summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-08-13 12:23:39 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-08-13 12:23:39 -0700
commitde5d1b39ea0b38a9f4dfb08966042b7b91e2df30 (patch)
tree3591bdac4fe6756b4e3dc68b2ed1c792c4104218 /kernel
parent1c594774283a7cfe6dc0f8ffdfb2dbfc497502c4 (diff)
parentfd2efaa4eb5317c3a86357a83a7d456a1b86a0ac (diff)
downloadlinux-de5d1b39ea0b38a9f4dfb08966042b7b91e2df30.tar.bz2
Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking/atomics update from Thomas Gleixner: "The locking, atomics and memory model brains delivered: - A larger update to the atomics code which reworks the ordering barriers, consolidates the atomic primitives, provides the new atomic64_fetch_add_unless() primitive and cleans up the include hell. - Simplify cmpxchg() instrumentation and add instrumentation for xchg() and cmpxchg_double(). - Updates to the memory model and documentation" * 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits) locking/atomics: Rework ordering barriers locking/atomics: Instrument cmpxchg_double*() locking/atomics: Instrument xchg() locking/atomics: Simplify cmpxchg() instrumentation locking/atomics/x86: Reduce arch_cmpxchg64*() instrumentation tools/memory-model: Rename litmus tests to comply to norm7 tools/memory-model/Documentation: Fix typo, smb->smp sched/Documentation: Update wake_up() & co. memory-barrier guarantees locking/spinlock, sched/core: Clarify requirements for smp_mb__after_spinlock() sched/core: Use smp_mb() in wake_woken_function() tools/memory-model: Add informal LKMM documentation to MAINTAINERS locking/atomics/Documentation: Describe atomic_set() as a write operation tools/memory-model: Make scripts executable tools/memory-model: Remove ACCESS_ONCE() from model tools/memory-model: Remove ACCESS_ONCE() from recipes locking/memory-barriers.txt/kokr: Update Korean translation to fix broken DMA vs. MMIO ordering example MAINTAINERS: Add Daniel Lustig as an LKMM reviewer tools/memory-model: Fix ISA2+pooncelock+pooncelock+pombonce name tools/memory-model: Add litmus test for full multicopy atomicity locking/refcount: Always allow checked forms ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/syscall.c4
-rw-r--r--kernel/sched/completion.c8
-rw-r--r--kernel/sched/core.c71
-rw-r--r--kernel/sched/wait.c55
4 files changed, 64 insertions, 74 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a31a1ba0f8ea..b41c6cf2eb88 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -575,7 +575,7 @@ static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map,
{
int refold;
- refold = __atomic_add_unless(&map->refcnt, 1, 0);
+ refold = atomic_fetch_add_unless(&map->refcnt, 1, 0);
if (refold >= BPF_MAX_REFCNT) {
__bpf_map_put(map, false);
@@ -1144,7 +1144,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
{
int refold;
- refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0);
+ refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0);
if (refold >= BPF_MAX_REFCNT) {
__bpf_prog_put(prog, false);
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index e426b0cb9ac6..a1ad5b7d5521 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -22,8 +22,8 @@
*
* See also complete_all(), wait_for_completion() and related routines.
*
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
*/
void complete(struct completion *x)
{
@@ -44,8 +44,8 @@ EXPORT_SYMBOL(complete);
*
* This will wake up all threads waiting on this particular completion event.
*
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
*
* Since complete_all() sets the completion of @x permanently to done
* to allow multiple waiters to finish, a call to reinit_completion()
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index deafa9fe602b..d17d99778356 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -406,8 +406,8 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
* its already queued (either by us or someone else) and will get the
* wakeup due to that.
*
- * This cmpxchg() implies a full barrier, which pairs with the write
- * barrier implied by the wakeup in wake_up_q().
+ * This cmpxchg() executes a full barrier, which pairs with the full
+ * barrier executed by the wakeup in wake_up_q().
*/
if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
return;
@@ -435,8 +435,8 @@ void wake_up_q(struct wake_q_head *head)
task->wake_q.next = NULL;
/*
- * wake_up_process() implies a wmb() to pair with the queueing
- * in wake_q_add() so as not to miss wakeups.
+ * wake_up_process() executes a full barrier, which pairs with
+ * the queueing in wake_q_add() so as not to miss wakeups.
*/
wake_up_process(task);
put_task_struct(task);
@@ -1859,8 +1859,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
* rq(c1)->lock (if not at the same time, then in that order).
* C) LOCK of the rq(c1)->lock scheduling in task
*
- * Transitivity guarantees that B happens after A and C after B.
- * Note: we only require RCpc transitivity.
+ * Release/acquire chaining guarantees that B happens after A and C after B.
* Note: the CPU doing B need not be c0 or c1
*
* Example:
@@ -1922,16 +1921,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
* UNLOCK rq(0)->lock
*
*
- * However; for wakeups there is a second guarantee we must provide, namely we
- * must observe the state that lead to our wakeup. That is, not only must our
- * task observe its own prior state, it must also observe the stores prior to
- * its wakeup.
- *
- * This means that any means of doing remote wakeups must order the CPU doing
- * the wakeup against the CPU the task is going to end up running on. This,
- * however, is already required for the regular Program-Order guarantee above,
- * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
- *
+ * However, for wakeups there is a second guarantee we must provide, namely we
+ * must ensure that CONDITION=1 done by the caller can not be reordered with
+ * accesses to the task state; see try_to_wake_up() and set_current_state().
*/
/**
@@ -1947,6 +1939,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
* Atomic against schedule() which would dequeue a task, also see
* set_current_state().
*
+ * This function executes a full memory barrier before accessing the task
+ * state; see set_current_state().
+ *
* Return: %true if @p->state changes (an actual wakeup was done),
* %false otherwise.
*/
@@ -1978,21 +1973,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
* be possible to, falsely, observe p->on_rq == 0 and get stuck
* in smp_cond_load_acquire() below.
*
- * sched_ttwu_pending() try_to_wake_up()
- * [S] p->on_rq = 1; [L] P->state
- * UNLOCK rq->lock -----.
- * \
- * +--- RMB
- * schedule() /
- * LOCK rq->lock -----'
- * UNLOCK rq->lock
+ * sched_ttwu_pending() try_to_wake_up()
+ * STORE p->on_rq = 1 LOAD p->state
+ * UNLOCK rq->lock
+ *
+ * __schedule() (switch to task 'p')
+ * LOCK rq->lock smp_rmb();
+ * smp_mb__after_spinlock();
+ * UNLOCK rq->lock
*
* [task p]
- * [S] p->state = UNINTERRUPTIBLE [L] p->on_rq
+ * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq
*
- * Pairs with the UNLOCK+LOCK on rq->lock from the
- * last wakeup of our task and the schedule that got our task
- * current.
+ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+ * __schedule(). See the comment for smp_mb__after_spinlock().
*/
smp_rmb();
if (p->on_rq && ttwu_remote(p, wake_flags))
@@ -2006,15 +2000,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
* One must be running (->on_cpu == 1) in order to remove oneself
* from the runqueue.
*
- * [S] ->on_cpu = 1; [L] ->on_rq
- * UNLOCK rq->lock
- * RMB
- * LOCK rq->lock
- * [S] ->on_rq = 0; [L] ->on_cpu
+ * __schedule() (switch to task 'p') try_to_wake_up()
+ * STORE p->on_cpu = 1 LOAD p->on_rq
+ * UNLOCK rq->lock
+ *
+ * __schedule() (put 'p' to sleep)
+ * LOCK rq->lock smp_rmb();
+ * smp_mb__after_spinlock();
+ * STORE p->on_rq = 0 LOAD p->on_cpu
*
- * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock
- * from the consecutive calls to schedule(); the first switching to our
- * task, the second putting it to sleep.
+ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+ * __schedule(). See the comment for smp_mb__after_spinlock().
*/
smp_rmb();
@@ -2120,8 +2116,7 @@ out:
*
* Return: 1 if the process was woken up, 0 if it was already running.
*
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * This function executes a full memory barrier before accessing the task state.
*/
int wake_up_process(struct task_struct *p)
{
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 928be527477e..870f97b313e3 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -134,8 +134,8 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int
* @nr_exclusive: how many wake-one or wake-many threads to wake up
* @key: is directly passed to the wakeup function
*
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
*/
void __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
int nr_exclusive, void *key)
@@ -180,8 +180,8 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark);
*
* On UP it can prevent extra preemption.
*
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
*/
void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode,
int nr_exclusive, void *key)
@@ -392,35 +392,36 @@ static inline bool is_kthread_should_stop(void)
* if (condition)
* break;
*
- * p->state = mode; condition = true;
- * smp_mb(); // A smp_wmb(); // C
- * if (!wq_entry->flags & WQ_FLAG_WOKEN) wq_entry->flags |= WQ_FLAG_WOKEN;
- * schedule() try_to_wake_up();
- * p->state = TASK_RUNNING; ~~~~~~~~~~~~~~~~~~
- * wq_entry->flags &= ~WQ_FLAG_WOKEN; condition = true;
- * smp_mb() // B smp_wmb(); // C
- * wq_entry->flags |= WQ_FLAG_WOKEN;
- * }
- * remove_wait_queue(&wq_head, &wait);
+ * // in wait_woken() // in woken_wake_function()
*
+ * p->state = mode; wq_entry->flags |= WQ_FLAG_WOKEN;
+ * smp_mb(); // A try_to_wake_up():
+ * if (!(wq_entry->flags & WQ_FLAG_WOKEN)) <full barrier>
+ * schedule() if (p->state & mode)
+ * p->state = TASK_RUNNING; p->state = TASK_RUNNING;
+ * wq_entry->flags &= ~WQ_FLAG_WOKEN; ~~~~~~~~~~~~~~~~~~
+ * smp_mb(); // B condition = true;
+ * } smp_mb(); // C
+ * remove_wait_queue(&wq_head, &wait); wq_entry->flags |= WQ_FLAG_WOKEN;
*/
long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout)
{
- set_current_state(mode); /* A */
/*
- * The above implies an smp_mb(), which matches with the smp_wmb() from
- * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must
- * also observe all state before the wakeup.
+ * The below executes an smp_mb(), which matches with the full barrier
+ * executed by the try_to_wake_up() in woken_wake_function() such that
+ * either we see the store to wq_entry->flags in woken_wake_function()
+ * or woken_wake_function() sees our store to current->state.
*/
+ set_current_state(mode); /* A */
if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
timeout = schedule_timeout(timeout);
__set_current_state(TASK_RUNNING);
/*
- * The below implies an smp_mb(), it too pairs with the smp_wmb() from
- * woken_wake_function() such that we must either observe the wait
- * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
- * an event.
+ * The below executes an smp_mb(), which matches with the smp_mb() (C)
+ * in woken_wake_function() such that either we see the wait condition
+ * being true or the store to wq_entry->flags in woken_wake_function()
+ * follows ours in the coherence order.
*/
smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */
@@ -430,14 +431,8 @@ EXPORT_SYMBOL(wait_woken);
int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key)
{
- /*
- * Although this function is called under waitqueue lock, LOCK
- * doesn't imply write barrier and the users expects write
- * barrier semantics on wakeup functions. The following
- * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
- * and is paired with smp_store_mb() in wait_woken().
- */
- smp_wmb(); /* C */
+ /* Pairs with the smp_store_mb() in wait_woken(). */
+ smp_mb(); /* C */
wq_entry->flags |= WQ_FLAG_WOKEN;
return default_wake_function(wq_entry, mode, sync, key);