2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-21 11:44:01 +08:00
linux-next/lib/lockref.c

189 lines
3.9 KiB
C
Raw Normal View History

#include <linux/export.h>
#include <linux/lockref.h>
#if USE_CMPXCHG_LOCKREF
lockref: implement lockless reference count updates using cmpxchg() Instead of taking the spinlock, the lockless versions atomically check that the lock is not taken, and do the reference count update using a cmpxchg() loop. This is semantically identical to doing the reference count update protected by the lock, but avoids the "wait for lock" contention that you get when accesses to the reference count are contended. Note that a "lockref" is absolutely _not_ equivalent to an atomic_t. Even when the lockref reference counts are updated atomically with cmpxchg, the fact that they also verify the state of the spinlock means that the lockless updates can never happen while somebody else holds the spinlock. So while "lockref_put_or_lock()" looks a lot like just another name for "atomic_dec_and_lock()", and both optimize to lockless updates, they are fundamentally different: the decrement done by atomic_dec_and_lock() is truly independent of any lock (as long as it doesn't decrement to zero), so a locked region can still see the count change. The lockref structure, in contrast, really is a *locked* reference count. If you hold the spinlock, the reference count will be stable and you can modify the reference count without using atomics, because even the lockless updates will see and respect the state of the lock. In order to enable the cmpxchg lockless code, the architecture needs to do three things: (1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit in an aligned u64, and have a "cmpxchg()" implementation that works on such a u64 data type. (2) define a helper function to test for a spinlock being unlocked ("arch_spin_value_unlocked()") (3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its Kconfig file. This enables it for x86-64 (but not 32-bit, we'd need to make sure cmpxchg() turns into the proper cmpxchg8b in order to enable it for 32-bit mode). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-03 03:12:15 +08:00
/*
* Note that the "cmpxchg()" reloads the "old" value for the
* failure case.
*/
#define CMPXCHG_LOOP(CODE, SUCCESS) do { \
struct lockref old; \
BUILD_BUG_ON(sizeof(old) != 8); \
old.lock_count = READ_ONCE(lockref->lock_count); \
lockref: implement lockless reference count updates using cmpxchg() Instead of taking the spinlock, the lockless versions atomically check that the lock is not taken, and do the reference count update using a cmpxchg() loop. This is semantically identical to doing the reference count update protected by the lock, but avoids the "wait for lock" contention that you get when accesses to the reference count are contended. Note that a "lockref" is absolutely _not_ equivalent to an atomic_t. Even when the lockref reference counts are updated atomically with cmpxchg, the fact that they also verify the state of the spinlock means that the lockless updates can never happen while somebody else holds the spinlock. So while "lockref_put_or_lock()" looks a lot like just another name for "atomic_dec_and_lock()", and both optimize to lockless updates, they are fundamentally different: the decrement done by atomic_dec_and_lock() is truly independent of any lock (as long as it doesn't decrement to zero), so a locked region can still see the count change. The lockref structure, in contrast, really is a *locked* reference count. If you hold the spinlock, the reference count will be stable and you can modify the reference count without using atomics, because even the lockless updates will see and respect the state of the lock. In order to enable the cmpxchg lockless code, the architecture needs to do three things: (1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit in an aligned u64, and have a "cmpxchg()" implementation that works on such a u64 data type. (2) define a helper function to test for a spinlock being unlocked ("arch_spin_value_unlocked()") (3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its Kconfig file. This enables it for x86-64 (but not 32-bit, we'd need to make sure cmpxchg() turns into the proper cmpxchg8b in order to enable it for 32-bit mode). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-03 03:12:15 +08:00
while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) { \
struct lockref new = old, prev = old; \
CODE \
old.lock_count = cmpxchg64_relaxed(&lockref->lock_count, \
old.lock_count, \
new.lock_count); \
lockref: implement lockless reference count updates using cmpxchg() Instead of taking the spinlock, the lockless versions atomically check that the lock is not taken, and do the reference count update using a cmpxchg() loop. This is semantically identical to doing the reference count update protected by the lock, but avoids the "wait for lock" contention that you get when accesses to the reference count are contended. Note that a "lockref" is absolutely _not_ equivalent to an atomic_t. Even when the lockref reference counts are updated atomically with cmpxchg, the fact that they also verify the state of the spinlock means that the lockless updates can never happen while somebody else holds the spinlock. So while "lockref_put_or_lock()" looks a lot like just another name for "atomic_dec_and_lock()", and both optimize to lockless updates, they are fundamentally different: the decrement done by atomic_dec_and_lock() is truly independent of any lock (as long as it doesn't decrement to zero), so a locked region can still see the count change. The lockref structure, in contrast, really is a *locked* reference count. If you hold the spinlock, the reference count will be stable and you can modify the reference count without using atomics, because even the lockless updates will see and respect the state of the lock. In order to enable the cmpxchg lockless code, the architecture needs to do three things: (1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit in an aligned u64, and have a "cmpxchg()" implementation that works on such a u64 data type. (2) define a helper function to test for a spinlock being unlocked ("arch_spin_value_unlocked()") (3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its Kconfig file. This enables it for x86-64 (but not 32-bit, we'd need to make sure cmpxchg() turns into the proper cmpxchg8b in order to enable it for 32-bit mode). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-03 03:12:15 +08:00
if (likely(old.lock_count == prev.lock_count)) { \
SUCCESS; \
} \
arch, locking: Ciao arch_mutex_cpu_relax() The arch_mutex_cpu_relax() function, introduced by 34b133f, is hacky and ugly. It was added a few years ago to address the fact that common cpu_relax() calls include yielding on s390, and thus impact the optimistic spinning functionality of mutexes. Nowadays we use this function well beyond mutexes: rwsem, qrwlock, mcs and lockref. Since the macro that defines the call is in the mutex header, any users must include mutex.h and the naming is misleading as well. This patch (i) renames the call to cpu_relax_lowlatency ("relax, but only if you can do it with very low latency") and (ii) defines it in each arch's asm/processor.h local header, just like for regular cpu_relax functions. On all archs, except s390, cpu_relax_lowlatency is simply cpu_relax, and thus we can take it out of mutex.h. While this can seem redundant, I believe it is a good choice as it allows us to move out arch specific logic from generic locking primitives and enables future(?) archs to transparently define it, similarly to System Z. Signed-off-by: Davidlohr Bueso <davidlohr@hp.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Anton Blanchard <anton@samba.org> Cc: Aurelien Jacquiot <a-jacquiot@ti.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Bharat Bhushan <r65777@freescale.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chen Liqin <liqin.linux@gmail.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: David Howells <dhowells@redhat.com> Cc: David S. Miller <davem@davemloft.net> Cc: Deepthi Dharwar <deepthi@linux.vnet.ibm.com> Cc: Dominik Dingel <dingel@linux.vnet.ibm.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: Haavard Skinnemoen <hskinnemoen@gmail.com> Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: James Hogan <james.hogan@imgtec.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Joe Perches <joe@perches.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Joseph Myers <joseph@codesourcery.com> Cc: Kees Cook <keescook@chromium.org> Cc: Koichi Yasutake <yasutake.koichi@jp.panasonic.com> Cc: Lennox Wu <lennox.wu@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Salter <msalter@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Neuling <mikey@neuling.org> Cc: Michal Simek <monstr@monstr.eu> Cc: Mikael Starvik <starvik@axis.com> Cc: Nicolas Pitre <nico@linaro.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Qais Yousef <qais.yousef@imgtec.com> Cc: Qiaowei Ren <qiaowei.ren@intel.com> Cc: Rafael Wysocki <rafael.j.wysocki@intel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Steven Miao <realmz6@gmail.com> Cc: Steven Rostedt <srostedt@redhat.com> Cc: Stratos Karafotis <stratosk@semaphore.gr> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Vasily Kulikov <segoon@openwall.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Vineet Gupta <Vineet.Gupta1@synopsys.com> Cc: Waiman Long <Waiman.Long@hp.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Wolfram Sang <wsa@the-dreams.de> Cc: adi-buildroot-devel@lists.sourceforge.net Cc: linux390@de.ibm.com Cc: linux-alpha@vger.kernel.org Cc: linux-am33-list@redhat.com Cc: linux-arm-kernel@lists.infradead.org Cc: linux-c6x-dev@linux-c6x.org Cc: linux-cris-kernel@axis.com Cc: linux-hexagon@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux@lists.openrisc.net Cc: linux-m32r-ja@ml.linux-m32r.org Cc: linux-m32r@ml.linux-m32r.org Cc: linux-m68k@lists.linux-m68k.org Cc: linux-metag@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: linux-xtensa@linux-xtensa.org Cc: sparclinux@vger.kernel.org Link: http://lkml.kernel.org/r/1404079773.2619.4.camel@buesod1.americas.hpqcorp.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-30 06:09:33 +08:00
cpu_relax_lowlatency(); \
lockref: implement lockless reference count updates using cmpxchg() Instead of taking the spinlock, the lockless versions atomically check that the lock is not taken, and do the reference count update using a cmpxchg() loop. This is semantically identical to doing the reference count update protected by the lock, but avoids the "wait for lock" contention that you get when accesses to the reference count are contended. Note that a "lockref" is absolutely _not_ equivalent to an atomic_t. Even when the lockref reference counts are updated atomically with cmpxchg, the fact that they also verify the state of the spinlock means that the lockless updates can never happen while somebody else holds the spinlock. So while "lockref_put_or_lock()" looks a lot like just another name for "atomic_dec_and_lock()", and both optimize to lockless updates, they are fundamentally different: the decrement done by atomic_dec_and_lock() is truly independent of any lock (as long as it doesn't decrement to zero), so a locked region can still see the count change. The lockref structure, in contrast, really is a *locked* reference count. If you hold the spinlock, the reference count will be stable and you can modify the reference count without using atomics, because even the lockless updates will see and respect the state of the lock. In order to enable the cmpxchg lockless code, the architecture needs to do three things: (1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit in an aligned u64, and have a "cmpxchg()" implementation that works on such a u64 data type. (2) define a helper function to test for a spinlock being unlocked ("arch_spin_value_unlocked()") (3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its Kconfig file. This enables it for x86-64 (but not 32-bit, we'd need to make sure cmpxchg() turns into the proper cmpxchg8b in order to enable it for 32-bit mode). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-03 03:12:15 +08:00
} \
} while (0)
#else
#define CMPXCHG_LOOP(CODE, SUCCESS) do { } while (0)
#endif
/**
* lockref_get - Increments reference count unconditionally
* @lockref: pointer to lockref structure
*
* This operation is only valid if you already hold a reference
* to the object, so you know the count cannot be zero.
*/
void lockref_get(struct lockref *lockref)
{
lockref: implement lockless reference count updates using cmpxchg() Instead of taking the spinlock, the lockless versions atomically check that the lock is not taken, and do the reference count update using a cmpxchg() loop. This is semantically identical to doing the reference count update protected by the lock, but avoids the "wait for lock" contention that you get when accesses to the reference count are contended. Note that a "lockref" is absolutely _not_ equivalent to an atomic_t. Even when the lockref reference counts are updated atomically with cmpxchg, the fact that they also verify the state of the spinlock means that the lockless updates can never happen while somebody else holds the spinlock. So while "lockref_put_or_lock()" looks a lot like just another name for "atomic_dec_and_lock()", and both optimize to lockless updates, they are fundamentally different: the decrement done by atomic_dec_and_lock() is truly independent of any lock (as long as it doesn't decrement to zero), so a locked region can still see the count change. The lockref structure, in contrast, really is a *locked* reference count. If you hold the spinlock, the reference count will be stable and you can modify the reference count without using atomics, because even the lockless updates will see and respect the state of the lock. In order to enable the cmpxchg lockless code, the architecture needs to do three things: (1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit in an aligned u64, and have a "cmpxchg()" implementation that works on such a u64 data type. (2) define a helper function to test for a spinlock being unlocked ("arch_spin_value_unlocked()") (3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its Kconfig file. This enables it for x86-64 (but not 32-bit, we'd need to make sure cmpxchg() turns into the proper cmpxchg8b in order to enable it for 32-bit mode). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-03 03:12:15 +08:00
CMPXCHG_LOOP(
new.count++;
,
return;
);
spin_lock(&lockref->lock);
lockref->count++;
spin_unlock(&lockref->lock);
}
EXPORT_SYMBOL(lockref_get);
/**
* lockref_get_not_zero - Increments count unless the count is 0 or dead
* @lockref: pointer to lockref structure
* Return: 1 if count updated successfully or 0 if count was zero
*/
int lockref_get_not_zero(struct lockref *lockref)
{
lockref: implement lockless reference count updates using cmpxchg() Instead of taking the spinlock, the lockless versions atomically check that the lock is not taken, and do the reference count update using a cmpxchg() loop. This is semantically identical to doing the reference count update protected by the lock, but avoids the "wait for lock" contention that you get when accesses to the reference count are contended. Note that a "lockref" is absolutely _not_ equivalent to an atomic_t. Even when the lockref reference counts are updated atomically with cmpxchg, the fact that they also verify the state of the spinlock means that the lockless updates can never happen while somebody else holds the spinlock. So while "lockref_put_or_lock()" looks a lot like just another name for "atomic_dec_and_lock()", and both optimize to lockless updates, they are fundamentally different: the decrement done by atomic_dec_and_lock() is truly independent of any lock (as long as it doesn't decrement to zero), so a locked region can still see the count change. The lockref structure, in contrast, really is a *locked* reference count. If you hold the spinlock, the reference count will be stable and you can modify the reference count without using atomics, because even the lockless updates will see and respect the state of the lock. In order to enable the cmpxchg lockless code, the architecture needs to do three things: (1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit in an aligned u64, and have a "cmpxchg()" implementation that works on such a u64 data type. (2) define a helper function to test for a spinlock being unlocked ("arch_spin_value_unlocked()") (3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its Kconfig file. This enables it for x86-64 (but not 32-bit, we'd need to make sure cmpxchg() turns into the proper cmpxchg8b in order to enable it for 32-bit mode). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-03 03:12:15 +08:00
int retval;
CMPXCHG_LOOP(
new.count++;
if (old.count <= 0)
lockref: implement lockless reference count updates using cmpxchg() Instead of taking the spinlock, the lockless versions atomically check that the lock is not taken, and do the reference count update using a cmpxchg() loop. This is semantically identical to doing the reference count update protected by the lock, but avoids the "wait for lock" contention that you get when accesses to the reference count are contended. Note that a "lockref" is absolutely _not_ equivalent to an atomic_t. Even when the lockref reference counts are updated atomically with cmpxchg, the fact that they also verify the state of the spinlock means that the lockless updates can never happen while somebody else holds the spinlock. So while "lockref_put_or_lock()" looks a lot like just another name for "atomic_dec_and_lock()", and both optimize to lockless updates, they are fundamentally different: the decrement done by atomic_dec_and_lock() is truly independent of any lock (as long as it doesn't decrement to zero), so a locked region can still see the count change. The lockref structure, in contrast, really is a *locked* reference count. If you hold the spinlock, the reference count will be stable and you can modify the reference count without using atomics, because even the lockless updates will see and respect the state of the lock. In order to enable the cmpxchg lockless code, the architecture needs to do three things: (1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit in an aligned u64, and have a "cmpxchg()" implementation that works on such a u64 data type. (2) define a helper function to test for a spinlock being unlocked ("arch_spin_value_unlocked()") (3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its Kconfig file. This enables it for x86-64 (but not 32-bit, we'd need to make sure cmpxchg() turns into the proper cmpxchg8b in order to enable it for 32-bit mode). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-03 03:12:15 +08:00
return 0;
,
return 1;
);
spin_lock(&lockref->lock);
lockref: implement lockless reference count updates using cmpxchg() Instead of taking the spinlock, the lockless versions atomically check that the lock is not taken, and do the reference count update using a cmpxchg() loop. This is semantically identical to doing the reference count update protected by the lock, but avoids the "wait for lock" contention that you get when accesses to the reference count are contended. Note that a "lockref" is absolutely _not_ equivalent to an atomic_t. Even when the lockref reference counts are updated atomically with cmpxchg, the fact that they also verify the state of the spinlock means that the lockless updates can never happen while somebody else holds the spinlock. So while "lockref_put_or_lock()" looks a lot like just another name for "atomic_dec_and_lock()", and both optimize to lockless updates, they are fundamentally different: the decrement done by atomic_dec_and_lock() is truly independent of any lock (as long as it doesn't decrement to zero), so a locked region can still see the count change. The lockref structure, in contrast, really is a *locked* reference count. If you hold the spinlock, the reference count will be stable and you can modify the reference count without using atomics, because even the lockless updates will see and respect the state of the lock. In order to enable the cmpxchg lockless code, the architecture needs to do three things: (1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit in an aligned u64, and have a "cmpxchg()" implementation that works on such a u64 data type. (2) define a helper function to test for a spinlock being unlocked ("arch_spin_value_unlocked()") (3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its Kconfig file. This enables it for x86-64 (but not 32-bit, we'd need to make sure cmpxchg() turns into the proper cmpxchg8b in order to enable it for 32-bit mode). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-03 03:12:15 +08:00
retval = 0;
if (lockref->count > 0) {
lockref->count++;
retval = 1;
}
spin_unlock(&lockref->lock);
return retval;
}
EXPORT_SYMBOL(lockref_get_not_zero);
/**
* lockref_get_or_lock - Increments count unless the count is 0 or dead
* @lockref: pointer to lockref structure
* Return: 1 if count updated successfully or 0 if count was zero
* and we got the lock instead.
*/
int lockref_get_or_lock(struct lockref *lockref)
{
lockref: implement lockless reference count updates using cmpxchg() Instead of taking the spinlock, the lockless versions atomically check that the lock is not taken, and do the reference count update using a cmpxchg() loop. This is semantically identical to doing the reference count update protected by the lock, but avoids the "wait for lock" contention that you get when accesses to the reference count are contended. Note that a "lockref" is absolutely _not_ equivalent to an atomic_t. Even when the lockref reference counts are updated atomically with cmpxchg, the fact that they also verify the state of the spinlock means that the lockless updates can never happen while somebody else holds the spinlock. So while "lockref_put_or_lock()" looks a lot like just another name for "atomic_dec_and_lock()", and both optimize to lockless updates, they are fundamentally different: the decrement done by atomic_dec_and_lock() is truly independent of any lock (as long as it doesn't decrement to zero), so a locked region can still see the count change. The lockref structure, in contrast, really is a *locked* reference count. If you hold the spinlock, the reference count will be stable and you can modify the reference count without using atomics, because even the lockless updates will see and respect the state of the lock. In order to enable the cmpxchg lockless code, the architecture needs to do three things: (1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit in an aligned u64, and have a "cmpxchg()" implementation that works on such a u64 data type. (2) define a helper function to test for a spinlock being unlocked ("arch_spin_value_unlocked()") (3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its Kconfig file. This enables it for x86-64 (but not 32-bit, we'd need to make sure cmpxchg() turns into the proper cmpxchg8b in order to enable it for 32-bit mode). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-03 03:12:15 +08:00
CMPXCHG_LOOP(
new.count++;
if (old.count <= 0)
lockref: implement lockless reference count updates using cmpxchg() Instead of taking the spinlock, the lockless versions atomically check that the lock is not taken, and do the reference count update using a cmpxchg() loop. This is semantically identical to doing the reference count update protected by the lock, but avoids the "wait for lock" contention that you get when accesses to the reference count are contended. Note that a "lockref" is absolutely _not_ equivalent to an atomic_t. Even when the lockref reference counts are updated atomically with cmpxchg, the fact that they also verify the state of the spinlock means that the lockless updates can never happen while somebody else holds the spinlock. So while "lockref_put_or_lock()" looks a lot like just another name for "atomic_dec_and_lock()", and both optimize to lockless updates, they are fundamentally different: the decrement done by atomic_dec_and_lock() is truly independent of any lock (as long as it doesn't decrement to zero), so a locked region can still see the count change. The lockref structure, in contrast, really is a *locked* reference count. If you hold the spinlock, the reference count will be stable and you can modify the reference count without using atomics, because even the lockless updates will see and respect the state of the lock. In order to enable the cmpxchg lockless code, the architecture needs to do three things: (1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit in an aligned u64, and have a "cmpxchg()" implementation that works on such a u64 data type. (2) define a helper function to test for a spinlock being unlocked ("arch_spin_value_unlocked()") (3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its Kconfig file. This enables it for x86-64 (but not 32-bit, we'd need to make sure cmpxchg() turns into the proper cmpxchg8b in order to enable it for 32-bit mode). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-03 03:12:15 +08:00
break;
,
return 1;
);
spin_lock(&lockref->lock);
if (lockref->count <= 0)
return 0;
lockref->count++;
spin_unlock(&lockref->lock);
return 1;
}
EXPORT_SYMBOL(lockref_get_or_lock);
/**
* lockref_put_return - Decrement reference count if possible
* @lockref: pointer to lockref structure
*
* Decrement the reference count and return the new value.
* If the lockref was dead or locked, return an error.
*/
int lockref_put_return(struct lockref *lockref)
{
CMPXCHG_LOOP(
new.count--;
if (old.count <= 0)
return -1;
,
return new.count;
);
return -1;
}
EXPORT_SYMBOL(lockref_put_return);
/**
* lockref_put_or_lock - decrements count unless count <= 1 before decrement
* @lockref: pointer to lockref structure
* Return: 1 if count updated successfully or 0 if count <= 1 and lock taken
*/
int lockref_put_or_lock(struct lockref *lockref)
{
lockref: implement lockless reference count updates using cmpxchg() Instead of taking the spinlock, the lockless versions atomically check that the lock is not taken, and do the reference count update using a cmpxchg() loop. This is semantically identical to doing the reference count update protected by the lock, but avoids the "wait for lock" contention that you get when accesses to the reference count are contended. Note that a "lockref" is absolutely _not_ equivalent to an atomic_t. Even when the lockref reference counts are updated atomically with cmpxchg, the fact that they also verify the state of the spinlock means that the lockless updates can never happen while somebody else holds the spinlock. So while "lockref_put_or_lock()" looks a lot like just another name for "atomic_dec_and_lock()", and both optimize to lockless updates, they are fundamentally different: the decrement done by atomic_dec_and_lock() is truly independent of any lock (as long as it doesn't decrement to zero), so a locked region can still see the count change. The lockref structure, in contrast, really is a *locked* reference count. If you hold the spinlock, the reference count will be stable and you can modify the reference count without using atomics, because even the lockless updates will see and respect the state of the lock. In order to enable the cmpxchg lockless code, the architecture needs to do three things: (1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit in an aligned u64, and have a "cmpxchg()" implementation that works on such a u64 data type. (2) define a helper function to test for a spinlock being unlocked ("arch_spin_value_unlocked()") (3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its Kconfig file. This enables it for x86-64 (but not 32-bit, we'd need to make sure cmpxchg() turns into the proper cmpxchg8b in order to enable it for 32-bit mode). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-03 03:12:15 +08:00
CMPXCHG_LOOP(
new.count--;
if (old.count <= 1)
break;
,
return 1;
);
spin_lock(&lockref->lock);
if (lockref->count <= 1)
return 0;
lockref->count--;
spin_unlock(&lockref->lock);
return 1;
}
EXPORT_SYMBOL(lockref_put_or_lock);
2013-09-08 06:49:18 +08:00
/**
* lockref_mark_dead - mark lockref dead
* @lockref: pointer to lockref structure
*/
void lockref_mark_dead(struct lockref *lockref)
{
assert_spin_locked(&lockref->lock);
lockref->count = -128;
}
EXPORT_SYMBOL(lockref_mark_dead);
2013-09-08 06:49:18 +08:00
/**
* lockref_get_not_dead - Increments count unless the ref is dead
* @lockref: pointer to lockref structure
* Return: 1 if count updated successfully or 0 if lockref was dead
*/
int lockref_get_not_dead(struct lockref *lockref)
{
int retval;
CMPXCHG_LOOP(
new.count++;
if (old.count < 0)
2013-09-08 06:49:18 +08:00
return 0;
,
return 1;
);
spin_lock(&lockref->lock);
retval = 0;
if (lockref->count >= 0) {
2013-09-08 06:49:18 +08:00
lockref->count++;
retval = 1;
}
spin_unlock(&lockref->lock);
return retval;
}
EXPORT_SYMBOL(lockref_get_not_dead);