_cmos_diff, sleep_start;
+
+static int timer_suspend(struct sys_device *dev, u32 state)
+{
+ /*
+ * Estimate time zone so that set_time can update the clock
+ */
+ clock_cmos_diff = -get_cmos_time();
+ clock_cmos_diff += get_seconds();
+ sleep_start = get_cmos_time();
+ return 0;
+}
+
+static int timer_resume(struct sys_device *dev)
+{
+ unsigned long flags;
+ unsigned long sec;
+ unsigned long sleep_length;
+
+#ifdef CONFIG_HPET_TIMER
+ if (is_hpet_enabled())
+ hpet_reenable();
+#endif
+ sec = get_cmos_time() + clock_cmos_diff;
+ sleep_length = (get_cmos_time() - sleep_start) * HZ;
+ write_seqlock_irqsave(&xtime_lock, flags);
+ xtime.tv_sec = sec;
+ xtime.tv_nsec = 0;
+ write_sequnlock_irqrestore(&xtime_lock, flags);
+ jiffies += sleep_length;
+ wall_jiffies += sleep_length;
+ return 0;
+}
+
+static struct sysdev_class timer_sysclass = {
+ .resume = timer_resume,
+ .suspend = timer_suspend,
+ set_kset_name("timer"),
+};
+
+
+/* XXX this driverfs stuff should probably go elsewhere later -john */
+static struct sys_device device_timer = {
+ .id = 0,
+ .cls = &timer_sysclass,
+};
+
+static int time_init_device(void)
+{
+ int error = sysdev_class_register(&timer_sysclass);
+ if (!error)
+ error = sysdev_register(&device_timer);
+ return error;
+}
+
+device_initcall(time_init_device);
+
+#ifdef CONFIG_HPET_TIMER
+extern void (*late_time_init)(void);
+/* Duplicate of time_init() below, with hpet_enable part added */
+void __init hpet_time_init(void)
+{
+ xtime.tv_sec = get_cmos_time();
+ xtime.tv_nsec = (INITIAL_JIFFIES % HZ) * (NSEC_PER_SEC / HZ);
+ set_normalized_timespec(&wall_to_monotonic,
+ -xtime.tv_sec, -xtime.tv_nsec);
+
+ if (hpet_enable() >= 0) {
+ printk("Using HPET for base-timer\n");
+ }
+
+ cur_timer = select_timer();
+ printk(KERN_INFO "Using %s for high-res timesource\n",cur_timer->name);
+
+ time_init_hook();
+}
+#endif
+
+/* Dynamically-mapped IRQ. */
+static DEFINE_PER_CPU(int, timer_irq);
+
+static struct irqaction irq_timer = {
+ timer_interrupt, SA_INTERRUPT, CPU_MASK_NONE, "timer0",
+ NULL, NULL
+};
+
+void __init time_init(void)
+{
+#ifdef CONFIG_HPET_TIMER
+ if (is_hpet_capable()) {
+ /*
+ * HPET initialization needs to do memory-mapped io. So, let
+ * us do a late initialization after mem_init().
+ */
+ late_time_init = hpet_time_init;
+ return;
+ }
+#endif
+ __get_time_values_from_xen();
+ xtime.tv_sec = shadow_tv.tv_sec;
+ xtime.tv_nsec = shadow_tv.tv_usec * NSEC_PER_USEC;
+ set_normalized_timespec(&wall_to_monotonic,
+ -xtime.tv_sec, -xtime.tv_nsec);
+ processed_system_time = shadow_system_time;
+ per_cpu(processed_system_time, 0) = processed_system_time;
+
+ if (timer_tsc_init.init(NULL) != 0)
+ BUG();
+ printk(KERN_INFO "Using %s for high-res timesource\n",cur_timer->name);
+
+#if defined(__x86_64__)
+ vxtime.mode = VXTIME_TSC;
+ vxtime.quot = (1000000L << 32) / vxtime_hz;
+ vxtime.tsc_quot = (1000L << 32) / cpu_khz;
+ vxtime.hz = vxtime_hz;
+ sync_core();
+ rdtscll(vxtime.last_tsc);
+#endif
+
+ per_cpu(timer_irq, 0) = bind_virq_to_irq(VIRQ_TIMER);
+ (void)setup_irq(per_cpu(timer_irq, 0), &irq_timer);
+}
+
+/* Convert jiffies to system time. */
+static inline u64 jiffies_to_st(unsigned long j)
+{
+ unsigned long seq;
+ long delta;
+ u64 st;
+
+ do {
+ seq = read_seqbegin(&xtime_lock);
+ delta = j - jiffies;
+ /* NB. The next check can trigger in some wrap-around cases,
+ * but that's ok: we'll just end up with a shorter timeout. */
+ if (delta < 1)
+ delta = 1;
+ st = processed_system_time + (delta * NS_PER_TICK);
+ } while (read_seqretry(&xtime_lock, seq));
+
+ return st;
+}
+
+/*
+ * stop_hz_timer / start_hz_timer - enter/exit 'tickless mode' on an idle cpu
+ * These functions are based on implementations from arch/s390/kernel/time.c
+ */
+void stop_hz_timer(void)
+{
+ unsigned int cpu = smp_processor_id();
+ unsigned long j;
+
+ /* s390 does this /before/ checking rcu_pending(). We copy them. */
+ cpu_set(cpu, nohz_cpu_mask);
+
+ /* Leave ourselves in 'tick mode' if rcu or softirq pending. */
+ if (rcu_pending(cpu) || local_softirq_pending()) {
+ cpu_clear(cpu, nohz_cpu_mask);
+ j = jiffies + 1;
+ } else {
+ j = next_timer_interrupt();
+ }
+
+ BUG_ON(HYPERVISOR_set_timer_op(jiffies_to_st(j)) != 0);
+}
+
+void start_hz_timer(void)
+{
+ cpu_clear(smp_processor_id(), nohz_cpu_mask);
+}
+
+void time_suspend(void)
+{
+ /* nothing */
+}
+
+/* No locking required. We are only CPU running, and interrupts are off. */
+void time_resume(void)
+{
+ if (timer_tsc_init.init(NULL) != 0)
+ BUG();
+
+ /* Get timebases for new environment. */
+ __get_time_values_from_xen();
+
+ /* Reset our own concept of passage of system time. */
+ processed_system_time = shadow_system_time;
+ per_cpu(processed_system_time, 0) = processed_system_time;
+
+ /* Accept a warp in UTC (wall-clock) time. */
+ last_seen_tv.tv_sec = 0;
+
+ /* Make sure we resync UTC time with Xen on next timer interrupt. */
+ last_update_from_xen = 0;
+}
+
+#ifdef CONFIG_SMP
+static char timer_name[NR_CPUS][15];
+void local_setup_timer(void)
+{
+ int seq, cpu = smp_processor_id();
+
+ do {
+ seq = read_seqbegin(&xtime_lock);
+ per_cpu(processed_system_time, cpu) = shadow_system_time;
+ } while (read_seqretry(&xtime_lock, seq));
+
+ per_cpu(timer_irq, cpu) = bind_virq_to_irq(VIRQ_TIMER);
+ sprintf(timer_name[cpu], "timer%d", cpu);
+ BUG_ON(request_irq(per_cpu(timer_irq, cpu), timer_interrupt,
+ SA_INTERRUPT, timer_name[cpu], NULL));
+}
+#endif
+
+/*
+ * /proc/sys/xen: This really belongs in another file. It can stay here for
+ * now however.
+ */
+static ctl_table xen_subtable[] = {
+ {1, "independent_wallclock", &independent_wallclock,
+ sizeof(independent_wallclock), 0644, NULL, proc_dointvec},
+ {0}
+};
+static ctl_table xen_table[] = {
+ {123, "xen", NULL, 0, 0555, xen_subtable},
+ {0}
+};
+static int __init xen_sysctl_init(void)
+{
+ (void)register_sysctl_table(xen_table, 0);
+ return 0;
+}
+__initcall(xen_sysctl_init);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/xenbus/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/xenbus/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,10 @@
+obj-y += xenbus.o
+
+xenbus-objs =
+xenbus-objs += xenbus_comms.o
+xenbus-objs += xenbus_xs.o
+xenbus-objs += xenbus_probe.o
+
+XEN_TOOLS_DIR := "../tools"
+vpath %.h $(XEN_TOOLS_DIR)
+EXTRA_CFLAGS += -I $(XEN_TOOLS_DIR)
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/balloon.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/balloon.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,51 @@
+/******************************************************************************
+ * balloon.h
+ *
+ * Xen balloon driver - enables returning/claiming memory to/from Xen.
+ *
+ * Copyright (c) 2003, B Dragovic
+ * Copyright (c) 2003-2004, M Williamson, K Fraser
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __ASM_BALLOON_H__
+#define __ASM_BALLOON_H__
+
+/*
+ * Inform the balloon driver that it should allow some slop for device-driver
+ * memory activities.
+ */
+extern void balloon_update_driver_allowance(long delta);
+
+/* Give up unmapped pages to the balloon driver. */
+extern void balloon_put_pages(unsigned long *mfn_list, unsigned long nr_mfns);
+
+/*
+ * Prevent the balloon driver from changing the memory reservation during
+ * a driver critical region.
+ */
+extern spinlock_t balloon_lock;
+#define balloon_lock(__flags) spin_lock_irqsave(&balloon_lock, __flags)
+#define balloon_unlock(__flags) spin_unlock_irqrestore(&balloon_lock, __flags)
+
+#endif /* __ASM_BALLOON_H__ */
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/drivers/char/mem.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/drivers/char/mem.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,812 @@
+/*
+ * linux/drivers/char/mem.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * Added devfs support.
+ * Jan-11-1998, C. Scott Ananian <cananian@xxxxxxxxxxxxxxxxxxxx>
+ * Shared /dev/zero mmaping support, Feb 2000, Kanoj Sarcar <kanoj@xxxxxxx>
+ *
+ * MODIFIED FOR XEN by Keir Fraser, 10th July 2003.
+ * Linux running on Xen has strange semantics for /dev/mem and /dev/kmem!!
+ * 1. mmap will not work on /dev/kmem
+ * 2. mmap on /dev/mem interprets the 'file offset' as a machine address
+ * rather than a physical address.
+ * I don't believe anyone sane mmaps /dev/kmem, but /dev/mem is mmapped
+ * to get at memory-mapped I/O spaces (eg. the VESA X server does this).
+ * For this to work at all we need to expect machine addresses.
+ * Reading/writing of /dev/kmem expects kernel virtual addresses, as usual.
+ * Reading/writing of /dev/mem expects 'physical addresses' as usual -- this
+ * is because /dev/mem can only read/write existing kernel mappings, which
+ * will be normal RAM, and we should present pseudo-physical layout for all
+ * except I/O (which is the sticky case that mmap is hacked to deal with).
+ */
+
+#include <linux/config.h>
+#include <linux/mm.h>
+#include <linux/miscdevice.h>
+#include <linux/tpqic02.h>
+#include <linux/ftape.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/mman.h>
+#include <linux/random.h>
+#include <linux/init.h>
+#include <linux/raw.h>
+#include <linux/tty.h>
+#include <linux/capability.h>
+#include <linux/ptrace.h>
+
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/pgalloc.h>
+
+#ifdef CONFIG_I2C
+extern int i2c_init_all(void);
+#endif
+#ifdef CONFIG_FB
+extern void fbmem_init(void);
+#endif
+#ifdef CONFIG_PROM_CONSOLE
+extern void prom_con_init(void);
+#endif
+#ifdef CONFIG_MDA_CONSOLE
+extern void mda_console_init(void);
+#endif
+#if defined(CONFIG_S390_TAPE) && defined(CONFIG_S390_TAPE_CHAR)
+extern void tapechar_init(void);
+#endif
+
+static ssize_t do_write_mem(struct file * file, void *p, unsigned long realp,
+ const char * buf, size_t count, loff_t *ppos)
+{
+ ssize_t written;
+
+ written = 0;
+#if defined(__sparc__) || defined(__mc68000__)
+ /* we don't have page 0 mapped on sparc and m68k.. */
+ if (realp < PAGE_SIZE) {
+ unsigned long sz = PAGE_SIZE-realp;
+ if (sz > count) sz = count;
+ /* Hmm. Do something? */
+ buf+=sz;
+ p+=sz;
+ count-=sz;
+ written+=sz;
+ }
+#endif
+ if (copy_from_user(p, buf, count))
+ return -EFAULT;
+ written += count;
+ *ppos = realp + written;
+ return written;
+}
+
+
+/*
+ * This funcion reads the *physical* memory. The f_pos points directly to the
+ * memory location.
+ */
+static ssize_t read_mem(struct file * file, char * buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long p = *ppos;
+ unsigned long end_mem;
+ ssize_t read;
+
+ end_mem = __pa(high_memory);
+ if (p >= end_mem)
+ return 0;
+ if (count > end_mem - p)
+ count = end_mem - p;
+ read = 0;
+#if defined(__sparc__) || defined(__mc68000__)
+ /* we don't have page 0 mapped on sparc and m68k.. */
+ if (p < PAGE_SIZE) {
+ unsigned long sz = PAGE_SIZE-p;
+ if (sz > count)
+ sz = count;
+ if (sz > 0) {
+ if (clear_user(buf, sz))
+ return -EFAULT;
+ buf += sz;
+ p += sz;
+ count -= sz;
+ read += sz;
+ }
+ }
+#endif
+ if (copy_to_user(buf, __va(p), count))
+ return -EFAULT;
+ read += count;
+ *ppos = p + read;
+ return read;
+}
+
+static ssize_t write_mem(struct file * file, const char * buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long p = *ppos;
+ unsigned long end_mem;
+
+ end_mem = __pa(high_memory);
+ if (p >= end_mem)
+ return 0;
+ if (count > end_mem - p)
+ count = end_mem - p;
+ return do_write_mem(file, __va(p), p, buf, count, ppos);
+}
+
+#ifndef pgprot_noncached
+
+/*
+ * This should probably be per-architecture in <asm/pgtable.h>
+ */
+static inline pgprot_t pgprot_noncached(pgprot_t _prot)
+{
+ unsigned long prot = pgprot_val(_prot);
+
+#if defined(__i386__) || defined(__x86_64__)
+ /* On PPro and successors, PCD alone doesn't always mean
+ uncached because of interactions with the MTRRs. PCD | PWT
+ means definitely uncached. */
+ if (boot_cpu_data.x86 > 3)
+ prot |= _PAGE_PCD | _PAGE_PWT;
+#elif defined(__powerpc__)
+ prot |= _PAGE_NO_CACHE | _PAGE_GUARDED;
+#elif defined(__mc68000__)
+#ifdef SUN3_PAGE_NOCACHE
+ if (MMU_IS_SUN3)
+ prot |= SUN3_PAGE_NOCACHE;
+ else
+#endif
+ if (MMU_IS_851 || MMU_IS_030)
+ prot |= _PAGE_NOCACHE030;
+ /* Use no-cache mode, serialized */
+ else if (MMU_IS_040 || MMU_IS_060)
+ prot = (prot & _CACHEMASK040) | _PAGE_NOCACHE_S;
+#endif
+
+ return __pgprot(prot);
+}
+
+#endif /* !pgprot_noncached */
+
+/*
+ * Architectures vary in how they handle caching for addresses
+ * outside of main memory.
+ */
+static inline int noncached_address(unsigned long addr)
+{
+#if defined(__i386__)
+ /*
+ * On the PPro and successors, the MTRRs are used to set
+ * memory types for physical addresses outside main memory,
+ * so blindly setting PCD or PWT on those pages is wrong.
+ * For Pentiums and earlier, the surround logic should disable
+ * caching for the high addresses through the KEN pin, but
+ * we maintain the tradition of paranoia in this code.
+ */
+ return !( test_bit(X86_FEATURE_MTRR, &boot_cpu_data.x86_capability) ||
+ test_bit(X86_FEATURE_K6_MTRR, &boot_cpu_data.x86_capability)
||
+ test_bit(X86_FEATURE_CYRIX_ARR,
&boot_cpu_data.x86_capability) ||
+ test_bit(X86_FEATURE_CENTAUR_MCR,
&boot_cpu_data.x86_capability) )
+ && addr >= __pa(high_memory);
+#else
+ return addr >= __pa(high_memory);
+#endif
+}
+
+#if !defined(CONFIG_XEN)
+static int mmap_mem(struct file * file, struct vm_area_struct * vma)
+{
+ unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
+
+ /*
+ * Accessing memory above the top the kernel knows about or
+ * through a file pointer that was marked O_SYNC will be
+ * done non-cached.
+ */
+ if (noncached_address(offset) || (file->f_flags & O_SYNC))
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+ /* Don't try to swap out physical pages.. */
+ vma->vm_flags |= VM_RESERVED;
+
+ /*
+ * Don't dump addresses that are not real memory to a core file.
+ */
+ if (offset >= __pa(high_memory) || (file->f_flags & O_SYNC))
+ vma->vm_flags |= VM_IO;
+
+ if (remap_page_range(vma->vm_start, offset, vma->vm_end-vma->vm_start,
+ vma->vm_page_prot))
+ return -EAGAIN;
+ return 0;
+}
+#elif !defined(CONFIG_XEN_PRIVILEGED_GUEST)
+static int mmap_mem(struct file * file, struct vm_area_struct * vma)
+{
+ return -ENXIO;
+}
+#else
+static int mmap_mem(struct file * file, struct vm_area_struct * vma)
+{
+ unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
+
+ if (!(xen_start_info.flags & SIF_PRIVILEGED))
+ return -ENXIO;
+
+ /* DONTCOPY is essential for Xen as copy_page_range is broken. */
+ vma->vm_flags |= VM_RESERVED | VM_IO | VM_DONTCOPY;
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+ if (direct_remap_area_pages(vma->vm_mm, vma->vm_start, offset,
+ vma->vm_end-vma->vm_start, vma->vm_page_prot,
+ DOMID_IO))
+ return -EAGAIN;
+ return 0;
+}
+#endif /* CONFIG_XEN */
+
+/*
+ * This function reads the *virtual* memory as seen by the kernel.
+ */
+static ssize_t read_kmem(struct file *file, char *buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long p = *ppos;
+ ssize_t read = 0;
+ ssize_t virtr = 0;
+ char * kbuf; /* k-addr because vread() takes vmlist_lock rwlock */
+
+ if (p < (unsigned long) high_memory) {
+ read = count;
+ if (count > (unsigned long) high_memory - p)
+ read = (unsigned long) high_memory - p;
+
+#if defined(__sparc__) || defined(__mc68000__)
+ /* we don't have page 0 mapped on sparc and m68k.. */
+ if (p < PAGE_SIZE && read > 0) {
+ size_t tmp = PAGE_SIZE - p;
+ if (tmp > read) tmp = read;
+ if (clear_user(buf, tmp))
+ return -EFAULT;
+ buf += tmp;
+ p += tmp;
+ read -= tmp;
+ count -= tmp;
+ }
+#endif
+ if (copy_to_user(buf, (char *)p, read))
+ return -EFAULT;
+ p += read;
+ buf += read;
+ count -= read;
+ }
+
+ if (count > 0) {
+ kbuf = (char *)__get_free_page(GFP_KERNEL);
+ if (!kbuf)
+ return -ENOMEM;
+ while (count > 0) {
+ int len = count;
+
+ if (len > PAGE_SIZE)
+ len = PAGE_SIZE;
+ len = vread(kbuf, (char *)p, len);
+ if (!len)
+ break;
+ if (copy_to_user(buf, kbuf, len)) {
+ free_page((unsigned long)kbuf);
+ return -EFAULT;
+ }
+ count -= len;
+ buf += len;
+ virtr += len;
+ p += len;
+ }
+ free_page((unsigned long)kbuf);
+ }
+ *ppos = p;
+ return virtr + read;
+}
+
+extern long vwrite(char *buf, char *addr, unsigned long count);
+
+/*
+ * This function writes to the *virtual* memory as seen by the kernel.
+ */
+static ssize_t write_kmem(struct file * file, const char * buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long p = *ppos;
+ ssize_t wrote = 0;
+ ssize_t virtr = 0;
+ char * kbuf; /* k-addr because vwrite() takes vmlist_lock rwlock */
+
+ if (p < (unsigned long) high_memory) {
+ wrote = count;
+ if (count > (unsigned long) high_memory - p)
+ wrote = (unsigned long) high_memory - p;
+
+ wrote = do_write_mem(file, (void*)p, p, buf, wrote, ppos);
+
+ p += wrote;
+ buf += wrote;
+ count -= wrote;
+ }
+
+ if (count > 0) {
+ kbuf = (char *)__get_free_page(GFP_KERNEL);
+ if (!kbuf)
+ return -ENOMEM;
+ while (count > 0) {
+ int len = count;
+
+ if (len > PAGE_SIZE)
+ len = PAGE_SIZE;
+ if (len && copy_from_user(kbuf, buf, len)) {
+ free_page((unsigned long)kbuf);
+ return -EFAULT;
+ }
+ len = vwrite(kbuf, (char *)p, len);
+ count -= len;
+ buf += len;
+ virtr += len;
+ p += len;
+ }
+ free_page((unsigned long)kbuf);
+ }
+
+ *ppos = p;
+ return virtr + wrote;
+}
+
+#if defined(CONFIG_ISA) || !defined(__mc68000__)
+static ssize_t read_port(struct file * file, char * buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long i = *ppos;
+ char *tmp = buf;
+
+ if (verify_area(VERIFY_WRITE,buf,count))
+ return -EFAULT;
+ while (count-- > 0 && i < 65536) {
+ if (__put_user(inb(i),tmp) < 0)
+ return -EFAULT;
+ i++;
+ tmp++;
+ }
+ *ppos = i;
+ return tmp-buf;
+}
+
+static ssize_t write_port(struct file * file, const char * buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long i = *ppos;
+ const char * tmp = buf;
+
+ if (verify_area(VERIFY_READ,buf,count))
+ return -EFAULT;
+ while (count-- > 0 && i < 65536) {
+ char c;
+ if (__get_user(c, tmp))
+ return -EFAULT;
+ outb(c,i);
+ i++;
+ tmp++;
+ }
+ *ppos = i;
+ return tmp-buf;
+}
+#endif
+
+static ssize_t read_null(struct file * file, char * buf,
+ size_t count, loff_t *ppos)
+{
+ return 0;
+}
+
+static ssize_t write_null(struct file * file, const char * buf,
+ size_t count, loff_t *ppos)
+{
+ return count;
+}
+
+/*
+ * For fun, we are using the MMU for this.
+ */
+static inline size_t read_zero_pagealigned(char * buf, size_t size)
+{
+ struct mm_struct *mm;
+ struct vm_area_struct * vma;
+ unsigned long addr=(unsigned long)buf;
+
+ mm = current->mm;
+ /* Oops, this was forgotten before. -ben */
+ down_read(&mm->mmap_sem);
+
+ /* For private mappings, just map in zero pages. */
+ for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) {
+ unsigned long count;
+
+ if (vma->vm_start > addr || (vma->vm_flags & VM_WRITE) == 0)
+ goto out_up;
+ if (vma->vm_flags & VM_SHARED)
+ break;
+ count = vma->vm_end - addr;
+ if (count > size)
+ count = size;
+
+ zap_page_range(mm, addr, count);
+ zeromap_page_range(addr, count, PAGE_COPY);
+
+ size -= count;
+ buf += count;
+ addr += count;
+ if (size == 0)
+ goto out_up;
+ }
+
+ up_read(&mm->mmap_sem);
+
+ /* The shared case is hard. Let's do the conventional zeroing. */
+ do {
+ unsigned long unwritten = clear_user(buf, PAGE_SIZE);
+ if (unwritten)
+ return size + unwritten - PAGE_SIZE;
+ if (current->need_resched)
+ schedule();
+ buf += PAGE_SIZE;
+ size -= PAGE_SIZE;
+ } while (size);
+
+ return size;
+out_up:
+ up_read(&mm->mmap_sem);
+ return size;
+}
+
+static ssize_t read_zero(struct file * file, char * buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long left, unwritten, written = 0;
+
+ if (!count)
+ return 0;
+
+ if (!access_ok(VERIFY_WRITE, buf, count))
+ return -EFAULT;
+
+ left = count;
+
+ /* do we want to be clever? Arbitrary cut-off */
+ if (count >= PAGE_SIZE*4) {
+ unsigned long partial;
+
+ /* How much left of the page? */
+ partial = (PAGE_SIZE-1) & -(unsigned long) buf;
+ unwritten = clear_user(buf, partial);
+ written = partial - unwritten;
+ if (unwritten)
+ goto out;
+ left -= partial;
+ buf += partial;
+ unwritten = read_zero_pagealigned(buf, left & PAGE_MASK);
+ written += (left & PAGE_MASK) - unwritten;
+ if (unwritten)
+ goto out;
+ buf += left & PAGE_MASK;
+ left &= ~PAGE_MASK;
+ }
+ unwritten = clear_user(buf, left);
+ written += left - unwritten;
+out:
+ return written ? written : -EFAULT;
+}
+
+static int mmap_zero(struct file * file, struct vm_area_struct * vma)
+{
+ if (vma->vm_flags & VM_SHARED)
+ return shmem_zero_setup(vma);
+ if (zeromap_page_range(vma->vm_start, vma->vm_end - vma->vm_start,
vma->vm_page_prot))
+ return -EAGAIN;
+ return 0;
+}
+
+static ssize_t write_full(struct file * file, const char * buf,
+ size_t count, loff_t *ppos)
+{
+ return -ENOSPC;
+}
+
+/*
+ * Special lseek() function for /dev/null and /dev/zero. Most notably, you
+ * can fopen() both devices with "a" now. This was previously impossible.
+ * -- SRB.
+ */
+
+static loff_t null_lseek(struct file * file, loff_t offset, int orig)
+{
+ return file->f_pos = 0;
+}
+
+/*
+ * The memory devices use the full 32/64 bits of the offset, and so we cannot
+ * check against negative addresses: they are ok. The return value is weird,
+ * though, in that case (0).
+ *
+ * also note that seeking relative to the "end of file" isn't supported:
+ * it has no meaning, so it returns -EINVAL.
+ */
+static loff_t memory_lseek(struct file * file, loff_t offset, int orig)
+{
+ loff_t ret;
+
+ switch (orig) {
+ case 0:
+ file->f_pos = offset;
+ ret = file->f_pos;
+ force_successful_syscall_return();
+ break;
+ case 1:
+ file->f_pos += offset;
+ ret = file->f_pos;
+ force_successful_syscall_return();
+ break;
+ default:
+ ret = -EINVAL;
+ }
+ return ret;
+}
+
+static int open_port(struct inode * inode, struct file * filp)
+{
+ return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
+}
+
+struct page *kmem_vm_nopage(struct vm_area_struct *vma, unsigned long address,
int write)
+{
+ unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
+ unsigned long kaddr;
+ pgd_t *pgd;
+ pmd_t *pmd;
+ pte_t *ptep, pte;
+ struct page *page = NULL;
+
+ /* address is user VA; convert to kernel VA of desired page */
+ kaddr = (address - vma->vm_start) + offset;
+ kaddr = VMALLOC_VMADDR(kaddr);
+
+ spin_lock(&init_mm.page_table_lock);
+
+ /* Lookup page structure for kernel VA */
+ pgd = pgd_offset(&init_mm, kaddr);
+ if (pgd_none(*pgd) || pgd_bad(*pgd))
+ goto out;
+ pmd = pmd_offset(pgd, kaddr);
+ if (pmd_none(*pmd) || pmd_bad(*pmd))
+ goto out;
+ ptep = pte_offset(pmd, kaddr);
+ if (!ptep)
+ goto out;
+ pte = *ptep;
+ if (!pte_present(pte))
+ goto out;
+ if (write && !pte_write(pte))
+ goto out;
+ page = pte_page(pte);
+ if (!VALID_PAGE(page)) {
+ page = NULL;
+ goto out;
+ }
+
+ /* Increment reference count on page */
+ get_page(page);
+
+out:
+ spin_unlock(&init_mm.page_table_lock);
+
+ return page;
+}
+
+struct vm_operations_struct kmem_vm_ops = {
+ nopage: kmem_vm_nopage,
+};
+
+static int mmap_kmem(struct file * file, struct vm_area_struct * vma)
+{
+ unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
+ unsigned long size = vma->vm_end - vma->vm_start;
+
+ /*
+ * If the user is not attempting to mmap a high memory address then
+ * the standard mmap_mem mechanism will work. High memory addresses
+ * need special handling, as remap_page_range expects a physically-
+ * contiguous range of kernel addresses (such as obtained in kmalloc).
+ */
+ if ((offset + size) < (unsigned long) high_memory)
+ return mmap_mem(file, vma);
+
+ /*
+ * Accessing memory above the top the kernel knows about or
+ * through a file pointer that was marked O_SYNC will be
+ * done non-cached.
+ */
+ if (noncached_address(offset) || (file->f_flags & O_SYNC))
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+ /* Don't do anything here; "nopage" will fill the holes */
+ vma->vm_ops = &kmem_vm_ops;
+
+ /* Don't try to swap out physical pages.. */
+ vma->vm_flags |= VM_RESERVED;
+
+ /*
+ * Don't dump addresses that are not real memory to a core file.
+ */
+ vma->vm_flags |= VM_IO;
+
+ return 0;
+}
+
+#define zero_lseek null_lseek
+#define full_lseek null_lseek
+#define write_zero write_null
+#define read_full read_zero
+#define open_mem open_port
+#define open_kmem open_mem
+
+static struct file_operations mem_fops = {
+ llseek: memory_lseek,
+ read: read_mem,
+ write: write_mem,
+ mmap: mmap_mem,
+ open: open_mem,
+};
+
+static struct file_operations kmem_fops = {
+ llseek: memory_lseek,
+ read: read_kmem,
+ write: write_kmem,
+#if !defined(CONFIG_XEN)
+ mmap: mmap_kmem,
+#endif
+ open: open_kmem,
+};
+
+static struct file_operations null_fops = {
+ llseek: null_lseek,
+ read: read_null,
+ write: write_null,
+};
+
+#if defined(CONFIG_ISA) || !defined(__mc68000__)
+static struct file_operations port_fops = {
+ llseek: memory_lseek,
+ read: read_port,
+ write: write_port,
+ open: open_port,
+};
+#endif
+
+static struct file_operations zero_fops = {
+ llseek: zero_lseek,
+ read: read_zero,
+ write: write_zero,
+ mmap: mmap_zero,
+};
+
+static struct file_operations full_fops = {
+ llseek: full_lseek,
+ read: read_full,
+ write: write_full,
+};
+
+static int memory_open(struct inode * inode, struct file * filp)
+{
+ switch (MINOR(inode->i_rdev)) {
+ case 1:
+ filp->f_op = &mem_fops;
+ break;
+ case 2:
+ filp->f_op = &kmem_fops;
+ break;
+ case 3:
+ filp->f_op = &null_fops;
+ break;
+#if defined(CONFIG_ISA) || !defined(__mc68000__)
+ case 4:
+ filp->f_op = &port_fops;
+ break;
+#endif
+ case 5:
+ filp->f_op = &zero_fops;
+ break;
+ case 7:
+ filp->f_op = &full_fops;
+ break;
+ case 8:
+ filp->f_op = &random_fops;
+ break;
+ case 9:
+ filp->f_op = &urandom_fops;
+ break;
+ default:
+ return -ENXIO;
+ }
+ if (filp->f_op && filp->f_op->open)
+ return filp->f_op->open(inode,filp);
+ return 0;
+}
+
+void __init memory_devfs_register (void)
+{
+ /* These are never unregistered */
+ static const struct {
+ unsigned short minor;
+ char *name;
+ umode_t mode;
+ struct file_operations *fops;
+ } list[] = { /* list of minor devices */
+ {1, "mem", S_IRUSR | S_IWUSR | S_IRGRP, &mem_fops},
+ {2, "kmem", S_IRUSR | S_IWUSR | S_IRGRP, &kmem_fops},
+ {3, "null", S_IRUGO | S_IWUGO, &null_fops},
+#if defined(CONFIG_ISA) || !defined(__mc68000__)
+ {4, "port", S_IRUSR | S_IWUSR | S_IRGRP, &port_fops},
+#endif
+ {5, "zero", S_IRUGO | S_IWUGO, &zero_fops},
+ {7, "full", S_IRUGO | S_IWUGO, &full_fops},
+ {8, "random", S_IRUGO | S_IWUSR, &random_fops},
+ {9, "urandom", S_IRUGO | S_IWUSR, &urandom_fops}
+ };
+ int i;
+
+ for (i=0; i<(sizeof(list)/sizeof(*list)); i++)
+ devfs_register (NULL, list[i].name, DEVFS_FL_NONE,
+ MEM_MAJOR, list[i].minor,
+ list[i].mode | S_IFCHR,
+ list[i].fops, NULL);
+}
+
+static struct file_operations memory_fops = {
+ open: memory_open, /* just a selector for the real open */
+};
+
+int __init chr_dev_init(void)
+{
+ if (devfs_register_chrdev(MEM_MAJOR,"mem",&memory_fops))
+ printk("unable to get major %d for memory devs\n", MEM_MAJOR);
+ memory_devfs_register();
+ rand_initialize();
+#ifdef CONFIG_I2C
+ i2c_init_all();
+#endif
+#if defined (CONFIG_FB)
+ fbmem_init();
+#endif
+#if defined (CONFIG_PROM_CONSOLE)
+ prom_con_init();
+#endif
+#if defined (CONFIG_MDA_CONSOLE)
+ mda_console_init();
+#endif
+ tty_init();
+#ifdef CONFIG_M68K_PRINTER
+ lp_m68k_init();
+#endif
+ misc_init();
+#if CONFIG_QIC02_TAPE
+ qic02_tape_init();
+#endif
+#ifdef CONFIG_FTAPE
+ ftape_init();
+#endif
+#if defined(CONFIG_S390_TAPE) && defined(CONFIG_S390_TAPE_CHAR)
+ tapechar_init();
+#endif
+ return 0;
+}
+
+__initcall(chr_dev_init);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/boot/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/boot/Makefile Fri Jul 15 13:39:50 2005
@@ -0,0 +1,8 @@
+
+OBJCOPYFLAGS := -g --strip-unneeded
+
+vmlinuz: vmlinux-stripped FORCE
+ $(call if_changed,gzip)
+
+vmlinux-stripped: vmlinux FORCE
+ $(call if_changed,objcopy)
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/arch/xen/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/Makefile Fri Jul 15 13:39:50 2005
@@ -0,0 +1,139 @@
+#
+# xen/Makefile
+#
+# This file is included by the global makefile so that you can add your own
+# architecture-specific flags and dependencies. Remember to do have actions
+# for "archclean" and "archdep" for cleaning up and making dependencies for
+# this architecture
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License. See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 1994 by Linus Torvalds
+#
+# 19990713 Artur Skawina <skawina@xxxxxxxxxxxxx>
+# Added '-march' and '-mpreferred-stack-boundary' support
+#
+
+# If no .config file exists then use the appropriate defconfig-* file
+ifneq (.config,$(wildcard .config))
+DUMMYX:=$(shell cp $(TOPDIR)/arch/xen/defconfig$(EXTRAVERSION)
$(TOPDIR)/.config)
+-include $(TOPDIR)/.config
+endif
+
+LD=$(CROSS_COMPILE)ld -m elf_i386
+OBJCOPY=$(CROSS_COMPILE)objcopy -R .note -R .comment -S
+LDFLAGS=-e stext
+LINKFLAGS =-T $(TOPDIR)/arch/xen/vmlinux.lds $(LDFLAGS)
+
+CFLAGS += -pipe
+
+check_gcc = $(shell if $(CC) $(1) -S -o /dev/null -xc /dev/null > /dev/null
2>&1; then echo "$(1)"; else echo "$(2)"; fi)
+
+# prevent gcc from keeping the stack 16 byte aligned
+CFLAGS += $(call check_gcc,-mpreferred-stack-boundary=2,)
+
+ifdef CONFIG_M686
+CFLAGS += -march=i686
+endif
+
+ifdef CONFIG_MPENTIUMIII
+CFLAGS += -march=i686
+endif
+
+ifdef CONFIG_MPENTIUM4
+CFLAGS += -march=i686
+endif
+
+ifdef CONFIG_MK7
+CFLAGS += $(call check_gcc,-march=athlon,-march=i686 -malign-functions=4)
+endif
+
+# Disable unit-at-a-time mode, it makes gcc use a lot more stack
+# due to the lack of sharing of stacklots.
+CFLAGS += $(call check_gcc,-fno-unit-at-a-time,)
+
+HEAD := arch/xen/kernel/head.o arch/xen/kernel/init_task.o
+
+SUBDIRS += arch/xen/kernel arch/xen/mm arch/xen/lib
+SUBDIRS += arch/xen/drivers/console
+SUBDIRS += arch/xen/drivers/evtchn
+SUBDIRS += arch/xen/drivers/blkif
+SUBDIRS += arch/xen/drivers/netif
+SUBDIRS += arch/xen/drivers/usbif
+SUBDIRS += arch/xen/drivers/balloon
+ifdef CONFIG_XEN_PRIVILEGED_GUEST
+SUBDIRS += arch/xen/drivers/dom0
+endif
+
+CORE_FILES += arch/xen/kernel/kernel.o arch/xen/mm/mm.o
+CORE_FILES += arch/xen/drivers/evtchn/drv.o
+CORE_FILES += arch/xen/drivers/console/drv.o
+DRIVERS += arch/xen/drivers/blkif/drv.o
+DRIVERS += arch/xen/drivers/netif/drv.o
+DRIVERS += arch/xen/drivers/usbif/drv.o
+ifdef CONFIG_XEN_PRIVILEGED_GUEST
+CORE_FILES += arch/xen/drivers/dom0/drv.o
+endif
+CORE_FILES += arch/xen/drivers/balloon/drv.o
+LIBS := $(TOPDIR)/arch/xen/lib/lib.a $(LIBS) $(TOPDIR)/arch/xen/lib/lib.a
+
+arch/xen/kernel: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xen/kernel
+
+arch/xen/mm: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xen/mm
+
+arch/xen/drivers/console: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xen/drivers/console
+
+arch/xen/drivers/network: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xen/drivers/network
+
+arch/xen/drivers/block: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xen/drivers/block
+
+arch/xen/drivers/dom0: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xen/drivers/dom0
+
+arch/xen/drivers/balloon: dummy
+ $(MAKE) linuxsubdirs SUBDIRS=arch/xen/drivers/balloon
+
+MAKEBOOT = $(MAKE) -C arch/$(ARCH)/boot
+
+vmlinux: arch/xen/vmlinux.lds
+
+FORCE: ;
+
+.PHONY: bzImage compressed clean archclean archmrproper archdep
+
+
+bzImage: vmlinux
+ @$(MAKEBOOT) bzImage
+
+INSTALL_NAME ?= $(KERNELRELEASE)
+install: bzImage
+ mkdir -p $(INSTALL_PATH)/boot
+ ln -f -s vmlinuz-$(INSTALL_NAME)$(INSTALL_SUFFIX)
$(INSTALL_PATH)/boot/vmlinuz-$(VERSION).$(PATCHLEVEL).$(SUBLEVEL)$(XENGUEST)$(INSTALL_SUFFIX)
+ rm -f $(INSTALL_PATH)/boot/vmlinuz-$(INSTALL_NAME)$(INSTALL_SUFFIX)
+ install -m0644 arch/$(ARCH)/boot/bzImage
$(INSTALL_PATH)/boot/vmlinuz-$(INSTALL_NAME)$(INSTALL_SUFFIX)
+ install -m0644 vmlinux
$(INSTALL_PATH)/boot/vmlinux-syms-$(INSTALL_NAME)$(INSTALL_SUFFIX)
+ install -m0664 .config
$(INSTALL_PATH)/boot/config-$(INSTALL_NAME)$(INSTALL_SUFFIX)
+ install -m0664 System.map
$(INSTALL_PATH)/boot/System.map-$(INSTALL_NAME)$(INSTALL_SUFFIX)
+ ln -f -s vmlinuz-$(INSTALL_NAME)$(INSTALL_SUFFIX)
$(INSTALL_PATH)/boot/vmlinuz-$(VERSION).$(PATCHLEVEL)$(XENGUEST)$(INSTALL_SUFFIX)
+
+%_config: arch/xen/defconfig-%
+ rm -f .config arch/xen/defconfig
+ cp -f arch/xen/defconfig-$(@:_config=) arch/xen/defconfig
+ cp -f arch/xen/defconfig-$(@:_config=) .config
+
+
+archclean:
+ @$(MAKEBOOT) clean
+
+archmrproper:
+ rm -f include/asm-xen/xen-public/arch
+
+archdep:
+ @$(MAKEBOOT) dep
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/mm/pageattr.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/mm/pageattr.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,254 @@
+/*
+ * Copyright 2002 Andi Kleen, SuSE Labs.
+ * Thanks to Ben LaHaise for precious feedback.
+ */
+
+#include <linux/config.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/highmem.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <asm/uaccess.h>
+#include <asm/processor.h>
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+#include <asm/io.h>
+
+void pte_free(struct page *pte)
+{
+ pte_t *ptep;
+
+ ptep = pfn_to_kaddr(page_to_pfn(pte));
+
+ xen_pte_unpin(__pa(ptep));
+ make_page_writable(ptep);
+ __free_page(pte);
+}
+
+static inline pte_t *lookup_address(unsigned long address)
+{
+ pgd_t *pgd = pgd_offset_k(address);
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+ if (pgd_none(*pgd))
+ return NULL;
+ pud = pud_offset(pgd, address);
+ if (!pud_present(*pud))
+ return NULL;
+ pmd = pmd_offset(pud, address);
+ if (!pmd_present(*pmd))
+ return NULL;
+ if (pmd_large(*pmd))
+ return (pte_t *)pmd;
+ pte = pte_offset_kernel(pmd, address);
+ if (pte && !pte_present(*pte))
+ pte = NULL;
+ return pte;
+}
+
+static struct page *split_large_page(unsigned long address, pgprot_t prot,
+ pgprot_t ref_prot)
+{
+ int i;
+ unsigned long addr;
+ struct page *base = alloc_pages(GFP_KERNEL, 0);
+ pte_t *pbase;
+ if (!base)
+ return NULL;
+ address = __pa(address);
+ addr = address & LARGE_PAGE_MASK;
+ pbase = (pte_t *)page_address(base);
+ for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE) {
+ pbase[i] = pfn_pte(addr >> PAGE_SHIFT,
+ addr == address ? prot : ref_prot);
+ }
+ return base;
+}
+
+
+static void flush_kernel_map(void *address)
+{
+ if (0 && address && cpu_has_clflush) {
+ /* is this worth it? */
+ int i;
+ for (i = 0; i < PAGE_SIZE; i += boot_cpu_data.x86_clflush_size)
+ asm volatile("clflush (%0)" :: "r" (address + i));
+ } else
+ asm volatile("wbinvd":::"memory");
+ if (address)
+ __flush_tlb_one((unsigned long) address);
+ else
+ __flush_tlb_all();
+}
+
+
+static inline void flush_map(unsigned long address)
+{
+ on_each_cpu(flush_kernel_map, (void *)address, 1, 1);
+}
+
+struct deferred_page {
+ struct deferred_page *next;
+ struct page *fpage;
+ unsigned long address;
+};
+static struct deferred_page *df_list; /* protected by init_mm.mmap_sem */
+
+static inline void save_page(unsigned long address, struct page *fpage)
+{
+ struct deferred_page *df;
+ df = kmalloc(sizeof(struct deferred_page), GFP_KERNEL);
+ if (!df) {
+ flush_map(address);
+ __free_page(fpage);
+ } else {
+ df->next = df_list;
+ df->fpage = fpage;
+ df->address = address;
+ df_list = df;
+ }
+}
+
+/*
+ * No more special protections in this 2/4MB area - revert to a
+ * large page again.
+ */
+static void revert_page(unsigned long address, pgprot_t ref_prot)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t large_pte;
+
+ pgd = pgd_offset_k(address);
+ BUG_ON(pgd_none(*pgd));
+ pud = pud_offset(pgd,address);
+ BUG_ON(pud_none(*pud));
+ pmd = pmd_offset(pud, address);
+ BUG_ON(pmd_val(*pmd) & _PAGE_PSE);
+ pgprot_val(ref_prot) |= _PAGE_PSE;
+ large_pte = mk_pte_phys(__pa(address) & LARGE_PAGE_MASK, ref_prot);
+ set_pte((pte_t *)pmd, large_pte);
+}
+
+static int
+__change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot,
+ pgprot_t ref_prot)
+{
+ pte_t *kpte;
+ struct page *kpte_page;
+ unsigned kpte_flags;
+ kpte = lookup_address(address);
+ if (!kpte) return 0;
+ kpte_page = virt_to_page(((unsigned long)kpte) & PAGE_MASK);
+ kpte_flags = pte_val(*kpte);
+ if (pgprot_val(prot) != pgprot_val(ref_prot)) {
+ if ((kpte_flags & _PAGE_PSE) == 0) {
+ set_pte(kpte, pfn_pte(pfn, prot));
+ } else {
+ /*
+ * split_large_page will take the reference for this
change_page_attr
+ * on the split page.
+ */
+ struct page *split = split_large_page(address, prot,
ref_prot);
+ if (!split)
+ return -ENOMEM;
+ set_pte(kpte,mk_pte(split, ref_prot));
+ kpte_page = split;
+ }
+ get_page(kpte_page);
+ } else if ((kpte_flags & _PAGE_PSE) == 0) {
+ set_pte(kpte, pfn_pte(pfn, ref_prot));
+ __put_page(kpte_page);
+ } else
+ BUG();
+
+ /* on x86-64 the direct mapping set at boot is not using 4k pages */
+// BUG_ON(PageReserved(kpte_page));
+ /*
+ * ..., but the XEN guest kernels (currently) do:
+ * If the pte was reserved, it means it was created at boot
+ * time (not via split_large_page) and in turn we must not
+ * replace it with a large page.
+ */
+ if (!PageReserved(kpte_page)) {
+ switch (page_count(kpte_page)) {
+ case 1:
+ save_page(address, kpte_page);
+ revert_page(address, ref_prot);
+ break;
+ case 0:
+ BUG(); /* memleak and failed 2M page regeneration */
+ }
+ }
+ return 0;
+}
+
+/*
+ * Change the page attributes of an page in the linear mapping.
+ *
+ * This should be used when a page is mapped with a different caching policy
+ * than write-back somewhere - some CPUs do not like it when mappings with
+ * different caching policies exist. This changes the page attributes of the
+ * in kernel linear mapping too.
+ *
+ * The caller needs to ensure that there are no conflicting mappings elsewhere.
+ * This function only deals with the kernel linear map.
+ *
+ * Caller must call global_flush_tlb() after this.
+ */
+int change_page_attr_addr(unsigned long address, int numpages, pgprot_t prot)
+{
+ int err = 0;
+ int i;
+
+ down_write(&init_mm.mmap_sem);
+ for (i = 0; i < numpages; i++, address += PAGE_SIZE) {
+ unsigned long pfn = __pa(address) >> PAGE_SHIFT;
+
+ err = __change_page_attr(address, pfn, prot, PAGE_KERNEL);
+ if (err)
+ break;
+ /* Handle kernel mapping too which aliases part of the
+ * lowmem */
+ if (__pa(address) < KERNEL_TEXT_SIZE) {
+ unsigned long addr2;
+ pgprot_t prot2 = prot;
+ addr2 = __START_KERNEL_map + __pa(address);
+ pgprot_val(prot2) &= ~_PAGE_NX;
+ err = __change_page_attr(addr2, pfn, prot2,
PAGE_KERNEL_EXEC);
+ }
+ }
+ up_write(&init_mm.mmap_sem);
+ return err;
+}
+
+/* Don't call this for MMIO areas that may not have a mem_map entry */
+int change_page_attr(struct page *page, int numpages, pgprot_t prot)
+{
+ unsigned long addr = (unsigned long)page_address(page);
+ return change_page_attr_addr(addr, numpages, prot);
+}
+
+void global_flush_tlb(void)
+{
+ struct deferred_page *df, *next_df;
+
+ down_read(&init_mm.mmap_sem);
+ df = xchg(&df_list, NULL);
+ up_read(&init_mm.mmap_sem);
+ if (!df)
+ return;
+ flush_map((df && !df->next) ? df->address : 0);
+ for (; df; df = next_df) {
+ next_df = df->next;
+ if (df->fpage)
+ __free_page(df->fpage);
+ kfree(df);
+ }
+}
+
+EXPORT_SYMBOL(change_page_attr);
+EXPORT_SYMBOL(global_flush_tlb);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/pgtable-2level.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/pgtable-2level.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,97 @@
+#ifndef _I386_PGTABLE_2LEVEL_H
+#define _I386_PGTABLE_2LEVEL_H
+
+/*
+ * traditional i386 two-level paging structure:
+ */
+
+#define PGDIR_SHIFT 22
+#define PTRS_PER_PGD 1024
+
+/*
+ * the i386 is two-level, so we don't really have any
+ * PMD directory physically.
+ */
+#define PMD_SHIFT 22
+#define PTRS_PER_PMD 1
+
+#define PTRS_PER_PTE 1024
+
+#define pte_ERROR(e) \
+ printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low)
+#define pmd_ERROR(e) \
+ printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
+#define pgd_ERROR(e) \
+ printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+/*
+ * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * setup: the pgd is never bad, and a pmd always exists (as it's folded
+ * into the pgd entry)
+ */
+static inline int pgd_none(pgd_t pgd) { return 0; }
+static inline int pgd_bad(pgd_t pgd) { return 0; }
+static inline int pgd_present(pgd_t pgd) { return 1; }
+#define pgd_clear(xp) do { } while (0)
+
+/*
+ * Certain architectures need to do special things when PTEs
+ * within a page table are directly modified. Thus, the following
+ * hook is made available.
+ */
+#define set_pte(pteptr, pteval) (*(pteptr) = pteval)
+#define set_pte_atomic(pteptr, pteval) (*(pteptr) = pteval)
+
+/*
+ * (pmds are folded into pgds so this doesnt get actually called,
+ * but the define is needed for a generic inline function.)
+ */
+#define set_pmd(pmdptr, pmdval) xen_l2_entry_update((pmdptr), (pmdval))
+#define set_pgd(pgdptr, pgdval) ((void)0)
+
+#define pgd_page(pgd) \
+((unsigned long) __va(pgd_val(pgd) & PAGE_MASK))
+
+static inline pmd_t * pmd_offset(pgd_t * dir, unsigned long address)
+{
+ return (pmd_t *) dir;
+}
+
+#define ptep_get_and_clear(xp) __pte_ma(xchg(&(xp)->pte_low, 0))
+#define pte_same(a, b) ((a).pte_low == (b).pte_low)
+
+/*
+ * We detect special mappings in one of two ways:
+ * 1. If the MFN is an I/O page then Xen will set the m2p entry
+ * to be outside our maximum possible pseudophys range.
+ * 2. If the MFN belongs to a different domain then we will certainly
+ * not have MFN in our p2m table. Conversely, if the page is ours,
+ * then we'll have p2m(m2p(MFN))==MFN.
+ * If we detect a special mapping then it doesn't have a 'struct page'.
+ * We force !VALID_PAGE() by returning an out-of-range pointer.
+ *
+ * NB. These checks require that, for any MFN that is not in our reservation,
+ * there is no PFN such that p2m(PFN) == MFN. Otherwise we can get confused if
+ * we are foreign-mapping the MFN, and the other domain as m2p(MFN) == PFN.
+ * Yikes! Various places must poke in INVALID_P2M_ENTRY for safety.
+ *
+ * NB2. When deliberately mapping foreign pages into the p2m table, you *must*
+ * use FOREIGN_FRAME(). This will cause pte_pfn() to choke on it, as we
+ * require. In all the cases we care about, the high bit gets shifted out
+ * (e.g., phys_to_machine()) so behaviour there is correct.
+ */
+#define INVALID_P2M_ENTRY (~0U)
+#define FOREIGN_FRAME(_m) ((_m) | (1UL<<((sizeof(unsigned long)*8)-1)))
+#define pte_page(_pte) \
+({ \
+ unsigned long mfn = (_pte).pte_low >> PAGE_SHIFT; \
+ unsigned long pfn = mfn_to_pfn(mfn); \
+ if ( (pfn >= max_mapnr) || (pfn_to_mfn(pfn) != mfn) ) \
+ pfn = max_mapnr; /* specia: force !VALID_PAGE() */ \
+ &mem_map[pfn]; \
+})
+
+#define pte_none(x) (!(x).pte_low)
+#define __mk_pte(page_nr,pgprot) __pte(((page_nr) << PAGE_SHIFT) |
pgprot_val(pgprot))
+
+#endif /* _I386_PGTABLE_2LEVEL_H */
diff -r 35b74976f598 -r a83ac0806d6b linux-2.6.11-xen-sparse/mm/memory.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/mm/memory.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,2321 @@
+/*
+ * linux/mm/memory.c
+ *
+ * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
+ */
+
+/*
+ * demand-loading started 01.12.91 - seems it is high on the list of
+ * things wanted, and it should be easy to implement. - Linus
+ */
+
+/*
+ * Ok, demand-loading was easy, shared pages a little bit tricker. Shared
+ * pages started 02.12.91, seems to work. - Linus.
+ *
+ * Tested sharing by executing about 30 /bin/sh: under the old kernel it
+ * would have taken more than the 6M I have free, but it worked well as
+ * far as I could see.
+ *
+ * Also corrected some "invalidate()"s - I wasn't doing enough of them.
+ */
+
+/*
+ * Real VM (paging to/from disk) started 18.12.91. Much more work and
+ * thought has to go into this. Oh, well..
+ * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why.
+ * Found it. Everything seems to work now.
+ * 20.12.91 - Ok, making the swap-device changeable like the root.
+ */
+
+/*
+ * 05.04.94 - Multi-page memory management added for v1.1.
+ * Idea by Alex Bligh (alex@xxxxxxxxxxxxxxx)
+ *
+ * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG
+ * (Gerhard.Wichert@xxxxxxxxxxxxxx)
+ *
+ * Aug/Sep 2004 Changed to four level page tables (Andi Kleen)
+ */
+
+#include <linux/kernel_stat.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/rmap.h>
+#include <linux/acct.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include <asm/pgalloc.h>
+#include <asm/uaccess.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/pgtable.h>
+
+#include <linux/swapops.h>
+#include <linux/elf.h>
+
+#ifndef CONFIG_DISCONTIGMEM
+/* use the per-pgdat data instead for discontigmem - mbligh */
+unsigned long max_mapnr;
+struct page *mem_map;
+
+EXPORT_SYMBOL(max_mapnr);
+EXPORT_SYMBOL(mem_map);
+#endif
+
+unsigned long num_physpages;
+/*
+ * A number of key systems in x86 including ioremap() rely on the assumption
+ * that high_memory defines the upper bound on direct map memory, then end
+ * of ZONE_NORMAL. Under CONFIG_DISCONTIG this means that max_low_pfn and
+ * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL
+ * and ZONE_HIGHMEM.
+ */
+void * high_memory;
+unsigned long vmalloc_earlyreserve;
+
+EXPORT_SYMBOL(num_physpages);
+EXPORT_SYMBOL(high_memory);
+EXPORT_SYMBOL(vmalloc_earlyreserve);
+
+/*
+ * Note: this doesn't free the actual pages themselves. That
+ * has been handled earlier when unmapping all the memory regions.
+ */
+static inline void clear_pmd_range(struct mmu_gather *tlb, pmd_t *pmd,
unsigned long start, unsigned long end)
+{
+ struct page *page;
+
+ if (pmd_none(*pmd))
+ return;
+ if (unlikely(pmd_bad(*pmd))) {
+ pmd_ERROR(*pmd);
+ pmd_clear(pmd);
+ return;
+ }
+ if (!((start | end) & ~PMD_MASK)) {
+ /* Only clear full, aligned ranges */
+ page = pmd_page(*pmd);
+ pmd_clear(pmd);
+ dec_page_state(nr_page_table_pages);
+ tlb->mm->nr_ptes--;
+ pte_free_tlb(tlb, page);
+ }
+}
+
+static inline void clear_pud_range(struct mmu_gather *tlb, pud_t *pud,
unsigned long start, unsigned long end)
+{
+ unsigned long addr = start, next;
+ pmd_t *pmd, *__pmd;
+
+ if (pud_none(*pud))
+ return;
+ if (unlikely(pud_bad(*pud))) {
+ pud_ERROR(*pud);
+ pud_clear(pud);
+ return;
+ }
+
+ pmd = __pmd = pmd_offset(pud, start);
+ do {
+ next = (addr + PMD_SIZE) & PMD_MASK;
+ if (next > end || next <= addr)
+ next = end;
+
+ clear_pmd_range(tlb, pmd, addr, next);
+ pmd++;
+ addr = next;
+ } while (addr && (addr < end));
+
+ if (!((start | end) & ~PUD_MASK)) {
+ /* Only clear full, aligned ranges */
+ pud_clear(pud);
+ pmd_free_tlb(tlb, __pmd);
+ }
+}
+
+
+static inline void clear_pgd_range(struct mmu_gather *tlb, pgd_t *pgd,
unsigned long start, unsigned long end)
+{
+ unsigned long addr = start, next;
+ pud_t *pud, *__pud;
+
+ if (pgd_none(*pgd))
+ return;
+ if (unlikely(pgd_bad(*pgd))) {
+ pgd_ERROR(*pgd);
+ pgd_clear(pgd);
+ return;
+ }
+
+ pud = __pud = pud_offset(pgd, start);
+ do {
+ next = (addr + PUD_SIZE) & PUD_MASK;
+ if (next > end || next <= addr)
+ next = end;
+
+ clear_pud_range(tlb, pud, addr, next);
+ pud++;
+ addr = next;
+ } while (addr && (addr < end));
+
+ if (!((start | end) & ~PGDIR_MASK)) {
+ /* Only clear full, aligned ranges */
+ pgd_clear(pgd);
+ pud_free_tlb(tlb, __pud);
+ }
+}
+
+/*
+ * This function clears user-level page tables of a process.
+ *
+ * Must be called with pagetable lock held.
+ */
+void clear_page_range(struct mmu_gather *tlb, unsigned long start, unsigned
long end)
+{
+ unsigned long addr = start, next;
+ pgd_t * pgd = pgd_offset(tlb->mm, start);
+ unsigned long i;
+
+ for (i = pgd_index(start); i <= pgd_index(end-1); i++) {
+ next = (addr + PGDIR_SIZE) & PGDIR_MASK;
+ if (next > end || next <= addr)
+ next = end;
+
+ clear_pgd_range(tlb, pgd, addr, next);
+ pgd++;
+ addr = next;
+ }
+}
+
+pte_t fastcall * pte_alloc_map(struct mm_struct *mm, pmd_t *pmd, unsigned long
address)
+{
+ if (!pmd_present(*pmd)) {
+ struct page *new;
+
+ spin_unlock(&mm->page_table_lock);
+ new = pte_alloc_one(mm, address);
+ spin_lock(&mm->page_table_lock);
+ if (!new)
+ return NULL;
+ /*
+ * Because we dropped the lock, we should re-check the
+ * entry, as somebody else could have populated it..
+ */
+ if (pmd_present(*pmd)) {
+ pte_free(new);
+ goto out;
+ }
+ mm->nr_ptes++;
+ inc_page_state(nr_page_table_pages);
+ pmd_populate(mm, pmd, new);
+ }
+out:
+ return pte_offset_map(pmd, address);
+}
+
+pte_t fastcall * pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd, unsigned
long address)
+{
+ if (!pmd_present(*pmd)) {
+ pte_t *new;
+
+ spin_unlock(&mm->page_table_lock);
+ new = pte_alloc_one_kernel(mm, address);
+ spin_lock(&mm->page_table_lock);
+ if (!new)
+ return NULL;
+
+ /*
+ * Because we dropped the lock, we should re-check the
+ * entry, as somebody else could have populated it..
+ */
+ if (pmd_present(*pmd)) {
+ pte_free_kernel(new);
+ goto out;
+ }
+ pmd_populate_kernel(mm, pmd, new);
+ }
+out:
+ return pte_offset_kernel(pmd, address);
+}
+
+/*
+ * copy one vm_area from one task to the other. Assumes the page tables
+ * already present in the new task to be cleared in the whole range
+ * covered by this vma.
+ *
+ * dst->page_table_lock is held on entry and exit,
+ * but may be dropped within p[mg]d_alloc() and pte_alloc_map().
+ */
+
+static inline void
+copy_swap_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t pte)
+{
+ if (pte_file(pte))
+ return;
+ swap_duplicate(pte_to_swp_entry(pte));
+ if (list_empty(&dst_mm->mmlist)) {
+ spin_lock(&mmlist_lock);
+ list_add(&dst_mm->mmlist, &src_mm->mmlist);
+ spin_unlock(&mmlist_lock);
+ }
+}
+
+static inline void
+copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ pte_t *dst_pte, pte_t *src_pte, unsigned long vm_flags,
+ unsigned long addr)
+{
+ pte_t pte = *src_pte;
+ struct page *page;
+ unsigned long pfn;
+
+ /* pte contains position in swap, so copy. */
+ if (!pte_present(pte)) {
+ copy_swap_pte(dst_mm, src_mm, pte);
+ set_pte(dst_pte, pte);
+ return;
+ }
+ pfn = pte_pfn(pte);
+ /* the pte points outside of valid memory, the
+ * mapping is assumed to be good, meaningful
+ * and not mapped via rmap - duplicate the
+ * mapping as is.
+ */
+ page = NULL;
+ if (pfn_valid(pfn))
+ page = pfn_to_page(pfn);
+
+ if (!page || PageReserved(page)) {
+ set_pte(dst_pte, pte);
+ return;
+ }
+
+ /*
+ * If it's a COW mapping, write protect it both
+ * in the parent and the child
+ */
+ if ((vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE) {
+ ptep_set_wrprotect(src_pte);
+ pte = *src_pte;
+ }
+
+ /*
+ * If it's a shared mapping, mark it clean in
+ * the child
+ */
+ if (vm_flags & VM_SHARED)
+ pte = pte_mkclean(pte);
+ pte = pte_mkold(pte);
+ get_page(page);
+ dst_mm->rss++;
+ if (PageAnon(page))
+ dst_mm->anon_rss++;
+ set_pte(dst_pte, pte);
+ page_dup_rmap(page);
+}
+
+static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end)
+{
+ pte_t *src_pte, *dst_pte;
+ pte_t *s, *d;
+ unsigned long vm_flags = vma->vm_flags;
+
+ d = dst_pte = pte_alloc_map(dst_mm, dst_pmd, addr);
+ if (!dst_pte)
+ return -ENOMEM;
+
+ spin_lock(&src_mm->page_table_lock);
+ s = src_pte = pte_offset_map_nested(src_pmd, addr);
+ for (; addr < end; addr += PAGE_SIZE, s++, d++) {
+ if (pte_none(*s))
+ continue;
+ copy_one_pte(dst_mm, src_mm, d, s, vm_flags, addr);
+ }
+ pte_unmap_nested(src_pte);
+ pte_unmap(dst_pte);
+ spin_unlock(&src_mm->page_table_lock);
+ cond_resched_lock(&dst_mm->page_table_lock);
+ return 0;
+}
+
+static int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end)
+{
+ pmd_t *src_pmd, *dst_pmd;
+ int err = 0;
+ unsigned long next;
+
+ src_pmd = pmd_offset(src_pud, addr);
+ dst_pmd = pmd_alloc(dst_mm, dst_pud, addr);
+ if (!dst_pmd)
+ return -ENOMEM;
+
+ for (; addr < end; addr = next, src_pmd++, dst_pmd++) {
+ next = (addr + PMD_SIZE) & PMD_MASK;
+ if (next > end || next <= addr)
+ next = end;
+ if (pmd_none(*src_pmd))
+ continue;
+ if (pmd_bad(*src_pmd)) {
+ pmd_ERROR(*src_pmd);
+ pmd_clear(src_pmd);
+ continue;
+ }
+ err = copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
+ vma, addr, next);
+ if (err)
+ break;
+ }
+ return err;
+}
+
+static int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end)
+{
+ pud_t *src_pud, *dst_pud;
+ int err = 0;
+ unsigned long next;
+
+ src_pud = pud_offset(src_pgd, addr);
+ dst_pud = pud_alloc(dst_mm, dst_pgd, addr);
+ if (!dst_pud)
+ return -ENOMEM;
+
+ for (; addr < end; addr = next, src_pud++, dst_pud++) {
+ next = (addr + PUD_SIZE) & PUD_MASK;
+ if (next > end || next <= addr)
+ next = end;
+ if (pud_none(*src_pud))
+ continue;
+ if (pud_bad(*src_pud)) {
+ pud_ERROR(*src_pud);
+ pud_clear(src_pud);
+ continue;
+ }
+ err = copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
+ vma, addr, next);
+ if (err)
+ break;
+ }
+ return err;
+}
+
+int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
+ struct vm_area_struct *vma)
+{
+ pgd_t *src_pgd, *dst_pgd;
+ unsigned long addr, start, end, next;
+ int err = 0;
+
+ if (is_vm_hugetlb_page(vma))
+ return copy_hugetlb_page_range(dst, src, vma);
+
+ start = vma->vm_start;
+ src_pgd = pgd_offset(src, start);
+ dst_pgd = pgd_offset(dst, start);
+
+ end = vma->vm_end;
+ addr = start;
+ while (addr && (addr < end-1)) {
+ next = (addr + PGDIR_SIZE) & PGDIR_MASK;
+ if (next > end || next <= addr)
+ next = end;
+ if (pgd_none(*src_pgd))
+ goto next_pgd;
+ if (pgd_bad(*src_pgd)) {
+ pgd_ERROR(*src_pgd);
+ pgd_clear(src_pgd);
+ goto next_pgd;
+ }
+ err = copy_pud_range(dst, src, dst_pgd, src_pgd,
+ vma, addr, next);
+ if (err)
+ break;
+
+next_pgd:
+ src_pgd++;
+ dst_pgd++;
+ addr = next;
+ }
+
+ return err;
+}
+
+static void zap_pte_range(struct mmu_gather *tlb,
+ pmd_t *pmd, unsigned long address,
+ unsigned long size, struct zap_details *details)
+{
+ unsigned long offset;
+ pte_t *ptep;
+
+ if (pmd_none(*pmd))
+ return;
+ if (unlikely(pmd_bad(*pmd))) {
+ pmd_ERROR(*pmd);
+ pmd_clear(pmd);
+ return;
+ }
+ ptep = pte_offset_map(pmd, address);
+ offset = address & ~PMD_MASK;
+ if (offset + size > PMD_SIZE)
+ size = PMD_SIZE - offset;
+ size &= PAGE_MASK;
+ if (details && !details->check_mapping && !details->nonlinear_vma)
+ details = NULL;
+ for (offset=0; offset < size; ptep++, offset += PAGE_SIZE) {
+ pte_t pte = *ptep;
+ if (pte_none(pte))
+ continue;
+ if (pte_present(pte)) {
+ struct page *page = NULL;
+ unsigned long pfn = pte_pfn(pte);
+ if (pfn_valid(pfn)) {
+ page = pfn_to_page(pfn);
+ if (PageReserved(page))
+ page = NULL;
+ }
+ if (unlikely(details) && page) {
+ /*
+ * unmap_shared_mapping_pages() wants to
+ * invalidate cache without truncating:
+ * unmap shared but keep private pages.
+ */
+ if (details->check_mapping &&
+ details->check_mapping != page->mapping)
+ continue;
+ /*
+ * Each page->index must be checked when
+ * invalidating or truncating nonlinear.
+ */
+ if (details->nonlinear_vma &&
+ (page->index < details->first_index ||
+ page->index > details->last_index))
+ continue;
+ }
+ pte = ptep_get_and_clear(ptep);
+ tlb_remove_tlb_entry(tlb, ptep, address+offset);
+ if (unlikely(!page))
+ continue;
+ if (unlikely(details) && details->nonlinear_vma
+ && linear_page_index(details->nonlinear_vma,
+ address+offset) != page->index)
+ set_pte(ptep, pgoff_to_pte(page->index));
+ if (pte_dirty(pte))
+ set_page_dirty(page);
+ if (PageAnon(page))
+ tlb->mm->anon_rss--;
+ else if (pte_young(pte))
+ mark_page_accessed(page);
+ tlb->freed++;
+ page_remove_rmap(page);
+ tlb_remove_page(tlb, page);
+ continue;
+ }
+ /*
+ * If details->check_mapping, we leave swap entries;
+ * if details->nonlinear_vma, we leave file entries.
+ */
+ if (unlikely(details))
+ continue;
+ if (!pte_file(pte))
+ free_swap_and_cache(pte_to_swp_entry(pte));
+ pte_clear(ptep);
+ }
+ pte_unmap(ptep-1);
+}
+
+static void zap_pmd_range(struct mmu_gather *tlb,
+ pud_t *pud, unsigned long address,
+ unsigned long size, struct zap_details *details)
+{
+ pmd_t * pmd;
+ unsigned long end;
+
+ if (pud_none(*pud))
+ return;
+ if (unlikely(pud_bad(*pud))) {
+ pud_ERROR(*pud);
+ pud_clear(pud);
+ return;
+ }
+ pmd = pmd_offset(pud, address);
+ end = address + size;
+ if (end > ((address + PUD_SIZE) & PUD_MASK))
+ end = ((address + PUD_SIZE) & PUD_MASK);
+ do {
+ zap_pte_range(tlb, pmd, address, end - address, details);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+}
+
+static void zap_pud_range(struct mmu_gather *tlb,
+ pgd_t * pgd, unsigned long address,
+ unsigned long end, struct zap_details *details)
+{
+ pud_t * pud;
+
+ if (pgd_none(*pgd))
+ return;
+ if (unlikely(pgd_bad(*pgd))) {
+ pgd_ERROR(*pgd);
+ pgd_clear(pgd);
+ return;
+ }
+ pud = pud_offset(pgd, address);
+ do {
+ zap_pmd_range(tlb, pud, address, end - address, details);
+ address = (address + PUD_SIZE) & PUD_MASK;
+ pud++;
+ } while (address && (address < end));
+}
+
+static void unmap_page_range(struct mmu_gather *tlb,
+ struct vm_area_struct *vma, unsigned long address,
+ unsigned long end, struct zap_details *details)
+{
+ unsigned long next;
+ pgd_t *pgd;
+ int i;
+
+ BUG_ON(address >= end);
+ pgd = pgd_offset(vma->vm_mm, address);
+ tlb_start_vma(tlb, vma);
+ for (i = pgd_index(address); i <= pgd_index(end-1); i++) {
+ next = (address + PGDIR_SIZE) & PGDIR_MASK;
+ if (next <= address || next > end)
+ next = end;
+ zap_pud_range(tlb, pgd, address, next, details);
+ address = next;
+ pgd++;
+ }
+ tlb_end_vma(tlb, vma);
+}
+
+#ifdef CONFIG_PREEMPT
+# define ZAP_BLOCK_SIZE (8 * PAGE_SIZE)
+#else
+/* No preempt: go for improved straight-line efficiency */
+# define ZAP_BLOCK_SIZE (1024 * PAGE_SIZE)
+#endif
+
+/**
+ * unmap_vmas - unmap a range of memory covered by a list of vma's
+ * @tlbp: address of the caller's struct mmu_gather
+ * @mm: the controlling mm_struct
+ * @vma: the starting vma
+ * @start_addr: virtual address at which to start unmapping
+ * @end_addr: virtual address at which to end unmapping
+ * @nr_accounted: Place number of unmapped pages in vm-accountable vma's here
+ * @details: details of nonlinear truncation or shared cache invalidation
+ *
+ * Returns the number of vma's which were covered by the unmapping.
+ *
+ * Unmap all pages in the vma list. Called under page_table_lock.
+ *
+ * We aim to not hold page_table_lock for too long (for scheduling latency
+ * reasons). So zap pages in ZAP_BLOCK_SIZE bytecounts. This means we need to
+ * return the ending mmu_gather to the caller.
+ *
+ * Only addresses between `start' and `end' will be unmapped.
+ *
+ * The VMA list must be sorted in ascending virtual address order.
+ *
+ * unmap_vmas() assumes that the caller will flush the whole unmapped address
+ * range after unmap_vmas() returns. So the only responsibility here is to
+ * ensure that any thus-far unmapped pages are flushed before unmap_vmas()
+ * drops the lock and schedules.
+ */
+int unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm,
+ struct vm_area_struct *vma, unsigned long start_addr,
+ unsigned long end_addr, unsigned long *nr_accounted,
+ struct zap_details *details)
+{
+ unsigned long zap_bytes = ZAP_BLOCK_SIZE;
+ unsigned long tlb_start = 0; /* For tlb_finish_mmu */
+ int tlb_start_valid = 0;
+ int ret = 0;
+ spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
+ int fullmm = tlb_is_full_mm(*tlbp);
+
+ for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) {
+ unsigned long start;
+ unsigned long end;
+
+ start = max(vma->vm_start, start_addr);
+ if (start >= vma->vm_end)
+ continue;
+ end = min(vma->vm_end, end_addr);
+ if (end <= vma->vm_start)
+ continue;
+
+ if (vma->vm_flags & VM_ACCOUNT)
+ *nr_accounted += (end - start) >> PAGE_SHIFT;
+
+ ret++;
+ while (start != end) {
+ unsigned long block;
+
+ if (!tlb_start_valid) {
+ tlb_start = start;
+ tlb_start_valid = 1;
+ }
+
+ if (is_vm_hugetlb_page(vma)) {
+ block = end - start;
+ unmap_hugepage_range(vma, start, end);
+ } else {
+ block = min(zap_bytes, end - start);
+ unmap_page_range(*tlbp, vma, start,
+ start + block, details);
+ }
+
+ start += block;
+ zap_bytes -= block;
+ if ((long)zap_bytes > 0)
+ continue;
+
+ tlb_finish_mmu(*tlbp, tlb_start, start);
+
+ if (need_resched() ||
+ need_lockbreak(&mm->page_table_lock) ||
+ (i_mmap_lock && need_lockbreak(i_mmap_lock))) {
+ if (i_mmap_lock) {
+ /* must reset count of rss freed */
+ *tlbp = tlb_gather_mmu(mm, fullmm);
+ details->break_addr = start;
+ goto out;
+ }
+ spin_unlock(&mm->page_table_lock);
+ cond_resched();
+ spin_lock(&mm->page_table_lock);
+ }
+
+ *tlbp = tlb_gather_mmu(mm, fullmm);
+ tlb_start_valid = 0;
+ zap_bytes = ZAP_BLOCK_SIZE;
+ }
+ }
+out:
+ return ret;
+}
+
+/**
+ * zap_page_range - remove user pages in a given range
+ * @vma: vm_area_struct holding the applicable pages
+ * @address: starting address of pages to zap
+ * @size: number of bytes to zap
+ * @details: details of nonlinear truncation or shared cache invalidation
+ */
+void zap_page_range(struct vm_area_struct *vma, unsigned long address,
+ unsigned long size, struct zap_details *details)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ struct mmu_gather *tlb;
+ unsigned long end = address + size;
+ unsigned long nr_accounted = 0;
+
+ if (is_vm_hugetlb_page(vma)) {
+ zap_hugepage_range(vma, address, size);
+ return;
+ }
+
+ lru_add_drain();
+ spin_lock(&mm->page_table_lock);
+ tlb = tlb_gather_mmu(mm, 0);
+ unmap_vmas(&tlb, mm, vma, address, end, &nr_accounted, details);
+ tlb_finish_mmu(tlb, address, end);
+ acct_update_integrals();
+ spin_unlock(&mm->page_table_lock);
+}
+
+/*
+ * Do a quick page-table lookup for a single page.
+ * mm->page_table_lock must be held.
+ */
+static struct page *
+__follow_page(struct mm_struct *mm, unsigned long address, int read, int write)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *ptep, pte;
+ unsigned long pfn;
+ struct page *page;
+
+ page = follow_huge_addr(mm, address, write);
+ if (! IS_ERR(page))
+ return page;
+
+ pgd = pgd_offset(mm, address);
+ if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
+ goto out;
+
+ pud = pud_offset(pgd, address);
+ if (pud_none(*pud) || unlikely(pud_bad(*pud)))
+ goto out;
+
+ pmd = pmd_offset(pud, address);
+ if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
+ goto out;
+ if (pmd_huge(*pmd))
+ return follow_huge_pmd(mm, address, pmd, write);
+
+ ptep = pte_offset_map(pmd, address);
+ if (!ptep)
+ goto out;
+
+ pte = *ptep;
+ pte_unmap(ptep);
+ if (pte_present(pte)) {
+ if (write && !pte_write(pte))
+ goto out;
+ if (read && !pte_read(pte))
+ goto out;
+ pfn = pte_pfn(pte);
+ if (pfn_valid(pfn)) {
+ page = pfn_to_page(pfn);
+ if (write && !pte_dirty(pte) && !PageDirty(page))
+ set_page_dirty(page);
+ mark_page_accessed(page);
+ return page;
+ }
+ }
+
+out:
+ return NULL;
+}
+
+struct page *
+follow_page(struct mm_struct *mm, unsigned long address, int write)
+{
+ return __follow_page(mm, address, /*read*/0, write);
+}
+
+int
+check_user_page_readable(struct mm_struct *mm, unsigned long address)
+{
+ return __follow_page(mm, address, /*read*/1, /*write*/0) != NULL;
+}
+
+EXPORT_SYMBOL(check_user_page_readable);
+
+/*
+ * Given a physical address, is there a useful struct page pointing to
+ * it? This may become more complex in the future if we start dealing
+ * with IO-aperture pages for direct-IO.
+ */
+
+static inline struct page *get_page_map(struct page *page)
+{
+ if (!pfn_valid(page_to_pfn(page)))
+ return NULL;
+ return page;
+}
+
+
+static inline int
+untouched_anonymous_page(struct mm_struct* mm, struct vm_area_struct *vma,
+ unsigned long address)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ /* Check if the vma is for an anonymous mapping. */
+ if (vma->vm_ops && vma->vm_ops->nopage)
+ return 0;
+
+ /* Check if page directory entry exists. */
+ pgd = pgd_offset(mm, address);
+ if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
+ return 1;
+
+ pud = pud_offset(pgd, address);
+ if (pud_none(*pud) || unlikely(pud_bad(*pud)))
+ return 1;
+
+ /* Check if page middle directory entry exists. */
+ pmd = pmd_offset(pud, address);
+ if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
+ return 1;
+
+ /* There is a pte slot for 'address' in 'mm'. */
+ return 0;
+}
+
+
+int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, int len, int write, int force,
+ struct page **pages, struct vm_area_struct **vmas)
+{
+ int i;
+ unsigned int flags;
+
+ /*
+ * Require read or write permissions.
+ * If 'force' is set, we only require the "MAY" flags.
+ */
+ flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
+ flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
+ i = 0;
+
+ do {
+ struct vm_area_struct * vma;
+
+ vma = find_extend_vma(mm, start);
+ if (!vma && in_gate_area(tsk, start)) {
+ unsigned long pg = start & PAGE_MASK;
+ struct vm_area_struct *gate_vma = get_gate_vma(tsk);
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+ if (write) /* user gate pages are read-only */
+ return i ? : -EFAULT;
+ if (pg > TASK_SIZE)
+ pgd = pgd_offset_k(pg);
+ else
+ pgd = pgd_offset_gate(mm, pg);
+ BUG_ON(pgd_none(*pgd));
+ pud = pud_offset(pgd, pg);
+ BUG_ON(pud_none(*pud));
+ pmd = pmd_offset(pud, pg);
+ BUG_ON(pmd_none(*pmd));
+ pte = pte_offset_map(pmd, pg);
+ BUG_ON(pte_none(*pte));
+ if (pages) {
+ pages[i] = pte_page(*pte);
+ get_page(pages[i]);
+ }
+ pte_unmap(pte);
+ if (vmas)
+ vmas[i] = gate_vma;
+ i++;
+ start += PAGE_SIZE;
+ len--;
+ continue;
+ }
+
+ if (vma && (vma->vm_flags & VM_FOREIGN))
+ {
+ struct page **map = vma->vm_private_data;
+ int offset = (start - vma->vm_start) >> PAGE_SHIFT;
+
+ if (map[offset] != NULL) {
+ if (pages) {
+ pages[i] = map[offset];
+ }
+ if (vmas)
+ vmas[i] = vma;
+ i++;
+ start += PAGE_SIZE;
+ len--;
+ continue;
+ }
+ }
+
+ if (!vma || (vma->vm_flags & VM_IO)
+ || !(flags & vma->vm_flags))
+ return i ? : -EFAULT;
+
+ if (is_vm_hugetlb_page(vma)) {
+ i = follow_hugetlb_page(mm, vma, pages, vmas,
+ &start, &len, i);
+ continue;
+ }
+ spin_lock(&mm->page_table_lock);
+ do {
+ struct page *map;
+ int lookup_write = write;
+
+ cond_resched_lock(&mm->page_table_lock);
+ while (!(map = follow_page(mm, start, lookup_write))) {
+ /*
+ * Shortcut for anonymous pages. We don't want
+ * to force the creation of pages tables for
+ * insanly big anonymously mapped areas that
+ * nobody touched so far. This is important
+ * for doing a core dump for these mappings.
+ */
+ if (!lookup_write &&
+ untouched_anonymous_page(mm,vma,start)) {
+ map = ZERO_PAGE(start);
+ break;
+ }
+ spin_unlock(&mm->page_table_lock);
+ switch (handle_mm_fault(mm,vma,start,write)) {
+ case VM_FAULT_MINOR:
+ tsk->min_flt++;
+ break;
+ case VM_FAULT_MAJOR:
+ tsk->maj_flt++;
+ break;
+ case VM_FAULT_SIGBUS:
+ return i ? i : -EFAULT;
+ case VM_FAULT_OOM:
+ return i ? i : -ENOMEM;
+ default:
+ BUG();
+ }
+ /*
+ * Now that we have performed a write fault
+ * and surely no longer have a shared page we
+ * shouldn't write, we shouldn't ignore an
+ * unwritable page in the page table if
+ * we are forcing write access.
+ */
+ lookup_write = write && !force;
+ spin_lock(&mm->page_table_lock);
+ }
+ if (pages) {
+ pages[i] = get_page_map(map);
+ if (!pages[i]) {
+ spin_unlock(&mm->page_table_lock);
+ while (i--)
+ page_cache_release(pages[i]);
+ i = -EFAULT;
+ goto out;
+ }
+ flush_dcache_page(pages[i]);
+ if (!PageReserved(pages[i]))
+ page_cache_get(pages[i]);
+ }
+ if (vmas)
+ vmas[i] = vma;
+ i++;
+ start += PAGE_SIZE;
+ len--;
+ } while(len && start < vma->vm_end);
+ spin_unlock(&mm->page_table_lock);
+ } while(len);
+out:
+ return i;
+}
+
+EXPORT_SYMBOL(get_user_pages);
+
+static void zeromap_pte_range(pte_t * pte, unsigned long address,
+ unsigned long size, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ do {
+ pte_t zero_pte = pte_wrprotect(mk_pte(ZERO_PAGE(address),
prot));
+ BUG_ON(!pte_none(*pte));
+ set_pte(pte, zero_pte);
+ address += PAGE_SIZE;
+ pte++;
+ } while (address && (address < end));
+}
+
+static inline int zeromap_pmd_range(struct mm_struct *mm, pmd_t * pmd,
+ unsigned long address, unsigned long size, pgprot_t prot)
+{
+ unsigned long base, end;
+
+ base = address & PUD_MASK;
+ address &= ~PUD_MASK;
+ end = address + size;
+ if (end > PUD_SIZE)
+ end = PUD_SIZE;
+ do {
+ pte_t * pte = pte_alloc_map(mm, pmd, base + address);
+ if (!pte)
+ return -ENOMEM;
+ zeromap_pte_range(pte, base + address, end - address, prot);
+ pte_unmap(pte);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+ return 0;
+}
+
+static inline int zeromap_pud_range(struct mm_struct *mm, pud_t * pud,
+ unsigned long address,
+ unsigned long size, pgprot_t prot)
+{
+ unsigned long base, end;
+ int error = 0;
+
+ base = address & PGDIR_MASK;
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ do {
+ pmd_t * pmd = pmd_alloc(mm, pud, base + address);
+ error = -ENOMEM;
+ if (!pmd)
+ break;
+ error = zeromap_pmd_range(mm, pmd, base + address,
+ end - address, prot);
+ if (error)
+ break;
+ address = (address + PUD_SIZE) & PUD_MASK;
+ pud++;
+ } while (address && (address < end));
+ return 0;
+}
+
+int zeromap_page_range(struct vm_area_struct *vma, unsigned long address,
+ unsigned long size, pgprot_t prot)
+{
+ int i;
+ int error = 0;
+ pgd_t * pgd;
+ unsigned long beg = address;
+ unsigned long end = address + size;
+ unsigned long next;
+ struct mm_struct *mm = vma->vm_mm;
+
+ pgd = pgd_offset(mm, address);
+ flush_cache_range(vma, beg, end);
+ BUG_ON(address >= end);
+ BUG_ON(end > vma->vm_end);
+
+ spin_lock(&mm->page_table_lock);
+ for (i = pgd_index(address); i <= pgd_index(end-1); i++) {
+ pud_t *pud = pud_alloc(mm, pgd, address);
+ error = -ENOMEM;
+ if (!pud)
+ break;
+ next = (address + PGDIR_SIZE) & PGDIR_MASK;
+ if (next <= beg || next > end)
+ next = end;
+ error = zeromap_pud_range(mm, pud, address,
+ next - address, prot);
+ if (error)
+ break;
+ address = next;
+ pgd++;
+ }
+ /*
+ * Why flush? zeromap_pte_range has a BUG_ON for !pte_none()
+ */
+ flush_tlb_range(vma, beg, end);
+ spin_unlock(&mm->page_table_lock);
+ return error;
+}
+
+/*
+ * maps a range of physical memory into the requested pages. the old
+ * mappings are removed. any references to nonexistent pages results
+ * in null mappings (currently treated as "copy-on-access")
+ */
+static inline void
+remap_pte_range(pte_t * pte, unsigned long address, unsigned long size,
+ unsigned long pfn, pgprot_t prot)
+{
+ unsigned long end;
+
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ do {
+ BUG_ON(!pte_none(*pte));
+ if (!pfn_valid(pfn) || PageReserved(pfn_to_page(pfn)))
+ set_pte(pte, pfn_pte(pfn, prot));
+ address += PAGE_SIZE;
+ pfn++;
+ pte++;
+ } while (address && (address < end));
+}
+
+static inline int
+remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address,
+ unsigned long size, unsigned long pfn, pgprot_t prot)
+{
+ unsigned long base, end;
+
+ base = address & PUD_MASK;
+ address &= ~PUD_MASK;
+ end = address + size;
+ if (end > PUD_SIZE)
+ end = PUD_SIZE;
+ pfn -= (address >> PAGE_SHIFT);
+ do {
+ pte_t * pte = pte_alloc_map(mm, pmd, base + address);
+ if (!pte)
+ return -ENOMEM;
+ remap_pte_range(pte, base + address, end - address,
+ (address >> PAGE_SHIFT) + pfn, prot);
+ pte_unmap(pte);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+ return 0;
+}
+
+static inline int remap_pud_range(struct mm_struct *mm, pud_t * pud,
+ unsigned long address, unsigned long size,
+ unsigned long pfn, pgprot_t prot)
+{
+ unsigned long base, end;
+ int error;
+
+ base = address & PGDIR_MASK;
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ pfn -= address >> PAGE_SHIFT;
+ do {
+ pmd_t *pmd = pmd_alloc(mm, pud, base+address);
+ error = -ENOMEM;
+ if (!pmd)
+ break;
+ error = remap_pmd_range(mm, pmd, base + address, end - address,
+ (address >> PAGE_SHIFT) + pfn, prot);
+ if (error)
+ break;
+ address = (address + PUD_SIZE) & PUD_MASK;
+ pud++;
+ } while (address && (address < end));
+ return error;
+}
+
+/* Note: this is only safe if the mm semaphore is held when called. */
+int remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
+ unsigned long pfn, unsigned long size, pgprot_t prot)
+{
+ int error = 0;
+ pgd_t *pgd;
+ unsigned long beg = from;
+ unsigned long end = from + size;
+ unsigned long next;
+ struct mm_struct *mm = vma->vm_mm;
+ int i;
+
+ pfn -= from >> PAGE_SHIFT;
+ pgd = pgd_offset(mm, from);
+ flush_cache_range(vma, beg, end);
+ BUG_ON(from >= end);
+
+ /*
+ * Physically remapped pages are special. Tell the
+ * rest of the world about it:
+ * VM_IO tells people not to look at these pages
+ * (accesses can have side effects).
+ * VM_RESERVED tells swapout not to try to touch
+ * this region.
+ */
+ vma->vm_flags |= VM_IO | VM_RESERVED;
+
+ spin_lock(&mm->page_table_lock);
+ for (i = pgd_index(beg); i <= pgd_index(end-1); i++) {
+ pud_t *pud = pud_alloc(mm, pgd, from);
+ error = -ENOMEM;
+ if (!pud)
+ break;
+ next = (from + PGDIR_SIZE) & PGDIR_MASK;
+ if (next > end || next <= from)
+ next = end;
+ error = remap_pud_range(mm, pud, from, end - from,
+ pfn + (from >> PAGE_SHIFT), prot);
+ if (error)
+ break;
+ from = next;
+ pgd++;
+ }
+ /*
+ * Why flush? remap_pte_range has a BUG_ON for !pte_none()
+ */
+ flush_tlb_range(vma, beg, end);
+ spin_unlock(&mm->page_table_lock);
+
+ return error;
+}
+
+EXPORT_SYMBOL(remap_pfn_range);
+
+/*
+ * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when
+ * servicing faults for write access. In the normal case, do always want
+ * pte_mkwrite. But get_user_pages can cause write faults for mappings
+ * that do not have writing enabled, when used by access_process_vm.
+ */
+static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
+{
+ if (likely(vma->vm_flags & VM_WRITE))
+ pte = pte_mkwrite(pte);
+ return pte;
+}
+
+/*
+ * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock
+ */
+static inline void break_cow(struct vm_area_struct * vma, struct page *
new_page, unsigned long address,
+ pte_t *page_table)
+{
+ pte_t entry;
+
+ flush_cache_page(vma, address);
+ entry = maybe_mkwrite(pte_mkdirty(mk_pte(new_page, vma->vm_page_prot)),
+ vma);
+ ptep_establish(vma, address, page_table, entry);
+ update_mmu_cache(vma, address, entry);
+}
+
+/*
+ * This routine handles present pages, when users try to write
+ * to a shared page. It is done by copying the page to a new address
+ * and decrementing the shared-page counter for the old page.
+ *
+ * Goto-purists beware: the only reason for goto's here is that it results
+ * in better assembly code.. The "default" path will see no jumps at all.
+ *
+ * Note that this routine assumes that the protection checks have been
+ * done by the caller (the low-level page fault routine in most cases).
+ * Thus we can safely just mark it writable once we've done any necessary
+ * COW.
+ *
+ * We also mark the page dirty at this point even though the page will
+ * change only once the write actually happens. This avoids a few races,
+ * and potentially makes it more efficient.
+ *
+ * We hold the mm semaphore and the page_table_lock on entry and exit
+ * with the page_table_lock released.
+ */
+static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
+ unsigned long address, pte_t *page_table, pmd_t *pmd, pte_t pte)
+{
+ struct page *old_page, *new_page;
+ unsigned long pfn = pte_pfn(pte);
+ pte_t entry;
+
+ if (unlikely(!pfn_valid(pfn))) {
+ /*
+ * This should really halt the system so it can be debugged or
+ * at least the kernel stops what it's doing before it corrupts
+ * data, but for the moment just pretend this is OOM.
+ */
+ pte_unmap(page_table);
+ printk(KERN_ERR "do_wp_page: bogus page at address %08lx\n",
+ address);
+ spin_unlock(&mm->page_table_lock);
+ return VM_FAULT_OOM;
+ }
+ old_page = pfn_to_page(pfn);
+
+ if (!TestSetPageLocked(old_page)) {
+ int reuse = can_share_swap_page(old_page);
+ unlock_page(old_page);
+ if (reuse) {
+ flush_cache_page(vma, address);
+ entry = maybe_mkwrite(pte_mkyoung(pte_mkdirty(pte)),
+ vma);
+ ptep_set_access_flags(vma, address, page_table, entry,
1);
+ update_mmu_cache(vma, address, entry);
+ pte_unmap(page_table);
+ spin_unlock(&mm->page_table_lock);
+ return VM_FAULT_MINOR;
+ }
+ }
+ pte_unmap(page_table);
+
+ /*
+ * Ok, we need to copy. Oh, well..
+ */
+ if (!PageReserved(old_page))
+ page_cache_get(old_page);
+ spin_unlock(&mm->page_table_lock);
+
+ if (unlikely(anon_vma_prepare(vma)))
+ goto no_new_page;
+ if (old_page == ZERO_PAGE(address)) {
+ new_page = alloc_zeroed_user_highpage(vma, address);
+ if (!new_page)
+ goto no_new_page;
+ } else {
+ new_page = alloc_page_vma(GFP_HIGHUSER, vma, address);
+ if (!new_page)
+ goto no_new_page;
+ copy_user_highpage(new_page, old_page, address);
+ }
+ /*
+ * Re-check the pte - we dropped the lock
+ */
+ spin_lock(&mm->page_table_lock);
+ page_table = pte_offset_map(pmd, address);
+ if (likely(pte_same(*page_table, pte))) {
+ if (PageAnon(old_page))
+ mm->anon_rss--;
+ if (PageReserved(old_page)) {
+ ++mm->rss;
+ acct_update_integrals();
+ update_mem_hiwater();
+ } else
+ page_remove_rmap(old_page);
+ break_cow(vma, new_page, address, page_table);
+ lru_cache_add_active(new_page);
+ page_add_anon_rmap(new_page, vma, address);
+
+ /* Free the old page.. */
+ new_page = old_page;
+ }
+ pte_unmap(page_table);
+ page_cache_release(new_page);
+ page_cache_release(old_page);
+ spin_unlock(&mm->page_table_lock);
+ return VM_FAULT_MINOR;
+
+no_new_page:
+ page_cache_release(old_page);
+ return VM_FAULT_OOM;
+}
+
+/*
+ * Helper functions for unmap_mapping_range().
+ *
+ * __ Notes on dropping i_mmap_lock to reduce latency while unmapping __
+ *
+ * We have to restart searching the prio_tree whenever we drop the lock,
+ * since the iterator is only valid while the lock is held, and anyway
+ * a later vma might be split and reinserted earlier while lock dropped.
+ *
+ * The list of nonlinear vmas could be handled more efficiently, using
+ * a placeholder, but handle it in the same way until a need is shown.
+ * It is important to search the prio_tree before nonlinear list: a vma
+ * may become nonlinear and be shifted from prio_tree to nonlinear list
+ * while the lock is dropped; but never shifted from list to prio_tree.
+ *
+ * In order to make forward progress despite restarting the search,
+ * vm_truncate_count is used to mark a vma as now dealt with, so we can
+ * quickly skip it next time around. Since the prio_tree search only
+ * shows us those vmas affected by unmapping the range in question, we
+ * can't efficiently keep all vmas in step with mapping->truncate_count:
+ * so instead reset them all whenever it wraps back to 0 (then go to 1).
+ * mapping->truncate_count and vma->vm_truncate_count are protected by
+ * i_mmap_lock.
+ *
+ * In order to make forward progress despite repeatedly restarting some
+ * large vma, note the break_addr set by unmap_vmas when it breaks out:
+ * and restart from that address when we reach that vma again. It might
+ * have been split or merged, shrunk or extended, but never shifted: so
+ * restart_addr remains valid so long as it remains in the vma's range.
+ * unmap_mapping_range forces truncate_count to leap over page-aligned
+ * values so we can save vma's restart_addr in its truncate_count field.
+ */
+#define is_restart_addr(truncate_count) (!((truncate_count) & ~PAGE_MASK))
+
+static void reset_vma_truncate_counts(struct address_space *mapping)
+{
+ struct vm_area_struct *vma;
+ struct prio_tree_iter iter;
+
+ vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)
+ vma->vm_truncate_count = 0;
+ list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
+ vma->vm_truncate_count = 0;
+}
+
+static int unmap_mapping_range_vma(struct vm_area_struct *vma,
+ unsigned long start_addr, unsigned long end_addr,
+ struct zap_details *details)
+{
+ unsigned long restart_addr;
+ int need_break;
+
+again:
+ restart_addr = vma->vm_truncate_count;
+ if (is_restart_addr(restart_addr) && start_addr < restart_addr) {
+ start_addr = restart_addr;
+ if (start_addr >= end_addr) {
+ /* Top of vma has been split off since last time */
+ vma->vm_truncate_count = details->truncate_count;
+ return 0;
+ }
+ }
+
+ details->break_addr = end_addr;
+ zap_page_range(vma, start_addr, end_addr - start_addr, details);
+
+ /*
+ * We cannot rely on the break test in unmap_vmas:
+ * on the one hand, we don't want to restart our loop
+ * just because that broke out for the page_table_lock;
+ * on the other hand, it does no test when vma is small.
+ */
+ need_break = need_resched() ||
+ need_lockbreak(details->i_mmap_lock);
+
+ if (details->break_addr >= end_addr) {
+ /* We have now completed this vma: mark it so */
+ vma->vm_truncate_count = details->truncate_count;
+ if (!need_break)
+ return 0;
+ } else {
+ /* Note restart_addr in vma's truncate_count field */
+ vma->vm_truncate_count = details->break_addr;
+ if (!need_break)
+ goto again;
+ }
+
+ spin_unlock(details->i_mmap_lock);
+ cond_resched();
+ spin_lock(details->i_mmap_lock);
+ return -EINTR;
+}
+
+static inline void unmap_mapping_range_tree(struct prio_tree_root *root,
+ struct zap_details *details)
+{
+ struct vm_area_struct *vma;
+ struct prio_tree_iter iter;
+ pgoff_t vba, vea, zba, zea;
+
+restart:
+ vma_prio_tree_foreach(vma, &iter, root,
+ details->first_index, details->last_index) {
+ /* Skip quickly over those we have already dealt with */
+ if (vma->vm_truncate_count == details->truncate_count)
+ continue;
+
+ vba = vma->vm_pgoff;
+ vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1;
+ /* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */
+ zba = details->first_index;
+ if (zba < vba)
+ zba = vba;
+ zea = details->last_index;
+ if (zea > vea)
+ zea = vea;
+
+ if (unmap_mapping_range_vma(vma,
+ ((zba - vba) << PAGE_SHIFT) + vma->vm_start,
+ ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
+ details) < 0)
+ goto restart;
+ }
+}
+
+static inline void unmap_mapping_range_list(struct list_head *head,
+ struct zap_details *details)
+{
+ struct vm_area_struct *vma;
+
+ /*
+ * In nonlinear VMAs there is no correspondence between virtual address
+ * offset and file offset. So we must perform an exhaustive search
+ * across *all* the pages in each nonlinear VMA, not just the pages
+ * whose virtual address lies outside the file truncation point.
+ */
+restart:
+ list_for_each_entry(vma, head, shared.vm_set.list) {
+ /* Skip quickly over those we have already dealt with */
+ if (vma->vm_truncate_count == details->truncate_count)
+ continue;
+ details->nonlinear_vma = vma;
+ if (unmap_mapping_range_vma(vma, vma->vm_start,
+ vma->vm_end, details) < 0)
+ goto restart;
+ }
+}
+
+/**
+ * unmap_mapping_range - unmap the portion of all mmaps
+ * in the specified address_space corresponding to the specified
+ * page range in the underlying file.
+ * @address_space: the address space containing mmaps to be unmapped.
+ * @holebegin: byte in first page to unmap, relative to the start of
+ * the underlying file. This will be rounded down to a PAGE_SIZE
+ * boundary. Note that this is different from vmtruncate(), which
+ * must keep the partial page. In contrast, we must get rid of
+ * partial pages.
+ * @holelen: size of prospective hole in bytes. This will be rounded
+ * up to a PAGE_SIZE boundary. A holelen of zero truncates to the
+ * end of the file.
+ * @even_cows: 1 when truncating a file, unmap even private COWed pages;
+ * but 0 when invalidating pagecache, don't throw away private data.
+ */
+void unmap_mapping_range(struct address_space *mapping,
+ loff_t const holebegin, loff_t const holelen, int even_cows)
+{
+ struct zap_details details;
+ pgoff_t hba = holebegin >> PAGE_SHIFT;
+ pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+ /* Check for overflow. */
+ if (sizeof(holelen) > sizeof(hlen)) {
+ long long holeend =
+ (holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (holeend & ~(long long)ULONG_MAX)
+ hlen = ULONG_MAX - hba + 1;
+ }
+
+ details.check_mapping = even_cows? NULL: mapping;
+ details.nonlinear_vma = NULL;
+ details.first_index = hba;
+ details.last_index = hba + hlen - 1;
+ if (details.last_index < details.first_index)
+ details.last_index = ULONG_MAX;
+ details.i_mmap_lock = &mapping->i_mmap_lock;
+
+ spin_lock(&mapping->i_mmap_lock);
+
+ /* serialize i_size write against truncate_count write */
+ smp_wmb();
+ /* Protect against page faults, and endless unmapping loops */
+ mapping->truncate_count++;
+ /*
+ * For archs where spin_lock has inclusive semantics like ia64
+ * this smp_mb() will prevent to read pagetable contents
+ * before the truncate_count increment is visible to
+ * other cpus.
+ */
+ smp_mb();
+ if (unlikely(is_restart_addr(mapping->truncate_count))) {
+ if (mapping->truncate_count == 0)
+ reset_vma_truncate_counts(mapping);
+ mapping->truncate_count++;
+ }
+ details.truncate_count = mapping->truncate_count;
+
+ if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
+ unmap_mapping_range_tree(&mapping->i_mmap, &details);
+ if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
+ unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
+ spin_unlock(&mapping->i_mmap_lock);
+}
+EXPORT_SYMBOL(unmap_mapping_range);
+
+/*
+ * Handle all mappings that got truncated by a "truncate()"
+ * system call.
+ *
+ * NOTE! We have to be ready to update the memory sharing
+ * between the file and the memory map for a potential last
+ * incomplete page. Ugly, but necessary.
+ */
+int vmtruncate(struct inode * inode, loff_t offset)
+{
+ struct address_space *mapping = inode->i_mapping;
+ unsigned long limit;
+
+ if (inode->i_size < offset)
+ goto do_expand;
+ /*
+ * truncation of in-use swapfiles is disallowed - it would cause
+ * subsequent swapout to scribble on the now-freed blocks.
+ */
+ if (IS_SWAPFILE(inode))
+ goto out_busy;
+ i_size_write(inode, offset);
+ unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
+ truncate_inode_pages(mapping, offset);
+ goto out_truncate;
+
+do_expand:
+ limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
+ if (limit != RLIM_INFINITY && offset > limit)
+ goto out_sig;
+ if (offset > inode->i_sb->s_maxbytes)
+ goto out_big;
+ i_size_write(inode, offset);
+
+out_truncate:
+ if (inode->i_op && inode->i_op->truncate)
+ inode->i_op->truncate(inode);
+ return 0;
+out_sig:
+ send_sig(SIGXFSZ, current, 0);
+out_big:
+ return -EFBIG;
+out_busy:
+ return -ETXTBSY;
+}
+
+EXPORT_SYMBOL(vmtruncate);
+
+/*
+ * Primitive swap readahead code. We simply read an aligned block of
+ * (1 << page_cluster) entries in the swap area. This method is chosen
+ * because it doesn't cost us any seek time. We also make sure to queue
+ * the 'original' request together with the readahead ones...
+ *
+ * This has been extended to use the NUMA policies from the mm triggering
+ * the readahead.
+ *
+ * Caller must hold down_read on the vma->vm_mm if vma is not NULL.
+ */
+void swapin_readahead(swp_entry_t entry, unsigned long addr,struct
vm_area_struct *vma)
+{
+#ifdef CONFIG_NUMA
+ struct vm_area_struct *next_vma = vma ? vma->vm_next : NULL;
+#endif
+ int i, num;
+ struct page *new_page;
+ unsigned long offset;
+
+ /*
+ * Get the number of handles we should do readahead io to.
+ */
+ num = valid_swaphandles(entry, &offset);
+ for (i = 0; i < num; offset++, i++) {
+ /* Ok, do the async read-ahead now */
+ new_page = read_swap_cache_async(swp_entry(swp_type(entry),
+ offset), vma, addr);
+ if (!new_page)
+ break;
+ page_cache_release(new_page);
+#ifdef CONFIG_NUMA
+ /*
+ * Find the next applicable VMA for the NUMA policy.
+ */
+ addr += PAGE_SIZE;
+ if (addr == 0)
+ vma = NULL;
+ if (vma) {
+ if (addr >= vma->vm_end) {
+ vma = next_vma;
+ next_vma = vma ? vma->vm_next : NULL;
+ }
+ if (vma && addr < vma->vm_start)
+ vma = NULL;
+ } else {
+ if (next_vma && addr >= next_vma->vm_start) {
+ vma = next_vma;
+ next_vma = vma->vm_next;
+ }
+ }
+#endif
+ }
+ lru_add_drain(); /* Push any new pages onto the LRU now */
+}
+
+/*
+ * We hold the mm semaphore and the page_table_lock on entry and
+ * should release the pagetable lock on exit..
+ */
+static int do_swap_page(struct mm_struct * mm,
+ struct vm_area_struct * vma, unsigned long address,
+ pte_t *page_table, pmd_t *pmd, pte_t orig_pte, int write_access)
+{
+ struct page *page;
+ swp_entry_t entry = pte_to_swp_entry(orig_pte);
+ pte_t pte;
+ int ret = VM_FAULT_MINOR;
+
+ pte_unmap(page_table);
+ spin_unlock(&mm->page_table_lock);
+ page = lookup_swap_cache(entry);
+ if (!page) {
+ swapin_readahead(entry, address, vma);
+ page = read_swap_cache_async(entry, vma, address);
+ if (!page) {
+ /*
+ * Back out if somebody else faulted in this pte while
+ * we released the page table lock.
+ */
+ spin_lock(&mm->page_table_lock);
+ page_table = pte_offset_map(pmd, address);
+ if (likely(pte_same(*page_table, orig_pte)))
+ ret = VM_FAULT_OOM;
+ else
+ ret = VM_FAULT_MINOR;
+ pte_unmap(page_table);
+ spin_unlock(&mm->page_table_lock);
+ goto out;
+ }
+
+ /* Had to read the page from swap area: Major fault */
+ ret = VM_FAULT_MAJOR;
+ inc_page_state(pgmajfault);
+ grab_swap_token();
+ }
+
+ mark_page_accessed(page);
+ lock_page(page);
+
+ /*
+ * Back out if somebody else faulted in this pte while we
+ * released the page table lock.
+ */
+ spin_lock(&mm->page_table_lock);
+ page_table = pte_offset_map(pmd, address);
+ if (unlikely(!pte_same(*page_table, orig_pte))) {
+ pte_unmap(page_table);
+ spin_unlock(&mm->page_table_lock);
+ unlock_page(page);
+ page_cache_release(page);
+ ret = VM_FAULT_MINOR;
+ goto out;
+ }
+
+ /* The page isn't present yet, go ahead with the fault. */
+
+ swap_free(entry);
+ if (vm_swap_full())
+ remove_exclusive_swap_page(page);
+
+ mm->rss++;
+ acct_update_integrals();
+ update_mem_hiwater();
+
+ pte = mk_pte(page, vma->vm_page_prot);
+ if (write_access && can_share_swap_page(page)) {
+ pte = maybe_mkwrite(pte_mkdirty(pte), vma);
+ write_access = 0;
+ }
+ unlock_page(page);
+
+ flush_icache_page(vma, page);
+ set_pte(page_table, pte);
+ page_add_anon_rmap(page, vma, address);
+
+ if (write_access) {
+ if (do_wp_page(mm, vma, address,
+ page_table, pmd, pte) == VM_FAULT_OOM)
+ ret = VM_FAULT_OOM;
+ goto out;
+ }
+
+ /* No need to invalidate - it was non-present before */
+ update_mmu_cache(vma, address, pte);
+ pte_unmap(page_table);
+ spin_unlock(&mm->page_table_lock);
+out:
+ return ret;
+}
+
+/*
+ * We are called with the MM semaphore and page_table_lock
+ * spinlock held to protect against concurrent faults in
+ * multithreaded programs.
+ */
+static int
+do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
+ pte_t *page_table, pmd_t *pmd, int write_access,
+ unsigned long addr)
+{
+ pte_t entry;
+ struct page * page = ZERO_PAGE(addr);
+
+ /* Read-only mapping of ZERO_PAGE. */
+ entry = pte_wrprotect(mk_pte(ZERO_PAGE(addr), vma->vm_page_prot));
+
+ /* ..except if it's a write access */
+ if (write_access) {
+ /* Allocate our own private page. */
+ pte_unmap(page_table);
+ spin_unlock(&mm->page_table_lock);
+
+ if (unlikely(anon_vma_prepare(vma)))
+ goto no_mem;
+ page = alloc_zeroed_user_highpage(vma, addr);
+ if (!page)
+ goto no_mem;
+
+ spin_lock(&mm->page_table_lock);
+ page_table = pte_offset_map(pmd, addr);
+
+ if (!pte_none(*page_table)) {
+ pte_unmap(page_table);
+ page_cache_release(page);
+ spin_unlock(&mm->page_table_lock);
+ goto out;
+ }
+ mm->rss++;
+ acct_update_integrals();
+ update_mem_hiwater();
+ entry = maybe_mkwrite(pte_mkdirty(mk_pte(page,
+ vma->vm_page_prot)),
+ vma);
+ lru_cache_add_active(page);
+ SetPageReferenced(page);
+ page_add_anon_rmap(page, vma, addr);
+ }
+
+ ptep_establish_new(vma, addr, page_table, entry);
+ pte_unmap(page_table);
+
+ /* No need to invalidate - it was non-present before */
+ update_mmu_cache(vma, addr, entry);
+ spin_unlock(&mm->page_table_lock);
+out:
+ return VM_FAULT_MINOR;
+no_mem:
+ return VM_FAULT_OOM;
+}
+
+/*
+ * do_no_page() tries to create a new page mapping. It aggressively
+ * tries to share with existing pages, but makes a separate copy if
+ * the "write_access" parameter is true in order to avoid the next
+ * page fault.
+ *
+ * As this is called only for pages that do not currently exist, we
+ * do not need to flush old virtual caches or the TLB.
+ *
+ * This is called with the MM semaphore held and the page table
+ * spinlock held. Exit with the spinlock released.
+ */
+static int
+do_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, int write_access, pte_t *page_table, pmd_t *pmd)
+{
+ struct page * new_page;
+ struct address_space *mapping = NULL;
+ pte_t entry;
+ unsigned int sequence = 0;
+ int ret = VM_FAULT_MINOR;
+ int anon = 0;
+
+ if (!vma->vm_ops || !vma->vm_ops->nopage)
+ return do_anonymous_page(mm, vma, page_table,
+ pmd, write_access, address);
+ pte_unmap(page_table);
+ spin_unlock(&mm->page_table_lock);
+
+ if (vma->vm_file) {
+ mapping = vma->vm_file->f_mapping;
+ sequence = mapping->truncate_count;
+ smp_rmb(); /* serializes i_size against truncate_count */
+ }
+retry:
+ cond_resched();
+ new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret);
+ /*
+ * No smp_rmb is needed here as long as there's a full
+ * spin_lock/unlock sequence inside the ->nopage callback
+ * (for the pagecache lookup) that acts as an implicit
+ * smp_mb() and prevents the i_size read to happen
+ * after the next truncate_count read.
+ */
+
+ /* no page was available -- either SIGBUS or OOM */
+ if (new_page == NOPAGE_SIGBUS)
+ return VM_FAULT_SIGBUS;
+ if (new_page == NOPAGE_OOM)
+ return VM_FAULT_OOM;
+
+ /*
+ * Should we do an early C-O-W break?
+ */
+ if (write_access && !(vma->vm_flags & VM_SHARED)) {
+ struct page *page;
+
+ if (unlikely(anon_vma_prepare(vma)))
+ goto oom;
+ page = alloc_page_vma(GFP_HIGHUSER, vma, address);
+ if (!page)
+ goto oom;
+ copy_user_highpage(page, new_page, address);
+ page_cache_release(new_page);
+ new_page = page;
+ anon = 1;
+ }
+
+ spin_lock(&mm->page_table_lock);
+ /*
+ * For a file-backed vma, someone could have truncated or otherwise
+ * invalidated this page. If unmap_mapping_range got called,
+ * retry getting the page.
+ */
+ if (mapping && unlikely(sequence != mapping->truncate_count)) {
+ sequence = mapping->truncate_count;
+ spin_unlock(&mm->page_table_lock);
+ page_cache_release(new_page);
+ goto retry;
+ }
+ page_table = pte_offset_map(pmd, address);
+
+ /*
+ * This silly early PAGE_DIRTY setting removes a race
+ * due to the bad i386 page protection. But it's valid
+ * for other architectures too.
+ *
+ * Note that if write_access is true, we either now have
+ * an exclusive copy of the page, or this is a shared mapping,
+ * so we can make it writable and dirty to avoid having to
+ * handle that later.
+ */
+ /* Only go through if we didn't race with anybody else... */
+ if (pte_none(*page_table)) {
+ if (!PageReserved(new_page))
+ ++mm->rss;
+ acct_update_integrals();
+ update_mem_hiwater();
+
+ flush_icache_page(vma, new_page);
+ entry = mk_pte(new_page, vma->vm_page_prot);
+ if (write_access)
+ entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+ ptep_establish_new(vma, address, page_table, entry);
+ if (anon) {
+ lru_cache_add_active(new_page);
+ page_add_anon_rmap(new_page, vma, address);
+ } else
+ page_add_file_rmap(new_page);
+ pte_unmap(page_table);
+ } else {
+ /* One of our sibling threads was faster, back out. */
+ pte_unmap(page_table);
+ page_cache_release(new_page);
+ spin_unlock(&mm->page_table_lock);
+ goto out;
+ }
+
+ /* no need to invalidate: a not-present page shouldn't be cached */
+ update_mmu_cache(vma, address, entry);
+ spin_unlock(&mm->page_table_lock);
+out:
+ return ret;
+oom:
+ page_cache_release(new_page);
+ ret = VM_FAULT_OOM;
+ goto out;
+}
+
+/*
+ * Fault of a previously existing named mapping. Repopulate the pte
+ * from the encoded file_pte if possible. This enables swappable
+ * nonlinear vmas.
+ */
+static int do_file_page(struct mm_struct * mm, struct vm_area_struct * vma,
+ unsigned long address, int write_access, pte_t *pte, pmd_t *pmd)
+{
+ unsigned long pgoff;
+ int err;
+
+ BUG_ON(!vma->vm_ops || !vma->vm_ops->nopage);
+ /*
+ * Fall back to the linear mapping if the fs does not support
+ * ->populate:
+ */
+ if (!vma->vm_ops || !vma->vm_ops->populate ||
+ (write_access && !(vma->vm_flags & VM_SHARED))) {
+ pte_clear(pte);
+ return do_no_page(mm, vma, address, write_access, pte, pmd);
+ }
+
+ pgoff = pte_to_pgoff(*pte);
+
+ pte_unmap(pte);
+ spin_unlock(&mm->page_table_lock);
+
+ err = vma->vm_ops->populate(vma, address & PAGE_MASK, PAGE_SIZE,
vma->vm_page_prot, pgoff, 0);
+ if (err == -ENOMEM)
+ return VM_FAULT_OOM;
+ if (err)
+ return VM_FAULT_SIGBUS;
+ return VM_FAULT_MAJOR;
+}
+
+/*
+ * These routines also need to handle stuff like marking pages dirty
+ * and/or accessed for architectures that don't do it in hardware (most
+ * RISC architectures). The early dirtying is also good on the i386.
+ *
+ * There is also a hook called "update_mmu_cache()" that architectures
+ * with external mmu caches can use to update those (ie the Sparc or
+ * PowerPC hashed page tables that act as extended TLBs).
+ *
+ * Note the "page_table_lock". It is to protect against kswapd removing
+ * pages from under us. Note that kswapd only ever _removes_ pages, never
+ * adds them. As such, once we have noticed that the page is not present,
+ * we can drop the lock early.
+ *
+ * The adding of pages is protected by the MM semaphore (which we hold),
+ * so we don't need to worry about a page being suddenly been added into
+ * our VM.
+ *
+ * We enter with the pagetable spinlock held, we are supposed to
+ * release it when done.
+ */
+static inline int handle_pte_fault(struct mm_struct *mm,
+ struct vm_area_struct * vma, unsigned long address,
+ int write_access, pte_t *pte, pmd_t *pmd)
+{
+ pte_t entry;
+
+ entry = *pte;
+ if (!pte_present(entry)) {
+ /*
+ * If it truly wasn't present, we know that kswapd
+ * and the PTE updates will not touch it later. So
+ * drop the lock.
+ */
+ if (pte_none(entry))
+ return do_no_page(mm, vma, address, write_access, pte,
pmd);
+ if (pte_file(entry))
+ return do_file_page(mm, vma, address, write_access,
pte, pmd);
+ return do_swap_page(mm, vma, address, pte, pmd, entry,
write_access);
+ }
+
+ if (write_access) {
+ if (!pte_write(entry))
+ return do_wp_page(mm, vma, address, pte, pmd, entry);
+
+ entry = pte_mkdirty(entry);
+ }
+ entry = pte_mkyoung(entry);
+ ptep_set_access_flags(vma, address, pte, entry, write_access);
+ update_mmu_cache(vma, address, entry);
+ pte_unmap(pte);
+ spin_unlock(&mm->page_table_lock);
+ return VM_FAULT_MINOR;
+}
+
+/*
+ * By the time we get here, we already hold the mm semaphore
+ */
+int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
+ unsigned long address, int write_access)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ __set_current_state(TASK_RUNNING);
+
+ inc_page_state(pgfault);
+
+ if (is_vm_hugetlb_page(vma))
+ return VM_FAULT_SIGBUS; /* mapping truncation does this. */
+
+ /*
+ * We need the page table lock to synchronize with kswapd
+ * and the SMP-safe atomic PTE updates.
+ */
+ pgd = pgd_offset(mm, address);
+ spin_lock(&mm->page_table_lock);
+
+ pud = pud_alloc(mm, pgd, address);
+ if (!pud)
+ goto oom;
+
+ pmd = pmd_alloc(mm, pud, address);
+ if (!pmd)
+ goto oom;
+
+ pte = pte_alloc_map(mm, pmd, address);
+ if (!pte)
+ goto oom;
+
+ return handle_pte_fault(mm, vma, address, write_access, pte, pmd);
+
+ oom:
+ spin_unlock(&mm->page_table_lock);
+ return VM_FAULT_OOM;
+}
+
+#ifndef __ARCH_HAS_4LEVEL_HACK
+/*
+ * Allocate page upper directory.
+ *
+ * We've already handled the fast-path in-line, and we own the
+ * page table lock.
+ *
+ * On a two-level or three-level page table, this ends up actually being
+ * entirely optimized away.
+ */
+pud_t fastcall *__pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long
address)
+{
+ pud_t *new;
+
+ spin_unlock(&mm->page_table_lock);
+ new = pud_alloc_one(mm, address);
+ spin_lock(&mm->page_table_lock);
+ if (!new)
+ return NULL;
+
+ /*
+ * Because we dropped the lock, we should re-check the
+ * entry, as somebody else could have populated it..
+ */
+ if (pgd_present(*pgd)) {
+ pud_free(new);
+ goto out;
+ }
+ pgd_populate(mm, pgd, new);
+ out:
+ return pud_offset(pgd, address);
+}
+
+/*
+ * Allocate page middle directory.
+ *
+ * We've already handled the fast-path in-line, and we own the
+ * page table lock.
+ *
+ * On a two-level page table, this ends up actually being entirely
+ * optimized away.
+ */
+pmd_t fastcall *__pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long
address)
+{
+ pmd_t *new;
+
+ spin_unlock(&mm->page_table_lock);
+ new = pmd_alloc_one(mm, address);
+ spin_lock(&mm->page_table_lock);
+ if (!new)
+ return NULL;
+
+ /*
+ * Because we dropped the lock, we should re-check the
+ * entry, as somebody else could have populated it..
+ */
+ if (pud_present(*pud)) {
+ pmd_free(new);
+ goto out;
+ }
+ pud_populate(mm, pud, new);
+ out:
+ return pmd_offset(pud, address);
+}
+#else
+pmd_t fastcall *__pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long
address)
+{
+ pmd_t *new;
+
+ spin_unlock(&mm->page_table_lock);
+ new = pmd_alloc_one(mm, address);
+ spin_lock(&mm->page_table_lock);
+ if (!new)
+ return NULL;
+
+ /*
+ * Because we dropped the lock, we should re-check the
+ * entry, as somebody else could have populated it..
+ */
+ if (pgd_present(*pud)) {
+ pmd_free(new);
+ goto out;
+ }
+ pgd_populate(mm, pud, new);
+out:
+ return pmd_offset(pud, address);
+}
+#endif
+
+int make_pages_present(unsigned long addr, unsigned long end)
+{
+ int ret, len, write;
+ struct vm_area_struct * vma;
+
+ vma = find_vma(current->mm, addr);
+ if (!vma)
+ return -1;
+ write = (vma->vm_flags & VM_WRITE) != 0;
+ if (addr >= end)
+ BUG();
+ if (end > vma->vm_end)
+ BUG();
+ len = (end+PAGE_SIZE-1)/PAGE_SIZE-addr/PAGE_SIZE;
+ ret = get_user_pages(current, current->mm, addr,
+ len, write, 0, NULL, NULL);
+ if (ret < 0)
+ return ret;
+ return ret == len ? 0 : -1;
+}
+
+/*
+ * Map a vmalloc()-space virtual address to the physical page.
+ */
+struct page * vmalloc_to_page(void * vmalloc_addr)
+{
+ unsigned long addr = (unsigned long) vmalloc_addr;
+ struct page *page = NULL;
+ pgd_t *pgd = pgd_offset_k(addr);
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *ptep, pte;
+
+ if (!pgd_none(*pgd)) {
+ pud = pud_offset(pgd, addr);
+ if (!pud_none(*pud)) {
+ pmd = pmd_offset(pud, addr);
+ if (!pmd_none(*pmd)) {
+ ptep = pte_offset_map(pmd, addr);
+ pte = *ptep;
+ if (pte_present(pte))
+ page = pte_page(pte);
+ pte_unmap(ptep);
+ }
+ }
+ }
+ return page;
+}
+
+EXPORT_SYMBOL(vmalloc_to_page);
+
+/*
+ * Map a vmalloc()-space virtual address to the physical page frame number.
+ */
+unsigned long vmalloc_to_pfn(void * vmalloc_addr)
+{
+ return page_to_pfn(vmalloc_to_page(vmalloc_addr));
+}
+
+EXPORT_SYMBOL(vmalloc_to_pfn);
+
+/*
+ * update_mem_hiwater
+ * - update per process rss and vm high water data
+ */
+void update_mem_hiwater(void)
+{
+ struct task_struct *tsk = current;
+
+ if (tsk->mm) {
+ if (tsk->mm->hiwater_rss < tsk->mm->rss)
+ tsk->mm->hiwater_rss = tsk->mm->rss;
+ if (tsk->mm->hiwater_vm < tsk->mm->total_vm)
+ tsk->mm->hiwater_vm = tsk->mm->total_vm;
+ }
+}
+
+#if !defined(__HAVE_ARCH_GATE_AREA)
+
+#if defined(AT_SYSINFO_EHDR)
+struct vm_area_struct gate_vma;
+
+static int __init gate_vma_init(void)
+{
+ gate_vma.vm_mm = NULL;
+ gate_vma.vm_start = FIXADDR_USER_START;
+ gate_vma.vm_end = FIXADDR_USER_END;
+ gate_vma.vm_page_prot = PAGE_READONLY;
+ gate_vma.vm_flags = 0;
+ return 0;
+}
+__initcall(gate_vma_init);
+#endif
+
+struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+{
+#ifdef AT_SYSINFO_EHDR
+ return &gate_vma;
+#else
+ return NULL;
+#endif
+}
+
+int in_gate_area_no_task(unsigned long addr)
+{
+#ifdef AT_SYSINFO_EHDR
+ if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END))
+ return 1;
+#endif
+ return 0;
+}
+
+#endif /* __HAVE_ARCH_GATE_AREA */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/bugs.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/bugs.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,53 @@
+/*
+ * include/asm-i386/bugs.h
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Cyrix stuff, June 1998 by:
+ * - Rafael R. Reilova (moved everything from head.S),
+ * <rreilova@xxxxxxxxxxxx>
+ * - Channing Corn (tests & fixes),
+ * - Andrew D. Balsa (code cleanup).
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000
+ */
+
+/*
+ * This is included by init/main.c to check for architecture-dependent bugs.
+ *
+ * Needs:
+ * void check_bugs(void);
+ */
+
+#include <linux/config.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/msr.h>
+
+
+static void __init check_fpu(void)
+{
+ boot_cpu_data.fdiv_bug = 0;
+}
+
+static void __init check_hlt(void)
+{
+ boot_cpu_data.hlt_works_ok = 1;
+}
+
+static void __init check_bugs(void)
+{
+ extern void __init boot_init_fpu(void);
+
+ identify_cpu(&boot_cpu_data);
+ boot_init_fpu();
+#ifndef CONFIG_SMP
+ printk("CPU: ");
+ print_cpu_info(&boot_cpu_data);
+#endif
+ check_fpu();
+ check_hlt();
+ system_utsname.machine[1] = '0' +
+ (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/pgtable-2level-defs.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/pgtable-2level-defs.h
Fri Jul 15 13:39:50 2005
@@ -0,0 +1,19 @@
+#ifndef _I386_PGTABLE_2LEVEL_DEFS_H
+#define _I386_PGTABLE_2LEVEL_DEFS_H
+
+/*
+ * traditional i386 two-level paging structure:
+ */
+
+#define PGDIR_SHIFT 22
+#define PTRS_PER_PGD 1024
+#define PTRS_PER_PGD_NO_HV (HYPERVISOR_VIRT_START >> PGDIR_SHIFT)
+
+/*
+ * the i386 is two-level, so we don't really have any
+ * PMD directory physically.
+ */
+
+#define PTRS_PER_PTE 1024
+
+#endif /* _I386_PGTABLE_2LEVEL_DEFS_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/page.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/page.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,178 @@
+#ifndef _I386_PAGE_H
+#define _I386_PAGE_H
+
+/* PAGE_SHIFT determines the page size */
+#define PAGE_SHIFT 12
+#define PAGE_SIZE (1UL << PAGE_SHIFT)
+#define PAGE_MASK (~(PAGE_SIZE-1))
+
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+
+#include <linux/config.h>
+#include <linux/string.h>
+#include <asm/types.h>
+#include <asm-xen/xen-public/xen.h>
+
+#ifdef CONFIG_XEN_SCRUB_PAGES
+#define scrub_pages(_p,_n) memset((void *)(_p), 0, (_n) << PAGE_SHIFT)
+#else
+#define scrub_pages(_p,_n) ((void)0)
+#endif
+
+#ifdef CONFIG_X86_USE_3DNOW
+
+#include <asm/mmx.h>
+
+#define clear_page(page) mmx_clear_page((void *)(page))
+#define copy_page(to,from) mmx_copy_page(to,from)
+
+#else
+
+/*
+ * On older X86 processors its not a win to use MMX here it seems.
+ * Maybe the K6-III ?
+ */
+
+#define clear_page(page) memset((void *)(page), 0, PAGE_SIZE)
+#define copy_page(to,from) memcpy((void *)(to), (void *)(from), PAGE_SIZE)
+
+#endif
+
+#define clear_user_page(page, vaddr) clear_page(page)
+#define copy_user_page(to, from, vaddr) copy_page(to, from)
+
+/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
+extern unsigned int *phys_to_machine_mapping;
+#define pfn_to_mfn(_pfn) ((unsigned long)(phys_to_machine_mapping[(_pfn)]))
+#define mfn_to_pfn(_mfn) ((unsigned long)(machine_to_phys_mapping[(_mfn)]))
+static inline unsigned long phys_to_machine(unsigned long phys)
+{
+ unsigned long machine = pfn_to_mfn(phys >> PAGE_SHIFT);
+ machine = (machine << PAGE_SHIFT) | (phys & ~PAGE_MASK);
+ return machine;
+}
+static inline unsigned long machine_to_phys(unsigned long machine)
+{
+ unsigned long phys = mfn_to_pfn(machine >> PAGE_SHIFT);
+ phys = (phys << PAGE_SHIFT) | (machine & ~PAGE_MASK);
+ return phys;
+}
+
+/*
+ * These are used to make use of C type-checking..
+ */
+#if CONFIG_X86_PAE
+typedef struct { unsigned long pte_low, pte_high; } pte_t;
+typedef struct { unsigned long long pmd; } pmd_t;
+typedef struct { unsigned long long pgd; } pgd_t;
+#define pte_val(x) ((x).pte_low | ((unsigned long long)(x).pte_high << 32))
+#else
+typedef struct { unsigned long pte_low; } pte_t;
+typedef struct { unsigned long pmd; } pmd_t;
+typedef struct { unsigned long pgd; } pgd_t;
+static inline unsigned long pte_val(pte_t x)
+{
+ unsigned long ret = x.pte_low;
+ if ( (ret & 1) ) ret = machine_to_phys(ret);
+ return ret;
+}
+#define pte_val_ma(x) ((x).pte_low)
+#endif
+#define PTE_MASK PAGE_MASK
+
+typedef struct { unsigned long pgprot; } pgprot_t;
+
+static inline unsigned long pmd_val(pmd_t x)
+{
+ unsigned long ret = x.pmd;
+ if ( ret ) ret = machine_to_phys(ret) | 1;
+ return ret;
+}
+#define pmd_val_ma(x) ((x).pmd)
+#define pgd_val(x) ({ BUG(); (unsigned long)0; })
+#define pgprot_val(x) ((x).pgprot)
+
+#define __pte(x) ({ unsigned long _x = (x); \
+ (((_x)&1) ? ((pte_t) {phys_to_machine(_x)}) : ((pte_t) {(_x)})); })
+#define __pte_ma(x) ((pte_t) { (x) } )
+#define __pmd(x) ({ unsigned long _x = (x); \
+ (((_x)&1) ? ((pmd_t) {phys_to_machine(_x)}) : ((pmd_t) {(_x)})); })
+#define __pgd(x) ({ BUG(); (pgprot_t) { 0 }; })
+#define __pgprot(x) ((pgprot_t) { (x) } )
+
+#endif /* !__ASSEMBLY__ */
+
+/* to align the pointer to the (next) page boundary */
+#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK)
+
+/*
+ * This handles the memory map.. We could make this a config
+ * option, but too many people screw it up, and too few need
+ * it.
+ *
+ * A __PAGE_OFFSET of 0xC0000000 means that the kernel has
+ * a virtual address space of one gigabyte, which limits the
+ * amount of physical memory you can use to about 950MB.
+ *
+ * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
+ * and CONFIG_HIGHMEM64G options in the kernel configuration.
+ */
+
+#define __PAGE_OFFSET (0xC0000000)
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Tell the user there is some problem. Beep too, so we can
+ * see^H^H^Hhear bugs in early bootup as well!
+ * The offending file and line are encoded after the "officially
+ * undefined" opcode for parsing in the trap handler.
+ */
+
+#if 1 /* Set to zero for a slightly smaller kernel */
+#define BUG() \
+ __asm__ __volatile__( "ud2\n" \
+ "\t.word %c0\n" \
+ "\t.long %c1\n" \
+ : : "i" (__LINE__), "i" (__FILE__))
+#else
+#define BUG() __asm__ __volatile__("ud2\n")
+#endif
+
+#define PAGE_BUG(page) do { \
+ BUG(); \
+} while (0)
+
+/* Pure 2^n version of get_order */
+static __inline__ int get_order(unsigned long size)
+{
+ int order;
+
+ size = (size-1) >> (PAGE_SHIFT-1);
+ order = -1;
+ do {
+ size >>= 1;
+ order++;
+ } while (size);
+ return order;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#define PAGE_OFFSET ((unsigned long)__PAGE_OFFSET)
+#define __pa(x) ((unsigned long)(x)-PAGE_OFFSET)
+#define __va(x) ((void *)((unsigned
long)(x)+PAGE_OFFSET))
+#define virt_to_page(kaddr) (mem_map + (__pa(kaddr) >> PAGE_SHIFT))
+#define VALID_PAGE(page) ((page - mem_map) < max_mapnr)
+
+#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \
+ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+/* VIRT <-> MACHINE conversion */
+#define virt_to_machine(_a) (phys_to_machine(__pa(_a)))
+#define machine_to_virt(_m) (__va(machine_to_phys(_m)))
+
+#endif /* __KERNEL__ */
+
+#endif /* _I386_PAGE_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/cpu/mtrr/main.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/cpu/mtrr/main.c Fri Jul
15 13:39:50 2005
@@ -0,0 +1,165 @@
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/ctype.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <asm/uaccess.h>
+
+#include <asm/mtrr.h>
+#include "mtrr.h"
+
+void generic_get_mtrr(unsigned int reg, unsigned long *base,
+ unsigned int *size, mtrr_type * type)
+{
+ dom0_op_t op;
+
+ op.cmd = DOM0_READ_MEMTYPE;
+ op.u.read_memtype.reg = reg;
+ (void)HYPERVISOR_dom0_op(&op);
+
+ *size = op.u.read_memtype.nr_pfns;
+ *base = op.u.read_memtype.pfn;
+ *type = op.u.read_memtype.type;
+}
+
+struct mtrr_ops generic_mtrr_ops = {
+ .use_intel_if = 1,
+ .get = generic_get_mtrr,
+};
+
+struct mtrr_ops *mtrr_if = &generic_mtrr_ops;
+unsigned int num_var_ranges;
+unsigned int *usage_table;
+
+void __init set_num_var_ranges(void)
+{
+ dom0_op_t op;
+
+ for (num_var_ranges = 0; ; num_var_ranges++) {
+ op.cmd = DOM0_READ_MEMTYPE;
+ op.u.read_memtype.reg = num_var_ranges;
+ if (HYPERVISOR_dom0_op(&op) != 0)
+ break;
+ }
+}
+
+static void __init init_table(void)
+{
+ int i, max;
+
+ max = num_var_ranges;
+ if ((usage_table = kmalloc(max * sizeof *usage_table, GFP_KERNEL))
+ == NULL) {
+ printk(KERN_ERR "mtrr: could not allocate\n");
+ return;
+ }
+ for (i = 0; i < max; i++)
+ usage_table[i] = 0;
+}
+
+int mtrr_add_page(unsigned long base, unsigned long size,
+ unsigned int type, char increment)
+{
+ int error;
+ dom0_op_t op;
+
+ op.cmd = DOM0_ADD_MEMTYPE;
+ op.u.add_memtype.pfn = base;
+ op.u.add_memtype.nr_pfns = size;
+ op.u.add_memtype.type = type;
+ if ((error = HYPERVISOR_dom0_op(&op)))
+ return error;
+
+ if (increment)
+ ++usage_table[op.u.add_memtype.reg];
+
+ return op.u.add_memtype.reg;
+}
+
+int
+mtrr_add(unsigned long base, unsigned long size, unsigned int type,
+ char increment)
+{
+ if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) {
+ printk(KERN_WARNING "mtrr: size and base must be multiples of 4
kiB\n");
+ printk(KERN_DEBUG "mtrr: size: 0x%lx base: 0x%lx\n", size,
base);
+ return -EINVAL;
+ }
+ return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type,
+ increment);
+}
+
+int mtrr_del_page(int reg, unsigned long base, unsigned long size)
+{
+ int i, max;
+ mtrr_type ltype;
+ unsigned long lbase;
+ unsigned int lsize;
+ int error = -EINVAL;
+ dom0_op_t op;
+
+ max = num_var_ranges;
+ if (reg < 0) {
+ /* Search for existing MTRR */
+ for (i = 0; i < max; ++i) {
+ mtrr_if->get(i, &lbase, &lsize, <ype);
+ if (lbase == base && lsize == size) {
+ reg = i;
+ break;
+ }
+ }
+ if (reg < 0) {
+ printk(KERN_DEBUG "mtrr: no MTRR for %lx000,%lx000
found\n", base,
+ size);
+ goto out;
+ }
+ }
+ if (usage_table[reg] < 1) {
+ printk(KERN_WARNING "mtrr: reg: %d has count=0\n", reg);
+ goto out;
+ }
+ if (--usage_table[reg] < 1) {
+ op.cmd = DOM0_DEL_MEMTYPE;
+ op.u.del_memtype.handle = 0;
+ op.u.add_memtype.reg = reg;
+ (void)HYPERVISOR_dom0_op(&op);
+ }
+ error = reg;
+ out:
+ return error;
+}
+
+int
+mtrr_del(int reg, unsigned long base, unsigned long size)
+{
+ if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) {
+ printk(KERN_INFO "mtrr: size and base must be multiples of 4
kiB\n");
+ printk(KERN_DEBUG "mtrr: size: 0x%lx base: 0x%lx\n", size,
base);
+ return -EINVAL;
+ }
+ return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT);
+}
+
+EXPORT_SYMBOL(mtrr_add);
+EXPORT_SYMBOL(mtrr_del);
+
+static int __init mtrr_init(void)
+{
+ struct cpuinfo_x86 *c = &boot_cpu_data;
+
+ if (!(xen_start_info.flags & SIF_PRIVILEGED))
+ return -ENODEV;
+
+ if ((!cpu_has(c, X86_FEATURE_MTRR)) &&
+ (!cpu_has(c, X86_FEATURE_K6_MTRR)) &&
+ (!cpu_has(c, X86_FEATURE_CYRIX_ARR)) &&
+ (!cpu_has(c, X86_FEATURE_CENTAUR_MCR)))
+ return -ENODEV;
+
+ set_num_var_ranges();
+ init_table();
+
+ return 0;
+}
+
+subsys_initcall(mtrr_init);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/ia32/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/ia32/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,58 @@
+#
+# Makefile for the ia32 kernel emulation subsystem.
+#
+XENARCH := $(subst ",,$(CONFIG_XENARCH))
+
+CFLAGS += -Iarch/$(XENARCH)/kernel
+
+obj-$(CONFIG_IA32_EMULATION) := ia32entry.o syscall32.o
+
+c-obj-$(CONFIG_IA32_EMULATION) := sys_ia32.o ia32_ioctl.o \
+ ia32_signal.o tls32.o \
+ ia32_binfmt.o fpu32.o ptrace32.o
+
+s-obj-y :=
+
+sysv-$(CONFIG_SYSVIPC) := ipc32.o
+c-obj-$(CONFIG_IA32_EMULATION) += $(sysv-y)
+
+c-obj-$(CONFIG_IA32_AOUT) += ia32_aout.o
+
+$(obj)/syscall32.o: $(src)/syscall32.c \
+ $(foreach F,int80 sysenter syscall,$(obj)/vsyscall-$F.so)
+
+# Teach kbuild about targets
+targets := $(foreach F,int80 sysenter syscall,vsyscall-$F.o vsyscall-$F.so)
+
+# The DSO images are built using a special linker script
+quiet_cmd_syscall = SYSCALL $@
+ cmd_syscall = $(CC) -m32 -nostdlib -shared -s \
+ -Wl,-soname=linux-gate.so.1 -o $@ \
+ -Wl,-T,$(filter-out FORCE,$^)
+
+
+$(obj)/vsyscall-int80.so $(obj)/vsyscall-sysenter.so
$(obj)/vsyscall-syscall.so: \
+$(obj)/vsyscall-%.so: $(obj)/vsyscall.lds $(obj)/vsyscall-%.o FORCE
+ $(call if_changed,syscall)
+
+AFLAGS_vsyscall-int80.o = -m32 -I$(obj)
+AFLAGS_vsyscall-sysenter.o = -m32
+AFLAGS_vsyscall-syscall.o = -m32
+CFLAGS_ia32_ioctl.o += -Ifs/
+
+s-link := vsyscall-syscall.o vsyscall-sysenter.o vsyscall-sigreturn.o
+
+$(obj)/vsyscall.lds:
+ @ln -fsn $(srctree)/arch/x86_64/ia32/$(notdir $@) $@
+
+$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)) $(patsubst
%.o,$(obj)/%.S,$(s-obj-y) $(s-link)):
+ @ln -fsn $(srctree)/arch/x86_64/ia32/$(notdir $@) $@
+
+$(obj)/vsyscall-int80.S: $(obj)/vsyscall-sigreturn.S
+$(obj)/vsyscall-sysenter.S: $(obj)/vsyscall-sigreturn.S
+$(obj)/vsyscall-syscall.S: $(obj)/vsyscall-sigreturn.S
+
+obj-y += $(c-obj-y) $(s-obj-y)
+
+clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link))
+clean-files += $(patsubst %.o,%.S,$(s-obj-y) $(s-obj-) $(s-link))
diff -r 35b74976f598 -r a83ac0806d6b linux-2.6.11-xen-sparse/mkbuildtree
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/mkbuildtree Fri Jul 15 13:39:50 2005
@@ -0,0 +1,111 @@
+#!/bin/bash
+
+# mkbuildtree <build tree>
+#
+# Creates symbolic links in <build tree> for the sparse tree
+# in the current directory.
+
+# Script to determine the relative path between two directories.
+# Copyright (c) D. J. Hawkey Jr. 2002
+# Fixed for Xen project by K. Fraser in 2003.
+abs_to_rel ()
+{
+ local CWD SRCPATH
+
+ if [ "$1" != "/" -a "${1##*[^/]}" = "/" ]; then
+ SRCPATH=${1%?}
+ else
+ SRCPATH=$1
+ fi
+ if [ "$2" != "/" -a "${2##*[^/]}" = "/" ]; then
+ DESTPATH=${2%?}
+ else
+ DESTPATH=$2
+ fi
+
+ CWD=$PWD
+ [ "${1%%[^/]*}" != "/" ] && cd $1 && SRCPATH=$PWD
+ [ "${2%%[^/]*}" != "/" ] && cd $2 && DESTPATH=$PWD
+ [ "$CWD" != "$PWD" ] && cd $CWD
+
+ BASEPATH=$SRCPATH
+
+ [ "$SRCPATH" = "$DESTPATH" ] && DESTPATH="." && return
+ [ "$SRCPATH" = "/" ] && DESTPATH=${DESTPATH#?} && return
+
+ while [ "$BASEPATH/" != "${DESTPATH%${DESTPATH#$BASEPATH/}}" ]; do
+ BASEPATH=${BASEPATH%/*}
+ done
+
+ SRCPATH=${SRCPATH#$BASEPATH}
+ DESTPATH=${DESTPATH#$BASEPATH}
+ DESTPATH=${DESTPATH#?}
+ while [ -n "$SRCPATH" ]; do
+ SRCPATH=${SRCPATH%/*}
+ DESTPATH="../$DESTPATH"
+ done
+
+ [ -z "$BASEPATH" ] && BASEPATH="/"
+ [ "${DESTPATH##*[^/]}" = "/" ] && DESTPATH=${DESTPATH%?}
+}
+
+# relative_lndir <target_dir>
+# Creates a tree of symlinks in the current working directory that mirror
+# real files in <target_dir>. <target_dir> should be relative to the current
+# working directory. Symlinks in <target_dir> are ignored. Source-control files
+# are ignored.
+relative_lndir ()
+{
+ local SYMLINK_DIR REAL_DIR pref i j
+ SYMLINK_DIR=$PWD
+ REAL_DIR=$1
+ (
+ cd $REAL_DIR
+ for i in `find . -type d | grep -v SCCS`; do
+ [ -d $SYMLINK_DIR/$i ] || mkdir -p $SYMLINK_DIR/$i
+ (
+ cd $i
+ pref=`echo $i | sed -e 's#/[^/]*#../#g' -e 's#^\.##'`
+ for j in `find . -maxdepth 1 -type f -o -type l`; do
+ ln -sf ${pref}${REAL_DIR}/$i/$j ${SYMLINK_DIR}/$i/$j
+ done
+ )
+ done
+ )
+}
+
+[ "$1" == "" ] && { echo "Syntax: $0 <linux tree to xenify>"; exit 1; }
+
+# Get absolute path to the destination directory
+pushd . >/dev/null
+cd ${1} || { echo "cannot cd to ${1}"; exit 1; }
+AD=$PWD
+popd >/dev/null
+
+# Get absolute path to the source directory
+AS=`pwd`
+
+# Get path to source, relative to destination
+abs_to_rel ${AD} ${AS}
+RS=$DESTPATH
+
+# Remove old copies of files and directories at the destination
+for i in `find . -type f -o -type l` ; do rm -f ${AD}/${i#./} ; done
+
+# We now work from the destination directory
+cd ${AD} || { echo "cannot cd to ${AD}"; exit 1; }
+
+# Remove old symlinks
+for i in `find . -type l`; do rm -f $i; done
+
+# Create symlinks of files and directories which exist in the sparse source
+relative_lndir ${RS}
+rm -f mkbuildtree
+
+
+# Create links to the shared definitions of the Xen interfaces.
+rm -rf ${AD}/include/asm-xen/xen-public
+mkdir ${AD}/include/asm-xen/xen-public
+cd ${AD}/include/asm-xen/xen-public
+relative_lndir ../../../${RS}/../xen/include/public
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/smpboot.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/smpboot.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,958 @@
+/*
+ * x86 SMP booting functions
+ *
+ * (c) 1995 Alan Cox, Building #3 <alan@xxxxxxxxxx>
+ * (c) 1998, 1999, 2000 Ingo Molnar <mingo@xxxxxxxxxx>
+ * Copyright 2001 Andi Kleen, SuSE Labs.
+ *
+ * Much of the core SMP work is based on previous work by Thomas Radke, to
+ * whom a great many thanks are extended.
+ *
+ * Thanks to Intel for making available several different Pentium,
+ * Pentium Pro and Pentium-II/Xeon MP machines.
+ * Original development of Linux SMP code supported by Caldera.
+ *
+ * This code is released under the GNU General Public License version 2 or
+ * later.
+ *
+ * Fixes
+ * Felix Koop : NR_CPUS used properly
+ * Jose Renau : Handle single CPU case.
+ * Alan Cox : By repeated request 8) - Total BogoMIP
report.
+ * Greg Wright : Fix for kernel stacks panic.
+ * Erich Boleyn : MP v1.4 and additional changes.
+ * Matthias Sattler : Changes for 2.1 kernel map.
+ * Michel Lespinasse : Changes for 2.1 kernel map.
+ * Michael Chastain : Change trampoline.S to gnu as.
+ * Alan Cox : Dumb bug: 'B' step PPro's are fine
+ * Ingo Molnar : Added APIC timers, based on code
+ * from Jose Renau
+ * Ingo Molnar : various cleanups and rewrites
+ * Tigran Aivazian : fixed "0.00 in /proc/uptime on SMP" bug.
+ * Maciej W. Rozycki : Bits for genuine 82489DX APICs
+ * Andi Kleen : Changed for SMP boot into long mode.
+ * Rusty Russell : Hacked into shape for new "hotplug"
boot process.
+ */
+
+#include <linux/config.h>
+#include <linux/init.h>
+
+#include <linux/mm.h>
+#include <linux/kernel_stat.h>
+#include <linux/smp_lock.h>
+#include <linux/irq.h>
+#include <linux/bootmem.h>
+#include <linux/thread_info.h>
+#include <linux/module.h>
+
+#include <linux/delay.h>
+#include <linux/mc146818rtc.h>
+#include <asm/mtrr.h>
+#include <asm/pgalloc.h>
+#include <asm/desc.h>
+#include <asm/kdebug.h>
+#include <asm/tlbflush.h>
+#include <asm/proto.h>
+
+/* Number of siblings per CPU package */
+int smp_num_siblings = 1;
+/* Package ID of each logical CPU */
+u8 phys_proc_id[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID };
+EXPORT_SYMBOL(phys_proc_id);
+
+/* Bitmask of currently online CPUs */
+cpumask_t cpu_online_map;
+
+cpumask_t cpu_callin_map;
+cpumask_t cpu_callout_map;
+static cpumask_t smp_commenced_mask;
+
+/* Per CPU bogomips and other parameters */
+struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned;
+
+/* Set when the idlers are all forked */
+int smp_threads_ready;
+
+cpumask_t cpu_sibling_map[NR_CPUS] __cacheline_aligned;
+
+/*
+ * Trampoline 80x86 program as an array.
+ */
+
+extern unsigned char trampoline_data [];
+extern unsigned char trampoline_end [];
+
+/*
+ * Currently trivial. Write the real->protected mode
+ * bootstrap into the page concerned. The caller
+ * has made sure it's suitably aligned.
+ */
+
+static unsigned long __init setup_trampoline(void)
+{
+ void *tramp = __va(SMP_TRAMPOLINE_BASE);
+ extern volatile __u32 tramp_gdt_ptr;
+ tramp_gdt_ptr = __pa_symbol(&cpu_gdt_table);
+ memcpy(tramp, trampoline_data, trampoline_end - trampoline_data);
+ return virt_to_phys(tramp);
+}
+
+/*
+ * The bootstrap kernel entry code has set these up. Save them for
+ * a given CPU
+ */
+
+static void __init smp_store_cpu_info(int id)
+{
+ struct cpuinfo_x86 *c = cpu_data + id;
+
+ *c = boot_cpu_data;
+ identify_cpu(c);
+}
+
+/*
+ * TSC synchronization.
+ *
+ * We first check whether all CPUs have their TSC's synchronized,
+ * then we print a warning if not, and always resync.
+ */
+
+static atomic_t tsc_start_flag = ATOMIC_INIT(0);
+static atomic_t tsc_count_start = ATOMIC_INIT(0);
+static atomic_t tsc_count_stop = ATOMIC_INIT(0);
+static unsigned long long tsc_values[NR_CPUS];
+
+#define NR_LOOPS 5
+
+extern unsigned int fast_gettimeoffset_quotient;
+
+static void __init synchronize_tsc_bp (void)
+{
+ int i;
+ unsigned long long t0;
+ unsigned long long sum, avg;
+ long long delta;
+ long one_usec;
+ int buggy = 0;
+
+ printk(KERN_INFO "checking TSC synchronization across %u CPUs:
",num_booting_cpus());
+
+ one_usec = cpu_khz;
+
+ atomic_set(&tsc_start_flag, 1);
+ wmb();
+
+ /*
+ * We loop a few times to get a primed instruction cache,
+ * then the last pass is more or less synchronized and
+ * the BP and APs set their cycle counters to zero all at
+ * once. This reduces the chance of having random offsets
+ * between the processors, and guarantees that the maximum
+ * delay between the cycle counters is never bigger than
+ * the latency of information-passing (cachelines) between
+ * two CPUs.
+ */
+ for (i = 0; i < NR_LOOPS; i++) {
+ /*
+ * all APs synchronize but they loop on '== num_cpus'
+ */
+ while (atomic_read(&tsc_count_start) != num_booting_cpus()-1)
mb();
+ atomic_set(&tsc_count_stop, 0);
+ wmb();
+ /*
+ * this lets the APs save their current TSC:
+ */
+ atomic_inc(&tsc_count_start);
+
+ sync_core();
+ rdtscll(tsc_values[smp_processor_id()]);
+ /*
+ * We clear the TSC in the last loop:
+ */
+ if (i == NR_LOOPS-1)
+ write_tsc(0, 0);
+
+ /*
+ * Wait for all APs to leave the synchronization point:
+ */
+ while (atomic_read(&tsc_count_stop) != num_booting_cpus()-1)
mb();
+ atomic_set(&tsc_count_start, 0);
+ wmb();
+ atomic_inc(&tsc_count_stop);
+ }
+
+ sum = 0;
+ for (i = 0; i < NR_CPUS; i++) {
+ if (cpu_isset(i, cpu_callout_map)) {
+ t0 = tsc_values[i];
+ sum += t0;
+ }
+ }
+ avg = sum / num_booting_cpus();
+
+ sum = 0;
+ for (i = 0; i < NR_CPUS; i++) {
+ if (!cpu_isset(i, cpu_callout_map))
+ continue;
+
+ delta = tsc_values[i] - avg;
+ if (delta < 0)
+ delta = -delta;
+ /*
+ * We report bigger than 2 microseconds clock differences.
+ */
+ if (delta > 2*one_usec) {
+ long realdelta;
+ if (!buggy) {
+ buggy = 1;
+ printk("\n");
+ }
+ realdelta = delta / one_usec;
+ if (tsc_values[i] < avg)
+ realdelta = -realdelta;
+
+ printk("BIOS BUG: CPU#%d improperly initialized, has
%ld usecs TSC skew! FIXED.\n",
+ i, realdelta);
+ }
+
+ sum += delta;
+ }
+ if (!buggy)
+ printk("passed.\n");
+}
+
+static void __init synchronize_tsc_ap (void)
+{
+ int i;
+
+ /*
+ * Not every cpu is online at the time
+ * this gets called, so we first wait for the BP to
+ * finish SMP initialization:
+ */
+ while (!atomic_read(&tsc_start_flag)) mb();
+
+ for (i = 0; i < NR_LOOPS; i++) {
+ atomic_inc(&tsc_count_start);
+ while (atomic_read(&tsc_count_start) != num_booting_cpus())
mb();
+
+ sync_core();
+ rdtscll(tsc_values[smp_processor_id()]);
+ if (i == NR_LOOPS-1)
+ write_tsc(0, 0);
+
+ atomic_inc(&tsc_count_stop);
+ while (atomic_read(&tsc_count_stop) != num_booting_cpus()) mb();
+ }
+}
+#undef NR_LOOPS
+
+static atomic_t init_deasserted;
+
+void __init smp_callin(void)
+{
+ int cpuid, phys_id;
+ unsigned long timeout;
+
+ /*
+ * If waken up by an INIT in an 82489DX configuration
+ * we may get here before an INIT-deassert IPI reaches
+ * our local APIC. We have to wait for the IPI or we'll
+ * lock up on an APIC access.
+ */
+ while (!atomic_read(&init_deasserted));
+
+ /*
+ * (This works even if the APIC is not enabled.)
+ */
+ phys_id = GET_APIC_ID(apic_read(APIC_ID));
+ cpuid = smp_processor_id();
+ if (cpu_isset(cpuid, cpu_callin_map)) {
+ panic("smp_callin: phys CPU#%d, CPU#%d already present??\n",
+ phys_id, cpuid);
+ }
+ Dprintk("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id);
+
+ /*
+ * STARTUP IPIs are fragile beasts as they might sometimes
+ * trigger some glue motherboard logic. Complete APIC bus
+ * silence for 1 second, this overestimates the time the
+ * boot CPU is spending to send the up to 2 STARTUP IPIs
+ * by a factor of two. This should be enough.
+ */
+
+ /*
+ * Waiting 2s total for startup (udelay is not yet working)
+ */
+ timeout = jiffies + 2*HZ;
+ while (time_before(jiffies, timeout)) {
+ /*
+ * Has the boot CPU finished it's STARTUP sequence?
+ */
+ if (cpu_isset(cpuid, cpu_callout_map))
+ break;
+ rep_nop();
+ }
+
+ if (!time_before(jiffies, timeout)) {
+ panic("smp_callin: CPU%d started up but did not get a
callout!\n",
+ cpuid);
+ }
+
+ /*
+ * the boot CPU has finished the init stage and is spinning
+ * on callin_map until we finish. We are free to set up this
+ * CPU, first the APIC. (this is probably redundant on most
+ * boards)
+ */
+
+ Dprintk("CALLIN, before setup_local_APIC().\n");
+ setup_local_APIC();
+
+ local_irq_enable();
+
+ /*
+ * Get our bogomips.
+ */
+ calibrate_delay();
+ Dprintk("Stack at about %p\n",&cpuid);
+
+ disable_APIC_timer();
+
+ /*
+ * Save our processor parameters
+ */
+ smp_store_cpu_info(cpuid);
+
+ local_irq_disable();
+
+ /*
+ * Allow the master to continue.
+ */
+ cpu_set(cpuid, cpu_callin_map);
+
+ /*
+ * Synchronize the TSC with the BP
+ */
+ if (cpu_has_tsc)
+ synchronize_tsc_ap();
+}
+
+int cpucount;
+
+/*
+ * Activate a secondary processor.
+ */
+void __init start_secondary(void)
+{
+ /*
+ * Dont put anything before smp_callin(), SMP
+ * booting is too fragile that we want to limit the
+ * things done here to the most necessary things.
+ */
+ cpu_init();
+ smp_callin();
+
+ /* otherwise gcc will move up the smp_processor_id before the cpu_init
*/
+ barrier();
+
+ Dprintk("cpu %d: waiting for commence\n", smp_processor_id());
+ while (!cpu_isset(smp_processor_id(), smp_commenced_mask))
+ rep_nop();
+
+ Dprintk("cpu %d: setting up apic clock\n", smp_processor_id());
+ setup_secondary_APIC_clock();
+
+ Dprintk("cpu %d: enabling apic timer\n", smp_processor_id());
+
+ if (nmi_watchdog == NMI_IO_APIC) {
+ disable_8259A_irq(0);
+ enable_NMI_through_LVT0(NULL);
+ enable_8259A_irq(0);
+ }
+
+
+ enable_APIC_timer();
+
+ /*
+ * low-memory mappings have been cleared, flush them from
+ * the local TLBs too.
+ */
+ local_flush_tlb();
+
+ Dprintk("cpu %d eSetting cpu_online_map\n", smp_processor_id());
+ cpu_set(smp_processor_id(), cpu_online_map);
+ wmb();
+
+ cpu_idle();
+}
+
+extern volatile unsigned long init_rsp;
+extern void (*initial_code)(void);
+
+#if APIC_DEBUG
+static inline void inquire_remote_apic(int apicid)
+{
+ unsigned i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 };
+ char *names[] = { "ID", "VERSION", "SPIV" };
+ int timeout, status;
+
+ printk(KERN_INFO "Inquiring remote APIC #%d...\n", apicid);
+
+ for (i = 0; i < sizeof(regs) / sizeof(*regs); i++) {
+ printk("... APIC #%d %s: ", apicid, names[i]);
+
+ /*
+ * Wait for idle.
+ */
+ apic_wait_icr_idle();
+
+ apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(apicid));
+ apic_write_around(APIC_ICR, APIC_DM_REMRD | regs[i]);
+
+ timeout = 0;
+ do {
+ udelay(100);
+ status = apic_read(APIC_ICR) & APIC_ICR_RR_MASK;
+ } while (status == APIC_ICR_RR_INPROG && timeout++ < 1000);
+
+ switch (status) {
+ case APIC_ICR_RR_VALID:
+ status = apic_read(APIC_RRR);
+ printk("%08x\n", status);
+ break;
+ default:
+ printk("failed\n");
+ }
+ }
+}
+#endif
+
+static int __init wakeup_secondary_via_INIT(int phys_apicid, unsigned int
start_rip)
+{
+ unsigned long send_status = 0, accept_status = 0;
+ int maxlvt, timeout, num_starts, j;
+
+ Dprintk("Asserting INIT.\n");
+
+ /*
+ * Turn INIT on target chip
+ */
+ apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
+
+ /*
+ * Send IPI
+ */
+ apic_write_around(APIC_ICR, APIC_INT_LEVELTRIG | APIC_INT_ASSERT
+ | APIC_DM_INIT);
+
+ Dprintk("Waiting for send to finish...\n");
+ timeout = 0;
+ do {
+ Dprintk("+");
+ udelay(100);
+ send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
+ } while (send_status && (timeout++ < 1000));
+
+ mdelay(10);
+
+ Dprintk("Deasserting INIT.\n");
+
+ /* Target chip */
+ apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
+
+ /* Send IPI */
+ apic_write_around(APIC_ICR, APIC_INT_LEVELTRIG | APIC_DM_INIT);
+
+ Dprintk("Waiting for send to finish...\n");
+ timeout = 0;
+ do {
+ Dprintk("+");
+ udelay(100);
+ send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
+ } while (send_status && (timeout++ < 1000));
+
+ atomic_set(&init_deasserted, 1);
+
+ /*
+ * Should we send STARTUP IPIs ?
+ *
+ * Determine this based on the APIC version.
+ * If we don't have an integrated APIC, don't send the STARTUP IPIs.
+ */
+ if (APIC_INTEGRATED(apic_version[phys_apicid]))
+ num_starts = 2;
+ else
+ num_starts = 0;
+
+ /*
+ * Run STARTUP IPI loop.
+ */
+ Dprintk("#startup loops: %d.\n", num_starts);
+
+ maxlvt = get_maxlvt();
+
+ for (j = 1; j <= num_starts; j++) {
+ Dprintk("Sending STARTUP #%d.\n",j);
+ apic_read_around(APIC_SPIV);
+ apic_write(APIC_ESR, 0);
+ apic_read(APIC_ESR);
+ Dprintk("After apic_write.\n");
+
+ /*
+ * STARTUP IPI
+ */
+
+ /* Target chip */
+ apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
+
+ /* Boot on the stack */
+ /* Kick the second */
+ apic_write_around(APIC_ICR, APIC_DM_STARTUP
+ | (start_rip >> 12));
+
+ /*
+ * Give the other CPU some time to accept the IPI.
+ */
+ udelay(300);
+
+ Dprintk("Startup point 1.\n");
+
+ Dprintk("Waiting for send to finish...\n");
+ timeout = 0;
+ do {
+ Dprintk("+");
+ udelay(100);
+ send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
+ } while (send_status && (timeout++ < 1000));
+
+ /*
+ * Give the other CPU some time to accept the IPI.
+ */
+ udelay(200);
+ /*
+ * Due to the Pentium erratum 3AP.
+ */
+ if (maxlvt > 3) {
+ apic_read_around(APIC_SPIV);
+ apic_write(APIC_ESR, 0);
+ }
+ accept_status = (apic_read(APIC_ESR) & 0xEF);
+ if (send_status || accept_status)
+ break;
+ }
+ Dprintk("After Startup.\n");
+
+ if (send_status)
+ printk(KERN_ERR "APIC never delivered???\n");
+ if (accept_status)
+ printk(KERN_ERR "APIC delivery error (%lx).\n", accept_status);
+
+ return (send_status | accept_status);
+}
+
+static void __init do_boot_cpu (int apicid)
+{
+ struct task_struct *idle;
+ unsigned long boot_error;
+ int timeout, cpu;
+ unsigned long start_rip;
+
+ cpu = ++cpucount;
+ /*
+ * We can't use kernel_thread since we must avoid to
+ * reschedule the child.
+ */
+ idle = fork_idle(cpu);
+ if (IS_ERR(idle))
+ panic("failed fork for CPU %d", cpu);
+ x86_cpu_to_apicid[cpu] = apicid;
+
+ cpu_pda[cpu].pcurrent = idle;
+
+ start_rip = setup_trampoline();
+
+ init_rsp = idle->thread.rsp;
+ per_cpu(init_tss,cpu).rsp0 = init_rsp;
+ initial_code = start_secondary;
+ clear_ti_thread_flag(idle->thread_info, TIF_FORK);
+
+ printk(KERN_INFO "Booting processor %d/%d rip %lx rsp %lx\n", cpu,
apicid,
+ start_rip, init_rsp);
+
+ /*
+ * This grunge runs the startup process for
+ * the targeted processor.
+ */
+
+ atomic_set(&init_deasserted, 0);
+
+ Dprintk("Setting warm reset code and vector.\n");
+
+ CMOS_WRITE(0xa, 0xf);
+ local_flush_tlb();
+ Dprintk("1.\n");
+ *((volatile unsigned short *) phys_to_virt(0x469)) = start_rip >> 4;
+ Dprintk("2.\n");
+ *((volatile unsigned short *) phys_to_virt(0x467)) = start_rip & 0xf;
+ Dprintk("3.\n");
+
+ /*
+ * Be paranoid about clearing APIC errors.
+ */
+ if (APIC_INTEGRATED(apic_version[apicid])) {
+ apic_read_around(APIC_SPIV);
+ apic_write(APIC_ESR, 0);
+ apic_read(APIC_ESR);
+ }
+
+ /*
+ * Status is now clean
+ */
+ boot_error = 0;
+
+ /*
+ * Starting actual IPI sequence...
+ */
+ boot_error = wakeup_secondary_via_INIT(apicid, start_rip);
+
+ if (!boot_error) {
+ /*
+ * allow APs to start initializing.
+ */
+ Dprintk("Before Callout %d.\n", cpu);
+ cpu_set(cpu, cpu_callout_map);
+ Dprintk("After Callout %d.\n", cpu);
+
+ /*
+ * Wait 5s total for a response
+ */
+ for (timeout = 0; timeout < 50000; timeout++) {
+ if (cpu_isset(cpu, cpu_callin_map))
+ break; /* It has booted */
+ udelay(100);
+ }
+
+ if (cpu_isset(cpu, cpu_callin_map)) {
+ /* number CPUs logically, starting from 1 (BSP is 0) */
+ Dprintk("OK.\n");
+ print_cpu_info(&cpu_data[cpu]);
+ Dprintk("CPU has booted.\n");
+ } else {
+ boot_error = 1;
+ if (*((volatile unsigned char
*)phys_to_virt(SMP_TRAMPOLINE_BASE))
+ == 0xA5)
+ /* trampoline started but...? */
+ printk("Stuck ??\n");
+ else
+ /* trampoline code not run */
+ printk("Not responding.\n");
+#if APIC_DEBUG
+ inquire_remote_apic(apicid);
+#endif
+ }
+ }
+ if (boot_error) {
+ cpu_clear(cpu, cpu_callout_map); /* was set here
(do_boot_cpu()) */
+ clear_bit(cpu, &cpu_initialized); /* was set by cpu_init() */
+ cpucount--;
+ x86_cpu_to_apicid[cpu] = BAD_APICID;
+ x86_cpu_to_log_apicid[cpu] = BAD_APICID;
+ }
+}
+
+cycles_t cacheflush_time;
+unsigned long cache_decay_ticks;
+
+static void smp_tune_scheduling (void)
+{
+ int cachesize; /* kB */
+ unsigned long bandwidth = 1000; /* MB/s */
+ /*
+ * Rough estimation for SMP scheduling, this is the number of
+ * cycles it takes for a fully memory-limited process to flush
+ * the SMP-local cache.
+ *
+ * (For a P5 this pretty much means we will choose another idle
+ * CPU almost always at wakeup time (this is due to the small
+ * L1 cache), on PIIs it's around 50-100 usecs, depending on
+ * the cache size)
+ */
+
+ if (!cpu_khz) {
+ /*
+ * this basically disables processor-affinity
+ * scheduling on SMP without a TSC.
+ */
+ cacheflush_time = 0;
+ return;
+ } else {
+ cachesize = boot_cpu_data.x86_cache_size;
+ if (cachesize == -1) {
+ cachesize = 16; /* Pentiums, 2x8kB cache */
+ bandwidth = 100;
+ }
+
+ cacheflush_time = (cpu_khz>>10) * (cachesize<<10) / bandwidth;
+ }
+
+ cache_decay_ticks = (long)cacheflush_time/cpu_khz * HZ / 1000;
+
+ printk(KERN_INFO "per-CPU timeslice cutoff: %ld.%02ld usecs.\n",
+ (long)cacheflush_time/(cpu_khz/1000),
+ ((long)cacheflush_time*100/(cpu_khz/1000)) % 100);
+ printk(KERN_INFO "task migration cache decay timeout: %ld msecs.\n",
+ (cache_decay_ticks + 1) * 1000 / HZ);
+}
+
+/*
+ * Cycle through the processors sending APIC IPIs to boot each.
+ */
+
+static void __init smp_boot_cpus(unsigned int max_cpus)
+{
+ unsigned apicid, cpu, bit, kicked;
+
+ nmi_watchdog_default();
+
+ /*
+ * Setup boot CPU information
+ */
+ smp_store_cpu_info(0); /* Final full version of the data */
+ printk(KERN_INFO "CPU%d: ", 0);
+ print_cpu_info(&cpu_data[0]);
+
+ current_thread_info()->cpu = 0;
+ smp_tune_scheduling();
+
+ if (!physid_isset(hard_smp_processor_id(), phys_cpu_present_map)) {
+ printk("weird, boot CPU (#%d) not listed by the BIOS.\n",
+ hard_smp_processor_id());
+ physid_set(hard_smp_processor_id(), phys_cpu_present_map);
+ }
+
+ /*
+ * If we couldn't find an SMP configuration at boot time,
+ * get out of here now!
+ */
+ if (!smp_found_config) {
+ printk(KERN_NOTICE "SMP motherboard not detected.\n");
+ io_apic_irqs = 0;
+ cpu_online_map = cpumask_of_cpu(0);
+ phys_cpu_present_map = physid_mask_of_physid(0);
+ if (APIC_init_uniprocessor())
+ printk(KERN_NOTICE "Local APIC not detected."
+ " Using dummy APIC emulation.\n");
+ goto smp_done;
+ }
+
+ /*
+ * Should not be necessary because the MP table should list the boot
+ * CPU too, but we do it for the sake of robustness anyway.
+ */
+ if (!physid_isset(boot_cpu_id, phys_cpu_present_map)) {
+ printk(KERN_NOTICE "weird, boot CPU (#%d) not listed by the
BIOS.\n",
+ boot_cpu_id);
+ physid_set(hard_smp_processor_id(), phys_cpu_present_map);
+ }
+
+ /*
+ * If we couldn't find a local APIC, then get out of here now!
+ */
+ if (APIC_INTEGRATED(apic_version[boot_cpu_id]) && !cpu_has_apic) {
+ printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n",
+ boot_cpu_id);
+ printk(KERN_ERR "... forcing use of dummy APIC emulation. (tell
your hw vendor)\n");
+ io_apic_irqs = 0;
+ cpu_online_map = cpumask_of_cpu(0);
+ phys_cpu_present_map = physid_mask_of_physid(0);
+ disable_apic = 1;
+ goto smp_done;
+ }
+
+ verify_local_APIC();
+
+ /*
+ * If SMP should be disabled, then really disable it!
+ */
+ if (!max_cpus) {
+ smp_found_config = 0;
+ printk(KERN_INFO "SMP mode deactivated, forcing use of dummy
APIC emulation.\n");
+ io_apic_irqs = 0;
+ cpu_online_map = cpumask_of_cpu(0);
+ phys_cpu_present_map = physid_mask_of_physid(0);
+ disable_apic = 1;
+ goto smp_done;
+ }
+
+ connect_bsp_APIC();
+ setup_local_APIC();
+
+ if (GET_APIC_ID(apic_read(APIC_ID)) != boot_cpu_id)
+ BUG();
+
+ x86_cpu_to_apicid[0] = boot_cpu_id;
+
+ /*
+ * Now scan the CPU present map and fire up the other CPUs.
+ */
+ Dprintk("CPU present map: %lx\n", physids_coerce(phys_cpu_present_map));
+
+ kicked = 1;
+ for (bit = 0; kicked < NR_CPUS && bit < MAX_APICS; bit++) {
+ apicid = cpu_present_to_apicid(bit);
+ /*
+ * Don't even attempt to start the boot CPU!
+ */
+ if (apicid == boot_cpu_id || (apicid == BAD_APICID))
+ continue;
+
+ if (!physid_isset(apicid, phys_cpu_present_map))
+ continue;
+ if ((max_cpus >= 0) && (max_cpus <= cpucount+1))
+ continue;
+
+ do_boot_cpu(apicid);
+ ++kicked;
+ }
+
+ /*
+ * Cleanup possible dangling ends...
+ */
+ {
+ /*
+ * Install writable page 0 entry to set BIOS data area.
+ */
+ local_flush_tlb();
+
+ /*
+ * Paranoid: Set warm reset code and vector here back
+ * to default values.
+ */
+ CMOS_WRITE(0, 0xf);
+
+ *((volatile int *) phys_to_virt(0x467)) = 0;
+ }
+
+ /*
+ * Allow the user to impress friends.
+ */
+
+ Dprintk("Before bogomips.\n");
+ if (!cpucount) {
+ printk(KERN_INFO "Only one processor found.\n");
+ } else {
+ unsigned long bogosum = 0;
+ for (cpu = 0; cpu < NR_CPUS; cpu++)
+ if (cpu_isset(cpu, cpu_callout_map))
+ bogosum += cpu_data[cpu].loops_per_jiffy;
+ printk(KERN_INFO "Total of %d processors activated (%lu.%02lu
BogoMIPS).\n",
+ cpucount+1,
+ bogosum/(500000/HZ),
+ (bogosum/(5000/HZ))%100);
+ Dprintk("Before bogocount - setting activated=1.\n");
+ }
+
+ /*
+ * Construct cpu_sibling_map[], so that we can tell the
+ * sibling CPU efficiently.
+ */
+ for (cpu = 0; cpu < NR_CPUS; cpu++)
+ cpus_clear(cpu_sibling_map[cpu]);
+
+ for (cpu = 0; cpu < NR_CPUS; cpu++) {
+ int siblings = 0;
+ int i;
+ if (!cpu_isset(cpu, cpu_callout_map))
+ continue;
+
+ if (smp_num_siblings > 1) {
+ for (i = 0; i < NR_CPUS; i++) {
+ if (!cpu_isset(i, cpu_callout_map))
+ continue;
+ if (phys_proc_id[cpu] == phys_proc_id[i]) {
+ siblings++;
+ cpu_set(i, cpu_sibling_map[cpu]);
+ }
+ }
+ } else {
+ siblings++;
+ cpu_set(cpu, cpu_sibling_map[cpu]);
+ }
+
+ if (siblings != smp_num_siblings) {
+ printk(KERN_WARNING
+ "WARNING: %d siblings found for CPU%d, should be %d\n",
+ siblings, cpu, smp_num_siblings);
+ smp_num_siblings = siblings;
+ }
+ }
+
+ Dprintk("Boot done.\n");
+
+ /*
+ * Here we can be sure that there is an IO-APIC in the system. Let's
+ * go and set it up:
+ */
+ if (!skip_ioapic_setup && nr_ioapics)
+ setup_IO_APIC();
+ else
+ nr_ioapics = 0;
+
+ setup_boot_APIC_clock();
+
+ /*
+ * Synchronize the TSC with the AP
+ */
+ if (cpu_has_tsc && cpucount)
+ synchronize_tsc_bp();
+
+ smp_done:
+ time_init_smp();
+}
+
+/* These are wrappers to interface to the new boot process. Someone
+ who understands all this stuff should rewrite it properly. --RR 15/Jul/02 */
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+ smp_boot_cpus(max_cpus);
+}
+
+void __devinit smp_prepare_boot_cpu(void)
+{
+ cpu_set(smp_processor_id(), cpu_online_map);
+ cpu_set(smp_processor_id(), cpu_callout_map);
+}
+
+int __devinit __cpu_up(unsigned int cpu)
+{
+ /* This only works at boot for x86. See "rewrite" above. */
+ if (cpu_isset(cpu, smp_commenced_mask)) {
+ local_irq_enable();
+ return -ENOSYS;
+ }
+
+ /* In case one didn't come up */
+ if (!cpu_isset(cpu, cpu_callin_map)) {
+ local_irq_enable();
+ return -EIO;
+ }
+ local_irq_enable();
+
+ /* Unleash the CPU! */
+ Dprintk("waiting for cpu %d\n", cpu);
+
+ cpu_set(cpu, smp_commenced_mask);
+ while (!cpu_isset(cpu, cpu_online_map))
+ mb();
+ return 0;
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+#ifdef CONFIG_X86_IO_APIC
+ setup_ioapic_dest();
+#endif
+ zap_low_mappings();
+}
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blkback/control.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blkback/control.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,61 @@
+/******************************************************************************
+ * arch/xen/drivers/blkif/backend/control.c
+ *
+ * Routines for interfacing with the control plane.
+ *
+ * Copyright (c) 2004, Keir Fraser
+ */
+
+#include "common.h"
+
+static void blkif_ctrlif_rx(ctrl_msg_t *msg, unsigned long id)
+{
+ DPRINTK("Received blkif backend message, subtype=%d\n", msg->subtype);
+
+ switch ( msg->subtype )
+ {
+ case CMSG_BLKIF_BE_CREATE:
+ blkif_create((blkif_be_create_t *)&msg->msg[0]);
+ break;
+ case CMSG_BLKIF_BE_DESTROY:
+ blkif_destroy((blkif_be_destroy_t *)&msg->msg[0]);
+ break;
+ case CMSG_BLKIF_BE_CONNECT:
+ blkif_connect((blkif_be_connect_t *)&msg->msg[0]);
+ break;
+ case CMSG_BLKIF_BE_DISCONNECT:
+ if ( !blkif_disconnect((blkif_be_disconnect_t *)&msg->msg[0],msg->id) )
+ return; /* Sending the response is deferred until later. */
+ break;
+ case CMSG_BLKIF_BE_VBD_CREATE:
+ vbd_create((blkif_be_vbd_create_t *)&msg->msg[0]);
+ break;
+ case CMSG_BLKIF_BE_VBD_DESTROY:
+ vbd_destroy((blkif_be_vbd_destroy_t *)&msg->msg[0]);
+ break;
+ default:
+ DPRINTK("Parse error while reading message subtype %d, len %d\n",
+ msg->subtype, msg->length);
+ msg->length = 0;
+ break;
+ }
+
+ ctrl_if_send_response(msg);
+}
+
+void blkif_ctrlif_init(void)
+{
+ ctrl_msg_t cmsg;
+ blkif_be_driver_status_t st;
+
+ (void)ctrl_if_register_receiver(CMSG_BLKIF_BE, blkif_ctrlif_rx,
+ CALLBACK_IN_BLOCKING_CONTEXT);
+
+ /* Send a driver-UP notification to the domain controller. */
+ cmsg.type = CMSG_BLKIF_BE;
+ cmsg.subtype = CMSG_BLKIF_BE_DRIVER_STATUS;
+ cmsg.length = sizeof(blkif_be_driver_status_t);
+ st.status = BLKIF_DRIVER_STATUS_UP;
+ memcpy(cmsg.msg, &st, sizeof(st));
+ ctrl_if_send_message_block(&cmsg, NULL, 0, TASK_UNINTERRUPTIBLE);
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/xenbus/xenbus_xs.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/xenbus/xenbus_xs.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,488 @@
+/******************************************************************************
+ * xenbus_xs.c
+ *
+ * This is the kernel equivalent of the "xs" library. We don't need everything
+ * and we use xenbus_comms to communication.
+ *
+ * Copyright (C) 2005 Rusty Russell, IBM Corporation
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include "xenstore/xenstored.h"
+#include <linux/uio.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/fcntl.h>
+#include <linux/kthread.h>
+#include <asm-xen/xenbus.h>
+#include "xenbus_comms.h"
+
+#define streq(a, b) (strcmp((a), (b)) == 0)
+
+static void *xs_in, *xs_out;
+static LIST_HEAD(watches);
+static DECLARE_MUTEX(watches_lock);
+DECLARE_MUTEX(xs_lock);
+
+static int get_error(const char *errorstring)
+{
+ unsigned int i;
+
+ for (i = 0; !streq(errorstring, xsd_errors[i].errstring); i++) {
+ if (i == ARRAY_SIZE(xsd_errors) - 1) {
+ printk(KERN_WARNING
+ "XENBUS xen store gave: unknown error %s",
+ errorstring);
+ return EINVAL;
+ }
+ }
+ return xsd_errors[i].errnum;
+}
+
+static void *read_reply(enum xsd_sockmsg_type *type, unsigned int *len)
+{
+ struct xsd_sockmsg msg;
+ void *ret;
+ int err;
+
+ err = xb_read(xs_in, &msg, sizeof(msg));
+ if (err)
+ return ERR_PTR(err);
+
+ ret = kmalloc(msg.len + 1, GFP_KERNEL);
+ if (!ret)
+ return ERR_PTR(-ENOMEM);
+
+ err = xb_read(xs_in, ret, msg.len);
+ if (err) {
+ kfree(ret);
+ return ERR_PTR(err);
+ }
+ ((char*)ret)[msg.len] = '\0';
+
+ *type = msg.type;
+ if (len)
+ *len = msg.len;
+ return ret;
+}
+
+/* Send message to xs, get kmalloc'ed reply. ERR_PTR() on error. */
+static void *xs_talkv(enum xsd_sockmsg_type type,
+ const struct kvec *iovec,
+ unsigned int num_vecs,
+ unsigned int *len)
+{
+ struct xsd_sockmsg msg;
+ void *ret = NULL;
+ unsigned int i;
+ int err;
+
+ WARN_ON(down_trylock(&xs_lock) == 0);
+
+ msg.type = type;
+ msg.len = 0;
+ for (i = 0; i < num_vecs; i++)
+ msg.len += iovec[i].iov_len;
+
+ err = xb_write(xs_out, &msg, sizeof(msg));
+ if (err)
+ return ERR_PTR(err);
+
+ for (i = 0; i < num_vecs; i++) {
+ err = xb_write(xs_out, iovec[i].iov_base, iovec[i].iov_len);;
+ if (err)
+ return ERR_PTR(err);
+ }
+
+ /* Watches can have fired before reply comes: daemon detects
+ * and re-transmits, so we can ignore this. */
+ do {
+ kfree(ret);
+ ret = read_reply(&msg.type, len);
+ if (IS_ERR(ret))
+ return ret;
+ } while (msg.type == XS_WATCH_EVENT);
+
+ if (msg.type == XS_ERROR) {
+ err = get_error(ret);
+ kfree(ret);
+ return ERR_PTR(-err);
+ }
+
+ BUG_ON(msg.type != type);
+ return ret;
+}
+
+/* Simplified version of xs_talkv: single message. */
+static void *xs_single(enum xsd_sockmsg_type type,
+ const char *string, unsigned int *len)
+{
+ struct kvec iovec;
+
+ iovec.iov_base = (void *)string;
+ iovec.iov_len = strlen(string) + 1;
+ return xs_talkv(type, &iovec, 1, len);
+}
+
+/* Many commands only need an ack, don't care what it says. */
+static int xs_error(char *reply)
+{
+ if (IS_ERR(reply))
+ return PTR_ERR(reply);
+ kfree(reply);
+ return 0;
+}
+
+static unsigned int count_strings(const char *strings, unsigned int len)
+{
+ unsigned int num;
+ const char *p;
+
+ for (p = strings, num = 0; p < strings + len; p += strlen(p) + 1)
+ num++;
+
+ return num;
+}
+
+char **xs_directory(const char *path, unsigned int *num)
+{
+ char *strings, *p, **ret;
+ unsigned int len;
+
+ strings = xs_single(XS_DIRECTORY, path, &len);
+ if (IS_ERR(strings))
+ return (char **)strings;
+
+ /* Count the strings. */
+ *num = count_strings(strings, len);
+
+ /* Transfer to one big alloc for easy freeing. */
+ ret = kmalloc(*num * sizeof(char *) + len, GFP_ATOMIC);
+ if (!ret) {
+ kfree(strings);
+ return ERR_PTR(-ENOMEM);
+ }
+ memcpy(&ret[*num], strings, len);
+ kfree(strings);
+
+ strings = (char *)&ret[*num];
+ for (p = strings, *num = 0; p < strings + len; p += strlen(p) + 1)
+ ret[(*num)++] = p;
+ return ret;
+}
+
+/* Check if a path exists. Return 1 if it does. */
+int xs_exists(const char *path)
+{
+ char **dir;
+ int dir_n;
+
+ dir = xs_directory(path, &dir_n);
+ if (IS_ERR(dir))
+ return 0;
+ kfree(dir);
+ return 1;
+}
+
+/* Make a directory, creating dirs on the path to it if necessary.
+ * Return 0 on success, error code otherwise.
+ */
+int xs_mkdirs(const char *path)
+{
+ int err = 0;
+ char s[strlen(path) + 1], *p = s;
+
+ if (xs_exists(path))
+ goto out;
+ strcpy(p, path);
+ if (*p == '/')
+ p++;
+ for (;;) {
+ p = strchr(p, '/');
+ if (p)
+ *p = '\0';
+ if (!xs_exists(s)) {
+ err = xs_mkdir(s);
+ if (err)
+ goto out;
+ }
+ if (!p)
+ break;
+ *p++ = '/';
+ }
+ out:
+ return err;
+}
+
+
+/* Get the value of a single file.
+ * Returns a kmalloced value: call free() on it after use.
+ * len indicates length in bytes.
+ */
+void *xs_read(const char *path, unsigned int *len)
+{
+ return xs_single(XS_READ, path, len);
+}
+
+/* Write the value of a single file.
+ * Returns -err on failure. createflags can be 0, O_CREAT, or O_CREAT|O_EXCL.
+ */
+int xs_write(const char *path,
+ const void *data, unsigned int len, int createflags)
+{
+ const char *flags;
+ struct kvec iovec[3];
+
+ /* Format: Flags (as string), path, data. */
+ if (createflags == 0)
+ flags = XS_WRITE_NONE;
+ else if (createflags == O_CREAT)
+ flags = XS_WRITE_CREATE;
+ else if (createflags == (O_CREAT|O_EXCL))
+ flags = XS_WRITE_CREATE_EXCL;
+ else
+ return -EINVAL;
+
+ iovec[0].iov_base = (void *)path;
+ iovec[0].iov_len = strlen(path) + 1;
+ iovec[1].iov_base = (void *)flags;
+ iovec[1].iov_len = strlen(flags) + 1;
+ iovec[2].iov_base = (void *)data;
+ iovec[2].iov_len = len;
+
+ return xs_error(xs_talkv(XS_WRITE, iovec, ARRAY_SIZE(iovec), NULL));
+}
+
+/* Create a new directory. */
+int xs_mkdir(const char *path)
+{
+ return xs_error(xs_single(XS_MKDIR, path, NULL));
+}
+
+/* Destroy a file or directory (directories must be empty). */
+int xs_rm(const char *path)
+{
+ return xs_error(xs_single(XS_RM, path, NULL));
+}
+
+/* Start a transaction: changes by others will not be seen during this
+ * transaction, and changes will not be visible to others until end.
+ * Transaction only applies to the given subtree.
+ * You can only have one transaction at any time.
+ */
+int xs_transaction_start(const char *subtree)
+{
+ return xs_error(xs_single(XS_TRANSACTION_START, subtree, NULL));
+}
+
+/* End a transaction.
+ * If abandon is true, transaction is discarded instead of committed.
+ */
+int xs_transaction_end(int abort)
+{
+ char abortstr[2];
+
+ if (abort)
+ strcpy(abortstr, "F");
+ else
+ strcpy(abortstr, "T");
+ return xs_error(xs_single(XS_TRANSACTION_END, abortstr, NULL));
+}
+
+char *xs_get_domain_path(domid_t domid)
+{
+ char domid_str[32];
+
+ sprintf(domid_str, "%u", domid);
+ return xs_single(XS_GETDOMAINPATH, domid_str, NULL);
+}
+
+static int xs_watch(const char *path, const char *token, unsigned int priority)
+{
+ char prio[32];
+ struct kvec iov[3];
+
+ sprintf(prio, "%u", priority);
+ iov[0].iov_base = (void *)path;
+ iov[0].iov_len = strlen(path) + 1;
+ iov[1].iov_base = (void *)token;
+ iov[1].iov_len = strlen(token) + 1;
+ iov[2].iov_base = prio;
+ iov[2].iov_len = strlen(prio) + 1;
+
+ return xs_error(xs_talkv(XS_WATCH, iov, ARRAY_SIZE(iov), NULL));
+}
+
+static char *xs_read_watch(char **token)
+{
+ enum xsd_sockmsg_type type;
+ char *ret;
+
+ ret = read_reply(&type, NULL);
+ if (IS_ERR(ret))
+ return ret;
+
+ BUG_ON(type != XS_WATCH_EVENT);
+ *token = ret + strlen(ret) + 1;
+ return ret;
+}
+
+static int xs_acknowledge_watch(const char *token)
+{
+ return xs_error(xs_single(XS_WATCH_ACK, token, NULL));
+}
+
+static int xs_unwatch(const char *path, const char *token)
+{
+ struct kvec iov[2];
+
+ iov[0].iov_base = (char *)path;
+ iov[0].iov_len = strlen(path) + 1;
+ iov[1].iov_base = (char *)token;
+ iov[1].iov_len = strlen(token) + 1;
+
+ return xs_error(xs_talkv(XS_UNWATCH, iov, ARRAY_SIZE(iov), NULL));
+}
+
+/* A little paranoia: we don't just trust token. */
+static struct xenbus_watch *find_watch(const char *token)
+{
+ struct xenbus_watch *i, *cmp;
+
+ cmp = (void *)simple_strtoul(token, NULL, 16);
+
+ list_for_each_entry(i, &watches, list)
+ if (i == cmp)
+ return i;
+ return NULL;
+}
+
+/* Register callback to watch this node. */
+int register_xenbus_watch(struct xenbus_watch *watch)
+{
+ /* Pointer in ascii is the token. */
+ char token[sizeof(watch) * 2 + 1];
+ int err;
+
+ sprintf(token, "%lX", (long)watch);
+ down(&watches_lock);
+ BUG_ON(find_watch(token));
+
+ down(&xs_lock);
+ err = xs_watch(watch->node, token, watch->priority);
+ up(&xs_lock);
+ if (!err)
+ list_add(&watch->list, &watches);
+ up(&watches_lock);
+ return err;
+}
+
+void unregister_xenbus_watch(struct xenbus_watch *watch)
+{
+ char token[sizeof(watch) * 2 + 1];
+ int err;
+
+ sprintf(token, "%lX", (long)watch);
+ down(&watches_lock);
+ BUG_ON(!find_watch(token));
+
+ down(&xs_lock);
+ err = xs_unwatch(watch->node, token);
+ up(&xs_lock);
+ list_del(&watch->list);
+ up(&watches_lock);
+
+ if (err)
+ printk(KERN_WARNING "XENBUS Failed to release watch %s: %i\n",
+ watch->node, err);
+}
+
+static int watch_thread(void *unused)
+{
+ int err;
+ unsigned long mtu;
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(HZ*10);
+ printk("watch_thread, doing read\n");
+ down(&xs_lock);
+ err = xenbus_read_long("", "mtu", &mtu);
+ up(&xs_lock);
+ printk("fake field read: %i (%lu)\n", err, mtu);
+
+ for (;;) {
+ char *token;
+ char *node = NULL;
+
+ wait_event(xb_waitq, xs_input_avail(xs_in));
+
+ /* If this is a spurious wakeup caused by someone
+ * doing an op, they'll hold the lock and the buffer
+ * will be empty by the time we get there.
+ */
+ down(&xs_lock);
+ if (xs_input_avail(xs_in))
+ node = xs_read_watch(&token);
+ /* Release lock before calling callback. */
+ up(&xs_lock);
+ if (node && !IS_ERR(node)) {
+ struct xenbus_watch *w;
+ int err;
+
+ down(&watches_lock);
+ w = find_watch(token);
+ BUG_ON(!w);
+ w->callback(w, node);
+ up(&watches_lock);
+ down(&xs_lock);
+ err = xs_acknowledge_watch(token);
+ if (err)
+ printk(KERN_WARNING
+ "XENBUS acknowledge %s failed %i\n",
+ node, err);
+ up(&xs_lock);
+ kfree(node);
+ } else
+ printk(KERN_WARNING "XENBUS xs_read_watch: %li\n",
+ PTR_ERR(node));
+ }
+}
+
+int xs_init(void)
+{
+ int err;
+ struct task_struct *watcher;
+
+ err = xb_init_comms(&xs_in, &xs_out);
+ if (err)
+ return err;
+
+ watcher = kthread_run(watch_thread, NULL, "kxbwatch");
+ if (IS_ERR(watcher))
+ return PTR_ERR(watcher);
+ return 0;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/kernel/head.S
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/kernel/head.S Fri Jul 15 13:39:50 2005
@@ -0,0 +1,41 @@
+
+.section __xen_guest
+ .ascii "GUEST_OS=linux,GUEST_VER=2.4,XEN_VER=3.0,VIRT_BASE=0xC0000000"
+ .ascii ",LOADER=generic"
+ .byte 0
+
+.text
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/desc.h>
+
+ENTRY(stext)
+ENTRY(_stext)
+ cld
+ lss stack_start,%esp
+ /* Copy the necessary stuff from xen_start_info structure. */
+ mov $SYMBOL_NAME(xen_start_info_union),%edi
+ mov $128,%ecx
+ rep movsl
+ jmp SYMBOL_NAME(start_kernel)
+
+ENTRY(stack_start)
+ .long SYMBOL_NAME(init_task_union)+8192, __KERNEL_DS
+
+.org 0x1000
+ENTRY(empty_zero_page)
+
+.org 0x2000
+ENTRY(default_ldt)
+
+.org 0x3000
+ENTRY(cpu0_pte_quicklist)
+
+.org 0x3400
+ENTRY(cpu0_pgd_quicklist)
+
+.org 0x3800
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/linux/highmem.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/linux/highmem.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,137 @@
+#ifndef _LINUX_HIGHMEM_H
+#define _LINUX_HIGHMEM_H
+
+#include <linux/config.h>
+#include <asm/pgalloc.h>
+
+#ifdef CONFIG_HIGHMEM
+
+extern struct page *highmem_start_page;
+
+#include <asm/highmem.h>
+
+/* declarations for linux/mm/highmem.c */
+unsigned int nr_free_highpages(void);
+void kmap_flush_unused(void);
+
+extern struct buffer_head *create_bounce(int rw, struct buffer_head * bh_orig);
+
+static inline char *bh_kmap(struct buffer_head *bh)
+{
+ return kmap(bh->b_page) + bh_offset(bh);
+}
+
+static inline void bh_kunmap(struct buffer_head *bh)
+{
+ kunmap(bh->b_page);
+}
+
+/*
+ * remember to add offset! and never ever reenable interrupts between a
+ * bh_kmap_irq and bh_kunmap_irq!!
+ */
+static inline char *bh_kmap_irq(struct buffer_head *bh, unsigned long *flags)
+{
+ unsigned long addr;
+
+ __save_flags(*flags);
+
+ /*
+ * could be low
+ */
+ if (!PageHighMem(bh->b_page))
+ return bh->b_data;
+
+ /*
+ * it's a highmem page
+ */
+ __cli();
+ addr = (unsigned long) kmap_atomic(bh->b_page, KM_BH_IRQ);
+
+ if (addr & ~PAGE_MASK)
+ BUG();
+
+ return (char *) addr + bh_offset(bh);
+}
+
+static inline void bh_kunmap_irq(char *buffer, unsigned long *flags)
+{
+ unsigned long ptr = (unsigned long) buffer & PAGE_MASK;
+
+ kunmap_atomic((void *) ptr, KM_BH_IRQ);
+ __restore_flags(*flags);
+}
+
+#else /* CONFIG_HIGHMEM */
+
+static inline unsigned int nr_free_highpages(void) { return 0; }
+static inline void kmap_flush_unused(void) { }
+
+static inline void *kmap(struct page *page) { return page_address(page); }
+
+#define kunmap(page) do { } while (0)
+
+#define kmap_atomic(page,idx) kmap(page)
+#define kunmap_atomic(page,idx) kunmap(page)
+
+#define bh_kmap(bh) ((bh)->b_data)
+#define bh_kunmap(bh) do { } while (0)
+#define kmap_nonblock(page) kmap(page)
+#define bh_kmap_irq(bh, flags) ((bh)->b_data)
+#define bh_kunmap_irq(bh, flags) do { *(flags) = 0; } while (0)
+
+#endif /* CONFIG_HIGHMEM */
+
+/* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */
+static inline void clear_user_highpage(struct page *page, unsigned long vaddr)
+{
+ void *addr = kmap_atomic(page, KM_USER0);
+ clear_user_page(addr, vaddr);
+ kunmap_atomic(addr, KM_USER0);
+}
+
+static inline void clear_highpage(struct page *page)
+{
+ clear_page(kmap(page));
+ kunmap(page);
+}
+
+/*
+ * Same but also flushes aliased cache contents to RAM.
+ */
+static inline void memclear_highpage_flush(struct page *page, unsigned int
offset, unsigned int size)
+{
+ char *kaddr;
+
+ if (offset + size > PAGE_SIZE)
+ out_of_line_bug();
+ kaddr = kmap(page);
+ memset(kaddr + offset, 0, size);
+ flush_dcache_page(page);
+ flush_page_to_ram(page);
+ kunmap(page);
+}
+
+static inline void copy_user_highpage(struct page *to, struct page *from,
unsigned long vaddr)
+{
+ char *vfrom, *vto;
+
+ vfrom = kmap_atomic(from, KM_USER0);
+ vto = kmap_atomic(to, KM_USER1);
+ copy_user_page(vto, vfrom, vaddr);
+ kunmap_atomic(vfrom, KM_USER0);
+ kunmap_atomic(vto, KM_USER1);
+}
+
+static inline void copy_highpage(struct page *to, struct page *from)
+{
+ char *vfrom, *vto;
+
+ vfrom = kmap_atomic(from, KM_USER0);
+ vto = kmap_atomic(to, KM_USER1);
+ copy_page(vto, vfrom);
+ kunmap_atomic(vfrom, KM_USER0);
+ kunmap_atomic(vto, KM_USER1);
+}
+
+#endif /* _LINUX_HIGHMEM_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/drivers/netif/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/drivers/netif/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,10 @@
+
+O_TARGET := drv.o
+
+subdir-$(CONFIG_XEN_NETDEV_FRONTEND) += frontend
+obj-$(CONFIG_XEN_NETDEV_FRONTEND) += frontend/drv.o
+
+subdir-$(CONFIG_XEN_PHYSDEV_ACCESS) += backend
+obj-$(CONFIG_XEN_PHYSDEV_ACCESS) += backend/drv.o
+
+include $(TOPDIR)/Rules.make
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/acpi/tables.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/acpi/tables.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,615 @@
+/*
+ * acpi_tables.c - ACPI Boot-Time Table Parsing
+ *
+ * Copyright (C) 2001 Paul Diefenbaugh <paul.s.diefenbaugh@xxxxxxxxx>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ */
+
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/irq.h>
+#include <linux/errno.h>
+#include <linux/acpi.h>
+#include <linux/bootmem.h>
+
+#define PREFIX "ACPI: "
+
+#define ACPI_MAX_TABLES 256
+
+static char *acpi_table_signatures[ACPI_TABLE_COUNT] = {
+ [ACPI_TABLE_UNKNOWN] = "????",
+ [ACPI_APIC] = "APIC",
+ [ACPI_BOOT] = "BOOT",
+ [ACPI_DBGP] = "DBGP",
+ [ACPI_DSDT] = "DSDT",
+ [ACPI_ECDT] = "ECDT",
+ [ACPI_ETDT] = "ETDT",
+ [ACPI_FADT] = "FACP",
+ [ACPI_FACS] = "FACS",
+ [ACPI_OEMX] = "OEM",
+ [ACPI_PSDT] = "PSDT",
+ [ACPI_SBST] = "SBST",
+ [ACPI_SLIT] = "SLIT",
+ [ACPI_SPCR] = "SPCR",
+ [ACPI_SRAT] = "SRAT",
+ [ACPI_SSDT] = "SSDT",
+ [ACPI_SPMI] = "SPMI",
+ [ACPI_HPET] = "HPET",
+ [ACPI_MCFG] = "MCFG",
+};
+
+static char *mps_inti_flags_polarity[] = { "dfl", "high", "res", "low" };
+static char *mps_inti_flags_trigger[] = { "dfl", "edge", "res", "level" };
+
+/* System Description Table (RSDT/XSDT) */
+struct acpi_table_sdt {
+ unsigned long pa;
+ enum acpi_table_id id;
+ unsigned long size;
+} __attribute__ ((packed));
+
+static unsigned long sdt_pa; /* Physical Address */
+static unsigned long sdt_count; /* Table count */
+
+static struct acpi_table_sdt sdt_entry[ACPI_MAX_TABLES];
+
+void
+acpi_table_print (
+ struct acpi_table_header *header,
+ unsigned long phys_addr)
+{
+ char *name = NULL;
+
+ if (!header)
+ return;
+
+ /* Some table signatures aren't good table names */
+
+ if (!strncmp((char *) &header->signature,
+ acpi_table_signatures[ACPI_APIC],
+ sizeof(header->signature))) {
+ name = "MADT";
+ }
+ else if (!strncmp((char *) &header->signature,
+ acpi_table_signatures[ACPI_FADT],
+ sizeof(header->signature))) {
+ name = "FADT";
+ }
+ else
+ name = header->signature;
+
+ printk(KERN_DEBUG PREFIX "%.4s (v%3.3d %6.6s %8.8s 0x%08x %.4s 0x%08x)
@ 0x%p\n",
+ name, header->revision, header->oem_id,
+ header->oem_table_id, header->oem_revision,
+ header->asl_compiler_id, header->asl_compiler_revision,
+ (void *) phys_addr);
+}
+
+
+void
+acpi_table_print_madt_entry (
+ acpi_table_entry_header *header)
+{
+ if (!header)
+ return;
+
+ switch (header->type) {
+
+ case ACPI_MADT_LAPIC:
+ {
+ struct acpi_table_lapic *p =
+ (struct acpi_table_lapic*) header;
+ printk(KERN_INFO PREFIX "LAPIC (acpi_id[0x%02x]
lapic_id[0x%02x] %s)\n",
+ p->acpi_id, p->id,
p->flags.enabled?"enabled":"disabled");
+ }
+ break;
+
+ case ACPI_MADT_IOAPIC:
+ {
+ struct acpi_table_ioapic *p =
+ (struct acpi_table_ioapic*) header;
+ printk(KERN_INFO PREFIX "IOAPIC (id[0x%02x] address[0x%08x]
gsi_base[%d])\n",
+ p->id, p->address, p->global_irq_base);
+ }
+ break;
+
+ case ACPI_MADT_INT_SRC_OVR:
+ {
+ struct acpi_table_int_src_ovr *p =
+ (struct acpi_table_int_src_ovr*) header;
+ printk(KERN_INFO PREFIX "INT_SRC_OVR (bus %d bus_irq %d
global_irq %d %s %s)\n",
+ p->bus, p->bus_irq, p->global_irq,
+ mps_inti_flags_polarity[p->flags.polarity],
+ mps_inti_flags_trigger[p->flags.trigger]);
+ if(p->flags.reserved)
+ printk(KERN_INFO PREFIX "INT_SRC_OVR unexpected
reserved flags: 0x%x\n",
+ p->flags.reserved);
+
+ }
+ break;
+
+ case ACPI_MADT_NMI_SRC:
+ {
+ struct acpi_table_nmi_src *p =
+ (struct acpi_table_nmi_src*) header;
+ printk(KERN_INFO PREFIX "NMI_SRC (%s %s global_irq %d)\n",
+ mps_inti_flags_polarity[p->flags.polarity],
+ mps_inti_flags_trigger[p->flags.trigger],
p->global_irq);
+ }
+ break;
+
+ case ACPI_MADT_LAPIC_NMI:
+ {
+ struct acpi_table_lapic_nmi *p =
+ (struct acpi_table_lapic_nmi*) header;
+ printk(KERN_INFO PREFIX "LAPIC_NMI (acpi_id[0x%02x] %s %s
lint[0x%x])\n",
+ p->acpi_id,
+ mps_inti_flags_polarity[p->flags.polarity],
+ mps_inti_flags_trigger[p->flags.trigger], p->lint);
+ }
+ break;
+
+ case ACPI_MADT_LAPIC_ADDR_OVR:
+ {
+ struct acpi_table_lapic_addr_ovr *p =
+ (struct acpi_table_lapic_addr_ovr*) header;
+ printk(KERN_INFO PREFIX "LAPIC_ADDR_OVR (address[%p])\n",
+ (void *) (unsigned long) p->address);
+ }
+ break;
+
+ case ACPI_MADT_IOSAPIC:
+ {
+ struct acpi_table_iosapic *p =
+ (struct acpi_table_iosapic*) header;
+ printk(KERN_INFO PREFIX "IOSAPIC (id[0x%x] address[%p]
gsi_base[%d])\n",
+ p->id, (void *) (unsigned long) p->address,
p->global_irq_base);
+ }
+ break;
+
+ case ACPI_MADT_LSAPIC:
+ {
+ struct acpi_table_lsapic *p =
+ (struct acpi_table_lsapic*) header;
+ printk(KERN_INFO PREFIX "LSAPIC (acpi_id[0x%02x]
lsapic_id[0x%02x] lsapic_eid[0x%02x] %s)\n",
+ p->acpi_id, p->id, p->eid,
p->flags.enabled?"enabled":"disabled");
+ }
+ break;
+
+ case ACPI_MADT_PLAT_INT_SRC:
+ {
+ struct acpi_table_plat_int_src *p =
+ (struct acpi_table_plat_int_src*) header;
+ printk(KERN_INFO PREFIX "PLAT_INT_SRC (%s %s type[0x%x]
id[0x%04x] eid[0x%x] iosapic_vector[0x%x] global_irq[0x%x]\n",
+ mps_inti_flags_polarity[p->flags.polarity],
+ mps_inti_flags_trigger[p->flags.trigger],
+ p->type, p->id, p->eid, p->iosapic_vector,
p->global_irq);
+ }
+ break;
+
+ default:
+ printk(KERN_WARNING PREFIX "Found unsupported MADT entry (type
= 0x%x)\n",
+ header->type);
+ break;
+ }
+}
+
+
+static int
+acpi_table_compute_checksum (
+ void *table_pointer,
+ unsigned long length)
+{
+ u8 *p = (u8 *) table_pointer;
+ unsigned long remains = length;
+ unsigned long sum = 0;
+
+ if (!p || !length)
+ return -EINVAL;
+
+ while (remains--)
+ sum += *p++;
+
+ return (sum & 0xFF);
+}
+
+/*
+ * acpi_get_table_header_early()
+ * for acpi_blacklisted(), acpi_table_get_sdt()
+ */
+int __init
+acpi_get_table_header_early (
+ enum acpi_table_id id,
+ struct acpi_table_header **header)
+{
+ unsigned int i;
+ enum acpi_table_id temp_id;
+
+ /* DSDT is different from the rest */
+ if (id == ACPI_DSDT)
+ temp_id = ACPI_FADT;
+ else
+ temp_id = id;
+
+ /* Locate the table. */
+
+ for (i = 0; i < sdt_count; i++) {
+ if (sdt_entry[i].id != temp_id)
+ continue;
+ *header = (void *)
+ __acpi_map_table(sdt_entry[i].pa, sdt_entry[i].size);
+ if (!*header) {
+ printk(KERN_WARNING PREFIX "Unable to map %s\n",
+ acpi_table_signatures[temp_id]);
+ return -ENODEV;
+ }
+ break;
+ }
+
+ if (!*header) {
+ printk(KERN_WARNING PREFIX "%s not present\n",
+ acpi_table_signatures[id]);
+ return -ENODEV;
+ }
+
+ /* Map the DSDT header via the pointer in the FADT */
+ if (id == ACPI_DSDT) {
+ struct fadt_descriptor_rev2 *fadt = (struct
fadt_descriptor_rev2 *) *header;
+
+ if (fadt->revision == 3 && fadt->Xdsdt) {
+ *header = (void *) __acpi_map_table(fadt->Xdsdt,
+ sizeof(struct acpi_table_header));
+ } else if (fadt->V1_dsdt) {
+ *header = (void *) __acpi_map_table(fadt->V1_dsdt,
+ sizeof(struct acpi_table_header));
+ } else
+ *header = NULL;
+
+ if (!*header) {
+ printk(KERN_WARNING PREFIX "Unable to map DSDT\n");
+ return -ENODEV;
+ }
+ }
+
+ return 0;
+}
+
+
+int __init
+acpi_table_parse_madt_family (
+ enum acpi_table_id id,
+ unsigned long madt_size,
+ int entry_id,
+ acpi_madt_entry_handler handler,
+ unsigned int max_entries)
+{
+ void *madt = NULL;
+ acpi_table_entry_header *entry;
+ unsigned int count = 0;
+ unsigned long madt_end;
+ unsigned int i;
+
+ if (!handler)
+ return -EINVAL;
+
+ /* Locate the MADT (if exists). There should only be one. */
+
+ for (i = 0; i < sdt_count; i++) {
+ if (sdt_entry[i].id != id)
+ continue;
+ madt = (void *)
+ __acpi_map_table(sdt_entry[i].pa, sdt_entry[i].size);
+ if (!madt) {
+ printk(KERN_WARNING PREFIX "Unable to map %s\n",
+ acpi_table_signatures[id]);
+ return -ENODEV;
+ }
+ break;
+ }
+
+ if (!madt) {
+ printk(KERN_WARNING PREFIX "%s not present\n",
+ acpi_table_signatures[id]);
+ return -ENODEV;
+ }
+
+ madt_end = (unsigned long) madt + sdt_entry[i].size;
+
+ /* Parse all entries looking for a match. */
+
+ entry = (acpi_table_entry_header *)
+ ((unsigned long) madt + madt_size);
+
+ while (((unsigned long) entry) + sizeof(acpi_table_entry_header) <
madt_end) {
+ if (entry->type == entry_id &&
+ (!max_entries || count++ < max_entries))
+ if (handler(entry, madt_end))
+ return -EINVAL;
+
+ entry = (acpi_table_entry_header *)
+ ((unsigned long) entry + entry->length);
+ }
+ if (max_entries && count > max_entries) {
+ printk(KERN_WARNING PREFIX "[%s:0x%02x] ignored %i entries of "
+ "%i found\n", acpi_table_signatures[id], entry_id,
+ count - max_entries, count);
+ }
+
+ return count;
+}
+
+
+int __init
+acpi_table_parse_madt (
+ enum acpi_madt_entry_id id,
+ acpi_madt_entry_handler handler,
+ unsigned int max_entries)
+{
+ return acpi_table_parse_madt_family(ACPI_APIC, sizeof(struct
acpi_table_madt),
+ id, handler, max_entries);
+}
+
+
+int __init
+acpi_table_parse (
+ enum acpi_table_id id,
+ acpi_table_handler handler)
+{
+ int count = 0;
+ unsigned int i = 0;
+
+ if (!handler)
+ return -EINVAL;
+
+ for (i = 0; i < sdt_count; i++) {
+ if (sdt_entry[i].id != id)
+ continue;
+ count++;
+ if (count == 1)
+ handler(sdt_entry[i].pa, sdt_entry[i].size);
+
+ else
+ printk(KERN_WARNING PREFIX "%d duplicate %s table
ignored.\n",
+ count, acpi_table_signatures[id]);
+ }
+
+ return count;
+}
+
+
+static int __init
+acpi_table_get_sdt (
+ struct acpi_table_rsdp *rsdp)
+{
+ struct acpi_table_header *header = NULL;
+ unsigned int i, id = 0;
+
+ if (!rsdp)
+ return -EINVAL;
+
+ /* First check XSDT (but only on ACPI 2.0-compatible systems) */
+
+ if ((rsdp->revision >= 2) &&
+ (((struct acpi20_table_rsdp*)rsdp)->xsdt_address)) {
+
+ struct acpi_table_xsdt *mapped_xsdt = NULL;
+
+ sdt_pa = ((struct acpi20_table_rsdp*)rsdp)->xsdt_address;
+
+ /* map in just the header */
+ header = (struct acpi_table_header *)
+ __acpi_map_table(sdt_pa, sizeof(struct
acpi_table_header));
+
+ if (!header) {
+ printk(KERN_WARNING PREFIX "Unable to map XSDT
header\n");
+ return -ENODEV;
+ }
+
+ /* remap in the entire table before processing */
+ mapped_xsdt = (struct acpi_table_xsdt *)
+ __acpi_map_table(sdt_pa, header->length);
+ if (!mapped_xsdt) {
+ printk(KERN_WARNING PREFIX "Unable to map XSDT\n");
+ return -ENODEV;
+ }
+ header = &mapped_xsdt->header;
+
+ if (strncmp(header->signature, "XSDT", 4)) {
+ printk(KERN_WARNING PREFIX "XSDT signature
incorrect\n");
+ return -ENODEV;
+ }
+
+ if (acpi_table_compute_checksum(header, header->length)) {
+ printk(KERN_WARNING PREFIX "Invalid XSDT checksum\n");
+ return -ENODEV;
+ }
+
+ sdt_count = (header->length - sizeof(struct acpi_table_header))
>> 3;
+ if (sdt_count > ACPI_MAX_TABLES) {
+ printk(KERN_WARNING PREFIX "Truncated %lu XSDT
entries\n",
+ (sdt_count - ACPI_MAX_TABLES));
+ sdt_count = ACPI_MAX_TABLES;
+ }
+
+ for (i = 0; i < sdt_count; i++)
+ sdt_entry[i].pa = (unsigned long) mapped_xsdt->entry[i];
+ }
+
+ /* Then check RSDT */
+
+ else if (rsdp->rsdt_address) {
+
+ struct acpi_table_rsdt *mapped_rsdt = NULL;
+
+ sdt_pa = rsdp->rsdt_address;
+
+ /* map in just the header */
+ header = (struct acpi_table_header *)
+ __acpi_map_table(sdt_pa, sizeof(struct
acpi_table_header));
+ if (!header) {
+ printk(KERN_WARNING PREFIX "Unable to map RSDT
header\n");
+ return -ENODEV;
+ }
+
+ /* remap in the entire table before processing */
+ mapped_rsdt = (struct acpi_table_rsdt *)
+ __acpi_map_table(sdt_pa, header->length);
+ if (!mapped_rsdt) {
+ printk(KERN_WARNING PREFIX "Unable to map RSDT\n");
+ return -ENODEV;
+ }
+ header = &mapped_rsdt->header;
+
+ if (strncmp(header->signature, "RSDT", 4)) {
+ printk(KERN_WARNING PREFIX "RSDT signature
incorrect\n");
+ return -ENODEV;
+ }
+
+ if (acpi_table_compute_checksum(header, header->length)) {
+ printk(KERN_WARNING PREFIX "Invalid RSDT checksum\n");
+ return -ENODEV;
+ }
+
+ sdt_count = (header->length - sizeof(struct acpi_table_header))
>> 2;
+ if (sdt_count > ACPI_MAX_TABLES) {
+ printk(KERN_WARNING PREFIX "Truncated %lu RSDT
entries\n",
+ (sdt_count - ACPI_MAX_TABLES));
+ sdt_count = ACPI_MAX_TABLES;
+ }
+
+ for (i = 0; i < sdt_count; i++)
+ sdt_entry[i].pa = (unsigned long) mapped_rsdt->entry[i];
+ }
+
+ else {
+ printk(KERN_WARNING PREFIX "No System Description Table
(RSDT/XSDT) specified in RSDP\n");
+ return -ENODEV;
+ }
+
+ acpi_table_print(header, sdt_pa);
+
+ for (i = 0; i < sdt_count; i++) {
+
+ /* map in just the header */
+ header = (struct acpi_table_header *)
+ __acpi_map_table(sdt_entry[i].pa,
+ sizeof(struct acpi_table_header));
+ if (!header)
+ continue;
+
+ /* remap in the entire table before processing */
+ header = (struct acpi_table_header *)
+ __acpi_map_table(sdt_entry[i].pa,
+ header->length);
+ if (!header)
+ continue;
+
+ acpi_table_print(header, sdt_entry[i].pa);
+
+ if (acpi_table_compute_checksum(header, header->length)) {
+ printk(KERN_WARNING " >>> ERROR: Invalid checksum\n");
+ continue;
+ }
+
+ sdt_entry[i].size = header->length;
+
+ for (id = 0; id < ACPI_TABLE_COUNT; id++) {
+ if (!strncmp((char *) &header->signature,
+ acpi_table_signatures[id],
+ sizeof(header->signature))) {
+ sdt_entry[i].id = id;
+ }
+ }
+ }
+
+ /*
+ * The DSDT is *not* in the RSDT (why not? no idea.) but we want
+ * to print its info, because this is what people usually blacklist
+ * against. Unfortunately, we don't know the phys_addr, so just
+ * print 0. Maybe no one will notice.
+ */
+ if(!acpi_get_table_header_early(ACPI_DSDT, &header))
+ acpi_table_print(header, 0);
+
+ return 0;
+}
+
+/*
+ * acpi_table_init()
+ *
+ * find RSDP, find and checksum SDT/XSDT.
+ * checksum all tables, print SDT/XSDT
+ *
+ * result: sdt_entry[] is initialized
+ */
+#if CONFIG_XEN
+#define acpi_rsdp_phys_to_va(rsdp_phys) (__fix_to_virt(FIX_ACPI_RSDP_PAGE) + \
+ (rsdp_phys & ~PAGE_MASK))
+#else
+#define acpi_rsdp_phys_to_va(rsdp_phys) __va(rsdp_phys)
+#endif
+
+int __init
+acpi_table_init (void)
+{
+ struct acpi_table_rsdp *rsdp = NULL;
+ unsigned long rsdp_phys = 0;
+ int result = 0;
+
+ /* Locate and map the Root System Description Table (RSDP) */
+
+ rsdp_phys = acpi_find_rsdp();
+ if (!rsdp_phys) {
+ printk(KERN_ERR PREFIX "Unable to locate RSDP\n");
+ return -ENODEV;
+ }
+
+ rsdp = (struct acpi_table_rsdp *) acpi_rsdp_phys_to_va(rsdp_phys);
+ if (!rsdp) {
+ printk(KERN_WARNING PREFIX "Unable to map RSDP\n");
+ return -ENODEV;
+ }
+
+ printk(KERN_DEBUG PREFIX "RSDP (v%3.3d %6.6s
) @ 0x%p\n",
+ rsdp->revision, rsdp->oem_id, (void *) rsdp_phys);
+
+ if (rsdp->revision < 2)
+ result = acpi_table_compute_checksum(rsdp, sizeof(struct
acpi_table_rsdp));
+ else
+ result = acpi_table_compute_checksum(rsdp, ((struct
acpi20_table_rsdp *)rsdp)->length);
+
+ if (result) {
+ printk(KERN_WARNING " >>> ERROR: Invalid checksum\n");
+ return -ENODEV;
+ }
+
+ /* Locate and map the System Description table (RSDT/XSDT) */
+
+ if (acpi_table_get_sdt(rsdp))
+ return -ENODEV;
+
+ return 0;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/Makefile Fri Jul 15 13:39:50 2005
@@ -0,0 +1,14 @@
+
+
+obj-y += console/
+obj-y += evtchn/
+obj-y += balloon/
+obj-y += privcmd/
+obj-y += xenbus/
+
+obj-$(CONFIG_XEN_BLKDEV_BACKEND) += blkback/
+obj-$(CONFIG_XEN_NETDEV_BACKEND) += netback/
+obj-$(CONFIG_XEN_BLKDEV_FRONTEND) += blkfront/
+obj-$(CONFIG_XEN_NETDEV_FRONTEND) += netfront/
+obj-$(CONFIG_XEN_BLKDEV_TAP) += blktap/
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/pci.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/pci.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,283 @@
+#ifndef __i386_PCI_H
+#define __i386_PCI_H
+
+#include <linux/config.h>
+
+#ifdef __KERNEL__
+
+/* Can be used to override the logic in pci_scan_bus for skipping
+ already-configured bus numbers - to be used for buggy BIOSes
+ or architectures with incomplete PCI setup by the loader */
+
+#ifdef CONFIG_PCI
+extern unsigned int pcibios_assign_all_busses(void);
+#else
+#define pcibios_assign_all_busses() 0
+#endif
+#define pcibios_scan_all_fns() 0
+
+extern unsigned long pci_mem_start;
+#define PCIBIOS_MIN_IO 0x1000
+#define PCIBIOS_MIN_MEM (pci_mem_start)
+
+void pcibios_config_init(void);
+struct pci_bus * pcibios_scan_root(int bus);
+extern int (*pci_config_read)(int seg, int bus, int dev, int fn, int reg, int
len, u32 *value);
+extern int (*pci_config_write)(int seg, int bus, int dev, int fn, int reg, int
len, u32 value);
+
+void pcibios_set_master(struct pci_dev *dev);
+void pcibios_penalize_isa_irq(int irq);
+struct irq_routing_table *pcibios_get_irq_routing_table(void);
+int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq);
+
+/* Dynamic DMA mapping stuff.
+ * i386 has everything mapped statically.
+ */
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <asm/scatterlist.h>
+#include <linux/string.h>
+#include <asm/io.h>
+
+struct pci_dev;
+
+/* The networking and block device layers use this boolean for bounce
+ * buffer decisions.
+ */
+#define PCI_DMA_BUS_IS_PHYS (0)
+
+/* Allocate and map kernel buffer using consistent mode DMA for a device.
+ * hwdev should be valid struct pci_dev pointer for PCI devices,
+ * NULL for PCI-like buses (ISA, EISA).
+ * Returns non-NULL cpu-view pointer to the buffer if successful and
+ * sets *dma_addrp to the pci side dma address as well, else *dma_addrp
+ * is undefined.
+ */
+extern void *pci_alloc_consistent(struct pci_dev *hwdev, size_t size,
+ dma_addr_t *dma_handle);
+
+/* Free and unmap a consistent DMA buffer.
+ * cpu_addr is what was returned from pci_alloc_consistent,
+ * size must be the same as what as passed into pci_alloc_consistent,
+ * and likewise dma_addr must be the same as what *dma_addrp was set to.
+ *
+ * References to the memory and mappings associated with cpu_addr/dma_addr
+ * past this call are illegal.
+ */
+extern void pci_free_consistent(struct pci_dev *hwdev, size_t size,
+ void *vaddr, dma_addr_t dma_handle);
+
+/* Map a single buffer of the indicated size for DMA in streaming mode.
+ * The 32-bit bus address to use is returned.
+ *
+ * Once the device is given the dma address, the device owns this memory
+ * until either pci_unmap_single or pci_dma_sync_single is performed.
+ */
+static inline dma_addr_t pci_map_single(struct pci_dev *hwdev, void *ptr,
+ size_t size, int direction)
+{
+ if (direction == PCI_DMA_NONE)
+ out_of_line_bug();
+ flush_write_buffers();
+ return virt_to_bus(ptr);
+}
+
+/* Unmap a single streaming mode DMA translation. The dma_addr and size
+ * must match what was provided for in a previous pci_map_single call. All
+ * other usages are undefined.
+ *
+ * After this call, reads by the cpu to the buffer are guarenteed to see
+ * whatever the device wrote there.
+ */
+static inline void pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr,
+ size_t size, int direction)
+{
+ if (direction == PCI_DMA_NONE)
+ out_of_line_bug();
+ /* Nothing to do */
+}
+
+/*
+ * pci_{map,unmap}_single_page maps a kernel page to a dma_addr_t. identical
+ * to pci_map_single, but takes a struct page instead of a virtual address
+ */
+static inline dma_addr_t pci_map_page(struct pci_dev *hwdev, struct page *page,
+ unsigned long offset, size_t size, int
direction)
+{
+ if (direction == PCI_DMA_NONE)
+ out_of_line_bug();
+
+ return page_to_bus(page) + offset;
+}
+
+static inline void pci_unmap_page(struct pci_dev *hwdev, dma_addr_t
dma_address,
+ size_t size, int direction)
+{
+ if (direction == PCI_DMA_NONE)
+ out_of_line_bug();
+ /* Nothing to do */
+}
+
+/* pci_unmap_{page,single} is a nop so... */
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)
+#define pci_unmap_addr(PTR, ADDR_NAME) (0)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0)
+#define pci_unmap_len(PTR, LEN_NAME) (0)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL) do { } while (0)
+
+/* Map a set of buffers described by scatterlist in streaming
+ * mode for DMA. This is the scather-gather version of the
+ * above pci_map_single interface. Here the scatter gather list
+ * elements are each tagged with the appropriate dma address
+ * and length. They are obtained via sg_dma_{address,length}(SG).
+ *
+ * NOTE: An implementation may be able to use a smaller number of
+ * DMA address/length pairs than there are SG table elements.
+ * (for example via virtual mapping capabilities)
+ * The routine returns the number of addr/length pairs actually
+ * used, at most nents.
+ *
+ * Device ownership issues as mentioned above for pci_map_single are
+ * the same here.
+ */
+static inline int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg,
+ int nents, int direction)
+{
+ int i;
+
+ if (direction == PCI_DMA_NONE)
+ out_of_line_bug();
+
+ /*
+ * temporary 2.4 hack
+ */
+ for (i = 0; i < nents; i++ ) {
+ if (sg[i].address && sg[i].page)
+ out_of_line_bug();
+ else if (!sg[i].address && !sg[i].page)
+ out_of_line_bug();
+
+ if (sg[i].address)
+ sg[i].dma_address = virt_to_bus(sg[i].address);
+ else
+ sg[i].dma_address = page_to_bus(sg[i].page) +
sg[i].offset;
+ }
+
+ flush_write_buffers();
+ return nents;
+}
+
+/* Unmap a set of streaming mode DMA translations.
+ * Again, cpu read rules concerning calls here are the same as for
+ * pci_unmap_single() above.
+ */
+static inline void pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg,
+ int nents, int direction)
+{
+ if (direction == PCI_DMA_NONE)
+ out_of_line_bug();
+ /* Nothing to do */
+}
+
+/* Make physical memory consistent for a single
+ * streaming mode DMA translation after a transfer.
+ *
+ * If you perform a pci_map_single() but wish to interrogate the
+ * buffer using the cpu, yet do not wish to teardown the PCI dma
+ * mapping, you must call this function before doing so. At the
+ * next point you give the PCI dma address back to the card, the
+ * device again owns the buffer.
+ */
+static inline void pci_dma_sync_single(struct pci_dev *hwdev,
+ dma_addr_t dma_handle,
+ size_t size, int direction)
+{
+ if (direction == PCI_DMA_NONE)
+ out_of_line_bug();
+ flush_write_buffers();
+}
+
+/* Make physical memory consistent for a set of streaming
+ * mode DMA translations after a transfer.
+ *
+ * The same as pci_dma_sync_single but for a scatter-gather list,
+ * same rules and usage.
+ */
+static inline void pci_dma_sync_sg(struct pci_dev *hwdev,
+ struct scatterlist *sg,
+ int nelems, int direction)
+{
+ if (direction == PCI_DMA_NONE)
+ out_of_line_bug();
+ flush_write_buffers();
+}
+
+/* Return whether the given PCI device DMA address mask can
+ * be supported properly. For example, if your device can
+ * only drive the low 24-bits during PCI bus mastering, then
+ * you would pass 0x00ffffff as the mask to this function.
+ */
+static inline int pci_dma_supported(struct pci_dev *hwdev, u64 mask)
+{
+ /*
+ * we fall back to GFP_DMA when the mask isn't all 1s,
+ * so we can't guarantee allocations that must be
+ * within a tighter range than GFP_DMA..
+ */
+ if(mask < 0x00ffffff)
+ return 0;
+
+ return 1;
+}
+
+/* This is always fine. */
+#define pci_dac_dma_supported(pci_dev, mask) (1)
+
+static __inline__ dma64_addr_t
+pci_dac_page_to_dma(struct pci_dev *pdev, struct page *page, unsigned long
offset, int direction)
+{
+ return ((dma64_addr_t) page_to_bus(page) +
+ (dma64_addr_t) offset);
+}
+
+static __inline__ struct page *
+pci_dac_dma_to_page(struct pci_dev *pdev, dma64_addr_t dma_addr)
+{
+ return bus_to_page(dma_addr);
+}
+
+static __inline__ unsigned long
+pci_dac_dma_to_offset(struct pci_dev *pdev, dma64_addr_t dma_addr)
+{
+ return (dma_addr & ~PAGE_MASK);
+}
+
+static __inline__ void
+pci_dac_dma_sync_single(struct pci_dev *pdev, dma64_addr_t dma_addr, size_t
len, int direction)
+{
+ flush_write_buffers();
+}
+
+/* These macros should be used after a pci_map_sg call has been done
+ * to get bus addresses of each of the SG entries and their lengths.
+ * You should only work with the number of sg entries pci_map_sg
+ * returns.
+ */
+#define sg_dma_address(sg) ((sg)->dma_address)
+#define sg_dma_len(sg) ((sg)->length)
+
+/* Return the index of the PCI controller for device. */
+static inline int pci_controller_num(struct pci_dev *dev)
+{
+ return 0;
+}
+
+#define HAVE_PCI_MMAP
+extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+ enum pci_mmap_state mmap_state, int
write_combine);
+
+#endif /* __KERNEL__ */
+
+#endif /* __i386_PCI_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/netback/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/netback/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,2 @@
+
+obj-y := netback.o control.o interface.o loopback.o
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/segment.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/segment.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,47 @@
+#ifndef _ASM_SEGMENT_H
+#define _ASM_SEGMENT_H
+
+#include <asm/cache.h>
+
+#define __KERNEL_CS 0x10
+#define __KERNEL_DS 0x1b
+
+#define __KERNEL32_CS 0x3b
+
+/*
+ * we cannot use the same code segment descriptor for user and kernel
+ * -- not even in the long flat mode, because of different DPL /kkeil
+ * The segment offset needs to contain a RPL. Grr. -AK
+ * GDT layout to get 64bit syscall right (sysret hardcodes gdt offsets)
+ */
+
+#define __USER32_CS 0x23 /* 4*8+3 */
+#define __USER_DS 0x2b /* 5*8+3 */
+#define __USER_CS 0x33 /* 6*8+3 */
+#define __USER32_DS __USER_DS
+#define __KERNEL16_CS (GDT_ENTRY_KERNELCS16 * 8)
+#define __KERNEL_COMPAT32_CS 0x8
+
+#define GDT_ENTRY_TLS 1
+#define GDT_ENTRY_TSS 8 /* needs two entries */
+#define GDT_ENTRY_LDT 10
+#define GDT_ENTRY_TLS_MIN 11
+#define GDT_ENTRY_TLS_MAX 13
+/* 14 free */
+#define GDT_ENTRY_KERNELCS16 15
+
+#define GDT_ENTRY_TLS_ENTRIES 3
+
+/* TLS indexes for 64bit - hardcoded in arch_prctl */
+#define FS_TLS 0
+#define GS_TLS 1
+
+#define GS_TLS_SEL ((GDT_ENTRY_TLS_MIN+GS_TLS)*8 + 3)
+#define FS_TLS_SEL ((GDT_ENTRY_TLS_MIN+FS_TLS)*8 + 3)
+
+#define IDT_ENTRIES 256
+#define GDT_ENTRIES 16
+#define GDT_SIZE (GDT_ENTRIES * 8)
+#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8)
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/kernel/pci-pc.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/kernel/pci-pc.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,260 @@
+/*
+ * Low-Level PCI Support for PC
+ *
+ * (c) 1999--2000 Martin Mares <mj@xxxxxx>
+ *
+ * Adjusted to use Xen's interface by Rolf Neugebauer, Intel Research Cambridge
+ * Further modifications by Keir Fraser, University of Cambridge
+ */
+
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/ioport.h>
+
+#include <asm/segment.h>
+#include <asm/io.h>
+
+#include <asm-xen/xen-public/xen.h>
+#include <asm-xen/xen-public/physdev.h>
+
+#include "pci-i386.h"
+
+/*
+ * NB. The following interface functions are not included here:
+ * 1. void eisa_set_level_irq(unsigned int irq)
+ * 2. irq_routing_table * __devinit pcibios_get_irq_routing_table(void)
+ * 3. int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq)
+ * All are used by the ACPI driver. This should be ported to Xen if it is
+ * ever required -- Xen is the ultimate source for IRQ-routing knowledge.
+ */
+
+struct pci_ops *pci_root_ops = NULL;
+
+int (*pci_config_read)(int seg, int bus, int dev, int fn,
+ int reg, int len, u32 *value) = NULL;
+int (*pci_config_write)(int seg, int bus, int dev, int fn,
+ int reg, int len, u32 value) = NULL;
+
+unsigned int pci_probe = PCI_PROBE_BIOS;
+
+struct pci_fixup pcibios_fixups[] = { { 0 } };
+
+static int pci_confx_read(int seg, int bus, int dev, int fn, int reg,
+ int len, u32 *value)
+{
+ int ret;
+ physdev_op_t op;
+
+ if (bus > 255 || dev > 31 || fn > 7 || reg > 255)
+ return -EINVAL;
+
+ op.cmd = PHYSDEVOP_PCI_CFGREG_READ;
+ op.u.pci_cfgreg_read.bus = bus;
+ op.u.pci_cfgreg_read.dev = dev;
+ op.u.pci_cfgreg_read.func = fn;
+ op.u.pci_cfgreg_read.reg = reg;
+ op.u.pci_cfgreg_read.len = len;
+
+ if ( (ret = HYPERVISOR_physdev_op(&op)) != 0 )
+ return ret;
+
+ *value = op.u.pci_cfgreg_read.value;
+
+ return 0;
+}
+
+static int pci_confx_write(int seg, int bus, int dev, int fn, int reg,
+ int len, u32 value)
+{
+ int ret;
+ physdev_op_t op;
+
+ if ((bus > 255 || dev > 31 || fn > 7 || reg > 255))
+ return -EINVAL;
+
+ op.cmd = PHYSDEVOP_PCI_CFGREG_WRITE;
+ op.u.pci_cfgreg_write.bus = bus;
+ op.u.pci_cfgreg_write.dev = dev;
+ op.u.pci_cfgreg_write.func = fn;
+ op.u.pci_cfgreg_write.reg = reg;
+ op.u.pci_cfgreg_write.len = len;
+ op.u.pci_cfgreg_write.value = value;
+
+ if ( (ret = HYPERVISOR_physdev_op(&op)) != 0 )
+ return ret;
+ return 0;
+}
+
+
+static int pci_confx_read_config_byte(struct pci_dev *dev,
+ int where, u8 *value)
+{
+ int result;
+ u32 data;
+
+ result = pci_confx_read(0, dev->bus->number, PCI_SLOT(dev->devfn),
+ PCI_FUNC(dev->devfn), where, 1, &data);
+
+ *value = (u8)data;
+
+ return result;
+}
+
+static int pci_confx_read_config_word(struct pci_dev *dev,
+ int where, u16 *value)
+{
+ int result;
+ u32 data;
+
+ result = pci_confx_read(0, dev->bus->number, PCI_SLOT(dev->devfn),
+ PCI_FUNC(dev->devfn), where, 2, &data);
+
+ *value = (u16)data;
+
+ return result;
+}
+
+static int pci_confx_read_config_dword(struct pci_dev *dev,
+ int where, u32 *value)
+{
+ return pci_confx_read(0, dev->bus->number, PCI_SLOT(dev->devfn),
+ PCI_FUNC(dev->devfn), where, 4, value);
+}
+
+static int pci_confx_write_config_byte(struct pci_dev *dev,
+ int where, u8 value)
+{
+ return pci_confx_write(0, dev->bus->number, PCI_SLOT(dev->devfn),
+ PCI_FUNC(dev->devfn), where, 1, value);
+}
+
+static int pci_confx_write_config_word(struct pci_dev *dev,
+ int where, u16 value)
+{
+ return pci_confx_write(0, dev->bus->number, PCI_SLOT(dev->devfn),
+ PCI_FUNC(dev->devfn), where, 2, value);
+}
+
+static int pci_confx_write_config_dword(struct pci_dev *dev,
+ int where, u32 value)
+{
+ return pci_confx_write(0, dev->bus->number, PCI_SLOT(dev->devfn),
+ PCI_FUNC(dev->devfn), where, 4, value);
+}
+
+static struct pci_ops pci_conf_xen = {
+ pci_confx_read_config_byte,
+ pci_confx_read_config_word,
+ pci_confx_read_config_dword,
+ pci_confx_write_config_byte,
+ pci_confx_write_config_word,
+ pci_confx_write_config_dword
+};
+
+void pcibios_penalize_isa_irq(int irq)
+{
+ /* nothing */
+}
+
+void __devinit pcibios_fixup_bus(struct pci_bus *b)
+{
+ pci_read_bridge_bases(b);
+}
+
+struct pci_bus * __devinit pcibios_scan_root(int busnum)
+{
+ struct list_head *list;
+ struct pci_bus *bus;
+
+ list_for_each ( list, &pci_root_buses )
+ {
+ bus = pci_bus_b(list);
+ if ( bus->number == busnum )
+ return bus;
+ }
+
+ printk("PCI: Probing PCI hardware (bus %02x)\n", busnum);
+ return pci_scan_bus(busnum, pci_root_ops, NULL);
+}
+
+void __init pcibios_init(void)
+{
+ int bus;
+ physdev_op_t op;
+
+ if ( !pci_probe )
+ return;
+
+ pci_root_ops = &pci_conf_xen;
+ pci_config_read = pci_confx_read;
+ pci_config_write = pci_confx_write;
+
+ pcibios_set_cacheline_size();
+
+ op.cmd = PHYSDEVOP_PCI_PROBE_ROOT_BUSES;
+ if ( HYPERVISOR_physdev_op(&op) != 0 )
+ {
+ printk(KERN_WARNING "PCI: System does not support PCI\n");
+ return;
+ }
+
+ printk(KERN_INFO "PCI: Probing PCI hardware\n");
+ for ( bus = 0; bus < 256; bus++ )
+ if ( test_bit(bus, &op.u.pci_probe_root_buses.busmask[0]) )
+ (void)pcibios_scan_root(bus);
+
+ pcibios_resource_survey();
+}
+
+char * __devinit pcibios_setup(char *str)
+{
+ if ( !strcmp(str, "off") )
+ pci_probe = 0;
+ return NULL;
+}
+
+unsigned int pcibios_assign_all_busses(void)
+{
+ return 0;
+}
+
+int pcibios_enable_device(struct pci_dev *dev, int mask)
+{
+ int err;
+ u8 pin;
+ physdev_op_t op;
+
+ /* Inform Xen that we are going to use this device. */
+ op.cmd = PHYSDEVOP_PCI_INITIALISE_DEVICE;
+ op.u.pci_initialise_device.bus = dev->bus->number;
+ op.u.pci_initialise_device.dev = PCI_SLOT(dev->devfn);
+ op.u.pci_initialise_device.func = PCI_FUNC(dev->devfn);
+ if ( (err = HYPERVISOR_physdev_op(&op)) != 0 )
+ return err;
+
+ /* Now we can bind to the very final IRQ line. */
+ pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &pin);
+ dev->irq = pin;
+
+ /* Turn on device I/O and memory access as necessary. */
+ if ( (err = pcibios_enable_resources(dev, mask)) < 0 )
+ return err;
+
+ /* Sanity-check that an interrupt-producing device is routed to an IRQ. */
+ pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+ if ( pin != 0 )
+ {
+ if ( dev->irq != 0 )
+ printk(KERN_INFO "PCI: Obtained IRQ %d for device %s\n",
+ dev->irq, dev->slot_name);
+ else
+ printk(KERN_WARNING "PCI: No IRQ known for interrupt pin %c of "
+ "device %s.\n", 'A' + pin - 1, dev->slot_name);
+ }
+
+ return 0;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/linux/sched.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/linux/sched.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,971 @@
+#ifndef _LINUX_SCHED_H
+#define _LINUX_SCHED_H
+
+#include <asm/param.h> /* for HZ */
+
+extern unsigned long event;
+
+#include <linux/config.h>
+#include <linux/binfmts.h>
+#include <linux/threads.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/times.h>
+#include <linux/timex.h>
+#include <linux/rbtree.h>
+
+#include <asm/system.h>
+#include <asm/semaphore.h>
+#include <asm/page.h>
+#include <asm/ptrace.h>
+#include <asm/mmu.h>
+
+#include <linux/smp.h>
+#include <linux/tty.h>
+#include <linux/sem.h>
+#include <linux/signal.h>
+#include <linux/securebits.h>
+#include <linux/fs_struct.h>
+
+struct exec_domain;
+
+/*
+ * cloning flags:
+ */
+#define CSIGNAL 0x000000ff /* signal mask to be sent at
exit */
+#define CLONE_VM 0x00000100 /* set if VM shared between processes */
+#define CLONE_FS 0x00000200 /* set if fs info shared between
processes */
+#define CLONE_FILES 0x00000400 /* set if open files shared between
processes */
+#define CLONE_SIGHAND 0x00000800 /* set if signal handlers and blocked
signals shared */
+#define CLONE_PID 0x00001000 /* set if pid shared */
+#define CLONE_PTRACE 0x00002000 /* set if we want to let tracing
continue on the child too */
+#define CLONE_VFORK 0x00004000 /* set if the parent wants the child to
wake it up on mm_release */
+#define CLONE_PARENT 0x00008000 /* set if we want to have the same
parent as the cloner */
+#define CLONE_THREAD 0x00010000 /* Same thread group? */
+#define CLONE_NEWNS 0x00020000 /* New namespace group? */
+
+#define CLONE_SIGNAL (CLONE_SIGHAND | CLONE_THREAD)
+
+/*
+ * These are the constant used to fake the fixed-point load-average
+ * counting. Some notes:
+ * - 11 bit fractions expand to 22 bits by the multiplies: this gives
+ * a load-average precision of 10 bits integer + 11 bits fractional
+ * - if you want to count load-averages more often, you need more
+ * precision, or rounding will get you. With 2-second counting freq,
+ * the EXP_n values would be 1981, 2034 and 2043 if still using only
+ * 11 bit fractions.
+ */
+extern unsigned long avenrun[]; /* Load averages */
+
+#define FSHIFT 11 /* nr of bits of precision */
+#define FIXED_1 (1<<FSHIFT) /* 1.0 as fixed-point */
+#define LOAD_FREQ (5*HZ) /* 5 sec intervals */
+#define EXP_1 1884 /* 1/exp(5sec/1min) as fixed-point */
+#define EXP_5 2014 /* 1/exp(5sec/5min) */
+#define EXP_15 2037 /* 1/exp(5sec/15min) */
+
+#define CALC_LOAD(load,exp,n) \
+ load *= exp; \
+ load += n*(FIXED_1-exp); \
+ load >>= FSHIFT;
+
+#define CT_TO_SECS(x) ((x) / HZ)
+#define CT_TO_USECS(x) (((x) % HZ) * 1000000/HZ)
+
+extern int nr_running, nr_threads;
+extern int last_pid;
+
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/param.h>
+#include <linux/resource.h>
+#ifdef __KERNEL__
+#include <linux/timer.h>
+#endif
+
+#include <asm/processor.h>
+
+#define TASK_RUNNING 0
+#define TASK_INTERRUPTIBLE 1
+#define TASK_UNINTERRUPTIBLE 2
+#define TASK_ZOMBIE 4
+#define TASK_STOPPED 8
+
+#define __set_task_state(tsk, state_value) \
+ do { (tsk)->state = (state_value); } while (0)
+#define set_task_state(tsk, state_value) \
+ set_mb((tsk)->state, (state_value))
+
+#define __set_current_state(state_value) \
+ do { current->state = (state_value); } while (0)
+#define set_current_state(state_value) \
+ set_mb(current->state, (state_value))
+
+/*
+ * Scheduling policies
+ */
+#define SCHED_OTHER 0
+#define SCHED_FIFO 1
+#define SCHED_RR 2
+
+/*
+ * This is an additional bit set when we want to
+ * yield the CPU for one re-schedule..
+ */
+#define SCHED_YIELD 0x10
+
+struct sched_param {
+ int sched_priority;
+};
+
+struct completion;
+
+#ifdef __KERNEL__
+
+#include <linux/spinlock.h>
+
+/*
+ * This serializes "schedule()" and also protects
+ * the run-queue from deletions/modifications (but
+ * _adding_ to the beginning of the run-queue has
+ * a separate lock).
+ */
+extern rwlock_t tasklist_lock;
+extern spinlock_t runqueue_lock;
+extern spinlock_t mmlist_lock;
+
+extern void sched_init(void);
+extern void init_idle(void);
+extern void show_state(void);
+extern void cpu_init (void);
+extern void trap_init(void);
+extern void update_process_times(int user);
+#ifdef CONFIG_NO_IDLE_HZ
+extern void update_process_times_us(int user, int system);
+#endif
+extern void update_one_process(struct task_struct *p, unsigned long user,
+ unsigned long system, int cpu);
+
+#define MAX_SCHEDULE_TIMEOUT LONG_MAX
+extern signed long FASTCALL(schedule_timeout(signed long timeout));
+asmlinkage void schedule(void);
+
+extern int schedule_task(struct tq_struct *task);
+extern void flush_scheduled_tasks(void);
+extern int start_context_thread(void);
+extern int current_is_keventd(void);
+
+#if CONFIG_SMP
+extern void set_cpus_allowed(struct task_struct *p, unsigned long new_mask);
+#else
+# define set_cpus_allowed(p, new_mask) do { } while (0)
+#endif
+
+/*
+ * The default fd array needs to be at least BITS_PER_LONG,
+ * as this is the granularity returned by copy_fdset().
+ */
+#define NR_OPEN_DEFAULT BITS_PER_LONG
+
+struct namespace;
+/*
+ * Open file table structure
+ */
+struct files_struct {
+ atomic_t count;
+ rwlock_t file_lock; /* Protects all the below members. Nests
inside tsk->alloc_lock */
+ int max_fds;
+ int max_fdset;
+ int next_fd;
+ struct file ** fd; /* current fd array */
+ fd_set *close_on_exec;
+ fd_set *open_fds;
+ fd_set close_on_exec_init;
+ fd_set open_fds_init;
+ struct file * fd_array[NR_OPEN_DEFAULT];
+};
+
+#define INIT_FILES \
+{ \
+ count: ATOMIC_INIT(1), \
+ file_lock: RW_LOCK_UNLOCKED, \
+ max_fds: NR_OPEN_DEFAULT, \
+ max_fdset: __FD_SETSIZE, \
+ next_fd: 0, \
+ fd: &init_files.fd_array[0], \
+ close_on_exec: &init_files.close_on_exec_init, \
+ open_fds: &init_files.open_fds_init, \
+ close_on_exec_init: { { 0, } }, \
+ open_fds_init: { { 0, } }, \
+ fd_array: { NULL, } \
+}
+
+/* Maximum number of active map areas.. This is a random (large) number */
+#define DEFAULT_MAX_MAP_COUNT (65536)
+
+extern int max_map_count;
+
+struct mm_struct {
+ struct vm_area_struct * mmap; /* list of VMAs */
+ rb_root_t mm_rb;
+ struct vm_area_struct * mmap_cache; /* last find_vma result */
+ pgd_t * pgd;
+ atomic_t mm_users; /* How many users with user
space? */
+ atomic_t mm_count; /* How many references to
"struct mm_struct" (users count as 1) */
+ int map_count; /* number of VMAs */
+ struct rw_semaphore mmap_sem;
+ spinlock_t page_table_lock; /* Protects task page tables
and mm->rss */
+
+ struct list_head mmlist; /* List of all active mm's.
These are globally strung
+ * together off init_mm.mmlist,
and are protected
+ * by mmlist_lock
+ */
+
+ unsigned long start_code, end_code, start_data, end_data;
+ unsigned long start_brk, brk, start_stack;
+ unsigned long arg_start, arg_end, env_start, env_end;
+ unsigned long rss, total_vm, locked_vm;
+ unsigned long def_flags;
+ unsigned long cpu_vm_mask;
+ unsigned long swap_address;
+
+ unsigned dumpable:1;
+
+ /* Architecture-specific MM context */
+ mm_context_t context;
+};
+
+extern int mmlist_nr;
+
+#define INIT_MM(name) \
+{ \
+ mm_rb: RB_ROOT, \
+ pgd: swapper_pg_dir, \
+ mm_users: ATOMIC_INIT(2), \
+ mm_count: ATOMIC_INIT(1), \
+ mmap_sem: __RWSEM_INITIALIZER(name.mmap_sem), \
+ page_table_lock: SPIN_LOCK_UNLOCKED, \
+ mmlist: LIST_HEAD_INIT(name.mmlist), \
+}
+
+struct signal_struct {
+ atomic_t count;
+ struct k_sigaction action[_NSIG];
+ spinlock_t siglock;
+};
+
+
+#define INIT_SIGNALS { \
+ count: ATOMIC_INIT(1), \
+ action: { {{0,}}, }, \
+ siglock: SPIN_LOCK_UNLOCKED \
+}
+
+/*
+ * Some day this will be a full-fledged user tracking system..
+ */
+struct user_struct {
+ atomic_t __count; /* reference count */
+ atomic_t processes; /* How many processes does this user have? */
+ atomic_t files; /* How many open files does this user have? */
+
+ /* Hash table maintenance information */
+ struct user_struct *next, **pprev;
+ uid_t uid;
+};
+
+#define get_current_user() ({ \
+ struct user_struct *__tmp_user = current->user; \
+ atomic_inc(&__tmp_user->__count); \
+ __tmp_user; })
+
+extern struct user_struct root_user;
+#define INIT_USER (&root_user)
+
+struct task_struct {
+ /*
+ * offsets of these are hardcoded elsewhere - touch with care
+ */
+ volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */
+ unsigned long flags; /* per process flags, defined below */
+ int sigpending;
+ mm_segment_t addr_limit; /* thread address space:
+ 0-0xBFFFFFFF for user-thead
+ 0-0xFFFFFFFF for kernel-thread
+ */
+ struct exec_domain *exec_domain;
+ volatile long need_resched;
+ unsigned long ptrace;
+
+ int lock_depth; /* Lock depth */
+
+/*
+ * offset 32 begins here on 32-bit platforms. We keep
+ * all fields in a single cacheline that are needed for
+ * the goodness() loop in schedule().
+ */
+ long counter;
+ long nice;
+ unsigned long policy;
+ struct mm_struct *mm;
+ int processor;
+ /*
+ * cpus_runnable is ~0 if the process is not running on any
+ * CPU. It's (1 << cpu) if it's running on a CPU. This mask
+ * is updated under the runqueue lock.
+ *
+ * To determine whether a process might run on a CPU, this
+ * mask is AND-ed with cpus_allowed.
+ */
+ unsigned long cpus_runnable, cpus_allowed;
+ /*
+ * (only the 'next' pointer fits into the cacheline, but
+ * that's just fine.)
+ */
+ struct list_head run_list;
+ unsigned long sleep_time;
+
+ struct task_struct *next_task, *prev_task;
+ struct mm_struct *active_mm;
+ struct list_head local_pages;
+ unsigned int allocation_order, nr_local_pages;
+
+/* task state */
+ struct linux_binfmt *binfmt;
+ int exit_code, exit_signal;
+ int pdeath_signal; /* The signal sent when the parent dies */
+ /* ??? */
+ unsigned long personality;
+ int did_exec:1;
+ unsigned task_dumpable:1;
+ pid_t pid;
+ pid_t pgrp;
+ pid_t tty_old_pgrp;
+ pid_t session;
+ pid_t tgid;
+ /* boolean value for session group leader */
+ int leader;
+ /*
+ * pointers to (original) parent process, youngest child, younger
sibling,
+ * older sibling, respectively. (p->father can be replaced with
+ * p->p_pptr->pid)
+ */
+ struct task_struct *p_opptr, *p_pptr, *p_cptr, *p_ysptr, *p_osptr;
+ struct list_head thread_group;
+
+ /* PID hash table linkage. */
+ struct task_struct *pidhash_next;
+ struct task_struct **pidhash_pprev;
+
+ wait_queue_head_t wait_chldexit; /* for wait4() */
+ struct completion *vfork_done; /* for vfork() */
+ unsigned long rt_priority;
+ unsigned long it_real_value, it_prof_value, it_virt_value;
+ unsigned long it_real_incr, it_prof_incr, it_virt_incr;
+ struct timer_list real_timer;
+ struct tms times;
+ unsigned long start_time;
+ long per_cpu_utime[NR_CPUS], per_cpu_stime[NR_CPUS];
+/* mm fault and swap info: this can arguably be seen as either mm-specific or
thread-specific */
+ unsigned long min_flt, maj_flt, nswap, cmin_flt, cmaj_flt, cnswap;
+ int swappable:1;
+/* process credentials */
+ uid_t uid,euid,suid,fsuid;
+ gid_t gid,egid,sgid,fsgid;
+ int ngroups;
+ gid_t groups[NGROUPS];
+ kernel_cap_t cap_effective, cap_inheritable, cap_permitted;
+ int keep_capabilities:1;
+ struct user_struct *user;
+/* limits */
+ struct rlimit rlim[RLIM_NLIMITS];
+ unsigned short used_math;
+ char comm[16];
+/* file system info */
+ int link_count, total_link_count;
+ struct tty_struct *tty; /* NULL if no tty */
+ unsigned int locks; /* How many file locks are being held */
+/* ipc stuff */
+ struct sem_undo *semundo;
+ struct sem_queue *semsleeping;
+/* CPU-specific state of this task */
+ struct thread_struct thread;
+/* filesystem information */
+ struct fs_struct *fs;
+/* open file information */
+ struct files_struct *files;
+/* namespace */
+ struct namespace *namespace;
+/* signal handlers */
+ spinlock_t sigmask_lock; /* Protects signal and blocked */
+ struct signal_struct *sig;
+
+ sigset_t blocked;
+ struct sigpending pending;
+
+ unsigned long sas_ss_sp;
+ size_t sas_ss_size;
+ int (*notifier)(void *priv);
+ void *notifier_data;
+ sigset_t *notifier_mask;
+
+/* Thread group tracking */
+ u32 parent_exec_id;
+ u32 self_exec_id;
+/* Protection of (de-)allocation: mm, files, fs, tty */
+ spinlock_t alloc_lock;
+
+/* journalling filesystem info */
+ void *journal_info;
+};
+
+/*
+ * Per process flags
+ */
+#define PF_ALIGNWARN 0x00000001 /* Print alignment warning msgs */
+ /* Not implemented yet, only for 486*/
+#define PF_STARTING 0x00000002 /* being created */
+#define PF_EXITING 0x00000004 /* getting shut down */
+#define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */
+#define PF_SUPERPRIV 0x00000100 /* used super-user privileges */
+#define PF_DUMPCORE 0x00000200 /* dumped core */
+#define PF_SIGNALED 0x00000400 /* killed by a signal */
+#define PF_MEMALLOC 0x00000800 /* Allocating memory */
+#define PF_MEMDIE 0x00001000 /* Killed for out-of-memory */
+#define PF_FREE_PAGES 0x00002000 /* per process page freeing */
+#define PF_NOIO 0x00004000 /* avoid generating further I/O
*/
+#define PF_FSTRANS 0x00008000 /* inside a filesystem transaction */
+
+#define PF_USEDFPU 0x00100000 /* task used FPU this quantum (SMP) */
+
+/*
+ * Ptrace flags
+ */
+
+#define PT_PTRACED 0x00000001
+#define PT_TRACESYS 0x00000002
+#define PT_DTRACE 0x00000004 /* delayed trace (used on m68k, i386) */
+#define PT_TRACESYSGOOD 0x00000008
+#define PT_PTRACE_CAP 0x00000010 /* ptracer can follow suid-exec */
+
+#define is_dumpable(tsk) ((tsk)->task_dumpable && (tsk)->mm &&
(tsk)->mm->dumpable)
+
+/*
+ * Limit the stack by to some sane default: root can always
+ * increase this limit if needed.. 8MB seems reasonable.
+ */
+#define _STK_LIM (8*1024*1024)
+
+#define DEF_COUNTER (10*HZ/100) /* 100 ms time slice */
+#define MAX_COUNTER (20*HZ/100)
+#define DEF_NICE (0)
+
+extern void yield(void);
+
+/*
+ * The default (Linux) execution domain.
+ */
+extern struct exec_domain default_exec_domain;
+
+/*
+ * INIT_TASK is used to set up the first task table, touch at
+ * your own risk!. Base=0, limit=0x1fffff (=2MB)
+ */
+#define INIT_TASK(tsk) \
+{ \
+ state: 0, \
+ flags: 0, \
+ sigpending: 0,
\
+ addr_limit: KERNEL_DS,
\
+ exec_domain: &default_exec_domain, \
+ lock_depth: -1,
\
+ counter: DEF_COUNTER, \
+ nice: DEF_NICE, \
+ policy: SCHED_OTHER, \
+ mm: NULL,
\
+ active_mm: &init_mm, \
+ cpus_runnable: ~0UL, \
+ cpus_allowed: ~0UL, \
+ run_list: LIST_HEAD_INIT(tsk.run_list), \
+ next_task: &tsk, \
+ prev_task: &tsk, \
+ p_opptr: &tsk, \
+ p_pptr: &tsk, \
+ thread_group: LIST_HEAD_INIT(tsk.thread_group), \
+ wait_chldexit: __WAIT_QUEUE_HEAD_INITIALIZER(tsk.wait_chldexit),\
+ real_timer: {
\
+ function: it_real_fn \
+ }, \
+ cap_effective: CAP_INIT_EFF_SET, \
+ cap_inheritable: CAP_INIT_INH_SET, \
+ cap_permitted: CAP_FULL_SET, \
+ keep_capabilities: 0, \
+ rlim: INIT_RLIMITS, \
+ user: INIT_USER, \
+ comm: "swapper", \
+ thread: INIT_THREAD, \
+ fs: &init_fs,
\
+ files: &init_files, \
+ sigmask_lock: SPIN_LOCK_UNLOCKED, \
+ sig: &init_signals, \
+ pending: { NULL, &tsk.pending.head, {{0}}}, \
+ blocked: {{0}}, \
+ alloc_lock: SPIN_LOCK_UNLOCKED,
\
+ journal_info: NULL, \
+}
+
+
+#ifndef INIT_TASK_SIZE
+# define INIT_TASK_SIZE 2048*sizeof(long)
+#endif
+
+union task_union {
+ struct task_struct task;
+ unsigned long stack[INIT_TASK_SIZE/sizeof(long)];
+};
+
+extern union task_union init_task_union;
+
+extern struct mm_struct init_mm;
+extern struct task_struct *init_tasks[NR_CPUS];
+
+/* PID hashing. (shouldnt this be dynamic?) */
+#define PIDHASH_SZ (4096 >> 2)
+extern struct task_struct *pidhash[PIDHASH_SZ];
+
+#define pid_hashfn(x) ((((x) >> 8) ^ (x)) & (PIDHASH_SZ - 1))
+
+static inline void hash_pid(struct task_struct *p)
+{
+ struct task_struct **htable = &pidhash[pid_hashfn(p->pid)];
+
+ if((p->pidhash_next = *htable) != NULL)
+ (*htable)->pidhash_pprev = &p->pidhash_next;
+ *htable = p;
+ p->pidhash_pprev = htable;
+}
+
+static inline void unhash_pid(struct task_struct *p)
+{
+ if(p->pidhash_next)
+ p->pidhash_next->pidhash_pprev = p->pidhash_pprev;
+ *p->pidhash_pprev = p->pidhash_next;
+}
+
+static inline struct task_struct *find_task_by_pid(int pid)
+{
+ struct task_struct *p, **htable = &pidhash[pid_hashfn(pid)];
+
+ for(p = *htable; p && p->pid != pid; p = p->pidhash_next)
+ ;
+
+ return p;
+}
+
+#define task_has_cpu(tsk) ((tsk)->cpus_runnable != ~0UL)
+
+static inline void task_set_cpu(struct task_struct *tsk, unsigned int cpu)
+{
+ tsk->processor = cpu;
+ tsk->cpus_runnable = 1UL << cpu;
+}
+
+static inline void task_release_cpu(struct task_struct *tsk)
+{
+ tsk->cpus_runnable = ~0UL;
+}
+
+/* per-UID process charging. */
+extern struct user_struct * alloc_uid(uid_t);
+extern void free_uid(struct user_struct *);
+extern void switch_uid(struct user_struct *);
+
+#include <asm/current.h>
+
+extern unsigned long volatile jiffies;
+extern unsigned long itimer_ticks;
+extern unsigned long itimer_next;
+extern struct timeval xtime;
+extern void do_timer(struct pt_regs *);
+#ifdef CONFIG_NO_IDLE_HZ
+extern void do_timer_ticks(int ticks);
+#endif
+
+extern unsigned int * prof_buffer;
+extern unsigned long prof_len;
+extern unsigned long prof_shift;
+
+#define CURRENT_TIME (xtime.tv_sec)
+
+extern void FASTCALL(__wake_up(wait_queue_head_t *q, unsigned int mode, int
nr));
+extern void FASTCALL(__wake_up_sync(wait_queue_head_t *q, unsigned int mode,
int nr));
+extern void FASTCALL(sleep_on(wait_queue_head_t *q));
+extern long FASTCALL(sleep_on_timeout(wait_queue_head_t *q,
+ signed long timeout));
+extern void FASTCALL(interruptible_sleep_on(wait_queue_head_t *q));
+extern long FASTCALL(interruptible_sleep_on_timeout(wait_queue_head_t *q,
+ signed long timeout));
+extern int FASTCALL(wake_up_process(struct task_struct * tsk));
+
+#define wake_up(x) __wake_up((x),TASK_UNINTERRUPTIBLE |
TASK_INTERRUPTIBLE, 1)
+#define wake_up_nr(x, nr) __wake_up((x),TASK_UNINTERRUPTIBLE |
TASK_INTERRUPTIBLE, nr)
+#define wake_up_all(x) __wake_up((x),TASK_UNINTERRUPTIBLE |
TASK_INTERRUPTIBLE, 0)
+#define wake_up_sync(x)
__wake_up_sync((x),TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, 1)
+#define wake_up_sync_nr(x, nr) __wake_up_sync((x),TASK_UNINTERRUPTIBLE
| TASK_INTERRUPTIBLE, nr)
+#define wake_up_interruptible(x) __wake_up((x),TASK_INTERRUPTIBLE, 1)
+#define wake_up_interruptible_nr(x, nr)
__wake_up((x),TASK_INTERRUPTIBLE, nr)
+#define wake_up_interruptible_all(x) __wake_up((x),TASK_INTERRUPTIBLE, 0)
+#define wake_up_interruptible_sync(x) __wake_up_sync((x),TASK_INTERRUPTIBLE,
1)
+#define wake_up_interruptible_sync_nr(x, nr)
__wake_up_sync((x),TASK_INTERRUPTIBLE, nr)
+asmlinkage long sys_wait4(pid_t pid,unsigned int * stat_addr, int options,
struct rusage * ru);
+
+extern int in_group_p(gid_t);
+extern int in_egroup_p(gid_t);
+
+extern void proc_caches_init(void);
+extern void flush_signals(struct task_struct *);
+extern void flush_signal_handlers(struct task_struct *);
+extern void sig_exit(int, int, struct siginfo *);
+extern int dequeue_signal(sigset_t *, siginfo_t *);
+extern void block_all_signals(int (*notifier)(void *priv), void *priv,
+ sigset_t *mask);
+extern void unblock_all_signals(void);
+extern int send_sig_info(int, struct siginfo *, struct task_struct *);
+extern int force_sig_info(int, struct siginfo *, struct task_struct *);
+extern int kill_pg_info(int, struct siginfo *, pid_t);
+extern int kill_sl_info(int, struct siginfo *, pid_t);
+extern int kill_proc_info(int, struct siginfo *, pid_t);
+extern void notify_parent(struct task_struct *, int);
+extern void do_notify_parent(struct task_struct *, int);
+extern void force_sig(int, struct task_struct *);
+extern int send_sig(int, struct task_struct *, int);
+extern int kill_pg(pid_t, int, int);
+extern int kill_sl(pid_t, int, int);
+extern int kill_proc(pid_t, int, int);
+extern int do_sigaction(int, const struct k_sigaction *, struct k_sigaction *);
+extern int do_sigaltstack(const stack_t *, stack_t *, unsigned long);
+
+static inline int signal_pending(struct task_struct *p)
+{
+ return (p->sigpending != 0);
+}
+
+/*
+ * Re-calculate pending state from the set of locally pending
+ * signals, globally pending signals, and blocked signals.
+ */
+static inline int has_pending_signals(sigset_t *signal, sigset_t *blocked)
+{
+ unsigned long ready;
+ long i;
+
+ switch (_NSIG_WORDS) {
+ default:
+ for (i = _NSIG_WORDS, ready = 0; --i >= 0 ;)
+ ready |= signal->sig[i] &~ blocked->sig[i];
+ break;
+
+ case 4: ready = signal->sig[3] &~ blocked->sig[3];
+ ready |= signal->sig[2] &~ blocked->sig[2];
+ ready |= signal->sig[1] &~ blocked->sig[1];
+ ready |= signal->sig[0] &~ blocked->sig[0];
+ break;
+
+ case 2: ready = signal->sig[1] &~ blocked->sig[1];
+ ready |= signal->sig[0] &~ blocked->sig[0];
+ break;
+
+ case 1: ready = signal->sig[0] &~ blocked->sig[0];
+ }
+ return ready != 0;
+}
+
+/* Reevaluate whether the task has signals pending delivery.
+ This is required every time the blocked sigset_t changes.
+ All callers should have t->sigmask_lock. */
+
+static inline void recalc_sigpending(struct task_struct *t)
+{
+ t->sigpending = has_pending_signals(&t->pending.signal, &t->blocked);
+}
+
+/* True if we are on the alternate signal stack. */
+
+static inline int on_sig_stack(unsigned long sp)
+{
+ return (sp - current->sas_ss_sp < current->sas_ss_size);
+}
+
+static inline int sas_ss_flags(unsigned long sp)
+{
+ return (current->sas_ss_size == 0 ? SS_DISABLE
+ : on_sig_stack(sp) ? SS_ONSTACK : 0);
+}
+
+extern int request_irq(unsigned int,
+ void (*handler)(int, void *, struct pt_regs *),
+ unsigned long, const char *, void *);
+extern void free_irq(unsigned int, void *);
+
+/*
+ * This has now become a routine instead of a macro, it sets a flag if
+ * it returns true (to do BSD-style accounting where the process is flagged
+ * if it uses root privs). The implication of this is that you should do
+ * normal permissions checks first, and check suser() last.
+ *
+ * [Dec 1997 -- Chris Evans]
+ * For correctness, the above considerations need to be extended to
+ * fsuser(). This is done, along with moving fsuser() checks to be
+ * last.
+ *
+ * These will be removed, but in the mean time, when the SECURE_NOROOT
+ * flag is set, uids don't grant privilege.
+ */
+static inline int suser(void)
+{
+ if (!issecure(SECURE_NOROOT) && current->euid == 0) {
+ current->flags |= PF_SUPERPRIV;
+ return 1;
+ }
+ return 0;
+}
+
+static inline int fsuser(void)
+{
+ if (!issecure(SECURE_NOROOT) && current->fsuid == 0) {
+ current->flags |= PF_SUPERPRIV;
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * capable() checks for a particular capability.
+ * New privilege checks should use this interface, rather than suser() or
+ * fsuser(). See include/linux/capability.h for defined capabilities.
+ */
+
+static inline int capable(int cap)
+{
+#if 1 /* ok now */
+ if (cap_raised(current->cap_effective, cap))
+#else
+ if (cap_is_fs_cap(cap) ? current->fsuid == 0 : current->euid == 0)
+#endif
+ {
+ current->flags |= PF_SUPERPRIV;
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * Routines for handling mm_structs
+ */
+extern struct mm_struct * mm_alloc(void);
+
+extern struct mm_struct * start_lazy_tlb(void);
+extern void end_lazy_tlb(struct mm_struct *mm);
+
+/* mmdrop drops the mm and the page tables */
+extern void FASTCALL(__mmdrop(struct mm_struct *));
+static inline void mmdrop(struct mm_struct * mm)
+{
+ if (atomic_dec_and_test(&mm->mm_count))
+ __mmdrop(mm);
+}
+
+/* mmput gets rid of the mappings and all user-space */
+extern void mmput(struct mm_struct *);
+/* Remove the current tasks stale references to the old mm_struct */
+extern void mm_release(void);
+
+/*
+ * Routines for handling the fd arrays
+ */
+extern struct file ** alloc_fd_array(int);
+extern int expand_fd_array(struct files_struct *, int nr);
+extern void free_fd_array(struct file **, int);
+
+extern fd_set *alloc_fdset(int);
+extern int expand_fdset(struct files_struct *, int nr);
+extern void free_fdset(fd_set *, int);
+
+extern int copy_thread(int, unsigned long, unsigned long, unsigned long,
struct task_struct *, struct pt_regs *);
+extern void flush_thread(void);
+extern void exit_thread(void);
+
+extern void exit_mm(struct task_struct *);
+extern void exit_files(struct task_struct *);
+extern void exit_sighand(struct task_struct *);
+
+extern void reparent_to_init(void);
+extern void daemonize(void);
+
+extern int do_execve(char *, char **, char **, struct pt_regs *);
+extern int do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned
long);
+
+extern void set_task_comm(struct task_struct *tsk, char *from);
+extern void get_task_comm(char *to, struct task_struct *tsk);
+
+extern void FASTCALL(add_wait_queue(wait_queue_head_t *q, wait_queue_t *
wait));
+extern void FASTCALL(add_wait_queue_exclusive(wait_queue_head_t *q,
wait_queue_t * wait));
+extern void FASTCALL(remove_wait_queue(wait_queue_head_t *q, wait_queue_t *
wait));
+
+extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
+
+#define __wait_event(wq, condition) \
+do { \
+ wait_queue_t __wait; \
+ init_waitqueue_entry(&__wait, current); \
+ \
+ add_wait_queue(&wq, &__wait); \
+ for (;;) { \
+ set_current_state(TASK_UNINTERRUPTIBLE); \
+ if (condition) \
+ break; \
+ schedule(); \
+ } \
+ current->state = TASK_RUNNING; \
+ remove_wait_queue(&wq, &__wait); \
+} while (0)
+
+#define wait_event(wq, condition) \
+do { \
+ if (condition) \
+ break; \
+ __wait_event(wq, condition); \
+} while (0)
+
+#define __wait_event_interruptible(wq, condition, ret) \
+do { \
+ wait_queue_t __wait; \
+ init_waitqueue_entry(&__wait, current); \
+ \
+ add_wait_queue(&wq, &__wait); \
+ for (;;) { \
+ set_current_state(TASK_INTERRUPTIBLE); \
+ if (condition) \
+ break; \
+ if (!signal_pending(current)) { \
+ schedule(); \
+ continue; \
+ } \
+ ret = -ERESTARTSYS; \
+ break; \
+ } \
+ current->state = TASK_RUNNING; \
+ remove_wait_queue(&wq, &__wait); \
+} while (0)
+
+#define wait_event_interruptible(wq, condition)
\
+({ \
+ int __ret = 0; \
+ if (!(condition)) \
+ __wait_event_interruptible(wq, condition, __ret); \
+ __ret; \
+})
+
+#define REMOVE_LINKS(p) do { \
+ (p)->next_task->prev_task = (p)->prev_task; \
+ (p)->prev_task->next_task = (p)->next_task; \
+ if ((p)->p_osptr) \
+ (p)->p_osptr->p_ysptr = (p)->p_ysptr; \
+ if ((p)->p_ysptr) \
+ (p)->p_ysptr->p_osptr = (p)->p_osptr; \
+ else \
+ (p)->p_pptr->p_cptr = (p)->p_osptr; \
+ } while (0)
+
+#define SET_LINKS(p) do { \
+ (p)->next_task = &init_task; \
+ (p)->prev_task = init_task.prev_task; \
+ init_task.prev_task->next_task = (p); \
+ init_task.prev_task = (p); \
+ (p)->p_ysptr = NULL; \
+ if (((p)->p_osptr = (p)->p_pptr->p_cptr) != NULL) \
+ (p)->p_osptr->p_ysptr = p; \
+ (p)->p_pptr->p_cptr = p; \
+ } while (0)
+
+#define for_each_task(p) \
+ for (p = &init_task ; (p = p->next_task) != &init_task ; )
+
+#define for_each_thread(task) \
+ for (task = next_thread(current) ; task != current ; task =
next_thread(task))
+
+#define next_thread(p) \
+ list_entry((p)->thread_group.next, struct task_struct, thread_group)
+
+#define thread_group_leader(p) (p->pid == p->tgid)
+
+static inline void del_from_runqueue(struct task_struct * p)
+{
+ nr_running--;
+ p->sleep_time = jiffies;
+ list_del(&p->run_list);
+ p->run_list.next = NULL;
+}
+
+static inline int task_on_runqueue(struct task_struct *p)
+{
+ return (p->run_list.next != NULL);
+}
+
+static inline void unhash_process(struct task_struct *p)
+{
+ if (task_on_runqueue(p))
+ out_of_line_bug();
+ write_lock_irq(&tasklist_lock);
+ nr_threads--;
+ unhash_pid(p);
+ REMOVE_LINKS(p);
+ list_del(&p->thread_group);
+ write_unlock_irq(&tasklist_lock);
+}
+
+/* Protects ->fs, ->files, ->mm, and synchronises with wait4(). Nests inside
tasklist_lock */
+static inline void task_lock(struct task_struct *p)
+{
+ spin_lock(&p->alloc_lock);
+}
+
+static inline void task_unlock(struct task_struct *p)
+{
+ spin_unlock(&p->alloc_lock);
+}
+
+/* write full pathname into buffer and return start of pathname */
+static inline char * d_path(struct dentry *dentry, struct vfsmount *vfsmnt,
+ char *buf, int buflen)
+{
+ char *res;
+ struct vfsmount *rootmnt;
+ struct dentry *root;
+ read_lock(¤t->fs->lock);
+ rootmnt = mntget(current->fs->rootmnt);
+ root = dget(current->fs->root);
+ read_unlock(¤t->fs->lock);
+ spin_lock(&dcache_lock);
+ res = __d_path(dentry, vfsmnt, root, rootmnt, buf, buflen);
+ spin_unlock(&dcache_lock);
+ dput(root);
+ mntput(rootmnt);
+ return res;
+}
+
+static inline int need_resched(void)
+{
+ return (unlikely(current->need_resched));
+}
+
+extern void __cond_resched(void);
+static inline void cond_resched(void)
+{
+ if (need_resched())
+ __cond_resched();
+}
+
+#endif /* __KERNEL__ */
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/irq.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/irq.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,105 @@
+/*
+ * linux/arch/x86_64/kernel/irq.c
+ *
+ * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
+ *
+ * This file contains the lowest level x86_64-specific interrupt
+ * entry and irq statistics code. All the remaining irq logic is
+ * done by the generic kernel/irq/ code and in the
+ * x86_64-specific irq controller code. (e.g. i8259.c and
+ * io_apic.c.)
+ */
+#include <asm/uaccess.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+
+/*
+ * Interrupt statistics:
+ */
+
+atomic_t irq_err_count;
+
+
+/*
+ * Generic, controller-independent functions:
+ */
+
+int show_interrupts(struct seq_file *p, void *v)
+{
+ int i = *(loff_t *) v, j;
+ struct irqaction * action;
+ unsigned long flags;
+
+ if (i == 0) {
+ seq_printf(p, " ");
+ for (j=0; j<NR_CPUS; j++)
+ if (cpu_online(j))
+ seq_printf(p, "CPU%d ",j);
+ seq_putc(p, '\n');
+ }
+
+ if (i < NR_IRQS) {
+ spin_lock_irqsave(&irq_desc[i].lock, flags);
+ action = irq_desc[i].action;
+ if (!action)
+ goto skip;
+ seq_printf(p, "%3d: ",i);
+#ifndef CONFIG_SMP
+ seq_printf(p, "%10u ", kstat_irqs(i));
+#else
+ for (j=0; j<NR_CPUS; j++)
+ if (cpu_online(j))
+ seq_printf(p, "%10u ",
+ kstat_cpu(j).irqs[i]);
+#endif
+ seq_printf(p, " %14s", irq_desc[i].handler->typename);
+
+ seq_printf(p, " %s", action->name);
+ for (action=action->next; action; action = action->next)
+ seq_printf(p, ", %s", action->name);
+ seq_putc(p, '\n');
+skip:
+ spin_unlock_irqrestore(&irq_desc[i].lock, flags);
+ } else if (i == NR_IRQS) {
+ seq_printf(p, "NMI: ");
+ for (j = 0; j < NR_CPUS; j++)
+ if (cpu_online(j))
+ seq_printf(p, "%10u ", cpu_pda[j].__nmi_count);
+ seq_putc(p, '\n');
+#ifdef CONFIG_X86_LOCAL_APIC
+ seq_printf(p, "LOC: ");
+ for (j = 0; j < NR_CPUS; j++)
+ if (cpu_online(j))
+ seq_printf(p, "%10u ",
cpu_pda[j].apic_timer_irqs);
+ seq_putc(p, '\n');
+#endif
+ seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
+#ifdef CONFIG_X86_IO_APIC
+#ifdef APIC_MISMATCH_DEBUG
+ seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));
+#endif
+#endif
+ }
+ return 0;
+}
+
+/*
+ * do_IRQ handles all normal device IRQ's (the special
+ * SMP cross-CPU interrupts have their own specific
+ * handlers).
+ */
+asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
+{
+ /* high bits used in ret_from_ code */
+ int irq = regs->orig_rax & __IRQ_MASK(HARDIRQ_BITS);
+
+ irq_enter();
+
+ __do_IRQ(irq, regs);
+ irq_exit();
+
+ return 1;
+}
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/setup.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/setup.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,1649 @@
+/*
+ * linux/arch/i386/kernel/setup.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ *
+ * Memory region support
+ * David Parsons <orc@xxxxxxxxxxxxxx>, July-August 1999
+ *
+ * Added E820 sanitization routine (removes overlapping memory regions);
+ * Brian Moyle <bmoyle@xxxxxxxxxx>, February 2001
+ *
+ * Moved CPU detection code to cpu/${cpu}.c
+ * Patrick Mochel <mochel@xxxxxxxx>, March 2002
+ *
+ * Provisions for empty E820 memory regions (reported by certain BIOSes).
+ * Alex Achenbach <xela@xxxxxxx>, December 2002.
+ *
+ */
+
+/*
+ * This file handles the architecture-dependent parts of initialization
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/tty.h>
+#include <linux/ioport.h>
+#include <linux/acpi.h>
+#include <linux/apm_bios.h>
+#include <linux/initrd.h>
+#include <linux/bootmem.h>
+#include <linux/seq_file.h>
+#include <linux/console.h>
+#include <linux/mca.h>
+#include <linux/root_dev.h>
+#include <linux/highmem.h>
+#include <linux/module.h>
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/edd.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <video/edid.h>
+#include <asm/e820.h>
+#include <asm/mpspec.h>
+#include <asm/setup.h>
+#include <asm/arch_hooks.h>
+#include <asm/sections.h>
+#include <asm/io_apic.h>
+#include <asm/ist.h>
+#include <asm/io.h>
+#include <asm-xen/hypervisor.h>
+#include <asm-xen/xen-public/physdev.h>
+#include "setup_arch_pre.h"
+#include <bios_ebda.h>
+
+/* Allows setting of maximum possible memory size */
+static unsigned long xen_override_max_pfn;
+
+static int xen_panic_event(struct notifier_block *, unsigned long, void *);
+static struct notifier_block xen_panic_block = {
+ xen_panic_event, NULL, 0 /* try to go last */
+};
+
+int disable_pse __initdata = 0;
+
+/*
+ * Machine setup..
+ */
+
+#ifdef CONFIG_EFI
+int efi_enabled = 0;
+EXPORT_SYMBOL(efi_enabled);
+#endif
+
+/* cpu data as detected by the assembly code in head.S */
+struct cpuinfo_x86 new_cpu_data __initdata = { 0, 0, 0, 0, -1, 0, 1, 0, -1 };
+/* common cpu data for all cpus */
+struct cpuinfo_x86 boot_cpu_data = { 0, 0, 0, 0, -1, 0, 1, 0, -1 };
+
+unsigned long mmu_cr4_features;
+EXPORT_SYMBOL_GPL(mmu_cr4_features);
+
+#ifdef CONFIG_ACPI_INTERPRETER
+ int acpi_disabled = 0;
+#else
+ int acpi_disabled = 1;
+#endif
+EXPORT_SYMBOL(acpi_disabled);
+
+#ifdef CONFIG_ACPI_BOOT
+int __initdata acpi_force = 0;
+extern acpi_interrupt_flags acpi_sci_flags;
+#endif
+
+/* for MCA, but anyone else can use it if they want */
+unsigned int machine_id;
+unsigned int machine_submodel_id;
+unsigned int BIOS_revision;
+unsigned int mca_pentium_flag;
+
+/* For PCI or other memory-mapped resources */
+unsigned long pci_mem_start = 0x10000000;
+
+/* Boot loader ID as an integer, for the benefit of proc_dointvec */
+int bootloader_type;
+
+/* user-defined highmem size */
+static unsigned int highmem_pages = -1;
+
+/*
+ * Setup options
+ */
+struct drive_info_struct { char dummy[32]; } drive_info;
+struct screen_info screen_info;
+struct apm_info apm_info;
+struct sys_desc_table_struct {
+ unsigned short length;
+ unsigned char table[0];
+};
+struct edid_info edid_info;
+struct ist_info ist_info;
+struct e820map e820;
+
+unsigned char aux_device_present;
+
+extern void early_cpu_init(void);
+extern void dmi_scan_machine(void);
+extern void generic_apic_probe(char *);
+extern int root_mountflags;
+
+unsigned long saved_videomode;
+
+#define RAMDISK_IMAGE_START_MASK 0x07FF
+#define RAMDISK_PROMPT_FLAG 0x8000
+#define RAMDISK_LOAD_FLAG 0x4000
+
+static char command_line[COMMAND_LINE_SIZE];
+
+unsigned char __initdata boot_params[PARAM_SIZE];
+
+static struct resource data_resource = {
+ .name = "Kernel data",
+ .start = 0,
+ .end = 0,
+ .flags = IORESOURCE_BUSY | IORESOURCE_MEM
+};
+
+static struct resource code_resource = {
+ .name = "Kernel code",
+ .start = 0,
+ .end = 0,
+ .flags = IORESOURCE_BUSY | IORESOURCE_MEM
+};
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+static struct resource system_rom_resource = {
+ .name = "System ROM",
+ .start = 0xf0000,
+ .end = 0xfffff,
+ .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
+};
+
+static struct resource extension_rom_resource = {
+ .name = "Extension ROM",
+ .start = 0xe0000,
+ .end = 0xeffff,
+ .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
+};
+
+static struct resource adapter_rom_resources[] = { {
+ .name = "Adapter ROM",
+ .start = 0xc8000,
+ .end = 0,
+ .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
+}, {
+ .name = "Adapter ROM",
+ .start = 0,
+ .end = 0,
+ .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
+}, {
+ .name = "Adapter ROM",
+ .start = 0,
+ .end = 0,
+ .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
+}, {
+ .name = "Adapter ROM",
+ .start = 0,
+ .end = 0,
+ .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
+}, {
+ .name = "Adapter ROM",
+ .start = 0,
+ .end = 0,
+ .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
+}, {
+ .name = "Adapter ROM",
+ .start = 0,
+ .end = 0,
+ .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
+} };
+
+#define ADAPTER_ROM_RESOURCES \
+ (sizeof adapter_rom_resources / sizeof adapter_rom_resources[0])
+
+static struct resource video_rom_resource = {
+ .name = "Video ROM",
+ .start = 0xc0000,
+ .end = 0xc7fff,
+ .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
+};
+#endif
+
+static struct resource video_ram_resource = {
+ .name = "Video RAM area",
+ .start = 0xa0000,
+ .end = 0xbffff,
+ .flags = IORESOURCE_BUSY | IORESOURCE_MEM
+};
+
+static struct resource standard_io_resources[] = { {
+ .name = "dma1",
+ .start = 0x0000,
+ .end = 0x001f,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO
+}, {
+ .name = "pic1",
+ .start = 0x0020,
+ .end = 0x0021,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO
+}, {
+ .name = "timer0",
+ .start = 0x0040,
+ .end = 0x0043,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO
+}, {
+ .name = "timer1",
+ .start = 0x0050,
+ .end = 0x0053,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO
+}, {
+ .name = "keyboard",
+ .start = 0x0060,
+ .end = 0x006f,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO
+}, {
+ .name = "dma page reg",
+ .start = 0x0080,
+ .end = 0x008f,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO
+}, {
+ .name = "pic2",
+ .start = 0x00a0,
+ .end = 0x00a1,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO
+}, {
+ .name = "dma2",
+ .start = 0x00c0,
+ .end = 0x00df,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO
+}, {
+ .name = "fpu",
+ .start = 0x00f0,
+ .end = 0x00ff,
+ .flags = IORESOURCE_BUSY | IORESOURCE_IO
+} };
+
+#define STANDARD_IO_RESOURCES \
+ (sizeof standard_io_resources / sizeof standard_io_resources[0])
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+#define romsignature(x) (*(unsigned short *)(x) == 0xaa55)
+
+static int __init romchecksum(unsigned char *rom, unsigned long length)
+{
+ unsigned char *p, sum = 0;
+
+ for (p = rom; p < rom + length; p++)
+ sum += *p;
+ return sum == 0;
+}
+
+static void __init probe_roms(void)
+{
+ unsigned long start, length, upper;
+ unsigned char *rom;
+ int i;
+
+ /* Nothing to do if not running in dom0. */
+ if (!(xen_start_info.flags & SIF_INITDOMAIN))
+ return;
+
+ /* video rom */
+ upper = adapter_rom_resources[0].start;
+ for (start = video_rom_resource.start; start < upper; start += 2048) {
+ rom = isa_bus_to_virt(start);
+ if (!romsignature(rom))
+ continue;
+
+ video_rom_resource.start = start;
+
+ /* 0 < length <= 0x7f * 512, historically */
+ length = rom[2] * 512;
+
+ /* if checksum okay, trust length byte */
+ if (length && romchecksum(rom, length))
+ video_rom_resource.end = start + length - 1;
+
+ request_resource(&iomem_resource, &video_rom_resource);
+ break;
+ }
+
+ start = (video_rom_resource.end + 1 + 2047) & ~2047UL;
+ if (start < upper)
+ start = upper;
+
+ /* system rom */
+ request_resource(&iomem_resource, &system_rom_resource);
+ upper = system_rom_resource.start;
+
+ /* check for extension rom (ignore length byte!) */
+ rom = isa_bus_to_virt(extension_rom_resource.start);
+ if (romsignature(rom)) {
+ length = extension_rom_resource.end -
extension_rom_resource.start + 1;
+ if (romchecksum(rom, length)) {
+ request_resource(&iomem_resource,
&extension_rom_resource);
+ upper = extension_rom_resource.start;
+ }
+ }
+
+ /* check for adapter roms on 2k boundaries */
+ for (i = 0; i < ADAPTER_ROM_RESOURCES && start < upper; start += 2048) {
+ rom = isa_bus_to_virt(start);
+ if (!romsignature(rom))
+ continue;
+
+ /* 0 < length <= 0x7f * 512, historically */
+ length = rom[2] * 512;
+
+ /* but accept any length that fits if checksum okay */
+ if (!length || start + length > upper || !romchecksum(rom,
length))
+ continue;
+
+ adapter_rom_resources[i].start = start;
+ adapter_rom_resources[i].end = start + length - 1;
+ request_resource(&iomem_resource, &adapter_rom_resources[i]);
+
+ start = adapter_rom_resources[i++].end & ~2047UL;
+ }
+}
+#endif
+
+/*
+ * Point at the empty zero page to start with. We map the real shared_info
+ * page as soon as fixmap is up and running.
+ */
+shared_info_t *HYPERVISOR_shared_info = (shared_info_t *)empty_zero_page;
+EXPORT_SYMBOL(HYPERVISOR_shared_info);
+
+unsigned int *phys_to_machine_mapping, *pfn_to_mfn_frame_list;
+EXPORT_SYMBOL(phys_to_machine_mapping);
+
+/* Raw start-of-day parameters from the hypervisor. */
+union xen_start_info_union xen_start_info_union;
+
+static void __init limit_regions(unsigned long long size)
+{
+ unsigned long long current_addr = 0;
+ int i;
+
+ if (efi_enabled) {
+ for (i = 0; i < memmap.nr_map; i++) {
+ current_addr = memmap.map[i].phys_addr +
+ (memmap.map[i].num_pages << 12);
+ if (memmap.map[i].type == EFI_CONVENTIONAL_MEMORY) {
+ if (current_addr >= size) {
+ memmap.map[i].num_pages -=
+ (((current_addr-size) +
PAGE_SIZE-1) >> PAGE_SHIFT);
+ memmap.nr_map = i + 1;
+ return;
+ }
+ }
+ }
+ }
+ for (i = 0; i < e820.nr_map; i++) {
+ if (e820.map[i].type == E820_RAM) {
+ current_addr = e820.map[i].addr + e820.map[i].size;
+ if (current_addr >= size) {
+ e820.map[i].size -= current_addr-size;
+ e820.nr_map = i + 1;
+ return;
+ }
+ }
+ }
+}
+
+static void __init add_memory_region(unsigned long long start,
+ unsigned long long size, int type)
+{
+ int x;
+
+ if (!efi_enabled) {
+ x = e820.nr_map;
+
+ if (x == E820MAX) {
+ printk(KERN_ERR "Ooops! Too many entries in the memory
map!\n");
+ return;
+ }
+
+ e820.map[x].addr = start;
+ e820.map[x].size = size;
+ e820.map[x].type = type;
+ e820.nr_map++;
+ }
+} /* add_memory_region */
+
+#define E820_DEBUG 1
+
+static void __init print_memory_map(char *who)
+{
+ int i;
+
+ for (i = 0; i < e820.nr_map; i++) {
+ printk(" %s: %016Lx - %016Lx ", who,
+ e820.map[i].addr,
+ e820.map[i].addr + e820.map[i].size);
+ switch (e820.map[i].type) {
+ case E820_RAM: printk("(usable)\n");
+ break;
+ case E820_RESERVED:
+ printk("(reserved)\n");
+ break;
+ case E820_ACPI:
+ printk("(ACPI data)\n");
+ break;
+ case E820_NVS:
+ printk("(ACPI NVS)\n");
+ break;
+ default: printk("type %lu\n", e820.map[i].type);
+ break;
+ }
+ }
+}
+
+#if 0
+/*
+ * Sanitize the BIOS e820 map.
+ *
+ * Some e820 responses include overlapping entries. The following
+ * replaces the original e820 map with a new one, removing overlaps.
+ *
+ */
+struct change_member {
+ struct e820entry *pbios; /* pointer to original bios entry */
+ unsigned long long addr; /* address for this change point */
+};
+struct change_member change_point_list[2*E820MAX] __initdata;
+struct change_member *change_point[2*E820MAX] __initdata;
+struct e820entry *overlap_list[E820MAX] __initdata;
+struct e820entry new_bios[E820MAX] __initdata;
+
+static int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map)
+{
+ struct change_member *change_tmp;
+ unsigned long current_type, last_type;
+ unsigned long long last_addr;
+ int chgidx, still_changing;
+ int overlap_entries;
+ int new_bios_entry;
+ int old_nr, new_nr, chg_nr;
+ int i;
+
+ /*
+ Visually we're performing the following (1,2,3,4 = memory
types)...
+
+ Sample memory map (w/overlaps):
+ ____22__________________
+ ______________________4_
+ ____1111________________
+ _44_____________________
+ 11111111________________
+ ____________________33__
+ ___________44___________
+ __________33333_________
+ ______________22________
+ ___________________2222_
+ _________111111111______
+ _____________________11_
+ _________________4______
+
+ Sanitized equivalent (no overlap):
+ 1_______________________
+ _44_____________________
+ ___1____________________
+ ____22__________________
+ ______11________________
+ _________1______________
+ __________3_____________
+ ___________44___________
+ _____________33_________
+ _______________2________
+ ________________1_______
+ _________________4______
+ ___________________2____
+ ____________________33__
+ ______________________4_
+ */
+
+ /* if there's only one memory region, don't bother */
+ if (*pnr_map < 2)
+ return -1;
+
+ old_nr = *pnr_map;
+
+ /* bail out if we find any unreasonable addresses in bios map */
+ for (i=0; i<old_nr; i++)
+ if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr)
+ return -1;
+
+ /* create pointers for initial change-point information (for sorting) */
+ for (i=0; i < 2*old_nr; i++)
+ change_point[i] = &change_point_list[i];
+
+ /* record all known change-points (starting and ending addresses),
+ omitting those that are for empty memory regions */
+ chgidx = 0;
+ for (i=0; i < old_nr; i++) {
+ if (biosmap[i].size != 0) {
+ change_point[chgidx]->addr = biosmap[i].addr;
+ change_point[chgidx++]->pbios = &biosmap[i];
+ change_point[chgidx]->addr = biosmap[i].addr +
biosmap[i].size;
+ change_point[chgidx++]->pbios = &biosmap[i];
+ }
+ }
+ chg_nr = chgidx; /* true number of change-points */
+
+ /* sort change-point list by memory addresses (low -> high) */
+ still_changing = 1;
+ while (still_changing) {
+ still_changing = 0;
+ for (i=1; i < chg_nr; i++) {
+ /* if <current_addr> > <last_addr>, swap */
+ /* or, if current=<start_addr> & last=<end_addr>, swap
*/
+ if ((change_point[i]->addr < change_point[i-1]->addr) ||
+ ((change_point[i]->addr ==
change_point[i-1]->addr) &&
+ (change_point[i]->addr ==
change_point[i]->pbios->addr) &&
+ (change_point[i-1]->addr !=
change_point[i-1]->pbios->addr))
+ )
+ {
+ change_tmp = change_point[i];
+ change_point[i] = change_point[i-1];
+ change_point[i-1] = change_tmp;
+ still_changing=1;
+ }
+ }
+ }
+
+ /* create a new bios memory map, removing overlaps */
+ overlap_entries=0; /* number of entries in the overlap table */
+ new_bios_entry=0; /* index for creating new bios map entries */
+ last_type = 0; /* start with undefined memory type */
+ last_addr = 0; /* start with 0 as last starting address */
+ /* loop through change-points, determining affect on the new bios map */
+ for (chgidx=0; chgidx < chg_nr; chgidx++)
+ {
+ /* keep track of all overlapping bios entries */
+ if (change_point[chgidx]->addr ==
change_point[chgidx]->pbios->addr)
+ {
+ /* add map entry to overlap list (> 1 entry implies an
overlap) */
+
overlap_list[overlap_entries++]=change_point[chgidx]->pbios;
+ }
+ else
+ {
+ /* remove entry from list (order independent, so swap
with last) */
+ for (i=0; i<overlap_entries; i++)
+ {
+ if (overlap_list[i] ==
change_point[chgidx]->pbios)
+ overlap_list[i] =
overlap_list[overlap_entries-1];
+ }
+ overlap_entries--;
+ }
+ /* if there are overlapping entries, decide which "type" to use
*/
+ /* (larger value takes precedence -- 1=usable,
2,3,4,4+=unusable) */
+ current_type = 0;
+ for (i=0; i<overlap_entries; i++)
+ if (overlap_list[i]->type > current_type)
+ current_type = overlap_list[i]->type;
+ /* continue building up new bios map based on this information
*/
+ if (current_type != last_type) {
+ if (last_type != 0) {
+ new_bios[new_bios_entry].size =
+ change_point[chgidx]->addr - last_addr;
+ /* move forward only if the new size was
non-zero */
+ if (new_bios[new_bios_entry].size != 0)
+ if (++new_bios_entry >= E820MAX)
+ break; /* no more space left
for new bios entries */
+ }
+ if (current_type != 0) {
+ new_bios[new_bios_entry].addr =
change_point[chgidx]->addr;
+ new_bios[new_bios_entry].type = current_type;
+ last_addr=change_point[chgidx]->addr;
+ }
+ last_type = current_type;
+ }
+ }
+ new_nr = new_bios_entry; /* retain count for new bios entries */
+
+ /* copy new bios mapping into original location */
+ memcpy(biosmap, new_bios, new_nr*sizeof(struct e820entry));
+ *pnr_map = new_nr;
+
+ return 0;
+}
+
+/*
+ * Copy the BIOS e820 map into a safe place.
+ *
+ * Sanity-check it while we're at it..
+ *
+ * If we're lucky and live on a modern system, the setup code
+ * will have given us a memory map that we can use to properly
+ * set up memory. If we aren't, we'll fake a memory map.
+ *
+ * We check to see that the memory map contains at least 2 elements
+ * before we'll use it, because the detection code in setup.S may
+ * not be perfect and most every PC known to man has two memory
+ * regions: one from 0 to 640k, and one from 1mb up. (The IBM
+ * thinkpad 560x, for example, does not cooperate with the memory
+ * detection code.)
+ */
+static int __init copy_e820_map(struct e820entry * biosmap, int nr_map)
+{
+ /* Only one memory region (or negative)? Ignore it */
+ if (nr_map < 2)
+ return -1;
+
+ do {
+ unsigned long long start = biosmap->addr;
+ unsigned long long size = biosmap->size;
+ unsigned long long end = start + size;
+ unsigned long type = biosmap->type;
+
+ /* Overflow in 64 bits? Ignore the memory map. */
+ if (start > end)
+ return -1;
+
+ /*
+ * Some BIOSes claim RAM in the 640k - 1M region.
+ * Not right. Fix it up.
+ */
+ if (type == E820_RAM) {
+ if (start < 0x100000ULL && end > 0xA0000ULL) {
+ if (start < 0xA0000ULL)
+ add_memory_region(start,
0xA0000ULL-start, type);
+ if (end <= 0x100000ULL)
+ continue;
+ start = 0x100000ULL;
+ size = end - start;
+ }
+ }
+ add_memory_region(start, size, type);
+ } while (biosmap++,--nr_map);
+ return 0;
+}
+#endif
+
+#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
+struct edd edd;
+#ifdef CONFIG_EDD_MODULE
+EXPORT_SYMBOL(edd);
+#endif
+/**
+ * copy_edd() - Copy the BIOS EDD information
+ * from boot_params into a safe place.
+ *
+ */
+static inline void copy_edd(void)
+{
+ memcpy(edd.mbr_signature, EDD_MBR_SIGNATURE, sizeof(edd.mbr_signature));
+ memcpy(edd.edd_info, EDD_BUF, sizeof(edd.edd_info));
+ edd.mbr_signature_nr = EDD_MBR_SIG_NR;
+ edd.edd_info_nr = EDD_NR;
+}
+#else
+static inline void copy_edd(void)
+{
+}
+#endif
+
+/*
+ * Do NOT EVER look at the BIOS memory size location.
+ * It does not work on many machines.
+ */
+#define LOWMEMSIZE() (0x9f000)
+
+static void __init parse_cmdline_early (char ** cmdline_p)
+{
+ char c = ' ', *to = command_line, *from = saved_command_line;
+ int len = 0, max_cmdline;
+ int userdef = 0;
+
+ if ((max_cmdline = MAX_GUEST_CMDLINE) > COMMAND_LINE_SIZE)
+ max_cmdline = COMMAND_LINE_SIZE;
+ memcpy(saved_command_line, xen_start_info.cmd_line, max_cmdline);
+ /* Save unparsed command line copy for /proc/cmdline */
+ saved_command_line[max_cmdline-1] = '\0';
+
+ for (;;) {
+ if (c != ' ')
+ goto next_char;
+ /*
+ * "mem=nopentium" disables the 4MB page tables.
+ * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM
+ * to <mem>, overriding the bios size.
+ * "memmap=XXX[KkmM]@XXX[KkmM]" defines a memory region from
+ * <start> to <start>+<mem>, overriding the bios size.
+ *
+ * HPA tells me bootloaders need to parse mem=, so no new
+ * option should be mem= [also see Documentation/i386/boot.txt]
+ */
+ if (!memcmp(from, "mem=", 4)) {
+ if (to != command_line)
+ to--;
+ if (!memcmp(from+4, "nopentium", 9)) {
+ from += 9+4;
+ clear_bit(X86_FEATURE_PSE,
boot_cpu_data.x86_capability);
+ disable_pse = 1;
+ } else {
+ /* If the user specifies memory size, we
+ * limit the BIOS-provided memory map to
+ * that size. exactmap can be used to specify
+ * the exact map. mem=number can be used to
+ * trim the existing memory map.
+ */
+ unsigned long long mem_size;
+
+ mem_size = memparse(from+4, &from);
+#if 0
+ limit_regions(mem_size);
+ userdef=1;
+#else
+ xen_override_max_pfn =
+ (unsigned long)(mem_size>>PAGE_SHIFT);
+#endif
+ }
+ }
+
+ else if (!memcmp(from, "memmap=", 7)) {
+ if (to != command_line)
+ to--;
+ if (!memcmp(from+7, "exactmap", 8)) {
+ from += 8+7;
+ e820.nr_map = 0;
+ userdef = 1;
+ } else {
+ /* If the user specifies memory size, we
+ * limit the BIOS-provided memory map to
+ * that size. exactmap can be used to specify
+ * the exact map. mem=number can be used to
+ * trim the existing memory map.
+ */
+ unsigned long long start_at, mem_size;
+
+ mem_size = memparse(from+7, &from);
+ if (*from == '@') {
+ start_at = memparse(from+1, &from);
+ add_memory_region(start_at, mem_size,
E820_RAM);
+ } else if (*from == '#') {
+ start_at = memparse(from+1, &from);
+ add_memory_region(start_at, mem_size,
E820_ACPI);
+ } else if (*from == '$') {
+ start_at = memparse(from+1, &from);
+ add_memory_region(start_at, mem_size,
E820_RESERVED);
+ } else {
+ limit_regions(mem_size);
+ userdef=1;
+ }
+ }
+ }
+
+ else if (!memcmp(from, "noexec=", 7))
+ noexec_setup(from + 7);
+
+
+#ifdef CONFIG_X86_MPPARSE
+ /*
+ * If the BIOS enumerates physical processors before logical,
+ * maxcpus=N at enumeration-time can be used to disable HT.
+ */
+ else if (!memcmp(from, "maxcpus=", 8)) {
+ extern unsigned int maxcpus;
+
+ maxcpus = simple_strtoul(from + 8, NULL, 0);
+ }
+#endif
+
+#ifdef CONFIG_ACPI_BOOT
+ /* "acpi=off" disables both ACPI table parsing and interpreter
*/
+ else if (!memcmp(from, "acpi=off", 8)) {
+ disable_acpi();
+ }
+
+ /* acpi=force to over-ride black-list */
+ else if (!memcmp(from, "acpi=force", 10)) {
+ acpi_force = 1;
+ acpi_ht = 1;
+ acpi_disabled = 0;
+ }
+
+ /* acpi=strict disables out-of-spec workarounds */
+ else if (!memcmp(from, "acpi=strict", 11)) {
+ acpi_strict = 1;
+ }
+
+ /* Limit ACPI just to boot-time to enable HT */
+ else if (!memcmp(from, "acpi=ht", 7)) {
+ if (!acpi_force)
+ disable_acpi();
+ acpi_ht = 1;
+ }
+
+ /* "pci=noacpi" disable ACPI IRQ routing and PCI scan */
+ else if (!memcmp(from, "pci=noacpi", 10)) {
+ acpi_disable_pci();
+ }
+ /* "acpi=noirq" disables ACPI interrupt routing */
+ else if (!memcmp(from, "acpi=noirq", 10)) {
+ acpi_noirq_set();
+ }
+
+ else if (!memcmp(from, "acpi_sci=edge", 13))
+ acpi_sci_flags.trigger = 1;
+
+ else if (!memcmp(from, "acpi_sci=level", 14))
+ acpi_sci_flags.trigger = 3;
+
+ else if (!memcmp(from, "acpi_sci=high", 13))
+ acpi_sci_flags.polarity = 1;
+
+ else if (!memcmp(from, "acpi_sci=low", 12))
+ acpi_sci_flags.polarity = 3;
+
+#ifdef CONFIG_X86_IO_APIC
+ else if (!memcmp(from, "acpi_skip_timer_override", 24))
+ acpi_skip_timer_override = 1;
+#endif
+
+#ifdef CONFIG_X86_LOCAL_APIC
+ /* disable IO-APIC */
+ else if (!memcmp(from, "noapic", 6))
+ disable_ioapic_setup();
+#endif /* CONFIG_X86_LOCAL_APIC */
+#endif /* CONFIG_ACPI_BOOT */
+
+ /*
+ * highmem=size forces highmem to be exactly 'size' bytes.
+ * This works even on boxes that have no highmem otherwise.
+ * This also works to reduce highmem size on bigger boxes.
+ */
+ else if (!memcmp(from, "highmem=", 8))
+ highmem_pages = memparse(from+8, &from) >> PAGE_SHIFT;
+
+ /*
+ * vmalloc=size forces the vmalloc area to be exactly 'size'
+ * bytes. This can be used to increase (or decrease) the
+ * vmalloc area - the default is 128m.
+ */
+ else if (!memcmp(from, "vmalloc=", 8))
+ __VMALLOC_RESERVE = memparse(from+8, &from);
+
+ next_char:
+ c = *(from++);
+ if (!c)
+ break;
+ if (COMMAND_LINE_SIZE <= ++len)
+ break;
+ *(to++) = c;
+ }
+ *to = '\0';
+ *cmdline_p = command_line;
+ if (userdef) {
+ printk(KERN_INFO "user-defined physical RAM map:\n");
+ print_memory_map("user");
+ }
+}
+
+#if 0 /* !XEN */
+/*
+ * Callback for efi_memory_walk.
+ */
+static int __init
+efi_find_max_pfn(unsigned long start, unsigned long end, void *arg)
+{
+ unsigned long *max_pfn = arg, pfn;
+
+ if (start < end) {
+ pfn = PFN_UP(end -1);
+ if (pfn > *max_pfn)
+ *max_pfn = pfn;
+ }
+ return 0;
+}
+
+
+/*
+ * Find the highest page frame number we have available
+ */
+void __init find_max_pfn(void)
+{
+ int i;
+
+ max_pfn = 0;
+ if (efi_enabled) {
+ efi_memmap_walk(efi_find_max_pfn, &max_pfn);
+ return;
+ }
+
+ for (i = 0; i < e820.nr_map; i++) {
+ unsigned long start, end;
+ /* RAM? */
+ if (e820.map[i].type != E820_RAM)
+ continue;
+ start = PFN_UP(e820.map[i].addr);
+ end = PFN_DOWN(e820.map[i].addr + e820.map[i].size);
+ if (start >= end)
+ continue;
+ if (end > max_pfn)
+ max_pfn = end;
+ }
+}
+#else
+/* We don't use the fake e820 because we need to respond to user override. */
+void __init find_max_pfn(void)
+{
+ if ( xen_override_max_pfn < xen_start_info.nr_pages )
+ xen_override_max_pfn = xen_start_info.nr_pages;
+ max_pfn = xen_override_max_pfn;
+}
+#endif /* XEN */
+
+/*
+ * Determine low and high memory ranges:
+ */
+unsigned long __init find_max_low_pfn(void)
+{
+ unsigned long max_low_pfn;
+
+ max_low_pfn = max_pfn;
+ if (max_low_pfn > MAXMEM_PFN) {
+ if (highmem_pages == -1)
+ highmem_pages = max_pfn - MAXMEM_PFN;
+ if (highmem_pages + MAXMEM_PFN < max_pfn)
+ max_pfn = MAXMEM_PFN + highmem_pages;
+ if (highmem_pages + MAXMEM_PFN > max_pfn) {
+ printk("only %luMB highmem pages available, ignoring
highmem size of %uMB.\n", pages_to_mb(max_pfn - MAXMEM_PFN),
pages_to_mb(highmem_pages));
+ highmem_pages = 0;
+ }
+ max_low_pfn = MAXMEM_PFN;
+#ifndef CONFIG_HIGHMEM
+ /* Maximum memory usable is what is directly addressable */
+ printk(KERN_WARNING "Warning only %ldMB will be used.\n",
+ MAXMEM>>20);
+ if (max_pfn > MAX_NONPAE_PFN)
+ printk(KERN_WARNING "Use a PAE enabled kernel.\n");
+ else
+ printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
+ max_pfn = MAXMEM_PFN;
+#else /* !CONFIG_HIGHMEM */
+#ifndef CONFIG_X86_PAE
+ if (max_pfn > MAX_NONPAE_PFN) {
+ max_pfn = MAX_NONPAE_PFN;
+ printk(KERN_WARNING "Warning only 4GB will be used.\n");
+ printk(KERN_WARNING "Use a PAE enabled kernel.\n");
+ }
+#endif /* !CONFIG_X86_PAE */
+#endif /* !CONFIG_HIGHMEM */
+ } else {
+ if (highmem_pages == -1)
+ highmem_pages = 0;
+#ifdef CONFIG_HIGHMEM
+ if (highmem_pages >= max_pfn) {
+ printk(KERN_ERR "highmem size specified (%uMB) is
bigger than pages available (%luMB)!.\n", pages_to_mb(highmem_pages),
pages_to_mb(max_pfn));
+ highmem_pages = 0;
+ }
+ if (highmem_pages) {
+ if (max_low_pfn-highmem_pages < 64*1024*1024/PAGE_SIZE){
+ printk(KERN_ERR "highmem size %uMB results in
smaller than 64MB lowmem, ignoring it.\n", pages_to_mb(highmem_pages));
+ highmem_pages = 0;
+ }
+ max_low_pfn -= highmem_pages;
+ }
+#else
+ if (highmem_pages)
+ printk(KERN_ERR "ignoring highmem size on non-highmem
kernel!\n");
+#endif
+ }
+ return max_low_pfn;
+}
+
+#ifndef CONFIG_DISCONTIGMEM
+
+/*
+ * Free all available memory for boot time allocation. Used
+ * as a callback function by efi_memory_walk()
+ */
+
+static int __init
+free_available_memory(unsigned long start, unsigned long end, void *arg)
+{
+ /* check max_low_pfn */
+ if (start >= ((max_low_pfn + 1) << PAGE_SHIFT))
+ return 0;
+ if (end >= ((max_low_pfn + 1) << PAGE_SHIFT))
+ end = (max_low_pfn + 1) << PAGE_SHIFT;
+ if (start < end)
+ free_bootmem(start, end - start);
+
+ return 0;
+}
+/*
+ * Register fully available low RAM pages with the bootmem allocator.
+ */
+static void __init register_bootmem_low_pages(unsigned long max_low_pfn)
+{
+ int i;
+
+ if (efi_enabled) {
+ efi_memmap_walk(free_available_memory, NULL);
+ return;
+ }
+ for (i = 0; i < e820.nr_map; i++) {
+ unsigned long curr_pfn, last_pfn, size;
+ /*
+ * Reserve usable low memory
+ */
+ if (e820.map[i].type != E820_RAM)
+ continue;
+ /*
+ * We are rounding up the start address of usable memory:
+ */
+ curr_pfn = PFN_UP(e820.map[i].addr);
+ if (curr_pfn >= max_low_pfn)
+ continue;
+ /*
+ * ... and at the end of the usable range downwards:
+ */
+ last_pfn = PFN_DOWN(e820.map[i].addr + e820.map[i].size);
+
+ if (last_pfn > max_low_pfn)
+ last_pfn = max_low_pfn;
+
+ /*
+ * .. finally, did all the rounding and playing
+ * around just make the area go away?
+ */
+ if (last_pfn <= curr_pfn)
+ continue;
+
+ size = last_pfn - curr_pfn;
+ free_bootmem(PFN_PHYS(curr_pfn), PFN_PHYS(size));
+ }
+}
+
+/*
+ * workaround for Dell systems that neglect to reserve EBDA
+ */
+static void __init reserve_ebda_region(void)
+{
+ unsigned int addr;
+ addr = get_bios_ebda();
+ if (addr)
+ reserve_bootmem(addr, PAGE_SIZE);
+}
+
+static unsigned long __init setup_memory(void)
+{
+ unsigned long bootmap_size, start_pfn, max_low_pfn;
+
+ /*
+ * partially used pages are not usable - thus
+ * we are rounding upwards:
+ */
+ start_pfn = PFN_UP(__pa(xen_start_info.pt_base)) +
xen_start_info.nr_pt_frames;
+
+ find_max_pfn();
+
+ max_low_pfn = find_max_low_pfn();
+
+#ifdef CONFIG_HIGHMEM
+ highstart_pfn = highend_pfn = max_pfn;
+ if (max_pfn > max_low_pfn) {
+ highstart_pfn = max_low_pfn;
+ }
+ printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
+ pages_to_mb(highend_pfn - highstart_pfn));
+#endif
+ printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
+ pages_to_mb(max_low_pfn));
+ /*
+ * Initialize the boot-time allocator (with low memory only):
+ */
+ bootmap_size = init_bootmem(start_pfn, max_low_pfn);
+
+ register_bootmem_low_pages(max_low_pfn);
+
+ /*
+ * Reserve the bootmem bitmap itself as well. We do this in two
+ * steps (first step was init_bootmem()) because this catches
+ * the (very unlikely) case of us accidentally initializing the
+ * bootmem allocator with an invalid RAM area.
+ */
+ reserve_bootmem(HIGH_MEMORY, (PFN_PHYS(start_pfn) +
+ bootmap_size + PAGE_SIZE-1) - (HIGH_MEMORY));
+
+ /* reserve EBDA region, it's a 4K region */
+ reserve_ebda_region();
+
+ /* could be an AMD 768MPX chipset. Reserve a page before VGA to prevent
+ PCI prefetch into it (errata #56). Usually the page is reserved anyways,
+ unless you have no PS/2 mouse plugged in. */
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
+ boot_cpu_data.x86 == 6)
+ reserve_bootmem(0xa0000 - 4096, 4096);
+
+#ifdef CONFIG_SMP
+ /*
+ * But first pinch a few for the stack/trampoline stuff
+ * FIXME: Don't need the extra page at 4K, but need to fix
+ * trampoline before removing it. (see the GDT stuff)
+ */
+ reserve_bootmem(PAGE_SIZE, PAGE_SIZE);
+#endif
+#ifdef CONFIG_ACPI_SLEEP
+ /*
+ * Reserve low memory region for sleep support.
+ */
+ acpi_reserve_bootmem();
+#endif
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (xen_start_info.mod_start) {
+ if (INITRD_START + INITRD_SIZE <= (max_low_pfn << PAGE_SHIFT)) {
+ /*reserve_bootmem(INITRD_START, INITRD_SIZE);*/
+ initrd_start = INITRD_START + PAGE_OFFSET;
+ initrd_end = initrd_start+INITRD_SIZE;
+ initrd_below_start_ok = 1;
+ }
+ else {
+ printk(KERN_ERR "initrd extends beyond end of memory "
+ "(0x%08lx > 0x%08lx)\ndisabling initrd\n",
+ INITRD_START + INITRD_SIZE,
+ max_low_pfn << PAGE_SHIFT);
+ initrd_start = 0;
+ }
+ }
+#endif
+
+ phys_to_machine_mapping = (unsigned int *)xen_start_info.mfn_list;
+
+ return max_low_pfn;
+}
+#else
+extern unsigned long setup_memory(void);
+#endif /* !CONFIG_DISCONTIGMEM */
+
+/*
+ * Request address space for all standard RAM and ROM resources
+ * and also for regions reported as reserved by the e820.
+ */
+static void __init
+legacy_init_iomem_resources(struct resource *code_resource, struct resource
*data_resource)
+{
+ int i;
+
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ probe_roms();
+#endif
+ for (i = 0; i < e820.nr_map; i++) {
+ struct resource *res;
+ if (e820.map[i].addr + e820.map[i].size > 0x100000000ULL)
+ continue;
+ res = alloc_bootmem_low(sizeof(struct resource));
+ switch (e820.map[i].type) {
+ case E820_RAM: res->name = "System RAM"; break;
+ case E820_ACPI: res->name = "ACPI Tables"; break;
+ case E820_NVS: res->name = "ACPI Non-volatile Storage"; break;
+ default: res->name = "reserved";
+ }
+ res->start = e820.map[i].addr;
+ res->end = res->start + e820.map[i].size - 1;
+ res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+ request_resource(&iomem_resource, res);
+ if (e820.map[i].type == E820_RAM) {
+ /*
+ * We don't know which RAM region contains kernel data,
+ * so we try it repeatedly and let the resource manager
+ * test it.
+ */
+ request_resource(res, code_resource);
+ request_resource(res, data_resource);
+ }
+ }
+}
+
+/*
+ * Request address space for all standard resources
+ */
+static void __init register_memory(void)
+{
+ unsigned long gapstart, gapsize;
+ unsigned long long last;
+ int i;
+
+ if (efi_enabled)
+ efi_initialize_iomem_resources(&code_resource, &data_resource);
+ else
+ legacy_init_iomem_resources(&code_resource, &data_resource);
+
+ if (xen_start_info.flags & SIF_INITDOMAIN)
+ /* EFI systems may still have VGA */
+ request_resource(&iomem_resource, &video_ram_resource);
+
+ /* request I/O space for devices used on all i[345]86 PCs */
+ for (i = 0; i < STANDARD_IO_RESOURCES; i++)
+ request_resource(&ioport_resource, &standard_io_resources[i]);
+
+ /*
+ * Search for the bigest gap in the low 32 bits of the e820
+ * memory space.
+ */
+ last = 0x100000000ull;
+ gapstart = 0x10000000;
+ gapsize = 0x400000;
+ i = e820.nr_map;
+ while (--i >= 0) {
+ unsigned long long start = e820.map[i].addr;
+ unsigned long long end = start + e820.map[i].size;
+
+ /*
+ * Since "last" is at most 4GB, we know we'll
+ * fit in 32 bits if this condition is true
+ */
+ if (last > end) {
+ unsigned long gap = last - end;
+
+ if (gap > gapsize) {
+ gapsize = gap;
+ gapstart = end;
+ }
+ }
+ if (start < last)
+ last = start;
+ }
+
+ /*
+ * Start allocating dynamic PCI memory a bit into the gap,
+ * aligned up to the nearest megabyte.
+ *
+ * Question: should we try to pad it up a bit (do something
+ * like " + (gapsize >> 3)" in there too?). We now have the
+ * technology.
+ */
+ pci_mem_start = (gapstart + 0xfffff) & ~0xfffff;
+
+ printk("Allocating PCI resources starting at %08lx (gap:
%08lx:%08lx)\n",
+ pci_mem_start, gapstart, gapsize);
+}
+
+/* Use inline assembly to define this because the nops are defined
+ as inline assembly strings in the include files and we cannot
+ get them easily into strings. */
+asm("\t.data\nintelnops: "
+ GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5
GENERIC_NOP6
+ GENERIC_NOP7 GENERIC_NOP8);
+asm("\t.data\nk8nops: "
+ K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
+ K8_NOP7 K8_NOP8);
+asm("\t.data\nk7nops: "
+ K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6
+ K7_NOP7 K7_NOP8);
+
+extern unsigned char intelnops[], k8nops[], k7nops[];
+static unsigned char *intel_nops[ASM_NOP_MAX+1] = {
+ NULL,
+ intelnops,
+ intelnops + 1,
+ intelnops + 1 + 2,
+ intelnops + 1 + 2 + 3,
+ intelnops + 1 + 2 + 3 + 4,
+ intelnops + 1 + 2 + 3 + 4 + 5,
+ intelnops + 1 + 2 + 3 + 4 + 5 + 6,
+ intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+};
+static unsigned char *k8_nops[ASM_NOP_MAX+1] = {
+ NULL,
+ k8nops,
+ k8nops + 1,
+ k8nops + 1 + 2,
+ k8nops + 1 + 2 + 3,
+ k8nops + 1 + 2 + 3 + 4,
+ k8nops + 1 + 2 + 3 + 4 + 5,
+ k8nops + 1 + 2 + 3 + 4 + 5 + 6,
+ k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+};
+static unsigned char *k7_nops[ASM_NOP_MAX+1] = {
+ NULL,
+ k7nops,
+ k7nops + 1,
+ k7nops + 1 + 2,
+ k7nops + 1 + 2 + 3,
+ k7nops + 1 + 2 + 3 + 4,
+ k7nops + 1 + 2 + 3 + 4 + 5,
+ k7nops + 1 + 2 + 3 + 4 + 5 + 6,
+ k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+};
+static struct nop {
+ int cpuid;
+ unsigned char **noptable;
+} noptypes[] = {
+ { X86_FEATURE_K8, k8_nops },
+ { X86_FEATURE_K7, k7_nops },
+ { -1, NULL }
+};
+
+/* Replace instructions with better alternatives for this CPU type.
+
+ This runs before SMP is initialized to avoid SMP problems with
+ self modifying code. This implies that assymetric systems where
+ APs have less capabilities than the boot processor are not handled.
+ In this case boot with "noreplacement". */
+void apply_alternatives(void *start, void *end)
+{
+ struct alt_instr *a;
+ int diff, i, k;
+ unsigned char **noptable = intel_nops;
+ for (i = 0; noptypes[i].cpuid >= 0; i++) {
+ if (boot_cpu_has(noptypes[i].cpuid)) {
+ noptable = noptypes[i].noptable;
+ break;
+ }
+ }
+ for (a = start; (void *)a < end; a++) {
+ if (!boot_cpu_has(a->cpuid))
+ continue;
+ BUG_ON(a->replacementlen > a->instrlen);
+ memcpy(a->instr, a->replacement, a->replacementlen);
+ diff = a->instrlen - a->replacementlen;
+ /* Pad the rest with nops */
+ for (i = a->replacementlen; diff > 0; diff -= k, i += k) {
+ k = diff;
+ if (k > ASM_NOP_MAX)
+ k = ASM_NOP_MAX;
+ memcpy(a->instr + i, noptable[k], k);
+ }
+ }
+}
+
+static int no_replacement __initdata = 0;
+
+void __init alternative_instructions(void)
+{
+ extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
+ if (no_replacement)
+ return;
+ apply_alternatives(__alt_instructions, __alt_instructions_end);
+}
+
+static int __init noreplacement_setup(char *s)
+{
+ no_replacement = 1;
+ return 0;
+}
+
+__setup("noreplacement", noreplacement_setup);
+
+static char * __init machine_specific_memory_setup(void);
+
+#ifdef CONFIG_MCA
+static void set_mca_bus(int x)
+{
+ MCA_bus = x;
+}
+#else
+static void set_mca_bus(int x) { }
+#endif
+
+/*
+ * Determine if we were loaded by an EFI loader. If so, then we have also been
+ * passed the efi memmap, systab, etc., so we should use these data structures
+ * for initialization. Note, the efi init code path is determined by the
+ * global efi_enabled. This allows the same kernel image to be used on existing
+ * systems (with a traditional BIOS) as well as on EFI systems.
+ */
+void __init setup_arch(char **cmdline_p)
+{
+ int i, j;
+ physdev_op_t op;
+ unsigned long max_low_pfn;
+
+ /* Force a quick death if the kernel panics. */
+ extern int panic_timeout;
+ if (panic_timeout == 0)
+ panic_timeout = 1;
+
+ /* Register a call for panic conditions. */
+ notifier_chain_register(&panic_notifier_list, &xen_panic_block);
+
+ HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments);
+ HYPERVISOR_vm_assist(VMASST_CMD_enable,
+ VMASST_TYPE_writable_pagetables);
+
+ memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
+ early_cpu_init();
+
+ /*
+ * FIXME: This isn't an official loader_type right
+ * now but does currently work with elilo.
+ * If we were configured as an EFI kernel, check to make
+ * sure that we were loaded correctly from elilo and that
+ * the system table is valid. If not, then initialize normally.
+ */
+#ifdef CONFIG_EFI
+ if ((LOADER_TYPE == 0x50) && EFI_SYSTAB)
+ efi_enabled = 1;
+#endif
+
+ /* This must be initialized to UNNAMED_MAJOR for ipconfig to work
+ properly. Setting ROOT_DEV to default to /dev/ram0 breaks initrd.
+ */
+ ROOT_DEV = MKDEV(UNNAMED_MAJOR,0);
+ drive_info = DRIVE_INFO;
+ screen_info = SCREEN_INFO;
+ edid_info = EDID_INFO;
+ apm_info.bios = APM_BIOS_INFO;
+ ist_info = IST_INFO;
+ saved_videomode = VIDEO_MODE;
+ if( SYS_DESC_TABLE.length != 0 ) {
+ set_mca_bus(SYS_DESC_TABLE.table[3] & 0x2);
+ machine_id = SYS_DESC_TABLE.table[0];
+ machine_submodel_id = SYS_DESC_TABLE.table[1];
+ BIOS_revision = SYS_DESC_TABLE.table[2];
+ }
+ aux_device_present = AUX_DEVICE_INFO;
+ bootloader_type = LOADER_TYPE;
+
+#ifdef CONFIG_XEN_PHYSDEV_ACCESS
+ /* This is drawn from a dump from vgacon:startup in standard Linux. */
+ screen_info.orig_video_mode = 3;
+ screen_info.orig_video_isVGA = 1;
+ screen_info.orig_video_lines = 25;
+ screen_info.orig_video_cols = 80;
+ screen_info.orig_video_ega_bx = 3;
+ screen_info.orig_video_points = 16;
+#endif
+
+#ifdef CONFIG_BLK_DEV_RAM
+ rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK;
+ rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0);
+ rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0);
+#endif
+ ARCH_SETUP
+ if (efi_enabled)
+ efi_init();
+ else {
+ printk(KERN_INFO "BIOS-provided physical RAM map:\n");
+ print_memory_map(machine_specific_memory_setup());
+ }
+
+ copy_edd();
+
+ if (!MOUNT_ROOT_RDONLY)
+ root_mountflags &= ~MS_RDONLY;
+ init_mm.start_code = (unsigned long) _text;
+ init_mm.end_code = (unsigned long) _etext;
+ init_mm.end_data = (unsigned long) _edata;
+ init_mm.brk = (PFN_UP(__pa(xen_start_info.pt_base)) +
+ xen_start_info.nr_pt_frames) << PAGE_SHIFT;
+
+ /* XEN: This is nonsense: kernel may not even be contiguous in RAM. */
+ /*code_resource.start = virt_to_phys(_text);*/
+ /*code_resource.end = virt_to_phys(_etext)-1;*/
+ /*data_resource.start = virt_to_phys(_etext);*/
+ /*data_resource.end = virt_to_phys(_edata)-1;*/
+
+ parse_cmdline_early(cmdline_p);
+
+ max_low_pfn = setup_memory();
+
+ /*
+ * NOTE: before this point _nobody_ is allowed to allocate
+ * any memory using the bootmem allocator. Although the
+ * alloctor is now initialised only the first 8Mb of the kernel
+ * virtual address space has been mapped. All allocations before
+ * paging_init() has completed must use the alloc_bootmem_low_pages()
+ * variant (which allocates DMA'able memory) and care must be taken
+ * not to exceed the 8Mb limit.
+ */
+
+#ifdef CONFIG_SMP
+ smp_alloc_memory(); /* AP processor realmode stacks in low memory*/
+#endif
+ paging_init();
+
+#ifdef CONFIG_X86_FIND_SMP_CONFIG
+ /*
+ * Find and reserve possible boot-time SMP configuration:
+ */
+ find_smp_config();
+#endif
+
+ /* Make sure we have a correctly sized P->M table. */
+ if (max_pfn != xen_start_info.nr_pages) {
+ phys_to_machine_mapping = alloc_bootmem_low_pages(
+ max_pfn * sizeof(unsigned long));
+
+ if (max_pfn > xen_start_info.nr_pages) {
+ /* set to INVALID_P2M_ENTRY */
+ memset(phys_to_machine_mapping, ~0,
+ max_pfn * sizeof(unsigned long));
+ memcpy(phys_to_machine_mapping,
+ (unsigned long *)xen_start_info.mfn_list,
+ xen_start_info.nr_pages * sizeof(unsigned
long));
+ } else {
+ memcpy(phys_to_machine_mapping,
+ (unsigned long *)xen_start_info.mfn_list,
+ max_pfn * sizeof(unsigned long));
+ if (HYPERVISOR_dom_mem_op(
+ MEMOP_decrease_reservation,
+ (unsigned long *)xen_start_info.mfn_list +
max_pfn,
+ xen_start_info.nr_pages - max_pfn, 0) !=
+ (xen_start_info.nr_pages - max_pfn)) BUG();
+ }
+ free_bootmem(
+ __pa(xen_start_info.mfn_list),
+ PFN_PHYS(PFN_UP(xen_start_info.nr_pages *
+ sizeof(unsigned long))));
+ }
+
+ pfn_to_mfn_frame_list = alloc_bootmem_low_pages(PAGE_SIZE);
+ for ( i=0, j=0; i < max_pfn; i+=(PAGE_SIZE/sizeof(unsigned long)), j++ )
+ {
+ pfn_to_mfn_frame_list[j] =
+ virt_to_machine(&phys_to_machine_mapping[i]) >> PAGE_SHIFT;
+ }
+ HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list =
+ virt_to_machine(pfn_to_mfn_frame_list) >> PAGE_SHIFT;
+
+
+ /*
+ * NOTE: at this point the bootmem allocator is fully available.
+ */
+
+#ifdef CONFIG_EARLY_PRINTK
+ {
+ char *s = strstr(*cmdline_p, "earlyprintk=");
+ if (s) {
+ extern void setup_early_printk(char *);
+
+ setup_early_printk(s);
+ printk("early console enabled\n");
+ }
+ }
+#endif
+
+
+ dmi_scan_machine();
+
+#ifdef CONFIG_X86_GENERICARCH
+ generic_apic_probe(*cmdline_p);
+#endif
+ if (efi_enabled)
+ efi_map_memmap();
+
+ op.cmd = PHYSDEVOP_SET_IOPL;
+ op.u.set_iopl.iopl = current->thread.io_pl = 1;
+ HYPERVISOR_physdev_op(&op);
+
+#ifdef CONFIG_ACPI_BOOT
+ if (!(xen_start_info.flags & SIF_INITDOMAIN)) {
+ printk(KERN_INFO "ACPI in unprivileged domain disabled\n");
+ acpi_disabled = 1;
+ acpi_ht = 0;
+ }
+#endif
+
+ /*
+ * Parse the ACPI tables for possible boot-time SMP configuration.
+ */
+ acpi_boot_table_init();
+ acpi_boot_init();
+
+#ifdef CONFIG_X86_LOCAL_APIC
+ if (smp_found_config)
+ get_smp_config();
+#endif
+
+ /* XXX Disable irqdebug until we have a way to avoid interrupt
+ * conflicts. */
+ noirqdebug_setup("");
+
+ register_memory();
+
+ if (xen_start_info.flags & SIF_INITDOMAIN) {
+ if (!(xen_start_info.flags & SIF_PRIVILEGED))
+ panic("Xen granted us console access "
+ "but not privileged status");
+
+#ifdef CONFIG_VT
+#if defined(CONFIG_VGA_CONSOLE)
+ if (!efi_enabled ||
+ (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
+ conswitchp = &vga_con;
+#elif defined(CONFIG_DUMMY_CONSOLE)
+ conswitchp = &dummy_con;
+#endif
+#endif
+ } else {
+#ifdef CONFIG_XEN_PRIVILEGED_GUEST
+ extern const struct consw xennull_con;
+ extern int console_use_vt;
+#if defined(CONFIG_VGA_CONSOLE)
+ /* disable VGA driver */
+ ORIG_VIDEO_ISVGA = VIDEO_TYPE_VLFB;
+#endif
+ conswitchp = &xennull_con;
+ console_use_vt = 0;
+#endif
+ }
+}
+
+static int
+xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr)
+{
+ HYPERVISOR_crash();
+ /* we're never actually going to get here... */
+ return NOTIFY_DONE;
+}
+
+#include "setup_arch_post.h"
+/*
+ * Local Variables:
+ * mode:c
+ * c-file-style:"k&r"
+ * c-basic-offset:8
+ * End:
+ */
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/mm/mremap.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/mm/mremap.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,390 @@
+/*
+ * linux/mm/remap.c
+ *
+ * (C) Copyright 1996 Linus Torvalds
+ */
+
+#include <linux/slab.h>
+#include <linux/smp_lock.h>
+#include <linux/shm.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+
+extern int vm_enough_memory(long pages);
+
+static inline pte_t *get_one_pte(struct mm_struct *mm, unsigned long addr)
+{
+ pgd_t * pgd;
+ pmd_t * pmd;
+ pte_t * pte = NULL;
+
+ pgd = pgd_offset(mm, addr);
+ if (pgd_none(*pgd))
+ goto end;
+ if (pgd_bad(*pgd)) {
+ pgd_ERROR(*pgd);
+ pgd_clear(pgd);
+ goto end;
+ }
+
+ pmd = pmd_offset(pgd, addr);
+ if (pmd_none(*pmd))
+ goto end;
+ if (pmd_bad(*pmd)) {
+ pmd_ERROR(*pmd);
+ pmd_clear(pmd);
+ goto end;
+ }
+
+ pte = pte_offset(pmd, addr);
+ if (pte_none(*pte))
+ pte = NULL;
+end:
+ return pte;
+}
+
+static inline pte_t *alloc_one_pte(struct mm_struct *mm, unsigned long addr)
+{
+ pmd_t * pmd;
+ pte_t * pte = NULL;
+
+ pmd = pmd_alloc(mm, pgd_offset(mm, addr), addr);
+ if (pmd)
+ pte = pte_alloc(mm, pmd, addr);
+ return pte;
+}
+
+static inline int copy_one_pte(struct mm_struct *mm, pte_t * src, pte_t * dst)
+{
+ int error = 0;
+ pte_t pte;
+
+ if (!pte_none(*src)) {
+ pte = ptep_get_and_clear(src);
+ if (!dst) {
+ /* No dest? We must put it back. */
+ dst = src;
+ error++;
+ }
+ set_pte(dst, pte);
+ }
+ return error;
+}
+
+static int move_one_page(struct mm_struct *mm, unsigned long old_addr,
unsigned long new_addr)
+{
+ int error = 0;
+ pte_t * src, * dst;
+
+ spin_lock(&mm->page_table_lock);
+ src = get_one_pte(mm, old_addr);
+ if (src) {
+ dst = alloc_one_pte(mm, new_addr);
+ src = get_one_pte(mm, old_addr);
+ if (src)
+ error = copy_one_pte(mm, src, dst);
+ }
+ spin_unlock(&mm->page_table_lock);
+ return error;
+}
+
+static int move_page_tables(struct mm_struct * mm,
+ unsigned long new_addr, unsigned long old_addr, unsigned long len)
+{
+ unsigned long offset = len;
+
+ flush_cache_range(mm, old_addr, old_addr + len);
+
+ /*
+ * This is not the clever way to do this, but we're taking the
+ * easy way out on the assumption that most remappings will be
+ * only a few pages.. This also makes error recovery easier.
+ */
+ while (offset) {
+ offset -= PAGE_SIZE;
+ if (move_one_page(mm, old_addr + offset, new_addr + offset))
+ goto oops_we_failed;
+ }
+ flush_tlb_range(mm, old_addr, old_addr + len);
+ return 0;
+
+ /*
+ * Ok, the move failed because we didn't have enough pages for
+ * the new page table tree. This is unlikely, but we have to
+ * take the possibility into account. In that case we just move
+ * all the pages back (this will work, because we still have
+ * the old page tables)
+ */
+oops_we_failed:
+ flush_cache_range(mm, new_addr, new_addr + len);
+ while ((offset += PAGE_SIZE) < len)
+ move_one_page(mm, new_addr + offset, old_addr + offset);
+ zap_page_range(mm, new_addr, len);
+ return -1;
+}
+
+static inline unsigned long move_vma(struct vm_area_struct * vma,
+ unsigned long addr, unsigned long old_len, unsigned long new_len,
+ unsigned long new_addr)
+{
+ struct mm_struct * mm = vma->vm_mm;
+ struct vm_area_struct * new_vma, * next, * prev;
+ int allocated_vma;
+
+ new_vma = NULL;
+ next = find_vma_prev(mm, new_addr, &prev);
+ if (next) {
+ if (prev && prev->vm_end == new_addr &&
+ can_vma_merge(prev, vma->vm_flags) && !vma->vm_file &&
!(vma->vm_flags & VM_SHARED)) {
+ spin_lock(&mm->page_table_lock);
+ prev->vm_end = new_addr + new_len;
+ spin_unlock(&mm->page_table_lock);
+ new_vma = prev;
+ if (next != prev->vm_next)
+ BUG();
+ if (prev->vm_end == next->vm_start &&
can_vma_merge(next, prev->vm_flags)) {
+ spin_lock(&mm->page_table_lock);
+ prev->vm_end = next->vm_end;
+ __vma_unlink(mm, next, prev);
+ spin_unlock(&mm->page_table_lock);
+
+ mm->map_count--;
+ kmem_cache_free(vm_area_cachep, next);
+ }
+ } else if (next->vm_start == new_addr + new_len &&
+ can_vma_merge(next, vma->vm_flags) && !vma->vm_file
&& !(vma->vm_flags & VM_SHARED)) {
+ spin_lock(&mm->page_table_lock);
+ next->vm_start = new_addr;
+ spin_unlock(&mm->page_table_lock);
+ new_vma = next;
+ }
+ } else {
+ prev = find_vma(mm, new_addr-1);
+ if (prev && prev->vm_end == new_addr &&
+ can_vma_merge(prev, vma->vm_flags) && !vma->vm_file &&
!(vma->vm_flags & VM_SHARED)) {
+ spin_lock(&mm->page_table_lock);
+ prev->vm_end = new_addr + new_len;
+ spin_unlock(&mm->page_table_lock);
+ new_vma = prev;
+ }
+ }
+
+ allocated_vma = 0;
+ if (!new_vma) {
+ new_vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ if (!new_vma)
+ goto out;
+ allocated_vma = 1;
+ }
+
+ if (!move_page_tables(current->mm, new_addr, addr, old_len)) {
+ unsigned long vm_locked = vma->vm_flags & VM_LOCKED;
+
+ if (allocated_vma) {
+ *new_vma = *vma;
+ new_vma->vm_start = new_addr;
+ new_vma->vm_end = new_addr+new_len;
+ new_vma->vm_pgoff += (addr-vma->vm_start) >> PAGE_SHIFT;
+ new_vma->vm_raend = 0;
+ if (new_vma->vm_file)
+ get_file(new_vma->vm_file);
+ if (new_vma->vm_ops && new_vma->vm_ops->open)
+ new_vma->vm_ops->open(new_vma);
+ insert_vm_struct(current->mm, new_vma);
+ }
+
+ /* XXX: possible errors masked, mapping might remain */
+ do_munmap(current->mm, addr, old_len);
+
+ current->mm->total_vm += new_len >> PAGE_SHIFT;
+ if (vm_locked) {
+ current->mm->locked_vm += new_len >> PAGE_SHIFT;
+ if (new_len > old_len)
+ make_pages_present(new_addr + old_len,
+ new_addr + new_len);
+ }
+ return new_addr;
+ }
+ if (allocated_vma)
+ kmem_cache_free(vm_area_cachep, new_vma);
+ out:
+ return -ENOMEM;
+}
+
+/*
+ * Expand (or shrink) an existing mapping, potentially moving it at the
+ * same time (controlled by the MREMAP_MAYMOVE flag and available VM space)
+ *
+ * MREMAP_FIXED option added 5-Dec-1999 by Benjamin LaHaise
+ * This option implies MREMAP_MAYMOVE.
+ */
+unsigned long do_mremap(unsigned long addr,
+ unsigned long old_len, unsigned long new_len,
+ unsigned long flags, unsigned long new_addr)
+{
+ struct vm_area_struct *vma;
+ unsigned long ret = -EINVAL;
+
+ if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
+ goto out;
+
+ if (addr & ~PAGE_MASK)
+ goto out;
+
+ old_len = PAGE_ALIGN(old_len);
+ new_len = PAGE_ALIGN(new_len);
+
+ if (old_len > TASK_SIZE || addr > TASK_SIZE - old_len)
+ goto out;
+
+ if (addr >= TASK_SIZE)
+ goto out;
+
+ /* new_addr is only valid if MREMAP_FIXED is specified */
+ if (flags & MREMAP_FIXED) {
+ if (new_addr & ~PAGE_MASK)
+ goto out;
+ if (!(flags & MREMAP_MAYMOVE))
+ goto out;
+
+ if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len)
+ goto out;
+
+ if (new_addr >= TASK_SIZE)
+ goto out;
+
+ /*
+ * Allow new_len == 0 only if new_addr == addr
+ * to preserve truncation in place (that was working
+ * safe and some app may depend on it).
+ */
+ if (unlikely(!new_len && new_addr != addr))
+ goto out;
+
+ /* Check if the location we're moving into overlaps the
+ * old location at all, and fail if it does.
+ */
+ if ((new_addr <= addr) && (new_addr+new_len) > addr)
+ goto out;
+
+ if ((addr <= new_addr) && (addr+old_len) > new_addr)
+ goto out;
+
+ ret = do_munmap(current->mm, new_addr, new_len);
+ if (ret && new_len)
+ goto out;
+ }
+
+ /*
+ * Always allow a shrinking remap: that just unmaps
+ * the unnecessary pages..
+ */
+ if (old_len >= new_len) {
+ ret = do_munmap(current->mm, addr+new_len, old_len - new_len);
+ if (ret && old_len != new_len)
+ goto out;
+ ret = addr;
+ if (!(flags & MREMAP_FIXED) || (new_addr == addr))
+ goto out;
+ }
+
+ /*
+ * Ok, we need to grow.. or relocate.
+ */
+ ret = -EFAULT;
+ vma = find_vma(current->mm, addr);
+ if (!vma || vma->vm_start > addr)
+ goto out;
+ /* We can't remap across vm area boundaries */
+ if (old_len > vma->vm_end - addr)
+ goto out;
+ if (vma->vm_flags & VM_DONTEXPAND) {
+ if (new_len > old_len)
+ goto out;
+ }
+ if (vma->vm_flags & VM_LOCKED) {
+ unsigned long locked = current->mm->locked_vm << PAGE_SHIFT;
+ locked += new_len - old_len;
+ ret = -EAGAIN;
+ if (locked > current->rlim[RLIMIT_MEMLOCK].rlim_cur)
+ goto out;
+ }
+ ret = -ENOMEM;
+ if ((current->mm->total_vm << PAGE_SHIFT) + (new_len - old_len)
+ > current->rlim[RLIMIT_AS].rlim_cur)
+ goto out;
+ /* Private writable mapping? Check memory availability.. */
+ if ((vma->vm_flags & (VM_SHARED | VM_WRITE)) == VM_WRITE &&
+ !(flags & MAP_NORESERVE) &&
+ !vm_enough_memory((new_len - old_len) >> PAGE_SHIFT))
+ goto out;
+
+#if defined(CONFIG_XEN_PRIVILEGED_GUEST)
+ /* mremap() unsupported for I/O mappings in Xenolinux. */
+ ret = -EINVAL;
+ if (vma->vm_flags & VM_IO)
+ goto out;
+#endif
+
+ /* old_len exactly to the end of the area..
+ * And we're not relocating the area.
+ */
+ if (old_len == vma->vm_end - addr &&
+ !((flags & MREMAP_FIXED) && (addr != new_addr)) &&
+ (old_len != new_len || !(flags & MREMAP_MAYMOVE))) {
+ unsigned long max_addr = TASK_SIZE;
+ if (vma->vm_next)
+ max_addr = vma->vm_next->vm_start;
+ /* can we just expand the current mapping? */
+ if (max_addr - addr >= new_len) {
+ int pages = (new_len - old_len) >> PAGE_SHIFT;
+ spin_lock(&vma->vm_mm->page_table_lock);
+ vma->vm_end = addr + new_len;
+ spin_unlock(&vma->vm_mm->page_table_lock);
+ current->mm->total_vm += pages;
+ if (vma->vm_flags & VM_LOCKED) {
+ current->mm->locked_vm += pages;
+ make_pages_present(addr + old_len,
+ addr + new_len);
+ }
+ ret = addr;
+ goto out;
+ }
+ }
+
+ /*
+ * We weren't able to just expand or shrink the area,
+ * we need to create a new one and move it..
+ */
+ ret = -ENOMEM;
+ if (flags & MREMAP_MAYMOVE) {
+ if (!(flags & MREMAP_FIXED)) {
+ unsigned long map_flags = 0;
+ if (vma->vm_flags & VM_SHARED)
+ map_flags |= MAP_SHARED;
+
+ new_addr = get_unmapped_area(vma->vm_file, 0, new_len,
vma->vm_pgoff, map_flags);
+ ret = new_addr;
+ if (new_addr & ~PAGE_MASK)
+ goto out;
+ }
+ ret = move_vma(vma, addr, old_len, new_len, new_addr);
+ }
+out:
+ return ret;
+}
+
+asmlinkage unsigned long sys_mremap(unsigned long addr,
+ unsigned long old_len, unsigned long new_len,
+ unsigned long flags, unsigned long new_addr)
+{
+ unsigned long ret;
+
+ down_write(¤t->mm->mmap_sem);
+ ret = do_mremap(addr, old_len, new_len, flags, new_addr);
+ up_write(¤t->mm->mmap_sem);
+ return ret;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blkback/common.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blkback/common.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,109 @@
+
+#ifndef __BLKIF__BACKEND__COMMON_H__
+#define __BLKIF__BACKEND__COMMON_H__
+
+#include <linux/config.h>
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/rbtree.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <asm/io.h>
+#include <asm/setup.h>
+#include <asm/pgalloc.h>
+#include <asm-xen/ctrl_if.h>
+#include <asm-xen/hypervisor.h>
+#include <asm-xen/xen-public/io/blkif.h>
+#include <asm-xen/xen-public/io/ring.h>
+
+#if 0
+#define ASSERT(_p) \
+ if ( !(_p) ) { printk("Assertion '%s' failed, line %d, file %s", #_p , \
+ __LINE__, __FILE__); *(int*)0=0; }
+#define DPRINTK(_f, _a...) printk(KERN_ALERT "(file=%s, line=%d) " _f, \
+ __FILE__ , __LINE__ , ## _a )
+#else
+#define ASSERT(_p) ((void)0)
+#define DPRINTK(_f, _a...) ((void)0)
+#endif
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+typedef struct rb_root rb_root_t;
+typedef struct rb_node rb_node_t;
+#else
+struct block_device;
+#endif
+
+typedef struct blkif_st {
+ /* Unique identifier for this interface. */
+ domid_t domid;
+ unsigned int handle;
+ /* Physical parameters of the comms window. */
+ unsigned long shmem_frame;
+ unsigned int evtchn;
+ int irq;
+ /* Comms information. */
+ blkif_back_ring_t blk_ring;
+ /* VBDs attached to this interface. */
+ rb_root_t vbd_rb; /* Mapping from 16-bit vdevices to VBDs.*/
+ spinlock_t vbd_lock; /* Protects VBD mapping. */
+ /* Private fields. */
+ enum { DISCONNECTED, DISCONNECTING, CONNECTED } status;
+ /*
+ * DISCONNECT response is deferred until pending requests are ack'ed.
+ * We therefore need to store the id from the original request.
+ */
+ u8 disconnect_rspid;
+#ifdef CONFIG_XEN_BLKDEV_TAP_BE
+ /* Is this a blktap frontend */
+ unsigned int is_blktap;
+#endif
+ struct blkif_st *hash_next;
+ struct list_head blkdev_list;
+ spinlock_t blk_ring_lock;
+ atomic_t refcnt;
+
+ struct work_struct work;
+#ifdef CONFIG_XEN_BLKDEV_GRANT
+ u16 shmem_handle;
+ memory_t shmem_vaddr;
+ grant_ref_t shmem_ref;
+#endif
+} blkif_t;
+
+void blkif_create(blkif_be_create_t *create);
+void blkif_destroy(blkif_be_destroy_t *destroy);
+void blkif_connect(blkif_be_connect_t *connect);
+int blkif_disconnect(blkif_be_disconnect_t *disconnect, u8 rsp_id);
+void blkif_disconnect_complete(blkif_t *blkif);
+blkif_t *blkif_find_by_handle(domid_t domid, unsigned int handle);
+#define blkif_get(_b) (atomic_inc(&(_b)->refcnt))
+#define blkif_put(_b) \
+ do { \
+ if ( atomic_dec_and_test(&(_b)->refcnt) ) \
+ blkif_disconnect_complete(_b); \
+ } while (0)
+
+void vbd_create(blkif_be_vbd_create_t *create);
+void vbd_destroy(blkif_be_vbd_destroy_t *delete);
+int vbd_probe(blkif_t *blkif, vdisk_t *vbd_info, int max_vbds);
+void destroy_all_vbds(blkif_t *blkif);
+
+struct phys_req {
+ unsigned short dev;
+ unsigned short nr_sects;
+ struct block_device *bdev;
+ blkif_sector_t sector_number;
+};
+
+int vbd_translate(struct phys_req *req, blkif_t *blkif, int operation);
+
+void blkif_interface_init(void);
+void blkif_ctrlif_init(void);
+
+void blkif_deschedule(blkif_t *blkif);
+
+irqreturn_t blkif_be_int(int irq, void *dev_id, struct pt_regs *regs);
+
+#endif /* __BLKIF__BACKEND__COMMON_H__ */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/drivers/blkif/frontend/common.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/drivers/blkif/frontend/common.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,93 @@
+/******************************************************************************
+ * arch/xen/drivers/blkif/frontend/common.h
+ *
+ * Shared definitions between all levels of XenoLinux Virtual block devices.
+ */
+
+#ifndef __XEN_DRIVERS_COMMON_H__
+#define __XEN_DRIVERS_COMMON_H__
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/hdreg.h>
+#include <linux/blkdev.h>
+#include <linux/major.h>
+#include <asm-xen/xen-public/xen.h>
+#include <asm/io.h>
+#include <asm/atomic.h>
+#include <asm/uaccess.h>
+#include <asm-xen/xen-public/io/blkif.h>
+
+#if 1
+#define IPRINTK(fmt, args...) \
+ printk(KERN_INFO "xen_blk: " fmt, ##args)
+#else
+#define IPRINTK(fmt, args...) ((void)0)
+#endif
+
+#if 1
+#define WPRINTK(fmt, args...) \
+ printk(KERN_WARNING "xen_blk: " fmt, ##args)
+#else
+#define WPRINTK(fmt, args...) ((void)0)
+#endif
+
+#if 0
+#define DPRINTK(_f, _a...) printk ( KERN_ALERT _f , ## _a )
+#else
+#define DPRINTK(_f, _a...) ((void)0)
+#endif
+
+#if 0
+#define DPRINTK_IOCTL(_f, _a...) printk ( KERN_ALERT _f , ## _a )
+#else
+#define DPRINTK_IOCTL(_f, _a...) ((void)0)
+#endif
+
+/* Private gendisk->flags[] values. */
+#define GENHD_FL_XEN 2 /* Is unit a Xen block device? */
+#define GENHD_FL_VIRT_PARTNS 4 /* Are unit partitions virtual? */
+
+/*
+ * We have one of these per vbd, whether ide, scsi or 'other'.
+ * They hang in an array off the gendisk structure. We may end up putting
+ * all kinds of interesting stuff here :-)
+ */
+typedef struct xl_disk {
+ int usage;
+} xl_disk_t;
+
+extern int blkif_open(struct inode *inode, struct file *filep);
+extern int blkif_release(struct inode *inode, struct file *filep);
+extern int blkif_ioctl(struct inode *inode, struct file *filep,
+ unsigned command, unsigned long argument);
+extern int blkif_check(kdev_t dev);
+extern int blkif_revalidate(kdev_t dev);
+extern void blkif_control_send(blkif_request_t *req, blkif_response_t *rsp);
+extern void do_blkif_request (request_queue_t *rq);
+
+extern void xlvbd_update_vbds(void);
+
+static inline xl_disk_t *xldev_to_xldisk(kdev_t xldev)
+{
+ struct gendisk *gd = get_gendisk(xldev);
+
+ if ( gd == NULL )
+ return NULL;
+
+ return (xl_disk_t *)gd->real_devices +
+ (MINOR(xldev) >> gd->minor_shift);
+}
+
+
+/* Virtual block-device subsystem. */
+extern int xlvbd_init(void);
+extern void xlvbd_cleanup(void);
+
+#endif /* __XEN_DRIVERS_COMMON_H__ */
diff -r 35b74976f598 -r a83ac0806d6b patches/linux-2.6.11/linux-2.6.11.12.patch
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/patches/linux-2.6.11/linux-2.6.11.12.patch Fri Jul 15 13:39:50 2005
@@ -0,0 +1,2579 @@
+diff --git a/Documentation/SecurityBugs b/Documentation/SecurityBugs
+new file mode 100644
+--- /dev/null
++++ b/Documentation/SecurityBugs
+@@ -0,0 +1,38 @@
++Linux kernel developers take security very seriously. As such, we'd
++like to know when a security bug is found so that it can be fixed and
++disclosed as quickly as possible. Please report security bugs to the
++Linux kernel security team.
++
++1) Contact
++
++The Linux kernel security team can be contacted by email at
++<security@xxxxxxxxxx>. This is a private list of security officers
++who will help verify the bug report and develop and release a fix.
++It is possible that the security team will bring in extra help from
++area maintainers to understand and fix the security vulnerability.
++
++As it is with any bug, the more information provided the easier it
++will be to diagnose and fix. Please review the procedure outlined in
++REPORTING-BUGS if you are unclear about what information is helpful.
++Any exploit code is very helpful and will not be released without
++consent from the reporter unless it has already been made public.
++
++2) Disclosure
++
++The goal of the Linux kernel security team is to work with the
++bug submitter to bug resolution as well as disclosure. We prefer
++to fully disclose the bug as soon as possible. It is reasonable to
++delay disclosure when the bug or the fix is not yet fully understood,
++the solution is not well-tested or for vendor coordination. However, we
++expect these delays to be short, measurable in days, not weeks or months.
++A disclosure date is negotiated by the security team working with the
++bug submitter as well as vendors. However, the kernel security team
++holds the final say when setting a disclosure date. The timeframe for
++disclosure is from immediate (esp. if it's already publically known)
++to a few weeks. As a basic default policy, we expect report date to
++disclosure date to be on the order of 7 days.
++
++3) Non-disclosure agreements
++
++The Linux kernel security team is not a formal body and therefore unable
++to enter any non-disclosure agreements.
+diff --git a/MAINTAINERS b/MAINTAINERS
+--- a/MAINTAINERS
++++ b/MAINTAINERS
+@@ -1966,6 +1966,11 @@ M: christer@xxxxxxxxxxx
+ W: http://www.weinigel.se
+ S: Supported
+
++SECURITY CONTACT
++P: Security Officers
++M: security@xxxxxxxxxx
++S: Supported
++
+ SELINUX SECURITY MODULE
+ P: Stephen Smalley
+ M: sds@xxxxxxxxxxxxxx
+diff --git a/Makefile b/Makefile
+--- a/Makefile
++++ b/Makefile
+@@ -1,8 +1,8 @@
+ VERSION = 2
+ PATCHLEVEL = 6
+ SUBLEVEL = 11
+-EXTRAVERSION =
+-NAME=Woozy Numbat
++EXTRAVERSION = .12
++NAME=Woozy Beaver
+
+ # *DOCUMENTATION*
+ # To see a list of typical targets execute "make help"
+diff --git a/REPORTING-BUGS b/REPORTING-BUGS
+--- a/REPORTING-BUGS
++++ b/REPORTING-BUGS
+@@ -16,6 +16,10 @@ code relevant to what you were doing. If
+ describe how to recreate it. That is worth even more than the oops itself.
+ The list of maintainers is in the MAINTAINERS file in this directory.
+
++ If it is a security bug, please copy the Security Contact listed
++in the MAINTAINERS file. They can help coordinate bugfix and disclosure.
++See Documentation/SecurityBugs for more infomation.
++
+ If you are totally stumped as to whom to send the report, send it to
+ linux-kernel@xxxxxxxxxxxxxxxx (For more information on the linux-kernel
+ mailing list see http://www.tux.org/lkml/).
+diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
+--- a/arch/ia64/kernel/fsys.S
++++ b/arch/ia64/kernel/fsys.S
+@@ -611,8 +611,10 @@ GLOBAL_ENTRY(fsys_bubble_down)
+ movl r2=ia64_ret_from_syscall
+ ;;
+ mov rp=r2 // set the real return addr
+- tbit.z p8,p0=r3,TIF_SYSCALL_TRACE
++ and r3=_TIF_SYSCALL_TRACEAUDIT,r3
+ ;;
++ cmp.eq p8,p0=r3,r0
++
+ (p10) br.cond.spnt.many ia64_ret_from_syscall // p10==true means out
registers are more than 8
+ (p8) br.call.sptk.many b6=b6 // ignore this return addr
+ br.cond.sptk ia64_trace_syscall
+diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c
+--- a/arch/ia64/kernel/signal.c
++++ b/arch/ia64/kernel/signal.c
+@@ -224,7 +224,8 @@ ia64_rt_sigreturn (struct sigscratch *sc
+ * could be corrupted.
+ */
+ retval = (long) &ia64_leave_kernel;
+- if (test_thread_flag(TIF_SYSCALL_TRACE))
++ if (test_thread_flag(TIF_SYSCALL_TRACE)
++ || test_thread_flag(TIF_SYSCALL_AUDIT))
+ /*
+ * strace expects to be notified after sigreturn returns even
though the
+ * context to which we return may not be in the middle of a
syscall.
+diff --git a/arch/ppc/oprofile/op_model_fsl_booke.c
b/arch/ppc/oprofile/op_model_fsl_booke.c
+--- a/arch/ppc/oprofile/op_model_fsl_booke.c
++++ b/arch/ppc/oprofile/op_model_fsl_booke.c
+@@ -150,7 +150,6 @@ static void fsl_booke_handle_interrupt(s
+ int is_kernel;
+ int val;
+ int i;
+- unsigned int cpu = smp_processor_id();
+
+ /* set the PMM bit (see comment below) */
+ mtmsr(mfmsr() | MSR_PMM);
+@@ -162,7 +161,7 @@ static void fsl_booke_handle_interrupt(s
+ val = ctr_read(i);
+ if (val < 0) {
+ if (oprofile_running && ctr[i].enabled) {
+- oprofile_add_sample(pc, is_kernel, i, cpu);
++ oprofile_add_pc(pc, is_kernel, i);
+ ctr_write(i, reset_value[i]);
+ } else {
+ ctr_write(i, 0);
+diff --git a/arch/ppc/platforms/4xx/ebony.h b/arch/ppc/platforms/4xx/ebony.h
+--- a/arch/ppc/platforms/4xx/ebony.h
++++ b/arch/ppc/platforms/4xx/ebony.h
+@@ -61,8 +61,8 @@
+ */
+
+ /* OpenBIOS defined UART mappings, used before early_serial_setup */
+-#define UART0_IO_BASE (u8 *) 0xE0000200
+-#define UART1_IO_BASE (u8 *) 0xE0000300
++#define UART0_IO_BASE 0xE0000200
++#define UART1_IO_BASE 0xE0000300
+
+ /* external Epson SG-615P */
+ #define BASE_BAUD 691200
+diff --git a/arch/ppc/platforms/4xx/luan.h b/arch/ppc/platforms/4xx/luan.h
+--- a/arch/ppc/platforms/4xx/luan.h
++++ b/arch/ppc/platforms/4xx/luan.h
+@@ -47,9 +47,9 @@
+ #define RS_TABLE_SIZE 3
+
+ /* PIBS defined UART mappings, used before early_serial_setup */
+-#define UART0_IO_BASE (u8 *) 0xa0000200
+-#define UART1_IO_BASE (u8 *) 0xa0000300
+-#define UART2_IO_BASE (u8 *) 0xa0000600
++#define UART0_IO_BASE 0xa0000200
++#define UART1_IO_BASE 0xa0000300
++#define UART2_IO_BASE 0xa0000600
+
+ #define BASE_BAUD 11059200
+ #define STD_UART_OP(num) \
+diff --git a/arch/ppc/platforms/4xx/ocotea.h b/arch/ppc/platforms/4xx/ocotea.h
+--- a/arch/ppc/platforms/4xx/ocotea.h
++++ b/arch/ppc/platforms/4xx/ocotea.h
+@@ -56,8 +56,8 @@
+ #define RS_TABLE_SIZE 2
+
+ /* OpenBIOS defined UART mappings, used before early_serial_setup */
+-#define UART0_IO_BASE (u8 *) 0xE0000200
+-#define UART1_IO_BASE (u8 *) 0xE0000300
++#define UART0_IO_BASE 0xE0000200
++#define UART1_IO_BASE 0xE0000300
+
+ #define BASE_BAUD 11059200/16
+ #define STD_UART_OP(num) \
+diff --git a/arch/ppc64/kernel/pSeries_iommu.c
b/arch/ppc64/kernel/pSeries_iommu.c
+--- a/arch/ppc64/kernel/pSeries_iommu.c
++++ b/arch/ppc64/kernel/pSeries_iommu.c
+@@ -401,6 +401,8 @@ static void iommu_bus_setup_pSeriesLP(st
+ struct device_node *dn, *pdn;
+ unsigned int *dma_window = NULL;
+
++ DBG("iommu_bus_setup_pSeriesLP, bus %p, bus->self %p\n", bus,
bus->self);
++
+ dn = pci_bus_to_OF_node(bus);
+
+ /* Find nearest ibm,dma-window, walking up the device tree */
+@@ -455,6 +457,56 @@ static void iommu_dev_setup_pSeries(stru
+ }
+ }
+
++static void iommu_dev_setup_pSeriesLP(struct pci_dev *dev)
++{
++ struct device_node *pdn, *dn;
++ struct iommu_table *tbl;
++ int *dma_window = NULL;
++
++ DBG("iommu_dev_setup_pSeriesLP, dev %p (%s)\n", dev, dev->pretty_name);
++
++ /* dev setup for LPAR is a little tricky, since the device tree might
++ * contain the dma-window properties per-device and not neccesarily
++ * for the bus. So we need to search upwards in the tree until we
++ * either hit a dma-window property, OR find a parent with a table
++ * already allocated.
++ */
++ dn = pci_device_to_OF_node(dev);
++
++ for (pdn = dn; pdn && !pdn->iommu_table; pdn = pdn->parent) {
++ dma_window = (unsigned int *)get_property(pdn,
"ibm,dma-window", NULL);
++ if (dma_window)
++ break;
++ }
++
++ /* Check for parent == NULL so we don't try to setup the empty EADS
++ * slots on POWER4 machines.
++ */
++ if (dma_window == NULL || pdn->parent == NULL) {
++ /* Fall back to regular (non-LPAR) dev setup */
++ DBG("No dma window for device, falling back to regular
setup\n");
++ iommu_dev_setup_pSeries(dev);
++ return;
++ } else {
++ DBG("Found DMA window, allocating table\n");
++ }
++
++ if (!pdn->iommu_table) {
++ /* iommu_table_setparms_lpar needs bussubno. */
++ pdn->bussubno = pdn->phb->bus->number;
++
++ tbl = (struct iommu_table *)kmalloc(sizeof(struct iommu_table),
++ GFP_KERNEL);
++
++ iommu_table_setparms_lpar(pdn->phb, pdn, tbl, dma_window);
++
++ pdn->iommu_table = iommu_init_table(tbl);
++ }
++
++ if (pdn != dn)
++ dn->iommu_table = pdn->iommu_table;
++}
++
+ static void iommu_bus_setup_null(struct pci_bus *b) { }
+ static void iommu_dev_setup_null(struct pci_dev *d) { }
+
+@@ -479,13 +531,14 @@ void iommu_init_early_pSeries(void)
+ ppc_md.tce_free = tce_free_pSeriesLP;
+ }
+ ppc_md.iommu_bus_setup = iommu_bus_setup_pSeriesLP;
++ ppc_md.iommu_dev_setup = iommu_dev_setup_pSeriesLP;
+ } else {
+ ppc_md.tce_build = tce_build_pSeries;
+ ppc_md.tce_free = tce_free_pSeries;
+ ppc_md.iommu_bus_setup = iommu_bus_setup_pSeries;
++ ppc_md.iommu_dev_setup = iommu_dev_setup_pSeries;
+ }
+
+- ppc_md.iommu_dev_setup = iommu_dev_setup_pSeries;
+
+ pci_iommu_init();
+ }
+diff --git a/arch/sparc/kernel/ptrace.c b/arch/sparc/kernel/ptrace.c
+--- a/arch/sparc/kernel/ptrace.c
++++ b/arch/sparc/kernel/ptrace.c
+@@ -531,18 +531,6 @@ asmlinkage void do_ptrace(struct pt_regs
+ pt_error_return(regs, EIO);
+ goto out_tsk;
+ }
+- if (addr != 1) {
+- if (addr & 3) {
+- pt_error_return(regs, EINVAL);
+- goto out_tsk;
+- }
+-#ifdef DEBUG_PTRACE
+- printk ("Original: %08lx %08lx\n",
child->thread.kregs->pc, child->thread.kregs->npc);
+- printk ("Continuing with %08lx %08lx\n", addr, addr+4);
+-#endif
+- child->thread.kregs->pc = addr;
+- child->thread.kregs->npc = addr + 4;
+- }
+
+ if (request == PTRACE_SYSCALL)
+ set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+diff --git a/arch/sparc64/kernel/ptrace.c b/arch/sparc64/kernel/ptrace.c
+--- a/arch/sparc64/kernel/ptrace.c
++++ b/arch/sparc64/kernel/ptrace.c
+@@ -514,25 +514,6 @@ asmlinkage void do_ptrace(struct pt_regs
+ pt_error_return(regs, EIO);
+ goto out_tsk;
+ }
+- if (addr != 1) {
+- unsigned long pc_mask = ~0UL;
+-
+- if ((child->thread_info->flags & _TIF_32BIT) != 0)
+- pc_mask = 0xffffffff;
+-
+- if (addr & 3) {
+- pt_error_return(regs, EINVAL);
+- goto out_tsk;
+- }
+-#ifdef DEBUG_PTRACE
+- printk ("Original: %016lx %016lx\n",
+- child->thread_info->kregs->tpc,
+- child->thread_info->kregs->tnpc);
+- printk ("Continuing with %016lx %016lx\n", addr,
addr+4);
+-#endif
+- child->thread_info->kregs->tpc = (addr & pc_mask);
+- child->thread_info->kregs->tnpc = ((addr + 4) &
pc_mask);
+- }
+
+ if (request == PTRACE_SYSCALL) {
+ set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+diff --git a/arch/sparc64/kernel/signal32.c b/arch/sparc64/kernel/signal32.c
+--- a/arch/sparc64/kernel/signal32.c
++++ b/arch/sparc64/kernel/signal32.c
+@@ -192,10 +192,13 @@ int copy_siginfo_to_user32(compat_siginf
+ err |= __put_user(from->si_uid, &to->si_uid);
+ break;
+ case __SI_FAULT >> 16:
+- case __SI_POLL >> 16:
+ err |= __put_user(from->si_trapno, &to->si_trapno);
+ err |= __put_user((unsigned long)from->si_addr,
&to->si_addr);
+ break;
++ case __SI_POLL >> 16:
++ err |= __put_user(from->si_band, &to->si_band);
++ err |= __put_user(from->si_fd, &to->si_fd);
++ break;
+ case __SI_RT >> 16: /* This is not generated by the kernel as
of now. */
+ case __SI_MESGQ >> 16:
+ err |= __put_user(from->si_pid, &to->si_pid);
+diff --git a/arch/sparc64/kernel/systbls.S b/arch/sparc64/kernel/systbls.S
+--- a/arch/sparc64/kernel/systbls.S
++++ b/arch/sparc64/kernel/systbls.S
+@@ -75,7 +75,7 @@ sys_call_table32:
+ /*260*/ .word compat_sys_sched_getaffinity,
compat_sys_sched_setaffinity, sys32_timer_settime, compat_sys_timer_gettime,
sys_timer_getoverrun
+ .word sys_timer_delete, sys32_timer_create, sys_ni_syscall,
compat_sys_io_setup, sys_io_destroy
+ /*270*/ .word sys32_io_submit, sys_io_cancel, compat_sys_io_getevents,
sys32_mq_open, sys_mq_unlink
+- .word sys_mq_timedsend, sys_mq_timedreceive, compat_sys_mq_notify,
compat_sys_mq_getsetattr, compat_sys_waitid
++ .word compat_sys_mq_timedsend, compat_sys_mq_timedreceive,
compat_sys_mq_notify, compat_sys_mq_getsetattr, compat_sys_waitid
+ /*280*/ .word sys_ni_syscall, sys_add_key, sys_request_key, sys_keyctl
+
+ #endif /* CONFIG_COMPAT */
+diff --git a/arch/um/include/sysdep-i386/syscalls.h
b/arch/um/include/sysdep-i386/syscalls.h
+--- a/arch/um/include/sysdep-i386/syscalls.h
++++ b/arch/um/include/sysdep-i386/syscalls.h
+@@ -23,6 +23,9 @@ extern long sys_mmap2(unsigned long addr
+ unsigned long prot, unsigned long flags,
+ unsigned long fd, unsigned long pgoff);
+
++/* On i386 they choose a meaningless naming.*/
++#define __NR_kexec_load __NR_sys_kexec_load
++
+ #define ARCH_SYSCALLS \
+ [ __NR_waitpid ] = (syscall_handler_t *) sys_waitpid, \
+ [ __NR_break ] = (syscall_handler_t *) sys_ni_syscall, \
+@@ -101,15 +104,12 @@ extern long sys_mmap2(unsigned long addr
+ [ 223 ] = (syscall_handler_t *) sys_ni_syscall, \
+ [ __NR_set_thread_area ] = (syscall_handler_t *) sys_ni_syscall, \
+ [ __NR_get_thread_area ] = (syscall_handler_t *) sys_ni_syscall, \
+- [ __NR_fadvise64 ] = (syscall_handler_t *) sys_fadvise64, \
+ [ 251 ] = (syscall_handler_t *) sys_ni_syscall, \
+- [ __NR_remap_file_pages ] = (syscall_handler_t *)
sys_remap_file_pages, \
+- [ __NR_utimes ] = (syscall_handler_t *) sys_utimes, \
+- [ __NR_vserver ] = (syscall_handler_t *) sys_ni_syscall,
+-
++ [ 285 ] = (syscall_handler_t *) sys_ni_syscall,
++
+ /* 222 doesn't yet have a name in include/asm-i386/unistd.h */
+
+-#define LAST_ARCH_SYSCALL __NR_vserver
++#define LAST_ARCH_SYSCALL 285
+
+ /*
+ * Overrides for Emacs so that we follow Linus's tabbing style.
+diff --git a/arch/um/include/sysdep-x86_64/syscalls.h
b/arch/um/include/sysdep-x86_64/syscalls.h
+--- a/arch/um/include/sysdep-x86_64/syscalls.h
++++ b/arch/um/include/sysdep-x86_64/syscalls.h
+@@ -71,12 +71,7 @@ extern syscall_handler_t sys_arch_prctl;
+ [ __NR_iopl ] = (syscall_handler_t *) sys_ni_syscall, \
+ [ __NR_set_thread_area ] = (syscall_handler_t *) sys_ni_syscall, \
+ [ __NR_get_thread_area ] = (syscall_handler_t *) sys_ni_syscall, \
+- [ __NR_remap_file_pages ] = (syscall_handler_t *)
sys_remap_file_pages, \
+ [ __NR_semtimedop ] = (syscall_handler_t *) sys_semtimedop, \
+- [ __NR_fadvise64 ] = (syscall_handler_t *) sys_fadvise64, \
+- [ 223 ] = (syscall_handler_t *) sys_ni_syscall, \
+- [ __NR_utimes ] = (syscall_handler_t *) sys_utimes, \
+- [ __NR_vserver ] = (syscall_handler_t *) sys_ni_syscall, \
+ [ 251 ] = (syscall_handler_t *) sys_ni_syscall,
+
+ #define LAST_ARCH_SYSCALL 251
+diff --git a/arch/um/kernel/skas/uaccess.c b/arch/um/kernel/skas/uaccess.c
+--- a/arch/um/kernel/skas/uaccess.c
++++ b/arch/um/kernel/skas/uaccess.c
+@@ -61,7 +61,8 @@ static void do_buffer_op(void *jmpbuf, v
+ void *arg;
+ int *res;
+
+- va_copy(args, *(va_list *)arg_ptr);
++ /* Some old gccs recognize __va_copy, but not va_copy */
++ __va_copy(args, *(va_list *)arg_ptr);
+ addr = va_arg(args, unsigned long);
+ len = va_arg(args, int);
+ is_write = va_arg(args, int);
+diff --git a/arch/um/kernel/sys_call_table.c b/arch/um/kernel/sys_call_table.c
+--- a/arch/um/kernel/sys_call_table.c
++++ b/arch/um/kernel/sys_call_table.c
+@@ -48,7 +48,6 @@ extern syscall_handler_t sys_vfork;
+ extern syscall_handler_t old_select;
+ extern syscall_handler_t sys_modify_ldt;
+ extern syscall_handler_t sys_rt_sigsuspend;
+-extern syscall_handler_t sys_vserver;
+ extern syscall_handler_t sys_mbind;
+ extern syscall_handler_t sys_get_mempolicy;
+ extern syscall_handler_t sys_set_mempolicy;
+@@ -242,6 +241,7 @@ syscall_handler_t *sys_call_table[] = {
+ [ __NR_epoll_create ] = (syscall_handler_t *) sys_epoll_create,
+ [ __NR_epoll_ctl ] = (syscall_handler_t *) sys_epoll_ctl,
+ [ __NR_epoll_wait ] = (syscall_handler_t *) sys_epoll_wait,
++ [ __NR_remap_file_pages ] = (syscall_handler_t *) sys_remap_file_pages,
+ [ __NR_set_tid_address ] = (syscall_handler_t *) sys_set_tid_address,
+ [ __NR_timer_create ] = (syscall_handler_t *) sys_timer_create,
+ [ __NR_timer_settime ] = (syscall_handler_t *) sys_timer_settime,
+@@ -252,12 +252,10 @@ syscall_handler_t *sys_call_table[] = {
+ [ __NR_clock_gettime ] = (syscall_handler_t *) sys_clock_gettime,
+ [ __NR_clock_getres ] = (syscall_handler_t *) sys_clock_getres,
+ [ __NR_clock_nanosleep ] = (syscall_handler_t *) sys_clock_nanosleep,
+- [ __NR_statfs64 ] = (syscall_handler_t *) sys_statfs64,
+- [ __NR_fstatfs64 ] = (syscall_handler_t *) sys_fstatfs64,
+ [ __NR_tgkill ] = (syscall_handler_t *) sys_tgkill,
+ [ __NR_utimes ] = (syscall_handler_t *) sys_utimes,
+- [ __NR_fadvise64_64 ] = (syscall_handler_t *) sys_fadvise64_64,
+- [ __NR_vserver ] = (syscall_handler_t *) sys_vserver,
++ [ __NR_fadvise64 ] = (syscall_handler_t *) sys_fadvise64,
++ [ __NR_vserver ] = (syscall_handler_t *) sys_ni_syscall,
+ [ __NR_mbind ] = (syscall_handler_t *) sys_mbind,
+ [ __NR_get_mempolicy ] = (syscall_handler_t *) sys_get_mempolicy,
+ [ __NR_set_mempolicy ] = (syscall_handler_t *) sys_set_mempolicy,
+@@ -267,9 +265,8 @@ syscall_handler_t *sys_call_table[] = {
+ [ __NR_mq_timedreceive ] = (syscall_handler_t *) sys_mq_timedreceive,
+ [ __NR_mq_notify ] = (syscall_handler_t *) sys_mq_notify,
+ [ __NR_mq_getsetattr ] = (syscall_handler_t *) sys_mq_getsetattr,
+- [ __NR_sys_kexec_load ] = (syscall_handler_t *) sys_ni_syscall,
++ [ __NR_kexec_load ] = (syscall_handler_t *) sys_ni_syscall,
+ [ __NR_waitid ] = (syscall_handler_t *) sys_waitid,
+- [ 285 ] = (syscall_handler_t *) sys_ni_syscall,
+ [ __NR_add_key ] = (syscall_handler_t *) sys_add_key,
+ [ __NR_request_key ] = (syscall_handler_t *) sys_request_key,
+ [ __NR_keyctl ] = (syscall_handler_t *) sys_keyctl,
+diff --git a/arch/x86_64/kernel/apic.c b/arch/x86_64/kernel/apic.c
+--- a/arch/x86_64/kernel/apic.c
++++ b/arch/x86_64/kernel/apic.c
+@@ -775,9 +775,7 @@ void __init setup_boot_APIC_clock (void)
+
+ void __init setup_secondary_APIC_clock(void)
+ {
+- local_irq_disable(); /* FIXME: Do we need this? --RR */
+ setup_APIC_timer(calibration_result);
+- local_irq_enable();
+ }
+
+ void __init disable_APIC_timer(void)
+diff --git a/arch/x86_64/kernel/ptrace.c b/arch/x86_64/kernel/ptrace.c
+--- a/arch/x86_64/kernel/ptrace.c
++++ b/arch/x86_64/kernel/ptrace.c
+@@ -129,13 +129,13 @@ static int putreg(struct task_struct *ch
+ value &= 0xffff;
+ return 0;
+ case offsetof(struct user_regs_struct,fs_base):
+- if (!((value >> 48) == 0 || (value >> 48) == 0xffff))
+- return -EIO;
++ if (value >= TASK_SIZE)
++ return -EIO;
+ child->thread.fs = value;
+ return 0;
+ case offsetof(struct user_regs_struct,gs_base):
+- if (!((value >> 48) == 0 || (value >> 48) == 0xffff))
+- return -EIO;
++ if (value >= TASK_SIZE)
++ return -EIO;
+ child->thread.gs = value;
+ return 0;
+ case offsetof(struct user_regs_struct, eflags):
+@@ -149,6 +149,11 @@ static int putreg(struct task_struct *ch
+ return -EIO;
+ value &= 0xffff;
+ break;
++ case offsetof(struct user_regs_struct, rip):
++ /* Check if the new RIP address is canonical */
++ if (value >= TASK_SIZE)
++ return -EIO;
++ break;
+ }
+ put_stack_long(child, regno - sizeof(struct pt_regs), value);
+ return 0;
+@@ -247,7 +252,7 @@ asmlinkage long sys_ptrace(long request,
+ break;
+
+ switch (addr) {
+- case 0 ... sizeof(struct user_regs_struct):
++ case 0 ... sizeof(struct user_regs_struct) - sizeof(long):
+ tmp = getreg(child, addr);
+ break;
+ case offsetof(struct user, u_debugreg[0]):
+@@ -292,7 +297,7 @@ asmlinkage long sys_ptrace(long request,
+ break;
+
+ switch (addr) {
+- case 0 ... sizeof(struct user_regs_struct):
++ case 0 ... sizeof(struct user_regs_struct) - sizeof(long):
+ ret = putreg(child, addr, data);
+ break;
+ /* Disallows to set a breakpoint into the vsyscall */
+diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c
+--- a/arch/x86_64/kernel/smpboot.c
++++ b/arch/x86_64/kernel/smpboot.c
+@@ -309,8 +309,6 @@ void __init smp_callin(void)
+ Dprintk("CALLIN, before setup_local_APIC().\n");
+ setup_local_APIC();
+
+- local_irq_enable();
+-
+ /*
+ * Get our bogomips.
+ */
+@@ -324,8 +322,6 @@ void __init smp_callin(void)
+ */
+ smp_store_cpu_info(cpuid);
+
+- local_irq_disable();
+-
+ /*
+ * Allow the master to continue.
+ */
+diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c
+--- a/arch/x86_64/mm/fault.c
++++ b/arch/x86_64/mm/fault.c
+@@ -236,6 +236,8 @@ static noinline void pgtable_bad(unsigne
+
+ /*
+ * Handle a fault on the vmalloc or module mapping area
++ *
++ * This assumes no large pages in there.
+ */
+ static int vmalloc_fault(unsigned long address)
+ {
+@@ -274,7 +276,10 @@ static int vmalloc_fault(unsigned long a
+ if (!pte_present(*pte_ref))
+ return -1;
+ pte = pte_offset_kernel(pmd, address);
+- if (!pte_present(*pte) || pte_page(*pte) != pte_page(*pte_ref))
++ /* Don't use pte_page here, because the mappings can point
++ outside mem_map, and the NUMA hash lookup cannot handle
++ that. */
++ if (!pte_present(*pte) || pte_pfn(*pte) != pte_pfn(*pte_ref))
+ BUG();
+ __flush_tlb_all();
+ return 0;
+@@ -348,7 +353,9 @@ asmlinkage void do_page_fault(struct pt_
+ * protection error (error_code & 1) == 0.
+ */
+ if (unlikely(address >= TASK_SIZE)) {
+- if (!(error_code & 5)) {
++ if (!(error_code & 5) &&
++ ((address >= VMALLOC_START && address < VMALLOC_END) ||
++ (address >= MODULES_VADDR && address < MODULES_END))) {
+ if (vmalloc_fault(address) < 0)
+ goto bad_area_nosemaphore;
+ return;
+diff --git a/arch/x86_64/mm/ioremap.c b/arch/x86_64/mm/ioremap.c
+--- a/arch/x86_64/mm/ioremap.c
++++ b/arch/x86_64/mm/ioremap.c
+@@ -266,7 +266,7 @@ void iounmap(volatile void __iomem *addr
+ if ((p->flags >> 20) &&
+ p->phys_addr + p->size - 1 < virt_to_phys(high_memory)) {
+ /* p->size includes the guard page, but cpa doesn't like that */
+- change_page_attr(virt_to_page(__va(p->phys_addr)),
++ change_page_attr_addr((unsigned long)(__va(p->phys_addr)),
+ (p->size - PAGE_SIZE) >> PAGE_SHIFT,
+ PAGE_KERNEL);
+ global_flush_tlb();
+diff --git a/drivers/block/ioctl.c b/drivers/block/ioctl.c
+--- a/drivers/block/ioctl.c
++++ b/drivers/block/ioctl.c
+@@ -237,3 +237,5 @@ long compat_blkdev_ioctl(struct file *fi
+ }
+ return ret;
+ }
++
++EXPORT_SYMBOL_GPL(blkdev_ioctl);
+diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
+--- a/drivers/block/pktcdvd.c
++++ b/drivers/block/pktcdvd.c
+@@ -2400,7 +2400,7 @@ static int pkt_ioctl(struct inode *inode
+ case CDROM_LAST_WRITTEN:
+ case CDROM_SEND_PACKET:
+ case SCSI_IOCTL_SEND_COMMAND:
+- return ioctl_by_bdev(pd->bdev, cmd, arg);
++ return blkdev_ioctl(pd->bdev->bd_inode, file, cmd, arg);
+
+ case CDROMEJECT:
+ /*
+@@ -2408,7 +2408,7 @@ static int pkt_ioctl(struct inode *inode
+ * have to unlock it or else the eject command fails.
+ */
+ pkt_lock_door(pd, 0);
+- return ioctl_by_bdev(pd->bdev, cmd, arg);
++ return blkdev_ioctl(pd->bdev->bd_inode, file, cmd, arg);
+
+ default:
+ printk("pktcdvd: Unknown ioctl for %s (%x)\n", pd->name, cmd);
+diff --git a/drivers/char/drm/drm_ioctl.c b/drivers/char/drm/drm_ioctl.c
+--- a/drivers/char/drm/drm_ioctl.c
++++ b/drivers/char/drm/drm_ioctl.c
+@@ -326,6 +326,8 @@ int drm_setversion(DRM_IOCTL_ARGS)
+
+ DRM_COPY_FROM_USER_IOCTL(sv, argp, sizeof(sv));
+
++ memset(&version, 0, sizeof(version));
++
+ dev->driver->version(&version);
+ retv.drm_di_major = DRM_IF_MAJOR;
+ retv.drm_di_minor = DRM_IF_MINOR;
+diff --git a/drivers/char/raw.c b/drivers/char/raw.c
+--- a/drivers/char/raw.c
++++ b/drivers/char/raw.c
+@@ -122,7 +122,7 @@ raw_ioctl(struct inode *inode, struct fi
+ {
+ struct block_device *bdev = filp->private_data;
+
+- return ioctl_by_bdev(bdev, command, arg);
++ return blkdev_ioctl(bdev->bd_inode, filp, command, arg);
+ }
+
+ static void bind_device(struct raw_config_request *rq)
+diff --git a/drivers/i2c/chips/eeprom.c b/drivers/i2c/chips/eeprom.c
+--- a/drivers/i2c/chips/eeprom.c
++++ b/drivers/i2c/chips/eeprom.c
+@@ -130,7 +130,8 @@ static ssize_t eeprom_read(struct kobjec
+
+ /* Hide Vaio security settings to regular users (16 first bytes) */
+ if (data->nature == VAIO && off < 16 && !capable(CAP_SYS_ADMIN)) {
+- int in_row1 = 16 - off;
++ size_t in_row1 = 16 - off;
++ in_row1 = min(in_row1, count);
+ memset(buf, 0, in_row1);
+ if (count - in_row1 > 0)
+ memcpy(buf + in_row1, &data->data[16], count - in_row1);
+diff --git a/drivers/i2c/chips/it87.c b/drivers/i2c/chips/it87.c
+--- a/drivers/i2c/chips/it87.c
++++ b/drivers/i2c/chips/it87.c
+@@ -631,7 +631,7 @@ static ssize_t show_alarms(struct device
+ struct it87_data *data = it87_update_device(dev);
+ return sprintf(buf,"%d\n", ALARMS_FROM_REG(data->alarms));
+ }
+-static DEVICE_ATTR(alarms, S_IRUGO | S_IWUSR, show_alarms, NULL);
++static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+
+ static ssize_t
+ show_vrm_reg(struct device *dev, char *buf)
+diff --git a/drivers/i2c/chips/via686a.c b/drivers/i2c/chips/via686a.c
+--- a/drivers/i2c/chips/via686a.c
++++ b/drivers/i2c/chips/via686a.c
+@@ -554,7 +554,7 @@ static ssize_t show_alarms(struct device
+ struct via686a_data *data = via686a_update_device(dev);
+ return sprintf(buf,"%d\n", ALARMS_FROM_REG(data->alarms));
+ }
+-static DEVICE_ATTR(alarms, S_IRUGO | S_IWUSR, show_alarms, NULL);
++static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+
+ /* The driver. I choose to use type i2c_driver, as at is identical to both
+ smbus_driver and isa_driver, and clients could be of either kind */
+diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
+--- a/drivers/ide/ide-disk.c
++++ b/drivers/ide/ide-disk.c
+@@ -133,6 +133,8 @@ static ide_startstop_t __ide_do_rw_disk(
+ if (hwif->no_lba48_dma && lba48 && dma) {
+ if (block + rq->nr_sectors > 1ULL << 28)
+ dma = 0;
++ else
++ lba48 = 0;
+ }
+
+ if (!dma) {
+@@ -146,7 +148,7 @@ static ide_startstop_t __ide_do_rw_disk(
+ /* FIXME: SELECT_MASK(drive, 0) ? */
+
+ if (drive->select.b.lba) {
+- if (drive->addressing == 1) {
++ if (lba48) {
+ task_ioreg_t tasklets[10];
+
+ pr_debug("%s: LBA=0x%012llx\n", drive->name, block);
+diff --git a/drivers/input/serio/i8042-x86ia64io.h
b/drivers/input/serio/i8042-x86ia64io.h
+--- a/drivers/input/serio/i8042-x86ia64io.h
++++ b/drivers/input/serio/i8042-x86ia64io.h
+@@ -88,7 +88,7 @@ static struct dmi_system_id __initdata i
+ };
+ #endif
+
+-#ifdef CONFIG_ACPI
++#if defined(__ia64__) && defined(CONFIG_ACPI)
+ #include <linux/acpi.h>
+ #include <acpi/acpi_bus.h>
+
+@@ -281,7 +281,7 @@ static inline int i8042_platform_init(vo
+ i8042_kbd_irq = I8042_MAP_IRQ(1);
+ i8042_aux_irq = I8042_MAP_IRQ(12);
+
+-#ifdef CONFIG_ACPI
++#if defined(__ia64__) && defined(CONFIG_ACPI)
+ if (i8042_acpi_init())
+ return -1;
+ #endif
+@@ -300,7 +300,7 @@ static inline int i8042_platform_init(vo
+
+ static inline void i8042_platform_exit(void)
+ {
+-#ifdef CONFIG_ACPI
++#if defined(__ia64__) && defined(CONFIG_ACPI)
+ i8042_acpi_exit();
+ #endif
+ }
+diff --git a/drivers/md/raid6altivec.uc b/drivers/md/raid6altivec.uc
+--- a/drivers/md/raid6altivec.uc
++++ b/drivers/md/raid6altivec.uc
+@@ -108,7 +108,11 @@ int raid6_have_altivec(void);
+ int raid6_have_altivec(void)
+ {
+ /* This assumes either all CPUs have Altivec or none does */
++#ifdef CONFIG_PPC64
+ return cur_cpu_spec->cpu_features & CPU_FTR_ALTIVEC;
++#else
++ return cur_cpu_spec[0]->cpu_features & CPU_FTR_ALTIVEC;
++#endif
+ }
+ #endif
+
+diff --git a/drivers/media/video/adv7170.c b/drivers/media/video/adv7170.c
+--- a/drivers/media/video/adv7170.c
++++ b/drivers/media/video/adv7170.c
+@@ -130,7 +130,7 @@ adv7170_write_block (struct i2c_client *
+ u8 block_data[32];
+
+ msg.addr = client->addr;
+- msg.flags = client->flags;
++ msg.flags = 0;
+ while (len >= 2) {
+ msg.buf = (char *) block_data;
+ msg.len = 0;
+diff --git a/drivers/media/video/adv7175.c b/drivers/media/video/adv7175.c
+--- a/drivers/media/video/adv7175.c
++++ b/drivers/media/video/adv7175.c
+@@ -126,7 +126,7 @@ adv7175_write_block (struct i2c_client *
+ u8 block_data[32];
+
+ msg.addr = client->addr;
+- msg.flags = client->flags;
++ msg.flags = 0;
+ while (len >= 2) {
+ msg.buf = (char *) block_data;
+ msg.len = 0;
+diff --git a/drivers/media/video/bt819.c b/drivers/media/video/bt819.c
+--- a/drivers/media/video/bt819.c
++++ b/drivers/media/video/bt819.c
+@@ -146,7 +146,7 @@ bt819_write_block (struct i2c_client *cl
+ u8 block_data[32];
+
+ msg.addr = client->addr;
+- msg.flags = client->flags;
++ msg.flags = 0;
+ while (len >= 2) {
+ msg.buf = (char *) block_data;
+ msg.len = 0;
+diff --git a/drivers/media/video/bttv-cards.c
b/drivers/media/video/bttv-cards.c
+--- a/drivers/media/video/bttv-cards.c
++++ b/drivers/media/video/bttv-cards.c
+@@ -1939,7 +1939,6 @@ struct tvcard bttv_tvcards[] = {
+ .no_tda9875 = 1,
+ .no_tda7432 = 1,
+ .tuner_type = TUNER_ABSENT,
+- .no_video = 1,
+ .pll = PLL_28,
+ },{
+ .name = "Teppro TEV-560/InterVision IV-560",
+@@ -2718,8 +2717,6 @@ void __devinit bttv_init_card2(struct bt
+ }
+ btv->pll.pll_current = -1;
+
+- bttv_reset_audio(btv);
+-
+ /* tuner configuration (from card list / autodetect / insmod option) */
+ if (UNSET != bttv_tvcards[btv->c.type].tuner_type)
+ if(UNSET == btv->tuner_type)
+diff --git a/drivers/media/video/saa7110.c b/drivers/media/video/saa7110.c
+--- a/drivers/media/video/saa7110.c
++++ b/drivers/media/video/saa7110.c
+@@ -60,8 +60,10 @@ MODULE_PARM_DESC(debug, "Debug level (0-
+
+ #define I2C_SAA7110 0x9C /* or 0x9E */
+
++#define SAA7110_NR_REG 0x35
++
+ struct saa7110 {
+- unsigned char reg[54];
++ u8 reg[SAA7110_NR_REG];
+
+ int norm;
+ int input;
+@@ -95,31 +97,28 @@ saa7110_write_block (struct i2c_client *
+ unsigned int len)
+ {
+ int ret = -1;
+- u8 reg = *data++;
++ u8 reg = *data; /* first register to write to */
+
+- len--;
++ /* Sanity check */
++ if (reg + (len - 1) > SAA7110_NR_REG)
++ return ret;
+
+ /* the saa7110 has an autoincrement function, use it if
+ * the adapter understands raw I2C */
+ if (i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
+ struct saa7110 *decoder = i2c_get_clientdata(client);
+ struct i2c_msg msg;
+- u8 block_data[54];
+
+- msg.len = 0;
+- msg.buf = (char *) block_data;
++ msg.len = len;
++ msg.buf = (char *) data;
+ msg.addr = client->addr;
+- msg.flags = client->flags;
+- while (len >= 1) {
+- msg.len = 0;
+- block_data[msg.len++] = reg;
+- while (len-- >= 1 && msg.len < 54)
+- block_data[msg.len++] =
+- decoder->reg[reg++] = *data++;
+- ret = i2c_transfer(client->adapter, &msg, 1);
+- }
++ msg.flags = 0;
++ ret = i2c_transfer(client->adapter, &msg, 1);
++
++ /* Cache the written data */
++ memcpy(decoder->reg + reg, data + 1, len - 1);
+ } else {
+- while (len-- >= 1) {
++ for (++data, --len; len; len--) {
+ if ((ret = saa7110_write(client, reg++,
+ *data++)) < 0)
+ break;
+@@ -192,7 +191,7 @@ saa7110_selmux (struct i2c_client *clien
+ return 0;
+ }
+
+-static const unsigned char initseq[] = {
++static const unsigned char initseq[1 + SAA7110_NR_REG] = {
+ 0, 0x4C, 0x3C, 0x0D, 0xEF, 0xBD, 0xF2, 0x03, 0x00,
+ /* 0x08 */ 0xF8, 0xF8, 0x60, 0x60, 0x00, 0x86, 0x18, 0x90,
+ /* 0x10 */ 0x00, 0x59, 0x40, 0x46, 0x42, 0x1A, 0xFF, 0xDA,
+diff --git a/drivers/media/video/saa7114.c b/drivers/media/video/saa7114.c
+--- a/drivers/media/video/saa7114.c
++++ b/drivers/media/video/saa7114.c
+@@ -163,7 +163,7 @@ saa7114_write_block (struct i2c_client *
+ u8 block_data[32];
+
+ msg.addr = client->addr;
+- msg.flags = client->flags;
++ msg.flags = 0;
+ while (len >= 2) {
+ msg.buf = (char *) block_data;
+ msg.len = 0;
+diff --git a/drivers/media/video/saa7185.c b/drivers/media/video/saa7185.c
+--- a/drivers/media/video/saa7185.c
++++ b/drivers/media/video/saa7185.c
+@@ -118,7 +118,7 @@ saa7185_write_block (struct i2c_client *
+ u8 block_data[32];
+
+ msg.addr = client->addr;
+- msg.flags = client->flags;
++ msg.flags = 0;
+ while (len >= 2) {
+ msg.buf = (char *) block_data;
+ msg.len = 0;
+diff --git a/drivers/net/3c59x.c b/drivers/net/3c59x.c
+--- a/drivers/net/3c59x.c
++++ b/drivers/net/3c59x.c
+@@ -1581,7 +1581,8 @@ vortex_up(struct net_device *dev)
+
+ if (VORTEX_PCI(vp)) {
+ pci_set_power_state(VORTEX_PCI(vp), PCI_D0); /* Go active */
+- pci_restore_state(VORTEX_PCI(vp));
++ if (vp->pm_state_valid)
++ pci_restore_state(VORTEX_PCI(vp));
+ pci_enable_device(VORTEX_PCI(vp));
+ }
+
+@@ -2741,6 +2742,7 @@ vortex_down(struct net_device *dev, int
+ outl(0, ioaddr + DownListPtr);
+
+ if (final_down && VORTEX_PCI(vp)) {
++ vp->pm_state_valid = 1;
+ pci_save_state(VORTEX_PCI(vp));
+ acpi_set_WOL(dev);
+ }
+@@ -3243,9 +3245,10 @@ static void acpi_set_WOL(struct net_devi
+ outw(RxEnable, ioaddr + EL3_CMD);
+
+ pci_enable_wake(VORTEX_PCI(vp), 0, 1);
++
++ /* Change the power state to D3; RxEnable doesn't take effect.
*/
++ pci_set_power_state(VORTEX_PCI(vp), PCI_D3hot);
+ }
+- /* Change the power state to D3; RxEnable doesn't take effect. */
+- pci_set_power_state(VORTEX_PCI(vp), PCI_D3hot);
+ }
+
+
+diff --git a/drivers/net/amd8111e.c b/drivers/net/amd8111e.c
+--- a/drivers/net/amd8111e.c
++++ b/drivers/net/amd8111e.c
+@@ -1381,6 +1381,8 @@ static int amd8111e_open(struct net_devi
+
+ if(amd8111e_restart(dev)){
+ spin_unlock_irq(&lp->lock);
++ if (dev->irq)
++ free_irq(dev->irq, dev);
+ return -ENOMEM;
+ }
+ /* Start ipg timer */
+diff --git a/drivers/net/ppp_async.c b/drivers/net/ppp_async.c
+--- a/drivers/net/ppp_async.c
++++ b/drivers/net/ppp_async.c
+@@ -1000,7 +1000,7 @@ static void async_lcp_peek(struct asyncp
+ data += 4;
+ dlen -= 4;
+ /* data[0] is code, data[1] is length */
+- while (dlen >= 2 && dlen >= data[1]) {
++ while (dlen >= 2 && dlen >= data[1] && data[1] >= 2) {
+ switch (data[0]) {
+ case LCP_MRU:
+ val = (data[2] << 8) + data[3];
+diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
+--- a/drivers/net/r8169.c
++++ b/drivers/net/r8169.c
+@@ -1683,16 +1683,19 @@ static void rtl8169_free_rx_skb(struct r
+ rtl8169_make_unusable_by_asic(desc);
+ }
+
+-static inline void rtl8169_return_to_asic(struct RxDesc *desc, int rx_buf_sz)
++static inline void rtl8169_mark_to_asic(struct RxDesc *desc, u32 rx_buf_sz)
+ {
+- desc->opts1 |= cpu_to_le32(DescOwn + rx_buf_sz);
++ u32 eor = le32_to_cpu(desc->opts1) & RingEnd;
++
++ desc->opts1 = cpu_to_le32(DescOwn | eor | rx_buf_sz);
+ }
+
+-static inline void rtl8169_give_to_asic(struct RxDesc *desc, dma_addr_t
mapping,
+- int rx_buf_sz)
++static inline void rtl8169_map_to_asic(struct RxDesc *desc, dma_addr_t
mapping,
++ u32 rx_buf_sz)
+ {
+ desc->addr = cpu_to_le64(mapping);
+- desc->opts1 |= cpu_to_le32(DescOwn + rx_buf_sz);
++ wmb();
++ rtl8169_mark_to_asic(desc, rx_buf_sz);
+ }
+
+ static int rtl8169_alloc_rx_skb(struct pci_dev *pdev, struct sk_buff
**sk_buff,
+@@ -1712,7 +1715,7 @@ static int rtl8169_alloc_rx_skb(struct p
+ mapping = pci_map_single(pdev, skb->tail, rx_buf_sz,
+ PCI_DMA_FROMDEVICE);
+
+- rtl8169_give_to_asic(desc, mapping, rx_buf_sz);
++ rtl8169_map_to_asic(desc, mapping, rx_buf_sz);
+
+ out:
+ return ret;
+@@ -2150,7 +2153,7 @@ static inline int rtl8169_try_rx_copy(st
+ skb_reserve(skb, NET_IP_ALIGN);
+ eth_copy_and_sum(skb, sk_buff[0]->tail, pkt_size, 0);
+ *sk_buff = skb;
+- rtl8169_return_to_asic(desc, rx_buf_sz);
++ rtl8169_mark_to_asic(desc, rx_buf_sz);
+ ret = 0;
+ }
+ }
+diff --git a/drivers/net/sis900.c b/drivers/net/sis900.c
+--- a/drivers/net/sis900.c
++++ b/drivers/net/sis900.c
+@@ -236,7 +236,7 @@ static int __devinit sis900_get_mac_addr
+ signature = (u16) read_eeprom(ioaddr, EEPROMSignature);
+ if (signature == 0xffff || signature == 0x0000) {
+ printk (KERN_INFO "%s: Error EERPOM read %x\n",
+- net_dev->name, signature);
++ pci_name(pci_dev), signature);
+ return 0;
+ }
+
+@@ -268,7 +268,7 @@ static int __devinit sis630e_get_mac_add
+ if (!isa_bridge)
+ isa_bridge = pci_get_device(PCI_VENDOR_ID_SI, 0x0018,
isa_bridge);
+ if (!isa_bridge) {
+- printk("%s: Can not find ISA bridge\n", net_dev->name);
++ printk("%s: Can not find ISA bridge\n", pci_name(pci_dev));
+ return 0;
+ }
+ pci_read_config_byte(isa_bridge, 0x48, ®);
+@@ -456,10 +456,6 @@ static int __devinit sis900_probe(struct
+ net_dev->tx_timeout = sis900_tx_timeout;
+ net_dev->watchdog_timeo = TX_TIMEOUT;
+ net_dev->ethtool_ops = &sis900_ethtool_ops;
+-
+- ret = register_netdev(net_dev);
+- if (ret)
+- goto err_unmap_rx;
+
+ /* Get Mac address according to the chip revision */
+ pci_read_config_byte(pci_dev, PCI_CLASS_REVISION, &revision);
+@@ -476,7 +472,7 @@ static int __devinit sis900_probe(struct
+
+ if (ret == 0) {
+ ret = -ENODEV;
+- goto err_out_unregister;
++ goto err_unmap_rx;
+ }
+
+ /* 630ET : set the mii access mode as software-mode */
+@@ -486,7 +482,7 @@ static int __devinit sis900_probe(struct
+ /* probe for mii transceiver */
+ if (sis900_mii_probe(net_dev) == 0) {
+ ret = -ENODEV;
+- goto err_out_unregister;
++ goto err_unmap_rx;
+ }
+
+ /* save our host bridge revision */
+@@ -496,6 +492,10 @@ static int __devinit sis900_probe(struct
+ pci_dev_put(dev);
+ }
+
++ ret = register_netdev(net_dev);
++ if (ret)
++ goto err_unmap_rx;
++
+ /* print some information about our NIC */
+ printk(KERN_INFO "%s: %s at %#lx, IRQ %d, ", net_dev->name,
+ card_name, ioaddr, net_dev->irq);
+@@ -505,8 +505,6 @@ static int __devinit sis900_probe(struct
+
+ return 0;
+
+- err_out_unregister:
+- unregister_netdev(net_dev);
+ err_unmap_rx:
+ pci_free_consistent(pci_dev, RX_TOTAL_SIZE, sis_priv->rx_ring,
+ sis_priv->rx_ring_dma);
+@@ -533,6 +531,7 @@ static int __devinit sis900_probe(struct
+ static int __init sis900_mii_probe(struct net_device * net_dev)
+ {
+ struct sis900_private * sis_priv = net_dev->priv;
++ const char *dev_name = pci_name(sis_priv->pci_dev);
+ u16 poll_bit = MII_STAT_LINK, status = 0;
+ unsigned long timeout = jiffies + 5 * HZ;
+ int phy_addr;
+@@ -582,21 +581,20 @@ static int __init sis900_mii_probe(struc
+ mii_phy->phy_types =
+ (mii_status & (MII_STAT_CAN_TX_FDX
| MII_STAT_CAN_TX)) ? LAN : HOME;
+ printk(KERN_INFO "%s: %s transceiver found at
address %d.\n",
+- net_dev->name, mii_chip_table[i].name,
++ dev_name, mii_chip_table[i].name,
+ phy_addr);
+ break;
+ }
+
+ if( !mii_chip_table[i].phy_id1 ) {
+ printk(KERN_INFO "%s: Unknown PHY transceiver found at
address %d.\n",
+- net_dev->name, phy_addr);
++ dev_name, phy_addr);
+ mii_phy->phy_types = UNKNOWN;
+ }
+ }
+
+ if (sis_priv->mii == NULL) {
+- printk(KERN_INFO "%s: No MII transceivers found!\n",
+- net_dev->name);
++ printk(KERN_INFO "%s: No MII transceivers found!\n", dev_name);
+ return 0;
+ }
+
+@@ -621,7 +619,7 @@ static int __init sis900_mii_probe(struc
+ poll_bit ^= (mdio_read(net_dev, sis_priv->cur_phy,
MII_STATUS) & poll_bit);
+ if (time_after_eq(jiffies, timeout)) {
+ printk(KERN_WARNING "%s: reset phy and link
down now\n",
+- net_dev->name);
++ dev_name);
+ return -ETIME;
+ }
+ }
+@@ -691,7 +689,7 @@ static u16 sis900_default_phy(struct net
+ sis_priv->mii = default_phy;
+ sis_priv->cur_phy = default_phy->phy_addr;
+ printk(KERN_INFO "%s: Using transceiver found at address %d as
default\n",
+- net_dev->name,sis_priv->cur_phy);
++ pci_name(sis_priv->pci_dev), sis_priv->cur_phy);
+ }
+
+ status = mdio_read(net_dev, sis_priv->cur_phy, MII_CONTROL);
+diff --git a/drivers/net/tun.c b/drivers/net/tun.c
+--- a/drivers/net/tun.c
++++ b/drivers/net/tun.c
+@@ -229,7 +229,7 @@ static __inline__ ssize_t tun_get_user(s
+ size_t len = count;
+
+ if (!(tun->flags & TUN_NO_PI)) {
+- if ((len -= sizeof(pi)) > len)
++ if ((len -= sizeof(pi)) > count)
+ return -EINVAL;
+
+ if(memcpy_fromiovec((void *)&pi, iv, sizeof(pi)))
+diff --git a/drivers/net/via-rhine.c b/drivers/net/via-rhine.c
+--- a/drivers/net/via-rhine.c
++++ b/drivers/net/via-rhine.c
+@@ -1197,8 +1197,10 @@ static int rhine_open(struct net_device
+ dev->name, rp->pdev->irq);
+
+ rc = alloc_ring(dev);
+- if (rc)
++ if (rc) {
++ free_irq(rp->pdev->irq, dev);
+ return rc;
++ }
+ alloc_rbufs(dev);
+ alloc_tbufs(dev);
+ rhine_chip_reset(dev);
+@@ -1899,6 +1901,9 @@ static void rhine_shutdown (struct devic
+ struct rhine_private *rp = netdev_priv(dev);
+ void __iomem *ioaddr = rp->base;
+
++ if (!(rp->quirks & rqWOL))
++ return; /* Nothing to do for non-WOL adapters */
++
+ rhine_power_init(dev);
+
+ /* Make sure we use pattern 0, 1 and not 4, 5 */
+diff --git a/drivers/net/wan/hd6457x.c b/drivers/net/wan/hd6457x.c
+--- a/drivers/net/wan/hd6457x.c
++++ b/drivers/net/wan/hd6457x.c
+@@ -315,7 +315,7 @@ static inline void sca_rx(card_t *card,
+ #endif
+ stats->rx_packets++;
+ stats->rx_bytes += skb->len;
+- skb->dev->last_rx = jiffies;
++ dev->last_rx = jiffies;
+ skb->protocol = hdlc_type_trans(skb, dev);
+ netif_rx(skb);
+ }
+diff --git a/drivers/pci/hotplug/pciehp_ctrl.c
b/drivers/pci/hotplug/pciehp_ctrl.c
+--- a/drivers/pci/hotplug/pciehp_ctrl.c
++++ b/drivers/pci/hotplug/pciehp_ctrl.c
+@@ -1354,10 +1354,11 @@ static u32 remove_board(struct pci_func
+ dbg("PCI Bridge Hot-Remove
s:b:d:f(%02x:%02x:%02x:%02x)\n",
+ ctrl->seg, func->bus, func->device,
func->function);
+ bridge_slot_remove(func);
+- } else
++ } else {
+ dbg("PCI Function Hot-Remove
s:b:d:f(%02x:%02x:%02x:%02x)\n",
+ ctrl->seg, func->bus, func->device,
func->function);
+ slot_remove(func);
++ }
+
+ func = pciehp_slot_find(ctrl->slot_bus, device, 0);
+ }
+diff --git a/drivers/usb/serial/visor.c b/drivers/usb/serial/visor.c
+--- a/drivers/usb/serial/visor.c
++++ b/drivers/usb/serial/visor.c
+@@ -386,6 +386,7 @@ struct visor_private {
+ int bytes_in;
+ int bytes_out;
+ int outstanding_urbs;
++ int throttled;
+ };
+
+ /* number of outstanding urbs to prevent userspace DoS from happening */
+@@ -415,6 +416,7 @@ static int visor_open (struct usb_serial
+ priv->bytes_in = 0;
+ priv->bytes_out = 0;
+ priv->outstanding_urbs = 0;
++ priv->throttled = 0;
+ spin_unlock_irqrestore(&priv->lock, flags);
+
+ /*
+@@ -602,6 +604,7 @@ static void visor_read_bulk_callback (st
+ struct tty_struct *tty;
+ unsigned long flags;
+ int i;
++ int throttled;
+ int result;
+
+ dbg("%s - port %d", __FUNCTION__, port->number);
+@@ -627,18 +630,21 @@ static void visor_read_bulk_callback (st
+ }
+ spin_lock_irqsave(&priv->lock, flags);
+ priv->bytes_in += urb->actual_length;
++ throttled = priv->throttled;
+ spin_unlock_irqrestore(&priv->lock, flags);
+
+- /* Continue trying to always read */
+- usb_fill_bulk_urb (port->read_urb, port->serial->dev,
+- usb_rcvbulkpipe(port->serial->dev,
+- port->bulk_in_endpointAddress),
+- port->read_urb->transfer_buffer,
+- port->read_urb->transfer_buffer_length,
+- visor_read_bulk_callback, port);
+- result = usb_submit_urb(port->read_urb, GFP_ATOMIC);
+- if (result)
+- dev_err(&port->dev, "%s - failed resubmitting read urb, error
%d\n", __FUNCTION__, result);
++ /* Continue trying to always read if we should */
++ if (!throttled) {
++ usb_fill_bulk_urb (port->read_urb, port->serial->dev,
++ usb_rcvbulkpipe(port->serial->dev,
++
port->bulk_in_endpointAddress),
++ port->read_urb->transfer_buffer,
++ port->read_urb->transfer_buffer_length,
++ visor_read_bulk_callback, port);
++ result = usb_submit_urb(port->read_urb, GFP_ATOMIC);
++ if (result)
++ dev_err(&port->dev, "%s - failed resubmitting read urb,
error %d\n", __FUNCTION__, result);
++ }
+ return;
+ }
+
+@@ -683,16 +689,26 @@ exit:
+
+ static void visor_throttle (struct usb_serial_port *port)
+ {
++ struct visor_private *priv = usb_get_serial_port_data(port);
++ unsigned long flags;
++
+ dbg("%s - port %d", __FUNCTION__, port->number);
+- usb_kill_urb(port->read_urb);
++ spin_lock_irqsave(&priv->lock, flags);
++ priv->throttled = 1;
++ spin_unlock_irqrestore(&priv->lock, flags);
+ }
+
+
+ static void visor_unthrottle (struct usb_serial_port *port)
+ {
++ struct visor_private *priv = usb_get_serial_port_data(port);
++ unsigned long flags;
+ int result;
+
+ dbg("%s - port %d", __FUNCTION__, port->number);
++ spin_lock_irqsave(&priv->lock, flags);
++ priv->throttled = 0;
++ spin_unlock_irqrestore(&priv->lock, flags);
+
+ port->read_urb->dev = port->serial->dev;
+ result = usb_submit_urb(port->read_urb, GFP_ATOMIC);
+diff --git a/drivers/video/matrox/matroxfb_accel.c
b/drivers/video/matrox/matroxfb_accel.c
+--- a/drivers/video/matrox/matroxfb_accel.c
++++ b/drivers/video/matrox/matroxfb_accel.c
+@@ -438,13 +438,21 @@ static void matroxfb_1bpp_imageblit(WPMI
+ } else if (step == 1) {
+ /* Special case for 1..8bit widths */
+ while (height--) {
+- mga_writel(mmio, 0, *chardata);
++#if defined(__BIG_ENDIAN)
++ fb_writel((*chardata) << 24, mmio.vaddr);
++#else
++ fb_writel(*chardata, mmio.vaddr);
++#endif
+ chardata++;
+ }
+ } else if (step == 2) {
+ /* Special case for 9..15bit widths */
+ while (height--) {
+- mga_writel(mmio, 0, *(u_int16_t*)chardata);
++#if defined(__BIG_ENDIAN)
++ fb_writel((*(u_int16_t*)chardata) << 16,
mmio.vaddr);
++#else
++ fb_writel(*(u_int16_t*)chardata, mmio.vaddr);
++#endif
+ chardata += 2;
+ }
+ } else {
+@@ -454,7 +462,7 @@ static void matroxfb_1bpp_imageblit(WPMI
+
+ for (i = 0; i < step; i += 4) {
+ /* Hope that there are at least three
readable bytes beyond the end of bitmap */
+- mga_writel(mmio, 0,
get_unaligned((u_int32_t*)(chardata + i)));
++
fb_writel(get_unaligned((u_int32_t*)(chardata + i)),mmio.vaddr);
+ }
+ chardata += step;
+ }
+diff --git a/drivers/video/matrox/matroxfb_base.h
b/drivers/video/matrox/matroxfb_base.h
+--- a/drivers/video/matrox/matroxfb_base.h
++++ b/drivers/video/matrox/matroxfb_base.h
+@@ -170,14 +170,14 @@ static inline void mga_memcpy_toio(vaddr
+
+ if ((unsigned long)src & 3) {
+ while (len >= 4) {
+- writel(get_unaligned((u32 *)src), addr);
++ fb_writel(get_unaligned((u32 *)src), addr);
+ addr++;
+ len -= 4;
+ src += 4;
+ }
+ } else {
+ while (len >= 4) {
+- writel(*(u32 *)src, addr);
++ fb_writel(*(u32 *)src, addr);
+ addr++;
+ len -= 4;
+ src += 4;
+diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
+--- a/fs/binfmt_elf.c
++++ b/fs/binfmt_elf.c
+@@ -257,7 +257,7 @@ create_elf_tables(struct linux_binprm *b
+ }
+
+ /* Populate argv and envp */
+- p = current->mm->arg_start;
++ p = current->mm->arg_end = current->mm->arg_start;
+ while (argc-- > 0) {
+ size_t len;
+ __put_user((elf_addr_t)p, argv++);
+@@ -1008,6 +1008,7 @@ out_free_ph:
+ static int load_elf_library(struct file *file)
+ {
+ struct elf_phdr *elf_phdata;
++ struct elf_phdr *eppnt;
+ unsigned long elf_bss, bss, len;
+ int retval, error, i, j;
+ struct elfhdr elf_ex;
+@@ -1031,44 +1032,47 @@ static int load_elf_library(struct file
+ /* j < ELF_MIN_ALIGN because elf_ex.e_phnum <= 2 */
+
+ error = -ENOMEM;
+- elf_phdata = (struct elf_phdr *) kmalloc(j, GFP_KERNEL);
++ elf_phdata = kmalloc(j, GFP_KERNEL);
+ if (!elf_phdata)
+ goto out;
+
++ eppnt = elf_phdata;
+ error = -ENOEXEC;
+- retval = kernel_read(file, elf_ex.e_phoff, (char *) elf_phdata, j);
++ retval = kernel_read(file, elf_ex.e_phoff, (char *)eppnt, j);
+ if (retval != j)
+ goto out_free_ph;
+
+ for (j = 0, i = 0; i<elf_ex.e_phnum; i++)
+- if ((elf_phdata + i)->p_type == PT_LOAD) j++;
++ if ((eppnt + i)->p_type == PT_LOAD)
++ j++;
+ if (j != 1)
+ goto out_free_ph;
+
+- while (elf_phdata->p_type != PT_LOAD) elf_phdata++;
++ while (eppnt->p_type != PT_LOAD)
++ eppnt++;
+
+ /* Now use mmap to map the library into memory. */
+ down_write(¤t->mm->mmap_sem);
+ error = do_mmap(file,
+- ELF_PAGESTART(elf_phdata->p_vaddr),
+- (elf_phdata->p_filesz +
+- ELF_PAGEOFFSET(elf_phdata->p_vaddr)),
++ ELF_PAGESTART(eppnt->p_vaddr),
++ (eppnt->p_filesz +
++ ELF_PAGEOFFSET(eppnt->p_vaddr)),
+ PROT_READ | PROT_WRITE | PROT_EXEC,
+ MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE,
+- (elf_phdata->p_offset -
+- ELF_PAGEOFFSET(elf_phdata->p_vaddr)));
++ (eppnt->p_offset -
++ ELF_PAGEOFFSET(eppnt->p_vaddr)));
+ up_write(¤t->mm->mmap_sem);
+- if (error != ELF_PAGESTART(elf_phdata->p_vaddr))
++ if (error != ELF_PAGESTART(eppnt->p_vaddr))
+ goto out_free_ph;
+
+- elf_bss = elf_phdata->p_vaddr + elf_phdata->p_filesz;
++ elf_bss = eppnt->p_vaddr + eppnt->p_filesz;
+ if (padzero(elf_bss)) {
+ error = -EFAULT;
+ goto out_free_ph;
+ }
+
+- len = ELF_PAGESTART(elf_phdata->p_filesz + elf_phdata->p_vaddr +
ELF_MIN_ALIGN - 1);
+- bss = elf_phdata->p_memsz + elf_phdata->p_vaddr;
++ len = ELF_PAGESTART(eppnt->p_filesz + eppnt->p_vaddr + ELF_MIN_ALIGN -
1);
++ bss = eppnt->p_memsz + eppnt->p_vaddr;
+ if (bss > len) {
+ down_write(¤t->mm->mmap_sem);
+ do_brk(len, bss - len);
+@@ -1275,7 +1279,7 @@ static void fill_prstatus(struct elf_prs
+ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
+ struct mm_struct *mm)
+ {
+- int i, len;
++ unsigned int i, len;
+
+ /* first copy the parameters from user space */
+ memset(psinfo, 0, sizeof(struct elf_prpsinfo));
+diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
+--- a/fs/cramfs/inode.c
++++ b/fs/cramfs/inode.c
+@@ -70,6 +70,7 @@ static struct inode *get_cramfs_inode(st
+ inode->i_data.a_ops = &cramfs_aops;
+ } else {
+ inode->i_size = 0;
++ inode->i_blocks = 0;
+ init_special_inode(inode, inode->i_mode,
+ old_decode_dev(cramfs_inode->size));
+ }
+diff --git a/fs/eventpoll.c b/fs/eventpoll.c
+--- a/fs/eventpoll.c
++++ b/fs/eventpoll.c
+@@ -619,6 +619,7 @@ eexit_1:
+ return error;
+ }
+
++#define MAX_EVENTS (INT_MAX / sizeof(struct epoll_event))
+
+ /*
+ * Implement the event wait interface for the eventpoll file. It is the kernel
+@@ -635,7 +636,7 @@ asmlinkage long sys_epoll_wait(int epfd,
+ current, epfd, events, maxevents, timeout));
+
+ /* The maximum number of event must be greater than zero */
+- if (maxevents <= 0)
++ if (maxevents <= 0 || maxevents > MAX_EVENTS)
+ return -EINVAL;
+
+ /* Verify that the area passed by the user is writeable */
+diff --git a/fs/exec.c b/fs/exec.c
+--- a/fs/exec.c
++++ b/fs/exec.c
+@@ -814,7 +814,7 @@ void get_task_comm(char *buf, struct tas
+ {
+ /* buf must be at least sizeof(tsk->comm) in size */
+ task_lock(tsk);
+- memcpy(buf, tsk->comm, sizeof(tsk->comm));
++ strncpy(buf, tsk->comm, sizeof(tsk->comm));
+ task_unlock(tsk);
+ }
+
+diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
+--- a/fs/ext2/dir.c
++++ b/fs/ext2/dir.c
+@@ -592,6 +592,7 @@ int ext2_make_empty(struct inode *inode,
+ goto fail;
+ }
+ kaddr = kmap_atomic(page, KM_USER0);
++ memset(kaddr, 0, chunk_size);
+ de = (struct ext2_dir_entry_2 *)kaddr;
+ de->name_len = 1;
+ de->rec_len = cpu_to_le16(EXT2_DIR_REC_LEN(1));
+diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
+--- a/fs/ext3/balloc.c
++++ b/fs/ext3/balloc.c
+@@ -268,7 +268,8 @@ void ext3_discard_reservation(struct ino
+
+ if (!rsv_is_empty(&rsv->rsv_window)) {
+ spin_lock(rsv_lock);
+- rsv_window_remove(inode->i_sb, rsv);
++ if (!rsv_is_empty(&rsv->rsv_window))
++ rsv_window_remove(inode->i_sb, rsv);
+ spin_unlock(rsv_lock);
+ }
+ }
+diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c
+--- a/fs/hfs/mdb.c
++++ b/fs/hfs/mdb.c
+@@ -333,6 +333,8 @@ void hfs_mdb_close(struct super_block *s
+ * Release the resources associated with the in-core MDB. */
+ void hfs_mdb_put(struct super_block *sb)
+ {
++ if (!HFS_SB(sb))
++ return;
+ /* free the B-trees */
+ hfs_btree_close(HFS_SB(sb)->ext_tree);
+ hfs_btree_close(HFS_SB(sb)->cat_tree);
+@@ -340,4 +342,7 @@ void hfs_mdb_put(struct super_block *sb)
+ /* free the buffers holding the primary and alternate MDBs */
+ brelse(HFS_SB(sb)->mdb_bh);
+ brelse(HFS_SB(sb)->alt_mdb_bh);
++
++ kfree(HFS_SB(sb));
++ sb->s_fs_info = NULL;
+ }
+diff --git a/fs/hfs/super.c b/fs/hfs/super.c
+--- a/fs/hfs/super.c
++++ b/fs/hfs/super.c
+@@ -263,7 +263,7 @@ static int hfs_fill_super(struct super_b
+ res = -EINVAL;
+ if (!parse_options((char *)data, sbi)) {
+ hfs_warn("hfs_fs: unable to parse mount options.\n");
+- goto bail3;
++ goto bail;
+ }
+
+ sb->s_op = &hfs_super_operations;
+@@ -276,7 +276,7 @@ static int hfs_fill_super(struct super_b
+ hfs_warn("VFS: Can't find a HFS filesystem on dev
%s.\n",
+ hfs_mdb_name(sb));
+ res = -EINVAL;
+- goto bail2;
++ goto bail;
+ }
+
+ /* try to get the root inode */
+@@ -306,10 +306,8 @@ bail_iput:
+ iput(root_inode);
+ bail_no_root:
+ hfs_warn("hfs_fs: get root inode failed.\n");
++bail:
+ hfs_mdb_put(sb);
+-bail2:
+-bail3:
+- kfree(sbi);
+ return res;
+ }
+
+diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
+--- a/fs/hfsplus/super.c
++++ b/fs/hfsplus/super.c
+@@ -207,7 +207,9 @@ static void hfsplus_write_super(struct s
+ static void hfsplus_put_super(struct super_block *sb)
+ {
+ dprint(DBG_SUPER, "hfsplus_put_super\n");
+- if (!(sb->s_flags & MS_RDONLY)) {
++ if (!sb->s_fs_info)
++ return;
++ if (!(sb->s_flags & MS_RDONLY) && HFSPLUS_SB(sb).s_vhdr) {
+ struct hfsplus_vh *vhdr = HFSPLUS_SB(sb).s_vhdr;
+
+ vhdr->modify_date = hfsp_now2mt();
+@@ -223,6 +225,8 @@ static void hfsplus_put_super(struct sup
+ iput(HFSPLUS_SB(sb).alloc_file);
+ iput(HFSPLUS_SB(sb).hidden_dir);
+ brelse(HFSPLUS_SB(sb).s_vhbh);
++ kfree(sb->s_fs_info);
++ sb->s_fs_info = NULL;
+ }
+
+ static int hfsplus_statfs(struct super_block *sb, struct kstatfs *buf)
+diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
+--- a/fs/isofs/inode.c
++++ b/fs/isofs/inode.c
+@@ -685,6 +685,8 @@ root_found:
+ sbi->s_log_zone_size = isonum_723 (h_pri->logical_block_size);
+ sbi->s_max_size = isonum_733(h_pri->volume_space_size);
+ } else {
++ if (!pri)
++ goto out_freebh;
+ rootp = (struct iso_directory_record *) pri->root_directory_record;
+ sbi->s_nzones = isonum_733 (pri->volume_space_size);
+ sbi->s_log_zone_size = isonum_723 (pri->logical_block_size);
+@@ -1395,6 +1397,9 @@ struct inode *isofs_iget(struct super_bl
+ struct inode *inode;
+ struct isofs_iget5_callback_data data;
+
++ if (offset >= 1ul << sb->s_blocksize_bits)
++ return NULL;
++
+ data.block = block;
+ data.offset = offset;
+
+diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
+--- a/fs/isofs/rock.c
++++ b/fs/isofs/rock.c
+@@ -53,6 +53,7 @@
+ if(LEN & 1) LEN++; \
+ CHR = ((unsigned char *) DE) + LEN; \
+ LEN = *((unsigned char *) DE) - LEN; \
++ if (LEN<0) LEN=0; \
+ if (ISOFS_SB(inode->i_sb)->s_rock_offset!=-1) \
+ { \
+ LEN-=ISOFS_SB(inode->i_sb)->s_rock_offset; \
+@@ -73,6 +74,10 @@
+ offset1 = 0; \
+ pbh = sb_bread(DEV->i_sb, block); \
+ if(pbh){ \
++ if (offset > pbh->b_size || offset + cont_size > pbh->b_size){ \
++ brelse(pbh); \
++ goto out; \
++ } \
+ memcpy(buffer + offset1, pbh->b_data + offset, cont_size - offset1); \
+ brelse(pbh); \
+ chr = (unsigned char *) buffer; \
+@@ -103,12 +108,13 @@ int get_rock_ridge_filename(struct iso_d
+ struct rock_ridge * rr;
+ int sig;
+
+- while (len > 1){ /* There may be one byte for padding somewhere */
++ while (len > 2){ /* There may be one byte for padding somewhere */
+ rr = (struct rock_ridge *) chr;
+- if (rr->len == 0) goto out; /* Something got screwed up here */
++ if (rr->len < 3) goto out; /* Something got screwed up here */
+ sig = isonum_721(chr);
+ chr += rr->len;
+ len -= rr->len;
++ if (len < 0) goto out; /* corrupted isofs */
+
+ switch(sig){
+ case SIG('R','R'):
+@@ -122,6 +128,7 @@ int get_rock_ridge_filename(struct iso_d
+ break;
+ case SIG('N','M'):
+ if (truncate) break;
++ if (rr->len < 5) break;
+ /*
+ * If the flags are 2 or 4, this indicates '.' or '..'.
+ * We don't want to do anything with this, because it
+@@ -186,12 +193,13 @@ parse_rock_ridge_inode_internal(struct i
+ struct rock_ridge * rr;
+ int rootflag;
+
+- while (len > 1){ /* There may be one byte for padding somewhere */
++ while (len > 2){ /* There may be one byte for padding somewhere */
+ rr = (struct rock_ridge *) chr;
+- if (rr->len == 0) goto out; /* Something got screwed up here */
++ if (rr->len < 3) goto out; /* Something got screwed up here */
+ sig = isonum_721(chr);
+ chr += rr->len;
+ len -= rr->len;
++ if (len < 0) goto out; /* corrupted isofs */
+
+ switch(sig){
+ #ifndef CONFIG_ZISOFS /* No flag for SF or ZF */
+@@ -462,7 +470,7 @@ static int rock_ridge_symlink_readpage(s
+ struct rock_ridge *rr;
+
+ if (!ISOFS_SB(inode->i_sb)->s_rock)
+- panic ("Cannot have symlink with high sierra variant of iso
filesystem\n");
++ goto error;
+
+ block = ei->i_iget5_block;
+ lock_kernel();
+@@ -487,13 +495,15 @@ static int rock_ridge_symlink_readpage(s
+ SETUP_ROCK_RIDGE(raw_inode, chr, len);
+
+ repeat:
+- while (len > 1) { /* There may be one byte for padding somewhere */
++ while (len > 2) { /* There may be one byte for padding somewhere */
+ rr = (struct rock_ridge *) chr;
+- if (rr->len == 0)
++ if (rr->len < 3)
+ goto out; /* Something got screwed up here */
+ sig = isonum_721(chr);
+ chr += rr->len;
+ len -= rr->len;
++ if (len < 0)
++ goto out; /* corrupted isofs */
+
+ switch (sig) {
+ case SIG('R', 'R'):
+@@ -543,6 +553,7 @@ static int rock_ridge_symlink_readpage(s
+ fail:
+ brelse(bh);
+ unlock_kernel();
++ error:
+ SetPageError(page);
+ kunmap(page);
+ unlock_page(page);
+diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c
+--- a/fs/jbd/checkpoint.c
++++ b/fs/jbd/checkpoint.c
+@@ -339,8 +339,10 @@ int log_do_checkpoint(journal_t *journal
+ }
+ } while (jh != last_jh && !retry);
+
+- if (batch_count)
++ if (batch_count) {
+ __flush_batch(journal, bhs, &batch_count);
++ retry = 1;
++ }
+
+ /*
+ * If someone cleaned up this transaction while we slept, we're
+diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
+--- a/fs/jbd/transaction.c
++++ b/fs/jbd/transaction.c
+@@ -1775,10 +1775,10 @@ static int journal_unmap_buffer(journal_
+ JBUFFER_TRACE(jh, "checkpointed: add to BJ_Forget");
+ ret = __dispose_buffer(jh,
+ journal->j_running_transaction);
++ journal_put_journal_head(jh);
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+ spin_unlock(&journal->j_state_lock);
+- journal_put_journal_head(jh);
+ return ret;
+ } else {
+ /* There is no currently-running transaction. So the
+@@ -1789,10 +1789,10 @@ static int journal_unmap_buffer(journal_
+ JBUFFER_TRACE(jh, "give to committing trans");
+ ret = __dispose_buffer(jh,
+ journal->j_committing_transaction);
++ journal_put_journal_head(jh);
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+ spin_unlock(&journal->j_state_lock);
+- journal_put_journal_head(jh);
+ return ret;
+ } else {
+ /* The orphan record's transaction has
+@@ -1813,10 +1813,10 @@ static int journal_unmap_buffer(journal_
+ journal->j_running_transaction);
+ jh->b_next_transaction = NULL;
+ }
++ journal_put_journal_head(jh);
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+ spin_unlock(&journal->j_state_lock);
+- journal_put_journal_head(jh);
+ return 0;
+ } else {
+ /* Good, the buffer belongs to the running transaction.
+diff --git a/include/asm-x86_64/processor.h b/include/asm-x86_64/processor.h
+--- a/include/asm-x86_64/processor.h
++++ b/include/asm-x86_64/processor.h
+@@ -160,9 +160,9 @@ static inline void clear_in_cr4 (unsigne
+
+
+ /*
+- * User space process size. 47bits.
++ * User space process size. 47bits minus one guard page.
+ */
+-#define TASK_SIZE (0x800000000000UL)
++#define TASK_SIZE (0x800000000000UL - 4096)
+
+ /* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+diff --git a/include/linux/err.h b/include/linux/err.h
+--- a/include/linux/err.h
++++ b/include/linux/err.h
+@@ -13,6 +13,8 @@
+ * This should be a per-architecture thing, to allow different
+ * error and pointer decisions.
+ */
++#define IS_ERR_VALUE(x) unlikely((x) > (unsigned long)-1000L)
++
+ static inline void *ERR_PTR(long error)
+ {
+ return (void *) error;
+@@ -25,7 +27,7 @@ static inline long PTR_ERR(const void *p
+
+ static inline long IS_ERR(const void *ptr)
+ {
+- return unlikely((unsigned long)ptr > (unsigned long)-1000L);
++ return IS_ERR_VALUE((unsigned long)ptr);
+ }
+
+ #endif /* _LINUX_ERR_H */
+diff --git a/kernel/exit.c b/kernel/exit.c
+--- a/kernel/exit.c
++++ b/kernel/exit.c
+@@ -516,8 +516,6 @@ static inline void choose_new_parent(tas
+ */
+ BUG_ON(p == reaper || reaper->exit_state >= EXIT_ZOMBIE);
+ p->real_parent = reaper;
+- if (p->parent == p->real_parent)
+- BUG();
+ }
+
+ static inline void reparent_thread(task_t *p, task_t *father, int traced)
+diff --git a/kernel/signal.c b/kernel/signal.c
+--- a/kernel/signal.c
++++ b/kernel/signal.c
+@@ -1728,6 +1728,7 @@ do_signal_stop(int signr)
+ * with another processor delivering a stop signal,
+ * then the SIGCONT that wakes us up should clear it.
+ */
++ read_unlock(&tasklist_lock);
+ return 0;
+ }
+
+diff --git a/lib/rwsem-spinlock.c b/lib/rwsem-spinlock.c
+--- a/lib/rwsem-spinlock.c
++++ b/lib/rwsem-spinlock.c
+@@ -140,12 +140,12 @@ void fastcall __sched __down_read(struct
+
+ rwsemtrace(sem, "Entering __down_read");
+
+- spin_lock(&sem->wait_lock);
++ spin_lock_irq(&sem->wait_lock);
+
+ if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+ /* granted */
+ sem->activity++;
+- spin_unlock(&sem->wait_lock);
++ spin_unlock_irq(&sem->wait_lock);
+ goto out;
+ }
+
+@@ -160,7 +160,7 @@ void fastcall __sched __down_read(struct
+ list_add_tail(&waiter.list, &sem->wait_list);
+
+ /* we don't need to touch the semaphore struct anymore */
+- spin_unlock(&sem->wait_lock);
++ spin_unlock_irq(&sem->wait_lock);
+
+ /* wait to be given the lock */
+ for (;;) {
+@@ -181,10 +181,12 @@ void fastcall __sched __down_read(struct
+ */
+ int fastcall __down_read_trylock(struct rw_semaphore *sem)
+ {
++ unsigned long flags;
+ int ret = 0;
++
+ rwsemtrace(sem, "Entering __down_read_trylock");
+
+- spin_lock(&sem->wait_lock);
++ spin_lock_irqsave(&sem->wait_lock, flags);
+
+ if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+ /* granted */
+@@ -192,7 +194,7 @@ int fastcall __down_read_trylock(struct
+ ret = 1;
+ }
+
+- spin_unlock(&sem->wait_lock);
++ spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+ rwsemtrace(sem, "Leaving __down_read_trylock");
+ return ret;
+@@ -209,12 +211,12 @@ void fastcall __sched __down_write(struc
+
+ rwsemtrace(sem, "Entering __down_write");
+
+- spin_lock(&sem->wait_lock);
++ spin_lock_irq(&sem->wait_lock);
+
+ if (sem->activity == 0 && list_empty(&sem->wait_list)) {
+ /* granted */
+ sem->activity = -1;
+- spin_unlock(&sem->wait_lock);
++ spin_unlock_irq(&sem->wait_lock);
+ goto out;
+ }
+
+@@ -229,7 +231,7 @@ void fastcall __sched __down_write(struc
+ list_add_tail(&waiter.list, &sem->wait_list);
+
+ /* we don't need to touch the semaphore struct anymore */
+- spin_unlock(&sem->wait_lock);
++ spin_unlock_irq(&sem->wait_lock);
+
+ /* wait to be given the lock */
+ for (;;) {
+@@ -250,10 +252,12 @@ void fastcall __sched __down_write(struc
+ */
+ int fastcall __down_write_trylock(struct rw_semaphore *sem)
+ {
++ unsigned long flags;
+ int ret = 0;
++
+ rwsemtrace(sem, "Entering __down_write_trylock");
+
+- spin_lock(&sem->wait_lock);
++ spin_lock_irqsave(&sem->wait_lock, flags);
+
+ if (sem->activity == 0 && list_empty(&sem->wait_list)) {
+ /* granted */
+@@ -261,7 +265,7 @@ int fastcall __down_write_trylock(struct
+ ret = 1;
+ }
+
+- spin_unlock(&sem->wait_lock);
++ spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+ rwsemtrace(sem, "Leaving __down_write_trylock");
+ return ret;
+@@ -272,14 +276,16 @@ int fastcall __down_write_trylock(struct
+ */
+ void fastcall __up_read(struct rw_semaphore *sem)
+ {
++ unsigned long flags;
++
+ rwsemtrace(sem, "Entering __up_read");
+
+- spin_lock(&sem->wait_lock);
++ spin_lock_irqsave(&sem->wait_lock, flags);
+
+ if (--sem->activity == 0 && !list_empty(&sem->wait_list))
+ sem = __rwsem_wake_one_writer(sem);
+
+- spin_unlock(&sem->wait_lock);
++ spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+ rwsemtrace(sem, "Leaving __up_read");
+ }
+@@ -289,15 +295,17 @@ void fastcall __up_read(struct rw_semaph
+ */
+ void fastcall __up_write(struct rw_semaphore *sem)
+ {
++ unsigned long flags;
++
+ rwsemtrace(sem, "Entering __up_write");
+
+- spin_lock(&sem->wait_lock);
++ spin_lock_irqsave(&sem->wait_lock, flags);
+
+ sem->activity = 0;
+ if (!list_empty(&sem->wait_list))
+ sem = __rwsem_do_wake(sem, 1);
+
+- spin_unlock(&sem->wait_lock);
++ spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+ rwsemtrace(sem, "Leaving __up_write");
+ }
+@@ -308,15 +316,17 @@ void fastcall __up_write(struct rw_semap
+ */
+ void fastcall __downgrade_write(struct rw_semaphore *sem)
+ {
++ unsigned long flags;
++
+ rwsemtrace(sem, "Entering __downgrade_write");
+
+- spin_lock(&sem->wait_lock);
++ spin_lock_irqsave(&sem->wait_lock, flags);
+
+ sem->activity = 1;
+ if (!list_empty(&sem->wait_list))
+ sem = __rwsem_do_wake(sem, 0);
+
+- spin_unlock(&sem->wait_lock);
++ spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+ rwsemtrace(sem, "Leaving __downgrade_write");
+ }
+diff --git a/lib/rwsem.c b/lib/rwsem.c
+--- a/lib/rwsem.c
++++ b/lib/rwsem.c
+@@ -150,7 +150,7 @@ rwsem_down_failed_common(struct rw_semap
+ set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+
+ /* set up my own style of waitqueue */
+- spin_lock(&sem->wait_lock);
++ spin_lock_irq(&sem->wait_lock);
+ waiter->task = tsk;
+ get_task_struct(tsk);
+
+@@ -163,7 +163,7 @@ rwsem_down_failed_common(struct rw_semap
+ if (!(count & RWSEM_ACTIVE_MASK))
+ sem = __rwsem_do_wake(sem, 0);
+
+- spin_unlock(&sem->wait_lock);
++ spin_unlock_irq(&sem->wait_lock);
+
+ /* wait to be given the lock */
+ for (;;) {
+@@ -219,15 +219,17 @@ rwsem_down_write_failed(struct rw_semaph
+ */
+ struct rw_semaphore fastcall *rwsem_wake(struct rw_semaphore *sem)
+ {
++ unsigned long flags;
++
+ rwsemtrace(sem, "Entering rwsem_wake");
+
+- spin_lock(&sem->wait_lock);
++ spin_lock_irqsave(&sem->wait_lock, flags);
+
+ /* do nothing if list empty */
+ if (!list_empty(&sem->wait_list))
+ sem = __rwsem_do_wake(sem, 0);
+
+- spin_unlock(&sem->wait_lock);
++ spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+ rwsemtrace(sem, "Leaving rwsem_wake");
+
+@@ -241,15 +243,17 @@ struct rw_semaphore fastcall *rwsem_wake
+ */
+ struct rw_semaphore fastcall *rwsem_downgrade_wake(struct rw_semaphore *sem)
+ {
++ unsigned long flags;
++
+ rwsemtrace(sem, "Entering rwsem_downgrade_wake");
+
+- spin_lock(&sem->wait_lock);
++ spin_lock_irqsave(&sem->wait_lock, flags);
+
+ /* do nothing if list empty */
+ if (!list_empty(&sem->wait_list))
+ sem = __rwsem_do_wake(sem, 1);
+
+- spin_unlock(&sem->wait_lock);
++ spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+ rwsemtrace(sem, "Leaving rwsem_downgrade_wake");
+ return sem;
+diff --git a/mm/mmap.c b/mm/mmap.c
+--- a/mm/mmap.c
++++ b/mm/mmap.c
+@@ -1315,37 +1315,40 @@ unsigned long
+ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
+ unsigned long pgoff, unsigned long flags)
+ {
+- if (flags & MAP_FIXED) {
+- unsigned long ret;
++ unsigned long ret;
+
+- if (addr > TASK_SIZE - len)
+- return -ENOMEM;
+- if (addr & ~PAGE_MASK)
+- return -EINVAL;
+- if (file && is_file_hugepages(file)) {
+- /*
+- * Check if the given range is hugepage aligned, and
+- * can be made suitable for hugepages.
+- */
+- ret = prepare_hugepage_range(addr, len);
+- } else {
+- /*
+- * Ensure that a normal request is not falling in a
+- * reserved hugepage range. For some archs like IA-64,
+- * there is a separate region for hugepages.
+- */
+- ret = is_hugepage_only_range(addr, len);
+- }
+- if (ret)
+- return -EINVAL;
+- return addr;
+- }
++ if (!(flags & MAP_FIXED)) {
++ unsigned long (*get_area)(struct file *, unsigned long,
unsigned long, unsigned long, unsigned long);
+
+- if (file && file->f_op && file->f_op->get_unmapped_area)
+- return file->f_op->get_unmapped_area(file, addr, len,
+- pgoff, flags);
++ get_area = current->mm->get_unmapped_area;
++ if (file && file->f_op && file->f_op->get_unmapped_area)
++ get_area = file->f_op->get_unmapped_area;
++ addr = get_area(file, addr, len, pgoff, flags);
++ if (IS_ERR_VALUE(addr))
++ return addr;
++ }
+
+- return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
++ if (addr > TASK_SIZE - len)
++ return -ENOMEM;
++ if (addr & ~PAGE_MASK)
++ return -EINVAL;
++ if (file && is_file_hugepages(file)) {
++ /*
++ * Check if the given range is hugepage aligned, and
++ * can be made suitable for hugepages.
++ */
++ ret = prepare_hugepage_range(addr, len);
++ } else {
++ /*
++ * Ensure that a normal request is not falling in a
++ * reserved hugepage range. For some archs like IA-64,
++ * there is a separate region for hugepages.
++ */
++ ret = is_hugepage_only_range(addr, len);
++ }
++ if (ret)
++ return -EINVAL;
++ return addr;
+ }
+
+ EXPORT_SYMBOL(get_unmapped_area);
+diff --git a/mm/rmap.c b/mm/rmap.c
+--- a/mm/rmap.c
++++ b/mm/rmap.c
+@@ -641,7 +641,7 @@ static void try_to_unmap_cluster(unsigne
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+- pte_t *pte;
++ pte_t *pte, *original_pte;
+ pte_t pteval;
+ struct page *page;
+ unsigned long address;
+@@ -673,7 +673,7 @@ static void try_to_unmap_cluster(unsigne
+ if (!pmd_present(*pmd))
+ goto out_unlock;
+
+- for (pte = pte_offset_map(pmd, address);
++ for (original_pte = pte = pte_offset_map(pmd, address);
+ address < end; pte++, address += PAGE_SIZE) {
+
+ if (!pte_present(*pte))
+@@ -710,7 +710,7 @@ static void try_to_unmap_cluster(unsigne
+ (*mapcount)--;
+ }
+
+- pte_unmap(pte);
++ pte_unmap(original_pte);
+
+ out_unlock:
+ spin_unlock(&mm->page_table_lock);
+diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
+--- a/net/bluetooth/af_bluetooth.c
++++ b/net/bluetooth/af_bluetooth.c
+@@ -64,7 +64,7 @@ static kmem_cache_t *bt_sock_cache;
+
+ int bt_sock_register(int proto, struct net_proto_family *ops)
+ {
+- if (proto >= BT_MAX_PROTO)
++ if (proto < 0 || proto >= BT_MAX_PROTO)
+ return -EINVAL;
+
+ if (bt_proto[proto])
+@@ -77,7 +77,7 @@ EXPORT_SYMBOL(bt_sock_register);
+
+ int bt_sock_unregister(int proto)
+ {
+- if (proto >= BT_MAX_PROTO)
++ if (proto < 0 || proto >= BT_MAX_PROTO)
+ return -EINVAL;
+
+ if (!bt_proto[proto])
+@@ -92,7 +92,7 @@ static int bt_sock_create(struct socket
+ {
+ int err = 0;
+
+- if (proto >= BT_MAX_PROTO)
++ if (proto < 0 || proto >= BT_MAX_PROTO)
+ return -EINVAL;
+
+ #if defined(CONFIG_KMOD)
+diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
+--- a/net/bridge/br_input.c
++++ b/net/bridge/br_input.c
+@@ -54,6 +54,9 @@ int br_handle_frame_finish(struct sk_buf
+ struct net_bridge_fdb_entry *dst;
+ int passedup = 0;
+
++ /* insert into forwarding database after filtering to avoid spoofing */
++ br_fdb_insert(p->br, p, eth_hdr(skb)->h_source, 0);
++
+ if (br->dev->flags & IFF_PROMISC) {
+ struct sk_buff *skb2;
+
+@@ -108,8 +111,7 @@ int br_handle_frame(struct net_bridge_po
+ if (eth_hdr(skb)->h_source[0] & 1)
+ goto err;
+
+- if (p->state == BR_STATE_LEARNING ||
+- p->state == BR_STATE_FORWARDING)
++ if (p->state == BR_STATE_LEARNING)
+ br_fdb_insert(p->br, p, eth_hdr(skb)->h_source, 0);
+
+ if (p->br->stp_enabled &&
+diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c
+--- a/net/bridge/br_stp_bpdu.c
++++ b/net/bridge/br_stp_bpdu.c
+@@ -140,6 +140,9 @@ int br_stp_handle_bpdu(struct sk_buff *s
+ struct net_bridge *br = p->br;
+ unsigned char *buf;
+
++ /* insert into forwarding database after filtering to avoid spoofing */
++ br_fdb_insert(p->br, p, eth_hdr(skb)->h_source, 0);
++
+ /* need at least the 802 and STP headers */
+ if (!pskb_may_pull(skb, sizeof(header)+1) ||
+ memcmp(skb->data, header, sizeof(header)))
+diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
+--- a/net/bridge/netfilter/ebtables.c
++++ b/net/bridge/netfilter/ebtables.c
+@@ -179,9 +179,10 @@ unsigned int ebt_do_table (unsigned int
+ struct ebt_chainstack *cs;
+ struct ebt_entries *chaininfo;
+ char *base;
+- struct ebt_table_info *private = table->private;
++ struct ebt_table_info *private;
+
+ read_lock_bh(&table->lock);
++ private = table->private;
+ cb_base = COUNTER_BASE(private->counters, private->nentries,
+ smp_processor_id());
+ if (private->chainstack)
+diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c
+--- a/net/ipv4/fib_hash.c
++++ b/net/ipv4/fib_hash.c
+@@ -919,13 +919,23 @@ out:
+ return fa;
+ }
+
++static struct fib_alias *fib_get_idx(struct seq_file *seq, loff_t pos)
++{
++ struct fib_alias *fa = fib_get_first(seq);
++
++ if (fa)
++ while (pos && (fa = fib_get_next(seq)))
++ --pos;
++ return pos ? NULL : fa;
++}
++
+ static void *fib_seq_start(struct seq_file *seq, loff_t *pos)
+ {
+ void *v = NULL;
+
+ read_lock(&fib_hash_lock);
+ if (ip_fib_main_table)
+- v = *pos ? fib_get_next(seq) : SEQ_START_TOKEN;
++ v = *pos ? fib_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
+ return v;
+ }
+
+diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
+--- a/net/ipv4/netfilter/ip_queue.c
++++ b/net/ipv4/netfilter/ip_queue.c
+@@ -3,6 +3,7 @@
+ * communicating with userspace via netlink.
+ *
+ * (C) 2000-2002 James Morris <jmorris@xxxxxxxxxxxxxxxx>
++ * (C) 2003-2005 Netfilter Core Team <coreteam@xxxxxxxxxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+@@ -14,6 +15,7 @@
+ * Zander).
+ * 2000-08-01: Added Nick Williams' MAC support.
+ * 2002-06-25: Code cleanup.
++ * 2005-05-26: local_bh_{disable,enable} around nf_reinject (Harald Welte)
+ *
+ */
+ #include <linux/module.h>
+@@ -66,7 +68,15 @@ static DECLARE_MUTEX(ipqnl_sem);
+ static void
+ ipq_issue_verdict(struct ipq_queue_entry *entry, int verdict)
+ {
++ /* TCP input path (and probably other bits) assume to be called
++ * from softirq context, not from syscall, like ipq_issue_verdict is
++ * called. TCP input path deadlocks with locks taken from timer
++ * softirq, e.g. We therefore emulate this by local_bh_disable() */
++
++ local_bh_disable();
+ nf_reinject(entry->skb, entry->info, verdict);
++ local_bh_enable();
++
+ kfree(entry);
+ }
+
+diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
+--- a/net/ipv4/tcp_input.c
++++ b/net/ipv4/tcp_input.c
+@@ -1653,7 +1653,10 @@ static void DBGUNDO(struct sock *sk, str
+ static void tcp_undo_cwr(struct tcp_sock *tp, int undo)
+ {
+ if (tp->prior_ssthresh) {
+- tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh<<1);
++ if (tcp_is_bic(tp))
++ tp->snd_cwnd = max(tp->snd_cwnd,
tp->bictcp.last_max_cwnd);
++ else
++ tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh<<1);
+
+ if (undo && tp->prior_ssthresh > tp->snd_ssthresh) {
+ tp->snd_ssthresh = tp->prior_ssthresh;
+diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
+--- a/net/ipv4/tcp_timer.c
++++ b/net/ipv4/tcp_timer.c
+@@ -38,6 +38,7 @@ static void tcp_keepalive_timer (unsigne
+
+ #ifdef TCP_DEBUG
+ const char tcp_timer_bug_msg[] = KERN_DEBUG "tcpbug: unknown timer value\n";
++EXPORT_SYMBOL(tcp_timer_bug_msg);
+ #endif
+
+ /*
+diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
+--- a/net/ipv4/xfrm4_output.c
++++ b/net/ipv4/xfrm4_output.c
+@@ -103,17 +103,17 @@ int xfrm4_output(struct sk_buff *skb)
+ goto error_nolock;
+ }
+
+- spin_lock_bh(&x->lock);
+- err = xfrm_state_check(x, skb);
+- if (err)
+- goto error;
+-
+ if (x->props.mode) {
+ err = xfrm4_tunnel_check_size(skb);
+ if (err)
+- goto error;
++ goto error_nolock;
+ }
+
++ spin_lock_bh(&x->lock);
++ err = xfrm_state_check(x, skb);
++ if (err)
++ goto error;
++
+ xfrm4_encap(skb);
+
+ err = x->type->output(skb);
+diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
+--- a/net/ipv6/xfrm6_output.c
++++ b/net/ipv6/xfrm6_output.c
+@@ -103,17 +103,17 @@ int xfrm6_output(struct sk_buff *skb)
+ goto error_nolock;
+ }
+
+- spin_lock_bh(&x->lock);
+- err = xfrm_state_check(x, skb);
+- if (err)
+- goto error;
+-
+ if (x->props.mode) {
+ err = xfrm6_tunnel_check_size(skb);
+ if (err)
+- goto error;
++ goto error_nolock;
+ }
+
++ spin_lock_bh(&x->lock);
++ err = xfrm_state_check(x, skb);
++ if (err)
++ goto error;
++
+ xfrm6_encap(skb);
+
+ err = x->type->output(skb);
+diff --git a/net/netrom/nr_in.c b/net/netrom/nr_in.c
+--- a/net/netrom/nr_in.c
++++ b/net/netrom/nr_in.c
+@@ -74,7 +74,6 @@ static int nr_queue_rx_frame(struct sock
+ static int nr_state1_machine(struct sock *sk, struct sk_buff *skb,
+ int frametype)
+ {
+- bh_lock_sock(sk);
+ switch (frametype) {
+ case NR_CONNACK: {
+ nr_cb *nr = nr_sk(sk);
+@@ -103,8 +102,6 @@ static int nr_state1_machine(struct sock
+ default:
+ break;
+ }
+- bh_unlock_sock(sk);
+-
+ return 0;
+ }
+
+@@ -116,7 +113,6 @@ static int nr_state1_machine(struct sock
+ static int nr_state2_machine(struct sock *sk, struct sk_buff *skb,
+ int frametype)
+ {
+- bh_lock_sock(sk);
+ switch (frametype) {
+ case NR_CONNACK | NR_CHOKE_FLAG:
+ nr_disconnect(sk, ECONNRESET);
+@@ -132,8 +128,6 @@ static int nr_state2_machine(struct sock
+ default:
+ break;
+ }
+- bh_unlock_sock(sk);
+-
+ return 0;
+ }
+
+@@ -154,7 +148,6 @@ static int nr_state3_machine(struct sock
+ nr = skb->data[18];
+ ns = skb->data[17];
+
+- bh_lock_sock(sk);
+ switch (frametype) {
+ case NR_CONNREQ:
+ nr_write_internal(sk, NR_CONNACK);
+@@ -265,8 +258,6 @@ static int nr_state3_machine(struct sock
+ default:
+ break;
+ }
+- bh_unlock_sock(sk);
+-
+ return queued;
+ }
+
+diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
+--- a/net/rose/rose_route.c
++++ b/net/rose/rose_route.c
+@@ -727,7 +727,8 @@ int rose_rt_ioctl(unsigned int cmd, void
+ }
+ if (rose_route.mask > 10) /* Mask can't be more than 10 digits
*/
+ return -EINVAL;
+-
++ if (rose_route.ndigis > 8) /* No more than 8 digipeats */
++ return -EINVAL;
+ err = rose_add_node(&rose_route, dev);
+ dev_put(dev);
+ return err;
+diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
+--- a/net/sched/sch_netem.c
++++ b/net/sched/sch_netem.c
+@@ -184,10 +184,15 @@ static int netem_enqueue(struct sk_buff
+ /* Random duplication */
+ if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor)) {
+ struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
+-
+- pr_debug("netem_enqueue: dup %p\n", skb2);
+- if (skb2)
+- delay_skb(sch, skb2);
++ if (skb2) {
++ struct Qdisc *rootq = sch->dev->qdisc;
++ u32 dupsave = q->duplicate;
++
++ /* prevent duplicating a dup... */
++ q->duplicate = 0;
++ rootq->enqueue(skb2, rootq);
++ q->duplicate = dupsave;
++ }
+ }
+
+ /* If doing simple delay then gap == 0 so all packets
+diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
+--- a/net/xfrm/xfrm_state.c
++++ b/net/xfrm/xfrm_state.c
+@@ -609,7 +609,7 @@ static struct xfrm_state *__xfrm_find_ac
+
+ for (i = 0; i < XFRM_DST_HSIZE; i++) {
+ list_for_each_entry(x, xfrm_state_bydst+i, bydst) {
+- if (x->km.seq == seq) {
++ if (x->km.seq == seq && x->km.state == XFRM_STATE_ACQ) {
+ xfrm_state_hold(x);
+ return x;
+ }
+diff --git a/security/keys/key.c b/security/keys/key.c
+--- a/security/keys/key.c
++++ b/security/keys/key.c
+@@ -57,9 +57,10 @@ struct key_user *key_user_lookup(uid_t u
+ {
+ struct key_user *candidate = NULL, *user;
+ struct rb_node *parent = NULL;
+- struct rb_node **p = &key_user_tree.rb_node;
++ struct rb_node **p;
+
+ try_again:
++ p = &key_user_tree.rb_node;
+ spin_lock(&key_user_lock);
+
+ /* search the tree for a user record with a matching UID */
+diff --git a/sound/core/timer.c b/sound/core/timer.c
+--- a/sound/core/timer.c
++++ b/sound/core/timer.c
+@@ -1117,7 +1117,8 @@ static void snd_timer_user_append_to_tqu
+ if (tu->qused >= tu->queue_size) {
+ tu->overrun++;
+ } else {
+- memcpy(&tu->queue[tu->qtail++], tread, sizeof(*tread));
++ memcpy(&tu->tqueue[tu->qtail++], tread, sizeof(*tread));
++ tu->qtail %= tu->queue_size;
+ tu->qused++;
+ }
+ }
+@@ -1140,6 +1141,8 @@ static void snd_timer_user_ccallback(snd
+ spin_lock(&tu->qlock);
+ snd_timer_user_append_to_tqueue(tu, &r1);
+ spin_unlock(&tu->qlock);
++ kill_fasync(&tu->fasync, SIGIO, POLL_IN);
++ wake_up(&tu->qchange_sleep);
+ }
+
+ static void snd_timer_user_tinterrupt(snd_timer_instance_t *timeri,
+diff --git a/sound/pci/ac97/ac97_codec.c b/sound/pci/ac97/ac97_codec.c
+--- a/sound/pci/ac97/ac97_codec.c
++++ b/sound/pci/ac97/ac97_codec.c
+@@ -1185,7 +1185,7 @@ snd_kcontrol_t *snd_ac97_cnew(const snd_
+ /*
+ * create mute switch(es) for normal stereo controls
+ */
+-static int snd_ac97_cmute_new(snd_card_t *card, char *name, int reg, ac97_t
*ac97)
++static int snd_ac97_cmute_new_stereo(snd_card_t *card, char *name, int reg,
int check_stereo, ac97_t *ac97)
+ {
+ snd_kcontrol_t *kctl;
+ int err;
+@@ -1196,7 +1196,7 @@ static int snd_ac97_cmute_new(snd_card_t
+
+ mute_mask = 0x8000;
+ val = snd_ac97_read(ac97, reg);
+- if (ac97->flags & AC97_STEREO_MUTES) {
++ if (check_stereo || (ac97->flags & AC97_STEREO_MUTES)) {
+ /* check whether both mute bits work */
+ val1 = val | 0x8080;
+ snd_ac97_write(ac97, reg, val1);
+@@ -1254,7 +1254,7 @@ static int snd_ac97_cvol_new(snd_card_t
+ /*
+ * create a mute-switch and a volume for normal stereo/mono controls
+ */
+-static int snd_ac97_cmix_new(snd_card_t *card, const char *pfx, int reg,
ac97_t *ac97)
++static int snd_ac97_cmix_new_stereo(snd_card_t *card, const char *pfx, int
reg, int check_stereo, ac97_t *ac97)
+ {
+ int err;
+ char name[44];
+@@ -1265,7 +1265,7 @@ static int snd_ac97_cmix_new(snd_card_t
+
+ if (snd_ac97_try_bit(ac97, reg, 15)) {
+ sprintf(name, "%s Switch", pfx);
+- if ((err = snd_ac97_cmute_new(card, name, reg, ac97)) < 0)
++ if ((err = snd_ac97_cmute_new_stereo(card, name, reg,
check_stereo, ac97)) < 0)
+ return err;
+ }
+ check_volume_resolution(ac97, reg, &lo_max, &hi_max);
+@@ -1277,6 +1277,8 @@ static int snd_ac97_cmix_new(snd_card_t
+ return 0;
+ }
+
++#define snd_ac97_cmix_new(card, pfx, reg, ac97)
snd_ac97_cmix_new_stereo(card, pfx, reg, 0, ac97)
++#define snd_ac97_cmute_new(card, name, reg, ac97)
snd_ac97_cmute_new_stereo(card, name, reg, 0, ac97)
+
+ static unsigned int snd_ac97_determine_spdif_rates(ac97_t *ac97);
+
+@@ -1327,7 +1329,8 @@ static int snd_ac97_mixer_build(ac97_t *
+
+ /* build surround controls */
+ if (snd_ac97_try_volume_mix(ac97, AC97_SURROUND_MASTER)) {
+- if ((err = snd_ac97_cmix_new(card, "Surround Playback",
AC97_SURROUND_MASTER, ac97)) < 0)
++ /* Surround Master (0x38) is with stereo mutes */
++ if ((err = snd_ac97_cmix_new_stereo(card, "Surround Playback",
AC97_SURROUND_MASTER, 1, ac97)) < 0)
+ return err;
+ }
+
+diff --git a/sound/usb/usbaudio.c b/sound/usb/usbaudio.c
+--- a/sound/usb/usbaudio.c
++++ b/sound/usb/usbaudio.c
+@@ -3276,7 +3276,7 @@ static void snd_usb_audio_disconnect(str
+ }
+ usb_chip[chip->index] = NULL;
+ up(®ister_mutex);
+- snd_card_free_in_thread(card);
++ snd_card_free(card);
+ } else {
+ up(®ister_mutex);
+ }
+diff --git a/sound/usb/usx2y/usbusx2y.c b/sound/usb/usx2y/usbusx2y.c
+--- a/sound/usb/usx2y/usbusx2y.c
++++ b/sound/usb/usx2y/usbusx2y.c
+@@ -1,6 +1,11 @@
+ /*
+ * usbusy2y.c - ALSA USB US-428 Driver
+ *
++2005-04-14 Karsten Wiese
++ Version 0.8.7.2:
++ Call snd_card_free() instead of snd_card_free_in_thread() to prevent
oops with dead keyboard symptom.
++ Tested ok with kernel 2.6.12-rc2.
++
+ 2004-12-14 Karsten Wiese
+ Version 0.8.7.1:
+ snd_pcm_open for rawusb pcm-devices now returns -EBUSY if called
without rawusb's hwdep device being open.
+@@ -143,7 +148,7 @@
+
+
+ MODULE_AUTHOR("Karsten Wiese <annabellesgarden@xxxxxxxx>");
+-MODULE_DESCRIPTION("TASCAM "NAME_ALLCAPS" Version 0.8.7.1");
++MODULE_DESCRIPTION("TASCAM "NAME_ALLCAPS" Version 0.8.7.2");
+ MODULE_LICENSE("GPL");
+ MODULE_SUPPORTED_DEVICE("{{TASCAM(0x1604),
"NAME_ALLCAPS"(0x8001)(0x8005)(0x8007) }}");
+
+@@ -430,8 +435,6 @@ static void usX2Y_usb_disconnect(struct
+ if (ptr) {
+ usX2Ydev_t* usX2Y = usX2Y((snd_card_t*)ptr);
+ struct list_head* p;
+- if (usX2Y->chip_status == USX2Y_STAT_CHIP_HUP) // on 2.6.1
kernel snd_usbmidi_disconnect()
+- return; // calls us
back. better leave :-) .
+ usX2Y->chip.shutdown = 1;
+ usX2Y->chip_status = USX2Y_STAT_CHIP_HUP;
+ usX2Y_unlinkSeq(&usX2Y->AS04);
+@@ -443,7 +446,7 @@ static void usX2Y_usb_disconnect(struct
+ }
+ if (usX2Y->us428ctls_sharedmem)
+ wake_up(&usX2Y->us428ctls_wait_queue_head);
+- snd_card_free_in_thread((snd_card_t*)ptr);
++ snd_card_free((snd_card_t*)ptr);
+ }
+ }
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/io.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/io.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,365 @@
+#ifndef _ASM_IO_H
+#define _ASM_IO_H
+
+#include <linux/config.h>
+#include <asm/fixmap.h>
+/*
+ * This file contains the definitions for the x86 IO instructions
+ * inb/inw/inl/outb/outw/outl and the "string versions" of the same
+ * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
+ * versions of the single-IO instructions (inb_p/inw_p/..).
+ *
+ * This file is not meant to be obfuscating: it's just complicated
+ * to (a) handle it all in a way that makes gcc able to optimize it
+ * as well as possible and (b) trying to avoid writing the same thing
+ * over and over again with slight variations and possibly making a
+ * mistake somewhere.
+ */
+
+/*
+ * Thanks to James van Artsdalen for a better timing-fix than
+ * the two short jumps: using outb's to a nonexistent port seems
+ * to guarantee better timings even on fast machines.
+ *
+ * On the other hand, I'd like to be sure of a non-existent port:
+ * I feel a bit unsafe about using 0x80 (should be safe, though)
+ *
+ * Linus
+ */
+
+ /*
+ * Bit simplified and optimized by Jan Hubicka
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
+ *
+ * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
+ * isa_read[wl] and isa_write[wl] fixed
+ * - Arnaldo Carvalho de Melo <acme@xxxxxxxxxxxxxxxx>
+ */
+
+#ifdef SLOW_IO_BY_JUMPING
+#define __SLOW_DOWN_IO "\njmp 1f\n1:\tjmp 1f\n1:"
+#else
+#define __SLOW_DOWN_IO "\noutb %%al,$0x80"
+#endif
+
+#ifdef REALLY_SLOW_IO
+#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO
__SLOW_DOWN_IO
+#else
+#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO
+#endif
+
+/*
+ * Talk about misusing macros..
+ */
+#define __OUT1(s,x) \
+extern inline void out##s(unsigned x value, unsigned short port) {
+
+#define __OUT2(s,s1,s2) \
+__asm__ __volatile__ ("out" #s " %" s1 "0,%" s2 "1"
+
+#define __OUT(s,s1,x) \
+__OUT1(s,x) __OUT2(s,s1,"w") : : "a" (value), "Nd" (port)); } \
+__OUT1(s##_p,x) __OUT2(s,s1,"w") __FULL_SLOW_DOWN_IO : : "a" (value), "Nd"
(port));} \
+
+#define __IN1(s) \
+extern inline RETURN_TYPE in##s(unsigned short port) { RETURN_TYPE _v;
+
+#define __IN2(s,s1,s2) \
+__asm__ __volatile__ ("in" #s " %" s2 "1,%" s1 "0"
+
+#define __IN(s,s1,i...) \
+__IN1(s) __IN2(s,s1,"w") : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \
+__IN1(s##_p) __IN2(s,s1,"w") __FULL_SLOW_DOWN_IO : "=a" (_v) : "Nd" (port)
,##i ); return _v; } \
+
+#define __INS(s) \
+extern inline void ins##s(unsigned short port, void * addr, unsigned long
count) \
+{ __asm__ __volatile__ ("rep ; ins" #s \
+: "=D" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); }
+
+#define __OUTS(s) \
+extern inline void outs##s(unsigned short port, const void * addr, unsigned
long count) \
+{ __asm__ __volatile__ ("rep ; outs" #s \
+: "=S" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); }
+
+#define RETURN_TYPE unsigned char
+__IN(b,"")
+#undef RETURN_TYPE
+#define RETURN_TYPE unsigned short
+__IN(w,"")
+#undef RETURN_TYPE
+#define RETURN_TYPE unsigned int
+__IN(l,"")
+#undef RETURN_TYPE
+
+__OUT(b,"b",char)
+__OUT(w,"w",short)
+__OUT(l,,int)
+
+__INS(b)
+__INS(w)
+__INS(l)
+
+__OUTS(b)
+__OUTS(w)
+__OUTS(l)
+
+#define IO_SPACE_LIMIT 0xffff
+
+#if defined(__KERNEL__) && __x86_64__
+
+#include <linux/vmalloc.h>
+
+#ifndef __i386__
+/*
+ * Change virtual addresses to physical addresses and vv.
+ * These are pretty trivial
+ */
+extern inline unsigned long virt_to_phys(volatile void * address)
+{
+ return __pa(address);
+}
+
+extern inline void * phys_to_virt(unsigned long address)
+{
+ return __va(address);
+}
+
+
+#define virt_to_bus(_x) phys_to_machine(__pa(_x))
+#define bus_to_virt(_x) __va(machine_to_phys(_x))
+#endif
+
+/*
+ * Change "struct page" to physical address.
+ */
+#ifdef CONFIG_DISCONTIGMEM
+#include <asm/mmzone.h>
+#define page_to_pseudophys(page) ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
+#define page_to_phys(page) (phys_to_machine(page_to_pseudophys(page)))
+
+#define bio_to_pseudophys(bio) (page_to_pseudophys(bio_page((bio))) + \
+ (unsigned long) bio_offset((bio)))
+#define bvec_to_pseudophys(bv) (page_to_pseudophys((bv)->bv_page) + \
+ (unsigned long) (bv)->bv_offset)
+
+#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \
+ (((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) && \
+ ((bvec_to_pseudophys((vec1)) + (vec1)->bv_len) == \
+ bvec_to_pseudophys((vec2))))
+#else
+// #define page_to_phys(page) ((page - mem_map) << PAGE_SHIFT)
+#define page_to_pseudophys(page) ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
+#define page_to_phys(page) (phys_to_machine(page_to_pseudophys(page)))
+
+#define bio_to_pseudophys(bio) (page_to_pseudophys(bio_page((bio))) + \
+ (unsigned long) bio_offset((bio)))
+#define bvec_to_pseudophys(bv) (page_to_pseudophys((bv)->bv_page) + \
+ (unsigned long) (bv)->bv_offset)
+
+#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \
+ (((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) && \
+ ((bvec_to_pseudophys((vec1)) + (vec1)->bv_len) == \
+ bvec_to_pseudophys((vec2))))
+#endif
+
+#include <asm-generic/iomap.h>
+
+extern void __iomem *__ioremap(unsigned long offset, unsigned long size,
unsigned long flags);
+
+extern inline void __iomem * ioremap (unsigned long offset, unsigned long size)
+{
+ return __ioremap(offset, size, 0);
+}
+
+/*
+ * This one maps high address device memory and turns off caching for that
area.
+ * it's useful if some control registers are in such an area and write
combining
+ * or read caching is not desirable:
+ */
+extern void __iomem * ioremap_nocache (unsigned long offset, unsigned long
size);
+extern void iounmap(volatile void __iomem *addr);
+
+/*
+ * ISA I/O bus memory addresses are 1:1 with the physical address.
+ */
+
+#define isa_virt_to_bus(_x) isa_virt_to_bus_is_UNSUPPORTED->x
+#define isa_page_to_bus(_x) isa_page_to_bus_is_UNSUPPORTED->x
+#ifdef CONFIG_XEN_PHYSDEV_ACCESS
+#define isa_bus_to_virt(_x) (void *)(__fix_to_virt(FIX_ISAMAP_BEGIN) + (_x))
+#else
+#define isa_bus_to_virt(_x) isa_bus_to_virt_needs_PRIVILEGED_BUILD
+#endif
+/*
+ * However PCI ones are not necessarily 1:1 and therefore these interfaces
+ * are forbidden in portable PCI drivers.
+ *
+ * Allow them on x86 for legacy drivers, though.
+ */
+#define virt_to_bus(_x) phys_to_machine(__pa(_x))
+#define bus_to_virt(_x) __va(machine_to_phys(_x))
+
+/*
+ * readX/writeX() are used to access memory mapped devices. On some
+ * architectures the memory mapped IO stuff needs to be accessed
+ * differently. On the x86 architecture, we just read/write the
+ * memory location directly.
+ */
+
+static inline __u8 __readb(const volatile void __iomem *addr)
+{
+ return *(__force volatile __u8 *)addr;
+}
+static inline __u16 __readw(const volatile void __iomem *addr)
+{
+ return *(__force volatile __u16 *)addr;
+}
+static inline __u32 __readl(const volatile void __iomem *addr)
+{
+ return *(__force volatile __u32 *)addr;
+}
+static inline __u64 __readq(const volatile void __iomem *addr)
+{
+ return *(__force volatile __u64 *)addr;
+}
+#define readb(x) __readb(x)
+#define readw(x) __readw(x)
+#define readl(x) __readl(x)
+#define readq(x) __readq(x)
+#define readb_relaxed(a) readb(a)
+#define readw_relaxed(a) readw(a)
+#define readl_relaxed(a) readl(a)
+#define readq_relaxed(a) readq(a)
+#define __raw_readb readb
+#define __raw_readw readw
+#define __raw_readl readl
+#define __raw_readq readq
+
+#define mmiowb()
+
+#ifdef CONFIG_UNORDERED_IO
+static inline void __writel(__u32 val, volatile void __iomem *addr)
+{
+ volatile __u32 __iomem *target = addr;
+ asm volatile("movnti %1,%0"
+ : "=m" (*target)
+ : "r" (val) : "memory");
+}
+
+static inline void __writeq(__u64 val, volatile void __iomem *addr)
+{
+ volatile __u64 __iomem *target = addr;
+ asm volatile("movnti %1,%0"
+ : "=m" (*target)
+ : "r" (val) : "memory");
+}
+#else
+static inline void __writel(__u32 b, volatile void __iomem *addr)
+{
+ *(__force volatile __u32 *)addr = b;
+}
+static inline void __writeq(__u64 b, volatile void __iomem *addr)
+{
+ *(__force volatile __u64 *)addr = b;
+}
+#endif
+static inline void __writeb(__u8 b, volatile void __iomem *addr)
+{
+ *(__force volatile __u8 *)addr = b;
+}
+static inline void __writew(__u16 b, volatile void __iomem *addr)
+{
+ *(__force volatile __u16 *)addr = b;
+}
+#define writeq(val,addr) __writeq((val),(addr))
+#define writel(val,addr) __writel((val),(addr))
+#define writew(val,addr) __writew((val),(addr))
+#define writeb(val,addr) __writeb((val),(addr))
+#define __raw_writeb writeb
+#define __raw_writew writew
+#define __raw_writel writel
+#define __raw_writeq writeq
+
+void __memcpy_fromio(void*,unsigned long,unsigned);
+void __memcpy_toio(unsigned long,const void*,unsigned);
+
+static inline void memcpy_fromio(void *to, const volatile void __iomem *from,
unsigned len)
+{
+ __memcpy_fromio(to,(unsigned long)from,len);
+}
+static inline void memcpy_toio(volatile void __iomem *to, const void *from,
unsigned len)
+{
+ __memcpy_toio((unsigned long)to,from,len);
+}
+
+void memset_io(volatile void __iomem *a, int b, size_t c);
+
+/*
+ * ISA space is 'always mapped' on a typical x86 system, no need to
+ * explicitly ioremap() it. The fact that the ISA IO space is mapped
+ * to PAGE_OFFSET is pure coincidence - it does not mean ISA values
+ * are physical addresses. The following constant pointer can be
+ * used as the IO-area pointer (it can be iounmapped as well, so the
+ * analogy with PCI is quite large):
+ */
+#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
+
+#define isa_readb(a) readb(__ISA_IO_base + (a))
+#define isa_readw(a) readw(__ISA_IO_base + (a))
+#define isa_readl(a) readl(__ISA_IO_base + (a))
+#define isa_writeb(b,a) writeb(b,__ISA_IO_base + (a))
+#define isa_writew(w,a) writew(w,__ISA_IO_base + (a))
+#define isa_writel(l,a) writel(l,__ISA_IO_base + (a))
+#define isa_memset_io(a,b,c) memset_io(__ISA_IO_base + (a),(b),(c))
+#define isa_memcpy_fromio(a,b,c) memcpy_fromio((a),__ISA_IO_base +
(b),(c))
+#define isa_memcpy_toio(a,b,c) memcpy_toio(__ISA_IO_base + (a),(b),(c))
+
+
+/*
+ * Again, x86-64 does not require mem IO specific function.
+ */
+
+#define eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void
*)(b),(c),(d))
+#define isa_eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void
*)(__ISA_IO_base + (b)),(c),(d))
+
+/**
+ * check_signature - find BIOS signatures
+ * @io_addr: mmio address to check
+ * @signature: signature block
+ * @length: length of signature
+ *
+ * Perform a signature comparison with the mmio address io_addr. This
+ * address should have been obtained by ioremap.
+ * Returns 1 on a match.
+ */
+
+static inline int check_signature(void __iomem *io_addr,
+ const unsigned char *signature, int length)
+{
+ int retval = 0;
+ do {
+ if (readb(io_addr) != *signature)
+ goto out;
+ io_addr++;
+ signature++;
+ length--;
+ } while (length);
+ retval = 1;
+out:
+ return retval;
+}
+
+/* Nothing to do */
+
+#define dma_cache_inv(_start,_size) do { } while (0)
+#define dma_cache_wback(_start,_size) do { } while (0)
+#define dma_cache_wback_inv(_start,_size) do { } while (0)
+
+#define flush_write_buffers()
+
+extern int iommu_bio_merge;
+#define BIO_VMERGE_BOUNDARY iommu_bio_merge
+
+#endif /* __KERNEL__ */
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b linux-2.6.11-xen-sparse/include/linux/irq.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/linux/irq.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,98 @@
+#ifndef __irq_h
+#define __irq_h
+
+/*
+ * Please do not include this file in generic code. There is currently
+ * no requirement for any architecture to implement anything held
+ * within this file.
+ *
+ * Thanks. --rmk
+ */
+
+#include <linux/config.h>
+
+#if !defined(CONFIG_ARCH_S390)
+
+#include <linux/linkage.h>
+#include <linux/cache.h>
+#include <linux/spinlock.h>
+#include <linux/cpumask.h>
+
+#include <asm/irq.h>
+#include <asm/ptrace.h>
+
+/*
+ * IRQ line status.
+ */
+#define IRQ_INPROGRESS 1 /* IRQ handler active - do not enter! */
+#define IRQ_DISABLED 2 /* IRQ disabled - do not enter! */
+#define IRQ_PENDING 4 /* IRQ pending - replay on enable */
+#define IRQ_REPLAY 8 /* IRQ has been replayed but not acked yet */
+#define IRQ_AUTODETECT 16 /* IRQ is being autodetected */
+#define IRQ_WAITING 32 /* IRQ not yet seen - for autodetection */
+#define IRQ_LEVEL 64 /* IRQ level triggered */
+#define IRQ_MASKED 128 /* IRQ masked - shouldn't be seen again */
+#define IRQ_PER_CPU 256 /* IRQ is per CPU */
+
+/*
+ * Interrupt controller descriptor. This is all we need
+ * to describe about the low-level hardware.
+ */
+struct hw_interrupt_type {
+ const char * typename;
+ unsigned int (*startup)(unsigned int irq);
+ void (*shutdown)(unsigned int irq);
+ void (*enable)(unsigned int irq);
+ void (*disable)(unsigned int irq);
+ void (*ack)(unsigned int irq);
+ void (*end)(unsigned int irq);
+ void (*set_affinity)(unsigned int irq, cpumask_t dest);
+};
+
+typedef struct hw_interrupt_type hw_irq_controller;
+
+/*
+ * This is the "IRQ descriptor", which contains various information
+ * about the irq, including what kind of hardware handling it has,
+ * whether it is disabled etc etc.
+ *
+ * Pad this out to 32 bytes for cache and indexing reasons.
+ */
+typedef struct irq_desc {
+ hw_irq_controller *handler;
+ void *handler_data;
+ struct irqaction *action; /* IRQ action list */
+ unsigned int status; /* IRQ status */
+ unsigned int depth; /* nested irq disables */
+ unsigned int irq_count; /* For detecting broken interrupts */
+ unsigned int irqs_unhandled;
+ spinlock_t lock;
+} ____cacheline_aligned irq_desc_t;
+
+extern irq_desc_t irq_desc [NR_IRQS];
+
+#include <asm/hw_irq.h> /* the arch dependent stuff */
+
+extern int setup_irq(unsigned int irq, struct irqaction * new);
+extern int teardown_irq(unsigned int irq, struct irqaction * old);
+
+#ifdef CONFIG_GENERIC_HARDIRQS
+extern cpumask_t irq_affinity[NR_IRQS];
+extern int no_irq_affinity;
+extern int noirqdebug_setup(char *str);
+
+extern fastcall int handle_IRQ_event(unsigned int irq, struct pt_regs *regs,
+ struct irqaction *action);
+extern fastcall unsigned int __do_IRQ(unsigned int irq, struct pt_regs *regs);
+extern void note_interrupt(unsigned int irq, irq_desc_t *desc, int action_ret);
+extern void report_bad_irq(unsigned int irq, irq_desc_t *desc, int action_ret);
+extern int can_request_irq(unsigned int irq, unsigned long irqflags);
+
+extern void init_irq_proc(void);
+#endif
+
+extern hw_irq_controller no_irq_type; /* needed in every arch ? */
+
+#endif
+
+#endif /* __irq_h */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,96 @@
+#
+# Makefile for the linux kernel.
+#
+
+XENARCH := $(subst ",,$(CONFIG_XENARCH))
+
+CFLAGS += -Iarch/$(XENARCH)/kernel
+
+extra-y := head.o init_task.o
+
+obj-y := process.o signal.o entry.o traps.o \
+ time.o ioport.o ldt.o setup.o \
+ pci-dma.o i386_ksyms.o irq.o
+
+c-obj-y := semaphore.o vm86.o \
+ ptrace.o sys_i386.o \
+ i387.o dmi_scan.o bootflag.o \
+ doublefault.o quirks.o
+s-obj-y :=
+
+obj-y += cpu/
+obj-y += timers/
+obj-$(CONFIG_ACPI_BOOT) += acpi/
+#c-obj-$(CONFIG_X86_BIOS_REBOOT) += reboot.o
+c-obj-$(CONFIG_MCA) += mca.o
+c-obj-$(CONFIG_X86_MSR) += msr.o
+c-obj-$(CONFIG_X86_CPUID) += cpuid.o
+obj-$(CONFIG_MICROCODE) += microcode.o
+c-obj-$(CONFIG_APM) += apm.o
+obj-$(CONFIG_X86_SMP) += smp.o smpboot.o
+#obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o
+obj-$(CONFIG_X86_MPPARSE) += mpparse.o
+obj-$(CONFIG_X86_LOCAL_APIC) += apic.o
+c-obj-$(CONFIG_X86_LOCAL_APIC) += nmi.o
+obj-$(CONFIG_X86_IO_APIC) += io_apic.o
+c-obj-$(CONFIG_X86_NUMAQ) += numaq.o
+c-obj-$(CONFIG_X86_SUMMIT_NUMA) += summit.o
+c-obj-$(CONFIG_MODULES) += module.o
+c-obj-y += sysenter.o
+obj-y += vsyscall.o
+c-obj-$(CONFIG_ACPI_SRAT) += srat.o
+c-obj-$(CONFIG_HPET_TIMER) += time_hpet.o
+c-obj-$(CONFIG_EFI) += efi.o efi_stub.o
+c-obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
+c-obj-$(CONFIG_SMP_ALTERNATIVES)+= smpalts.o
+
+EXTRA_AFLAGS := -traditional
+
+c-obj-$(CONFIG_SCx200) += scx200.o
+
+# vsyscall.o contains the vsyscall DSO images as __initdata.
+# We must build both images before we can assemble it.
+# Note: kbuild does not track this dependency due to usage of .incbin
+$(obj)/vsyscall.o: $(obj)/vsyscall-int80.so $(obj)/vsyscall-sysenter.so
+targets += $(foreach F,int80 sysenter,vsyscall-$F.o vsyscall-$F.so)
+targets += vsyscall.lds
+
+# The DSO images are built using a special linker script.
+quiet_cmd_syscall = SYSCALL $@
+ cmd_syscall = $(CC) -nostdlib -m32 $(SYSCFLAGS_$(@F)) \
+ -Wl,-T,$(filter-out FORCE,$^) -o $@
+
+export CPPFLAGS_vsyscall.lds += -P -C -U$(ARCH)
+
+vsyscall-flags = -shared -s -Wl,-soname=linux-gate.so.1
+SYSCFLAGS_vsyscall-sysenter.so = $(vsyscall-flags)
+SYSCFLAGS_vsyscall-int80.so = $(vsyscall-flags)
+
+$(obj)/vsyscall-int80.so $(obj)/vsyscall-sysenter.so: \
+$(obj)/vsyscall-%.so: $(src)/vsyscall.lds $(obj)/vsyscall-%.o FORCE
+ $(call if_changed,syscall)
+
+# We also create a special relocatable object that should mirror the symbol
+# table and layout of the linked DSO. With ld -R we can then refer to
+# these symbols in the kernel code rather than hand-coded addresses.
+extra-y += vsyscall-syms.o
+$(obj)/built-in.o: $(obj)/vsyscall-syms.o
+$(obj)/built-in.o: ld_flags += -R $(obj)/vsyscall-syms.o
+
+SYSCFLAGS_vsyscall-syms.o = -r
+$(obj)/vsyscall-syms.o: $(src)/vsyscall.lds $(obj)/vsyscall-sysenter.o FORCE
+ $(call if_changed,syscall)
+
+c-link := init_task.o
+s-link := vsyscall-int80.o vsyscall-sysenter.o vsyscall-sigreturn.o
vsyscall.lds.o
+
+$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-obj-m) $(c-link)) $(patsubst
%.o,$(obj)/%.S,$(s-obj-y) $(s-link)):
+ @ln -fsn $(srctree)/arch/i386/kernel/$(notdir $@) $@
+
+$(obj)/vsyscall-int80.S: $(obj)/vsyscall-sigreturn.S
+
+obj-y += $(c-obj-y) $(s-obj-y)
+obj-m += $(c-obj-m)
+
+clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-m) $(c-obj-) $(c-link))
+clean-files += $(patsubst %.o,%.S,$(s-obj-y) $(s-obj-) $(s-link))
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/usbback/control.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/usbback/control.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,61 @@
+/******************************************************************************
+ * arch/xen/drivers/usbif/backend/control.c
+ *
+ * Routines for interfacing with the control plane.
+ *
+ * Copyright (c) 2004, Keir Fraser
+ */
+
+#include "common.h"
+
+static void usbif_ctrlif_rx(ctrl_msg_t *msg, unsigned long id)
+{
+ DPRINTK("Received usbif backend message, subtype=%d\n", msg->subtype);
+
+ switch ( msg->subtype )
+ {
+ case CMSG_USBIF_BE_CREATE:
+ usbif_create((usbif_be_create_t *)&msg->msg[0]);
+ break;
+ case CMSG_USBIF_BE_DESTROY:
+ usbif_destroy((usbif_be_destroy_t *)&msg->msg[0]);
+ break;
+ case CMSG_USBIF_BE_CONNECT:
+ usbif_connect((usbif_be_connect_t *)&msg->msg[0]);
+ break;
+ case CMSG_USBIF_BE_DISCONNECT:
+ if ( !usbif_disconnect((usbif_be_disconnect_t *)&msg->msg[0],msg->id) )
+ return; /* Sending the response is deferred until later. */
+ break;
+ case CMSG_USBIF_BE_CLAIM_PORT:
+ usbif_claim_port((usbif_be_claim_port_t *)&msg->msg[0]);
+ break;
+ case CMSG_USBIF_BE_RELEASE_PORT:
+ usbif_release_port((usbif_be_release_port_t *)&msg->msg[0]);
+ break;
+ default:
+ DPRINTK("Parse error while reading message subtype %d, len %d\n",
+ msg->subtype, msg->length);
+ msg->length = 0;
+ break;
+ }
+
+ ctrl_if_send_response(msg);
+}
+
+void usbif_ctrlif_init(void)
+{
+ ctrl_msg_t cmsg;
+ usbif_be_driver_status_changed_t st;
+
+ (void)ctrl_if_register_receiver(CMSG_USBIF_BE, usbif_ctrlif_rx,
+ CALLBACK_IN_BLOCKING_CONTEXT);
+
+ /* Send a driver-UP notification to the domain controller. */
+ cmsg.type = CMSG_USBIF_BE;
+ cmsg.subtype = CMSG_USBIF_BE_DRIVER_STATUS_CHANGED;
+ cmsg.length = sizeof(usbif_be_driver_status_changed_t);
+ st.status = USBIF_DRIVER_STATUS_UP;
+ memcpy(cmsg.msg, &st, sizeof(st));
+ ctrl_if_send_message_block(&cmsg, NULL, 0, TASK_UNINTERRUPTIBLE);
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/kernel/process.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/kernel/process.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,448 @@
+/*
+ * linux/arch/i386/kernel/process.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000
+ */
+
+/*
+ * This file handles the architecture-dependent parts of process handling..
+ */
+
+#define __KERNEL_SYSCALLS__
+#include <stdarg.h>
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/user.h>
+#include <linux/a.out.h>
+#include <linux/interrupt.h>
+#include <linux/config.h>
+#include <linux/delay.h>
+#include <linux/reboot.h>
+#include <linux/init.h>
+#include <linux/mc146818rtc.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/ldt.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/desc.h>
+#include <asm/mmu_context.h>
+#include <asm-xen/xen-public/physdev.h>
+
+#include <linux/irq.h>
+
+asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
+
+int hlt_counter;
+
+/*
+ * Powermanagement idle function, if any..
+ */
+void (*pm_idle)(void);
+
+/*
+ * Power off function, if any
+ */
+void (*pm_power_off)(void);
+
+void disable_hlt(void)
+{
+ hlt_counter++;
+}
+
+void enable_hlt(void)
+{
+ hlt_counter--;
+}
+
+/*
+ * The idle thread. There's no useful work to be
+ * done, so just try to conserve power and have a
+ * low exit latency (ie sit in a loop waiting for
+ * somebody to say that they'd like to reschedule)
+ */
+void cpu_idle (void)
+{
+ extern int set_timeout_timer(void);
+
+ /* Endless idle loop with no priority at all. */
+ init_idle();
+ current->nice = 20;
+ current->counter = -100;
+
+ for ( ; ; )
+ {
+ while ( !current->need_resched )
+ {
+ __cli();
+ if ( current->need_resched )
+ {
+ /* The race-free check for events failed. */
+ __sti();
+ break;
+ }
+ else if ( set_timeout_timer() == 0 )
+ {
+ /* NB. Blocking reenable events in a race-free manner. */
+ HYPERVISOR_block();
+ }
+ else
+ {
+ /* No race here: yielding will get us the CPU again anyway. */
+ __sti();
+ HYPERVISOR_yield();
+ }
+ }
+ schedule();
+ check_pgt_cache();
+ }
+}
+
+extern void show_trace(unsigned long* esp);
+
+void show_regs(struct pt_regs * regs)
+{
+ printk("\n");
+ printk("Pid: %d, comm: %20s\n", current->pid, current->comm);
+ printk("EIP: %04x:[<%08lx>] CPU: %d",0xffff & regs->xcs,regs->eip,
smp_processor_id());
+ if (regs->xcs & 2)
+ printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp);
+ printk(" EFLAGS: %08lx %s\n",regs->eflags, print_tainted());
+ printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
+ regs->eax,regs->ebx,regs->ecx,regs->edx);
+ printk("ESI: %08lx EDI: %08lx EBP: %08lx",
+ regs->esi, regs->edi, regs->ebp);
+ printk(" DS: %04x ES: %04x\n",
+ 0xffff & regs->xds,0xffff & regs->xes);
+
+ show_trace(®s->esp);
+}
+
+
+/*
+ * Create a kernel thread
+ */
+int arch_kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
+{
+ long retval, d0;
+
+ __asm__ __volatile__(
+ "movl %%esp,%%esi\n\t"
+ "int $0x80\n\t" /* Linux/i386 system call */
+ "cmpl %%esp,%%esi\n\t" /* child or parent? */
+ "je 1f\n\t" /* parent - jump */
+ /* Load the argument into eax, and push it. That way, it does
+ * not matter whether the called function is compiled with
+ * -mregparm or not. */
+ "movl %4,%%eax\n\t"
+ "pushl %%eax\n\t"
+ "call *%5\n\t" /* call fn */
+ "movl %3,%0\n\t" /* exit */
+ "int $0x80\n"
+ "1:\t"
+ :"=&a" (retval), "=&S" (d0)
+ :"0" (__NR_clone), "i" (__NR_exit),
+ "r" (arg), "r" (fn),
+ "b" (flags | CLONE_VM)
+ : "memory");
+
+ return retval;
+}
+
+/*
+ * Free current thread data structures etc..
+ */
+void exit_thread(void)
+{
+ /* nothing to do ... */
+}
+
+void flush_thread(void)
+{
+ struct task_struct *tsk = current;
+
+ memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8);
+
+ /*
+ * Forget coprocessor state..
+ */
+ clear_fpu(tsk);
+ tsk->used_math = 0;
+}
+
+void release_thread(struct task_struct *dead_task)
+{
+ if (dead_task->mm) {
+ // temporary debugging check
+ if (dead_task->mm->context.size) {
+ printk("WARNING: dead process %8s still has LDT? <%p/%08x>\n",
+ dead_task->comm,
+ dead_task->mm->context.ldt,
+ dead_task->mm->context.size);
+ BUG();
+ }
+ }
+ //release_x86_irqs(dead_task);
+}
+
+
+/*
+ * Save a segment.
+ */
+#define savesegment(seg,value) \
+ asm volatile("movl %%" #seg ",%0":"=m" (*(int *)&(value)))
+
+int copy_thread(int nr, unsigned long clone_flags, unsigned long esp,
+ unsigned long unused,
+ struct task_struct * p, struct pt_regs * regs)
+{
+ struct pt_regs * childregs;
+
+ childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long) p)) - 1;
+ struct_cpy(childregs, regs);
+ childregs->eax = 0;
+ childregs->esp = esp;
+
+ p->thread.esp = (unsigned long) childregs;
+ p->thread.esp0 = (unsigned long) (childregs+1);
+
+ p->thread.eip = (unsigned long) ret_from_fork;
+
+ savesegment(fs,p->thread.fs);
+ savesegment(gs,p->thread.gs);
+
+ unlazy_fpu(current);
+ struct_cpy(&p->thread.i387, ¤t->thread.i387);
+
+ p->thread.io_pl = current->thread.io_pl;
+
+ return 0;
+}
+
+/*
+ * fill in the user structure for a core dump..
+ */
+void dump_thread(struct pt_regs * regs, struct user * dump)
+{
+ int i;
+
+/* changed the size calculations - should hopefully work better. lbt */
+ dump->magic = CMAGIC;
+ dump->start_code = 0;
+ dump->start_stack = regs->esp & ~(PAGE_SIZE - 1);
+ dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT;
+ dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >>
PAGE_SHIFT;
+ dump->u_dsize -= dump->u_tsize;
+ dump->u_ssize = 0;
+ for (i = 0; i < 8; i++)
+ dump->u_debugreg[i] = current->thread.debugreg[i];
+
+ if (dump->start_stack < TASK_SIZE)
+ dump->u_ssize = ((unsigned long) (TASK_SIZE - dump->start_stack)) >>
PAGE_SHIFT;
+
+ dump->regs.ebx = regs->ebx;
+ dump->regs.ecx = regs->ecx;
+ dump->regs.edx = regs->edx;
+ dump->regs.esi = regs->esi;
+ dump->regs.edi = regs->edi;
+ dump->regs.ebp = regs->ebp;
+ dump->regs.eax = regs->eax;
+ dump->regs.ds = regs->xds;
+ dump->regs.es = regs->xes;
+ savesegment(fs,dump->regs.fs);
+ savesegment(gs,dump->regs.gs);
+ dump->regs.orig_eax = regs->orig_eax;
+ dump->regs.eip = regs->eip;
+ dump->regs.cs = regs->xcs;
+ dump->regs.eflags = regs->eflags;
+ dump->regs.esp = regs->esp;
+ dump->regs.ss = regs->xss;
+
+ dump->u_fpvalid = dump_fpu (regs, &dump->i387);
+}
+
+/*
+ * switch_to(x,yn) should switch tasks from x to y.
+ *
+ * We fsave/fwait so that an exception goes off at the right time
+ * (as a call from the fsave or fwait in effect) rather than to
+ * the wrong process. Lazy FP saving no longer makes any sense
+ * with modern CPU's, and this simplifies a lot of things (SMP
+ * and UP become the same).
+ *
+ * NOTE! We used to use the x86 hardware context switching. The
+ * reason for not using it any more becomes apparent when you
+ * try to recover gracefully from saved state that is no longer
+ * valid (stale segment register values in particular). With the
+ * hardware task-switch, there is no way to fix up bad state in
+ * a reasonable manner.
+ *
+ * The fact that Intel documents the hardware task-switching to
+ * be slow is a fairly red herring - this code is not noticeably
+ * faster. However, there _is_ some room for improvement here,
+ * so the performance issues may eventually be a valid point.
+ * More important, however, is the fact that this allows us much
+ * more flexibility.
+ */
+void fastcall __switch_to(struct task_struct *prev_p, struct task_struct
*next_p)
+{
+ struct thread_struct *next = &next_p->thread;
+ physdev_op_t op;
+ multicall_entry_t _mcl[8], *mcl = _mcl;
+
+ /*
+ * This is basically 'unlazy_fpu', except that we queue a multicall to
+ * indicate FPU task switch, rather than synchronously trapping to Xen.
+ */
+ if ( prev_p->flags & PF_USEDFPU )
+ {
+ if ( cpu_has_fxsr )
+ asm volatile( "fxsave %0 ; fnclex"
+ : "=m" (prev_p->thread.i387.fxsave) );
+ else
+ asm volatile( "fnsave %0 ; fwait"
+ : "=m" (prev_p->thread.i387.fsave) );
+ prev_p->flags &= ~PF_USEDFPU;
+ mcl->op = __HYPERVISOR_fpu_taskswitch;
+ mcl->args[0] = 1;
+ mcl++;
+ }
+
+ mcl->op = __HYPERVISOR_stack_switch;
+ mcl->args[0] = __KERNEL_DS;
+ mcl->args[1] = next->esp0;
+ mcl++;
+
+ if ( prev_p->thread.io_pl != next->io_pl )
+ {
+ op.cmd = PHYSDEVOP_SET_IOPL;
+ op.u.set_iopl.iopl = next->io_pl;
+ mcl->op = __HYPERVISOR_physdev_op;
+ mcl->args[0] = (unsigned long)&op;
+ mcl++;
+ }
+
+ (void)HYPERVISOR_multicall(_mcl, mcl - _mcl);
+
+ /*
+ * Restore %fs and %gs.
+ */
+ loadsegment(fs, next->fs);
+ loadsegment(gs, next->gs);
+
+ /*
+ * Now maybe reload the debug registers
+ */
+ if ( next->debugreg[7] != 0 )
+ {
+ HYPERVISOR_set_debugreg(0, next->debugreg[0]);
+ HYPERVISOR_set_debugreg(1, next->debugreg[1]);
+ HYPERVISOR_set_debugreg(2, next->debugreg[2]);
+ HYPERVISOR_set_debugreg(3, next->debugreg[3]);
+ /* no 4 and 5 */
+ HYPERVISOR_set_debugreg(6, next->debugreg[6]);
+ HYPERVISOR_set_debugreg(7, next->debugreg[7]);
+ }
+}
+
+asmlinkage int sys_fork(struct pt_regs regs)
+{
+ return do_fork(SIGCHLD, regs.esp, ®s, 0);
+}
+
+asmlinkage int sys_clone(struct pt_regs regs)
+{
+ unsigned long clone_flags;
+ unsigned long newsp;
+
+ clone_flags = regs.ebx;
+ newsp = regs.ecx;
+ if (!newsp)
+ newsp = regs.esp;
+ return do_fork(clone_flags, newsp, ®s, 0);
+}
+
+/*
+ * This is trivial, and on the face of it looks like it
+ * could equally well be done in user mode.
+ *
+ * Not so, for quite unobvious reasons - register pressure.
+ * In user mode vfork() cannot have a stack frame, and if
+ * done by calling the "clone()" system call directly, you
+ * do not have enough call-clobbered registers to hold all
+ * the information you need.
+ */
+asmlinkage int sys_vfork(struct pt_regs regs)
+{
+ return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.esp, ®s, 0);
+}
+
+/*
+ * sys_execve() executes a new program.
+ */
+asmlinkage int sys_execve(struct pt_regs regs)
+{
+ int error;
+ char * filename;
+
+ filename = getname((char *) regs.ebx);
+ error = PTR_ERR(filename);
+ if (IS_ERR(filename))
+ goto out;
+ error = do_execve(filename, (char **) regs.ecx, (char **) regs.edx, ®s);
+ if (error == 0)
+ current->ptrace &= ~PT_DTRACE;
+ putname(filename);
+ out:
+ return error;
+}
+
+/*
+ * These bracket the sleeping functions..
+ */
+extern void scheduling_functions_start_here(void);
+extern void scheduling_functions_end_here(void);
+#define first_sched ((unsigned long) scheduling_functions_start_here)
+#define last_sched ((unsigned long) scheduling_functions_end_here)
+
+unsigned long get_wchan(struct task_struct *p)
+{
+ unsigned long ebp, esp, eip;
+ unsigned long stack_page;
+ int count = 0;
+ if (!p || p == current || p->state == TASK_RUNNING)
+ return 0;
+ stack_page = (unsigned long)p;
+ esp = p->thread.esp;
+ if (!stack_page || esp < stack_page || esp > 8188+stack_page)
+ return 0;
+ /* include/asm-i386/system.h:switch_to() pushes ebp last. */
+ ebp = *(unsigned long *) esp;
+ do {
+ if (ebp < stack_page || ebp > 8184+stack_page)
+ return 0;
+ eip = *(unsigned long *) (ebp+4);
+ if (eip < first_sched || eip >= last_sched)
+ return eip;
+ ebp = *(unsigned long *) ebp;
+ } while (count++ < 16);
+ return 0;
+}
+#undef last_sched
+#undef first_sched
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/mm/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/mm/Makefile Fri Jul 15 13:39:50 2005
@@ -0,0 +1,16 @@
+#
+# Makefile for the linux i386-specific parts of the memory manager.
+#
+# Note! Dependencies are done automagically by 'make dep', which also
+# removes any old dependencies. DON'T put your own dependencies here
+# unless it's something special (ie not a .c file).
+#
+# Note 2! The CFLAGS definition is now in the main makefile...
+
+O_TARGET := mm.o
+
+obj-y := init.o fault.o extable.o pageattr.o hypervisor.o ioremap.o
+
+export-objs := pageattr.o
+
+include $(TOPDIR)/Rules.make
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/kernel/timer.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/kernel/timer.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,968 @@
+/*
+ * linux/kernel/timer.c
+ *
+ * Kernel internal timers, kernel timekeeping, basic process system calls
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * 1997-01-28 Modified by Finn Arne Gangstad to make timers scale better.
+ *
+ * 1997-09-10 Updated NTP code according to technical memorandum Jan '96
+ * "A Kernel Model for Precision Timekeeping" by Dave Mills
+ * 1998-12-24 Fixed a xtime SMP race (we need the xtime_lock rw spinlock to
+ * serialize accesses to xtime/lost_ticks).
+ * Copyright (C) 1998 Andrea Arcangeli
+ * 1999-03-10 Improved NTP compatibility by Ulrich Windl
+ */
+
+#include <linux/config.h>
+#include <linux/mm.h>
+#include <linux/timex.h>
+#include <linux/delay.h>
+#include <linux/smp_lock.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+
+#include <asm/uaccess.h>
+
+/*
+ * Timekeeping variables
+ */
+
+long tick = (1000000 + HZ/2) / HZ; /* timer interrupt period */
+
+/* The current time */
+struct timeval xtime __attribute__ ((aligned (16)));
+
+/* Don't completely fail for HZ > 500. */
+int tickadj = 500/HZ ? : 1; /* microsecs */
+
+DECLARE_TASK_QUEUE(tq_timer);
+DECLARE_TASK_QUEUE(tq_immediate);
+
+/*
+ * phase-lock loop variables
+ */
+/* TIME_ERROR prevents overwriting the CMOS clock */
+int time_state = TIME_OK; /* clock synchronization status */
+int time_status = STA_UNSYNC; /* clock status bits */
+long time_offset; /* time adjustment (us) */
+long time_constant = 2; /* pll time constant
*/
+long time_tolerance = MAXFREQ; /* frequency tolerance (ppm) */
+long time_precision = 1; /* clock precision (us) */
+long time_maxerror = NTP_PHASE_LIMIT; /* maximum error (us) */
+long time_esterror = NTP_PHASE_LIMIT; /* estimated error (us) */
+long time_phase; /* phase offset (scaled us) */
+long time_freq = ((1000000 + HZ/2) % HZ - HZ/2) << SHIFT_USEC;
+ /* frequency offset (scaled ppm)*/
+long time_adj; /* tick adjust (scaled 1 / HZ) */
+long time_reftime; /* time at last adjustment (s) */
+
+long time_adjust;
+long time_adjust_step;
+
+unsigned long event;
+
+extern int do_setitimer(int, struct itimerval *, struct itimerval *);
+
+unsigned long volatile jiffies;
+
+unsigned int * prof_buffer;
+unsigned long prof_len;
+unsigned long prof_shift;
+
+/*
+ * Event timer code
+ */
+#define TVN_BITS 6
+#define TVR_BITS 8
+#define TVN_SIZE (1 << TVN_BITS)
+#define TVR_SIZE (1 << TVR_BITS)
+#define TVN_MASK (TVN_SIZE - 1)
+#define TVR_MASK (TVR_SIZE - 1)
+
+struct timer_vec {
+ int index;
+ struct list_head vec[TVN_SIZE];
+};
+
+struct timer_vec_root {
+ int index;
+ struct list_head vec[TVR_SIZE];
+};
+
+static struct timer_vec tv5;
+static struct timer_vec tv4;
+static struct timer_vec tv3;
+static struct timer_vec tv2;
+static struct timer_vec_root tv1;
+
+static struct timer_vec * const tvecs[] = {
+ (struct timer_vec *)&tv1, &tv2, &tv3, &tv4, &tv5
+};
+
+static struct list_head * run_timer_list_running;
+
+#define NOOF_TVECS (sizeof(tvecs) / sizeof(tvecs[0]))
+
+void init_timervecs (void)
+{
+ int i;
+
+ for (i = 0; i < TVN_SIZE; i++) {
+ INIT_LIST_HEAD(tv5.vec + i);
+ INIT_LIST_HEAD(tv4.vec + i);
+ INIT_LIST_HEAD(tv3.vec + i);
+ INIT_LIST_HEAD(tv2.vec + i);
+ }
+ for (i = 0; i < TVR_SIZE; i++)
+ INIT_LIST_HEAD(tv1.vec + i);
+}
+
+static unsigned long timer_jiffies;
+
+static inline void internal_add_timer(struct timer_list *timer)
+{
+ /*
+ * must be cli-ed when calling this
+ */
+ unsigned long expires = timer->expires;
+ unsigned long idx = expires - timer_jiffies;
+ struct list_head * vec;
+
+ if (run_timer_list_running)
+ vec = run_timer_list_running;
+ else if (idx < TVR_SIZE) {
+ int i = expires & TVR_MASK;
+ vec = tv1.vec + i;
+ } else if (idx < 1 << (TVR_BITS + TVN_BITS)) {
+ int i = (expires >> TVR_BITS) & TVN_MASK;
+ vec = tv2.vec + i;
+ } else if (idx < 1 << (TVR_BITS + 2 * TVN_BITS)) {
+ int i = (expires >> (TVR_BITS + TVN_BITS)) & TVN_MASK;
+ vec = tv3.vec + i;
+ } else if (idx < 1 << (TVR_BITS + 3 * TVN_BITS)) {
+ int i = (expires >> (TVR_BITS + 2 * TVN_BITS)) & TVN_MASK;
+ vec = tv4.vec + i;
+ } else if ((signed long) idx < 0) {
+ /* can happen if you add a timer with expires == jiffies,
+ * or you set a timer to go off in the past
+ */
+ vec = tv1.vec + tv1.index;
+ } else if (idx <= 0xffffffffUL) {
+ int i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK;
+ vec = tv5.vec + i;
+ } else {
+ /* Can only get here on architectures with 64-bit jiffies */
+ INIT_LIST_HEAD(&timer->list);
+ return;
+ }
+ /*
+ * Timers are FIFO!
+ */
+ list_add(&timer->list, vec->prev);
+}
+
+/* Initialize both explicitly - let's try to have them in the same cache line
*/
+spinlock_t timerlist_lock = SPIN_LOCK_UNLOCKED;
+
+#ifdef CONFIG_SMP
+volatile struct timer_list * volatile running_timer;
+#define timer_enter(t) do { running_timer = t; mb(); } while (0)
+#define timer_exit() do { running_timer = NULL; } while (0)
+#define timer_is_running(t) (running_timer == t)
+#define timer_synchronize(t) while (timer_is_running(t)) barrier()
+#else
+#define timer_enter(t) do { } while (0)
+#define timer_exit() do { } while (0)
+#endif
+
+void add_timer(struct timer_list *timer)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&timerlist_lock, flags);
+ if (timer_pending(timer))
+ goto bug;
+ internal_add_timer(timer);
+ spin_unlock_irqrestore(&timerlist_lock, flags);
+ return;
+bug:
+ spin_unlock_irqrestore(&timerlist_lock, flags);
+ printk("bug: kernel timer added twice at %p.\n",
+ __builtin_return_address(0));
+}
+
+static inline int detach_timer (struct timer_list *timer)
+{
+ if (!timer_pending(timer))
+ return 0;
+ list_del(&timer->list);
+ return 1;
+}
+
+int mod_timer(struct timer_list *timer, unsigned long expires)
+{
+ int ret;
+ unsigned long flags;
+
+ spin_lock_irqsave(&timerlist_lock, flags);
+ timer->expires = expires;
+ ret = detach_timer(timer);
+ internal_add_timer(timer);
+ spin_unlock_irqrestore(&timerlist_lock, flags);
+ return ret;
+}
+
+int del_timer(struct timer_list * timer)
+{
+ int ret;
+ unsigned long flags;
+
+ spin_lock_irqsave(&timerlist_lock, flags);
+ ret = detach_timer(timer);
+ timer->list.next = timer->list.prev = NULL;
+ spin_unlock_irqrestore(&timerlist_lock, flags);
+ return ret;
+}
+
+#ifdef CONFIG_SMP
+void sync_timers(void)
+{
+ spin_unlock_wait(&global_bh_lock);
+}
+
+/*
+ * SMP specific function to delete periodic timer.
+ * Caller must disable by some means restarting the timer
+ * for new. Upon exit the timer is not queued and handler is not running
+ * on any CPU. It returns number of times, which timer was deleted
+ * (for reference counting).
+ */
+
+int del_timer_sync(struct timer_list * timer)
+{
+ int ret = 0;
+
+ for (;;) {
+ unsigned long flags;
+ int running;
+
+ spin_lock_irqsave(&timerlist_lock, flags);
+ ret += detach_timer(timer);
+ timer->list.next = timer->list.prev = 0;
+ running = timer_is_running(timer);
+ spin_unlock_irqrestore(&timerlist_lock, flags);
+
+ if (!running)
+ break;
+
+ timer_synchronize(timer);
+ }
+
+ return ret;
+}
+#endif
+
+
+static inline void cascade_timers(struct timer_vec *tv)
+{
+ /* cascade all the timers from tv up one level */
+ struct list_head *head, *curr, *next;
+
+ head = tv->vec + tv->index;
+ curr = head->next;
+ /*
+ * We are removing _all_ timers from the list, so we don't have to
+ * detach them individually, just clear the list afterwards.
+ */
+ while (curr != head) {
+ struct timer_list *tmp;
+
+ tmp = list_entry(curr, struct timer_list, list);
+ next = curr->next;
+ list_del(curr); // not needed
+ internal_add_timer(tmp);
+ curr = next;
+ }
+ INIT_LIST_HEAD(head);
+ tv->index = (tv->index + 1) & TVN_MASK;
+}
+
+static inline void run_timer_list(void)
+{
+ spin_lock_irq(&timerlist_lock);
+ while ((long)(jiffies - timer_jiffies) >= 0) {
+ LIST_HEAD(queued);
+ struct list_head *head, *curr;
+ if (!tv1.index) {
+ int n = 1;
+ do {
+ cascade_timers(tvecs[n]);
+ } while (tvecs[n]->index == 1 && ++n < NOOF_TVECS);
+ }
+ run_timer_list_running = &queued;
+repeat:
+ head = tv1.vec + tv1.index;
+ curr = head->next;
+ if (curr != head) {
+ struct timer_list *timer;
+ void (*fn)(unsigned long);
+ unsigned long data;
+
+ timer = list_entry(curr, struct timer_list, list);
+ fn = timer->function;
+ data= timer->data;
+
+ detach_timer(timer);
+ timer->list.next = timer->list.prev = NULL;
+ timer_enter(timer);
+ spin_unlock_irq(&timerlist_lock);
+ fn(data);
+ spin_lock_irq(&timerlist_lock);
+ timer_exit();
+ goto repeat;
+ }
+ run_timer_list_running = NULL;
+ ++timer_jiffies;
+ tv1.index = (tv1.index + 1) & TVR_MASK;
+
+ curr = queued.next;
+ while (curr != &queued) {
+ struct timer_list *timer;
+
+ timer = list_entry(curr, struct timer_list, list);
+ curr = curr->next;
+ internal_add_timer(timer);
+ }
+ }
+ spin_unlock_irq(&timerlist_lock);
+}
+
+#ifdef CONFIG_NO_IDLE_HZ
+/*
+ * Find out when the next timer event is due to happen. This
+ * is used on S/390 to stop all activity when all cpus are idle.
+ * And in XenoLinux to achieve the same.
+ * The timerlist_lock must be acquired before calling this function.
+ */
+struct timer_list *next_timer_event(void)
+{
+ struct timer_list *nte, *tmp;
+ struct list_head *lst;
+ int i, j;
+
+ /* Look for the next timer event in tv1. */
+ i = 0;
+ j = tvecs[0]->index;
+ do {
+ struct list_head *head = tvecs[0]->vec + j;
+ if (!list_empty(head)) {
+ nte = list_entry(head->next, struct timer_list, list);
+ goto found;
+ }
+ j = (j + 1) & TVR_MASK;
+ } while (j != tv1.index);
+
+ /* No event found in tv1. Check tv2-tv5. */
+ for (i = 1; i < NOOF_TVECS; i++) {
+ j = tvecs[i]->index;
+ do {
+ nte = NULL;
+ list_for_each(lst, tvecs[i]->vec + j) {
+ tmp = list_entry(lst, struct timer_list, list);
+ if (nte == NULL ||
+ time_before(tmp->expires, nte->expires))
+ nte = tmp;
+ }
+ if (nte)
+ goto found;
+ j = (j + 1) & TVN_MASK;
+ } while (j != tvecs[i]->index);
+ }
+ return NULL;
+found:
+ /* Found timer event in tvecs[i]->vec[j] */
+ if (j < tvecs[i]->index && i < NOOF_TVECS-1) {
+ /*
+ * The search wrapped. We need to look at the next list
+ * from tvecs[i+1] that would cascade into tvecs[i].
+ */
+ list_for_each(lst, tvecs[i+1]->vec+tvecs[i+1]->index) {
+ tmp = list_entry(lst, struct timer_list, list);
+ if (time_before(tmp->expires, nte->expires))
+ nte = tmp;
+ }
+ }
+ return nte;
+}
+#endif
+
+spinlock_t tqueue_lock = SPIN_LOCK_UNLOCKED;
+
+void tqueue_bh(void)
+{
+ run_task_queue(&tq_timer);
+}
+
+void immediate_bh(void)
+{
+ run_task_queue(&tq_immediate);
+}
+
+/*
+ * this routine handles the overflow of the microsecond field
+ *
+ * The tricky bits of code to handle the accurate clock support
+ * were provided by Dave Mills (Mills@xxxxxxxx) of NTP fame.
+ * They were originally developed for SUN and DEC kernels.
+ * All the kudos should go to Dave for this stuff.
+ *
+ */
+static void second_overflow(void)
+{
+ long ltemp;
+
+ /* Bump the maxerror field */
+ time_maxerror += time_tolerance >> SHIFT_USEC;
+ if ( time_maxerror > NTP_PHASE_LIMIT ) {
+ time_maxerror = NTP_PHASE_LIMIT;
+ time_status |= STA_UNSYNC;
+ }
+
+ /*
+ * Leap second processing. If in leap-insert state at
+ * the end of the day, the system clock is set back one
+ * second; if in leap-delete state, the system clock is
+ * set ahead one second. The microtime() routine or
+ * external clock driver will insure that reported time
+ * is always monotonic. The ugly divides should be
+ * replaced.
+ */
+ switch (time_state) {
+
+ case TIME_OK:
+ if (time_status & STA_INS)
+ time_state = TIME_INS;
+ else if (time_status & STA_DEL)
+ time_state = TIME_DEL;
+ break;
+
+ case TIME_INS:
+ if (xtime.tv_sec % 86400 == 0) {
+ xtime.tv_sec--;
+ time_state = TIME_OOP;
+ printk(KERN_NOTICE "Clock: inserting leap second 23:59:60 UTC\n");
+ }
+ break;
+
+ case TIME_DEL:
+ if ((xtime.tv_sec + 1) % 86400 == 0) {
+ xtime.tv_sec++;
+ time_state = TIME_WAIT;
+ printk(KERN_NOTICE "Clock: deleting leap second 23:59:59 UTC\n");
+ }
+ break;
+
+ case TIME_OOP:
+ time_state = TIME_WAIT;
+ break;
+
+ case TIME_WAIT:
+ if (!(time_status & (STA_INS | STA_DEL)))
+ time_state = TIME_OK;
+ }
+
+ /*
+ * Compute the phase adjustment for the next second. In
+ * PLL mode, the offset is reduced by a fixed factor
+ * times the time constant. In FLL mode the offset is
+ * used directly. In either mode, the maximum phase
+ * adjustment for each second is clamped so as to spread
+ * the adjustment over not more than the number of
+ * seconds between updates.
+ */
+ if (time_offset < 0) {
+ ltemp = -time_offset;
+ if (!(time_status & STA_FLL))
+ ltemp >>= SHIFT_KG + time_constant;
+ if (ltemp > (MAXPHASE / MINSEC) << SHIFT_UPDATE)
+ ltemp = (MAXPHASE / MINSEC) << SHIFT_UPDATE;
+ time_offset += ltemp;
+ time_adj = -ltemp << (SHIFT_SCALE - SHIFT_HZ - SHIFT_UPDATE);
+ } else {
+ ltemp = time_offset;
+ if (!(time_status & STA_FLL))
+ ltemp >>= SHIFT_KG + time_constant;
+ if (ltemp > (MAXPHASE / MINSEC) << SHIFT_UPDATE)
+ ltemp = (MAXPHASE / MINSEC) << SHIFT_UPDATE;
+ time_offset -= ltemp;
+ time_adj = ltemp << (SHIFT_SCALE - SHIFT_HZ - SHIFT_UPDATE);
+ }
+
+ /*
+ * Compute the frequency estimate and additional phase
+ * adjustment due to frequency error for the next
+ * second. When the PPS signal is engaged, gnaw on the
+ * watchdog counter and update the frequency computed by
+ * the pll and the PPS signal.
+ */
+ pps_valid++;
+ if (pps_valid == PPS_VALID) { /* PPS signal lost */
+ pps_jitter = MAXTIME;
+ pps_stabil = MAXFREQ;
+ time_status &= ~(STA_PPSSIGNAL | STA_PPSJITTER |
+ STA_PPSWANDER | STA_PPSERROR);
+ }
+ ltemp = time_freq + pps_freq;
+ if (ltemp < 0)
+ time_adj -= -ltemp >>
+ (SHIFT_USEC + SHIFT_HZ - SHIFT_SCALE);
+ else
+ time_adj += ltemp >>
+ (SHIFT_USEC + SHIFT_HZ - SHIFT_SCALE);
+
+#if HZ == 100
+ /* Compensate for (HZ==100) != (1 << SHIFT_HZ).
+ * Add 25% and 3.125% to get 128.125; => only 0.125% error (p. 14)
+ */
+ if (time_adj < 0)
+ time_adj -= (-time_adj >> 2) + (-time_adj >> 5);
+ else
+ time_adj += (time_adj >> 2) + (time_adj >> 5);
+#endif
+}
+
+/* in the NTP reference this is called "hardclock()" */
+static void update_wall_time_one_tick(void)
+{
+ if ( (time_adjust_step = time_adjust) != 0 ) {
+ /* We are doing an adjtime thing.
+ *
+ * Prepare time_adjust_step to be within bounds.
+ * Note that a positive time_adjust means we want the clock
+ * to run faster.
+ *
+ * Limit the amount of the step to be in the range
+ * -tickadj .. +tickadj
+ */
+ if (time_adjust > tickadj)
+ time_adjust_step = tickadj;
+ else if (time_adjust < -tickadj)
+ time_adjust_step = -tickadj;
+
+ /* Reduce by this step the amount of time left */
+ time_adjust -= time_adjust_step;
+ }
+ xtime.tv_usec += tick + time_adjust_step;
+ /*
+ * Advance the phase, once it gets to one microsecond, then
+ * advance the tick more.
+ */
+ time_phase += time_adj;
+ if (time_phase <= -FINEUSEC) {
+ long ltemp = -time_phase >> SHIFT_SCALE;
+ time_phase += ltemp << SHIFT_SCALE;
+ xtime.tv_usec -= ltemp;
+ }
+ else if (time_phase >= FINEUSEC) {
+ long ltemp = time_phase >> SHIFT_SCALE;
+ time_phase -= ltemp << SHIFT_SCALE;
+ xtime.tv_usec += ltemp;
+ }
+}
+
+/*
+ * Using a loop looks inefficient, but "ticks" is
+ * usually just one (we shouldn't be losing ticks,
+ * we're doing this this way mainly for interrupt
+ * latency reasons, not because we think we'll
+ * have lots of lost timer ticks
+ */
+static void update_wall_time(unsigned long ticks)
+{
+ do {
+ ticks--;
+ update_wall_time_one_tick();
+ } while (ticks);
+
+ while (xtime.tv_usec >= 1000000) {
+ xtime.tv_usec -= 1000000;
+ xtime.tv_sec++;
+ second_overflow();
+ }
+}
+
+static inline void do_process_times(struct task_struct *p,
+ unsigned long user, unsigned long system)
+{
+ unsigned long psecs;
+
+ psecs = (p->times.tms_utime += user);
+ psecs += (p->times.tms_stime += system);
+ if (psecs / HZ > p->rlim[RLIMIT_CPU].rlim_cur) {
+ /* Send SIGXCPU every second.. */
+ if (!(psecs % HZ))
+ send_sig(SIGXCPU, p, 1);
+ /* and SIGKILL when we go over max.. */
+ if (psecs / HZ > p->rlim[RLIMIT_CPU].rlim_max)
+ send_sig(SIGKILL, p, 1);
+ }
+}
+
+static inline void do_it_virt(struct task_struct * p, unsigned long ticks)
+{
+ unsigned long it_virt = p->it_virt_value;
+
+ if (it_virt) {
+ it_virt -= ticks;
+ if (!it_virt) {
+ it_virt = p->it_virt_incr;
+ send_sig(SIGVTALRM, p, 1);
+ }
+ p->it_virt_value = it_virt;
+ }
+}
+
+static inline void do_it_prof(struct task_struct *p)
+{
+ unsigned long it_prof = p->it_prof_value;
+
+ if (it_prof) {
+ if (--it_prof == 0) {
+ it_prof = p->it_prof_incr;
+ send_sig(SIGPROF, p, 1);
+ }
+ p->it_prof_value = it_prof;
+ }
+}
+
+void update_one_process(struct task_struct *p, unsigned long user,
+ unsigned long system, int cpu)
+{
+ p->per_cpu_utime[cpu] += user;
+ p->per_cpu_stime[cpu] += system;
+ do_process_times(p, user, system);
+ do_it_virt(p, user);
+ do_it_prof(p);
+}
+
+/*
+ * Called from the timer interrupt handler to charge one tick to the current
+ * process. user_tick is 1 if the tick is user time, 0 for system.
+ */
+void update_process_times(int user_tick)
+{
+ struct task_struct *p = current;
+ int cpu = smp_processor_id(), system = user_tick ^ 1;
+
+ update_one_process(p, user_tick, system, cpu);
+ if (p->pid) {
+ if (--p->counter <= 0) {
+ p->counter = 0;
+ /*
+ * SCHED_FIFO is priority preemption, so this is
+ * not the place to decide whether to reschedule a
+ * SCHED_FIFO task or not - Bhavesh Davda
+ */
+ if (p->policy != SCHED_FIFO) {
+ p->need_resched = 1;
+ }
+ }
+ if (p->nice > 0)
+ kstat.per_cpu_nice[cpu] += user_tick;
+ else
+ kstat.per_cpu_user[cpu] += user_tick;
+ kstat.per_cpu_system[cpu] += system;
+ } else if (local_bh_count(cpu) || local_irq_count(cpu) > 1)
+ kstat.per_cpu_system[cpu] += system;
+}
+
+/*
+ * Called from the timer interrupt handler to charge a couple of ticks
+ * to the current process.
+ */
+void update_process_times_us(int user_ticks, int system_ticks)
+{
+ struct task_struct *p = current;
+ int cpu = smp_processor_id();
+
+ update_one_process(p, user_ticks, system_ticks, cpu);
+ if (p->pid) {
+ p->counter -= user_ticks + system_ticks;
+ if (p->counter <= 0) {
+ p->counter = 0;
+ p->need_resched = 1;
+ }
+ if (p->nice > 0)
+ kstat.per_cpu_nice[cpu] += user_ticks;
+ else
+ kstat.per_cpu_user[cpu] += user_ticks;
+ kstat.per_cpu_system[cpu] += system_ticks;
+ } else if (local_bh_count(cpu) || local_irq_count(cpu) > 1)
+ kstat.per_cpu_system[cpu] += system_ticks;
+}
+
+/*
+ * Nr of active tasks - counted in fixed-point numbers
+ */
+static unsigned long count_active_tasks(void)
+{
+ struct task_struct *p;
+ unsigned long nr = 0;
+
+ read_lock(&tasklist_lock);
+ for_each_task(p) {
+ if ((p->state == TASK_RUNNING ||
+ (p->state & TASK_UNINTERRUPTIBLE)))
+ nr += FIXED_1;
+ }
+ read_unlock(&tasklist_lock);
+ return nr;
+}
+
+/*
+ * Hmm.. Changed this, as the GNU make sources (load.c) seems to
+ * imply that avenrun[] is the standard name for this kind of thing.
+ * Nothing else seems to be standardized: the fractional size etc
+ * all seem to differ on different machines.
+ */
+unsigned long avenrun[3];
+
+static inline void calc_load(unsigned long ticks)
+{
+ unsigned long active_tasks; /* fixed-point */
+ static int count = LOAD_FREQ;
+
+ count -= ticks;
+ while (count < 0) {
+ count += LOAD_FREQ;
+ active_tasks = count_active_tasks();
+ CALC_LOAD(avenrun[0], EXP_1, active_tasks);
+ CALC_LOAD(avenrun[1], EXP_5, active_tasks);
+ CALC_LOAD(avenrun[2], EXP_15, active_tasks);
+ }
+}
+
+/* jiffies at the most recent update of wall time */
+unsigned long wall_jiffies;
+
+/*
+ * This spinlock protect us from races in SMP while playing with xtime. -arca
+ */
+rwlock_t xtime_lock = RW_LOCK_UNLOCKED;
+
+static inline void update_times(void)
+{
+ unsigned long ticks;
+
+ /*
+ * update_times() is run from the raw timer_bh handler so we
+ * just know that the irqs are locally enabled and so we don't
+ * need to save/restore the flags of the local CPU here. -arca
+ */
+ write_lock_irq(&xtime_lock);
+ vxtime_lock();
+
+ ticks = jiffies - wall_jiffies;
+ if (ticks) {
+ wall_jiffies += ticks;
+ update_wall_time(ticks);
+ }
+ vxtime_unlock();
+ write_unlock_irq(&xtime_lock);
+ calc_load(ticks);
+}
+
+void timer_bh(void)
+{
+ update_times();
+ run_timer_list();
+}
+
+void do_timer(struct pt_regs *regs)
+{
+ (*(unsigned long *)&jiffies)++;
+#ifndef CONFIG_SMP
+ /* SMP process accounting uses the local APIC timer */
+
+ update_process_times(user_mode(regs));
+#endif
+ mark_bh(TIMER_BH);
+ if (TQ_ACTIVE(tq_timer))
+ mark_bh(TQUEUE_BH);
+}
+
+void do_timer_ticks(int ticks)
+{
+ (*(unsigned long *)&jiffies) += ticks;
+ mark_bh(TIMER_BH);
+ if (TQ_ACTIVE(tq_timer))
+ mark_bh(TQUEUE_BH);
+}
+
+#if !defined(__alpha__) && !defined(__ia64__)
+
+/*
+ * For backwards compatibility? This can be done in libc so Alpha
+ * and all newer ports shouldn't need it.
+ */
+asmlinkage unsigned long sys_alarm(unsigned int seconds)
+{
+ struct itimerval it_new, it_old;
+ unsigned int oldalarm;
+
+ it_new.it_interval.tv_sec = it_new.it_interval.tv_usec = 0;
+ it_new.it_value.tv_sec = seconds;
+ it_new.it_value.tv_usec = 0;
+ do_setitimer(ITIMER_REAL, &it_new, &it_old);
+ oldalarm = it_old.it_value.tv_sec;
+ /* ehhh.. We can't return 0 if we have an alarm pending.. */
+ /* And we'd better return too much than too little anyway */
+ if (it_old.it_value.tv_usec)
+ oldalarm++;
+ return oldalarm;
+}
+
+#endif
+
+#ifndef __alpha__
+
+/*
+ * The Alpha uses getxpid, getxuid, and getxgid instead. Maybe this
+ * should be moved into arch/i386 instead?
+ */
+
+/**
+ * sys_getpid - return the thread group id of the current process
+ *
+ * Note, despite the name, this returns the tgid not the pid. The tgid and
+ * the pid are identical unless CLONE_THREAD was specified on clone() in
+ * which case the tgid is the same in all threads of the same group.
+ *
+ * This is SMP safe as current->tgid does not change.
+ */
+asmlinkage long sys_getpid(void)
+{
+ return current->tgid;
+}
+
+/*
+ * This is not strictly SMP safe: p_opptr could change
+ * from under us. However, rather than getting any lock
+ * we can use an optimistic algorithm: get the parent
+ * pid, and go back and check that the parent is still
+ * the same. If it has changed (which is extremely unlikely
+ * indeed), we just try again..
+ *
+ * NOTE! This depends on the fact that even if we _do_
+ * get an old value of "parent", we can happily dereference
+ * the pointer: we just can't necessarily trust the result
+ * until we know that the parent pointer is valid.
+ *
+ * The "mb()" macro is a memory barrier - a synchronizing
+ * event. It also makes sure that gcc doesn't optimize
+ * away the necessary memory references.. The barrier doesn't
+ * have to have all that strong semantics: on x86 we don't
+ * really require a synchronizing instruction, for example.
+ * The barrier is more important for code generation than
+ * for any real memory ordering semantics (even if there is
+ * a small window for a race, using the old pointer is
+ * harmless for a while).
+ */
+asmlinkage long sys_getppid(void)
+{
+ int pid;
+ struct task_struct * me = current;
+ struct task_struct * parent;
+
+ parent = me->p_opptr;
+ for (;;) {
+ pid = parent->pid;
+#if CONFIG_SMP
+{
+ struct task_struct *old = parent;
+ mb();
+ parent = me->p_opptr;
+ if (old != parent)
+ continue;
+}
+#endif
+ break;
+ }
+ return pid;
+}
+
+asmlinkage long sys_getuid(void)
+{
+ /* Only we change this so SMP safe */
+ return current->uid;
+}
+
+asmlinkage long sys_geteuid(void)
+{
+ /* Only we change this so SMP safe */
+ return current->euid;
+}
+
+asmlinkage long sys_getgid(void)
+{
+ /* Only we change this so SMP safe */
+ return current->gid;
+}
+
+asmlinkage long sys_getegid(void)
+{
+ /* Only we change this so SMP safe */
+ return current->egid;
+}
+
+#endif
+
+/* Thread ID - the internal kernel "pid" */
+asmlinkage long sys_gettid(void)
+{
+ return current->pid;
+}
+
+asmlinkage long sys_nanosleep(struct timespec *rqtp, struct timespec *rmtp)
+{
+ struct timespec t;
+ unsigned long expire;
+
+ if(copy_from_user(&t, rqtp, sizeof(struct timespec)))
+ return -EFAULT;
+
+ if (t.tv_nsec >= 1000000000L || t.tv_nsec < 0 || t.tv_sec < 0)
+ return -EINVAL;
+
+
+ if (t.tv_sec == 0 && t.tv_nsec <= 2000000L &&
+ current->policy != SCHED_OTHER)
+ {
+ /*
+ * Short delay requests up to 2 ms will be handled with
+ * high precision by a busy wait for all real-time processes.
+ *
+ * Its important on SMP not to do this holding locks.
+ */
+ udelay((t.tv_nsec + 999) / 1000);
+ return 0;
+ }
+
+ expire = timespec_to_jiffies(&t) + (t.tv_sec || t.tv_nsec);
+
+ current->state = TASK_INTERRUPTIBLE;
+ expire = schedule_timeout(expire);
+
+ if (expire) {
+ if (rmtp) {
+ jiffies_to_timespec(expire, &t);
+ if (copy_to_user(rmtp, &t, sizeof(struct timespec)))
+ return -EFAULT;
+ }
+ return -EINTR;
+ }
+ return 0;
+}
+
diff -r 35b74976f598 -r a83ac0806d6b linux-2.4.30-xen-sparse/mm/mprotect.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/mm/mprotect.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,344 @@
+/*
+ * linux/mm/mprotect.c
+ *
+ * (C) Copyright 1994 Linus Torvalds
+ */
+#include <linux/slab.h>
+#include <linux/smp_lock.h>
+#include <linux/shm.h>
+#include <linux/mman.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+
+static inline void change_pte_range(pmd_t * pmd, unsigned long address,
+ unsigned long size, pgprot_t newprot)
+{
+ pte_t * pte;
+ unsigned long end;
+
+ if (pmd_none(*pmd))
+ return;
+ if (pmd_bad(*pmd)) {
+ pmd_ERROR(*pmd);
+ pmd_clear(pmd);
+ return;
+ }
+ pte = pte_offset(pmd, address);
+ address &= ~PMD_MASK;
+ end = address + size;
+ if (end > PMD_SIZE)
+ end = PMD_SIZE;
+ do {
+ if (pte_present(*pte)) {
+ pte_t entry;
+
+ /* Avoid an SMP race with hardware updated dirty/clean
+ * bits by wiping the pte and then setting the new pte
+ * into place.
+ */
+ entry = ptep_get_and_clear(pte);
+ set_pte(pte, pte_modify(entry, newprot));
+ }
+ address += PAGE_SIZE;
+ pte++;
+ } while (address && (address < end));
+}
+
+static inline void change_pmd_range(pgd_t * pgd, unsigned long address,
+ unsigned long size, pgprot_t newprot)
+{
+ pmd_t * pmd;
+ unsigned long end;
+
+ if (pgd_none(*pgd))
+ return;
+ if (pgd_bad(*pgd)) {
+ pgd_ERROR(*pgd);
+ pgd_clear(pgd);
+ return;
+ }
+ pmd = pmd_offset(pgd, address);
+ address &= ~PGDIR_MASK;
+ end = address + size;
+ if (end > PGDIR_SIZE)
+ end = PGDIR_SIZE;
+ do {
+ change_pte_range(pmd, address, end - address, newprot);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ pmd++;
+ } while (address && (address < end));
+}
+
+static void change_protection(unsigned long start, unsigned long end, pgprot_t
newprot)
+{
+ pgd_t *dir;
+ unsigned long beg = start;
+
+ dir = pgd_offset(current->mm, start);
+ flush_cache_range(current->mm, beg, end);
+ if (start >= end)
+ BUG();
+ spin_lock(¤t->mm->page_table_lock);
+ do {
+ change_pmd_range(dir, start, end - start, newprot);
+ start = (start + PGDIR_SIZE) & PGDIR_MASK;
+ dir++;
+ } while (start && (start < end));
+ spin_unlock(¤t->mm->page_table_lock);
+ flush_tlb_range(current->mm, beg, end);
+ return;
+}
+
+static inline int mprotect_fixup_all(struct vm_area_struct * vma, struct
vm_area_struct ** pprev,
+ int newflags, pgprot_t prot)
+{
+ struct vm_area_struct * prev = *pprev;
+ struct mm_struct * mm = vma->vm_mm;
+
+ if (prev && prev->vm_end == vma->vm_start && can_vma_merge(prev,
newflags) &&
+ !vma->vm_file && !(vma->vm_flags & VM_SHARED)) {
+ spin_lock(&mm->page_table_lock);
+ prev->vm_end = vma->vm_end;
+ __vma_unlink(mm, vma, prev);
+ spin_unlock(&mm->page_table_lock);
+
+ kmem_cache_free(vm_area_cachep, vma);
+ mm->map_count--;
+
+ return 0;
+ }
+
+ spin_lock(&mm->page_table_lock);
+ vma->vm_flags = newflags;
+ vma->vm_page_prot = prot;
+ spin_unlock(&mm->page_table_lock);
+
+ *pprev = vma;
+
+ return 0;
+}
+
+static inline int mprotect_fixup_start(struct vm_area_struct * vma, struct
vm_area_struct ** pprev,
+ unsigned long end,
+ int newflags, pgprot_t prot)
+{
+ struct vm_area_struct * n, * prev = *pprev;
+
+ *pprev = vma;
+
+ if (prev && prev->vm_end == vma->vm_start && can_vma_merge(prev,
newflags) &&
+ !vma->vm_file && !(vma->vm_flags & VM_SHARED)) {
+ spin_lock(&vma->vm_mm->page_table_lock);
+ prev->vm_end = end;
+ vma->vm_start = end;
+ spin_unlock(&vma->vm_mm->page_table_lock);
+
+ return 0;
+ }
+ n = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ if (!n)
+ return -ENOMEM;
+ *n = *vma;
+ n->vm_end = end;
+ n->vm_flags = newflags;
+ n->vm_raend = 0;
+ n->vm_page_prot = prot;
+ if (n->vm_file)
+ get_file(n->vm_file);
+ if (n->vm_ops && n->vm_ops->open)
+ n->vm_ops->open(n);
+ vma->vm_pgoff += (end - vma->vm_start) >> PAGE_SHIFT;
+ lock_vma_mappings(vma);
+ spin_lock(&vma->vm_mm->page_table_lock);
+ vma->vm_start = end;
+ __insert_vm_struct(current->mm, n);
+ spin_unlock(&vma->vm_mm->page_table_lock);
+ unlock_vma_mappings(vma);
+
+ return 0;
+}
+
+static inline int mprotect_fixup_end(struct vm_area_struct * vma, struct
vm_area_struct ** pprev,
+ unsigned long start,
+ int newflags, pgprot_t prot)
+{
+ struct vm_area_struct * n;
+
+ n = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+ if (!n)
+ return -ENOMEM;
+ *n = *vma;
+ n->vm_start = start;
+ n->vm_pgoff += (n->vm_start - vma->vm_start) >> PAGE_SHIFT;
+ n->vm_flags = newflags;
+ n->vm_raend = 0;
+ n->vm_page_prot = prot;
+ if (n->vm_file)
+ get_file(n->vm_file);
+ if (n->vm_ops && n->vm_ops->open)
+ n->vm_ops->open(n);
+ lock_vma_mappings(vma);
+ spin_lock(&vma->vm_mm->page_table_lock);
+ vma->vm_end = start;
+ __insert_vm_struct(current->mm, n);
+ spin_unlock(&vma->vm_mm->page_table_lock);
+ unlock_vma_mappings(vma);
+
+ *pprev = n;
+
+ return 0;
+}
+
+static inline int mprotect_fixup_middle(struct vm_area_struct * vma, struct
vm_area_struct ** pprev,
+ unsigned long start, unsigned long end,
+ int newflags, pgprot_t prot)
+{
+ struct vm_area_struct * left, * right;
+
+ left = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ if (!left)
+ return -ENOMEM;
+ right = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ if (!right) {
+ kmem_cache_free(vm_area_cachep, left);
+ return -ENOMEM;
+ }
+ *left = *vma;
+ *right = *vma;
+ left->vm_end = start;
+ right->vm_start = end;
+ right->vm_pgoff += (right->vm_start - left->vm_start) >> PAGE_SHIFT;
+ left->vm_raend = 0;
+ right->vm_raend = 0;
+ if (vma->vm_file)
+ atomic_add(2,&vma->vm_file->f_count);
+ if (vma->vm_ops && vma->vm_ops->open) {
+ vma->vm_ops->open(left);
+ vma->vm_ops->open(right);
+ }
+ vma->vm_pgoff += (start - vma->vm_start) >> PAGE_SHIFT;
+ vma->vm_raend = 0;
+ vma->vm_page_prot = prot;
+ lock_vma_mappings(vma);
+ spin_lock(&vma->vm_mm->page_table_lock);
+ vma->vm_start = start;
+ vma->vm_end = end;
+ vma->vm_flags = newflags;
+ __insert_vm_struct(current->mm, left);
+ __insert_vm_struct(current->mm, right);
+ spin_unlock(&vma->vm_mm->page_table_lock);
+ unlock_vma_mappings(vma);
+
+ *pprev = right;
+
+ return 0;
+}
+
+static int mprotect_fixup(struct vm_area_struct * vma, struct vm_area_struct
** pprev,
+ unsigned long start, unsigned long end, unsigned int newflags)
+{
+ pgprot_t newprot;
+ int error;
+
+ if (newflags == vma->vm_flags) {
+ *pprev = vma;
+ return 0;
+ }
+ newprot = protection_map[newflags & 0xf];
+ if (start == vma->vm_start) {
+ if (end == vma->vm_end)
+ error = mprotect_fixup_all(vma, pprev, newflags,
newprot);
+ else
+ error = mprotect_fixup_start(vma, pprev, end, newflags,
newprot);
+ } else if (end == vma->vm_end)
+ error = mprotect_fixup_end(vma, pprev, start, newflags,
newprot);
+ else
+ error = mprotect_fixup_middle(vma, pprev, start, end, newflags,
newprot);
+
+ if (error)
+ return error;
+
+ change_protection(start, end, newprot);
+ return 0;
+}
+
+asmlinkage long sys_mprotect(unsigned long start, size_t len, unsigned long
prot)
+{
+ unsigned long nstart, end, tmp;
+ struct vm_area_struct * vma, * next, * prev;
+ int error = -EINVAL;
+
+ if (start & ~PAGE_MASK)
+ return -EINVAL;
+ len = PAGE_ALIGN(len);
+ end = start + len;
+ if (end < start)
+ return -ENOMEM;
+ if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC))
+ return -EINVAL;
+ if (end == start)
+ return 0;
+
+ down_write(¤t->mm->mmap_sem);
+
+ vma = find_vma_prev(current->mm, start, &prev);
+ error = -ENOMEM;
+ if (!vma || vma->vm_start > start)
+ goto out;
+
+#if defined(CONFIG_XEN_PRIVILEGED_GUEST)
+ /* mprotect() unsupported for I/O mappings in Xenolinux. */
+ error = -EINVAL;
+ if (vma->vm_flags & VM_IO)
+ goto out;
+#endif
+
+ for (nstart = start ; ; ) {
+ unsigned int newflags;
+ int last = 0;
+
+ /* Here we know that vma->vm_start <= nstart < vma->vm_end. */
+
+ newflags = prot | (vma->vm_flags & ~(PROT_READ | PROT_WRITE |
PROT_EXEC));
+ if ((newflags & ~(newflags >> 4)) & 0xf) {
+ error = -EACCES;
+ goto out;
+ }
+
+ if (vma->vm_end > end) {
+ error = mprotect_fixup(vma, &prev, nstart, end,
newflags);
+ goto out;
+ }
+ if (vma->vm_end == end)
+ last = 1;
+
+ tmp = vma->vm_end;
+ next = vma->vm_next;
+ error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
+ if (error)
+ goto out;
+ if (last)
+ break;
+ nstart = tmp;
+ vma = next;
+ if (!vma || vma->vm_start != nstart) {
+ error = -ENOMEM;
+ goto out;
+ }
+ }
+ if (next && prev->vm_end == next->vm_start && can_vma_merge(next,
prev->vm_flags) &&
+ !prev->vm_file && !(prev->vm_flags & VM_SHARED)) {
+ spin_lock(&prev->vm_mm->page_table_lock);
+ prev->vm_end = next->vm_end;
+ __vma_unlink(prev->vm_mm, next, prev);
+ spin_unlock(&prev->vm_mm->page_table_lock);
+
+ kmem_cache_free(vm_area_cachep, next);
+ prev->vm_mm->map_count--;
+ }
+out:
+ up_write(¤t->mm->mmap_sem);
+ return error;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/fixmap.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/fixmap.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,107 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ */
+
+#ifndef _ASM_FIXMAP_H
+#define _ASM_FIXMAP_H
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <asm/apicdef.h>
+#include <asm/page.h>
+#include <asm-xen/gnttab.h>
+#ifdef CONFIG_HIGHMEM
+#include <linux/threads.h>
+#include <asm/kmap_types.h>
+#endif
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process. We allocate these special addresses
+ * from the end of virtual memory (0xfffff000) backwards.
+ * Also this lets us do fail-safe vmalloc(), we
+ * can guarantee that these special addresses and
+ * vmalloc()-ed addresses never overlap.
+ *
+ * these 'compile-time allocated' memory buffers are
+ * fixed-size 4k pages. (or larger if used with an increment
+ * highger than 1) use fixmap_set(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ * TLB entries of such buffers will not be flushed across
+ * task switches.
+ */
+
+enum fixed_addresses {
+#ifdef CONFIG_HIGHMEM
+ FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */
+ FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
+#endif
+ FIX_BLKRING_BASE,
+ FIX_NETRING0_BASE,
+ FIX_NETRING1_BASE,
+ FIX_NETRING2_BASE,
+ FIX_NETRING3_BASE,
+ FIX_SHARED_INFO,
+ FIX_GNTTAB_BEGIN,
+ FIX_GNTTAB_END = FIX_GNTTAB_BEGIN + NR_GRANT_FRAMES - 1,
+#ifdef CONFIG_VGA_CONSOLE
+#define NR_FIX_BTMAPS 32 /* 128KB For the Dom0 VGA Console A0000-C0000 */
+#else
+#define NR_FIX_BTMAPS 1 /* in case anyone wants it in future... */
+#endif
+ FIX_BTMAP_END,
+ FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS - 1,
+ /* our bt_ioremap is permanent, unlike other architectures */
+
+ __end_of_permanent_fixed_addresses,
+ __end_of_fixed_addresses = __end_of_permanent_fixed_addresses
+};
+
+extern void __set_fixmap (enum fixed_addresses idx,
+ unsigned long phys, pgprot_t flags);
+
+#define set_fixmap(idx, phys) \
+ __set_fixmap(idx, phys, PAGE_KERNEL)
+/*
+ * Some hardware wants to get fixmapped without caching.
+ */
+#define set_fixmap_nocache(idx, phys) \
+ __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
+
+extern void clear_fixmap(enum fixed_addresses idx);
+
+/*
+ * used by vmalloc.c.
+ *
+ * Leave one empty page between vmalloc'ed areas and
+ * the start of the fixmap, and leave one page empty
+ * at the top of mem..
+ */
+#define FIXADDR_TOP (HYPERVISOR_VIRT_START - 2*PAGE_SIZE)
+#define __FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START (FIXADDR_TOP - __FIXADDR_SIZE)
+
+#define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT))
+
+/*
+ * 'index to address' translation. If anyone tries to use the idx
+ * directly without tranlation, we catch the bug with a NULL-deference
+ * kernel oops. Illegal ranges of incoming indices are caught too.
+ */
+static inline unsigned long fix_to_virt(unsigned int idx)
+{
+ return __fix_to_virt(idx);
+}
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/acpi/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/acpi/Makefile Fri Jul
15 13:39:50 2005
@@ -0,0 +1,20 @@
+i386-obj-$(CONFIG_ACPI_BOOT) := boot.o
+c-obj-$(CONFIG_X86_IO_APIC) := earlyquirk.o
+c-obj-$(CONFIG_ACPI_SLEEP) += sleep.o
+s-obj-$(CONFIG_ACPI_SLEEP) += wakeup.o
+
+c-link :=
+
+$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)):
+ @ln -fsn $(srctree)/arch/i386/kernel/acpi/$(notdir $@) $@
+
+$(patsubst %.o,$(obj)/%.S,$(s-obj-y) $(s-link)):
+ @ln -fsn $(srctree)/arch/x86_64/kernel/acpi/$(notdir $@) $@
+
+$(patsubst %.o,$(obj)/%.c,$(i386-obj-y)):
+ @ln -fsn $(srctree)/arch/xen/i386/kernel/acpi/$(notdir $@) $@
+
+obj-y += $(c-obj-y) $(s-obj-y) $(i386-obj-y)
+
+clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link))
+clean-files += $(patsubst %.o,%.S,$(s-obj-y) $(s-obj-) $(s-link))
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/blkfront/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/blkfront/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,3 @@
+
+obj-y := blkfront.o vbd.o
+
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/ia32/syscall32.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/ia32/syscall32.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,143 @@
+/* Copyright 2002,2003 Andi Kleen, SuSE Labs */
+
+/* vsyscall handling for 32bit processes. Map a stub page into it
+ on demand because 32bit cannot reach the kernel's fixmaps */
+
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/gfp.h>
+#include <linux/init.h>
+#include <linux/stringify.h>
+#include <asm/proto.h>
+#include <asm/tlbflush.h>
+#include <asm/ia32_unistd.h>
+
+#define USE_INT80
+
+#ifdef USE_INT80
+/* 32bit VDSOs mapped into user space. */
+asm(".section \".init.data\",\"aw\"\n"
+ "syscall32_int80:\n"
+ ".incbin \"arch/xen/x86_64/ia32/vsyscall-int80.so\"\n"
+ "syscall32_int80_end:\n"
+ "syscall32_syscall:\n"
+ ".incbin \"arch/xen/x86_64/ia32/vsyscall-syscall.so\"\n"
+ "syscall32_syscall_end:\n"
+ "syscall32_sysenter:\n"
+ ".incbin \"arch/xen/x86_64/ia32/vsyscall-sysenter.so\"\n"
+ "syscall32_sysenter_end:\n"
+ ".previous");
+
+extern unsigned char syscall32_int80[], syscall32_int80_end[];
+#else
+/* 32bit VDSOs mapped into user space. */
+asm(".section \".init.data\",\"aw\"\n"
+ "syscall32_syscall:\n"
+ ".incbin \"arch/xen/x86_64/ia32/vsyscall-syscall.so\"\n"
+ "syscall32_syscall_end:\n"
+ "syscall32_sysenter:\n"
+ ".incbin \"arch/xen/x86_64/ia32/vsyscall-sysenter.so\"\n"
+ "syscall32_sysenter_end:\n"
+ ".previous");
+
+static int use_sysenter = -1;
+#endif
+
+extern unsigned char syscall32_syscall[], syscall32_syscall_end[];
+extern unsigned char syscall32_sysenter[], syscall32_sysenter_end[];
+extern int sysctl_vsyscall32;
+
+char *syscall32_page;
+
+/*
+ * Map the 32bit vsyscall page on demand.
+ *
+ * RED-PEN: This knows too much about high level VM.
+ *
+ * Alternative would be to generate a vma with appropriate backing options
+ * and let it be handled by generic VM.
+ */
+int __map_syscall32(struct mm_struct *mm, unsigned long address)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pte_t *pte;
+ pmd_t *pmd;
+ int err = -ENOMEM;
+
+ spin_lock(&mm->page_table_lock);
+ pgd = pgd_offset(mm, address);
+ pud = pud_alloc(mm, pgd, address);
+ if (pud) {
+ pmd = pmd_alloc(mm, pud, address);
+ if (pmd && (pte = pte_alloc_map(mm, pmd, address)) != NULL) {
+ if (pte_none(*pte)) {
+ set_pte(pte,
+ mk_pte(virt_to_page(syscall32_page),
+ PAGE_KERNEL_VSYSCALL32));
+ }
+ /* Flush only the local CPU. Other CPUs taking a fault
+ will just end up here again
+ This probably not needed and just paranoia. */
+ __flush_tlb_one(address);
+ err = 0;
+ }
+ }
+ spin_unlock(&mm->page_table_lock);
+ return err;
+}
+
+int map_syscall32(struct mm_struct *mm, unsigned long address)
+{
+ int err;
+ down_read(&mm->mmap_sem);
+ err = __map_syscall32(mm, address);
+ up_read(&mm->mmap_sem);
+ return err;
+}
+
+static int __init init_syscall32(void)
+{
+ syscall32_page = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!syscall32_page)
+ panic("Cannot allocate syscall32 page");
+ SetPageReserved(virt_to_page(syscall32_page));
+
+#ifdef USE_INT80
+ /*
+ * At this point we use int 0x80.
+ */
+ memcpy(syscall32_page, syscall32_int80,
+ syscall32_int80_end - syscall32_int80);
+#else
+
+ if (use_sysenter > 0) {
+ memcpy(syscall32_page, syscall32_sysenter,
+ syscall32_sysenter_end - syscall32_sysenter);
+ } else {
+ memcpy(syscall32_page, syscall32_syscall,
+ syscall32_syscall_end - syscall32_syscall);
+ }
+#endif
+ return 0;
+}
+
+__initcall(init_syscall32);
+
+/* May not be __init: called during resume */
+void syscall32_cpu_init(void)
+{
+#ifndef USE_INT80
+ if (use_sysenter < 0)
+ use_sysenter = (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL);
+
+ /* Load these always in case some future AMD CPU supports
+ SYSENTER from compat mode too. */
+ checking_wrmsrl(MSR_IA32_SYSENTER_CS, (u64)(__KERNEL_CS | 3));
+ checking_wrmsrl(MSR_IA32_SYSENTER_ESP, 0ULL);
+ checking_wrmsrl(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
+
+ wrmsrl(MSR_CSTAR, ia32_cstar_target);
+#endif
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/io.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/io.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,457 @@
+#ifndef _ASM_IO_H
+#define _ASM_IO_H
+
+#include <linux/config.h>
+
+/*
+ * This file contains the definitions for the x86 IO instructions
+ * inb/inw/inl/outb/outw/outl and the "string versions" of the same
+ * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
+ * versions of the single-IO instructions (inb_p/inw_p/..).
+ *
+ * This file is not meant to be obfuscating: it's just complicated
+ * to (a) handle it all in a way that makes gcc able to optimize it
+ * as well as possible and (b) trying to avoid writing the same thing
+ * over and over again with slight variations and possibly making a
+ * mistake somewhere.
+ */
+
+/*
+ * Thanks to James van Artsdalen for a better timing-fix than
+ * the two short jumps: using outb's to a nonexistent port seems
+ * to guarantee better timings even on fast machines.
+ *
+ * On the other hand, I'd like to be sure of a non-existent port:
+ * I feel a bit unsafe about using 0x80 (should be safe, though)
+ *
+ * Linus
+ */
+
+ /*
+ * Bit simplified and optimized by Jan Hubicka
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
+ *
+ * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
+ * isa_read[wl] and isa_write[wl] fixed
+ * - Arnaldo Carvalho de Melo <acme@xxxxxxxxxxxxxxxx>
+ */
+
+#define IO_SPACE_LIMIT 0xffff
+
+#define XQUAD_PORTIO_BASE 0xfe400000
+#define XQUAD_PORTIO_QUAD 0x40000 /* 256k per quad. */
+#define XQUAD_PORTIO_LEN 0x80000 /* Only remapping first 2 quads */
+
+#ifdef __KERNEL__
+
+#include <linux/vmalloc.h>
+
+/*
+ * Temporary debugging check to catch old code using
+ * unmapped ISA addresses. Will be removed in 2.4.
+ */
+#if CONFIG_DEBUG_IOVIRT
+ extern void *__io_virt_debug(unsigned long x, const char *file, int line);
+ extern unsigned long __io_phys_debug(unsigned long x, const char *file, int
line);
+ #define __io_virt(x) __io_virt_debug((unsigned long)(x), __FILE__, __LINE__)
+//#define __io_phys(x) __io_phys_debug((unsigned long)(x), __FILE__, __LINE__)
+#else
+ #define __io_virt(x) ((void *)(x))
+//#define __io_phys(x) __pa(x)
+#endif
+
+/**
+ * virt_to_phys - map virtual addresses to physical
+ * @address: address to remap
+ *
+ * The returned physical address is the physical (CPU) mapping for
+ * the memory address given. It is only valid to use this function on
+ * addresses directly mapped or allocated via kmalloc.
+ *
+ * This function does not give bus mappings for DMA transfers. In
+ * almost all conceivable cases a device driver should not be using
+ * this function
+ */
+
+static inline unsigned long virt_to_phys(volatile void * address)
+{
+ return __pa(address);
+}
+
+/**
+ * phys_to_virt - map physical address to virtual
+ * @address: address to remap
+ *
+ * The returned virtual address is a current CPU mapping for
+ * the memory address given. It is only valid to use this function on
+ * addresses that have a kernel mapping
+ *
+ * This function does not handle bus mappings for DMA transfers. In
+ * almost all conceivable cases a device driver should not be using
+ * this function
+ */
+
+static inline void * phys_to_virt(unsigned long address)
+{
+ return __va(address);
+}
+
+/*
+ * We define page_to_phys 'incorrectly' because it is used when merging blkdev
+ * requests, and the correct thing to do there is to use machine addresses.
+ */
+#define page_to_phys(_x) phys_to_machine(((_x) - mem_map) << PAGE_SHIFT)
+
+extern void * __ioremap(unsigned long offset, unsigned long size, unsigned
long flags);
+
+/**
+ * ioremap - map bus memory into CPU space
+ * @offset: bus address of the memory
+ * @size: size of the resource to map
+ *
+ * ioremap performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ */
+
+static inline void * ioremap (unsigned long offset, unsigned long size)
+{
+ return __ioremap(offset, size, 0);
+}
+
+/**
+ * ioremap_nocache - map bus memory into CPU space
+ * @offset: bus address of the memory
+ * @size: size of the resource to map
+ *
+ * ioremap_nocache performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * This version of ioremap ensures that the memory is marked uncachable
+ * on the CPU as well as honouring existing caching rules from things like
+ * the PCI bus. Note that there are other caches and buffers on many
+ * busses. In paticular driver authors should read up on PCI writes
+ *
+ * It's useful if some control registers are in such an area and
+ * write combining or read caching is not desirable:
+ */
+
+static inline void * ioremap_nocache (unsigned long offset, unsigned long size)
+{
+ return __ioremap(offset, size, _PAGE_PCD);
+}
+
+extern void iounmap(void *addr);
+
+/*
+ * bt_ioremap() and bt_iounmap() are for temporary early boot-time
+ * mappings, before the real ioremap() is functional.
+ * A boot-time mapping is currently limited to at most 16 pages.
+ */
+extern void *bt_ioremap(unsigned long offset, unsigned long size);
+extern void bt_iounmap(void *addr, unsigned long size);
+
+#define virt_to_bus(_x) phys_to_machine(virt_to_phys(_x))
+#define bus_to_virt(_x) phys_to_virt(machine_to_phys(_x))
+#define page_to_bus(_x) phys_to_machine(((_x) - mem_map) << PAGE_SHIFT)
+#define bus_to_phys(_x) machine_to_phys(_x)
+#define bus_to_page(_x) (mem_map + (bus_to_phys(_x) >> PAGE_SHIFT))
+
+/*
+ * readX/writeX() are used to access memory mapped devices. On some
+ * architectures the memory mapped IO stuff needs to be accessed
+ * differently. On the x86 architecture, we just read/write the
+ * memory location directly.
+ */
+
+#define readb(addr) (*(volatile unsigned char *) __io_virt(addr))
+#define readw(addr) (*(volatile unsigned short *) __io_virt(addr))
+#define readl(addr) (*(volatile unsigned int *) __io_virt(addr))
+#define __raw_readb readb
+#define __raw_readw readw
+#define __raw_readl readl
+
+#define writeb(b,addr) (*(volatile unsigned char *) __io_virt(addr) = (b))
+#define writew(b,addr) (*(volatile unsigned short *) __io_virt(addr) = (b))
+#define writel(b,addr) (*(volatile unsigned int *) __io_virt(addr) = (b))
+#define __raw_writeb writeb
+#define __raw_writew writew
+#define __raw_writel writel
+
+#define memset_io(a,b,c) __memset(__io_virt(a),(b),(c))
+#define memcpy_fromio(a,b,c) __memcpy((a),__io_virt(b),(c))
+#define memcpy_toio(a,b,c) __memcpy(__io_virt(a),(b),(c))
+
+/*
+ * ISA space is 'always mapped' on a typical x86 system, no need to
+ * explicitly ioremap() it. The fact that the ISA IO space is mapped
+ * to PAGE_OFFSET is pure coincidence - it does not mean ISA values
+ * are physical addresses. The following constant pointer can be
+ * used as the IO-area pointer (it can be iounmapped as well, so the
+ * analogy with PCI is quite large):
+ */
+#define __ISA_IO_base ((char *)(PAGE_OFFSET))
+
+#define isa_readb(a) readb(__ISA_IO_base + (a))
+#define isa_readw(a) readw(__ISA_IO_base + (a))
+#define isa_readl(a) readl(__ISA_IO_base + (a))
+#define isa_writeb(b,a) writeb(b,__ISA_IO_base + (a))
+#define isa_writew(w,a) writew(w,__ISA_IO_base + (a))
+#define isa_writel(l,a) writel(l,__ISA_IO_base + (a))
+#define isa_memset_io(a,b,c) memset_io(__ISA_IO_base + (a),(b),(c))
+#define isa_memcpy_fromio(a,b,c) memcpy_fromio((a),__ISA_IO_base +
(b),(c))
+#define isa_memcpy_toio(a,b,c) memcpy_toio(__ISA_IO_base + (a),(b),(c))
+
+
+/*
+ * Again, i386 does not require mem IO specific function.
+ */
+
+#define eth_io_copy_and_sum(a,b,c,d)
eth_copy_and_sum((a),__io_virt(b),(c),(d))
+#define isa_eth_io_copy_and_sum(a,b,c,d)
eth_copy_and_sum((a),__io_virt(__ISA_IO_base + (b)),(c),(d))
+
+/**
+ * check_signature - find BIOS signatures
+ * @io_addr: mmio address to check
+ * @signature: signature block
+ * @length: length of signature
+ *
+ * Perform a signature comparison with the mmio address io_addr. This
+ * address should have been obtained by ioremap.
+ * Returns 1 on a match.
+ */
+
+static inline int check_signature(unsigned long io_addr,
+ const unsigned char *signature, int length)
+{
+ int retval = 0;
+ do {
+ if (readb(io_addr) != *signature)
+ goto out;
+ io_addr++;
+ signature++;
+ length--;
+ } while (length);
+ retval = 1;
+out:
+ return retval;
+}
+
+/**
+ * isa_check_signature - find BIOS signatures
+ * @io_addr: mmio address to check
+ * @signature: signature block
+ * @length: length of signature
+ *
+ * Perform a signature comparison with the ISA mmio address io_addr.
+ * Returns 1 on a match.
+ *
+ * This function is deprecated. New drivers should use ioremap and
+ * check_signature.
+ */
+
+
+static inline int isa_check_signature(unsigned long io_addr,
+ const unsigned char *signature, int length)
+{
+ int retval = 0;
+ do {
+ if (isa_readb(io_addr) != *signature)
+ goto out;
+ io_addr++;
+ signature++;
+ length--;
+ } while (length);
+ retval = 1;
+out:
+ return retval;
+}
+
+/*
+ * Cache management
+ *
+ * This needed for two cases
+ * 1. Out of order aware processors
+ * 2. Accidentally out of order processors (PPro errata #51)
+ */
+
+#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+
+static inline void flush_write_buffers(void)
+{
+ __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory");
+}
+
+#define dma_cache_inv(_start,_size) flush_write_buffers()
+#define dma_cache_wback(_start,_size) flush_write_buffers()
+#define dma_cache_wback_inv(_start,_size) flush_write_buffers()
+
+#else
+
+/* Nothing to do */
+
+#define dma_cache_inv(_start,_size) do { } while (0)
+#define dma_cache_wback(_start,_size) do { } while (0)
+#define dma_cache_wback_inv(_start,_size) do { } while (0)
+#define flush_write_buffers()
+
+#endif
+
+#endif /* __KERNEL__ */
+
+#ifdef SLOW_IO_BY_JUMPING
+#define __SLOW_DOWN_IO "\njmp 1f\n1:\tjmp 1f\n1:"
+#elif defined(__UNSAFE_IO__)
+#define __SLOW_DOWN_IO "\noutb %%al,$0x80"
+#else
+#define __SLOW_DOWN_IO "\n1: outb %%al,$0x80\n" \
+ "2:\n" \
+ ".section __ex_table,\"a\"\n\t" \
+ ".align 4\n\t" \
+ ".long 1b,2b\n" \
+ ".previous"
+#endif
+
+#ifdef REALLY_SLOW_IO
+#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO
__SLOW_DOWN_IO
+#else
+#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO
+#endif
+
+#ifdef CONFIG_MULTIQUAD
+extern void *xquad_portio; /* Where the IO area was mapped */
+#endif /* CONFIG_MULTIQUAD */
+
+/*
+ * Talk about misusing macros..
+ */
+#define __OUT1(s,x) \
+static inline void out##s(unsigned x value, unsigned short port) {
+
+#ifdef __UNSAFE_IO__
+#define __OUT2(s,s1,s2) \
+__asm__ __volatile__ ("out" #s " %" s1 "0,%" s2 "1"
+#else
+#define __OUT2(s,s1,s2) \
+__asm__ __volatile__ ("1: out" #s " %" s1 "0,%" s2 "1\n" \
+ "2:\n" \
+ ".section __ex_table,\"a\"\n\t" \
+ ".align 4\n\t" \
+ ".long 1b,2b\n" \
+ ".previous"
+#endif
+
+#if defined (CONFIG_MULTIQUAD) && !defined(STANDALONE)
+#define __OUTQ(s,ss,x) /* Do the equivalent of the portio op on quads */ \
+static inline void out##ss(unsigned x value, unsigned short port) { \
+ if (xquad_portio) \
+ write##s(value, (unsigned long) xquad_portio + port); \
+ else /* We're still in early boot, running on quad 0 */ \
+ out##ss##_local(value, port); \
+} \
+static inline void out##ss##_quad(unsigned x value, unsigned short port, int
quad) { \
+ if (xquad_portio) \
+ write##s(value, (unsigned long) xquad_portio +
(XQUAD_PORTIO_QUAD*quad)\
+ + port); \
+}
+
+#define __INQ(s,ss) /* Do the equivalent of the portio op on quads */ \
+static inline RETURN_TYPE in##ss(unsigned short port) { \
+ if (xquad_portio) \
+ return read##s((unsigned long) xquad_portio + port); \
+ else /* We're still in early boot, running on quad 0 */ \
+ return in##ss##_local(port); \
+} \
+static inline RETURN_TYPE in##ss##_quad(unsigned short port, int quad) { \
+ if (xquad_portio) \
+ return read##s((unsigned long) xquad_portio +
(XQUAD_PORTIO_QUAD*quad)\
+ + port); \
+ else\
+ return 0;\
+}
+#endif /* CONFIG_MULTIQUAD && !STANDALONE */
+
+#if !defined(CONFIG_MULTIQUAD) || defined(STANDALONE)
+#define __OUT(s,s1,x) \
+__OUT1(s,x) __OUT2(s,s1,"w") : : "a" (value), "Nd" (port)); } \
+__OUT1(s##_p,x) __OUT2(s,s1,"w") __FULL_SLOW_DOWN_IO : : "a" (value), "Nd"
(port));}
+#else
+/* Make the default portio routines operate on quad 0 */
+#define __OUT(s,s1,x) \
+__OUT1(s##_local,x) __OUT2(s,s1,"w") : : "a" (value), "Nd" (port)); } \
+__OUT1(s##_p_local,x) __OUT2(s,s1,"w") __FULL_SLOW_DOWN_IO : : "a" (value),
"Nd" (port));} \
+__OUTQ(s,s,x) \
+__OUTQ(s,s##_p,x)
+#endif /* !CONFIG_MULTIQUAD || STANDALONE */
+
+#define __IN1(s) \
+static inline RETURN_TYPE in##s(unsigned short port) { RETURN_TYPE _v;
+
+#ifdef __UNSAFE_IO__
+#define __IN2(s,s1,s2) \
+__asm__ __volatile__ ("in" #s " %" s2 "1,%" s1 "0"
+#else
+#define __IN2(s,s1,s2) \
+__asm__ __volatile__ ("1: in" #s " %" s2 "1,%" s1 "0\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: mov" #s " $~0,%" s1 "0\n\t" \
+ "jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n\t" \
+ ".align 4\n\t" \
+ ".long 1b,3b\n" \
+ ".previous"
+#endif
+
+#if !defined(CONFIG_MULTIQUAD) || defined(STANDALONE)
+#define __IN(s,s1,i...) \
+__IN1(s) __IN2(s,s1,"w") : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \
+__IN1(s##_p) __IN2(s,s1,"w") __FULL_SLOW_DOWN_IO : "=a" (_v) : "Nd" (port)
,##i ); return _v; }
+#else
+/* Make the default portio routines operate on quad 0 */
+#define __IN(s,s1,i...) \
+__IN1(s##_local) __IN2(s,s1,"w") : "=a" (_v) : "Nd" (port) ,##i ); return _v;
} \
+__IN1(s##_p_local) __IN2(s,s1,"w") __FULL_SLOW_DOWN_IO : "=a" (_v) : "Nd"
(port) ,##i ); return _v; } \
+__INQ(s,s) \
+__INQ(s,s##_p)
+#endif /* !CONFIG_MULTIQUAD || STANDALONE */
+
+#define __INS(s) \
+static inline void ins##s(unsigned short port, void * addr, unsigned long
count) \
+{ __asm__ __volatile__ ("rep ; ins" #s \
+: "=D" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); }
+
+#define __OUTS(s) \
+static inline void outs##s(unsigned short port, const void * addr, unsigned
long count) \
+{ __asm__ __volatile__ ("rep ; outs" #s \
+: "=S" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); }
+
+#define RETURN_TYPE unsigned char
+__IN(b,"")
+#undef RETURN_TYPE
+#define RETURN_TYPE unsigned short
+__IN(w,"")
+#undef RETURN_TYPE
+#define RETURN_TYPE unsigned int
+__IN(l,"")
+#undef RETURN_TYPE
+
+__OUT(b,"b",char)
+__OUT(w,"w",short)
+__OUT(l,,int)
+
+__INS(b)
+__INS(w)
+__INS(l)
+
+__OUTS(b)
+__OUTS(w)
+__OUTS(l)
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/mm/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/mm/Makefile Fri Jul 15 13:39:50 2005
@@ -0,0 +1,24 @@
+#
+# Makefile for the linux i386-specific parts of the memory manager.
+#
+
+XENARCH := $(subst ",,$(CONFIG_XENARCH))
+
+CFLAGS += -Iarch/$(XENARCH)/mm
+
+obj-y := init.o pgtable.o fault.o ioremap.o hypervisor.o
+c-obj-y := extable.o mmap.o pageattr.o
+
+c-obj-$(CONFIG_DISCONTIGMEM) += discontig.o
+c-obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+obj-$(CONFIG_HIGHMEM) += highmem.o
+c-obj-$(CONFIG_BOOT_IOREMAP) += boot_ioremap.o
+
+c-link :=
+
+$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)):
+ @ln -fsn $(srctree)/arch/i386/mm/$(notdir $@) $@
+
+obj-y += $(c-obj-y)
+
+clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link))
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/pci-dma.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/pci-dma.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,154 @@
+/*
+ * Dynamic DMA mapping support.
+ *
+ * On i386 there is no hardware dynamic DMA address translation,
+ * so consistent alloc/free are merely page allocation/freeing.
+ * The rest of the dynamic DMA mapping interface is implemented
+ * in asm/pci.h.
+ */
+
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/pci.h>
+#include <linux/version.h>
+#include <asm/io.h>
+#include <asm-xen/balloon.h>
+#include <asm/tlbflush.h>
+
+struct dma_coherent_mem {
+ void *virt_base;
+ u32 device_base;
+ int size;
+ int flags;
+ unsigned long *bitmap;
+};
+
+void *dma_alloc_coherent(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, int gfp)
+{
+ void *ret;
+ struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+ unsigned int order = get_order(size);
+ unsigned long vstart;
+ /* ignore region specifiers */
+ gfp &= ~(__GFP_DMA | __GFP_HIGHMEM);
+
+ if (mem) {
+ int page = bitmap_find_free_region(mem->bitmap, mem->size,
+ order);
+ if (page >= 0) {
+ *dma_handle = mem->device_base + (page << PAGE_SHIFT);
+ ret = mem->virt_base + (page << PAGE_SHIFT);
+ memset(ret, 0, size);
+ return ret;
+ }
+ if (mem->flags & DMA_MEMORY_EXCLUSIVE)
+ return NULL;
+ }
+
+ if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff))
+ gfp |= GFP_DMA;
+
+ vstart = __get_free_pages(gfp, order);
+ ret = (void *)vstart;
+
+ if (ret != NULL) {
+ xen_contig_memory(vstart, order);
+
+ memset(ret, 0, size);
+ *dma_handle = virt_to_bus(ret);
+ }
+ return ret;
+}
+
+void dma_free_coherent(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle)
+{
+ struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+ int order = get_order(size);
+
+ if (mem && vaddr >= mem->virt_base && vaddr < (mem->virt_base +
(mem->size << PAGE_SHIFT))) {
+ int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+
+ bitmap_release_region(mem->bitmap, page, order);
+ } else
+ free_pages((unsigned long)vaddr, order);
+}
+
+int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
+ dma_addr_t device_addr, size_t size, int flags)
+{
+ void __iomem *mem_base;
+ int pages = size >> PAGE_SHIFT;
+ int bitmap_size = (pages + 31)/32;
+
+ if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
+ goto out;
+ if (!size)
+ goto out;
+ if (dev->dma_mem)
+ goto out;
+
+ /* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
+
+ mem_base = ioremap(bus_addr, size);
+ if (!mem_base)
+ goto out;
+
+ dev->dma_mem = kmalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
+ if (!dev->dma_mem)
+ goto out;
+ memset(dev->dma_mem, 0, sizeof(struct dma_coherent_mem));
+ dev->dma_mem->bitmap = kmalloc(bitmap_size, GFP_KERNEL);
+ if (!dev->dma_mem->bitmap)
+ goto free1_out;
+ memset(dev->dma_mem->bitmap, 0, bitmap_size);
+
+ dev->dma_mem->virt_base = mem_base;
+ dev->dma_mem->device_base = device_addr;
+ dev->dma_mem->size = pages;
+ dev->dma_mem->flags = flags;
+
+ if (flags & DMA_MEMORY_MAP)
+ return DMA_MEMORY_MAP;
+
+ return DMA_MEMORY_IO;
+
+ free1_out:
+ kfree(dev->dma_mem->bitmap);
+ out:
+ return 0;
+}
+EXPORT_SYMBOL(dma_declare_coherent_memory);
+
+void dma_release_declared_memory(struct device *dev)
+{
+ struct dma_coherent_mem *mem = dev->dma_mem;
+
+ if(!mem)
+ return;
+ dev->dma_mem = NULL;
+ iounmap(mem->virt_base);
+ kfree(mem->bitmap);
+ kfree(mem);
+}
+EXPORT_SYMBOL(dma_release_declared_memory);
+
+void *dma_mark_declared_memory_occupied(struct device *dev,
+ dma_addr_t device_addr, size_t size)
+{
+ struct dma_coherent_mem *mem = dev->dma_mem;
+ int pages = (size + (device_addr & ~PAGE_MASK) + PAGE_SIZE - 1) >>
PAGE_SHIFT;
+ int pos, err;
+
+ if (!mem)
+ return ERR_PTR(-EINVAL);
+
+ pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
+ err = bitmap_allocate_region(mem->bitmap, pos, get_order(pages));
+ if (err != 0)
+ return ERR_PTR(err);
+ return mem->virt_base + (pos << PAGE_SHIFT);
+}
+EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/configs/xen0_defconfig_x86_64
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/configs/xen0_defconfig_x86_64 Fri Jul
15 13:39:50 2005
@@ -0,0 +1,1023 @@
+#
+# Automatically generated make config: don't edit
+# Linux kernel version: 2.6.11.1-xen0
+# Tue May 10 11:07:02 2005
+#
+CONFIG_XEN=y
+CONFIG_ARCH_XEN=y
+CONFIG_NO_IDLE_HZ=y
+
+#
+# XEN
+#
+CONFIG_XEN_PRIVILEGED_GUEST=y
+CONFIG_XEN_PHYSDEV_ACCESS=y
+CONFIG_XEN_BLKDEV_BACKEND=y
+# CONFIG_XEN_BLKDEV_TAP_BE is not set
+CONFIG_XEN_BLKDEV_GRANT=y
+CONFIG_XEN_NETDEV_BACKEND=y
+CONFIG_XEN_BLKDEV_FRONTEND=y
+CONFIG_XEN_NETDEV_FRONTEND=y
+# CONFIG_XEN_NETDEV_FRONTEND_PIPELINED_TRANSMITTER is not set
+# CONFIG_XEN_BLKDEV_TAP is not set
+# CONFIG_XEN_SHADOW_MODE is not set
+CONFIG_XEN_SCRUB_PAGES=y
+# CONFIG_XEN_X86 is not set
+CONFIG_XEN_X86_64=y
+CONFIG_HAVE_ARCH_DEV_ALLOC_SKB=y
+
+#
+# Code maturity level options
+#
+CONFIG_EXPERIMENTAL=y
+# CONFIG_CLEAN_COMPILE is not set
+CONFIG_BROKEN=y
+CONFIG_BROKEN_ON_SMP=y
+
+#
+# General setup
+#
+CONFIG_LOCALVERSION=""
+CONFIG_SWAP=y
+CONFIG_SYSVIPC=y
+# CONFIG_POSIX_MQUEUE is not set
+# CONFIG_BSD_PROCESS_ACCT is not set
+CONFIG_SYSCTL=y
+# CONFIG_AUDIT is not set
+CONFIG_LOG_BUF_SHIFT=14
+# CONFIG_HOTPLUG is not set
+CONFIG_KOBJECT_UEVENT=y
+# CONFIG_IKCONFIG is not set
+# CONFIG_EMBEDDED is not set
+CONFIG_KALLSYMS=y
+# CONFIG_KALLSYMS_EXTRA_PASS is not set
+CONFIG_FUTEX=y
+CONFIG_EPOLL=y
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
+CONFIG_SHMEM=y
+CONFIG_CC_ALIGN_FUNCTIONS=0
+CONFIG_CC_ALIGN_LABELS=0
+CONFIG_CC_ALIGN_LOOPS=0
+CONFIG_CC_ALIGN_JUMPS=0
+# CONFIG_TINY_SHMEM is not set
+
+#
+# Loadable module support
+#
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_MODULE_FORCE_UNLOAD is not set
+CONFIG_OBSOLETE_MODPARM=y
+# CONFIG_MODVERSIONS is not set
+# CONFIG_MODULE_SRCVERSION_ALL is not set
+CONFIG_KMOD=y
+CONFIG_XENARCH="x86_64"
+CONFIG_X86=y
+CONFIG_MMU=y
+CONFIG_GENERIC_ISA_DMA=y
+CONFIG_GENERIC_IOMAP=y
+CONFIG_X86_CMPXCHG=y
+CONFIG_X86_L1_CACHE_SHIFT=7
+CONFIG_RWSEM_GENERIC_SPINLOCK=y
+CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_X86_GOOD_APIC=y
+# CONFIG_HPET_TIMER is not set
+# CONFIG_SMP is not set
+# CONFIG_PREEMPT is not set
+# CONFIG_MICROCODE is not set
+# CONFIG_X86_CPUID is not set
+# CONFIG_NUMA is not set
+# CONFIG_MTRR is not set
+CONFIG_X86_LOCAL_APIC=y
+CONFIG_X86_IO_APIC=y
+CONFIG_PCI=y
+CONFIG_PCI_DIRECT=y
+# CONFIG_PCI_MMCONFIG is not set
+CONFIG_EARLY_PRINTK=y
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_IRQ_PROBE=y
+
+#
+# X86_64 processor configuration
+#
+CONFIG_X86_64=y
+CONFIG_64BIT=y
+
+#
+# Processor type and features
+#
+# CONFIG_MPSC is not set
+CONFIG_GENERIC_CPU=y
+CONFIG_X86_L1_CACHE_BYTES=128
+# CONFIG_X86_TSC is not set
+# CONFIG_X86_MSR is not set
+# CONFIG_GART_IOMMU is not set
+CONFIG_DUMMY_IOMMU=y
+# CONFIG_X86_MCE is not set
+
+#
+# Power management options
+#
+# CONFIG_PM is not set
+
+#
+# CPU Frequency scaling
+#
+# CONFIG_CPU_FREQ is not set
+
+#
+# Bus options (PCI etc.)
+#
+# CONFIG_UNORDERED_IO is not set
+
+#
+# Executable file formats / Emulations
+#
+CONFIG_IA32_EMULATION=y
+# CONFIG_IA32_AOUT is not set
+#
+# Executable file formats
+#
+CONFIG_BINFMT_ELF=y
+CONFIG_BINFMT_MISC=y
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+CONFIG_STANDALONE=y
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FW_LOADER is not set
+
+#
+# Memory Technology Devices (MTD)
+#
+# CONFIG_MTD is not set
+
+#
+# Parallel port support
+#
+# CONFIG_PARPORT is not set
+
+#
+# Plug and Play support
+#
+# CONFIG_PNP is not set
+
+#
+# Block devices
+#
+CONFIG_BLK_DEV_FD=y
+# CONFIG_BLK_CPQ_DA is not set
+CONFIG_BLK_CPQ_CISS_DA=y
+# CONFIG_CISS_SCSI_TAPE is not set
+# CONFIG_BLK_DEV_DAC960 is not set
+# CONFIG_BLK_DEV_UMEM is not set
+# CONFIG_BLK_DEV_COW_COMMON is not set
+CONFIG_BLK_DEV_LOOP=y
+# CONFIG_BLK_DEV_CRYPTOLOOP is not set
+# CONFIG_BLK_DEV_NBD is not set
+# CONFIG_BLK_DEV_SX8 is not set
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=16
+CONFIG_BLK_DEV_RAM_SIZE=16384
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE=""
+# CONFIG_LBD is not set
+# CONFIG_CDROM_PKTCDVD is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+# CONFIG_ATA_OVER_ETH is not set
+
+#
+# ATA/ATAPI/MFM/RLL support
+#
+CONFIG_IDE=y
+CONFIG_BLK_DEV_IDE=y
+
+#
+# Please see Documentation/ide.txt for help/info on IDE drives
+#
+# CONFIG_BLK_DEV_IDE_SATA is not set
+# CONFIG_BLK_DEV_HD_IDE is not set
+CONFIG_BLK_DEV_IDEDISK=y
+# CONFIG_IDEDISK_MULTI_MODE is not set
+CONFIG_BLK_DEV_IDECD=y
+# CONFIG_BLK_DEV_IDETAPE is not set
+# CONFIG_BLK_DEV_IDEFLOPPY is not set
+# CONFIG_BLK_DEV_IDESCSI is not set
+# CONFIG_IDE_TASK_IOCTL is not set
+
+#
+# IDE chipset support/bugfixes
+#
+CONFIG_IDE_GENERIC=y
+# CONFIG_BLK_DEV_CMD640 is not set
+CONFIG_BLK_DEV_IDEPCI=y
+# CONFIG_IDEPCI_SHARE_IRQ is not set
+# CONFIG_BLK_DEV_OFFBOARD is not set
+CONFIG_BLK_DEV_GENERIC=y
+# CONFIG_BLK_DEV_OPTI621 is not set
+# CONFIG_BLK_DEV_RZ1000 is not set
+CONFIG_BLK_DEV_IDEDMA_PCI=y
+# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
+CONFIG_IDEDMA_PCI_AUTO=y
+# CONFIG_IDEDMA_ONLYDISK is not set
+# CONFIG_BLK_DEV_AEC62XX is not set
+# CONFIG_BLK_DEV_ALI15X3 is not set
+# CONFIG_BLK_DEV_AMD74XX is not set
+# CONFIG_BLK_DEV_ATIIXP is not set
+# CONFIG_BLK_DEV_CMD64X is not set
+# CONFIG_BLK_DEV_TRIFLEX is not set
+# CONFIG_BLK_DEV_CY82C693 is not set
+# CONFIG_BLK_DEV_CS5520 is not set
+# CONFIG_BLK_DEV_CS5530 is not set
+# CONFIG_BLK_DEV_HPT34X is not set
+# CONFIG_BLK_DEV_HPT366 is not set
+# CONFIG_BLK_DEV_SC1200 is not set
+CONFIG_BLK_DEV_PIIX=y
+# CONFIG_BLK_DEV_NS87415 is not set
+# CONFIG_BLK_DEV_PDC202XX_OLD is not set
+# CONFIG_BLK_DEV_PDC202XX_NEW is not set
+CONFIG_BLK_DEV_SVWKS=y
+# CONFIG_BLK_DEV_SIIMAGE is not set
+# CONFIG_BLK_DEV_SIS5513 is not set
+# CONFIG_BLK_DEV_SLC90E66 is not set
+# CONFIG_BLK_DEV_TRM290 is not set
+# CONFIG_BLK_DEV_VIA82CXXX is not set
+# CONFIG_IDE_ARM is not set
+CONFIG_BLK_DEV_IDEDMA=y
+# CONFIG_IDEDMA_IVB is not set
+CONFIG_IDEDMA_AUTO=y
+# CONFIG_BLK_DEV_HD is not set
+
+#
+# SCSI device support
+#
+CONFIG_SCSI=y
+CONFIG_SCSI_PROC_FS=y
+
+#
+# SCSI support type (disk, tape, CD-ROM)
+#
+CONFIG_BLK_DEV_SD=y
+# CONFIG_CHR_DEV_ST is not set
+# CONFIG_CHR_DEV_OSST is not set
+# CONFIG_BLK_DEV_SR is not set
+# CONFIG_CHR_DEV_SG is not set
+
+#
+# Some SCSI devices (e.g. CD jukebox) support multiple LUNs
+#
+# CONFIG_SCSI_MULTI_LUN is not set
+# CONFIG_SCSI_CONSTANTS is not set
+# CONFIG_SCSI_LOGGING is not set
+
+#
+# SCSI Transport Attributes
+#
+# CONFIG_SCSI_SPI_ATTRS is not set
+# CONFIG_SCSI_FC_ATTRS is not set
+# CONFIG_SCSI_ISCSI_ATTRS is not set
+
+#
+# SCSI low-level drivers
+#
+CONFIG_BLK_DEV_3W_XXXX_RAID=y
+# CONFIG_SCSI_3W_9XXX is not set
+# CONFIG_SCSI_ACARD is not set
+CONFIG_SCSI_AACRAID=y
+CONFIG_SCSI_AIC7XXX=y
+CONFIG_AIC7XXX_CMDS_PER_DEVICE=32
+CONFIG_AIC7XXX_RESET_DELAY_MS=15000
+# CONFIG_AIC7XXX_BUILD_FIRMWARE is not set
+CONFIG_AIC7XXX_DEBUG_ENABLE=y
+CONFIG_AIC7XXX_DEBUG_MASK=0
+CONFIG_AIC7XXX_REG_PRETTY_PRINT=y
+# CONFIG_SCSI_AIC7XXX_OLD is not set
+CONFIG_SCSI_AIC79XX=y
+CONFIG_AIC79XX_CMDS_PER_DEVICE=32
+CONFIG_AIC79XX_RESET_DELAY_MS=15000
+# CONFIG_AIC79XX_BUILD_FIRMWARE is not set
+# CONFIG_AIC79XX_ENABLE_RD_STRM is not set
+CONFIG_AIC79XX_DEBUG_ENABLE=y
+CONFIG_AIC79XX_DEBUG_MASK=0
+CONFIG_AIC79XX_REG_PRETTY_PRINT=y
+# CONFIG_SCSI_ADVANSYS is not set
+CONFIG_MEGARAID_NEWGEN=y
+# CONFIG_MEGARAID_MM is not set
+CONFIG_SCSI_SATA=y
+# CONFIG_SCSI_SATA_AHCI is not set
+# CONFIG_SCSI_SATA_SVW is not set
+CONFIG_SCSI_ATA_PIIX=y
+# CONFIG_SCSI_SATA_NV is not set
+CONFIG_SCSI_SATA_PROMISE=y
+# CONFIG_SCSI_SATA_QSTOR is not set
+CONFIG_SCSI_SATA_SX4=y
+CONFIG_SCSI_SATA_SIL=y
+# CONFIG_SCSI_SATA_SIS is not set
+# CONFIG_SCSI_SATA_ULI is not set
+# CONFIG_SCSI_SATA_VIA is not set
+# CONFIG_SCSI_SATA_VITESSE is not set
+CONFIG_SCSI_BUSLOGIC=y
+# CONFIG_SCSI_OMIT_FLASHPOINT is not set
+# CONFIG_SCSI_CPQFCTS is not set
+# CONFIG_SCSI_DMX3191D is not set
+# CONFIG_SCSI_EATA is not set
+# CONFIG_SCSI_EATA_PIO is not set
+# CONFIG_SCSI_FUTURE_DOMAIN is not set
+# CONFIG_SCSI_GDTH is not set
+# CONFIG_SCSI_IPS is not set
+# CONFIG_SCSI_INITIO is not set
+# CONFIG_SCSI_INIA100 is not set
+# CONFIG_SCSI_SYM53C8XX_2 is not set
+# CONFIG_SCSI_IPR is not set
+# CONFIG_SCSI_PCI2000 is not set
+# CONFIG_SCSI_PCI2220I is not set
+# CONFIG_SCSI_QLOGIC_ISP is not set
+# CONFIG_SCSI_QLOGIC_FC is not set
+# CONFIG_SCSI_QLOGIC_1280 is not set
+CONFIG_SCSI_QLA2XXX=y
+# CONFIG_SCSI_QLA21XX is not set
+# CONFIG_SCSI_QLA22XX is not set
+# CONFIG_SCSI_QLA2300 is not set
+# CONFIG_SCSI_QLA2322 is not set
+# CONFIG_SCSI_QLA6312 is not set
+# CONFIG_SCSI_DC395x is not set
+# CONFIG_SCSI_DC390T is not set
+# CONFIG_SCSI_DEBUG is not set
+
+#
+# Multi-device support (RAID and LVM)
+#
+# CONFIG_MD is not set
+
+#
+# Fusion MPT device support
+#
+CONFIG_FUSION=y
+CONFIG_FUSION_MAX_SGE=40
+# CONFIG_FUSION_CTL is not set
+
+#
+# IEEE 1394 (FireWire) support
+#
+# CONFIG_IEEE1394 is not set
+
+#
+# I2O device support
+#
+# CONFIG_I2O is not set
+
+#
+# Networking support
+#
+CONFIG_NET=y
+
+#
+# Networking options
+#
+CONFIG_PACKET=y
+# CONFIG_PACKET_MMAP is not set
+# CONFIG_NETLINK_DEV is not set
+CONFIG_UNIX=y
+# CONFIG_NET_KEY is not set
+CONFIG_INET=y
+# CONFIG_IP_MULTICAST is not set
+# CONFIG_IP_ADVANCED_ROUTER is not set
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+# CONFIG_IP_PNP_BOOTP is not set
+# CONFIG_IP_PNP_RARP is not set
+# CONFIG_NET_IPIP is not set
+# CONFIG_NET_IPGRE is not set
+# CONFIG_ARPD is not set
+# CONFIG_SYN_COOKIES is not set
+# CONFIG_INET_AH is not set
+# CONFIG_INET_ESP is not set
+# CONFIG_INET_IPCOMP is not set
+# CONFIG_INET_TUNNEL is not set
+CONFIG_IP_TCPDIAG=y
+# CONFIG_IP_TCPDIAG_IPV6 is not set
+
+#
+# IP: Virtual Server Configuration
+#
+# CONFIG_IP_VS is not set
+# CONFIG_IPV6 is not set
+CONFIG_NETFILTER=y
+# CONFIG_NETFILTER_DEBUG is not set
+CONFIG_BRIDGE_NETFILTER=y
+
+#
+# IP: Netfilter Configuration
+#
+CONFIG_IP_NF_CONNTRACK=m
+CONFIG_IP_NF_CT_ACCT=y
+# CONFIG_IP_NF_CONNTRACK_MARK is not set
+# CONFIG_IP_NF_CT_PROTO_SCTP is not set
+CONFIG_IP_NF_FTP=m
+# CONFIG_IP_NF_IRC is not set
+# CONFIG_IP_NF_TFTP is not set
+# CONFIG_IP_NF_AMANDA is not set
+# CONFIG_IP_NF_QUEUE is not set
+CONFIG_IP_NF_IPTABLES=m
+# CONFIG_IP_NF_MATCH_LIMIT is not set
+CONFIG_IP_NF_MATCH_IPRANGE=m
+# CONFIG_IP_NF_MATCH_MAC is not set
+# CONFIG_IP_NF_MATCH_PKTTYPE is not set
+# CONFIG_IP_NF_MATCH_MARK is not set
+# CONFIG_IP_NF_MATCH_MULTIPORT is not set
+# CONFIG_IP_NF_MATCH_TOS is not set
+# CONFIG_IP_NF_MATCH_RECENT is not set
+# CONFIG_IP_NF_MATCH_ECN is not set
+# CONFIG_IP_NF_MATCH_DSCP is not set
+# CONFIG_IP_NF_MATCH_AH_ESP is not set
+# CONFIG_IP_NF_MATCH_LENGTH is not set
+# CONFIG_IP_NF_MATCH_TTL is not set
+# CONFIG_IP_NF_MATCH_TCPMSS is not set
+# CONFIG_IP_NF_MATCH_HELPER is not set
+# CONFIG_IP_NF_MATCH_STATE is not set
+# CONFIG_IP_NF_MATCH_CONNTRACK is not set
+# CONFIG_IP_NF_MATCH_OWNER is not set
+# CONFIG_IP_NF_MATCH_PHYSDEV is not set
+# CONFIG_IP_NF_MATCH_ADDRTYPE is not set
+# CONFIG_IP_NF_MATCH_REALM is not set
+# CONFIG_IP_NF_MATCH_SCTP is not set
+# CONFIG_IP_NF_MATCH_COMMENT is not set
+# CONFIG_IP_NF_MATCH_HASHLIMIT is not set
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_TARGET_REJECT=m
+# CONFIG_IP_NF_TARGET_LOG is not set
+# CONFIG_IP_NF_TARGET_ULOG is not set
+# CONFIG_IP_NF_TARGET_TCPMSS is not set
+CONFIG_IP_NF_NAT=m
+CONFIG_IP_NF_NAT_NEEDED=y
+CONFIG_IP_NF_TARGET_MASQUERADE=m
+# CONFIG_IP_NF_TARGET_REDIRECT is not set
+# CONFIG_IP_NF_TARGET_NETMAP is not set
+# CONFIG_IP_NF_TARGET_SAME is not set
+# CONFIG_IP_NF_NAT_SNMP_BASIC is not set
+CONFIG_IP_NF_NAT_FTP=m
+# CONFIG_IP_NF_MANGLE is not set
+# CONFIG_IP_NF_RAW is not set
+# CONFIG_IP_NF_ARPTABLES is not set
+
+#
+# Bridge: Netfilter Configuration
+#
+# CONFIG_BRIDGE_NF_EBTABLES is not set
+
+#
+# SCTP Configuration (EXPERIMENTAL)
+#
+# CONFIG_IP_SCTP is not set
+# CONFIG_ATM is not set
+CONFIG_BRIDGE=y
+# CONFIG_VLAN_8021Q is not set
+# CONFIG_DECNET is not set
+# CONFIG_LLC2 is not set
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+# CONFIG_NET_DIVERT is not set
+# CONFIG_ECONET is not set
+# CONFIG_WAN_ROUTER is not set
+
+#
+# QoS and/or fair queueing
+#
+# CONFIG_NET_SCHED is not set
+# CONFIG_NET_CLS_ROUTE is not set
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+# CONFIG_NETPOLL is not set
+# CONFIG_NET_POLL_CONTROLLER is not set
+# CONFIG_HAMRADIO is not set
+# CONFIG_IRDA is not set
+# CONFIG_BT is not set
+CONFIG_NETDEVICES=y
+# CONFIG_DUMMY is not set
+# CONFIG_BONDING is not set
+# CONFIG_EQUALIZER is not set
+CONFIG_TUN=y
+
+#
+# ARCnet devices
+#
+# CONFIG_ARCNET is not set
+
+#
+# Ethernet (10 or 100Mbit)
+#
+CONFIG_NET_ETHERNET=y
+CONFIG_MII=y
+# CONFIG_HAPPYMEAL is not set
+# CONFIG_SUNGEM is not set
+CONFIG_NET_VENDOR_3COM=y
+CONFIG_VORTEX=y
+# CONFIG_TYPHOON is not set
+
+#
+# Tulip family network device support
+#
+CONFIG_NET_TULIP=y
+# CONFIG_DE2104X is not set
+CONFIG_TULIP=y
+# CONFIG_TULIP_MWI is not set
+# CONFIG_TULIP_MMIO is not set
+# CONFIG_TULIP_NAPI is not set
+# CONFIG_DE4X5 is not set
+# CONFIG_WINBOND_840 is not set
+# CONFIG_DM9102 is not set
+# CONFIG_HP100 is not set
+CONFIG_NET_PCI=y
+CONFIG_PCNET32=y
+# CONFIG_AMD8111_ETH is not set
+# CONFIG_ADAPTEC_STARFIRE is not set
+# CONFIG_B44 is not set
+# CONFIG_FORCEDETH is not set
+# CONFIG_DGRS is not set
+# CONFIG_EEPRO100 is not set
+CONFIG_E100=y
+# CONFIG_E100_NAPI is not set
+# CONFIG_FEALNX is not set
+# CONFIG_NATSEMI is not set
+CONFIG_NE2K_PCI=y
+# CONFIG_8139CP is not set
+CONFIG_8139TOO=y
+CONFIG_8139TOO_PIO=y
+# CONFIG_8139TOO_TUNE_TWISTER is not set
+# CONFIG_8139TOO_8129 is not set
+# CONFIG_8139_OLD_RX_RESET is not set
+# CONFIG_SIS900 is not set
+# CONFIG_EPIC100 is not set
+# CONFIG_SUNDANCE is not set
+CONFIG_VIA_RHINE=y
+# CONFIG_VIA_RHINE_MMIO is not set
+
+#
+# Ethernet (1000 Mbit)
+#
+CONFIG_ACENIC=y
+# CONFIG_ACENIC_OMIT_TIGON_I is not set
+# CONFIG_DL2K is not set
+CONFIG_E1000=y
+# CONFIG_E1000_NAPI is not set
+# CONFIG_NS83820 is not set
+# CONFIG_HAMACHI is not set
+# CONFIG_YELLOWFIN is not set
+# CONFIG_R8169 is not set
+# CONFIG_SK98LIN is not set
+# CONFIG_VIA_VELOCITY is not set
+CONFIG_TIGON3=y
+
+#
+# Ethernet (10000 Mbit)
+#
+# CONFIG_IXGB is not set
+# CONFIG_S2IO is not set
+
+#
+# Token Ring devices
+#
+# CONFIG_TR is not set
+
+#
+# Wireless LAN (non-hamradio)
+#
+# CONFIG_NET_RADIO is not set
+
+#
+# Wan interfaces
+#
+# CONFIG_WAN is not set
+# CONFIG_FDDI is not set
+# CONFIG_HIPPI is not set
+# CONFIG_PPP is not set
+# CONFIG_SLIP is not set
+# CONFIG_NET_FC is not set
+# CONFIG_SHAPER is not set
+# CONFIG_NETCONSOLE is not set
+
+#
+# ISDN subsystem
+#
+# CONFIG_ISDN is not set
+
+#
+# Telephony Support
+#
+# CONFIG_PHONE is not set
+
+#
+# Input device support
+#
+CONFIG_INPUT=y
+
+#
+# Userland interfaces
+#
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_INPUT_MOUSEDEV_PSAUX=y
+CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
+CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
+# CONFIG_INPUT_JOYDEV is not set
+# CONFIG_INPUT_TSDEV is not set
+# CONFIG_INPUT_EVDEV is not set
+# CONFIG_INPUT_EVBUG is not set
+
+#
+# Input I/O drivers
+#
+# CONFIG_GAMEPORT is not set
+CONFIG_SOUND_GAMEPORT=y
+CONFIG_SERIO=y
+CONFIG_SERIO_I8042=y
+CONFIG_SERIO_SERPORT=y
+# CONFIG_SERIO_CT82C710 is not set
+# CONFIG_SERIO_PCIPS2 is not set
+CONFIG_SERIO_LIBPS2=y
+# CONFIG_SERIO_RAW is not set
+
+#
+# Input Device Drivers
+#
+CONFIG_INPUT_KEYBOARD=y
+CONFIG_KEYBOARD_ATKBD=y
+# CONFIG_KEYBOARD_SUNKBD is not set
+# CONFIG_KEYBOARD_LKKBD is not set
+# CONFIG_KEYBOARD_XTKBD is not set
+# CONFIG_KEYBOARD_NEWTON is not set
+CONFIG_INPUT_MOUSE=y
+CONFIG_MOUSE_PS2=y
+# CONFIG_MOUSE_SERIAL is not set
+# CONFIG_MOUSE_VSXXXAA is not set
+# CONFIG_INPUT_JOYSTICK is not set
+# CONFIG_INPUT_TOUCHSCREEN is not set
+# CONFIG_INPUT_MISC is not set
+
+#
+# Character devices
+#
+CONFIG_VT=y
+CONFIG_VT_CONSOLE=y
+CONFIG_HW_CONSOLE=y
+# CONFIG_SERIAL_NONSTANDARD is not set
+
+#
+# Serial drivers
+#
+# CONFIG_SERIAL_8250 is not set
+
+#
+# Non-8250 serial port support
+#
+CONFIG_UNIX98_PTYS=y
+CONFIG_LEGACY_PTYS=y
+CONFIG_LEGACY_PTY_COUNT=256
+
+#
+# IPMI
+#
+# CONFIG_IPMI_HANDLER is not set
+
+#
+# Watchdog Cards
+#
+# CONFIG_WATCHDOG is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_NVRAM is not set
+CONFIG_RTC=y
+# CONFIG_GEN_RTC is not set
+# CONFIG_DTLK is not set
+# CONFIG_R3964 is not set
+# CONFIG_APPLICOM is not set
+
+#
+# Ftape, the floppy tape device driver
+#
+# CONFIG_FTAPE is not set
+CONFIG_AGP=m
+CONFIG_AGP_AMD64=m
+CONFIG_AGP_INTEL_MCH=m
+CONFIG_DRM=m
+CONFIG_DRM_TDFX=m
+# CONFIG_DRM_GAMMA is not set
+CONFIG_DRM_R128=m
+CONFIG_DRM_RADEON=m
+CONFIG_DRM_MGA=m
+CONFIG_DRM_SIS=m
+# CONFIG_MWAVE is not set
+# CONFIG_RAW_DRIVER is not set
+# CONFIG_HPET is not set
+# CONFIG_HANGCHECK_TIMER is not set
+
+#
+# I2C support
+#
+# CONFIG_I2C is not set
+
+#
+# Dallas's 1-wire bus
+#
+# CONFIG_W1 is not set
+
+#
+# Misc devices
+#
+# CONFIG_IBM_ASM is not set
+
+#
+# Multimedia devices
+#
+# CONFIG_VIDEO_DEV is not set
+
+#
+# Digital Video Broadcasting Devices
+#
+# CONFIG_DVB is not set
+
+#
+# Graphics support
+#
+# CONFIG_FB is not set
+# CONFIG_VIDEO_SELECT is not set
+
+#
+# Console display driver support
+#
+CONFIG_VGA_CONSOLE=y
+CONFIG_DUMMY_CONSOLE=y
+
+#
+# Sound
+#
+# CONFIG_SOUND is not set
+
+#
+# USB support
+#
+# CONFIG_USB is not set
+CONFIG_USB_ARCH_HAS_HCD=y
+CONFIG_USB_ARCH_HAS_OHCI=y
+
+#
+# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed;
see USB_STORAGE Help for more information
+#
+
+#
+# USB Gadget Support
+#
+# CONFIG_USB_GADGET is not set
+
+#
+# MMC/SD Card support
+#
+# CONFIG_MMC is not set
+
+#
+# InfiniBand support
+#
+# CONFIG_INFINIBAND is not set
+
+#
+# Power management options
+#
+
+#
+# ACPI (Advanced Configuration and Power Interface) Support
+#
+CONFIG_ACPI=y
+CONFIG_ACPI_BOOT=y
+CONFIG_ACPI_INTERPRETER=y
+CONFIG_ACPI_AC=m
+CONFIG_ACPI_BATTERY=m
+CONFIG_ACPI_BUTTON=m
+CONFIG_ACPI_VIDEO=m
+CONFIG_ACPI_FAN=m
+CONFIG_ACPI_PROCESSOR=m
+CONFIG_ACPI_THERMAL=m
+CONFIG_ACPI_ASUS=m
+CONFIG_ACPI_IBM=m
+CONFIG_ACPI_TOSHIBA=m
+CONFIG_ACPI_BLACKLIST_YEAR=0
+# CONFIG_ACPI_DEBUG is not set
+CONFIG_ACPI_BUS=y
+CONFIG_ACPI_EC=y
+CONFIG_ACPI_POWER=y
+CONFIG_ACPI_PCI=y
+CONFIG_ACPI_SYSTEM=y
+# CONFIG_ACPI_CONTAINER is not set
+
+#
+# File systems
+#
+CONFIG_EXT2_FS=y
+# CONFIG_EXT2_FS_XATTR is not set
+CONFIG_EXT3_FS=y
+CONFIG_EXT3_FS_XATTR=y
+# CONFIG_EXT3_FS_POSIX_ACL is not set
+# CONFIG_EXT3_FS_SECURITY is not set
+CONFIG_JBD=y
+# CONFIG_JBD_DEBUG is not set
+CONFIG_FS_MBCACHE=y
+CONFIG_REISERFS_FS=y
+# CONFIG_REISERFS_CHECK is not set
+# CONFIG_REISERFS_PROC_INFO is not set
+# CONFIG_REISERFS_FS_XATTR is not set
+# CONFIG_JFS_FS is not set
+
+#
+# XFS support
+#
+# CONFIG_XFS_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_ROMFS_FS is not set
+# CONFIG_QUOTA is not set
+CONFIG_DNOTIFY=y
+CONFIG_AUTOFS_FS=y
+CONFIG_AUTOFS4_FS=y
+
+#
+# CD-ROM/DVD Filesystems
+#
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+CONFIG_ZISOFS_FS=y
+# CONFIG_UDF_FS is not set
+
+#
+# DOS/FAT/NT Filesystems
+#
+CONFIG_FAT_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_FAT_DEFAULT_CODEPAGE=437
+CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
+# CONFIG_NTFS_FS is not set
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_SYSFS=y
+# CONFIG_DEVFS_FS is not set
+# CONFIG_DEVPTS_FS_XATTR is not set
+CONFIG_TMPFS=y
+# CONFIG_TMPFS_XATTR is not set
+# CONFIG_HUGETLBFS is not set
+# CONFIG_HUGETLB_PAGE is not set
+CONFIG_RAMFS=y
+
+#
+# Miscellaneous filesystems
+#
+# CONFIG_ADFS_FS is not set
+# CONFIG_AFFS_FS is not set
+# CONFIG_HFS_FS is not set
+# CONFIG_HFSPLUS_FS is not set
+# CONFIG_BEFS_FS is not set
+# CONFIG_BFS_FS is not set
+# CONFIG_EFS_FS is not set
+# CONFIG_CRAMFS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_HPFS_FS is not set
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_SYSV_FS is not set
+# CONFIG_UFS_FS is not set
+
+#
+# Network File Systems
+#
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+# CONFIG_NFS_V4 is not set
+# CONFIG_NFS_DIRECTIO is not set
+CONFIG_NFSD=m
+CONFIG_NFSD_V3=y
+# CONFIG_NFSD_V4 is not set
+CONFIG_NFSD_TCP=y
+CONFIG_ROOT_NFS=y
+CONFIG_LOCKD=y
+CONFIG_LOCKD_V4=y
+CONFIG_EXPORTFS=m
+CONFIG_SUNRPC=y
+# CONFIG_RPCSEC_GSS_KRB5 is not set
+# CONFIG_RPCSEC_GSS_SPKM3 is not set
+# CONFIG_SMB_FS is not set
+# CONFIG_CIFS is not set
+# CONFIG_NCP_FS is not set
+# CONFIG_CODA_FS is not set
+# CONFIG_AFS_FS is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+
+#
+# Native Language Support
+#
+CONFIG_NLS=y
+CONFIG_NLS_DEFAULT="iso8859-1"
+CONFIG_NLS_CODEPAGE_437=y
+# CONFIG_NLS_CODEPAGE_737 is not set
+# CONFIG_NLS_CODEPAGE_775 is not set
+# CONFIG_NLS_CODEPAGE_850 is not set
+# CONFIG_NLS_CODEPAGE_852 is not set
+# CONFIG_NLS_CODEPAGE_855 is not set
+# CONFIG_NLS_CODEPAGE_857 is not set
+# CONFIG_NLS_CODEPAGE_860 is not set
+# CONFIG_NLS_CODEPAGE_861 is not set
+# CONFIG_NLS_CODEPAGE_862 is not set
+# CONFIG_NLS_CODEPAGE_863 is not set
+# CONFIG_NLS_CODEPAGE_864 is not set
+# CONFIG_NLS_CODEPAGE_865 is not set
+# CONFIG_NLS_CODEPAGE_866 is not set
+# CONFIG_NLS_CODEPAGE_869 is not set
+# CONFIG_NLS_CODEPAGE_936 is not set
+# CONFIG_NLS_CODEPAGE_950 is not set
+# CONFIG_NLS_CODEPAGE_932 is not set
+# CONFIG_NLS_CODEPAGE_949 is not set
+# CONFIG_NLS_CODEPAGE_874 is not set
+# CONFIG_NLS_ISO8859_8 is not set
+# CONFIG_NLS_CODEPAGE_1250 is not set
+# CONFIG_NLS_CODEPAGE_1251 is not set
+# CONFIG_NLS_ASCII is not set
+CONFIG_NLS_ISO8859_1=y
+# CONFIG_NLS_ISO8859_2 is not set
+# CONFIG_NLS_ISO8859_3 is not set
+# CONFIG_NLS_ISO8859_4 is not set
+# CONFIG_NLS_ISO8859_5 is not set
+# CONFIG_NLS_ISO8859_6 is not set
+# CONFIG_NLS_ISO8859_7 is not set
+# CONFIG_NLS_ISO8859_9 is not set
+# CONFIG_NLS_ISO8859_13 is not set
+# CONFIG_NLS_ISO8859_14 is not set
+# CONFIG_NLS_ISO8859_15 is not set
+# CONFIG_NLS_KOI8_R is not set
+# CONFIG_NLS_KOI8_U is not set
+# CONFIG_NLS_UTF8 is not set
+
+#
+# Security options
+#
+# CONFIG_KEYS is not set
+# CONFIG_SECURITY is not set
+
+#
+# Cryptographic options
+#
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_HMAC=y
+# CONFIG_CRYPTO_NULL is not set
+# CONFIG_CRYPTO_MD4 is not set
+CONFIG_CRYPTO_MD5=m
+CONFIG_CRYPTO_SHA1=m
+# CONFIG_CRYPTO_SHA256 is not set
+# CONFIG_CRYPTO_SHA512 is not set
+# CONFIG_CRYPTO_WP512 is not set
+CONFIG_CRYPTO_DES=m
+# CONFIG_CRYPTO_BLOWFISH is not set
+# CONFIG_CRYPTO_TWOFISH is not set
+# CONFIG_CRYPTO_SERPENT is not set
+# CONFIG_CRYPTO_AES is not set
+# CONFIG_CRYPTO_CAST5 is not set
+# CONFIG_CRYPTO_CAST6 is not set
+# CONFIG_CRYPTO_TEA is not set
+# CONFIG_CRYPTO_ARC4 is not set
+# CONFIG_CRYPTO_KHAZAD is not set
+# CONFIG_CRYPTO_ANUBIS is not set
+# CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_MICHAEL_MIC is not set
+CONFIG_CRYPTO_CRC32C=m
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Hardware crypto devices
+#
+
+#
+# Library routines
+#
+# CONFIG_CRC_CCITT is not set
+CONFIG_CRC32=y
+CONFIG_LIBCRC32C=y
+CONFIG_ZLIB_INFLATE=y
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/early_printk.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/early_printk.c Fri Jul
15 13:39:50 2005
@@ -0,0 +1,242 @@
+#include <linux/config.h>
+#include <linux/console.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <asm/io.h>
+#include <asm/processor.h>
+
+/* Simple VGA output */
+
+#ifdef __i386__
+#define VGABASE (__ISA_IO_base + 0xb8000)
+#else
+#define VGABASE ((void __iomem *)0xffffffff800b8000UL)
+#endif
+
+#define MAX_YPOS 25
+#define MAX_XPOS 80
+
+static int current_ypos = 1, current_xpos = 0;
+
+static void early_vga_write(struct console *con, const char *str, unsigned n)
+{
+ char c;
+ int i, k, j;
+
+ while ((c = *str++) != '\0' && n-- > 0) {
+ if (current_ypos >= MAX_YPOS) {
+ /* scroll 1 line up */
+ for (k = 1, j = 0; k < MAX_YPOS; k++, j++) {
+ for (i = 0; i < MAX_XPOS; i++) {
+ writew(readw(VGABASE + 2*(MAX_XPOS*k +
i)),
+ VGABASE + 2*(MAX_XPOS*j + i));
+ }
+ }
+ for (i = 0; i < MAX_XPOS; i++)
+ writew(0x720, VGABASE + 2*(MAX_XPOS*j + i));
+ current_ypos = MAX_YPOS-1;
+ }
+ if (c == '\n') {
+ current_xpos = 0;
+ current_ypos++;
+ } else if (c != '\r') {
+ writew(((0x7 << 8) | (unsigned short) c),
+ VGABASE + 2*(MAX_XPOS*current_ypos +
+ current_xpos++));
+ if (current_xpos >= MAX_XPOS) {
+ current_xpos = 0;
+ current_ypos++;
+ }
+ }
+ }
+}
+
+static struct console early_vga_console = {
+ .name = "earlyvga",
+ .write = early_vga_write,
+ .flags = CON_PRINTBUFFER,
+ .index = -1,
+};
+
+#ifndef CONFIG_XEN
+/* Serial functions loosely based on a similar package from Klaus P. Gerlicher
*/
+
+int early_serial_base = 0x3f8; /* ttyS0 */
+
+#define XMTRDY 0x20
+
+#define DLAB 0x80
+
+#define TXR 0 /* Transmit register (WRITE) */
+#define RXR 0 /* Receive register (READ) */
+#define IER 1 /* Interrupt Enable */
+#define IIR 2 /* Interrupt ID */
+#define FCR 2 /* FIFO control */
+#define LCR 3 /* Line control */
+#define MCR 4 /* Modem control */
+#define LSR 5 /* Line Status */
+#define MSR 6 /* Modem Status */
+#define DLL 0 /* Divisor Latch Low */
+#define DLH 1 /* Divisor latch High */
+
+static int early_serial_putc(unsigned char ch)
+{
+ unsigned timeout = 0xffff;
+ while ((inb(early_serial_base + LSR) & XMTRDY) == 0 && --timeout)
+ cpu_relax();
+ outb(ch, early_serial_base + TXR);
+ return timeout ? 0 : -1;
+}
+
+static void early_serial_write(struct console *con, const char *s, unsigned n)
+{
+ while (*s && n-- > 0) {
+ early_serial_putc(*s);
+ if (*s == '\n')
+ early_serial_putc('\r');
+ s++;
+ }
+}
+
+#define DEFAULT_BAUD 9600
+
+static __init void early_serial_init(char *s)
+{
+ unsigned char c;
+ unsigned divisor;
+ unsigned baud = DEFAULT_BAUD;
+ char *e;
+
+ if (*s == ',')
+ ++s;
+
+ if (*s) {
+ unsigned port;
+ if (!strncmp(s,"0x",2)) {
+ early_serial_base = simple_strtoul(s, &e, 16);
+ } else {
+ static int bases[] = { 0x3f8, 0x2f8 };
+
+ if (!strncmp(s,"ttyS",4))
+ s += 4;
+ port = simple_strtoul(s, &e, 10);
+ if (port > 1 || s == e)
+ port = 0;
+ early_serial_base = bases[port];
+ }
+ s += strcspn(s, ",");
+ if (*s == ',')
+ s++;
+ }
+
+ outb(0x3, early_serial_base + LCR); /* 8n1 */
+ outb(0, early_serial_base + IER); /* no interrupt */
+ outb(0, early_serial_base + FCR); /* no fifo */
+ outb(0x3, early_serial_base + MCR); /* DTR + RTS */
+
+ if (*s) {
+ baud = simple_strtoul(s, &e, 0);
+ if (baud == 0 || s == e)
+ baud = DEFAULT_BAUD;
+ }
+
+ divisor = 115200 / baud;
+ c = inb(early_serial_base + LCR);
+ outb(c | DLAB, early_serial_base + LCR);
+ outb(divisor & 0xff, early_serial_base + DLL);
+ outb((divisor >> 8) & 0xff, early_serial_base + DLH);
+ outb(c & ~DLAB, early_serial_base + LCR);
+}
+#else
+
+static void
+early_serial_write(struct console *con, const char *s, unsigned count)
+{
+ int n;
+
+ while (count > 0) {
+ n = HYPERVISOR_console_io(CONSOLEIO_write, count, (char *)s);
+ if (n <= 0)
+ break;
+ count -= n;
+ s += n;
+ }
+}
+
+static __init void early_serial_init(char *s)
+{
+}
+#endif
+
+static struct console early_serial_console = {
+ .name = "earlyser",
+ .write = early_serial_write,
+ .flags = CON_PRINTBUFFER,
+ .index = -1,
+};
+
+/* Direct interface for emergencies */
+struct console *early_console = &early_vga_console;
+static int early_console_initialized = 0;
+
+void early_printk(const char *fmt, ...)
+{
+ char buf[512];
+ int n;
+ va_list ap;
+
+ va_start(ap,fmt);
+ n = vscnprintf(buf,512,fmt,ap);
+ early_console->write(early_console,buf,n);
+ va_end(ap);
+}
+
+static int keep_early;
+
+int __init setup_early_printk(char *opt)
+{
+ char *space;
+ char buf[256];
+
+ if (early_console_initialized)
+ return -1;
+
+ opt = strchr(opt, '=') + 1;
+
+ strlcpy(buf,opt,sizeof(buf));
+ space = strchr(buf, ' ');
+ if (space)
+ *space = 0;
+
+ if (strstr(buf,"keep"))
+ keep_early = 1;
+
+ if (!strncmp(buf, "serial", 6)) {
+ early_serial_init(buf + 6);
+ early_console = &early_serial_console;
+ } else if (!strncmp(buf, "ttyS", 4)) {
+ early_serial_init(buf);
+ early_console = &early_serial_console;
+ } else if (!strncmp(buf, "vga", 3)) {
+ early_console = &early_vga_console;
+ }
+ early_console_initialized = 1;
+ register_console(early_console);
+ return 0;
+}
+
+void __init disable_early_printk(void)
+{
+ if (!early_console_initialized || !early_console)
+ return;
+ if (!keep_early) {
+ printk("disabling early console\n");
+ unregister_console(early_console);
+ early_console_initialized = 0;
+ } else {
+ printk("keeping early console\n");
+ }
+}
+
+__setup("earlyprintk=", setup_early_printk);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/pgalloc.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/pgalloc.h Fri Jul
15 13:39:50 2005
@@ -0,0 +1,62 @@
+#ifndef _I386_PGALLOC_H
+#define _I386_PGALLOC_H
+
+#include <linux/config.h>
+#include <asm/processor.h>
+#include <asm/fixmap.h>
+#include <linux/threads.h>
+#include <linux/mm.h> /* for struct page */
+#include <asm/io.h> /* for phys_to_virt and page_to_pseudophys */
+
+#define pmd_populate_kernel(mm, pmd, pte) \
+ set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte)))
+
+#define pmd_populate(mm, pmd, pte) \
+do { \
+ if (unlikely((mm)->context.pinned)) { \
+ if (!PageHighMem(pte)) \
+ HYPERVISOR_update_va_mapping( \
+ (unsigned long)__va(page_to_pfn(pte)<<PAGE_SHIFT),\
+ pfn_pte(page_to_pfn(pte), PAGE_KERNEL_RO), 0);\
+ set_pmd(pmd, __pmd(_PAGE_TABLE + \
+ ((unsigned long long)page_to_pfn(pte) << \
+ (unsigned long long) PAGE_SHIFT))); \
+ } else { \
+ *(pmd) = __pmd(_PAGE_TABLE + \
+ ((unsigned long long)page_to_pfn(pte) << \
+ (unsigned long long) PAGE_SHIFT)); \
+ } \
+} while (0)
+
+/*
+ * Allocate and free page tables.
+ */
+extern pgd_t *pgd_alloc(struct mm_struct *);
+extern void pgd_free(pgd_t *pgd);
+
+extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long);
+extern struct page *pte_alloc_one(struct mm_struct *, unsigned long);
+
+static inline void pte_free_kernel(pte_t *pte)
+{
+ free_page((unsigned long)pte);
+ make_page_writable(pte);
+}
+
+extern void pte_free(struct page *pte);
+
+#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte))
+
+#ifdef CONFIG_X86_PAE
+/*
+ * In the PAE case we free the pmds as part of the pgd.
+ */
+#define pmd_alloc_one(mm, addr) ({ BUG(); ((pmd_t *)2); })
+#define pmd_free(x) do { } while (0)
+#define __pmd_free_tlb(tlb,x) do { } while (0)
+#define pud_populate(mm, pmd, pte) BUG()
+#endif
+
+#define check_pgt_cache() do { } while (0)
+
+#endif /* _I386_PGALLOC_H */
diff -r 35b74976f598 -r a83ac0806d6b linux-2.6.11-xen-sparse/arch/xen/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/Makefile Fri Jul 15 13:39:50 2005
@@ -0,0 +1,91 @@
+#
+# xen/Makefile
+#
+# This file is included by the global makefile so that you can add your own
+# architecture-specific flags and dependencies. Remember to do have actions
+# for "archclean" cleaning up for this architecture.
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License. See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 2004 by Christian Limpach
+#
+
+XENARCH := $(subst ",,$(CONFIG_XENARCH))
+
+# pick up headers from include/asm-xen/asm in preference over include/asm
+NOSTDINC_FLAGS = -nostdinc -iwithprefix include/asm-xen -Iinclude/asm-xen
-iwithprefix include
+ifneq ($(KBUILD_SRC),)
+NOSTDINC_FLAGS += -I$(srctree)/include/asm-xen
+endif
+
+# make uname return the processor arch
+UTS_MACHINE := $(XENARCH)
+
+core-y += arch/xen/kernel/
+
+.PHONY: include2/asm
+include2/asm:
+ifneq ($(KBUILD_SRC),)
+ @echo ' SYMLINK ../include/asm-$(XENARCH) -> include2/asm'
+ $(Q)ln -fsn ../include/asm-$(XENARCH) include2/asm
+endif
+
+include/.asm-ignore: include/asm
+ @rm -f include/.asm-ignore
+ @mv include/asm include/.asm-ignore
+ @echo ' SYMLINK include/asm -> include/asm-$(XENARCH)'
+ $(Q)if [ ! -d include ]; then mkdir -p include; fi;
+ @ln -fsn $(srctree)/include/asm-$(XENARCH) include/asm
+
+include/asm-xen/asm:
+ @echo ' SYMLINK $@ -> include/asm-xen/asm-$(XENARCH)'
+ @mkdir -p include/asm-xen
+ @ln -fsn $(srctree)/include/asm-xen/asm-$(XENARCH) $@
+
+arch/xen/arch:
+ @rm -f $@
+ @mkdir -p arch/xen
+ @ln -fsn $(srctree)/arch/xen/$(XENARCH) $@
+
+arch/$(XENARCH)/kernel/asm-offsets.s: include/asm include/linux/version.h \
+ include/config/MARKER
+
+include/asm-$(ARCH)/asm_offsets.h: arch/$(XENARCH)/kernel/asm-offsets.s
+ $(call filechk,gen-asm-offsets)
+
+prepare: include/.asm-ignore include/asm-xen/asm \
+ arch/xen/arch include/asm-$(ARCH)/asm_offsets.h include2/asm ;
+
+all: vmlinuz
+
+vmlinuz: vmlinux
+ $(Q)$(MAKE) $(build)=arch/xen/boot vmlinuz
+
+XINSTALL_NAME ?= $(KERNELRELEASE)
+install: vmlinuz
+ mkdir -p $(INSTALL_PATH)/boot
+ ln -f -s vmlinuz-$(XINSTALL_NAME)$(INSTALL_SUFFIX)
$(INSTALL_PATH)/boot/vmlinuz-$(VERSION).$(PATCHLEVEL).$(SUBLEVEL)$(XENGUEST)$(INSTALL_SUFFIX)
+ rm -f $(INSTALL_PATH)/boot/vmlinuz-$(XINSTALL_NAME)$(INSTALL_SUFFIX)
+ install -m0644 vmlinuz
$(INSTALL_PATH)/boot/vmlinuz-$(XINSTALL_NAME)$(INSTALL_SUFFIX)
+ install -m0644 vmlinux
$(INSTALL_PATH)/boot/vmlinux-syms-$(XINSTALL_NAME)$(INSTALL_SUFFIX)
+ install -m0664 .config
$(INSTALL_PATH)/boot/config-$(XINSTALL_NAME)$(INSTALL_SUFFIX)
+ install -m0664 System.map
$(INSTALL_PATH)/boot/System.map-$(XINSTALL_NAME)$(INSTALL_SUFFIX)
+ ln -f -s vmlinuz-$(XINSTALL_NAME)$(INSTALL_SUFFIX)
$(INSTALL_PATH)/boot/vmlinuz-$(VERSION).$(PATCHLEVEL)$(XENGUEST)$(INSTALL_SUFFIX)
+ mkdir -p $(INSTALL_PATH)/usr/include/xen/linux
+ install -m0644 $(srctree)/include/asm-xen/linux-public/*.h
$(INSTALL_PATH)/usr/include/xen/linux
+
+archclean:
+ @if [ -e arch/xen/arch ]; then $(MAKE) $(clean)=arch/xen/arch; fi;
+ @rm -f arch/xen/arch include/.asm-ignore include/asm-xen/asm
+ @rm -f vmlinux-stripped vmlinuz
+
+define archhelp
+ echo '* vmlinuz - Compressed kernel image'
+ echo ' install - Install kernel image and config file'
+endef
+
+ifneq ($(XENARCH),)
+include $(srctree)/arch/xen/$(XENARCH)/Makefile
+endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/io_apic.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/io_apic.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,2611 @@
+/*
+ * Intel IO-APIC support for multi-Pentium hosts.
+ *
+ * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar, Hajnalka Szabo
+ *
+ * Many thanks to Stig Venaas for trying out countless experimental
+ * patches and reporting/debugging problems patiently!
+ *
+ * (c) 1999, Multiple IO-APIC support, developed by
+ * Ken-ichi Yaku <yaku@xxxxxxxxxxxxxxxxxxxx> and
+ * Hidemi Kishimoto <kisimoto@xxxxxxxxxxxxxxxxxxxx>,
+ * further tested and cleaned up by Zach Brown <zab@xxxxxxxxxx>
+ * and Ingo Molnar <mingo@xxxxxxxxxx>
+ *
+ * Fixes
+ * Maciej W. Rozycki : Bits for genuine 82489DX APICs;
+ * thanks to Eric Gilmore
+ * and Rolf G. Tews
+ * for testing these extensively
+ * Paul Diefenbaugh : Added full ACPI support
+ */
+
+#include <linux/mm.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/config.h>
+#include <linux/smp_lock.h>
+#include <linux/mc146818rtc.h>
+#include <linux/compiler.h>
+#include <linux/acpi.h>
+
+#include <linux/sysdev.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/desc.h>
+#include <asm/timer.h>
+
+#include <mach_apic.h>
+
+#include "io_ports.h"
+
+#ifdef CONFIG_XEN
+
+#include <asm-xen/xen-public/xen.h>
+#include <asm-xen/xen-public/physdev.h>
+
+/* Fake i8259 */
+#define make_8259A_irq(_irq) (io_apic_irqs &= ~(1UL<<(_irq)))
+#define disable_8259A_irq(_irq) ((void)0)
+#define i8259A_irq_pending(_irq) (0)
+
+unsigned long io_apic_irqs;
+
+static inline unsigned int xen_io_apic_read(unsigned int apic, unsigned int
reg)
+{
+ physdev_op_t op;
+ int ret;
+
+ op.cmd = PHYSDEVOP_APIC_READ;
+ op.u.apic_op.apic = mp_ioapics[apic].mpc_apicid;
+ op.u.apic_op.offset = reg;
+ ret = HYPERVISOR_physdev_op(&op);
+ if (ret)
+ return ret;
+ return op.u.apic_op.value;
+}
+
+static inline void xen_io_apic_write(unsigned int apic, unsigned int reg,
unsigned int value)
+{
+ physdev_op_t op;
+
+ op.cmd = PHYSDEVOP_APIC_WRITE;
+ op.u.apic_op.apic = mp_ioapics[apic].mpc_apicid;
+ op.u.apic_op.offset = reg;
+ op.u.apic_op.value = value;
+ HYPERVISOR_physdev_op(&op);
+}
+
+#define io_apic_read(a,r) xen_io_apic_read(a,r)
+#define io_apic_write(a,r,v) xen_io_apic_write(a,r,v)
+
+#endif /* CONFIG_XEN */
+
+int (*ioapic_renumber_irq)(int ioapic, int irq);
+atomic_t irq_mis_count;
+
+static DEFINE_SPINLOCK(ioapic_lock);
+
+/*
+ * Is the SiS APIC rmw bug present ?
+ * -1 = don't know, 0 = no, 1 = yes
+ */
+int sis_apic_bug = -1;
+
+/*
+ * # of IRQ routing registers
+ */
+int nr_ioapic_registers[MAX_IO_APICS];
+
+/*
+ * Rough estimation of how many shared IRQs there are, can
+ * be changed anytime.
+ */
+#define MAX_PLUS_SHARED_IRQS NR_IRQS
+#define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS)
+
+/*
+ * This is performance-critical, we want to do it O(1)
+ *
+ * the indexing order of this array favors 1:1 mappings
+ * between pins and IRQs.
+ */
+
+static struct irq_pin_list {
+ int apic, pin, next;
+} irq_2_pin[PIN_MAP_SIZE];
+
+int vector_irq[NR_VECTORS] = { [0 ... NR_VECTORS - 1] = -1};
+#ifdef CONFIG_PCI_MSI
+#define vector_to_irq(vector) \
+ (platform_legacy_irq(vector) ? vector : vector_irq[vector])
+#else
+#define vector_to_irq(vector) (vector)
+#endif
+
+/*
+ * The common case is 1:1 IRQ<->pin mappings. Sometimes there are
+ * shared ISA-space IRQs, so we have to support them. We are super
+ * fast in the common case, and fast for shared ISA-space IRQs.
+ */
+static void add_pin_to_irq(unsigned int irq, int apic, int pin)
+{
+ static int first_free_entry = NR_IRQS;
+ struct irq_pin_list *entry = irq_2_pin + irq;
+
+ while (entry->next)
+ entry = irq_2_pin + entry->next;
+
+ if (entry->pin != -1) {
+ entry->next = first_free_entry;
+ entry = irq_2_pin + entry->next;
+ if (++first_free_entry >= PIN_MAP_SIZE)
+ panic("io_apic.c: whoops");
+ }
+ entry->apic = apic;
+ entry->pin = pin;
+}
+
+#ifndef CONFIG_XEN
+/*
+ * Reroute an IRQ to a different pin.
+ */
+static void __init replace_pin_at_irq(unsigned int irq,
+ int oldapic, int oldpin,
+ int newapic, int newpin)
+{
+ struct irq_pin_list *entry = irq_2_pin + irq;
+
+ while (1) {
+ if (entry->apic == oldapic && entry->pin == oldpin) {
+ entry->apic = newapic;
+ entry->pin = newpin;
+ }
+ if (!entry->next)
+ break;
+ entry = irq_2_pin + entry->next;
+ }
+}
+
+static void __modify_IO_APIC_irq (unsigned int irq, unsigned long enable,
unsigned long disable)
+{
+ struct irq_pin_list *entry = irq_2_pin + irq;
+ unsigned int pin, reg;
+
+ for (;;) {
+ pin = entry->pin;
+ if (pin == -1)
+ break;
+ reg = io_apic_read(entry->apic, 0x10 + pin*2);
+ reg &= ~disable;
+ reg |= enable;
+ io_apic_modify(entry->apic, 0x10 + pin*2, reg);
+ if (!entry->next)
+ break;
+ entry = irq_2_pin + entry->next;
+ }
+}
+
+/* mask = 1 */
+static void __mask_IO_APIC_irq (unsigned int irq)
+{
+ __modify_IO_APIC_irq(irq, 0x00010000, 0);
+}
+
+/* mask = 0 */
+static void __unmask_IO_APIC_irq (unsigned int irq)
+{
+ __modify_IO_APIC_irq(irq, 0, 0x00010000);
+}
+
+/* mask = 1, trigger = 0 */
+static void __mask_and_edge_IO_APIC_irq (unsigned int irq)
+{
+ __modify_IO_APIC_irq(irq, 0x00010000, 0x00008000);
+}
+
+/* mask = 0, trigger = 1 */
+static void __unmask_and_level_IO_APIC_irq (unsigned int irq)
+{
+ __modify_IO_APIC_irq(irq, 0x00008000, 0x00010000);
+}
+
+static void mask_IO_APIC_irq (unsigned int irq)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ __mask_IO_APIC_irq(irq);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+static void unmask_IO_APIC_irq (unsigned int irq)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ __unmask_IO_APIC_irq(irq);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
+{
+ struct IO_APIC_route_entry entry;
+ unsigned long flags;
+
+ /* Check delivery_mode to be sure we're not clearing an SMI pin */
+ spin_lock_irqsave(&ioapic_lock, flags);
+ *(((int*)&entry) + 0) = io_apic_read(apic, 0x10 + 2 * pin);
+ *(((int*)&entry) + 1) = io_apic_read(apic, 0x11 + 2 * pin);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ if (entry.delivery_mode == dest_SMI)
+ return;
+
+ /*
+ * Disable it in the IO-APIC irq-routing table:
+ */
+ memset(&entry, 0, sizeof(entry));
+ entry.mask = 1;
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(apic, 0x10 + 2 * pin, *(((int *)&entry) + 0));
+ io_apic_write(apic, 0x11 + 2 * pin, *(((int *)&entry) + 1));
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+static void clear_IO_APIC (void)
+{
+ int apic, pin;
+
+ for (apic = 0; apic < nr_ioapics; apic++)
+ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++)
+ clear_IO_APIC_pin(apic, pin);
+}
+
+static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
+{
+ unsigned long flags;
+ int pin;
+ struct irq_pin_list *entry = irq_2_pin + irq;
+ unsigned int apicid_value;
+
+ apicid_value = cpu_mask_to_apicid(cpumask);
+ /* Prepare to do the io_apic_write */
+ apicid_value = apicid_value << 24;
+ spin_lock_irqsave(&ioapic_lock, flags);
+ for (;;) {
+ pin = entry->pin;
+ if (pin == -1)
+ break;
+ io_apic_write(entry->apic, 0x10 + 1 + pin*2, apicid_value);
+ if (!entry->next)
+ break;
+ entry = irq_2_pin + entry->next;
+ }
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+#else
+#define clear_IO_APIC() ((void)0)
+#endif
+
+#if defined(CONFIG_IRQBALANCE)
+# include <asm/processor.h> /* kernel_thread() */
+# include <linux/kernel_stat.h> /* kstat */
+# include <linux/slab.h> /* kmalloc() */
+# include <linux/timer.h> /* time_after() */
+
+# ifdef CONFIG_BALANCED_IRQ_DEBUG
+# define TDprintk(x...) do { printk("<%ld:%s:%d>: ", jiffies, __FILE__,
__LINE__); printk(x); } while (0)
+# define Dprintk(x...) do { TDprintk(x); } while (0)
+# else
+# define TDprintk(x...)
+# define Dprintk(x...)
+# endif
+
+cpumask_t __cacheline_aligned pending_irq_balance_cpumask[NR_IRQS];
+
+#define IRQBALANCE_CHECK_ARCH -999
+static int irqbalance_disabled = IRQBALANCE_CHECK_ARCH;
+static int physical_balance = 0;
+
+struct irq_cpu_info {
+ unsigned long * last_irq;
+ unsigned long * irq_delta;
+ unsigned long irq;
+} irq_cpu_data[NR_CPUS];
+
+#define CPU_IRQ(cpu) (irq_cpu_data[cpu].irq)
+#define LAST_CPU_IRQ(cpu,irq) (irq_cpu_data[cpu].last_irq[irq])
+#define IRQ_DELTA(cpu,irq) (irq_cpu_data[cpu].irq_delta[irq])
+
+#define IDLE_ENOUGH(cpu,now) \
+ (idle_cpu(cpu) && ((now) - irq_stat[(cpu)].idle_timestamp > 1))
+
+#define IRQ_ALLOWED(cpu, allowed_mask) cpu_isset(cpu, allowed_mask)
+
+#define CPU_TO_PACKAGEINDEX(i) (first_cpu(cpu_sibling_map[i]))
+
+#define MAX_BALANCED_IRQ_INTERVAL (5*HZ)
+#define MIN_BALANCED_IRQ_INTERVAL (HZ/2)
+#define BALANCED_IRQ_MORE_DELTA (HZ/10)
+#define BALANCED_IRQ_LESS_DELTA (HZ)
+
+long balanced_irq_interval = MAX_BALANCED_IRQ_INTERVAL;
+
+static unsigned long move(int curr_cpu, cpumask_t allowed_mask,
+ unsigned long now, int direction)
+{
+ int search_idle = 1;
+ int cpu = curr_cpu;
+
+ goto inside;
+
+ do {
+ if (unlikely(cpu == curr_cpu))
+ search_idle = 0;
+inside:
+ if (direction == 1) {
+ cpu++;
+ if (cpu >= NR_CPUS)
+ cpu = 0;
+ } else {
+ cpu--;
+ if (cpu == -1)
+ cpu = NR_CPUS-1;
+ }
+ } while (!cpu_online(cpu) || !IRQ_ALLOWED(cpu,allowed_mask) ||
+ (search_idle && !IDLE_ENOUGH(cpu,now)));
+
+ return cpu;
+}
+
+static inline void balance_irq(int cpu, int irq)
+{
+ unsigned long now = jiffies;
+ cpumask_t allowed_mask;
+ unsigned int new_cpu;
+
+ if (irqbalance_disabled)
+ return;
+
+ cpus_and(allowed_mask, cpu_online_map, irq_affinity[irq]);
+ new_cpu = move(cpu, allowed_mask, now, 1);
+ if (cpu != new_cpu) {
+ irq_desc_t *desc = irq_desc + irq;
+ unsigned long flags;
+
+ spin_lock_irqsave(&desc->lock, flags);
+ pending_irq_balance_cpumask[irq] = cpumask_of_cpu(new_cpu);
+ spin_unlock_irqrestore(&desc->lock, flags);
+ }
+}
+
+static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
+{
+ int i, j;
+ Dprintk("Rotating IRQs among CPUs.\n");
+ for (i = 0; i < NR_CPUS; i++) {
+ for (j = 0; cpu_online(i) && (j < NR_IRQS); j++) {
+ if (!irq_desc[j].action)
+ continue;
+ /* Is it a significant load ? */
+ if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i),j) <
+ useful_load_threshold)
+ continue;
+ balance_irq(i, j);
+ }
+ }
+ balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL,
+ balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
+ return;
+}
+
+static void do_irq_balance(void)
+{
+ int i, j;
+ unsigned long max_cpu_irq = 0, min_cpu_irq = (~0);
+ unsigned long move_this_load = 0;
+ int max_loaded = 0, min_loaded = 0;
+ int load;
+ unsigned long useful_load_threshold = balanced_irq_interval + 10;
+ int selected_irq;
+ int tmp_loaded, first_attempt = 1;
+ unsigned long tmp_cpu_irq;
+ unsigned long imbalance = 0;
+ cpumask_t allowed_mask, target_cpu_mask, tmp;
+
+ for (i = 0; i < NR_CPUS; i++) {
+ int package_index;
+ CPU_IRQ(i) = 0;
+ if (!cpu_online(i))
+ continue;
+ package_index = CPU_TO_PACKAGEINDEX(i);
+ for (j = 0; j < NR_IRQS; j++) {
+ unsigned long value_now, delta;
+ /* Is this an active IRQ? */
+ if (!irq_desc[j].action)
+ continue;
+ if ( package_index == i )
+ IRQ_DELTA(package_index,j) = 0;
+ /* Determine the total count per processor per IRQ */
+ value_now = (unsigned long) kstat_cpu(i).irqs[j];
+
+ /* Determine the activity per processor per IRQ */
+ delta = value_now - LAST_CPU_IRQ(i,j);
+
+ /* Update last_cpu_irq[][] for the next time */
+ LAST_CPU_IRQ(i,j) = value_now;
+
+ /* Ignore IRQs whose rate is less than the clock */
+ if (delta < useful_load_threshold)
+ continue;
+ /* update the load for the processor or package total */
+ IRQ_DELTA(package_index,j) += delta;
+
+ /* Keep track of the higher numbered sibling as well */
+ if (i != package_index)
+ CPU_IRQ(i) += delta;
+ /*
+ * We have sibling A and sibling B in the package
+ *
+ * cpu_irq[A] = load for cpu A + load for cpu B
+ * cpu_irq[B] = load for cpu B
+ */
+ CPU_IRQ(package_index) += delta;
+ }
+ }
+ /* Find the least loaded processor package */
+ for (i = 0; i < NR_CPUS; i++) {
+ if (!cpu_online(i))
+ continue;
+ if (i != CPU_TO_PACKAGEINDEX(i))
+ continue;
+ if (min_cpu_irq > CPU_IRQ(i)) {
+ min_cpu_irq = CPU_IRQ(i);
+ min_loaded = i;
+ }
+ }
+ max_cpu_irq = ULONG_MAX;
+
+tryanothercpu:
+ /* Look for heaviest loaded processor.
+ * We may come back to get the next heaviest loaded processor.
+ * Skip processors with trivial loads.
+ */
+ tmp_cpu_irq = 0;
+ tmp_loaded = -1;
+ for (i = 0; i < NR_CPUS; i++) {
+ if (!cpu_online(i))
+ continue;
+ if (i != CPU_TO_PACKAGEINDEX(i))
+ continue;
+ if (max_cpu_irq <= CPU_IRQ(i))
+ continue;
+ if (tmp_cpu_irq < CPU_IRQ(i)) {
+ tmp_cpu_irq = CPU_IRQ(i);
+ tmp_loaded = i;
+ }
+ }
+
+ if (tmp_loaded == -1) {
+ /* In the case of small number of heavy interrupt sources,
+ * loading some of the cpus too much. We use Ingo's original
+ * approach to rotate them around.
+ */
+ if (!first_attempt && imbalance >= useful_load_threshold) {
+ rotate_irqs_among_cpus(useful_load_threshold);
+ return;
+ }
+ goto not_worth_the_effort;
+ }
+
+ first_attempt = 0; /* heaviest search */
+ max_cpu_irq = tmp_cpu_irq; /* load */
+ max_loaded = tmp_loaded; /* processor */
+ imbalance = (max_cpu_irq - min_cpu_irq) / 2;
+
+ Dprintk("max_loaded cpu = %d\n", max_loaded);
+ Dprintk("min_loaded cpu = %d\n", min_loaded);
+ Dprintk("max_cpu_irq load = %ld\n", max_cpu_irq);
+ Dprintk("min_cpu_irq load = %ld\n", min_cpu_irq);
+ Dprintk("load imbalance = %lu\n", imbalance);
+
+ /* if imbalance is less than approx 10% of max load, then
+ * observe diminishing returns action. - quit
+ */
+ if (imbalance < (max_cpu_irq >> 3)) {
+ Dprintk("Imbalance too trivial\n");
+ goto not_worth_the_effort;
+ }
+
+tryanotherirq:
+ /* if we select an IRQ to move that can't go where we want, then
+ * see if there is another one to try.
+ */
+ move_this_load = 0;
+ selected_irq = -1;
+ for (j = 0; j < NR_IRQS; j++) {
+ /* Is this an active IRQ? */
+ if (!irq_desc[j].action)
+ continue;
+ if (imbalance <= IRQ_DELTA(max_loaded,j))
+ continue;
+ /* Try to find the IRQ that is closest to the imbalance
+ * without going over.
+ */
+ if (move_this_load < IRQ_DELTA(max_loaded,j)) {
+ move_this_load = IRQ_DELTA(max_loaded,j);
+ selected_irq = j;
+ }
+ }
+ if (selected_irq == -1) {
+ goto tryanothercpu;
+ }
+
+ imbalance = move_this_load;
+
+ /* For physical_balance case, we accumlated both load
+ * values in the one of the siblings cpu_irq[],
+ * to use the same code for physical and logical processors
+ * as much as possible.
+ *
+ * NOTE: the cpu_irq[] array holds the sum of the load for
+ * sibling A and sibling B in the slot for the lowest numbered
+ * sibling (A), _AND_ the load for sibling B in the slot for
+ * the higher numbered sibling.
+ *
+ * We seek the least loaded sibling by making the comparison
+ * (A+B)/2 vs B
+ */
+ load = CPU_IRQ(min_loaded) >> 1;
+ for_each_cpu_mask(j, cpu_sibling_map[min_loaded]) {
+ if (load > CPU_IRQ(j)) {
+ /* This won't change cpu_sibling_map[min_loaded] */
+ load = CPU_IRQ(j);
+ min_loaded = j;
+ }
+ }
+
+ cpus_and(allowed_mask, cpu_online_map, irq_affinity[selected_irq]);
+ target_cpu_mask = cpumask_of_cpu(min_loaded);
+ cpus_and(tmp, target_cpu_mask, allowed_mask);
+
+ if (!cpus_empty(tmp)) {
+ irq_desc_t *desc = irq_desc + selected_irq;
+ unsigned long flags;
+
+ Dprintk("irq = %d moved to cpu = %d\n",
+ selected_irq, min_loaded);
+ /* mark for change destination */
+ spin_lock_irqsave(&desc->lock, flags);
+ pending_irq_balance_cpumask[selected_irq] =
+ cpumask_of_cpu(min_loaded);
+ spin_unlock_irqrestore(&desc->lock, flags);
+ /* Since we made a change, come back sooner to
+ * check for more variation.
+ */
+ balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL,
+ balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
+ return;
+ }
+ goto tryanotherirq;
+
+not_worth_the_effort:
+ /*
+ * if we did not find an IRQ to move, then adjust the time interval
+ * upward
+ */
+ balanced_irq_interval = min((long)MAX_BALANCED_IRQ_INTERVAL,
+ balanced_irq_interval + BALANCED_IRQ_MORE_DELTA);
+ Dprintk("IRQ worth rotating not found\n");
+ return;
+}
+
+static int balanced_irq(void *unused)
+{
+ int i;
+ unsigned long prev_balance_time = jiffies;
+ long time_remaining = balanced_irq_interval;
+
+ daemonize("kirqd");
+
+ /* push everything to CPU 0 to give us a starting point. */
+ for (i = 0 ; i < NR_IRQS ; i++) {
+ pending_irq_balance_cpumask[i] = cpumask_of_cpu(0);
+ }
+
+ for ( ; ; ) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ time_remaining = schedule_timeout(time_remaining);
+ try_to_freeze(PF_FREEZE);
+ if (time_after(jiffies,
+ prev_balance_time+balanced_irq_interval)) {
+ do_irq_balance();
+ prev_balance_time = jiffies;
+ time_remaining = balanced_irq_interval;
+ }
+ }
+ return 0;
+}
+
+static int __init balanced_irq_init(void)
+{
+ int i;
+ struct cpuinfo_x86 *c;
+ cpumask_t tmp;
+
+ cpus_shift_right(tmp, cpu_online_map, 2);
+ c = &boot_cpu_data;
+ /* When not overwritten by the command line ask subarchitecture. */
+ if (irqbalance_disabled == IRQBALANCE_CHECK_ARCH)
+ irqbalance_disabled = NO_BALANCE_IRQ;
+ if (irqbalance_disabled)
+ return 0;
+
+ /* disable irqbalance completely if there is only one processor online
*/
+ if (num_online_cpus() < 2) {
+ irqbalance_disabled = 1;
+ return 0;
+ }
+ /*
+ * Enable physical balance only if more than 1 physical processor
+ * is present
+ */
+ if (smp_num_siblings > 1 && !cpus_empty(tmp))
+ physical_balance = 1;
+
+ for (i = 0; i < NR_CPUS; i++) {
+ if (!cpu_online(i))
+ continue;
+ irq_cpu_data[i].irq_delta = kmalloc(sizeof(unsigned long) *
NR_IRQS, GFP_KERNEL);
+ irq_cpu_data[i].last_irq = kmalloc(sizeof(unsigned long) *
NR_IRQS, GFP_KERNEL);
+ if (irq_cpu_data[i].irq_delta == NULL ||
irq_cpu_data[i].last_irq == NULL) {
+ printk(KERN_ERR "balanced_irq_init: out of memory");
+ goto failed;
+ }
+ memset(irq_cpu_data[i].irq_delta,0,sizeof(unsigned long) *
NR_IRQS);
+ memset(irq_cpu_data[i].last_irq,0,sizeof(unsigned long) *
NR_IRQS);
+ }
+
+ printk(KERN_INFO "Starting balanced_irq\n");
+ if (kernel_thread(balanced_irq, NULL, CLONE_KERNEL) >= 0)
+ return 0;
+ else
+ printk(KERN_ERR "balanced_irq_init: failed to spawn
balanced_irq");
+failed:
+ for (i = 0; i < NR_CPUS; i++) {
+ if(irq_cpu_data[i].irq_delta)
+ kfree(irq_cpu_data[i].irq_delta);
+ if(irq_cpu_data[i].last_irq)
+ kfree(irq_cpu_data[i].last_irq);
+ }
+ return 0;
+}
+
+int __init irqbalance_disable(char *str)
+{
+ irqbalance_disabled = 1;
+ return 0;
+}
+
+__setup("noirqbalance", irqbalance_disable);
+
+static inline void move_irq(int irq)
+{
+ /* note - we hold the desc->lock */
+ if (unlikely(!cpus_empty(pending_irq_balance_cpumask[irq]))) {
+ set_ioapic_affinity_irq(irq, pending_irq_balance_cpumask[irq]);
+ cpus_clear(pending_irq_balance_cpumask[irq]);
+ }
+}
+
+late_initcall(balanced_irq_init);
+
+#else /* !CONFIG_IRQBALANCE */
+static inline void move_irq(int irq) { }
+#endif /* CONFIG_IRQBALANCE */
+
+#ifndef CONFIG_SMP
+void fastcall send_IPI_self(int vector)
+{
+#ifndef CONFIG_XEN
+ unsigned int cfg;
+
+ /*
+ * Wait for idle.
+ */
+ apic_wait_icr_idle();
+ cfg = APIC_DM_FIXED | APIC_DEST_SELF | vector | APIC_DEST_LOGICAL;
+ /*
+ * Send the IPI. The write to APIC_ICR fires this off.
+ */
+ apic_write_around(APIC_ICR, cfg);
+#endif
+}
+#endif /* !CONFIG_SMP */
+
+
+/*
+ * support for broken MP BIOSs, enables hand-redirection of PIRQ0-7 to
+ * specific CPU-side IRQs.
+ */
+
+#define MAX_PIRQS 8
+int pirq_entries [MAX_PIRQS];
+int pirqs_enabled;
+int skip_ioapic_setup;
+
+static int __init ioapic_setup(char *str)
+{
+ skip_ioapic_setup = 1;
+ return 1;
+}
+
+__setup("noapic", ioapic_setup);
+
+static int __init ioapic_pirq_setup(char *str)
+{
+ int i, max;
+ int ints[MAX_PIRQS+1];
+
+ get_options(str, ARRAY_SIZE(ints), ints);
+
+ for (i = 0; i < MAX_PIRQS; i++)
+ pirq_entries[i] = -1;
+
+ pirqs_enabled = 1;
+ apic_printk(APIC_VERBOSE, KERN_INFO
+ "PIRQ redirection, working around broken MP-BIOS.\n");
+ max = MAX_PIRQS;
+ if (ints[0] < MAX_PIRQS)
+ max = ints[0];
+
+ for (i = 0; i < max; i++) {
+ apic_printk(APIC_VERBOSE, KERN_DEBUG
+ "... PIRQ%d -> IRQ %d\n", i, ints[i+1]);
+ /*
+ * PIRQs are mapped upside down, usually.
+ */
+ pirq_entries[MAX_PIRQS-i-1] = ints[i+1];
+ }
+ return 1;
+}
+
+__setup("pirq=", ioapic_pirq_setup);
+
+/*
+ * Find the IRQ entry number of a certain pin.
+ */
+static int find_irq_entry(int apic, int pin, int type)
+{
+ int i;
+
+ for (i = 0; i < mp_irq_entries; i++)
+ if (mp_irqs[i].mpc_irqtype == type &&
+ (mp_irqs[i].mpc_dstapic == mp_ioapics[apic].mpc_apicid ||
+ mp_irqs[i].mpc_dstapic == MP_APIC_ALL) &&
+ mp_irqs[i].mpc_dstirq == pin)
+ return i;
+
+ return -1;
+}
+
+#ifndef CONFIG_XEN
+/*
+ * Find the pin to which IRQ[irq] (ISA) is connected
+ */
+static int find_isa_irq_pin(int irq, int type)
+{
+ int i;
+
+ for (i = 0; i < mp_irq_entries; i++) {
+ int lbus = mp_irqs[i].mpc_srcbus;
+
+ if ((mp_bus_id_to_type[lbus] == MP_BUS_ISA ||
+ mp_bus_id_to_type[lbus] == MP_BUS_EISA ||
+ mp_bus_id_to_type[lbus] == MP_BUS_MCA ||
+ mp_bus_id_to_type[lbus] == MP_BUS_NEC98
+ ) &&
+ (mp_irqs[i].mpc_irqtype == type) &&
+ (mp_irqs[i].mpc_srcbusirq == irq))
+
+ return mp_irqs[i].mpc_dstirq;
+ }
+ return -1;
+}
+#endif
+
+/*
+ * Find a specific PCI IRQ entry.
+ * Not an __init, possibly needed by modules
+ */
+static int pin_2_irq(int idx, int apic, int pin);
+
+int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
+{
+ int apic, i, best_guess = -1;
+
+ apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, "
+ "slot:%d, pin:%d.\n", bus, slot, pin);
+ if (mp_bus_id_to_pci_bus[bus] == -1) {
+ printk(KERN_WARNING "PCI BIOS passed nonexistent PCI bus
%d!\n", bus);
+ return -1;
+ }
+ for (i = 0; i < mp_irq_entries; i++) {
+ int lbus = mp_irqs[i].mpc_srcbus;
+
+ for (apic = 0; apic < nr_ioapics; apic++)
+ if (mp_ioapics[apic].mpc_apicid ==
mp_irqs[i].mpc_dstapic ||
+ mp_irqs[i].mpc_dstapic == MP_APIC_ALL)
+ break;
+
+ if ((mp_bus_id_to_type[lbus] == MP_BUS_PCI) &&
+ !mp_irqs[i].mpc_irqtype &&
+ (bus == lbus) &&
+ (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) {
+ int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq);
+
+ if (!(apic || IO_APIC_IRQ(irq)))
+ continue;
+
+ if (pin == (mp_irqs[i].mpc_srcbusirq & 3))
+ return irq;
+ /*
+ * Use the first all-but-pin matching entry as a
+ * best-guess fuzzy result for broken mptables.
+ */
+ if (best_guess < 0)
+ best_guess = irq;
+ }
+ }
+ return best_guess;
+}
+
+#ifndef CONFIG_XEN
+/*
+ * This function currently is only a helper for the i386 smp boot process
where
+ * we need to reprogram the ioredtbls to cater for the cpus which have come
online
+ * so mask in all cases should simply be TARGET_CPUS
+ */
+void __init setup_ioapic_dest(void)
+{
+ int pin, ioapic, irq, irq_entry;
+
+ if (skip_ioapic_setup == 1)
+ return;
+
+ for (ioapic = 0; ioapic < nr_ioapics; ioapic++) {
+ for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
+ irq_entry = find_irq_entry(ioapic, pin, mp_INT);
+ if (irq_entry == -1)
+ continue;
+ irq = pin_2_irq(irq_entry, ioapic, pin);
+ set_ioapic_affinity_irq(irq, TARGET_CPUS);
+ }
+
+ }
+}
+#endif /* !CONFIG_XEN */
+
+/*
+ * EISA Edge/Level control register, ELCR
+ */
+static int EISA_ELCR(unsigned int irq)
+{
+ if (irq < 16) {
+ unsigned int port = 0x4d0 + (irq >> 3);
+ return (inb(port) >> (irq & 7)) & 1;
+ }
+ apic_printk(APIC_VERBOSE, KERN_INFO
+ "Broken MPtable reports ISA irq %d\n", irq);
+ return 0;
+}
+
+/* EISA interrupts are always polarity zero and can be edge or level
+ * trigger depending on the ELCR value. If an interrupt is listed as
+ * EISA conforming in the MP table, that means its trigger type must
+ * be read in from the ELCR */
+
+#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mpc_srcbusirq))
+#define default_EISA_polarity(idx) (0)
+
+/* ISA interrupts are always polarity zero edge triggered,
+ * when listed as conforming in the MP table. */
+
+#define default_ISA_trigger(idx) (0)
+#define default_ISA_polarity(idx) (0)
+
+/* PCI interrupts are always polarity one level triggered,
+ * when listed as conforming in the MP table. */
+
+#define default_PCI_trigger(idx) (1)
+#define default_PCI_polarity(idx) (1)
+
+/* MCA interrupts are always polarity zero level triggered,
+ * when listed as conforming in the MP table. */
+
+#define default_MCA_trigger(idx) (1)
+#define default_MCA_polarity(idx) (0)
+
+/* NEC98 interrupts are always polarity zero edge triggered,
+ * when listed as conforming in the MP table. */
+
+#define default_NEC98_trigger(idx) (0)
+#define default_NEC98_polarity(idx) (0)
+
+static int __init MPBIOS_polarity(int idx)
+{
+ int bus = mp_irqs[idx].mpc_srcbus;
+ int polarity;
+
+ /*
+ * Determine IRQ line polarity (high active or low active):
+ */
+ switch (mp_irqs[idx].mpc_irqflag & 3)
+ {
+ case 0: /* conforms, ie. bus-type dependent polarity */
+ {
+ switch (mp_bus_id_to_type[bus])
+ {
+ case MP_BUS_ISA: /* ISA pin */
+ {
+ polarity = default_ISA_polarity(idx);
+ break;
+ }
+ case MP_BUS_EISA: /* EISA pin */
+ {
+ polarity = default_EISA_polarity(idx);
+ break;
+ }
+ case MP_BUS_PCI: /* PCI pin */
+ {
+ polarity = default_PCI_polarity(idx);
+ break;
+ }
+ case MP_BUS_MCA: /* MCA pin */
+ {
+ polarity = default_MCA_polarity(idx);
+ break;
+ }
+ case MP_BUS_NEC98: /* NEC 98 pin */
+ {
+ polarity = default_NEC98_polarity(idx);
+ break;
+ }
+ default:
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ polarity = 1;
+ break;
+ }
+ }
+ break;
+ }
+ case 1: /* high active */
+ {
+ polarity = 0;
+ break;
+ }
+ case 2: /* reserved */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ polarity = 1;
+ break;
+ }
+ case 3: /* low active */
+ {
+ polarity = 1;
+ break;
+ }
+ default: /* invalid */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ polarity = 1;
+ break;
+ }
+ }
+ return polarity;
+}
+
+static int MPBIOS_trigger(int idx)
+{
+ int bus = mp_irqs[idx].mpc_srcbus;
+ int trigger;
+
+ /*
+ * Determine IRQ trigger mode (edge or level sensitive):
+ */
+ switch ((mp_irqs[idx].mpc_irqflag>>2) & 3)
+ {
+ case 0: /* conforms, ie. bus-type dependent */
+ {
+ switch (mp_bus_id_to_type[bus])
+ {
+ case MP_BUS_ISA: /* ISA pin */
+ {
+ trigger = default_ISA_trigger(idx);
+ break;
+ }
+ case MP_BUS_EISA: /* EISA pin */
+ {
+ trigger = default_EISA_trigger(idx);
+ break;
+ }
+ case MP_BUS_PCI: /* PCI pin */
+ {
+ trigger = default_PCI_trigger(idx);
+ break;
+ }
+ case MP_BUS_MCA: /* MCA pin */
+ {
+ trigger = default_MCA_trigger(idx);
+ break;
+ }
+ case MP_BUS_NEC98: /* NEC 98 pin */
+ {
+ trigger = default_NEC98_trigger(idx);
+ break;
+ }
+ default:
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ trigger = 1;
+ break;
+ }
+ }
+ break;
+ }
+ case 1: /* edge */
+ {
+ trigger = 0;
+ break;
+ }
+ case 2: /* reserved */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ trigger = 1;
+ break;
+ }
+ case 3: /* level */
+ {
+ trigger = 1;
+ break;
+ }
+ default: /* invalid */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ trigger = 0;
+ break;
+ }
+ }
+ return trigger;
+}
+
+static inline int irq_polarity(int idx)
+{
+ return MPBIOS_polarity(idx);
+}
+
+static inline int irq_trigger(int idx)
+{
+ return MPBIOS_trigger(idx);
+}
+
+static int pin_2_irq(int idx, int apic, int pin)
+{
+ int irq, i;
+ int bus = mp_irqs[idx].mpc_srcbus;
+
+ /*
+ * Debugging check, we are in big trouble if this message pops up!
+ */
+ if (mp_irqs[idx].mpc_dstirq != pin)
+ printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n");
+
+ switch (mp_bus_id_to_type[bus])
+ {
+ case MP_BUS_ISA: /* ISA pin */
+ case MP_BUS_EISA:
+ case MP_BUS_MCA:
+ case MP_BUS_NEC98:
+ {
+ irq = mp_irqs[idx].mpc_srcbusirq;
+ break;
+ }
+ case MP_BUS_PCI: /* PCI pin */
+ {
+ /*
+ * PCI IRQs are mapped in order
+ */
+ i = irq = 0;
+ while (i < apic)
+ irq += nr_ioapic_registers[i++];
+ irq += pin;
+
+ /*
+ * For MPS mode, so far only needed by ES7000 platform
+ */
+ if (ioapic_renumber_irq)
+ irq = ioapic_renumber_irq(apic, irq);
+
+ break;
+ }
+ default:
+ {
+ printk(KERN_ERR "unknown bus type %d.\n",bus);
+ irq = 0;
+ break;
+ }
+ }
+
+ /*
+ * PCI IRQ command line redirection. Yes, limits are hardcoded.
+ */
+ if ((pin >= 16) && (pin <= 23)) {
+ if (pirq_entries[pin-16] != -1) {
+ if (!pirq_entries[pin-16]) {
+ apic_printk(APIC_VERBOSE, KERN_DEBUG
+ "disabling PIRQ%d\n", pin-16);
+ } else {
+ irq = pirq_entries[pin-16];
+ apic_printk(APIC_VERBOSE, KERN_DEBUG
+ "using PIRQ%d -> IRQ %d\n",
+ pin-16, irq);
+ }
+ }
+ }
+ return irq;
+}
+
+static inline int IO_APIC_irq_trigger(int irq)
+{
+ int apic, idx, pin;
+
+ for (apic = 0; apic < nr_ioapics; apic++) {
+ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
+ idx = find_irq_entry(apic,pin,mp_INT);
+ if ((idx != -1) && (irq == pin_2_irq(idx,apic,pin)))
+ return irq_trigger(idx);
+ }
+ }
+ /*
+ * nonexistent IRQs are edge default
+ */
+ return 0;
+}
+
+/* irq_vectors is indexed by the sum of all RTEs in all I/O APICs. */
+u8 irq_vector[NR_IRQ_VECTORS]; /* = { FIRST_DEVICE_VECTOR , 0 }; */
+
+int assign_irq_vector(int irq)
+{
+ static int current_vector = FIRST_DEVICE_VECTOR;
+ physdev_op_t op;
+
+ BUG_ON(irq >= NR_IRQ_VECTORS);
+ if (irq != AUTO_ASSIGN && IO_APIC_VECTOR(irq) > 0)
+ return IO_APIC_VECTOR(irq);
+
+ op.cmd = PHYSDEVOP_ASSIGN_VECTOR;
+ op.u.irq_op.irq = irq;
+ if (HYPERVISOR_physdev_op(&op))
+ return -ENOSPC;
+ current_vector = op.u.irq_op.vector;
+
+ vector_irq[current_vector] = irq;
+ if (irq != AUTO_ASSIGN)
+ IO_APIC_VECTOR(irq) = current_vector;
+
+ return current_vector;
+}
+
+#ifndef CONFIG_XEN
+static struct hw_interrupt_type ioapic_level_type;
+static struct hw_interrupt_type ioapic_edge_type;
+
+#define IOAPIC_AUTO -1
+#define IOAPIC_EDGE 0
+#define IOAPIC_LEVEL 1
+
+static inline void ioapic_register_intr(int irq, int vector, unsigned long
trigger)
+{
+ if (use_pci_vector() && !platform_legacy_irq(irq)) {
+ if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
+ trigger == IOAPIC_LEVEL)
+ irq_desc[vector].handler = &ioapic_level_type;
+ else
+ irq_desc[vector].handler = &ioapic_edge_type;
+ set_intr_gate(vector, interrupt[vector]);
+ } else {
+ if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
+ trigger == IOAPIC_LEVEL)
+ irq_desc[irq].handler = &ioapic_level_type;
+ else
+ irq_desc[irq].handler = &ioapic_edge_type;
+ set_intr_gate(vector, interrupt[irq]);
+ }
+}
+#else
+#define ioapic_register_intr(_irq,_vector,_trigger) ((void)0)
+#endif
+
+void __init setup_IO_APIC_irqs(void)
+{
+ struct IO_APIC_route_entry entry;
+ int apic, pin, idx, irq, first_notcon = 1, vector;
+ unsigned long flags;
+
+ apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
+
+ for (apic = 0; apic < nr_ioapics; apic++) {
+ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
+
+ /*
+ * add it to the IO-APIC irq-routing table:
+ */
+ memset(&entry,0,sizeof(entry));
+
+ entry.delivery_mode = INT_DELIVERY_MODE;
+ entry.dest_mode = INT_DEST_MODE;
+ entry.mask = 0; /* enable IRQ */
+ entry.dest.logical.logical_dest =
+ cpu_mask_to_apicid(TARGET_CPUS);
+
+ idx = find_irq_entry(apic,pin,mp_INT);
+ if (idx == -1) {
+ if (first_notcon) {
+ apic_printk(APIC_VERBOSE, KERN_DEBUG
+ " IO-APIC (apicid-pin) %d-%d",
+ mp_ioapics[apic].mpc_apicid,
+ pin);
+ first_notcon = 0;
+ } else
+ apic_printk(APIC_VERBOSE, ", %d-%d",
+ mp_ioapics[apic].mpc_apicid, pin);
+ continue;
+ }
+
+ entry.trigger = irq_trigger(idx);
+ entry.polarity = irq_polarity(idx);
+
+ if (irq_trigger(idx)) {
+ entry.trigger = 1;
+ entry.mask = 1;
+ }
+
+ irq = pin_2_irq(idx, apic, pin);
+ /*
+ * skip adding the timer int on secondary nodes, which causes
+ * a small but painful rift in the time-space continuum
+ */
+ if (multi_timer_check(apic, irq))
+ continue;
+ else
+ add_pin_to_irq(irq, apic, pin);
+
+ if (/*!apic &&*/ !IO_APIC_IRQ(irq))
+ continue;
+
+ if (IO_APIC_IRQ(irq)) {
+ vector = assign_irq_vector(irq);
+ entry.vector = vector;
+ ioapic_register_intr(irq, vector, IOAPIC_AUTO);
+
+ if (!apic && (irq < 16))
+ disable_8259A_irq(irq);
+ }
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(apic, 0x11+2*pin, *(((int *)&entry)+1));
+ io_apic_write(apic, 0x10+2*pin, *(((int *)&entry)+0));
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ }
+ }
+
+ if (!first_notcon)
+ apic_printk(APIC_VERBOSE, " not connected.\n");
+}
+
+/*
+ * Set up the 8259A-master output pin:
+ */
+#ifndef CONFIG_XEN
+void __init setup_ExtINT_IRQ0_pin(unsigned int pin, int vector)
+{
+ struct IO_APIC_route_entry entry;
+ unsigned long flags;
+
+ memset(&entry,0,sizeof(entry));
+
+ disable_8259A_irq(0);
+
+ /* mask LVT0 */
+ apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
+
+ /*
+ * We use logical delivery to get the timer IRQ
+ * to the first CPU.
+ */
+ entry.dest_mode = INT_DEST_MODE;
+ entry.mask = 0; /* unmask IRQ now */
+ entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS);
+ entry.delivery_mode = INT_DELIVERY_MODE;
+ entry.polarity = 0;
+ entry.trigger = 0;
+ entry.vector = vector;
+
+ /*
+ * The timer IRQ doesn't have to know that behind the
+ * scene we have a 8259A-master in AEOI mode ...
+ */
+ irq_desc[0].handler = &ioapic_edge_type;
+
+ /*
+ * Add it to the IO-APIC irq-routing table:
+ */
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(0, 0x11+2*pin, *(((int *)&entry)+1));
+ io_apic_write(0, 0x10+2*pin, *(((int *)&entry)+0));
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ enable_8259A_irq(0);
+}
+
+static inline void UNEXPECTED_IO_APIC(void)
+{
+}
+
+void __init print_IO_APIC(void)
+{
+ int apic, i;
+ union IO_APIC_reg_00 reg_00;
+ union IO_APIC_reg_01 reg_01;
+ union IO_APIC_reg_02 reg_02;
+ union IO_APIC_reg_03 reg_03;
+ unsigned long flags;
+
+ if (apic_verbosity == APIC_QUIET)
+ return;
+
+ printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
+ for (i = 0; i < nr_ioapics; i++)
+ printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
+ mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]);
+
+ /*
+ * We are a bit conservative about what we expect. We have to
+ * know about every hardware change ASAP.
+ */
+ printk(KERN_INFO "testing the IO APIC.......................\n");
+
+ for (apic = 0; apic < nr_ioapics; apic++) {
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(apic, 0);
+ reg_01.raw = io_apic_read(apic, 1);
+ if (reg_01.bits.version >= 0x10)
+ reg_02.raw = io_apic_read(apic, 2);
+ if (reg_01.bits.version >= 0x20)
+ reg_03.raw = io_apic_read(apic, 3);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid);
+ printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
+ printk(KERN_DEBUG "....... : physical APIC id: %02X\n",
reg_00.bits.ID);
+ printk(KERN_DEBUG "....... : Delivery Type: %X\n",
reg_00.bits.delivery_type);
+ printk(KERN_DEBUG "....... : LTS : %X\n", reg_00.bits.LTS);
+ if (reg_00.bits.ID >= get_physical_broadcast())
+ UNEXPECTED_IO_APIC();
+ if (reg_00.bits.__reserved_1 || reg_00.bits.__reserved_2)
+ UNEXPECTED_IO_APIC();
+
+ printk(KERN_DEBUG ".... register #01: %08X\n", reg_01.raw);
+ printk(KERN_DEBUG "....... : max redirection entries: %04X\n",
reg_01.bits.entries);
+ if ( (reg_01.bits.entries != 0x0f) && /* older (Neptune) boards */
+ (reg_01.bits.entries != 0x17) && /* typical ISA+PCI boards */
+ (reg_01.bits.entries != 0x1b) && /* Compaq Proliant boards */
+ (reg_01.bits.entries != 0x1f) && /* dual Xeon boards */
+ (reg_01.bits.entries != 0x22) && /* bigger Xeon boards */
+ (reg_01.bits.entries != 0x2E) &&
+ (reg_01.bits.entries != 0x3F)
+ )
+ UNEXPECTED_IO_APIC();
+
+ printk(KERN_DEBUG "....... : PRQ implemented: %X\n",
reg_01.bits.PRQ);
+ printk(KERN_DEBUG "....... : IO APIC version: %04X\n",
reg_01.bits.version);
+ if ( (reg_01.bits.version != 0x01) && /* 82489DX IO-APICs */
+ (reg_01.bits.version != 0x10) && /* oldest IO-APICs */
+ (reg_01.bits.version != 0x11) && /* Pentium/Pro IO-APICs */
+ (reg_01.bits.version != 0x13) && /* Xeon IO-APICs */
+ (reg_01.bits.version != 0x20) /* Intel P64H (82806 AA) */
+ )
+ UNEXPECTED_IO_APIC();
+ if (reg_01.bits.__reserved_1 || reg_01.bits.__reserved_2)
+ UNEXPECTED_IO_APIC();
+
+ /*
+ * Some Intel chipsets with IO APIC VERSION of 0x1? don't have reg_02,
+ * but the value of reg_02 is read as the previous read register
+ * value, so ignore it if reg_02 == reg_01.
+ */
+ if (reg_01.bits.version >= 0x10 && reg_02.raw != reg_01.raw) {
+ printk(KERN_DEBUG ".... register #02: %08X\n", reg_02.raw);
+ printk(KERN_DEBUG "....... : arbitration: %02X\n",
reg_02.bits.arbitration);
+ if (reg_02.bits.__reserved_1 || reg_02.bits.__reserved_2)
+ UNEXPECTED_IO_APIC();
+ }
+
+ /*
+ * Some Intel chipsets with IO APIC VERSION of 0x2? don't have reg_02
+ * or reg_03, but the value of reg_0[23] is read as the previous read
+ * register value, so ignore it if reg_03 == reg_0[12].
+ */
+ if (reg_01.bits.version >= 0x20 && reg_03.raw != reg_02.raw &&
+ reg_03.raw != reg_01.raw) {
+ printk(KERN_DEBUG ".... register #03: %08X\n", reg_03.raw);
+ printk(KERN_DEBUG "....... : Boot DT : %X\n",
reg_03.bits.boot_DT);
+ if (reg_03.bits.__reserved_1)
+ UNEXPECTED_IO_APIC();
+ }
+
+ printk(KERN_DEBUG ".... IRQ redirection table:\n");
+
+ printk(KERN_DEBUG " NR Log Phy Mask Trig IRR Pol"
+ " Stat Dest Deli Vect: \n");
+
+ for (i = 0; i <= reg_01.bits.entries; i++) {
+ struct IO_APIC_route_entry entry;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ *(((int *)&entry)+0) = io_apic_read(apic, 0x10+i*2);
+ *(((int *)&entry)+1) = io_apic_read(apic, 0x11+i*2);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ printk(KERN_DEBUG " %02x %03X %02X ",
+ i,
+ entry.dest.logical.logical_dest,
+ entry.dest.physical.physical_dest
+ );
+
+ printk("%1d %1d %1d %1d %1d %1d %1d %02X\n",
+ entry.mask,
+ entry.trigger,
+ entry.irr,
+ entry.polarity,
+ entry.delivery_status,
+ entry.dest_mode,
+ entry.delivery_mode,
+ entry.vector
+ );
+ }
+ }
+ if (use_pci_vector())
+ printk(KERN_INFO "Using vector-based indexing\n");
+ printk(KERN_DEBUG "IRQ to pin mappings:\n");
+ for (i = 0; i < NR_IRQS; i++) {
+ struct irq_pin_list *entry = irq_2_pin + i;
+ if (entry->pin < 0)
+ continue;
+ if (use_pci_vector() && !platform_legacy_irq(i))
+ printk(KERN_DEBUG "IRQ%d ", IO_APIC_VECTOR(i));
+ else
+ printk(KERN_DEBUG "IRQ%d ", i);
+ for (;;) {
+ printk("-> %d:%d", entry->apic, entry->pin);
+ if (!entry->next)
+ break;
+ entry = irq_2_pin + entry->next;
+ }
+ printk("\n");
+ }
+
+ printk(KERN_INFO ".................................... done.\n");
+
+ return;
+}
+
+static void print_APIC_bitfield (int base)
+{
+ unsigned int v;
+ int i, j;
+
+ if (apic_verbosity == APIC_QUIET)
+ return;
+
+ printk(KERN_DEBUG "0123456789abcdef0123456789abcdef\n" KERN_DEBUG);
+ for (i = 0; i < 8; i++) {
+ v = apic_read(base + i*0x10);
+ for (j = 0; j < 32; j++) {
+ if (v & (1<<j))
+ printk("1");
+ else
+ printk("0");
+ }
+ printk("\n");
+ }
+}
+
+void /*__init*/ print_local_APIC(void * dummy)
+{
+ unsigned int v, ver, maxlvt;
+
+ if (apic_verbosity == APIC_QUIET)
+ return;
+
+ printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
+ smp_processor_id(), hard_smp_processor_id());
+ v = apic_read(APIC_ID);
+ printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, GET_APIC_ID(v));
+ v = apic_read(APIC_LVR);
+ printk(KERN_INFO "... APIC VERSION: %08x\n", v);
+ ver = GET_APIC_VERSION(v);
+ maxlvt = get_maxlvt();
+
+ v = apic_read(APIC_TASKPRI);
+ printk(KERN_DEBUG "... APIC TASKPRI: %08x (%02x)\n", v, v &
APIC_TPRI_MASK);
+
+ if (APIC_INTEGRATED(ver)) { /* !82489DX */
+ v = apic_read(APIC_ARBPRI);
+ printk(KERN_DEBUG "... APIC ARBPRI: %08x (%02x)\n", v,
+ v & APIC_ARBPRI_MASK);
+ v = apic_read(APIC_PROCPRI);
+ printk(KERN_DEBUG "... APIC PROCPRI: %08x\n", v);
+ }
+
+ v = apic_read(APIC_EOI);
+ printk(KERN_DEBUG "... APIC EOI: %08x\n", v);
+ v = apic_read(APIC_RRR);
+ printk(KERN_DEBUG "... APIC RRR: %08x\n", v);
+ v = apic_read(APIC_LDR);
+ printk(KERN_DEBUG "... APIC LDR: %08x\n", v);
+ v = apic_read(APIC_DFR);
+ printk(KERN_DEBUG "... APIC DFR: %08x\n", v);
+ v = apic_read(APIC_SPIV);
+ printk(KERN_DEBUG "... APIC SPIV: %08x\n", v);
+
+ printk(KERN_DEBUG "... APIC ISR field:\n");
+ print_APIC_bitfield(APIC_ISR);
+ printk(KERN_DEBUG "... APIC TMR field:\n");
+ print_APIC_bitfield(APIC_TMR);
+ printk(KERN_DEBUG "... APIC IRR field:\n");
+ print_APIC_bitfield(APIC_IRR);
+
+ if (APIC_INTEGRATED(ver)) { /* !82489DX */
+ if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
+ apic_write(APIC_ESR, 0);
+ v = apic_read(APIC_ESR);
+ printk(KERN_DEBUG "... APIC ESR: %08x\n", v);
+ }
+
+ v = apic_read(APIC_ICR);
+ printk(KERN_DEBUG "... APIC ICR: %08x\n", v);
+ v = apic_read(APIC_ICR2);
+ printk(KERN_DEBUG "... APIC ICR2: %08x\n", v);
+
+ v = apic_read(APIC_LVTT);
+ printk(KERN_DEBUG "... APIC LVTT: %08x\n", v);
+
+ if (maxlvt > 3) { /* PC is LVT#4. */
+ v = apic_read(APIC_LVTPC);
+ printk(KERN_DEBUG "... APIC LVTPC: %08x\n", v);
+ }
+ v = apic_read(APIC_LVT0);
+ printk(KERN_DEBUG "... APIC LVT0: %08x\n", v);
+ v = apic_read(APIC_LVT1);
+ printk(KERN_DEBUG "... APIC LVT1: %08x\n", v);
+
+ if (maxlvt > 2) { /* ERR is LVT#3. */
+ v = apic_read(APIC_LVTERR);
+ printk(KERN_DEBUG "... APIC LVTERR: %08x\n", v);
+ }
+
+ v = apic_read(APIC_TMICT);
+ printk(KERN_DEBUG "... APIC TMICT: %08x\n", v);
+ v = apic_read(APIC_TMCCT);
+ printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v);
+ v = apic_read(APIC_TDCR);
+ printk(KERN_DEBUG "... APIC TDCR: %08x\n", v);
+ printk("\n");
+}
+
+void print_all_local_APICs (void)
+{
+ on_each_cpu(print_local_APIC, NULL, 1, 1);
+}
+
+void /*__init*/ print_PIC(void)
+{
+ extern spinlock_t i8259A_lock;
+ unsigned int v;
+ unsigned long flags;
+
+ if (apic_verbosity == APIC_QUIET)
+ return;
+
+ printk(KERN_DEBUG "\nprinting PIC contents\n");
+
+ spin_lock_irqsave(&i8259A_lock, flags);
+
+ v = inb(0xa1) << 8 | inb(0x21);
+ printk(KERN_DEBUG "... PIC IMR: %04x\n", v);
+
+ v = inb(0xa0) << 8 | inb(0x20);
+ printk(KERN_DEBUG "... PIC IRR: %04x\n", v);
+
+ outb(0x0b,0xa0);
+ outb(0x0b,0x20);
+ v = inb(0xa0) << 8 | inb(0x20);
+ outb(0x0a,0xa0);
+ outb(0x0a,0x20);
+
+ spin_unlock_irqrestore(&i8259A_lock, flags);
+
+ printk(KERN_DEBUG "... PIC ISR: %04x\n", v);
+
+ v = inb(0x4d1) << 8 | inb(0x4d0);
+ printk(KERN_DEBUG "... PIC ELCR: %04x\n", v);
+}
+#else
+void __init print_IO_APIC(void) { }
+#endif /* !CONFIG_XEN */
+
+static void __init enable_IO_APIC(void)
+{
+ union IO_APIC_reg_01 reg_01;
+ int i;
+ unsigned long flags;
+
+ for (i = 0; i < PIN_MAP_SIZE; i++) {
+ irq_2_pin[i].pin = -1;
+ irq_2_pin[i].next = 0;
+ }
+ if (!pirqs_enabled)
+ for (i = 0; i < MAX_PIRQS; i++)
+ pirq_entries[i] = -1;
+
+ /*
+ * The number of IO-APIC IRQ registers (== #pins):
+ */
+ for (i = 0; i < nr_ioapics; i++) {
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_01.raw = io_apic_read(i, 1);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ nr_ioapic_registers[i] = reg_01.bits.entries+1;
+ }
+
+ /*
+ * Do not trust the IO-APIC being empty at bootup
+ */
+ clear_IO_APIC();
+}
+
+/*
+ * Not an __init, needed by the reboot code
+ */
+void disable_IO_APIC(void)
+{
+ /*
+ * Clear the IO-APIC before rebooting:
+ */
+ clear_IO_APIC();
+
+#ifndef CONFIG_XEN
+ disconnect_bsp_APIC();
+#endif
+}
+
+/*
+ * function to set the IO-APIC physical IDs based on the
+ * values stored in the MPC table.
+ *
+ * by Matt Domsch <Matt_Domsch@xxxxxxxx> Tue Dec 21 12:25:05 CST 1999
+ */
+
+#if !defined(CONFIG_XEN) && !defined(CONFIG_X86_NUMAQ)
+static void __init setup_ioapic_ids_from_mpc(void)
+{
+ union IO_APIC_reg_00 reg_00;
+ physid_mask_t phys_id_present_map;
+ int apic;
+ int i;
+ unsigned char old_id;
+ unsigned long flags;
+
+ /*
+ * This is broken; anything with a real cpu count has to
+ * circumvent this idiocy regardless.
+ */
+ phys_id_present_map = ioapic_phys_id_map(phys_cpu_present_map);
+
+ /*
+ * Set the IOAPIC ID to the value stored in the MPC table.
+ */
+ for (apic = 0; apic < nr_ioapics; apic++) {
+
+ /* Read the register 0 value */
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(apic, 0);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ old_id = mp_ioapics[apic].mpc_apicid;
+
+ if (mp_ioapics[apic].mpc_apicid >= get_physical_broadcast()) {
+ printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the
MPC table!...\n",
+ apic, mp_ioapics[apic].mpc_apicid);
+ printk(KERN_ERR "... fixing up to %d. (tell your hw
vendor)\n",
+ reg_00.bits.ID);
+ mp_ioapics[apic].mpc_apicid = reg_00.bits.ID;
+ }
+
+ /* Don't check I/O APIC IDs for some xAPIC systems. They have
+ * no meaning without the serial APIC bus. */
+ if (NO_IOAPIC_CHECK)
+ continue;
+ /*
+ * Sanity check, is the ID really free? Every APIC in a
+ * system must have a unique ID or we get lots of nice
+ * 'stuck on smp_invalidate_needed IPI wait' messages.
+ */
+ if (check_apicid_used(phys_id_present_map,
+ mp_ioapics[apic].mpc_apicid)) {
+ printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already
used!...\n",
+ apic, mp_ioapics[apic].mpc_apicid);
+ for (i = 0; i < get_physical_broadcast(); i++)
+ if (!physid_isset(i, phys_id_present_map))
+ break;
+ if (i >= get_physical_broadcast())
+ panic("Max APIC ID exceeded!\n");
+ printk(KERN_ERR "... fixing up to %d. (tell your hw
vendor)\n",
+ i);
+ physid_set(i, phys_id_present_map);
+ mp_ioapics[apic].mpc_apicid = i;
+ } else {
+ physid_mask_t tmp;
+ tmp =
apicid_to_cpu_present(mp_ioapics[apic].mpc_apicid);
+ apic_printk(APIC_VERBOSE, "Setting %d in the "
+ "phys_id_present_map\n",
+ mp_ioapics[apic].mpc_apicid);
+ physids_or(phys_id_present_map, phys_id_present_map,
tmp);
+ }
+
+
+ /*
+ * We need to adjust the IRQ routing table
+ * if the ID changed.
+ */
+ if (old_id != mp_ioapics[apic].mpc_apicid)
+ for (i = 0; i < mp_irq_entries; i++)
+ if (mp_irqs[i].mpc_dstapic == old_id)
+ mp_irqs[i].mpc_dstapic
+ = mp_ioapics[apic].mpc_apicid;
+
+ /*
+ * Read the right value from the MPC table and
+ * write it into the ID register.
+ */
+ apic_printk(APIC_VERBOSE, KERN_INFO
+ "...changing IO-APIC physical APIC ID to %d ...",
+ mp_ioapics[apic].mpc_apicid);
+
+ reg_00.bits.ID = mp_ioapics[apic].mpc_apicid;
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(apic, 0, reg_00.raw);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ /*
+ * Sanity check
+ */
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(apic, 0);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ if (reg_00.bits.ID != mp_ioapics[apic].mpc_apicid)
+ printk("could not set ID!\n");
+ else
+ apic_printk(APIC_VERBOSE, " ok.\n");
+ }
+}
+#else
+static void __init setup_ioapic_ids_from_mpc(void) { }
+#endif
+
+#ifndef CONFIG_XEN
+/*
+ * There is a nasty bug in some older SMP boards, their mptable lies
+ * about the timer IRQ. We do the following to work around the situation:
+ *
+ * - timer IRQ defaults to IO-APIC IRQ
+ * - if this function detects that timer IRQs are defunct, then we fall
+ * back to ISA timer IRQs
+ */
+static int __init timer_irq_works(void)
+{
+ unsigned long t1 = jiffies;
+
+ local_irq_enable();
+ /* Let ten ticks pass... */
+ mdelay((10 * 1000) / HZ);
+
+ /*
+ * Expect a few ticks at least, to be sure some possible
+ * glue logic does not lock up after one or two first
+ * ticks in a non-ExtINT mode. Also the local APIC
+ * might have cached one ExtINT interrupt. Finally, at
+ * least one tick may be lost due to delays.
+ */
+ if (jiffies - t1 > 4)
+ return 1;
+
+ return 0;
+}
+
+/*
+ * In the SMP+IOAPIC case it might happen that there are an unspecified
+ * number of pending IRQ events unhandled. These cases are very rare,
+ * so we 'resend' these IRQs via IPIs, to the same CPU. It's much
+ * better to do it this way as thus we do not have to be aware of
+ * 'pending' interrupts in the IRQ path, except at this point.
+ */
+/*
+ * Edge triggered needs to resend any interrupt
+ * that was delayed but this is now handled in the device
+ * independent code.
+ */
+
+/*
+ * Starting up a edge-triggered IO-APIC interrupt is
+ * nasty - we need to make sure that we get the edge.
+ * If it is already asserted for some reason, we need
+ * return 1 to indicate that is was pending.
+ *
+ * This is not complete - we should be able to fake
+ * an edge even if it isn't on the 8259A...
+ */
+static unsigned int startup_edge_ioapic_irq(unsigned int irq)
+{
+ int was_pending = 0;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ if (irq < 16) {
+ disable_8259A_irq(irq);
+ if (i8259A_irq_pending(irq))
+ was_pending = 1;
+ }
+ __unmask_IO_APIC_irq(irq);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return was_pending;
+}
+
+/*
+ * Once we have recorded IRQ_PENDING already, we can mask the
+ * interrupt for real. This prevents IRQ storms from unhandled
+ * devices.
+ */
+static void ack_edge_ioapic_irq(unsigned int irq)
+{
+ move_irq(irq);
+ if ((irq_desc[irq].status & (IRQ_PENDING | IRQ_DISABLED))
+ == (IRQ_PENDING | IRQ_DISABLED))
+ mask_IO_APIC_irq(irq);
+ ack_APIC_irq();
+}
+
+/*
+ * Level triggered interrupts can just be masked,
+ * and shutting down and starting up the interrupt
+ * is the same as enabling and disabling them -- except
+ * with a startup need to return a "was pending" value.
+ *
+ * Level triggered interrupts are special because we
+ * do not touch any IO-APIC register while handling
+ * them. We ack the APIC in the end-IRQ handler, not
+ * in the start-IRQ-handler. Protection against reentrance
+ * from the same interrupt is still provided, both by the
+ * generic IRQ layer and by the fact that an unacked local
+ * APIC does not accept IRQs.
+ */
+static unsigned int startup_level_ioapic_irq (unsigned int irq)
+{
+ unmask_IO_APIC_irq(irq);
+
+ return 0; /* don't check for pending */
+}
+
+static void end_level_ioapic_irq (unsigned int irq)
+{
+ unsigned long v;
+ int i;
+
+ move_irq(irq);
+/*
+ * It appears there is an erratum which affects at least version 0x11
+ * of I/O APIC (that's the 82093AA and cores integrated into various
+ * chipsets). Under certain conditions a level-triggered interrupt is
+ * erroneously delivered as edge-triggered one but the respective IRR
+ * bit gets set nevertheless. As a result the I/O unit expects an EOI
+ * message but it will never arrive and further interrupts are blocked
+ * from the source. The exact reason is so far unknown, but the
+ * phenomenon was observed when two consecutive interrupt requests
+ * from a given source get delivered to the same CPU and the source is
+ * temporarily disabled in between.
+ *
+ * A workaround is to simulate an EOI message manually. We achieve it
+ * by setting the trigger mode to edge and then to level when the edge
+ * trigger mode gets detected in the TMR of a local APIC for a
+ * level-triggered interrupt. We mask the source for the time of the
+ * operation to prevent an edge-triggered interrupt escaping meanwhile.
+ * The idea is from Manfred Spraul. --macro
+ */
+ i = IO_APIC_VECTOR(irq);
+
+ v = apic_read(APIC_TMR + ((i & ~0x1f) >> 1));
+
+ ack_APIC_irq();
+
+ if (!(v & (1 << (i & 0x1f)))) {
+ atomic_inc(&irq_mis_count);
+ spin_lock(&ioapic_lock);
+ __mask_and_edge_IO_APIC_irq(irq);
+ __unmask_and_level_IO_APIC_irq(irq);
+ spin_unlock(&ioapic_lock);
+ }
+}
+
+#ifdef CONFIG_PCI_MSI
+static unsigned int startup_edge_ioapic_vector(unsigned int vector)
+{
+ int irq = vector_to_irq(vector);
+
+ return startup_edge_ioapic_irq(irq);
+}
+
+static void ack_edge_ioapic_vector(unsigned int vector)
+{
+ int irq = vector_to_irq(vector);
+
+ ack_edge_ioapic_irq(irq);
+}
+
+static unsigned int startup_level_ioapic_vector (unsigned int vector)
+{
+ int irq = vector_to_irq(vector);
+
+ return startup_level_ioapic_irq (irq);
+}
+
+static void end_level_ioapic_vector (unsigned int vector)
+{
+ int irq = vector_to_irq(vector);
+
+ end_level_ioapic_irq(irq);
+}
+
+static void mask_IO_APIC_vector (unsigned int vector)
+{
+ int irq = vector_to_irq(vector);
+
+ mask_IO_APIC_irq(irq);
+}
+
+static void unmask_IO_APIC_vector (unsigned int vector)
+{
+ int irq = vector_to_irq(vector);
+
+ unmask_IO_APIC_irq(irq);
+}
+
+static void set_ioapic_affinity_vector (unsigned int vector,
+ cpumask_t cpu_mask)
+{
+ int irq = vector_to_irq(vector);
+
+ set_ioapic_affinity_irq(irq, cpu_mask);
+}
+#endif
+
+/*
+ * Level and edge triggered IO-APIC interrupts need different handling,
+ * so we use two separate IRQ descriptors. Edge triggered IRQs can be
+ * handled with the level-triggered descriptor, but that one has slightly
+ * more overhead. Level-triggered interrupts cannot be handled with the
+ * edge-triggered handler, without risking IRQ storms and other ugly
+ * races.
+ */
+static struct hw_interrupt_type ioapic_edge_type = {
+ .typename = "IO-APIC-edge",
+ .startup = startup_edge_ioapic,
+ .shutdown = shutdown_edge_ioapic,
+ .enable = enable_edge_ioapic,
+ .disable = disable_edge_ioapic,
+ .ack = ack_edge_ioapic,
+ .end = end_edge_ioapic,
+ .set_affinity = set_ioapic_affinity,
+};
+
+static struct hw_interrupt_type ioapic_level_type = {
+ .typename = "IO-APIC-level",
+ .startup = startup_level_ioapic,
+ .shutdown = shutdown_level_ioapic,
+ .enable = enable_level_ioapic,
+ .disable = disable_level_ioapic,
+ .ack = mask_and_ack_level_ioapic,
+ .end = end_level_ioapic,
+ .set_affinity = set_ioapic_affinity,
+};
+#endif /* !CONFIG_XEN */
+
+static inline void init_IO_APIC_traps(void)
+{
+ int irq;
+
+ /*
+ * NOTE! The local APIC isn't very good at handling
+ * multiple interrupts at the same interrupt level.
+ * As the interrupt level is determined by taking the
+ * vector number and shifting that right by 4, we
+ * want to spread these out a bit so that they don't
+ * all fall in the same interrupt level.
+ *
+ * Also, we've got to be careful not to trash gate
+ * 0x80, because int 0x80 is hm, kind of importantish. ;)
+ */
+ for (irq = 0; irq < NR_IRQS ; irq++) {
+ int tmp = irq;
+ if (use_pci_vector()) {
+ if (!platform_legacy_irq(tmp))
+ if ((tmp = vector_to_irq(tmp)) == -1)
+ continue;
+ }
+ if (IO_APIC_IRQ(tmp) && !IO_APIC_VECTOR(tmp)) {
+ /*
+ * Hmm.. We don't have an entry for this,
+ * so default to an old-fashioned 8259
+ * interrupt if we can..
+ */
+ if (irq < 16)
+ make_8259A_irq(irq);
+#ifndef CONFIG_XEN
+ else
+ /* Strange. Oh, well.. */
+ irq_desc[irq].handler = &no_irq_type;
+#endif
+ }
+ }
+}
+
+#ifndef CONFIG_XEN
+static void enable_lapic_irq (unsigned int irq)
+{
+ unsigned long v;
+
+ v = apic_read(APIC_LVT0);
+ apic_write_around(APIC_LVT0, v & ~APIC_LVT_MASKED);
+}
+
+static void disable_lapic_irq (unsigned int irq)
+{
+ unsigned long v;
+
+ v = apic_read(APIC_LVT0);
+ apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED);
+}
+
+static void ack_lapic_irq (unsigned int irq)
+{
+ ack_APIC_irq();
+}
+
+static void end_lapic_irq (unsigned int i) { /* nothing */ }
+
+static struct hw_interrupt_type lapic_irq_type = {
+ .typename = "local-APIC-edge",
+ .startup = NULL, /* startup_irq() not used for IRQ0 */
+ .shutdown = NULL, /* shutdown_irq() not used for IRQ0 */
+ .enable = enable_lapic_irq,
+ .disable = disable_lapic_irq,
+ .ack = ack_lapic_irq,
+ .end = end_lapic_irq
+};
+
+static void setup_nmi (void)
+{
+ /*
+ * Dirty trick to enable the NMI watchdog ...
+ * We put the 8259A master into AEOI mode and
+ * unmask on all local APICs LVT0 as NMI.
+ *
+ * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire')
+ * is from Maciej W. Rozycki - so we do not have to EOI from
+ * the NMI handler or the timer interrupt.
+ */
+ apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ...");
+
+ on_each_cpu(enable_NMI_through_LVT0, NULL, 1, 1);
+
+ apic_printk(APIC_VERBOSE, " done.\n");
+}
+
+/*
+ * This looks a bit hackish but it's about the only one way of sending
+ * a few INTA cycles to 8259As and any associated glue logic. ICR does
+ * not support the ExtINT mode, unfortunately. We need to send these
+ * cycles as some i82489DX-based boards have glue logic that keeps the
+ * 8259A interrupt line asserted until INTA. --macro
+ */
+static inline void unlock_ExtINT_logic(void)
+{
+ int pin, i;
+ struct IO_APIC_route_entry entry0, entry1;
+ unsigned char save_control, save_freq_select;
+ unsigned long flags;
+
+ pin = find_isa_irq_pin(8, mp_INT);
+ if (pin == -1)
+ return;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ *(((int *)&entry0) + 1) = io_apic_read(0, 0x11 + 2 * pin);
+ *(((int *)&entry0) + 0) = io_apic_read(0, 0x10 + 2 * pin);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+ clear_IO_APIC_pin(0, pin);
+
+ memset(&entry1, 0, sizeof(entry1));
+
+ entry1.dest_mode = 0; /* physical delivery */
+ entry1.mask = 0; /* unmask IRQ now */
+ entry1.dest.physical.physical_dest = hard_smp_processor_id();
+ entry1.delivery_mode = dest_ExtINT;
+ entry1.polarity = entry0.polarity;
+ entry1.trigger = 0;
+ entry1.vector = 0;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry1) + 1));
+ io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry1) + 0));
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ save_control = CMOS_READ(RTC_CONTROL);
+ save_freq_select = CMOS_READ(RTC_FREQ_SELECT);
+ CMOS_WRITE((save_freq_select & ~RTC_RATE_SELECT) | 0x6,
+ RTC_FREQ_SELECT);
+ CMOS_WRITE(save_control | RTC_PIE, RTC_CONTROL);
+
+ i = 100;
+ while (i-- > 0) {
+ mdelay(10);
+ if ((CMOS_READ(RTC_INTR_FLAGS) & RTC_PF) == RTC_PF)
+ i -= 10;
+ }
+
+ CMOS_WRITE(save_control, RTC_CONTROL);
+ CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
+ clear_IO_APIC_pin(0, pin);
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry0) + 1));
+ io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry0) + 0));
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+/*
+ * This code may look a bit paranoid, but it's supposed to cooperate with
+ * a wide range of boards and BIOS bugs. Fortunately only the timer IRQ
+ * is so screwy. Thanks to Brian Perkins for testing/hacking this beast
+ * fanatically on his truly buggy board.
+ */
+static inline void check_timer(void)
+{
+ int pin1, pin2;
+ int vector;
+
+ /*
+ * get/set the timer IRQ vector:
+ */
+ disable_8259A_irq(0);
+ vector = assign_irq_vector(0);
+ set_intr_gate(vector, interrupt[0]);
+
+ /*
+ * Subtle, code in do_timer_interrupt() expects an AEOI
+ * mode for the 8259A whenever interrupts are routed
+ * through I/O APICs. Also IRQ0 has to be enabled in
+ * the 8259A which implies the virtual wire has to be
+ * disabled in the local APIC.
+ */
+ apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
+ init_8259A(1);
+ timer_ack = 1;
+ enable_8259A_irq(0);
+
+ pin1 = find_isa_irq_pin(0, mp_INT);
+ pin2 = find_isa_irq_pin(0, mp_ExtINT);
+
+ printk(KERN_INFO "..TIMER: vector=0x%02X pin1=%d pin2=%d\n", vector,
pin1, pin2);
+
+ if (pin1 != -1) {
+ /*
+ * Ok, does IRQ0 through the IOAPIC work?
+ */
+ unmask_IO_APIC_irq(0);
+ if (timer_irq_works()) {
+ if (nmi_watchdog == NMI_IO_APIC) {
+ disable_8259A_irq(0);
+ setup_nmi();
+ enable_8259A_irq(0);
+ check_nmi_watchdog();
+ }
+ return;
+ }
+ clear_IO_APIC_pin(0, pin1);
+ printk(KERN_ERR "..MP-BIOS bug: 8254 timer not connected to
IO-APIC\n");
+ }
+
+ printk(KERN_INFO "...trying to set up timer (IRQ0) through the 8259A
... ");
+ if (pin2 != -1) {
+ printk("\n..... (found pin %d) ...", pin2);
+ /*
+ * legacy devices should be connected to IO APIC #0
+ */
+ setup_ExtINT_IRQ0_pin(pin2, vector);
+ if (timer_irq_works()) {
+ printk("works.\n");
+ if (pin1 != -1)
+ replace_pin_at_irq(0, 0, pin1, 0, pin2);
+ else
+ add_pin_to_irq(0, 0, pin2);
+ if (nmi_watchdog == NMI_IO_APIC) {
+ setup_nmi();
+ check_nmi_watchdog();
+ }
+ return;
+ }
+ /*
+ * Cleanup, just in case ...
+ */
+ clear_IO_APIC_pin(0, pin2);
+ }
+ printk(" failed.\n");
+
+ if (nmi_watchdog == NMI_IO_APIC) {
+ printk(KERN_WARNING "timer doesn't work through the IO-APIC -
disabling NMI Watchdog!\n");
+ nmi_watchdog = 0;
+ }
+
+ printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
+
+ disable_8259A_irq(0);
+ irq_desc[0].handler = &lapic_irq_type;
+ apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector); /* Fixed mode */
+ enable_8259A_irq(0);
+
+ if (timer_irq_works()) {
+ printk(" works.\n");
+ return;
+ }
+ apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector);
+ printk(" failed.\n");
+
+ printk(KERN_INFO "...trying to set up timer as ExtINT IRQ...");
+
+ timer_ack = 0;
+ init_8259A(0);
+ make_8259A_irq(0);
+ apic_write_around(APIC_LVT0, APIC_DM_EXTINT);
+
+ unlock_ExtINT_logic();
+
+ if (timer_irq_works()) {
+ printk(" works.\n");
+ return;
+ }
+ printk(" failed :(.\n");
+ panic("IO-APIC + timer doesn't work! Boot with apic=debug and send a "
+ "report. Then try booting with the 'noapic' option");
+}
+#else
+#define check_timer() ((void)0)
+#endif
+
+/*
+ *
+ * IRQ's that are handled by the PIC in the MPS IOAPIC case.
+ * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ.
+ * Linux doesn't really care, as it's not actually used
+ * for any interrupt handling anyway.
+ */
+#define PIC_IRQS (1 << PIC_CASCADE_IR)
+
+void __init setup_IO_APIC(void)
+{
+ enable_IO_APIC();
+
+ if (acpi_ioapic)
+ io_apic_irqs = ~0; /* all IRQs go through IOAPIC */
+ else
+ io_apic_irqs = ~PIC_IRQS;
+
+ printk("ENABLING IO-APIC IRQs\n");
+
+ /*
+ * Set up IO-APIC IRQ routing.
+ */
+ if (!acpi_ioapic)
+ setup_ioapic_ids_from_mpc();
+#ifndef CONFIG_XEN
+ sync_Arb_IDs();
+#endif
+ setup_IO_APIC_irqs();
+ init_IO_APIC_traps();
+ check_timer();
+ if (!acpi_ioapic)
+ print_IO_APIC();
+}
+
+/*
+ * Called after all the initialization is done. If we didnt find any
+ * APIC bugs then we can allow the modify fast path
+ */
+
+static int __init io_apic_bug_finalize(void)
+{
+ if(sis_apic_bug == -1)
+ sis_apic_bug = 0;
+ return 0;
+}
+
+late_initcall(io_apic_bug_finalize);
+
+struct sysfs_ioapic_data {
+ struct sys_device dev;
+ struct IO_APIC_route_entry entry[0];
+};
+static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS];
+
+static int ioapic_suspend(struct sys_device *dev, u32 state)
+{
+ struct IO_APIC_route_entry *entry;
+ struct sysfs_ioapic_data *data;
+ unsigned long flags;
+ int i;
+
+ data = container_of(dev, struct sysfs_ioapic_data, dev);
+ entry = data->entry;
+ spin_lock_irqsave(&ioapic_lock, flags);
+ for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) {
+ *(((int *)entry) + 1) = io_apic_read(dev->id, 0x11 + 2 * i);
+ *(((int *)entry) + 0) = io_apic_read(dev->id, 0x10 + 2 * i);
+ }
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return 0;
+}
+
+static int ioapic_resume(struct sys_device *dev)
+{
+ struct IO_APIC_route_entry *entry;
+ struct sysfs_ioapic_data *data;
+ unsigned long flags;
+ union IO_APIC_reg_00 reg_00;
+ int i;
+
+ data = container_of(dev, struct sysfs_ioapic_data, dev);
+ entry = data->entry;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(dev->id, 0);
+ if (reg_00.bits.ID != mp_ioapics[dev->id].mpc_apicid) {
+ reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid;
+ io_apic_write(dev->id, 0, reg_00.raw);
+ }
+ for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) {
+ io_apic_write(dev->id, 0x11+2*i, *(((int *)entry)+1));
+ io_apic_write(dev->id, 0x10+2*i, *(((int *)entry)+0));
+ }
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return 0;
+}
+
+static struct sysdev_class ioapic_sysdev_class = {
+ set_kset_name("ioapic"),
+ .suspend = ioapic_suspend,
+ .resume = ioapic_resume,
+};
+
+static int __init ioapic_init_sysfs(void)
+{
+ struct sys_device * dev;
+ int i, size, error = 0;
+
+ error = sysdev_class_register(&ioapic_sysdev_class);
+ if (error)
+ return error;
+
+ for (i = 0; i < nr_ioapics; i++ ) {
+ size = sizeof(struct sys_device) + nr_ioapic_registers[i]
+ * sizeof(struct IO_APIC_route_entry);
+ mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL);
+ if (!mp_ioapic_data[i]) {
+ printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
+ continue;
+ }
+ memset(mp_ioapic_data[i], 0, size);
+ dev = &mp_ioapic_data[i]->dev;
+ dev->id = i;
+ dev->cls = &ioapic_sysdev_class;
+ error = sysdev_register(dev);
+ if (error) {
+ kfree(mp_ioapic_data[i]);
+ mp_ioapic_data[i] = NULL;
+ printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
+ continue;
+ }
+ }
+
+ return 0;
+}
+
+device_initcall(ioapic_init_sysfs);
+
+/* --------------------------------------------------------------------------
+ ACPI-based IOAPIC Configuration
+ --------------------------------------------------------------------------
*/
+
+#ifdef CONFIG_ACPI_BOOT
+
+int __init io_apic_get_unique_id (int ioapic, int apic_id)
+{
+#ifndef CONFIG_XEN
+ union IO_APIC_reg_00 reg_00;
+ static physid_mask_t apic_id_map = PHYSID_MASK_NONE;
+ physid_mask_t tmp;
+ unsigned long flags;
+ int i = 0;
+
+ /*
+ * The P4 platform supports up to 256 APIC IDs on two separate APIC
+ * buses (one for LAPICs, one for IOAPICs), where predecessors only
+ * supports up to 16 on one shared APIC bus.
+ *
+ * TBD: Expand LAPIC/IOAPIC support on P4-class systems to take full
+ * advantage of new APIC bus architecture.
+ */
+
+ if (physids_empty(apic_id_map))
+ apic_id_map = ioapic_phys_id_map(phys_cpu_present_map);
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(ioapic, 0);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ if (apic_id >= get_physical_broadcast()) {
+ printk(KERN_WARNING "IOAPIC[%d]: Invalid apic_id %d, trying "
+ "%d\n", ioapic, apic_id, reg_00.bits.ID);
+ apic_id = reg_00.bits.ID;
+ }
+
+ /*
+ * Every APIC in a system must have a unique ID or we get lots of nice
+ * 'stuck on smp_invalidate_needed IPI wait' messages.
+ */
+ if (check_apicid_used(apic_id_map, apic_id)) {
+
+ for (i = 0; i < get_physical_broadcast(); i++) {
+ if (!check_apicid_used(apic_id_map, i))
+ break;
+ }
+
+ if (i == get_physical_broadcast())
+ panic("Max apic_id exceeded!\n");
+
+ printk(KERN_WARNING "IOAPIC[%d]: apic_id %d already used, "
+ "trying %d\n", ioapic, apic_id, i);
+
+ apic_id = i;
+ }
+
+ tmp = apicid_to_cpu_present(apic_id);
+ physids_or(apic_id_map, apic_id_map, tmp);
+
+ if (reg_00.bits.ID != apic_id) {
+ reg_00.bits.ID = apic_id;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(ioapic, 0, reg_00.raw);
+ reg_00.raw = io_apic_read(ioapic, 0);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ /* Sanity check */
+ if (reg_00.bits.ID != apic_id)
+ panic("IOAPIC[%d]: Unable change apic_id!\n", ioapic);
+ }
+
+ apic_printk(APIC_VERBOSE, KERN_INFO
+ "IOAPIC[%d]: Assigned apic_id %d\n", ioapic, apic_id);
+#endif /* !CONFIG_XEN */
+
+ return apic_id;
+}
+
+
+int __init io_apic_get_version (int ioapic)
+{
+ union IO_APIC_reg_01 reg_01;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_01.raw = io_apic_read(ioapic, 1);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return reg_01.bits.version;
+}
+
+
+int __init io_apic_get_redir_entries (int ioapic)
+{
+ union IO_APIC_reg_01 reg_01;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ reg_01.raw = io_apic_read(ioapic, 1);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return reg_01.bits.entries;
+}
+
+
+int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int
active_high_low)
+{
+ struct IO_APIC_route_entry entry;
+ unsigned long flags;
+
+ if (!IO_APIC_IRQ(irq)) {
+ printk(KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
+ ioapic);
+ return -EINVAL;
+ }
+
+ /*
+ * Generate a PCI IRQ routing entry and program the IOAPIC accordingly.
+ * Note that we mask (disable) IRQs now -- these get enabled when the
+ * corresponding device driver registers for this IRQ.
+ */
+
+ memset(&entry,0,sizeof(entry));
+
+ entry.delivery_mode = INT_DELIVERY_MODE;
+ entry.dest_mode = INT_DEST_MODE;
+ entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS);
+ entry.trigger = edge_level;
+ entry.polarity = active_high_low;
+ entry.mask = 1;
+
+ /*
+ * IRQs < 16 are already in the irq_2_pin[] map
+ */
+ if (irq >= 16)
+ add_pin_to_irq(irq, ioapic, pin);
+
+ entry.vector = assign_irq_vector(irq);
+
+ apic_printk(APIC_DEBUG, KERN_DEBUG "IOAPIC[%d]: Set PCI routing entry "
+ "(%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i)\n", ioapic,
+ mp_ioapics[ioapic].mpc_apicid, pin, entry.vector, irq,
+ edge_level, active_high_low);
+
+ ioapic_register_intr(irq, entry.vector, edge_level);
+
+ if (!ioapic && (irq < 16))
+ disable_8259A_irq(irq);
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(ioapic, 0x11+2*pin, *(((int *)&entry)+1));
+ io_apic_write(ioapic, 0x10+2*pin, *(((int *)&entry)+0));
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return 0;
+}
+
+#endif /*CONFIG_ACPI_BOOT*/
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/desc.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/desc.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,142 @@
+#ifndef __ARCH_DESC_H
+#define __ARCH_DESC_H
+
+#include <asm/ldt.h>
+#include <asm/segment.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/preempt.h>
+#include <linux/smp.h>
+
+#include <asm/mmu.h>
+
+extern struct desc_struct cpu_gdt_table[NR_CPUS][GDT_ENTRIES];
+
+struct Xgt_desc_struct {
+ unsigned short size;
+ unsigned long address __attribute__((packed));
+ unsigned short pad;
+} __attribute__ ((packed));
+
+extern struct Xgt_desc_struct idt_descr, cpu_gdt_descr[NR_CPUS];
+
+#define load_TR_desc() __asm__ __volatile__("ltr %%ax"::"a" (GDT_ENTRY_TSS*8))
+#define load_LDT_desc() __asm__ __volatile__("lldt %%ax"::"a"
(GDT_ENTRY_LDT*8))
+
+#define get_cpu_gdt_table(_cpu) ((struct desc_struct
*)cpu_gdt_descr[(_cpu)].address)
+
+/*
+ * This is the ldt that every process will get unless we need
+ * something other than this.
+ */
+extern struct desc_struct default_ldt[];
+extern void set_intr_gate(unsigned int irq, void * addr);
+
+#define _set_tssldt_desc(n,addr,limit,type) \
+__asm__ __volatile__ ("movw %w3,0(%2)\n\t" \
+ "movw %%ax,2(%2)\n\t" \
+ "rorl $16,%%eax\n\t" \
+ "movb %%al,4(%2)\n\t" \
+ "movb %4,5(%2)\n\t" \
+ "movb $0,6(%2)\n\t" \
+ "movb %%ah,7(%2)\n\t" \
+ "rorl $16,%%eax" \
+ : "=m"(*(n)) : "a" (addr), "r"(n), "ir"(limit), "i"(type))
+
+static inline void __set_tss_desc(unsigned int cpu, unsigned int entry, void
*addr)
+{
+ _set_tssldt_desc(&get_cpu_gdt_table(cpu)[entry], (int)addr,
+ offsetof(struct tss_struct, __cacheline_filler) - 1, 0x89);
+}
+
+#define set_tss_desc(cpu,addr) __set_tss_desc(cpu, GDT_ENTRY_TSS, addr)
+
+static inline void set_ldt_desc(unsigned int cpu, void *addr, unsigned int
size)
+{
+ _set_tssldt_desc(&get_cpu_gdt_table(cpu)[GDT_ENTRY_LDT],
+ (int)addr, ((size << 3)-1), 0x82);
+}
+
+#define LDT_entry_a(info) \
+ ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
+
+#define LDT_entry_b(info) \
+ (((info)->base_addr & 0xff000000) | \
+ (((info)->base_addr & 0x00ff0000) >> 16) | \
+ ((info)->limit & 0xf0000) | \
+ (((info)->read_exec_only ^ 1) << 9) | \
+ ((info)->contents << 10) | \
+ (((info)->seg_not_present ^ 1) << 15) | \
+ ((info)->seg_32bit << 22) | \
+ ((info)->limit_in_pages << 23) | \
+ ((info)->useable << 20) | \
+ 0x7000)
+
+#define LDT_empty(info) (\
+ (info)->base_addr == 0 && \
+ (info)->limit == 0 && \
+ (info)->contents == 0 && \
+ (info)->read_exec_only == 1 && \
+ (info)->seg_32bit == 0 && \
+ (info)->limit_in_pages == 0 && \
+ (info)->seg_not_present == 1 && \
+ (info)->useable == 0 )
+
+#if TLS_SIZE != 24
+# error update this code.
+#endif
+
+static inline void load_TLS(struct thread_struct *t, unsigned int cpu)
+{
+#define C(i)
HYPERVISOR_update_descriptor(virt_to_machine(&get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN
+ i]), ((u32 *)&t->tls_array[i])[0], ((u32 *)&t->tls_array[i])[1])
+ C(0); C(1); C(2);
+#undef C
+}
+
+static inline void clear_LDT(void)
+{
+ int cpu = get_cpu();
+
+ /*
+ * NB. We load the default_ldt for lcall7/27 handling on demand, as
+ * it slows down context switching. Noone uses it anyway.
+ */
+ cpu = cpu; /* XXX avoid compiler warning */
+ xen_set_ldt(0UL, 0);
+ put_cpu();
+}
+
+/*
+ * load one particular LDT into the current CPU
+ */
+static inline void load_LDT_nolock(mm_context_t *pc, int cpu)
+{
+ void *segments = pc->ldt;
+ int count = pc->size;
+
+ if (likely(!count))
+ segments = NULL;
+
+ xen_set_ldt((unsigned long)segments, count);
+}
+
+static inline void load_LDT(mm_context_t *pc)
+{
+ int cpu = get_cpu();
+ load_LDT_nolock(pc, cpu);
+ put_cpu();
+}
+
+static inline unsigned long get_desc_base(unsigned long *desc)
+{
+ unsigned long base;
+ base = ((desc[0] >> 16) & 0x0000ffff) |
+ ((desc[1] << 16) & 0x00ff0000) |
+ (desc[1] & 0xff000000);
+ return base;
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/netfront/netfront.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/netfront/netfront.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,1480 @@
+/******************************************************************************
+ * Virtual network driver for conversing with remote driver backends.
+ *
+ * Copyright (c) 2002-2004, K A Fraser
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/version.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/init.h>
+#include <linux/bitops.h>
+#include <linux/proc_fs.h>
+#include <linux/ethtool.h>
+#include <net/sock.h>
+#include <net/pkt_sched.h>
+#include <net/arp.h>
+#include <net/route.h>
+#include <asm/io.h>
+#include <asm/uaccess.h>
+#include <asm-xen/evtchn.h>
+#include <asm-xen/ctrl_if.h>
+#include <asm-xen/xen-public/io/netif.h>
+#include <asm-xen/balloon.h>
+#include <asm/page.h>
+#include <asm/uaccess.h>
+
+#ifndef __GFP_NOWARN
+#define __GFP_NOWARN 0
+#endif
+#define alloc_xen_skb(_l) __dev_alloc_skb((_l), GFP_ATOMIC|__GFP_NOWARN)
+
+#define init_skb_shinfo(_skb) \
+ do { \
+ atomic_set(&(skb_shinfo(_skb)->dataref), 1); \
+ skb_shinfo(_skb)->nr_frags = 0; \
+ skb_shinfo(_skb)->frag_list = NULL; \
+ } while (0)
+
+/* Allow headroom on each rx pkt for Ethernet header, alignment padding, ... */
+#define RX_HEADROOM 200
+
+/*
+ * If the backend driver is pipelining transmit requests then we can be very
+ * aggressive in avoiding new-packet notifications -- only need to send a
+ * notification if there are no outstanding unreceived responses.
+ * If the backend may be buffering our transmit buffers for any reason then we
+ * are rather more conservative.
+ */
+#ifdef CONFIG_XEN_NETDEV_FRONTEND_PIPELINED_TRANSMITTER
+#define TX_TEST_IDX resp_prod /* aggressive: any outstanding responses? */
+#else
+#define TX_TEST_IDX req_cons /* conservative: not seen all our requests? */
+#endif
+
+static void network_tx_buf_gc(struct net_device *dev);
+static void network_alloc_rx_buffers(struct net_device *dev);
+
+static unsigned long rx_pfn_array[NETIF_RX_RING_SIZE];
+static multicall_entry_t rx_mcl[NETIF_RX_RING_SIZE+1];
+static mmu_update_t rx_mmu[NETIF_RX_RING_SIZE];
+
+#ifdef CONFIG_PROC_FS
+static int xennet_proc_init(void);
+static int xennet_proc_addif(struct net_device *dev);
+static void xennet_proc_delif(struct net_device *dev);
+#else
+#define xennet_proc_init() (0)
+#define xennet_proc_addif(d) (0)
+#define xennet_proc_delif(d) ((void)0)
+#endif
+
+static struct list_head dev_list;
+
+struct net_private
+{
+ struct list_head list;
+ struct net_device *dev;
+
+ struct net_device_stats stats;
+ NETIF_RING_IDX rx_resp_cons, tx_resp_cons;
+ unsigned int tx_full;
+
+ netif_tx_interface_t *tx;
+ netif_rx_interface_t *rx;
+
+ spinlock_t tx_lock;
+ spinlock_t rx_lock;
+
+ unsigned int handle;
+ unsigned int evtchn;
+ unsigned int irq;
+
+ /* What is the status of our connection to the remote backend? */
+#define BEST_CLOSED 0
+#define BEST_DISCONNECTED 1
+#define BEST_CONNECTED 2
+ unsigned int backend_state;
+
+ /* Is this interface open or closed (down or up)? */
+#define UST_CLOSED 0
+#define UST_OPEN 1
+ unsigned int user_state;
+
+ /* Receive-ring batched refills. */
+#define RX_MIN_TARGET 8
+#define RX_MAX_TARGET NETIF_RX_RING_SIZE
+ int rx_min_target, rx_max_target, rx_target;
+ struct sk_buff_head rx_batch;
+
+ /*
+ * {tx,rx}_skbs store outstanding skbuffs. The first entry in each
+ * array is an index into a chain of free entries.
+ */
+ struct sk_buff *tx_skbs[NETIF_TX_RING_SIZE+1];
+ struct sk_buff *rx_skbs[NETIF_RX_RING_SIZE+1];
+};
+
+/* Access macros for acquiring freeing slots in {tx,rx}_skbs[]. */
+#define ADD_ID_TO_FREELIST(_list, _id) \
+ (_list)[(_id)] = (_list)[0]; \
+ (_list)[0] = (void *)(unsigned long)(_id);
+#define GET_ID_FROM_FREELIST(_list) \
+ ({ unsigned long _id = (unsigned long)(_list)[0]; \
+ (_list)[0] = (_list)[_id]; \
+ (unsigned short)_id; })
+
+static char *status_name[] = {
+ [NETIF_INTERFACE_STATUS_CLOSED] = "closed",
+ [NETIF_INTERFACE_STATUS_DISCONNECTED] = "disconnected",
+ [NETIF_INTERFACE_STATUS_CONNECTED] = "connected",
+ [NETIF_INTERFACE_STATUS_CHANGED] = "changed",
+};
+
+static char *be_state_name[] = {
+ [BEST_CLOSED] = "closed",
+ [BEST_DISCONNECTED] = "disconnected",
+ [BEST_CONNECTED] = "connected",
+};
+
+#if DEBUG
+#define DPRINTK(fmt, args...) \
+ printk(KERN_ALERT "xen_net (%s:%d) " fmt, __FUNCTION__, __LINE__, ##args)
+#else
+#define DPRINTK(fmt, args...) ((void)0)
+#endif
+#define IPRINTK(fmt, args...) \
+ printk(KERN_INFO "xen_net: " fmt, ##args)
+#define WPRINTK(fmt, args...) \
+ printk(KERN_WARNING "xen_net: " fmt, ##args)
+
+static struct net_device *find_dev_by_handle(unsigned int handle)
+{
+ struct list_head *ent;
+ struct net_private *np;
+ list_for_each (ent, &dev_list) {
+ np = list_entry(ent, struct net_private, list);
+ if (np->handle == handle)
+ return np->dev;
+ }
+ return NULL;
+}
+
+/** Network interface info. */
+struct netif_ctrl {
+ /** Number of interfaces. */
+ int interface_n;
+ /** Number of connected interfaces. */
+ int connected_n;
+ /** Error code. */
+ int err;
+ int up;
+};
+
+static struct netif_ctrl netctrl;
+
+static void netctrl_init(void)
+{
+ memset(&netctrl, 0, sizeof(netctrl));
+ netctrl.up = NETIF_DRIVER_STATUS_DOWN;
+}
+
+/** Get or set a network interface error.
+ */
+static int netctrl_err(int err)
+{
+ if ((err < 0) && !netctrl.err)
+ netctrl.err = err;
+ return netctrl.err;
+}
+
+/** Test if all network interfaces are connected.
+ *
+ * @return 1 if all connected, 0 if not, negative error code otherwise
+ */
+static int netctrl_connected(void)
+{
+ int ok;
+
+ if (netctrl.err)
+ ok = netctrl.err;
+ else if (netctrl.up == NETIF_DRIVER_STATUS_UP)
+ ok = (netctrl.connected_n == netctrl.interface_n);
+ else
+ ok = 0;
+
+ return ok;
+}
+
+/** Count the connected network interfaces.
+ *
+ * @return connected count
+ */
+static int netctrl_connected_count(void)
+{
+
+ struct list_head *ent;
+ struct net_private *np;
+ unsigned int connected;
+
+ connected = 0;
+
+ list_for_each(ent, &dev_list) {
+ np = list_entry(ent, struct net_private, list);
+ if (np->backend_state == BEST_CONNECTED)
+ connected++;
+ }
+
+ netctrl.connected_n = connected;
+ DPRINTK("> connected_n=%d interface_n=%d\n",
+ netctrl.connected_n, netctrl.interface_n);
+ return connected;
+}
+
+/** Send a packet on a net device to encourage switches to learn the
+ * MAC. We send a fake ARP request.
+ *
+ * @param dev device
+ * @return 0 on success, error code otherwise
+ */
+static int send_fake_arp(struct net_device *dev)
+{
+ struct sk_buff *skb;
+ u32 src_ip, dst_ip;
+
+ dst_ip = INADDR_BROADCAST;
+ src_ip = inet_select_addr(dev, dst_ip, RT_SCOPE_LINK);
+
+ /* No IP? Then nothing to do. */
+ if (src_ip == 0)
+ return 0;
+
+ skb = arp_create(ARPOP_REPLY, ETH_P_ARP,
+ dst_ip, dev, src_ip,
+ /*dst_hw*/ NULL, /*src_hw*/ NULL,
+ /*target_hw*/ dev->dev_addr);
+ if (skb == NULL)
+ return -ENOMEM;
+
+ return dev_queue_xmit(skb);
+}
+
+static int network_open(struct net_device *dev)
+{
+ struct net_private *np = netdev_priv(dev);
+
+ memset(&np->stats, 0, sizeof(np->stats));
+
+ np->user_state = UST_OPEN;
+
+ network_alloc_rx_buffers(dev);
+ np->rx->event = np->rx_resp_cons + 1;
+
+ netif_start_queue(dev);
+
+ return 0;
+}
+
+static void network_tx_buf_gc(struct net_device *dev)
+{
+ NETIF_RING_IDX i, prod;
+ unsigned short id;
+ struct net_private *np = netdev_priv(dev);
+ struct sk_buff *skb;
+
+ if (np->backend_state != BEST_CONNECTED)
+ return;
+
+ do {
+ prod = np->tx->resp_prod;
+ rmb(); /* Ensure we see responses up to 'rp'. */
+
+ for (i = np->tx_resp_cons; i != prod; i++) {
+ id = np->tx->ring[MASK_NETIF_TX_IDX(i)].resp.id;
+ skb = np->tx_skbs[id];
+ ADD_ID_TO_FREELIST(np->tx_skbs, id);
+ dev_kfree_skb_irq(skb);
+ }
+
+ np->tx_resp_cons = prod;
+
+ /*
+ * Set a new event, then check for race with update of tx_cons. Note
+ * that it is essential to schedule a callback, no matter how few
+ * buffers are pending. Even if there is space in the transmit ring,
+ * higher layers may be blocked because too much data is outstanding:
+ * in such cases notification from Xen is likely to be the only kick
+ * that we'll get.
+ */
+ np->tx->event =
+ prod + ((np->tx->req_prod - prod) >> 1) + 1;
+ mb();
+ } while (prod != np->tx->resp_prod);
+
+ if (np->tx_full && ((np->tx->req_prod - prod) < NETIF_TX_RING_SIZE)) {
+ np->tx_full = 0;
+ if (np->user_state == UST_OPEN)
+ netif_wake_queue(dev);
+ }
+}
+
+
+static void network_alloc_rx_buffers(struct net_device *dev)
+{
+ unsigned short id;
+ struct net_private *np = netdev_priv(dev);
+ struct sk_buff *skb;
+ int i, batch_target;
+ NETIF_RING_IDX req_prod = np->rx->req_prod;
+
+ if (unlikely(np->backend_state != BEST_CONNECTED))
+ return;
+
+ /*
+ * Allocate skbuffs greedily, even though we batch updates to the
+ * receive ring. This creates a less bursty demand on the memory allocator,
+ * so should reduce the chance of failed allocation requests both for
+ * ourself and for other kernel subsystems.
+ */
+ batch_target = np->rx_target - (req_prod - np->rx_resp_cons);
+ for (i = skb_queue_len(&np->rx_batch); i < batch_target; i++) {
+ if (unlikely((skb = alloc_xen_skb(dev->mtu + RX_HEADROOM)) == NULL))
+ break;
+ __skb_queue_tail(&np->rx_batch, skb);
+ }
+
+ /* Is the batch large enough to be worthwhile? */
+ if (i < (np->rx_target/2))
+ return;
+
+ for (i = 0; ; i++) {
+ if ((skb = __skb_dequeue(&np->rx_batch)) == NULL)
+ break;
+
+ skb->dev = dev;
+
+ id = GET_ID_FROM_FREELIST(np->rx_skbs);
+
+ np->rx_skbs[id] = skb;
+
+ np->rx->ring[MASK_NETIF_RX_IDX(req_prod + i)].req.id = id;
+
+ rx_pfn_array[i] = virt_to_machine(skb->head) >> PAGE_SHIFT;
+
+ /* Remove this page from pseudo phys map before passing back to Xen. */
+ phys_to_machine_mapping[__pa(skb->head) >> PAGE_SHIFT]
+ = INVALID_P2M_ENTRY;
+
+ MULTI_update_va_mapping(rx_mcl+i, (unsigned long)skb->head,
+ __pte(0), 0);
+ }
+
+ /* After all PTEs have been zapped we blow away stale TLB entries. */
+ rx_mcl[i-1].args[2] = UVMF_TLB_FLUSH|UVMF_ALL;
+
+ /* Give away a batch of pages. */
+ rx_mcl[i].op = __HYPERVISOR_dom_mem_op;
+ rx_mcl[i].args[0] = MEMOP_decrease_reservation;
+ rx_mcl[i].args[1] = (unsigned long)rx_pfn_array;
+ rx_mcl[i].args[2] = (unsigned long)i;
+ rx_mcl[i].args[3] = 0;
+ rx_mcl[i].args[4] = DOMID_SELF;
+
+ /* Tell the ballon driver what is going on. */
+ balloon_update_driver_allowance(i);
+
+ /* Zap PTEs and give away pages in one big multicall. */
+ (void)HYPERVISOR_multicall(rx_mcl, i+1);
+
+ /* Check return status of HYPERVISOR_dom_mem_op(). */
+ if (unlikely(rx_mcl[i].result != i))
+ panic("Unable to reduce memory reservation\n");
+
+ /* Above is a suitable barrier to ensure backend will see requests. */
+ np->rx->req_prod = req_prod + i;
+
+ /* Adjust our floating fill target if we risked running out of buffers. */
+ if (((req_prod - np->rx->resp_prod) < (np->rx_target / 4)) &&
+ ((np->rx_target *= 2) > np->rx_max_target))
+ np->rx_target = np->rx_max_target;
+}
+
+
+static int network_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ unsigned short id;
+ struct net_private *np = netdev_priv(dev);
+ netif_tx_request_t *tx;
+ NETIF_RING_IDX i;
+
+ if (unlikely(np->tx_full)) {
+ printk(KERN_ALERT "%s: full queue wasn't stopped!\n", dev->name);
+ netif_stop_queue(dev);
+ goto drop;
+ }
+
+ if (unlikely((((unsigned long)skb->data & ~PAGE_MASK) + skb->len) >=
+ PAGE_SIZE)) {
+ struct sk_buff *nskb;
+ if (unlikely((nskb = alloc_xen_skb(skb->len)) == NULL))
+ goto drop;
+ skb_put(nskb, skb->len);
+ memcpy(nskb->data, skb->data, skb->len);
+ nskb->dev = skb->dev;
+ dev_kfree_skb(skb);
+ skb = nskb;
+ }
+
+ spin_lock_irq(&np->tx_lock);
+
+ if (np->backend_state != BEST_CONNECTED) {
+ spin_unlock_irq(&np->tx_lock);
+ goto drop;
+ }
+
+ i = np->tx->req_prod;
+
+ id = GET_ID_FROM_FREELIST(np->tx_skbs);
+ np->tx_skbs[id] = skb;
+
+ tx = &np->tx->ring[MASK_NETIF_TX_IDX(i)].req;
+
+ tx->id = id;
+ tx->addr = virt_to_machine(skb->data);
+ tx->size = skb->len;
+ tx->csum_blank = (skb->ip_summed == CHECKSUM_HW);
+
+ wmb(); /* Ensure that backend will see the request. */
+ np->tx->req_prod = i + 1;
+
+ network_tx_buf_gc(dev);
+
+ if ((i - np->tx_resp_cons) == (NETIF_TX_RING_SIZE - 1)) {
+ np->tx_full = 1;
+ netif_stop_queue(dev);
+ }
+
+ spin_unlock_irq(&np->tx_lock);
+
+ np->stats.tx_bytes += skb->len;
+ np->stats.tx_packets++;
+
+ /* Only notify Xen if we really have to. */
+ mb();
+ if (np->tx->TX_TEST_IDX == i)
+ notify_via_evtchn(np->evtchn);
+
+ return 0;
+
+ drop:
+ np->stats.tx_dropped++;
+ dev_kfree_skb(skb);
+ return 0;
+}
+
+static irqreturn_t netif_int(int irq, void *dev_id, struct pt_regs *ptregs)
+{
+ struct net_device *dev = dev_id;
+ struct net_private *np = netdev_priv(dev);
+ unsigned long flags;
+
+ spin_lock_irqsave(&np->tx_lock, flags);
+ network_tx_buf_gc(dev);
+ spin_unlock_irqrestore(&np->tx_lock, flags);
+
+ if ((np->rx_resp_cons != np->rx->resp_prod) && (np->user_state ==
UST_OPEN))
+ netif_rx_schedule(dev);
+
+ return IRQ_HANDLED;
+}
+
+
+static int netif_poll(struct net_device *dev, int *pbudget)
+{
+ struct net_private *np = netdev_priv(dev);
+ struct sk_buff *skb, *nskb;
+ netif_rx_response_t *rx;
+ NETIF_RING_IDX i, rp;
+ mmu_update_t *mmu = rx_mmu;
+ multicall_entry_t *mcl = rx_mcl;
+ int work_done, budget, more_to_do = 1;
+ struct sk_buff_head rxq;
+ unsigned long flags;
+
+ spin_lock(&np->rx_lock);
+
+ if (np->backend_state != BEST_CONNECTED) {
+ spin_unlock(&np->rx_lock);
+ return 0;
+ }
+
+ skb_queue_head_init(&rxq);
+
+ if ((budget = *pbudget) > dev->quota)
+ budget = dev->quota;
+
+ rp = np->rx->resp_prod;
+ rmb(); /* Ensure we see queued responses up to 'rp'. */
+
+ for (i = np->rx_resp_cons, work_done = 0;
+ (i != rp) && (work_done < budget);
+ i++, work_done++) {
+ rx = &np->rx->ring[MASK_NETIF_RX_IDX(i)].resp;
+
+ /*
+ * An error here is very odd. Usually indicates a backend bug,
+ * low-memory condition, or that we didn't have reservation headroom.
+ */
+ if (unlikely(rx->status <= 0)) {
+ if (net_ratelimit())
+ printk(KERN_WARNING "Bad rx buffer (memory squeeze?).\n");
+ np->rx->ring[MASK_NETIF_RX_IDX(np->rx->req_prod)].req.id = rx->id;
+ wmb();
+ np->rx->req_prod++;
+ work_done--;
+ continue;
+ }
+
+ skb = np->rx_skbs[rx->id];
+ ADD_ID_TO_FREELIST(np->rx_skbs, rx->id);
+
+ /* NB. We handle skb overflow later. */
+ skb->data = skb->head + (rx->addr & ~PAGE_MASK);
+ skb->len = rx->status;
+ skb->tail = skb->data + skb->len;
+
+ if ( rx->csum_valid )
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+ np->stats.rx_packets++;
+ np->stats.rx_bytes += rx->status;
+
+ /* Remap the page. */
+ mmu->ptr = (rx->addr & PAGE_MASK) | MMU_MACHPHYS_UPDATE;
+ mmu->val = __pa(skb->head) >> PAGE_SHIFT;
+ mmu++;
+ MULTI_update_va_mapping(mcl, (unsigned long)skb->head,
+ pfn_pte_ma(rx->addr >> PAGE_SHIFT,
PAGE_KERNEL), 0);
+ mcl++;
+
+ phys_to_machine_mapping[__pa(skb->head) >> PAGE_SHIFT] =
+ rx->addr >> PAGE_SHIFT;
+
+ __skb_queue_tail(&rxq, skb);
+ }
+
+ /* Some pages are no longer absent... */
+ balloon_update_driver_allowance(-work_done);
+
+ /* Do all the remapping work, and M->P updates, in one big hypercall. */
+ if (likely((mcl - rx_mcl) != 0)) {
+ mcl->op = __HYPERVISOR_mmu_update;
+ mcl->args[0] = (unsigned long)rx_mmu;
+ mcl->args[1] = mmu - rx_mmu;
+ mcl->args[2] = 0;
+ mcl->args[3] = DOMID_SELF;
+ mcl++;
+ (void)HYPERVISOR_multicall(rx_mcl, mcl - rx_mcl);
+ }
+
+ while ((skb = __skb_dequeue(&rxq)) != NULL) {
+ /*
+ * Enough room in skbuff for the data we were passed? Also, Linux
+ * expects at least 16 bytes headroom in each receive buffer.
+ */
+ if (unlikely(skb->tail > skb->end) ||
+ unlikely((skb->data - skb->head) < 16)) {
+ nskb = NULL;
+
+ /* Only copy the packet if it fits in the current MTU. */
+ if (skb->len <= (dev->mtu + ETH_HLEN)) {
+ if ((skb->tail > skb->end) && net_ratelimit())
+ printk(KERN_INFO "Received packet needs %zd bytes more "
+ "headroom.\n", skb->tail - skb->end);
+
+ if ((nskb = alloc_xen_skb(skb->len + 2)) != NULL) {
+ skb_reserve(nskb, 2);
+ skb_put(nskb, skb->len);
+ memcpy(nskb->data, skb->data, skb->len);
+ nskb->dev = skb->dev;
+ }
+ }
+ else if (net_ratelimit())
+ printk(KERN_INFO "Received packet too big for MTU "
+ "(%d > %d)\n", skb->len - ETH_HLEN, dev->mtu);
+
+ /* Reinitialise and then destroy the old skbuff. */
+ skb->len = 0;
+ skb->tail = skb->data;
+ init_skb_shinfo(skb);
+ dev_kfree_skb(skb);
+
+ /* Switch old for new, if we copied the buffer. */
+ if ((skb = nskb) == NULL)
+ continue;
+ }
+
+ /* Set the shared-info area, which is hidden behind the real data. */
+ init_skb_shinfo(skb);
+
+ /* Ethernet-specific work. Delayed to here as it peeks the header. */
+ skb->protocol = eth_type_trans(skb, dev);
+
+ /* Pass it up. */
+ netif_receive_skb(skb);
+ dev->last_rx = jiffies;
+ }
+
+ np->rx_resp_cons = i;
+
+ /* If we get a callback with very few responses, reduce fill target. */
+ /* NB. Note exponential increase, linear decrease. */
+ if (((np->rx->req_prod - np->rx->resp_prod) > ((3*np->rx_target) / 4)) &&
+ (--np->rx_target < np->rx_min_target))
+ np->rx_target = np->rx_min_target;
+
+ network_alloc_rx_buffers(dev);
+
+ *pbudget -= work_done;
+ dev->quota -= work_done;
+
+ if (work_done < budget) {
+ local_irq_save(flags);
+
+ np->rx->event = i + 1;
+
+ /* Deal with hypervisor racing our resetting of rx_event. */
+ mb();
+ if (np->rx->resp_prod == i) {
+ __netif_rx_complete(dev);
+ more_to_do = 0;
+ }
+
+ local_irq_restore(flags);
+ }
+
+ spin_unlock(&np->rx_lock);
+
+ return more_to_do;
+}
+
+
+static int network_close(struct net_device *dev)
+{
+ struct net_private *np = netdev_priv(dev);
+ np->user_state = UST_CLOSED;
+ netif_stop_queue(np->dev);
+ return 0;
+}
+
+
+static struct net_device_stats *network_get_stats(struct net_device *dev)
+{
+ struct net_private *np = netdev_priv(dev);
+ return &np->stats;
+}
+
+
+static void network_connect(struct net_device *dev,
+ netif_fe_interface_status_t *status)
+{
+ struct net_private *np;
+ int i, requeue_idx;
+ netif_tx_request_t *tx;
+
+ np = netdev_priv(dev);
+ spin_lock_irq(&np->tx_lock);
+ spin_lock(&np->rx_lock);
+
+ /* Recovery procedure: */
+
+ /* Step 1: Reinitialise variables. */
+ np->rx_resp_cons = np->tx_resp_cons = np->tx_full = 0;
+ np->rx->event = np->tx->event = 1;
+
+ /* Step 2: Rebuild the RX and TX ring contents.
+ * NB. We could just free the queued TX packets now but we hope
+ * that sending them out might do some good. We have to rebuild
+ * the RX ring because some of our pages are currently flipped out
+ * so we can't just free the RX skbs.
+ * NB2. Freelist index entries are always going to be less than
+ * __PAGE_OFFSET, whereas pointers to skbs will always be equal or
+ * greater than __PAGE_OFFSET: we use this property to distinguish
+ * them.
+ */
+
+ /* Rebuild the TX buffer freelist and the TX ring itself.
+ * NB. This reorders packets. We could keep more private state
+ * to avoid this but maybe it doesn't matter so much given the
+ * interface has been down.
+ */
+ for (requeue_idx = 0, i = 1; i <= NETIF_TX_RING_SIZE; i++) {
+ if ((unsigned long)np->tx_skbs[i] >= __PAGE_OFFSET) {
+ struct sk_buff *skb = np->tx_skbs[i];
+
+ tx = &np->tx->ring[requeue_idx++].req;
+
+ tx->id = i;
+ tx->addr = virt_to_machine(skb->data);
+ tx->size = skb->len;
+
+ np->stats.tx_bytes += skb->len;
+ np->stats.tx_packets++;
+ }
+ }
+ wmb();
+ np->tx->req_prod = requeue_idx;
+
+ /* Rebuild the RX buffer freelist and the RX ring itself. */
+ for (requeue_idx = 0, i = 1; i <= NETIF_RX_RING_SIZE; i++)
+ if ((unsigned long)np->rx_skbs[i] >= __PAGE_OFFSET)
+ np->rx->ring[requeue_idx++].req.id = i;
+ wmb();
+ np->rx->req_prod = requeue_idx;
+
+ /* Step 3: All public and private state should now be sane. Get
+ * ready to start sending and receiving packets and give the driver
+ * domain a kick because we've probably just requeued some
+ * packets.
+ */
+ np->backend_state = BEST_CONNECTED;
+ wmb();
+ notify_via_evtchn(status->evtchn);
+ network_tx_buf_gc(dev);
+
+ if (np->user_state == UST_OPEN)
+ netif_start_queue(dev);
+
+ spin_unlock(&np->rx_lock);
+ spin_unlock_irq(&np->tx_lock);
+}
+
+static void vif_show(struct net_private *np)
+{
+#if DEBUG
+ if (np) {
+ IPRINTK("<vif handle=%u %s(%s) evtchn=%u irq=%u tx=%p rx=%p>\n",
+ np->handle,
+ be_state_name[np->backend_state],
+ np->user_state ? "open" : "closed",
+ np->evtchn,
+ np->irq,
+ np->tx,
+ np->rx);
+ } else {
+ IPRINTK("<vif NULL>\n");
+ }
+#endif
+}
+
+/* Send a connect message to xend to tell it to bring up the interface. */
+static void send_interface_connect(struct net_private *np)
+{
+ ctrl_msg_t cmsg = {
+ .type = CMSG_NETIF_FE,
+ .subtype = CMSG_NETIF_FE_INTERFACE_CONNECT,
+ .length = sizeof(netif_fe_interface_connect_t),
+ };
+ netif_fe_interface_connect_t *msg = (void*)cmsg.msg;
+
+ msg->handle = np->handle;
+ msg->tx_shmem_frame = (virt_to_machine(np->tx) >> PAGE_SHIFT);
+ msg->rx_shmem_frame = (virt_to_machine(np->rx) >> PAGE_SHIFT);
+
+ ctrl_if_send_message_block(&cmsg, NULL, 0, TASK_UNINTERRUPTIBLE);
+}
+
+/* Send a driver status notification to the domain controller. */
+static int send_driver_status(int ok)
+{
+ int err = 0;
+ ctrl_msg_t cmsg = {
+ .type = CMSG_NETIF_FE,
+ .subtype = CMSG_NETIF_FE_DRIVER_STATUS,
+ .length = sizeof(netif_fe_driver_status_t),
+ };
+ netif_fe_driver_status_t *msg = (void*)cmsg.msg;
+
+ msg->status = (ok ? NETIF_DRIVER_STATUS_UP : NETIF_DRIVER_STATUS_DOWN);
+ err = ctrl_if_send_message_block(&cmsg, NULL, 0, TASK_UNINTERRUPTIBLE);
+ return err;
+}
+
+/* Stop network device and free tx/rx queues and irq.
+ */
+static void vif_release(struct net_private *np)
+{
+ /* Stop old i/f to prevent errors whilst we rebuild the state. */
+ spin_lock_irq(&np->tx_lock);
+ spin_lock(&np->rx_lock);
+ netif_stop_queue(np->dev);
+ /* np->backend_state = BEST_DISCONNECTED; */
+ spin_unlock(&np->rx_lock);
+ spin_unlock_irq(&np->tx_lock);
+
+ /* Free resources. */
+ if(np->tx != NULL){
+ free_irq(np->irq, np->dev);
+ unbind_evtchn_from_irq(np->evtchn);
+ free_page((unsigned long)np->tx);
+ free_page((unsigned long)np->rx);
+ np->irq = 0;
+ np->evtchn = 0;
+ np->tx = NULL;
+ np->rx = NULL;
+ }
+}
+
+/* Release vif resources and close it down completely.
+ */
+static void vif_close(struct net_private *np)
+{
+ WPRINTK("Unexpected netif-CLOSED message in state %s\n",
+ be_state_name[np->backend_state]);
+ vif_release(np);
+ np->backend_state = BEST_CLOSED;
+ /* todo: take dev down and free. */
+ vif_show(np);
+}
+
+/* Move the vif into disconnected state.
+ * Allocates tx/rx pages.
+ * Sends connect message to xend.
+ */
+static void vif_disconnect(struct net_private *np)
+{
+ if(np->tx) free_page((unsigned long)np->tx);
+ if(np->rx) free_page((unsigned long)np->rx);
+ // Before this np->tx and np->rx had better be null.
+ np->tx = (netif_tx_interface_t *)__get_free_page(GFP_KERNEL);
+ np->rx = (netif_rx_interface_t *)__get_free_page(GFP_KERNEL);
+ memset(np->tx, 0, PAGE_SIZE);
+ memset(np->rx, 0, PAGE_SIZE);
+ np->backend_state = BEST_DISCONNECTED;
+ send_interface_connect(np);
+ vif_show(np);
+}
+
+/* Begin interface recovery.
+ *
+ * NB. Whilst we're recovering, we turn the carrier state off. We
+ * take measures to ensure that this device isn't used for
+ * anything. We also stop the queue for this device. Various
+ * different approaches (e.g. continuing to buffer packets) have
+ * been tested but don't appear to improve the overall impact on
+ * TCP connections.
+ *
+ * TODO: (MAW) Change the Xend<->Guest protocol so that a recovery
+ * is initiated by a special "RESET" message - disconnect could
+ * just mean we're not allowed to use this interface any more.
+ */
+static void vif_reset(struct net_private *np)
+{
+ IPRINTK("Attempting to reconnect network interface: handle=%u\n",
+ np->handle);
+ vif_release(np);
+ vif_disconnect(np);
+ vif_show(np);
+}
+
+/* Move the vif into connected state.
+ * Sets the mac and event channel from the message.
+ * Binds the irq to the event channel.
+ */
+static void
+vif_connect(struct net_private *np, netif_fe_interface_status_t *status)
+{
+ struct net_device *dev = np->dev;
+ memcpy(dev->dev_addr, status->mac, ETH_ALEN);
+ network_connect(dev, status);
+ np->evtchn = status->evtchn;
+ np->irq = bind_evtchn_to_irq(np->evtchn);
+ (void)request_irq(np->irq, netif_int, SA_SAMPLE_RANDOM, dev->name, dev);
+ netctrl_connected_count();
+ (void)send_fake_arp(dev);
+ vif_show(np);
+}
+
+static struct ethtool_ops network_ethtool_ops =
+{
+ .get_tx_csum = ethtool_op_get_tx_csum,
+ .set_tx_csum = ethtool_op_set_tx_csum,
+};
+
+/** Create a network device.
+ * @param handle device handle
+ * @param val return parameter for created device
+ * @return 0 on success, error code otherwise
+ */
+static int create_netdev(int handle, struct net_device **val)
+{
+ int i, err = 0;
+ struct net_device *dev = NULL;
+ struct net_private *np = NULL;
+
+ if ((dev = alloc_etherdev(sizeof(struct net_private))) == NULL) {
+ printk(KERN_WARNING "%s> alloc_etherdev failed.\n", __FUNCTION__);
+ err = -ENOMEM;
+ goto exit;
+ }
+
+ np = netdev_priv(dev);
+ np->backend_state = BEST_CLOSED;
+ np->user_state = UST_CLOSED;
+ np->handle = handle;
+
+ spin_lock_init(&np->tx_lock);
+ spin_lock_init(&np->rx_lock);
+
+ skb_queue_head_init(&np->rx_batch);
+ np->rx_target = RX_MIN_TARGET;
+ np->rx_min_target = RX_MIN_TARGET;
+ np->rx_max_target = RX_MAX_TARGET;
+
+ /* Initialise {tx,rx}_skbs to be a free chain containing every entry. */
+ for (i = 0; i <= NETIF_TX_RING_SIZE; i++)
+ np->tx_skbs[i] = (void *)((unsigned long) i+1);
+ for (i = 0; i <= NETIF_RX_RING_SIZE; i++)
+ np->rx_skbs[i] = (void *)((unsigned long) i+1);
+
+ dev->open = network_open;
+ dev->hard_start_xmit = network_start_xmit;
+ dev->stop = network_close;
+ dev->get_stats = network_get_stats;
+ dev->poll = netif_poll;
+ dev->weight = 64;
+ dev->features = NETIF_F_IP_CSUM;
+
+ SET_ETHTOOL_OPS(dev, &network_ethtool_ops);
+
+ if ((err = register_netdev(dev)) != 0) {
+ printk(KERN_WARNING "%s> register_netdev err=%d\n", __FUNCTION__, err);
+ goto exit;
+ }
+
+ if ((err = xennet_proc_addif(dev)) != 0) {
+ unregister_netdev(dev);
+ goto exit;
+ }
+
+ np->dev = dev;
+ list_add(&np->list, &dev_list);
+
+ exit:
+ if ((err != 0) && (dev != NULL))
+ kfree(dev);
+ else if (val != NULL)
+ *val = dev;
+ return err;
+}
+
+/* Get the target interface for a status message.
+ * Creates the interface when it makes sense.
+ * The returned interface may be null when there is no error.
+ *
+ * @param status status message
+ * @param np return parameter for interface state
+ * @return 0 on success, error code otherwise
+ */
+static int
+target_vif(netif_fe_interface_status_t *status, struct net_private **np)
+{
+ int err = 0;
+ struct net_device *dev;
+
+ DPRINTK("> handle=%d\n", status->handle);
+ if (status->handle < 0) {
+ err = -EINVAL;
+ goto exit;
+ }
+
+ if ((dev = find_dev_by_handle(status->handle)) != NULL)
+ goto exit;
+
+ if (status->status == NETIF_INTERFACE_STATUS_CLOSED)
+ goto exit;
+ if (status->status == NETIF_INTERFACE_STATUS_CHANGED)
+ goto exit;
+
+ /* It's a new interface in a good state - create it. */
+ DPRINTK("> create device...\n");
+ if ((err = create_netdev(status->handle, &dev)) != 0)
+ goto exit;
+
+ netctrl.interface_n++;
+
+ exit:
+ if (np != NULL)
+ *np = ((dev && !err) ? netdev_priv(dev) : NULL);
+ DPRINTK("< err=%d\n", err);
+ return err;
+}
+
+/* Handle an interface status message. */
+static void netif_interface_status(netif_fe_interface_status_t *status)
+{
+ int err = 0;
+ struct net_private *np = NULL;
+
+ DPRINTK("> status=%s handle=%d\n",
+ status_name[status->status], status->handle);
+
+ if ((err = target_vif(status, &np)) != 0) {
+ WPRINTK("Invalid netif: handle=%u\n", status->handle);
+ return;
+ }
+
+ if (np == NULL) {
+ DPRINTK("> no vif\n");
+ return;
+ }
+
+ switch (status->status) {
+ case NETIF_INTERFACE_STATUS_CLOSED:
+ switch (np->backend_state) {
+ case BEST_CLOSED:
+ case BEST_DISCONNECTED:
+ case BEST_CONNECTED:
+ vif_close(np);
+ break;
+ }
+ break;
+
+ case NETIF_INTERFACE_STATUS_DISCONNECTED:
+ switch (np->backend_state) {
+ case BEST_CLOSED:
+ vif_disconnect(np);
+ break;
+ case BEST_DISCONNECTED:
+ case BEST_CONNECTED:
+ vif_reset(np);
+ break;
+ }
+ break;
+
+ case NETIF_INTERFACE_STATUS_CONNECTED:
+ switch (np->backend_state) {
+ case BEST_CLOSED:
+ WPRINTK("Unexpected netif status %s in state %s\n",
+ status_name[status->status],
+ be_state_name[np->backend_state]);
+ vif_disconnect(np);
+ vif_connect(np, status);
+ break;
+ case BEST_DISCONNECTED:
+ vif_connect(np, status);
+ break;
+ }
+ break;
+
+ case NETIF_INTERFACE_STATUS_CHANGED:
+ /*
+ * The domain controller is notifying us that a device has been
+ * added or removed.
+ */
+ break;
+
+ default:
+ WPRINTK("Invalid netif status code %d\n", status->status);
+ break;
+ }
+
+ vif_show(np);
+}
+
+/*
+ * Initialize the network control interface.
+ */
+static void netif_driver_status(netif_fe_driver_status_t *status)
+{
+ netctrl.up = status->status;
+ netctrl_connected_count();
+}
+
+/* Receive handler for control messages. */
+static void netif_ctrlif_rx(ctrl_msg_t *msg, unsigned long id)
+{
+
+ switch (msg->subtype) {
+ case CMSG_NETIF_FE_INTERFACE_STATUS:
+ netif_interface_status((netif_fe_interface_status_t *) &msg->msg[0]);
+ break;
+
+ case CMSG_NETIF_FE_DRIVER_STATUS:
+ netif_driver_status((netif_fe_driver_status_t *) &msg->msg[0]);
+ break;
+
+ default:
+ msg->length = 0;
+ break;
+ }
+
+ ctrl_if_send_response(msg);
+}
+
+
+#if 1
+/* Wait for all interfaces to be connected.
+ *
+ * This works OK, but we'd like to use the probing mode (see below).
+ */
+static int probe_interfaces(void)
+{
+ int err = 0, conn = 0;
+ int wait_i, wait_n = 100;
+
+ DPRINTK(">\n");
+
+ for (wait_i = 0; wait_i < wait_n; wait_i++) {
+ DPRINTK("> wait_i=%d\n", wait_i);
+ conn = netctrl_connected();
+ if(conn) break;
+ DPRINTK("> schedule_timeout...\n");
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(10);
+ }
+
+ DPRINTK("> wait finished...\n");
+ if (conn <= 0) {
+ err = netctrl_err(-ENETDOWN);
+ WPRINTK("Failed to connect all virtual interfaces: err=%d\n", err);
+ }
+
+ DPRINTK("< err=%d\n", err);
+
+ return err;
+}
+#else
+/* Probe for interfaces until no more are found.
+ *
+ * This is the mode we'd like to use, but at the moment it panics the kernel.
+*/
+static int probe_interfaces(void)
+{
+ int err = 0;
+ int wait_i, wait_n = 100;
+ ctrl_msg_t cmsg = {
+ .type = CMSG_NETIF_FE,
+ .subtype = CMSG_NETIF_FE_INTERFACE_STATUS,
+ .length = sizeof(netif_fe_interface_status_t),
+ };
+ netif_fe_interface_status_t msg = {};
+ ctrl_msg_t rmsg = {};
+ netif_fe_interface_status_t *reply = (void*)rmsg.msg;
+ int state = TASK_UNINTERRUPTIBLE;
+ u32 query = -1;
+
+ DPRINTK(">\n");
+
+ netctrl.interface_n = 0;
+ for (wait_i = 0; wait_i < wait_n; wait_i++) {
+ DPRINTK("> wait_i=%d query=%d\n", wait_i, query);
+ msg.handle = query;
+ memcpy(cmsg.msg, &msg, sizeof(msg));
+ DPRINTK("> set_current_state...\n");
+ set_current_state(state);
+ DPRINTK("> rmsg=%p msg=%p, reply=%p\n", &rmsg, rmsg.msg, reply);
+ DPRINTK("> sending...\n");
+ err = ctrl_if_send_message_and_get_response(&cmsg, &rmsg, state);
+ DPRINTK("> err=%d\n", err);
+ if(err) goto exit;
+ DPRINTK("> rmsg=%p msg=%p, reply=%p\n", &rmsg, rmsg.msg, reply);
+ if((int)reply->handle < 0) {
+ // No more interfaces.
+ break;
+ }
+ query = -reply->handle - 2;
+ DPRINTK(">netif_interface_status ...\n");
+ netif_interface_status(reply);
+ }
+
+ exit:
+ if (err) {
+ err = netctrl_err(-ENETDOWN);
+ WPRINTK("Connecting virtual network interfaces failed: err=%d\n", err);
+ }
+
+ DPRINTK("< err=%d\n", err);
+ return err;
+}
+
+#endif
+
+/*
+ * We use this notifier to send out a fake ARP reply to reset switches and
+ * router ARP caches when an IP interface is brought up on a VIF.
+ */
+static int
+inetdev_notify(struct notifier_block *this, unsigned long event, void *ptr)
+{
+ struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
+ struct net_device *dev = ifa->ifa_dev->dev;
+ struct list_head *ent;
+ struct net_private *np;
+
+ if (event != NETDEV_UP)
+ goto out;
+
+ list_for_each (ent, &dev_list) {
+ np = list_entry(ent, struct net_private, list);
+ if (np->dev == dev)
+ (void)send_fake_arp(dev);
+ }
+
+ out:
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block notifier_inetdev = {
+ .notifier_call = inetdev_notify,
+ .next = NULL,
+ .priority = 0
+};
+
+static int __init netif_init(void)
+{
+ int err = 0;
+
+ if (xen_start_info.flags & SIF_INITDOMAIN)
+ return 0;
+
+ if ((err = xennet_proc_init()) != 0)
+ return err;
+
+ IPRINTK("Initialising virtual ethernet driver.\n");
+ INIT_LIST_HEAD(&dev_list);
+ (void)register_inetaddr_notifier(¬ifier_inetdev);
+ netctrl_init();
+ (void)ctrl_if_register_receiver(CMSG_NETIF_FE, netif_ctrlif_rx,
+ CALLBACK_IN_BLOCKING_CONTEXT);
+ send_driver_status(1);
+ err = probe_interfaces();
+ if (err)
+ ctrl_if_unregister_receiver(CMSG_NETIF_FE, netif_ctrlif_rx);
+
+ DPRINTK("< err=%d\n", err);
+ return err;
+}
+
+static void vif_suspend(struct net_private *np)
+{
+ /* Avoid having tx/rx stuff happen until we're ready. */
+ free_irq(np->irq, np->dev);
+ unbind_evtchn_from_irq(np->evtchn);
+}
+
+static void vif_resume(struct net_private *np)
+{
+ /*
+ * Connect regardless of whether IFF_UP flag set.
+ * Stop bad things from happening until we're back up.
+ */
+ np->backend_state = BEST_DISCONNECTED;
+ memset(np->tx, 0, PAGE_SIZE);
+ memset(np->rx, 0, PAGE_SIZE);
+
+ send_interface_connect(np);
+}
+
+void netif_suspend(void)
+{
+ struct list_head *ent;
+ struct net_private *np;
+
+ list_for_each (ent, &dev_list) {
+ np = list_entry(ent, struct net_private, list);
+ vif_suspend(np);
+ }
+}
+
+void netif_resume(void)
+{
+ struct list_head *ent;
+ struct net_private *np;
+
+ list_for_each (ent, &dev_list) {
+ np = list_entry(ent, struct net_private, list);
+ vif_resume(np);
+ }
+}
+
+#ifdef CONFIG_PROC_FS
+
+#define TARGET_MIN 0UL
+#define TARGET_MAX 1UL
+#define TARGET_CUR 2UL
+
+static int xennet_proc_read(
+ char *page, char **start, off_t off, int count, int *eof, void *data)
+{
+ struct net_device *dev = (struct net_device *)((unsigned long)data & ~3UL);
+ struct net_private *np = netdev_priv(dev);
+ int len = 0, which_target = (long)data & 3;
+
+ switch (which_target)
+ {
+ case TARGET_MIN:
+ len = sprintf(page, "%d\n", np->rx_min_target);
+ break;
+ case TARGET_MAX:
+ len = sprintf(page, "%d\n", np->rx_max_target);
+ break;
+ case TARGET_CUR:
+ len = sprintf(page, "%d\n", np->rx_target);
+ break;
+ }
+
+ *eof = 1;
+ return len;
+}
+
+static int xennet_proc_write(
+ struct file *file, const char __user *buffer,
+ unsigned long count, void *data)
+{
+ struct net_device *dev = (struct net_device *)((unsigned long)data & ~3UL);
+ struct net_private *np = netdev_priv(dev);
+ int which_target = (long)data & 3;
+ char string[64];
+ long target;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (count <= 1)
+ return -EBADMSG; /* runt */
+ if (count > sizeof(string))
+ return -EFBIG; /* too long */
+
+ if (copy_from_user(string, buffer, count))
+ return -EFAULT;
+ string[sizeof(string)-1] = '\0';
+
+ target = simple_strtol(string, NULL, 10);
+ if (target < RX_MIN_TARGET)
+ target = RX_MIN_TARGET;
+ if (target > RX_MAX_TARGET)
+ target = RX_MAX_TARGET;
+
+ spin_lock(&np->rx_lock);
+
+ switch (which_target)
+ {
+ case TARGET_MIN:
+ if (target > np->rx_max_target)
+ np->rx_max_target = target;
+ np->rx_min_target = target;
+ if (target > np->rx_target)
+ np->rx_target = target;
+ break;
+ case TARGET_MAX:
+ if (target < np->rx_min_target)
+ np->rx_min_target = target;
+ np->rx_max_target = target;
+ if (target < np->rx_target)
+ np->rx_target = target;
+ break;
+ case TARGET_CUR:
+ break;
+ }
+
+ network_alloc_rx_buffers(dev);
+
+ spin_unlock(&np->rx_lock);
+
+ return count;
+}
+
+static int xennet_proc_init(void)
+{
+ if (proc_mkdir("xen/net", NULL) == NULL)
+ return -ENOMEM;
+ return 0;
+}
+
+static int xennet_proc_addif(struct net_device *dev)
+{
+ struct proc_dir_entry *dir, *min, *max, *cur;
+ char name[30];
+
+ sprintf(name, "xen/net/%s", dev->name);
+
+ dir = proc_mkdir(name, NULL);
+ if (!dir)
+ goto nomem;
+
+ min = create_proc_entry("rxbuf_min", 0644, dir);
+ max = create_proc_entry("rxbuf_max", 0644, dir);
+ cur = create_proc_entry("rxbuf_cur", 0444, dir);
+ if (!min || !max || !cur)
+ goto nomem;
+
+ min->read_proc = xennet_proc_read;
+ min->write_proc = xennet_proc_write;
+ min->data = (void *)((unsigned long)dev | TARGET_MIN);
+
+ max->read_proc = xennet_proc_read;
+ max->write_proc = xennet_proc_write;
+ max->data = (void *)((unsigned long)dev | TARGET_MAX);
+
+ cur->read_proc = xennet_proc_read;
+ cur->write_proc = xennet_proc_write;
+ cur->data = (void *)((unsigned long)dev | TARGET_CUR);
+
+ return 0;
+
+ nomem:
+ xennet_proc_delif(dev);
+ return -ENOMEM;
+}
+
+static void xennet_proc_delif(struct net_device *dev)
+{
+ char name[30];
+
+ sprintf(name, "xen/net/%s/rxbuf_min", dev->name);
+ remove_proc_entry(name, NULL);
+
+ sprintf(name, "xen/net/%s/rxbuf_max", dev->name);
+ remove_proc_entry(name, NULL);
+
+ sprintf(name, "xen/net/%s/rxbuf_cur", dev->name);
+ remove_proc_entry(name, NULL);
+
+ sprintf(name, "xen/net/%s", dev->name);
+ remove_proc_entry(name, NULL);
+}
+
+#endif
+
+module_init(netif_init);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/mm/hypervisor.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/mm/hypervisor.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,346 @@
+/******************************************************************************
+ * mm/hypervisor.c
+ *
+ * Update page tables via the hypervisor.
+ *
+ * Copyright (c) 2002-2004, K A Fraser
+ *
+ * This file may be distributed separately from the Linux kernel, or
+ * incorporated into other software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm-xen/hypervisor.h>
+#include <asm-xen/balloon.h>
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0)
+#include <linux/percpu.h>
+#include <asm/tlbflush.h>
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
+#define pte_offset_kernel pte_offset
+#define pud_t pgd_t
+#define pud_offset(d, va) d
+#elif defined(CONFIG_X86_64)
+#define pmd_val_ma(v) (v).pmd
+#else
+#define pmd_val_ma(v) (v).pud.pgd.pgd
+#endif
+
+#ifndef CONFIG_XEN_SHADOW_MODE
+void xen_l1_entry_update(pte_t *ptr, unsigned long val)
+{
+ mmu_update_t u;
+ u.ptr = virt_to_machine(ptr);
+ u.val = val;
+ BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_l2_entry_update(pmd_t *ptr, pmd_t val)
+{
+ mmu_update_t u;
+ u.ptr = virt_to_machine(ptr);
+ u.val = pmd_val_ma(val);
+ BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0);
+}
+
+#ifdef CONFIG_X86_64
+void xen_l3_entry_update(pud_t *ptr, pud_t val)
+{
+ mmu_update_t u;
+ u.ptr = virt_to_machine(ptr);
+ u.val = val.pud;
+ BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_l4_entry_update(pgd_t *ptr, pgd_t val)
+{
+ mmu_update_t u;
+ u.ptr = virt_to_machine(ptr);
+ u.val = val.pgd;
+ BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0);
+}
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_XEN_SHADOW_MODE */
+
+void xen_machphys_update(unsigned long mfn, unsigned long pfn)
+{
+ mmu_update_t u;
+ u.ptr = (mfn << PAGE_SHIFT) | MMU_MACHPHYS_UPDATE;
+ u.val = pfn;
+ BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_pt_switch(unsigned long ptr)
+{
+ struct mmuext_op op;
+ op.cmd = MMUEXT_NEW_BASEPTR;
+ op.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT);
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_new_user_pt(unsigned long ptr)
+{
+ struct mmuext_op op;
+ op.cmd = MMUEXT_NEW_USER_BASEPTR;
+ op.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT);
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_tlb_flush(void)
+{
+ struct mmuext_op op;
+ op.cmd = MMUEXT_TLB_FLUSH_LOCAL;
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_invlpg(unsigned long ptr)
+{
+ struct mmuext_op op;
+ op.cmd = MMUEXT_INVLPG_LOCAL;
+ op.linear_addr = ptr & PAGE_MASK;
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+#ifdef CONFIG_SMP
+
+void xen_tlb_flush_all(void)
+{
+ struct mmuext_op op;
+ op.cmd = MMUEXT_TLB_FLUSH_ALL;
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_tlb_flush_mask(cpumask_t *mask)
+{
+ struct mmuext_op op;
+ if ( cpus_empty(*mask) )
+ return;
+ op.cmd = MMUEXT_TLB_FLUSH_MULTI;
+ op.vcpumask = mask->bits;
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_invlpg_all(unsigned long ptr)
+{
+ struct mmuext_op op;
+ op.cmd = MMUEXT_INVLPG_ALL;
+ op.linear_addr = ptr & PAGE_MASK;
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_invlpg_mask(cpumask_t *mask, unsigned long ptr)
+{
+ struct mmuext_op op;
+ if ( cpus_empty(*mask) )
+ return;
+ op.cmd = MMUEXT_INVLPG_MULTI;
+ op.vcpumask = mask->bits;
+ op.linear_addr = ptr & PAGE_MASK;
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+#endif /* CONFIG_SMP */
+
+#ifndef CONFIG_XEN_SHADOW_MODE
+void xen_pgd_pin(unsigned long ptr)
+{
+ struct mmuext_op op;
+#ifdef CONFIG_X86_64
+ op.cmd = MMUEXT_PIN_L4_TABLE;
+#else
+ op.cmd = MMUEXT_PIN_L2_TABLE;
+#endif
+ op.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT);
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_pgd_unpin(unsigned long ptr)
+{
+ struct mmuext_op op;
+ op.cmd = MMUEXT_UNPIN_TABLE;
+ op.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT);
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_pte_pin(unsigned long ptr)
+{
+ struct mmuext_op op;
+ op.cmd = MMUEXT_PIN_L1_TABLE;
+ op.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT);
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_pte_unpin(unsigned long ptr)
+{
+ struct mmuext_op op;
+ op.cmd = MMUEXT_UNPIN_TABLE;
+ op.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT);
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+#ifdef CONFIG_X86_64
+void xen_pud_pin(unsigned long ptr)
+{
+ struct mmuext_op op;
+ op.cmd = MMUEXT_PIN_L3_TABLE;
+ op.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT);
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_pud_unpin(unsigned long ptr)
+{
+ struct mmuext_op op;
+ op.cmd = MMUEXT_UNPIN_TABLE;
+ op.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT);
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_pmd_pin(unsigned long ptr)
+{
+ struct mmuext_op op;
+ op.cmd = MMUEXT_PIN_L2_TABLE;
+ op.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT);
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_pmd_unpin(unsigned long ptr)
+{
+ struct mmuext_op op;
+ op.cmd = MMUEXT_UNPIN_TABLE;
+ op.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT);
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_XEN_SHADOW_MODE */
+
+void xen_set_ldt(unsigned long ptr, unsigned long len)
+{
+ struct mmuext_op op;
+ op.cmd = MMUEXT_SET_LDT;
+ op.linear_addr = ptr;
+ op.nr_ents = len;
+ BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0);
+}
+
+void xen_contig_memory(unsigned long vstart, unsigned int order)
+{
+ /*
+ * Ensure multi-page extents are contiguous in machine memory. This code
+ * could be cleaned up some, and the number of hypercalls reduced.
+ */
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+ unsigned long mfn, i, flags;
+
+ scrub_pages(vstart, 1 << order);
+
+ balloon_lock(flags);
+
+ /* 1. Zap current PTEs, giving away the underlying pages. */
+ for (i = 0; i < (1<<order); i++) {
+ pgd = pgd_offset_k(vstart + (i*PAGE_SIZE));
+ pud = pud_offset(pgd, (vstart + (i*PAGE_SIZE)));
+ pmd = pmd_offset(pud, (vstart + (i*PAGE_SIZE)));
+ pte = pte_offset_kernel(pmd, (vstart + (i*PAGE_SIZE)));
+ mfn = pte_mfn(*pte);
+ HYPERVISOR_update_va_mapping(
+ vstart + (i*PAGE_SIZE), __pte_ma(0), 0);
+ phys_to_machine_mapping[(__pa(vstart)>>PAGE_SHIFT)+i] =
+ INVALID_P2M_ENTRY;
+ BUG_ON(HYPERVISOR_dom_mem_op(
+ MEMOP_decrease_reservation, &mfn, 1, 0) != 1);
+ }
+
+ /* 2. Get a new contiguous memory extent. */
+ BUG_ON(HYPERVISOR_dom_mem_op(
+ MEMOP_increase_reservation, &mfn, 1, order) != 1);
+
+ /* 3. Map the new extent in place of old pages. */
+ for (i = 0; i < (1<<order); i++) {
+ HYPERVISOR_update_va_mapping(
+ vstart + (i*PAGE_SIZE),
+ __pte_ma(((mfn+i)<<PAGE_SHIFT)|__PAGE_KERNEL), 0);
+ xen_machphys_update(mfn+i, (__pa(vstart)>>PAGE_SHIFT)+i);
+ phys_to_machine_mapping[(__pa(vstart)>>PAGE_SHIFT)+i] = mfn+i;
+ }
+
+ flush_tlb_all();
+
+ balloon_unlock(flags);
+}
+
+#ifdef CONFIG_XEN_PHYSDEV_ACCESS
+
+unsigned long allocate_empty_lowmem_region(unsigned long pages)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+ unsigned long *pfn_array;
+ unsigned long vstart;
+ unsigned long i;
+ unsigned int order = get_order(pages*PAGE_SIZE);
+
+ vstart = __get_free_pages(GFP_KERNEL, order);
+ if ( vstart == 0 )
+ return 0UL;
+
+ scrub_pages(vstart, 1 << order);
+
+ pfn_array = vmalloc((1<<order) * sizeof(*pfn_array));
+ if ( pfn_array == NULL )
+ BUG();
+
+ for ( i = 0; i < (1<<order); i++ )
+ {
+ pgd = pgd_offset_k( (vstart + (i*PAGE_SIZE)));
+ pud = pud_offset(pgd, (vstart + (i*PAGE_SIZE)));
+ pmd = pmd_offset(pud, (vstart + (i*PAGE_SIZE)));
+ pte = pte_offset_kernel(pmd, (vstart + (i*PAGE_SIZE)));
+ pfn_array[i] = pte_mfn(*pte);
+#ifdef CONFIG_X86_64
+ xen_l1_entry_update(pte, 0);
+#else
+ HYPERVISOR_update_va_mapping(vstart + (i*PAGE_SIZE), __pte_ma(0), 0);
+#endif
+ phys_to_machine_mapping[(__pa(vstart)>>PAGE_SHIFT)+i] =
+ INVALID_P2M_ENTRY;
+ }
+
+ flush_tlb_all();
+
+ balloon_put_pages(pfn_array, 1 << order);
+
+ vfree(pfn_array);
+
+ return vstart;
+}
+
+#endif /* CONFIG_XEN_PHYSDEV_ACCESS */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/mm/init.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/mm/init.c Fri Jul 15 13:39:50 2005
@@ -0,0 +1,966 @@
+/*
+ * linux/arch/x86_64/mm/init.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ * Copyright (C) 2000 Pavel Machek <pavel@xxxxxxx>
+ * Copyright (C) 2002,2003 Andi Kleen <ak@xxxxxxx>
+ *
+ * Jun Nakajima <jun.nakajima@xxxxxxxxx>
+ * Modified for Xen.
+ */
+
+#include <linux/config.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/pagemap.h>
+#include <linux/bootmem.h>
+#include <linux/proc_fs.h>
+
+#include <asm/processor.h>
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/dma.h>
+#include <asm/fixmap.h>
+#include <asm/e820.h>
+#include <asm/apic.h>
+#include <asm/tlb.h>
+#include <asm/mmu_context.h>
+#include <asm/proto.h>
+#include <asm/smp.h>
+
+#ifndef Dprintk
+#define Dprintk(x...)
+#endif
+
+#ifdef CONFIG_GART_IOMMU
+extern int swiotlb;
+#endif
+
+extern char _stext[];
+
+DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
+extern unsigned long start_pfn;
+
+static int init_mapping_done;
+
+/*
+ * Use this until direct mapping is established, i.e. before __va() is
+ * avaialble in init_memory_mapping().
+ */
+
+#define addr_to_page(addr, page) \
+ (addr) &= PHYSICAL_PAGE_MASK; \
+ (page) = ((unsigned long *) ((unsigned long)(((mfn_to_pfn((addr) >>
PAGE_SHIFT)) << PAGE_SHIFT) + __START_KERNEL_map)))
+
+static void __make_page_readonly(unsigned long va)
+{
+ unsigned long addr;
+ pte_t *pte;
+ unsigned long *page = (unsigned long *) init_level4_pgt;
+
+ addr = (unsigned long) page[pgd_index(va)];
+ addr_to_page(addr, page);
+
+ addr = page[pud_index(va)];
+ addr_to_page(addr, page);
+
+ addr = page[pmd_index(va)];
+ addr_to_page(addr, page);
+
+ pte = (pte_t *) &page[pte_index(va)];
+ xen_l1_entry_update(pte, (*(unsigned long*)pte) & ~_PAGE_RW);
+ __flush_tlb_one(addr);
+}
+
+static void __make_page_writable(unsigned long va)
+{
+ unsigned long addr;
+ pte_t *pte;
+ unsigned long *page = (unsigned long *) init_level4_pgt;
+
+ addr = (unsigned long) page[pgd_index(va)];
+ addr_to_page(addr, page);
+
+ addr = page[pud_index(va)];
+ addr_to_page(addr, page);
+
+ addr = page[pmd_index(va)];
+ addr_to_page(addr, page);
+
+ pte = (pte_t *) &page[pte_index(va)];
+ xen_l1_entry_update(pte, (*(unsigned long*)pte)| _PAGE_RW);
+ __flush_tlb_one(addr);
+}
+
+
+/*
+ * Assume the translation is already established.
+ */
+void make_page_readonly(void *va)
+{
+ pgd_t* pgd; pud_t *pud; pmd_t* pmd; pte_t *pte;
+ unsigned long addr = (unsigned long) va;
+
+ if (!init_mapping_done) {
+ __make_page_readonly(addr);
+ return;
+ }
+
+ pgd = pgd_offset_k(addr);
+ pud = pud_offset(pgd, addr);
+ pmd = pmd_offset(pud, addr);
+ pte = pte_offset_kernel(pmd, addr);
+ xen_l1_entry_update(pte, (*(unsigned long*)pte)&~_PAGE_RW);
+ __flush_tlb_one(addr);
+}
+
+void make_page_writable(void *va)
+{
+ pgd_t* pgd; pud_t *pud; pmd_t* pmd; pte_t *pte;
+ unsigned long addr = (unsigned long) va;
+
+ if (!init_mapping_done) {
+ __make_page_writable(addr);
+ return;
+ }
+
+ pgd = pgd_offset_k(addr);
+ pud = pud_offset(pgd, addr);
+ pmd = pmd_offset(pud, addr);
+ pte = pte_offset_kernel(pmd, addr);
+ xen_l1_entry_update(pte, (*(unsigned long*)pte)|_PAGE_RW);
+ __flush_tlb_one(addr);
+}
+
+void make_pages_readonly(void* va, unsigned nr)
+{
+ while ( nr-- != 0 ) {
+ make_page_readonly(va);
+ va = (void*)((unsigned long)va + PAGE_SIZE);
+ }
+}
+
+void make_pages_writable(void* va, unsigned nr)
+{
+ while ( nr-- != 0 ) {
+ make_page_writable(va);
+ va = (void*)((unsigned long)va + PAGE_SIZE);
+ }
+}
+
+/*
+ * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
+ * physical space so we can cache the place of the first one and move
+ * around without checking the pgd every time.
+ */
+
+void show_mem(void)
+{
+ int i, total = 0, reserved = 0;
+ int shared = 0, cached = 0;
+ pg_data_t *pgdat;
+ struct page *page;
+
+ printk("Mem-info:\n");
+ show_free_areas();
+ printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
+
+ for_each_pgdat(pgdat) {
+ for (i = 0; i < pgdat->node_spanned_pages; ++i) {
+ page = pfn_to_page(pgdat->node_start_pfn + i);
+ total++;
+ if (PageReserved(page))
+ reserved++;
+ else if (PageSwapCache(page))
+ cached++;
+ else if (page_count(page))
+ shared += page_count(page) - 1;
+ }
+ }
+ printk("%d pages of RAM\n", total);
+ printk("%d reserved pages\n",reserved);
+ printk("%d pages shared\n",shared);
+ printk("%d pages swap cached\n",cached);
+}
+
+/* References to section boundaries */
+
+extern char _text, _etext, _edata, __bss_start, _end[];
+extern char __init_begin, __init_end;
+
+int after_bootmem;
+
+static void *spp_getpage(void)
+{
+ void *ptr;
+ if (after_bootmem)
+ ptr = (void *) get_zeroed_page(GFP_ATOMIC);
+ else
+ ptr = alloc_bootmem_pages(PAGE_SIZE);
+ if (!ptr || ((unsigned long)ptr & ~PAGE_MASK))
+ panic("set_pte_phys: cannot allocate page data %s\n",
after_bootmem?"after bootmem":"");
+
+ Dprintk("spp_getpage %p\n", ptr);
+ return ptr;
+}
+
+#define pgd_offset_u(address) (pgd_t *)(init_level4_user_pgt +
pgd_index(address))
+
+static inline pud_t *pud_offset_u(unsigned long address)
+{
+ pud_t *pud = level3_user_pgt;
+
+ return pud + pud_index(address);
+}
+
+static void set_pte_phys(unsigned long vaddr,
+ unsigned long phys, pgprot_t prot, int user_mode)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte, new_pte;
+
+ Dprintk("set_pte_phys %lx to %lx\n", vaddr, phys);
+
+ pgd = (user_mode ? pgd_offset_u(vaddr) : pgd_offset_k(vaddr));
+
+ if (pgd_none(*pgd)) {
+ printk("PGD FIXMAP MISSING, it should be setup in head.S!\n");
+ return;
+ }
+
+ pud = (user_mode ? pud_offset_u(vaddr) : pud_offset(pgd, vaddr));
+
+ if (pud_none(*pud)) {
+ pmd = (pmd_t *) spp_getpage();
+
+ make_page_readonly(pmd);
+ xen_pmd_pin(__pa(pmd));
+ set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | _PAGE_USER));
+ if (pmd != pmd_offset(pud, 0)) {
+ printk("PAGETABLE BUG #01! %p <-> %p\n", pmd,
pmd_offset(pud,0));
+ return;
+ }
+ }
+
+ pmd = pmd_offset(pud, vaddr);
+
+ if (pmd_none(*pmd)) {
+ pte = (pte_t *) spp_getpage();
+ make_page_readonly(pte);
+
+ xen_pte_pin(__pa(pte));
+ set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE | _PAGE_USER));
+ if (pte != pte_offset_kernel(pmd, 0)) {
+ printk("PAGETABLE BUG #02!\n");
+ return;
+ }
+ }
+ new_pte = pfn_pte(phys >> PAGE_SHIFT, prot);
+
+ pte = pte_offset_kernel(pmd, vaddr);
+
+ if (!pte_none(*pte) &&
+ pte_val(*pte) != (pte_val(new_pte) & __supported_pte_mask))
+ pte_ERROR(*pte);
+ xen_l1_entry_update(pte, new_pte.pte);
+
+ /*
+ * It's enough to flush this one mapping.
+ * (PGE mappings get flushed as well)
+ */
+ __flush_tlb_one(vaddr);
+}
+
+static void set_pte_phys_ma(unsigned long vaddr,
+ unsigned long phys, pgprot_t prot)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte, new_pte;
+
+ Dprintk("set_pte_phys %lx to %lx\n", vaddr, phys);
+
+ pgd = pgd_offset_k(vaddr);
+ if (pgd_none(*pgd)) {
+ printk("PGD FIXMAP MISSING, it should be setup in head.S!\n");
+ return;
+ }
+ pud = pud_offset(pgd, vaddr);
+ if (pud_none(*pud)) {
+
+ pmd = (pmd_t *) spp_getpage();
+ make_page_readonly(pmd);
+ xen_pmd_pin(__pa(pmd));
+
+ set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | _PAGE_USER));
+
+ if (pmd != pmd_offset(pud, 0)) {
+ printk("PAGETABLE BUG #01! %p <-> %p\n", pmd,
pmd_offset(pud,0));
+ return;
+ }
+ }
+ pmd = pmd_offset(pud, vaddr);
+
+ if (pmd_none(*pmd)) {
+ pte = (pte_t *) spp_getpage();
+ make_page_readonly(pte);
+ xen_pte_pin(__pa(pte));
+
+ set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE | _PAGE_USER));
+ if (pte != pte_offset_kernel(pmd, 0)) {
+ printk("PAGETABLE BUG #02!\n");
+ return;
+ }
+ }
+
+ new_pte = pfn_pte_ma(phys >> PAGE_SHIFT, prot);
+ pte = pte_offset_kernel(pmd, vaddr);
+
+ if (!pte_none(*pte) &&
+ pte_val_ma(*pte) != (pte_val_ma(new_pte) & __supported_pte_mask))
+ pte_ERROR(*pte);
+
+ /*
+ * Note that the pte page is already RO, thus we want to use
+ * xen_l1_entry_update(), not set_pte().
+ */
+ xen_l1_entry_update(pte,
+ (pfn_pte_ma(phys >> PAGE_SHIFT, prot).pte));
+
+ /*
+ * It's enough to flush this one mapping.
+ * (PGE mappings get flushed as well)
+ */
+ __flush_tlb_one(vaddr);
+}
+
+#define SET_FIXMAP_KERNEL 0
+#define SET_FIXMAP_USER 1
+
+/* NOTE: this is meant to be run only at boot */
+void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
+{
+ unsigned long address = __fix_to_virt(idx);
+
+ if (idx >= __end_of_fixed_addresses) {
+ printk("Invalid __set_fixmap\n");
+ return;
+ }
+ switch (idx) {
+ case VSYSCALL_FIRST_PAGE:
+ set_pte_phys(address, phys, prot, SET_FIXMAP_KERNEL);
+ break;
+ default:
+ set_pte_phys_ma(address, phys, prot);
+ break;
+ }
+}
+
+
+/*
+ * At this point it only supports vsyscall area.
+ */
+void __set_fixmap_user (enum fixed_addresses idx, unsigned long phys, pgprot_t
prot)
+{
+ unsigned long address = __fix_to_virt(idx);
+
+ if (idx >= __end_of_fixed_addresses) {
+ printk("Invalid __set_fixmap\n");
+ return;
+ }
+
+ set_pte_phys(address, phys, prot, SET_FIXMAP_USER);
+}
+
+unsigned long __initdata table_start, table_end, tables_space;
+
+unsigned long get_machine_pfn(unsigned long addr)
+{
+ pud_t* pud = pud_offset_k(addr);
+ pmd_t* pmd = pmd_offset(pud, addr);
+ pte_t *pte = pte_offset_kernel(pmd, addr);
+
+ return pte_mfn(*pte);
+}
+
+#define ALIGN_TO_4K __attribute__((section(".data.page_aligned")))
+#define MAX_LOW_PAGES 0x20
+static unsigned long __init_pgt[MAX_LOW_PAGES][512] ALIGN_TO_4K;
+static int __init_pgt_index;
+
+/*
+ * We start using from start_pfn
+ */
+static __init void *alloc_static_page(unsigned long *phys)
+{
+ int i = __init_pgt_index++;
+
+ if (__init_pgt_index >= MAX_LOW_PAGES) {
+ printk("Need to increase MAX_LOW_PAGES");
+ BUG();
+ }
+
+ *phys = __pa(__init_pgt[i]);
+
+ return (void *) __init_pgt[i];
+}
+
+/*
+ * Get RO page
+ */
+static void __init *alloc_low_page(unsigned long *phys)
+{
+ unsigned long pfn = table_end++;
+
+ *phys = (pfn << PAGE_SHIFT);
+ memset((void *) ((pfn << PAGE_SHIFT) + __START_KERNEL_map), 0,
PAGE_SIZE);
+ return (void *)((pfn << PAGE_SHIFT) + __START_KERNEL_map);
+}
+
+#define PTE_SIZE PAGE_SIZE
+
+static inline void __set_pte(pte_t *dst, pte_t val)
+{
+ *dst = val;
+}
+
+void __init phys_pud_init(pud_t *pud, unsigned long address, unsigned long end)
+{
+ long i, j, k;
+ unsigned long paddr;
+
+ i = pud_index(address);
+ pud = pud + i;
+
+ for (; i < PTRS_PER_PUD; pud++, i++) {
+ unsigned long pmd_phys;
+ pmd_t *pmd;
+
+ paddr = address + i*PUD_SIZE;
+ if (paddr >= end) {
+ for (; i < PTRS_PER_PUD; i++, pud++)
+ set_pud(pud, __pud(0));
+ break;
+ }
+
+ pmd = alloc_low_page(&pmd_phys);
+ make_page_readonly(pmd);
+ xen_pmd_pin(pmd_phys);
+ set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE));
+
+ for (j = 0; j < PTRS_PER_PMD; pmd++, j++) {
+ unsigned long pte_phys;
+ pte_t *pte, *pte_save;
+
+ if (paddr >= end) {
+ for (; j < PTRS_PER_PMD; j++, pmd++)
+ set_pmd(pmd, __pmd(0));
+ break;
+ }
+ pte = alloc_low_page(&pte_phys);
+ pte_save = pte;
+ for (k = 0; k < PTRS_PER_PTE; pte++, k++, paddr +=
PTE_SIZE) {
+ if (paddr < (table_start << PAGE_SHIFT)
+ + tables_space)
+ {
+ __set_pte(pte,
+ __pte(paddr | (_KERNPG_TABLE &
~_PAGE_RW)));
+ continue;
+ }
+ if (paddr >= end) {
+ for (; k < PTRS_PER_PTE; k++, pte++)
+ __set_pte(pte, __pte(0));
+ break;
+ }
+ __set_pte(pte, __pte(paddr | _KERNPG_TABLE));
+ }
+ pte = pte_save;
+ make_page_readonly(pte);
+ xen_pte_pin(pte_phys);
+ set_pmd(pmd, __pmd(pte_phys | _KERNPG_TABLE));
+ }
+ }
+ __flush_tlb();
+}
+
+static void __init find_early_table_space(unsigned long end)
+{
+ unsigned long puds, pmds, ptes;
+
+ puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
+ pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
+ ptes = (end + PTE_SIZE - 1) >> PAGE_SHIFT;
+
+ tables_space = round_up(puds * 8, PAGE_SIZE) +
+ round_up(pmds * 8, PAGE_SIZE) +
+ round_up(ptes * 8, PAGE_SIZE);
+}
+
+
+/*
+ * Extend kernel mapping to access pages for page tables. The initial
+ * mapping done by Xen is minimal (e.g. 8MB) and we need to extend the
+ * mapping for early initialization.
+ */
+
+#define MIN_INIT_SIZE 0x800000
+static unsigned long current_size, extended_size;
+
+void __init extend_init_mapping(void)
+{
+ unsigned long va = __START_KERNEL_map;
+ unsigned long addr, *pte_page;
+
+ unsigned long phys;
+ pmd_t *pmd;
+ pte_t *pte, new_pte;
+ unsigned long *page = (unsigned long *) init_level4_pgt;
+ int i;
+
+ addr = (unsigned long) page[pgd_index(va)];
+ addr_to_page(addr, page);
+
+ addr = page[pud_index(va)];
+ addr_to_page(addr, page);
+
+ for (;;) {
+ pmd = (pmd_t *) &page[pmd_index(va)];
+ if (pmd_present(*pmd)) {
+ /*
+ * if pmd is valid, check pte.
+ */
+ addr = page[pmd_index(va)];
+ addr_to_page(addr, pte_page);
+
+ for (i = 0; i < PTRS_PER_PTE; i++) {
+ pte = (pte_t *) &pte_page[pte_index(va)];
+
+ if (pte_present(*pte)) {
+ va += PAGE_SIZE;
+ current_size += PAGE_SIZE;
+ } else
+ break;
+ }
+
+ } else
+ break;
+ }
+
+ for (; va < __START_KERNEL_map + current_size + tables_space; ) {
+ pmd = (pmd_t *) &page[pmd_index(va)];
+
+ if (pmd_none(*pmd)) {
+ pte_page = (unsigned long *) alloc_static_page(&phys);
+ make_page_readonly(pte_page);
+ xen_pte_pin(phys);
+ set_pmd(pmd, __pmd(phys | _KERNPG_TABLE | _PAGE_USER));
+
+ for (i = 0; i < PTRS_PER_PTE; i++, va += PAGE_SIZE) {
+ new_pte = pfn_pte((va - __START_KERNEL_map) >>
PAGE_SHIFT,
+ __pgprot(_KERNPG_TABLE |
_PAGE_USER));
+
+ pte = (pte_t *) &pte_page[pte_index(va)];
+ xen_l1_entry_update(pte, new_pte.pte);
+ extended_size += PAGE_SIZE;
+ }
+ }
+ }
+}
+
+
+/* Setup the direct mapping of the physical memory at PAGE_OFFSET.
+ This runs before bootmem is initialized and gets pages directly from the
+ physical memory. To access them they are temporarily mapped. */
+void __init init_memory_mapping(unsigned long start, unsigned long end)
+{
+ unsigned long next;
+
+ Dprintk("init_memory_mapping\n");
+
+ find_early_table_space(end);
+ extend_init_mapping();
+ start_pfn = current_size >> PAGE_SHIFT;
+
+ table_start = start_pfn;
+ table_end = table_start;
+
+ start = (unsigned long)__va(start);
+ end = (unsigned long)__va(end);
+
+ for (; start < end; start = next) {
+ unsigned long pud_phys;
+ pud_t *pud = alloc_low_page(&pud_phys);
+ make_page_readonly(pud);
+ xen_pud_pin(pud_phys);
+ next = start + PGDIR_SIZE;
+ if (next > end)
+ next = end;
+ phys_pud_init(pud, __pa(start), __pa(next));
+ set_pgd(pgd_offset_k(start), mk_kernel_pgd(pud_phys));
+ }
+
+ printk("kernel direct mapping tables upto %lx @ %lx-%lx\n", end,
+ table_start<<PAGE_SHIFT,
+ table_end<<PAGE_SHIFT);
+
+ start_pfn = ((current_size + extended_size) >> PAGE_SHIFT);
+
+ /*
+ * TBD: Need to calculate at runtime
+ */
+
+ __flush_tlb_all();
+ init_mapping_done = 1;
+}
+
+extern struct x8664_pda cpu_pda[NR_CPUS];
+
+void zap_low_mappings(void)
+{
+ /* this is not required for Xen */
+#if 0
+ swap_low_mappings();
+#endif
+}
+
+#ifndef CONFIG_DISCONTIGMEM
+void __init paging_init(void)
+{
+ int i;
+
+ {
+ unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0};
+ /* unsigned int max_dma; */
+ /* max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >>
PAGE_SHIFT; */
+ /* if (end_pfn < max_dma) */
+ zones_size[ZONE_DMA] = end_pfn;
+#if 0
+ else {
+ zones_size[ZONE_DMA] = max_dma;
+ zones_size[ZONE_NORMAL] = end_pfn - max_dma;
+ }
+#endif
+ free_area_init(zones_size);
+ }
+
+ set_fixmap(FIX_SHARED_INFO, xen_start_info.shared_info);
+ HYPERVISOR_shared_info = (shared_info_t *)fix_to_virt(FIX_SHARED_INFO);
+
+ memset(empty_zero_page, 0, sizeof(empty_zero_page));
+
+#ifdef CONFIG_XEN_PHYSDEV_ACCESS
+ /* Setup mapping of lower 1st MB */
+ for (i = 0; i < NR_FIX_ISAMAPS; i++)
+ if (xen_start_info.flags & SIF_PRIVILEGED)
+ set_fixmap(FIX_ISAMAP_BEGIN - i, i * PAGE_SIZE);
+ else
+ __set_fixmap(FIX_ISAMAP_BEGIN - i,
+ virt_to_machine(empty_zero_page),
+ PAGE_KERNEL_RO);
+#endif
+
+}
+#endif
+
+/* Unmap a kernel mapping if it exists. This is useful to avoid prefetches
+ from the CPU leading to inconsistent cache lines. address and size
+ must be aligned to 2MB boundaries.
+ Does nothing when the mapping doesn't exist. */
+void __init clear_kernel_mapping(unsigned long address, unsigned long size)
+{
+ unsigned long end = address + size;
+
+ BUG_ON(address & ~LARGE_PAGE_MASK);
+ BUG_ON(size & ~LARGE_PAGE_MASK);
+
+ for (; address < end; address += LARGE_PAGE_SIZE) {
+ pgd_t *pgd = pgd_offset_k(address);
+ pud_t *pud;
+ pmd_t *pmd;
+ if (pgd_none(*pgd))
+ continue;
+ pud = pud_offset(pgd, address);
+ if (pud_none(*pud))
+ continue;
+ pmd = pmd_offset(pud, address);
+ if (!pmd || pmd_none(*pmd))
+ continue;
+ if (0 == (pmd_val(*pmd) & _PAGE_PSE)) {
+ /* Could handle this, but it should not happen
currently. */
+ printk(KERN_ERR
+ "clear_kernel_mapping: mapping has been split. will leak
memory\n");
+ pmd_ERROR(*pmd);
+ }
+ set_pmd(pmd, __pmd(0));
+ }
+ __flush_tlb_all();
+}
+
+static inline int page_is_ram (unsigned long pagenr)
+{
+ if (pagenr < start_pfn || pagenr >= end_pfn)
+ return 0;
+
+ return 1;
+}
+
+extern int swiotlb_force;
+
+static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules,
+ kcore_vsyscall;
+
+void __init mem_init(void)
+{
+ int codesize, reservedpages, datasize, initsize;
+ int tmp;
+
+#ifdef CONFIG_SWIOTLB
+ if (swiotlb_force)
+ swiotlb = 1;
+ if (!iommu_aperture &&
+ (end_pfn >= 0xffffffff>>PAGE_SHIFT || force_iommu))
+ swiotlb = 1;
+ if (swiotlb)
+ swiotlb_init();
+#endif
+
+ /* How many end-of-memory variables you have, grandma! */
+ max_low_pfn = end_pfn;
+ max_pfn = end_pfn;
+ num_physpages = end_pfn;
+ high_memory = (void *) __va(end_pfn * PAGE_SIZE);
+
+ /* clear the zero-page */
+ memset(empty_zero_page, 0, PAGE_SIZE);
+
+ reservedpages = 0;
+
+ /* this will put all low memory onto the freelists */
+#ifdef CONFIG_DISCONTIGMEM
+ totalram_pages += numa_free_all_bootmem();
+ tmp = 0;
+ /* should count reserved pages here for all nodes */
+#else
+ max_mapnr = end_pfn;
+ if (!mem_map) BUG();
+
+ totalram_pages += free_all_bootmem();
+
+ for (tmp = 0; tmp < end_pfn; tmp++)
+ /*
+ * Only count reserved RAM pages
+ */
+ if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp)))
+ reservedpages++;
+#endif
+
+ after_bootmem = 1;
+
+ codesize = (unsigned long) &_etext - (unsigned long) &_text;
+ datasize = (unsigned long) &_edata - (unsigned long) &_etext;
+ initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
+
+ /* Register memory areas for /proc/kcore */
+ kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT);
+ kclist_add(&kcore_vmalloc, (void *)VMALLOC_START,
+ VMALLOC_END-VMALLOC_START);
+ kclist_add(&kcore_kernel, &_stext, _end - _stext);
+ kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN);
+ kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START,
+ VSYSCALL_END - VSYSCALL_START);
+
+ printk("Memory: %luk/%luk available (%dk kernel code, %dk reserved, %dk
data, %dk init)\n",
+ (unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
+ end_pfn << (PAGE_SHIFT-10),
+ codesize >> 10,
+ reservedpages << (PAGE_SHIFT-10),
+ datasize >> 10,
+ initsize >> 10);
+
+ /*
+ * Subtle. SMP is doing its boot stuff late (because it has to
+ * fork idle threads) - but it also needs low mappings for the
+ * protected-mode entry to work. We zap these entries only after
+ * the WP-bit has been tested.
+ */
+#ifndef CONFIG_SMP
+ zap_low_mappings();
+#endif
+}
+
+extern char __initdata_begin[], __initdata_end[];
+
+void free_initmem(void)
+{
+#ifdef __DO_LATER__
+ /*
+ * Some pages can be pinned, but some are not. Unpinning such pages
+ * triggers BUG().
+ */
+ unsigned long addr;
+
+ addr = (unsigned long)(&__init_begin);
+ for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
+ ClearPageReserved(virt_to_page(addr));
+ set_page_count(virt_to_page(addr), 1);
+ memset((void *)(addr & ~(PAGE_SIZE-1)), 0xcc, PAGE_SIZE);
+ xen_pte_unpin(__pa(addr));
+ make_page_writable(__va(__pa(addr)));
+ /*
+ * Make pages from __PAGE_OFFSET address as well
+ */
+ make_page_writable((void *)addr);
+ free_page(addr);
+ totalram_pages++;
+ }
+ memset(__initdata_begin, 0xba, __initdata_end - __initdata_begin);
+ printk ("Freeing unused kernel memory: %luk freed\n", (&__init_end -
&__init_begin) >> 10);
+#endif
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void free_initrd_mem(unsigned long start, unsigned long end)
+{
+ if (start < (unsigned long)&_end)
+ return;
+ printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
+ for (; start < end; start += PAGE_SIZE) {
+ ClearPageReserved(virt_to_page(start));
+ set_page_count(virt_to_page(start), 1);
+ free_page(start);
+ totalram_pages++;
+ }
+}
+#endif
+
+void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
+{
+ /* Should check here against the e820 map to avoid double free */
+#ifdef CONFIG_DISCONTIGMEM
+ int nid = phys_to_nid(phys);
+ reserve_bootmem_node(NODE_DATA(nid), phys, len);
+#else
+ reserve_bootmem(phys, len);
+#endif
+}
+
+int kern_addr_valid(unsigned long addr)
+{
+ unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ if (above != 0 && above != -1UL)
+ return 0;
+
+ pgd = pgd_offset_k(addr);
+ if (pgd_none(*pgd))
+ return 0;
+
+ pud = pud_offset_k(addr);
+ if (pud_none(*pud))
+ return 0;
+
+ pmd = pmd_offset(pud, addr);
+ if (pmd_none(*pmd))
+ return 0;
+ if (pmd_large(*pmd))
+ return pfn_valid(pmd_pfn(*pmd));
+
+ pte = pte_offset_kernel(pmd, addr);
+ if (pte_none(*pte))
+ return 0;
+ return pfn_valid(pte_pfn(*pte));
+}
+
+#ifdef CONFIG_SYSCTL
+#include <linux/sysctl.h>
+
+extern int exception_trace, page_fault_trace;
+
+static ctl_table debug_table2[] = {
+ { 99, "exception-trace", &exception_trace, sizeof(int), 0644, NULL,
+ proc_dointvec },
+#ifdef CONFIG_CHECKING
+ { 100, "page-fault-trace", &page_fault_trace, sizeof(int), 0644, NULL,
+ proc_dointvec },
+#endif
+ { 0, }
+};
+
+static ctl_table debug_root_table2[] = {
+ { .ctl_name = CTL_DEBUG, .procname = "debug", .mode = 0555,
+ .child = debug_table2 },
+ { 0 },
+};
+
+static __init int x8664_sysctl_init(void)
+{
+ register_sysctl_table(debug_root_table2, 1);
+ return 0;
+}
+__initcall(x8664_sysctl_init);
+#endif
+
+/* Pseudo VMAs to allow ptrace access for the vsyscall pages. x86-64 has two
+ different ones: one for 32bit and one for 64bit. Use the appropiate
+ for the target task. */
+
+static struct vm_area_struct gate_vma = {
+ .vm_start = VSYSCALL_START,
+ .vm_end = VSYSCALL_END,
+ .vm_page_prot = PAGE_READONLY
+};
+
+static struct vm_area_struct gate32_vma = {
+ .vm_start = VSYSCALL32_BASE,
+ .vm_end = VSYSCALL32_END,
+ .vm_page_prot = PAGE_READONLY
+};
+
+struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+{
+#ifdef CONFIG_IA32_EMULATION
+ if (test_tsk_thread_flag(tsk, TIF_IA32)) {
+ /* lookup code assumes the pages are present. set them up
+ now */
+ if (__map_syscall32(tsk->mm, VSYSCALL32_BASE) < 0)
+ return NULL;
+ return &gate32_vma;
+ }
+#endif
+ return &gate_vma;
+}
+
+int in_gate_area(struct task_struct *task, unsigned long addr)
+{
+ struct vm_area_struct *vma = get_gate_vma(task);
+ return (addr >= vma->vm_start) && (addr < vma->vm_end);
+}
+
+/* Use this when you have no reliable task/vma, typically from interrupt
+ * context. It is less reliable than using the task's vma and may give
+ * false positives.
+ */
+int in_gate_area_no_task(unsigned long addr)
+{
+ return (((addr >= VSYSCALL_START) && (addr < VSYSCALL_END)) ||
+ ((addr >= VSYSCALL32_BASE) && (addr < VSYSCALL32_END)));
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/linux/skbuff.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/linux/skbuff.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,1181 @@
+/*
+ * Definitions for the 'struct sk_buff' memory handlers.
+ *
+ * Authors:
+ * Alan Cox, <gw4pts@xxxxxxxxxxxxxxx>
+ * Florian La Roche, <rzsfl@xxxxxxxxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_SKBUFF_H
+#define _LINUX_SKBUFF_H
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/time.h>
+#include <linux/cache.h>
+
+#include <asm/atomic.h>
+#include <asm/types.h>
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+
+#define HAVE_ALLOC_SKB /* For the drivers to know */
+#define HAVE_ALIGNABLE_SKB /* Ditto 8) */
+#define SLAB_SKB /* Slabified skbuffs */
+
+#define CHECKSUM_NONE 0
+#define CHECKSUM_HW 1
+#define CHECKSUM_UNNECESSARY 2
+
+#define SKB_DATA_ALIGN(X) (((X) + (SMP_CACHE_BYTES-1)) &
~(SMP_CACHE_BYTES-1))
+#define SKB_MAX_ORDER(X,ORDER) (((PAGE_SIZE<<(ORDER)) - (X) - sizeof(struct
skb_shared_info))&~(SMP_CACHE_BYTES-1))
+#define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X),0))
+#define SKB_MAX_ALLOC (SKB_MAX_ORDER(0,2))
+
+/* A. Checksumming of received packets by device.
+ *
+ * NONE: device failed to checksum this packet.
+ * skb->csum is undefined.
+ *
+ * UNNECESSARY: device parsed packet and wouldbe verified checksum.
+ * skb->csum is undefined.
+ * It is bad option, but, unfortunately, many of vendors do this.
+ * Apparently with secret goal to sell you new device, when you
+ * will add new protocol to your host. F.e. IPv6. 8)
+ *
+ * HW: the most generic way. Device supplied checksum of _all_
+ * the packet as seen by netif_rx in skb->csum.
+ * NOTE: Even if device supports only some protocols, but
+ * is able to produce some skb->csum, it MUST use HW,
+ * not UNNECESSARY.
+ *
+ * B. Checksumming on output.
+ *
+ * NONE: skb is checksummed by protocol or csum is not required.
+ *
+ * HW: device is required to csum packet as seen by hard_start_xmit
+ * from skb->h.raw to the end and to record the checksum
+ * at skb->h.raw+skb->csum.
+ *
+ * Device must show its capabilities in dev->features, set
+ * at device setup time.
+ * NETIF_F_HW_CSUM - it is clever device, it is able to checksum
+ * everything.
+ * NETIF_F_NO_CSUM - loopback or reliable single hop media.
+ * NETIF_F_IP_CSUM - device is dumb. It is able to csum only
+ * TCP/UDP over IPv4. Sigh. Vendors like this
+ * way by an unknown reason. Though, see comment above
+ * about CHECKSUM_UNNECESSARY. 8)
+ *
+ * Any questions? No questions, good. --ANK
+ */
+
+#ifdef __i386__
+#define NET_CALLER(arg) (*(((void**)&arg)-1))
+#else
+#define NET_CALLER(arg) __builtin_return_address(0)
+#endif
+
+#ifdef CONFIG_NETFILTER
+struct nf_conntrack {
+ atomic_t use;
+ void (*destroy)(struct nf_conntrack *);
+};
+
+struct nf_ct_info {
+ struct nf_conntrack *master;
+};
+#endif
+
+struct sk_buff_head {
+ /* These two members must be first. */
+ struct sk_buff * next;
+ struct sk_buff * prev;
+
+ __u32 qlen;
+ spinlock_t lock;
+};
+
+struct sk_buff;
+
+#define MAX_SKB_FRAGS 6
+
+typedef struct skb_frag_struct skb_frag_t;
+
+struct skb_frag_struct
+{
+ struct page *page;
+ __u16 page_offset;
+ __u16 size;
+};
+
+/* This data is invariant across clones and lives at
+ * the end of the header data, ie. at skb->end.
+ */
+struct skb_shared_info {
+ atomic_t dataref;
+ unsigned int nr_frags;
+ struct sk_buff *frag_list;
+ skb_frag_t frags[MAX_SKB_FRAGS];
+};
+
+struct sk_buff {
+ /* These two members must be first. */
+ struct sk_buff * next; /* Next buffer in list
*/
+ struct sk_buff * prev; /* Previous buffer in list
*/
+
+ struct sk_buff_head * list; /* List we are on
*/
+ struct sock *sk; /* Socket we are owned by
*/
+ struct timeval stamp; /* Time we arrived
*/
+ struct net_device *dev; /* Device we arrived on/are
leaving by */
+ struct net_device *real_dev; /* For support of point to
point protocols
+ (e.g. 802.3ad) over bonding,
we must save the
+ physical device that got the
packet before
+ replacing skb->dev with the
virtual device. */
+
+ /* Transport layer header */
+ union
+ {
+ struct tcphdr *th;
+ struct udphdr *uh;
+ struct icmphdr *icmph;
+ struct igmphdr *igmph;
+ struct iphdr *ipiph;
+ struct spxhdr *spxh;
+ unsigned char *raw;
+ } h;
+
+ /* Network layer header */
+ union
+ {
+ struct iphdr *iph;
+ struct ipv6hdr *ipv6h;
+ struct arphdr *arph;
+ struct ipxhdr *ipxh;
+ unsigned char *raw;
+ } nh;
+
+ /* Link layer header */
+ union
+ {
+ struct ethhdr *ethernet;
+ unsigned char *raw;
+ } mac;
+
+ struct dst_entry *dst;
+
+ /*
+ * This is the control buffer. It is free to use for every
+ * layer. Please put your private variables there. If you
+ * want to keep them across layers you have to do a skb_clone()
+ * first. This is owned by whoever has the skb queued ATM.
+ */
+ char cb[48];
+
+ unsigned int len; /* Length of actual data
*/
+ unsigned int data_len;
+ unsigned int csum; /* Checksum
*/
+ unsigned char __unused, /* Dead field, may be reused
*/
+ cloned, /* head may be cloned (check
refcnt to be sure). */
+ pkt_type, /* Packet class
*/
+ ip_summed; /* Driver fed us an IP checksum
*/
+ __u32 priority; /* Packet queueing priority
*/
+ atomic_t users; /* User count - see
datagram.c,tcp.c */
+ unsigned short protocol; /* Packet protocol from driver.
*/
+ unsigned short security; /* Security level of packet
*/
+ unsigned int truesize; /* Buffer size
*/
+
+ unsigned char *head; /* Head of buffer
*/
+ unsigned char *data; /* Data head pointer
*/
+ unsigned char *tail; /* Tail pointer
*/
+ unsigned char *end; /* End pointer
*/
+
+ void (*destructor)(struct sk_buff *); /* Destruct
function */
+#ifdef CONFIG_NETFILTER
+ /* Can be used for communication between hooks. */
+ unsigned long nfmark;
+ /* Cache info */
+ __u32 nfcache;
+ /* Associated connection, if any */
+ struct nf_ct_info *nfct;
+#ifdef CONFIG_NETFILTER_DEBUG
+ unsigned int nf_debug;
+#endif
+#endif /*CONFIG_NETFILTER*/
+
+#if defined(CONFIG_HIPPI)
+ union{
+ __u32 ifield;
+ } private;
+#endif
+
+#ifdef CONFIG_NET_SCHED
+ __u32 tc_index; /* traffic control index */
+#endif
+};
+
+#ifdef __KERNEL__
+/*
+ * Handling routines are only of interest to the kernel
+ */
+#include <linux/slab.h>
+
+#include <asm/system.h>
+
+extern void __kfree_skb(struct sk_buff *skb);
+extern struct sk_buff * alloc_skb(unsigned int size, int
priority);
+extern struct sk_buff * alloc_skb_from_cache(kmem_cache_t *cp,
unsigned int size, int priority);
+extern void kfree_skbmem(struct sk_buff *skb);
+extern struct sk_buff * skb_clone(struct sk_buff *skb, int
priority);
+extern struct sk_buff * skb_copy(const struct sk_buff *skb, int
priority);
+extern struct sk_buff * pskb_copy(struct sk_buff *skb, int
gfp_mask);
+extern int pskb_expand_head(struct sk_buff *skb, int
nhead, int ntail, int gfp_mask);
+extern struct sk_buff * skb_realloc_headroom(struct sk_buff
*skb, unsigned int headroom);
+extern struct sk_buff * skb_copy_expand(const struct sk_buff
*skb,
+ int newheadroom,
+ int newtailroom,
+ int priority);
+extern struct sk_buff * skb_pad(struct sk_buff *skb, int pad);
+#define dev_kfree_skb(a) kfree_skb(a)
+extern void skb_over_panic(struct sk_buff *skb, int len, void *here);
+extern void skb_under_panic(struct sk_buff *skb, int len, void *here);
+
+/* Internal */
+#define skb_shinfo(SKB) ((struct skb_shared_info *)((SKB)->end))
+
+/**
+ * skb_queue_empty - check if a queue is empty
+ * @list: queue head
+ *
+ * Returns true if the queue is empty, false otherwise.
+ */
+
+static inline int skb_queue_empty(struct sk_buff_head *list)
+{
+ return (list->next == (struct sk_buff *) list);
+}
+
+/**
+ * skb_get - reference buffer
+ * @skb: buffer to reference
+ *
+ * Makes another reference to a socket buffer and returns a pointer
+ * to the buffer.
+ */
+
+static inline struct sk_buff *skb_get(struct sk_buff *skb)
+{
+ atomic_inc(&skb->users);
+ return skb;
+}
+
+/*
+ * If users==1, we are the only owner and are can avoid redundant
+ * atomic change.
+ */
+
+/**
+ * kfree_skb - free an sk_buff
+ * @skb: buffer to free
+ *
+ * Drop a reference to the buffer and free it if the usage count has
+ * hit zero.
+ */
+
+static inline void kfree_skb(struct sk_buff *skb)
+{
+ if (likely(atomic_read(&skb->users) == 1))
+ smp_rmb();
+ else if (likely(!atomic_dec_and_test(&skb->users)))
+ return;
+ __kfree_skb(skb);
+}
+
+/**
+ * skb_cloned - is the buffer a clone
+ * @skb: buffer to check
+ *
+ * Returns true if the buffer was generated with skb_clone() and is
+ * one of multiple shared copies of the buffer. Cloned buffers are
+ * shared data so must not be written to under normal circumstances.
+ */
+
+static inline int skb_cloned(struct sk_buff *skb)
+{
+ return skb->cloned && atomic_read(&skb_shinfo(skb)->dataref) != 1;
+}
+
+/**
+ * skb_shared - is the buffer shared
+ * @skb: buffer to check
+ *
+ * Returns true if more than one person has a reference to this
+ * buffer.
+ */
+
+static inline int skb_shared(struct sk_buff *skb)
+{
+ return (atomic_read(&skb->users) != 1);
+}
+
+/**
+ * skb_share_check - check if buffer is shared and if so clone it
+ * @skb: buffer to check
+ * @pri: priority for memory allocation
+ *
+ * If the buffer is shared the buffer is cloned and the old copy
+ * drops a reference. A new clone with a single reference is returned.
+ * If the buffer is not shared the original buffer is returned. When
+ * being called from interrupt status or with spinlocks held pri must
+ * be GFP_ATOMIC.
+ *
+ * NULL is returned on a memory allocation failure.
+ */
+
+static inline struct sk_buff *skb_share_check(struct sk_buff *skb, int pri)
+{
+ if (skb_shared(skb)) {
+ struct sk_buff *nskb;
+ nskb = skb_clone(skb, pri);
+ kfree_skb(skb);
+ return nskb;
+ }
+ return skb;
+}
+
+
+/*
+ * Copy shared buffers into a new sk_buff. We effectively do COW on
+ * packets to handle cases where we have a local reader and forward
+ * and a couple of other messy ones. The normal one is tcpdumping
+ * a packet thats being forwarded.
+ */
+
+/**
+ * skb_unshare - make a copy of a shared buffer
+ * @skb: buffer to check
+ * @pri: priority for memory allocation
+ *
+ * If the socket buffer is a clone then this function creates a new
+ * copy of the data, drops a reference count on the old copy and returns
+ * the new copy with the reference count at 1. If the buffer is not a clone
+ * the original buffer is returned. When called with a spinlock held or
+ * from interrupt state @pri must be %GFP_ATOMIC
+ *
+ * %NULL is returned on a memory allocation failure.
+ */
+
+static inline struct sk_buff *skb_unshare(struct sk_buff *skb, int pri)
+{
+ struct sk_buff *nskb;
+ if(!skb_cloned(skb))
+ return skb;
+ nskb=skb_copy(skb, pri);
+ kfree_skb(skb); /* Free our shared copy */
+ return nskb;
+}
+
+/**
+ * skb_peek
+ * @list_: list to peek at
+ *
+ * Peek an &sk_buff. Unlike most other operations you _MUST_
+ * be careful with this one. A peek leaves the buffer on the
+ * list and someone else may run off with it. You must hold
+ * the appropriate locks or have a private queue to do this.
+ *
+ * Returns %NULL for an empty list or a pointer to the head element.
+ * The reference count is not incremented and the reference is therefore
+ * volatile. Use with caution.
+ */
+
+static inline struct sk_buff *skb_peek(struct sk_buff_head *list_)
+{
+ struct sk_buff *list = ((struct sk_buff *)list_)->next;
+ if (list == (struct sk_buff *)list_)
+ list = NULL;
+ return list;
+}
+
+/**
+ * skb_peek_tail
+ * @list_: list to peek at
+ *
+ * Peek an &sk_buff. Unlike most other operations you _MUST_
+ * be careful with this one. A peek leaves the buffer on the
+ * list and someone else may run off with it. You must hold
+ * the appropriate locks or have a private queue to do this.
+ *
+ * Returns %NULL for an empty list or a pointer to the tail element.
+ * The reference count is not incremented and the reference is therefore
+ * volatile. Use with caution.
+ */
+
+static inline struct sk_buff *skb_peek_tail(struct sk_buff_head *list_)
+{
+ struct sk_buff *list = ((struct sk_buff *)list_)->prev;
+ if (list == (struct sk_buff *)list_)
+ list = NULL;
+ return list;
+}
+
+/**
+ * skb_queue_len - get queue length
+ * @list_: list to measure
+ *
+ * Return the length of an &sk_buff queue.
+ */
+
+static inline __u32 skb_queue_len(struct sk_buff_head *list_)
+{
+ return(list_->qlen);
+}
+
+static inline void skb_queue_head_init(struct sk_buff_head *list)
+{
+ spin_lock_init(&list->lock);
+ list->prev = (struct sk_buff *)list;
+ list->next = (struct sk_buff *)list;
+ list->qlen = 0;
+}
+
+/*
+ * Insert an sk_buff at the start of a list.
+ *
+ * The "__skb_xxxx()" functions are the non-atomic ones that
+ * can only be called with interrupts disabled.
+ */
+
+/**
+ * __skb_queue_head - queue a buffer at the list head
+ * @list: list to use
+ * @newsk: buffer to queue
+ *
+ * Queue a buffer at the start of a list. This function takes no locks
+ * and you must therefore hold required locks before calling it.
+ *
+ * A buffer cannot be placed on two lists at the same time.
+ */
+
+static inline void __skb_queue_head(struct sk_buff_head *list, struct sk_buff
*newsk)
+{
+ struct sk_buff *prev, *next;
+
+ newsk->list = list;
+ list->qlen++;
+ prev = (struct sk_buff *)list;
+ next = prev->next;
+ newsk->next = next;
+ newsk->prev = prev;
+ next->prev = newsk;
+ prev->next = newsk;
+}
+
+
+/**
+ * skb_queue_head - queue a buffer at the list head
+ * @list: list to use
+ * @newsk: buffer to queue
+ *
+ * Queue a buffer at the start of the list. This function takes the
+ * list lock and can be used safely with other locking &sk_buff functions
+ * safely.
+ *
+ * A buffer cannot be placed on two lists at the same time.
+ */
+
+static inline void skb_queue_head(struct sk_buff_head *list, struct sk_buff
*newsk)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&list->lock, flags);
+ __skb_queue_head(list, newsk);
+ spin_unlock_irqrestore(&list->lock, flags);
+}
+
+/**
+ * __skb_queue_tail - queue a buffer at the list tail
+ * @list: list to use
+ * @newsk: buffer to queue
+ *
+ * Queue a buffer at the end of a list. This function takes no locks
+ * and you must therefore hold required locks before calling it.
+ *
+ * A buffer cannot be placed on two lists at the same time.
+ */
+
+
+static inline void __skb_queue_tail(struct sk_buff_head *list, struct sk_buff
*newsk)
+{
+ struct sk_buff *prev, *next;
+
+ newsk->list = list;
+ list->qlen++;
+ next = (struct sk_buff *)list;
+ prev = next->prev;
+ newsk->next = next;
+ newsk->prev = prev;
+ next->prev = newsk;
+ prev->next = newsk;
+}
+
+/**
+ * skb_queue_tail - queue a buffer at the list tail
+ * @list: list to use
+ * @newsk: buffer to queue
+ *
+ * Queue a buffer at the tail of the list. This function takes the
+ * list lock and can be used safely with other locking &sk_buff functions
+ * safely.
+ *
+ * A buffer cannot be placed on two lists at the same time.
+ */
+
+static inline void skb_queue_tail(struct sk_buff_head *list, struct sk_buff
*newsk)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&list->lock, flags);
+ __skb_queue_tail(list, newsk);
+ spin_unlock_irqrestore(&list->lock, flags);
+}
+
+/**
+ * __skb_dequeue - remove from the head of the queue
+ * @list: list to dequeue from
+ *
+ * Remove the head of the list. This function does not take any locks
+ * so must be used with appropriate locks held only. The head item is
+ * returned or %NULL if the list is empty.
+ */
+
+static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list)
+{
+ struct sk_buff *next, *prev, *result;
+
+ prev = (struct sk_buff *) list;
+ next = prev->next;
+ result = NULL;
+ if (next != prev) {
+ result = next;
+ next = next->next;
+ list->qlen--;
+ next->prev = prev;
+ prev->next = next;
+ result->next = NULL;
+ result->prev = NULL;
+ result->list = NULL;
+ }
+ return result;
+}
+
+/**
+ * skb_dequeue - remove from the head of the queue
+ * @list: list to dequeue from
+ *
+ * Remove the head of the list. The list lock is taken so the function
+ * may be used safely with other locking list functions. The head item is
+ * returned or %NULL if the list is empty.
+ */
+
+static inline struct sk_buff *skb_dequeue(struct sk_buff_head *list)
+{
+ unsigned long flags;
+ struct sk_buff *result;
+
+ spin_lock_irqsave(&list->lock, flags);
+ result = __skb_dequeue(list);
+ spin_unlock_irqrestore(&list->lock, flags);
+ return result;
+}
+
+/*
+ * Insert a packet on a list.
+ */
+
+static inline void __skb_insert(struct sk_buff *newsk,
+ struct sk_buff * prev, struct sk_buff *next,
+ struct sk_buff_head * list)
+{
+ newsk->next = next;
+ newsk->prev = prev;
+ next->prev = newsk;
+ prev->next = newsk;
+ newsk->list = list;
+ list->qlen++;
+}
+
+/**
+ * skb_insert - insert a buffer
+ * @old: buffer to insert before
+ * @newsk: buffer to insert
+ *
+ * Place a packet before a given packet in a list. The list locks are taken
+ * and this function is atomic with respect to other list locked calls
+ * A buffer cannot be placed on two lists at the same time.
+ */
+
+static inline void skb_insert(struct sk_buff *old, struct sk_buff *newsk)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&old->list->lock, flags);
+ __skb_insert(newsk, old->prev, old, old->list);
+ spin_unlock_irqrestore(&old->list->lock, flags);
+}
+
+/*
+ * Place a packet after a given packet in a list.
+ */
+
+static inline void __skb_append(struct sk_buff *old, struct sk_buff *newsk)
+{
+ __skb_insert(newsk, old, old->next, old->list);
+}
+
+/**
+ * skb_append - append a buffer
+ * @old: buffer to insert after
+ * @newsk: buffer to insert
+ *
+ * Place a packet after a given packet in a list. The list locks are taken
+ * and this function is atomic with respect to other list locked calls.
+ * A buffer cannot be placed on two lists at the same time.
+ */
+
+
+static inline void skb_append(struct sk_buff *old, struct sk_buff *newsk)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&old->list->lock, flags);
+ __skb_append(old, newsk);
+ spin_unlock_irqrestore(&old->list->lock, flags);
+}
+
+/*
+ * remove sk_buff from list. _Must_ be called atomically, and with
+ * the list known..
+ */
+
+static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
+{
+ struct sk_buff * next, * prev;
+
+ list->qlen--;
+ next = skb->next;
+ prev = skb->prev;
+ skb->next = NULL;
+ skb->prev = NULL;
+ skb->list = NULL;
+ next->prev = prev;
+ prev->next = next;
+}
+
+/**
+ * skb_unlink - remove a buffer from a list
+ * @skb: buffer to remove
+ *
+ * Place a packet after a given packet in a list. The list locks are taken
+ * and this function is atomic with respect to other list locked calls
+ *
+ * Works even without knowing the list it is sitting on, which can be
+ * handy at times. It also means that THE LIST MUST EXIST when you
+ * unlink. Thus a list must have its contents unlinked before it is
+ * destroyed.
+ */
+
+static inline void skb_unlink(struct sk_buff *skb)
+{
+ struct sk_buff_head *list = skb->list;
+
+ if(list) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&list->lock, flags);
+ if(skb->list == list)
+ __skb_unlink(skb, skb->list);
+ spin_unlock_irqrestore(&list->lock, flags);
+ }
+}
+
+/* XXX: more streamlined implementation */
+
+/**
+ * __skb_dequeue_tail - remove from the tail of the queue
+ * @list: list to dequeue from
+ *
+ * Remove the tail of the list. This function does not take any locks
+ * so must be used with appropriate locks held only. The tail item is
+ * returned or %NULL if the list is empty.
+ */
+
+static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list)
+{
+ struct sk_buff *skb = skb_peek_tail(list);
+ if (skb)
+ __skb_unlink(skb, list);
+ return skb;
+}
+
+/**
+ * skb_dequeue - remove from the head of the queue
+ * @list: list to dequeue from
+ *
+ * Remove the head of the list. The list lock is taken so the function
+ * may be used safely with other locking list functions. The tail item is
+ * returned or %NULL if the list is empty.
+ */
+
+static inline struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list)
+{
+ unsigned long flags;
+ struct sk_buff *result;
+
+ spin_lock_irqsave(&list->lock, flags);
+ result = __skb_dequeue_tail(list);
+ spin_unlock_irqrestore(&list->lock, flags);
+ return result;
+}
+
+static inline int skb_is_nonlinear(const struct sk_buff *skb)
+{
+ return skb->data_len;
+}
+
+static inline unsigned int skb_headlen(const struct sk_buff *skb)
+{
+ return skb->len - skb->data_len;
+}
+
+#define SKB_PAGE_ASSERT(skb) do { if (skb_shinfo(skb)->nr_frags)
out_of_line_bug(); } while (0)
+#define SKB_FRAG_ASSERT(skb) do { if (skb_shinfo(skb)->frag_list)
out_of_line_bug(); } while (0)
+#define SKB_LINEAR_ASSERT(skb) do { if (skb_is_nonlinear(skb))
out_of_line_bug(); } while (0)
+
+/*
+ * Add data to an sk_buff
+ */
+
+static inline unsigned char *__skb_put(struct sk_buff *skb, unsigned int len)
+{
+ unsigned char *tmp=skb->tail;
+ SKB_LINEAR_ASSERT(skb);
+ skb->tail+=len;
+ skb->len+=len;
+ return tmp;
+}
+
+/**
+ * skb_put - add data to a buffer
+ * @skb: buffer to use
+ * @len: amount of data to add
+ *
+ * This function extends the used data area of the buffer. If this would
+ * exceed the total buffer size the kernel will panic. A pointer to the
+ * first byte of the extra data is returned.
+ */
+
+static inline unsigned char *skb_put(struct sk_buff *skb, unsigned int len)
+{
+ unsigned char *tmp=skb->tail;
+ SKB_LINEAR_ASSERT(skb);
+ skb->tail+=len;
+ skb->len+=len;
+ if(skb->tail>skb->end) {
+ skb_over_panic(skb, len, current_text_addr());
+ }
+ return tmp;
+}
+
+static inline unsigned char *__skb_push(struct sk_buff *skb, unsigned int len)
+{
+ skb->data-=len;
+ skb->len+=len;
+ return skb->data;
+}
+
+/**
+ * skb_push - add data to the start of a buffer
+ * @skb: buffer to use
+ * @len: amount of data to add
+ *
+ * This function extends the used data area of the buffer at the buffer
+ * start. If this would exceed the total buffer headroom the kernel will
+ * panic. A pointer to the first byte of the extra data is returned.
+ */
+
+static inline unsigned char *skb_push(struct sk_buff *skb, unsigned int len)
+{
+ skb->data-=len;
+ skb->len+=len;
+ if(skb->data<skb->head) {
+ skb_under_panic(skb, len, current_text_addr());
+ }
+ return skb->data;
+}
+
+static inline char *__skb_pull(struct sk_buff *skb, unsigned int len)
+{
+ skb->len-=len;
+ if (skb->len < skb->data_len)
+ out_of_line_bug();
+ return skb->data+=len;
+}
+
+/**
+ * skb_pull - remove data from the start of a buffer
+ * @skb: buffer to use
+ * @len: amount of data to remove
+ *
+ * This function removes data from the start of a buffer, returning
+ * the memory to the headroom. A pointer to the next data in the buffer
+ * is returned. Once the data has been pulled future pushes will overwrite
+ * the old data.
+ */
+
+static inline unsigned char * skb_pull(struct sk_buff *skb, unsigned int len)
+{
+ if (len > skb->len)
+ return NULL;
+ return __skb_pull(skb,len);
+}
+
+extern unsigned char * __pskb_pull_tail(struct sk_buff *skb, int delta);
+
+static inline char *__pskb_pull(struct sk_buff *skb, unsigned int len)
+{
+ if (len > skb_headlen(skb) &&
+ __pskb_pull_tail(skb, len-skb_headlen(skb)) == NULL)
+ return NULL;
+ skb->len -= len;
+ return skb->data += len;
+}
+
+static inline unsigned char * pskb_pull(struct sk_buff *skb, unsigned int len)
+{
+ if (len > skb->len)
+ return NULL;
+ return __pskb_pull(skb,len);
+}
+
+static inline int pskb_may_pull(struct sk_buff *skb, unsigned int len)
+{
+ if (len <= skb_headlen(skb))
+ return 1;
+ if (len > skb->len)
+ return 0;
+ return (__pskb_pull_tail(skb, len-skb_headlen(skb)) != NULL);
+}
+
+/**
+ * skb_headroom - bytes at buffer head
+ * @skb: buffer to check
+ *
+ * Return the number of bytes of free space at the head of an &sk_buff.
+ */
+
+static inline int skb_headroom(const struct sk_buff *skb)
+{
+ return skb->data-skb->head;
+}
+
+/**
+ * skb_tailroom - bytes at buffer end
+ * @skb: buffer to check
+ *
+ * Return the number of bytes of free space at the tail of an sk_buff
+ */
+
+static inline int skb_tailroom(const struct sk_buff *skb)
+{
+ return skb_is_nonlinear(skb) ? 0 : skb->end-skb->tail;
+}
+
+/**
+ * skb_reserve - adjust headroom
+ * @skb: buffer to alter
+ * @len: bytes to move
+ *
+ * Increase the headroom of an empty &sk_buff by reducing the tail
+ * room. This is only allowed for an empty buffer.
+ */
+
+static inline void skb_reserve(struct sk_buff *skb, unsigned int len)
+{
+ skb->data+=len;
+ skb->tail+=len;
+}
+
+extern int ___pskb_trim(struct sk_buff *skb, unsigned int len, int realloc);
+
+static inline void __skb_trim(struct sk_buff *skb, unsigned int len)
+{
+ if (!skb->data_len) {
+ skb->len = len;
+ skb->tail = skb->data+len;
+ } else {
+ ___pskb_trim(skb, len, 0);
+ }
+}
+
+/**
+ * skb_trim - remove end from a buffer
+ * @skb: buffer to alter
+ * @len: new length
+ *
+ * Cut the length of a buffer down by removing data from the tail. If
+ * the buffer is already under the length specified it is not modified.
+ */
+
+static inline void skb_trim(struct sk_buff *skb, unsigned int len)
+{
+ if (skb->len > len) {
+ __skb_trim(skb, len);
+ }
+}
+
+
+static inline int __pskb_trim(struct sk_buff *skb, unsigned int len)
+{
+ if (!skb->data_len) {
+ skb->len = len;
+ skb->tail = skb->data+len;
+ return 0;
+ } else {
+ return ___pskb_trim(skb, len, 1);
+ }
+}
+
+static inline int pskb_trim(struct sk_buff *skb, unsigned int len)
+{
+ if (len < skb->len)
+ return __pskb_trim(skb, len);
+ return 0;
+}
+
+/**
+ * skb_orphan - orphan a buffer
+ * @skb: buffer to orphan
+ *
+ * If a buffer currently has an owner then we call the owner's
+ * destructor function and make the @skb unowned. The buffer continues
+ * to exist but is no longer charged to its former owner.
+ */
+
+
+static inline void skb_orphan(struct sk_buff *skb)
+{
+ if (skb->destructor)
+ skb->destructor(skb);
+ skb->destructor = NULL;
+ skb->sk = NULL;
+}
+
+/**
+ * skb_purge - empty a list
+ * @list: list to empty
+ *
+ * Delete all buffers on an &sk_buff list. Each buffer is removed from
+ * the list and one reference dropped. This function takes the list
+ * lock and is atomic with respect to other list locking functions.
+ */
+
+
+static inline void skb_queue_purge(struct sk_buff_head *list)
+{
+ struct sk_buff *skb;
+ while ((skb=skb_dequeue(list))!=NULL)
+ kfree_skb(skb);
+}
+
+/**
+ * __skb_purge - empty a list
+ * @list: list to empty
+ *
+ * Delete all buffers on an &sk_buff list. Each buffer is removed from
+ * the list and one reference dropped. This function does not take the
+ * list lock and the caller must hold the relevant locks to use it.
+ */
+
+
+static inline void __skb_queue_purge(struct sk_buff_head *list)
+{
+ struct sk_buff *skb;
+ while ((skb=__skb_dequeue(list))!=NULL)
+ kfree_skb(skb);
+}
+
+/**
+ * __dev_alloc_skb - allocate an skbuff for sending
+ * @length: length to allocate
+ * @gfp_mask: get_free_pages mask, passed to alloc_skb
+ *
+ * Allocate a new &sk_buff and assign it a usage count of one. The
+ * buffer has unspecified headroom built in. Users should allocate
+ * the headroom they think they need without accounting for the
+ * built in space. The built in space is used for optimisations.
+ *
+ * %NULL is returned in there is no free memory.
+ */
+#ifndef CONFIG_XEN
+static inline struct sk_buff *__dev_alloc_skb(unsigned int length,
+ int gfp_mask)
+{
+ struct sk_buff *skb = alloc_skb(length+16, gfp_mask);
+ if (skb)
+ skb_reserve(skb,16);
+ return skb;
+}
+#else
+extern struct sk_buff *__dev_alloc_skb(unsigned int length, int gfp_mask);
+#endif
+
+/**
+ * dev_alloc_skb - allocate an skbuff for sending
+ * @length: length to allocate
+ *
+ * Allocate a new &sk_buff and assign it a usage count of one. The
+ * buffer has unspecified headroom built in. Users should allocate
+ * the headroom they think they need without accounting for the
+ * built in space. The built in space is used for optimisations.
+ *
+ * %NULL is returned in there is no free memory. Although this function
+ * allocates memory it can be called from an interrupt.
+ */
+
+static inline struct sk_buff *dev_alloc_skb(unsigned int length)
+{
+ return __dev_alloc_skb(length, GFP_ATOMIC);
+}
+
+/**
+ * skb_cow - copy header of skb when it is required
+ * @skb: buffer to cow
+ * @headroom: needed headroom
+ *
+ * If the skb passed lacks sufficient headroom or its data part
+ * is shared, data is reallocated. If reallocation fails, an error
+ * is returned and original skb is not changed.
+ *
+ * The result is skb with writable area skb->head...skb->tail
+ * and at least @headroom of space at head.
+ */
+
+static inline int
+skb_cow(struct sk_buff *skb, unsigned int headroom)
+{
+ int delta = (headroom > 16 ? headroom : 16) - skb_headroom(skb);
+
+ if (delta < 0)
+ delta = 0;
+
+ if (delta || skb_cloned(skb))
+ return pskb_expand_head(skb, (delta+15)&~15, 0, GFP_ATOMIC);
+ return 0;
+}
+
+/**
+ * skb_padto - pad an skbuff up to a minimal size
+ * @skb: buffer to pad
+ * @len: minimal length
+ *
+ * Pads up a buffer to ensure the trailing bytes exist and are
+ * blanked. If the buffer already contains sufficient data it
+ * is untouched. Returns the buffer, which may be a replacement
+ * for the original, or NULL for out of memory - in which case
+ * the original buffer is still freed.
+ */
+
+static inline struct sk_buff *skb_padto(struct sk_buff *skb, unsigned int len)
+{
+ unsigned int size = skb->len;
+ if(likely(size >= len))
+ return skb;
+ return skb_pad(skb, len-size);
+}
+
+/**
+ * skb_linearize - convert paged skb to linear one
+ * @skb: buffer to linarize
+ * @gfp: allocation mode
+ *
+ * If there is no free memory -ENOMEM is returned, otherwise zero
+ * is returned and the old skb data released. */
+int skb_linearize(struct sk_buff *skb, int gfp);
+
+static inline void *kmap_skb_frag(const skb_frag_t *frag)
+{
+#ifdef CONFIG_HIGHMEM
+ if (in_irq())
+ out_of_line_bug();
+
+ local_bh_disable();
+#endif
+ return kmap_atomic(frag->page, KM_SKB_DATA_SOFTIRQ);
+}
+
+static inline void kunmap_skb_frag(void *vaddr)
+{
+ kunmap_atomic(vaddr, KM_SKB_DATA_SOFTIRQ);
+#ifdef CONFIG_HIGHMEM
+ local_bh_enable();
+#endif
+}
+
+#define skb_queue_walk(queue, skb) \
+ for (skb = (queue)->next; \
+ (skb != (struct sk_buff *)(queue)); \
+ skb=skb->next)
+
+
+extern struct sk_buff * skb_recv_datagram(struct sock
*sk,unsigned flags,int noblock, int *err);
+extern unsigned int datagram_poll(struct file *file, struct socket
*sock, struct poll_table_struct *wait);
+extern int skb_copy_datagram(const struct sk_buff *from,
int offset, char *to,int size);
+extern int skb_copy_datagram_iovec(const struct sk_buff
*from, int offset, struct iovec *to,int size);
+extern int skb_copy_and_csum_datagram(const struct sk_buff
*skb, int offset, u8 *to, int len, unsigned int *csump);
+extern int skb_copy_and_csum_datagram_iovec(const struct
sk_buff *skb, int hlen, struct iovec *iov);
+extern void skb_free_datagram(struct sock * sk, struct
sk_buff *skb);
+
+extern unsigned int skb_checksum(const struct sk_buff *skb, int
offset, int len, unsigned int csum);
+extern int skb_copy_bits(const struct sk_buff *skb, int
offset, void *to, int len);
+extern unsigned int skb_copy_and_csum_bits(const struct sk_buff
*skb, int offset, u8 *to, int len, unsigned int csum);
+extern void skb_copy_and_csum_dev(const struct sk_buff
*skb, u8 *to);
+
+extern void skb_init(void);
+extern void skb_add_mtu(int mtu);
+
+#ifdef CONFIG_NETFILTER
+static inline void
+nf_conntrack_put(struct nf_ct_info *nfct)
+{
+ if (nfct && atomic_dec_and_test(&nfct->master->use))
+ nfct->master->destroy(nfct->master);
+}
+static inline void
+nf_conntrack_get(struct nf_ct_info *nfct)
+{
+ if (nfct)
+ atomic_inc(&nfct->master->use);
+}
+static inline void
+nf_reset(struct sk_buff *skb)
+{
+ nf_conntrack_put(skb->nfct);
+ skb->nfct = NULL;
+#ifdef CONFIG_NETFILTER_DEBUG
+ skb->nf_debug = 0;
+#endif
+}
+#else /* CONFIG_NETFILTER */
+static inline void nf_reset(struct sk_buff *skb) {}
+#endif /* CONFIG_NETFILTER */
+
+#endif /* __KERNEL__ */
+#endif /* _LINUX_SKBUFF_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/netback/loopback.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/netback/loopback.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,164 @@
+/******************************************************************************
+ * netback/loopback.c
+ *
+ * A two-interface loopback device to emulate a local netfront-netback
+ * connection. This ensures that local packet delivery looks identical
+ * to inter-domain delivery. Most importantly, packets delivered locally
+ * originating from other domains will get *copied* when they traverse this
+ * driver. This prevents unbounded delays in socket-buffer queues from
+ * causing the netback driver to "seize up".
+ *
+ * This driver creates a symmetric pair of loopback interfaces with names
+ * vif0.0 and veth0. The intention is that 'vif0.0' is bound to an Ethernet
+ * bridge, just like a proper netback interface, while a local IP interface
+ * is configured on 'veth0'.
+ *
+ * As with a real netback interface, vif0.0 is configured with a suitable
+ * dummy MAC address. No default is provided for veth0: a reasonable strategy
+ * is to transfer eth0's MAC address to veth0, and give eth0 a dummy address
+ * (to avoid confusing the Etherbridge).
+ *
+ * Copyright (c) 2005 K A Fraser
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <net/dst.h>
+
+struct net_private {
+ struct net_device *loopback_dev;
+ struct net_device_stats stats;
+};
+
+static int loopback_open(struct net_device *dev)
+{
+ struct net_private *np = netdev_priv(dev);
+ memset(&np->stats, 0, sizeof(np->stats));
+ netif_start_queue(dev);
+ return 0;
+}
+
+static int loopback_close(struct net_device *dev)
+{
+ netif_stop_queue(dev);
+ return 0;
+}
+
+static int loopback_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct net_private *np = netdev_priv(dev);
+
+ dst_release(skb->dst);
+ skb->dst = NULL;
+
+ skb_orphan(skb);
+
+ np->stats.tx_bytes += skb->len;
+ np->stats.tx_packets++;
+
+ /* Switch to loopback context. */
+ dev = np->loopback_dev;
+ np = netdev_priv(dev);
+
+ np->stats.rx_bytes += skb->len;
+ np->stats.rx_packets++;
+
+ if ( skb->ip_summed == CHECKSUM_HW )
+ {
+ /* Defer checksum calculation. */
+ skb->proto_csum_blank = 1;
+ /* Must be a local packet: assert its integrity. */
+ skb->proto_csum_valid = 1;
+ }
+
+ skb->ip_summed = skb->proto_csum_valid ?
+ CHECKSUM_UNNECESSARY : CHECKSUM_NONE;
+
+ skb->pkt_type = PACKET_HOST; /* overridden by eth_type_trans() */
+ skb->protocol = eth_type_trans(skb, dev);
+ skb->dev = dev;
+ dev->last_rx = jiffies;
+ netif_rx(skb);
+
+ return 0;
+}
+
+static struct net_device_stats *loopback_get_stats(struct net_device *dev)
+{
+ struct net_private *np = netdev_priv(dev);
+ return &np->stats;
+}
+
+static void loopback_construct(struct net_device *dev, struct net_device *lo)
+{
+ struct net_private *np = netdev_priv(dev);
+
+ np->loopback_dev = lo;
+
+ dev->open = loopback_open;
+ dev->stop = loopback_close;
+ dev->hard_start_xmit = loopback_start_xmit;
+ dev->get_stats = loopback_get_stats;
+
+ dev->tx_queue_len = 0;
+
+ dev->features = NETIF_F_HIGHDMA | NETIF_F_LLTX;
+
+ /*
+ * We do not set a jumbo MTU on the interface. Otherwise the network
+ * stack will try to send large packets that will get dropped by the
+ * Ethernet bridge (unless the physical Ethernet interface is configured
+ * to transfer jumbo packets). If a larger MTU is desired then the system
+ * administrator can specify it using the 'ifconfig' command.
+ */
+ /*dev->mtu = 16*1024;*/
+}
+
+static int __init loopback_init(void)
+{
+ struct net_device *dev1, *dev2;
+ int err = -ENOMEM;
+
+ dev1 = alloc_netdev(sizeof(struct net_private), "vif0.0", ether_setup);
+ dev2 = alloc_netdev(sizeof(struct net_private), "veth0", ether_setup);
+ if ( (dev1 == NULL) || (dev2 == NULL) )
+ goto fail;
+
+ loopback_construct(dev1, dev2);
+ loopback_construct(dev2, dev1);
+
+ dev1->features |= NETIF_F_NO_CSUM;
+ dev2->features |= NETIF_F_IP_CSUM;
+
+ /*
+ * Initialise a dummy MAC address for the 'dummy backend' interface. We
+ * choose the numerically largest non-broadcast address to prevent the
+ * address getting stolen by an Ethernet bridge for STP purposes.
+ */
+ memset(dev1->dev_addr, 0xFF, ETH_ALEN);
+ dev1->dev_addr[0] &= ~0x01;
+
+ if ( (err = register_netdev(dev1)) != 0 )
+ goto fail;
+
+ if ( (err = register_netdev(dev2)) != 0 )
+ {
+ unregister_netdev(dev1);
+ goto fail;
+ }
+
+ return 0;
+
+ fail:
+ if ( dev1 != NULL )
+ kfree(dev1);
+ if ( dev2 != NULL )
+ kfree(dev2);
+ return err;
+}
+
+module_init(loopback_init);
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/cpu/mtrr/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/cpu/mtrr/Makefile Fri Jul
15 13:39:50 2005
@@ -0,0 +1,16 @@
+obj-y := main.o
+c-obj-y := if.o
+
+c-link :=
+
+$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)): $(obj)/mtrr.h
+ @ln -fsn $(srctree)/arch/i386/kernel/cpu/mtrr/$(notdir $@) $@
+
+$(patsubst %.o,$(obj)/%.c,$(obj-y)): $(obj)/mtrr.h
+
+$(obj)/mtrr.h:
+ @ln -fsn $(srctree)/arch/i386/kernel/cpu/mtrr/mtrr.h $@
+
+obj-y += $(c-obj-y)
+
+clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link))
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/i386/kernel/ldt.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/i386/kernel/ldt.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,275 @@
+/*
+ * linux/kernel/ldt.c
+ *
+ * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds
+ * Copyright (C) 1999 Ingo Molnar <mingo@xxxxxxxxxx>
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/ldt.h>
+#include <asm/desc.h>
+#include <asm/mmu_context.h>
+
+#ifdef CONFIG_SMP /* avoids "defined but not used" warnig */
+static void flush_ldt(void *null)
+{
+ if (current->active_mm)
+ load_LDT(¤t->active_mm->context);
+}
+#endif
+
+static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
+{
+ void *oldldt;
+ void *newldt;
+ int oldsize;
+
+ if (mincount <= pc->size)
+ return 0;
+ oldsize = pc->size;
+ mincount = (mincount+511)&(~511);
+ if (mincount*LDT_ENTRY_SIZE > PAGE_SIZE)
+ newldt = vmalloc(mincount*LDT_ENTRY_SIZE);
+ else
+ newldt = kmalloc(mincount*LDT_ENTRY_SIZE, GFP_KERNEL);
+
+ if (!newldt)
+ return -ENOMEM;
+
+ if (oldsize)
+ memcpy(newldt, pc->ldt, oldsize*LDT_ENTRY_SIZE);
+ oldldt = pc->ldt;
+ memset(newldt+oldsize*LDT_ENTRY_SIZE, 0,
(mincount-oldsize)*LDT_ENTRY_SIZE);
+ pc->ldt = newldt;
+ wmb();
+ pc->size = mincount;
+ wmb();
+
+ if (reload) {
+#ifdef CONFIG_SMP
+ cpumask_t mask;
+ preempt_disable();
+#endif
+ make_pages_readonly(pc->ldt, (pc->size * LDT_ENTRY_SIZE) /
+ PAGE_SIZE);
+ load_LDT(pc);
+#ifdef CONFIG_SMP
+ mask = cpumask_of_cpu(smp_processor_id());
+ if (!cpus_equal(current->mm->cpu_vm_mask, mask))
+ smp_call_function(flush_ldt, NULL, 1, 1);
+ preempt_enable();
+#endif
+ }
+ if (oldsize) {
+ make_pages_writable(oldldt, (oldsize * LDT_ENTRY_SIZE) /
+ PAGE_SIZE);
+ if (oldsize*LDT_ENTRY_SIZE > PAGE_SIZE)
+ vfree(oldldt);
+ else
+ kfree(oldldt);
+ }
+ return 0;
+}
+
+static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
+{
+ int err = alloc_ldt(new, old->size, 0);
+ if (err < 0)
+ return err;
+ memcpy(new->ldt, old->ldt, old->size*LDT_ENTRY_SIZE);
+ make_pages_readonly(new->ldt, (new->size * LDT_ENTRY_SIZE) /
+ PAGE_SIZE);
+ return 0;
+}
+
+/*
+ * we do not have to muck with descriptors here, that is
+ * done in switch_mm() as needed.
+ */
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+ struct mm_struct * old_mm;
+ int retval = 0;
+
+ memset(&mm->context, 0, sizeof(mm->context));
+ init_MUTEX(&mm->context.sem);
+ old_mm = current->mm;
+ if (old_mm && old_mm->context.size > 0) {
+ down(&old_mm->context.sem);
+ retval = copy_ldt(&mm->context, &old_mm->context);
+ up(&old_mm->context.sem);
+ }
+ if (retval == 0) {
+ spin_lock(&mm_unpinned_lock);
+ list_add(&mm->context.unpinned, &mm_unpinned);
+ spin_unlock(&mm_unpinned_lock);
+ }
+ return retval;
+}
+
+/*
+ * No need to lock the MM as we are the last user
+ */
+void destroy_context(struct mm_struct *mm)
+{
+ if (mm->context.size) {
+ if (mm == current->active_mm)
+ clear_LDT();
+ make_pages_writable(mm->context.ldt,
+ (mm->context.size * LDT_ENTRY_SIZE) /
+ PAGE_SIZE);
+ if (mm->context.size*LDT_ENTRY_SIZE > PAGE_SIZE)
+ vfree(mm->context.ldt);
+ else
+ kfree(mm->context.ldt);
+ mm->context.size = 0;
+ }
+ if (!mm->context.pinned) {
+ spin_lock(&mm_unpinned_lock);
+ list_del(&mm->context.unpinned);
+ spin_unlock(&mm_unpinned_lock);
+ }
+}
+
+static int read_ldt(void __user * ptr, unsigned long bytecount)
+{
+ int err;
+ unsigned long size;
+ struct mm_struct * mm = current->mm;
+
+ if (!mm->context.size)
+ return 0;
+ if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES)
+ bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES;
+
+ down(&mm->context.sem);
+ size = mm->context.size*LDT_ENTRY_SIZE;
+ if (size > bytecount)
+ size = bytecount;
+
+ err = 0;
+ if (copy_to_user(ptr, mm->context.ldt, size))
+ err = -EFAULT;
+ up(&mm->context.sem);
+ if (err < 0)
+ goto error_return;
+ if (size != bytecount) {
+ /* zero-fill the rest */
+ if (clear_user(ptr+size, bytecount-size) != 0) {
+ err = -EFAULT;
+ goto error_return;
+ }
+ }
+ return bytecount;
+error_return:
+ return err;
+}
+
+static int read_default_ldt(void __user * ptr, unsigned long bytecount)
+{
+ int err;
+ unsigned long size;
+ void *address;
+
+ err = 0;
+ address = &default_ldt[0];
+ size = 5*sizeof(struct desc_struct);
+ if (size > bytecount)
+ size = bytecount;
+
+ err = size;
+ if (copy_to_user(ptr, address, size))
+ err = -EFAULT;
+
+ return err;
+}
+
+static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode)
+{
+ struct mm_struct * mm = current->mm;
+ __u32 entry_1, entry_2, *lp;
+ unsigned long mach_lp;
+ int error;
+ struct user_desc ldt_info;
+
+ error = -EINVAL;
+ if (bytecount != sizeof(ldt_info))
+ goto out;
+ error = -EFAULT;
+ if (copy_from_user(&ldt_info, ptr, sizeof(ldt_info)))
+ goto out;
+
+ error = -EINVAL;
+ if (ldt_info.entry_number >= LDT_ENTRIES)
+ goto out;
+ if (ldt_info.contents == 3) {
+ if (oldmode)
+ goto out;
+ if (ldt_info.seg_not_present == 0)
+ goto out;
+ }
+
+ down(&mm->context.sem);
+ if (ldt_info.entry_number >= mm->context.size) {
+ error = alloc_ldt(¤t->mm->context,
ldt_info.entry_number+1, 1);
+ if (error < 0)
+ goto out_unlock;
+ }
+
+ lp = (__u32 *) ((ldt_info.entry_number << 3) + (char *)
mm->context.ldt);
+ mach_lp = arbitrary_virt_to_machine(lp);
+
+ /* Allow LDTs to be cleared by the user. */
+ if (ldt_info.base_addr == 0 && ldt_info.limit == 0) {
+ if (oldmode || LDT_empty(&ldt_info)) {
+ entry_1 = 0;
+ entry_2 = 0;
+ goto install;
+ }
+ }
+
+ entry_1 = LDT_entry_a(&ldt_info);
+ entry_2 = LDT_entry_b(&ldt_info);
+ if (oldmode)
+ entry_2 &= ~(1 << 20);
+
+ /* Install the new entry ... */
+install:
+ error = HYPERVISOR_update_descriptor(mach_lp, entry_1, entry_2);
+
+out_unlock:
+ up(&mm->context.sem);
+out:
+ return error;
+}
+
+asmlinkage int sys_modify_ldt(int func, void __user *ptr, unsigned long
bytecount)
+{
+ int ret = -ENOSYS;
+
+ switch (func) {
+ case 0:
+ ret = read_ldt(ptr, bytecount);
+ break;
+ case 1:
+ ret = write_ldt(ptr, bytecount, 1);
+ break;
+ case 2:
+ ret = read_default_ldt(ptr, bytecount);
+ break;
+ case 0x11:
+ ret = write_ldt(ptr, bytecount, 0);
+ break;
+ }
+ return ret;
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/mach-xen/setup_arch_post.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++
b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/mach-xen/setup_arch_post.h
Fri Jul 15 13:39:50 2005
@@ -0,0 +1,51 @@
+/**
+ * machine_specific_memory_setup - Hook for machine specific memory setup.
+ *
+ * Description:
+ * This is included late in kernel/setup.c so that it can make
+ * use of all of the static functions.
+ **/
+
+static char * __init machine_specific_memory_setup(void)
+{
+ char *who;
+ unsigned long start_pfn, max_pfn;
+
+ who = "Xen";
+
+ /* In dom0, we have to start the fake e820 map above the first
+ * 1MB, in other domains, it can start at 0. */
+ if (xen_start_info.flags & SIF_INITDOMAIN)
+ start_pfn = 0x100;
+ else
+ start_pfn = 0;
+ max_pfn = xen_start_info.nr_pages;
+
+ e820.nr_map = 0;
+ add_memory_region(PFN_PHYS(start_pfn), PFN_PHYS(max_pfn) -
PFN_PHYS(start_pfn), E820_RAM);
+
+ return who;
+}
+
+void __init machine_specific_modify_cpu_capabilities(struct cpuinfo_x86 *c)
+{
+ clear_bit(X86_FEATURE_VME, c->x86_capability);
+ clear_bit(X86_FEATURE_DE, c->x86_capability);
+ clear_bit(X86_FEATURE_PSE, c->x86_capability);
+ clear_bit(X86_FEATURE_PGE, c->x86_capability);
+ clear_bit(X86_FEATURE_SEP, c->x86_capability);
+ if (!(xen_start_info.flags & SIF_PRIVILEGED))
+ clear_bit(X86_FEATURE_MTRR, c->x86_capability);
+}
+
+extern void hypervisor_callback(void);
+extern void failsafe_callback(void);
+
+static void __init machine_specific_arch_setup(void)
+{
+ HYPERVISOR_set_callbacks(
+ __KERNEL_CS, (unsigned long)hypervisor_callback,
+ __KERNEL_CS, (unsigned long)failsafe_callback);
+
+ machine_specific_modify_cpu_capabilities(&boot_cpu_data);
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/drivers/blkif/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/drivers/blkif/Makefile Fri Jul 15
13:39:50 2005
@@ -0,0 +1,10 @@
+
+O_TARGET := drv.o
+
+subdir-$(CONFIG_XEN_BLKDEV_FRONTEND) += frontend
+obj-$(CONFIG_XEN_BLKDEV_FRONTEND) += frontend/drv.o
+
+subdir-$(CONFIG_XEN_PHYSDEV_ACCESS) += backend
+obj-$(CONFIG_XEN_PHYSDEV_ACCESS) += backend/drv.o
+
+include $(TOPDIR)/Rules.make
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/arch/xen/boot/Makefile
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/arch/xen/boot/Makefile Fri Jul 15 13:39:50 2005
@@ -0,0 +1,13 @@
+#
+# arch/xen/boot/Makefile
+#
+
+bzImage: $(TOPDIR)/vmlinux
+ $(OBJCOPY) $< Image
+ gzip -f -9 < Image > $@
+ rm -f Image
+
+dep:
+
+clean:
+ rm -f bzImage Image
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/pci.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-x86_64/pci.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,148 @@
+#ifndef __x8664_PCI_H
+#define __x8664_PCI_H
+
+#include <linux/config.h>
+#include <asm/io.h>
+
+#ifdef __KERNEL__
+
+#include <linux/mm.h> /* for struct page */
+
+/* Can be used to override the logic in pci_scan_bus for skipping
+ already-configured bus numbers - to be used for buggy BIOSes
+ or architectures with incomplete PCI setup by the loader */
+
+#ifdef CONFIG_PCI
+extern unsigned int pcibios_assign_all_busses(void);
+#else
+#define pcibios_assign_all_busses() 0
+#endif
+#define pcibios_scan_all_fns(a, b) 0
+
+extern int no_iommu, force_iommu;
+
+extern unsigned long pci_mem_start;
+#define PCIBIOS_MIN_IO 0x1000
+#define PCIBIOS_MIN_MEM (pci_mem_start)
+
+#define PCIBIOS_MIN_CARDBUS_IO 0x4000
+
+void pcibios_config_init(void);
+struct pci_bus * pcibios_scan_root(int bus);
+extern int (*pci_config_read)(int seg, int bus, int dev, int fn, int reg, int
len, u32 *value);
+extern int (*pci_config_write)(int seg, int bus, int dev, int fn, int reg, int
len, u32 value);
+
+void pcibios_set_master(struct pci_dev *dev);
+void pcibios_penalize_isa_irq(int irq);
+struct irq_routing_table *pcibios_get_irq_routing_table(void);
+int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq);
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <asm/scatterlist.h>
+#include <linux/string.h>
+#include <asm/page.h>
+
+extern int iommu_setup(char *opt);
+
+#ifdef CONFIG_GART_IOMMU
+/* The PCI address space does equal the physical memory
+ * address space. The networking and block device layers use
+ * this boolean for bounce buffer decisions
+ *
+ * On AMD64 it mostly equals, but we set it to zero to tell some subsystems
+ * that an IOMMU is available.
+ */
+#define PCI_DMA_BUS_IS_PHYS (no_iommu ? 1 : 0)
+
+/*
+ * x86-64 always supports DAC, but sometimes it is useful to force
+ * devices through the IOMMU to get automatic sg list merging.
+ * Optional right now.
+ */
+extern int iommu_sac_force;
+#define pci_dac_dma_supported(pci_dev, mask) (!iommu_sac_force)
+
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \
+ dma_addr_t ADDR_NAME;
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \
+ __u32 LEN_NAME;
+#define pci_unmap_addr(PTR, ADDR_NAME) \
+ ((PTR)->ADDR_NAME)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \
+ (((PTR)->ADDR_NAME) = (VAL))
+#define pci_unmap_len(PTR, LEN_NAME) \
+ ((PTR)->LEN_NAME)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \
+ (((PTR)->LEN_NAME) = (VAL))
+
+#else
+/* No IOMMU */
+
+#define PCI_DMA_BUS_IS_PHYS 1
+#define pci_dac_dma_supported(pci_dev, mask) 1
+
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)
+#define pci_unmap_addr(PTR, ADDR_NAME) (0)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0)
+#define pci_unmap_len(PTR, LEN_NAME) (0)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL) do { } while (0)
+
+#endif
+
+#include <asm-generic/pci-dma-compat.h>
+
+static inline dma64_addr_t
+pci_dac_page_to_dma(struct pci_dev *pdev, struct page *page, unsigned long
offset, int direction)
+{
+ return ((dma64_addr_t) page_to_phys(page) +
+ (dma64_addr_t) offset);
+}
+
+static inline struct page *
+pci_dac_dma_to_page(struct pci_dev *pdev, dma64_addr_t dma_addr)
+{
+ return virt_to_page(__va(dma_addr));
+}
+
+static inline unsigned long
+pci_dac_dma_to_offset(struct pci_dev *pdev, dma64_addr_t dma_addr)
+{
+ return (dma_addr & ~PAGE_MASK);
+}
+
+static inline void
+pci_dac_dma_sync_single_for_cpu(struct pci_dev *pdev, dma64_addr_t dma_addr,
size_t len, int direction)
+{
+}
+
+static inline void
+pci_dac_dma_sync_single_for_device(struct pci_dev *pdev, dma64_addr_t
dma_addr, size_t len, int direction)
+{
+ flush_write_buffers();
+}
+
+#define HAVE_PCI_MMAP
+extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+ enum pci_mmap_state mmap_state, int
write_combine);
+
+static inline void pcibios_add_platform_entries(struct pci_dev *dev)
+{
+}
+
+#endif /* __KERNEL__ */
+
+/* generic pci stuff */
+#ifdef CONFIG_PCI
+#include <asm-generic/pci.h>
+#endif
+
+/* On Xen we have to scan all functions since Xen hides bridges from
+ * us. If a bridge is at fn=0 and that slot has a multifunction
+ * device, we won't find the additional devices without scanning all
+ * functions. */
+#undef pcibios_scan_all_fns
+#define pcibios_scan_all_fns(a, b) 1
+
+#endif /* __x8664_PCI_H */
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/system.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/include/asm-xen/asm-i386/system.h Fri Jul 15
13:39:50 2005
@@ -0,0 +1,577 @@
+#ifndef __ASM_SYSTEM_H
+#define __ASM_SYSTEM_H
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <asm-xen/synch_bitops.h>
+#include <asm/segment.h>
+#include <asm/cpufeature.h>
+#include <asm-xen/hypervisor.h>
+#include <asm/smp_alt.h>
+
+#ifdef __KERNEL__
+
+struct task_struct; /* one of the stranger aspects of C forward
declarations.. */
+extern struct task_struct * FASTCALL(__switch_to(struct task_struct *prev,
struct task_struct *next));
+
+#define switch_to(prev,next,last) do { \
+ unsigned long esi,edi; \
+ asm volatile("pushfl\n\t" \
+ "pushl %%ebp\n\t" \
+ "movl %%esp,%0\n\t" /* save ESP */ \
+ "movl %5,%%esp\n\t" /* restore ESP */ \
+ "movl $1f,%1\n\t" /* save EIP */ \
+ "pushl %6\n\t" /* restore EIP */ \
+ "jmp __switch_to\n" \
+ "1:\t" \
+ "popl %%ebp\n\t" \
+ "popfl" \
+ :"=m" (prev->thread.esp),"=m" (prev->thread.eip), \
+ "=a" (last),"=S" (esi),"=D" (edi) \
+ :"m" (next->thread.esp),"m" (next->thread.eip), \
+ "2" (prev), "d" (next)); \
+} while (0)
+
+#define _set_base(addr,base) do { unsigned long __pr; \
+__asm__ __volatile__ ("movw %%dx,%1\n\t" \
+ "rorl $16,%%edx\n\t" \
+ "movb %%dl,%2\n\t" \
+ "movb %%dh,%3" \
+ :"=&d" (__pr) \
+ :"m" (*((addr)+2)), \
+ "m" (*((addr)+4)), \
+ "m" (*((addr)+7)), \
+ "0" (base) \
+ ); } while(0)
+
+#define _set_limit(addr,limit) do { unsigned long __lr; \
+__asm__ __volatile__ ("movw %%dx,%1\n\t" \
+ "rorl $16,%%edx\n\t" \
+ "movb %2,%%dh\n\t" \
+ "andb $0xf0,%%dh\n\t" \
+ "orb %%dh,%%dl\n\t" \
+ "movb %%dl,%2" \
+ :"=&d" (__lr) \
+ :"m" (*(addr)), \
+ "m" (*((addr)+6)), \
+ "0" (limit) \
+ ); } while(0)
+
+#define set_base(ldt,base) _set_base( ((char *)&(ldt)) , (base) )
+#define set_limit(ldt,limit) _set_limit( ((char *)&(ldt)) , ((limit)-1)>>12 )
+
+static inline unsigned long _get_base(char * addr)
+{
+ unsigned long __base;
+ __asm__("movb %3,%%dh\n\t"
+ "movb %2,%%dl\n\t"
+ "shll $16,%%edx\n\t"
+ "movw %1,%%dx"
+ :"=&d" (__base)
+ :"m" (*((addr)+2)),
+ "m" (*((addr)+4)),
+ "m" (*((addr)+7)));
+ return __base;
+}
+
+#define get_base(ldt) _get_base( ((char *)&(ldt)) )
+
+/*
+ * Load a segment. Fall back on loading the zero
+ * segment if something goes wrong..
+ */
+#define loadsegment(seg,value) \
+ asm volatile("\n" \
+ "1:\t" \
+ "movl %0,%%" #seg "\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3:\t" \
+ "pushl $0\n\t" \
+ "popl %%" #seg "\n\t" \
+ "jmp 2b\n" \
+ ".previous\n" \
+ ".section __ex_table,\"a\"\n\t" \
+ ".align 4\n\t" \
+ ".long 1b,3b\n" \
+ ".previous" \
+ : :"m" (*(unsigned int *)&(value)))
+
+/*
+ * Save a segment register away
+ */
+#define savesegment(seg, value) \
+ asm volatile("movl %%" #seg ",%0":"=m" (*(int *)&(value)))
+
+/*
+ * Clear and set 'TS' bit respectively
+ */
+#define clts() (HYPERVISOR_fpu_taskswitch(0))
+#define read_cr0() ({ \
+ unsigned int __dummy; \
+ __asm__( \
+ "movl %%cr0,%0\n\t" \
+ :"=r" (__dummy)); \
+ __dummy; \
+})
+#define write_cr0(x) \
+ __asm__("movl %0,%%cr0": :"r" (x));
+
+#define read_cr4() ({ \
+ unsigned int __dummy; \
+ __asm__( \
+ "movl %%cr4,%0\n\t" \
+ :"=r" (__dummy)); \
+ __dummy; \
+})
+#define write_cr4(x) \
+ __asm__("movl %0,%%cr4": :"r" (x));
+#define stts() (HYPERVISOR_fpu_taskswitch(1))
+
+#endif /* __KERNEL__ */
+
+#define wbinvd() \
+ __asm__ __volatile__ ("wbinvd": : :"memory");
+
+static inline unsigned long get_limit(unsigned long segment)
+{
+ unsigned long __limit;
+ __asm__("lsll %1,%0"
+ :"=r" (__limit):"r" (segment));
+ return __limit+1;
+}
+
+#define nop() __asm__ __volatile__ ("nop")
+
+#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned
long)(v),(ptr),sizeof(*(ptr))))
+
+#define tas(ptr) (xchg((ptr),1))
+
+struct __xchg_dummy { unsigned long a[100]; };
+#define __xg(x) ((struct __xchg_dummy *)(x))
+
+
+/*
+ * The semantics of XCHGCMP8B are a bit strange, this is why
+ * there is a loop and the loading of %%eax and %%edx has to
+ * be inside. This inlines well in most cases, the cached
+ * cost is around ~38 cycles. (in the future we might want
+ * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that
+ * might have an implicit FPU-save as a cost, so it's not
+ * clear which path to go.)
+ *
+ * cmpxchg8b must be used with the lock prefix here to allow
+ * the instruction to be executed atomically, see page 3-102
+ * of the instruction set reference 24319102.pdf. We need
+ * the reader side to see the coherent 64bit value.
+ */
+static inline void __set_64bit (unsigned long long * ptr,
+ unsigned int low, unsigned int high)
+{
+ __asm__ __volatile__ (
+ "\n1:\t"
+ "movl (%0), %%eax\n\t"
+ "movl 4(%0), %%edx\n\t"
+ "lock cmpxchg8b (%0)\n\t"
+ "jnz 1b"
+ : /* no outputs */
+ : "D"(ptr),
+ "b"(low),
+ "c"(high)
+ : "ax","dx","memory");
+}
+
+static inline void __set_64bit_constant (unsigned long long *ptr,
+ unsigned long long value)
+{
+ __set_64bit(ptr,(unsigned int)(value), (unsigned int)((value)>>32ULL));
+}
+#define ll_low(x) *(((unsigned int*)&(x))+0)
+#define ll_high(x) *(((unsigned int*)&(x))+1)
+
+static inline void __set_64bit_var (unsigned long long *ptr,
+ unsigned long long value)
+{
+ __set_64bit(ptr,ll_low(value), ll_high(value));
+}
+
+#define set_64bit(ptr,value) \
+(__builtin_constant_p(value) ? \
+ __set_64bit_constant(ptr, value) : \
+ __set_64bit_var(ptr, value) )
+
+#define _set_64bit(ptr,value) \
+(__builtin_constant_p(value) ? \
+ __set_64bit(ptr, (unsigned int)(value), (unsigned int)((value)>>32ULL) ) : \
+ __set_64bit(ptr, ll_low(value), ll_high(value)) )
+
+/*
+ * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
+ * Note 2: xchg has side effect, so that attribute volatile is necessary,
+ * but generally the primitive is invalid, *ptr is output argument. --ANK
+ */
+static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int
size)
+{
+ switch (size) {
+ case 1:
+ __asm__ __volatile__("xchgb %b0,%1"
+ :"=q" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ case 2:
+ __asm__ __volatile__("xchgw %w0,%1"
+ :"=r" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ case 4:
+ __asm__ __volatile__("xchgl %0,%1"
+ :"=r" (x)
+ :"m" (*__xg(ptr)), "0" (x)
+ :"memory");
+ break;
+ }
+ return x;
+}
+
+/*
+ * Atomic compare and exchange. Compare OLD with MEM, if identical,
+ * store NEW in MEM. Return the initial value in MEM. Success is
+ * indicated by comparing RETURN with OLD.
+ */
+
+#ifdef CONFIG_X86_CMPXCHG
+#define __HAVE_ARCH_CMPXCHG 1
+#endif
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+ unsigned long new, int size)
+{
+ unsigned long prev;
+ switch (size) {
+ case 1:
+ __asm__ __volatile__(LOCK "cmpxchgb %b1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ case 2:
+ __asm__ __volatile__(LOCK "cmpxchgw %w1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ case 4:
+ __asm__ __volatile__(LOCK "cmpxchgl %1,%2"
+ : "=a"(prev)
+ : "q"(new), "m"(*__xg(ptr)), "0"(old)
+ : "memory");
+ return prev;
+ }
+ return old;
+}
+
+#define cmpxchg(ptr,o,n)\
+ ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
+ (unsigned long)(n),sizeof(*(ptr))))
+
+#ifdef __KERNEL__
+struct alt_instr {
+ __u8 *instr; /* original instruction */
+ __u8 *replacement;
+ __u8 cpuid; /* cpuid bit set for replacement */
+ __u8 instrlen; /* length of original instruction */
+ __u8 replacementlen; /* length of new instruction, <= instrlen */
+ __u8 pad;
+};
+#endif
+
+/*
+ * Alternative instructions for different CPU types or capabilities.
+ *
+ * This allows to use optimized instructions even on generic binary
+ * kernels.
+ *
+ * length of oldinstr must be longer or equal the length of newinstr
+ * It can be padded with nops as needed.
+ *
+ * For non barrier like inlines please define new variants
+ * without volatile and memory clobber.
+ */
+#define alternative(oldinstr, newinstr, feature) \
+ asm volatile ("661:\n\t" oldinstr "\n662:\n" \
+ ".section .altinstructions,\"a\"\n" \
+ " .align 4\n" \
+ " .long 661b\n" /* label */ \
+ " .long 663f\n" /* new instruction */
\
+ " .byte %c0\n" /* feature bit */ \
+ " .byte 662b-661b\n" /* sourcelen */ \
+ " .byte 664f-663f\n" /* replacementlen */ \
+ ".previous\n"
\
+ ".section .altinstr_replacement,\"ax\"\n"
\
+ "663:\n\t" newinstr "\n664:\n" /* replacement */ \
+ ".previous" :: "i" (feature) : "memory")
+
+/*
+ * Alternative inline assembly with input.
+ *
+ * Pecularities:
+ * No memory clobber here.
+ * Argument numbers start with 1.
+ * Best is to use constraints that are fixed size (like (%1) ... "r")
+ * If you use variable sized constraints like "m" or "g" in the
+ * replacement maake sure to pad to the worst case length.
+ */
+#define alternative_input(oldinstr, newinstr, feature, input...)
\
+ asm volatile ("661:\n\t" oldinstr "\n662:\n"
\
+ ".section .altinstructions,\"a\"\n"
\
+ " .align 4\n"
\
+ " .long 661b\n" /* label */
\
+ " .long 663f\n" /* new instruction */
\
+ " .byte %c0\n" /* feature bit */
\
+ " .byte 662b-661b\n" /* sourcelen */
\
+ " .byte 664f-663f\n" /* replacementlen */
\
+ ".previous\n"
\
+ ".section .altinstr_replacement,\"ax\"\n"
\
+ "663:\n\t" newinstr "\n664:\n" /* replacement */
\
+ ".previous" :: "i" (feature), ##input)
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ *
+ * For now, "wmb()" doesn't actually do anything, as all
+ * Intel CPU's follow what Intel calls a *Processor Order*,
+ * in which all writes are seen in the program order even
+ * outside the CPU.
+ *
+ * I expect future Intel CPU's to have a weaker ordering,
+ * but I'd also expect them to finally get their act together
+ * and add some real memory barriers if so.
+ *
+ * Some non intel clones support out of order store. wmb() ceases to be a
+ * nop for these.
+ */
+
+
+/*
+ * Actually only lfence would be needed for mb() because all stores done
+ * by the kernel should be already ordered. But keep a full barrier for now.
+ */
+
+#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
+#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
+
+/**
+ * read_barrier_depends - Flush all pending reads that subsequents reads
+ * depend on.
+ *
+ * No data-dependent reads from memory-like regions are ever reordered
+ * over this barrier. All reads preceding this primitive are guaranteed
+ * to access memory (but not necessarily other CPUs' caches) before any
+ * reads following this primitive that depend on the data return by
+ * any of the preceding reads. This primitive is much lighter weight than
+ * rmb() on most CPUs, and is never heavier weight than is
+ * rmb().
+ *
+ * These ordering constraints are respected by both the local CPU
+ * and the compiler.
+ *
+ * Ordering is not guaranteed by anything other than these primitives,
+ * not even by data dependencies. See the documentation for
+ * memory_barrier() for examples and URLs to more information.
+ *
+ * For example, the following code would force ordering (the initial
+ * value of "a" is zero, "b" is one, and "p" is "&a"):
+ *
+ * <programlisting>
+ * CPU 0 CPU 1
+ *
+ * b = 2;
+ * memory_barrier();
+ * p = &b; q = p;
+ * read_barrier_depends();
+ * d = *q;
+ * </programlisting>
+ *
+ * because the read of "*q" depends on the read of "p" and these
+ * two reads are separated by a read_barrier_depends(). However,
+ * the following code, with the same initial values for "a" and "b":
+ *
+ * <programlisting>
+ * CPU 0 CPU 1
+ *
+ * a = 2;
+ * memory_barrier();
+ * b = 3; y = b;
+ * read_barrier_depends();
+ * x = a;
+ * </programlisting>
+ *
+ * does not enforce ordering, since there is no data dependency between
+ * the read of "a" and the read of "b". Therefore, on some CPUs, such
+ * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb()
+ * in cases like thiswhere there are no data dependencies.
+ **/
+
+#define read_barrier_depends() do { } while(0)
+
+#ifdef CONFIG_X86_OOSTORE
+/* Actually there are no OOO store capable CPUs for now that do SSE,
+ but make it already an possibility. */
+#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+#else
+#define wmb() __asm__ __volatile__ ("": : :"memory")
+#endif
+
+#ifdef CONFIG_SMP
+#define smp_wmb() wmb()
+#if defined(CONFIG_SMP_ALTERNATIVES) && !defined(MODULE)
+#define smp_alt_mb(instr) \
+__asm__ __volatile__("6667:\nnop\nnop\nnop\nnop\nnop\nnop\n6668:\n" \
+ ".section __smp_alternatives,\"a\"\n" \
+ ".long 6667b\n" \
+ ".long 6673f\n" \
+ ".previous\n" \
+ ".section __smp_replacements,\"a\"\n" \
+ "6673:.byte 6668b-6667b\n" \
+ ".byte 6670f-6669f\n" \
+ ".byte 6671f-6670f\n" \
+ ".byte 0\n" \
+ ".byte %c0\n" \
+ "6669:lock;addl $0,0(%%esp)\n" \
+ "6670:" instr "\n" \
+ "6671:\n" \
+ ".previous\n" \
+ : \
+ : "i" (X86_FEATURE_XMM2) \
+ : "memory")
+#define smp_rmb() smp_alt_mb("lfence")
+#define smp_mb() smp_alt_mb("mfence")
+#define set_mb(var, value) do { \
+unsigned long __set_mb_temp; \
+__asm__ __volatile__("6667:movl %1, %0\n6668:\n" \
+ ".section __smp_alternatives,\"a\"\n" \
+ ".long 6667b\n" \
+ ".long 6673f\n" \
+ ".previous\n" \
+ ".section __smp_replacements,\"a\"\n" \
+ "6673: .byte 6668b-6667b\n" \
+ ".byte 6670f-6669f\n" \
+ ".byte 0\n" \
+ ".byte 6671f-6670f\n" \
+ ".byte -1\n" \
+ "6669: xchg %1, %0\n" \
+ "6670:movl %1, %0\n" \
+ "6671:\n" \
+ ".previous\n" \
+ : "=m" (var), "=r" (__set_mb_temp) \
+ : "1" (value) \
+ : "memory"); } while (0)
+#else
+#define smp_rmb() rmb()
+#define smp_mb() mb()
+#define set_mb(var, value) do { xchg(&var, value); } while (0)
+#endif
+#define smp_read_barrier_depends() read_barrier_depends()
+#else
+#define smp_mb() barrier()
+#define smp_rmb() barrier()
+#define smp_wmb() barrier()
+#define smp_read_barrier_depends() do { } while(0)
+#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#endif
+
+#define set_wmb(var, value) do { var = value; wmb(); } while (0)
+
+/* interrupt control.. */
+
+/*
+ * The use of 'barrier' in the following reflects their use as local-lock
+ * operations. Reentrancy must be prevented (e.g., __cli()) /before/ following
+ * critical operations are executed. All critical operations must complete
+ * /before/ reentrancy is permitted (e.g., __sti()). Alpha architecture also
+ * includes these barriers, for example.
+ */
+
+#define __cli()
\
+do { \
+ vcpu_info_t *_vcpu; \
+ preempt_disable(); \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_data[smp_processor_id()]; \
+ _vcpu->evtchn_upcall_mask = 1; \
+ preempt_enable_no_resched(); \
+ barrier(); \
+} while (0)
+
+#define __sti()
\
+do { \
+ vcpu_info_t *_vcpu; \
+ barrier(); \
+ preempt_disable(); \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_data[smp_processor_id()]; \
+ _vcpu->evtchn_upcall_mask = 0; \
+ barrier(); /* unmask then check (avoid races) */ \
+ if ( unlikely(_vcpu->evtchn_upcall_pending) ) \
+ force_evtchn_callback(); \
+ preempt_enable(); \
+} while (0)
+
+#define __save_flags(x)
\
+do { \
+ vcpu_info_t *_vcpu; \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_data[smp_processor_id()]; \
+ (x) = _vcpu->evtchn_upcall_mask; \
+} while (0)
+
+#define __restore_flags(x) \
+do { \
+ vcpu_info_t *_vcpu; \
+ barrier(); \
+ preempt_disable(); \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_data[smp_processor_id()]; \
+ if ((_vcpu->evtchn_upcall_mask = (x)) == 0) { \
+ barrier(); /* unmask then check (avoid races) */ \
+ if ( unlikely(_vcpu->evtchn_upcall_pending) ) \
+ force_evtchn_callback(); \
+ preempt_enable(); \
+ } else \
+ preempt_enable_no_resched(); \
+} while (0)
+
+#define safe_halt() ((void)0)
+
+#define __save_and_cli(x) \
+do { \
+ vcpu_info_t *_vcpu; \
+ preempt_disable(); \
+ _vcpu = &HYPERVISOR_shared_info->vcpu_data[smp_processor_id()]; \
+ (x) = _vcpu->evtchn_upcall_mask; \
+ _vcpu->evtchn_upcall_mask = 1; \
+ preempt_enable_no_resched(); \
+ barrier(); \
+} while (0)
+
+#define local_irq_save(x) __save_and_cli(x)
+#define local_irq_restore(x) __restore_flags(x)
+#define local_save_flags(x) __save_flags(x)
+#define local_irq_disable() __cli()
+#define local_irq_enable() __sti()
+
+#define irqs_disabled() \
+ HYPERVISOR_shared_info->vcpu_data[smp_processor_id()].evtchn_upcall_mask
+
+/*
+ * disable hlt during certain critical i/o operations
+ */
+#define HAVE_DISABLE_HLT
+void disable_hlt(void);
+void enable_hlt(void);
+
+extern int es7000_plat;
+void cpu_idle_wait(void);
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.4.30-xen-sparse/include/asm-xen/segment.h
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.4.30-xen-sparse/include/asm-xen/segment.h Fri Jul 15 13:39:50 2005
@@ -0,0 +1,15 @@
+#ifndef _ASM_SEGMENT_H
+#define _ASM_SEGMENT_H
+
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+#endif
+#include <asm-xen/xen-public/xen.h>
+
+#define __KERNEL_CS FLAT_RING1_CS
+#define __KERNEL_DS FLAT_RING1_DS
+
+#define __USER_CS FLAT_RING3_CS
+#define __USER_DS FLAT_RING3_DS
+
+#endif
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/pci/Makefile-BUS
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/pci/Makefile-BUS Fri Jul 15
13:39:50 2005
@@ -0,0 +1,22 @@
+#
+# Makefile for X86_64 specific PCI routines
+#
+# Reuse the i386 PCI subsystem
+#
+CFLAGS += -I arch/i386/pci
+
+obj-y := i386.o
+obj-$(CONFIG_PCI_DIRECT)+= direct.o
+obj-y += fixup.o
+obj-$(CONFIG_ACPI_PCI) += acpi.o
+obj-y += legacy.o irq.o common.o
+# mmconfig has a 64bit special
+obj-$(CONFIG_PCI_MMCONFIG) += mmconfig.o
+
+direct-y += ../../i386/pci/direct.o
+acpi-y += ../../i386/pci/acpi.o
+legacy-y += ../../i386/pci/legacy.o
+irq-y += ../../i386/pci/irq.o
+common-y += ../../i386/pci/common.o
+fixup-y += ../../i386/pci/fixup.o
+i386-y += ../../i386/pci/i386.o
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/drivers/xen/netback/control.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/drivers/xen/netback/control.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,58 @@
+/******************************************************************************
+ * arch/xen/drivers/netif/backend/control.c
+ *
+ * Routines for interfacing with the control plane.
+ *
+ * Copyright (c) 2004, Keir Fraser
+ */
+
+#include "common.h"
+
+static void netif_ctrlif_rx(ctrl_msg_t *msg, unsigned long id)
+{
+ DPRINTK("Received netif backend message, subtype=%d\n", msg->subtype);
+
+ switch ( msg->subtype )
+ {
+ case CMSG_NETIF_BE_CREATE:
+ netif_create((netif_be_create_t *)&msg->msg[0]);
+ break;
+ case CMSG_NETIF_BE_DESTROY:
+ netif_destroy((netif_be_destroy_t *)&msg->msg[0]);
+ break;
+ case CMSG_NETIF_BE_CREDITLIMIT:
+ netif_creditlimit((netif_be_creditlimit_t *)&msg->msg[0]);
+ break;
+ case CMSG_NETIF_BE_CONNECT:
+ netif_connect((netif_be_connect_t *)&msg->msg[0]);
+ break;
+ case CMSG_NETIF_BE_DISCONNECT:
+ if ( !netif_disconnect((netif_be_disconnect_t *)&msg->msg[0],msg->id) )
+ return; /* Sending the response is deferred until later. */
+ break;
+ default:
+ DPRINTK("Parse error while reading message subtype %d, len %d\n",
+ msg->subtype, msg->length);
+ msg->length = 0;
+ break;
+ }
+
+ ctrl_if_send_response(msg);
+}
+
+void netif_ctrlif_init(void)
+{
+ ctrl_msg_t cmsg;
+ netif_be_driver_status_t st;
+
+ (void)ctrl_if_register_receiver(CMSG_NETIF_BE, netif_ctrlif_rx,
+ CALLBACK_IN_BLOCKING_CONTEXT);
+
+ /* Send a driver-UP notification to the domain controller. */
+ cmsg.type = CMSG_NETIF_BE;
+ cmsg.subtype = CMSG_NETIF_BE_DRIVER_STATUS;
+ cmsg.length = sizeof(netif_be_driver_status_t);
+ st.status = NETIF_DRIVER_STATUS_UP;
+ memcpy(cmsg.msg, &st, sizeof(st));
+ ctrl_if_send_message_block(&cmsg, NULL, 0, TASK_UNINTERRUPTIBLE);
+}
diff -r 35b74976f598 -r a83ac0806d6b
linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/process.c
--- /dev/null Fri Jul 15 12:52:02 2005
+++ b/linux-2.6.11-xen-sparse/arch/xen/x86_64/kernel/process.c Fri Jul 15
13:39:50 2005
@@ -0,0 +1,725 @@
+/*
+ * linux/arch/x86-64/kernel/process.c
+ *
+ * Copyright (C) 1995 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000
+ *
+ * X86-64 port
+ * Andi Kleen.
+ *
+ * $Id: process.c,v 1.38 2002/01/15 10:08:03 ak Exp $
+ *
+ * Jun Nakajima <jun.nakajima@xxxxxxxxx>
+ * Modified for Xen
+ */
+
+/*
+ * This file handles the architecture-dependent parts of process handling..
+ */
+
+#include <stdarg.h>
+
+#include <linux/cpu.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/elfcore.h>
+#include <linux/smp.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/module.h>
+#include <linux/a.out.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/ptrace.h>
+#include <linux/utsname.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/mmu_context.h>
+#include <asm/pda.h>
+#include <asm/prctl.h>
+#include <asm/kdebug.h>
+#include <asm-xen/xen-public/dom0_ops.h>
+#include <asm-xen/xen-public/physdev.h>
+#include <asm/desc.h>
+#include <asm/proto.h>
+#include <asm/hardirq.h>
+#include <asm/ia32.h>
+
+asmlinkage extern void ret_from_fork(void);
+
+unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;
+
+atomic_t hlt_counter = ATOMIC_INIT(0);
+
+unsigned long boot_option_idle_override = 0;
+EXPORT_SYMBOL(boot_option_idle_override);
+
+/*
+ * Powermanagement idle function, if any..
+ */
+void (*pm_idle)(void);
+static cpumask_t cpu_idle_map;
+
+void disable_hlt(void)
+{
+ atomic_inc(&hlt_counter);
+}
+
+EXPORT_SYMBOL(disable_hlt);
+
+void enable_hlt(void)
+{
+ atomic_dec(&hlt_counter);
+}
+
+EXPORT_SYMBOL(enable_hlt);
+
+/* XXX XEN doesn't use default_idle(), poll_idle(). Use xen_idle() instead. */
+extern void stop_hz_timer(void);
+extern void start_hz_timer(void);
+void xen_idle(void)
+{
+ local_irq_disable();
+
+ if (need_resched()) {
+ local_irq_enable();
+ } else {
+ stop_hz_timer();
+ HYPERVISOR_block(); /* implicit local_irq_enable() */
+ start_hz_timer();
+ }
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+#include <asm/nmi.h>
+/* We don't actually take CPU down, just spin without interrupts. */
+static inline void play_dead(void)
+{
+ /* Ack it */
+ __get_cpu_var(cpu_state) = CPU_DEAD;
+
+ /* We shouldn't have to disable interrupts while dead, but
+ * some interrupts just don't seem to go away, and this makes
+ * it "work" for testing purposes. */
+ /* Death loop */
+ while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE)
+ HYPERVISOR_yield();
+
+ local_irq_disable();
+ __flush_tlb_all();
+ cpu_set(smp_processor_id(), cpu_online_map);
+ local_irq_enable();
+}
+#else
+static inline void play_dead(void)
+{
+ BUG();
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+/*
+ * The idle thread. There's no useful work to be
+ * done, so just try to conserve power and have a
+ * low exit latency (ie sit in a loop waiting for
+ * somebody to say that they'd like to reschedule)
+ */
+void cpu_idle (void)
+{
+ int cpu = smp_processor_id();
+
+ /* endless idle loop with no priority at all */
+ while (1) {
+ while (!need_resched()) {
+ if (cpu_isset(cpu, cpu_idle_map))
+ cpu_clear(cpu, cpu_idle_map);
+ rmb();
+
+ if (cpu_is_offline(cpu))
+ play_dead();
+
+ __IRQ_STAT(cpu,idle_timestamp) = jiffies;
+ xen_idle();
+ }
+ schedule();
+ }
+}
+
+void cpu_idle_wait(void)
+{
+ int cpu;
+ cpumask_t map;
+
+ for_each_online_cpu(cpu)
+ cpu_set(cpu, cpu_idle_map);
+
+ wmb();
+ do {
+ ssleep(1);
+ cpus_and(map, cpu_idle_map, cpu_online_map);
+ } while (!cpus_empty(map));
+}
+EXPORT_SYMBOL_GPL(cpu_idle_wait);
+
+/* XXX XEN doesn't use mwait_idle(), select_idle_routine(), idle_setup(). */
+/* Always use xen_idle() instead. */
+void __init select_idle_routine(const struct cpuinfo_x86 *c) {}
+
+/* Prints also some state that isn't saved in the pt_regs */
+void __show_regs(struct pt_regs * regs)
+{
+ unsigned long fs, gs, shadowgs;
+ unsigned int fsindex,gsindex;
+ unsigned int ds,cs,es;
+
+ printk("\n");
+ print_modules();
+ printk("Pid: %d, comm: %.20s %s %s\n",
+ current->pid, current->comm, print_tainted(),
system_utsname.release);
+ printk("RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->rip);
+ printk_address(regs->rip);
+ printk("\nRSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, regs->rsp,
regs->eflags);
+ printk("RAX: %016lx RBX: %016lx RCX: %016lx\n",
+ regs->rax, regs->rbx, regs->rcx);
+ printk("RDX: %016lx RSI: %016lx RDI: %016lx\n",
+ regs->rdx, regs->rsi, regs->rdi);
+ printk("RBP: %016lx R08: %016lx R09: %016lx\n",
+ regs->rbp, regs->r8, regs->r9);
+ printk("R10: %016lx R11: %016lx R12: %016lx\n",
+ regs->r10, regs->r11, regs->r12);
+ printk("R13: %016lx R14: %016lx R15: %016lx\n",
+ regs->r13, regs->r14, regs->r15);
+
+ asm("movl %%ds,%0" : "=r" (ds));
+ asm("movl %%cs,%0" : "=r" (cs));
+ asm("movl %%es,%0" : "=r" (es));
+ asm("movl %%fs,%0" : "=r" (fsindex));
+ asm("movl %%gs,%0" : "=r" (gsindex));
+
+ rdmsrl(MSR_FS_BASE, fs);
+ rdmsrl(MSR_GS_BASE, gs);
+ rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
+
+ printk("FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
+ fs,fsindex,gs,gsindex,shadowgs);
+ printk("CS: %04x DS: %04x ES: %04x\n", cs, ds, es);
+
+}
+
+void show_regs(struct pt_regs *regs)
+{
+ __show_regs(regs);
+ show_trace(®s->rsp);
+}
+
+/*
+ * Free current thread data structures etc..
+ */
+void exit_thread(void)
+{
+ struct task_struct *me = current;
+ struct thread_struct *t = &me->thread;
+ if (me->thread.io_bitmap_ptr) {
+ struct tss_struct *tss = &per_cpu(init_tss, get_cpu());
+
+ kfree(t->io_bitmap_ptr);
+ t->io_bitmap_ptr = NULL;
+ /*
+ * Careful, clear this in the TSS too:
+ */
+ memset(tss->io_bitmap, 0xff, t->io_bitmap_max);
+ t->io_bitmap_max = 0;
+ put_cpu();
+ }
+}
+
+void load_gs_index(unsigned gs)
+{
+ HYPERVISOR_set_segment_base(SEGBASE_GS_USER_SEL, gs);
+}
+
+void flush_thread(void)
+{
+ struct task_struct *tsk = current;
+ struct thread_info *t = current_thread_info();
+
+ if (t->flags & _TIF_ABI_PENDING)
+ t->flags ^= (_TIF_ABI_PENDING | _TIF_IA32);
+
+ tsk->thread.debugreg0 = 0;
+ tsk->thread.debugreg1 = 0;
+ tsk->thread.debugreg2 = 0;
+ tsk->thread.debugreg3 = 0;
+ tsk->thread.debugreg6 = 0;
+ tsk->thread.debugreg7 = 0;
+ memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
+ /*
+ * Forget coprocessor state..
+ */
+ clear_fpu(tsk);
+ clear_used_math();
+}
+
+void release_thread(struct task_struct *dead_task)
+{
+ if (dead_task->mm) {
+ if (dead_task->mm->context.size) {
+ printk("WARNING: dead process %8s still has LDT?
<%p/%d>\n",
+ dead_task->comm,
+ dead_task->mm->context.ldt,
+ dead_task->mm->context.size);
+ BUG();
+ }
+ }
+}
+
+static inline void set_32bit_tls(struct task_struct *t, int tls, u32 addr)
+{
+ struct user_desc ud = {
+ .base_addr = addr,
+ .limit = 0xfffff,
+ .contents = (3 << 3), /* user */
+ .seg_32bit = 1,
+ .limit_in_pages = 1,
+ .useable = 1,
+ };
+ struct n_desc_struct *desc = (void *)t->thread.tls_array;
+ desc += tls;
+ desc->a = LDT_entry_a(&ud);
+ desc->b = LDT_entry_b(&ud);
+}
+
+static inline u32 read_32bit_tls(struct task_struct *t, int tls)
+{
+ struct desc_struct *desc = (void *)t->thread.tls_array;
+ desc += tls;
+ return desc->base0 |
+ (((u32)desc->base1) << 16) |
+ (((u32)desc->base2) << 24);
+}
+
+/*
+ * This gets called before we allocate a new thread and copy
+ * the current task into it.
+ */
+void prepare_to_copy(struct task_struct *tsk)
+{
+ unlazy_fpu(tsk);
+}
+
+int copy_thread(int nr, unsigned long clone_flags, unsigned long rsp,
+ unsigned long unused,
+ struct task_struct * p, struct pt_regs * regs)
+{
+ int err;
+ struct pt_regs * childregs;
+ struct task_struct *me = current;
+
+ childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long)
p->thread_info)) - 1;
+
+ *childregs = *regs;
+
+ childregs->rax = 0;
+ childregs->rsp = rsp;
+ if (rsp == ~0UL) {
+ childregs->rsp = (unsigned long)childregs;
+ }
+
+ p->thread.rsp = (unsigned long) childregs;
+ p->thread.rsp0 = (unsigned long) (childregs+1);
+ p->thread.userrsp = me->thread.userrsp;
+
+ set_ti_thread_flag(p->thread_info, TIF_FORK);
+
+ p->thread.fs = me->thread.fs;
+ p->thread.gs = me->thread.gs;
+
+ asm("movl %%gs,%0" : "=m" (p->thread.gsindex));
+ asm("movl %%fs,%0" : "=m" (p->thread.fsindex));
+ asm("movl %%es,%0" : "=m" (p->thread.es));
+ asm("movl %%ds,%0" : "=m" (p->thread.ds));
+
+ if (unlikely(me->thread.io_bitmap_ptr != NULL)) {
+ p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL);
+ if (!p->thread.io_bitmap_ptr) {
+ p->thread.io_bitmap_max = 0;
+ return -ENOMEM;
+ }
+ memcpy(p->thread.io_bitmap_ptr, me->thread.io_bitmap_ptr,
IO_BITMAP_BYTES);
+ }
+
+ /*
+ * Set a new TLS for the child thread?
+ */
+ if (clone_flags & CLONE_SETTLS) {
+#ifdef CONFIG_IA32_EMULATION
+ if (test_thread_flag(TIF_IA32))
+ err = ia32_child_tls(p, childregs);
+ else
+#endif
+ err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8);
+ if (err)
+ goto out;
+ }
+ p->thread.io_pl = current->thread.io_pl;
+
+ err = 0;
+out:
+ if (err && p->thread.io_bitmap_ptr) {
+ kfree(p->thread.io_bitmap_ptr);
+ p->thread.io_bitmap_max = 0;
+ }
+ return err;
+}
+
+/*
+ * This special macro can be used to load a debugging register
+ */
+#define loaddebug(thread,register) \
+ HYPERVISOR_set_debugreg((register), \
+ (thread->debugreg ## register))
+
+
+static inline void __save_init_fpu( struct task_struct *tsk )
+{
+ asm volatile( "rex64 ; fxsave %0 ; fnclex"
+ : "=m" (tsk->thread.i387.fxsave));
+ tsk->thread_info->status &= ~TS_USEDFPU;
+}
+
+/*
+ * switch_to(x,y) should switch tasks from x to y.
+ *
+ * This could still be optimized:
+ * - fold all the options into a flag word and test it with a single test.
+ * - could test fs/gs bitsliced
+ */
+struct task_struct *__switch_to(struct task_struct *prev_p, struct task_struct
*next_p)
+{
+ struct thread_struct *prev = &prev_p->thread,
+ *next = &next_p->thread;
+ int cpu = smp_processor_id();
+ struct tss_struct *tss = &per_cpu(init_tss, cpu);
+ physdev_op_t iopl_op, iobmp_op;
+ multicall_entry_t _mcl[8], *mcl = _mcl;
+
+ /*
+ * This is basically '__unlazy_fpu', except that we queue a
+ * multicall to indicate FPU task switch, rather than
+ * synchronously trapping to Xen.
+ */
+ if (prev_p->thread_info->status & TS_USEDFPU) {
+ __save_init_fpu(prev_p); /* _not_ save_init_fpu() */
+ mcl->op = __HYPERVISOR_fpu_taskswitch;
+ mcl->args[0] = 1;
+ mcl++;
+ }
+
+ /*
+ * Reload esp0, LDT and the page table pointer:
+ */
+ tss->rsp0 = next->rsp0;
+ mcl->op = __HYPERVISOR_stack_switch;
+ mcl->args[0] = __KERNEL_DS;
+ mcl->args[1] = tss->rsp0;
+ mcl++;
+
+ /*
+ * Load the per-thread Thread-Local Storage descriptor.
+ * This is load_TLS(next, cpu) with multicalls.
+ */
+#define C(i) do { \
+ if (unlikely(next->tls_array[i] != prev->tls_array[i])) { \
+ mcl->op = __HYPERVISOR_update_descriptor; \
+ mcl->args[0] = virt_to_machine(&get_cpu_gdt_table(cpu) \
+ [GDT_ENTRY_TLS_MIN + i]); \
+ mcl->args[1] = next->tls_array[i]; \
+ mcl++; \
+ } \
+} while (0)
+ C(0); C(1); C(2);
+#undef C
+
+ if (unlikely(prev->io_pl != next->io_pl)) {
+ iopl_op.cmd = PHYSDEVOP_SET_IOPL;
+ iopl_op.u.set_iopl.iopl = next->io_pl;
+ mcl->op = __HYPERVISOR_physdev_op;
+ mcl->args[0] = (unsigned long)&iopl_op;
+ mcl++;
+ }
+
+ if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr)) {
+ iobmp_op.cmd =
+ PHYSDEVOP_SET_IOBITMAP;
+ iobmp_op.u.set_iobitmap.bitmap =
+ (unsigned long)next->io_bitmap_ptr;
+ iobmp_op.u.set_iobitmap.nr_ports =
+ next->io_bitmap_ptr ? IO_BITMAP_BITS : 0;
+ mcl->op = __HYPERVISOR_physdev_op;
+ mcl->args[0] = (unsigned long)&iobmp_op;
+ mcl++;
+ }
+
+ (void)HYPERVISOR_multicall(_mcl, mcl - _mcl);
+ /*
+ * Switch DS and ES.
+ * This won't pick up thread selector changes, but I guess that is ok.
+ */
+ if (unlikely(next->es))
+ loadsegment(es, next->es);
+
+ if (unlikely(next->ds))
+ loadsegment(ds, next->ds);
+
+ /*
+ * Switch FS and GS.
+ */
+ if (unlikely(next->fsindex))
+ loadsegment(fs, next->fsindex);
+
+ if (next->fs)
+ HYPERVISOR_set_segment_base(SEGBASE_FS, next->fs);
+
+ if (unlikely(next->gsindex))
+ load_gs_index(next->gsindex);
+
+ if (next->gs)
+ HYPERVISOR_set_segment_base(SEGBASE_GS_USER, next->gs);
+
+ /*
+ * Switch the PDA context.
+ */
+ prev->userrsp = read_pda(oldrsp);
+ write_pda(oldrsp, next->userrsp);
+ write_pda(pcurrent, next_p);
+ write_pda(kernelstack, (unsigned long)next_p->thread_info + THREAD_SIZE
- PDA_STACKOFFSET);
+
+ /*
+ * Now maybe reload the debug registers
+ */
+ if (unlikely(next->debugreg7)) {
+ loaddebug(next, 0);
+ loaddebug(next, 1);
+ loaddebug(next, 2);
+ loaddebug(next, 3);
+ /* no 4 and 5 */
+ loaddebug(next, 6);
+ loaddebug(next, 7);
+ }
+
+ return prev_p;
+}
+
+/*
+ * sys_execve() executes a new program.
+ */
+asmlinkage
+long sys_execve(char __user *name, char __user * __user *argv,
+ char __user * __user *envp, struct pt_regs regs)
+{
+ long error;
+ char * filename;
+
+ filename = getname(name);
+ error = PTR_ERR(filename);
+ if (IS_ERR(filename))
+ return error;
+ error = do_execve(filename, argv, envp, ®s);
+ if (error == 0) {
+ task_lock(current);
+ current->ptrace &= ~PT_DTRACE;
+ task_unlock(current);
+ }
+ putname(filename);
+ return error;
+}
+
+void set_personality_64bit(void)
+{
+ /* inherit personality from parent */
+
+ /* Make sure to be in 64bit mode */
+ clear_thread_flag(TIF_IA32);
+
+ /* TBD: overwrites user setup. Should have two bits.
+ But 64bit processes have always behaved this way,
+ so it's not too bad. The main problem is just that
+ 32bit childs are affected again. */
+ current->personality &= ~READ_IMPLIES_EXEC;
+}
+
+asmlinkage long sys_fork(struct pt_regs *regs)
+{
+ return do_fork(SIGCHLD, regs->rsp, regs, 0, NULL, NULL);
+}
+
+asmlinkage long sys_clone(unsigned long clone_flags, unsigned long newsp, void
__user *parent_tid, void __user *child_tid, struct pt_regs *regs)
+{
+ if (!newsp)
+ newsp = regs->rsp;
+ return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
+}
+
+/*
+ * This is trivial, and on the face of it looks like it
+ * could equally well be done in user mode.
+ *
+ * Not so, for quite unobvious reasons - register pressure.
+ * In user mode vfork() cannot have a stack frame, and if
+ * done by calling the "clone()" system call directly, you
+ * do not have enough call-clobbered registers to hold all
+ * the information you need.
+ */
+asmlinkage long sys_vfork(struct pt_regs *regs)
+{
+ return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->rsp, regs, 0,
+ NULL, NULL);
+}
+
+unsigned long get_wchan(struct task_struct *p)
+{
+ unsigned long stack;
+ u64 fp,rip;
+ int count = 0;
+
+ if (!p || p == current || p->state==TASK_RUNNING)
+ return 0;
+ stack = (unsigned long)p->thread_info;
+ if (p->thread.rsp < stack || p->thread.rsp > stack+THREAD_SIZE)
+ return 0;
+ fp = *(u64 *)(p->thread.rsp);
+ do {
+ if (fp < (unsigned long)stack || fp > (unsigned
long)stack+THREAD_SIZE)
+ return 0;
+ rip = *(u64 *)(fp+8);
+ if (!in_sched_functions(rip))
+ return rip;
+ fp = *(u64 *)fp;
+ } while (count++ < 16);
+ return 0;
+}
+
+long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
+{
+ int ret = 0;
+ int doit = task == current;
+ int cpu;
+
+ switch (code) {
+ case ARCH_SET_GS:
+ if (addr >= TASK_SIZE)
+ return -EPERM;
+ cpu = get_cpu();
+ /* handle small bases via the GDT because that's faster to
+ switch. */
+ if (addr <= 0xffffffff) {
+ set_32bit_tls(task, GS_TLS, addr);
+ if (doit) {
+ load_TLS(&task->thread, cpu);
+ load_gs_index(GS_TLS_SEL);
+ }
+ task->thread.gsindex = GS_TLS_SEL;
+ task->thread.gs = 0;
+ } else {
+ task->thread.gsindex = 0;
+ task->thread.gs = addr;
+ if (doit) {
+ load_gs_index(0);
+ ret = HYPERVISOR_set_segment_base(SEGBASE_GS_USER, addr);
+ }
+ }
+ put_cpu();
+ break;
+ case ARCH_SET_FS:
+ /* Not strictly needed for fs, but do it for symmetry
+ with gs */
+ if (addr >= TASK_SIZE)
+ return -EPERM;
+ cpu = get_cpu();
+ /* handle small bases via the GDT because that's faster to
+ switch. */
+ if (addr <= 0xffffffff) {
+ set_32bit_tls(task, FS_TLS, addr);
+ if (doit) {
+ load_TLS(&task->thread, cpu);
+ asm volatile("movl %0,%%fs" :: "r"
(FS_TLS_SEL));
+ }
+ task->thread.fsindex = FS_TLS_SEL;
+ task->thread.fs = 0;
+ } else {
+ task->thread.fsindex = 0;
+ task->thread.fs = addr;
+ if (doit) {
+ /* set the selector to 0 to not confuse
+ __switch_to */
+ asm volatile("movl %0,%%fs" :: "r" (0));
+ ret = HYPERVISOR_set_segment_base(SEGBASE_FS,
addr);
+
+ }
+ }
+ put_cpu();
+ break;
+ case ARCH_GET_FS: {
+ unsigned long base;
+ if (task->thread.fsindex == FS_TLS_SEL)
+ base = read_32bit_tls(task, FS_TLS);
+ else if (doit) {
+ rdmsrl(MSR_FS_BASE, base);
+ } else
+ base = task->thread.fs;
+ ret = put_user(base, (unsigned long __user *)addr);
+ break;
+ }
+ case ARCH_GET_GS: {
+ unsigned long base;
+ if (task->thread.gsindex == GS_TLS_SEL)
+ base = read_32bit_tls(task, GS_TLS);
+ else if (doit) {
+ rdmsrl(MSR_KERNEL_GS_BASE, base);
+ } else
+ base = task->thread.gs;
+ ret = put_user(base, (unsigned long __user *)addr);
+ break;
+ }
+
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+long sys_arch_prctl(int code, unsigned long addr)
+{
+ return do_arch_prctl(current, code, addr);
+}
+
+/*
+ * Capture the user space registers if the task is not running (in user space)
+ */
+int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs)
+{
+ struct pt_regs *pp, ptregs;
+
+ pp = (struct pt_regs *)(tsk->thread.rsp0);
+ --pp;
+
+ ptregs = *pp;
+ ptregs.cs &= 0xffff;
+ ptregs.ss &= 0xffff;
+
+ elf_core_copy_regs(regs, &ptregs);
+
+ boot_option_idle_override = 1;
+ return 1;
+}
_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-changelog
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |