mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-02 05:16:47 +07:00
0d1622d7f5
The Intel Architecture Optimization Reference Manual states that a short load that follows a long store to the same object will suffer a store forwading penalty, particularly if the two accesses use different addresses. Trivially, a long load that follows a short store will also suffer a penalty. __downgrade_write() in rwsem incurs both penalties: the increment operation will not be able to reuse a recently-loaded rwsem value, and its result will not be reused by any recently-following rwsem operation. A comment in the code states that this is because 64-bit immediates are special and expensive; but while they are slightly special (only a single instruction allows them), they aren't expensive: a test shows that two loops, one loading a 32-bit immediate and one loading a 64-bit immediate, both take 1.5 cycles per iteration. Fix this by changing __downgrade_write to use the same add instruction on i386 and on x86_64, so that it uses the same operand size as all the other rwsem functions. Signed-off-by: Avi Kivity <avi@redhat.com> LKML-Reference: <1266049992-17419-1-git-send-email-avi@redhat.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
283 lines
7.5 KiB
C
283 lines
7.5 KiB
C
/* 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 consequtive 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 <linux/list.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/lockdep.h>
|
|
#include <asm/asm.h>
|
|
|
|
struct rwsem_waiter;
|
|
|
|
extern asmregparm struct rw_semaphore *
|
|
rwsem_down_read_failed(struct rw_semaphore *sem);
|
|
extern asmregparm struct rw_semaphore *
|
|
rwsem_down_write_failed(struct rw_semaphore *sem);
|
|
extern asmregparm struct rw_semaphore *
|
|
rwsem_wake(struct rw_semaphore *);
|
|
extern asmregparm struct rw_semaphore *
|
|
rwsem_downgrade_wake(struct rw_semaphore *sem);
|
|
|
|
/*
|
|
* the semaphore definition
|
|
*
|
|
* 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)
|
|
|
|
typedef signed long rwsem_count_t;
|
|
|
|
struct rw_semaphore {
|
|
rwsem_count_t count;
|
|
spinlock_t wait_lock;
|
|
struct list_head wait_list;
|
|
#ifdef CONFIG_DEBUG_LOCK_ALLOC
|
|
struct lockdep_map dep_map;
|
|
#endif
|
|
};
|
|
|
|
#ifdef CONFIG_DEBUG_LOCK_ALLOC
|
|
# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
|
|
#else
|
|
# define __RWSEM_DEP_MAP_INIT(lockname)
|
|
#endif
|
|
|
|
|
|
#define __RWSEM_INITIALIZER(name) \
|
|
{ \
|
|
RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
|
|
LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) \
|
|
}
|
|
|
|
#define DECLARE_RWSEM(name) \
|
|
struct rw_semaphore name = __RWSEM_INITIALIZER(name)
|
|
|
|
extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
|
|
struct lock_class_key *key);
|
|
|
|
#define init_rwsem(sem) \
|
|
do { \
|
|
static struct lock_class_key __key; \
|
|
\
|
|
__init_rwsem((sem), #sem, &__key); \
|
|
} while (0)
|
|
|
|
/*
|
|
* 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, returns the old value */
|
|
" 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 int __down_read_trylock(struct rw_semaphore *sem)
|
|
{
|
|
rwsem_count_t result, tmp;
|
|
asm volatile("# beginning __down_read_trylock\n\t"
|
|
" mov %0,%1\n\t"
|
|
"1:\n\t"
|
|
" mov %1,%2\n\t"
|
|
" add %3,%2\n\t"
|
|
" jle 2f\n\t"
|
|
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 ? 1 : 0;
|
|
}
|
|
|
|
/*
|
|
* lock for writing
|
|
*/
|
|
static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
|
|
{
|
|
rwsem_count_t tmp;
|
|
|
|
tmp = RWSEM_ACTIVE_WRITE_BIAS;
|
|
asm volatile("# beginning down_write\n\t"
|
|
LOCK_PREFIX " xadd %1,(%2)\n\t"
|
|
/* subtract 0x0000ffff, returns the old value */
|
|
" test %1,%1\n\t"
|
|
/* was the count 0 before? */
|
|
" jz 1f\n"
|
|
" call call_rwsem_down_write_failed\n"
|
|
"1:\n"
|
|
"# ending down_write"
|
|
: "+m" (sem->count), "=d" (tmp)
|
|
: "a" (sem), "1" (tmp)
|
|
: "memory", "cc");
|
|
}
|
|
|
|
static inline void __down_write(struct rw_semaphore *sem)
|
|
{
|
|
__down_write_nested(sem, 0);
|
|
}
|
|
|
|
/*
|
|
* trylock for writing -- returns 1 if successful, 0 if contention
|
|
*/
|
|
static inline int __down_write_trylock(struct rw_semaphore *sem)
|
|
{
|
|
rwsem_count_t ret = cmpxchg(&sem->count,
|
|
RWSEM_UNLOCKED_VALUE,
|
|
RWSEM_ACTIVE_WRITE_BIAS);
|
|
if (ret == RWSEM_UNLOCKED_VALUE)
|
|
return 1;
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* unlock after reading
|
|
*/
|
|
static inline void __up_read(struct rw_semaphore *sem)
|
|
{
|
|
rwsem_count_t tmp = -RWSEM_ACTIVE_READ_BIAS;
|
|
asm volatile("# beginning __up_read\n\t"
|
|
LOCK_PREFIX " xadd %1,(%2)\n\t"
|
|
/* subtracts 1, returns the old value */
|
|
" jns 1f\n\t"
|
|
" call call_rwsem_wake\n"
|
|
"1:\n"
|
|
"# ending __up_read\n"
|
|
: "+m" (sem->count), "=d" (tmp)
|
|
: "a" (sem), "1" (tmp)
|
|
: "memory", "cc");
|
|
}
|
|
|
|
/*
|
|
* unlock after writing
|
|
*/
|
|
static inline void __up_write(struct rw_semaphore *sem)
|
|
{
|
|
rwsem_count_t tmp;
|
|
asm volatile("# beginning __up_write\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), "=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");
|
|
}
|
|
|
|
/*
|
|
* implement atomic add functionality
|
|
*/
|
|
static inline void rwsem_atomic_add(rwsem_count_t delta,
|
|
struct rw_semaphore *sem)
|
|
{
|
|
asm volatile(LOCK_PREFIX _ASM_ADD "%1,%0"
|
|
: "+m" (sem->count)
|
|
: "er" (delta));
|
|
}
|
|
|
|
/*
|
|
* implement exchange and add functionality
|
|
*/
|
|
static inline rwsem_count_t rwsem_atomic_update(rwsem_count_t delta,
|
|
struct rw_semaphore *sem)
|
|
{
|
|
rwsem_count_t tmp = delta;
|
|
|
|
asm volatile(LOCK_PREFIX "xadd %0,%1"
|
|
: "+r" (tmp), "+m" (sem->count)
|
|
: : "memory");
|
|
|
|
return tmp + delta;
|
|
}
|
|
|
|
static inline int rwsem_is_locked(struct rw_semaphore *sem)
|
|
{
|
|
return (sem->count != 0);
|
|
}
|
|
|
|
#endif /* __KERNEL__ */
|
|
#endif /* _ASM_X86_RWSEM_H */
|