[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-devel] [PATCH RFC v12 13/21] pvh: Support read_segment_register for PVH



This will be necessary to do PV-style emulated operations for PVH guests.

Signed-off-by: George Dunlap <george.dunlap@xxxxxxxxxxxxx>
Signed-off-by: Mukesh Rathor <mukesh.rathor@xxxxxxxxxx>
CC: Jan Beulich <jan.beulich@xxxxxxxx>
CC: Tim Deegan <tim@xxxxxxx>
CC: Keir Fraser <keir@xxxxxxx>
---
 xen/arch/x86/domain.c         |    8 ++++----
 xen/arch/x86/hvm/vmx/vmx.c    |   40 ++++++++++++++++++++++++++++++++++++++++
 xen/arch/x86/traps.c          |   26 ++++++++++++--------------
 xen/arch/x86/x86_64/traps.c   |   16 ++++++++--------
 xen/include/asm-x86/hvm/hvm.h |    6 ++++++
 xen/include/asm-x86/system.h  |   19 +++++++++++++++----
 6 files changed, 85 insertions(+), 30 deletions(-)

diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index c75798b..02a6479 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -1217,10 +1217,10 @@ static void save_segments(struct vcpu *v)
     struct cpu_user_regs *regs = &v->arch.user_regs;
     unsigned int dirty_segment_mask = 0;
 
-    regs->ds = read_segment_register(ds);
-    regs->es = read_segment_register(es);
-    regs->fs = read_segment_register(fs);
-    regs->gs = read_segment_register(gs);
+    regs->ds = read_segment_register(v, regs, ds);
+    regs->es = read_segment_register(v, regs, es);
+    regs->fs = read_segment_register(v, regs, fs);
+    regs->gs = read_segment_register(v, regs, gs);
 
     if ( regs->ds )
         dirty_segment_mask |= DIRTY_DS;
diff --git a/xen/arch/x86/hvm/vmx/vmx.c b/xen/arch/x86/hvm/vmx/vmx.c
index 0ac96ab..c2156af 100644
--- a/xen/arch/x86/hvm/vmx/vmx.c
+++ b/xen/arch/x86/hvm/vmx/vmx.c
@@ -664,6 +664,45 @@ static void vmx_ctxt_switch_to(struct vcpu *v)
         .fields = { .type = 0xb, .s = 0, .dpl = 0, .p = 1, .avl = 0,    \
                     .l = 0, .db = 0, .g = 0, .pad = 0 } }).bytes)
 
+u16 vmx_read_selector(struct vcpu *v, enum x86_segment seg)
+{
+    u16 sel = 0;
+
+    vmx_vmcs_enter(v);
+    switch ( seg )
+    {
+    case x86_seg_cs:
+        sel = __vmread(GUEST_CS_SELECTOR);
+        break;
+
+    case x86_seg_ss:
+        sel = __vmread(GUEST_SS_SELECTOR);
+        break;
+
+    case x86_seg_es:
+        sel = __vmread(GUEST_ES_SELECTOR);
+        break;
+
+    case x86_seg_ds:
+        sel = __vmread(GUEST_DS_SELECTOR);
+        break;
+
+    case x86_seg_fs:
+        sel = __vmread(GUEST_FS_SELECTOR);
+        break;
+
+    case x86_seg_gs:
+        sel = __vmread(GUEST_GS_SELECTOR);
+        break;
+
+    default:
+        BUG();
+    }
+    vmx_vmcs_exit(v);
+
+    return sel;
+}
+
 void vmx_get_segment_register(struct vcpu *v, enum x86_segment seg,
                               struct segment_register *reg)
 {
@@ -1566,6 +1605,7 @@ static struct hvm_function_table __initdata 
vmx_function_table = {
     .sync_pir_to_irr      = vmx_sync_pir_to_irr,
     .handle_eoi           = vmx_handle_eoi,
     .nhvm_hap_walk_L1_p2m = nvmx_hap_walk_L1_p2m,
+    .read_selector        = vmx_read_selector,
 };
 
 const struct hvm_function_table * __init start_vmx(void)
diff --git a/xen/arch/x86/traps.c b/xen/arch/x86/traps.c
index e4f080c..a5d8349 100644
--- a/xen/arch/x86/traps.c
+++ b/xen/arch/x86/traps.c
@@ -1833,8 +1833,6 @@ static inline uint64_t guest_misc_enable(uint64_t val)
     }                                                                       \
     (eip) += sizeof(_x); _x; })
 
-#define read_sreg(regs, sr) read_segment_register(sr)
-
 static int is_cpufreq_controller(struct domain *d)
 {
     return ((cpufreq_controller == FREQCTL_dom0_kernel) &&
@@ -1879,7 +1877,7 @@ static int emulate_privileged_op(struct cpu_user_regs 
*regs)
         goto fail;
 
     /* emulating only opcodes not allowing SS to be default */
-    data_sel = read_sreg(regs, ds);
+    data_sel = read_segment_register(v, regs, ds);
 
     /* Legacy prefixes. */
     for ( i = 0; i < 8; i++, rex == opcode || (rex = 0) )
@@ -1897,17 +1895,17 @@ static int emulate_privileged_op(struct cpu_user_regs 
*regs)
             data_sel = regs->cs;
             continue;
         case 0x3e: /* DS override */
-            data_sel = read_sreg(regs, ds);
+            data_sel = read_segment_register(v, regs, ds);
             continue;
         case 0x26: /* ES override */
-            data_sel = read_sreg(regs, es);
+            data_sel = read_segment_register(v, regs, es);
             continue;
         case 0x64: /* FS override */
-            data_sel = read_sreg(regs, fs);
+            data_sel = read_segment_register(v, regs, fs);
             lm_ovr = lm_seg_fs;
             continue;
         case 0x65: /* GS override */
-            data_sel = read_sreg(regs, gs);
+            data_sel = read_segment_register(v, regs, gs);
             lm_ovr = lm_seg_gs;
             continue;
         case 0x36: /* SS override */
@@ -1954,7 +1952,7 @@ static int emulate_privileged_op(struct cpu_user_regs 
*regs)
 
         if ( !(opcode & 2) )
         {
-            data_sel = read_sreg(regs, es);
+            data_sel = read_segment_register(v, regs, es);
             lm_ovr = lm_seg_none;
         }
 
@@ -2687,22 +2685,22 @@ static void emulate_gate_op(struct cpu_user_regs *regs)
             ASSERT(opnd_sel);
             continue;
         case 0x3e: /* DS override */
-            opnd_sel = read_sreg(regs, ds);
+            opnd_sel = read_segment_register(v, regs, ds);
             if ( !opnd_sel )
                 opnd_sel = dpl;
             continue;
         case 0x26: /* ES override */
-            opnd_sel = read_sreg(regs, es);
+            opnd_sel = read_segment_register(v, regs, es);
             if ( !opnd_sel )
                 opnd_sel = dpl;
             continue;
         case 0x64: /* FS override */
-            opnd_sel = read_sreg(regs, fs);
+            opnd_sel = read_segment_register(v, regs, fs);
             if ( !opnd_sel )
                 opnd_sel = dpl;
             continue;
         case 0x65: /* GS override */
-            opnd_sel = read_sreg(regs, gs);
+            opnd_sel = read_segment_register(v, regs, gs);
             if ( !opnd_sel )
                 opnd_sel = dpl;
             continue;
@@ -2755,7 +2753,7 @@ static void emulate_gate_op(struct cpu_user_regs *regs)
                             switch ( modrm & 7 )
                             {
                             default:
-                                opnd_sel = read_sreg(regs, ds);
+                                opnd_sel = read_segment_register(v, regs, ds);
                                 break;
                             case 4: case 5:
                                 opnd_sel = regs->ss;
@@ -2783,7 +2781,7 @@ static void emulate_gate_op(struct cpu_user_regs *regs)
                             break;
                         }
                         if ( !opnd_sel )
-                            opnd_sel = read_sreg(regs, ds);
+                            opnd_sel = read_segment_register(v, regs, ds);
                         switch ( modrm & 7 )
                         {
                         case 0: case 2: case 4:
diff --git a/xen/arch/x86/x86_64/traps.c b/xen/arch/x86/x86_64/traps.c
index 8644aaf..3dfb309 100644
--- a/xen/arch/x86/x86_64/traps.c
+++ b/xen/arch/x86/x86_64/traps.c
@@ -123,10 +123,10 @@ void show_registers(struct cpu_user_regs *regs)
         fault_crs[0] = read_cr0();
         fault_crs[3] = read_cr3();
         fault_crs[4] = read_cr4();
-        fault_regs.ds = read_segment_register(ds);
-        fault_regs.es = read_segment_register(es);
-        fault_regs.fs = read_segment_register(fs);
-        fault_regs.gs = read_segment_register(gs);
+        fault_regs.ds = read_segment_register(v, regs, ds);
+        fault_regs.es = read_segment_register(v, regs, es);
+        fault_regs.fs = read_segment_register(v, regs, fs);
+        fault_regs.gs = read_segment_register(v, regs, gs);
     }
 
     print_xen_info();
@@ -239,10 +239,10 @@ void do_double_fault(struct cpu_user_regs *regs)
     crs[2] = read_cr2();
     crs[3] = read_cr3();
     crs[4] = read_cr4();
-    regs->ds = read_segment_register(ds);
-    regs->es = read_segment_register(es);
-    regs->fs = read_segment_register(fs);
-    regs->gs = read_segment_register(gs);
+    regs->ds = read_segment_register(current, regs, ds);
+    regs->es = read_segment_register(current, regs, es);
+    regs->fs = read_segment_register(current, regs, fs);
+    regs->gs = read_segment_register(current, regs, gs);
 
     printk("CPU:    %d\n", cpu);
     _show_registers(regs, crs, CTXT_hypervisor, NULL);
diff --git a/xen/include/asm-x86/hvm/hvm.h b/xen/include/asm-x86/hvm/hvm.h
index 00489cf..401fa4c 100644
--- a/xen/include/asm-x86/hvm/hvm.h
+++ b/xen/include/asm-x86/hvm/hvm.h
@@ -193,6 +193,7 @@ struct hvm_function_table {
                                 paddr_t *L1_gpa, unsigned int *page_order,
                                 uint8_t *p2m_acc, bool_t access_r,
                                 bool_t access_w, bool_t access_x);
+    u16 (*read_selector)(struct vcpu *v, enum x86_segment seg);
 };
 
 extern struct hvm_function_table hvm_funcs;
@@ -344,6 +345,11 @@ static inline int hvm_event_pending(struct vcpu *v)
     return hvm_funcs.event_pending(v);
 }
 
+static inline u16 pvh_get_selector(struct vcpu *v, enum x86_segment seg)
+{
+    return hvm_funcs.read_selector(v, seg);
+}
+
 /* These reserved bits in lower 32 remain 0 after any load of CR0 */
 #define HVM_CR0_GUEST_RESERVED_BITS             \
     (~((unsigned long)                          \
diff --git a/xen/include/asm-x86/system.h b/xen/include/asm-x86/system.h
index 6ab7d56..1242657 100644
--- a/xen/include/asm-x86/system.h
+++ b/xen/include/asm-x86/system.h
@@ -4,10 +4,21 @@
 #include <xen/lib.h>
 #include <xen/bitops.h>
 
-#define read_segment_register(name)                             \
-({  u16 __sel;                                                  \
-    asm volatile ( "movw %%" STR(name) ",%0" : "=r" (__sel) );  \
-    __sel;                                                      \
+/*
+ * We need vcpu because during context switch, going from PV to PVH,
+ * in save_segments() current has been updated to next, and no longer pointing
+ * to the PV, but the intention is to get selector for the PV. Checking
+ * is_pvh_vcpu(current) will yield incorrect results in such a case.
+ */
+#define read_segment_register(vcpu, regs, name)                   \
+({  u16 __sel;                                                    \
+    struct cpu_user_regs *_regs = (regs);                         \
+                                                                  \
+    if ( is_pvh_vcpu(vcpu) && guest_mode(_regs) )                 \
+        __sel = pvh_get_selector(vcpu, x86_seg_##name);           \
+    else                                                          \
+        asm volatile ( "movw %%" #name ",%0" : "=r" (__sel) );    \
+    __sel;                                                        \
 })
 
 #define wbinvd() \
-- 
1.7.9.5


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.