summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit_watch.c85
-rw-r--r--kernel/capability.c2
-rw-r--r--kernel/cgroup.c54
-rw-r--r--kernel/cpuset.c7
-rw-r--r--kernel/cred.c18
-rw-r--r--kernel/futex.c147
-rw-r--r--kernel/hrtimer.c6
-rw-r--r--kernel/irq/internals.h6
-rw-r--r--kernel/irq/irqdesc.c11
-rw-r--r--kernel/irq/manage.c13
-rw-r--r--kernel/irq/migration.c14
-rw-r--r--kernel/irq/pm.c3
-rw-r--r--kernel/irq/resend.c2
-rw-r--r--kernel/module.c16
-rw-r--r--kernel/perf_event.c1031
-rw-r--r--kernel/power/main.c2
-rw-r--r--kernel/power/process.c6
-rw-r--r--kernel/power/snapshot.c7
-rw-r--r--kernel/printk.c54
-rw-r--r--kernel/ptrace.c8
-rw-r--r--kernel/rtmutex-debug.c1
-rw-r--r--kernel/rtmutex-tester.c40
-rw-r--r--kernel/rtmutex.c318
-rw-r--r--kernel/rtmutex_common.h16
-rw-r--r--kernel/sched.c334
-rw-r--r--kernel/sched_autogroup.c15
-rw-r--r--kernel/sched_autogroup.h5
-rw-r--r--kernel/sched_debug.c2
-rw-r--r--kernel/sched_fair.c397
-rw-r--r--kernel/sched_idletask.c26
-rw-r--r--kernel/sched_rt.c35
-rw-r--r--kernel/sched_stoptask.c7
-rw-r--r--kernel/softirq.c3
-rw-r--r--kernel/sys_ni.c5
-rw-r--r--kernel/sysctl.c26
-rw-r--r--kernel/sysctl_binary.c19
-rw-r--r--kernel/time.c22
-rw-r--r--kernel/time/tick-broadcast.c10
-rw-r--r--kernel/time/tick-common.c6
-rw-r--r--kernel/time/tick-internal.h3
-rw-r--r--kernel/time/timer_list.c4
-rw-r--r--kernel/timer.c37
-rw-r--r--kernel/trace/blktrace.c23
-rw-r--r--kernel/trace/ftrace.c52
-rw-r--r--kernel/trace/ring_buffer.c24
-rw-r--r--kernel/trace/trace.c38
-rw-r--r--kernel/trace/trace.h41
-rw-r--r--kernel/trace/trace_entries.h6
-rw-r--r--kernel/trace/trace_events.c14
-rw-r--r--kernel/trace/trace_events_filter.c885
-rw-r--r--kernel/trace/trace_export.c6
-rw-r--r--kernel/trace/trace_kprobe.c111
-rw-r--r--kernel/trace/trace_output.c36
-rw-r--r--kernel/trace/trace_sched_switch.c48
-rw-r--r--kernel/trace/trace_syscalls.c59
-rw-r--r--kernel/tracepoint.c31
-rw-r--r--kernel/watchdog.c53
-rw-r--r--kernel/workqueue.c43
58 files changed, 2992 insertions, 1301 deletions
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index d2e3c7866460..e683869365d9 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -144,9 +144,9 @@ int audit_watch_compare(struct audit_watch *watch, unsigned long ino, dev_t dev)
}
/* Initialize a parent watch entry. */
-static struct audit_parent *audit_init_parent(struct nameidata *ndp)
+static struct audit_parent *audit_init_parent(struct path *path)
{
- struct inode *inode = ndp->path.dentry->d_inode;
+ struct inode *inode = path->dentry->d_inode;
struct audit_parent *parent;
int ret;
@@ -353,53 +353,40 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
}
/* Get path information necessary for adding watches. */
-static int audit_get_nd(char *path, struct nameidata **ndp, struct nameidata **ndw)
+static int audit_get_nd(struct audit_watch *watch, struct path *parent)
{
- struct nameidata *ndparent, *ndwatch;
+ struct nameidata nd;
+ struct dentry *d;
int err;
- ndparent = kmalloc(sizeof(*ndparent), GFP_KERNEL);
- if (unlikely(!ndparent))
- return -ENOMEM;
+ err = kern_path_parent(watch->path, &nd);
+ if (err)
+ return err;
- ndwatch = kmalloc(sizeof(*ndwatch), GFP_KERNEL);
- if (unlikely(!ndwatch)) {
- kfree(ndparent);
- return -ENOMEM;
+ if (nd.last_type != LAST_NORM) {
+ path_put(&nd.path);
+ return -EINVAL;
}
- err = path_lookup(path, LOOKUP_PARENT, ndparent);
- if (err) {
- kfree(ndparent);
- kfree(ndwatch);
- return err;
+ mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+ d = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
+ if (IS_ERR(d)) {
+ mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+ path_put(&nd.path);
+ return PTR_ERR(d);
}
-
- err = path_lookup(path, 0, ndwatch);
- if (err) {
- kfree(ndwatch);
- ndwatch = NULL;
+ if (d->d_inode) {
+ /* update watch filter fields */
+ watch->dev = d->d_inode->i_sb->s_dev;
+ watch->ino = d->d_inode->i_ino;
}
+ mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
- *ndp = ndparent;
- *ndw = ndwatch;
-
+ *parent = nd.path;
+ dput(d);
return 0;
}
-/* Release resources used for watch path information. */
-static void audit_put_nd(struct nameidata *ndp, struct nameidata *ndw)
-{
- if (ndp) {
- path_put(&ndp->path);
- kfree(ndp);
- }
- if (ndw) {
- path_put(&ndw->path);
- kfree(ndw);
- }
-}
-
/* Associate the given rule with an existing parent.
* Caller must hold audit_filter_mutex. */
static void audit_add_to_parent(struct audit_krule *krule,
@@ -440,31 +427,24 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
{
struct audit_watch *watch = krule->watch;
struct audit_parent *parent;
- struct nameidata *ndp = NULL, *ndw = NULL;
+ struct path parent_path;
int h, ret = 0;
mutex_unlock(&audit_filter_mutex);
/* Avoid calling path_lookup under audit_filter_mutex. */
- ret = audit_get_nd(watch->path, &ndp, &ndw);
- if (ret) {
- /* caller expects mutex locked */
- mutex_lock(&audit_filter_mutex);
- goto error;
- }
+ ret = audit_get_nd(watch, &parent_path);
+ /* caller expects mutex locked */
mutex_lock(&audit_filter_mutex);
- /* update watch filter fields */
- if (ndw) {
- watch->dev = ndw->path.dentry->d_inode->i_sb->s_dev;
- watch->ino = ndw->path.dentry->d_inode->i_ino;
- }
+ if (ret)
+ return ret;
/* either find an old parent or attach a new one */
- parent = audit_find_parent(ndp->path.dentry->d_inode);
+ parent = audit_find_parent(parent_path.dentry->d_inode);
if (!parent) {
- parent = audit_init_parent(ndp);
+ parent = audit_init_parent(&parent_path);
if (IS_ERR(parent)) {
ret = PTR_ERR(parent);
goto error;
@@ -479,9 +459,8 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
h = audit_hash_ino((u32)watch->ino);
*list = &audit_inode_hash[h];
error:
- audit_put_nd(ndp, ndw); /* NULL args OK */
+ path_put(&parent_path);
return ret;
-
}
void audit_remove_watch_rule(struct audit_krule *krule)
diff --git a/kernel/capability.c b/kernel/capability.c
index 2f05303715a5..9e9385f132c8 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -306,7 +306,7 @@ int capable(int cap)
BUG();
}
- if (security_capable(cap) == 0) {
+ if (security_capable(current_cred(), cap) == 0) {
current->flags |= PF_SUPERPRIV;
return 1;
}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b24d7027b83c..95362d15128c 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4230,20 +4230,8 @@ void cgroup_post_fork(struct task_struct *child)
*/
void cgroup_exit(struct task_struct *tsk, int run_callbacks)
{
- int i;
struct css_set *cg;
-
- if (run_callbacks && need_forkexit_callback) {
- /*
- * modular subsystems can't use callbacks, so no need to lock
- * the subsys array
- */
- for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
- struct cgroup_subsys *ss = subsys[i];
- if (ss->exit)
- ss->exit(ss, tsk);
- }
- }
+ int i;
/*
* Unlink from the css_set task list if necessary.
@@ -4261,7 +4249,24 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
task_lock(tsk);
cg = tsk->cgroups;
tsk->cgroups = &init_css_set;
+
+ if (run_callbacks && need_forkexit_callback) {
+ /*
+ * modular subsystems can't use callbacks, so no need to lock
+ * the subsys array
+ */
+ for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+ if (ss->exit) {
+ struct cgroup *old_cgrp =
+ rcu_dereference_raw(cg->subsys[i])->cgroup;
+ struct cgroup *cgrp = task_cgroup(tsk, i);
+ ss->exit(ss, cgrp, old_cgrp, tsk);
+ }
+ }
+ }
task_unlock(tsk);
+
if (cg)
put_css_set_taskexit(cg);
}
@@ -4813,6 +4818,29 @@ css_get_next(struct cgroup_subsys *ss, int id,
return ret;
}
+/*
+ * get corresponding css from file open on cgroupfs directory
+ */
+struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id)
+{
+ struct cgroup *cgrp;
+ struct inode *inode;
+ struct cgroup_subsys_state *css;
+
+ inode = f->f_dentry->d_inode;
+ /* check in cgroup filesystem dir */
+ if (inode->i_op != &cgroup_dir_inode_operations)
+ return ERR_PTR(-EBADF);
+
+ if (id < 0 || id >= CGROUP_SUBSYS_COUNT)
+ return ERR_PTR(-EINVAL);
+
+ /* get cgroup */
+ cgrp = __d_cgrp(f->f_dentry);
+ css = cgrp->subsys[id];
+ return css ? css : ERR_PTR(-ENOENT);
+}
+
#ifdef CONFIG_CGROUP_DEBUG
static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
struct cgroup *cont)
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4349935c2ad8..e92e98189032 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1575,8 +1575,10 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
return -ENODEV;
trialcs = alloc_trial_cpuset(cs);
- if (!trialcs)
- return -ENOMEM;
+ if (!trialcs) {
+ retval = -ENOMEM;
+ goto out;
+ }
switch (cft->private) {
case FILE_CPULIST:
@@ -1591,6 +1593,7 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
}
free_trial_cpuset(trialcs);
+out:
cgroup_unlock();
return retval;
}
diff --git a/kernel/cred.c b/kernel/cred.c
index 6a1aa004e376..2343c132c5a7 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -35,7 +35,7 @@ static struct kmem_cache *cred_jar;
static struct thread_group_cred init_tgcred = {
.usage = ATOMIC_INIT(2),
.tgid = 0,
- .lock = SPIN_LOCK_UNLOCKED,
+ .lock = __SPIN_LOCK_UNLOCKED(init_cred.tgcred.lock),
};
#endif
@@ -252,13 +252,13 @@ struct cred *cred_alloc_blank(void)
#endif
atomic_set(&new->usage, 1);
+#ifdef CONFIG_DEBUG_CREDENTIALS
+ new->magic = CRED_MAGIC;
+#endif
if (security_cred_alloc_blank(new, GFP_KERNEL) < 0)
goto error;
-#ifdef CONFIG_DEBUG_CREDENTIALS
- new->magic = CRED_MAGIC;
-#endif
return new;
error:
@@ -657,6 +657,8 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
validate_creds(old);
*new = *old;
+ atomic_set(&new->usage, 1);
+ set_cred_subscribers(new, 0);
get_uid(new->user);
get_group_info(new->group_info);
@@ -674,8 +676,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
goto error;
- atomic_set(&new->usage, 1);
- set_cred_subscribers(new, 0);
put_cred(old);
validate_creds(new);
return new;
@@ -748,7 +748,11 @@ bool creds_are_invalid(const struct cred *cred)
if (cred->magic != CRED_MAGIC)
return true;
#ifdef CONFIG_SECURITY_SELINUX
- if (selinux_is_enabled()) {
+ /*
+ * cred->security == NULL if security_cred_alloc_blank() or
+ * security_prepare_creds() returned an error.
+ */
+ if (selinux_is_enabled() && cred->security) {
if ((unsigned long) cred->security < PAGE_SIZE)
return true;
if ((*(u32 *)cred->security & 0xffffff00) ==
diff --git a/kernel/futex.c b/kernel/futex.c
index b766d28accd6..bda415715382 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -381,15 +381,16 @@ static struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb,
return NULL;
}
-static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
+static int cmpxchg_futex_value_locked(u32 *curval, u32 __user *uaddr,
+ u32 uval, u32 newval)
{
- u32 curval;
+ int ret;
pagefault_disable();
- curval = futex_atomic_cmpxchg_inatomic(uaddr, uval, newval);
+ ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval);
pagefault_enable();
- return curval;
+ return ret;
}
static int get_futex_value_locked(u32 *dest, u32 __user *from)
@@ -674,7 +675,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
struct task_struct *task, int set_waiters)
{
int lock_taken, ret, ownerdied = 0;
- u32 uval, newval, curval;
+ u32 uval, newval, curval, vpid = task_pid_vnr(task);
retry:
ret = lock_taken = 0;
@@ -684,19 +685,17 @@ retry:
* (by doing a 0 -> TID atomic cmpxchg), while holding all
* the locks. It will most likely not succeed.
*/
- newval = task_pid_vnr(task);
+ newval = vpid;
if (set_waiters)
newval |= FUTEX_WAITERS;
- curval = cmpxchg_futex_value_locked(uaddr, 0, newval);
-
- if (unlikely(curval == -EFAULT))
+ if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval)))
return -EFAULT;
/*
* Detect deadlocks.
*/
- if ((unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(task))))
+ if ((unlikely((curval & FUTEX_TID_MASK) == vpid)))
return -EDEADLK;
/*
@@ -723,14 +722,12 @@ retry:
*/
if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
/* Keep the OWNER_DIED bit */
- newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(task);
+ newval = (curval & ~FUTEX_TID_MASK) | vpid;
ownerdied = 0;
lock_taken = 1;
}
- curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
- if (unlikely(curval == -EFAULT))
+ if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
return -EFAULT;
if (unlikely(curval != uval))
goto retry;
@@ -775,6 +772,24 @@ retry:
return ret;
}
+/**
+ * __unqueue_futex() - Remove the futex_q from its futex_hash_bucket
+ * @q: The futex_q to unqueue
+ *
+ * The q->lock_ptr must not be NULL and must be held by the caller.
+ */
+static void __unqueue_futex(struct futex_q *q)
+{
+ struct futex_hash_bucket *hb;
+
+ if (WARN_ON(!q->lock_ptr || !spin_is_locked(q->lock_ptr)
+ || plist_node_empty(&q->list)))
+ return;
+
+ hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
+ plist_del(&q->list, &hb->chain);
+}
+
/*
* The hash bucket lock must be held when this is called.
* Afterwards, the futex_q must not be accessed.
@@ -792,7 +807,7 @@ static void wake_futex(struct futex_q *q)
*/
get_task_struct(p);
- plist_del(&q->list, &q->list.plist);
+ __unqueue_futex(q);
/*
* The waiting task can free the futex_q as soon as
* q->lock_ptr = NULL is written, without taking any locks. A
@@ -843,9 +858,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
- curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
- if (curval == -EFAULT)
+ if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
ret = -EFAULT;
else if (curval != uval)
ret = -EINVAL;
@@ -880,10 +893,8 @@ static int unlock_futex_pi(u32 __user *uaddr, u32 uval)
* There is no waiter, so we unlock the futex. The owner died
* bit has not to be preserved here. We are the owner:
*/
- oldval = cmpxchg_futex_value_locked(uaddr, uval, 0);
-
- if (oldval == -EFAULT)
- return oldval;
+ if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0))
+ return -EFAULT;
if (oldval != uval)
return -EAGAIN;
@@ -1071,9 +1082,6 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
plist_del(&q->list, &hb1->chain);
plist_add(&q->list, &hb2->chain);
q->lock_ptr = &hb2->lock;
-#ifdef CONFIG_DEBUG_PI_LIST
- q->list.plist.spinlock = &hb2->lock;
-#endif
}
get_futex_key_refs(key2);
q->key = *key2;
@@ -1100,16 +1108,12 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
get_futex_key_refs(key);
q->key = *key;
- WARN_ON(plist_node_empty(&q->list));
- plist_del(&q->list, &q->list.plist);
+ __unqueue_futex(q);
WARN_ON(!q->rt_waiter);
q->rt_waiter = NULL;
q->lock_ptr = &hb->lock;
-#ifdef CONFIG_DEBUG_PI_LIST
- q->list.plist.spinlock = &hb->lock;
-#endif
wake_up_state(q->task, TASK_NORMAL);
}
@@ -1457,9 +1461,6 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
prio = min(current->normal_prio, MAX_RT_PRIO);
plist_node_init(&q->list, prio);
-#ifdef CONFIG_DEBUG_PI_LIST
- q->list.plist.spinlock = &hb->lock;
-#endif
plist_add(&q->list, &hb->chain);
q->task = current;
spin_unlock(&hb->lock);
@@ -1504,8 +1505,7 @@ retry:
spin_unlock(lock_ptr);
goto retry;
}
- WARN_ON(plist_node_empty(&q->list));
- plist_del(&q->list, &q->list.plist);
+ __unqueue_futex(q);
BUG_ON(q->pi_state);
@@ -1525,8 +1525,7 @@ retry:
static void unqueue_me_pi(struct futex_q *q)
__releases(q->lock_ptr)
{
- WARN_ON(plist_node_empty(&q->list));
- plist_del(&q->list, &q->list.plist);
+ __unqueue_futex(q);
BUG_ON(!q->pi_state);
free_pi_state(q->pi_state);
@@ -1556,10 +1555,10 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
/*
* We are here either because we stole the rtmutex from the
- * pending owner or we are the pending owner which failed to
- * get the rtmutex. We have to replace the pending owner TID
- * in the user space variable. This must be atomic as we have
- * to preserve the owner died bit here.
+ * previous highest priority waiter or we are the highest priority
+ * waiter but failed to get the rtmutex the first time.
+ * We have to replace the newowner TID in the user space variable.
+ * This must be atomic as we have to preserve the owner died bit here.
*
* Note: We write the user space value _before_ changing the pi_state
* because we can fault here. Imagine swapped out pages or a fork
@@ -1578,9 +1577,7 @@ retry:
while (1) {
newval = (uval & FUTEX_OWNER_DIED) | newtid;
- curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
- if (curval == -EFAULT)
+ if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
goto handle_fault;
if (curval == uval)
break;
@@ -1608,8 +1605,8 @@ retry:
/*
* To handle the page fault we need to drop the hash bucket
- * lock here. That gives the other task (either the pending
- * owner itself or the task which stole the rtmutex) the
+ * lock here. That gives the other task (either the highest priority
+ * waiter itself or the task which stole the rtmutex) the
* chance to try the fixup of the pi_state. So once we are
* back from handling the fault we need to check the pi_state
* after reacquiring the hash bucket lock and before trying to
@@ -1685,18 +1682,20 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
/*
* pi_state is incorrect, some other task did a lock steal and
* we returned due to timeout or signal without taking the
- * rt_mutex. Too late. We can access the rt_mutex_owner without
- * locking, as the other task is now blocked on the hash bucket
- * lock. Fix the state up.
+ * rt_mutex. Too late.
*/
+ raw_spin_lock(&q->pi_state->pi_mutex.wait_lock);
owner = rt_mutex_owner(&q->pi_state->pi_mutex);
+ if (!owner)
+ owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
+ raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock);
ret = fixup_pi_state_owner(uaddr, q, owner);
goto out;
}
/*
* Paranoia check. If we did not take the lock, then we should not be
- * the owner, nor the pending owner, of the rt_mutex.
+ * the owner of the rt_mutex.
*/
if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
@@ -1781,13 +1780,14 @@ static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
*
* The basic logical guarantee of a futex is that it blocks ONLY
* if cond(var) is known to be true at the time of blocking, for
- * any cond. If we queued after testing *uaddr, that would open
- * a race condition where we could block indefinitely with
+ * any cond. If we locked the hash-bucket after testing *uaddr, that
+ * would open a race condition where we could block indefinitely with
* cond(var) false, which would violate the guarantee.
*
- * A consequence is that futex_wait() can return zero and absorb
- * a wakeup when *uaddr != val on entry to the syscall. This is
- * rare, but normal.
+ * On the other hand, we insert q and release the hash-bucket only
+ * after testing *uaddr. This guarantees that futex_wait() will NOT
+ * absorb a wakeup if *uaddr does not match the desired values
+ * while the syscall executes.
*/
retry:
ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key);
@@ -2046,9 +2046,9 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
- u32 uval;
struct plist_head *head;
union futex_key key = FUTEX_KEY_INIT;
+ u32 uval, vpid = task_pid_vnr(current);
int ret;
retry:
@@ -2057,7 +2057,7 @@ retry:
/*
* We release only a lock we actually own:
*/
- if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current))
+ if ((uval & FUTEX_TID_MASK) != vpid)
return -EPERM;
ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key);
@@ -2072,17 +2072,14 @@ retry:
* again. If it succeeds then we can return without waking
* anyone else up:
*/
- if (!(uval & FUTEX_OWNER_DIED))
- uval = cmpxchg_futex_value_locked(uaddr, task_pid_vnr(current), 0);
-
-
- if (unlikely(uval == -EFAULT))
+ if (!(uval & FUTEX_OWNER_DIED) &&
+ cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
goto pi_faulted;
/*
* Rare case: we managed to release the lock atomically,
* no need to wake anyone else up:
*/
- if (unlikely(uval == task_pid_vnr(current)))
+ if (unlikely(uval == vpid))
goto out_unlock;
/*
@@ -2167,7 +2164,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
* We were woken prior to requeue by a timeout or a signal.
* Unqueue the futex_q and determine which it was.
*/
- plist_del(&q->list, &q->list.plist);
+ plist_del(&q->list, &hb->chain);
/* Handle spurious wakeups gracefully */
ret = -EWOULDBLOCK;
@@ -2463,11 +2460,20 @@ retry:
* userspace.
*/
mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
- nval = futex_atomic_cmpxchg_inatomic(uaddr, uval, mval);
-
- if (nval == -EFAULT)
- return -1;
-
+ /*
+ * We are not holding a lock here, but we want to have
+ * the pagefault_disable/enable() protection because
+ * we want to handle the fault gracefully. If the
+ * access fails we try to fault in the futex with R/W
+ * verification via get_user_pages. get_user() above
+ * does not guarantee R/W access. If that fails we
+ * give up and leave the futex locked.
+ */
+ if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) {
+ if (fault_in_user_writeable(uaddr))
+ return -1;
+ goto retry;
+ }
if (nval != uval)
goto retry;
@@ -2678,8 +2684,7 @@ static int __init futex_init(void)
* implementation, the non-functional ones will return
* -ENOSYS.
*/
- curval = cmpxchg_futex_value_locked(NULL, 0, 0);
- if (curval == -EFAULT)
+ if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
futex_cmpxchg_enabled = 1;
for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 63fb74972b75..9017478c5d4c 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -343,6 +343,11 @@ EXPORT_SYMBOL_GPL(ktime_add_safe);
static struct debug_obj_descr hrtimer_debug_descr;
+static void *hrtimer_debug_hint(void *addr)
+{
+ return ((struct hrtimer *) addr)->function;
+}
+
/*
* fixup_init is called when:
* - an active object is initialized
@@ -402,6 +407,7 @@ static int hrtimer_fixup_free(void *addr, enum debug_obj_state state)
static struct debug_obj_descr hrtimer_debug_descr = {
.name = "hrtimer",
+ .debug_hint = hrtimer_debug_hint,
.fixup_init = hrtimer_fixup_init,
.fixup_activate = hrtimer_fixup_activate,
.fixup_free = hrtimer_fixup_free,
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 4571ae7e085a..99c3bc8a6fb4 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -3,6 +3,12 @@
*/
#include <linux/irqdesc.h>
+#ifdef CONFIG_SPARSE_IRQ
+# define IRQ_BITMAP_BITS (NR_IRQS + 8196)
+#else
+# define IRQ_BITMAP_BITS NR_IRQS
+#endif
+
extern int noirqdebug;
#define irq_data_to_desc(data) container_of(data, struct irq_desc, irq_data)
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 282f20230e67..2039bea31bdf 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -94,7 +94,7 @@ int nr_irqs = NR_IRQS;
EXPORT_SYMBOL_GPL(nr_irqs);
static DEFINE_MUTEX(sparse_irq_lock);
-static DECLARE_BITMAP(allocated_irqs, NR_IRQS);
+static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS);
#ifdef CONFIG_SPARSE_IRQ
@@ -217,6 +217,15 @@ int __init early_irq_init(void)
initcnt = arch_probe_nr_irqs();
printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt);
+ if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS))
+ nr_irqs = IRQ_BITMAP_BITS;
+
+ if (WARN_ON(initcnt > IRQ_BITMAP_BITS))
+ initcnt = IRQ_BITMAP_BITS;
+
+ if (initcnt > nr_irqs)
+ nr_irqs = initcnt;
+
for (i = 0; i < initcnt; i++) {
desc = alloc_desc(i, node);
set_bit(i, allocated_irqs);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 0caa59f747dd..2782bacdf494 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -282,8 +282,17 @@ EXPORT_SYMBOL(disable_irq);
void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
{
- if (resume)
+ if (resume) {
+ if (!(desc->status & IRQ_SUSPENDED)) {
+ if (!desc->action)
+ return;
+ if (!(desc->action->flags & IRQF_FORCE_RESUME))
+ return;
+ /* Pretend that it got disabled ! */
+ desc->depth++;
+ }
desc->status &= ~IRQ_SUSPENDED;
+ }
switch (desc->depth) {
case 0:
@@ -1100,7 +1109,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
if (retval)
kfree(action);
-#ifdef CONFIG_DEBUG_SHIRQ
+#ifdef CONFIG_DEBUG_SHIRQ_FIXME
if (!retval && (irqflags & IRQF_SHARED)) {
/*
* It's a shared IRQ -- the driver ought to be prepared for it
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 1d2541940480..441fd629ff04 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -56,6 +56,7 @@ void move_masked_irq(int irq)
void move_native_irq(int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
+ bool masked;
if (likely(!(desc->status & IRQ_MOVE_PENDING)))
return;
@@ -63,8 +64,15 @@ void move_native_irq(int irq)
if (unlikely(desc->status & IRQ_DISABLED))
return;
- desc->irq_data.chip->irq_mask(&desc->irq_data);
+ /*
+ * Be careful vs. already masked interrupts. If this is a
+ * threaded interrupt with ONESHOT set, we can end up with an
+ * interrupt storm.
+ */
+ masked = desc->status & IRQ_MASKED;
+ if (!masked)
+ desc->irq_data.chip->irq_mask(&desc->irq_data);
move_masked_irq(irq);
- desc->irq_data.chip->irq_unmask(&desc->irq_data);
+ if (!masked)
+ desc->irq_data.chip->irq_unmask(&desc->irq_data);
}
-
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 0d4005d85b03..d6bfb89cce91 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -53,9 +53,6 @@ void resume_device_irqs(void)
for_each_irq_desc(irq, desc) {
unsigned long flags;
- if (!(desc->status & IRQ_SUSPENDED))
- continue;
-
raw_spin_lock_irqsave(&desc->lock, flags);
__enable_irq(desc, irq, true);
raw_spin_unlock_irqrestore(&desc->lock, flags);
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 891115a929aa..dc49358b73fa 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -23,7 +23,7 @@
#ifdef CONFIG_HARDIRQS_SW_RESEND
/* Bitmap to handle software resend of interrupts: */
-static DECLARE_BITMAP(irqs_resend, NR_IRQS);
+static DECLARE_BITMAP(irqs_resend, IRQ_BITMAP_BITS);
/*
* Run software resends of IRQ's
diff --git a/kernel/module.c b/kernel/module.c
index 34e00b708fad..efa290ea94bf 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2460,9 +2460,9 @@ static void find_module_sections(struct module *mod, struct load_info *info)
#endif
#ifdef CONFIG_TRACEPOINTS
- mod->tracepoints = section_objs(info, "__tracepoints",
- sizeof(*mod->tracepoints),
- &mod->num_tracepoints);
+ mod->tracepoints_ptrs = section_objs(info, "__tracepoints_ptrs",
+ sizeof(*mod->tracepoints_ptrs),
+ &mod->num_tracepoints);
#endif
#ifdef HAVE_JUMP_LABEL
mod->jump_entries = section_objs(info, "__jump_table",
@@ -3393,7 +3393,7 @@ void module_layout(struct module *mod,
struct modversion_info *ver,
struct kernel_param *kp,
struct kernel_symbol *ks,
- struct tracepoint *tp)
+ struct tracepoint * const *tp)
{
}
EXPORT_SYMBOL(module_layout);
@@ -3407,8 +3407,8 @@ void module_update_tracepoints(void)
mutex_lock(&module_mutex);
list_for_each_entry(mod, &modules, list)
if (!mod->taints)
- tracepoint_update_probe_range(mod->tracepoints,
- mod->tracepoints + mod->num_tracepoints);
+ tracepoint_update_probe_range(mod->tracepoints_ptrs,
+ mod->tracepoints_ptrs + mod->num_tracepoints);
mutex_unlock(&module_mutex);
}
@@ -3432,8 +3432,8 @@ int module_get_iter_tracepoints(struct tracepoint_iter *iter)
else if (iter_mod > iter->module)
iter->tracepoint = NULL;
found = tracepoint_get_iter_range(&iter->tracepoint,
- iter_mod->tracepoints,
- iter_mod->tracepoints
+ iter_mod->tracepoints_ptrs,
+ iter_mod->tracepoints_ptrs
+ iter_mod->num_tracepoints);
if (found) {
iter->module = iter_mod;
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 126a302c481c..ed253aa24ba4 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -38,13 +38,96 @@
#include <asm/irq_regs.h>
+struct remote_function_call {
+ struct task_struct *p;
+ int (*func)(void *info);
+ void *info;
+ int ret;
+};
+
+static void remote_function(void *data)
+{
+ struct remote_function_call *tfc = data;
+ struct task_struct *p = tfc->p;
+
+ if (p) {
+ tfc->ret = -EAGAIN;
+ if (task_cpu(p) != smp_processor_id() || !task_curr(p))
+ return;
+ }
+
+ tfc->ret = tfc->func(tfc->info);
+}
+
+/**
+ * task_function_call - call a function on the cpu on which a task runs
+ * @p: the task to evaluate
+ * @func: the function to be called
+ * @info: the function call argument
+ *
+ * Calls the function @func when the task is currently running. This might
+ * be on the current CPU, which just calls the function directly
+ *
+ * returns: @func return value, or
+ * -ESRCH - when the process isn't running
+ * -EAGAIN - when the process moved away
+ */
+static int
+task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
+{
+ struct remote_function_call data = {
+ .p = p,
+ .func = func,
+ .info = info,
+ .ret = -ESRCH, /* No such (running) process */
+ };
+
+ if (task_curr(p))
+ smp_call_function_single(task_cpu(p), remote_function, &data, 1);
+
+ return data.ret;
+}
+
+/**
+ * cpu_function_call - call a function on the cpu
+ * @func: the function to be called
+ * @info: the function call argument
+ *
+ * Calls the function @func on the remote cpu.
+ *
+ * returns: @func return value or -ENXIO when the cpu is offline
+ */
+static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
+{
+ struct remote_function_call data = {
+ .p = NULL,
+ .func = func,
+ .info = info,
+ .ret = -ENXIO, /* No such CPU */
+ };
+
+ smp_call_function_single(cpu, remote_function, &data, 1);
+
+ return data.ret;
+}
+
+#define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
+ PERF_FLAG_FD_OUTPUT |\
+ PERF_FLAG_PID_CGROUP)
+
enum event_type_t {
EVENT_FLEXIBLE = 0x1,
EVENT_PINNED = 0x2,
EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
};
-atomic_t perf_task_events __read_mostly;
+/*
+ * perf_sched_events : >0 events exist
+ * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
+ */
+atomic_t perf_sched_events __read_mostly;
+static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
+
static atomic_t nr_mmap_events __read_mostly;
static atomic_t nr_comm_events __read_mostly;
static atomic_t nr_task_events __read_mostly;
@@ -67,7 +150,24 @@ int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */
/*
* max perf event sample rate
*/
-int sysctl_perf_event_sample_rate __read_mostly = 100000;
+#define DEFAULT_MAX_SAMPLE_RATE 100000
+int sysctl_perf_event_sample_rate __read_mostly = DEFAULT_MAX_SAMPLE_RATE;
+static int max_samples_per_tick __read_mostly =
+ DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ);
+
+int perf_proc_update_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+ if (ret || !write)
+ return ret;
+
+ max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ);
+
+ return 0;
+}
static atomic64_t perf_event_id;
@@ -75,7 +175,11 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
enum event_type_t event_type);
static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
- enum event_type_t event_type);
+ enum event_type_t event_type,
+ struct task_struct *task);
+
+static void update_context_time(struct perf_event_context *ctx);
+static u64 perf_event_time(struct perf_event *event);
void __weak perf_event_print_debug(void) { }
@@ -89,6 +193,360 @@ static inline u64 perf_clock(void)
return local_clock();
}
+static inline struct perf_cpu_context *
+__get_cpu_context(struct perf_event_context *ctx)
+{
+ return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
+}
+
+#ifdef CONFIG_CGROUP_PERF
+
+/*
+ * Must ensure cgroup is pinned (css_get) before calling
+ * this function. In other words, we cannot call this function
+ * if there is no cgroup event for the current CPU context.
+ */
+static inline struct perf_cgroup *
+perf_cgroup_from_task(struct task_struct *task)
+{
+ return container_of(task_subsys_state(task, perf_subsys_id),
+ struct perf_cgroup, css);
+}
+
+static inline bool
+perf_cgroup_match(struct perf_event *event)
+{
+ struct perf_event_context *ctx = event->ctx;
+ struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+
+ return !event->cgrp || event->cgrp == cpuctx->cgrp;
+}
+
+static inline void perf_get_cgroup(struct perf_event *event)
+{
+ css_get(&event->cgrp->css);
+}
+
+static inline void perf_put_cgroup(struct perf_event *event)
+{
+ css_put(&event->cgrp->css);
+}
+
+static inline void perf_detach_cgroup(struct perf_event *event)
+{
+ perf_put_cgroup(event);
+ event->cgrp = NULL;
+}
+
+static inline int is_cgroup_event(struct perf_event *event)
+{
+ return event->cgrp != NULL;
+}
+
+static inline u64 perf_cgroup_event_time(struct perf_event *event)
+{
+ struct perf_cgroup_info *t;
+
+ t = per_cpu_ptr(event->cgrp->info, event->cpu);
+ return t->time;
+}
+
+static inline void __update_cgrp_time(struct perf_cgroup *cgrp)
+{
+ struct perf_cgroup_info *info;
+ u64 now;
+
+ now = perf_clock();
+
+ info = this_cpu_ptr(cgrp->info);
+
+ info->time += now - info->timestamp;
+ info->timestamp = now;
+}
+
+static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
+{
+ struct perf_cgroup *cgrp_out = cpuctx->cgrp;
+ if (cgrp_out)
+ __update_cgrp_time(cgrp_out);
+}
+
+static inline void update_cgrp_time_from_event(struct perf_event *event)
+{
+ struct perf_cgroup *cgrp;
+
+ /*
+ * ensure we access cgroup data only when needed and
+ * when we know the cgroup is pinned (css_get)
+ */
+ if (!is_cgroup_event(event))
+ return;
+
+ cgrp = perf_cgroup_from_task(current);
+ /*
+ * Do not update time when cgroup is not active
+ */
+ if (cgrp == event->cgrp)
+ __update_cgrp_time(event->cgrp);
+}
+
+static inline void
+perf_cgroup_set_timestamp(struct task_struct *task,
+ struct perf_event_context *ctx)
+{
+ struct perf_cgroup *cgrp;
+ struct perf_cgroup_info *info;
+
+ /*
+ * ctx->lock held by caller
+ * ensure we do not access cgroup data
+ * unless we have the cgroup pinned (css_get)
+ */
+ if (!task || !ctx->nr_cgroups)
+ return;
+
+ cgrp = perf_cgroup_from_task(task);
+ info = this_cpu_ptr(cgrp->info);
+ info->timestamp = ctx->timestamp;
+}
+
+#define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */
+#define PERF_CGROUP_SWIN 0x2 /* cgroup switch in events based on task */
+
+/*
+ * reschedule events based on the cgroup constraint of task.
+ *
+ * mode SWOUT : schedule out everything
+ * mode SWIN : schedule in based on cgroup for next
+ */
+void perf_cgroup_switch(struct task_struct *task, int mode)
+{
+ struct perf_cpu_context *cpuctx;
+ struct pmu *pmu;
+ unsigned long flags;
+
+ /*
+ * disable interrupts to avoid geting nr_cgroup
+ * changes via __perf_event_disable(). Also
+ * avoids preemption.
+ */
+ local_irq_save(flags);
+
+ /*
+ * we reschedule only in the presence of cgroup
+ * constrained events.
+ */
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(pmu, &pmus, entry) {
+
+ cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+ perf_pmu_disable(cpuctx->ctx.pmu);
+
+ /*
+ * perf_cgroup_events says at least one
+ * context on this CPU has cgroup events.
+ *
+ * ctx->nr_cgroups reports the number of cgroup
+ * events for a context.
+ */
+ if (cpuctx->ctx.nr_cgroups > 0) {
+
+ if (mode & PERF_CGROUP_SWOUT) {
+ cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+ /*
+ * must not be done before ctxswout due
+ * to event_filter_match() in event_sched_out()
+ */
+ cpuctx->cgrp = NULL;
+ }
+
+ if (mode & PERF_CGROUP_SWIN) {
+ /* set cgrp before ctxsw in to
+ * allow event_filter_match() to not
+ * have to pass task around
+ */
+ cpuctx->cgrp = perf_cgroup_from_task(task);
+ cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
+ }
+ }
+
+ perf_pmu_enable(cpuctx->ctx.pmu);
+ }
+
+ rcu_read_unlock();
+
+ local_irq_restore(flags);
+}
+
+static inline void perf_cgroup_sched_out(struct task_struct *task)
+{
+ perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
+}
+
+static inline void perf_cgroup_sched_in(struct task_struct *task)
+{
+ perf_cgroup_switch(task, PERF_CGROUP_SWIN);
+}
+
+static inline int perf_cgroup_connect(int fd, struct perf_event *event,
+ struct perf_event_attr *attr,
+ struct perf_event *group_leader)
+{
+ struct perf_cgroup *cgrp;
+ struct cgroup_subsys_state *css;
+ struct file *file;
+ int ret = 0, fput_needed;
+
+ file = fget_light(fd, &fput_needed);
+ if (!file)
+ return -EBADF;
+
+ css = cgroup_css_from_dir(file, perf_subsys_id);
+ if (IS_ERR(css)) {
+ ret = PTR_ERR(css);
+ goto out;
+ }
+
+ cgrp = container_of(css, struct perf_cgroup, css);
+ event->cgrp = cgrp;
+
+ /* must be done before we fput() the file */
+ perf_get_cgroup(event);
+
+ /*
+ * all events in a group must monitor
+ * the same cgroup because a task belongs
+ * to only one perf cgroup at a time
+ */
+ if (group_leader && group_leader->cgrp != cgrp) {
+ perf_detach_cgroup(event);
+ ret = -EINVAL;
+ }
+out:
+ fput_light(file, fput_needed);
+ return ret;
+}
+
+static inline void
+perf_cgroup_set_shadow_time(struct perf_event *event, u64 now)
+{
+ struct perf_cgroup_info *t;
+ t = per_cpu_ptr(event->cgrp->info, event->cpu);
+ event->shadow_ctx_time = now - t->timestamp;
+}
+
+static inline void
+perf_cgroup_defer_enabled(struct perf_event *event)
+{
+ /*
+ * when the current task's perf cgroup does not match
+ * the event's, we need to remember to call the
+ * perf_mark_enable() function the first time a task with
+ * a matching perf cgroup is scheduled in.
+ */
+ if (is_cgroup_event(event) && !perf_cgroup_match(event))
+ event->cgrp_defer_enabled = 1;
+}
+
+static inline void
+perf_cgroup_mark_enabled(struct perf_event *event,
+ struct perf_event_context *ctx)
+{
+ struct perf_event *sub;
+ u64 tstamp = perf_event_time(event);
+
+ if (!event->cgrp_defer_enabled)
+ return;
+
+ event->cgrp_defer_enabled = 0;
+
+ event->tstamp_enabled = tstamp - event->total_time_enabled;
+ list_for_each_entry(sub, &event->sibling_list, group_entry) {
+ if (sub->state >= PERF_EVENT_STATE_INACTIVE) {
+ sub->tstamp_enabled = tstamp - sub->total_time_enabled;
+ sub->cgrp_defer_enabled = 0;
+ }
+ }
+}
+#else /* !CONFIG_CGROUP_PERF */
+
+static inline bool
+perf_cgroup_match(struct perf_event *event)
+{
+ return true;
+}
+
+static inline void perf_detach_cgroup(struct perf_event *event)
+{}
+
+static inline int is_cgroup_event(struct perf_event *event)
+{
+ return 0;
+}
+
+static inline u64 perf_cgroup_event_cgrp_time(struct perf_event *event)
+{
+ return 0;
+}
+
+static inline void update_cgrp_time_from_event(struct perf_event *event)
+{
+}
+
+static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
+{
+}
+
+static inline void perf_cgroup_sched_out(struct task_struct *task)
+{
+}
+
+static inline void perf_cgroup_sched_in(struct task_struct *task)
+{
+}
+
+static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event,
+ struct perf_event_attr *attr,
+ struct perf_event *group_leader)
+{
+ return -EINVAL;
+}
+
+static inline void
+perf_cgroup_set_timestamp(struct task_struct *task,
+ struct perf_event_context *ctx)
+{
+}
+
+void
+perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
+{
+}
+
+static inline void
+perf_cgroup_set_shadow_time(struct perf_event *event, u64 now)
+{
+}
+
+static inline u64 perf_cgroup_event_time(struct perf_event *event)
+{
+ return 0;
+}
+
+static inline void
+perf_cgroup_defer_enabled(struct perf_event *event)
+{
+}
+
+static inline void
+perf_cgroup_mark_enabled(struct perf_event *event,
+ struct perf_event_context *ctx)
+{
+}
+#endif
+
void perf_pmu_disable(struct pmu *pmu)
{
int *count = this_cpu_ptr(pmu->pmu_disable_count);
@@ -254,7 +712,6 @@ static void perf_unpin_context(struct perf_event_context *ctx)
raw_spin_lock_irqsave(&ctx->lock, flags);
--ctx->pin_count;
raw_spin_unlock_irqrestore(&ctx->lock, flags);
- put_ctx(ctx);
}
/*
@@ -271,6 +728,10 @@ static void update_context_time(struct perf_event_context *ctx)
static u64 perf_event_time(struct perf_event *event)
{
struct perf_event_context *ctx = event->ctx;
+
+ if (is_cgroup_event(event))
+ return perf_cgroup_event_time(event);
+
return ctx ? ctx->time : 0;
}
@@ -285,9 +746,20 @@ static void update_event_times(struct perf_event *event)
if (event->state < PERF_EVENT_STATE_INACTIVE ||
event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
return;
-
- if (ctx->is_active)
+ /*
+ * in cgroup mode, time_enabled represents
+ * the time the event was enabled AND active
+ * tasks were in the monitored cgroup. This is
+ * independent of the activity of the context as
+ * there may be a mix of cgroup and non-cgroup events.
+ *
+ * That is why we treat cgroup events differently
+ * here.
+ */
+ if (is_cgroup_event(event))
run_end = perf_event_time(event);
+ else if (ctx->is_active)
+ run_end = ctx->time;
else
run_end = event->tstamp_stopped;
@@ -299,6 +771,7 @@ static void update_event_times(struct perf_event *event)
run_end = perf_event_time(event);
event->total_time_running = run_end - event->tstamp_running;
+
}
/*
@@ -347,6 +820,9 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
list_add_tail(&event->group_entry, list);
}
+ if (is_cgroup_event(event))
+ ctx->nr_cgroups++;
+
list_add_rcu(&event->event_entry, &ctx->event_list);
if (!ctx->nr_events)
perf_pmu_rotate_start(ctx->pmu);
@@ -473,6 +949,9 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
event->attach_state &= ~PERF_ATTACH_CONTEXT;
+ if (is_cgroup_event(event))
+ ctx->nr_cgroups--;
+
ctx->nr_events--;
if (event->attr.inherit_stat)
ctx->nr_stat--;
@@ -544,7 +1023,8 @@ out:
static inline int
event_filter_match(struct perf_event *event)
{
- return event->cpu == -1 || event->cpu == smp_processor_id();
+ return (event->cpu == -1 || event->cpu == smp_processor_id())
+ && perf_cgroup_match(event);
}
static void
@@ -562,7 +1042,7 @@ event_sched_out(struct perf_event *event,
*/
if (event->state == PERF_EVENT_STATE_INACTIVE
&& !event_filter_match(event)) {
- delta = ctx->time - event->tstamp_stopped;
+ delta = tstamp - event->tstamp_stopped;
event->tstamp_running += delta;
event->tstamp_stopped = tstamp;
}
@@ -606,47 +1086,30 @@ group_sched_out(struct perf_event *group_event,
cpuctx->exclusive = 0;
}
-static inline struct perf_cpu_context *
-__get_cpu_context(struct perf_event_context *ctx)
-{
- return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
-}
-
/*
* Cross CPU call to remove a performance event
*
* We disable the event on the hardware level first. After that we
* remove it from the context list.
*/
-static void __perf_event_remove_from_context(void *info)
+static int __perf_remove_from_context(void *info)
{
struct perf_event *event = info;
struct perf_event_context *ctx = event->ctx;
struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
- /*
- * If this is a task context, we need to check whether it is
- * the current task context of this cpu. If not it has been
- * scheduled out before the smp call arrived.
- */
- if (ctx->task && cpuctx->task_ctx != ctx)
- return;
-
raw_spin_lock(&ctx->lock);
-
event_sched_out(event, cpuctx, ctx);
-
list_del_event(event, ctx);
-
raw_spin_unlock(&ctx->lock);
+
+ return 0;
}
/*
* Remove the event from a task's (or a CPU's) list of events.
*
- * Must be called with ctx->mutex held.
- *
* CPU events are removed with a smp call. For task events we only
* call when the task is on a CPU.
*
@@ -657,49 +1120,48 @@ static void __perf_event_remove_from_context(void *info)
* When called from perf_event_exit_task, it's OK because the
* context has been detached from its task.
*/
-static void perf_event_remove_from_context(struct perf_event *event)
+static void perf_remove_from_context(struct perf_event *event)
{
struct perf_event_context *ctx = event->ctx;
struct task_struct *task = ctx->task;
+ lockdep_assert_held(&ctx->mutex);
+
if (!task) {
/*
* Per cpu events are removed via an smp call and
* the removal is always successful.
*/
- smp_call_function_single(event->cpu,
- __perf_event_remove_from_context,
- event, 1);
+ cpu_function_call(event->cpu, __perf_remove_from_context, event);
return;
}
retry:
- task_oncpu_function_call(task, __perf_event_remove_from_context,
- event);
+ if (!task_function_call(task, __perf_remove_from_context, event))
+ return;
raw_spin_lock_irq(&ctx->lock);
/*
- * If the context is active we need to retry the smp call.
+ * If we failed to find a running task, but find the context active now
+ * that we've acquired the ctx->lock, retry.
*/
- if (ctx->nr_active && !list_empty(&event->group_entry)) {
+ if (ctx->is_active) {
raw_spin_unlock_irq(&ctx->lock);
goto retry;
}
/*
- * The lock prevents that this context is scheduled in so we
- * can remove the event safely, if the call above did not
- * succeed.
+ * Since the task isn't running, its safe to remove the event, us
+ * holding the ctx->lock ensures the task won't get scheduled in.
*/
- if (!list_empty(&event->group_entry))
- list_del_event(event, ctx);
+ list_del_event(event, ctx);
raw_spin_unlock_irq(&ctx->lock);
}
/*
* Cross CPU call to disable a performance event
*/
-static void __perf_event_disable(void *info)
+static int __perf_event_disable(void *info)
{
struct perf_event *event = info;
struct perf_event_context *ctx = event->ctx;
@@ -708,9 +1170,12 @@ static void __perf_event_disable(void *info)
/*
* If this is a per-task event, need to check whether this
* event's task is the current task on this cpu.
+ *
+ * Can trigger due to concurrent perf_event_context_sched_out()
+ * flipping contexts around.
*/
if (ctx->task && cpuctx->task_ctx != ctx)
- return;
+ return -EINVAL;
raw_spin_lock(&ctx->lock);
@@ -720,6 +1185,7 @@ static void __perf_event_disable(void *info)
*/
if (event->state >= PERF_EVENT_STATE_INACTIVE) {
update_context_time(ctx);
+ update_cgrp_time_from_event(event);
update_group_times(event);
if (event == event->group_leader)
group_sched_out(event, cpuctx, ctx);
@@ -729,6 +1195,8 @@ static void __perf_event_disable(void *info)
}
raw_spin_unlock(&ctx->lock);
+
+ return 0;
}
/*
@@ -753,13 +1221,13 @@ void perf_event_disable(struct perf_event *event)
/*
* Disable the event on the cpu that it's on
*/
- smp_call_function_single(event->cpu, __perf_event_disable,
- event, 1);
+ cpu_function_call(event->cpu, __perf_event_disable, event);
return;
}
retry:
- task_oncpu_function_call(task, __perf_event_disable, event);
+ if (!task_function_call(task, __perf_event_disable, event))
+ return;
raw_spin_lock_irq(&ctx->lock);
/*
@@ -767,6 +1235,11 @@ retry:
*/
if (event->state == PERF_EVENT_STATE_ACTIVE) {
raw_spin_unlock_irq(&ctx->lock);
+ /*
+ * Reload the task pointer, it might have been changed by
+ * a concurrent perf_event_context_sched_out().
+ */
+ task = ctx->task;
goto retry;
}
@@ -778,10 +1251,48 @@ retry:
update_group_times(event);
event->state = PERF_EVENT_STATE_OFF;
}
-
raw_spin_unlock_irq(&ctx->lock);
}
+static void perf_set_shadow_time(struct perf_event *event,
+ struct perf_event_context *ctx,
+ u64 tstamp)
+{
+ /*
+ * use the correct time source for the time snapshot
+ *
+ * We could get by without this by leveraging the
+ * fact that to get to this function, the caller
+ * has most likely already called update_context_time()
+ * and update_cgrp_time_xx() and thus both timestamp
+ * are identical (or very close). Given that tstamp is,
+ * already adjusted for cgroup, we could say that:
+ * tstamp - ctx->timestamp
+ * is equivalent to
+ * tstamp - cgrp->timestamp.
+ *
+ * Then, in perf_output_read(), the calculation would
+ * work with no changes because:
+ * - event is guaranteed scheduled in
+ * - no scheduled out in between
+ * - thus the timestamp would be the same
+ *
+ * But this is a bit hairy.
+ *
+ * So instead, we have an explicit cgroup call to remain
+ * within the time time source all along. We believe it
+ * is cleaner and simpler to understand.
+ */
+ if (is_cgroup_event(event))
+ perf_cgroup_set_shadow_time(event, tstamp);
+ else
+ event->shadow_ctx_time = tstamp - ctx->timestamp;
+}
+
+#define MAX_INTERRUPTS (~0ULL)
+
+static void perf_log_throttle(struct perf_event *event, int enable);
+
static int
event_sched_in(struct perf_event *event,
struct perf_cpu_context *cpuctx,
@@ -794,6 +1305,17 @@ event_sched_in(struct perf_event *event,
event->state = PERF_EVENT_STATE_ACTIVE;
event->oncpu = smp_processor_id();
+
+ /*
+ * Unthrottle events, since we scheduled we might have missed several
+ * ticks already, also for a heavily scheduling task there is little
+ * guarantee it'll get a tick in a timely manner.
+ */
+ if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) {
+ perf_log_throttle(event, 1);
+ event->hw.interrupts = 0;
+ }
+
/*
* The new state must be visible before we turn it on in the hardware:
*/
@@ -807,7 +1329,7 @@ event_sched_in(struct perf_event *event,
event->tstamp_running += tstamp - event->tstamp_stopped;
- event->shadow_ctx_time = tstamp - ctx->timestamp;
+ perf_set_shadow_time(event, ctx, tstamp);
if (!is_software_event(event))
cpuctx->active_oncpu++;
@@ -928,12 +1450,15 @@ static void add_event_to_ctx(struct perf_event *event,
event->tstamp_stopped = tstamp;
}
+static void perf_event_context_sched_in(struct perf_event_context *ctx,
+ struct task_struct *tsk);
+
/*
* Cross CPU call to install and enable a performance event
*
* Must be called with ctx->mutex held
*/
-static void __perf_install_in_context(void *info)
+static int __perf_install_in_context(void *info)
{
struct perf_event *event = info;
struct perf_event_context *ctx = event->ctx;
@@ -942,21 +1467,22 @@ static void __perf_install_in_context(void *info)
int err;
/*
- * If this is a task context, we need to check whether it is
- * the current task context of this cpu. If not it has been
- * scheduled out before the smp call arrived.
- * Or possibly this is the right context but it isn't
- * on this cpu because it had no events.
+ * In case we're installing a new context to an already running task,
+ * could also happen before perf_event_task_sched_in() on architectures
+ * which do context switches with IRQs enabled.
*/
- if (ctx->task && cpuctx->task_ctx != ctx) {
- if (cpuctx->task_ctx || ctx->task != current)
- return;
- cpuctx->task_ctx = ctx;
- }
+ if (ctx->task && !cpuctx->task_ctx)
+ perf_event_context_sched_in(ctx, ctx->task);
raw_spin_lock(&ctx->lock);
ctx->is_active = 1;
update_context_time(ctx);
+ /*
+ * update cgrp time only if current cgrp
+ * matches event->cgrp. Must be done before
+ * calling add_event_to_ctx()
+ */
+ update_cgrp_time_from_event(event);
add_event_to_ctx(event, ctx);
@@ -997,6 +1523,8 @@ static void __perf_install_in_context(void *info)
unlock:
raw_spin_unlock(&ctx->lock);
+
+ return 0;
}
/*
@@ -1008,8 +1536,6 @@ unlock:
* If the event is attached to a task which is on a CPU we use a smp
* call to enable it in the task context. The task might have been
* scheduled away, but we check this in the smp call again.
- *
- * Must be called with ctx->mutex held.
*/
static void
perf_install_in_context(struct perf_event_context *ctx,
@@ -1018,6 +1544,8 @@ perf_install_in_context(struct perf_event_context *ctx,
{
struct task_struct *task = ctx->task;
+ lockdep_assert_held(&ctx->mutex);
+
event->ctx = ctx;
if (!task) {
@@ -1025,31 +1553,29 @@ perf_install_in_context(struct perf_event_context *ctx,
* Per cpu events are installed via an smp call and
* the install is always successful.
*/
- smp_call_function_single(cpu, __perf_install_in_context,
- event, 1);
+ cpu_function_call(cpu, __perf_install_in_context, event);
return;
}
retry:
- task_oncpu_function_call(task, __perf_install_in_context,
- event);
+ if (!task_function_call(task, __perf_install_in_context, event))
+ return;
raw_spin_lock_irq(&ctx->lock);
/*
- * we need to retry the smp call.
+ * If we failed to find a running task, but find the context active now
+ * that we've acquired the ctx->lock, retry.
*/
- if (ctx->is_active && list_empty(&event->group_entry)) {
+ if (ctx->is_active) {
raw_spin_unlock_irq(&ctx->lock);
goto retry;
}
/*
- * The lock prevents that this context is scheduled in so we
- * can add the event safely, if it the call above did not
- * succeed.
+ * Since the task isn't running, its safe to add the event, us holding
+ * the ctx->lock ensures the task won't get scheduled in.
*/
- if (list_empty(&event->group_entry))
- add_event_to_ctx(event, ctx);
+ add_event_to_ctx(event, ctx);
raw_spin_unlock_irq(&ctx->lock);
}
@@ -1078,7 +1604,7 @@ static void __perf_event_mark_enabled(struct perf_event *event,
/*
* Cross CPU call to enable a performance event
*/
-static void __perf_event_enable(void *info)
+static int __perf_event_enable(void *info)
{
struct perf_event *event = info;
struct perf_event_context *ctx = event->ctx;
@@ -1086,26 +1612,27 @@ static void __perf_event_enable(void *info)
struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
int err;
- /*
- * If this is a per-task event, need to check whether this
- * event's task is the current task on this cpu.
- */
- if (ctx->task && cpuctx->task_ctx != ctx) {
- if (cpuctx->task_ctx || ctx->task != current)
- return;
- cpuctx->task_ctx = ctx;
- }
+ if (WARN_ON_ONCE(!ctx->is_active))
+ return -EINVAL;
raw_spin_lock(&ctx->lock);
- ctx->is_active = 1;
update_context_time(ctx);
if (event->state >= PERF_EVENT_STATE_INACTIVE)
goto unlock;
+
+ /*
+ * set current task's cgroup time reference point
+ */
+ perf_cgroup_set_timestamp(current, ctx);
+
__perf_event_mark_enabled(event, ctx);
- if (!event_filter_match(event))
+ if (!event_filter_match(event)) {
+ if (is_cgroup_event(event))
+ perf_cgroup_defer_enabled(event);
goto unlock;
+ }
/*
* If the event is in a group and isn't the group leader,
@@ -1138,6 +1665,8 @@ static void __perf_event_enable(void *info)
unlock:
raw_spin_unlock(&ctx->lock);
+
+ return 0;
}
/*
@@ -1158,8 +1687,7 @@ void perf_event_enable(struct perf_event *event)
/*
* Enable the event on the cpu that it's on
*/
- smp_call_function_single(event->cpu, __perf_event_enable,
- event, 1);
+ cpu_function_call(event->cpu, __perf_event_enable, event);
return;
}
@@ -1178,8 +1706,15 @@ void perf_event_enable(struct perf_event *event)
event->state = PERF_EVENT_STATE_OFF;
retry:
+ if (!ctx->is_active) {
+ __perf_event_mark_enabled(event, ctx);
+ goto out;
+ }
+
raw_spin_unlock_irq(&ctx->lock);
- task_oncpu_function_call(task, __perf_event_enable, event);
+
+ if (!task_function_call(task, __perf_event_enable, event))
+ return;
raw_spin_lock_irq(&ctx->lock);
@@ -1187,15 +1722,14 @@ retry:
* If the context is active and the event is still off,
* we need to retry the cross-call.
*/
- if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF)
+ if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF) {
+ /*
+ * task could have been flipped by a concurrent
+ * perf_event_context_sched_out()
+ */
+ task = ctx->task;
goto retry;
-
- /*
- * Since we have the lock this context can't be scheduled
- * in, so we can change the state safely.
- */
- if (event->state == PERF_EVENT_STATE_OFF)
- __perf_event_mark_enabled(event, ctx);
+ }
out:
raw_spin_unlock_irq(&ctx->lock);
@@ -1227,6 +1761,7 @@ static void ctx_sched_out(struct perf_event_context *ctx,
if (likely(!ctx->nr_events))
goto out;
update_context_time(ctx);
+ update_cgrp_time_from_cpuctx(cpuctx);
if (!ctx->nr_active)
goto out;
@@ -1339,8 +1874,8 @@ static void perf_event_sync_stat(struct perf_event_context *ctx,
}
}
-void perf_event_context_sched_out(struct task_struct *task, int ctxn,
- struct task_struct *next)
+static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
+ struct task_struct *next)
{
struct perf_event_context *ctx = task->perf_event_ctxp[ctxn];
struct perf_event_context *next_ctx;
@@ -1416,6 +1951,14 @@ void __perf_event_task_sched_out(struct task_struct *task,
for_each_task_context_nr(ctxn)
perf_event_context_sched_out(task, ctxn, next);
+
+ /*
+ * if cgroup events exist on this CPU, then we need
+ * to check if we have to switch out PMU state.
+ * cgroup event are system-wide mode only
+ */
+ if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+ perf_cgroup_sched_out(task);
}
static void task_ctx_sched_out(struct perf_event_context *ctx,
@@ -1454,6 +1997,10 @@ ctx_pinned_sched_in(struct perf_event_context *ctx,
if (!event_filter_match(event))
continue;
+ /* may need to reset tstamp_enabled */
+ if (is_cgroup_event(event))
+ perf_cgroup_mark_enabled(event, ctx);
+
if (group_can_go_on(event, cpuctx, 1))
group_sched_in(event, cpuctx, ctx);
@@ -1486,6 +2033,10 @@ ctx_flexible_sched_in(struct perf_event_context *ctx,
if (!event_filter_match(event))
continue;
+ /* may need to reset tstamp_enabled */
+ if (is_cgroup_event(event))
+ perf_cgroup_mark_enabled(event, ctx);
+
if (group_can_go_on(event, cpuctx, can_add_hw)) {
if (group_sched_in(event, cpuctx, ctx))
can_add_hw = 0;
@@ -1496,15 +2047,19 @@ ctx_flexible_sched_in(struct perf_event_context *ctx,
static void
ctx_sched_in(struct perf_event_context *ctx,
struct perf_cpu_context *cpuctx,
- enum event_type_t event_type)
+ enum event_type_t event_type,
+ struct task_struct *task)
{
+ u64 now;
+
raw_spin_lock(&ctx->lock);
ctx->is_active = 1;
if (likely(!ctx->nr_events))
goto out;
- ctx->timestamp = perf_clock();
-
+ now = perf_clock();
+ ctx->timestamp = now;
+ perf_cgroup_set_timestamp(task, ctx);
/*
* First go through the list and put on any pinned groups
* in order to give them the best chance of going on.
@@ -1521,11 +2076,12 @@ out:
}
static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
- enum event_type_t event_type)
+ enum event_type_t event_type,
+ struct task_struct *task)
{
struct perf_event_context *ctx = &cpuctx->ctx;
- ctx_sched_in(ctx, cpuctx, event_type);
+ ctx_sched_in(ctx, cpuctx, event_type, task);
}
static void task_ctx_sched_in(struct perf_event_context *ctx,
@@ -1533,15 +2089,16 @@ static void task_ctx_sched_in(struct perf_event_context *ctx,
{
struct perf_cpu_context *cpuctx;
- cpuctx = __get_cpu_context(ctx);
+ cpuctx = __get_cpu_context(ctx);
if (cpuctx->task_ctx == ctx)
return;
- ctx_sched_in(ctx, cpuctx, event_type);
+ ctx_sched_in(ctx, cpuctx, event_type, NULL);
cpuctx->task_ctx = ctx;
}
-void perf_event_context_sched_in(struct perf_event_context *ctx)
+static void perf_event_context_sched_in(struct perf_event_context *ctx,
+ struct task_struct *task)
{
struct perf_cpu_context *cpuctx;
@@ -1557,9 +2114,9 @@ void perf_event_context_sched_in(struct perf_event_context *ctx)
*/
cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
- ctx_sched_in(ctx, cpuctx, EVENT_PINNED);
- cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
- ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE);
+ ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task);
+ cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task);
+ ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
cpuctx->task_ctx = ctx;
@@ -1592,14 +2149,17 @@ void __perf_event_task_sched_in(struct task_struct *task)
if (likely(!ctx))
continue;
- perf_event_context_sched_in(ctx);
+ perf_event_context_sched_in(ctx, task);
}
+ /*
+ * if cgroup events exist on this CPU, then we need
+ * to check if we have to switch in PMU state.
+ * cgroup event are system-wide mode only
+ */
+ if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+ perf_cgroup_sched_in(task);
}
-#define MAX_INTERRUPTS (~0ULL)
-
-static void perf_log_throttle(struct perf_event *event, int enable);
-
static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
{
u64 frequency = event->attr.sample_freq;
@@ -1627,7 +2187,7 @@ static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
* Reduce accuracy by one bit such that @a and @b converge
* to a similar magnitude.
*/
-#define REDUCE_FLS(a, b) \
+#define REDUCE_FLS(a, b) \
do { \
if (a##_fls > b##_fls) { \
a >>= 1; \
@@ -1797,7 +2357,7 @@ static void perf_rotate_context(struct perf_cpu_context *cpuctx)
if (ctx)
rotate_ctx(ctx);
- cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
+ cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, current);
if (ctx)
task_ctx_sched_in(ctx, EVENT_FLEXIBLE);
@@ -1876,7 +2436,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
raw_spin_unlock(&ctx->lock);
- perf_event_context_sched_in(ctx);
+ perf_event_context_sched_in(ctx, ctx->task);
out:
local_irq_restore(flags);
}
@@ -1901,11 +2461,14 @@ static void __perf_event_read(void *info)
return;
raw_spin_lock(&ctx->lock);
- update_context_time(ctx);
+ if (ctx->is_active) {
+ update_context_time(ctx);
+ update_cgrp_time_from_event(event);
+ }
update_event_times(event);
+ if (event->state == PERF_EVENT_STATE_ACTIVE)
+ event->pmu->read(event);
raw_spin_unlock(&ctx->lock);
-
- event->pmu->read(event);
}
static inline u64 perf_event_count(struct perf_event *event)
@@ -1932,8 +2495,10 @@ static u64 perf_event_read(struct perf_event *event)
* (e.g., thread is blocked), in that case
* we cannot update context time
*/
- if (ctx->is_active)
+ if (ctx->is_active) {
update_context_time(ctx);
+ update_cgrp_time_from_event(event);
+ }
update_event_times(event);
raw_spin_unlock_irqrestore(&ctx->lock, flags);
}
@@ -1999,8 +2564,7 @@ static int alloc_callchain_buffers(void)
* accessed from NMI. Use a temporary manual per cpu allocation
* until that gets sorted out.
*/
- size = sizeof(*entries) + sizeof(struct perf_callchain_entry *) *
- num_possible_cpus();
+ size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]);
entries = kzalloc(size, GFP_KERNEL);
if (!entries)
@@ -2213,6 +2777,9 @@ errout:
}
+/*
+ * Returns a matching context with refcount and pincount.
+ */
static struct perf_event_context *
find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
{
@@ -2237,6 +2804,7 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
ctx = &cpuctx->ctx;
get_ctx(ctx);
+ ++ctx->pin_count;
return ctx;
}
@@ -2250,6 +2818,7 @@ retry:
ctx = perf_lock_task_context(task, ctxn, &flags);
if (ctx) {
unclone_ctx(ctx);
+ ++ctx->pin_count;
raw_spin_unlock_irqrestore(&ctx->lock, flags);
}
@@ -2271,8 +2840,10 @@ retry:
err = -ESRCH;
else if (task->perf_event_ctxp[ctxn])
err = -EAGAIN;
- else
+ else {
+ ++ctx->pin_count;
rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx);
+ }
mutex_unlock(&task->perf_event_mutex);
if (unlikely(err)) {
@@ -2312,7 +2883,7 @@ static void free_event(struct perf_event *event)
if (!event->parent) {
if (event->attach_state & PERF_ATTACH_TASK)
- jump_label_dec(&perf_task_events);
+ jump_label_dec(&perf_sched_events);
if (event->attr.mmap || event->attr.mmap_data)
atomic_dec(&nr_mmap_events);
if (event->attr.comm)
@@ -2321,6 +2892,10 @@ static void free_event(struct perf_event *event)
atomic_dec(&nr_task_events);
if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
put_callchain_buffers();
+ if (is_cgroup_event(event)) {
+ atomic_dec(&per_cpu(perf_cgroup_events, event->cpu));
+ jump_label_dec(&perf_sched_events);
+ }
}
if (event->buffer) {
@@ -2328,6 +2903,9 @@ static void free_event(struct perf_event *event)
event->buffer = NULL;
}
+ if (is_cgroup_event(event))
+ perf_detach_cgroup(event);
+
if (event->destroy)
event->destroy(event);
@@ -4395,26 +4973,14 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
if (unlikely(!is_sampling_event(event)))
return 0;
- if (!throttle) {
- hwc->interrupts++;
- } else {
- if (hwc->interrupts != MAX_INTERRUPTS) {
- hwc->interrupts++;
- if (HZ * hwc->interrupts >
- (u64)sysctl_perf_event_sample_rate) {
- hwc->interrupts = MAX_INTERRUPTS;
- perf_log_throttle(event, 0);
- ret = 1;
- }
- } else {
- /*
- * Keep re-disabling events even though on the previous
- * pass we disabled it - just in case we raced with a
- * sched-in and the event got enabled again:
- */
+ if (unlikely(hwc->interrupts >= max_samples_per_tick)) {
+ if (throttle) {
+ hwc->interrupts = MAX_INTERRUPTS;
+ perf_log_throttle(event, 0);
ret = 1;
}
- }
+ } else
+ hwc->interrupts++;
if (event->attr.freq) {
u64 now = perf_clock();
@@ -5051,6 +5617,10 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
u64 period;
event = container_of(hrtimer, struct perf_event, hw.hrtimer);
+
+ if (event->state != PERF_EVENT_STATE_ACTIVE)
+ return HRTIMER_NORESTART;
+
event->pmu->read(event);
perf_sample_data_init(&data, 0);
@@ -5077,9 +5647,6 @@ static void perf_swevent_start_hrtimer(struct perf_event *event)
if (!is_sampling_event(event))
return;
- hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- hwc->hrtimer.function = perf_swevent_hrtimer;
-
period = local64_read(&hwc->period_left);
if (period) {
if (period < 0)
@@ -5106,6 +5673,30 @@ static void perf_swevent_cancel_hrtimer(struct perf_event *event)
}
}
+static void perf_swevent_init_hrtimer(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!is_sampling_event(event))
+ return;
+
+ hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hwc->hrtimer.function = perf_swevent_hrtimer;
+
+ /*
+ * Since hrtimers have a fixed rate, we can do a static freq->period
+ * mapping and avoid the whole period adjust feedback stuff.
+ */
+ if (event->attr.freq) {
+ long freq = event->attr.sample_freq;
+
+ event->attr.sample_period = NSEC_PER_SEC / freq;
+ hwc->sample_period = event->attr.sample_period;
+ local64_set(&hwc->period_left, hwc->sample_period);
+ event->attr.freq = 0;
+ }
+}
+
/*
* Software event: cpu wall time clock
*/
@@ -5158,6 +5749,8 @@ static int cpu_clock_event_init(struct perf_event *event)
if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK)
return -ENOENT;
+ perf_swevent_init_hrtimer(event);
+
return 0;
}
@@ -5213,16 +5806,9 @@ static void task_clock_event_del(struct perf_event *event, int flags)
static void task_clock_event_read(struct perf_event *event)
{
- u64 time;
-
- if (!in_nmi()) {
- update_context_time(event->ctx);
- time = event->ctx->time;
- } else {
- u64 now = perf_clock();
- u64 delta = now - event->ctx->timestamp;
- time = event->ctx->time + delta;
- }
+ u64 now = perf_clock();
+ u64 delta = now - event->ctx->timestamp;
+ u64 time = event->ctx->time + delta;
task_clock_event_update(event, time);
}
@@ -5235,6 +5821,8 @@ static int task_clock_event_init(struct perf_event *event)
if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK)
return -ENOENT;
+ perf_swevent_init_hrtimer(event);
+
return 0;
}
@@ -5506,17 +6094,22 @@ struct pmu *perf_init_event(struct perf_event *event)
{
struct pmu *pmu = NULL;
int idx;
+ int ret;
idx = srcu_read_lock(&pmus_srcu);
rcu_read_lock();
pmu = idr_find(&pmu_idr, event->attr.type);
rcu_read_unlock();
- if (pmu)
+ if (pmu) {
+ ret = pmu->event_init(event);
+ if (ret)
+ pmu = ERR_PTR(ret);
goto unlock;
+ }
list_for_each_entry_rcu(pmu, &pmus, entry) {
- int ret = pmu->event_init(event);
+ ret = pmu->event_init(event);
if (!ret)
goto unlock;
@@ -5642,7 +6235,7 @@ done:
if (!event->parent) {
if (event->attach_state & PERF_ATTACH_TASK)
- jump_label_inc(&perf_task_events);
+ jump_label_inc(&perf_sched_events);
if (event->attr.mmap || event->attr.mmap_data)
atomic_inc(&nr_mmap_events);
if (event->attr.comm)
@@ -5817,7 +6410,7 @@ SYSCALL_DEFINE5(perf_event_open,
int err;
/* for future expandability... */
- if (flags & ~(PERF_FLAG_FD_NO_GROUP | PERF_FLAG_FD_OUTPUT))
+ if (flags & ~PERF_FLAG_ALL)
return -EINVAL;
err = perf_copy_attr(attr_uptr, &attr);
@@ -5834,6 +6427,15 @@ SYSCALL_DEFINE5(perf_event_open,
return -EINVAL;
}
+ /*
+ * In cgroup mode, the pid argument is used to pass the fd
+ * opened to the cgroup directory in cgroupfs. The cpu argument
+ * designates the cpu on which to monitor threads from that
+ * cgroup.
+ */
+ if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1))
+ return -EINVAL;
+
event_fd = get_unused_fd_flags(O_RDWR);
if (event_fd < 0)
return event_fd;
@@ -5851,7 +6453,7 @@ SYSCALL_DEFINE5(perf_event_open,
group_leader = NULL;
}
- if (pid != -1) {
+ if (pid != -1 && !(flags & PERF_FLAG_PID_CGROUP)) {
task = find_lively_task_by_vpid(pid);
if (IS_ERR(task)) {
err = PTR_ERR(task);
@@ -5865,6 +6467,19 @@ SYSCALL_DEFINE5(perf_event_open,
goto err_task;
}
+ if (flags & PERF_FLAG_PID_CGROUP) {
+ err = perf_cgroup_connect(pid, event, &attr, group_leader);
+ if (err)
+ goto err_alloc;
+ /*
+ * one more event:
+ * - that has cgroup constraint on event->cpu
+ * - that may need work on context switch
+ */
+ atomic_inc(&per_cpu(perf_cgroup_events, event->cpu));
+ jump_label_inc(&perf_sched_events);
+ }
+
/*
* Special case software events and allow them to be part of
* any hardware group.
@@ -5950,10 +6565,10 @@ SYSCALL_DEFINE5(perf_event_open,
struct perf_event_context *gctx = group_leader->ctx;
mutex_lock(&gctx->mutex);
- perf_event_remove_from_context(group_leader);
+ perf_remove_from_context(group_leader);
list_for_each_entry(sibling, &group_leader->sibling_list,
group_entry) {
- perf_event_remove_from_context(sibling);
+ perf_remove_from_context(sibling);
put_ctx(gctx);
}
mutex_unlock(&gctx->mutex);
@@ -5976,6 +6591,7 @@ SYSCALL_DEFINE5(perf_event_open,
perf_install_in_context(ctx, event, cpu);
++ctx->generation;
+ perf_unpin_context(ctx);
mutex_unlock(&ctx->mutex);
event->owner = current;
@@ -6001,6 +6617,7 @@ SYSCALL_DEFINE5(perf_event_open,
return event_fd;
err_context:
+ perf_unpin_context(ctx);
put_ctx(ctx);
err_alloc:
free_event(event);
@@ -6051,6 +6668,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
mutex_lock(&ctx->mutex);
perf_install_in_context(ctx, event, cpu);
++ctx->generation;
+ perf_unpin_context(ctx);
mutex_unlock(&ctx->mutex);
return event;
@@ -6104,7 +6722,7 @@ __perf_event_exit_task(struct perf_event *child_event,
{
struct perf_event *parent_event;
- perf_event_remove_from_context(child_event);
+ perf_remove_from_context(child_event);
parent_event = child_event->parent;
/*
@@ -6411,7 +7029,7 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent,
return 0;
}
- child_ctx = child->perf_event_ctxp[ctxn];
+ child_ctx = child->perf_event_ctxp[ctxn];
if (!child_ctx) {
/*
* This is executed from the parent task context, so
@@ -6526,6 +7144,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
mutex_unlock(&parent_ctx->mutex);
perf_unpin_context(parent_ctx);
+ put_ctx(parent_ctx);
return ret;
}
@@ -6595,9 +7214,9 @@ static void __perf_event_exit_context(void *__info)
perf_pmu_rotate_stop(ctx->pmu);
list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
- __perf_event_remove_from_context(event);
+ __perf_remove_from_context(event);
list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
- __perf_event_remove_from_context(event);
+ __perf_remove_from_context(event);
}
static void perf_event_exit_cpu_context(int cpu)
@@ -6721,3 +7340,83 @@ unlock:
return ret;
}
device_initcall(perf_event_sysfs_init);
+
+#ifdef CONFIG_CGROUP_PERF
+static struct cgroup_subsys_state *perf_cgroup_create(
+ struct cgroup_subsys *ss, struct cgroup *cont)
+{
+ struct perf_cgroup *jc;
+
+ jc = kzalloc(sizeof(*jc), GFP_KERNEL);
+ if (!jc)
+ return ERR_PTR(-ENOMEM);
+
+ jc->info = alloc_percpu(struct perf_cgroup_info);
+ if (!jc->info) {
+ kfree(jc);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ return &jc->css;
+}
+
+static void perf_cgroup_destroy(struct cgroup_subsys *ss,
+ struct cgroup *cont)
+{
+ struct perf_cgroup *jc;
+ jc = container_of(cgroup_subsys_state(cont, perf_subsys_id),
+ struct perf_cgroup, css);
+ free_percpu(jc->info);
+ kfree(jc);
+}
+
+static int __perf_cgroup_move(void *info)
+{
+ struct task_struct *task = info;
+ perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN);
+ return 0;
+}
+
+static void perf_cgroup_move(struct task_struct *task)
+{
+ task_function_call(task, __perf_cgroup_move, task);
+}
+
+static void perf_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct cgroup *old_cgrp, struct task_struct *task,
+ bool threadgroup)
+{
+ perf_cgroup_move(task);
+ if (threadgroup) {
+ struct task_struct *c;
+ rcu_read_lock();
+ list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
+ perf_cgroup_move(c);
+ }
+ rcu_read_unlock();
+ }
+}
+
+static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct cgroup *old_cgrp, struct task_struct *task)
+{
+ /*
+ * cgroup_exit() is called in the copy_process() failure path.
+ * Ignore this case since the task hasn't ran yet, this avoids
+ * trying to poke a half freed task state from generic code.
+ */
+ if (!(task->flags & PF_EXITING))
+ return;
+
+ perf_cgroup_move(task);
+}
+
+struct cgroup_subsys perf_subsys = {
+ .name = "perf_event",
+ .subsys_id = perf_subsys_id,
+ .create = perf_cgroup_create,
+ .destroy = perf_cgroup_destroy,
+ .exit = perf_cgroup_exit,
+ .attach = perf_cgroup_attach,
+};
+#endif /* CONFIG_CGROUP_PERF */
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 7b5db6a8561e..701853042c28 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -326,7 +326,7 @@ EXPORT_SYMBOL_GPL(pm_wq);
static int __init pm_start_workqueue(void)
{
- pm_wq = alloc_workqueue("pm", WQ_FREEZEABLE, 0);
+ pm_wq = alloc_workqueue("pm", WQ_FREEZABLE, 0);
return pm_wq ? 0 : -ENOMEM;
}
diff --git a/kernel/power/process.c b/kernel/power/process.c
index d6d2a10320e0..0cf3a27a6c9d 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -22,7 +22,7 @@
*/
#define TIMEOUT (20 * HZ)
-static inline int freezeable(struct task_struct * p)
+static inline int freezable(struct task_struct * p)
{
if ((p == current) ||
(p->flags & PF_NOFREEZE) ||
@@ -53,7 +53,7 @@ static int try_to_freeze_tasks(bool sig_only)
todo = 0;
read_lock(&tasklist_lock);
do_each_thread(g, p) {
- if (frozen(p) || !freezeable(p))
+ if (frozen(p) || !freezable(p))
continue;
if (!freeze_task(p, sig_only))
@@ -167,7 +167,7 @@ static void thaw_tasks(bool nosig_only)
read_lock(&tasklist_lock);
do_each_thread(g, p) {
- if (!freezeable(p))
+ if (!freezable(p))
continue;
if (nosig_only && should_send_signal(p))
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 0dac75ea4456..64db648ff911 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1519,11 +1519,8 @@ static int
swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
unsigned int nr_pages, unsigned int nr_highmem)
{
- int error = 0;
-
if (nr_highmem > 0) {
- error = get_highmem_buffer(PG_ANY);
- if (error)
+ if (get_highmem_buffer(PG_ANY))
goto err_out;
if (nr_highmem > alloc_highmem) {
nr_highmem -= alloc_highmem;
@@ -1546,7 +1543,7 @@ swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
err_out:
swsusp_free();
- return error;
+ return -ENOMEM;
}
asmlinkage int swsusp_save(void)
diff --git a/kernel/printk.c b/kernel/printk.c
index 2ddbdc73aade..36231525e22f 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -262,25 +262,47 @@ int dmesg_restrict = 1;
int dmesg_restrict;
#endif
+static int syslog_action_restricted(int type)
+{
+ if (dmesg_restrict)
+ return 1;
+ /* Unless restricted, we allow "read all" and "get buffer size" for everybody */
+ return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER;
+}
+
+static int check_syslog_permissions(int type, bool from_file)
+{
+ /*
+ * If this is from /proc/kmsg and we've already opened it, then we've
+ * already done the capabilities checks at open time.
+ */
+ if (from_file && type != SYSLOG_ACTION_OPEN)
+ return 0;
+
+ if (syslog_action_restricted(type)) {
+ if (capable(CAP_SYSLOG))
+ return 0;
+ /* For historical reasons, accept CAP_SYS_ADMIN too, with a warning */
+ if (capable(CAP_SYS_ADMIN)) {
+ WARN_ONCE(1, "Attempt to access syslog with CAP_SYS_ADMIN "
+ "but no CAP_SYSLOG (deprecated).\n");
+ return 0;
+ }
+ return -EPERM;
+ }
+ return 0;
+}
+
int do_syslog(int type, char __user *buf, int len, bool from_file)
{
unsigned i, j, limit, count;
int do_clear = 0;
char c;
- int error = 0;
+ int error;
- /*
- * If this is from /proc/kmsg we only do the capabilities checks
- * at open time.
- */
- if (type == SYSLOG_ACTION_OPEN || !from_file) {
- if (dmesg_restrict && !capable(CAP_SYSLOG))
- goto warn; /* switch to return -EPERM after 2.6.39 */
- if ((type != SYSLOG_ACTION_READ_ALL &&
- type != SYSLOG_ACTION_SIZE_BUFFER) &&
- !capable(CAP_SYSLOG))
- goto warn; /* switch to return -EPERM after 2.6.39 */
- }
+ error = check_syslog_permissions(type, from_file);
+ if (error)
+ goto out;
error = security_syslog(type);
if (error)
@@ -423,12 +445,6 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
}
out:
return error;
-warn:
- /* remove after 2.6.39 */
- if (capable(CAP_SYS_ADMIN))
- WARN_ONCE(1, "Attempt to access syslog with CAP_SYS_ADMIN "
- "but no CAP_SYSLOG (deprecated and denied).\n");
- return -EPERM;
}
SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len)
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 99bbaa3e5b0d..e2302e40b360 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -163,7 +163,7 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode)
return !err;
}
-int ptrace_attach(struct task_struct *task)
+static int ptrace_attach(struct task_struct *task)
{
int retval;
@@ -219,7 +219,7 @@ out:
* Performs checks and sets PT_PTRACED.
* Should be used by all ptrace implementations for PTRACE_TRACEME.
*/
-int ptrace_traceme(void)
+static int ptrace_traceme(void)
{
int ret = -EPERM;
@@ -293,7 +293,7 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
return false;
}
-int ptrace_detach(struct task_struct *child, unsigned int data)
+static int ptrace_detach(struct task_struct *child, unsigned int data)
{
bool dead = false;
@@ -313,7 +313,7 @@ int ptrace_detach(struct task_struct *child, unsigned int data)
child->exit_code = data;
dead = __ptrace_detach(current, child);
if (!child->exit_state)
- wake_up_process(child);
+ wake_up_state(child, TASK_TRACED | TASK_STOPPED);
}
write_unlock_irq(&tasklist_lock);
diff --git a/kernel/rtmutex-debug.c b/kernel/rtmutex-debug.c
index ddabb54bb5c8..3c7cbc2c33be 100644
--- a/kernel/rtmutex-debug.c
+++ b/kernel/rtmutex-debug.c
@@ -215,7 +215,6 @@ void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
put_pid(waiter->deadlock_task_pid);
TRACE_WARN_ON(!plist_node_empty(&waiter->list_entry));
TRACE_WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
- TRACE_WARN_ON(waiter->task);
memset(waiter, 0x22, sizeof(*waiter));
}
diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c
index 66cb89bc5ef1..5c9ccd380966 100644
--- a/kernel/rtmutex-tester.c
+++ b/kernel/rtmutex-tester.c
@@ -9,7 +9,6 @@
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/sched.h>
-#include <linux/smp_lock.h>
#include <linux/spinlock.h>
#include <linux/sysdev.h>
#include <linux/timer.h>
@@ -27,7 +26,6 @@ struct test_thread_data {
int opcode;
int opdata;
int mutexes[MAX_RT_TEST_MUTEXES];
- int bkl;
int event;
struct sys_device sysdev;
};
@@ -46,9 +44,8 @@ enum test_opcodes {
RTTEST_LOCKINTNOWAIT, /* 6 Lock interruptible no wait in wakeup, data = lockindex */
RTTEST_LOCKCONT, /* 7 Continue locking after the wakeup delay */
RTTEST_UNLOCK, /* 8 Unlock, data = lockindex */
- RTTEST_LOCKBKL, /* 9 Lock BKL */
- RTTEST_UNLOCKBKL, /* 10 Unlock BKL */
- RTTEST_SIGNAL, /* 11 Signal other test thread, data = thread id */
+ /* 9, 10 - reserved for BKL commemoration */
+ RTTEST_SIGNAL = 11, /* 11 Signal other test thread, data = thread id */
RTTEST_RESETEVENT = 98, /* 98 Reset event counter */
RTTEST_RESET = 99, /* 99 Reset all pending operations */
};
@@ -74,13 +71,6 @@ static int handle_op(struct test_thread_data *td, int lockwakeup)
td->mutexes[i] = 0;
}
}
-
- if (!lockwakeup && td->bkl == 4) {
-#ifdef CONFIG_LOCK_KERNEL
- unlock_kernel();
-#endif
- td->bkl = 0;
- }
return 0;
case RTTEST_RESETEVENT:
@@ -131,25 +121,6 @@ static int handle_op(struct test_thread_data *td, int lockwakeup)
td->mutexes[id] = 0;
return 0;
- case RTTEST_LOCKBKL:
- if (td->bkl)
- return 0;
- td->bkl = 1;
-#ifdef CONFIG_LOCK_KERNEL
- lock_kernel();
-#endif
- td->bkl = 4;
- return 0;
-
- case RTTEST_UNLOCKBKL:
- if (td->bkl != 4)
- break;
-#ifdef CONFIG_LOCK_KERNEL
- unlock_kernel();
-#endif
- td->bkl = 0;
- return 0;
-
default:
break;
}
@@ -196,7 +167,6 @@ void schedule_rt_mutex_test(struct rt_mutex *mutex)
td->event = atomic_add_return(1, &rttest_event);
break;
- case RTTEST_LOCKBKL:
default:
break;
}
@@ -229,8 +199,6 @@ void schedule_rt_mutex_test(struct rt_mutex *mutex)
td->event = atomic_add_return(1, &rttest_event);
return;
- case RTTEST_LOCKBKL:
- return;
default:
return;
}
@@ -380,11 +348,11 @@ static ssize_t sysfs_test_status(struct sys_device *dev, struct sysdev_attribute
spin_lock(&rttest_lock);
curr += sprintf(curr,
- "O: %4d, E:%8d, S: 0x%08lx, P: %4d, N: %4d, B: %p, K: %d, M:",
+ "O: %4d, E:%8d, S: 0x%08lx, P: %4d, N: %4d, B: %p, M:",
td->opcode, td->event, tsk->state,
(MAX_RT_PRIO - 1) - tsk->prio,
(MAX_RT_PRIO - 1) - tsk->normal_prio,
- tsk->pi_blocked_on, td->bkl);
+ tsk->pi_blocked_on);
for (i = MAX_RT_TEST_MUTEXES - 1; i >=0 ; i--)
curr += sprintf(curr, "%d", td->mutexes[i]);
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index a9604815786a..ab449117aaf2 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -20,41 +20,34 @@
/*
* lock->owner state tracking:
*
- * lock->owner holds the task_struct pointer of the owner. Bit 0 and 1
- * are used to keep track of the "owner is pending" and "lock has
- * waiters" state.
+ * lock->owner holds the task_struct pointer of the owner. Bit 0
+ * is used to keep track of the "lock has waiters" state.
*
- * owner bit1 bit0
- * NULL 0 0 lock is free (fast acquire possible)
- * NULL 0 1 invalid state
- * NULL 1 0 Transitional State*
- * NULL 1 1 invalid state
- * taskpointer 0 0 lock is held (fast release possible)
- * taskpointer 0 1 task is pending owner
- * taskpointer 1 0 lock is held and has waiters
- * taskpointer 1 1 task is pending owner and lock has more waiters
- *
- * Pending ownership is assigned to the top (highest priority)
- * waiter of the lock, when the lock is released. The thread is woken
- * up and can now take the lock. Until the lock is taken (bit 0
- * cleared) a competing higher priority thread can steal the lock
- * which puts the woken up thread back on the waiters list.
+ * owner bit0
+ * NULL 0 lock is free (fast acquire possible)
+ * NULL 1 lock is free and has waiters and the top waiter
+ * is going to take the lock*
+ * taskpointer 0 lock is held (fast release possible)
+ * taskpointer 1 lock is held and has waiters**
*
* The fast atomic compare exchange based acquire and release is only
- * possible when bit 0 and 1 of lock->owner are 0.
+ * possible when bit 0 of lock->owner is 0.
+ *
+ * (*) It also can be a transitional state when grabbing the lock
+ * with ->wait_lock is held. To prevent any fast path cmpxchg to the lock,
+ * we need to set the bit0 before looking at the lock, and the owner may be
+ * NULL in this small time, hence this can be a transitional state.
*
- * (*) There's a small time where the owner can be NULL and the
- * "lock has waiters" bit is set. This can happen when grabbing the lock.
- * To prevent a cmpxchg of the owner releasing the lock, we need to set this
- * bit before looking at the lock, hence the reason this is a transitional
- * state.
+ * (**) There is a small time when bit 0 is set but there are no
+ * waiters. This can happen when grabbing the lock in the slow path.
+ * To prevent a cmpxchg of the owner releasing the lock, we need to
+ * set this bit before looking at the lock.
*/
static void
-rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner,
- unsigned long mask)
+rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner)
{
- unsigned long val = (unsigned long)owner | mask;
+ unsigned long val = (unsigned long)owner;
if (rt_mutex_has_waiters(lock))
val |= RT_MUTEX_HAS_WAITERS;
@@ -203,15 +196,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
* reached or the state of the chain has changed while we
* dropped the locks.
*/
- if (!waiter || !waiter->task)
+ if (!waiter)
goto out_unlock_pi;
/*
* Check the orig_waiter state. After we dropped the locks,
- * the previous owner of the lock might have released the lock
- * and made us the pending owner:
+ * the previous owner of the lock might have released the lock.
*/
- if (orig_waiter && !orig_waiter->task)
+ if (orig_waiter && !rt_mutex_owner(orig_lock))
goto out_unlock_pi;
/*
@@ -254,6 +246,17 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
/* Release the task */
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ if (!rt_mutex_owner(lock)) {
+ /*
+ * If the requeue above changed the top waiter, then we need
+ * to wake the new top waiter up to try to get the lock.
+ */
+
+ if (top_waiter != rt_mutex_top_waiter(lock))
+ wake_up_process(rt_mutex_top_waiter(lock)->task);
+ raw_spin_unlock(&lock->wait_lock);
+ goto out_put_task;
+ }
put_task_struct(task);
/* Grab the next task */
@@ -296,78 +299,16 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
}
/*
- * Optimization: check if we can steal the lock from the
- * assigned pending owner [which might not have taken the
- * lock yet]:
- */
-static inline int try_to_steal_lock(struct rt_mutex *lock,
- struct task_struct *task)
-{
- struct task_struct *pendowner = rt_mutex_owner(lock);
- struct rt_mutex_waiter *next;
- unsigned long flags;
-
- if (!rt_mutex_owner_pending(lock))
- return 0;
-
- if (pendowner == task)
- return 1;
-
- raw_spin_lock_irqsave(&pendowner->pi_lock, flags);
- if (task->prio >= pendowner->prio) {
- raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
- return 0;
- }
-
- /*
- * Check if a waiter is enqueued on the pending owners
- * pi_waiters list. Remove it and readjust pending owners
- * priority.
- */
- if (likely(!rt_mutex_has_waiters(lock))) {
- raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
- return 1;
- }
-
- /* No chain handling, pending owner is not blocked on anything: */
- next = rt_mutex_top_waiter(lock);
- plist_del(&next->pi_list_entry, &pendowner->pi_waiters);
- __rt_mutex_adjust_prio(pendowner);
- raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-
- /*
- * We are going to steal the lock and a waiter was
- * enqueued on the pending owners pi_waiters queue. So
- * we have to enqueue this waiter into
- * task->pi_waiters list. This covers the case,
- * where task is boosted because it holds another
- * lock and gets unboosted because the booster is
- * interrupted, so we would delay a waiter with higher
- * priority as task->normal_prio.
- *
- * Note: in the rare case of a SCHED_OTHER task changing
- * its priority and thus stealing the lock, next->task
- * might be task:
- */
- if (likely(next->task != task)) {
- raw_spin_lock_irqsave(&task->pi_lock, flags);
- plist_add(&next->pi_list_entry, &task->pi_waiters);
- __rt_mutex_adjust_prio(task);
- raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- }
- return 1;
-}
-
-/*
* Try to take an rt-mutex
*
- * This fails
- * - when the lock has a real owner
- * - when a different pending owner exists and has higher priority than current
- *
* Must be called with lock->wait_lock held.
+ *
+ * @lock: the lock to be acquired.
+ * @task: the task which wants to acquire the lock
+ * @waiter: the waiter that is queued to the lock's wait list. (could be NULL)
*/
-static int try_to_take_rt_mutex(struct rt_mutex *lock)
+static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
+ struct rt_mutex_waiter *waiter)
{
/*
* We have to be careful here if the atomic speedups are
@@ -390,15 +331,52 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock)
*/
mark_rt_mutex_waiters(lock);
- if (rt_mutex_owner(lock) && !try_to_steal_lock(lock, current))
+ if (rt_mutex_owner(lock))
return 0;
+ /*
+ * It will get the lock because of one of these conditions:
+ * 1) there is no waiter
+ * 2) higher priority than waiters
+ * 3) it is top waiter
+ */
+ if (rt_mutex_has_waiters(lock)) {
+ if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) {
+ if (!waiter || waiter != rt_mutex_top_waiter(lock))
+ return 0;
+ }
+ }
+
+ if (waiter || rt_mutex_has_waiters(lock)) {
+ unsigned long flags;
+ struct rt_mutex_waiter *top;
+
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
+
+ /* remove the queued waiter. */
+ if (waiter) {
+ plist_del(&waiter->list_entry, &lock->wait_list);
+ task->pi_blocked_on = NULL;
+ }
+
+ /*
+ * We have to enqueue the top waiter(if it exists) into
+ * task->pi_waiters list.
+ */
+ if (rt_mutex_has_waiters(lock)) {
+ top = rt_mutex_top_waiter(lock);
+ top->pi_list_entry.prio = top->list_entry.prio;
+ plist_add(&top->pi_list_entry, &task->pi_waiters);
+ }
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ }
+
/* We got the lock. */
debug_rt_mutex_lock(lock);
- rt_mutex_set_owner(lock, current, 0);
+ rt_mutex_set_owner(lock, task);
- rt_mutex_deadlock_account_lock(lock, current);
+ rt_mutex_deadlock_account_lock(lock, task);
return 1;
}
@@ -436,6 +414,9 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ if (!owner)
+ return 0;
+
if (waiter == rt_mutex_top_waiter(lock)) {
raw_spin_lock_irqsave(&owner->pi_lock, flags);
plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
@@ -472,21 +453,18 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
/*
* Wake up the next waiter on the lock.
*
- * Remove the top waiter from the current tasks waiter list and from
- * the lock waiter list. Set it as pending owner. Then wake it up.
+ * Remove the top waiter from the current tasks waiter list and wake it up.
*
* Called with lock->wait_lock held.
*/
static void wakeup_next_waiter(struct rt_mutex *lock)
{
struct rt_mutex_waiter *waiter;
- struct task_struct *pendowner;
unsigned long flags;
raw_spin_lock_irqsave(&current->pi_lock, flags);
waiter = rt_mutex_top_waiter(lock);
- plist_del(&waiter->list_entry, &lock->wait_list);
/*
* Remove it from current->pi_waiters. We do not adjust a
@@ -495,43 +473,19 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
* lock->wait_lock.
*/
plist_del(&waiter->pi_list_entry, &current->pi_waiters);
- pendowner = waiter->task;
- waiter->task = NULL;
- rt_mutex_set_owner(lock, pendowner, RT_MUTEX_OWNER_PENDING);
+ rt_mutex_set_owner(lock, NULL);
raw_spin_unlock_irqrestore(&current->pi_lock, flags);
- /*
- * Clear the pi_blocked_on variable and enqueue a possible
- * waiter into the pi_waiters list of the pending owner. This
- * prevents that in case the pending owner gets unboosted a
- * waiter with higher priority than pending-owner->normal_prio
- * is blocked on the unboosted (pending) owner.
- */
- raw_spin_lock_irqsave(&pendowner->pi_lock, flags);
-
- WARN_ON(!pendowner->pi_blocked_on);
- WARN_ON(pendowner->pi_blocked_on != waiter);
- WARN_ON(pendowner->pi_blocked_on->lock != lock);
-
- pendowner->pi_blocked_on = NULL;
-
- if (rt_mutex_has_waiters(lock)) {
- struct rt_mutex_waiter *next;
-
- next = rt_mutex_top_waiter(lock);
- plist_add(&next->pi_list_entry, &pendowner->pi_waiters);
- }
- raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-
- wake_up_process(pendowner);
+ wake_up_process(waiter->task);
}
/*
- * Remove a waiter from a lock
+ * Remove a waiter from a lock and give up
*
- * Must be called with lock->wait_lock held
+ * Must be called with lock->wait_lock held and
+ * have just failed to try_to_take_rt_mutex().
*/
static void remove_waiter(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter)
@@ -543,11 +497,13 @@ static void remove_waiter(struct rt_mutex *lock,
raw_spin_lock_irqsave(&current->pi_lock, flags);
plist_del(&waiter->list_entry, &lock->wait_list);
- waiter->task = NULL;
current->pi_blocked_on = NULL;
raw_spin_unlock_irqrestore(&current->pi_lock, flags);
- if (first && owner != current) {
+ if (!owner)
+ return;
+
+ if (first) {
raw_spin_lock_irqsave(&owner->pi_lock, flags);
@@ -614,21 +570,19 @@ void rt_mutex_adjust_pi(struct task_struct *task)
* or TASK_UNINTERRUPTIBLE)
* @timeout: the pre-initialized and started timer, or NULL for none
* @waiter: the pre-initialized rt_mutex_waiter
- * @detect_deadlock: passed to task_blocks_on_rt_mutex
*
* lock->wait_lock must be held by the caller.
*/
static int __sched
__rt_mutex_slowlock(struct rt_mutex *lock, int state,
struct hrtimer_sleeper *timeout,
- struct rt_mutex_waiter *waiter,
- int detect_deadlock)
+ struct rt_mutex_waiter *waiter)
{
int ret = 0;
for (;;) {
/* Try to acquire the lock: */
- if (try_to_take_rt_mutex(lock))
+ if (try_to_take_rt_mutex(lock, current, waiter))
break;
/*
@@ -645,39 +599,11 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
break;
}
- /*
- * waiter->task is NULL the first time we come here and
- * when we have been woken up by the previous owner
- * but the lock got stolen by a higher prio task.
- */
- if (!waiter->task) {
- ret = task_blocks_on_rt_mutex(lock, waiter, current,
- detect_deadlock);
- /*
- * If we got woken up by the owner then start loop
- * all over without going into schedule to try
- * to get the lock now:
- */
- if (unlikely(!waiter->task)) {
- /*
- * Reset the return value. We might
- * have returned with -EDEADLK and the
- * owner released the lock while we
- * were walking the pi chain.
- */
- ret = 0;
- continue;
- }
- if (unlikely(ret))
- break;
- }
-
raw_spin_unlock(&lock->wait_lock);
debug_rt_mutex_print_deadlock(waiter);
- if (waiter->task)
- schedule_rt_mutex(lock);
+ schedule_rt_mutex(lock);
raw_spin_lock(&lock->wait_lock);
set_current_state(state);
@@ -698,12 +624,11 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
int ret = 0;
debug_rt_mutex_init_waiter(&waiter);
- waiter.task = NULL;
raw_spin_lock(&lock->wait_lock);
/* Try to acquire the lock again: */
- if (try_to_take_rt_mutex(lock)) {
+ if (try_to_take_rt_mutex(lock, current, NULL)) {
raw_spin_unlock(&lock->wait_lock);
return 0;
}
@@ -717,12 +642,14 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
timeout->task = NULL;
}
- ret = __rt_mutex_slowlock(lock, state, timeout, &waiter,
- detect_deadlock);
+ ret = task_blocks_on_rt_mutex(lock, &waiter, current, detect_deadlock);
+
+ if (likely(!ret))
+ ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
set_current_state(TASK_RUNNING);
- if (unlikely(waiter.task))
+ if (unlikely(ret))
remove_waiter(lock, &waiter);
/*
@@ -737,14 +664,6 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
if (unlikely(timeout))
hrtimer_cancel(&timeout->timer);
- /*
- * Readjust priority, when we did not get the lock. We might
- * have been the pending owner and boosted. Since we did not
- * take the lock, the PI boost has to go.
- */
- if (unlikely(ret))
- rt_mutex_adjust_prio(current);
-
debug_rt_mutex_free_waiter(&waiter);
return ret;
@@ -762,7 +681,7 @@ rt_mutex_slowtrylock(struct rt_mutex *lock)
if (likely(rt_mutex_owner(lock) != current)) {
- ret = try_to_take_rt_mutex(lock);
+ ret = try_to_take_rt_mutex(lock, current, NULL);
/*
* try_to_take_rt_mutex() sets the lock waiters
* bit unconditionally. Clean this up.
@@ -992,7 +911,7 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
{
__rt_mutex_init(lock, NULL);
debug_rt_mutex_proxy_lock(lock, proxy_owner);
- rt_mutex_set_owner(lock, proxy_owner, 0);
+ rt_mutex_set_owner(lock, proxy_owner);
rt_mutex_deadlock_account_lock(lock, proxy_owner);
}
@@ -1008,7 +927,7 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
struct task_struct *proxy_owner)
{
debug_rt_mutex_proxy_unlock(lock);
- rt_mutex_set_owner(lock, NULL, 0);
+ rt_mutex_set_owner(lock, NULL);
rt_mutex_deadlock_account_unlock(proxy_owner);
}
@@ -1034,20 +953,14 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
raw_spin_lock(&lock->wait_lock);
- mark_rt_mutex_waiters(lock);
-
- if (!rt_mutex_owner(lock) || try_to_steal_lock(lock, task)) {
- /* We got the lock for task. */
- debug_rt_mutex_lock(lock);
- rt_mutex_set_owner(lock, task, 0);
+ if (try_to_take_rt_mutex(lock, task, NULL)) {
raw_spin_unlock(&lock->wait_lock);
- rt_mutex_deadlock_account_lock(lock, task);
return 1;
}
ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
- if (ret && !waiter->task) {
+ if (ret && !rt_mutex_owner(lock)) {
/*
* Reset the return value. We might have
* returned with -EDEADLK and the owner
@@ -1056,6 +969,10 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
*/
ret = 0;
}
+
+ if (unlikely(ret))
+ remove_waiter(lock, waiter);
+
raw_spin_unlock(&lock->wait_lock);
debug_rt_mutex_print_deadlock(waiter);
@@ -1110,12 +1027,11 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
set_current_state(TASK_INTERRUPTIBLE);
- ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter,
- detect_deadlock);
+ ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
set_current_state(TASK_RUNNING);
- if (unlikely(waiter->task))
+ if (unlikely(ret))
remove_waiter(lock, waiter);
/*
@@ -1126,13 +1042,5 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
raw_spin_unlock(&lock->wait_lock);
- /*
- * Readjust priority, when we did not get the lock. We might have been
- * the pending owner and boosted. Since we did not take the lock, the
- * PI boost has to go.
- */
- if (unlikely(ret))
- rt_mutex_adjust_prio(current);
-
return ret;
}
diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h
index 97a2f81866af..53a66c85261b 100644
--- a/kernel/rtmutex_common.h
+++ b/kernel/rtmutex_common.h
@@ -91,9 +91,8 @@ task_top_pi_waiter(struct task_struct *p)
/*
* lock->owner state tracking:
*/
-#define RT_MUTEX_OWNER_PENDING 1UL
-#define RT_MUTEX_HAS_WAITERS 2UL
-#define RT_MUTEX_OWNER_MASKALL 3UL
+#define RT_MUTEX_HAS_WAITERS 1UL
+#define RT_MUTEX_OWNER_MASKALL 1UL
static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
{
@@ -101,17 +100,6 @@ static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL);
}
-static inline struct task_struct *rt_mutex_real_owner(struct rt_mutex *lock)
-{
- return (struct task_struct *)
- ((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS);
-}
-
-static inline unsigned long rt_mutex_owner_pending(struct rt_mutex *lock)
-{
- return (unsigned long)lock->owner & RT_MUTEX_OWNER_PENDING;
-}
-
/*
* PI-futex support (proxy locking functions, etc.):
*/
diff --git a/kernel/sched.c b/kernel/sched.c
index 18d38e4ec7ba..27125e413576 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -324,7 +324,7 @@ struct cfs_rq {
* 'curr' points to currently running entity on this cfs_rq.
* It is set to NULL otherwise (i.e when none are currently running).
*/
- struct sched_entity *curr, *next, *last;
+ struct sched_entity *curr, *next, *last, *skip;
unsigned int nr_spread_over;
@@ -606,9 +606,6 @@ static inline struct task_group *task_group(struct task_struct *p)
struct task_group *tg;
struct cgroup_subsys_state *css;
- if (p->flags & PF_EXITING)
- return &root_task_group;
-
css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
lockdep_is_held(&task_rq(p)->lock));
tg = container_of(css, struct task_group, css);
@@ -1686,6 +1683,39 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
__release(rq2->lock);
}
+#else /* CONFIG_SMP */
+
+/*
+ * double_rq_lock - safely lock two runqueues
+ *
+ * Note this does not disable interrupts like task_rq_lock,
+ * you need to do so manually before calling.
+ */
+static void double_rq_lock(struct rq *rq1, struct rq *rq2)
+ __acquires(rq1->lock)
+ __acquires(rq2->lock)
+{
+ BUG_ON(!irqs_disabled());
+ BUG_ON(rq1 != rq2);
+ raw_spin_lock(&rq1->lock);
+ __acquire(rq2->lock); /* Fake it out ;) */
+}
+
+/*
+ * double_rq_unlock - safely unlock two runqueues
+ *
+ * Note this does not restore interrupts like task_rq_unlock,
+ * you need to do so manually after calling.
+ */
+static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
+ __releases(rq1->lock)
+ __releases(rq2->lock)
+{
+ BUG_ON(rq1 != rq2);
+ raw_spin_unlock(&rq1->lock);
+ __release(rq2->lock);
+}
+
#endif
static void calc_load_account_idle(struct rq *this_rq);
@@ -1880,7 +1910,7 @@ void account_system_vtime(struct task_struct *curr)
*/
if (hardirq_count())
__this_cpu_add(cpu_hardirq_time, delta);
- else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
+ else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
__this_cpu_add(cpu_softirq_time, delta);
irq_time_write_end();
@@ -1920,8 +1950,40 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
sched_rt_avg_update(rq, irq_delta);
}
+static int irqtime_account_hi_update(void)
+{
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+ unsigned long flags;
+ u64 latest_ns;
+ int ret = 0;
+
+ local_irq_save(flags);
+ latest_ns = this_cpu_read(cpu_hardirq_time);
+ if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->irq))
+ ret = 1;
+ local_irq_restore(flags);
+ return ret;
+}
+
+static int irqtime_account_si_update(void)
+{
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+ unsigned long flags;
+ u64 latest_ns;
+ int ret = 0;
+
+ local_irq_save(flags);
+ latest_ns = this_cpu_read(cpu_softirq_time);
+ if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->softirq))
+ ret = 1;
+ local_irq_restore(flags);
+ return ret;
+}
+
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+#define sched_clock_irqtime (0)
+
static void update_rq_clock_task(struct rq *rq, s64 delta)
{
rq->clock_task += delta;
@@ -2025,14 +2087,14 @@ inline int task_curr(const struct task_struct *p)
static inline void check_class_changed(struct rq *rq, struct task_struct *p,
const struct sched_class *prev_class,
- int oldprio, int running)
+ int oldprio)
{
if (prev_class != p->sched_class) {
if (prev_class->switched_from)
- prev_class->switched_from(rq, p, running);
- p->sched_class->switched_to(rq, p, running);
- } else
- p->sched_class->prio_changed(rq, p, oldprio, running);
+ prev_class->switched_from(rq, p);
+ p->sched_class->switched_to(rq, p);
+ } else if (oldprio != p->prio)
+ p->sched_class->prio_changed(rq, p, oldprio);
}
static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
@@ -2265,27 +2327,6 @@ void kick_process(struct task_struct *p)
EXPORT_SYMBOL_GPL(kick_process);
#endif /* CONFIG_SMP */
-/**
- * task_oncpu_function_call - call a function on the cpu on which a task runs
- * @p: the task to evaluate
- * @func: the function to be called
- * @info: the function call argument
- *
- * Calls the function @func when the task is currently running. This might
- * be on the current CPU, which just calls the function directly
- */
-void task_oncpu_function_call(struct task_struct *p,
- void (*func) (void *info), void *info)
-{
- int cpu;
-
- preempt_disable();
- cpu = task_cpu(p);
- if (task_curr(p))
- smp_call_function_single(cpu, func, info, 1);
- preempt_enable();
-}
-
#ifdef CONFIG_SMP
/*
* ->cpus_allowed is protected by either TASK_WAKING or rq->lock held.
@@ -2566,6 +2607,7 @@ static void __sched_fork(struct task_struct *p)
p->se.sum_exec_runtime = 0;
p->se.prev_sum_exec_runtime = 0;
p->se.nr_migrations = 0;
+ p->se.vruntime = 0;
#ifdef CONFIG_SCHEDSTATS
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
@@ -2776,9 +2818,12 @@ static inline void
prepare_task_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
+ sched_info_switch(prev, next);
+ perf_event_task_sched_out(prev, next);
fire_sched_out_preempt_notifiers(prev, next);
prepare_lock_switch(rq, next);
prepare_arch_switch(next);
+ trace_sched_switch(prev, next);
}
/**
@@ -2911,7 +2956,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
struct mm_struct *mm, *oldmm;
prepare_task_switch(rq, prev, next);
- trace_sched_switch(prev, next);
+
mm = next->mm;
oldmm = prev->active_mm;
/*
@@ -3568,6 +3613,32 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime,
}
/*
+ * Account system cpu time to a process and desired cpustat field
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ * @target_cputime64: pointer to cpustat field that has to be updated
+ */
+static inline
+void __account_system_time(struct task_struct *p, cputime_t cputime,
+ cputime_t cputime_scaled, cputime64_t *target_cputime64)
+{
+ cputime64_t tmp = cputime_to_cputime64(cputime);
+
+ /* Add system time to process. */
+ p->stime = cputime_add(p->stime, cputime);
+ p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
+ account_group_system_time(p, cputime);
+
+ /* Add system time to cpustat. */
+ *target_cputime64 = cputime64_add(*target_cputime64, tmp);
+ cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);
+
+ /* Account for system time used */
+ acct_update_integrals(p);
+}
+
+/*
* Account system cpu time to a process.
* @p: the process that the cpu time gets accounted to
* @hardirq_offset: the offset to subtract from hardirq_count()
@@ -3578,36 +3649,26 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
cputime_t cputime, cputime_t cputime_scaled)
{
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
- cputime64_t tmp;
+ cputime64_t *target_cputime64;
if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
account_guest_time(p, cputime, cputime_scaled);
return;
}
- /* Add system time to process. */
- p->stime = cputime_add(p->stime, cputime);
- p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
- account_group_system_time(p, cputime);
-
- /* Add system time to cpustat. */
- tmp = cputime_to_cputime64(cputime);
if (hardirq_count() - hardirq_offset)
- cpustat->irq = cputime64_add(cpustat->irq, tmp);
+ target_cputime64 = &cpustat->irq;
else if (in_serving_softirq())
- cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+ target_cputime64 = &cpustat->softirq;
else
- cpustat->system = cputime64_add(cpustat->system, tmp);
+ target_cputime64 = &cpustat->system;
- cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);
-
- /* Account for system time used */
- acct_update_integrals(p);
+ __account_system_time(p, cputime, cputime_scaled, target_cputime64);
}
/*
* Account for involuntary wait time.
- * @steal: the cpu time spent in involuntary wait
+ * @cputime: the cpu time spent in involuntary wait
*/
void account_steal_time(cputime_t cputime)
{
@@ -3635,6 +3696,73 @@ void account_idle_time(cputime_t cputime)
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+/*
+ * Account a tick to a process and cpustat
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: is the tick from userspace
+ * @rq: the pointer to rq
+ *
+ * Tick demultiplexing follows the order
+ * - pending hardirq update
+ * - pending softirq update
+ * - user_time
+ * - idle_time
+ * - system time
+ * - check for guest_time
+ * - else account as system_time
+ *
+ * Check for hardirq is done both for system and user time as there is
+ * no timer going off while we are on hardirq and hence we may never get an
+ * opportunity to update it solely in system time.
+ * p->stime and friends are only updated on system time and not on irq
+ * softirq as those do not count in task exec_runtime any more.
+ */
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+ struct rq *rq)
+{
+ cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+ cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy);
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+
+ if (irqtime_account_hi_update()) {
+ cpustat->irq = cputime64_add(cpustat->irq, tmp);
+ } else if (irqtime_account_si_update()) {
+ cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+ } else if (this_cpu_ksoftirqd() == p) {
+ /*
+ * ksoftirqd time do not get accounted in cpu_softirq_time.
+ * So, we have to handle it separately here.
+ * Also, p->stime needs to be updated for ksoftirqd.
+ */
+ __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+ &cpustat->softirq);
+ } else if (user_tick) {
+ account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ } else if (p == rq->idle) {
+ account_idle_time(cputime_one_jiffy);
+ } else if (p->flags & PF_VCPU) { /* System time or guest time */
+ account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ } else {
+ __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+ &cpustat->system);
+ }
+}
+
+static void irqtime_account_idle_ticks(int ticks)
+{
+ int i;
+ struct rq *rq = this_rq();
+
+ for (i = 0; i < ticks; i++)
+ irqtime_account_process_tick(current, 0, rq);
+}
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+static void irqtime_account_idle_ticks(int ticks) {}
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+ struct rq *rq) {}
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
/*
* Account a single tick of cpu time.
* @p: the process that the cpu time gets accounted to
@@ -3645,6 +3773,11 @@ void account_process_tick(struct task_struct *p, int user_tick)
cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
struct rq *rq = this_rq();
+ if (sched_clock_irqtime) {
+ irqtime_account_process_tick(p, user_tick, rq);
+ return;
+ }
+
if (user_tick)
account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
@@ -3670,6 +3803,12 @@ void account_steal_ticks(unsigned long ticks)
*/
void account_idle_ticks(unsigned long ticks)
{
+
+ if (sched_clock_irqtime) {
+ irqtime_account_idle_ticks(ticks);
+ return;
+ }
+
account_idle_time(jiffies_to_cputime(ticks));
}
@@ -3989,9 +4128,6 @@ need_resched_nonpreemptible:
rq->skip_clock_update = 0;
if (likely(prev != next)) {
- sched_info_switch(prev, next);
- perf_event_task_sched_out(prev, next);
-
rq->nr_switches++;
rq->curr = next;
++*switch_count;
@@ -4213,6 +4349,7 @@ void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
{
__wake_up_common(q, mode, 1, 0, key);
}
+EXPORT_SYMBOL_GPL(__wake_up_locked_key);
/**
* __wake_up_sync_key - wake up threads blocked on a waitqueue.
@@ -4570,11 +4707,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
if (running)
p->sched_class->set_curr_task(rq);
- if (on_rq) {
+ if (on_rq)
enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
- check_class_changed(rq, p, prev_class, oldprio, running);
- }
+ check_class_changed(rq, p, prev_class, oldprio);
task_rq_unlock(rq, &flags);
}
@@ -4822,12 +4958,15 @@ recheck:
param->sched_priority > rlim_rtprio)
return -EPERM;
}
+
/*
- * Like positive nice levels, dont allow tasks to
- * move out of SCHED_IDLE either:
+ * Treat SCHED_IDLE as nice 20. Only allow a switch to
+ * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
*/
- if (p->policy == SCHED_IDLE && policy != SCHED_IDLE)
- return -EPERM;
+ if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
+ if (!can_nice(p, TASK_NICE(p)))
+ return -EPERM;
+ }
/* can't change other user's priorities */
if (!check_same_owner(p))
@@ -4902,11 +5041,10 @@ recheck:
if (running)
p->sched_class->set_curr_task(rq);
- if (on_rq) {
+ if (on_rq)
activate_task(rq, p, 0);
- check_class_changed(rq, p, prev_class, oldprio, running);
- }
+ check_class_changed(rq, p, prev_class, oldprio);
__task_rq_unlock(rq);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
@@ -5323,6 +5461,65 @@ void __sched yield(void)
}
EXPORT_SYMBOL(yield);
+/**
+ * yield_to - yield the current processor to another thread in
+ * your thread group, or accelerate that thread toward the
+ * processor it's on.
+ *
+ * It's the caller's job to ensure that the target task struct
+ * can't go away on us before we can do any checks.
+ *
+ * Returns true if we indeed boosted the target task.
+ */
+bool __sched yield_to(struct task_struct *p, bool preempt)
+{
+ struct task_struct *curr = current;
+ struct rq *rq, *p_rq;
+ unsigned long flags;
+ bool yielded = 0;
+
+ local_irq_save(flags);
+ rq = this_rq();
+
+again:
+ p_rq = task_rq(p);
+ double_rq_lock(rq, p_rq);
+ while (task_rq(p) != p_rq) {
+ double_rq_unlock(rq, p_rq);
+ goto again;
+ }
+
+ if (!curr->sched_class->yield_to_task)
+ goto out;
+
+ if (curr->sched_class != p->sched_class)
+ goto out;
+
+ if (task_running(p_rq, p) || p->state)
+ goto out;
+
+ yielded = curr->sched_class->yield_to_task(rq, p, preempt);
+ if (yielded) {
+ schedstat_inc(rq, yld_count);
+ /*
+ * Make p's CPU reschedule; pick_next_entity takes care of
+ * fairness.
+ */
+ if (preempt && rq != p_rq)
+ resched_task(p_rq->curr);
+ }
+
+out:
+ double_rq_unlock(rq, p_rq);
+ local_irq_restore(flags);
+
+ if (yielded)
+ schedule();
+
+ return yielded;
+}
+EXPORT_SYMBOL_GPL(yield_to);
+
/*
* This task is about to go to sleep on IO. Increment rq->nr_iowait so
* that process accounting knows that this is a task in IO wait state.
@@ -5571,7 +5768,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
* The idle tasks have their own, simple scheduling class:
*/
idle->sched_class = &idle_sched_class;
- ftrace_graph_init_task(idle);
+ ftrace_graph_init_idle_task(idle, cpu);
}
/*
@@ -7796,6 +7993,10 @@ static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
INIT_LIST_HEAD(&cfs_rq->tasks);
#ifdef CONFIG_FAIR_GROUP_SCHED
cfs_rq->rq = rq;
+ /* allow initial update_cfs_load() to truncate */
+#ifdef CONFIG_SMP
+ cfs_rq->load_stamp = 1;
+#endif
#endif
cfs_rq->min_vruntime = (u64)(-(1LL << 20));
}
@@ -8109,6 +8310,8 @@ EXPORT_SYMBOL(__might_sleep);
#ifdef CONFIG_MAGIC_SYSRQ
static void normalize_task(struct rq *rq, struct task_struct *p)
{
+ const struct sched_class *prev_class = p->sched_class;
+ int old_prio = p->prio;
int on_rq;
on_rq = p->se.on_rq;
@@ -8119,6 +8322,8 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
activate_task(rq, p, 0);
resched_task(rq->curr);
}
+
+ check_class_changed(rq, p, prev_class, old_prio);
}
void normalize_rt_tasks(void)
@@ -8510,7 +8715,7 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
/* Propagate contribution to hierarchy */
raw_spin_lock_irqsave(&rq->lock, flags);
for_each_sched_entity(se)
- update_cfs_shares(group_cfs_rq(se), 0);
+ update_cfs_shares(group_cfs_rq(se));
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
@@ -8884,7 +9089,8 @@ cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
}
static void
-cpu_cgroup_exit(struct cgroup_subsys *ss, struct task_struct *task)
+cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct cgroup *old_cgrp, struct task_struct *task)
{
/*
* cgroup_exit() is called in the copy_process() failure path.
diff --git a/kernel/sched_autogroup.c b/kernel/sched_autogroup.c
index 9fb656283157..5946ac515602 100644
--- a/kernel/sched_autogroup.c
+++ b/kernel/sched_autogroup.c
@@ -12,7 +12,6 @@ static atomic_t autogroup_seq_nr;
static void __init autogroup_init(struct task_struct *init_task)
{
autogroup_default.tg = &root_task_group;
- root_task_group.autogroup = &autogroup_default;
kref_init(&autogroup_default.kref);
init_rwsem(&autogroup_default.lock);
init_task->signal->autogroup = &autogroup_default;
@@ -130,7 +129,7 @@ task_wants_autogroup(struct task_struct *p, struct task_group *tg)
static inline bool task_group_is_autogroup(struct task_group *tg)
{
- return tg != &root_task_group && tg->autogroup;
+ return !!tg->autogroup;
}
static inline struct task_group *
@@ -161,11 +160,15 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
p->signal->autogroup = autogroup_kref_get(ag);
+ if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled))
+ goto out;
+
t = p;
do {
sched_move_task(t);
} while_each_thread(p, t);
+out:
unlock_task_sighand(p, &flags);
autogroup_kref_put(prev);
}
@@ -247,10 +250,14 @@ void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
{
struct autogroup *ag = autogroup_task_get(p);
+ if (!task_group_is_autogroup(ag->tg))
+ goto out;
+
down_read(&ag->lock);
seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice);
up_read(&ag->lock);
+out:
autogroup_kref_put(ag);
}
#endif /* CONFIG_PROC_FS */
@@ -258,9 +265,7 @@ void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
#ifdef CONFIG_SCHED_DEBUG
static inline int autogroup_path(struct task_group *tg, char *buf, int buflen)
{
- int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
-
- if (!enabled || !tg->autogroup)
+ if (!task_group_is_autogroup(tg))
return 0;
return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id);
diff --git a/kernel/sched_autogroup.h b/kernel/sched_autogroup.h
index 7b859ffe5dad..05577055cfca 100644
--- a/kernel/sched_autogroup.h
+++ b/kernel/sched_autogroup.h
@@ -1,6 +1,11 @@
#ifdef CONFIG_SCHED_AUTOGROUP
struct autogroup {
+ /*
+ * reference doesn't mean how many thread attach to this
+ * autogroup now. It just stands for the number of task
+ * could use this autogroup.
+ */
struct kref kref;
struct task_group *tg;
struct rw_semaphore lock;
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index eb6cb8edd075..7bacd83a4158 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -179,7 +179,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
raw_spin_lock_irqsave(&rq->lock, flags);
if (cfs_rq->rb_leftmost)
- MIN_vruntime = (__pick_next_entity(cfs_rq))->vruntime;
+ MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime;
last = __pick_last_entity(cfs_rq);
if (last)
max_vruntime = last->vruntime;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 0c26e2df450e..3f7ec9e27ee1 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -69,14 +69,6 @@ static unsigned int sched_nr_latency = 8;
unsigned int sysctl_sched_child_runs_first __read_mostly;
/*
- * sys_sched_yield() compat mode
- *
- * This option switches the agressive yield implementation of the
- * old scheduler back on.
- */
-unsigned int __read_mostly sysctl_sched_compat_yield;
-
-/*
* SCHED_OTHER wake-up granularity.
* (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
*
@@ -419,7 +411,7 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
}
-static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
+static struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *left = cfs_rq->rb_leftmost;
@@ -429,6 +421,17 @@ static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
return rb_entry(left, struct sched_entity, run_node);
}
+static struct sched_entity *__pick_next_entity(struct sched_entity *se)
+{
+ struct rb_node *next = rb_next(&se->run_node);
+
+ if (!next)
+ return NULL;
+
+ return rb_entry(next, struct sched_entity, run_node);
+}
+
+#ifdef CONFIG_SCHED_DEBUG
static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
@@ -443,7 +446,6 @@ static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
* Scheduling class statistics methods:
*/
-#ifdef CONFIG_SCHED_DEBUG
int sched_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
@@ -540,7 +542,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
}
static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update);
-static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta);
+static void update_cfs_shares(struct cfs_rq *cfs_rq);
/*
* Update the current task's runtime statistics. Skip current tasks that
@@ -733,6 +735,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
now - cfs_rq->load_last > 4 * period) {
cfs_rq->load_period = 0;
cfs_rq->load_avg = 0;
+ delta = period - 1;
}
cfs_rq->load_stamp = now;
@@ -763,16 +766,15 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
list_del_leaf_cfs_rq(cfs_rq);
}
-static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
- long weight_delta)
+static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
long load_weight, load, shares;
- load = cfs_rq->load.weight + weight_delta;
+ load = cfs_rq->load.weight;
load_weight = atomic_read(&tg->load_weight);
- load_weight -= cfs_rq->load_contribution;
load_weight += load;
+ load_weight -= cfs_rq->load_contribution;
shares = (tg->shares * load);
if (load_weight)
@@ -790,7 +792,7 @@ static void update_entity_shares_tick(struct cfs_rq *cfs_rq)
{
if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) {
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
}
}
# else /* CONFIG_SMP */
@@ -798,8 +800,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
{
}
-static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
- long weight_delta)
+static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
return tg->shares;
}
@@ -824,7 +825,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
account_entity_enqueue(cfs_rq, se);
}
-static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+static void update_cfs_shares(struct cfs_rq *cfs_rq)
{
struct task_group *tg;
struct sched_entity *se;
@@ -838,7 +839,7 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
if (likely(se->load.weight == tg->shares))
return;
#endif
- shares = calc_cfs_shares(cfs_rq, tg, weight_delta);
+ shares = calc_cfs_shares(cfs_rq, tg);
reweight_entity(cfs_rq_of(se), se, shares);
}
@@ -847,7 +848,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
{
}
-static inline void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
{
}
@@ -978,8 +979,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
*/
update_curr(cfs_rq);
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, se->load.weight);
account_entity_enqueue(cfs_rq, se);
+ update_cfs_shares(cfs_rq);
if (flags & ENQUEUE_WAKEUP) {
place_entity(cfs_rq, se, 0);
@@ -996,19 +997,49 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
list_add_leaf_cfs_rq(cfs_rq);
}
-static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __clear_buddies_last(struct sched_entity *se)
+{
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ if (cfs_rq->last == se)
+ cfs_rq->last = NULL;
+ else
+ break;
+ }
+}
+
+static void __clear_buddies_next(struct sched_entity *se)
{
- if (!se || cfs_rq->last == se)
- cfs_rq->last = NULL;
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ if (cfs_rq->next == se)
+ cfs_rq->next = NULL;
+ else
+ break;
+ }
+}
- if (!se || cfs_rq->next == se)
- cfs_rq->next = NULL;
+static void __clear_buddies_skip(struct sched_entity *se)
+{
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ if (cfs_rq->skip == se)
+ cfs_rq->skip = NULL;
+ else
+ break;
+ }
}
static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- for_each_sched_entity(se)
- __clear_buddies(cfs_rq_of(se), se);
+ if (cfs_rq->last == se)
+ __clear_buddies_last(se);
+
+ if (cfs_rq->next == se)
+ __clear_buddies_next(se);
+
+ if (cfs_rq->skip == se)
+ __clear_buddies_skip(se);
}
static void
@@ -1041,7 +1072,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
update_cfs_load(cfs_rq, 0);
account_entity_dequeue(cfs_rq, se);
update_min_vruntime(cfs_rq);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
/*
* Normalize the entity after updating the min_vruntime because the
@@ -1084,7 +1115,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
return;
if (cfs_rq->nr_running > 1) {
- struct sched_entity *se = __pick_next_entity(cfs_rq);
+ struct sched_entity *se = __pick_first_entity(cfs_rq);
s64 delta = curr->vruntime - se->vruntime;
if (delta < 0)
@@ -1128,13 +1159,27 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
static int
wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
+/*
+ * Pick the next process, keeping these things in mind, in this order:
+ * 1) keep things fair between processes/task groups
+ * 2) pick the "next" process, since someone really wants that to run
+ * 3) pick the "last" process, for cache locality
+ * 4) do not run the "skip" process, if something else is available
+ */
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
- struct sched_entity *se = __pick_next_entity(cfs_rq);
+ struct sched_entity *se = __pick_first_entity(cfs_rq);
struct sched_entity *left = se;
- if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
- se = cfs_rq->next;
+ /*
+ * Avoid running the skip buddy, if running something else can
+ * be done without getting too unfair.
+ */
+ if (cfs_rq->skip == se) {
+ struct sched_entity *second = __pick_next_entity(se);
+ if (second && wakeup_preempt_entity(second, left) < 1)
+ se = second;
+ }
/*
* Prefer last buddy, try to return the CPU to a preempted task.
@@ -1142,6 +1187,12 @@ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
se = cfs_rq->last;
+ /*
+ * Someone really wants this to run. If it's not unfair, run it.
+ */
+ if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+ se = cfs_rq->next;
+
clear_buddies(cfs_rq, se);
return se;
@@ -1282,7 +1333,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
struct cfs_rq *cfs_rq = cfs_rq_of(se);
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
}
hrtick_update(rq);
@@ -1312,58 +1363,12 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
struct cfs_rq *cfs_rq = cfs_rq_of(se);
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
}
hrtick_update(rq);
}
-/*
- * sched_yield() support is very simple - we dequeue and enqueue.
- *
- * If compat_yield is turned on then we requeue to the end of the tree.
- */
-static void yield_task_fair(struct rq *rq)
-{
- struct task_struct *curr = rq->curr;
- struct cfs_rq *cfs_rq = task_cfs_rq(curr);
- struct sched_entity *rightmost, *se = &curr->se;
-
- /*
- * Are we the only task in the tree?
- */
- if (unlikely(cfs_rq->nr_running == 1))
- return;
-
- clear_buddies(cfs_rq, se);
-
- if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
- update_rq_clock(rq);
- /*
- * Update run-time statistics of the 'current'.
- */
- update_curr(cfs_rq);
-
- return;
- }
- /*
- * Find the rightmost entry in the rbtree:
- */
- rightmost = __pick_last_entity(cfs_rq);
- /*
- * Already in the rightmost position?
- */
- if (unlikely(!rightmost || entity_before(rightmost, se)))
- return;
-
- /*
- * Minimally necessary key value to be last in the tree:
- * Upon rescheduling, sched_class::put_prev_task() will place
- * 'current' within the tree based on its new key value.
- */
- se->vruntime = rightmost->vruntime + 1;
-}
-
#ifdef CONFIG_SMP
static void task_waking_fair(struct rq *rq, struct task_struct *p)
@@ -1834,6 +1839,14 @@ static void set_next_buddy(struct sched_entity *se)
}
}
+static void set_skip_buddy(struct sched_entity *se)
+{
+ if (likely(task_of(se)->policy != SCHED_IDLE)) {
+ for_each_sched_entity(se)
+ cfs_rq_of(se)->skip = se;
+ }
+}
+
/*
* Preempt the current task with a newly woken task if needed:
*/
@@ -1857,16 +1870,18 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
if (test_tsk_need_resched(curr))
return;
+ /* Idle tasks are by definition preempted by non-idle tasks. */
+ if (unlikely(curr->policy == SCHED_IDLE) &&
+ likely(p->policy != SCHED_IDLE))
+ goto preempt;
+
/*
- * Batch and idle tasks do not preempt (their preemption is driven by
- * the tick):
+ * Batch and idle tasks do not preempt non-idle tasks (their preemption
+ * is driven by the tick):
*/
if (unlikely(p->policy != SCHED_NORMAL))
return;
- /* Idle tasks are by definition preempted by everybody. */
- if (unlikely(curr->policy == SCHED_IDLE))
- goto preempt;
if (!sched_feat(WAKEUP_PREEMPT))
return;
@@ -1932,6 +1947,51 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
}
}
+/*
+ * sched_yield() is very simple
+ *
+ * The magic of dealing with the ->skip buddy is in pick_next_entity.
+ */
+static void yield_task_fair(struct rq *rq)
+{
+ struct task_struct *curr = rq->curr;
+ struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+ struct sched_entity *se = &curr->se;
+
+ /*
+ * Are we the only task in the tree?
+ */
+ if (unlikely(rq->nr_running == 1))
+ return;
+
+ clear_buddies(cfs_rq, se);
+
+ if (curr->policy != SCHED_BATCH) {
+ update_rq_clock(rq);
+ /*
+ * Update run-time statistics of the 'current'.
+ */
+ update_curr(cfs_rq);
+ }
+
+ set_skip_buddy(se);
+}
+
+static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt)
+{
+ struct sched_entity *se = &p->se;
+
+ if (!se->on_rq)
+ return false;
+
+ /* Tell the scheduler that we'd really like pse to run next. */
+ set_next_buddy(se);
+
+ yield_task_fair(rq);
+
+ return true;
+}
+
#ifdef CONFIG_SMP
/**************************************************
* Fair scheduling class load-balancing methods:
@@ -2123,7 +2183,7 @@ static int update_shares_cpu(struct task_group *tg, int cpu)
* We need to update shares after updating tg->load_weight in
* order to adjust the weight of groups with long running tasks.
*/
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
raw_spin_unlock_irqrestore(&rq->lock, flags);
@@ -2610,7 +2670,6 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
* @this_cpu: Cpu for which load balance is currently performed.
* @idle: Idle status of this_cpu
* @load_idx: Load index of sched_domain of this_cpu for load calc.
- * @sd_idle: Idle status of the sched_domain containing group.
* @local_group: Does group contain this_cpu.
* @cpus: Set of cpus considered for load balancing.
* @balance: Should we balance.
@@ -2618,7 +2677,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
*/
static inline void update_sg_lb_stats(struct sched_domain *sd,
struct sched_group *group, int this_cpu,
- enum cpu_idle_type idle, int load_idx, int *sd_idle,
+ enum cpu_idle_type idle, int load_idx,
int local_group, const struct cpumask *cpus,
int *balance, struct sg_lb_stats *sgs)
{
@@ -2638,9 +2697,6 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
for_each_cpu_and(i, sched_group_cpus(group), cpus) {
struct rq *rq = cpu_rq(i);
- if (*sd_idle && rq->nr_running)
- *sd_idle = 0;
-
/* Bias balancing toward cpus of our domain */
if (local_group) {
if (idle_cpu(i) && !first_idle_cpu) {
@@ -2685,7 +2741,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
/*
* Consider the group unbalanced when the imbalance is larger
- * than the average weight of two tasks.
+ * than the average weight of a task.
*
* APZ: with cgroup the avg task weight can vary wildly and
* might not be a suitable number - should we keep a
@@ -2695,7 +2751,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
if (sgs->sum_nr_running)
avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
- if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task && max_nr_running > 1)
+ if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1)
sgs->group_imb = 1;
sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
@@ -2755,15 +2811,13 @@ static bool update_sd_pick_busiest(struct sched_domain *sd,
* @sd: sched_domain whose statistics are to be updated.
* @this_cpu: Cpu for which load balance is currently performed.
* @idle: Idle status of this_cpu
- * @sd_idle: Idle status of the sched_domain containing sg.
* @cpus: Set of cpus considered for load balancing.
* @balance: Should we balance.
* @sds: variable to hold the statistics for this sched_domain.
*/
static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
- enum cpu_idle_type idle, int *sd_idle,
- const struct cpumask *cpus, int *balance,
- struct sd_lb_stats *sds)
+ enum cpu_idle_type idle, const struct cpumask *cpus,
+ int *balance, struct sd_lb_stats *sds)
{
struct sched_domain *child = sd->child;
struct sched_group *sg = sd->groups;
@@ -2781,7 +2835,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
local_group = cpumask_test_cpu(this_cpu, sched_group_cpus(sg));
memset(&sgs, 0, sizeof(sgs));
- update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx, sd_idle,
+ update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx,
local_group, cpus, balance, &sgs);
if (local_group && !(*balance))
@@ -3033,7 +3087,6 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
* @imbalance: Variable which stores amount of weighted load which should
* be moved to restore balance/put a group to idle.
* @idle: The idle status of this_cpu.
- * @sd_idle: The idleness of sd
* @cpus: The set of CPUs under consideration for load-balancing.
* @balance: Pointer to a variable indicating if this_cpu
* is the appropriate cpu to perform load balancing at this_level.
@@ -3046,7 +3099,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
unsigned long *imbalance, enum cpu_idle_type idle,
- int *sd_idle, const struct cpumask *cpus, int *balance)
+ const struct cpumask *cpus, int *balance)
{
struct sd_lb_stats sds;
@@ -3056,22 +3109,11 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
* Compute the various statistics relavent for load balancing at
* this level.
*/
- update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus,
- balance, &sds);
-
- /* Cases where imbalance does not exist from POV of this_cpu */
- /* 1) this_cpu is not the appropriate cpu to perform load balancing
- * at this level.
- * 2) There is no busy sibling group to pull from.
- * 3) This group is the busiest group.
- * 4) This group is more busy than the avg busieness at this
- * sched_domain.
- * 5) The imbalance is within the specified limit.
- *
- * Note: when doing newidle balance, if the local group has excess
- * capacity (i.e. nr_running < group_capacity) and the busiest group
- * does not have any capacity, we force a load balance to pull tasks
- * to the local group. In this case, we skip past checks 3, 4 and 5.
+ update_sd_lb_stats(sd, this_cpu, idle, cpus, balance, &sds);
+
+ /*
+ * this_cpu is not the appropriate cpu to perform load balancing at
+ * this level.
*/
if (!(*balance))
goto ret;
@@ -3080,41 +3122,55 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
check_asym_packing(sd, &sds, this_cpu, imbalance))
return sds.busiest;
+ /* There is no busy sibling group to pull tasks from */
if (!sds.busiest || sds.busiest_nr_running == 0)
goto out_balanced;
- /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
+ /*
+ * If the busiest group is imbalanced the below checks don't
+ * work because they assumes all things are equal, which typically
+ * isn't true due to cpus_allowed constraints and the like.
+ */
+ if (sds.group_imb)
+ goto force_balance;
+
+ /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity &&
!sds.busiest_has_capacity)
goto force_balance;
+ /*
+ * If the local group is more busy than the selected busiest group
+ * don't try and pull any tasks.
+ */
if (sds.this_load >= sds.max_load)
goto out_balanced;
+ /*
+ * Don't pull any tasks if this group is already above the domain
+ * average load.
+ */
sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
-
if (sds.this_load >= sds.avg_load)
goto out_balanced;
- /*
- * In the CPU_NEWLY_IDLE, use imbalance_pct to be conservative.
- * And to check for busy balance use !idle_cpu instead of
- * CPU_NOT_IDLE. This is because HT siblings will use CPU_NOT_IDLE
- * even when they are idle.
- */
- if (idle == CPU_NEWLY_IDLE || !idle_cpu(this_cpu)) {
- if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
- goto out_balanced;
- } else {
+ if (idle == CPU_IDLE) {
/*
* This cpu is idle. If the busiest group load doesn't
* have more tasks than the number of available cpu's and
* there is no imbalance between this and busiest group
* wrt to idle cpu's, it is balanced.
*/
- if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) &&
+ if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) &&
sds.busiest_nr_running <= sds.busiest_group_weight)
goto out_balanced;
+ } else {
+ /*
+ * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use
+ * imbalance_pct to be conservative.
+ */
+ if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+ goto out_balanced;
}
force_balance:
@@ -3193,7 +3249,7 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group,
/* Working cpumask for load_balance and load_balance_newidle. */
static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
-static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle,
+static int need_active_balance(struct sched_domain *sd, int idle,
int busiest_cpu, int this_cpu)
{
if (idle == CPU_NEWLY_IDLE) {
@@ -3225,10 +3281,6 @@ static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle,
* move_tasks() will succeed. ld_moved will be true and this
* active balance code will not be triggered.
*/
- if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- return 0;
-
if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
return 0;
}
@@ -3246,7 +3298,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
struct sched_domain *sd, enum cpu_idle_type idle,
int *balance)
{
- int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
+ int ld_moved, all_pinned = 0, active_balance = 0;
struct sched_group *group;
unsigned long imbalance;
struct rq *busiest;
@@ -3255,20 +3307,10 @@ static int load_balance(int this_cpu, struct rq *this_rq,
cpumask_copy(cpus, cpu_active_mask);
- /*
- * When power savings policy is enabled for the parent domain, idle
- * sibling can pick up load irrespective of busy siblings. In this case,
- * let the state of idle sibling percolate up as CPU_IDLE, instead of
- * portraying it as CPU_NOT_IDLE.
- */
- if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- sd_idle = 1;
-
schedstat_inc(sd, lb_count[idle]);
redo:
- group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
+ group = find_busiest_group(sd, this_cpu, &imbalance, idle,
cpus, balance);
if (*balance == 0)
@@ -3330,8 +3372,7 @@ redo:
if (idle != CPU_NEWLY_IDLE)
sd->nr_balance_failed++;
- if (need_active_balance(sd, sd_idle, idle, cpu_of(busiest),
- this_cpu)) {
+ if (need_active_balance(sd, idle, cpu_of(busiest), this_cpu)) {
raw_spin_lock_irqsave(&busiest->lock, flags);
/* don't kick the active_load_balance_cpu_stop,
@@ -3386,10 +3427,6 @@ redo:
sd->balance_interval *= 2;
}
- if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- ld_moved = -1;
-
goto out;
out_balanced:
@@ -3403,11 +3440,7 @@ out_one_pinned:
(sd->balance_interval < sd->max_interval))
sd->balance_interval *= 2;
- if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- ld_moved = -1;
- else
- ld_moved = 0;
+ ld_moved = 0;
out:
return ld_moved;
}
@@ -3831,8 +3864,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
if (load_balance(cpu, rq, sd, idle, &balance)) {
/*
* We've pulled tasks over so either we're no
- * longer idle, or one of our SMT siblings is
- * not idle.
+ * longer idle.
*/
idle = CPU_NOT_IDLE;
}
@@ -4079,33 +4111,62 @@ static void task_fork_fair(struct task_struct *p)
* Priority of the task has changed. Check to see if we preempt
* the current task.
*/
-static void prio_changed_fair(struct rq *rq, struct task_struct *p,
- int oldprio, int running)
+static void
+prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
{
+ if (!p->se.on_rq)
+ return;
+
/*
* Reschedule if we are currently running on this runqueue and
* our priority decreased, or if we are not currently running on
* this runqueue and our priority is higher than the current's
*/
- if (running) {
+ if (rq->curr == p) {
if (p->prio > oldprio)
resched_task(rq->curr);
} else
check_preempt_curr(rq, p, 0);
}
+static void switched_from_fair(struct rq *rq, struct task_struct *p)
+{
+ struct sched_entity *se = &p->se;
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ /*
+ * Ensure the task's vruntime is normalized, so that when its
+ * switched back to the fair class the enqueue_entity(.flags=0) will
+ * do the right thing.
+ *
+ * If it was on_rq, then the dequeue_entity(.flags=0) will already
+ * have normalized the vruntime, if it was !on_rq, then only when
+ * the task is sleeping will it still have non-normalized vruntime.
+ */
+ if (!se->on_rq && p->state != TASK_RUNNING) {
+ /*
+ * Fix up our vruntime so that the current sleep doesn't
+ * cause 'unlimited' sleep bonus.
+ */
+ place_entity(cfs_rq, se, 0);
+ se->vruntime -= cfs_rq->min_vruntime;
+ }
+}
+
/*
* We switched to the sched_fair class.
*/
-static void switched_to_fair(struct rq *rq, struct task_struct *p,
- int running)
+static void switched_to_fair(struct rq *rq, struct task_struct *p)
{
+ if (!p->se.on_rq)
+ return;
+
/*
* We were most likely switched from sched_rt, so
* kick off the schedule if running, otherwise just see
* if we can still preempt the current task.
*/
- if (running)
+ if (rq->curr == p)
resched_task(rq->curr);
else
check_preempt_curr(rq, p, 0);
@@ -4171,6 +4232,7 @@ static const struct sched_class fair_sched_class = {
.enqueue_task = enqueue_task_fair,
.dequeue_task = dequeue_task_fair,
.yield_task = yield_task_fair,
+ .yield_to_task = yield_to_task_fair,
.check_preempt_curr = check_preempt_wakeup,
@@ -4191,6 +4253,7 @@ static const struct sched_class fair_sched_class = {
.task_fork = task_fork_fair,
.prio_changed = prio_changed_fair,
+ .switched_from = switched_from_fair,
.switched_to = switched_to_fair,
.get_rr_interval = get_rr_interval_fair,
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index 9fa0f402c87c..c82f26c1b7c3 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -52,31 +52,15 @@ static void set_curr_task_idle(struct rq *rq)
{
}
-static void switched_to_idle(struct rq *rq, struct task_struct *p,
- int running)
+static void switched_to_idle(struct rq *rq, struct task_struct *p)
{
- /* Can this actually happen?? */
- if (running)
- resched_task(rq->curr);
- else
- check_preempt_curr(rq, p, 0);
+ BUG();
}
-static void prio_changed_idle(struct rq *rq, struct task_struct *p,
- int oldprio, int running)
+static void
+prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio)
{
- /* This can happen for hot plug CPUS */
-
- /*
- * Reschedule if we are currently running on this runqueue and
- * our priority decreased, or if we are not currently running on
- * this runqueue and our priority is higher than the current's
- */
- if (running) {
- if (p->prio > oldprio)
- resched_task(rq->curr);
- } else
- check_preempt_curr(rq, p, 0);
+ BUG();
}
static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index c914ec747ca6..db308cb08b75 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -210,11 +210,12 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se);
static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
{
- int this_cpu = smp_processor_id();
struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
struct sched_rt_entity *rt_se;
- rt_se = rt_rq->tg->rt_se[this_cpu];
+ int cpu = cpu_of(rq_of_rt_rq(rt_rq));
+
+ rt_se = rt_rq->tg->rt_se[cpu];
if (rt_rq->rt_nr_running) {
if (rt_se && !on_rt_rq(rt_se))
@@ -226,10 +227,10 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
{
- int this_cpu = smp_processor_id();
struct sched_rt_entity *rt_se;
+ int cpu = cpu_of(rq_of_rt_rq(rt_rq));
- rt_se = rt_rq->tg->rt_se[this_cpu];
+ rt_se = rt_rq->tg->rt_se[cpu];
if (rt_se && on_rt_rq(rt_se))
dequeue_rt_entity(rt_se);
@@ -565,8 +566,11 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
if (rt_rq->rt_time || rt_rq->rt_nr_running)
idle = 0;
raw_spin_unlock(&rt_rq->rt_runtime_lock);
- } else if (rt_rq->rt_nr_running)
+ } else if (rt_rq->rt_nr_running) {
idle = 0;
+ if (!rt_rq_throttled(rt_rq))
+ enqueue = 1;
+ }
if (enqueue)
sched_rt_rq_enqueue(rt_rq);
@@ -625,7 +629,7 @@ static void update_curr_rt(struct rq *rq)
struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
u64 delta_exec;
- if (!task_has_rt_policy(curr))
+ if (curr->sched_class != &rt_sched_class)
return;
delta_exec = rq->clock_task - curr->se.exec_start;
@@ -1595,8 +1599,7 @@ static void rq_offline_rt(struct rq *rq)
* When switch from the rt queue, we bring ourselves to a position
* that we might want to pull RT tasks from other runqueues.
*/
-static void switched_from_rt(struct rq *rq, struct task_struct *p,
- int running)
+static void switched_from_rt(struct rq *rq, struct task_struct *p)
{
/*
* If there are other RT tasks then we will reschedule
@@ -1605,7 +1608,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p,
* we may need to handle the pulling of RT tasks
* now.
*/
- if (!rq->rt.rt_nr_running)
+ if (p->se.on_rq && !rq->rt.rt_nr_running)
pull_rt_task(rq);
}
@@ -1624,8 +1627,7 @@ static inline void init_sched_rt_class(void)
* with RT tasks. In this case we try to push them off to
* other runqueues.
*/
-static void switched_to_rt(struct rq *rq, struct task_struct *p,
- int running)
+static void switched_to_rt(struct rq *rq, struct task_struct *p)
{
int check_resched = 1;
@@ -1636,7 +1638,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p,
* If that current running task is also an RT task
* then see if we can move to another run queue.
*/
- if (!running) {
+ if (p->se.on_rq && rq->curr != p) {
#ifdef CONFIG_SMP
if (rq->rt.overloaded && push_rt_task(rq) &&
/* Don't resched if we changed runqueues */
@@ -1652,10 +1654,13 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p,
* Priority of the task has changed. This may cause
* us to initiate a push or pull.
*/
-static void prio_changed_rt(struct rq *rq, struct task_struct *p,
- int oldprio, int running)
+static void
+prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
{
- if (running) {
+ if (!p->se.on_rq)
+ return;
+
+ if (rq->curr == p) {
#ifdef CONFIG_SMP
/*
* If our priority decreases while running, we
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
index 2bf6b47058c1..84ec9bcf82d9 100644
--- a/kernel/sched_stoptask.c
+++ b/kernel/sched_stoptask.c
@@ -59,14 +59,13 @@ static void set_curr_task_stop(struct rq *rq)
{
}
-static void switched_to_stop(struct rq *rq, struct task_struct *p,
- int running)
+static void switched_to_stop(struct rq *rq, struct task_struct *p)
{
BUG(); /* its impossible to change to this class */
}
-static void prio_changed_stop(struct rq *rq, struct task_struct *p,
- int oldprio, int running)
+static void
+prio_changed_stop(struct rq *rq, struct task_struct *p, int oldprio)
{
BUG(); /* how!?, what priority? */
}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 68eb5efec388..0cee50487629 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -54,7 +54,7 @@ EXPORT_SYMBOL(irq_stat);
static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
+DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
char *softirq_to_name[NR_SOFTIRQS] = {
"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
@@ -721,7 +721,6 @@ static int run_ksoftirqd(void * __bind_cpu)
{
set_current_state(TASK_INTERRUPTIBLE);
- current->flags |= PF_KSOFTIRQD;
while (!kthread_should_stop()) {
preempt_disable();
if (!local_softirq_pending()) {
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index c782fe9924c7..25cc41cd8f33 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -186,3 +186,8 @@ cond_syscall(sys_perf_event_open);
/* fanotify! */
cond_syscall(sys_fanotify_init);
cond_syscall(sys_fanotify_mark);
+
+/* open by handle */
+cond_syscall(sys_name_to_handle_at);
+cond_syscall(sys_open_by_handle_at);
+cond_syscall(compat_sys_open_by_handle_at);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 0f1bd83db985..51054fea5d99 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -194,9 +194,9 @@ static int sysrq_sysctl_handler(ctl_table *table, int write,
static struct ctl_table root_table[];
static struct ctl_table_root sysctl_table_root;
static struct ctl_table_header root_table_header = {
- .count = 1,
+ {{.count = 1,
.ctl_table = root_table,
- .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),
+ .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),}},
.root = &sysctl_table_root,
.set = &sysctl_table_root.default_set,
};
@@ -361,20 +361,13 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.proc_handler = sched_rt_handler,
},
- {
- .procname = "sched_compat_yield",
- .data = &sysctl_sched_compat_yield,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
#ifdef CONFIG_SCHED_AUTOGROUP
{
.procname = "sched_autogroup_enabled",
.data = &sysctl_sched_autogroup_enabled,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
@@ -948,7 +941,7 @@ static struct ctl_table kern_table[] = {
.data = &sysctl_perf_event_sample_rate,
.maxlen = sizeof(sysctl_perf_event_sample_rate),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = perf_proc_update_handler,
},
#endif
#ifdef CONFIG_KMEMCHECK
@@ -1567,11 +1560,16 @@ void sysctl_head_get(struct ctl_table_header *head)
spin_unlock(&sysctl_lock);
}
+static void free_head(struct rcu_head *rcu)
+{
+ kfree(container_of(rcu, struct ctl_table_header, rcu));
+}
+
void sysctl_head_put(struct ctl_table_header *head)
{
spin_lock(&sysctl_lock);
if (!--head->count)
- kfree(head);
+ call_rcu(&head->rcu, free_head);
spin_unlock(&sysctl_lock);
}
@@ -1948,10 +1946,10 @@ void unregister_sysctl_table(struct ctl_table_header * header)
start_unregistering(header);
if (!--header->parent->count) {
WARN_ON(1);
- kfree(header->parent);
+ call_rcu(&header->parent->rcu, free_head);
}
if (!--header->count)
- kfree(header);
+ call_rcu(&header->rcu, free_head);
spin_unlock(&sysctl_lock);
}
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index b875bedf7c9a..3b8e028b9601 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -1321,13 +1321,11 @@ static ssize_t binary_sysctl(const int *name, int nlen,
void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
{
const struct bin_table *table = NULL;
- struct nameidata nd;
struct vfsmount *mnt;
struct file *file;
ssize_t result;
char *pathname;
int flags;
- int acc_mode;
pathname = sysctl_getname(name, nlen, &table);
result = PTR_ERR(pathname);
@@ -1337,28 +1335,17 @@ static ssize_t binary_sysctl(const int *name, int nlen,
/* How should the sysctl be accessed? */
if (oldval && oldlen && newval && newlen) {
flags = O_RDWR;
- acc_mode = MAY_READ | MAY_WRITE;
} else if (newval && newlen) {
flags = O_WRONLY;
- acc_mode = MAY_WRITE;
} else if (oldval && oldlen) {
flags = O_RDONLY;
- acc_mode = MAY_READ;
} else {
result = 0;
goto out_putname;
}
mnt = current->nsproxy->pid_ns->proc_mnt;
- result = vfs_path_lookup(mnt->mnt_root, mnt, pathname, 0, &nd);
- if (result)
- goto out_putname;
-
- result = may_open(&nd.path, acc_mode, flags);
- if (result)
- goto out_putpath;
-
- file = dentry_open(nd.path.dentry, nd.path.mnt, flags, current_cred());
+ file = file_open_root(mnt->mnt_root, mnt, pathname, flags);
result = PTR_ERR(file);
if (IS_ERR(file))
goto out_putname;
@@ -1370,10 +1357,6 @@ out_putname:
putname(pathname);
out:
return result;
-
-out_putpath:
- path_put(&nd.path);
- goto out_putname;
}
diff --git a/kernel/time.c b/kernel/time.c
index 5cb80533d8b5..8e8dc6d705c9 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -645,7 +645,7 @@ u64 nsec_to_clock_t(u64 x)
}
/**
- * nsecs_to_jiffies - Convert nsecs in u64 to jiffies
+ * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64
*
* @n: nsecs in u64
*
@@ -657,7 +657,7 @@ u64 nsec_to_clock_t(u64 x)
* NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
* ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
*/
-unsigned long nsecs_to_jiffies(u64 n)
+u64 nsecs_to_jiffies64(u64 n)
{
#if (NSEC_PER_SEC % HZ) == 0
/* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */
@@ -674,6 +674,24 @@ unsigned long nsecs_to_jiffies(u64 n)
#endif
}
+/**
+ * nsecs_to_jiffies - Convert nsecs in u64 to jiffies
+ *
+ * @n: nsecs in u64
+ *
+ * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64.
+ * And this doesn't return MAX_JIFFY_OFFSET since this function is designed
+ * for scheduler, not for use in device drivers to calculate timeout value.
+ *
+ * note:
+ * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
+ * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
+ */
+unsigned long nsecs_to_jiffies(u64 n)
+{
+ return (unsigned long)nsecs_to_jiffies64(n);
+}
+
/*
* Add two timespec values and do a safety check for overflow.
* It's assumed that both values are valid (>= 0)
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 92ef9a54f0a4..da800ffa810c 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -599,4 +599,14 @@ int tick_broadcast_oneshot_active(void)
return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT;
}
+/*
+ * Check whether the broadcast device supports oneshot.
+ */
+bool tick_broadcast_oneshot_available(void)
+{
+ struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+ return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false;
+}
+
#endif
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 0e98fac3d479..119528de8235 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -50,7 +50,11 @@ int tick_is_oneshot_available(void)
{
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
- return dev && (dev->features & CLOCK_EVT_FEAT_ONESHOT);
+ if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+ return 0;
+ if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
+ return 1;
+ return tick_broadcast_oneshot_available();
}
/*
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index f77b93df0006..1009b06d6f89 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -40,6 +40,7 @@ extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
extern int tick_broadcast_oneshot_active(void);
extern void tick_check_oneshot_broadcast(int cpu);
+bool tick_broadcast_oneshot_available(void);
# else /* BROADCAST */
static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
{
@@ -50,6 +51,7 @@ static inline void tick_broadcast_switch_to_oneshot(void) { }
static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
static inline int tick_broadcast_oneshot_active(void) { return 0; }
static inline void tick_check_oneshot_broadcast(int cpu) { }
+static inline bool tick_broadcast_oneshot_available(void) { return true; }
# endif /* !BROADCAST */
#else /* !ONESHOT */
@@ -80,6 +82,7 @@ static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
return 0;
}
static inline int tick_broadcast_oneshot_active(void) { return 0; }
+static inline bool tick_broadcast_oneshot_available(void) { return false; }
#endif /* !TICK_ONESHOT */
/*
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 32a19f9397fc..3258455549f4 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -41,7 +41,7 @@ static void print_name_offset(struct seq_file *m, void *sym)
char symname[KSYM_NAME_LEN];
if (lookup_symbol_name((unsigned long)sym, symname) < 0)
- SEQ_printf(m, "<%p>", sym);
+ SEQ_printf(m, "<%pK>", sym);
else
SEQ_printf(m, "%s", symname);
}
@@ -112,7 +112,7 @@ next_one:
static void
print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
{
- SEQ_printf(m, " .base: %p\n", base);
+ SEQ_printf(m, " .base: %pK\n", base);
SEQ_printf(m, " .index: %d\n",
base->index);
SEQ_printf(m, " .resolution: %Lu nsecs\n",
diff --git a/kernel/timer.c b/kernel/timer.c
index 87f656cc2a55..fd6198692b57 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -404,6 +404,11 @@ static void timer_stats_account_timer(struct timer_list *timer) {}
static struct debug_obj_descr timer_debug_descr;
+static void *timer_debug_hint(void *addr)
+{
+ return ((struct timer_list *) addr)->function;
+}
+
/*
* fixup_init is called when:
* - an active object is initialized
@@ -477,6 +482,7 @@ static int timer_fixup_free(void *addr, enum debug_obj_state state)
static struct debug_obj_descr timer_debug_descr = {
.name = "timer_list",
+ .debug_hint = timer_debug_hint,
.fixup_init = timer_fixup_init,
.fixup_activate = timer_fixup_activate,
.fixup_free = timer_fixup_free,
@@ -959,20 +965,45 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
*
* Synchronization rules: Callers must prevent restarting of the timer,
* otherwise this function is meaningless. It must not be called from
- * hardirq contexts. The caller must not hold locks which would prevent
+ * interrupt contexts. The caller must not hold locks which would prevent
* completion of the timer's handler. The timer's handler must not call
* add_timer_on(). Upon exit the timer is not queued and the handler is
* not running on any CPU.
*
+ * Note: You must not hold locks that are held in interrupt context
+ * while calling this function. Even if the lock has nothing to do
+ * with the timer in question. Here's why:
+ *
+ * CPU0 CPU1
+ * ---- ----
+ * <SOFTIRQ>
+ * call_timer_fn();
+ * base->running_timer = mytimer;
+ * spin_lock_irq(somelock);
+ * <IRQ>
+ * spin_lock(somelock);
+ * del_timer_sync(mytimer);
+ * while (base->running_timer == mytimer);
+ *
+ * Now del_timer_sync() will never return and never release somelock.
+ * The interrupt on the other CPU is waiting to grab somelock but
+ * it has interrupted the softirq that CPU0 is waiting to finish.
+ *
* The function returns whether it has deactivated a pending timer or not.
*/
int del_timer_sync(struct timer_list *timer)
{
#ifdef CONFIG_LOCKDEP
- local_bh_disable();
+ unsigned long flags;
+
+ /*
+ * If lockdep gives a backtrace here, please reference
+ * the synchronization rules above.
+ */
+ local_irq_save(flags);
lock_map_acquire(&timer->lockdep_map);
lock_map_release(&timer->lockdep_map);
- local_bh_enable();
+ local_irq_restore(flags);
#endif
/*
* don't use it in hardirq context, because it
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 153562d0b93c..cbafed7d4f38 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -138,6 +138,13 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...)
!blk_tracer_enabled))
return;
+ /*
+ * If the BLK_TC_NOTIFY action mask isn't set, don't send any note
+ * message to the trace.
+ */
+ if (!(bt->act_mask & BLK_TC_NOTIFY))
+ return;
+
local_irq_save(flags);
buf = per_cpu_ptr(bt->msg_data, smp_processor_id());
va_start(args, fmt);
@@ -1820,21 +1827,5 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
rwbs[i] = '\0';
}
-void blk_fill_rwbs_rq(char *rwbs, struct request *rq)
-{
- int rw = rq->cmd_flags & 0x03;
- int bytes;
-
- if (rq->cmd_flags & REQ_DISCARD)
- rw |= REQ_DISCARD;
-
- if (rq->cmd_flags & REQ_SECURE)
- rw |= REQ_SECURE;
-
- bytes = blk_rq_bytes(rq);
-
- blk_fill_rwbs(rwbs, rw, bytes);
-}
-
#endif /* CONFIG_EVENT_TRACING */
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f3dadae83883..888b611897d3 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3328,7 +3328,7 @@ static int start_graph_tracing(void)
/* The cpu_boot init_task->ret_stack will never be freed */
for_each_online_cpu(cpu) {
if (!idle_task(cpu)->ret_stack)
- ftrace_graph_init_task(idle_task(cpu));
+ ftrace_graph_init_idle_task(idle_task(cpu), cpu);
}
do {
@@ -3418,6 +3418,49 @@ void unregister_ftrace_graph(void)
mutex_unlock(&ftrace_lock);
}
+static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack);
+
+static void
+graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack)
+{
+ atomic_set(&t->tracing_graph_pause, 0);
+ atomic_set(&t->trace_overrun, 0);
+ t->ftrace_timestamp = 0;
+ /* make curr_ret_stack visable before we add the ret_stack */
+ smp_wmb();
+ t->ret_stack = ret_stack;
+}
+
+/*
+ * Allocate a return stack for the idle task. May be the first
+ * time through, or it may be done by CPU hotplug online.
+ */
+void ftrace_graph_init_idle_task(struct task_struct *t, int cpu)
+{
+ t->curr_ret_stack = -1;
+ /*
+ * The idle task has no parent, it either has its own
+ * stack or no stack at all.
+ */
+ if (t->ret_stack)
+ WARN_ON(t->ret_stack != per_cpu(idle_ret_stack, cpu));
+
+ if (ftrace_graph_active) {
+ struct ftrace_ret_stack *ret_stack;
+
+ ret_stack = per_cpu(idle_ret_stack, cpu);
+ if (!ret_stack) {
+ ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
+ * sizeof(struct ftrace_ret_stack),
+ GFP_KERNEL);
+ if (!ret_stack)
+ return;
+ per_cpu(idle_ret_stack, cpu) = ret_stack;
+ }
+ graph_init_task(t, ret_stack);
+ }
+}
+
/* Allocate a return stack for newly created task */
void ftrace_graph_init_task(struct task_struct *t)
{
@@ -3433,12 +3476,7 @@ void ftrace_graph_init_task(struct task_struct *t)
GFP_KERNEL);
if (!ret_stack)
return;
- atomic_set(&t->tracing_graph_pause, 0);
- atomic_set(&t->trace_overrun, 0);
- t->ftrace_timestamp = 0;
- /* make curr_ret_stack visable before we add the ret_stack */
- smp_wmb();
- t->ret_stack = ret_stack;
+ graph_init_task(t, ret_stack);
}
}
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index bd1c35a4fbcc..db7b439d23ee 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5,7 +5,6 @@
*/
#include <linux/ring_buffer.h>
#include <linux/trace_clock.h>
-#include <linux/ftrace_irq.h>
#include <linux/spinlock.h>
#include <linux/debugfs.h>
#include <linux/uaccess.h>
@@ -1429,6 +1428,17 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
}
EXPORT_SYMBOL_GPL(ring_buffer_resize);
+void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val)
+{
+ mutex_lock(&buffer->mutex);
+ if (val)
+ buffer->flags |= RB_FL_OVERWRITE;
+ else
+ buffer->flags &= ~RB_FL_OVERWRITE;
+ mutex_unlock(&buffer->mutex);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite);
+
static inline void *
__rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
{
@@ -2162,11 +2172,19 @@ rb_reserve_next_event(struct ring_buffer *buffer,
if (likely(ts >= cpu_buffer->write_stamp)) {
delta = diff;
if (unlikely(test_time_stamp(delta))) {
+ int local_clock_stable = 1;
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+ local_clock_stable = sched_clock_stable;
+#endif
WARN_ONCE(delta > (1ULL << 59),
- KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n",
+ KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s",
(unsigned long long)delta,
(unsigned long long)ts,
- (unsigned long long)cpu_buffer->write_stamp);
+ (unsigned long long)cpu_buffer->write_stamp,
+ local_clock_stable ? "" :
+ "If you just came from a suspend/resume,\n"
+ "please switch to the trace global clock:\n"
+ " echo global > /sys/kernel/debug/tracing/trace_clock\n");
add_timestamp = 1;
}
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dc53ecb80589..9541c27c1cf2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -41,8 +41,6 @@
#include "trace.h"
#include "trace_output.h"
-#define TRACE_BUFFER_FLAGS (RB_FL_OVERWRITE)
-
/*
* On boot up, the ring buffer is set to the minimum size, so that
* we do not waste memory on systems that are not using tracing.
@@ -340,7 +338,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
/* trace_flags holds trace_options default values */
unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
- TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD;
+ TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE;
static int trace_stop_count;
static DEFINE_SPINLOCK(tracing_start_lock);
@@ -425,6 +423,7 @@ static const char *trace_options[] = {
"sleep-time",
"graph-time",
"record-cmd",
+ "overwrite",
NULL
};
@@ -780,6 +779,11 @@ __acquires(kernel_lock)
tracing_reset_online_cpus(tr);
current_trace = type;
+
+ /* If we expanded the buffers, make sure the max is expanded too */
+ if (ring_buffer_expanded && type->use_max_tr)
+ ring_buffer_resize(max_tr.buffer, trace_buf_size);
+
/* the test is responsible for initializing and enabling */
pr_info("Testing tracer %s: ", type->name);
ret = type->selftest(type, tr);
@@ -792,6 +796,10 @@ __acquires(kernel_lock)
/* Only reset on passing, to avoid touching corrupted buffers */
tracing_reset_online_cpus(tr);
+ /* Shrink the max buffer again */
+ if (ring_buffer_expanded && type->use_max_tr)
+ ring_buffer_resize(max_tr.buffer, 1);
+
printk(KERN_CONT "PASSED\n");
}
#endif
@@ -1102,7 +1110,6 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
entry->preempt_count = pc & 0xff;
entry->pid = (tsk) ? tsk->pid : 0;
- entry->lock_depth = (tsk) ? tsk->lock_depth : 0;
entry->flags =
#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
@@ -1749,10 +1756,9 @@ static void print_lat_help_header(struct seq_file *m)
seq_puts(m, "# | / _----=> need-resched \n");
seq_puts(m, "# || / _---=> hardirq/softirq \n");
seq_puts(m, "# ||| / _--=> preempt-depth \n");
- seq_puts(m, "# |||| /_--=> lock-depth \n");
- seq_puts(m, "# |||||/ delay \n");
- seq_puts(m, "# cmd pid |||||| time | caller \n");
- seq_puts(m, "# \\ / |||||| \\ | / \n");
+ seq_puts(m, "# |||| / delay \n");
+ seq_puts(m, "# cmd pid ||||| time | caller \n");
+ seq_puts(m, "# \\ / ||||| \\ | / \n");
}
static void print_func_help_header(struct seq_file *m)
@@ -2529,6 +2535,9 @@ static void set_tracer_flags(unsigned int mask, int enabled)
if (mask == TRACE_ITER_RECORD_CMD)
trace_event_enable_cmd_record(enabled);
+
+ if (mask == TRACE_ITER_OVERWRITE)
+ ring_buffer_change_overwrite(global_trace.buffer, enabled);
}
static ssize_t
@@ -2710,6 +2719,10 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf,
mutex_lock(&trace_types_lock);
if (tracer_enabled ^ val) {
+
+ /* Only need to warn if this is used to change the state */
+ WARN_ONCE(1, "tracing_enabled is deprecated. Use tracing_on");
+
if (val) {
tracer_enabled = 1;
if (current_trace->start)
@@ -4551,9 +4564,11 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
__init static int tracer_alloc_buffers(void)
{
int ring_buf_size;
+ enum ring_buffer_flags rb_flags;
int i;
int ret = -ENOMEM;
+
if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL))
goto out;
@@ -4566,12 +4581,13 @@ __init static int tracer_alloc_buffers(void)
else
ring_buf_size = 1;
+ rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
+
cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
cpumask_copy(tracing_cpumask, cpu_all_mask);
/* TODO: make the number of buffers hot pluggable with CPUS */
- global_trace.buffer = ring_buffer_alloc(ring_buf_size,
- TRACE_BUFFER_FLAGS);
+ global_trace.buffer = ring_buffer_alloc(ring_buf_size, rb_flags);
if (!global_trace.buffer) {
printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
WARN_ON(1);
@@ -4581,7 +4597,7 @@ __init static int tracer_alloc_buffers(void)
#ifdef CONFIG_TRACER_MAX_TRACE
- max_tr.buffer = ring_buffer_alloc(1, TRACE_BUFFER_FLAGS);
+ max_tr.buffer = ring_buffer_alloc(1, rb_flags);
if (!max_tr.buffer) {
printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
WARN_ON(1);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 9021f8c0c0c3..5e9dfc6286dd 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -272,8 +272,8 @@ struct tracer {
/* If you handled the flag setting, return 0 */
int (*set_flag)(u32 old_flags, u32 bit, int set);
struct tracer *next;
- int print_max;
struct tracer_flags *flags;
+ int print_max;
int use_max_tr;
};
@@ -606,6 +606,7 @@ enum trace_iterator_flags {
TRACE_ITER_SLEEP_TIME = 0x40000,
TRACE_ITER_GRAPH_TIME = 0x80000,
TRACE_ITER_RECORD_CMD = 0x100000,
+ TRACE_ITER_OVERWRITE = 0x200000,
};
/*
@@ -661,8 +662,10 @@ struct ftrace_event_field {
};
struct event_filter {
- int n_preds;
- struct filter_pred **preds;
+ int n_preds; /* Number assigned */
+ int a_preds; /* allocated */
+ struct filter_pred *preds;
+ struct filter_pred *root;
char *filter_string;
};
@@ -674,11 +677,23 @@ struct event_subsystem {
int nr_events;
};
+#define FILTER_PRED_INVALID ((unsigned short)-1)
+#define FILTER_PRED_IS_RIGHT (1 << 15)
+#define FILTER_PRED_FOLD (1 << 15)
+
+/*
+ * The max preds is the size of unsigned short with
+ * two flags at the MSBs. One bit is used for both the IS_RIGHT
+ * and FOLD flags. The other is reserved.
+ *
+ * 2^14 preds is way more than enough.
+ */
+#define MAX_FILTER_PRED 16384
+
struct filter_pred;
struct regex;
-typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
- int val1, int val2);
+typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
typedef int (*regex_match_func)(char *str, struct regex *r, int len);
@@ -700,11 +715,23 @@ struct filter_pred {
filter_pred_fn_t fn;
u64 val;
struct regex regex;
- char *field_name;
+ /*
+ * Leaf nodes use field_name, ops is used by AND and OR
+ * nodes. The field_name is always freed when freeing a pred.
+ * We can overload field_name for ops and have it freed
+ * as well.
+ */
+ union {
+ char *field_name;
+ unsigned short *ops;
+ };
int offset;
int not;
int op;
- int pop_n;
+ unsigned short index;
+ unsigned short parent;
+ unsigned short left;
+ unsigned short right;
};
extern struct list_head ftrace_common_fields;
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 6cf223764be8..1516cb3ec549 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -109,12 +109,12 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
*/
#define FTRACE_CTX_FIELDS \
__field( unsigned int, prev_pid ) \
+ __field( unsigned int, next_pid ) \
+ __field( unsigned int, next_cpu ) \
__field( unsigned char, prev_prio ) \
__field( unsigned char, prev_state ) \
- __field( unsigned int, next_pid ) \
__field( unsigned char, next_prio ) \
- __field( unsigned char, next_state ) \
- __field( unsigned int, next_cpu )
+ __field( unsigned char, next_state )
FTRACE_ENTRY(context_switch, ctx_switch_entry,
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 35fde09b81de..e88f74fe1d4c 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -116,7 +116,6 @@ static int trace_define_common_fields(void)
__common_field(unsigned char, flags);
__common_field(unsigned char, preempt_count);
__common_field(int, pid);
- __common_field(int, lock_depth);
return ret;
}
@@ -326,6 +325,7 @@ int trace_set_clr_event(const char *system, const char *event, int set)
{
return __ftrace_set_clr_event(NULL, system, event, set);
}
+EXPORT_SYMBOL_GPL(trace_set_clr_event);
/* 128 should be much more than enough */
#define EVENT_BUF_SIZE 127
@@ -1284,7 +1284,7 @@ trace_create_file_ops(struct module *mod)
static void trace_module_add_events(struct module *mod)
{
struct ftrace_module_file_ops *file_ops = NULL;
- struct ftrace_event_call *call, *start, *end;
+ struct ftrace_event_call **call, **start, **end;
start = mod->trace_events;
end = mod->trace_events + mod->num_trace_events;
@@ -1297,7 +1297,7 @@ static void trace_module_add_events(struct module *mod)
return;
for_each_event(call, start, end) {
- __trace_add_event_call(call, mod,
+ __trace_add_event_call(*call, mod,
&file_ops->id, &file_ops->enable,
&file_ops->filter, &file_ops->format);
}
@@ -1367,8 +1367,8 @@ static struct notifier_block trace_module_nb = {
.priority = 0,
};
-extern struct ftrace_event_call __start_ftrace_events[];
-extern struct ftrace_event_call __stop_ftrace_events[];
+extern struct ftrace_event_call *__start_ftrace_events[];
+extern struct ftrace_event_call *__stop_ftrace_events[];
static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
@@ -1384,7 +1384,7 @@ __setup("trace_event=", setup_trace_event);
static __init int event_trace_init(void)
{
- struct ftrace_event_call *call;
+ struct ftrace_event_call **call;
struct dentry *d_tracer;
struct dentry *entry;
struct dentry *d_events;
@@ -1430,7 +1430,7 @@ static __init int event_trace_init(void)
pr_warning("tracing: Failed to allocate common fields");
for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
- __trace_add_event_call(call, NULL, &ftrace_event_id_fops,
+ __trace_add_event_call(*call, NULL, &ftrace_event_id_fops,
&ftrace_enable_fops,
&ftrace_event_filter_fops,
&ftrace_event_format_fops);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 36d40104b17f..3249b4f77ef0 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -123,9 +123,13 @@ struct filter_parse_state {
} operand;
};
+struct pred_stack {
+ struct filter_pred **preds;
+ int index;
+};
+
#define DEFINE_COMPARISON_PRED(type) \
-static int filter_pred_##type(struct filter_pred *pred, void *event, \
- int val1, int val2) \
+static int filter_pred_##type(struct filter_pred *pred, void *event) \
{ \
type *addr = (type *)(event + pred->offset); \
type val = (type)pred->val; \
@@ -152,8 +156,7 @@ static int filter_pred_##type(struct filter_pred *pred, void *event, \
}
#define DEFINE_EQUALITY_PRED(size) \
-static int filter_pred_##size(struct filter_pred *pred, void *event, \
- int val1, int val2) \
+static int filter_pred_##size(struct filter_pred *pred, void *event) \
{ \
u##size *addr = (u##size *)(event + pred->offset); \
u##size val = (u##size)pred->val; \
@@ -178,23 +181,8 @@ DEFINE_EQUALITY_PRED(32);
DEFINE_EQUALITY_PRED(16);
DEFINE_EQUALITY_PRED(8);
-static int filter_pred_and(struct filter_pred *pred __attribute((unused)),
- void *event __attribute((unused)),
- int val1, int val2)
-{
- return val1 && val2;
-}
-
-static int filter_pred_or(struct filter_pred *pred __attribute((unused)),
- void *event __attribute((unused)),
- int val1, int val2)
-{
- return val1 || val2;
-}
-
/* Filter predicate for fixed sized arrays of characters */
-static int filter_pred_string(struct filter_pred *pred, void *event,
- int val1, int val2)
+static int filter_pred_string(struct filter_pred *pred, void *event)
{
char *addr = (char *)(event + pred->offset);
int cmp, match;
@@ -207,8 +195,7 @@ static int filter_pred_string(struct filter_pred *pred, void *event,
}
/* Filter predicate for char * pointers */
-static int filter_pred_pchar(struct filter_pred *pred, void *event,
- int val1, int val2)
+static int filter_pred_pchar(struct filter_pred *pred, void *event)
{
char **addr = (char **)(event + pred->offset);
int cmp, match;
@@ -231,8 +218,7 @@ static int filter_pred_pchar(struct filter_pred *pred, void *event,
* and add it to the address of the entry, and at last we have
* the address of the string.
*/
-static int filter_pred_strloc(struct filter_pred *pred, void *event,
- int val1, int val2)
+static int filter_pred_strloc(struct filter_pred *pred, void *event)
{
u32 str_item = *(u32 *)(event + pred->offset);
int str_loc = str_item & 0xffff;
@@ -247,8 +233,7 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event,
return match;
}
-static int filter_pred_none(struct filter_pred *pred, void *event,
- int val1, int val2)
+static int filter_pred_none(struct filter_pred *pred, void *event)
{
return 0;
}
@@ -377,32 +362,147 @@ static void filter_build_regex(struct filter_pred *pred)
pred->not ^= not;
}
+enum move_type {
+ MOVE_DOWN,
+ MOVE_UP_FROM_LEFT,
+ MOVE_UP_FROM_RIGHT
+};
+
+static struct filter_pred *
+get_pred_parent(struct filter_pred *pred, struct filter_pred *preds,
+ int index, enum move_type *move)
+{
+ if (pred->parent & FILTER_PRED_IS_RIGHT)
+ *move = MOVE_UP_FROM_RIGHT;
+ else
+ *move = MOVE_UP_FROM_LEFT;
+ pred = &preds[pred->parent & ~FILTER_PRED_IS_RIGHT];
+
+ return pred;
+}
+
+/*
+ * A series of AND or ORs where found together. Instead of
+ * climbing up and down the tree branches, an array of the
+ * ops were made in order of checks. We can just move across
+ * the array and short circuit if needed.
+ */
+static int process_ops(struct filter_pred *preds,
+ struct filter_pred *op, void *rec)
+{
+ struct filter_pred *pred;
+ int type;
+ int match;
+ int i;
+
+ /*
+ * Micro-optimization: We set type to true if op
+ * is an OR and false otherwise (AND). Then we
+ * just need to test if the match is equal to
+ * the type, and if it is, we can short circuit the
+ * rest of the checks:
+ *
+ * if ((match && op->op == OP_OR) ||
+ * (!match && op->op == OP_AND))
+ * return match;
+ */
+ type = op->op == OP_OR;
+
+ for (i = 0; i < op->val; i++) {
+ pred = &preds[op->ops[i]];
+ match = pred->fn(pred, rec);
+ if (!!match == type)
+ return match;
+ }
+ return match;
+}
+
/* return 1 if event matches, 0 otherwise (discard) */
int filter_match_preds(struct event_filter *filter, void *rec)
{
- int match, top = 0, val1 = 0, val2 = 0;
- int stack[MAX_FILTER_PRED];
+ int match = -1;
+ enum move_type move = MOVE_DOWN;
+ struct filter_pred *preds;
struct filter_pred *pred;
- int i;
+ struct filter_pred *root;
+ int n_preds;
+ int done = 0;
+
+ /* no filter is considered a match */
+ if (!filter)
+ return 1;
+
+ n_preds = filter->n_preds;
+
+ if (!n_preds)
+ return 1;
+
+ /*
+ * n_preds, root and filter->preds are protect with preemption disabled.
+ */
+ preds = rcu_dereference_sched(filter->preds);
+ root = rcu_dereference_sched(filter->root);
+ if (!root)
+ return 1;
+
+ pred = root;
- for (i = 0; i < filter->n_preds; i++) {
- pred = filter->preds[i];
- if (!pred->pop_n) {
- match = pred->fn(pred, rec, val1, val2);
- stack[top++] = match;
+ /* match is currently meaningless */
+ match = -1;
+
+ do {
+ switch (move) {
+ case MOVE_DOWN:
+ /* only AND and OR have children */
+ if (pred->left != FILTER_PRED_INVALID) {
+ /* If ops is set, then it was folded. */
+ if (!pred->ops) {
+ /* keep going to down the left side */
+ pred = &preds[pred->left];
+ continue;
+ }
+ /* We can treat folded ops as a leaf node */
+ match = process_ops(preds, pred, rec);
+ } else
+ match = pred->fn(pred, rec);
+ /* If this pred is the only pred */
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ case MOVE_UP_FROM_LEFT:
+ /*
+ * Check for short circuits.
+ *
+ * Optimization: !!match == (pred->op == OP_OR)
+ * is the same as:
+ * if ((match && pred->op == OP_OR) ||
+ * (!match && pred->op == OP_AND))
+ */
+ if (!!match == (pred->op == OP_OR)) {
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ }
+ /* now go down the right side of the tree. */
+ pred = &preds[pred->right];
+ move = MOVE_DOWN;
+ continue;
+ case MOVE_UP_FROM_RIGHT:
+ /* We finished this equation. */
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
continue;
}
- if (pred->pop_n > top) {
- WARN_ON_ONCE(1);
- return 0;
- }
- val1 = stack[--top];
- val2 = stack[--top];
- match = pred->fn(pred, rec, val1, val2);
- stack[top++] = match;
- }
+ done = 1;
+ } while (!done);
- return stack[--top];
+ return match;
}
EXPORT_SYMBOL_GPL(filter_match_preds);
@@ -414,6 +514,9 @@ static void parse_error(struct filter_parse_state *ps, int err, int pos)
static void remove_filter_string(struct event_filter *filter)
{
+ if (!filter)
+ return;
+
kfree(filter->filter_string);
filter->filter_string = NULL;
}
@@ -473,9 +576,10 @@ static void append_filter_err(struct filter_parse_state *ps,
void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
{
- struct event_filter *filter = call->filter;
+ struct event_filter *filter;
mutex_lock(&event_mutex);
+ filter = call->filter;
if (filter && filter->filter_string)
trace_seq_printf(s, "%s\n", filter->filter_string);
else
@@ -486,9 +590,10 @@ void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
void print_subsystem_event_filter(struct event_subsystem *system,
struct trace_seq *s)
{
- struct event_filter *filter = system->filter;
+ struct event_filter *filter;
mutex_lock(&event_mutex);
+ filter = system->filter;
if (filter && filter->filter_string)
trace_seq_printf(s, "%s\n", filter->filter_string);
else
@@ -539,10 +644,58 @@ static void filter_clear_pred(struct filter_pred *pred)
pred->regex.len = 0;
}
-static int filter_set_pred(struct filter_pred *dest,
+static int __alloc_pred_stack(struct pred_stack *stack, int n_preds)
+{
+ stack->preds = kzalloc(sizeof(*stack->preds)*(n_preds + 1), GFP_KERNEL);
+ if (!stack->preds)
+ return -ENOMEM;
+ stack->index = n_preds;
+ return 0;
+}
+
+static void __free_pred_stack(struct pred_stack *stack)
+{
+ kfree(stack->preds);
+ stack->index = 0;
+}
+
+static int __push_pred_stack(struct pred_stack *stack,
+ struct filter_pred *pred)
+{
+ int index = stack->index;
+
+ if (WARN_ON(index == 0))
+ return -ENOSPC;
+
+ stack->preds[--index] = pred;
+ stack->index = index;
+ return 0;
+}
+
+static struct filter_pred *
+__pop_pred_stack(struct pred_stack *stack)
+{
+ struct filter_pred *pred;
+ int index = stack->index;
+
+ pred = stack->preds[index++];
+ if (!pred)
+ return NULL;
+
+ stack->index = index;
+ return pred;
+}
+
+static int filter_set_pred(struct event_filter *filter,
+ int idx,
+ struct pred_stack *stack,
struct filter_pred *src,
filter_pred_fn_t fn)
{
+ struct filter_pred *dest = &filter->preds[idx];
+ struct filter_pred *left;
+ struct filter_pred *right;
+
*dest = *src;
if (src->field_name) {
dest->field_name = kstrdup(src->field_name, GFP_KERNEL);
@@ -550,116 +703,140 @@ static int filter_set_pred(struct filter_pred *dest,
return -ENOMEM;
}
dest->fn = fn;
+ dest->index = idx;
- return 0;
+ if (dest->op == OP_OR || dest->op == OP_AND) {
+ right = __pop_pred_stack(stack);
+ left = __pop_pred_stack(stack);
+ if (!left || !right)
+ return -EINVAL;
+ /*
+ * If both children can be folded
+ * and they are the same op as this op or a leaf,
+ * then this op can be folded.
+ */
+ if (left->index & FILTER_PRED_FOLD &&
+ (left->op == dest->op ||
+ left->left == FILTER_PRED_INVALID) &&
+ right->index & FILTER_PRED_FOLD &&
+ (right->op == dest->op ||
+ right->left == FILTER_PRED_INVALID))
+ dest->index |= FILTER_PRED_FOLD;
+
+ dest->left = left->index & ~FILTER_PRED_FOLD;
+ dest->right = right->index & ~FILTER_PRED_FOLD;
+ left->parent = dest->index & ~FILTER_PRED_FOLD;
+ right->parent = dest->index | FILTER_PRED_IS_RIGHT;
+ } else {
+ /*
+ * Make dest->left invalid to be used as a quick
+ * way to know this is a leaf node.
+ */
+ dest->left = FILTER_PRED_INVALID;
+
+ /* All leafs allow folding the parent ops. */
+ dest->index |= FILTER_PRED_FOLD;
+ }
+
+ return __push_pred_stack(stack, dest);
}
-static void filter_disable_preds(struct ftrace_event_call *call)
+static void __free_preds(struct event_filter *filter)
{
- struct event_filter *filter = call->filter;
int i;
- call->flags &= ~TRACE_EVENT_FL_FILTERED;
+ if (filter->preds) {
+ for (i = 0; i < filter->a_preds; i++)
+ kfree(filter->preds[i].field_name);
+ kfree(filter->preds);
+ filter->preds = NULL;
+ }
+ filter->a_preds = 0;
filter->n_preds = 0;
-
- for (i = 0; i < MAX_FILTER_PRED; i++)
- filter->preds[i]->fn = filter_pred_none;
}
-static void __free_preds(struct event_filter *filter)
+static void filter_disable(struct ftrace_event_call *call)
{
- int i;
+ call->flags &= ~TRACE_EVENT_FL_FILTERED;
+}
+static void __free_filter(struct event_filter *filter)
+{
if (!filter)
return;
- for (i = 0; i < MAX_FILTER_PRED; i++) {
- if (filter->preds[i])
- filter_free_pred(filter->preds[i]);
- }
- kfree(filter->preds);
+ __free_preds(filter);
kfree(filter->filter_string);
kfree(filter);
}
+/*
+ * Called when destroying the ftrace_event_call.
+ * The call is being freed, so we do not need to worry about
+ * the call being currently used. This is for module code removing
+ * the tracepoints from within it.
+ */
void destroy_preds(struct ftrace_event_call *call)
{
- __free_preds(call->filter);
+ __free_filter(call->filter);
call->filter = NULL;
- call->flags &= ~TRACE_EVENT_FL_FILTERED;
}
-static struct event_filter *__alloc_preds(void)
+static struct event_filter *__alloc_filter(void)
{
struct event_filter *filter;
+
+ filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+ return filter;
+}
+
+static int __alloc_preds(struct event_filter *filter, int n_preds)
+{
struct filter_pred *pred;
int i;
- filter = kzalloc(sizeof(*filter), GFP_KERNEL);
- if (!filter)
- return ERR_PTR(-ENOMEM);
+ if (filter->preds)
+ __free_preds(filter);
- filter->n_preds = 0;
+ filter->preds =
+ kzalloc(sizeof(*filter->preds) * n_preds, GFP_KERNEL);
- filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), GFP_KERNEL);
if (!filter->preds)
- goto oom;
+ return -ENOMEM;
- for (i = 0; i < MAX_FILTER_PRED; i++) {
- pred = kzalloc(sizeof(*pred), GFP_KERNEL);
- if (!pred)
- goto oom;
+ filter->a_preds = n_preds;
+ filter->n_preds = 0;
+
+ for (i = 0; i < n_preds; i++) {
+ pred = &filter->preds[i];
pred->fn = filter_pred_none;
- filter->preds[i] = pred;
}
- return filter;
-
-oom:
- __free_preds(filter);
- return ERR_PTR(-ENOMEM);
-}
-
-static int init_preds(struct ftrace_event_call *call)
-{
- if (call->filter)
- return 0;
-
- call->flags &= ~TRACE_EVENT_FL_FILTERED;
- call->filter = __alloc_preds();
- if (IS_ERR(call->filter))
- return PTR_ERR(call->filter);
-
return 0;
}
-static int init_subsystem_preds(struct event_subsystem *system)
+static void filter_free_subsystem_preds(struct event_subsystem *system)
{
struct ftrace_event_call *call;
- int err;
list_for_each_entry(call, &ftrace_events, list) {
if (strcmp(call->class->system, system->name) != 0)
continue;
- err = init_preds(call);
- if (err)
- return err;
+ filter_disable(call);
+ remove_filter_string(call->filter);
}
-
- return 0;
}
-static void filter_free_subsystem_preds(struct event_subsystem *system)
+static void filter_free_subsystem_filters(struct event_subsystem *system)
{
struct ftrace_event_call *call;
list_for_each_entry(call, &ftrace_events, list) {
if (strcmp(call->class->system, system->name) != 0)
continue;
-
- filter_disable_preds(call);
- remove_filter_string(call->filter);
+ __free_filter(call->filter);
+ call->filter = NULL;
}
}
@@ -667,18 +844,19 @@ static int filter_add_pred_fn(struct filter_parse_state *ps,
struct ftrace_event_call *call,
struct event_filter *filter,
struct filter_pred *pred,
+ struct pred_stack *stack,
filter_pred_fn_t fn)
{
int idx, err;
- if (filter->n_preds == MAX_FILTER_PRED) {
+ if (WARN_ON(filter->n_preds == filter->a_preds)) {
parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
return -ENOSPC;
}
idx = filter->n_preds;
- filter_clear_pred(filter->preds[idx]);
- err = filter_set_pred(filter->preds[idx], pred, fn);
+ filter_clear_pred(&filter->preds[idx]);
+ err = filter_set_pred(filter, idx, stack, pred, fn);
if (err)
return err;
@@ -763,6 +941,7 @@ static int filter_add_pred(struct filter_parse_state *ps,
struct ftrace_event_call *call,
struct event_filter *filter,
struct filter_pred *pred,
+ struct pred_stack *stack,
bool dry_run)
{
struct ftrace_event_field *field;
@@ -770,17 +949,12 @@ static int filter_add_pred(struct filter_parse_state *ps,
unsigned long long val;
int ret;
- pred->fn = filter_pred_none;
+ fn = pred->fn = filter_pred_none;
- if (pred->op == OP_AND) {
- pred->pop_n = 2;
- fn = filter_pred_and;
+ if (pred->op == OP_AND)
goto add_pred_fn;
- } else if (pred->op == OP_OR) {
- pred->pop_n = 2;
- fn = filter_pred_or;
+ else if (pred->op == OP_OR)
goto add_pred_fn;
- }
field = find_event_field(call, pred->field_name);
if (!field) {
@@ -829,7 +1003,7 @@ static int filter_add_pred(struct filter_parse_state *ps,
add_pred_fn:
if (!dry_run)
- return filter_add_pred_fn(ps, call, filter, pred, fn);
+ return filter_add_pred_fn(ps, call, filter, pred, stack, fn);
return 0;
}
@@ -1187,6 +1361,234 @@ static int check_preds(struct filter_parse_state *ps)
return 0;
}
+static int count_preds(struct filter_parse_state *ps)
+{
+ struct postfix_elt *elt;
+ int n_preds = 0;
+
+ list_for_each_entry(elt, &ps->postfix, list) {
+ if (elt->op == OP_NONE)
+ continue;
+ n_preds++;
+ }
+
+ return n_preds;
+}
+
+/*
+ * The tree is walked at filtering of an event. If the tree is not correctly
+ * built, it may cause an infinite loop. Check here that the tree does
+ * indeed terminate.
+ */
+static int check_pred_tree(struct event_filter *filter,
+ struct filter_pred *root)
+{
+ struct filter_pred *preds;
+ struct filter_pred *pred;
+ enum move_type move = MOVE_DOWN;
+ int count = 0;
+ int done = 0;
+ int max;
+
+ /*
+ * The max that we can hit a node is three times.
+ * Once going down, once coming up from left, and
+ * once coming up from right. This is more than enough
+ * since leafs are only hit a single time.
+ */
+ max = 3 * filter->n_preds;
+
+ preds = filter->preds;
+ if (!preds)
+ return -EINVAL;
+ pred = root;
+
+ do {
+ if (WARN_ON(count++ > max))
+ return -EINVAL;
+
+ switch (move) {
+ case MOVE_DOWN:
+ if (pred->left != FILTER_PRED_INVALID) {
+ pred = &preds[pred->left];
+ continue;
+ }
+ /* A leaf at the root is just a leaf in the tree */
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ case MOVE_UP_FROM_LEFT:
+ pred = &preds[pred->right];
+ move = MOVE_DOWN;
+ continue;
+ case MOVE_UP_FROM_RIGHT:
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ }
+ done = 1;
+ } while (!done);
+
+ /* We are fine. */
+ return 0;
+}
+
+static int count_leafs(struct filter_pred *preds, struct filter_pred *root)
+{
+ struct filter_pred *pred;
+ enum move_type move = MOVE_DOWN;
+ int count = 0;
+ int done = 0;
+
+ pred = root;
+
+ do {
+ switch (move) {
+ case MOVE_DOWN:
+ if (pred->left != FILTER_PRED_INVALID) {
+ pred = &preds[pred->left];
+ continue;
+ }
+ /* A leaf at the root is just a leaf in the tree */
+ if (pred == root)
+ return 1;
+ count++;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ case MOVE_UP_FROM_LEFT:
+ pred = &preds[pred->right];
+ move = MOVE_DOWN;
+ continue;
+ case MOVE_UP_FROM_RIGHT:
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ }
+ done = 1;
+ } while (!done);
+
+ return count;
+}
+
+static int fold_pred(struct filter_pred *preds, struct filter_pred *root)
+{
+ struct filter_pred *pred;
+ enum move_type move = MOVE_DOWN;
+ int count = 0;
+ int children;
+ int done = 0;
+
+ /* No need to keep the fold flag */
+ root->index &= ~FILTER_PRED_FOLD;
+
+ /* If the root is a leaf then do nothing */
+ if (root->left == FILTER_PRED_INVALID)
+ return 0;
+
+ /* count the children */
+ children = count_leafs(preds, &preds[root->left]);
+ children += count_leafs(preds, &preds[root->right]);
+
+ root->ops = kzalloc(sizeof(*root->ops) * children, GFP_KERNEL);
+ if (!root->ops)
+ return -ENOMEM;
+
+ root->val = children;
+
+ pred = root;
+ do {
+ switch (move) {
+ case MOVE_DOWN:
+ if (pred->left != FILTER_PRED_INVALID) {
+ pred = &preds[pred->left];
+ continue;
+ }
+ if (WARN_ON(count == children))
+ return -EINVAL;
+ pred->index &= ~FILTER_PRED_FOLD;
+ root->ops[count++] = pred->index;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ case MOVE_UP_FROM_LEFT:
+ pred = &preds[pred->right];
+ move = MOVE_DOWN;
+ continue;
+ case MOVE_UP_FROM_RIGHT:
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ }
+ done = 1;
+ } while (!done);
+
+ return 0;
+}
+
+/*
+ * To optimize the processing of the ops, if we have several "ors" or
+ * "ands" together, we can put them in an array and process them all
+ * together speeding up the filter logic.
+ */
+static int fold_pred_tree(struct event_filter *filter,
+ struct filter_pred *root)
+{
+ struct filter_pred *preds;
+ struct filter_pred *pred;
+ enum move_type move = MOVE_DOWN;
+ int done = 0;
+ int err;
+
+ preds = filter->preds;
+ if (!preds)
+ return -EINVAL;
+ pred = root;
+
+ do {
+ switch (move) {
+ case MOVE_DOWN:
+ if (pred->index & FILTER_PRED_FOLD) {
+ err = fold_pred(preds, pred);
+ if (err)
+ return err;
+ /* Folded nodes are like leafs */
+ } else if (pred->left != FILTER_PRED_INVALID) {
+ pred = &preds[pred->left];
+ continue;
+ }
+
+ /* A leaf at the root is just a leaf in the tree */
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ case MOVE_UP_FROM_LEFT:
+ pred = &preds[pred->right];
+ move = MOVE_DOWN;
+ continue;
+ case MOVE_UP_FROM_RIGHT:
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ }
+ done = 1;
+ } while (!done);
+
+ return 0;
+}
+
static int replace_preds(struct ftrace_event_call *call,
struct event_filter *filter,
struct filter_parse_state *ps,
@@ -1195,14 +1597,32 @@ static int replace_preds(struct ftrace_event_call *call,
{
char *operand1 = NULL, *operand2 = NULL;
struct filter_pred *pred;
+ struct filter_pred *root;
struct postfix_elt *elt;
+ struct pred_stack stack = { }; /* init to NULL */
int err;
int n_preds = 0;
+ n_preds = count_preds(ps);
+ if (n_preds >= MAX_FILTER_PRED) {
+ parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+ return -ENOSPC;
+ }
+
err = check_preds(ps);
if (err)
return err;
+ if (!dry_run) {
+ err = __alloc_pred_stack(&stack, n_preds);
+ if (err)
+ return err;
+ err = __alloc_preds(filter, n_preds);
+ if (err)
+ goto fail;
+ }
+
+ n_preds = 0;
list_for_each_entry(elt, &ps->postfix, list) {
if (elt->op == OP_NONE) {
if (!operand1)
@@ -1211,14 +1631,16 @@ static int replace_preds(struct ftrace_event_call *call,
operand2 = elt->operand;
else {
parse_error(ps, FILT_ERR_TOO_MANY_OPERANDS, 0);
- return -EINVAL;
+ err = -EINVAL;
+ goto fail;
}
continue;
}
- if (n_preds++ == MAX_FILTER_PRED) {
+ if (WARN_ON(n_preds++ == MAX_FILTER_PRED)) {
parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
- return -ENOSPC;
+ err = -ENOSPC;
+ goto fail;
}
if (elt->op == OP_AND || elt->op == OP_OR) {
@@ -1228,76 +1650,181 @@ static int replace_preds(struct ftrace_event_call *call,
if (!operand1 || !operand2) {
parse_error(ps, FILT_ERR_MISSING_FIELD, 0);
- return -EINVAL;
+ err = -EINVAL;
+ goto fail;
}
pred = create_pred(elt->op, operand1, operand2);
add_pred:
- if (!pred)
- return -ENOMEM;
- err = filter_add_pred(ps, call, filter, pred, dry_run);
+ if (!pred) {
+ err = -ENOMEM;
+ goto fail;
+ }
+ err = filter_add_pred(ps, call, filter, pred, &stack, dry_run);
filter_free_pred(pred);
if (err)
- return err;
+ goto fail;
operand1 = operand2 = NULL;
}
- return 0;
+ if (!dry_run) {
+ /* We should have one item left on the stack */
+ pred = __pop_pred_stack(&stack);
+ if (!pred)
+ return -EINVAL;
+ /* This item is where we start from in matching */
+ root = pred;
+ /* Make sure the stack is empty */
+ pred = __pop_pred_stack(&stack);
+ if (WARN_ON(pred)) {
+ err = -EINVAL;
+ filter->root = NULL;
+ goto fail;
+ }
+ err = check_pred_tree(filter, root);
+ if (err)
+ goto fail;
+
+ /* Optimize the tree */
+ err = fold_pred_tree(filter, root);
+ if (err)
+ goto fail;
+
+ /* We don't set root until we know it works */
+ barrier();
+ filter->root = root;
+ }
+
+ err = 0;
+fail:
+ __free_pred_stack(&stack);
+ return err;
}
+struct filter_list {
+ struct list_head list;
+ struct event_filter *filter;
+};
+
static int replace_system_preds(struct event_subsystem *system,
struct filter_parse_state *ps,
char *filter_string)
{
struct ftrace_event_call *call;
+ struct filter_list *filter_item;
+ struct filter_list *tmp;
+ LIST_HEAD(filter_list);
bool fail = true;
int err;
list_for_each_entry(call, &ftrace_events, list) {
- struct event_filter *filter = call->filter;
if (strcmp(call->class->system, system->name) != 0)
continue;
- /* try to see if the filter can be applied */
- err = replace_preds(call, filter, ps, filter_string, true);
+ /*
+ * Try to see if the filter can be applied
+ * (filter arg is ignored on dry_run)
+ */
+ err = replace_preds(call, NULL, ps, filter_string, true);
if (err)
+ goto fail;
+ }
+
+ list_for_each_entry(call, &ftrace_events, list) {
+ struct event_filter *filter;
+
+ if (strcmp(call->class->system, system->name) != 0)
continue;
- /* really apply the filter */
- filter_disable_preds(call);
- err = replace_preds(call, filter, ps, filter_string, false);
+ filter_item = kzalloc(sizeof(*filter_item), GFP_KERNEL);
+ if (!filter_item)
+ goto fail_mem;
+
+ list_add_tail(&filter_item->list, &filter_list);
+
+ filter_item->filter = __alloc_filter();
+ if (!filter_item->filter)
+ goto fail_mem;
+ filter = filter_item->filter;
+
+ /* Can only fail on no memory */
+ err = replace_filter_string(filter, filter_string);
if (err)
- filter_disable_preds(call);
- else {
+ goto fail_mem;
+
+ err = replace_preds(call, filter, ps, filter_string, false);
+ if (err) {
+ filter_disable(call);
+ parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+ append_filter_err(ps, filter);
+ } else
call->flags |= TRACE_EVENT_FL_FILTERED;
- replace_filter_string(filter, filter_string);
- }
+ /*
+ * Regardless of if this returned an error, we still
+ * replace the filter for the call.
+ */
+ filter = call->filter;
+ call->filter = filter_item->filter;
+ filter_item->filter = filter;
+
fail = false;
}
- if (fail) {
- parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
- return -EINVAL;
+ if (fail)
+ goto fail;
+
+ /*
+ * The calls can still be using the old filters.
+ * Do a synchronize_sched() to ensure all calls are
+ * done with them before we free them.
+ */
+ synchronize_sched();
+ list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
+ __free_filter(filter_item->filter);
+ list_del(&filter_item->list);
+ kfree(filter_item);
}
return 0;
+ fail:
+ /* No call succeeded */
+ list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
+ list_del(&filter_item->list);
+ kfree(filter_item);
+ }
+ parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+ return -EINVAL;
+ fail_mem:
+ /* If any call succeeded, we still need to sync */
+ if (!fail)
+ synchronize_sched();
+ list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
+ __free_filter(filter_item->filter);
+ list_del(&filter_item->list);
+ kfree(filter_item);
+ }
+ return -ENOMEM;
}
int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
{
- int err;
struct filter_parse_state *ps;
+ struct event_filter *filter;
+ struct event_filter *tmp;
+ int err = 0;
mutex_lock(&event_mutex);
- err = init_preds(call);
- if (err)
- goto out_unlock;
-
if (!strcmp(strstrip(filter_string), "0")) {
- filter_disable_preds(call);
- remove_filter_string(call->filter);
+ filter_disable(call);
+ filter = call->filter;
+ if (!filter)
+ goto out_unlock;
+ call->filter = NULL;
+ /* Make sure the filter is not being used */
+ synchronize_sched();
+ __free_filter(filter);
goto out_unlock;
}
@@ -1306,22 +1833,41 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
if (!ps)
goto out_unlock;
- filter_disable_preds(call);
- replace_filter_string(call->filter, filter_string);
+ filter = __alloc_filter();
+ if (!filter) {
+ kfree(ps);
+ goto out_unlock;
+ }
+
+ replace_filter_string(filter, filter_string);
parse_init(ps, filter_ops, filter_string);
err = filter_parse(ps);
if (err) {
- append_filter_err(ps, call->filter);
+ append_filter_err(ps, filter);
goto out;
}
- err = replace_preds(call, call->filter, ps, filter_string, false);
- if (err)
- append_filter_err(ps, call->filter);
- else
+ err = replace_preds(call, filter, ps, filter_string, false);
+ if (err) {
+ filter_disable(call);
+ append_filter_err(ps, filter);
+ } else
call->flags |= TRACE_EVENT_FL_FILTERED;
out:
+ /*
+ * Always swap the call filter with the new filter
+ * even if there was an error. If there was an error
+ * in the filter, we disable the filter and show the error
+ * string
+ */
+ tmp = call->filter;
+ call->filter = filter;
+ if (tmp) {
+ /* Make sure the call is done with the filter */
+ synchronize_sched();
+ __free_filter(tmp);
+ }
filter_opstack_clear(ps);
postfix_clear(ps);
kfree(ps);
@@ -1334,18 +1880,21 @@ out_unlock:
int apply_subsystem_event_filter(struct event_subsystem *system,
char *filter_string)
{
- int err;
struct filter_parse_state *ps;
+ struct event_filter *filter;
+ int err = 0;
mutex_lock(&event_mutex);
- err = init_subsystem_preds(system);
- if (err)
- goto out_unlock;
-
if (!strcmp(strstrip(filter_string), "0")) {
filter_free_subsystem_preds(system);
remove_filter_string(system->filter);
+ filter = system->filter;
+ system->filter = NULL;
+ /* Ensure all filters are no longer used */
+ synchronize_sched();
+ filter_free_subsystem_filters(system);
+ __free_filter(filter);
goto out_unlock;
}
@@ -1354,7 +1903,17 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
if (!ps)
goto out_unlock;
- replace_filter_string(system->filter, filter_string);
+ filter = __alloc_filter();
+ if (!filter)
+ goto out;
+
+ replace_filter_string(filter, filter_string);
+ /*
+ * No event actually uses the system filter
+ * we can free it without synchronize_sched().
+ */
+ __free_filter(system->filter);
+ system->filter = filter;
parse_init(ps, filter_ops, filter_string);
err = filter_parse(ps);
@@ -1384,7 +1943,7 @@ void ftrace_profile_free_filter(struct perf_event *event)
struct event_filter *filter = event->filter;
event->filter = NULL;
- __free_preds(filter);
+ __free_filter(filter);
}
int ftrace_profile_set_filter(struct perf_event *event, int event_id,
@@ -1410,8 +1969,8 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
if (event->filter)
goto out_unlock;
- filter = __alloc_preds();
- if (IS_ERR(filter)) {
+ filter = __alloc_filter();
+ if (!filter) {
err = PTR_ERR(filter);
goto out_unlock;
}
@@ -1419,7 +1978,7 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
err = -ENOMEM;
ps = kzalloc(sizeof(*ps), GFP_KERNEL);
if (!ps)
- goto free_preds;
+ goto free_filter;
parse_init(ps, filter_ops, filter_str);
err = filter_parse(ps);
@@ -1435,9 +1994,9 @@ free_ps:
postfix_clear(ps);
kfree(ps);
-free_preds:
+free_filter:
if (err)
- __free_preds(filter);
+ __free_filter(filter);
out_unlock:
mutex_unlock(&event_mutex);
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 4b74d71705c0..bbeec31e0ae3 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -161,13 +161,13 @@ struct ftrace_event_class event_class_ftrace_##call = { \
.fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\
}; \
\
-struct ftrace_event_call __used \
-__attribute__((__aligned__(4))) \
-__attribute__((section("_ftrace_events"))) event_##call = { \
+struct ftrace_event_call __used event_##call = { \
.name = #call, \
.event.type = etype, \
.class = &event_class_ftrace_##call, \
.print_fmt = print, \
}; \
+struct ftrace_event_call __used \
+__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
#include "trace_entries.h"
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 2dec9bcde8b4..8435b43b1782 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -353,6 +353,43 @@ static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
kfree(data);
}
+/* Bitfield fetch function */
+struct bitfield_fetch_param {
+ struct fetch_param orig;
+ unsigned char hi_shift;
+ unsigned char low_shift;
+};
+
+#define DEFINE_FETCH_bitfield(type) \
+static __kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,\
+ void *data, void *dest) \
+{ \
+ struct bitfield_fetch_param *bprm = data; \
+ type buf = 0; \
+ call_fetch(&bprm->orig, regs, &buf); \
+ if (buf) { \
+ buf <<= bprm->hi_shift; \
+ buf >>= bprm->low_shift; \
+ } \
+ *(type *)dest = buf; \
+}
+DEFINE_BASIC_FETCH_FUNCS(bitfield)
+#define fetch_bitfield_string NULL
+#define fetch_bitfield_string_size NULL
+
+static __kprobes void
+free_bitfield_fetch_param(struct bitfield_fetch_param *data)
+{
+ /*
+ * Don't check the bitfield itself, because this must be the
+ * last fetch function.
+ */
+ if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+ free_deref_fetch_param(data->orig.data);
+ else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+ free_symbol_cache(data->orig.data);
+ kfree(data);
+}
/* Default (unsigned long) fetch type */
#define __DEFAULT_FETCH_TYPE(t) u##t
#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
@@ -367,6 +404,7 @@ enum {
FETCH_MTD_memory,
FETCH_MTD_symbol,
FETCH_MTD_deref,
+ FETCH_MTD_bitfield,
FETCH_MTD_END,
};
@@ -387,6 +425,7 @@ ASSIGN_FETCH_FUNC(retval, ftype), \
ASSIGN_FETCH_FUNC(memory, ftype), \
ASSIGN_FETCH_FUNC(symbol, ftype), \
ASSIGN_FETCH_FUNC(deref, ftype), \
+ASSIGN_FETCH_FUNC(bitfield, ftype), \
} \
}
@@ -430,9 +469,33 @@ static const struct fetch_type *find_fetch_type(const char *type)
if (!type)
type = DEFAULT_FETCH_TYPE_STR;
+ /* Special case: bitfield */
+ if (*type == 'b') {
+ unsigned long bs;
+ type = strchr(type, '/');
+ if (!type)
+ goto fail;
+ type++;
+ if (strict_strtoul(type, 0, &bs))
+ goto fail;
+ switch (bs) {
+ case 8:
+ return find_fetch_type("u8");
+ case 16:
+ return find_fetch_type("u16");
+ case 32:
+ return find_fetch_type("u32");
+ case 64:
+ return find_fetch_type("u64");
+ default:
+ goto fail;
+ }
+ }
+
for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++)
if (strcmp(type, fetch_type_table[i].name) == 0)
return &fetch_type_table[i];
+fail:
return NULL;
}
@@ -586,7 +649,9 @@ error:
static void free_probe_arg(struct probe_arg *arg)
{
- if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
+ if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
+ free_bitfield_fetch_param(arg->fetch.data);
+ else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
free_deref_fetch_param(arg->fetch.data);
else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
free_symbol_cache(arg->fetch.data);
@@ -767,16 +832,15 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t,
}
break;
case '+': /* deref memory */
+ arg++; /* Skip '+', because strict_strtol() rejects it. */
case '-':
tmp = strchr(arg, '(');
if (!tmp)
break;
*tmp = '\0';
- ret = strict_strtol(arg + 1, 0, &offset);
+ ret = strict_strtol(arg, 0, &offset);
if (ret)
break;
- if (arg[0] == '-')
- offset = -offset;
arg = tmp + 1;
tmp = strrchr(arg, ')');
if (tmp) {
@@ -807,6 +871,41 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t,
return ret;
}
+#define BYTES_TO_BITS(nb) ((BITS_PER_LONG * (nb)) / sizeof(long))
+
+/* Bitfield type needs to be parsed into a fetch function */
+static int __parse_bitfield_probe_arg(const char *bf,
+ const struct fetch_type *t,
+ struct fetch_param *f)
+{
+ struct bitfield_fetch_param *bprm;
+ unsigned long bw, bo;
+ char *tail;
+
+ if (*bf != 'b')
+ return 0;
+
+ bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
+ if (!bprm)
+ return -ENOMEM;
+ bprm->orig = *f;
+ f->fn = t->fetch[FETCH_MTD_bitfield];
+ f->data = (void *)bprm;
+
+ bw = simple_strtoul(bf + 1, &tail, 0); /* Use simple one */
+ if (bw == 0 || *tail != '@')
+ return -EINVAL;
+
+ bf = tail + 1;
+ bo = simple_strtoul(bf, &tail, 0);
+ if (tail == bf || *tail != '/')
+ return -EINVAL;
+
+ bprm->hi_shift = BYTES_TO_BITS(t->size) - (bw + bo);
+ bprm->low_shift = bprm->hi_shift + bo;
+ return (BYTES_TO_BITS(t->size) < (bw + bo)) ? -EINVAL : 0;
+}
+
/* String length checking wrapper */
static int parse_probe_arg(char *arg, struct trace_probe *tp,
struct probe_arg *parg, int is_return)
@@ -836,6 +935,8 @@ static int parse_probe_arg(char *arg, struct trace_probe *tp,
parg->offset = tp->size;
tp->size += parg->type->size;
ret = __parse_probe_arg(arg, parg->type, &parg->fetch, is_return);
+ if (ret >= 0 && t != NULL)
+ ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch);
if (ret >= 0) {
parg->fetch_size.fn = get_fetch_size_function(parg->type,
parg->fetch.fn);
@@ -1130,7 +1231,7 @@ static int command_trace_probe(const char *buf)
return ret;
}
-#define WRITE_BUFSIZE 128
+#define WRITE_BUFSIZE 4096
static ssize_t probes_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 02272baa2206..456be9063c2d 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -529,24 +529,34 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
* @entry: The trace entry field from the ring buffer
*
* Prints the generic fields of irqs off, in hard or softirq, preempt
- * count and lock depth.
+ * count.
*/
int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
{
- int hardirq, softirq;
+ char hardsoft_irq;
+ char need_resched;
+ char irqs_off;
+ int hardirq;
+ int softirq;
int ret;
hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
+ irqs_off =
+ (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
+ (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' :
+ '.';
+ need_resched =
+ (entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.';
+ hardsoft_irq =
+ (hardirq && softirq) ? 'H' :
+ hardirq ? 'h' :
+ softirq ? 's' :
+ '.';
+
if (!trace_seq_printf(s, "%c%c%c",
- (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
- (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ?
- 'X' : '.',
- (entry->flags & TRACE_FLAG_NEED_RESCHED) ?
- 'N' : '.',
- (hardirq && softirq) ? 'H' :
- hardirq ? 'h' : softirq ? 's' : '.'))
+ irqs_off, need_resched, hardsoft_irq))
return 0;
if (entry->preempt_count)
@@ -554,13 +564,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
else
ret = trace_seq_putc(s, '.');
- if (!ret)
- return 0;
-
- if (entry->lock_depth < 0)
- return trace_seq_putc(s, '.');
-
- return trace_seq_printf(s, "%d", entry->lock_depth);
+ return ret;
}
static int
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 8f758d070c43..7e62c0a18456 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -247,51 +247,3 @@ void tracing_sched_switch_assign_trace(struct trace_array *tr)
ctx_trace = tr;
}
-static void stop_sched_trace(struct trace_array *tr)
-{
- tracing_stop_sched_switch_record();
-}
-
-static int sched_switch_trace_init(struct trace_array *tr)
-{
- ctx_trace = tr;
- tracing_reset_online_cpus(tr);
- tracing_start_sched_switch_record();
- return 0;
-}
-
-static void sched_switch_trace_reset(struct trace_array *tr)
-{
- if (sched_ref)
- stop_sched_trace(tr);
-}
-
-static void sched_switch_trace_start(struct trace_array *tr)
-{
- sched_stopped = 0;
-}
-
-static void sched_switch_trace_stop(struct trace_array *tr)
-{
- sched_stopped = 1;
-}
-
-static struct tracer sched_switch_trace __read_mostly =
-{
- .name = "sched_switch",
- .init = sched_switch_trace_init,
- .reset = sched_switch_trace_reset,
- .start = sched_switch_trace_start,
- .stop = sched_switch_trace_stop,
- .wait_pipe = poll_wait_pipe,
-#ifdef CONFIG_FTRACE_SELFTEST
- .selftest = trace_selftest_startup_sched_switch,
-#endif
-};
-
-__init static int init_sched_switch_trace(void)
-{
- return register_tracer(&sched_switch_trace);
-}
-device_initcall(init_sched_switch_trace);
-
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index b706529b4fc7..ee7b5a0bb9f8 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -55,31 +55,42 @@ struct ftrace_event_class event_class_syscall_exit = {
.raw_init = init_syscall_trace,
};
-extern unsigned long __start_syscalls_metadata[];
-extern unsigned long __stop_syscalls_metadata[];
+extern struct syscall_metadata *__start_syscalls_metadata[];
+extern struct syscall_metadata *__stop_syscalls_metadata[];
static struct syscall_metadata **syscalls_metadata;
-static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
+#ifndef ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
{
- struct syscall_metadata *start;
- struct syscall_metadata *stop;
+ /*
+ * Only compare after the "sys" prefix. Archs that use
+ * syscall wrappers may have syscalls symbols aliases prefixed
+ * with "SyS" instead of "sys", leading to an unwanted
+ * mismatch.
+ */
+ return !strcmp(sym + 3, name + 3);
+}
+#endif
+
+static __init struct syscall_metadata *
+find_syscall_meta(unsigned long syscall)
+{
+ struct syscall_metadata **start;
+ struct syscall_metadata **stop;
char str[KSYM_SYMBOL_LEN];
- start = (struct syscall_metadata *)__start_syscalls_metadata;
- stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+ start = __start_syscalls_metadata;
+ stop = __stop_syscalls_metadata;
kallsyms_lookup(syscall, NULL, NULL, NULL, str);
+ if (arch_syscall_match_sym_name(str, "sys_ni_syscall"))
+ return NULL;
+
for ( ; start < stop; start++) {
- /*
- * Only compare after the "sys" prefix. Archs that use
- * syscall wrappers may have syscalls symbols aliases prefixed
- * with "SyS" instead of "sys", leading to an unwanted
- * mismatch.
- */
- if (start->name && !strcmp(start->name + 3, str + 3))
- return start;
+ if ((*start)->name && arch_syscall_match_sym_name(str, (*start)->name))
+ return *start;
}
return NULL;
}
@@ -358,7 +369,7 @@ int reg_event_syscall_enter(struct ftrace_event_call *call)
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
- if (num < 0 || num >= NR_syscalls)
+ if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_refcount_enter)
@@ -376,7 +387,7 @@ void unreg_event_syscall_enter(struct ftrace_event_call *call)
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
- if (num < 0 || num >= NR_syscalls)
+ if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
return;
mutex_lock(&syscall_trace_lock);
sys_refcount_enter--;
@@ -392,7 +403,7 @@ int reg_event_syscall_exit(struct ftrace_event_call *call)
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
- if (num < 0 || num >= NR_syscalls)
+ if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_refcount_exit)
@@ -410,7 +421,7 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call)
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
- if (num < 0 || num >= NR_syscalls)
+ if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
return;
mutex_lock(&syscall_trace_lock);
sys_refcount_exit--;
@@ -423,6 +434,14 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call)
int init_syscall_trace(struct ftrace_event_call *call)
{
int id;
+ int num;
+
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
+ if (num < 0 || num >= NR_syscalls) {
+ pr_debug("syscall %s metadata not mapped, disabling ftrace event\n",
+ ((struct syscall_metadata *)call->data)->name);
+ return -ENOSYS;
+ }
if (set_syscall_print_fmt(call) < 0)
return -ENOMEM;
@@ -437,7 +456,7 @@ int init_syscall_trace(struct ftrace_event_call *call)
return id;
}
-unsigned long __init arch_syscall_addr(int nr)
+unsigned long __init __weak arch_syscall_addr(int nr)
{
return (unsigned long)sys_call_table[nr];
}
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index e95ee7f31d43..68187af4889e 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -27,8 +27,8 @@
#include <linux/sched.h>
#include <linux/jump_label.h>
-extern struct tracepoint __start___tracepoints[];
-extern struct tracepoint __stop___tracepoints[];
+extern struct tracepoint * const __start___tracepoints_ptrs[];
+extern struct tracepoint * const __stop___tracepoints_ptrs[];
/* Set to 1 to enable tracepoint debug output */
static const int tracepoint_debug;
@@ -298,10 +298,10 @@ static void disable_tracepoint(struct tracepoint *elem)
*
* Updates the probe callback corresponding to a range of tracepoints.
*/
-void
-tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end)
+void tracepoint_update_probe_range(struct tracepoint * const *begin,
+ struct tracepoint * const *end)
{
- struct tracepoint *iter;
+ struct tracepoint * const *iter;
struct tracepoint_entry *mark_entry;
if (!begin)
@@ -309,12 +309,12 @@ tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end)
mutex_lock(&tracepoints_mutex);
for (iter = begin; iter < end; iter++) {
- mark_entry = get_tracepoint(iter->name);
+ mark_entry = get_tracepoint((*iter)->name);
if (mark_entry) {
- set_tracepoint(&mark_entry, iter,
+ set_tracepoint(&mark_entry, *iter,
!!mark_entry->refcount);
} else {
- disable_tracepoint(iter);
+ disable_tracepoint(*iter);
}
}
mutex_unlock(&tracepoints_mutex);
@@ -326,8 +326,8 @@ tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end)
static void tracepoint_update_probes(void)
{
/* Core kernel tracepoints */
- tracepoint_update_probe_range(__start___tracepoints,
- __stop___tracepoints);
+ tracepoint_update_probe_range(__start___tracepoints_ptrs,
+ __stop___tracepoints_ptrs);
/* tracepoints in modules. */
module_update_tracepoints();
}
@@ -514,8 +514,8 @@ EXPORT_SYMBOL_GPL(tracepoint_probe_update_all);
* Will return the first tracepoint in the range if the input tracepoint is
* NULL.
*/
-int tracepoint_get_iter_range(struct tracepoint **tracepoint,
- struct tracepoint *begin, struct tracepoint *end)
+int tracepoint_get_iter_range(struct tracepoint * const **tracepoint,
+ struct tracepoint * const *begin, struct tracepoint * const *end)
{
if (!*tracepoint && begin != end) {
*tracepoint = begin;
@@ -534,7 +534,8 @@ static void tracepoint_get_iter(struct tracepoint_iter *iter)
/* Core kernel tracepoints */
if (!iter->module) {
found = tracepoint_get_iter_range(&iter->tracepoint,
- __start___tracepoints, __stop___tracepoints);
+ __start___tracepoints_ptrs,
+ __stop___tracepoints_ptrs);
if (found)
goto end;
}
@@ -585,8 +586,8 @@ int tracepoint_module_notify(struct notifier_block *self,
switch (val) {
case MODULE_STATE_COMING:
case MODULE_STATE_GOING:
- tracepoint_update_probe_range(mod->tracepoints,
- mod->tracepoints + mod->num_tracepoints);
+ tracepoint_update_probe_range(mod->tracepoints_ptrs,
+ mod->tracepoints_ptrs + mod->num_tracepoints);
break;
}
return 0;
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index d7ebdf4cea98..18bb15776c57 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -27,7 +27,7 @@
#include <asm/irq_regs.h>
#include <linux/perf_event.h>
-int watchdog_enabled;
+int watchdog_enabled = 1;
int __read_mostly softlockup_thresh = 60;
static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
@@ -43,9 +43,6 @@ static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
#endif
-static int no_watchdog;
-
-
/* boot commands */
/*
* Should we panic when a soft-lockup or hard-lockup occurs:
@@ -58,7 +55,7 @@ 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;
+ watchdog_enabled = 0;
return 1;
}
__setup("nmi_watchdog=", hardlockup_panic_setup);
@@ -77,7 +74,7 @@ __setup("softlockup_panic=", softlockup_panic_setup);
static int __init nowatchdog_setup(char *str)
{
- no_watchdog = 1;
+ watchdog_enabled = 0;
return 1;
}
__setup("nowatchdog", nowatchdog_setup);
@@ -85,7 +82,7 @@ __setup("nowatchdog", nowatchdog_setup);
/* deprecated */
static int __init nosoftlockup_setup(char *str)
{
- no_watchdog = 1;
+ watchdog_enabled = 0;
return 1;
}
__setup("nosoftlockup", nosoftlockup_setup);
@@ -366,8 +363,14 @@ static int watchdog_nmi_enable(int cpu)
goto out_save;
}
- printk(KERN_ERR "NMI watchdog disabled for cpu%i: unable to create perf event: %ld\n",
- cpu, PTR_ERR(event));
+
+ /* vary the KERN level based on the returned errno */
+ if (PTR_ERR(event) == -EOPNOTSUPP)
+ printk(KERN_INFO "NMI watchdog disabled (cpu%i): not supported (no LAPIC?)\n", cpu);
+ else if (PTR_ERR(event) == -ENOENT)
+ printk(KERN_WARNING "NMI watchdog disabled (cpu%i): hardware events not enabled\n", cpu);
+ else
+ printk(KERN_ERR "NMI watchdog disabled (cpu%i): unable to create perf event: %ld\n", cpu, PTR_ERR(event));
return PTR_ERR(event);
/* success path */
@@ -432,9 +435,6 @@ static int watchdog_enable(int cpu)
wake_up_process(p);
}
- /* if any cpu succeeds, watchdog is considered enabled for the system */
- watchdog_enabled = 1;
-
return 0;
}
@@ -462,12 +462,16 @@ static void watchdog_disable(int cpu)
static void watchdog_enable_all_cpus(void)
{
int cpu;
- int result = 0;
+
+ watchdog_enabled = 0;
for_each_online_cpu(cpu)
- result += watchdog_enable(cpu);
+ if (!watchdog_enable(cpu))
+ /* if any cpu succeeds, watchdog is considered
+ enabled for the system */
+ watchdog_enabled = 1;
- if (result)
+ if (!watchdog_enabled)
printk(KERN_ERR "watchdog: failed to be enabled on some cpus\n");
}
@@ -476,9 +480,6 @@ static void watchdog_disable_all_cpus(void)
{
int cpu;
- if (no_watchdog)
- return;
-
for_each_online_cpu(cpu)
watchdog_disable(cpu);
@@ -498,10 +499,12 @@ int proc_dowatchdog_enabled(struct ctl_table *table, int write,
{
proc_dointvec(table, write, buffer, length, ppos);
- if (watchdog_enabled)
- watchdog_enable_all_cpus();
- else
- watchdog_disable_all_cpus();
+ if (write) {
+ if (watchdog_enabled)
+ watchdog_enable_all_cpus();
+ else
+ watchdog_disable_all_cpus();
+ }
return 0;
}
@@ -530,7 +533,8 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
- err = watchdog_enable(hotcpu);
+ if (watchdog_enabled)
+ err = watchdog_enable(hotcpu);
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_UP_CANCELED:
@@ -555,9 +559,6 @@ void __init lockup_detector_init(void)
void *cpu = (void *)(long)smp_processor_id();
int err;
- if (no_watchdog)
- return;
-
err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
WARN_ON(notifier_to_errno(err));
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 11869faa6819..b5fe4c00eb3c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -79,7 +79,9 @@ enum {
MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */
IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */
- MAYDAY_INITIAL_TIMEOUT = HZ / 100, /* call for help after 10ms */
+ MAYDAY_INITIAL_TIMEOUT = HZ / 100 >= 2 ? HZ / 100 : 2,
+ /* call for help after 10ms
+ (min two ticks) */
MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */
CREATE_COOLDOWN = HZ, /* time to breath after fail */
TRUSTEE_COOLDOWN = HZ / 10, /* for trustee draining */
@@ -314,6 +316,11 @@ static inline int __next_wq_cpu(int cpu, const struct cpumask *mask,
static struct debug_obj_descr work_debug_descr;
+static void *work_debug_hint(void *addr)
+{
+ return ((struct work_struct *) addr)->func;
+}
+
/*
* fixup_init is called when:
* - an active object is initialized
@@ -385,6 +392,7 @@ static int work_fixup_free(void *addr, enum debug_obj_state state)
static struct debug_obj_descr work_debug_descr = {
.name = "work_struct",
+ .debug_hint = work_debug_hint,
.fixup_init = work_fixup_init,
.fixup_activate = work_fixup_activate,
.fixup_free = work_fixup_free,
@@ -2047,6 +2055,15 @@ repeat:
move_linked_works(work, scheduled, &n);
process_scheduled_works(rescuer);
+
+ /*
+ * Leave this gcwq. If keep_working() is %true, notify a
+ * regular worker; otherwise, we end up with 0 concurrency
+ * and stalling the execution.
+ */
+ if (keep_working(gcwq))
+ wake_up_worker(gcwq);
+
spin_unlock_irq(&gcwq->lock);
}
@@ -2956,7 +2973,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name,
*/
spin_lock(&workqueue_lock);
- if (workqueue_freezing && wq->flags & WQ_FREEZEABLE)
+ if (workqueue_freezing && wq->flags & WQ_FREEZABLE)
for_each_cwq_cpu(cpu, wq)
get_cwq(cpu, wq)->max_active = 0;
@@ -3068,7 +3085,7 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
spin_lock_irq(&gcwq->lock);
- if (!(wq->flags & WQ_FREEZEABLE) ||
+ if (!(wq->flags & WQ_FREEZABLE) ||
!(gcwq->flags & GCWQ_FREEZING))
get_cwq(gcwq->cpu, wq)->max_active = max_active;
@@ -3318,7 +3335,7 @@ static int __cpuinit trustee_thread(void *__gcwq)
* want to get it over with ASAP - spam rescuers, wake up as
* many idlers as necessary and create new ones till the
* worklist is empty. Note that if the gcwq is frozen, there
- * may be frozen works in freezeable cwqs. Don't declare
+ * may be frozen works in freezable cwqs. Don't declare
* completion while frozen.
*/
while (gcwq->nr_workers != gcwq->nr_idle ||
@@ -3576,9 +3593,9 @@ EXPORT_SYMBOL_GPL(work_on_cpu);
/**
* freeze_workqueues_begin - begin freezing workqueues
*
- * Start freezing workqueues. After this function returns, all
- * freezeable workqueues will queue new works to their frozen_works
- * list instead of gcwq->worklist.
+ * Start freezing workqueues. After this function returns, all freezable
+ * workqueues will queue new works to their frozen_works list instead of
+ * gcwq->worklist.
*
* CONTEXT:
* Grabs and releases workqueue_lock and gcwq->lock's.
@@ -3604,7 +3621,7 @@ void freeze_workqueues_begin(void)
list_for_each_entry(wq, &workqueues, list) {
struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
- if (cwq && wq->flags & WQ_FREEZEABLE)
+ if (cwq && wq->flags & WQ_FREEZABLE)
cwq->max_active = 0;
}
@@ -3615,7 +3632,7 @@ void freeze_workqueues_begin(void)
}
/**
- * freeze_workqueues_busy - are freezeable workqueues still busy?
+ * freeze_workqueues_busy - are freezable workqueues still busy?
*
* Check whether freezing is complete. This function must be called
* between freeze_workqueues_begin() and thaw_workqueues().
@@ -3624,8 +3641,8 @@ void freeze_workqueues_begin(void)
* Grabs and releases workqueue_lock.
*
* RETURNS:
- * %true if some freezeable workqueues are still busy. %false if
- * freezing is complete.
+ * %true if some freezable workqueues are still busy. %false if freezing
+ * is complete.
*/
bool freeze_workqueues_busy(void)
{
@@ -3645,7 +3662,7 @@ bool freeze_workqueues_busy(void)
list_for_each_entry(wq, &workqueues, list) {
struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
- if (!cwq || !(wq->flags & WQ_FREEZEABLE))
+ if (!cwq || !(wq->flags & WQ_FREEZABLE))
continue;
BUG_ON(cwq->nr_active < 0);
@@ -3690,7 +3707,7 @@ void thaw_workqueues(void)
list_for_each_entry(wq, &workqueues, list) {
struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
- if (!cwq || !(wq->flags & WQ_FREEZEABLE))
+ if (!cwq || !(wq->flags & WQ_FREEZABLE))
continue;
/* restore max_active and repopulate worklist */