From d32cdbfb0ba319e44f75437afde868f7cafdc467 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 23 Nov 2015 18:36:16 +0100 Subject: [PATCH] locking/lglock: Remove lglock implementation It is now unused, remove it before someone else thinks its a good idea to use this. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- Documentation/locking/lglock.txt | 166 ------------------------------- include/linux/lglock.h | 76 -------------- kernel/locking/Makefile | 1 - kernel/locking/lglock.c | 89 ----------------- 4 files changed, 332 deletions(-) delete mode 100644 Documentation/locking/lglock.txt delete mode 100644 include/linux/lglock.h delete mode 100644 kernel/locking/lglock.c diff --git a/Documentation/locking/lglock.txt b/Documentation/locking/lglock.txt deleted file mode 100644 index a6971e34fabe..000000000000 --- a/Documentation/locking/lglock.txt +++ /dev/null @@ -1,166 +0,0 @@ -lglock - local/global locks for mostly local access patterns ------------------------------------------------------------- - -Origin: Nick Piggin's VFS scalability series introduced during - 2.6.35++ [1] [2] -Location: kernel/locking/lglock.c - include/linux/lglock.h -Users: currently only the VFS and stop_machine related code - -Design Goal: ------------- - -Improve scalability of globally used large data sets that are -distributed over all CPUs as per_cpu elements. - -To manage global data structures that are partitioned over all CPUs -as per_cpu elements but can be mostly handled by CPU local actions -lglock will be used where the majority of accesses are cpu local -reading and occasional cpu local writing with very infrequent -global write access. - - -* deal with things locally whenever possible - - very fast access to the local per_cpu data - - reasonably fast access to specific per_cpu data on a different - CPU -* while making global action possible when needed - - by expensive access to all CPUs locks - effectively - resulting in a globally visible critical section. - -Design: -------- - -Basically it is an array of per_cpu spinlocks with the -lg_local_lock/unlock accessing the local CPUs lock object and the -lg_local_lock_cpu/unlock_cpu accessing a remote CPUs lock object -the lg_local_lock has to disable preemption as migration protection so -that the reference to the local CPUs lock does not go out of scope. -Due to the lg_local_lock/unlock only touching cpu-local resources it -is fast. Taking the local lock on a different CPU will be more -expensive but still relatively cheap. - -One can relax the migration constraints by acquiring the current -CPUs lock with lg_local_lock_cpu, remember the cpu, and release that -lock at the end of the critical section even if migrated. This should -give most of the performance benefits without inhibiting migration -though needs careful considerations for nesting of lglocks and -consideration of deadlocks with lg_global_lock. - -The lg_global_lock/unlock locks all underlying spinlocks of all -possible CPUs (including those off-line). The preemption disable/enable -are needed in the non-RT kernels to prevent deadlocks like: - - on cpu 1 - - task A task B - lg_global_lock - got cpu 0 lock - <<<< preempt <<<< - lg_local_lock_cpu for cpu 0 - spin on cpu 0 lock - -On -RT this deadlock scenario is resolved by the arch_spin_locks in the -lglocks being replaced by rt_mutexes which resolve the above deadlock -by boosting the lock-holder. - - -Implementation: ---------------- - -The initial lglock implementation from Nick Piggin used some complex -macros to generate the lglock/brlock in lglock.h - they were later -turned into a set of functions by Andi Kleen [7]. The change to functions -was motivated by the presence of multiple lock users and also by them -being easier to maintain than the generating macros. This change to -functions is also the basis to eliminated the restriction of not -being initializeable in kernel modules (the remaining problem is that -locks are not explicitly initialized - see lockdep-design.txt) - -Declaration and initialization: -------------------------------- - - #include - - DEFINE_LGLOCK(name) - or: - DEFINE_STATIC_LGLOCK(name); - - lg_lock_init(&name, "lockdep_name_string"); - - on UP this is mapped to DEFINE_SPINLOCK(name) in both cases, note - also that as of 3.18-rc6 all declaration in use are of the _STATIC_ - variant (and it seems that the non-static was never in use). - lg_lock_init is initializing the lockdep map only. - -Usage: ------- - -From the locking semantics it is a spinlock. It could be called a -locality aware spinlock. lg_local_* behaves like a per_cpu -spinlock and lg_global_* like a global spinlock. -No surprises in the API. - - lg_local_lock(*lglock); - access to protected per_cpu object on this CPU - lg_local_unlock(*lglock); - - lg_local_lock_cpu(*lglock, cpu); - access to protected per_cpu object on other CPU cpu - lg_local_unlock_cpu(*lglock, cpu); - - lg_global_lock(*lglock); - access all protected per_cpu objects on all CPUs - lg_global_unlock(*lglock); - - There are no _trylock variants of the lglocks. - -Note that the lg_global_lock/unlock has to iterate over all possible -CPUs rather than the actually present CPUs or a CPU could go off-line -with a held lock [4] and that makes it very expensive. A discussion on -these issues can be found at [5] - -Constraints: ------------- - - * currently the declaration of lglocks in kernel modules is not - possible, though this should be doable with little change. - * lglocks are not recursive. - * suitable for code that can do most operations on the CPU local - data and will very rarely need the global lock - * lg_global_lock/unlock is *very* expensive and does not scale - * on UP systems all lg_* primitives are simply spinlocks - * in PREEMPT_RT the spinlock becomes an rt-mutex and can sleep but - does not change the tasks state while sleeping [6]. - * in PREEMPT_RT the preempt_disable/enable in lg_local_lock/unlock - is downgraded to a migrate_disable/enable, the other - preempt_disable/enable are downgraded to barriers [6]. - The deadlock noted for non-RT above is resolved due to rt_mutexes - boosting the lock-holder in this case which arch_spin_locks do - not do. - -lglocks were designed for very specific problems in the VFS and probably -only are the right answer in these corner cases. Any new user that looks -at lglocks probably wants to look at the seqlock and RCU alternatives as -her first choice. There are also efforts to resolve the RCU issues that -currently prevent using RCU in place of view remaining lglocks. - -Note on brlock history: ------------------------ - -The 'Big Reader' read-write spinlocks were originally introduced by -Ingo Molnar in 2000 (2.4/2.5 kernel series) and removed in 2003. They -later were introduced by the VFS scalability patch set in 2.6 series -again as the "big reader lock" brlock [2] variant of lglock which has -been replaced by seqlock primitives or by RCU based primitives in the -3.13 kernel series as was suggested in [3] in 2003. The brlock was -entirely removed in the 3.13 kernel series. - -Link: 1 http://lkml.org/lkml/2010/8/2/81 -Link: 2 http://lwn.net/Articles/401738/ -Link: 3 http://lkml.org/lkml/2003/3/9/205 -Link: 4 https://lkml.org/lkml/2011/8/24/185 -Link: 5 http://lkml.org/lkml/2011/12/18/189 -Link: 6 https://www.kernel.org/pub/linux/kernel/projects/rt/ - patch series - lglocks-rt.patch.patch -Link: 7 http://lkml.org/lkml/2012/3/5/26 diff --git a/include/linux/lglock.h b/include/linux/lglock.h deleted file mode 100644 index 0081f000e34b..000000000000 --- a/include/linux/lglock.h +++ /dev/null @@ -1,76 +0,0 @@ -/* - * Specialised local-global spinlock. Can only be declared as global variables - * to avoid overhead and keep things simple (and we don't want to start using - * these inside dynamically allocated structures). - * - * "local/global locks" (lglocks) can be used to: - * - * - Provide fast exclusive access to per-CPU data, with exclusive access to - * another CPU's data allowed but possibly subject to contention, and to - * provide very slow exclusive access to all per-CPU data. - * - Or to provide very fast and scalable read serialisation, and to provide - * very slow exclusive serialisation of data (not necessarily per-CPU data). - * - * Brlocks are also implemented as a short-hand notation for the latter use - * case. - * - * Copyright 2009, 2010, Nick Piggin, Novell Inc. - */ -#ifndef __LINUX_LGLOCK_H -#define __LINUX_LGLOCK_H - -#include -#include -#include -#include -#include - -#ifdef CONFIG_SMP - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -#define LOCKDEP_INIT_MAP lockdep_init_map -#else -#define LOCKDEP_INIT_MAP(a, b, c, d) -#endif - -struct lglock { - arch_spinlock_t __percpu *lock; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lock_class_key lock_key; - struct lockdep_map lock_dep_map; -#endif -}; - -#define DEFINE_LGLOCK(name) \ - static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ - = __ARCH_SPIN_LOCK_UNLOCKED; \ - struct lglock name = { .lock = &name ## _lock } - -#define DEFINE_STATIC_LGLOCK(name) \ - static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ - = __ARCH_SPIN_LOCK_UNLOCKED; \ - static struct lglock name = { .lock = &name ## _lock } - -void lg_lock_init(struct lglock *lg, char *name); -void lg_local_lock(struct lglock *lg); -void lg_local_unlock(struct lglock *lg); -void lg_local_lock_cpu(struct lglock *lg, int cpu); -void lg_local_unlock_cpu(struct lglock *lg, int cpu); -void lg_global_lock(struct lglock *lg); -void lg_global_unlock(struct lglock *lg); - -#else -/* When !CONFIG_SMP, map lglock to spinlock */ -#define lglock spinlock -#define DEFINE_LGLOCK(name) DEFINE_SPINLOCK(name) -#define DEFINE_STATIC_LGLOCK(name) static DEFINE_SPINLOCK(name) -#define lg_lock_init(lg, name) spin_lock_init(lg) -#define lg_local_lock spin_lock -#define lg_local_unlock spin_unlock -#define lg_local_lock_cpu(lg, cpu) spin_lock(lg) -#define lg_local_unlock_cpu(lg, cpu) spin_unlock(lg) -#define lg_global_lock spin_lock -#define lg_global_unlock spin_unlock -#endif - -#endif diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 31322a4275cd..6f88e352cd4f 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -18,7 +18,6 @@ obj-$(CONFIG_LOCKDEP) += lockdep_proc.o endif obj-$(CONFIG_SMP) += spinlock.o obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o -obj-$(CONFIG_SMP) += lglock.o obj-$(CONFIG_PROVE_LOCKING) += spinlock.o obj-$(CONFIG_QUEUED_SPINLOCKS) += qspinlock.o obj-$(CONFIG_RT_MUTEXES) += rtmutex.o diff --git a/kernel/locking/lglock.c b/kernel/locking/lglock.c deleted file mode 100644 index 86ae2aebf004..000000000000 --- a/kernel/locking/lglock.c +++ /dev/null @@ -1,89 +0,0 @@ -/* See include/linux/lglock.h for description */ -#include -#include -#include -#include - -/* - * Note there is no uninit, so lglocks cannot be defined in - * modules (but it's fine to use them from there) - * Could be added though, just undo lg_lock_init - */ - -void lg_lock_init(struct lglock *lg, char *name) -{ - LOCKDEP_INIT_MAP(&lg->lock_dep_map, name, &lg->lock_key, 0); -} -EXPORT_SYMBOL(lg_lock_init); - -void lg_local_lock(struct lglock *lg) -{ - arch_spinlock_t *lock; - - preempt_disable(); - lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); - lock = this_cpu_ptr(lg->lock); - arch_spin_lock(lock); -} -EXPORT_SYMBOL(lg_local_lock); - -void lg_local_unlock(struct lglock *lg) -{ - arch_spinlock_t *lock; - - lock_release(&lg->lock_dep_map, 1, _RET_IP_); - lock = this_cpu_ptr(lg->lock); - arch_spin_unlock(lock); - preempt_enable(); -} -EXPORT_SYMBOL(lg_local_unlock); - -void lg_local_lock_cpu(struct lglock *lg, int cpu) -{ - arch_spinlock_t *lock; - - preempt_disable(); - lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); - lock = per_cpu_ptr(lg->lock, cpu); - arch_spin_lock(lock); -} -EXPORT_SYMBOL(lg_local_lock_cpu); - -void lg_local_unlock_cpu(struct lglock *lg, int cpu) -{ - arch_spinlock_t *lock; - - lock_release(&lg->lock_dep_map, 1, _RET_IP_); - lock = per_cpu_ptr(lg->lock, cpu); - arch_spin_unlock(lock); - preempt_enable(); -} -EXPORT_SYMBOL(lg_local_unlock_cpu); - -void lg_global_lock(struct lglock *lg) -{ - int i; - - preempt_disable(); - lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); - for_each_possible_cpu(i) { - arch_spinlock_t *lock; - lock = per_cpu_ptr(lg->lock, i); - arch_spin_lock(lock); - } -} -EXPORT_SYMBOL(lg_global_lock); - -void lg_global_unlock(struct lglock *lg) -{ - int i; - - lock_release(&lg->lock_dep_map, 1, _RET_IP_); - for_each_possible_cpu(i) { - arch_spinlock_t *lock; - lock = per_cpu_ptr(lg->lock, i); - arch_spin_unlock(lock); - } - preempt_enable(); -} -EXPORT_SYMBOL(lg_global_unlock);