From 3ba1d59d6e3bd0fe7694c8f7962723656c6bd18e Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Tue, 21 Jan 2014 15:36:22 -0800 Subject: locking/mcs: Allow architecture specific asm files to be used for contended case This patch allows each architecture to add its specific assembly optimized arch_mcs_spin_lock_contended and arch_mcs_spinlock_uncontended for MCS lock and unlock functions. Signed-off-by: Tim Chen Cc: Scott J Norton Cc: Raghavendra K T Cc: AswinChandramouleeswaran Cc: George Spelvin Cc: Rik vanRiel Cc: Andrea Arcangeli Cc: MichelLespinasse Cc: Peter Hurley Cc: Andi Kleen Cc: Alex Shi Cc: Dave Hansen Cc: Tim Chen Cc: Arnd Bergmann Cc: "Figo.zhang" Cc: "Paul E.McKenney" Cc: "H. Peter Anvin" Cc: Davidlohr Bueso Cc: Waiman Long Cc: Ingo Molnar Cc: Will Deacon Cc: Andrew Morton Cc: Linus Torvalds Cc: Matthew R Wilcox Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1390347382.3138.67.camel@schen9-DESK Signed-off-by: Ingo Molnar Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git Git-commit: ddf1d169c0a489d498c1799a7043904a43b0c159 [joonwoop@codeaurora.org: Resolve merge conflicts; we don't have changes for arch other than ARM/ARM64] Signed-off-by: Joonwoo Park --- include/linux/mcs_spinlock.h | 114 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 114 insertions(+) create mode 100644 include/linux/mcs_spinlock.h (limited to 'include/linux') diff --git a/include/linux/mcs_spinlock.h b/include/linux/mcs_spinlock.h new file mode 100644 index 000000000..f2a5c6360 --- /dev/null +++ b/include/linux/mcs_spinlock.h @@ -0,0 +1,114 @@ +/* + * MCS lock defines + * + * This file contains the main data structure and API definitions of MCS lock. + * + * The MCS lock (proposed by Mellor-Crummey and Scott) is a simple spin-lock + * with the desirable properties of being fair, and with each cpu trying + * to acquire the lock spinning on a local variable. + * It avoids expensive cache bouncings that common test-and-set spin-lock + * implementations incur. + */ +#ifndef __LINUX_MCS_SPINLOCK_H +#define __LINUX_MCS_SPINLOCK_H + +#include + +struct mcs_spinlock { + struct mcs_spinlock *next; + int locked; /* 1 if lock acquired */ +}; + +#ifndef arch_mcs_spin_lock_contended +/* + * Using smp_load_acquire() provides a memory barrier that ensures + * subsequent operations happen after the lock is acquired. + */ +#define arch_mcs_spin_lock_contended(l) \ +do { \ + while (!(smp_load_acquire(l))) \ + arch_mutex_cpu_relax(); \ +} while (0) +#endif + +#ifndef arch_mcs_spin_unlock_contended +/* + * smp_store_release() provides a memory barrier to ensure all + * operations in the critical section has been completed before + * unlocking. + */ +#define arch_mcs_spin_unlock_contended(l) \ + smp_store_release((l), 1) +#endif + +/* + * Note: the smp_load_acquire/smp_store_release pair is not + * sufficient to form a full memory barrier across + * cpus for many architectures (except x86) for mcs_unlock and mcs_lock. + * For applications that need a full barrier across multiple cpus + * with mcs_unlock and mcs_lock pair, smp_mb__after_unlock_lock() should be + * used after mcs_lock. + */ + +/* + * In order to acquire the lock, the caller should declare a local node and + * pass a reference of the node to this function in addition to the lock. + * If the lock has already been acquired, then this will proceed to spin + * on this node->locked until the previous lock holder sets the node->locked + * in mcs_spin_unlock(). + * + * We don't inline mcs_spin_lock() so that perf can correctly account for the + * time spent in this lock function. + */ +static inline +void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) +{ + struct mcs_spinlock *prev; + + /* Init node */ + node->locked = 0; + node->next = NULL; + + prev = xchg(lock, node); + if (likely(prev == NULL)) { + /* + * Lock acquired, don't need to set node->locked to 1. Threads + * only spin on its own node->locked value for lock acquisition. + * However, since this thread can immediately acquire the lock + * and does not proceed to spin on its own node->locked, this + * value won't be used. If a debug mode is needed to + * audit lock status, then set node->locked value here. + */ + return; + } + ACCESS_ONCE(prev->next) = node; + + /* Wait until the lock holder passes the lock down. */ + arch_mcs_spin_lock_contended(&node->locked); +} + +/* + * Releases the lock. The caller should pass in the corresponding node that + * was used to acquire the lock. + */ +static inline +void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node) +{ + struct mcs_spinlock *next = ACCESS_ONCE(node->next); + + if (likely(!next)) { + /* + * Release the lock by setting it to NULL + */ + if (likely(cmpxchg(lock, node, NULL) == node)) + return; + /* Wait until the next pointer is set */ + while (!(next = ACCESS_ONCE(node->next))) + arch_mutex_cpu_relax(); + } + + /* Pass lock to next waiter. */ + arch_mcs_spin_unlock_contended(&next->locked); +} + +#endif /* __LINUX_MCS_SPINLOCK_H */ -- cgit v1.2.3