kernel_optimize_test/kernel/locking/rwsem.h
Waiman Long ddb20d1d3a locking/rwsem: Optimize down_read_trylock()
Modify __down_read_trylock() to optimize for an unlocked rwsem and make
it generate slightly better code.

Before this patch, down_read_trylock:

   0x0000000000000000 <+0>:     callq  0x5 <down_read_trylock+5>
   0x0000000000000005 <+5>:     jmp    0x18 <down_read_trylock+24>
   0x0000000000000007 <+7>:     lea    0x1(%rdx),%rcx
   0x000000000000000b <+11>:    mov    %rdx,%rax
   0x000000000000000e <+14>:    lock cmpxchg %rcx,(%rdi)
   0x0000000000000013 <+19>:    cmp    %rax,%rdx
   0x0000000000000016 <+22>:    je     0x23 <down_read_trylock+35>
   0x0000000000000018 <+24>:    mov    (%rdi),%rdx
   0x000000000000001b <+27>:    test   %rdx,%rdx
   0x000000000000001e <+30>:    jns    0x7 <down_read_trylock+7>
   0x0000000000000020 <+32>:    xor    %eax,%eax
   0x0000000000000022 <+34>:    retq
   0x0000000000000023 <+35>:    mov    %gs:0x0,%rax
   0x000000000000002c <+44>:    or     $0x3,%rax
   0x0000000000000030 <+48>:    mov    %rax,0x20(%rdi)
   0x0000000000000034 <+52>:    mov    $0x1,%eax
   0x0000000000000039 <+57>:    retq

After patch, down_read_trylock:

   0x0000000000000000 <+0>:	callq  0x5 <down_read_trylock+5>
   0x0000000000000005 <+5>:	xor    %eax,%eax
   0x0000000000000007 <+7>:	lea    0x1(%rax),%rdx
   0x000000000000000b <+11>:	lock cmpxchg %rdx,(%rdi)
   0x0000000000000010 <+16>:	jne    0x29 <down_read_trylock+41>
   0x0000000000000012 <+18>:	mov    %gs:0x0,%rax
   0x000000000000001b <+27>:	or     $0x3,%rax
   0x000000000000001f <+31>:	mov    %rax,0x20(%rdi)
   0x0000000000000023 <+35>:	mov    $0x1,%eax
   0x0000000000000028 <+40>:	retq
   0x0000000000000029 <+41>:	test   %rax,%rax
   0x000000000000002c <+44>:	jns    0x7 <down_read_trylock+7>
   0x000000000000002e <+46>:	xor    %eax,%eax
   0x0000000000000030 <+48>:	retq

By using a rwsem microbenchmark, the down_read_trylock() rate (with a
load of 10 to lengthen the lock critical section) on a x86-64 system
before and after the patch were:

                 Before Patch    After Patch
   # of Threads     rlock           rlock
   ------------     -----           -----
        1           14,496          14,716
        2            8,644           8,453
	4            6,799           6,983
	8            5,664           7,190

On a ARM64 system, the performance results were:

                 Before Patch    After Patch
   # of Threads     rlock           rlock
   ------------     -----           -----
        1           23,676          24,488
        2            7,697           9,502
        4            4,945           3,440
        8            2,641           1,603

For the uncontended case (1 thread), the new down_read_trylock() is a
little bit faster. For the contended cases, the new down_read_trylock()
perform pretty well in x86-64, but performance degrades at high
contention level on ARM64.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-c6x-dev@linux-c6x.org
Cc: linux-m68k@lists.linux-m68k.org
Cc: linux-riscv@lists.infradead.org
Cc: linux-um@lists.infradead.org
Cc: linux-xtensa@linux-xtensa.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: nios2-dev@lists.rocketboards.org
Cc: openrisc@lists.librecores.org
Cc: uclinux-h8-devel@lists.sourceforge.jp
Link: https://lkml.kernel.org/r/20190322143008.21313-4-longman@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-04-03 14:50:52 +02:00

265 lines
7.2 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* The least significant 2 bits of the owner value has the following
* meanings when set.
* - RWSEM_READER_OWNED (bit 0): The rwsem is owned by readers
* - RWSEM_ANONYMOUSLY_OWNED (bit 1): The rwsem is anonymously owned,
* i.e. the owner(s) cannot be readily determined. It can be reader
* owned or the owning writer is indeterminate.
*
* When a writer acquires a rwsem, it puts its task_struct pointer
* into the owner field. It is cleared after an unlock.
*
* When a reader acquires a rwsem, it will also puts its task_struct
* pointer into the owner field with both the RWSEM_READER_OWNED and
* RWSEM_ANONYMOUSLY_OWNED bits set. On unlock, the owner field will
* largely be left untouched. So for a free or reader-owned rwsem,
* the owner value may contain information about the last reader that
* acquires the rwsem. The anonymous bit is set because that particular
* reader may or may not still own the lock.
*
* That information may be helpful in debugging cases where the system
* seems to hang on a reader owned rwsem especially if only one reader
* is involved. Ideally we would like to track all the readers that own
* a rwsem, but the overhead is simply too big.
*/
#define RWSEM_READER_OWNED (1UL << 0)
#define RWSEM_ANONYMOUSLY_OWNED (1UL << 1)
#ifdef CONFIG_DEBUG_RWSEMS
# define DEBUG_RWSEMS_WARN_ON(c) DEBUG_LOCKS_WARN_ON(c)
#else
# define DEBUG_RWSEMS_WARN_ON(c)
#endif
/*
* R/W semaphores originally for PPC using the stuff in lib/rwsem.c.
* Adapted largely from include/asm-i386/rwsem.h
* by Paul Mackerras <paulus@samba.org>.
*/
/*
* the semaphore definition
*/
#ifdef CONFIG_64BIT
# define RWSEM_ACTIVE_MASK 0xffffffffL
#else
# define RWSEM_ACTIVE_MASK 0x0000ffffL
#endif
#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)
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
/*
* All writes to owner are protected by WRITE_ONCE() to make sure that
* store tearing can't happen as optimistic spinners may read and use
* the owner value concurrently without lock. Read from owner, however,
* may not need READ_ONCE() as long as the pointer value is only used
* for comparison and isn't being dereferenced.
*/
static inline void rwsem_set_owner(struct rw_semaphore *sem)
{
WRITE_ONCE(sem->owner, current);
}
static inline void rwsem_clear_owner(struct rw_semaphore *sem)
{
WRITE_ONCE(sem->owner, NULL);
}
/*
* The task_struct pointer of the last owning reader will be left in
* the owner field.
*
* Note that the owner value just indicates the task has owned the rwsem
* previously, it may not be the real owner or one of the real owners
* anymore when that field is examined, so take it with a grain of salt.
*/
static inline void __rwsem_set_reader_owned(struct rw_semaphore *sem,
struct task_struct *owner)
{
unsigned long val = (unsigned long)owner | RWSEM_READER_OWNED
| RWSEM_ANONYMOUSLY_OWNED;
WRITE_ONCE(sem->owner, (struct task_struct *)val);
}
static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
{
__rwsem_set_reader_owned(sem, current);
}
/*
* Return true if the a rwsem waiter can spin on the rwsem's owner
* and steal the lock, i.e. the lock is not anonymously owned.
* N.B. !owner is considered spinnable.
*/
static inline bool is_rwsem_owner_spinnable(struct task_struct *owner)
{
return !((unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED);
}
/*
* Return true if rwsem is owned by an anonymous writer or readers.
*/
static inline bool rwsem_has_anonymous_owner(struct task_struct *owner)
{
return (unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED;
}
#ifdef CONFIG_DEBUG_RWSEMS
/*
* With CONFIG_DEBUG_RWSEMS configured, it will make sure that if there
* is a task pointer in owner of a reader-owned rwsem, it will be the
* real owner or one of the real owners. The only exception is when the
* unlock is done by up_read_non_owner().
*/
#define rwsem_clear_reader_owned rwsem_clear_reader_owned
static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
{
unsigned long val = (unsigned long)current | RWSEM_READER_OWNED
| RWSEM_ANONYMOUSLY_OWNED;
if (READ_ONCE(sem->owner) == (struct task_struct *)val)
cmpxchg_relaxed((unsigned long *)&sem->owner, val,
RWSEM_READER_OWNED | RWSEM_ANONYMOUSLY_OWNED);
}
#endif
#else
static inline void rwsem_set_owner(struct rw_semaphore *sem)
{
}
static inline void rwsem_clear_owner(struct rw_semaphore *sem)
{
}
static inline void __rwsem_set_reader_owned(struct rw_semaphore *sem,
struct task_struct *owner)
{
}
static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
{
}
#endif
#ifndef rwsem_clear_reader_owned
static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
{
}
#endif
/*
* lock for reading
*/
static inline void __down_read(struct rw_semaphore *sem)
{
if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0))
rwsem_down_read_failed(sem);
}
static inline int __down_read_killable(struct rw_semaphore *sem)
{
if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) {
if (IS_ERR(rwsem_down_read_failed_killable(sem)))
return -EINTR;
}
return 0;
}
static inline int __down_read_trylock(struct rw_semaphore *sem)
{
/*
* Optimize for the case when the rwsem is not locked at all.
*/
long tmp = RWSEM_UNLOCKED_VALUE;
do {
if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
tmp + RWSEM_ACTIVE_READ_BIAS)) {
return 1;
}
} while (tmp >= 0);
return 0;
}
/*
* lock for writing
*/
static inline void __down_write(struct rw_semaphore *sem)
{
long tmp;
tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
&sem->count);
if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
rwsem_down_write_failed(sem);
}
static inline int __down_write_killable(struct rw_semaphore *sem)
{
long tmp;
tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
&sem->count);
if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
if (IS_ERR(rwsem_down_write_failed_killable(sem)))
return -EINTR;
return 0;
}
static inline int __down_write_trylock(struct rw_semaphore *sem)
{
long tmp;
tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
RWSEM_ACTIVE_WRITE_BIAS);
return tmp == RWSEM_UNLOCKED_VALUE;
}
/*
* unlock after reading
*/
static inline void __up_read(struct rw_semaphore *sem)
{
long tmp;
tmp = atomic_long_dec_return_release(&sem->count);
if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
rwsem_wake(sem);
}
/*
* unlock after writing
*/
static inline void __up_write(struct rw_semaphore *sem)
{
if (unlikely(atomic_long_sub_return_release(RWSEM_ACTIVE_WRITE_BIAS,
&sem->count) < 0))
rwsem_wake(sem);
}
/*
* downgrade write lock to read lock
*/
static inline void __downgrade_write(struct rw_semaphore *sem)
{
long tmp;
/*
* When downgrading from exclusive to shared ownership,
* anything inside the write-locked region cannot leak
* into the read side. In contrast, anything in the
* read-locked region is ok to be re-ordered into the
* write side. As such, rely on RELEASE semantics.
*/
tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, &sem->count);
if (tmp < 0)
rwsem_downgrade_wake(sem);
}