summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/futex.c14
-rw-r--r--kernel/jump_label.c36
-rw-r--r--kernel/locking/mutex.c9
-rw-r--r--kernel/locking/qspinlock.c60
-rw-r--r--kernel/sched/fair.c33
-rw-r--r--kernel/sched/idle.c2
-rw-r--r--kernel/trace/trace_printk.c7
7 files changed, 142 insertions, 19 deletions
diff --git a/kernel/futex.c b/kernel/futex.c
index c20f06f38..6555d5459 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -469,7 +469,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
{
unsigned long address = (unsigned long)uaddr;
struct mm_struct *mm = current->mm;
- struct page *page;
+ struct page *page, *tail;
struct address_space *mapping;
int err, ro = 0;
@@ -530,7 +530,15 @@ again:
* considered here and page lock forces unnecessarily serialization
* From this point on, mapping will be re-verified if necessary and
* page lock will be acquired only if it is unavoidable
- */
+ *
+ * Mapping checks require the head page for any compound page so the
+ * head page and mapping is looked up now. For anonymous pages, it
+ * does not matter if the page splits in the future as the key is
+ * based on the address. For filesystem-backed pages, the tail is
+ * required as the index of the page determines the key. For
+ * base pages, there is no tail page and tail == page.
+ */
+ tail = page;
page = compound_head(page);
mapping = READ_ONCE(page->mapping);
@@ -654,7 +662,7 @@ again:
key->both.offset |= FUT_OFF_INODE; /* inode-based key */
key->shared.inode = inode;
- key->shared.pgoff = basepage_index(page);
+ key->shared.pgoff = basepage_index(tail);
rcu_read_unlock();
}
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 05254eeb4..4b353e0be 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -58,13 +58,36 @@ static void jump_label_update(struct static_key *key);
void static_key_slow_inc(struct static_key *key)
{
+ int v, v1;
+
STATIC_KEY_CHECK_USE();
- if (atomic_inc_not_zero(&key->enabled))
- return;
+
+ /*
+ * Careful if we get concurrent static_key_slow_inc() calls;
+ * later calls must wait for the first one to _finish_ the
+ * jump_label_update() process. At the same time, however,
+ * the jump_label_update() call below wants to see
+ * static_key_enabled(&key) for jumps to be updated properly.
+ *
+ * So give a special meaning to negative key->enabled: it sends
+ * static_key_slow_inc() down the slow path, and it is non-zero
+ * so it counts as "enabled" in jump_label_update(). Note that
+ * atomic_inc_unless_negative() checks >= 0, so roll our own.
+ */
+ for (v = atomic_read(&key->enabled); v > 0; v = v1) {
+ v1 = atomic_cmpxchg(&key->enabled, v, v + 1);
+ if (likely(v1 == v))
+ return;
+ }
jump_label_lock();
- if (atomic_inc_return(&key->enabled) == 1)
+ if (atomic_read(&key->enabled) == 0) {
+ atomic_set(&key->enabled, -1);
jump_label_update(key);
+ atomic_set(&key->enabled, 1);
+ } else {
+ atomic_inc(&key->enabled);
+ }
jump_label_unlock();
}
EXPORT_SYMBOL_GPL(static_key_slow_inc);
@@ -72,6 +95,13 @@ EXPORT_SYMBOL_GPL(static_key_slow_inc);
static void __static_key_slow_dec(struct static_key *key,
unsigned long rate_limit, struct delayed_work *work)
{
+ /*
+ * The negative count check is valid even when a negative
+ * key->enabled is in use by static_key_slow_inc(); a
+ * __static_key_slow_dec() before the first static_key_slow_inc()
+ * returns is unbalanced, because all other static_key_slow_inc()
+ * instances block while the update is in progress.
+ */
if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
WARN(atomic_read(&key->enabled) < 0,
"jump label: negative count!\n");
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index e364b424b..79d2d765a 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -486,9 +486,6 @@ __ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx)
if (!hold_ctx)
return 0;
- if (unlikely(ctx == hold_ctx))
- return -EALREADY;
-
if (ctx->stamp - hold_ctx->stamp <= LONG_MAX &&
(ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) {
#ifdef CONFIG_DEBUG_MUTEXES
@@ -514,6 +511,12 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
unsigned long flags;
int ret;
+ if (use_ww_ctx) {
+ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+ if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
+ return -EALREADY;
+ }
+
preempt_disable();
mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index ce2f75e32..5fc8c311b 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -267,6 +267,66 @@ static __always_inline u32 __pv_wait_head_or_lock(struct qspinlock *lock,
#define queued_spin_lock_slowpath native_queued_spin_lock_slowpath
#endif
+/*
+ * queued_spin_lock_slowpath() can (load-)ACQUIRE the lock before
+ * issuing an _unordered_ store to set _Q_LOCKED_VAL.
+ *
+ * This means that the store can be delayed, but no later than the
+ * store-release from the unlock. This means that simply observing
+ * _Q_LOCKED_VAL is not sufficient to determine if the lock is acquired.
+ *
+ * There are two paths that can issue the unordered store:
+ *
+ * (1) clear_pending_set_locked(): *,1,0 -> *,0,1
+ *
+ * (2) set_locked(): t,0,0 -> t,0,1 ; t != 0
+ * atomic_cmpxchg_relaxed(): t,0,0 -> 0,0,1
+ *
+ * However, in both cases we have other !0 state we've set before to queue
+ * ourseves:
+ *
+ * For (1) we have the atomic_cmpxchg_acquire() that set _Q_PENDING_VAL, our
+ * load is constrained by that ACQUIRE to not pass before that, and thus must
+ * observe the store.
+ *
+ * For (2) we have a more intersting scenario. We enqueue ourselves using
+ * xchg_tail(), which ends up being a RELEASE. This in itself is not
+ * sufficient, however that is followed by an smp_cond_acquire() on the same
+ * word, giving a RELEASE->ACQUIRE ordering. This again constrains our load and
+ * guarantees we must observe that store.
+ *
+ * Therefore both cases have other !0 state that is observable before the
+ * unordered locked byte store comes through. This means we can use that to
+ * wait for the lock store, and then wait for an unlock.
+ */
+#ifndef queued_spin_unlock_wait
+void queued_spin_unlock_wait(struct qspinlock *lock)
+{
+ u32 val;
+
+ for (;;) {
+ val = atomic_read(&lock->val);
+
+ if (!val) /* not locked, we're done */
+ goto done;
+
+ if (val & _Q_LOCKED_MASK) /* locked, go wait for unlock */
+ break;
+
+ /* not locked, but pending, wait until we observe the lock */
+ cpu_relax();
+ }
+
+ /* any unlock is good */
+ while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
+ cpu_relax();
+
+done:
+ smp_rmb(); /* CTRL + RMB -> ACQUIRE */
+}
+EXPORT_SYMBOL(queued_spin_unlock_wait);
+#endif
+
#endif /* _GEN_PV_LOCK_SLOWPATH */
/**
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5518a9621..7078bba60 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2846,6 +2846,23 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
+/*
+ * Unsigned subtract and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define sub_positive(_ptr, _val) do { \
+ typeof(_ptr) ptr = (_ptr); \
+ typeof(*ptr) val = (_val); \
+ typeof(*ptr) res, var = READ_ONCE(*ptr); \
+ res = var - val; \
+ if (res > var) \
+ res = 0; \
+ WRITE_ONCE(*ptr, res); \
+} while (0)
+
/* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
{
@@ -2854,15 +2871,15 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
if (atomic_long_read(&cfs_rq->removed_load_avg)) {
s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
- sa->load_avg = max_t(long, sa->load_avg - r, 0);
- sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
+ sub_positive(&sa->load_avg, r);
+ sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
removed = 1;
}
if (atomic_long_read(&cfs_rq->removed_util_avg)) {
long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
- sa->util_avg = max_t(long, sa->util_avg - r, 0);
- sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0);
+ sub_positive(&sa->util_avg, r);
+ sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
}
decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
@@ -2952,10 +2969,10 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
&se->avg, se->on_rq * scale_load_down(se->load.weight),
cfs_rq->curr == se, NULL);
- cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
- cfs_rq->avg.load_sum = max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0);
- cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
- cfs_rq->avg.util_sum = max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0);
+ sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
+ sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
+ sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
+ sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
}
/* Add the load generated by se into cfs_rq's load average */
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index f9d1dbfbe..e362a836c 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -131,7 +131,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
*/
static void cpuidle_idle_call(void)
{
- struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+ struct cpuidle_device *dev = cpuidle_get_device();
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index f96f0383f..ad1d6164e 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -36,6 +36,10 @@ struct trace_bprintk_fmt {
static inline struct trace_bprintk_fmt *lookup_format(const char *fmt)
{
struct trace_bprintk_fmt *pos;
+
+ if (!fmt)
+ return ERR_PTR(-EINVAL);
+
list_for_each_entry(pos, &trace_bprintk_fmt_list, list) {
if (!strcmp(pos->fmt, fmt))
return pos;
@@ -57,7 +61,8 @@ void hold_module_trace_bprintk_format(const char **start, const char **end)
for (iter = start; iter < end; iter++) {
struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter);
if (tb_fmt) {
- *iter = tb_fmt->fmt;
+ if (!IS_ERR(tb_fmt))
+ *iter = tb_fmt->fmt;
continue;
}