summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-11-13 12:38:26 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-11-13 12:38:26 -0800
commit8e9a2dba8686187d8c8179e5b86640e653963889 (patch)
treea4ba543649219cbb28d91aab65b785d763f5d069 /kernel
parent6098850e7e6978f95a958f79a645a653228d0002 (diff)
parent450cbdd0125cfa5d7bbf9e2a6b6961cc48d29730 (diff)
downloadlinux-8e9a2dba8686187d8c8179e5b86640e653963889.tar.bz2
Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull core locking updates from Ingo Molnar: "The main changes in this cycle are: - Another attempt at enabling cross-release lockdep dependency tracking (automatically part of CONFIG_PROVE_LOCKING=y), this time with better performance and fewer false positives. (Byungchul Park) - Introduce lockdep_assert_irqs_enabled()/disabled() and convert open-coded equivalents to lockdep variants. (Frederic Weisbecker) - Add down_read_killable() and use it in the VFS's iterate_dir() method. (Kirill Tkhai) - Convert remaining uses of ACCESS_ONCE() to READ_ONCE()/WRITE_ONCE(). Most of the conversion was Coccinelle driven. (Mark Rutland, Paul E. McKenney) - Get rid of lockless_dereference(), by strengthening Alpha atomics, strengthening READ_ONCE() with smp_read_barrier_depends() and thus being able to convert users of lockless_dereference() to READ_ONCE(). (Will Deacon) - Various micro-optimizations: - better PV qspinlocks (Waiman Long), - better x86 barriers (Michael S. Tsirkin) - better x86 refcounts (Kees Cook) - ... plus other fixes and enhancements. (Borislav Petkov, Juergen Gross, Miguel Bernal Marin)" * 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (70 commits) locking/x86: Use LOCK ADD for smp_mb() instead of MFENCE rcu: Use lockdep to assert IRQs are disabled/enabled netpoll: Use lockdep to assert IRQs are disabled/enabled timers/posix-cpu-timers: Use lockdep to assert IRQs are disabled/enabled sched/clock, sched/cputime: Use lockdep to assert IRQs are disabled/enabled irq_work: Use lockdep to assert IRQs are disabled/enabled irq/timings: Use lockdep to assert IRQs are disabled/enabled perf/core: Use lockdep to assert IRQs are disabled/enabled x86: Use lockdep to assert IRQs are disabled/enabled smp/core: Use lockdep to assert IRQs are disabled/enabled timers/hrtimer: Use lockdep to assert IRQs are disabled/enabled timers/nohz: Use lockdep to assert IRQs are disabled/enabled workqueue: Use lockdep to assert IRQs are disabled/enabled irq/softirqs: Use lockdep to assert IRQs are disabled/enabled locking/lockdep: Add IRQs disabled/enabled assertion APIs: lockdep_assert_irqs_enabled()/disabled() locking/pvqspinlock: Implement hybrid PV queued/unfair locks locking/rwlocks: Fix comments x86/paravirt: Set up the virt_spin_lock_key after static keys get initialized block, locking/lockdep: Assign a lock_class per gendisk used for wait_for_completion() workqueue: Remove now redundant lock acquisitions wrt. workqueue flushes ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/acct.c4
-rw-r--r--kernel/events/core.c22
-rw-r--r--kernel/events/ring_buffer.c2
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/irq/timings.c2
-rw-r--r--kernel/irq_work.c2
-rw-r--r--kernel/jump_label.c14
-rw-r--r--kernel/locking/lockdep.c23
-rw-r--r--kernel/locking/qrwlock.c86
-rw-r--r--kernel/locking/qspinlock_paravirt.h47
-rw-r--r--kernel/locking/rwsem.c16
-rw-r--r--kernel/locking/spinlock.c9
-rw-r--r--kernel/rcu/tree.c16
-rw-r--r--kernel/rcu/tree_plugin.h10
-rw-r--r--kernel/sched/clock.c2
-rw-r--r--kernel/sched/cputime.c3
-rw-r--r--kernel/seccomp.c2
-rw-r--r--kernel/smp.c2
-rw-r--r--kernel/softirq.c10
-rw-r--r--kernel/task_work.c2
-rw-r--r--kernel/time/hrtimer.c4
-rw-r--r--kernel/time/posix-cpu-timers.c6
-rw-r--r--kernel/time/tick-sched.c5
-rw-r--r--kernel/trace/ring_buffer.c2
-rw-r--r--kernel/trace/trace.h2
-rw-r--r--kernel/trace/trace_stack.c2
-rw-r--r--kernel/user_namespace.c2
-rw-r--r--kernel/workqueue.c25
28 files changed, 156 insertions, 168 deletions
diff --git a/kernel/acct.c b/kernel/acct.c
index 6670fbd3e466..d15c0ee4d955 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -147,7 +147,7 @@ static struct bsd_acct_struct *acct_get(struct pid_namespace *ns)
again:
smp_rmb();
rcu_read_lock();
- res = to_acct(ACCESS_ONCE(ns->bacct));
+ res = to_acct(READ_ONCE(ns->bacct));
if (!res) {
rcu_read_unlock();
return NULL;
@@ -159,7 +159,7 @@ again:
}
rcu_read_unlock();
mutex_lock(&res->lock);
- if (res != to_acct(ACCESS_ONCE(ns->bacct))) {
+ if (res != to_acct(READ_ONCE(ns->bacct))) {
mutex_unlock(&res->lock);
acct_put(res);
goto again;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 10cdb9c26b5d..c298847d4b85 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -209,7 +209,7 @@ static int event_function(void *info)
struct perf_event_context *task_ctx = cpuctx->task_ctx;
int ret = 0;
- WARN_ON_ONCE(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
perf_ctx_lock(cpuctx, task_ctx);
/*
@@ -306,7 +306,7 @@ static void event_function_local(struct perf_event *event, event_f func, void *d
struct task_struct *task = READ_ONCE(ctx->task);
struct perf_event_context *task_ctx = NULL;
- WARN_ON_ONCE(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
if (task) {
if (task == TASK_TOMBSTONE)
@@ -1006,7 +1006,7 @@ static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr)
struct perf_cpu_context *cpuctx;
int rotations = 0;
- WARN_ON(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
cpuctx = container_of(hr, struct perf_cpu_context, hrtimer);
rotations = perf_rotate_context(cpuctx);
@@ -1093,7 +1093,7 @@ static void perf_event_ctx_activate(struct perf_event_context *ctx)
{
struct list_head *head = this_cpu_ptr(&active_ctx_list);
- WARN_ON(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
WARN_ON(!list_empty(&ctx->active_ctx_list));
@@ -1102,7 +1102,7 @@ static void perf_event_ctx_activate(struct perf_event_context *ctx)
static void perf_event_ctx_deactivate(struct perf_event_context *ctx)
{
- WARN_ON(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
WARN_ON(list_empty(&ctx->active_ctx_list));
@@ -1202,7 +1202,7 @@ perf_event_ctx_lock_nested(struct perf_event *event, int nesting)
again:
rcu_read_lock();
- ctx = ACCESS_ONCE(event->ctx);
+ ctx = READ_ONCE(event->ctx);
if (!atomic_inc_not_zero(&ctx->refcount)) {
rcu_read_unlock();
goto again;
@@ -3523,7 +3523,7 @@ void perf_event_task_tick(void)
struct perf_event_context *ctx, *tmp;
int throttled;
- WARN_ON(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
__this_cpu_inc(perf_throttled_seq);
throttled = __this_cpu_xchg(perf_throttled_count, 0);
@@ -4233,7 +4233,7 @@ static void perf_remove_from_owner(struct perf_event *event)
* indeed free this event, otherwise we need to serialize on
* owner->perf_event_mutex.
*/
- owner = lockless_dereference(event->owner);
+ owner = READ_ONCE(event->owner);
if (owner) {
/*
* Since delayed_put_task_struct() also drops the last
@@ -4330,7 +4330,7 @@ again:
* Cannot change, child events are not migrated, see the
* comment with perf_event_ctx_lock_nested().
*/
- ctx = lockless_dereference(child->ctx);
+ ctx = READ_ONCE(child->ctx);
/*
* Since child_mutex nests inside ctx::mutex, we must jump
* through hoops. We start by grabbing a reference on the ctx.
@@ -5304,8 +5304,8 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
if (!rb)
goto aux_unlock;
- aux_offset = ACCESS_ONCE(rb->user_page->aux_offset);
- aux_size = ACCESS_ONCE(rb->user_page->aux_size);
+ aux_offset = READ_ONCE(rb->user_page->aux_offset);
+ aux_size = READ_ONCE(rb->user_page->aux_size);
if (aux_offset < perf_data_size(rb) + PAGE_SIZE)
goto aux_unlock;
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index f684d8e5fa2b..f3e37971c842 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -381,7 +381,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
* (B) <-> (C) ordering is still observed by the pmu driver.
*/
if (!rb->aux_overwrite) {
- aux_tail = ACCESS_ONCE(rb->user_page->aux_tail);
+ aux_tail = READ_ONCE(rb->user_page->aux_tail);
handle->wakeup = rb->aux_wakeup + rb->aux_watermark;
if (aux_head - aux_tail < perf_aux_size(rb))
handle->size = CIRC_SPACE(aux_head, aux_tail, perf_aux_size(rb));
diff --git a/kernel/exit.c b/kernel/exit.c
index f6cad39f35df..6b4298a41167 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1339,7 +1339,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
* Ensure that EXIT_ZOMBIE -> EXIT_DEAD/EXIT_TRACE transition
* can't confuse the checks below.
*/
- int exit_state = ACCESS_ONCE(p->exit_state);
+ int exit_state = READ_ONCE(p->exit_state);
int ret;
if (unlikely(exit_state == EXIT_DEAD))
diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c
index c8c1d073fbf1..e0923fa4927a 100644
--- a/kernel/irq/timings.c
+++ b/kernel/irq/timings.c
@@ -264,7 +264,7 @@ u64 irq_timings_next_event(u64 now)
* order to prevent the timings circular buffer to be updated
* while we are reading it.
*/
- WARN_ON_ONCE(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
/*
* Number of elements in the circular buffer: If it happens it
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 9f20f6c72579..ec8ac337404d 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -191,7 +191,7 @@ void irq_work_tick(void)
*/
void irq_work_sync(struct irq_work *work)
{
- WARN_ON_ONCE(irqs_disabled());
+ lockdep_assert_irqs_enabled();
while (work->flags & IRQ_WORK_BUSY)
cpu_relax();
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 0bf2e8f5244a..8ff4ca4665ff 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -83,7 +83,7 @@ static void static_key_slow_inc_cpuslocked(struct static_key *key)
{
int v, v1;
- STATIC_KEY_CHECK_USE();
+ STATIC_KEY_CHECK_USE(key);
/*
* Careful if we get concurrent static_key_slow_inc() calls;
@@ -128,7 +128,7 @@ EXPORT_SYMBOL_GPL(static_key_slow_inc);
void static_key_enable_cpuslocked(struct static_key *key)
{
- STATIC_KEY_CHECK_USE();
+ STATIC_KEY_CHECK_USE(key);
if (atomic_read(&key->enabled) > 0) {
WARN_ON_ONCE(atomic_read(&key->enabled) != 1);
@@ -158,7 +158,7 @@ EXPORT_SYMBOL_GPL(static_key_enable);
void static_key_disable_cpuslocked(struct static_key *key)
{
- STATIC_KEY_CHECK_USE();
+ STATIC_KEY_CHECK_USE(key);
if (atomic_read(&key->enabled) != 1) {
WARN_ON_ONCE(atomic_read(&key->enabled) != 0);
@@ -224,21 +224,21 @@ static void jump_label_update_timeout(struct work_struct *work)
void static_key_slow_dec(struct static_key *key)
{
- STATIC_KEY_CHECK_USE();
+ STATIC_KEY_CHECK_USE(key);
__static_key_slow_dec(key, 0, NULL);
}
EXPORT_SYMBOL_GPL(static_key_slow_dec);
void static_key_slow_dec_deferred(struct static_key_deferred *key)
{
- STATIC_KEY_CHECK_USE();
+ STATIC_KEY_CHECK_USE(key);
__static_key_slow_dec(&key->key, key->timeout, &key->work);
}
EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
void static_key_deferred_flush(struct static_key_deferred *key)
{
- STATIC_KEY_CHECK_USE();
+ STATIC_KEY_CHECK_USE(key);
flush_delayed_work(&key->work);
}
EXPORT_SYMBOL_GPL(static_key_deferred_flush);
@@ -246,7 +246,7 @@ EXPORT_SYMBOL_GPL(static_key_deferred_flush);
void jump_label_rate_limit(struct static_key_deferred *key,
unsigned long rl)
{
- STATIC_KEY_CHECK_USE();
+ STATIC_KEY_CHECK_USE(key);
key->timeout = rl;
INIT_DELAYED_WORK(&key->work, jump_label_update_timeout);
}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index e36e652d996f..db933d063bfc 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -76,6 +76,19 @@ module_param(lock_stat, int, 0644);
#define lock_stat 0
#endif
+#ifdef CONFIG_BOOTPARAM_LOCKDEP_CROSSRELEASE_FULLSTACK
+static int crossrelease_fullstack = 1;
+#else
+static int crossrelease_fullstack;
+#endif
+static int __init allow_crossrelease_fullstack(char *str)
+{
+ crossrelease_fullstack = 1;
+ return 0;
+}
+
+early_param("crossrelease_fullstack", allow_crossrelease_fullstack);
+
/*
* lockdep_lock: protects the lockdep graph, the hashes and the
* class/list/hash allocators.
@@ -4863,8 +4876,14 @@ static void add_xhlock(struct held_lock *hlock)
xhlock->trace.nr_entries = 0;
xhlock->trace.max_entries = MAX_XHLOCK_TRACE_ENTRIES;
xhlock->trace.entries = xhlock->trace_entries;
- xhlock->trace.skip = 3;
- save_stack_trace(&xhlock->trace);
+
+ if (crossrelease_fullstack) {
+ xhlock->trace.skip = 3;
+ save_stack_trace(&xhlock->trace);
+ } else {
+ xhlock->trace.nr_entries = 1;
+ xhlock->trace.entries[0] = hlock->acquire_ip;
+ }
}
static inline int same_context_xhlock(struct hist_lock *xhlock)
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index 2655f26ec882..c7471c3fb798 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -23,49 +23,11 @@
#include <linux/spinlock.h>
#include <asm/qrwlock.h>
-/*
- * This internal data structure is used for optimizing access to some of
- * the subfields within the atomic_t cnts.
- */
-struct __qrwlock {
- union {
- atomic_t cnts;
- struct {
-#ifdef __LITTLE_ENDIAN
- u8 wmode; /* Writer mode */
- u8 rcnts[3]; /* Reader counts */
-#else
- u8 rcnts[3]; /* Reader counts */
- u8 wmode; /* Writer mode */
-#endif
- };
- };
- arch_spinlock_t lock;
-};
-
-/**
- * rspin_until_writer_unlock - inc reader count & spin until writer is gone
- * @lock : Pointer to queue rwlock structure
- * @writer: Current queue rwlock writer status byte
- *
- * In interrupt context or at the head of the queue, the reader will just
- * increment the reader count & wait until the writer releases the lock.
- */
-static __always_inline void
-rspin_until_writer_unlock(struct qrwlock *lock, u32 cnts)
-{
- while ((cnts & _QW_WMASK) == _QW_LOCKED) {
- cpu_relax();
- cnts = atomic_read_acquire(&lock->cnts);
- }
-}
-
/**
* queued_read_lock_slowpath - acquire read lock of a queue rwlock
* @lock: Pointer to queue rwlock structure
- * @cnts: Current qrwlock lock value
*/
-void queued_read_lock_slowpath(struct qrwlock *lock, u32 cnts)
+void queued_read_lock_slowpath(struct qrwlock *lock)
{
/*
* Readers come here when they cannot get the lock without waiting
@@ -73,13 +35,11 @@ void queued_read_lock_slowpath(struct qrwlock *lock, u32 cnts)
if (unlikely(in_interrupt())) {
/*
* Readers in interrupt context will get the lock immediately
- * if the writer is just waiting (not holding the lock yet).
- * The rspin_until_writer_unlock() function returns immediately
- * in this case. Otherwise, they will spin (with ACQUIRE
- * semantics) until the lock is available without waiting in
- * the queue.
+ * if the writer is just waiting (not holding the lock yet),
+ * so spin with ACQUIRE semantics until the lock is available
+ * without waiting in the queue.
*/
- rspin_until_writer_unlock(lock, cnts);
+ atomic_cond_read_acquire(&lock->cnts, !(VAL & _QW_LOCKED));
return;
}
atomic_sub(_QR_BIAS, &lock->cnts);
@@ -88,14 +48,14 @@ void queued_read_lock_slowpath(struct qrwlock *lock, u32 cnts)
* Put the reader into the wait queue
*/
arch_spin_lock(&lock->wait_lock);
+ atomic_add(_QR_BIAS, &lock->cnts);
/*
* The ACQUIRE semantics of the following spinning code ensure
* that accesses can't leak upwards out of our subsequent critical
* section in the case that the lock is currently held for write.
*/
- cnts = atomic_fetch_add_acquire(_QR_BIAS, &lock->cnts);
- rspin_until_writer_unlock(lock, cnts);
+ atomic_cond_read_acquire(&lock->cnts, !(VAL & _QW_LOCKED));
/*
* Signal the next one in queue to become queue head
@@ -110,8 +70,6 @@ EXPORT_SYMBOL(queued_read_lock_slowpath);
*/
void queued_write_lock_slowpath(struct qrwlock *lock)
{
- u32 cnts;
-
/* Put the writer into the wait queue */
arch_spin_lock(&lock->wait_lock);
@@ -120,30 +78,14 @@ void queued_write_lock_slowpath(struct qrwlock *lock)
(atomic_cmpxchg_acquire(&lock->cnts, 0, _QW_LOCKED) == 0))
goto unlock;
- /*
- * Set the waiting flag to notify readers that a writer is pending,
- * or wait for a previous writer to go away.
- */
- for (;;) {
- struct __qrwlock *l = (struct __qrwlock *)lock;
-
- if (!READ_ONCE(l->wmode) &&
- (cmpxchg_relaxed(&l->wmode, 0, _QW_WAITING) == 0))
- break;
+ /* Set the waiting flag to notify readers that a writer is pending */
+ atomic_add(_QW_WAITING, &lock->cnts);
- cpu_relax();
- }
-
- /* When no more readers, set the locked flag */
- for (;;) {
- cnts = atomic_read(&lock->cnts);
- if ((cnts == _QW_WAITING) &&
- (atomic_cmpxchg_acquire(&lock->cnts, _QW_WAITING,
- _QW_LOCKED) == _QW_WAITING))
- break;
-
- cpu_relax();
- }
+ /* When no more readers or writers, set the locked flag */
+ do {
+ atomic_cond_read_acquire(&lock->cnts, VAL == _QW_WAITING);
+ } while (atomic_cmpxchg_relaxed(&lock->cnts, _QW_WAITING,
+ _QW_LOCKED) != _QW_WAITING);
unlock:
arch_spin_unlock(&lock->wait_lock);
}
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 15b6a39366c6..6ee477765e6c 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -61,21 +61,50 @@ struct pv_node {
#include "qspinlock_stat.h"
/*
+ * Hybrid PV queued/unfair lock
+ *
* By replacing the regular queued_spin_trylock() with the function below,
* it will be called once when a lock waiter enter the PV slowpath before
- * being queued. By allowing one lock stealing attempt here when the pending
- * bit is off, it helps to reduce the performance impact of lock waiter
- * preemption without the drawback of lock starvation.
+ * being queued.
+ *
+ * The pending bit is set by the queue head vCPU of the MCS wait queue in
+ * pv_wait_head_or_lock() to signal that it is ready to spin on the lock.
+ * When that bit becomes visible to the incoming waiters, no lock stealing
+ * is allowed. The function will return immediately to make the waiters
+ * enter the MCS wait queue. So lock starvation shouldn't happen as long
+ * as the queued mode vCPUs are actively running to set the pending bit
+ * and hence disabling lock stealing.
+ *
+ * When the pending bit isn't set, the lock waiters will stay in the unfair
+ * mode spinning on the lock unless the MCS wait queue is empty. In this
+ * case, the lock waiters will enter the queued mode slowpath trying to
+ * become the queue head and set the pending bit.
+ *
+ * This hybrid PV queued/unfair lock combines the best attributes of a
+ * queued lock (no lock starvation) and an unfair lock (good performance
+ * on not heavily contended locks).
*/
-#define queued_spin_trylock(l) pv_queued_spin_steal_lock(l)
-static inline bool pv_queued_spin_steal_lock(struct qspinlock *lock)
+#define queued_spin_trylock(l) pv_hybrid_queued_unfair_trylock(l)
+static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
{
struct __qspinlock *l = (void *)lock;
- if (!(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) &&
- (cmpxchg_acquire(&l->locked, 0, _Q_LOCKED_VAL) == 0)) {
- qstat_inc(qstat_pv_lock_stealing, true);
- return true;
+ /*
+ * Stay in unfair lock mode as long as queued mode waiters are
+ * present in the MCS wait queue but the pending bit isn't set.
+ */
+ for (;;) {
+ int val = atomic_read(&lock->val);
+
+ if (!(val & _Q_LOCKED_PENDING_MASK) &&
+ (cmpxchg_acquire(&l->locked, 0, _Q_LOCKED_VAL) == 0)) {
+ qstat_inc(qstat_pv_lock_stealing, true);
+ return true;
+ }
+ if (!(val & _Q_TAIL_MASK) || (val & _Q_PENDING_MASK))
+ break;
+
+ cpu_relax();
}
return false;
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index a6c76a4832b4..f549c552dbf1 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -29,6 +29,22 @@ void __sched down_read(struct rw_semaphore *sem)
EXPORT_SYMBOL(down_read);
+int __sched down_read_killable(struct rw_semaphore *sem)
+{
+ might_sleep();
+ rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);
+
+ if (LOCK_CONTENDED_RETURN(sem, __down_read_trylock, __down_read_killable)) {
+ rwsem_release(&sem->dep_map, 1, _RET_IP_);
+ return -EINTR;
+ }
+
+ rwsem_set_reader_owned(sem);
+ return 0;
+}
+
+EXPORT_SYMBOL(down_read_killable);
+
/*
* trylock for reading -- returns 1 if successful, 0 if contention
*/
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 6e40fdfba326..1fd1a7543cdd 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -30,11 +30,10 @@
#if !defined(CONFIG_GENERIC_LOCKBREAK) || defined(CONFIG_DEBUG_LOCK_ALLOC)
/*
* The __lock_function inlines are taken from
- * include/linux/spinlock_api_smp.h
+ * spinlock : include/linux/spinlock_api_smp.h
+ * rwlock : include/linux/rwlock_api_smp.h
*/
#else
-#define raw_read_can_lock(l) read_can_lock(l)
-#define raw_write_can_lock(l) write_can_lock(l)
/*
* Some architectures can relax in favour of the CPU owning the lock.
@@ -69,7 +68,7 @@ void __lockfunc __raw_##op##_lock(locktype##_t *lock) \
\
if (!(lock)->break_lock) \
(lock)->break_lock = 1; \
- while (!raw_##op##_can_lock(lock) && (lock)->break_lock)\
+ while ((lock)->break_lock) \
arch_##op##_relax(&lock->raw_lock); \
} \
(lock)->break_lock = 0; \
@@ -89,7 +88,7 @@ unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock) \
\
if (!(lock)->break_lock) \
(lock)->break_lock = 1; \
- while (!raw_##op##_can_lock(lock) && (lock)->break_lock)\
+ while ((lock)->break_lock) \
arch_##op##_relax(&lock->raw_lock); \
} \
(lock)->break_lock = 0; \
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index e4fe06d42385..f9c0ca2ccf0c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -734,7 +734,7 @@ static int rcu_future_needs_gp(struct rcu_state *rsp)
int idx = (READ_ONCE(rnp->completed) + 1) & 0x1;
int *fp = &rnp->need_future_gp[idx];
- RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_future_needs_gp() invoked with irqs enabled!!!");
+ lockdep_assert_irqs_disabled();
return READ_ONCE(*fp);
}
@@ -746,7 +746,7 @@ static int rcu_future_needs_gp(struct rcu_state *rsp)
static bool
cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
{
- RCU_LOCKDEP_WARN(!irqs_disabled(), "cpu_needs_another_gp() invoked with irqs enabled!!!");
+ lockdep_assert_irqs_disabled();
if (rcu_gp_in_progress(rsp))
return false; /* No, a grace period is already in progress. */
if (rcu_future_needs_gp(rsp))
@@ -773,7 +773,7 @@ static void rcu_eqs_enter_common(bool user)
struct rcu_data *rdp;
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
- RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_eqs_enter_common() invoked with irqs enabled!!!");
+ lockdep_assert_irqs_disabled();
trace_rcu_dyntick(TPS("Start"), rdtp->dynticks_nesting, 0);
if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
!user && !is_idle_task(current)) {
@@ -843,7 +843,7 @@ static void rcu_eqs_enter(bool user)
*/
void rcu_idle_enter(void)
{
- RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_idle_enter() invoked with irqs enabled!!!");
+ lockdep_assert_irqs_disabled();
rcu_eqs_enter(false);
}
@@ -861,7 +861,7 @@ void rcu_idle_enter(void)
*/
void rcu_user_enter(void)
{
- RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_user_enter() invoked with irqs enabled!!!");
+ lockdep_assert_irqs_disabled();
rcu_eqs_enter(true);
}
#endif /* CONFIG_NO_HZ_FULL */
@@ -889,7 +889,7 @@ void rcu_irq_exit(void)
{
struct rcu_dynticks *rdtp;
- RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!");
+ lockdep_assert_irqs_disabled();
rdtp = this_cpu_ptr(&rcu_dynticks);
/* Page faults can happen in NMI handlers, so check... */
@@ -959,7 +959,7 @@ static void rcu_eqs_exit(bool user)
struct rcu_dynticks *rdtp;
long long oldval;
- RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_eqs_exit() invoked with irqs enabled!!!");
+ lockdep_assert_irqs_disabled();
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
@@ -1039,7 +1039,7 @@ void rcu_irq_enter(void)
struct rcu_dynticks *rdtp;
long long oldval;
- RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!");
+ lockdep_assert_irqs_disabled();
rdtp = this_cpu_ptr(&rcu_dynticks);
/* Page faults can happen in NMI handlers, so check... */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 4c857e583802..dd4d0d390e5b 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -326,7 +326,7 @@ static void rcu_preempt_note_context_switch(bool preempt)
struct rcu_data *rdp;
struct rcu_node *rnp;
- RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_preempt_note_context_switch() invoked with interrupts enabled!!!\n");
+ lockdep_assert_irqs_disabled();
WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0);
if (t->rcu_read_lock_nesting > 0 &&
!t->rcu_read_unlock_special.b.blocked) {
@@ -1420,7 +1420,7 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
unsigned long dj;
- RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_needs_cpu() invoked with irqs enabled!!!");
+ lockdep_assert_irqs_disabled();
/* Snapshot to detect later posting of non-lazy callback. */
rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
@@ -1469,7 +1469,7 @@ static void rcu_prepare_for_idle(void)
struct rcu_state *rsp;
int tne;
- RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_prepare_for_idle() invoked with irqs enabled!!!");
+ lockdep_assert_irqs_disabled();
if (rcu_is_nocb_cpu(smp_processor_id()))
return;
@@ -1524,7 +1524,7 @@ static void rcu_prepare_for_idle(void)
*/
static void rcu_cleanup_after_idle(void)
{
- RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_cleanup_after_idle() invoked with irqs enabled!!!");
+ lockdep_assert_irqs_disabled();
if (rcu_is_nocb_cpu(smp_processor_id()))
return;
if (rcu_try_advance_all_cbs())
@@ -2016,7 +2016,7 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_data *my_rdp,
struct rcu_data *rdp,
unsigned long flags)
{
- RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_nocb_adopt_orphan_cbs() invoked with irqs enabled!!!");
+ lockdep_assert_irqs_disabled();
if (!rcu_is_nocb_cpu(smp_processor_id()))
return false; /* Not NOCBs CPU, caller must migrate CBs. */
__call_rcu_nocb_enqueue(my_rdp, rcu_segcblist_head(&rdp->cblist),
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index ca0f8fc945c6..e086babe6c61 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -388,7 +388,7 @@ void sched_clock_tick(void)
if (unlikely(!sched_clock_running))
return;
- WARN_ON_ONCE(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
scd = this_scd();
__scd_stamp(scd);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 14d2dbf97c53..9be8b68a66da 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -259,8 +259,7 @@ static inline u64 account_other_time(u64 max)
{
u64 accounted;
- /* Shall be converted to a lockdep-enabled lightweight check */
- WARN_ON_ONCE(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
accounted = steal_account_process_time(max);
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 418a1c045933..5f0dfb2abb8d 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -190,7 +190,7 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd,
u32 ret = SECCOMP_RET_ALLOW;
/* Make sure cross-thread synced filter points somewhere sane. */
struct seccomp_filter *f =
- lockless_dereference(current->seccomp.filter);
+ READ_ONCE(current->seccomp.filter);
/* Ensure unexpected behavior doesn't result in failing open. */
if (unlikely(WARN_ON(f == NULL)))
diff --git a/kernel/smp.c b/kernel/smp.c
index c94dd85c8d41..084c8b3a2681 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -213,7 +213,7 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
call_single_data_t *csd, *csd_next;
static bool warned;
- WARN_ON(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
head = this_cpu_ptr(&call_single_queue);
entry = llist_del_all(head);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 4e09821f9d9e..662f7b1b7a78 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -137,7 +137,7 @@ EXPORT_SYMBOL(__local_bh_disable_ip);
static void __local_bh_enable(unsigned int cnt)
{
- WARN_ON_ONCE(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
if (softirq_count() == (cnt & SOFTIRQ_MASK))
trace_softirqs_on(_RET_IP_);
@@ -158,7 +158,8 @@ EXPORT_SYMBOL(_local_bh_enable);
void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
{
- WARN_ON_ONCE(in_irq() || irqs_disabled());
+ WARN_ON_ONCE(in_irq());
+ lockdep_assert_irqs_enabled();
#ifdef CONFIG_TRACE_IRQFLAGS
local_irq_disable();
#endif
@@ -396,9 +397,8 @@ void irq_exit(void)
#ifndef __ARCH_IRQ_EXIT_IRQS_DISABLED
local_irq_disable();
#else
- WARN_ON_ONCE(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
#endif
-
account_irq_exit_time(current);
preempt_count_sub(HARDIRQ_OFFSET);
if (!in_interrupt() && local_softirq_pending())
@@ -488,7 +488,7 @@ EXPORT_SYMBOL(__tasklet_hi_schedule);
void __tasklet_hi_schedule_first(struct tasklet_struct *t)
{
- BUG_ON(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
t->next = __this_cpu_read(tasklet_hi_vec.head);
__this_cpu_write(tasklet_hi_vec.head, t);
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 5718b3ea202a..0fef395662a6 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -68,7 +68,7 @@ task_work_cancel(struct task_struct *task, task_work_func_t func)
* we raced with task_work_run(), *pprev == NULL/exited.
*/
raw_spin_lock_irqsave(&task->pi_lock, flags);
- while ((work = lockless_dereference(*pprev))) {
+ while ((work = READ_ONCE(*pprev))) {
if (work->func != func)
pprev = &work->next;
else if (cmpxchg(pprev, work, work->next) == work)
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 88f75f92ef36..d32520840fde 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -758,9 +758,7 @@ void clock_was_set(void)
*/
void hrtimers_resume(void)
{
- WARN_ONCE(!irqs_disabled(),
- KERN_INFO "hrtimers_resume() called with IRQs enabled!");
-
+ lockdep_assert_irqs_disabled();
/* Retrigger on the local CPU */
retrigger_next_event(NULL);
/* And schedule a retrigger for all others */
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 5b117110b55b..1f27887aa194 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -603,7 +603,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
/*
* Disarm any old timer after extracting its expiry time.
*/
- WARN_ON_ONCE(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
ret = 0;
old_incr = timer->it.cpu.incr;
@@ -1034,7 +1034,7 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer)
/*
* Now re-arm for the new expiry time.
*/
- WARN_ON_ONCE(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
arm_timer(timer);
unlock:
unlock_task_sighand(p, &flags);
@@ -1125,7 +1125,7 @@ void run_posix_cpu_timers(struct task_struct *tsk)
struct k_itimer *timer, *next;
unsigned long flags;
- WARN_ON_ONCE(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
/*
* The fast path checks that there are no expired thread or thread
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index c7a899c5ce64..dd4b7b492c9b 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -198,7 +198,7 @@ static bool check_tick_dependency(atomic_t *dep)
static bool can_stop_full_tick(int cpu, struct tick_sched *ts)
{
- WARN_ON_ONCE(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
if (unlikely(!cpu_online(cpu)))
return false;
@@ -960,8 +960,7 @@ void tick_nohz_idle_enter(void)
{
struct tick_sched *ts;
- WARN_ON_ONCE(irqs_disabled());
-
+ lockdep_assert_irqs_enabled();
/*
* Update the idle state in the scheduler domain hierarchy
* when tick_nohz_stop_sched_tick() is called from the idle loop.
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 81279c6602ff..845f3805c73d 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2724,7 +2724,7 @@ rb_reserve_next_event(struct ring_buffer *buffer,
* if it happened, we have to fail the write.
*/
barrier();
- if (unlikely(ACCESS_ONCE(cpu_buffer->buffer) != buffer)) {
+ if (unlikely(READ_ONCE(cpu_buffer->buffer) != buffer)) {
local_dec(&cpu_buffer->committing);
local_dec(&cpu_buffer->commits);
return NULL;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 401b0639116f..6b0b343a36a2 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1460,7 +1460,7 @@ extern struct trace_event_file *find_event_file(struct trace_array *tr,
static inline void *event_file_data(struct file *filp)
{
- return ACCESS_ONCE(file_inode(filp)->i_private);
+ return READ_ONCE(file_inode(filp)->i_private);
}
extern struct mutex event_mutex;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 719a52a4064a..734accc02418 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -78,7 +78,7 @@ check_stack(unsigned long ip, unsigned long *stack)
{
unsigned long this_size, flags; unsigned long *p, *top, *start;
static int tracer_frame;
- int frame_size = ACCESS_ONCE(tracer_frame);
+ int frame_size = READ_ONCE(tracer_frame);
int i, x;
this_size = ((unsigned long)stack) & (THREAD_SIZE-1);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index c490f1e4313b..d32b45662fb6 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -894,7 +894,7 @@ static bool new_idmap_permitted(const struct file *file,
int proc_setgroups_show(struct seq_file *seq, void *v)
{
struct user_namespace *ns = seq->private;
- unsigned long userns_flags = ACCESS_ONCE(ns->flags);
+ unsigned long userns_flags = READ_ONCE(ns->flags);
seq_printf(seq, "%s\n",
(userns_flags & USERNS_SETGROUPS_ALLOWED) ?
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index a2dccfe1acec..13f67b5a0a0c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1376,7 +1376,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
* queued or lose PENDING. Grabbing PENDING and queueing should
* happen with IRQ disabled.
*/
- WARN_ON_ONCE(!irqs_disabled());
+ lockdep_assert_irqs_disabled();
debug_work_activate(work);
@@ -2491,15 +2491,8 @@ static void insert_wq_barrier(struct pool_workqueue *pwq,
INIT_WORK_ONSTACK(&barr->work, wq_barrier_func);
__set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work));
- /*
- * Explicitly init the crosslock for wq_barrier::done, make its lock
- * key a subkey of the corresponding work. As a result we won't
- * build a dependency between wq_barrier::done and unrelated work.
- */
- lockdep_init_map_crosslock((struct lockdep_map *)&barr->done.map,
- "(complete)wq_barr::done",
- target->lockdep_map.key, 1);
- __init_completion(&barr->done);
+ init_completion_map(&barr->done, &target->lockdep_map);
+
barr->task = current;
/*
@@ -2605,16 +2598,13 @@ void flush_workqueue(struct workqueue_struct *wq)
struct wq_flusher this_flusher = {
.list = LIST_HEAD_INIT(this_flusher.list),
.flush_color = -1,
- .done = COMPLETION_INITIALIZER_ONSTACK(this_flusher.done),
+ .done = COMPLETION_INITIALIZER_ONSTACK_MAP(this_flusher.done, wq->lockdep_map),
};
int next_color;
if (WARN_ON(!wq_online))
return;
- lock_map_acquire(&wq->lockdep_map);
- lock_map_release(&wq->lockdep_map);
-
mutex_lock(&wq->mutex);
/*
@@ -2877,9 +2867,6 @@ bool flush_work(struct work_struct *work)
if (WARN_ON(!wq_online))
return false;
- lock_map_acquire(&work->lockdep_map);
- lock_map_release(&work->lockdep_map);
-
if (start_flush_work(work, &barr)) {
wait_for_completion(&barr.done);
destroy_work_on_stack(&barr.work);
@@ -4640,7 +4627,7 @@ static void rebind_workers(struct worker_pool *pool)
* concurrency management. Note that when or whether
* @worker clears REBOUND doesn't affect correctness.
*
- * ACCESS_ONCE() is necessary because @worker->flags may be
+ * WRITE_ONCE() is necessary because @worker->flags may be
* tested without holding any lock in
* wq_worker_waking_up(). Without it, NOT_RUNNING test may
* fail incorrectly leading to premature concurrency
@@ -4649,7 +4636,7 @@ static void rebind_workers(struct worker_pool *pool)
WARN_ON_ONCE(!(worker_flags & WORKER_UNBOUND));
worker_flags |= WORKER_REBOUND;
worker_flags &= ~WORKER_UNBOUND;
- ACCESS_ONCE(worker->flags) = worker_flags;
+ WRITE_ONCE(worker->flags, worker_flags);
}
spin_unlock_irq(&pool->lock);