x86-32: clean up rwsem inline asm statements

This makes gcc use the right register names and instruction operand sizes
automatically for the rwsem inline asm statements.

So instead of using "(%%eax)" to specify the memory address that is the
semaphore, we use "(%1)" or similar. And instead of forcing the operation
to always be 32-bit, we use "%z0", taking the size from the actual
semaphore data structure itself.

This doesn't actually matter on x86-32, but if we want to use the same
inline asm for x86-64, we'll need to have the compiler generate the proper
64-bit names for the registers (%rax instead of %eax), and if we want to
use a 64-bit counter too (in order to avoid the 15-bit limit on the
write counter that limits concurrent users to 32767 threads), we'll need
to be able to generate instructions with "q" accesses rather than "l".

Since this header currently isn't enabled on x86-64, none of that matters,
but we do want to use the xadd version of the semaphores rather than have
to take spinlocks to do a rwsem. The mm->mmap_sem can be heavily contended
when you have lots of threads all taking page faults, and the fallback
rwsem code that uses a spinlock performs abysmally badly in that case.

[ hpa: modified the patch to skip size suffixes entirely when they are
  redundant due to register operands. ]

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
LKML-Reference: <alpine.LFD.2.00.1001121613560.17145@localhost.localdomain>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index ca7517d3377634b6251ce727326d06dd30627fc5..413620024768a15b18a5ed77a3327a21d6e217cb 100644 (file)
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -105,7 +105,7 @@ do {                                                                \
 static inline void __down_read(struct rw_semaphore *sem)
 {
        asm volatile("# beginning down_read\n\t"
-                    LOCK_PREFIX "  incl      (%%eax)\n\t"
+                    LOCK_PREFIX "  inc%z0      (%1)\n\t"
                     /* adds 0x00000001, returns the old value */
                     "  jns        1f\n"
                     "  call call_rwsem_down_read_failed\n"
@@ -123,12 +123,12 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
        __s32 result, tmp;
        asm volatile("# beginning __down_read_trylock\n\t"
-                    "  movl      %0,%1\n\t"
+                    "  mov          %0,%1\n\t"
                     "1:\n\t"
-                    "  movl         %1,%2\n\t"
-                    "  addl      %3,%2\n\t"
+                    "  mov          %1,%2\n\t"
+                    "  add          %3,%2\n\t"
                     "  jle          2f\n\t"
-                    LOCK_PREFIX "  cmpxchgl  %2,%0\n\t"
+                    LOCK_PREFIX "  cmpxchg  %2,%0\n\t"
                     "  jnz          1b\n\t"
                     "2:\n\t"
                     "# ending __down_read_trylock\n\t"
@@ -147,9 +147,9 @@ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
 
        tmp = RWSEM_ACTIVE_WRITE_BIAS;
        asm volatile("# beginning down_write\n\t"
-                    LOCK_PREFIX "  xadd      %%edx,(%%eax)\n\t"
+                    LOCK_PREFIX "  xadd      %1,(%2)\n\t"
                     /* subtract 0x0000ffff, returns the old value */
-                    "  testl     %%edx,%%edx\n\t"
+                    "  test      %1,%1\n\t"
                     /* was the count 0 before? */
                     "  jz        1f\n"
                     "  call call_rwsem_down_write_failed\n"
@@ -185,7 +185,7 @@ static inline void __up_read(struct rw_semaphore *sem)
 {
        __s32 tmp = -RWSEM_ACTIVE_READ_BIAS;
        asm volatile("# beginning __up_read\n\t"
-                    LOCK_PREFIX "  xadd      %%edx,(%%eax)\n\t"
+                    LOCK_PREFIX "  xadd      %1,(%2)\n\t"
                     /* subtracts 1, returns the old value */
                     "  jns        1f\n\t"
                     "  call call_rwsem_wake\n"
@@ -201,18 +201,18 @@ static inline void __up_read(struct rw_semaphore *sem)
  */
 static inline void __up_write(struct rw_semaphore *sem)
 {
+       unsigned long tmp;
        asm volatile("# beginning __up_write\n\t"
-                    "  movl      %2,%%edx\n\t"
-                    LOCK_PREFIX "  xaddl     %%edx,(%%eax)\n\t"
+                    LOCK_PREFIX "  xadd      %1,(%2)\n\t"
                     /* tries to transition
                        0xffff0001 -> 0x00000000 */
                     "  jz       1f\n"
                     "  call call_rwsem_wake\n"
                     "1:\n\t"
                     "# ending __up_write\n"
-                    : "+m" (sem->count)
-                    : "a" (sem), "i" (-RWSEM_ACTIVE_WRITE_BIAS)
-                    : "memory", "cc", "edx");
+                    : "+m" (sem->count), "=d" (tmp)
+                    : "a" (sem), "1" (-RWSEM_ACTIVE_WRITE_BIAS)
+                    : "memory", "cc");
 }
 
 /*
@@ -221,7 +221,7 @@ static inline void __up_write(struct rw_semaphore *sem)
 static inline void __downgrade_write(struct rw_semaphore *sem)
 {
        asm volatile("# beginning __downgrade_write\n\t"
-                    LOCK_PREFIX "  addl      %2,(%%eax)\n\t"
+                    LOCK_PREFIX "  add%z0    %2,(%1)\n\t"
                     /* transitions 0xZZZZ0001 -> 0xYYYY0001 */
                     "  jns       1f\n\t"
                     "  call call_rwsem_downgrade_wake\n"
@@ -237,7 +237,7 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
  */
 static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
 {
-       asm volatile(LOCK_PREFIX "addl %1,%0"
+       asm volatile(LOCK_PREFIX "add%z0 %1,%0"
                     : "+m" (sem->count)
                     : "ir" (delta));
 }