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

[Xen-changelog] [xen master] xen: arm: update arm32 assembly primitives to Linux v3.16-rc6



commit 65e9f0660697e895ada7999a4e9822c716bc4ec7
Author:     Ian Campbell <ian.campbell@xxxxxxxxxx>
AuthorDate: Fri Jul 25 16:22:52 2014 +0100
Commit:     Ian Campbell <ian.campbell@xxxxxxxxxx>
CommitDate: Mon Aug 4 16:53:31 2014 +0100

    xen: arm: update arm32 assembly primitives to Linux v3.16-rc6
    
    bitops, cmpxchg, atomics: Import:
      c32ffce ARM: 7984/1: prefetch: add prefetchw invocations for barriered 
atomics
        Author: Will Deacon <will.deacon@xxxxxxx>
        Signed-off-by: Will Deacon <will.deacon@xxxxxxx>
        Signed-off-by: Russell King <rmk+kernel@xxxxxxxxxxxxxxxx>
    
    atomics: In addition to the above import:
      db38ee8 ARM: 7983/1: atomics: implement a better __atomic_add_unless for 
v6+
        Author: Will Deacon <will.deacon@xxxxxxx>
        Signed-off-by: Will Deacon <will.deacon@xxxxxxx>
        Signed-off-by: Russell King <rmk+kernel@xxxxxxxxxxxxxxxx>
    
    spinlocks: We have diverged from Linux, so no updates but note this in the 
README.
    
    mem* and str*: Import:
      d98b90e ARM: 7990/1: asm: rename logical shift macros push pull into 
lspush lspull
        Author: Victor Kamensky <victor.kamensky@xxxxxxxxxx>
        Suggested-by: Will Deacon <will.deacon@xxxxxxx>
        Signed-off-by: Victor Kamensky <victor.kamensky@xxxxxxxxxx>
        Acked-by: Nicolas Pitre <nico@xxxxxxxxxx>
        Signed-off-by: Russell King <rmk+kernel@xxxxxxxxxxxxxxxx>
    
      For some reason str* were mentioned under mem* in the README, fix.
    
    libgcc: No changes, update baseline
    
    Signed-off-by: Ian Campbell <ian.campbell@xxxxxxxxxx>
    Acked-by: Julien Grall <julien.grall@xxxxxxxxxx>
---
 xen/arch/arm/README.LinuxPrimitives    |   17 +++++++--------
 xen/arch/arm/arm32/lib/assembler.h     |    8 +++---
 xen/arch/arm/arm32/lib/bitops.h        |    5 ++++
 xen/arch/arm/arm32/lib/copy_template.S |   36 ++++++++++++++++----------------
 xen/arch/arm/arm32/lib/memmove.S       |   36 ++++++++++++++++----------------
 xen/include/asm-arm/arm32/atomic.h     |   32 ++++++++++++++++++++++++++++
 xen/include/asm-arm/arm32/cmpxchg.h    |    5 ++++
 7 files changed, 90 insertions(+), 49 deletions(-)

diff --git a/xen/arch/arm/README.LinuxPrimitives 
b/xen/arch/arm/README.LinuxPrimitives
index 69eeb70..7e15b04 100644
--- a/xen/arch/arm/README.LinuxPrimitives
+++ b/xen/arch/arm/README.LinuxPrimitives
@@ -65,7 +65,7 @@ linux/arch/arm64/lib/copy_page.S        unused in Xen
 arm32
 =====================================================================
 
-bitops: last sync @ v3.14-rc7 (last commit: b7ec699)
+bitops: last sync @ v3.16-rc6 (last commit: c32ffce0f66e)
 
 linux/arch/arm/lib/bitops.h             xen/arch/arm/arm32/lib/bitops.h
 linux/arch/arm/lib/changebit.S          xen/arch/arm/arm32/lib/changebit.S
@@ -83,13 +83,13 @@ done
 
 ---------------------------------------------------------------------
 
-cmpxchg: last sync @ v3.14-rc7 (last commit: 775ebcc)
+cmpxchg: last sync @ v3.16-rc6 (last commit: c32ffce0f66e)
 
 linux/arch/arm/include/asm/cmpxchg.h    xen/include/asm-arm/arm32/cmpxchg.h
 
 ---------------------------------------------------------------------
 
-atomics: last sync @ v3.14-rc7 (last commit: aed3a4e)
+atomics: last sync @ v3.16-rc6 (last commit: 030d0178bdbd)
 
 linux/arch/arm/include/asm/atomic.h     xen/include/asm-arm/arm32/atomic.h
 
@@ -99,6 +99,8 @@ spinlocks: last sync: 15e7e5c1ebf5
 
 linux/arch/arm/include/asm/spinlock.h   xen/include/asm-arm/arm32/spinlock.h
 
+*** Linux has switched to ticket locks but we still use bitlocks.
+
 resync to v3.14-rc7:
 
   7c8746a ARM: 7955/1: spinlock: ensure we have a compiler barrier before sev
@@ -111,7 +113,7 @@ resync to v3.14-rc7:
 
 ---------------------------------------------------------------------
 
-mem*: last sync @ v3.14-rc7 (last commit: 418df63a)
+mem*: last sync @ v3.16-rc6 (last commit: d98b90ea22b0)
 
 linux/arch/arm/lib/copy_template.S      xen/arch/arm/arm32/lib/copy_template.S
 linux/arch/arm/lib/memchr.S             xen/arch/arm/arm32/lib/memchr.S
@@ -120,9 +122,6 @@ linux/arch/arm/lib/memmove.S            
xen/arch/arm/arm32/lib/memmove.S
 linux/arch/arm/lib/memset.S             xen/arch/arm/arm32/lib/memset.S
 linux/arch/arm/lib/memzero.S            xen/arch/arm/arm32/lib/memzero.S
 
-linux/arch/arm/lib/strchr.S             xen/arch/arm/arm32/lib/strchr.S
-linux/arch/arm/lib/strrchr.S            xen/arch/arm/arm32/lib/strrchr.S
-
 for i in copy_template.S memchr.S memcpy.S memmove.S memset.S \
          memzero.S ; do
     diff -u linux/arch/arm/lib/$i xen/arch/arm/arm32/lib/$i
@@ -130,7 +129,7 @@ done
 
 ---------------------------------------------------------------------
 
-str*: last sync @ v3.13-rc7 (last commit: 93ed397)
+str*: last sync @ v3.16-rc6 (last commit: d98b90ea22b0)
 
 linux/arch/arm/lib/strchr.S             xen/arch/arm/arm32/lib/strchr.S
 linux/arch/arm/lib/strrchr.S            xen/arch/arm/arm32/lib/strrchr.S
@@ -145,7 +144,7 @@ clear_page == memset
 
 ---------------------------------------------------------------------
 
-libgcc: last sync @ v3.14-rc7 (last commit: 01885bc)
+libgcc: last sync @ v3.16-rc6 (last commit: 01885bc)
 
 linux/arch/arm/lib/lib1funcs.S          xen/arch/arm/arm32/lib/lib1funcs.S
 linux/arch/arm/lib/lshrdi3.S            xen/arch/arm/arm32/lib/lshrdi3.S
diff --git a/xen/arch/arm/arm32/lib/assembler.h 
b/xen/arch/arm/arm32/lib/assembler.h
index f8d4b3a..6de2638 100644
--- a/xen/arch/arm/arm32/lib/assembler.h
+++ b/xen/arch/arm/arm32/lib/assembler.h
@@ -36,8 +36,8 @@
  * Endian independent macros for shifting bytes within registers.
  */
 #ifndef __ARMEB__
-#define pull            lsr
-#define push            lsl
+#define lspull          lsr
+#define lspush          lsl
 #define get_byte_0      lsl #0
 #define get_byte_1     lsr #8
 #define get_byte_2     lsr #16
@@ -47,8 +47,8 @@
 #define put_byte_2     lsl #16
 #define put_byte_3     lsl #24
 #else
-#define pull            lsl
-#define push            lsr
+#define lspull          lsl
+#define lspush          lsr
 #define get_byte_0     lsr #24
 #define get_byte_1     lsr #16
 #define get_byte_2     lsr #8
diff --git a/xen/arch/arm/arm32/lib/bitops.h b/xen/arch/arm/arm32/lib/bitops.h
index 25784c3..a167c2d 100644
--- a/xen/arch/arm/arm32/lib/bitops.h
+++ b/xen/arch/arm/arm32/lib/bitops.h
@@ -37,6 +37,11 @@ UNWIND(      .fnstart        )
        add     r1, r1, r0, lsl #2      @ Get word offset
        mov     r3, r2, lsl r3          @ create mask
        smp_dmb
+#if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
+       .arch_extension mp
+       ALT_SMP(W(pldw) [r1])
+       ALT_UP(W(nop))
+#endif
 1:     ldrex   r2, [r1]
        ands    r0, r2, r3              @ save old value of bit
        \instr  r2, r2, r3              @ toggle bit
diff --git a/xen/arch/arm/arm32/lib/copy_template.S 
b/xen/arch/arm/arm32/lib/copy_template.S
index 805e3f8..3bc8eb8 100644
--- a/xen/arch/arm/arm32/lib/copy_template.S
+++ b/xen/arch/arm/arm32/lib/copy_template.S
@@ -197,24 +197,24 @@
 
 12:    PLD(    pld     [r1, #124]              )
 13:            ldr4w   r1, r4, r5, r6, r7, abort=19f
-               mov     r3, lr, pull #\pull
+               mov     r3, lr, lspull #\pull
                subs    r2, r2, #32
                ldr4w   r1, r8, r9, ip, lr, abort=19f
-               orr     r3, r3, r4, push #\push
-               mov     r4, r4, pull #\pull
-               orr     r4, r4, r5, push #\push
-               mov     r5, r5, pull #\pull
-               orr     r5, r5, r6, push #\push
-               mov     r6, r6, pull #\pull
-               orr     r6, r6, r7, push #\push
-               mov     r7, r7, pull #\pull
-               orr     r7, r7, r8, push #\push
-               mov     r8, r8, pull #\pull
-               orr     r8, r8, r9, push #\push
-               mov     r9, r9, pull #\pull
-               orr     r9, r9, ip, push #\push
-               mov     ip, ip, pull #\pull
-               orr     ip, ip, lr, push #\push
+               orr     r3, r3, r4, lspush #\push
+               mov     r4, r4, lspull #\pull
+               orr     r4, r4, r5, lspush #\push
+               mov     r5, r5, lspull #\pull
+               orr     r5, r5, r6, lspush #\push
+               mov     r6, r6, lspull #\pull
+               orr     r6, r6, r7, lspush #\push
+               mov     r7, r7, lspull #\pull
+               orr     r7, r7, r8, lspush #\push
+               mov     r8, r8, lspull #\pull
+               orr     r8, r8, r9, lspush #\push
+               mov     r9, r9, lspull #\pull
+               orr     r9, r9, ip, lspush #\push
+               mov     ip, ip, lspull #\pull
+               orr     ip, ip, lr, lspush #\push
                str8w   r0, r3, r4, r5, r6, r7, r8, r9, ip, , abort=19f
                bge     12b
        PLD(    cmn     r2, #96                 )
@@ -225,10 +225,10 @@
 14:            ands    ip, r2, #28
                beq     16f
 
-15:            mov     r3, lr, pull #\pull
+15:            mov     r3, lr, lspull #\pull
                ldr1w   r1, lr, abort=21f
                subs    ip, ip, #4
-               orr     r3, r3, lr, push #\push
+               orr     r3, r3, lr, lspush #\push
                str1w   r0, r3, abort=21f
                bgt     15b
        CALGN(  cmp     r2, #0                  )
diff --git a/xen/arch/arm/arm32/lib/memmove.S b/xen/arch/arm/arm32/lib/memmove.S
index 4e142b8..18634c3 100644
--- a/xen/arch/arm/arm32/lib/memmove.S
+++ b/xen/arch/arm/arm32/lib/memmove.S
@@ -148,24 +148,24 @@ ENTRY(memmove)
 
 12:    PLD(    pld     [r1, #-128]             )
 13:            ldmdb   r1!, {r7, r8, r9, ip}
-               mov     lr, r3, push #\push
+               mov     lr, r3, lspush #\push
                subs    r2, r2, #32
                ldmdb   r1!, {r3, r4, r5, r6}
-               orr     lr, lr, ip, pull #\pull
-               mov     ip, ip, push #\push
-               orr     ip, ip, r9, pull #\pull
-               mov     r9, r9, push #\push
-               orr     r9, r9, r8, pull #\pull
-               mov     r8, r8, push #\push
-               orr     r8, r8, r7, pull #\pull
-               mov     r7, r7, push #\push
-               orr     r7, r7, r6, pull #\pull
-               mov     r6, r6, push #\push
-               orr     r6, r6, r5, pull #\pull
-               mov     r5, r5, push #\push
-               orr     r5, r5, r4, pull #\pull
-               mov     r4, r4, push #\push
-               orr     r4, r4, r3, pull #\pull
+               orr     lr, lr, ip, lspull #\pull
+               mov     ip, ip, lspush #\push
+               orr     ip, ip, r9, lspull #\pull
+               mov     r9, r9, lspush #\push
+               orr     r9, r9, r8, lspull #\pull
+               mov     r8, r8, lspush #\push
+               orr     r8, r8, r7, lspull #\pull
+               mov     r7, r7, lspush #\push
+               orr     r7, r7, r6, lspull #\pull
+               mov     r6, r6, lspush #\push
+               orr     r6, r6, r5, lspull #\pull
+               mov     r5, r5, lspush #\push
+               orr     r5, r5, r4, lspull #\pull
+               mov     r4, r4, lspush #\push
+               orr     r4, r4, r3, lspull #\pull
                stmdb   r0!, {r4 - r9, ip, lr}
                bge     12b
        PLD(    cmn     r2, #96                 )
@@ -176,10 +176,10 @@ ENTRY(memmove)
 14:            ands    ip, r2, #28
                beq     16f
 
-15:            mov     lr, r3, push #\push
+15:            mov     lr, r3, lspush #\push
                ldr     r3, [r1, #-4]!
                subs    ip, ip, #4
-               orr     lr, lr, r3, pull #\pull
+               orr     lr, lr, r3, lspull #\pull
                str     lr, [r0, #-4]!
                bgt     15b
        CALGN(  cmp     r2, #0                  )
diff --git a/xen/include/asm-arm/arm32/atomic.h 
b/xen/include/asm-arm/arm32/atomic.h
index 3d601d1..7ec712f 100644
--- a/xen/include/asm-arm/arm32/atomic.h
+++ b/xen/include/asm-arm/arm32/atomic.h
@@ -39,6 +39,7 @@ static inline int atomic_add_return(int i, atomic_t *v)
        int result;
 
        smp_mb();
+       prefetchw(&v->counter);
 
        __asm__ __volatile__("@ atomic_add_return\n"
 "1:    ldrex   %0, [%3]\n"
@@ -78,6 +79,7 @@ static inline int atomic_sub_return(int i, atomic_t *v)
        int result;
 
        smp_mb();
+       prefetchw(&v->counter);
 
        __asm__ __volatile__("@ atomic_sub_return\n"
 "1:    ldrex   %0, [%3]\n"
@@ -100,6 +102,7 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, 
int new)
        unsigned long res;
 
        smp_mb();
+       prefetchw(&ptr->counter);
 
        do {
                __asm__ __volatile__("@ atomic_cmpxchg\n"
@@ -117,6 +120,35 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, 
int new)
        return oldval;
 }
 
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+       int oldval, newval;
+       unsigned long tmp;
+
+       smp_mb();
+       prefetchw(&v->counter);
+
+       __asm__ __volatile__ ("@ atomic_add_unless\n"
+"1:    ldrex   %0, [%4]\n"
+"      teq     %0, %5\n"
+"      beq     2f\n"
+"      add     %1, %0, %6\n"
+"      strex   %2, %1, [%4]\n"
+"      teq     %2, #0\n"
+"      bne     1b\n"
+"2:"
+       : "=&r" (oldval), "=&r" (newval), "=&r" (tmp), "+Qo" (v->counter)
+       : "r" (&v->counter), "r" (u), "r" (a)
+       : "cc");
+
+       if (oldval != u)
+               smp_mb();
+
+       return oldval;
+}
+
+#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+
 #define atomic_inc(v)          atomic_add(1, v)
 #define atomic_dec(v)          atomic_sub(1, v)
 
diff --git a/xen/include/asm-arm/arm32/cmpxchg.h 
b/xen/include/asm-arm/arm32/cmpxchg.h
index 9a511f2..03e0bed 100644
--- a/xen/include/asm-arm/arm32/cmpxchg.h
+++ b/xen/include/asm-arm/arm32/cmpxchg.h
@@ -1,6 +1,8 @@
 #ifndef __ASM_ARM32_CMPXCHG_H
 #define __ASM_ARM32_CMPXCHG_H
 
+#include <xen/prefetch.h>
+
 extern void __bad_xchg(volatile void *, int);
 
 static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int 
size)
@@ -9,6 +11,7 @@ static inline unsigned long __xchg(unsigned long x, volatile 
void *ptr, int size
        unsigned int tmp;
 
        smp_mb();
+       prefetchw((const void *)ptr);
 
        switch (size) {
        case 1:
@@ -56,6 +59,8 @@ static always_inline unsigned long __cmpxchg(
 {
        unsigned long oldval, res;
 
+       prefetchw((const void *)ptr);
+
        switch (size) {
        case 1:
                do {
--
generated by git-patchbot for /home/xen/git/xen.git#master

_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxx
http://lists.xensource.com/xen-changelog


 


Rackspace

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