1
0
Fork 0
alistair23-linux/arch/x86/include/asm/rwsem.h

221 lines
6.3 KiB
C
Raw Normal View History

/* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for i486+
*
* Written by David Howells (dhowells@redhat.com).
*
* Derived from asm-x86/semaphore.h
*
*
* The MSW of the count is the negated number of active writers and waiting
* lockers, and the LSW is the total number of active locks
*
* The lock count is initialized to 0 (no active and no waiting lockers).
*
* When a writer subtracts WRITE_BIAS, it'll get 0xffff0001 for the case of an
* uncontended lock. This can be determined because XADD returns the old value.
* Readers increment by 1 and see a positive value when uncontended, negative
* if there are writers (and maybe) readers waiting (in which case it goes to
* sleep).
*
* The value of WAITING_BIAS supports up to 32766 waiting processes. This can
* be extended to 65534 by manually checking the whole MSW rather than relying
* on the S flag.
*
* The value of ACTIVE_BIAS supports up to 65535 active processes.
*
* This should be totally fair - if anything is waiting, a process that wants a
* lock will go to the back of the queue. When the currently active lock is
* released, if there's a writer at the front of the queue, then that and only
* that will be woken up; if there's a bunch of consecutive readers at the
* front, then they'll all be woken up, but no other readers will be.
*/
#ifndef _ASM_X86_RWSEM_H
#define _ASM_X86_RWSEM_H
#ifndef _LINUX_RWSEM_H
#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
#endif
#ifdef __KERNEL__
#include <asm/asm.h>
/*
* The bias values and the counter type limits the number of
* potential readers/writers to 32767 for 32 bits and 2147483647
* for 64 bits.
*/
#ifdef CONFIG_X86_64
# define RWSEM_ACTIVE_MASK 0xffffffffL
#else
# define RWSEM_ACTIVE_MASK 0x0000ffffL
#endif
#define RWSEM_UNLOCKED_VALUE 0x00000000L
#define RWSEM_ACTIVE_BIAS 0x00000001L
#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1)
#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
/*
* lock for reading
*/
static inline void __down_read(struct rw_semaphore *sem)
{
asm volatile("# beginning down_read\n\t"
LOCK_PREFIX _ASM_INC "(%1)\n\t"
/* adds 0x00000001 */
" jns 1f\n"
" call call_rwsem_down_read_failed\n"
"1:\n\t"
"# ending down_read\n\t"
: "+m" (sem->count)
: "a" (sem)
: "memory", "cc");
}
/*
* trylock for reading -- returns 1 if successful, 0 if contention
*/
static inline bool __down_read_trylock(struct rw_semaphore *sem)
{
long result, tmp;
asm volatile("# beginning __down_read_trylock\n\t"
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>
2010-01-12 17:21:09 -07:00
" mov %0,%1\n\t"
"1:\n\t"
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>
2010-01-12 17:21:09 -07:00
" mov %1,%2\n\t"
" add %3,%2\n\t"
" jle 2f\n\t"
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>
2010-01-12 17:21:09 -07:00
LOCK_PREFIX " cmpxchg %2,%0\n\t"
" jnz 1b\n\t"
"2:\n\t"
"# ending __down_read_trylock\n\t"
: "+m" (sem->count), "=&a" (result), "=&r" (tmp)
: "i" (RWSEM_ACTIVE_READ_BIAS)
: "memory", "cc");
return result >= 0;
}
/*
* lock for writing
*/
#define ____down_write(sem, slow_path) \
({ \
long tmp; \
struct rw_semaphore* ret; \
\
asm volatile("# beginning down_write\n\t" \
LOCK_PREFIX " xadd %1,(%4)\n\t" \
/* adds 0xffff0001, returns the old value */ \
" test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \
/* was the active mask 0 before? */\
" jz 1f\n" \
" call " slow_path "\n" \
"1:\n" \
"# ending down_write" \
x86/asm: Fix inline asm call constraints for Clang For inline asm statements which have a CALL instruction, we list the stack pointer as a constraint to convince GCC to ensure the frame pointer is set up first: static inline void foo() { register void *__sp asm(_ASM_SP); asm("call bar" : "+r" (__sp)) } Unfortunately, that pattern causes Clang to corrupt the stack pointer. The fix is easy: convert the stack pointer register variable to a global variable. It should be noted that the end result is different based on the GCC version. With GCC 6.4, this patch has exactly the same result as before: defconfig defconfig-nofp distro distro-nofp before 9820389 9491555 8816046 8516940 after 9820389 9491555 8816046 8516940 With GCC 7.2, however, GCC's behavior has changed. It now changes its behavior based on the conversion of the register variable to a global. That somehow convinces it to *always* set up the frame pointer before inserting *any* inline asm. (Therefore, listing the variable as an output constraint is a no-op and is no longer necessary.) It's a bit overkill, but the performance impact should be negligible. And in fact, there's a nice improvement with frame pointers disabled: defconfig defconfig-nofp distro distro-nofp before 9796316 9468236 9076191 8790305 after 9796957 9464267 9076381 8785949 So in summary, while listing the stack pointer as an output constraint is no longer necessary for newer versions of GCC, it's still needed for older versions. Suggested-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Reported-by: Matthias Kaehlcke <mka@chromium.org> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Alexander Potapenko <glider@google.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dmitriy Vyukov <dvyukov@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Miguel Bernal Marin <miguel.bernal.marin@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/3db862e970c432ae823cf515c52b54fec8270e0e.1505942196.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-09-20 15:24:33 -06:00
: "+m" (sem->count), "=d" (tmp), \
"=a" (ret), ASM_CALL_CONSTRAINT \
: "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \
: "memory", "cc"); \
ret; \
})
static inline void __down_write(struct rw_semaphore *sem)
{
____down_write(sem, "call_rwsem_down_write_failed");
}
static inline int __down_write_killable(struct rw_semaphore *sem)
{
if (IS_ERR(____down_write(sem, "call_rwsem_down_write_failed_killable")))
return -EINTR;
return 0;
}
/*
* trylock for writing -- returns 1 if successful, 0 if contention
*/
static inline bool __down_write_trylock(struct rw_semaphore *sem)
{
bool result;
long tmp0, tmp1;
asm volatile("# beginning __down_write_trylock\n\t"
" mov %0,%1\n\t"
"1:\n\t"
" test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t"
/* was the active mask 0 before? */
" jnz 2f\n\t"
" mov %1,%2\n\t"
" add %4,%2\n\t"
LOCK_PREFIX " cmpxchg %2,%0\n\t"
" jnz 1b\n\t"
"2:\n\t"
CC_SET(e)
"# ending __down_write_trylock\n\t"
: "+m" (sem->count), "=&a" (tmp0), "=&r" (tmp1),
CC_OUT(e) (result)
: "er" (RWSEM_ACTIVE_WRITE_BIAS)
: "memory");
return result;
}
/*
* unlock after reading
*/
static inline void __up_read(struct rw_semaphore *sem)
{
long tmp;
asm volatile("# beginning __up_read\n\t"
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>
2010-01-12 17:21:09 -07:00
LOCK_PREFIX " xadd %1,(%2)\n\t"
/* subtracts 1, returns the old value */
" jns 1f\n\t"
" call call_rwsem_wake\n" /* expects old value in %edx */
"1:\n"
"# ending __up_read\n"
: "+m" (sem->count), "=d" (tmp)
: "a" (sem), "1" (-RWSEM_ACTIVE_READ_BIAS)
: "memory", "cc");
}
/*
* unlock after writing
*/
static inline void __up_write(struct rw_semaphore *sem)
{
long tmp;
asm volatile("# beginning __up_write\n\t"
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>
2010-01-12 17:21:09 -07:00
LOCK_PREFIX " xadd %1,(%2)\n\t"
/* subtracts 0xffff0001, returns the old value */
" jns 1f\n\t"
" call call_rwsem_wake\n" /* expects old value in %edx */
"1:\n\t"
"# ending __up_write\n"
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>
2010-01-12 17:21:09 -07:00
: "+m" (sem->count), "=d" (tmp)
: "a" (sem), "1" (-RWSEM_ACTIVE_WRITE_BIAS)
: "memory", "cc");
}
/*
* downgrade write lock to read lock
*/
static inline void __downgrade_write(struct rw_semaphore *sem)
{
asm volatile("# beginning __downgrade_write\n\t"
LOCK_PREFIX _ASM_ADD "%2,(%1)\n\t"
/*
* transitions 0xZZZZ0001 -> 0xYYYY0001 (i386)
* 0xZZZZZZZZ00000001 -> 0xYYYYYYYY00000001 (x86_64)
*/
" jns 1f\n\t"
" call call_rwsem_downgrade_wake\n"
"1:\n\t"
"# ending __downgrade_write\n"
: "+m" (sem->count)
: "a" (sem), "er" (-RWSEM_WAITING_BIAS)
: "memory", "cc");
}
#endif /* __KERNEL__ */
#endif /* _ASM_X86_RWSEM_H */