summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit_watch.c85
-rw-r--r--kernel/cred.c2
-rw-r--r--kernel/futex.c147
-rw-r--r--kernel/hrtimer.c6
-rw-r--r--kernel/irq/manage.c11
-rw-r--r--kernel/irq/pm.c3
-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.c1
-rw-r--r--kernel/sched_rt.c14
-rw-r--r--kernel/sys_ni.c5
-rw-r--r--kernel/sysctl.c15
-rw-r--r--kernel/sysctl_binary.c19
-rw-r--r--kernel/timer.c29
-rw-r--r--kernel/workqueue.c6
17 files changed, 305 insertions, 413 deletions
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index d2e3c786646..e683869365d 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/cred.c b/kernel/cred.c
index 3a9d6dd53a6..2343c132c5a 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
diff --git a/kernel/futex.c b/kernel/futex.c
index b766d28accd..bda41571538 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 0c8d7c04861..e38f5a073d0 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -334,6 +334,11 @@ 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
@@ -393,6 +398,7 @@ 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/manage.c b/kernel/irq/manage.c
index 9033c1c7082..2782bacdf49 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:
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 0d4005d85b0..d6bfb89cce9 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/rtmutex-debug.c b/kernel/rtmutex-debug.c
index ddabb54bb5c..3c7cbc2c33b 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 66cb89bc5ef..5c9ccd38096 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 a9604815786..ab449117aaf 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 97a2f81866a..53a66c85261 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 79e611cd83d..57a18e8d28c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4189,6 +4189,7 @@ 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.
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index ad6267714c8..01f75a5f17a 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);
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index c782fe9924c..25cc41cd8f3 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 daef911cbad..19b9d85e06c 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,
};
@@ -1567,11 +1567,16 @@ 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 +1953,10 @@ 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 b875bedf7c9..3b8e028b960 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/timer.c b/kernel/timer.c
index d6459923d24..3503c17ac1d 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,
@@ -964,6 +970,25 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
* 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)
@@ -971,6 +996,10 @@ int del_timer_sync(struct timer_list *timer)
#ifdef CONFIG_LOCKDEP
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);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ee6578b578a..b5fe4c00eb3 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -316,6 +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
@@ -387,6 +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,