zfs/module/spl/spl-rwlock.c

121 lines
3.7 KiB
C
Raw Normal View History

/*****************************************************************************\
* Copyright (C) 2007-2010 Lawrence Livermore National Security, LLC.
* Copyright (C) 2007 The Regents of the University of California.
* Produced at Lawrence Livermore National Laboratory (cf, DISCLAIMER).
* Written by Brian Behlendorf <behlendorf1@llnl.gov>.
* UCRL-CODE-235197
*
* This file is part of the SPL, Solaris Porting Layer.
* For details, see <http://zfsonlinux.org/>.
*
* The SPL is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
* Free Software Foundation; either version 2 of the License, or (at your
* option) any later version.
*
* The SPL is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* for more details.
*
* You should have received a copy of the GNU General Public License along
* with the SPL. If not, see <http://www.gnu.org/licenses/>.
*****************************************************************************
* Solaris Porting Layer (SPL) Reader/Writer Lock Implementation.
\*****************************************************************************/
#include <sys/rwlock.h>
#ifdef DEBUG_SUBSYSTEM
#undef DEBUG_SUBSYSTEM
#endif
#define DEBUG_SUBSYSTEM S_RWLOCK
#if defined(CONFIG_PREEMPT_RT_FULL)
#include <linux/rtmutex.h>
#define RT_MUTEX_OWNER_MASKALL 1UL
static int
__rwsem_tryupgrade(struct rw_semaphore *rwsem)
{
ASSERT((struct task_struct *)
((unsigned long)rwsem->lock.owner & ~RT_MUTEX_OWNER_MASKALL) ==
current);
/*
* Under the realtime patch series, rwsem is implemented as a
* single mutex held by readers and writers alike. However,
* this implementation would prevent a thread from taking a
* read lock twice, as the mutex would already be locked on
* the second attempt. Therefore the implementation allows a
* single thread to take a rwsem as read lock multiple times
* tracking that nesting as read_depth counter.
*/
if (rwsem->read_depth <= 1) {
/*
* In case, the current thread has not taken the lock
* more than once as read lock, we can allow an
* upgrade to a write lock. rwsem_rt.h implements
* write locks as read_depth == 0.
*/
rwsem->read_depth = 0;
return (1);
}
return (0);
}
#elif defined(CONFIG_RWSEM_GENERIC_SPINLOCK)
static int
__rwsem_tryupgrade(struct rw_semaphore *rwsem)
{
int ret = 0;
unsigned long flags;
spl_rwsem_lock_irqsave(&rwsem->wait_lock, flags);
if (RWSEM_COUNT(rwsem) == SPL_RWSEM_SINGLE_READER_VALUE &&
list_empty(&rwsem->wait_list)) {
ret = 1;
RWSEM_COUNT(rwsem) = SPL_RWSEM_SINGLE_WRITER_VALUE;
}
spl_rwsem_unlock_irqrestore(&rwsem->wait_lock, flags);
return (ret);
}
#elif defined(HAVE_RWSEM_ATOMIC_LONG_COUNT)
static int
__rwsem_tryupgrade(struct rw_semaphore *rwsem)
{
long val;
val = atomic_long_cmpxchg(&rwsem->count, SPL_RWSEM_SINGLE_READER_VALUE,
SPL_RWSEM_SINGLE_WRITER_VALUE);
return (val == SPL_RWSEM_SINGLE_READER_VALUE);
}
#else
static int
__rwsem_tryupgrade(struct rw_semaphore *rwsem)
{
typeof (rwsem->count) val;
val = cmpxchg(&rwsem->count, SPL_RWSEM_SINGLE_READER_VALUE,
SPL_RWSEM_SINGLE_WRITER_VALUE);
return (val == SPL_RWSEM_SINGLE_READER_VALUE);
}
#endif
int
rwsem_tryupgrade(struct rw_semaphore *rwsem)
{
if (__rwsem_tryupgrade(rwsem)) {
rwsem_release(&rwsem->dep_map, 1, _RET_IP_);
rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_);
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
rwsem->owner = current;
#endif
return (1);
}
return (0);
}
EXPORT_SYMBOL(rwsem_tryupgrade);
Update rwlocks to track owner to ensure correct semantics The behavior of RW_*_HELD was updated because it was not quite right. It is not sufficient to return non-zero when the lock is help, we must only do this when the current task in the holder. This means we need to track the lock owner which is not something tracked in a Linux semaphore. After some experimentation the solution I settled on was to embed the Linux semaphore at the start of a larger krwlock_t structure which includes the owner field. This maintains good performance and allows us to cleanly intergrate with the kernel lock analysis tools. My reasons: 1) By placing the Linux semaphore at the start of krwlock_t we can then simply cast krwlock_t to a rw_semaphore and pass that on to the linux kernel. This allows us to use '#defines so the preprocessor can do direct replacement of the Solaris primative with the linux equivilant. This is important because it then maintains the location information for each rw_* call point. 2) Additionally, by adding the owner to krwlock_t we can keep this needed extra information adjacent to the lock itself. This removes the need for a fancy lookup to get the owner which is optimal for performance. We can also leverage the existing spin lock in the semaphore to ensure owner is updated correctly. 3) All helper functions which do not need to strictly be implemented as a define to preserve location information can be done as a static inline function. 4) Adding the owner to krwlock_t allows us to remove all memory allocations done during lock initialization. This is good for all the obvious reasons, we do give up the ability to specific the lock name. The Linux profiling tools will stringify the lock name used in the code via the preprocessor and use that. Update rwlocks validated on: - SLES10 (ppc64) - SLES11 (x86_64) - CHAOS4.2 (x86_64) - RHEL5.3 (x86_64) - RHEL6 (x86_64) - FC11 (x86_64)
2009-09-25 21:14:35 +00:00
int spl_rw_init(void) { return 0; }
void spl_rw_fini(void) { }