summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/futex.c235
-rw-r--r--kernel/hw_breakpoint.c2
-rw-r--r--kernel/kprobes.c565
-rw-r--r--kernel/perf_event.c573
-rw-r--r--kernel/power/suspend.c3
-rw-r--r--kernel/rcutiny.c105
-rw-r--r--kernel/rcutiny_plugin.h433
-rw-r--r--kernel/rcutorture.c270
-rw-r--r--kernel/rcutree.c156
-rw-r--r--kernel/rcutree.h61
-rw-r--r--kernel/rcutree_plugin.h135
-rw-r--r--kernel/rcutree_trace.c12
-rw-r--r--kernel/sched.c71
-rw-r--r--kernel/srcu.c8
-rw-r--r--kernel/sysctl.c16
-rw-r--r--kernel/sysctl_binary.c1
-rw-r--r--kernel/trace/Kconfig15
-rw-r--r--kernel/trace/power-traces.c5
-rw-r--r--kernel/trace/trace_event_perf.c31
-rw-r--r--kernel/trace/trace_events.c6
-rw-r--r--kernel/trace/trace_export.c14
-rw-r--r--kernel/watchdog.c9
22 files changed, 2000 insertions, 726 deletions
diff --git a/kernel/futex.c b/kernel/futex.c
index 40a8777a27d0..3019b92e6917 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -69,6 +69,14 @@ int __read_mostly futex_cmpxchg_enabled;
#define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8)
/*
+ * Futex flags used to encode options to functions and preserve them across
+ * restarts.
+ */
+#define FLAGS_SHARED 0x01
+#define FLAGS_CLOCKRT 0x02
+#define FLAGS_HAS_TIMEOUT 0x04
+
+/*
* Priority Inheritance state:
*/
struct futex_pi_state {
@@ -123,6 +131,12 @@ struct futex_q {
u32 bitset;
};
+static const struct futex_q futex_q_init = {
+ /* list gets initialized in queue_me()*/
+ .key = FUTEX_KEY_INIT,
+ .bitset = FUTEX_BITSET_MATCH_ANY
+};
+
/*
* Hash buckets are shared by all the futex_keys that hash to the same
* location. Each key may have multiple futex_q structures, one for each task
@@ -283,8 +297,7 @@ again:
return 0;
}
-static inline
-void put_futex_key(int fshared, union futex_key *key)
+static inline void put_futex_key(union futex_key *key)
{
drop_futex_key_refs(key);
}
@@ -870,7 +883,8 @@ double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
/*
* Wake up waiters matching bitset queued on this futex (uaddr).
*/
-static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
+static int
+futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
@@ -881,7 +895,7 @@ static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
if (!bitset)
return -EINVAL;
- ret = get_futex_key(uaddr, fshared, &key);
+ ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key);
if (unlikely(ret != 0))
goto out;
@@ -907,7 +921,7 @@ static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
}
spin_unlock(&hb->lock);
- put_futex_key(fshared, &key);
+ put_futex_key(&key);
out:
return ret;
}
@@ -917,7 +931,7 @@ out:
* to this virtual address:
*/
static int
-futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
+futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
int nr_wake, int nr_wake2, int op)
{
union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
@@ -927,10 +941,10 @@ futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
int ret, op_ret;
retry:
- ret = get_futex_key(uaddr1, fshared, &key1);
+ ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1);
if (unlikely(ret != 0))
goto out;
- ret = get_futex_key(uaddr2, fshared, &key2);
+ ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2);
if (unlikely(ret != 0))
goto out_put_key1;
@@ -962,11 +976,11 @@ retry_private:
if (ret)
goto out_put_keys;
- if (!fshared)
+ if (!(flags & FLAGS_SHARED))
goto retry_private;
- put_futex_key(fshared, &key2);
- put_futex_key(fshared, &key1);
+ put_futex_key(&key2);
+ put_futex_key(&key1);
goto retry;
}
@@ -996,9 +1010,9 @@ retry_private:
double_unlock_hb(hb1, hb2);
out_put_keys:
- put_futex_key(fshared, &key2);
+ put_futex_key(&key2);
out_put_key1:
- put_futex_key(fshared, &key1);
+ put_futex_key(&key1);
out:
return ret;
}
@@ -1133,13 +1147,13 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
/**
* futex_requeue() - Requeue waiters from uaddr1 to uaddr2
* @uaddr1: source futex user address
- * @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
+ * @flags: futex flags (FLAGS_SHARED, etc.)
* @uaddr2: target futex user address
* @nr_wake: number of waiters to wake (must be 1 for requeue_pi)
* @nr_requeue: number of waiters to requeue (0-INT_MAX)
* @cmpval: @uaddr1 expected value (or %NULL)
* @requeue_pi: if we are attempting to requeue from a non-pi futex to a
- * pi futex (pi to pi requeue is not supported)
+ * pi futex (pi to pi requeue is not supported)
*
* Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire
* uaddr2 atomically on behalf of the top waiter.
@@ -1148,9 +1162,9 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
* >=0 - on success, the number of tasks requeued or woken
* <0 - on error
*/
-static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
- int nr_wake, int nr_requeue, u32 *cmpval,
- int requeue_pi)
+static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
+ u32 __user *uaddr2, int nr_wake, int nr_requeue,
+ u32 *cmpval, int requeue_pi)
{
union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
int drop_count = 0, task_count = 0, ret;
@@ -1191,10 +1205,10 @@ retry:
pi_state = NULL;
}
- ret = get_futex_key(uaddr1, fshared, &key1);
+ ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1);
if (unlikely(ret != 0))
goto out;
- ret = get_futex_key(uaddr2, fshared, &key2);
+ ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2);
if (unlikely(ret != 0))
goto out_put_key1;
@@ -1216,11 +1230,11 @@ retry_private:
if (ret)
goto out_put_keys;
- if (!fshared)
+ if (!(flags & FLAGS_SHARED))
goto retry_private;
- put_futex_key(fshared, &key2);
- put_futex_key(fshared, &key1);
+ put_futex_key(&key2);
+ put_futex_key(&key1);
goto retry;
}
if (curval != *cmpval) {
@@ -1260,8 +1274,8 @@ retry_private:
break;
case -EFAULT:
double_unlock_hb(hb1, hb2);
- put_futex_key(fshared, &key2);
- put_futex_key(fshared, &key1);
+ put_futex_key(&key2);
+ put_futex_key(&key1);
ret = fault_in_user_writeable(uaddr2);
if (!ret)
goto retry;
@@ -1269,8 +1283,8 @@ retry_private:
case -EAGAIN:
/* The owner was exiting, try again. */
double_unlock_hb(hb1, hb2);
- put_futex_key(fshared, &key2);
- put_futex_key(fshared, &key1);
+ put_futex_key(&key2);
+ put_futex_key(&key1);
cond_resched();
goto retry;
default:
@@ -1352,9 +1366,9 @@ out_unlock:
drop_futex_key_refs(&key1);
out_put_keys:
- put_futex_key(fshared, &key2);
+ put_futex_key(&key2);
out_put_key1:
- put_futex_key(fshared, &key1);
+ put_futex_key(&key1);
out:
if (pi_state != NULL)
free_pi_state(pi_state);
@@ -1494,7 +1508,7 @@ static void unqueue_me_pi(struct futex_q *q)
* private futexes.
*/
static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
- struct task_struct *newowner, int fshared)
+ struct task_struct *newowner)
{
u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
struct futex_pi_state *pi_state = q->pi_state;
@@ -1587,20 +1601,11 @@ handle_fault:
goto retry;
}
-/*
- * In case we must use restart_block to restart a futex_wait,
- * we encode in the 'flags' shared capability
- */
-#define FLAGS_SHARED 0x01
-#define FLAGS_CLOCKRT 0x02
-#define FLAGS_HAS_TIMEOUT 0x04
-
static long futex_wait_restart(struct restart_block *restart);
/**
* fixup_owner() - Post lock pi_state and corner case management
* @uaddr: user address of the futex
- * @fshared: whether the futex is shared (1) or not (0)
* @q: futex_q (contains pi_state and access to the rt_mutex)
* @locked: if the attempt to take the rt_mutex succeeded (1) or not (0)
*
@@ -1613,8 +1618,7 @@ static long futex_wait_restart(struct restart_block *restart);
* 0 - success, lock not taken
* <0 - on error (-EFAULT)
*/
-static int fixup_owner(u32 __user *uaddr, int fshared, struct futex_q *q,
- int locked)
+static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
{
struct task_struct *owner;
int ret = 0;
@@ -1625,7 +1629,7 @@ static int fixup_owner(u32 __user *uaddr, int fshared, struct futex_q *q,
* did a lock-steal - fix up the PI-state in that case:
*/
if (q->pi_state->owner != current)
- ret = fixup_pi_state_owner(uaddr, q, current, fshared);
+ ret = fixup_pi_state_owner(uaddr, q, current);
goto out;
}
@@ -1652,7 +1656,7 @@ static int fixup_owner(u32 __user *uaddr, int fshared, struct futex_q *q,
* lock. Fix the state up.
*/
owner = rt_mutex_owner(&q->pi_state->pi_mutex);
- ret = fixup_pi_state_owner(uaddr, q, owner, fshared);
+ ret = fixup_pi_state_owner(uaddr, q, owner);
goto out;
}
@@ -1715,7 +1719,7 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
* futex_wait_setup() - Prepare to wait on a futex
* @uaddr: the futex userspace address
* @val: the expected value
- * @fshared: whether the futex is shared (1) or not (0)
+ * @flags: futex flags (FLAGS_SHARED, etc.)
* @q: the associated futex_q
* @hb: storage for hash_bucket pointer to be returned to caller
*
@@ -1728,7 +1732,7 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
* 0 - uaddr contains val and hb has been locked
* <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlcoked
*/
-static int futex_wait_setup(u32 __user *uaddr, u32 val, int fshared,
+static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
struct futex_q *q, struct futex_hash_bucket **hb)
{
u32 uval;
@@ -1752,8 +1756,7 @@ static int futex_wait_setup(u32 __user *uaddr, u32 val, int fshared,
* rare, but normal.
*/
retry:
- q->key = FUTEX_KEY_INIT;
- ret = get_futex_key(uaddr, fshared, &q->key);
+ ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key);
if (unlikely(ret != 0))
return ret;
@@ -1769,10 +1772,10 @@ retry_private:
if (ret)
goto out;
- if (!fshared)
+ if (!(flags & FLAGS_SHARED))
goto retry_private;
- put_futex_key(fshared, &q->key);
+ put_futex_key(&q->key);
goto retry;
}
@@ -1783,32 +1786,29 @@ retry_private:
out:
if (ret)
- put_futex_key(fshared, &q->key);
+ put_futex_key(&q->key);
return ret;
}
-static int futex_wait(u32 __user *uaddr, int fshared,
- u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
+static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
+ ktime_t *abs_time, u32 bitset)
{
struct hrtimer_sleeper timeout, *to = NULL;
struct restart_block *restart;
struct futex_hash_bucket *hb;
- struct futex_q q;
+ struct futex_q q = futex_q_init;
int ret;
if (!bitset)
return -EINVAL;
-
- q.pi_state = NULL;
q.bitset = bitset;
- q.rt_waiter = NULL;
- q.requeue_pi_key = NULL;
if (abs_time) {
to = &timeout;
- hrtimer_init_on_stack(&to->timer, clockrt ? CLOCK_REALTIME :
- CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ?
+ CLOCK_REALTIME : CLOCK_MONOTONIC,
+ HRTIMER_MODE_ABS);
hrtimer_init_sleeper(to, current);
hrtimer_set_expires_range_ns(&to->timer, *abs_time,
current->timer_slack_ns);
@@ -1819,7 +1819,7 @@ retry:
* Prepare to wait on uaddr. On success, holds hb lock and increments
* q.key refs.
*/
- ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
+ ret = futex_wait_setup(uaddr, val, flags, &q, &hb);
if (ret)
goto out;
@@ -1852,12 +1852,7 @@ retry:
restart->futex.val = val;
restart->futex.time = abs_time->tv64;
restart->futex.bitset = bitset;
- restart->futex.flags = FLAGS_HAS_TIMEOUT;
-
- if (fshared)
- restart->futex.flags |= FLAGS_SHARED;
- if (clockrt)
- restart->futex.flags |= FLAGS_CLOCKRT;
+ restart->futex.flags = flags;
ret = -ERESTART_RESTARTBLOCK;
@@ -1873,7 +1868,6 @@ out:
static long futex_wait_restart(struct restart_block *restart)
{
u32 __user *uaddr = restart->futex.uaddr;
- int fshared = 0;
ktime_t t, *tp = NULL;
if (restart->futex.flags & FLAGS_HAS_TIMEOUT) {
@@ -1881,11 +1875,9 @@ static long futex_wait_restart(struct restart_block *restart)
tp = &t;
}
restart->fn = do_no_restart_syscall;
- if (restart->futex.flags & FLAGS_SHARED)
- fshared = 1;
- return (long)futex_wait(uaddr, fshared, restart->futex.val, tp,
- restart->futex.bitset,
- restart->futex.flags & FLAGS_CLOCKRT);
+
+ return (long)futex_wait(uaddr, restart->futex.flags,
+ restart->futex.val, tp, restart->futex.bitset);
}
@@ -1895,12 +1887,12 @@ static long futex_wait_restart(struct restart_block *restart)
* if there are waiters then it will block, it does PI, etc. (Due to
* races the kernel might see a 0 value of the futex too.)
*/
-static int futex_lock_pi(u32 __user *uaddr, int fshared,
- int detect, ktime_t *time, int trylock)
+static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, int detect,
+ ktime_t *time, int trylock)
{
struct hrtimer_sleeper timeout, *to = NULL;
struct futex_hash_bucket *hb;
- struct futex_q q;
+ struct futex_q q = futex_q_init;
int res, ret;
if (refill_pi_state_cache())
@@ -1914,12 +1906,8 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
hrtimer_set_expires(&to->timer, *time);
}
- q.pi_state = NULL;
- q.rt_waiter = NULL;
- q.requeue_pi_key = NULL;
retry:
- q.key = FUTEX_KEY_INIT;
- ret = get_futex_key(uaddr, fshared, &q.key);
+ ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key);
if (unlikely(ret != 0))
goto out;
@@ -1941,7 +1929,7 @@ retry_private:
* exit to complete.
*/
queue_unlock(&q, hb);
- put_futex_key(fshared, &q.key);
+ put_futex_key(&q.key);
cond_resched();
goto retry;
default:
@@ -1971,7 +1959,7 @@ retry_private:
* Fixup the pi_state owner and possibly acquire the lock if we
* haven't already.
*/
- res = fixup_owner(uaddr, fshared, &q, !ret);
+ res = fixup_owner(uaddr, &q, !ret);
/*
* If fixup_owner() returned an error, proprogate that. If it acquired
* the lock, clear our -ETIMEDOUT or -EINTR.
@@ -1995,7 +1983,7 @@ out_unlock_put_key:
queue_unlock(&q, hb);
out_put_key:
- put_futex_key(fshared, &q.key);
+ put_futex_key(&q.key);
out:
if (to)
destroy_hrtimer_on_stack(&to->timer);
@@ -2008,10 +1996,10 @@ uaddr_faulted:
if (ret)
goto out_put_key;
- if (!fshared)
+ if (!(flags & FLAGS_SHARED))
goto retry_private;
- put_futex_key(fshared, &q.key);
+ put_futex_key(&q.key);
goto retry;
}
@@ -2020,7 +2008,7 @@ uaddr_faulted:
* This is the in-kernel slowpath: we look up the PI state (if any),
* and do the rt-mutex unlock.
*/
-static int futex_unlock_pi(u32 __user *uaddr, int fshared)
+static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
@@ -2038,7 +2026,7 @@ retry:
if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current))
return -EPERM;
- ret = get_futex_key(uaddr, fshared, &key);
+ ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key);
if (unlikely(ret != 0))
goto out;
@@ -2093,14 +2081,14 @@ retry:
out_unlock:
spin_unlock(&hb->lock);
- put_futex_key(fshared, &key);
+ put_futex_key(&key);
out:
return ret;
pi_faulted:
spin_unlock(&hb->lock);
- put_futex_key(fshared, &key);
+ put_futex_key(&key);
ret = fault_in_user_writeable(uaddr);
if (!ret)
@@ -2160,7 +2148,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
/**
* futex_wait_requeue_pi() - Wait on uaddr and take uaddr2
* @uaddr: the futex we initially wait on (non-pi)
- * @fshared: whether the futexes are shared (1) or not (0). They must be
+ * @flags: futex flags (FLAGS_SHARED, FLAGS_CLOCKRT, etc.), they must be
* the same type, no requeueing from private to shared, etc.
* @val: the expected value of uaddr
* @abs_time: absolute timeout
@@ -2198,16 +2186,16 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
* 0 - On success
* <0 - On error
*/
-static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
+static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
u32 val, ktime_t *abs_time, u32 bitset,
- int clockrt, u32 __user *uaddr2)
+ u32 __user *uaddr2)
{
struct hrtimer_sleeper timeout, *to = NULL;
struct rt_mutex_waiter rt_waiter;
struct rt_mutex *pi_mutex = NULL;
struct futex_hash_bucket *hb;
- union futex_key key2;
- struct futex_q q;
+ union futex_key key2 = FUTEX_KEY_INIT;
+ struct futex_q q = futex_q_init;
int res, ret;
if (!bitset)
@@ -2215,8 +2203,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
if (abs_time) {
to = &timeout;
- hrtimer_init_on_stack(&to->timer, clockrt ? CLOCK_REALTIME :
- CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ?
+ CLOCK_REALTIME : CLOCK_MONOTONIC,
+ HRTIMER_MODE_ABS);
hrtimer_init_sleeper(to, current);
hrtimer_set_expires_range_ns(&to->timer, *abs_time,
current->timer_slack_ns);
@@ -2229,12 +2218,10 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
debug_rt_mutex_init_waiter(&rt_waiter);
rt_waiter.task = NULL;
- key2 = FUTEX_KEY_INIT;
- ret = get_futex_key(uaddr2, fshared, &key2);
+ ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2);
if (unlikely(ret != 0))
goto out;
- q.pi_state = NULL;
q.bitset = bitset;
q.rt_waiter = &rt_waiter;
q.requeue_pi_key = &key2;
@@ -2243,7 +2230,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
* Prepare to wait on uaddr. On success, increments q.key (key1) ref
* count.
*/
- ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
+ ret = futex_wait_setup(uaddr, val, flags, &q, &hb);
if (ret)
goto out_key2;
@@ -2273,8 +2260,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
*/
if (q.pi_state && (q.pi_state->owner != current)) {
spin_lock(q.lock_ptr);
- ret = fixup_pi_state_owner(uaddr2, &q, current,
- fshared);
+ ret = fixup_pi_state_owner(uaddr2, &q, current);
spin_unlock(q.lock_ptr);
}
} else {
@@ -2293,7 +2279,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
* Fixup the pi_state owner and possibly acquire the lock if we
* haven't already.
*/
- res = fixup_owner(uaddr2, fshared, &q, !ret);
+ res = fixup_owner(uaddr2, &q, !ret);
/*
* If fixup_owner() returned an error, proprogate that. If it
* acquired the lock, clear -ETIMEDOUT or -EINTR.
@@ -2324,9 +2310,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
}
out_put_keys:
- put_futex_key(fshared, &q.key);
+ put_futex_key(&q.key);
out_key2:
- put_futex_key(fshared, &key2);
+ put_futex_key(&key2);
out:
if (to) {
@@ -2551,58 +2537,57 @@ void exit_robust_list(struct task_struct *curr)
long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
u32 __user *uaddr2, u32 val2, u32 val3)
{
- int clockrt, ret = -ENOSYS;
- int cmd = op & FUTEX_CMD_MASK;
- int fshared = 0;
+ int ret = -ENOSYS, cmd = op & FUTEX_CMD_MASK;
+ unsigned int flags = 0;
if (!(op & FUTEX_PRIVATE_FLAG))
- fshared = 1;
+ flags |= FLAGS_SHARED;
- clockrt = op & FUTEX_CLOCK_REALTIME;
- if (clockrt && cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI)
- return -ENOSYS;
+ if (op & FUTEX_CLOCK_REALTIME) {
+ flags |= FLAGS_CLOCKRT;
+ if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI)
+ return -ENOSYS;
+ }
switch (cmd) {
case FUTEX_WAIT:
val3 = FUTEX_BITSET_MATCH_ANY;
case FUTEX_WAIT_BITSET:
- ret = futex_wait(uaddr, fshared, val, timeout, val3, clockrt);
+ ret = futex_wait(uaddr, flags, val, timeout, val3);
break;
case FUTEX_WAKE:
val3 = FUTEX_BITSET_MATCH_ANY;
case FUTEX_WAKE_BITSET:
- ret = futex_wake(uaddr, fshared, val, val3);
+ ret = futex_wake(uaddr, flags, val, val3);
break;
case FUTEX_REQUEUE:
- ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, NULL, 0);
+ ret = futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0);
break;
case FUTEX_CMP_REQUEUE:
- ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3,
- 0);
+ ret = futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0);
break;
case FUTEX_WAKE_OP:
- ret = futex_wake_op(uaddr, fshared, uaddr2, val, val2, val3);
+ ret = futex_wake_op(uaddr, flags, uaddr2, val, val2, val3);
break;
case FUTEX_LOCK_PI:
if (futex_cmpxchg_enabled)
- ret = futex_lock_pi(uaddr, fshared, val, timeout, 0);
+ ret = futex_lock_pi(uaddr, flags, val, timeout, 0);
break;
case FUTEX_UNLOCK_PI:
if (futex_cmpxchg_enabled)
- ret = futex_unlock_pi(uaddr, fshared);
+ ret = futex_unlock_pi(uaddr, flags);
break;
case FUTEX_TRYLOCK_PI:
if (futex_cmpxchg_enabled)
- ret = futex_lock_pi(uaddr, fshared, 0, timeout, 1);
+ ret = futex_lock_pi(uaddr, flags, 0, timeout, 1);
break;
case FUTEX_WAIT_REQUEUE_PI:
val3 = FUTEX_BITSET_MATCH_ANY;
- ret = futex_wait_requeue_pi(uaddr, fshared, val, timeout, val3,
- clockrt, uaddr2);
+ ret = futex_wait_requeue_pi(uaddr, flags, val, timeout, val3,
+ uaddr2);
break;
case FUTEX_CMP_REQUEUE_PI:
- ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3,
- 1);
+ ret = futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1);
break;
default:
ret = -ENOSYS;
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index e5325825aeb6..086adf25a55e 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -641,7 +641,7 @@ int __init init_hw_breakpoint(void)
constraints_initialized = 1;
- perf_pmu_register(&perf_breakpoint);
+ perf_pmu_register(&perf_breakpoint, "breakpoint", PERF_TYPE_BREAKPOINT);
return register_die_notifier(&hw_breakpoint_exceptions_nb);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 9737a76e106f..7663e5df0e6f 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -354,13 +354,20 @@ static inline int kprobe_aggrprobe(struct kprobe *p)
return p->pre_handler == aggr_pre_handler;
}
+/* Return true(!0) if the kprobe is unused */
+static inline int kprobe_unused(struct kprobe *p)
+{
+ return kprobe_aggrprobe(p) && kprobe_disabled(p) &&
+ list_empty(&p->list);
+}
+
/*
* Keep all fields in the kprobe consistent
*/
-static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p)
+static inline void copy_kprobe(struct kprobe *ap, struct kprobe *p)
{
- memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t));
- memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn));
+ memcpy(&p->opcode, &ap->opcode, sizeof(kprobe_opcode_t));
+ memcpy(&p->ainsn, &ap->ainsn, sizeof(struct arch_specific_insn));
}
#ifdef CONFIG_OPTPROBES
@@ -384,6 +391,17 @@ void __kprobes opt_pre_handler(struct kprobe *p, struct pt_regs *regs)
}
}
+/* Free optimized instructions and optimized_kprobe */
+static __kprobes void free_aggr_kprobe(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ op = container_of(p, struct optimized_kprobe, kp);
+ arch_remove_optimized_kprobe(op);
+ arch_remove_kprobe(p);
+ kfree(op);
+}
+
/* Return true(!0) if the kprobe is ready for optimization. */
static inline int kprobe_optready(struct kprobe *p)
{
@@ -397,6 +415,33 @@ static inline int kprobe_optready(struct kprobe *p)
return 0;
}
+/* Return true(!0) if the kprobe is disarmed. Note: p must be on hash list */
+static inline int kprobe_disarmed(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ /* If kprobe is not aggr/opt probe, just return kprobe is disabled */
+ if (!kprobe_aggrprobe(p))
+ return kprobe_disabled(p);
+
+ op = container_of(p, struct optimized_kprobe, kp);
+
+ return kprobe_disabled(p) && list_empty(&op->list);
+}
+
+/* Return true(!0) if the probe is queued on (un)optimizing lists */
+static int __kprobes kprobe_queued(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ if (kprobe_aggrprobe(p)) {
+ op = container_of(p, struct optimized_kprobe, kp);
+ if (!list_empty(&op->list))
+ return 1;
+ }
+ return 0;
+}
+
/*
* Return an optimized kprobe whose optimizing code replaces
* instructions including addr (exclude breakpoint).
@@ -422,30 +467,23 @@ static struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr)
/* Optimization staging list, protected by kprobe_mutex */
static LIST_HEAD(optimizing_list);
+static LIST_HEAD(unoptimizing_list);
static void kprobe_optimizer(struct work_struct *work);
static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
+static DECLARE_COMPLETION(optimizer_comp);
#define OPTIMIZE_DELAY 5
-/* Kprobe jump optimizer */
-static __kprobes void kprobe_optimizer(struct work_struct *work)
+/*
+ * Optimize (replace a breakpoint with a jump) kprobes listed on
+ * optimizing_list.
+ */
+static __kprobes void do_optimize_kprobes(void)
{
- struct optimized_kprobe *op, *tmp;
-
- /* Lock modules while optimizing kprobes */
- mutex_lock(&module_mutex);
- mutex_lock(&kprobe_mutex);
- if (kprobes_all_disarmed || !kprobes_allow_optimization)
- goto end;
-
- /*
- * Wait for quiesence period to ensure all running interrupts
- * are done. Because optprobe may modify multiple instructions
- * there is a chance that Nth instruction is interrupted. In that
- * case, running interrupt can return to 2nd-Nth byte of jump
- * instruction. This wait is for avoiding it.
- */
- synchronize_sched();
+ /* Optimization never be done when disarmed */
+ if (kprobes_all_disarmed || !kprobes_allow_optimization ||
+ list_empty(&optimizing_list))
+ return;
/*
* The optimization/unoptimization refers online_cpus via
@@ -459,17 +497,111 @@ static __kprobes void kprobe_optimizer(struct work_struct *work)
*/
get_online_cpus();
mutex_lock(&text_mutex);
- list_for_each_entry_safe(op, tmp, &optimizing_list, list) {
- WARN_ON(kprobe_disabled(&op->kp));
- if (arch_optimize_kprobe(op) < 0)
- op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
- list_del_init(&op->list);
+ arch_optimize_kprobes(&optimizing_list);
+ mutex_unlock(&text_mutex);
+ put_online_cpus();
+}
+
+/*
+ * Unoptimize (replace a jump with a breakpoint and remove the breakpoint
+ * if need) kprobes listed on unoptimizing_list.
+ */
+static __kprobes void do_unoptimize_kprobes(struct list_head *free_list)
+{
+ struct optimized_kprobe *op, *tmp;
+
+ /* Unoptimization must be done anytime */
+ if (list_empty(&unoptimizing_list))
+ return;
+
+ /* Ditto to do_optimize_kprobes */
+ get_online_cpus();
+ mutex_lock(&text_mutex);
+ arch_unoptimize_kprobes(&unoptimizing_list, free_list);
+ /* Loop free_list for disarming */
+ list_for_each_entry_safe(op, tmp, free_list, list) {
+ /* Disarm probes if marked disabled */
+ if (kprobe_disabled(&op->kp))
+ arch_disarm_kprobe(&op->kp);
+ if (kprobe_unused(&op->kp)) {
+ /*
+ * Remove unused probes from hash list. After waiting
+ * for synchronization, these probes are reclaimed.
+ * (reclaiming is done by do_free_cleaned_kprobes.)
+ */
+ hlist_del_rcu(&op->kp.hlist);
+ } else
+ list_del_init(&op->list);
}
mutex_unlock(&text_mutex);
put_online_cpus();
-end:
+}
+
+/* Reclaim all kprobes on the free_list */
+static __kprobes void do_free_cleaned_kprobes(struct list_head *free_list)
+{
+ struct optimized_kprobe *op, *tmp;
+
+ list_for_each_entry_safe(op, tmp, free_list, list) {
+ BUG_ON(!kprobe_unused(&op->kp));
+ list_del_init(&op->list);
+ free_aggr_kprobe(&op->kp);
+ }
+}
+
+/* Start optimizer after OPTIMIZE_DELAY passed */
+static __kprobes void kick_kprobe_optimizer(void)
+{
+ if (!delayed_work_pending(&optimizing_work))
+ schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY);
+}
+
+/* Kprobe jump optimizer */
+static __kprobes void kprobe_optimizer(struct work_struct *work)
+{
+ LIST_HEAD(free_list);
+
+ /* Lock modules while optimizing kprobes */
+ mutex_lock(&module_mutex);
+ mutex_lock(&kprobe_mutex);
+
+ /*
+ * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed)
+ * kprobes before waiting for quiesence period.
+ */
+ do_unoptimize_kprobes(&free_list);
+
+ /*
+ * Step 2: Wait for quiesence period to ensure all running interrupts
+ * are done. Because optprobe may modify multiple instructions
+ * there is a chance that Nth instruction is interrupted. In that
+ * case, running interrupt can return to 2nd-Nth byte of jump
+ * instruction. This wait is for avoiding it.
+ */
+ synchronize_sched();
+
+ /* Step 3: Optimize kprobes after quiesence period */
+ do_optimize_kprobes();
+
+ /* Step 4: Free cleaned kprobes after quiesence period */
+ do_free_cleaned_kprobes(&free_list);
+
mutex_unlock(&kprobe_mutex);
mutex_unlock(&module_mutex);
+
+ /* Step 5: Kick optimizer again if needed */
+ if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list))
+ kick_kprobe_optimizer();
+ else
+ /* Wake up all waiters */
+ complete_all(&optimizer_comp);
+}
+
+/* Wait for completing optimization and unoptimization */
+static __kprobes void wait_for_kprobe_optimizer(void)
+{
+ if (delayed_work_pending(&optimizing_work))
+ wait_for_completion(&optimizer_comp);
}
/* Optimize kprobe if p is ready to be optimized */
@@ -495,42 +627,99 @@ static __kprobes void optimize_kprobe(struct kprobe *p)
/* Check if it is already optimized. */
if (op->kp.flags & KPROBE_FLAG_OPTIMIZED)
return;
-
op->kp.flags |= KPROBE_FLAG_OPTIMIZED;
- list_add(&op->list, &optimizing_list);
- if (!delayed_work_pending(&optimizing_work))
- schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY);
+
+ if (!list_empty(&op->list))
+ /* This is under unoptimizing. Just dequeue the probe */
+ list_del_init(&op->list);
+ else {
+ list_add(&op->list, &optimizing_list);
+ kick_kprobe_optimizer();
+ }
+}
+
+/* Short cut to direct unoptimizing */
+static __kprobes void force_unoptimize_kprobe(struct optimized_kprobe *op)
+{
+ get_online_cpus();
+ arch_unoptimize_kprobe(op);
+ put_online_cpus();
+ if (kprobe_disabled(&op->kp))
+ arch_disarm_kprobe(&op->kp);
}
/* Unoptimize a kprobe if p is optimized */
-static __kprobes void unoptimize_kprobe(struct kprobe *p)
+static __kprobes void unoptimize_kprobe(struct kprobe *p, bool force)
{
struct optimized_kprobe *op;
- if ((p->flags & KPROBE_FLAG_OPTIMIZED) && kprobe_aggrprobe(p)) {
- op = container_of(p, struct optimized_kprobe, kp);
- if (!list_empty(&op->list))
- /* Dequeue from the optimization queue */
+ if (!kprobe_aggrprobe(p) || kprobe_disarmed(p))
+ return; /* This is not an optprobe nor optimized */
+
+ op = container_of(p, struct optimized_kprobe, kp);
+ if (!kprobe_optimized(p)) {
+ /* Unoptimized or unoptimizing case */
+ if (force && !list_empty(&op->list)) {
+ /*
+ * Only if this is unoptimizing kprobe and forced,
+ * forcibly unoptimize it. (No need to unoptimize
+ * unoptimized kprobe again :)
+ */
list_del_init(&op->list);
- else
- /* Replace jump with break */
- arch_unoptimize_kprobe(op);
- op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+ force_unoptimize_kprobe(op);
+ }
+ return;
+ }
+
+ op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+ if (!list_empty(&op->list)) {
+ /* Dequeue from the optimization queue */
+ list_del_init(&op->list);
+ return;
+ }
+ /* Optimized kprobe case */
+ if (force)
+ /* Forcibly update the code: this is a special case */
+ force_unoptimize_kprobe(op);
+ else {
+ list_add(&op->list, &unoptimizing_list);
+ kick_kprobe_optimizer();
}
}
+/* Cancel unoptimizing for reusing */
+static void reuse_unused_kprobe(struct kprobe *ap)
+{
+ struct optimized_kprobe *op;
+
+ BUG_ON(!kprobe_unused(ap));
+ /*
+ * Unused kprobe MUST be on the way of delayed unoptimizing (means
+ * there is still a relative jump) and disabled.
+ */
+ op = container_of(ap, struct optimized_kprobe, kp);
+ if (unlikely(list_empty(&op->list)))
+ printk(KERN_WARNING "Warning: found a stray unused "
+ "aggrprobe@%p\n", ap->addr);
+ /* Enable the probe again */
+ ap->flags &= ~KPROBE_FLAG_DISABLED;
+ /* Optimize it again (remove from op->list) */
+ BUG_ON(!kprobe_optready(ap));
+ optimize_kprobe(ap);
+}
+
/* Remove optimized instructions */
static void __kprobes kill_optimized_kprobe(struct kprobe *p)
{
struct optimized_kprobe *op;
op = container_of(p, struct optimized_kprobe, kp);
- if (!list_empty(&op->list)) {
- /* Dequeue from the optimization queue */
+ if (!list_empty(&op->list))
+ /* Dequeue from the (un)optimization queue */
list_del_init(&op->list);
- op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
- }
- /* Don't unoptimize, because the target code will be freed. */
+
+ op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+ /* Don't touch the code, because it is already freed. */
arch_remove_optimized_kprobe(op);
}
@@ -543,16 +732,6 @@ static __kprobes void prepare_optimized_kprobe(struct kprobe *p)
arch_prepare_optimized_kprobe(op);
}
-/* Free optimized instructions and optimized_kprobe */
-static __kprobes void free_aggr_kprobe(struct kprobe *p)
-{
- struct optimized_kprobe *op;
-
- op = container_of(p, struct optimized_kprobe, kp);
- arch_remove_optimized_kprobe(op);
- kfree(op);
-}
-
/* Allocate new optimized_kprobe and try to prepare optimized instructions */
static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
{
@@ -587,7 +766,8 @@ static __kprobes void try_to_optimize_kprobe(struct kprobe *p)
op = container_of(ap, struct optimized_kprobe, kp);
if (!arch_prepared_optinsn(&op->optinsn)) {
/* If failed to setup optimizing, fallback to kprobe */
- free_aggr_kprobe(ap);
+ arch_remove_optimized_kprobe(op);
+ kfree(op);
return;
}
@@ -631,21 +811,16 @@ static void __kprobes unoptimize_all_kprobes(void)
return;
kprobes_allow_optimization = false;
- printk(KERN_INFO "Kprobes globally unoptimized\n");
- get_online_cpus(); /* For avoiding text_mutex deadlock */
- mutex_lock(&text_mutex);
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
hlist_for_each_entry_rcu(p, node, head, hlist) {
if (!kprobe_disabled(p))
- unoptimize_kprobe(p);
+ unoptimize_kprobe(p, false);
}
}
-
- mutex_unlock(&text_mutex);
- put_online_cpus();
- /* Allow all currently running kprobes to complete */
- synchronize_sched();
+ /* Wait for unoptimizing completion */
+ wait_for_kprobe_optimizer();
+ printk(KERN_INFO "Kprobes globally unoptimized\n");
}
int sysctl_kprobes_optimization;
@@ -669,44 +844,60 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
}
#endif /* CONFIG_SYSCTL */
+/* Put a breakpoint for a probe. Must be called with text_mutex locked */
static void __kprobes __arm_kprobe(struct kprobe *p)
{
- struct kprobe *old_p;
+ struct kprobe *_p;
/* Check collision with other optimized kprobes */
- old_p = get_optimized_kprobe((unsigned long)p->addr);
- if (unlikely(old_p))
- unoptimize_kprobe(old_p); /* Fallback to unoptimized kprobe */
+ _p = get_optimized_kprobe((unsigned long)p->addr);
+ if (unlikely(_p))
+ /* Fallback to unoptimized kprobe */
+ unoptimize_kprobe(_p, true);
arch_arm_kprobe(p);
optimize_kprobe(p); /* Try to optimize (add kprobe to a list) */
}
-static void __kprobes __disarm_kprobe(struct kprobe *p)
+/* Remove the breakpoint of a probe. Must be called with text_mutex locked */
+static void __kprobes __disarm_kprobe(struct kprobe *p, bool reopt)
{
- struct kprobe *old_p;
+ struct kprobe *_p;
- unoptimize_kprobe(p); /* Try to unoptimize */
- arch_disarm_kprobe(p);
+ unoptimize_kprobe(p, false); /* Try to unoptimize */
- /* If another kprobe was blocked, optimize it. */
- old_p = get_optimized_kprobe((unsigned long)p->addr);
- if (unlikely(old_p))
- optimize_kprobe(old_p);
+ if (!kprobe_queued(p)) {
+ arch_disarm_kprobe(p);
+ /* If another kprobe was blocked, optimize it. */
+ _p = get_optimized_kprobe((unsigned long)p->addr);
+ if (unlikely(_p) && reopt)
+ optimize_kprobe(_p);
+ }
+ /* TODO: reoptimize others after unoptimized this probe */
}
#else /* !CONFIG_OPTPROBES */
#define optimize_kprobe(p) do {} while (0)
-#define unoptimize_kprobe(p) do {} while (0)
+#define unoptimize_kprobe(p, f) do {} while (0)
#define kill_optimized_kprobe(p) do {} while (0)
#define prepare_optimized_kprobe(p) do {} while (0)
#define try_to_optimize_kprobe(p) do {} while (0)
#define __arm_kprobe(p) arch_arm_kprobe(p)
-#define __disarm_kprobe(p) arch_disarm_kprobe(p)
+#define __disarm_kprobe(p, o) arch_disarm_kprobe(p)
+#define kprobe_disarmed(p) kprobe_disabled(p)
+#define wait_for_kprobe_optimizer() do {} while (0)
+
+/* There should be no unused kprobes can be reused without optimization */
+static void reuse_unused_kprobe(struct kprobe *ap)
+{
+ printk(KERN_ERR "Error: There should be no unused kprobe here.\n");
+ BUG_ON(kprobe_unused(ap));
+}
static __kprobes void free_aggr_kprobe(struct kprobe *p)
{
+ arch_remove_kprobe(p);
kfree(p);
}
@@ -732,11 +923,10 @@ static void __kprobes arm_kprobe(struct kprobe *kp)
/* Disarm a kprobe with text_mutex */
static void __kprobes disarm_kprobe(struct kprobe *kp)
{
- get_online_cpus(); /* For avoiding text_mutex deadlock */
+ /* Ditto */
mutex_lock(&text_mutex);
- __disarm_kprobe(kp);
+ __disarm_kprobe(kp, true);
mutex_unlock(&text_mutex);
- put_online_cpus();
}
/*
@@ -942,7 +1132,7 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
if (p->break_handler || p->post_handler)
- unoptimize_kprobe(ap); /* Fall back to normal kprobe */
+ unoptimize_kprobe(ap, true); /* Fall back to normal kprobe */
if (p->break_handler) {
if (ap->break_handler)
@@ -993,19 +1183,21 @@ static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
* This is the second or subsequent kprobe at the address - handle
* the intricacies
*/
-static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
+static int __kprobes register_aggr_kprobe(struct kprobe *orig_p,
struct kprobe *p)
{
int ret = 0;
- struct kprobe *ap = old_p;
+ struct kprobe *ap = orig_p;
- if (!kprobe_aggrprobe(old_p)) {
- /* If old_p is not an aggr_kprobe, create new aggr_kprobe. */
- ap = alloc_aggr_kprobe(old_p);
+ if (!kprobe_aggrprobe(orig_p)) {
+ /* If orig_p is not an aggr_kprobe, create new aggr_kprobe. */
+ ap = alloc_aggr_kprobe(orig_p);
if (!ap)
return -ENOMEM;
- init_aggr_kprobe(ap, old_p);
- }
+ init_aggr_kprobe(ap, orig_p);
+ } else if (kprobe_unused(ap))
+ /* This probe is going to die. Rescue it */
+ reuse_unused_kprobe(ap);
if (kprobe_gone(ap)) {
/*
@@ -1039,23 +1231,6 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
return add_new_kprobe(ap, p);
}
-/* Try to disable aggr_kprobe, and return 1 if succeeded.*/
-static int __kprobes try_to_disable_aggr_kprobe(struct kprobe *p)
-{
- struct kprobe *kp;
-
- list_for_each_entry_rcu(kp, &p->list, list) {
- if (!kprobe_disabled(kp))
- /*
- * There is an active probe on the list.
- * We can't disable aggr_kprobe.
- */
- return 0;
- }
- p->flags |= KPROBE_FLAG_DISABLED;
- return 1;
-}
-
static int __kprobes in_kprobes_functions(unsigned long addr)
{
struct kprobe_blackpoint *kb;
@@ -1098,34 +1273,33 @@ static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p)
/* Check passed kprobe is valid and return kprobe in kprobe_table. */
static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p)
{
- struct kprobe *old_p, *list_p;
+ struct kprobe *ap, *list_p;
- old_p = get_kprobe(p->addr);
- if (unlikely(!old_p))
+ ap = get_kprobe(p->addr);
+ if (unlikely(!ap))
return NULL;
- if (p != old_p) {
- list_for_each_entry_rcu(list_p, &old_p->list, list)
+ if (p != ap) {
+ list_for_each_entry_rcu(list_p, &ap->list, list)
if (list_p == p)
/* kprobe p is a valid probe */
goto valid;
return NULL;
}
valid:
- return old_p;
+ return ap;
}
/* Return error if the kprobe is being re-registered */
static inline int check_kprobe_rereg(struct kprobe *p)
{
int ret = 0;
- struct kprobe *old_p;
mutex_lock(&kprobe_mutex);
- old_p = __get_valid_kprobe(p);
- if (old_p)
+ if (__get_valid_kprobe(p))
ret = -EINVAL;
mutex_unlock(&kprobe_mutex);
+
return ret;
}
@@ -1229,67 +1403,121 @@ fail_with_jump_label:
}
EXPORT_SYMBOL_GPL(register_kprobe);
+/* Check if all probes on the aggrprobe are disabled */
+static int __kprobes aggr_kprobe_disabled(struct kprobe *ap)
+{
+ struct kprobe *kp;
+
+ list_for_each_entry_rcu(kp, &ap->list, list)
+ if (!kprobe_disabled(kp))
+ /*
+ * There is an active probe on the list.
+ * We can't disable this ap.
+ */
+ return 0;
+
+ return 1;
+}
+
+/* Disable one kprobe: Make sure called under kprobe_mutex is locked */
+static struct kprobe *__kprobes __disable_kprobe(struct kprobe *p)
+{
+ struct kprobe *orig_p;
+
+ /* Get an original kprobe for return */
+ orig_p = __get_valid_kprobe(p);
+ if (unlikely(orig_p == NULL))
+ return NULL;
+
+ if (!kprobe_disabled(p)) {
+ /* Disable probe if it is a child probe */
+ if (p != orig_p)
+ p->flags |= KPROBE_FLAG_DISABLED;
+
+ /* Try to disarm and disable this/parent probe */
+ if (p == orig_p || aggr_kprobe_disabled(orig_p)) {
+ disarm_kprobe(orig_p);
+ orig_p->flags |= KPROBE_FLAG_DISABLED;
+ }
+ }
+
+ return orig_p;
+}
+
/*
* Unregister a kprobe without a scheduler synchronization.
*/
static int __kprobes __unregister_kprobe_top(struct kprobe *p)
{
- struct kprobe *old_p, *list_p;
+ struct kprobe *ap, *list_p;
- old_p = __get_valid_kprobe(p);
- if (old_p == NULL)
+ /* Disable kprobe. This will disarm it if needed. */
+ ap = __disable_kprobe(p);
+ if (ap == NULL)
return -EINVAL;
- if (old_p == p ||
- (kprobe_aggrprobe(old_p) &&
- list_is_singular(&old_p->list))) {
+ if (ap == p)
/*
- * Only probe on the hash list. Disarm only if kprobes are
- * enabled and not gone - otherwise, the breakpoint would
- * already have been removed. We save on flushing icache.
+ * This probe is an independent(and non-optimized) kprobe
+ * (not an aggrprobe). Remove from the hash list.
*/
- if (!kprobes_all_disarmed && !kprobe_disabled(old_p))
- disarm_kprobe(old_p);
- hlist_del_rcu(&old_p->hlist);
- } else {
+ goto disarmed;
+
+ /* Following process expects this probe is an aggrprobe */
+ WARN_ON(!kprobe_aggrprobe(ap));
+
+ if (list_is_singular(&ap->list) && kprobe_disarmed(ap))
+ /*
+ * !disarmed could be happen if the probe is under delayed
+ * unoptimizing.
+ */
+ goto disarmed;
+ else {
+ /* If disabling probe has special handlers, update aggrprobe */
if (p->break_handler && !kprobe_gone(p))
- old_p->break_handler = NULL;
+ ap->break_handler = NULL;
if (p->post_handler && !kprobe_gone(p)) {
- list_for_each_entry_rcu(list_p, &old_p->list, list) {
+ list_for_each_entry_rcu(list_p, &ap->list, list) {
if ((list_p != p) && (list_p->post_handler))
goto noclean;
}
- old_p->post_handler = NULL;
+ ap->post_handler = NULL;
}
noclean:
+ /*
+ * Remove from the aggrprobe: this path will do nothing in
+ * __unregister_kprobe_bottom().
+ */
list_del_rcu(&p->list);
- if (!kprobe_disabled(old_p)) {
- try_to_disable_aggr_kprobe(old_p);
- if (!kprobes_all_disarmed) {
- if (kprobe_disabled(old_p))
- disarm_kprobe(old_p);
- else
- /* Try to optimize this probe again */
- optimize_kprobe(old_p);
- }
- }
+ if (!kprobe_disabled(ap) && !kprobes_all_disarmed)
+ /*
+ * Try to optimize this probe again, because post
+ * handler may have been changed.
+ */
+ optimize_kprobe(ap);
}
return 0;
+
+disarmed:
+ BUG_ON(!kprobe_disarmed(ap));
+ hlist_del_rcu(&ap->hlist);
+ return 0;
}
static void __kprobes __unregister_kprobe_bottom(struct kprobe *p)
{
- struct kprobe *old_p;
+ struct kprobe *ap;
if (list_empty(&p->list))
+ /* This is an independent kprobe */
arch_remove_kprobe(p);
else if (list_is_singular(&p->list)) {
- /* "p" is the last child of an aggr_kprobe */
- old_p = list_entry(p->list.next, struct kprobe, list);
+ /* This is the last child of an aggrprobe */
+ ap = list_entry(p->list.next, struct kprobe, list);
list_del(&p->list);
- arch_remove_kprobe(old_p);
- free_aggr_kprobe(old_p);
+ free_aggr_kprobe(ap);
}
+ /* Otherwise, do nothing. */
}
int __kprobes register_kprobes(struct kprobe **kps, int num)
@@ -1607,29 +1835,13 @@ static void __kprobes kill_kprobe(struct kprobe *p)
int __kprobes disable_kprobe(struct kprobe *kp)
{
int ret = 0;
- struct kprobe *p;
mutex_lock(&kprobe_mutex);
- /* Check whether specified probe is valid. */
- p = __get_valid_kprobe(kp);
- if (unlikely(p == NULL)) {
+ /* Disable this kprobe */
+ if (__disable_kprobe(kp) == NULL)
ret = -EINVAL;
- goto out;
- }
- /* If the probe is already disabled (or gone), just return */
- if (kprobe_disabled(kp))
- goto out;
-
- kp->flags |= KPROBE_FLAG_DISABLED;
- if (p != kp)
- /* When kp != p, p is always enabled. */
- try_to_disable_aggr_kprobe(p);
-
- if (!kprobes_all_disarmed && kprobe_disabled(p))
- disarm_kprobe(p);
-out:
mutex_unlock(&kprobe_mutex);
return ret;
}
@@ -1927,36 +2139,27 @@ static void __kprobes disarm_all_kprobes(void)
mutex_lock(&kprobe_mutex);
/* If kprobes are already disarmed, just return */
- if (kprobes_all_disarmed)
- goto already_disabled;
+ if (kprobes_all_disarmed) {
+ mutex_unlock(&kprobe_mutex);
+ return;
+ }
kprobes_all_disarmed = true;
printk(KERN_INFO "Kprobes globally disabled\n");
- /*
- * Here we call get_online_cpus() for avoiding text_mutex deadlock,
- * because disarming may also unoptimize kprobes.
- */
- get_online_cpus();
mutex_lock(&text_mutex);
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
hlist_for_each_entry_rcu(p, node, head, hlist) {
if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p))
- __disarm_kprobe(p);
+ __disarm_kprobe(p, false);
}
}
-
mutex_unlock(&text_mutex);
- put_online_cpus();
mutex_unlock(&kprobe_mutex);
- /* Allow all currently running kprobes to complete */
- synchronize_sched();
- return;
-already_disabled:
- mutex_unlock(&kprobe_mutex);
- return;
+ /* Wait for disarming all kprobes by optimizer */
+ wait_for_kprobe_optimizer();
}
/*
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 2870feee81dd..11847bf1e8cc 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -13,6 +13,7 @@
#include <linux/mm.h>
#include <linux/cpu.h>
#include <linux/smp.h>
+#include <linux/idr.h>
#include <linux/file.h>
#include <linux/poll.h>
#include <linux/slab.h>
@@ -21,7 +22,9 @@
#include <linux/dcache.h>
#include <linux/percpu.h>
#include <linux/ptrace.h>
+#include <linux/reboot.h>
#include <linux/vmstat.h>
+#include <linux/device.h>
#include <linux/vmalloc.h>
#include <linux/hardirq.h>
#include <linux/rculist.h>
@@ -133,6 +136,28 @@ static void unclone_ctx(struct perf_event_context *ctx)
}
}
+static u32 perf_event_pid(struct perf_event *event, struct task_struct *p)
+{
+ /*
+ * only top level events have the pid namespace they were created in
+ */
+ if (event->parent)
+ event = event->parent;
+
+ return task_tgid_nr_ns(p, event->ns);
+}
+
+static u32 perf_event_tid(struct perf_event *event, struct task_struct *p)
+{
+ /*
+ * only top level events have the pid namespace they were created in
+ */
+ if (event->parent)
+ event = event->parent;
+
+ return task_pid_nr_ns(p, event->ns);
+}
+
/*
* If we inherit events we want to return the parent event id
* to userspace.
@@ -312,9 +337,84 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
ctx->nr_stat++;
}
+/*
+ * Called at perf_event creation and when events are attached/detached from a
+ * group.
+ */
+static void perf_event__read_size(struct perf_event *event)
+{
+ int entry = sizeof(u64); /* value */
+ int size = 0;
+ int nr = 1;
+
+ if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+ size += sizeof(u64);
+
+ if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+ size += sizeof(u64);
+
+ if (event->attr.read_format & PERF_FORMAT_ID)
+ entry += sizeof(u64);
+
+ if (event->attr.read_format & PERF_FORMAT_GROUP) {
+ nr += event->group_leader->nr_siblings;
+ size += sizeof(u64);
+ }
+
+ size += entry * nr;
+ event->read_size = size;
+}
+
+static void perf_event__header_size(struct perf_event *event)
+{
+ struct perf_sample_data *data;
+ u64 sample_type = event->attr.sample_type;
+ u16 size = 0;
+
+ perf_event__read_size(event);
+
+ if (sample_type & PERF_SAMPLE_IP)
+ size += sizeof(data->ip);
+
+ if (sample_type & PERF_SAMPLE_ADDR)
+ size += sizeof(data->addr);
+
+ if (sample_type & PERF_SAMPLE_PERIOD)
+ size += sizeof(data->period);
+
+ if (sample_type & PERF_SAMPLE_READ)
+ size += event->read_size;
+
+ event->header_size = size;
+}
+
+static void perf_event__id_header_size(struct perf_event *event)
+{
+ struct perf_sample_data *data;
+ u64 sample_type = event->attr.sample_type;
+ u16 size = 0;
+
+ if (sample_type & PERF_SAMPLE_TID)
+ size += sizeof(data->tid_entry);
+
+ if (sample_type & PERF_SAMPLE_TIME)
+ size += sizeof(data->time);
+
+ if (sample_type & PERF_SAMPLE_ID)
+ size += sizeof(data->id);
+
+ if (sample_type & PERF_SAMPLE_STREAM_ID)
+ size += sizeof(data->stream_id);
+
+ if (sample_type & PERF_SAMPLE_CPU)
+ size += sizeof(data->cpu_entry);
+
+ event->id_header_size = size;
+}
+
static void perf_group_attach(struct perf_event *event)
{
- struct perf_event *group_leader = event->group_leader;
+ struct perf_event *group_leader = event->group_leader, *pos;
/*
* We can have double attach due to group movement in perf_event_open.
@@ -333,6 +433,11 @@ static void perf_group_attach(struct perf_event *event)
list_add_tail(&event->group_entry, &group_leader->sibling_list);
group_leader->nr_siblings++;
+
+ perf_event__header_size(group_leader);
+
+ list_for_each_entry(pos, &group_leader->sibling_list, group_entry)
+ perf_event__header_size(pos);
}
/*
@@ -391,7 +496,7 @@ static void perf_group_detach(struct perf_event *event)
if (event->group_leader != event) {
list_del_init(&event->group_entry);
event->group_leader->nr_siblings--;
- return;
+ goto out;
}
if (!list_empty(&event->group_entry))
@@ -410,6 +515,12 @@ static void perf_group_detach(struct perf_event *event)
/* Inherit group flags from the previous leader */
sibling->group_flags = event->group_flags;
}
+
+out:
+ perf_event__header_size(event->group_leader);
+
+ list_for_each_entry(tmp, &event->group_leader->sibling_list, group_entry)
+ perf_event__header_size(tmp);
}
static inline int
@@ -1073,7 +1184,7 @@ static int perf_event_refresh(struct perf_event *event, int refresh)
/*
* not supported on inherited events
*/
- if (event->attr.inherit)
+ if (event->attr.inherit || !is_sampling_event(event))
return -EINVAL;
atomic_add(refresh, &event->event_limit);
@@ -2289,31 +2400,6 @@ static int perf_release(struct inode *inode, struct file *file)
return perf_event_release_kernel(event);
}
-static int perf_event_read_size(struct perf_event *event)
-{
- int entry = sizeof(u64); /* value */
- int size = 0;
- int nr = 1;
-
- if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
- size += sizeof(u64);
-
- if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
- size += sizeof(u64);
-
- if (event->attr.read_format & PERF_FORMAT_ID)
- entry += sizeof(u64);
-
- if (event->attr.read_format & PERF_FORMAT_GROUP) {
- nr += event->group_leader->nr_siblings;
- size += sizeof(u64);
- }
-
- size += entry * nr;
-
- return size;
-}
-
u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
{
struct perf_event *child;
@@ -2428,7 +2514,7 @@ perf_read_hw(struct perf_event *event, char __user *buf, size_t count)
if (event->state == PERF_EVENT_STATE_ERROR)
return 0;
- if (count < perf_event_read_size(event))
+ if (count < event->read_size)
return -ENOSPC;
WARN_ON_ONCE(event->ctx->parent_ctx);
@@ -2514,7 +2600,7 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
int ret = 0;
u64 value;
- if (!event->attr.sample_period)
+ if (!is_sampling_event(event))
return -EINVAL;
if (copy_from_user(&value, arg, sizeof(value)))
@@ -3305,6 +3391,73 @@ __always_inline void perf_output_copy(struct perf_output_handle *handle,
} while (len);
}
+static void __perf_event_header__init_id(struct perf_event_header *header,
+ struct perf_sample_data *data,
+ struct perf_event *event)
+{
+ u64 sample_type = event->attr.sample_type;
+
+ data->type = sample_type;
+ header->size += event->id_header_size;
+
+ if (sample_type & PERF_SAMPLE_TID) {
+ /* namespace issues */
+ data->tid_entry.pid = perf_event_pid(event, current);
+ data->tid_entry.tid = perf_event_tid(event, current);
+ }
+
+ if (sample_type & PERF_SAMPLE_TIME)
+ data->time = perf_clock();
+
+ if (sample_type & PERF_SAMPLE_ID)
+ data->id = primary_event_id(event);
+
+ if (sample_type & PERF_SAMPLE_STREAM_ID)
+ data->stream_id = event->id;
+
+ if (sample_type & PERF_SAMPLE_CPU) {
+ data->cpu_entry.cpu = raw_smp_processor_id();
+ data->cpu_entry.reserved = 0;
+ }
+}
+
+static void perf_event_header__init_id(struct perf_event_header *header,
+ struct perf_sample_data *data,
+ struct perf_event *event)
+{
+ if (event->attr.sample_id_all)
+ __perf_event_header__init_id(header, data, event);
+}
+
+static void __perf_event__output_id_sample(struct perf_output_handle *handle,
+ struct perf_sample_data *data)
+{
+ u64 sample_type = data->type;
+
+ if (sample_type & PERF_SAMPLE_TID)
+ perf_output_put(handle, data->tid_entry);
+
+ if (sample_type & PERF_SAMPLE_TIME)
+ perf_output_put(handle, data->time);
+
+ if (sample_type & PERF_SAMPLE_ID)
+ perf_output_put(handle, data->id);
+
+ if (sample_type & PERF_SAMPLE_STREAM_ID)
+ perf_output_put(handle, data->stream_id);
+
+ if (sample_type & PERF_SAMPLE_CPU)
+ perf_output_put(handle, data->cpu_entry);
+}
+
+static void perf_event__output_id_sample(struct perf_event *event,
+ struct perf_output_handle *handle,
+ struct perf_sample_data *sample)
+{
+ if (event->attr.sample_id_all)
+ __perf_event__output_id_sample(handle, sample);
+}
+
int perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size,
int nmi, int sample)
@@ -3312,6 +3465,7 @@ int perf_output_begin(struct perf_output_handle *handle,
struct perf_buffer *buffer;
unsigned long tail, offset, head;
int have_lost;
+ struct perf_sample_data sample_data;
struct {
struct perf_event_header header;
u64 id;
@@ -3338,8 +3492,12 @@ int perf_output_begin(struct perf_output_handle *handle,
goto out;
have_lost = local_read(&buffer->lost);
- if (have_lost)
- size += sizeof(lost_event);
+ if (have_lost) {
+ lost_event.header.size = sizeof(lost_event);
+ perf_event_header__init_id(&lost_event.header, &sample_data,
+ event);
+ size += lost_event.header.size;
+ }
perf_output_get_handle(handle);
@@ -3370,11 +3528,11 @@ int perf_output_begin(struct perf_output_handle *handle,
if (have_lost) {
lost_event.header.type = PERF_RECORD_LOST;
lost_event.header.misc = 0;
- lost_event.header.size = sizeof(lost_event);
lost_event.id = event->id;
lost_event.lost = local_xchg(&buffer->lost, 0);
perf_output_put(handle, lost_event);
+ perf_event__output_id_sample(event, handle, &sample_data);
}
return 0;
@@ -3407,28 +3565,6 @@ void perf_output_end(struct perf_output_handle *handle)
rcu_read_unlock();
}
-static u32 perf_event_pid(struct perf_event *event, struct task_struct *p)
-{
- /*
- * only top level events have the pid namespace they were created in
- */
- if (event->parent)
- event = event->parent;
-
- return task_tgid_nr_ns(p, event->ns);
-}
-
-static u32 perf_event_tid(struct perf_event *event, struct task_struct *p)
-{
- /*
- * only top level events have the pid namespace they were created in
- */
- if (event->parent)
- event = event->parent;
-
- return task_pid_nr_ns(p, event->ns);
-}
-
static void perf_output_read_one(struct perf_output_handle *handle,
struct perf_event *event,
u64 enabled, u64 running)
@@ -3603,61 +3739,16 @@ void perf_prepare_sample(struct perf_event_header *header,
{
u64 sample_type = event->attr.sample_type;
- data->type = sample_type;
-
header->type = PERF_RECORD_SAMPLE;
- header->size = sizeof(*header);
+ header->size = sizeof(*header) + event->header_size;
header->misc = 0;
header->misc |= perf_misc_flags(regs);
- if (sample_type & PERF_SAMPLE_IP) {
- data->ip = perf_instruction_pointer(regs);
-
- header->size += sizeof(data->ip);
- }
-
- if (sample_type & PERF_SAMPLE_TID) {
- /* namespace issues */
- data->tid_entry.pid = perf_event_pid(event, current);
- data->tid_entry.tid = perf_event_tid(event, current);
-
- header->size += sizeof(data->tid_entry);
- }
-
- if (sample_type & PERF_SAMPLE_TIME) {
- data->time = perf_clock();
-
- header->size += sizeof(data->time);
- }
-
- if (sample_type & PERF_SAMPLE_ADDR)
- header->size += sizeof(data->addr);
-
- if (sample_type & PERF_SAMPLE_ID) {
- data->id = primary_event_id(event);
-
- header->size += sizeof(data->id);
- }
-
- if (sample_type & PERF_SAMPLE_STREAM_ID) {
- data->stream_id = event->id;
-
- header->size += sizeof(data->stream_id);
- }
-
- if (sample_type & PERF_SAMPLE_CPU) {
- data->cpu_entry.cpu = raw_smp_processor_id();
- data->cpu_entry.reserved = 0;
-
- header->size += sizeof(data->cpu_entry);
- }
-
- if (sample_type & PERF_SAMPLE_PERIOD)
- header->size += sizeof(data->period);
+ __perf_event_header__init_id(header, data, event);
- if (sample_type & PERF_SAMPLE_READ)
- header->size += perf_event_read_size(event);
+ if (sample_type & PERF_SAMPLE_IP)
+ data->ip = perf_instruction_pointer(regs);
if (sample_type & PERF_SAMPLE_CALLCHAIN) {
int size = 1;
@@ -3722,23 +3813,26 @@ perf_event_read_event(struct perf_event *event,
struct task_struct *task)
{
struct perf_output_handle handle;
+ struct perf_sample_data sample;
struct perf_read_event read_event = {
.header = {
.type = PERF_RECORD_READ,
.misc = 0,
- .size = sizeof(read_event) + perf_event_read_size(event),
+ .size = sizeof(read_event) + event->read_size,
},
.pid = perf_event_pid(event, task),
.tid = perf_event_tid(event, task),
};
int ret;
+ perf_event_header__init_id(&read_event.header, &sample, event);
ret = perf_output_begin(&handle, event, read_event.header.size, 0, 0);
if (ret)
return;
perf_output_put(&handle, read_event);
perf_output_read(&handle, event);
+ perf_event__output_id_sample(event, &handle, &sample);
perf_output_end(&handle);
}
@@ -3768,14 +3862,16 @@ static void perf_event_task_output(struct perf_event *event,
struct perf_task_event *task_event)
{
struct perf_output_handle handle;
+ struct perf_sample_data sample;
struct task_struct *task = task_event->task;
- int size, ret;
+ int ret, size = task_event->event_id.header.size;
- size = task_event->event_id.header.size;
- ret = perf_output_begin(&handle, event, size, 0, 0);
+ perf_event_header__init_id(&task_event->event_id.header, &sample, event);
+ ret = perf_output_begin(&handle, event,
+ task_event->event_id.header.size, 0, 0);
if (ret)
- return;
+ goto out;
task_event->event_id.pid = perf_event_pid(event, task);
task_event->event_id.ppid = perf_event_pid(event, current);
@@ -3785,7 +3881,11 @@ static void perf_event_task_output(struct perf_event *event,
perf_output_put(&handle, task_event->event_id);
+ perf_event__output_id_sample(event, &handle, &sample);
+
perf_output_end(&handle);
+out:
+ task_event->event_id.header.size = size;
}
static int perf_event_task_match(struct perf_event *event)
@@ -3900,11 +4000,16 @@ static void perf_event_comm_output(struct perf_event *event,
struct perf_comm_event *comm_event)
{
struct perf_output_handle handle;
+ struct perf_sample_data sample;
int size = comm_event->event_id.header.size;
- int ret = perf_output_begin(&handle, event, size, 0, 0);
+ int ret;
+
+ perf_event_header__init_id(&comm_event->event_id.header, &sample, event);
+ ret = perf_output_begin(&handle, event,
+ comm_event->event_id.header.size, 0, 0);
if (ret)
- return;
+ goto out;
comm_event->event_id.pid = perf_event_pid(event, comm_event->task);
comm_event->event_id.tid = perf_event_tid(event, comm_event->task);
@@ -3912,7 +4017,12 @@ static void perf_event_comm_output(struct perf_event *event,
perf_output_put(&handle, comm_event->event_id);
perf_output_copy(&handle, comm_event->comm,
comm_event->comm_size);
+
+ perf_event__output_id_sample(event, &handle, &sample);
+
perf_output_end(&handle);
+out:
+ comm_event->event_id.header.size = size;
}
static int perf_event_comm_match(struct perf_event *event)
@@ -3957,7 +4067,6 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
comm_event->comm_size = size;
comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;
-
rcu_read_lock();
list_for_each_entry_rcu(pmu, &pmus, entry) {
cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
@@ -4038,11 +4147,15 @@ static void perf_event_mmap_output(struct perf_event *event,
struct perf_mmap_event *mmap_event)
{
struct perf_output_handle handle;
+ struct perf_sample_data sample;
int size = mmap_event->event_id.header.size;
- int ret = perf_output_begin(&handle, event, size, 0, 0);
+ int ret;
+ perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
+ ret = perf_output_begin(&handle, event,
+ mmap_event->event_id.header.size, 0, 0);
if (ret)
- return;
+ goto out;
mmap_event->event_id.pid = perf_event_pid(event, current);
mmap_event->event_id.tid = perf_event_tid(event, current);
@@ -4050,7 +4163,12 @@ static void perf_event_mmap_output(struct perf_event *event,
perf_output_put(&handle, mmap_event->event_id);
perf_output_copy(&handle, mmap_event->file_name,
mmap_event->file_size);
+
+ perf_event__output_id_sample(event, &handle, &sample);
+
perf_output_end(&handle);
+out:
+ mmap_event->event_id.header.size = size;
}
static int perf_event_mmap_match(struct perf_event *event,
@@ -4205,6 +4323,7 @@ void perf_event_mmap(struct vm_area_struct *vma)
static void perf_log_throttle(struct perf_event *event, int enable)
{
struct perf_output_handle handle;
+ struct perf_sample_data sample;
int ret;
struct {
@@ -4226,11 +4345,15 @@ static void perf_log_throttle(struct perf_event *event, int enable)
if (enable)
throttle_event.header.type = PERF_RECORD_UNTHROTTLE;
- ret = perf_output_begin(&handle, event, sizeof(throttle_event), 1, 0);
+ perf_event_header__init_id(&throttle_event.header, &sample, event);
+
+ ret = perf_output_begin(&handle, event,
+ throttle_event.header.size, 1, 0);
if (ret)
return;
perf_output_put(&handle, throttle_event);
+ perf_event__output_id_sample(event, &handle, &sample);
perf_output_end(&handle);
}
@@ -4246,6 +4369,13 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
struct hw_perf_event *hwc = &event->hw;
int ret = 0;
+ /*
+ * Non-sampling counters might still use the PMI to fold short
+ * hardware counters, ignore those.
+ */
+ if (unlikely(!is_sampling_event(event)))
+ return 0;
+
if (!throttle) {
hwc->interrupts++;
} else {
@@ -4391,7 +4521,7 @@ static void perf_swevent_event(struct perf_event *event, u64 nr,
if (!regs)
return;
- if (!hwc->sample_period)
+ if (!is_sampling_event(event))
return;
if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq)
@@ -4554,7 +4684,7 @@ static int perf_swevent_add(struct perf_event *event, int flags)
struct hw_perf_event *hwc = &event->hw;
struct hlist_head *head;
- if (hwc->sample_period) {
+ if (is_sampling_event(event)) {
hwc->last_period = hwc->sample_period;
perf_swevent_set_period(event);
}
@@ -4811,15 +4941,6 @@ static int perf_tp_event_init(struct perf_event *event)
if (event->attr.type != PERF_TYPE_TRACEPOINT)
return -ENOENT;
- /*
- * Raw tracepoint data is a severe data leak, only allow root to
- * have these.
- */
- if ((event->attr.sample_type & PERF_SAMPLE_RAW) &&
- perf_paranoid_tracepoint_raw() &&
- !capable(CAP_SYS_ADMIN))
- return -EPERM;
-
err = perf_trace_init(event);
if (err)
return err;
@@ -4842,7 +4963,7 @@ static struct pmu perf_tracepoint = {
static inline void perf_tp_register(void)
{
- perf_pmu_register(&perf_tracepoint);
+ perf_pmu_register(&perf_tracepoint, "tracepoint", PERF_TYPE_TRACEPOINT);
}
static int perf_event_set_filter(struct perf_event *event, void __user *arg)
@@ -4932,31 +5053,33 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
static void perf_swevent_start_hrtimer(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
+ s64 period;
+
+ if (!is_sampling_event(event))
+ return;
hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
hwc->hrtimer.function = perf_swevent_hrtimer;
- if (hwc->sample_period) {
- s64 period = local64_read(&hwc->period_left);
- if (period) {
- if (period < 0)
- period = 10000;
+ period = local64_read(&hwc->period_left);
+ if (period) {
+ if (period < 0)
+ period = 10000;
- local64_set(&hwc->period_left, 0);
- } else {
- period = max_t(u64, 10000, hwc->sample_period);
- }
- __hrtimer_start_range_ns(&hwc->hrtimer,
+ local64_set(&hwc->period_left, 0);
+ } else {
+ period = max_t(u64, 10000, hwc->sample_period);
+ }
+ __hrtimer_start_range_ns(&hwc->hrtimer,
ns_to_ktime(period), 0,
HRTIMER_MODE_REL_PINNED, 0);
- }
}
static void perf_swevent_cancel_hrtimer(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- if (hwc->sample_period) {
+ if (is_sampling_event(event)) {
ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
local64_set(&hwc->period_left, ktime_to_ns(remaining));
@@ -5184,8 +5307,61 @@ static void free_pmu_context(struct pmu *pmu)
out:
mutex_unlock(&pmus_lock);
}
+static struct idr pmu_idr;
+
+static ssize_t
+type_show(struct device *dev, struct device_attribute *attr, char *page)
+{
+ struct pmu *pmu = dev_get_drvdata(dev);
+
+ return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->type);
+}
+
+static struct device_attribute pmu_dev_attrs[] = {
+ __ATTR_RO(type),
+ __ATTR_NULL,
+};
+
+static int pmu_bus_running;
+static struct bus_type pmu_bus = {
+ .name = "event_source",
+ .dev_attrs = pmu_dev_attrs,
+};
+
+static void pmu_dev_release(struct device *dev)
+{
+ kfree(dev);
+}
+
+static int pmu_dev_alloc(struct pmu *pmu)
+{
+ int ret = -ENOMEM;
+
+ pmu->dev = kzalloc(sizeof(struct device), GFP_KERNEL);
+ if (!pmu->dev)
+ goto out;
+
+ device_initialize(pmu->dev);
+ ret = dev_set_name(pmu->dev, "%s", pmu->name);
+ if (ret)
+ goto free_dev;
+
+ dev_set_drvdata(pmu->dev, pmu);
+ pmu->dev->bus = &pmu_bus;
+ pmu->dev->release = pmu_dev_release;
+ ret = device_add(pmu->dev);
+ if (ret)
+ goto free_dev;
+
+out:
+ return ret;
+
+free_dev:
+ put_device(pmu->dev);
+ goto out;
+}
-int perf_pmu_register(struct pmu *pmu)
+int perf_pmu_register(struct pmu *pmu, char *name, int type)
{
int cpu, ret;
@@ -5195,13 +5371,38 @@ int perf_pmu_register(struct pmu *pmu)
if (!pmu->pmu_disable_count)
goto unlock;
+ pmu->type = -1;
+ if (!name)
+ goto skip_type;
+ pmu->name = name;
+
+ if (type < 0) {
+ int err = idr_pre_get(&pmu_idr, GFP_KERNEL);
+ if (!err)
+ goto free_pdc;
+
+ err = idr_get_new_above(&pmu_idr, pmu, PERF_TYPE_MAX, &type);
+ if (err) {
+ ret = err;
+ goto free_pdc;
+ }
+ }
+ pmu->type = type;
+
+ if (pmu_bus_running) {
+ ret = pmu_dev_alloc(pmu);
+ if (ret)
+ goto free_idr;
+ }
+
+skip_type:
pmu->pmu_cpu_context = find_pmu_context(pmu->task_ctx_nr);
if (pmu->pmu_cpu_context)
goto got_cpu_context;
pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context);
if (!pmu->pmu_cpu_context)
- goto free_pdc;
+ goto free_dev;
for_each_possible_cpu(cpu) {
struct perf_cpu_context *cpuctx;
@@ -5245,6 +5446,14 @@ unlock:
return ret;
+free_dev:
+ device_del(pmu->dev);
+ put_device(pmu->dev);
+
+free_idr:
+ if (pmu->type >= PERF_TYPE_MAX)
+ idr_remove(&pmu_idr, pmu->type);
+
free_pdc:
free_percpu(pmu->pmu_disable_count);
goto unlock;
@@ -5264,6 +5473,10 @@ void perf_pmu_unregister(struct pmu *pmu)
synchronize_rcu();
free_percpu(pmu->pmu_disable_count);
+ if (pmu->type >= PERF_TYPE_MAX)
+ idr_remove(&pmu_idr, pmu->type);
+ device_del(pmu->dev);
+ put_device(pmu->dev);
free_pmu_context(pmu);
}
@@ -5273,6 +5486,13 @@ struct pmu *perf_init_event(struct perf_event *event)
int idx;
idx = srcu_read_lock(&pmus_srcu);
+
+ rcu_read_lock();
+ pmu = idr_find(&pmu_idr, event->attr.type);
+ rcu_read_unlock();
+ if (pmu)
+ goto unlock;
+
list_for_each_entry_rcu(pmu, &pmus, entry) {
int ret = pmu->event_init(event);
if (!ret)
@@ -5738,6 +5958,12 @@ SYSCALL_DEFINE5(perf_event_open,
mutex_unlock(&current->perf_event_mutex);
/*
+ * Precalculate sample_data sizes
+ */
+ perf_event__header_size(event);
+ perf_event__id_header_size(event);
+
+ /*
* Drop the reference on the group_event after placing the
* new event on the sibling_list. This ensures destruction
* of the group leader will find the pointer to itself in
@@ -6090,6 +6316,12 @@ inherit_event(struct perf_event *parent_event,
child_event->overflow_handler = parent_event->overflow_handler;
/*
+ * Precalculate sample_data sizes
+ */
+ perf_event__header_size(child_event);
+ perf_event__id_header_size(child_event);
+
+ /*
* Link it up in the child's context:
*/
raw_spin_lock_irqsave(&child_ctx->lock, flags);
@@ -6320,7 +6552,7 @@ static void __cpuinit perf_event_init_cpu(int cpu)
mutex_unlock(&swhash->hlist_mutex);
}
-#ifdef CONFIG_HOTPLUG_CPU
+#if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC
static void perf_pmu_rotate_stop(struct pmu *pmu)
{
struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
@@ -6374,6 +6606,26 @@ static void perf_event_exit_cpu(int cpu)
static inline void perf_event_exit_cpu(int cpu) { }
#endif
+static int
+perf_reboot(struct notifier_block *notifier, unsigned long val, void *v)
+{
+ int cpu;
+
+ for_each_online_cpu(cpu)
+ perf_event_exit_cpu(cpu);
+
+ return NOTIFY_OK;
+}
+
+/*
+ * Run the perf reboot notifier at the very last possible moment so that
+ * the generic watchdog code runs as long as possible.
+ */
+static struct notifier_block perf_reboot_notifier = {
+ .notifier_call = perf_reboot,
+ .priority = INT_MIN,
+};
+
static int __cpuinit
perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
{
@@ -6402,14 +6654,45 @@ void __init perf_event_init(void)
{
int ret;
+ idr_init(&pmu_idr);
+
perf_event_init_all_cpus();
init_srcu_struct(&pmus_srcu);
- perf_pmu_register(&perf_swevent);
- perf_pmu_register(&perf_cpu_clock);
- perf_pmu_register(&perf_task_clock);
+ perf_pmu_register(&perf_swevent, "software", PERF_TYPE_SOFTWARE);
+ perf_pmu_register(&perf_cpu_clock, NULL, -1);
+ perf_pmu_register(&perf_task_clock, NULL, -1);
perf_tp_register();
perf_cpu_notifier(perf_cpu_notify);
+ register_reboot_notifier(&perf_reboot_notifier);
ret = init_hw_breakpoint();
WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
}
+
+static int __init perf_event_sysfs_init(void)
+{
+ struct pmu *pmu;
+ int ret;
+
+ mutex_lock(&pmus_lock);
+
+ ret = bus_register(&pmu_bus);
+ if (ret)
+ goto unlock;
+
+ list_for_each_entry(pmu, &pmus, entry) {
+ if (!pmu->name || pmu->type < 0)
+ continue;
+
+ ret = pmu_dev_alloc(pmu);
+ WARN(ret, "Failed to register pmu: %s, reason %d\n", pmu->name, ret);
+ }
+ pmu_bus_running = 1;
+ ret = 0;
+
+unlock:
+ mutex_unlock(&pmus_lock);
+
+ return ret;
+}
+device_initcall(perf_event_sysfs_init);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index ecf770509d0d..031d5e3a6197 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -22,6 +22,7 @@
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/suspend.h>
+#include <trace/events/power.h>
#include "power.h"
@@ -201,6 +202,7 @@ int suspend_devices_and_enter(suspend_state_t state)
if (!suspend_ops)
return -ENOSYS;
+ trace_machine_suspend(state);
if (suspend_ops->begin) {
error = suspend_ops->begin(state);
if (error)
@@ -229,6 +231,7 @@ int suspend_devices_and_enter(suspend_state_t state)
Close:
if (suspend_ops->end)
suspend_ops->end();
+ trace_machine_suspend(PWR_EVENT_EXIT);
return error;
Recover_platform:
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index d806735342ac..034493724749 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -36,31 +36,16 @@
#include <linux/time.h>
#include <linux/cpu.h>
-/* Global control variables for rcupdate callback mechanism. */
-struct rcu_ctrlblk {
- struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */
- struct rcu_head **donetail; /* ->next pointer of last "done" CB. */
- struct rcu_head **curtail; /* ->next pointer of last CB. */
-};
-
-/* Definition for rcupdate control block. */
-static struct rcu_ctrlblk rcu_sched_ctrlblk = {
- .donetail = &rcu_sched_ctrlblk.rcucblist,
- .curtail = &rcu_sched_ctrlblk.rcucblist,
-};
-
-static struct rcu_ctrlblk rcu_bh_ctrlblk = {
- .donetail = &rcu_bh_ctrlblk.rcucblist,
- .curtail = &rcu_bh_ctrlblk.rcucblist,
-};
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-int rcu_scheduler_active __read_mostly;
-EXPORT_SYMBOL_GPL(rcu_scheduler_active);
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+/* Controls for rcu_kthread() kthread, replacing RCU_SOFTIRQ used previously. */
+static struct task_struct *rcu_kthread_task;
+static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq);
+static unsigned long have_rcu_kthread_work;
+static void invoke_rcu_kthread(void);
/* Forward declarations for rcutiny_plugin.h. */
-static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp);
+struct rcu_ctrlblk;
+static void rcu_process_callbacks(struct rcu_ctrlblk *rcp);
+static int rcu_kthread(void *arg);
static void __call_rcu(struct rcu_head *head,
void (*func)(struct rcu_head *rcu),
struct rcu_ctrlblk *rcp);
@@ -123,7 +108,7 @@ void rcu_sched_qs(int cpu)
{
if (rcu_qsctr_help(&rcu_sched_ctrlblk) +
rcu_qsctr_help(&rcu_bh_ctrlblk))
- raise_softirq(RCU_SOFTIRQ);
+ invoke_rcu_kthread();
}
/*
@@ -132,7 +117,7 @@ void rcu_sched_qs(int cpu)
void rcu_bh_qs(int cpu)
{
if (rcu_qsctr_help(&rcu_bh_ctrlblk))
- raise_softirq(RCU_SOFTIRQ);
+ invoke_rcu_kthread();
}
/*
@@ -152,13 +137,14 @@ void rcu_check_callbacks(int cpu, int user)
}
/*
- * Helper function for rcu_process_callbacks() that operates on the
- * specified rcu_ctrlkblk structure.
+ * Invoke the RCU callbacks on the specified rcu_ctrlkblk structure
+ * whose grace period has elapsed.
*/
-static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
+static void rcu_process_callbacks(struct rcu_ctrlblk *rcp)
{
struct rcu_head *next, *list;
unsigned long flags;
+ RCU_TRACE(int cb_count = 0);
/* If no RCU callbacks ready to invoke, just return. */
if (&rcp->rcucblist == rcp->donetail)
@@ -180,19 +166,58 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
next = list->next;
prefetch(next);
debug_rcu_head_unqueue(list);
+ local_bh_disable();
list->func(list);
+ local_bh_enable();
list = next;
+ RCU_TRACE(cb_count++);
}
+ RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count));
}
/*
- * Invoke any callbacks whose grace period has completed.
+ * This kthread invokes RCU callbacks whose grace periods have
+ * elapsed. It is awakened as needed, and takes the place of the
+ * RCU_SOFTIRQ that was used previously for this purpose.
+ * This is a kthread, but it is never stopped, at least not until
+ * the system goes down.
*/
-static void rcu_process_callbacks(struct softirq_action *unused)
+static int rcu_kthread(void *arg)
{
- __rcu_process_callbacks(&rcu_sched_ctrlblk);
- __rcu_process_callbacks(&rcu_bh_ctrlblk);
- rcu_preempt_process_callbacks();
+ unsigned long work;
+ unsigned long morework;
+ unsigned long flags;
+
+ for (;;) {
+ wait_event(rcu_kthread_wq, have_rcu_kthread_work != 0);
+ morework = rcu_boost();
+ local_irq_save(flags);
+ work = have_rcu_kthread_work;
+ have_rcu_kthread_work = morework;
+ local_irq_restore(flags);
+ if (work) {
+ rcu_process_callbacks(&rcu_sched_ctrlblk);
+ rcu_process_callbacks(&rcu_bh_ctrlblk);
+ rcu_preempt_process_callbacks();
+ }
+ schedule_timeout_interruptible(1); /* Leave CPU for others. */
+ }
+
+ return 0; /* Not reached, but needed to shut gcc up. */
+}
+
+/*
+ * Wake up rcu_kthread() to process callbacks now eligible for invocation
+ * or to boost readers.
+ */
+static void invoke_rcu_kthread(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ have_rcu_kthread_work = 1;
+ wake_up(&rcu_kthread_wq);
+ local_irq_restore(flags);
}
/*
@@ -230,6 +255,7 @@ static void __call_rcu(struct rcu_head *head,
local_irq_save(flags);
*rcp->curtail = head;
rcp->curtail = &head->next;
+ RCU_TRACE(rcp->qlen++);
local_irq_restore(flags);
}
@@ -282,7 +308,16 @@ void rcu_barrier_sched(void)
}
EXPORT_SYMBOL_GPL(rcu_barrier_sched);
-void __init rcu_init(void)
+/*
+ * Spawn the kthread that invokes RCU callbacks.
+ */
+static int __init rcu_spawn_kthreads(void)
{
- open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+ struct sched_param sp;
+
+ rcu_kthread_task = kthread_run(rcu_kthread, NULL, "rcu_kthread");
+ sp.sched_priority = RCU_BOOST_PRIO;
+ sched_setscheduler_nocheck(rcu_kthread_task, SCHED_FIFO, &sp);
+ return 0;
}
+early_initcall(rcu_spawn_kthreads);
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index 6ceca4f745ff..015abaea962a 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -22,6 +22,40 @@
* Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
+#include <linux/kthread.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#ifdef CONFIG_RCU_TRACE
+#define RCU_TRACE(stmt) stmt
+#else /* #ifdef CONFIG_RCU_TRACE */
+#define RCU_TRACE(stmt)
+#endif /* #else #ifdef CONFIG_RCU_TRACE */
+
+/* Global control variables for rcupdate callback mechanism. */
+struct rcu_ctrlblk {
+ struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */
+ struct rcu_head **donetail; /* ->next pointer of last "done" CB. */
+ struct rcu_head **curtail; /* ->next pointer of last CB. */
+ RCU_TRACE(long qlen); /* Number of pending CBs. */
+};
+
+/* Definition for rcupdate control block. */
+static struct rcu_ctrlblk rcu_sched_ctrlblk = {
+ .donetail = &rcu_sched_ctrlblk.rcucblist,
+ .curtail = &rcu_sched_ctrlblk.rcucblist,
+};
+
+static struct rcu_ctrlblk rcu_bh_ctrlblk = {
+ .donetail = &rcu_bh_ctrlblk.rcucblist,
+ .curtail = &rcu_bh_ctrlblk.rcucblist,
+};
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+int rcu_scheduler_active __read_mostly;
+EXPORT_SYMBOL_GPL(rcu_scheduler_active);
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
#ifdef CONFIG_TINY_PREEMPT_RCU
#include <linux/delay.h>
@@ -46,17 +80,45 @@ struct rcu_preempt_ctrlblk {
struct list_head *gp_tasks;
/* Pointer to the first task blocking the */
/* current grace period, or NULL if there */
- /* is not such task. */
+ /* is no such task. */
struct list_head *exp_tasks;
/* Pointer to first task blocking the */
/* current expedited grace period, or NULL */
/* if there is no such task. If there */
/* is no current expedited grace period, */
/* then there cannot be any such task. */
+#ifdef CONFIG_RCU_BOOST
+ struct list_head *boost_tasks;
+ /* Pointer to first task that needs to be */
+ /* priority-boosted, or NULL if no priority */
+ /* boosting is needed. If there is no */
+ /* current or expedited grace period, there */
+ /* can be no such task. */
+#endif /* #ifdef CONFIG_RCU_BOOST */
u8 gpnum; /* Current grace period. */
u8 gpcpu; /* Last grace period blocked by the CPU. */
u8 completed; /* Last grace period completed. */
/* If all three are equal, RCU is idle. */
+#ifdef CONFIG_RCU_BOOST
+ s8 boosted_this_gp; /* Has boosting already happened? */
+ unsigned long boost_time; /* When to start boosting (jiffies) */
+#endif /* #ifdef CONFIG_RCU_BOOST */
+#ifdef CONFIG_RCU_TRACE
+ unsigned long n_grace_periods;
+#ifdef CONFIG_RCU_BOOST
+ unsigned long n_tasks_boosted;
+ unsigned long n_exp_boosts;
+ unsigned long n_normal_boosts;
+ unsigned long n_normal_balk_blkd_tasks;
+ unsigned long n_normal_balk_gp_tasks;
+ unsigned long n_normal_balk_boost_tasks;
+ unsigned long n_normal_balk_boosted;
+ unsigned long n_normal_balk_notyet;
+ unsigned long n_normal_balk_nos;
+ unsigned long n_exp_balk_blkd_tasks;
+ unsigned long n_exp_balk_nos;
+#endif /* #ifdef CONFIG_RCU_BOOST */
+#endif /* #ifdef CONFIG_RCU_TRACE */
};
static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = {
@@ -122,6 +184,210 @@ static int rcu_preempt_gp_in_progress(void)
}
/*
+ * Advance a ->blkd_tasks-list pointer to the next entry, instead
+ * returning NULL if at the end of the list.
+ */
+static struct list_head *rcu_next_node_entry(struct task_struct *t)
+{
+ struct list_head *np;
+
+ np = t->rcu_node_entry.next;
+ if (np == &rcu_preempt_ctrlblk.blkd_tasks)
+ np = NULL;
+ return np;
+}
+
+#ifdef CONFIG_RCU_TRACE
+
+#ifdef CONFIG_RCU_BOOST
+static void rcu_initiate_boost_trace(void);
+static void rcu_initiate_exp_boost_trace(void);
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
+/*
+ * Dump additional statistice for TINY_PREEMPT_RCU.
+ */
+static void show_tiny_preempt_stats(struct seq_file *m)
+{
+ seq_printf(m, "rcu_preempt: qlen=%ld gp=%lu g%u/p%u/c%u tasks=%c%c%c\n",
+ rcu_preempt_ctrlblk.rcb.qlen,
+ rcu_preempt_ctrlblk.n_grace_periods,
+ rcu_preempt_ctrlblk.gpnum,
+ rcu_preempt_ctrlblk.gpcpu,
+ rcu_preempt_ctrlblk.completed,
+ "T."[list_empty(&rcu_preempt_ctrlblk.blkd_tasks)],
+ "N."[!rcu_preempt_ctrlblk.gp_tasks],
+ "E."[!rcu_preempt_ctrlblk.exp_tasks]);
+#ifdef CONFIG_RCU_BOOST
+ seq_printf(m, " ttb=%c btg=",
+ "B."[!rcu_preempt_ctrlblk.boost_tasks]);
+ switch (rcu_preempt_ctrlblk.boosted_this_gp) {
+ case -1:
+ seq_puts(m, "exp");
+ break;
+ case 0:
+ seq_puts(m, "no");
+ break;
+ case 1:
+ seq_puts(m, "begun");
+ break;
+ case 2:
+ seq_puts(m, "done");
+ break;
+ default:
+ seq_printf(m, "?%d?", rcu_preempt_ctrlblk.boosted_this_gp);
+ }
+ seq_printf(m, " ntb=%lu neb=%lu nnb=%lu j=%04x bt=%04x\n",
+ rcu_preempt_ctrlblk.n_tasks_boosted,
+ rcu_preempt_ctrlblk.n_exp_boosts,
+ rcu_preempt_ctrlblk.n_normal_boosts,
+ (int)(jiffies & 0xffff),
+ (int)(rcu_preempt_ctrlblk.boost_time & 0xffff));
+ seq_printf(m, " %s: nt=%lu gt=%lu bt=%lu b=%lu ny=%lu nos=%lu\n",
+ "normal balk",
+ rcu_preempt_ctrlblk.n_normal_balk_blkd_tasks,
+ rcu_preempt_ctrlblk.n_normal_balk_gp_tasks,
+ rcu_preempt_ctrlblk.n_normal_balk_boost_tasks,
+ rcu_preempt_ctrlblk.n_normal_balk_boosted,
+ rcu_preempt_ctrlblk.n_normal_balk_notyet,
+ rcu_preempt_ctrlblk.n_normal_balk_nos);
+ seq_printf(m, " exp balk: bt=%lu nos=%lu\n",
+ rcu_preempt_ctrlblk.n_exp_balk_blkd_tasks,
+ rcu_preempt_ctrlblk.n_exp_balk_nos);
+#endif /* #ifdef CONFIG_RCU_BOOST */
+}
+
+#endif /* #ifdef CONFIG_RCU_TRACE */
+
+#ifdef CONFIG_RCU_BOOST
+
+#include "rtmutex_common.h"
+
+/*
+ * Carry out RCU priority boosting on the task indicated by ->boost_tasks,
+ * and advance ->boost_tasks to the next task in the ->blkd_tasks list.
+ */
+static int rcu_boost(void)
+{
+ unsigned long flags;
+ struct rt_mutex mtx;
+ struct list_head *np;
+ struct task_struct *t;
+
+ if (rcu_preempt_ctrlblk.boost_tasks == NULL)
+ return 0; /* Nothing to boost. */
+ raw_local_irq_save(flags);
+ rcu_preempt_ctrlblk.boosted_this_gp++;
+ t = container_of(rcu_preempt_ctrlblk.boost_tasks, struct task_struct,
+ rcu_node_entry);
+ np = rcu_next_node_entry(t);
+ rt_mutex_init_proxy_locked(&mtx, t);
+ t->rcu_boost_mutex = &mtx;
+ t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BOOSTED;
+ raw_local_irq_restore(flags);
+ rt_mutex_lock(&mtx);
+ RCU_TRACE(rcu_preempt_ctrlblk.n_tasks_boosted++);
+ rcu_preempt_ctrlblk.boosted_this_gp++;
+ rt_mutex_unlock(&mtx);
+ return rcu_preempt_ctrlblk.boost_tasks != NULL;
+}
+
+/*
+ * Check to see if it is now time to start boosting RCU readers blocking
+ * the current grace period, and, if so, tell the rcu_kthread_task to
+ * start boosting them. If there is an expedited boost in progress,
+ * we wait for it to complete.
+ *
+ * If there are no blocked readers blocking the current grace period,
+ * return 0 to let the caller know, otherwise return 1. Note that this
+ * return value is independent of whether or not boosting was done.
+ */
+static int rcu_initiate_boost(void)
+{
+ if (!rcu_preempt_blocked_readers_cgp()) {
+ RCU_TRACE(rcu_preempt_ctrlblk.n_normal_balk_blkd_tasks++);
+ return 0;
+ }
+ if (rcu_preempt_ctrlblk.gp_tasks != NULL &&
+ rcu_preempt_ctrlblk.boost_tasks == NULL &&
+ rcu_preempt_ctrlblk.boosted_this_gp == 0 &&
+ ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time)) {
+ rcu_preempt_ctrlblk.boost_tasks = rcu_preempt_ctrlblk.gp_tasks;
+ invoke_rcu_kthread();
+ RCU_TRACE(rcu_preempt_ctrlblk.n_normal_boosts++);
+ } else
+ RCU_TRACE(rcu_initiate_boost_trace());
+ return 1;
+}
+
+/*
+ * Initiate boosting for an expedited grace period.
+ */
+static void rcu_initiate_expedited_boost(void)
+{
+ unsigned long flags;
+
+ raw_local_irq_save(flags);
+ if (!list_empty(&rcu_preempt_ctrlblk.blkd_tasks)) {
+ rcu_preempt_ctrlblk.boost_tasks =
+ rcu_preempt_ctrlblk.blkd_tasks.next;
+ rcu_preempt_ctrlblk.boosted_this_gp = -1;
+ invoke_rcu_kthread();
+ RCU_TRACE(rcu_preempt_ctrlblk.n_exp_boosts++);
+ } else
+ RCU_TRACE(rcu_initiate_exp_boost_trace());
+ raw_local_irq_restore(flags);
+}
+
+#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000);
+
+/*
+ * Do priority-boost accounting for the start of a new grace period.
+ */
+static void rcu_preempt_boost_start_gp(void)
+{
+ rcu_preempt_ctrlblk.boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES;
+ if (rcu_preempt_ctrlblk.boosted_this_gp > 0)
+ rcu_preempt_ctrlblk.boosted_this_gp = 0;
+}
+
+#else /* #ifdef CONFIG_RCU_BOOST */
+
+/*
+ * If there is no RCU priority boosting, we don't boost.
+ */
+static int rcu_boost(void)
+{
+ return 0;
+}
+
+/*
+ * If there is no RCU priority boosting, we don't initiate boosting,
+ * but we do indicate whether there are blocked readers blocking the
+ * current grace period.
+ */
+static int rcu_initiate_boost(void)
+{
+ return rcu_preempt_blocked_readers_cgp();
+}
+
+/*
+ * If there is no RCU priority boosting, we don't initiate expedited boosting.
+ */
+static void rcu_initiate_expedited_boost(void)
+{
+}
+
+/*
+ * If there is no RCU priority boosting, nothing to do at grace-period start.
+ */
+static void rcu_preempt_boost_start_gp(void)
+{
+}
+
+#endif /* else #ifdef CONFIG_RCU_BOOST */
+
+/*
* Record a preemptible-RCU quiescent state for the specified CPU. Note
* that this just means that the task currently running on the CPU is
* in a quiescent state. There might be any number of tasks blocked
@@ -148,11 +414,14 @@ static void rcu_preempt_cpu_qs(void)
rcu_preempt_ctrlblk.gpcpu = rcu_preempt_ctrlblk.gpnum;
current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+ /* If there is no GP then there is nothing more to do. */
+ if (!rcu_preempt_gp_in_progress())
+ return;
/*
- * If there is no GP, or if blocked readers are still blocking GP,
- * then there is nothing more to do.
+ * Check up on boosting. If there are no readers blocking the
+ * current grace period, leave.
*/
- if (!rcu_preempt_gp_in_progress() || rcu_preempt_blocked_readers_cgp())
+ if (rcu_initiate_boost())
return;
/* Advance callbacks. */
@@ -164,9 +433,9 @@ static void rcu_preempt_cpu_qs(void)
if (!rcu_preempt_blocked_readers_any())
rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.nexttail;
- /* If there are done callbacks, make RCU_SOFTIRQ process them. */
+ /* If there are done callbacks, cause them to be invoked. */
if (*rcu_preempt_ctrlblk.rcb.donetail != NULL)
- raise_softirq(RCU_SOFTIRQ);
+ invoke_rcu_kthread();
}
/*
@@ -178,12 +447,16 @@ static void rcu_preempt_start_gp(void)
/* Official start of GP. */
rcu_preempt_ctrlblk.gpnum++;
+ RCU_TRACE(rcu_preempt_ctrlblk.n_grace_periods++);
/* Any blocked RCU readers block new GP. */
if (rcu_preempt_blocked_readers_any())
rcu_preempt_ctrlblk.gp_tasks =
rcu_preempt_ctrlblk.blkd_tasks.next;
+ /* Set up for RCU priority boosting. */
+ rcu_preempt_boost_start_gp();
+
/* If there is no running reader, CPU is done with GP. */
if (!rcu_preempt_running_reader())
rcu_preempt_cpu_qs();
@@ -304,14 +577,16 @@ static void rcu_read_unlock_special(struct task_struct *t)
*/
empty = !rcu_preempt_blocked_readers_cgp();
empty_exp = rcu_preempt_ctrlblk.exp_tasks == NULL;
- np = t->rcu_node_entry.next;
- if (np == &rcu_preempt_ctrlblk.blkd_tasks)
- np = NULL;
+ np = rcu_next_node_entry(t);
list_del(&t->rcu_node_entry);
if (&t->rcu_node_entry == rcu_preempt_ctrlblk.gp_tasks)
rcu_preempt_ctrlblk.gp_tasks = np;
if (&t->rcu_node_entry == rcu_preempt_ctrlblk.exp_tasks)
rcu_preempt_ctrlblk.exp_tasks = np;
+#ifdef CONFIG_RCU_BOOST
+ if (&t->rcu_node_entry == rcu_preempt_ctrlblk.boost_tasks)
+ rcu_preempt_ctrlblk.boost_tasks = np;
+#endif /* #ifdef CONFIG_RCU_BOOST */
INIT_LIST_HEAD(&t->rcu_node_entry);
/*
@@ -331,6 +606,14 @@ static void rcu_read_unlock_special(struct task_struct *t)
if (!empty_exp && rcu_preempt_ctrlblk.exp_tasks == NULL)
rcu_report_exp_done();
}
+#ifdef CONFIG_RCU_BOOST
+ /* Unboost self if was boosted. */
+ if (special & RCU_READ_UNLOCK_BOOSTED) {
+ t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BOOSTED;
+ rt_mutex_unlock(t->rcu_boost_mutex);
+ t->rcu_boost_mutex = NULL;
+ }
+#endif /* #ifdef CONFIG_RCU_BOOST */
local_irq_restore(flags);
}
@@ -374,7 +657,7 @@ static void rcu_preempt_check_callbacks(void)
rcu_preempt_cpu_qs();
if (&rcu_preempt_ctrlblk.rcb.rcucblist !=
rcu_preempt_ctrlblk.rcb.donetail)
- raise_softirq(RCU_SOFTIRQ);
+ invoke_rcu_kthread();
if (rcu_preempt_gp_in_progress() &&
rcu_cpu_blocking_cur_gp() &&
rcu_preempt_running_reader())
@@ -383,7 +666,7 @@ static void rcu_preempt_check_callbacks(void)
/*
* TINY_PREEMPT_RCU has an extra callback-list tail pointer to
- * update, so this is invoked from __rcu_process_callbacks() to
+ * update, so this is invoked from rcu_process_callbacks() to
* handle that case. Of course, it is invoked for all flavors of
* RCU, but RCU callbacks can appear only on one of the lists, and
* neither ->nexttail nor ->donetail can possibly be NULL, so there
@@ -400,7 +683,7 @@ static void rcu_preempt_remove_callbacks(struct rcu_ctrlblk *rcp)
*/
static void rcu_preempt_process_callbacks(void)
{
- __rcu_process_callbacks(&rcu_preempt_ctrlblk.rcb);
+ rcu_process_callbacks(&rcu_preempt_ctrlblk.rcb);
}
/*
@@ -417,6 +700,7 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
local_irq_save(flags);
*rcu_preempt_ctrlblk.nexttail = head;
rcu_preempt_ctrlblk.nexttail = &head->next;
+ RCU_TRACE(rcu_preempt_ctrlblk.rcb.qlen++);
rcu_preempt_start_gp(); /* checks to see if GP needed. */
local_irq_restore(flags);
}
@@ -532,6 +816,7 @@ void synchronize_rcu_expedited(void)
/* Wait for tail of ->blkd_tasks list to drain. */
if (rcu_preempted_readers_exp())
+ rcu_initiate_expedited_boost();
wait_event(sync_rcu_preempt_exp_wq,
!rcu_preempted_readers_exp());
@@ -572,6 +857,27 @@ void exit_rcu(void)
#else /* #ifdef CONFIG_TINY_PREEMPT_RCU */
+#ifdef CONFIG_RCU_TRACE
+
+/*
+ * Because preemptible RCU does not exist, it is not necessary to
+ * dump out its statistics.
+ */
+static void show_tiny_preempt_stats(struct seq_file *m)
+{
+}
+
+#endif /* #ifdef CONFIG_RCU_TRACE */
+
+/*
+ * Because preemptible RCU does not exist, it is never necessary to
+ * boost preempted RCU readers.
+ */
+static int rcu_boost(void)
+{
+ return 0;
+}
+
/*
* Because preemptible RCU does not exist, it never has any callbacks
* to check.
@@ -599,17 +905,116 @@ static void rcu_preempt_process_callbacks(void)
#endif /* #else #ifdef CONFIG_TINY_PREEMPT_RCU */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
-
#include <linux/kernel_stat.h>
/*
* During boot, we forgive RCU lockdep issues. After this function is
* invoked, we start taking RCU lockdep issues seriously.
*/
-void rcu_scheduler_starting(void)
+void __init rcu_scheduler_starting(void)
{
WARN_ON(nr_context_switches() > 0);
rcu_scheduler_active = 1;
}
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+#ifdef CONFIG_RCU_BOOST
+#define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO
+#else /* #ifdef CONFIG_RCU_BOOST */
+#define RCU_BOOST_PRIO 1
+#endif /* #else #ifdef CONFIG_RCU_BOOST */
+
+#ifdef CONFIG_RCU_TRACE
+
+#ifdef CONFIG_RCU_BOOST
+
+static void rcu_initiate_boost_trace(void)
+{
+ if (rcu_preempt_ctrlblk.gp_tasks == NULL)
+ rcu_preempt_ctrlblk.n_normal_balk_gp_tasks++;
+ else if (rcu_preempt_ctrlblk.boost_tasks != NULL)
+ rcu_preempt_ctrlblk.n_normal_balk_boost_tasks++;
+ else if (rcu_preempt_ctrlblk.boosted_this_gp != 0)
+ rcu_preempt_ctrlblk.n_normal_balk_boosted++;
+ else if (!ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time))
+ rcu_preempt_ctrlblk.n_normal_balk_notyet++;
+ else
+ rcu_preempt_ctrlblk.n_normal_balk_nos++;
+}
+
+static void rcu_initiate_exp_boost_trace(void)
+{
+ if (list_empty(&rcu_preempt_ctrlblk.blkd_tasks))
+ rcu_preempt_ctrlblk.n_exp_balk_blkd_tasks++;
+ else
+ rcu_preempt_ctrlblk.n_exp_balk_nos++;
+}
+
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
+static void rcu_trace_sub_qlen(struct rcu_ctrlblk *rcp, int n)
+{
+ unsigned long flags;
+
+ raw_local_irq_save(flags);
+ rcp->qlen -= n;
+ raw_local_irq_restore(flags);
+}
+
+/*
+ * Dump statistics for TINY_RCU, such as they are.
+ */
+static int show_tiny_stats(struct seq_file *m, void *unused)
+{
+ show_tiny_preempt_stats(m);
+ seq_printf(m, "rcu_sched: qlen: %ld\n", rcu_sched_ctrlblk.qlen);
+ seq_printf(m, "rcu_bh: qlen: %ld\n", rcu_bh_ctrlblk.qlen);
+ return 0;
+}
+
+static int show_tiny_stats_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, show_tiny_stats, NULL);
+}
+
+static const struct file_operations show_tiny_stats_fops = {
+ .owner = THIS_MODULE,
+ .open = show_tiny_stats_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static struct dentry *rcudir;
+
+static int __init rcutiny_trace_init(void)
+{
+ struct dentry *retval;
+
+ rcudir = debugfs_create_dir("rcu", NULL);
+ if (!rcudir)
+ goto free_out;
+ retval = debugfs_create_file("rcudata", 0444, rcudir,
+ NULL, &show_tiny_stats_fops);
+ if (!retval)
+ goto free_out;
+ return 0;
+free_out:
+ debugfs_remove_recursive(rcudir);
+ return 1;
+}
+
+static void __exit rcutiny_trace_cleanup(void)
+{
+ debugfs_remove_recursive(rcudir);
+}
+
+module_init(rcutiny_trace_init);
+module_exit(rcutiny_trace_cleanup);
+
+MODULE_AUTHOR("Paul E. McKenney");
+MODULE_DESCRIPTION("Read-Copy Update tracing for tiny implementation");
+MODULE_LICENSE("GPL");
+
+#endif /* #ifdef CONFIG_RCU_TRACE */
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 9d8e8fb2515f..89613f97ff26 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -47,6 +47,7 @@
#include <linux/srcu.h>
#include <linux/slab.h>
#include <asm/byteorder.h>
+#include <linux/sched.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and "
@@ -64,6 +65,9 @@ static int irqreader = 1; /* RCU readers from irq (timers). */
static int fqs_duration = 0; /* Duration of bursts (us), 0 to disable. */
static int fqs_holdoff = 0; /* Hold time within burst (us). */
static int fqs_stutter = 3; /* Wait time between bursts (s). */
+static int test_boost = 1; /* Test RCU prio boost: 0=no, 1=maybe, 2=yes. */
+static int test_boost_interval = 7; /* Interval between boost tests, seconds. */
+static int test_boost_duration = 4; /* Duration of each boost test, seconds. */
static char *torture_type = "rcu"; /* What RCU implementation to torture. */
module_param(nreaders, int, 0444);
@@ -88,6 +92,12 @@ module_param(fqs_holdoff, int, 0444);
MODULE_PARM_DESC(fqs_holdoff, "Holdoff time within fqs bursts (us)");
module_param(fqs_stutter, int, 0444);
MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)");
+module_param(test_boost, int, 0444);
+MODULE_PARM_DESC(test_boost, "Test RCU prio boost: 0=no, 1=maybe, 2=yes.");
+module_param(test_boost_interval, int, 0444);
+MODULE_PARM_DESC(test_boost_interval, "Interval between boost tests, seconds.");
+module_param(test_boost_duration, int, 0444);
+MODULE_PARM_DESC(test_boost_duration, "Duration of each boost test, seconds.");
module_param(torture_type, charp, 0444);
MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, srcu)");
@@ -109,6 +119,7 @@ static struct task_struct *stats_task;
static struct task_struct *shuffler_task;
static struct task_struct *stutter_task;
static struct task_struct *fqs_task;
+static struct task_struct *boost_tasks[NR_CPUS];
#define RCU_TORTURE_PIPE_LEN 10
@@ -134,6 +145,12 @@ static atomic_t n_rcu_torture_alloc_fail;
static atomic_t n_rcu_torture_free;
static atomic_t n_rcu_torture_mberror;
static atomic_t n_rcu_torture_error;
+static long n_rcu_torture_boost_ktrerror;
+static long n_rcu_torture_boost_rterror;
+static long n_rcu_torture_boost_allocerror;
+static long n_rcu_torture_boost_afferror;
+static long n_rcu_torture_boost_failure;
+static long n_rcu_torture_boosts;
static long n_rcu_torture_timers;
static struct list_head rcu_torture_removed;
static cpumask_var_t shuffle_tmp_mask;
@@ -147,6 +164,16 @@ static int stutter_pause_test;
#endif
int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
+#ifdef CONFIG_RCU_BOOST
+#define rcu_can_boost() 1
+#else /* #ifdef CONFIG_RCU_BOOST */
+#define rcu_can_boost() 0
+#endif /* #else #ifdef CONFIG_RCU_BOOST */
+
+static unsigned long boost_starttime; /* jiffies of next boost test start. */
+DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */
+ /* and boost task create/destroy. */
+
/* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */
#define FULLSTOP_DONTSTOP 0 /* Normal operation. */
@@ -277,6 +304,7 @@ struct rcu_torture_ops {
void (*fqs)(void);
int (*stats)(char *page);
int irq_capable;
+ int can_boost;
char *name;
};
@@ -366,6 +394,7 @@ static struct rcu_torture_ops rcu_ops = {
.fqs = rcu_force_quiescent_state,
.stats = NULL,
.irq_capable = 1,
+ .can_boost = rcu_can_boost(),
.name = "rcu"
};
@@ -408,6 +437,7 @@ static struct rcu_torture_ops rcu_sync_ops = {
.fqs = rcu_force_quiescent_state,
.stats = NULL,
.irq_capable = 1,
+ .can_boost = rcu_can_boost(),
.name = "rcu_sync"
};
@@ -424,6 +454,7 @@ static struct rcu_torture_ops rcu_expedited_ops = {
.fqs = rcu_force_quiescent_state,
.stats = NULL,
.irq_capable = 1,
+ .can_boost = rcu_can_boost(),
.name = "rcu_expedited"
};
@@ -684,6 +715,110 @@ static struct rcu_torture_ops sched_expedited_ops = {
};
/*
+ * RCU torture priority-boost testing. Runs one real-time thread per
+ * CPU for moderate bursts, repeatedly registering RCU callbacks and
+ * spinning waiting for them to be invoked. If a given callback takes
+ * too long to be invoked, we assume that priority inversion has occurred.
+ */
+
+struct rcu_boost_inflight {
+ struct rcu_head rcu;
+ int inflight;
+};
+
+static void rcu_torture_boost_cb(struct rcu_head *head)
+{
+ struct rcu_boost_inflight *rbip =
+ container_of(head, struct rcu_boost_inflight, rcu);
+
+ smp_mb(); /* Ensure RCU-core accesses precede clearing ->inflight */
+ rbip->inflight = 0;
+}
+
+static int rcu_torture_boost(void *arg)
+{
+ unsigned long call_rcu_time;
+ unsigned long endtime;
+ unsigned long oldstarttime;
+ struct rcu_boost_inflight rbi = { .inflight = 0 };
+ struct sched_param sp;
+
+ VERBOSE_PRINTK_STRING("rcu_torture_boost started");
+
+ /* Set real-time priority. */
+ sp.sched_priority = 1;
+ if (sched_setscheduler(current, SCHED_FIFO, &sp) < 0) {
+ VERBOSE_PRINTK_STRING("rcu_torture_boost RT prio failed!");
+ n_rcu_torture_boost_rterror++;
+ }
+
+ /* Each pass through the following loop does one boost-test cycle. */
+ do {
+ /* Wait for the next test interval. */
+ oldstarttime = boost_starttime;
+ while (jiffies - oldstarttime > ULONG_MAX / 2) {
+ schedule_timeout_uninterruptible(1);
+ rcu_stutter_wait("rcu_torture_boost");
+ if (kthread_should_stop() ||
+ fullstop != FULLSTOP_DONTSTOP)
+ goto checkwait;
+ }
+
+ /* Do one boost-test interval. */
+ endtime = oldstarttime + test_boost_duration * HZ;
+ call_rcu_time = jiffies;
+ while (jiffies - endtime > ULONG_MAX / 2) {
+ /* If we don't have a callback in flight, post one. */
+ if (!rbi.inflight) {
+ smp_mb(); /* RCU core before ->inflight = 1. */
+ rbi.inflight = 1;
+ call_rcu(&rbi.rcu, rcu_torture_boost_cb);
+ if (jiffies - call_rcu_time >
+ test_boost_duration * HZ - HZ / 2) {
+ VERBOSE_PRINTK_STRING("rcu_torture_boost boosting failed");
+ n_rcu_torture_boost_failure++;
+ }
+ call_rcu_time = jiffies;
+ }
+ cond_resched();
+ rcu_stutter_wait("rcu_torture_boost");
+ if (kthread_should_stop() ||
+ fullstop != FULLSTOP_DONTSTOP)
+ goto checkwait;
+ }
+
+ /*
+ * Set the start time of the next test interval.
+ * Yes, this is vulnerable to long delays, but such
+ * delays simply cause a false negative for the next
+ * interval. Besides, we are running at RT priority,
+ * so delays should be relatively rare.
+ */
+ while (oldstarttime == boost_starttime) {
+ if (mutex_trylock(&boost_mutex)) {
+ boost_starttime = jiffies +
+ test_boost_interval * HZ;
+ n_rcu_torture_boosts++;
+ mutex_unlock(&boost_mutex);
+ break;
+ }
+ schedule_timeout_uninterruptible(1);
+ }
+
+ /* Go do the stutter. */
+checkwait: rcu_stutter_wait("rcu_torture_boost");
+ } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
+
+ /* Clean up and exit. */
+ VERBOSE_PRINTK_STRING("rcu_torture_boost task stopping");
+ rcutorture_shutdown_absorb("rcu_torture_boost");
+ while (!kthread_should_stop() || rbi.inflight)
+ schedule_timeout_uninterruptible(1);
+ smp_mb(); /* order accesses to ->inflight before stack-frame death. */
+ return 0;
+}
+
+/*
* RCU torture force-quiescent-state kthread. Repeatedly induces
* bursts of calls to force_quiescent_state(), increasing the probability
* of occurrence of some important types of race conditions.
@@ -933,7 +1068,8 @@ rcu_torture_printk(char *page)
cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG);
cnt += sprintf(&page[cnt],
"rtc: %p ver: %ld tfle: %d rta: %d rtaf: %d rtf: %d "
- "rtmbe: %d nt: %ld",
+ "rtmbe: %d rtbke: %ld rtbre: %ld rtbae: %ld rtbafe: %ld "
+ "rtbf: %ld rtb: %ld nt: %ld",
rcu_torture_current,
rcu_torture_current_version,
list_empty(&rcu_torture_freelist),
@@ -941,8 +1077,19 @@ rcu_torture_printk(char *page)
atomic_read(&n_rcu_torture_alloc_fail),
atomic_read(&n_rcu_torture_free),
atomic_read(&n_rcu_torture_mberror),
+ n_rcu_torture_boost_ktrerror,
+ n_rcu_torture_boost_rterror,
+ n_rcu_torture_boost_allocerror,
+ n_rcu_torture_boost_afferror,
+ n_rcu_torture_boost_failure,
+ n_rcu_torture_boosts,
n_rcu_torture_timers);
- if (atomic_read(&n_rcu_torture_mberror) != 0)
+ if (atomic_read(&n_rcu_torture_mberror) != 0 ||
+ n_rcu_torture_boost_ktrerror != 0 ||
+ n_rcu_torture_boost_rterror != 0 ||
+ n_rcu_torture_boost_allocerror != 0 ||
+ n_rcu_torture_boost_afferror != 0 ||
+ n_rcu_torture_boost_failure != 0)
cnt += sprintf(&page[cnt], " !!!");
cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
if (i > 1) {
@@ -1094,22 +1241,91 @@ rcu_torture_stutter(void *arg)
}
static inline void
-rcu_torture_print_module_parms(char *tag)
+rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, char *tag)
{
printk(KERN_ALERT "%s" TORTURE_FLAG
"--- %s: nreaders=%d nfakewriters=%d "
"stat_interval=%d verbose=%d test_no_idle_hz=%d "
"shuffle_interval=%d stutter=%d irqreader=%d "
- "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d\n",
+ "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d "
+ "test_boost=%d/%d test_boost_interval=%d "
+ "test_boost_duration=%d\n",
torture_type, tag, nrealreaders, nfakewriters,
stat_interval, verbose, test_no_idle_hz, shuffle_interval,
- stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter);
+ stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
+ test_boost, cur_ops->can_boost,
+ test_boost_interval, test_boost_duration);
}
-static struct notifier_block rcutorture_nb = {
+static struct notifier_block rcutorture_shutdown_nb = {
.notifier_call = rcutorture_shutdown_notify,
};
+static void rcutorture_booster_cleanup(int cpu)
+{
+ struct task_struct *t;
+
+ if (boost_tasks[cpu] == NULL)
+ return;
+ mutex_lock(&boost_mutex);
+ VERBOSE_PRINTK_STRING("Stopping rcu_torture_boost task");
+ t = boost_tasks[cpu];
+ boost_tasks[cpu] = NULL;
+ mutex_unlock(&boost_mutex);
+
+ /* This must be outside of the mutex, otherwise deadlock! */
+ kthread_stop(t);
+}
+
+static int rcutorture_booster_init(int cpu)
+{
+ int retval;
+
+ if (boost_tasks[cpu] != NULL)
+ return 0; /* Already created, nothing more to do. */
+
+ /* Don't allow time recalculation while creating a new task. */
+ mutex_lock(&boost_mutex);
+ VERBOSE_PRINTK_STRING("Creating rcu_torture_boost task");
+ boost_tasks[cpu] = kthread_create(rcu_torture_boost, NULL,
+ "rcu_torture_boost");
+ if (IS_ERR(boost_tasks[cpu])) {
+ retval = PTR_ERR(boost_tasks[cpu]);
+ VERBOSE_PRINTK_STRING("rcu_torture_boost task create failed");
+ n_rcu_torture_boost_ktrerror++;
+ boost_tasks[cpu] = NULL;
+ mutex_unlock(&boost_mutex);
+ return retval;
+ }
+ kthread_bind(boost_tasks[cpu], cpu);
+ wake_up_process(boost_tasks[cpu]);
+ mutex_unlock(&boost_mutex);
+ return 0;
+}
+
+static int rcutorture_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ long cpu = (long)hcpu;
+
+ switch (action) {
+ case CPU_ONLINE:
+ case CPU_DOWN_FAILED:
+ (void)rcutorture_booster_init(cpu);
+ break;
+ case CPU_DOWN_PREPARE:
+ rcutorture_booster_cleanup(cpu);
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block rcutorture_cpu_nb = {
+ .notifier_call = rcutorture_cpu_notify,
+};
+
static void
rcu_torture_cleanup(void)
{
@@ -1127,7 +1343,7 @@ rcu_torture_cleanup(void)
}
fullstop = FULLSTOP_RMMOD;
mutex_unlock(&fullstop_mutex);
- unregister_reboot_notifier(&rcutorture_nb);
+ unregister_reboot_notifier(&rcutorture_shutdown_nb);
if (stutter_task) {
VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task");
kthread_stop(stutter_task);
@@ -1184,6 +1400,12 @@ rcu_torture_cleanup(void)
kthread_stop(fqs_task);
}
fqs_task = NULL;
+ if ((test_boost == 1 && cur_ops->can_boost) ||
+ test_boost == 2) {
+ unregister_cpu_notifier(&rcutorture_cpu_nb);
+ for_each_possible_cpu(i)
+ rcutorture_booster_cleanup(i);
+ }
/* Wait for all RCU callbacks to fire. */
@@ -1195,9 +1417,9 @@ rcu_torture_cleanup(void)
if (cur_ops->cleanup)
cur_ops->cleanup();
if (atomic_read(&n_rcu_torture_error))
- rcu_torture_print_module_parms("End of test: FAILURE");
+ rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE");
else
- rcu_torture_print_module_parms("End of test: SUCCESS");
+ rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS");
}
static int __init
@@ -1242,7 +1464,7 @@ rcu_torture_init(void)
nrealreaders = nreaders;
else
nrealreaders = 2 * num_online_cpus();
- rcu_torture_print_module_parms("Start of test");
+ rcu_torture_print_module_parms(cur_ops, "Start of test");
fullstop = FULLSTOP_DONTSTOP;
/* Set up the freelist. */
@@ -1263,6 +1485,12 @@ rcu_torture_init(void)
atomic_set(&n_rcu_torture_free, 0);
atomic_set(&n_rcu_torture_mberror, 0);
atomic_set(&n_rcu_torture_error, 0);
+ n_rcu_torture_boost_ktrerror = 0;
+ n_rcu_torture_boost_rterror = 0;
+ n_rcu_torture_boost_allocerror = 0;
+ n_rcu_torture_boost_afferror = 0;
+ n_rcu_torture_boost_failure = 0;
+ n_rcu_torture_boosts = 0;
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
atomic_set(&rcu_torture_wcount[i], 0);
for_each_possible_cpu(cpu) {
@@ -1376,7 +1604,27 @@ rcu_torture_init(void)
goto unwind;
}
}
- register_reboot_notifier(&rcutorture_nb);
+ if (test_boost_interval < 1)
+ test_boost_interval = 1;
+ if (test_boost_duration < 2)
+ test_boost_duration = 2;
+ if ((test_boost == 1 && cur_ops->can_boost) ||
+ test_boost == 2) {
+ int retval;
+
+ boost_starttime = jiffies + test_boost_interval * HZ;
+ register_cpu_notifier(&rcutorture_cpu_nb);
+ for_each_possible_cpu(i) {
+ if (cpu_is_offline(i))
+ continue; /* Heuristic: CPU can go offline. */
+ retval = rcutorture_booster_init(i);
+ if (retval < 0) {
+ firsterr = retval;
+ goto unwind;
+ }
+ }
+ }
+ register_reboot_notifier(&rcutorture_shutdown_nb);
mutex_unlock(&fullstop_mutex);
return 0;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index ccdc04c47981..d0ddfea6579d 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -67,9 +67,6 @@ static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
.gpnum = -300, \
.completed = -300, \
.onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname.onofflock), \
- .orphan_cbs_list = NULL, \
- .orphan_cbs_tail = &structname.orphan_cbs_list, \
- .orphan_qlen = 0, \
.fqslock = __RAW_SPIN_LOCK_UNLOCKED(&structname.fqslock), \
.n_force_qs = 0, \
.n_force_qs_ngp = 0, \
@@ -620,9 +617,17 @@ static void __init check_cpu_stall_init(void)
static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
{
if (rdp->gpnum != rnp->gpnum) {
- rdp->qs_pending = 1;
- rdp->passed_quiesc = 0;
+ /*
+ * If the current grace period is waiting for this CPU,
+ * set up to detect a quiescent state, otherwise don't
+ * go looking for one.
+ */
rdp->gpnum = rnp->gpnum;
+ if (rnp->qsmask & rdp->grpmask) {
+ rdp->qs_pending = 1;
+ rdp->passed_quiesc = 0;
+ } else
+ rdp->qs_pending = 0;
}
}
@@ -681,6 +686,24 @@ __rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_dat
/* Remember that we saw this grace-period completion. */
rdp->completed = rnp->completed;
+
+ /*
+ * If we were in an extended quiescent state, we may have
+ * missed some grace periods that others CPUs handled on
+ * our behalf. Catch up with this state to avoid noting
+ * spurious new grace periods. If another grace period
+ * has started, then rnp->gpnum will have advanced, so
+ * we will detect this later on.
+ */
+ if (ULONG_CMP_LT(rdp->gpnum, rdp->completed))
+ rdp->gpnum = rdp->completed;
+
+ /*
+ * If RCU does not need a quiescent state from this CPU,
+ * then make sure that this CPU doesn't go looking for one.
+ */
+ if ((rnp->qsmask & rdp->grpmask) == 0)
+ rdp->qs_pending = 0;
}
}
@@ -984,53 +1007,31 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
#ifdef CONFIG_HOTPLUG_CPU
/*
- * Move a dying CPU's RCU callbacks to the ->orphan_cbs_list for the
- * specified flavor of RCU. The callbacks will be adopted by the next
- * _rcu_barrier() invocation or by the CPU_DEAD notifier, whichever
- * comes first. Because this is invoked from the CPU_DYING notifier,
- * irqs are already disabled.
+ * Move a dying CPU's RCU callbacks to online CPU's callback list.
+ * Synchronization is not required because this function executes
+ * in stop_machine() context.
*/
-static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
+static void rcu_send_cbs_to_online(struct rcu_state *rsp)
{
int i;
+ /* current DYING CPU is cleared in the cpu_online_mask */
+ int receive_cpu = cpumask_any(cpu_online_mask);
struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
+ struct rcu_data *receive_rdp = per_cpu_ptr(rsp->rda, receive_cpu);
if (rdp->nxtlist == NULL)
return; /* irqs disabled, so comparison is stable. */
- raw_spin_lock(&rsp->onofflock); /* irqs already disabled. */
- *rsp->orphan_cbs_tail = rdp->nxtlist;
- rsp->orphan_cbs_tail = rdp->nxttail[RCU_NEXT_TAIL];
+
+ *receive_rdp->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist;
+ receive_rdp->nxttail[RCU_NEXT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+ receive_rdp->qlen += rdp->qlen;
+ receive_rdp->n_cbs_adopted += rdp->qlen;
+ rdp->n_cbs_orphaned += rdp->qlen;
+
rdp->nxtlist = NULL;
for (i = 0; i < RCU_NEXT_SIZE; i++)
rdp->nxttail[i] = &rdp->nxtlist;
- rsp->orphan_qlen += rdp->qlen;
- rdp->n_cbs_orphaned += rdp->qlen;
rdp->qlen = 0;
- raw_spin_unlock(&rsp->onofflock); /* irqs remain disabled. */
-}
-
-/*
- * Adopt previously orphaned RCU callbacks.
- */
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
-{
- unsigned long flags;
- struct rcu_data *rdp;
-
- raw_spin_lock_irqsave(&rsp->onofflock, flags);
- rdp = this_cpu_ptr(rsp->rda);
- if (rsp->orphan_cbs_list == NULL) {
- raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
- return;
- }
- *rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_list;
- rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_tail;
- rdp->qlen += rsp->orphan_qlen;
- rdp->n_cbs_adopted += rsp->orphan_qlen;
- rsp->orphan_cbs_list = NULL;
- rsp->orphan_cbs_tail = &rsp->orphan_cbs_list;
- rsp->orphan_qlen = 0;
- raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
}
/*
@@ -1081,8 +1082,6 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
raw_spin_unlock_irqrestore(&rnp->lock, flags);
if (need_report & RCU_OFL_TASKS_EXP_GP)
rcu_report_exp_rnp(rsp, rnp);
-
- rcu_adopt_orphan_cbs(rsp);
}
/*
@@ -1100,11 +1099,7 @@ static void rcu_offline_cpu(int cpu)
#else /* #ifdef CONFIG_HOTPLUG_CPU */
-static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
-{
-}
-
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+static void rcu_send_cbs_to_online(struct rcu_state *rsp)
{
}
@@ -1440,22 +1435,11 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
*/
local_irq_save(flags);
rdp = this_cpu_ptr(rsp->rda);
- rcu_process_gp_end(rsp, rdp);
- check_for_new_grace_period(rsp, rdp);
/* Add the callback to our list. */
*rdp->nxttail[RCU_NEXT_TAIL] = head;
rdp->nxttail[RCU_NEXT_TAIL] = &head->next;
- /* Start a new grace period if one not already started. */
- if (!rcu_gp_in_progress(rsp)) {
- unsigned long nestflag;
- struct rcu_node *rnp_root = rcu_get_root(rsp);
-
- raw_spin_lock_irqsave(&rnp_root->lock, nestflag);
- rcu_start_gp(rsp, nestflag); /* releases rnp_root->lock. */
- }
-
/*
* Force the grace period if too many callbacks or too long waiting.
* Enforce hysteresis, and don't invoke force_quiescent_state()
@@ -1464,12 +1448,27 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
* is the only one waiting for a grace period to complete.
*/
if (unlikely(++rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {
- rdp->blimit = LONG_MAX;
- if (rsp->n_force_qs == rdp->n_force_qs_snap &&
- *rdp->nxttail[RCU_DONE_TAIL] != head)
- force_quiescent_state(rsp, 0);
- rdp->n_force_qs_snap = rsp->n_force_qs;
- rdp->qlen_last_fqs_check = rdp->qlen;
+
+ /* Are we ignoring a completed grace period? */
+ rcu_process_gp_end(rsp, rdp);
+ check_for_new_grace_period(rsp, rdp);
+
+ /* Start a new grace period if one not already started. */
+ if (!rcu_gp_in_progress(rsp)) {
+ unsigned long nestflag;
+ struct rcu_node *rnp_root = rcu_get_root(rsp);
+
+ raw_spin_lock_irqsave(&rnp_root->lock, nestflag);
+ rcu_start_gp(rsp, nestflag); /* rlses rnp_root->lock */
+ } else {
+ /* Give the grace period a kick. */
+ rdp->blimit = LONG_MAX;
+ if (rsp->n_force_qs == rdp->n_force_qs_snap &&
+ *rdp->nxttail[RCU_DONE_TAIL] != head)
+ force_quiescent_state(rsp, 0);
+ rdp->n_force_qs_snap = rsp->n_force_qs;
+ rdp->qlen_last_fqs_check = rdp->qlen;
+ }
} else if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies))
force_quiescent_state(rsp, 1);
local_irq_restore(flags);
@@ -1699,13 +1698,12 @@ static void _rcu_barrier(struct rcu_state *rsp,
* decrement rcu_barrier_cpu_count -- otherwise the first CPU
* might complete its grace period before all of the other CPUs
* did their increment, causing this function to return too
- * early.
+ * early. Note that on_each_cpu() disables irqs, which prevents
+ * any CPUs from coming online or going offline until each online
+ * CPU has queued its RCU-barrier callback.
*/
atomic_set(&rcu_barrier_cpu_count, 1);
- preempt_disable(); /* stop CPU_DYING from filling orphan_cbs_list */
- rcu_adopt_orphan_cbs(rsp);
on_each_cpu(rcu_barrier_func, (void *)call_rcu_func, 1);
- preempt_enable(); /* CPU_DYING can again fill orphan_cbs_list */
if (atomic_dec_and_test(&rcu_barrier_cpu_count))
complete(&rcu_barrier_completion);
wait_for_completion(&rcu_barrier_completion);
@@ -1831,18 +1829,13 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
case CPU_DYING:
case CPU_DYING_FROZEN:
/*
- * preempt_disable() in _rcu_barrier() prevents stop_machine(),
- * so when "on_each_cpu(rcu_barrier_func, (void *)type, 1);"
- * returns, all online cpus have queued rcu_barrier_func().
- * The dying CPU clears its cpu_online_mask bit and
- * moves all of its RCU callbacks to ->orphan_cbs_list
- * in the context of stop_machine(), so subsequent calls
- * to _rcu_barrier() will adopt these callbacks and only
- * then queue rcu_barrier_func() on all remaining CPUs.
+ * The whole machine is "stopped" except this CPU, so we can
+ * touch any data without introducing corruption. We send the
+ * dying CPU's callbacks to an arbitrarily chosen online CPU.
*/
- rcu_send_cbs_to_orphanage(&rcu_bh_state);
- rcu_send_cbs_to_orphanage(&rcu_sched_state);
- rcu_preempt_send_cbs_to_orphanage();
+ rcu_send_cbs_to_online(&rcu_bh_state);
+ rcu_send_cbs_to_online(&rcu_sched_state);
+ rcu_preempt_send_cbs_to_online();
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
@@ -1880,8 +1873,9 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
{
int i;
- for (i = NUM_RCU_LVLS - 1; i >= 0; i--)
+ for (i = NUM_RCU_LVLS - 1; i > 0; i--)
rsp->levelspread[i] = CONFIG_RCU_FANOUT;
+ rsp->levelspread[0] = RCU_FANOUT_LEAF;
}
#else /* #ifdef CONFIG_RCU_FANOUT_EXACT */
static void __init rcu_init_levelspread(struct rcu_state *rsp)
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 91d4170c5c13..e8f057e44e3e 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -31,46 +31,51 @@
/*
* Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT.
* In theory, it should be possible to add more levels straightforwardly.
- * In practice, this has not been tested, so there is probably some
- * bug somewhere.
+ * In practice, this did work well going from three levels to four.
+ * Of course, your mileage may vary.
*/
#define MAX_RCU_LVLS 4
-#define RCU_FANOUT (CONFIG_RCU_FANOUT)
-#define RCU_FANOUT_SQ (RCU_FANOUT * RCU_FANOUT)
-#define RCU_FANOUT_CUBE (RCU_FANOUT_SQ * RCU_FANOUT)
-#define RCU_FANOUT_FOURTH (RCU_FANOUT_CUBE * RCU_FANOUT)
-
-#if NR_CPUS <= RCU_FANOUT
+#if CONFIG_RCU_FANOUT > 16
+#define RCU_FANOUT_LEAF 16
+#else /* #if CONFIG_RCU_FANOUT > 16 */
+#define RCU_FANOUT_LEAF (CONFIG_RCU_FANOUT)
+#endif /* #else #if CONFIG_RCU_FANOUT > 16 */
+#define RCU_FANOUT_1 (RCU_FANOUT_LEAF)
+#define RCU_FANOUT_2 (RCU_FANOUT_1 * CONFIG_RCU_FANOUT)
+#define RCU_FANOUT_3 (RCU_FANOUT_2 * CONFIG_RCU_FANOUT)
+#define RCU_FANOUT_4 (RCU_FANOUT_3 * CONFIG_RCU_FANOUT)
+
+#if NR_CPUS <= RCU_FANOUT_1
# define NUM_RCU_LVLS 1
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 (NR_CPUS)
# define NUM_RCU_LVL_2 0
# define NUM_RCU_LVL_3 0
# define NUM_RCU_LVL_4 0
-#elif NR_CPUS <= RCU_FANOUT_SQ
+#elif NR_CPUS <= RCU_FANOUT_2
# define NUM_RCU_LVLS 2
# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
# define NUM_RCU_LVL_2 (NR_CPUS)
# define NUM_RCU_LVL_3 0
# define NUM_RCU_LVL_4 0
-#elif NR_CPUS <= RCU_FANOUT_CUBE
+#elif NR_CPUS <= RCU_FANOUT_3
# define NUM_RCU_LVLS 3
# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
-# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
-# define NUM_RCU_LVL_3 NR_CPUS
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
+# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+# define NUM_RCU_LVL_3 (NR_CPUS)
# define NUM_RCU_LVL_4 0
-#elif NR_CPUS <= RCU_FANOUT_FOURTH
+#elif NR_CPUS <= RCU_FANOUT_4
# define NUM_RCU_LVLS 4
# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_CUBE)
-# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
-# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
-# define NUM_RCU_LVL_4 NR_CPUS
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
+# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
+# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+# define NUM_RCU_LVL_4 (NR_CPUS)
#else
# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
-#endif /* #if (NR_CPUS) <= RCU_FANOUT */
+#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4)
#define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
@@ -203,8 +208,8 @@ struct rcu_data {
long qlen_last_fqs_check;
/* qlen at last check for QS forcing */
unsigned long n_cbs_invoked; /* count of RCU cbs invoked. */
- unsigned long n_cbs_orphaned; /* RCU cbs sent to orphanage. */
- unsigned long n_cbs_adopted; /* RCU cbs adopted from orphanage. */
+ unsigned long n_cbs_orphaned; /* RCU cbs orphaned by dying CPU */
+ unsigned long n_cbs_adopted; /* RCU cbs adopted from dying CPU */
unsigned long n_force_qs_snap;
/* did other CPU force QS recently? */
long blimit; /* Upper limit on a processed batch */
@@ -309,15 +314,7 @@ struct rcu_state {
/* End of fields guarded by root rcu_node's lock. */
raw_spinlock_t onofflock; /* exclude on/offline and */
- /* starting new GP. Also */
- /* protects the following */
- /* orphan_cbs fields. */
- struct rcu_head *orphan_cbs_list; /* list of rcu_head structs */
- /* orphaned by all CPUs in */
- /* a given leaf rcu_node */
- /* going offline. */
- struct rcu_head **orphan_cbs_tail; /* And tail pointer. */
- long orphan_qlen; /* Number of orphaned cbs. */
+ /* starting new GP. */
raw_spinlock_t fqslock; /* Only one task forcing */
/* quiescent states. */
unsigned long jiffies_force_qs; /* Time at which to invoke */
@@ -390,7 +387,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp);
static int rcu_preempt_pending(int cpu);
static int rcu_preempt_needs_cpu(int cpu);
static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
-static void rcu_preempt_send_cbs_to_orphanage(void);
+static void rcu_preempt_send_cbs_to_online(void);
static void __init __rcu_init_preempt(void);
static void rcu_needs_cpu_flush(void);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 71a4147473f9..a3638710dc67 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -25,6 +25,7 @@
*/
#include <linux/delay.h>
+#include <linux/stop_machine.h>
/*
* Check the RCU kernel configuration parameters and print informative
@@ -773,11 +774,11 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
}
/*
- * Move preemptable RCU's callbacks to ->orphan_cbs_list.
+ * Move preemptable RCU's callbacks from dying CPU to other online CPU.
*/
-static void rcu_preempt_send_cbs_to_orphanage(void)
+static void rcu_preempt_send_cbs_to_online(void)
{
- rcu_send_cbs_to_orphanage(&rcu_preempt_state);
+ rcu_send_cbs_to_online(&rcu_preempt_state);
}
/*
@@ -1001,7 +1002,7 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
/*
* Because there is no preemptable RCU, there are no callbacks to move.
*/
-static void rcu_preempt_send_cbs_to_orphanage(void)
+static void rcu_preempt_send_cbs_to_online(void)
{
}
@@ -1014,6 +1015,132 @@ static void __init __rcu_init_preempt(void)
#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
+#ifndef CONFIG_SMP
+
+void synchronize_sched_expedited(void)
+{
+ cond_resched();
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#else /* #ifndef CONFIG_SMP */
+
+static atomic_t sync_sched_expedited_started = ATOMIC_INIT(0);
+static atomic_t sync_sched_expedited_done = ATOMIC_INIT(0);
+
+static int synchronize_sched_expedited_cpu_stop(void *data)
+{
+ /*
+ * There must be a full memory barrier on each affected CPU
+ * between the time that try_stop_cpus() is called and the
+ * time that it returns.
+ *
+ * In the current initial implementation of cpu_stop, the
+ * above condition is already met when the control reaches
+ * this point and the following smp_mb() is not strictly
+ * necessary. Do smp_mb() anyway for documentation and
+ * robustness against future implementation changes.
+ */
+ smp_mb(); /* See above comment block. */
+ return 0;
+}
+
+/*
+ * Wait for an rcu-sched grace period to elapse, but use "big hammer"
+ * approach to force grace period to end quickly. This consumes
+ * significant time on all CPUs, and is thus not recommended for
+ * any sort of common-case code.
+ *
+ * Note that it is illegal to call this function while holding any
+ * lock that is acquired by a CPU-hotplug notifier. Failing to
+ * observe this restriction will result in deadlock.
+ *
+ * This implementation can be thought of as an application of ticket
+ * locking to RCU, with sync_sched_expedited_started and
+ * sync_sched_expedited_done taking on the roles of the halves
+ * of the ticket-lock word. Each task atomically increments
+ * sync_sched_expedited_started upon entry, snapshotting the old value,
+ * then attempts to stop all the CPUs. If this succeeds, then each
+ * CPU will have executed a context switch, resulting in an RCU-sched
+ * grace period. We are then done, so we use atomic_cmpxchg() to
+ * update sync_sched_expedited_done to match our snapshot -- but
+ * only if someone else has not already advanced past our snapshot.
+ *
+ * On the other hand, if try_stop_cpus() fails, we check the value
+ * of sync_sched_expedited_done. If it has advanced past our
+ * initial snapshot, then someone else must have forced a grace period
+ * some time after we took our snapshot. In this case, our work is
+ * done for us, and we can simply return. Otherwise, we try again,
+ * but keep our initial snapshot for purposes of checking for someone
+ * doing our work for us.
+ *
+ * If we fail too many times in a row, we fall back to synchronize_sched().
+ */
+void synchronize_sched_expedited(void)
+{
+ int firstsnap, s, snap, trycount = 0;
+
+ /* Note that atomic_inc_return() implies full memory barrier. */
+ firstsnap = snap = atomic_inc_return(&sync_sched_expedited_started);
+ get_online_cpus();
+
+ /*
+ * Each pass through the following loop attempts to force a
+ * context switch on each CPU.
+ */
+ while (try_stop_cpus(cpu_online_mask,
+ synchronize_sched_expedited_cpu_stop,
+ NULL) == -EAGAIN) {
+ put_online_cpus();
+
+ /* No joy, try again later. Or just synchronize_sched(). */
+ if (trycount++ < 10)
+ udelay(trycount * num_online_cpus());
+ else {
+ synchronize_sched();
+ return;
+ }
+
+ /* Check to see if someone else did our work for us. */
+ s = atomic_read(&sync_sched_expedited_done);
+ if (UINT_CMP_GE((unsigned)s, (unsigned)firstsnap)) {
+ smp_mb(); /* ensure test happens before caller kfree */
+ return;
+ }
+
+ /*
+ * Refetching sync_sched_expedited_started allows later
+ * callers to piggyback on our grace period. We subtract
+ * 1 to get the same token that the last incrementer got.
+ * We retry after they started, so our grace period works
+ * for them, and they started after our first try, so their
+ * grace period works for us.
+ */
+ get_online_cpus();
+ snap = atomic_read(&sync_sched_expedited_started) - 1;
+ smp_mb(); /* ensure read is before try_stop_cpus(). */
+ }
+
+ /*
+ * Everyone up to our most recent fetch is covered by our grace
+ * period. Update the counter, but only if our work is still
+ * relevant -- which it won't be if someone who started later
+ * than we did beat us to the punch.
+ */
+ do {
+ s = atomic_read(&sync_sched_expedited_done);
+ if (UINT_CMP_GE((unsigned)s, (unsigned)snap)) {
+ smp_mb(); /* ensure test happens before caller kfree */
+ break;
+ }
+ } while (atomic_cmpxchg(&sync_sched_expedited_done, s, snap) != s);
+
+ put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#endif /* #else #ifndef CONFIG_SMP */
+
#if !defined(CONFIG_RCU_FAST_NO_HZ)
/*
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index d15430b9d122..c8e97853b970 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -166,13 +166,13 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
gpnum = rsp->gpnum;
seq_printf(m, "c=%lu g=%lu s=%d jfq=%ld j=%x "
- "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld\n",
+ "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n",
rsp->completed, gpnum, rsp->signaled,
(long)(rsp->jiffies_force_qs - jiffies),
(int)(jiffies & 0xffff),
rsp->n_force_qs, rsp->n_force_qs_ngp,
rsp->n_force_qs - rsp->n_force_qs_ngp,
- rsp->n_force_qs_lh, rsp->orphan_qlen);
+ rsp->n_force_qs_lh);
for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) {
if (rnp->level != level) {
seq_puts(m, "\n");
@@ -300,7 +300,7 @@ static const struct file_operations rcu_pending_fops = {
static struct dentry *rcudir;
-static int __init rcuclassic_trace_init(void)
+static int __init rcutree_trace_init(void)
{
struct dentry *retval;
@@ -337,14 +337,14 @@ free_out:
return 1;
}
-static void __exit rcuclassic_trace_cleanup(void)
+static void __exit rcutree_trace_cleanup(void)
{
debugfs_remove_recursive(rcudir);
}
-module_init(rcuclassic_trace_init);
-module_exit(rcuclassic_trace_cleanup);
+module_init(rcutree_trace_init);
+module_exit(rcutree_trace_cleanup);
MODULE_AUTHOR("Paul E. McKenney");
MODULE_DESCRIPTION("Read-Copy Update tracing for hierarchical implementation");
diff --git a/kernel/sched.c b/kernel/sched.c
index 114a0deb2b01..04949089e760 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -8067,8 +8067,6 @@ void __init sched_init(void)
zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
#endif /* SMP */
- perf_event_init();
-
scheduler_running = 1;
}
@@ -9241,72 +9239,3 @@ struct cgroup_subsys cpuacct_subsys = {
};
#endif /* CONFIG_CGROUP_CPUACCT */
-#ifndef CONFIG_SMP
-
-void synchronize_sched_expedited(void)
-{
- barrier();
-}
-EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
-
-#else /* #ifndef CONFIG_SMP */
-
-static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0);
-
-static int synchronize_sched_expedited_cpu_stop(void *data)
-{
- /*
- * There must be a full memory barrier on each affected CPU
- * between the time that try_stop_cpus() is called and the
- * time that it returns.
- *
- * In the current initial implementation of cpu_stop, the
- * above condition is already met when the control reaches
- * this point and the following smp_mb() is not strictly
- * necessary. Do smp_mb() anyway for documentation and
- * robustness against future implementation changes.
- */
- smp_mb(); /* See above comment block. */
- return 0;
-}
-
-/*
- * Wait for an rcu-sched grace period to elapse, but use "big hammer"
- * approach to force grace period to end quickly. This consumes
- * significant time on all CPUs, and is thus not recommended for
- * any sort of common-case code.
- *
- * Note that it is illegal to call this function while holding any
- * lock that is acquired by a CPU-hotplug notifier. Failing to
- * observe this restriction will result in deadlock.
- */
-void synchronize_sched_expedited(void)
-{
- int snap, trycount = 0;
-
- smp_mb(); /* ensure prior mod happens before capturing snap. */
- snap = atomic_read(&synchronize_sched_expedited_count) + 1;
- get_online_cpus();
- while (try_stop_cpus(cpu_online_mask,
- synchronize_sched_expedited_cpu_stop,
- NULL) == -EAGAIN) {
- put_online_cpus();
- if (trycount++ < 10)
- udelay(trycount * num_online_cpus());
- else {
- synchronize_sched();
- return;
- }
- if (atomic_read(&synchronize_sched_expedited_count) - snap > 0) {
- smp_mb(); /* ensure test happens before caller kfree */
- return;
- }
- get_online_cpus();
- }
- atomic_inc(&synchronize_sched_expedited_count);
- smp_mb__after_atomic_inc(); /* ensure post-GP actions seen after GP. */
- put_online_cpus();
-}
-EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
-
-#endif /* #else #ifndef CONFIG_SMP */
diff --git a/kernel/srcu.c b/kernel/srcu.c
index c71e07500536..98d8c1e80edb 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -31,6 +31,7 @@
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/smp.h>
+#include <linux/delay.h>
#include <linux/srcu.h>
static int init_srcu_struct_fields(struct srcu_struct *sp)
@@ -203,9 +204,14 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
* all srcu_read_lock() calls using the old counters have completed.
* Their corresponding critical sections might well be still
* executing, but the srcu_read_lock() primitives themselves
- * will have finished executing.
+ * will have finished executing. We initially give readers
+ * an arbitrarily chosen 10 microseconds to get out of their
+ * SRCU read-side critical sections, then loop waiting 1/HZ
+ * seconds per iteration.
*/
+ if (srcu_readers_active_idx(sp, idx))
+ udelay(CONFIG_SRCU_SYNCHRONIZE_DELAY);
while (srcu_readers_active_idx(sp, idx))
schedule_timeout_interruptible(1);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 121e4fff03d1..ae5cbb1e3ced 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -744,21 +744,21 @@ static struct ctl_table kern_table[] = {
.extra1 = &zero,
.extra2 = &one,
},
-#endif
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) && !defined(CONFIG_LOCKUP_DETECTOR)
{
- .procname = "unknown_nmi_panic",
- .data = &unknown_nmi_panic,
+ .procname = "nmi_watchdog",
+ .data = &watchdog_enabled,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dowatchdog_enabled,
},
+#endif
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
{
- .procname = "nmi_watchdog",
- .data = &nmi_watchdog_enabled,
+ .procname = "unknown_nmi_panic",
+ .data = &unknown_nmi_panic,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = proc_nmi_enabled,
+ .proc_handler = proc_dointvec,
},
#endif
#if defined(CONFIG_X86)
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 1357c5786064..4b2545a136ff 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -136,7 +136,6 @@ static const struct bin_table bin_kern_table[] = {
{ CTL_INT, KERN_IA64_UNALIGNED, "ignore-unaligned-usertrap" },
{ CTL_INT, KERN_COMPAT_LOG, "compat-log" },
{ CTL_INT, KERN_MAX_LOCK_DEPTH, "max_lock_depth" },
- { CTL_INT, KERN_NMI_WATCHDOG, "nmi_watchdog" },
{ CTL_INT, KERN_PANIC_ON_NMI, "panic_on_unrecovered_nmi" },
{}
};
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index ea37e2ff4164..14674dce77a6 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -69,6 +69,21 @@ config EVENT_TRACING
select CONTEXT_SWITCH_TRACER
bool
+config EVENT_POWER_TRACING_DEPRECATED
+ depends on EVENT_TRACING
+ bool "Deprecated power event trace API, to be removed"
+ default y
+ help
+ Provides old power event types:
+ C-state/idle accounting events:
+ power:power_start
+ power:power_end
+ and old cpufreq accounting event:
+ power:power_frequency
+ This is for userspace compatibility
+ and will vanish after 5 kernel iterations,
+ namely 2.6.41.
+
config CONTEXT_SWITCH_TRACER
bool
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
index a22582a06161..f55fcf61b223 100644
--- a/kernel/trace/power-traces.c
+++ b/kernel/trace/power-traces.c
@@ -13,5 +13,8 @@
#define CREATE_TRACE_POINTS
#include <trace/events/power.h>
-EXPORT_TRACEPOINT_SYMBOL_GPL(power_frequency);
+#ifdef EVENT_POWER_TRACING_DEPRECATED
+EXPORT_TRACEPOINT_SYMBOL_GPL(power_start);
+#endif
+EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 39c059ca670e..19a359d5e6d5 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -21,17 +21,46 @@ typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
/* Count the events in use (per event id, not per instance) */
static int total_ref_count;
+static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
+ struct perf_event *p_event)
+{
+ /* No tracing, just counting, so no obvious leak */
+ if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
+ return 0;
+
+ /* Some events are ok to be traced by non-root users... */
+ if (p_event->attach_state == PERF_ATTACH_TASK) {
+ if (tp_event->flags & TRACE_EVENT_FL_CAP_ANY)
+ return 0;
+ }
+
+ /*
+ * ...otherwise raw tracepoint data can be a severe data leak,
+ * only allow root to have these.
+ */
+ if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ return 0;
+}
+
static int perf_trace_event_init(struct ftrace_event_call *tp_event,
struct perf_event *p_event)
{
struct hlist_head __percpu *list;
- int ret = -ENOMEM;
+ int ret;
int cpu;
+ ret = perf_trace_event_perm(tp_event, p_event);
+ if (ret)
+ return ret;
+
p_event->tp_event = tp_event;
if (tp_event->perf_refcount++ > 0)
return 0;
+ ret = -ENOMEM;
+
list = alloc_percpu(struct hlist_head);
if (!list)
goto fail;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 0725eeab1937..35fde09b81de 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -27,6 +27,12 @@
DEFINE_MUTEX(event_mutex);
+DEFINE_MUTEX(event_storage_mutex);
+EXPORT_SYMBOL_GPL(event_storage_mutex);
+
+char event_storage[EVENT_STORAGE_SIZE];
+EXPORT_SYMBOL_GPL(event_storage);
+
LIST_HEAD(ftrace_events);
LIST_HEAD(ftrace_common_fields);
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 4ba44deaac25..4b74d71705c0 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -83,13 +83,19 @@ static void __always_unused ____ftrace_check_##name(void) \
#undef __array
#define __array(type, item, len) \
- BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
- ret = trace_define_field(event_call, #type "[" #len "]", #item, \
+ do { \
+ BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
+ mutex_lock(&event_storage_mutex); \
+ snprintf(event_storage, sizeof(event_storage), \
+ "%s[%d]", #type, len); \
+ ret = trace_define_field(event_call, event_storage, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
is_signed_type(type), FILTER_OTHER); \
- if (ret) \
- return ret;
+ mutex_unlock(&event_storage_mutex); \
+ if (ret) \
+ return ret; \
+ } while (0);
#undef __array_desc
#define __array_desc(type, container, item, len) \
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index c812c4927cab..6e7b575ac33c 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -57,6 +57,8 @@ static int __init hardlockup_panic_setup(char *str)
{
if (!strncmp(str, "panic", 5))
hardlockup_panic = 1;
+ else if (!strncmp(str, "0", 1))
+ no_watchdog = 1;
return 1;
}
__setup("nmi_watchdog=", hardlockup_panic_setup);
@@ -548,13 +550,13 @@ static struct notifier_block __cpuinitdata cpu_nfb = {
.notifier_call = cpu_callback
};
-static int __init spawn_watchdog_task(void)
+void __init lockup_detector_init(void)
{
void *cpu = (void *)(long)smp_processor_id();
int err;
if (no_watchdog)
- return 0;
+ return;
err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
WARN_ON(notifier_to_errno(err));
@@ -562,6 +564,5 @@ static int __init spawn_watchdog_task(void)
cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
register_cpu_notifier(&cpu_nfb);
- return 0;
+ return;
}
-early_initcall(spawn_watchdog_task);
generated by cgit v1.2.3 (git 2.0.4) at 2025-09-03 19:08:09 +0000