From: Kent Overstreet <kent.overstreet@linux.dev>
To: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-bcachefs@vger.kernel.org
Cc: Kent Overstreet <kent.overstreet@gmail.com>,
Kent Overstreet <kent.overstreet@linux.dev>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>, Will Deacon <will@kernel.org>,
Waiman Long <longman@redhat.com>,
Boqun Feng <boqun.feng@gmail.com>
Subject: [PATCH 04/32] locking: SIX locks (shared/intent/exclusive)
Date: Tue, 9 May 2023 12:56:29 -0400 [thread overview]
Message-ID: <20230509165657.1735798-5-kent.overstreet@linux.dev> (raw)
In-Reply-To: <20230509165657.1735798-1-kent.overstreet@linux.dev>
From: Kent Overstreet <kent.overstreet@gmail.com>
New lock for bcachefs, like read/write locks but with a third state,
intent.
Intent locks conflict with each other, but not with read locks; taking a
write lock requires first holding an intent lock.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Will Deacon <will@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
---
include/linux/six.h | 210 +++++++++++
kernel/Kconfig.locks | 3 +
kernel/locking/Makefile | 1 +
kernel/locking/six.c | 779 ++++++++++++++++++++++++++++++++++++++++
4 files changed, 993 insertions(+)
create mode 100644 include/linux/six.h
create mode 100644 kernel/locking/six.c
diff --git a/include/linux/six.h b/include/linux/six.h
new file mode 100644
index 0000000000..41ddf63b74
--- /dev/null
+++ b/include/linux/six.h
@@ -0,0 +1,210 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_SIX_H
+#define _LINUX_SIX_H
+
+/*
+ * Shared/intent/exclusive locks: sleepable read/write locks, much like rw
+ * semaphores, except with a third intermediate state, intent. Basic operations
+ * are:
+ *
+ * six_lock_read(&foo->lock);
+ * six_unlock_read(&foo->lock);
+ *
+ * six_lock_intent(&foo->lock);
+ * six_unlock_intent(&foo->lock);
+ *
+ * six_lock_write(&foo->lock);
+ * six_unlock_write(&foo->lock);
+ *
+ * Intent locks block other intent locks, but do not block read locks, and you
+ * must have an intent lock held before taking a write lock, like so:
+ *
+ * six_lock_intent(&foo->lock);
+ * six_lock_write(&foo->lock);
+ * six_unlock_write(&foo->lock);
+ * six_unlock_intent(&foo->lock);
+ *
+ * Other operations:
+ *
+ * six_trylock_read()
+ * six_trylock_intent()
+ * six_trylock_write()
+ *
+ * six_lock_downgrade(): convert from intent to read
+ * six_lock_tryupgrade(): attempt to convert from read to intent
+ *
+ * Locks also embed a sequence number, which is incremented when the lock is
+ * locked or unlocked for write. The current sequence number can be grabbed
+ * while a lock is held from lock->state.seq; then, if you drop the lock you can
+ * use six_relock_(read|intent_write)(lock, seq) to attempt to retake the lock
+ * iff it hasn't been locked for write in the meantime.
+ *
+ * There are also operations that take the lock type as a parameter, where the
+ * type is one of SIX_LOCK_read, SIX_LOCK_intent, or SIX_LOCK_write:
+ *
+ * six_lock_type(lock, type)
+ * six_unlock_type(lock, type)
+ * six_relock(lock, type, seq)
+ * six_trylock_type(lock, type)
+ * six_trylock_convert(lock, from, to)
+ *
+ * A lock may be held multiple types by the same thread (for read or intent,
+ * not write). However, the six locks code does _not_ implement the actual
+ * recursive checks itself though - rather, if your code (e.g. btree iterator
+ * code) knows that the current thread already has a lock held, and for the
+ * correct type, six_lock_increment() may be used to bump up the counter for
+ * that type - the only effect is that one more call to unlock will be required
+ * before the lock is unlocked.
+ */
+
+#include <linux/lockdep.h>
+#include <linux/osq_lock.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+
+#define SIX_LOCK_SEPARATE_LOCKFNS
+
+union six_lock_state {
+ struct {
+ atomic64_t counter;
+ };
+
+ struct {
+ u64 v;
+ };
+
+ struct {
+ /* for waitlist_bitnr() */
+ unsigned long l;
+ };
+
+ struct {
+ unsigned read_lock:27;
+ unsigned write_locking:1;
+ unsigned intent_lock:1;
+ unsigned waiters:3;
+ /*
+ * seq works much like in seqlocks: it's incremented every time
+ * we lock and unlock for write.
+ *
+ * If it's odd write lock is held, even unlocked.
+ *
+ * Thus readers can unlock, and then lock again later iff it
+ * hasn't been modified in the meantime.
+ */
+ u32 seq;
+ };
+};
+
+enum six_lock_type {
+ SIX_LOCK_read,
+ SIX_LOCK_intent,
+ SIX_LOCK_write,
+};
+
+struct six_lock {
+ union six_lock_state state;
+ unsigned intent_lock_recurse;
+ struct task_struct *owner;
+ struct optimistic_spin_queue osq;
+ unsigned __percpu *readers;
+
+ raw_spinlock_t wait_lock;
+ struct list_head wait_list[2];
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ struct lockdep_map dep_map;
+#endif
+};
+
+typedef int (*six_lock_should_sleep_fn)(struct six_lock *lock, void *);
+
+static __always_inline void __six_lock_init(struct six_lock *lock,
+ const char *name,
+ struct lock_class_key *key)
+{
+ atomic64_set(&lock->state.counter, 0);
+ raw_spin_lock_init(&lock->wait_lock);
+ INIT_LIST_HEAD(&lock->wait_list[SIX_LOCK_read]);
+ INIT_LIST_HEAD(&lock->wait_list[SIX_LOCK_intent]);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ debug_check_no_locks_freed((void *) lock, sizeof(*lock));
+ lockdep_init_map(&lock->dep_map, name, key, 0);
+#endif
+}
+
+#define six_lock_init(lock) \
+do { \
+ static struct lock_class_key __key; \
+ \
+ __six_lock_init((lock), #lock, &__key); \
+} while (0)
+
+#define __SIX_VAL(field, _v) (((union six_lock_state) { .field = _v }).v)
+
+#define __SIX_LOCK(type) \
+bool six_trylock_##type(struct six_lock *); \
+bool six_relock_##type(struct six_lock *, u32); \
+int six_lock_##type(struct six_lock *, six_lock_should_sleep_fn, void *);\
+void six_unlock_##type(struct six_lock *);
+
+__SIX_LOCK(read)
+__SIX_LOCK(intent)
+__SIX_LOCK(write)
+#undef __SIX_LOCK
+
+#define SIX_LOCK_DISPATCH(type, fn, ...) \
+ switch (type) { \
+ case SIX_LOCK_read: \
+ return fn##_read(__VA_ARGS__); \
+ case SIX_LOCK_intent: \
+ return fn##_intent(__VA_ARGS__); \
+ case SIX_LOCK_write: \
+ return fn##_write(__VA_ARGS__); \
+ default: \
+ BUG(); \
+ }
+
+static inline bool six_trylock_type(struct six_lock *lock, enum six_lock_type type)
+{
+ SIX_LOCK_DISPATCH(type, six_trylock, lock);
+}
+
+static inline bool six_relock_type(struct six_lock *lock, enum six_lock_type type,
+ unsigned seq)
+{
+ SIX_LOCK_DISPATCH(type, six_relock, lock, seq);
+}
+
+static inline int six_lock_type(struct six_lock *lock, enum six_lock_type type,
+ six_lock_should_sleep_fn should_sleep_fn, void *p)
+{
+ SIX_LOCK_DISPATCH(type, six_lock, lock, should_sleep_fn, p);
+}
+
+static inline void six_unlock_type(struct six_lock *lock, enum six_lock_type type)
+{
+ SIX_LOCK_DISPATCH(type, six_unlock, lock);
+}
+
+void six_lock_downgrade(struct six_lock *);
+bool six_lock_tryupgrade(struct six_lock *);
+bool six_trylock_convert(struct six_lock *, enum six_lock_type,
+ enum six_lock_type);
+
+void six_lock_increment(struct six_lock *, enum six_lock_type);
+
+void six_lock_wakeup_all(struct six_lock *);
+
+void six_lock_pcpu_free_rcu(struct six_lock *);
+void six_lock_pcpu_free(struct six_lock *);
+void six_lock_pcpu_alloc(struct six_lock *);
+
+struct six_lock_count {
+ unsigned read;
+ unsigned intent;
+};
+
+struct six_lock_count six_lock_counts(struct six_lock *);
+
+#endif /* _LINUX_SIX_H */
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 4198f0273e..b2abd9a5d9 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -259,3 +259,6 @@ config ARCH_HAS_MMIOWB
config MMIOWB
def_bool y if ARCH_HAS_MMIOWB
depends on SMP
+
+config SIXLOCKS
+ bool
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 0db4093d17..a095dbbf01 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -32,3 +32,4 @@ obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o
obj-$(CONFIG_LOCK_EVENT_COUNTS) += lock_events.o
+obj-$(CONFIG_SIXLOCKS) += six.o
diff --git a/kernel/locking/six.c b/kernel/locking/six.c
new file mode 100644
index 0000000000..5b2d92c6e9
--- /dev/null
+++ b/kernel/locking/six.c
@@ -0,0 +1,779 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/export.h>
+#include <linux/log2.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/sched/rt.h>
+#include <linux/six.h>
+#include <linux/slab.h>
+
+#ifdef DEBUG
+#define EBUG_ON(cond) BUG_ON(cond)
+#else
+#define EBUG_ON(cond) do {} while (0)
+#endif
+
+#define six_acquire(l, t) lock_acquire(l, 0, t, 0, 0, NULL, _RET_IP_)
+#define six_release(l) lock_release(l, _RET_IP_)
+
+struct six_lock_vals {
+ /* Value we add to the lock in order to take the lock: */
+ u64 lock_val;
+
+ /* If the lock has this value (used as a mask), taking the lock fails: */
+ u64 lock_fail;
+
+ /* Value we add to the lock in order to release the lock: */
+ u64 unlock_val;
+
+ /* Mask that indicates lock is held for this type: */
+ u64 held_mask;
+
+ /* Waitlist we wakeup when releasing the lock: */
+ enum six_lock_type unlock_wakeup;
+};
+
+#define __SIX_LOCK_HELD_read __SIX_VAL(read_lock, ~0)
+#define __SIX_LOCK_HELD_intent __SIX_VAL(intent_lock, ~0)
+#define __SIX_LOCK_HELD_write __SIX_VAL(seq, 1)
+
+#define LOCK_VALS { \
+ [SIX_LOCK_read] = { \
+ .lock_val = __SIX_VAL(read_lock, 1), \
+ .lock_fail = __SIX_LOCK_HELD_write + __SIX_VAL(write_locking, 1),\
+ .unlock_val = -__SIX_VAL(read_lock, 1), \
+ .held_mask = __SIX_LOCK_HELD_read, \
+ .unlock_wakeup = SIX_LOCK_write, \
+ }, \
+ [SIX_LOCK_intent] = { \
+ .lock_val = __SIX_VAL(intent_lock, 1), \
+ .lock_fail = __SIX_LOCK_HELD_intent, \
+ .unlock_val = -__SIX_VAL(intent_lock, 1), \
+ .held_mask = __SIX_LOCK_HELD_intent, \
+ .unlock_wakeup = SIX_LOCK_intent, \
+ }, \
+ [SIX_LOCK_write] = { \
+ .lock_val = __SIX_VAL(seq, 1), \
+ .lock_fail = __SIX_LOCK_HELD_read, \
+ .unlock_val = __SIX_VAL(seq, 1), \
+ .held_mask = __SIX_LOCK_HELD_write, \
+ .unlock_wakeup = SIX_LOCK_read, \
+ }, \
+}
+
+static inline void six_set_owner(struct six_lock *lock, enum six_lock_type type,
+ union six_lock_state old)
+{
+ if (type != SIX_LOCK_intent)
+ return;
+
+ if (!old.intent_lock) {
+ EBUG_ON(lock->owner);
+ lock->owner = current;
+ } else {
+ EBUG_ON(lock->owner != current);
+ }
+}
+
+static inline unsigned pcpu_read_count(struct six_lock *lock)
+{
+ unsigned read_count = 0;
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ read_count += *per_cpu_ptr(lock->readers, cpu);
+ return read_count;
+}
+
+struct six_lock_waiter {
+ struct list_head list;
+ struct task_struct *task;
+};
+
+/* This is probably up there with the more evil things I've done */
+#define waitlist_bitnr(id) ilog2((((union six_lock_state) { .waiters = 1 << (id) }).l))
+
+static inline void six_lock_wakeup(struct six_lock *lock,
+ union six_lock_state state,
+ unsigned waitlist_id)
+{
+ if (waitlist_id == SIX_LOCK_write) {
+ if (state.write_locking && !state.read_lock) {
+ struct task_struct *p = READ_ONCE(lock->owner);
+ if (p)
+ wake_up_process(p);
+ }
+ } else {
+ struct list_head *wait_list = &lock->wait_list[waitlist_id];
+ struct six_lock_waiter *w, *next;
+
+ if (!(state.waiters & (1 << waitlist_id)))
+ return;
+
+ clear_bit(waitlist_bitnr(waitlist_id),
+ (unsigned long *) &lock->state.v);
+
+ raw_spin_lock(&lock->wait_lock);
+
+ list_for_each_entry_safe(w, next, wait_list, list) {
+ list_del_init(&w->list);
+
+ if (wake_up_process(w->task) &&
+ waitlist_id != SIX_LOCK_read) {
+ if (!list_empty(wait_list))
+ set_bit(waitlist_bitnr(waitlist_id),
+ (unsigned long *) &lock->state.v);
+ break;
+ }
+ }
+
+ raw_spin_unlock(&lock->wait_lock);
+ }
+}
+
+static __always_inline bool do_six_trylock_type(struct six_lock *lock,
+ enum six_lock_type type,
+ bool try)
+{
+ const struct six_lock_vals l[] = LOCK_VALS;
+ union six_lock_state old, new;
+ bool ret;
+ u64 v;
+
+ EBUG_ON(type == SIX_LOCK_write && lock->owner != current);
+ EBUG_ON(type == SIX_LOCK_write && (lock->state.seq & 1));
+
+ EBUG_ON(type == SIX_LOCK_write && (try != !(lock->state.write_locking)));
+
+ /*
+ * Percpu reader mode:
+ *
+ * The basic idea behind this algorithm is that you can implement a lock
+ * between two threads without any atomics, just memory barriers:
+ *
+ * For two threads you'll need two variables, one variable for "thread a
+ * has the lock" and another for "thread b has the lock".
+ *
+ * To take the lock, a thread sets its variable indicating that it holds
+ * the lock, then issues a full memory barrier, then reads from the
+ * other thread's variable to check if the other thread thinks it has
+ * the lock. If we raced, we backoff and retry/sleep.
+ */
+
+ if (type == SIX_LOCK_read && lock->readers) {
+retry:
+ preempt_disable();
+ this_cpu_inc(*lock->readers); /* signal that we own lock */
+
+ smp_mb();
+
+ old.v = READ_ONCE(lock->state.v);
+ ret = !(old.v & l[type].lock_fail);
+
+ this_cpu_sub(*lock->readers, !ret);
+ preempt_enable();
+
+ /*
+ * If we failed because a writer was trying to take the
+ * lock, issue a wakeup because we might have caused a
+ * spurious trylock failure:
+ */
+ if (old.write_locking) {
+ struct task_struct *p = READ_ONCE(lock->owner);
+
+ if (p)
+ wake_up_process(p);
+ }
+
+ /*
+ * If we failed from the lock path and the waiting bit wasn't
+ * set, set it:
+ */
+ if (!try && !ret) {
+ v = old.v;
+
+ do {
+ new.v = old.v = v;
+
+ if (!(old.v & l[type].lock_fail))
+ goto retry;
+
+ if (new.waiters & (1 << type))
+ break;
+
+ new.waiters |= 1 << type;
+ } while ((v = atomic64_cmpxchg(&lock->state.counter,
+ old.v, new.v)) != old.v);
+ }
+ } else if (type == SIX_LOCK_write && lock->readers) {
+ if (try) {
+ atomic64_add(__SIX_VAL(write_locking, 1),
+ &lock->state.counter);
+ smp_mb__after_atomic();
+ }
+
+ ret = !pcpu_read_count(lock);
+
+ /*
+ * On success, we increment lock->seq; also we clear
+ * write_locking unless we failed from the lock path:
+ */
+ v = 0;
+ if (ret)
+ v += __SIX_VAL(seq, 1);
+ if (ret || try)
+ v -= __SIX_VAL(write_locking, 1);
+
+ if (try && !ret) {
+ old.v = atomic64_add_return(v, &lock->state.counter);
+ six_lock_wakeup(lock, old, SIX_LOCK_read);
+ } else {
+ atomic64_add(v, &lock->state.counter);
+ }
+ } else {
+ v = READ_ONCE(lock->state.v);
+ do {
+ new.v = old.v = v;
+
+ if (!(old.v & l[type].lock_fail)) {
+ new.v += l[type].lock_val;
+
+ if (type == SIX_LOCK_write)
+ new.write_locking = 0;
+ } else if (!try && type != SIX_LOCK_write &&
+ !(new.waiters & (1 << type)))
+ new.waiters |= 1 << type;
+ else
+ break; /* waiting bit already set */
+ } while ((v = atomic64_cmpxchg_acquire(&lock->state.counter,
+ old.v, new.v)) != old.v);
+
+ ret = !(old.v & l[type].lock_fail);
+
+ EBUG_ON(ret && !(lock->state.v & l[type].held_mask));
+ }
+
+ if (ret)
+ six_set_owner(lock, type, old);
+
+ EBUG_ON(type == SIX_LOCK_write && (try || ret) && (lock->state.write_locking));
+
+ return ret;
+}
+
+__always_inline __flatten
+static bool __six_trylock_type(struct six_lock *lock, enum six_lock_type type)
+{
+ if (!do_six_trylock_type(lock, type, true))
+ return false;
+
+ if (type != SIX_LOCK_write)
+ six_acquire(&lock->dep_map, 1);
+ return true;
+}
+
+__always_inline __flatten
+static bool __six_relock_type(struct six_lock *lock, enum six_lock_type type,
+ unsigned seq)
+{
+ const struct six_lock_vals l[] = LOCK_VALS;
+ union six_lock_state old;
+ u64 v;
+
+ EBUG_ON(type == SIX_LOCK_write);
+
+ if (type == SIX_LOCK_read &&
+ lock->readers) {
+ bool ret;
+
+ preempt_disable();
+ this_cpu_inc(*lock->readers);
+
+ smp_mb();
+
+ old.v = READ_ONCE(lock->state.v);
+ ret = !(old.v & l[type].lock_fail) && old.seq == seq;
+
+ this_cpu_sub(*lock->readers, !ret);
+ preempt_enable();
+
+ /*
+ * Similar to the lock path, we may have caused a spurious write
+ * lock fail and need to issue a wakeup:
+ */
+ if (old.write_locking) {
+ struct task_struct *p = READ_ONCE(lock->owner);
+
+ if (p)
+ wake_up_process(p);
+ }
+
+ if (ret)
+ six_acquire(&lock->dep_map, 1);
+
+ return ret;
+ }
+
+ v = READ_ONCE(lock->state.v);
+ do {
+ old.v = v;
+
+ if (old.seq != seq || old.v & l[type].lock_fail)
+ return false;
+ } while ((v = atomic64_cmpxchg_acquire(&lock->state.counter,
+ old.v,
+ old.v + l[type].lock_val)) != old.v);
+
+ six_set_owner(lock, type, old);
+ if (type != SIX_LOCK_write)
+ six_acquire(&lock->dep_map, 1);
+ return true;
+}
+
+#ifdef CONFIG_LOCK_SPIN_ON_OWNER
+
+static inline int six_can_spin_on_owner(struct six_lock *lock)
+{
+ struct task_struct *owner;
+ int retval = 1;
+
+ if (need_resched())
+ return 0;
+
+ rcu_read_lock();
+ owner = READ_ONCE(lock->owner);
+ if (owner)
+ retval = owner->on_cpu;
+ rcu_read_unlock();
+ /*
+ * if lock->owner is not set, the mutex owner may have just acquired
+ * it and not set the owner yet or the mutex has been released.
+ */
+ return retval;
+}
+
+static inline bool six_spin_on_owner(struct six_lock *lock,
+ struct task_struct *owner)
+{
+ bool ret = true;
+
+ rcu_read_lock();
+ while (lock->owner == owner) {
+ /*
+ * Ensure we emit the owner->on_cpu, dereference _after_
+ * checking lock->owner still matches owner. If that fails,
+ * owner might point to freed memory. If it still matches,
+ * the rcu_read_lock() ensures the memory stays valid.
+ */
+ barrier();
+
+ if (!owner->on_cpu || need_resched()) {
+ ret = false;
+ break;
+ }
+
+ cpu_relax();
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
+static inline bool six_optimistic_spin(struct six_lock *lock, enum six_lock_type type)
+{
+ struct task_struct *task = current;
+
+ if (type == SIX_LOCK_write)
+ return false;
+
+ preempt_disable();
+ if (!six_can_spin_on_owner(lock))
+ goto fail;
+
+ if (!osq_lock(&lock->osq))
+ goto fail;
+
+ while (1) {
+ struct task_struct *owner;
+
+ /*
+ * If there's an owner, wait for it to either
+ * release the lock or go to sleep.
+ */
+ owner = READ_ONCE(lock->owner);
+ if (owner && !six_spin_on_owner(lock, owner))
+ break;
+
+ if (do_six_trylock_type(lock, type, false)) {
+ osq_unlock(&lock->osq);
+ preempt_enable();
+ return true;
+ }
+
+ /*
+ * When there's no owner, we might have preempted between the
+ * owner acquiring the lock and setting the owner field. If
+ * we're an RT task that will live-lock because we won't let
+ * the owner complete.
+ */
+ if (!owner && (need_resched() || rt_task(task)))
+ break;
+
+ /*
+ * The cpu_relax() call is a compiler barrier which forces
+ * everything in this loop to be re-loaded. We don't need
+ * memory barriers as we'll eventually observe the right
+ * values at the cost of a few extra spins.
+ */
+ cpu_relax();
+ }
+
+ osq_unlock(&lock->osq);
+fail:
+ preempt_enable();
+
+ /*
+ * If we fell out of the spin path because of need_resched(),
+ * reschedule now, before we try-lock again. This avoids getting
+ * scheduled out right after we obtained the lock.
+ */
+ if (need_resched())
+ schedule();
+
+ return false;
+}
+
+#else /* CONFIG_LOCK_SPIN_ON_OWNER */
+
+static inline bool six_optimistic_spin(struct six_lock *lock, enum six_lock_type type)
+{
+ return false;
+}
+
+#endif
+
+noinline
+static int __six_lock_type_slowpath(struct six_lock *lock, enum six_lock_type type,
+ six_lock_should_sleep_fn should_sleep_fn, void *p)
+{
+ union six_lock_state old;
+ struct six_lock_waiter wait;
+ int ret = 0;
+
+ if (type == SIX_LOCK_write) {
+ EBUG_ON(lock->state.write_locking);
+ atomic64_add(__SIX_VAL(write_locking, 1), &lock->state.counter);
+ smp_mb__after_atomic();
+ }
+
+ ret = should_sleep_fn ? should_sleep_fn(lock, p) : 0;
+ if (ret)
+ goto out_before_sleep;
+
+ if (six_optimistic_spin(lock, type))
+ goto out_before_sleep;
+
+ lock_contended(&lock->dep_map, _RET_IP_);
+
+ INIT_LIST_HEAD(&wait.list);
+ wait.task = current;
+
+ while (1) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ if (type == SIX_LOCK_write)
+ EBUG_ON(lock->owner != current);
+ else if (list_empty_careful(&wait.list)) {
+ raw_spin_lock(&lock->wait_lock);
+ list_add_tail(&wait.list, &lock->wait_list[type]);
+ raw_spin_unlock(&lock->wait_lock);
+ }
+
+ if (do_six_trylock_type(lock, type, false))
+ break;
+
+ ret = should_sleep_fn ? should_sleep_fn(lock, p) : 0;
+ if (ret)
+ break;
+
+ schedule();
+ }
+
+ __set_current_state(TASK_RUNNING);
+
+ if (!list_empty_careful(&wait.list)) {
+ raw_spin_lock(&lock->wait_lock);
+ list_del_init(&wait.list);
+ raw_spin_unlock(&lock->wait_lock);
+ }
+out_before_sleep:
+ if (ret && type == SIX_LOCK_write) {
+ old.v = atomic64_sub_return(__SIX_VAL(write_locking, 1),
+ &lock->state.counter);
+ six_lock_wakeup(lock, old, SIX_LOCK_read);
+ }
+
+ return ret;
+}
+
+__always_inline
+static int __six_lock_type(struct six_lock *lock, enum six_lock_type type,
+ six_lock_should_sleep_fn should_sleep_fn, void *p)
+{
+ int ret;
+
+ if (type != SIX_LOCK_write)
+ six_acquire(&lock->dep_map, 0);
+
+ ret = do_six_trylock_type(lock, type, true) ? 0
+ : __six_lock_type_slowpath(lock, type, should_sleep_fn, p);
+
+ if (ret && type != SIX_LOCK_write)
+ six_release(&lock->dep_map);
+ if (!ret)
+ lock_acquired(&lock->dep_map, _RET_IP_);
+
+ return ret;
+}
+
+__always_inline __flatten
+static void __six_unlock_type(struct six_lock *lock, enum six_lock_type type)
+{
+ const struct six_lock_vals l[] = LOCK_VALS;
+ union six_lock_state state;
+
+ EBUG_ON(type == SIX_LOCK_write &&
+ !(lock->state.v & __SIX_LOCK_HELD_intent));
+
+ if (type != SIX_LOCK_write)
+ six_release(&lock->dep_map);
+
+ if (type == SIX_LOCK_intent) {
+ EBUG_ON(lock->owner != current);
+
+ if (lock->intent_lock_recurse) {
+ --lock->intent_lock_recurse;
+ return;
+ }
+
+ lock->owner = NULL;
+ }
+
+ if (type == SIX_LOCK_read &&
+ lock->readers) {
+ smp_mb(); /* unlock barrier */
+ this_cpu_dec(*lock->readers);
+ smp_mb(); /* between unlocking and checking for waiters */
+ state.v = READ_ONCE(lock->state.v);
+ } else {
+ EBUG_ON(!(lock->state.v & l[type].held_mask));
+ state.v = atomic64_add_return_release(l[type].unlock_val,
+ &lock->state.counter);
+ }
+
+ six_lock_wakeup(lock, state, l[type].unlock_wakeup);
+}
+
+#define __SIX_LOCK(type) \
+bool six_trylock_##type(struct six_lock *lock) \
+{ \
+ return __six_trylock_type(lock, SIX_LOCK_##type); \
+} \
+EXPORT_SYMBOL_GPL(six_trylock_##type); \
+ \
+bool six_relock_##type(struct six_lock *lock, u32 seq) \
+{ \
+ return __six_relock_type(lock, SIX_LOCK_##type, seq); \
+} \
+EXPORT_SYMBOL_GPL(six_relock_##type); \
+ \
+int six_lock_##type(struct six_lock *lock, \
+ six_lock_should_sleep_fn should_sleep_fn, void *p) \
+{ \
+ return __six_lock_type(lock, SIX_LOCK_##type, should_sleep_fn, p);\
+} \
+EXPORT_SYMBOL_GPL(six_lock_##type); \
+ \
+void six_unlock_##type(struct six_lock *lock) \
+{ \
+ __six_unlock_type(lock, SIX_LOCK_##type); \
+} \
+EXPORT_SYMBOL_GPL(six_unlock_##type);
+
+__SIX_LOCK(read)
+__SIX_LOCK(intent)
+__SIX_LOCK(write)
+
+#undef __SIX_LOCK
+
+/* Convert from intent to read: */
+void six_lock_downgrade(struct six_lock *lock)
+{
+ six_lock_increment(lock, SIX_LOCK_read);
+ six_unlock_intent(lock);
+}
+EXPORT_SYMBOL_GPL(six_lock_downgrade);
+
+bool six_lock_tryupgrade(struct six_lock *lock)
+{
+ union six_lock_state old, new;
+ u64 v = READ_ONCE(lock->state.v);
+
+ do {
+ new.v = old.v = v;
+
+ if (new.intent_lock)
+ return false;
+
+ if (!lock->readers) {
+ EBUG_ON(!new.read_lock);
+ new.read_lock--;
+ }
+
+ new.intent_lock = 1;
+ } while ((v = atomic64_cmpxchg_acquire(&lock->state.counter,
+ old.v, new.v)) != old.v);
+
+ if (lock->readers)
+ this_cpu_dec(*lock->readers);
+
+ six_set_owner(lock, SIX_LOCK_intent, old);
+
+ return true;
+}
+EXPORT_SYMBOL_GPL(six_lock_tryupgrade);
+
+bool six_trylock_convert(struct six_lock *lock,
+ enum six_lock_type from,
+ enum six_lock_type to)
+{
+ EBUG_ON(to == SIX_LOCK_write || from == SIX_LOCK_write);
+
+ if (to == from)
+ return true;
+
+ if (to == SIX_LOCK_read) {
+ six_lock_downgrade(lock);
+ return true;
+ } else {
+ return six_lock_tryupgrade(lock);
+ }
+}
+EXPORT_SYMBOL_GPL(six_trylock_convert);
+
+/*
+ * Increment read/intent lock count, assuming we already have it read or intent
+ * locked:
+ */
+void six_lock_increment(struct six_lock *lock, enum six_lock_type type)
+{
+ const struct six_lock_vals l[] = LOCK_VALS;
+
+ six_acquire(&lock->dep_map, 0);
+
+ /* XXX: assert already locked, and that we don't overflow: */
+
+ switch (type) {
+ case SIX_LOCK_read:
+ if (lock->readers) {
+ this_cpu_inc(*lock->readers);
+ } else {
+ EBUG_ON(!lock->state.read_lock &&
+ !lock->state.intent_lock);
+ atomic64_add(l[type].lock_val, &lock->state.counter);
+ }
+ break;
+ case SIX_LOCK_intent:
+ EBUG_ON(!lock->state.intent_lock);
+ lock->intent_lock_recurse++;
+ break;
+ case SIX_LOCK_write:
+ BUG();
+ break;
+ }
+}
+EXPORT_SYMBOL_GPL(six_lock_increment);
+
+void six_lock_wakeup_all(struct six_lock *lock)
+{
+ struct six_lock_waiter *w;
+
+ raw_spin_lock(&lock->wait_lock);
+
+ list_for_each_entry(w, &lock->wait_list[0], list)
+ wake_up_process(w->task);
+ list_for_each_entry(w, &lock->wait_list[1], list)
+ wake_up_process(w->task);
+
+ raw_spin_unlock(&lock->wait_lock);
+}
+EXPORT_SYMBOL_GPL(six_lock_wakeup_all);
+
+struct free_pcpu_rcu {
+ struct rcu_head rcu;
+ void __percpu *p;
+};
+
+static void free_pcpu_rcu_fn(struct rcu_head *_rcu)
+{
+ struct free_pcpu_rcu *rcu =
+ container_of(_rcu, struct free_pcpu_rcu, rcu);
+
+ free_percpu(rcu->p);
+ kfree(rcu);
+}
+
+void six_lock_pcpu_free_rcu(struct six_lock *lock)
+{
+ struct free_pcpu_rcu *rcu = kzalloc(sizeof(*rcu), GFP_KERNEL);
+
+ if (!rcu)
+ return;
+
+ rcu->p = lock->readers;
+ lock->readers = NULL;
+
+ call_rcu(&rcu->rcu, free_pcpu_rcu_fn);
+}
+EXPORT_SYMBOL_GPL(six_lock_pcpu_free_rcu);
+
+void six_lock_pcpu_free(struct six_lock *lock)
+{
+ BUG_ON(lock->readers && pcpu_read_count(lock));
+ BUG_ON(lock->state.read_lock);
+
+ free_percpu(lock->readers);
+ lock->readers = NULL;
+}
+EXPORT_SYMBOL_GPL(six_lock_pcpu_free);
+
+void six_lock_pcpu_alloc(struct six_lock *lock)
+{
+#ifdef __KERNEL__
+ if (!lock->readers)
+ lock->readers = alloc_percpu(unsigned);
+#endif
+}
+EXPORT_SYMBOL_GPL(six_lock_pcpu_alloc);
+
+/*
+ * Returns lock held counts, for both read and intent
+ */
+struct six_lock_count six_lock_counts(struct six_lock *lock)
+{
+ struct six_lock_count ret = { 0, lock->state.intent_lock };
+
+ if (!lock->readers)
+ ret.read += lock->state.read_lock;
+ else {
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ ret.read += *per_cpu_ptr(lock->readers, cpu);
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(six_lock_counts);
--
2.40.1
next prev parent reply other threads:[~2023-05-09 16:57 UTC|newest]
Thread overview: 186+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-09 16:56 [PATCH 00/32] bcachefs - a new COW filesystem Kent Overstreet
2023-05-09 16:56 ` [PATCH 01/32] Compiler Attributes: add __flatten Kent Overstreet
2023-05-09 17:04 ` Miguel Ojeda
2023-05-09 17:24 ` Kent Overstreet
2023-05-09 16:56 ` [PATCH 02/32] locking/lockdep: lock_class_is_held() Kent Overstreet
2023-05-09 19:30 ` Peter Zijlstra
2023-05-09 20:11 ` Kent Overstreet
2023-05-09 16:56 ` [PATCH 03/32] locking/lockdep: lockdep_set_no_check_recursion() Kent Overstreet
2023-05-09 19:31 ` Peter Zijlstra
2023-05-09 19:57 ` Kent Overstreet
2023-05-09 20:18 ` Kent Overstreet
2023-05-09 20:27 ` Waiman Long
2023-05-09 20:35 ` Kent Overstreet
2023-05-09 21:37 ` Waiman Long
2023-05-10 8:59 ` Peter Zijlstra
2023-05-10 20:38 ` Kent Overstreet
2023-05-11 8:25 ` Peter Zijlstra
2023-05-11 9:32 ` Kent Overstreet
2023-05-12 20:49 ` Kent Overstreet
2023-05-09 16:56 ` Kent Overstreet [this message]
2023-05-11 12:14 ` [PATCH 04/32] locking: SIX locks (shared/intent/exclusive) Jan Engelhardt
2023-05-12 20:58 ` Kent Overstreet
2023-05-12 22:39 ` Jan Engelhardt
2023-05-12 23:26 ` Kent Overstreet
2023-05-12 23:49 ` Randy Dunlap
2023-05-13 0:17 ` Kent Overstreet
2023-05-13 0:45 ` Eric Biggers
2023-05-13 0:51 ` Kent Overstreet
2023-05-14 12:15 ` Jeff Layton
2023-05-15 2:39 ` Kent Overstreet
2023-05-09 16:56 ` [PATCH 05/32] MAINTAINERS: Add entry for six locks Kent Overstreet
2023-05-09 16:56 ` [PATCH 06/32] sched: Add task_struct->faults_disabled_mapping Kent Overstreet
2023-05-10 1:07 ` Jan Kara
2023-05-10 6:18 ` Kent Overstreet
2023-05-23 13:34 ` Jan Kara
2023-05-23 16:21 ` [Cluster-devel] " Christoph Hellwig
2023-05-23 16:35 ` Kent Overstreet
2023-05-24 6:43 ` Christoph Hellwig
2023-05-24 8:09 ` Kent Overstreet
2023-05-25 8:58 ` Christoph Hellwig
2023-05-25 20:50 ` Kent Overstreet
2023-05-26 8:06 ` Christoph Hellwig
2023-05-26 8:34 ` Kent Overstreet
2023-05-25 21:40 ` Kent Overstreet
2023-05-25 22:25 ` Andreas Grünbacher
2023-05-25 23:20 ` Kent Overstreet
2023-05-26 0:05 ` Andreas Grünbacher
2023-05-26 0:39 ` Kent Overstreet
2023-05-26 8:10 ` Christoph Hellwig
2023-05-26 8:38 ` Kent Overstreet
2023-05-23 16:49 ` Kent Overstreet
2023-05-25 8:47 ` Jan Kara
2023-05-25 21:36 ` Kent Overstreet
2023-05-25 22:45 ` Andreas Grünbacher
2023-05-25 22:04 ` Andreas Grünbacher
2023-05-09 16:56 ` [PATCH 07/32] mm: Bring back vmalloc_exec Kent Overstreet
2023-05-09 18:19 ` Lorenzo Stoakes
2023-05-09 20:15 ` Kent Overstreet
2023-05-09 20:46 ` Christoph Hellwig
2023-05-09 21:12 ` Lorenzo Stoakes
2023-05-09 21:29 ` Kent Overstreet
2023-05-10 6:48 ` Eric Biggers
2023-05-12 18:36 ` Kent Overstreet
2023-05-13 1:57 ` Eric Biggers
2023-05-13 19:28 ` Kent Overstreet
2023-05-14 5:45 ` Kent Overstreet
2023-05-14 18:43 ` Eric Biggers
2023-05-15 5:38 ` Kent Overstreet
2023-05-15 6:13 ` Eric Biggers
2023-05-15 6:18 ` Kent Overstreet
2023-05-15 7:13 ` Eric Biggers
2023-05-15 7:26 ` Kent Overstreet
2023-05-21 21:33 ` Eric Biggers
2023-05-21 22:04 ` Kent Overstreet
2023-05-15 10:29 ` David Laight
2023-05-10 11:56 ` David Laight
2023-05-09 21:43 ` Darrick J. Wong
2023-05-09 21:54 ` Kent Overstreet
2023-05-11 5:33 ` Theodore Ts'o
2023-05-11 5:44 ` Kent Overstreet
2023-05-13 13:25 ` Lorenzo Stoakes
2023-05-14 18:39 ` Christophe Leroy
2023-05-14 23:43 ` Kent Overstreet
2023-05-15 4:45 ` Christophe Leroy
2023-05-15 5:02 ` Kent Overstreet
2023-05-10 14:18 ` Christophe Leroy
2023-05-10 15:05 ` Johannes Thumshirn
2023-05-11 22:28 ` Kees Cook
2023-05-12 18:41 ` Kent Overstreet
2023-05-16 21:02 ` Kees Cook
2023-05-16 21:20 ` Kent Overstreet
2023-05-16 21:47 ` Matthew Wilcox
2023-05-16 21:57 ` Kent Overstreet
2023-05-17 5:28 ` Kent Overstreet
2023-05-17 14:04 ` Mike Rapoport
2023-05-17 14:18 ` Kent Overstreet
2023-05-17 15:44 ` Mike Rapoport
2023-05-17 15:59 ` Kent Overstreet
2023-06-17 4:13 ` Andy Lutomirski
2023-06-17 15:34 ` Kent Overstreet
2023-06-17 19:19 ` Andy Lutomirski
2023-06-17 20:08 ` Kent Overstreet
2023-06-17 20:35 ` Andy Lutomirski
2023-06-19 19:45 ` Kees Cook
2023-06-20 0:39 ` Kent Overstreet
2023-06-19 9:19 ` Mark Rutland
2023-06-19 10:47 ` Kent Overstreet
2023-06-19 12:47 ` Mark Rutland
2023-06-19 19:17 ` Kent Overstreet
2023-06-20 17:42 ` Andy Lutomirski
2023-06-20 18:08 ` Kent Overstreet
2023-06-20 18:15 ` Andy Lutomirski
2023-06-20 18:48 ` Dave Hansen
2023-06-20 20:18 ` Kent Overstreet
2023-06-20 20:42 ` Andy Lutomirski
2023-06-20 22:32 ` Andy Lutomirski
2023-06-20 22:43 ` Nadav Amit
2023-06-21 1:27 ` Andy Lutomirski
2023-05-09 16:56 ` [PATCH 08/32] fs: factor out d_mark_tmpfile() Kent Overstreet
2023-05-09 16:56 ` [PATCH 09/32] block: Add some exports for bcachefs Kent Overstreet
2023-05-09 16:56 ` [PATCH 10/32] block: Allow bio_iov_iter_get_pages() with bio->bi_bdev unset Kent Overstreet
2023-05-09 16:56 ` [PATCH 11/32] block: Bring back zero_fill_bio_iter Kent Overstreet
2023-05-09 16:56 ` [PATCH 12/32] block: Rework bio_for_each_segment_all() Kent Overstreet
2023-05-09 16:56 ` [PATCH 13/32] block: Rework bio_for_each_folio_all() Kent Overstreet
2023-05-09 16:56 ` [PATCH 14/32] block: Don't block on s_umount from __invalidate_super() Kent Overstreet
2023-05-09 16:56 ` [PATCH 15/32] bcache: move closures to lib/ Kent Overstreet
2023-05-10 1:10 ` Randy Dunlap
2023-05-09 16:56 ` [PATCH 16/32] MAINTAINERS: Add entry for closures Kent Overstreet
2023-05-09 17:05 ` Coly Li
2023-05-09 21:03 ` Randy Dunlap
2023-05-09 16:56 ` [PATCH 17/32] closures: closure_wait_event() Kent Overstreet
2023-05-09 16:56 ` [PATCH 18/32] closures: closure_nr_remaining() Kent Overstreet
2023-05-09 16:56 ` [PATCH 19/32] closures: Add a missing include Kent Overstreet
2023-05-09 16:56 ` [PATCH 20/32] vfs: factor out inode hash head calculation Kent Overstreet
2023-05-23 9:27 ` (subset) " Christian Brauner
2023-05-23 22:53 ` Dave Chinner
2023-05-24 6:44 ` Christoph Hellwig
2023-05-24 7:35 ` Dave Chinner
2023-05-24 8:31 ` Christian Brauner
2023-05-24 8:41 ` Kent Overstreet
2023-05-09 16:56 ` [PATCH 21/32] hlist-bl: add hlist_bl_fake() Kent Overstreet
2023-05-10 4:48 ` Dave Chinner
2023-05-23 9:27 ` (subset) " Christian Brauner
2023-05-09 16:56 ` [PATCH 22/32] vfs: inode cache conversion to hash-bl Kent Overstreet
2023-05-10 4:45 ` Dave Chinner
2023-05-16 15:45 ` Christian Brauner
2023-05-16 16:17 ` Kent Overstreet
2023-05-16 23:15 ` Dave Chinner
2023-05-22 13:04 ` Christian Brauner
2023-05-23 9:28 ` (subset) " Christian Brauner
2023-10-19 15:30 ` Mateusz Guzik
2023-10-19 15:59 ` Mateusz Guzik
2023-10-20 11:38 ` Dave Chinner
2023-10-20 17:49 ` Mateusz Guzik
2023-10-21 12:13 ` Mateusz Guzik
2023-10-23 5:10 ` Dave Chinner
2023-10-27 17:13 ` Mateusz Guzik
2023-10-27 18:36 ` Darrick J. Wong
2023-10-31 11:02 ` Christian Brauner
2023-10-31 11:31 ` Mateusz Guzik
2023-11-02 2:36 ` Kent Overstreet
2023-11-04 20:51 ` Dave Chinner
2023-05-09 16:56 ` [PATCH 23/32] iov_iter: copy_folio_from_iter_atomic() Kent Overstreet
2023-05-10 2:20 ` kernel test robot
2023-05-11 2:08 ` kernel test robot
2023-05-09 16:56 ` [PATCH 24/32] MAINTAINERS: Add entry for generic-radix-tree Kent Overstreet
2023-05-09 21:03 ` Randy Dunlap
2023-05-09 16:56 ` [PATCH 25/32] lib/generic-radix-tree.c: Don't overflow in peek() Kent Overstreet
2023-05-09 16:56 ` [PATCH 26/32] lib/generic-radix-tree.c: Add a missing include Kent Overstreet
2023-05-09 16:56 ` [PATCH 27/32] lib/generic-radix-tree.c: Add peek_prev() Kent Overstreet
2023-05-09 16:56 ` [PATCH 28/32] stacktrace: Export stack_trace_save_tsk Kent Overstreet
2023-06-19 9:10 ` Mark Rutland
2023-06-19 11:16 ` Kent Overstreet
2023-05-09 16:56 ` [PATCH 29/32] lib/string_helpers: string_get_size() now returns characters wrote Kent Overstreet
2023-07-12 19:58 ` Kees Cook
2023-07-12 20:19 ` Kent Overstreet
2023-07-12 22:38 ` Kees Cook
2023-07-12 23:53 ` Kent Overstreet
2023-07-12 20:23 ` Kent Overstreet
2023-05-09 16:56 ` [PATCH 30/32] lib: Export errname Kent Overstreet
2023-05-09 16:56 ` [PATCH 31/32] lib: add mean and variance module Kent Overstreet
2023-05-09 16:56 ` [PATCH 32/32] MAINTAINERS: Add entry for bcachefs Kent Overstreet
2023-05-09 21:04 ` Randy Dunlap
2023-05-09 21:07 ` Kent Overstreet
2023-06-15 20:41 ` [PATCH 00/32] bcachefs - a new COW filesystem Pavel Machek
2023-06-15 21:26 ` Kent Overstreet
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230509165657.1735798-5-kent.overstreet@linux.dev \
--to=kent.overstreet@linux.dev \
--cc=boqun.feng@gmail.com \
--cc=kent.overstreet@gmail.com \
--cc=linux-bcachefs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=longman@redhat.com \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=will@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).