aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile1
-rw-r--r--kernel/acct.c6
-rw-r--r--kernel/cgroup.c151
-rw-r--r--kernel/exit.c1
-rw-r--r--kernel/fork.c9
-rw-r--r--kernel/freezer.c7
-rw-r--r--kernel/futex.c3
-rw-r--r--kernel/hrtimer.c110
-rw-r--r--kernel/irq/internals.h3
-rw-r--r--kernel/irq/manage.c55
-rw-r--r--kernel/irq/migration.c2
-rw-r--r--kernel/kexec.c2
-rw-r--r--kernel/kmod.c1
-rw-r--r--kernel/kprobes.c8
-rw-r--r--kernel/kthread.c10
-rw-r--r--kernel/module.c9
-rw-r--r--kernel/panic.c1
-rw-r--r--kernel/perf_counter.c583
-rw-r--r--kernel/posix-timers.c7
-rw-r--r--kernel/power/user.c1
-rw-r--r--kernel/profile.c5
-rw-r--r--kernel/ptrace.c4
-rw-r--r--kernel/rcutree.c3
-rw-r--r--kernel/resource.c2
-rw-r--r--kernel/sched.c61
-rw-r--r--kernel/sched_cpupri.c15
-rw-r--r--kernel/sched_fair.c45
-rw-r--r--kernel/sched_rt.c18
-rw-r--r--kernel/signal.c25
-rw-r--r--kernel/softirq.c64
-rw-r--r--kernel/sysctl.c13
-rw-r--r--kernel/time/clockevents.c11
-rw-r--r--kernel/time/clocksource.c2
-rw-r--r--kernel/time/timer_stats.c16
-rw-r--r--kernel/timer.c4
-rw-r--r--kernel/trace/Kconfig6
-rw-r--r--kernel/trace/blktrace.c1
-rw-r--r--kernel/trace/ftrace.c84
-rw-r--r--kernel/trace/ring_buffer.c11
-rw-r--r--kernel/trace/trace.c36
-rw-r--r--kernel/trace/trace.h7
-rw-r--r--kernel/trace/trace_event_types.h3
-rw-r--r--kernel/trace/trace_events.c30
-rw-r--r--kernel/trace/trace_functions.c5
-rw-r--r--kernel/trace/trace_functions_graph.c11
-rw-r--r--kernel/trace/trace_output.c3
-rw-r--r--kernel/trace/trace_printk.c28
-rw-r--r--kernel/trace/trace_stack.c11
-rw-r--r--kernel/trace/trace_stat.c40
49 files changed, 1056 insertions, 478 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 780c8dcf451..2093a691f1c 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -96,6 +96,7 @@ obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
obj-$(CONFIG_FUNCTION_TRACER) += trace/
obj-$(CONFIG_TRACING) += trace/
obj-$(CONFIG_X86_DS) += trace/
+obj-$(CONFIG_RING_BUFFER) += trace/
obj-$(CONFIG_SMP) += sched_cpupri.o
obj-$(CONFIG_SLOW_WORK) += slow-work.o
obj-$(CONFIG_PERF_COUNTERS) += perf_counter.o
diff --git a/kernel/acct.c b/kernel/acct.c
index 7afa3156416..9f3391090b3 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -215,6 +215,7 @@ static void acct_file_reopen(struct bsd_acct_struct *acct, struct file *file,
static int acct_on(char *name)
{
struct file *file;
+ struct vfsmount *mnt;
int error;
struct pid_namespace *ns;
struct bsd_acct_struct *acct = NULL;
@@ -256,11 +257,12 @@ static int acct_on(char *name)
acct = NULL;
}
- mnt_pin(file->f_path.mnt);
+ mnt = file->f_path.mnt;
+ mnt_pin(mnt);
acct_file_reopen(ns->bacct, file, ns);
spin_unlock(&acct_lock);
- mntput(file->f_path.mnt); /* it's pinned, now give up active reference */
+ mntput(mnt); /* it's pinned, now give up active reference */
kfree(acct);
return 0;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 3737a682cdf..b6eadfe30e7 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -47,6 +47,7 @@
#include <linux/hash.h>
#include <linux/namei.h>
#include <linux/smp_lock.h>
+#include <linux/pid_namespace.h>
#include <asm/atomic.h>
@@ -734,16 +735,28 @@ static void cgroup_d_remove_dir(struct dentry *dentry)
* reference to css->refcnt. In general, this refcnt is expected to goes down
* to zero, soon.
*
- * CGRP_WAIT_ON_RMDIR flag is modified under cgroup's inode->i_mutex;
+ * CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex;
*/
DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
-static void cgroup_wakeup_rmdir_waiters(const struct cgroup *cgrp)
+static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp)
{
- if (unlikely(test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
+ if (unlikely(test_and_clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
wake_up_all(&cgroup_rmdir_waitq);
}
+void cgroup_exclude_rmdir(struct cgroup_subsys_state *css)
+{
+ css_get(css);
+}
+
+void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css)
+{
+ cgroup_wakeup_rmdir_waiter(css->cgroup);
+ css_put(css);
+}
+
+
static int rebind_subsystems(struct cgroupfs_root *root,
unsigned long final_bits)
{
@@ -960,6 +973,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
INIT_LIST_HEAD(&cgrp->children);
INIT_LIST_HEAD(&cgrp->css_sets);
INIT_LIST_HEAD(&cgrp->release_list);
+ INIT_LIST_HEAD(&cgrp->pids_list);
init_rwsem(&cgrp->pids_mutex);
}
static void init_cgroup_root(struct cgroupfs_root *root)
@@ -1357,7 +1371,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
* wake up rmdir() waiter. the rmdir should fail since the cgroup
* is no longer empty.
*/
- cgroup_wakeup_rmdir_waiters(cgrp);
+ cgroup_wakeup_rmdir_waiter(cgrp);
return 0;
}
@@ -2201,12 +2215,30 @@ err:
return ret;
}
+/*
+ * Cache pids for all threads in the same pid namespace that are
+ * opening the same "tasks" file.
+ */
+struct cgroup_pids {
+ /* The node in cgrp->pids_list */
+ struct list_head list;
+ /* The cgroup those pids belong to */
+ struct cgroup *cgrp;
+ /* The namepsace those pids belong to */
+ struct pid_namespace *ns;
+ /* Array of process ids in the cgroup */
+ pid_t *tasks_pids;
+ /* How many files are using the this tasks_pids array */
+ int use_count;
+ /* Length of the current tasks_pids array */
+ int length;
+};
+
static int cmppid(const void *a, const void *b)
{
return *(pid_t *)a - *(pid_t *)b;
}
-
/*
* seq_file methods for the "tasks" file. The seq_file position is the
* next pid to display; the seq_file iterator is a pointer to the pid
@@ -2221,45 +2253,47 @@ static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
* after a seek to the start). Use a binary-search to find the
* next pid to display, if any
*/
- struct cgroup *cgrp = s->private;
+ struct cgroup_pids *cp = s->private;
+ struct cgroup *cgrp = cp->cgrp;
int index = 0, pid = *pos;
int *iter;
down_read(&cgrp->pids_mutex);
if (pid) {
- int end = cgrp->pids_length;
+ int end = cp->length;
while (index < end) {
int mid = (index + end) / 2;
- if (cgrp->tasks_pids[mid] == pid) {
+ if (cp->tasks_pids[mid] == pid) {
index = mid;
break;
- } else if (cgrp->tasks_pids[mid] <= pid)
+ } else if (cp->tasks_pids[mid] <= pid)
index = mid + 1;
else
end = mid;
}
}
/* If we're off the end of the array, we're done */
- if (index >= cgrp->pids_length)
+ if (index >= cp->length)
return NULL;
/* Update the abstract position to be the actual pid that we found */
- iter = cgrp->tasks_pids + index;
+ iter = cp->tasks_pids + index;
*pos = *iter;
return iter;
}
static void cgroup_tasks_stop(struct seq_file *s, void *v)
{
- struct cgroup *cgrp = s->private;
+ struct cgroup_pids *cp = s->private;
+ struct cgroup *cgrp = cp->cgrp;
up_read(&cgrp->pids_mutex);
}
static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
{
- struct cgroup *cgrp = s->private;
+ struct cgroup_pids *cp = s->private;
int *p = v;
- int *end = cgrp->tasks_pids + cgrp->pids_length;
+ int *end = cp->tasks_pids + cp->length;
/*
* Advance to the next pid in the array. If this goes off the
@@ -2286,26 +2320,33 @@ static struct seq_operations cgroup_tasks_seq_operations = {
.show = cgroup_tasks_show,
};
-static void release_cgroup_pid_array(struct cgroup *cgrp)
+static void release_cgroup_pid_array(struct cgroup_pids *cp)
{
+ struct cgroup *cgrp = cp->cgrp;
+
down_write(&cgrp->pids_mutex);
- BUG_ON(!cgrp->pids_use_count);
- if (!--cgrp->pids_use_count) {
- kfree(cgrp->tasks_pids);
- cgrp->tasks_pids = NULL;
- cgrp->pids_length = 0;
+ BUG_ON(!cp->use_count);
+ if (!--cp->use_count) {
+ list_del(&cp->list);
+ put_pid_ns(cp->ns);
+ kfree(cp->tasks_pids);
+ kfree(cp);
}
up_write(&cgrp->pids_mutex);
}
static int cgroup_tasks_release(struct inode *inode, struct file *file)
{
- struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
+ struct seq_file *seq;
+ struct cgroup_pids *cp;
if (!(file->f_mode & FMODE_READ))
return 0;
- release_cgroup_pid_array(cgrp);
+ seq = file->private_data;
+ cp = seq->private;
+
+ release_cgroup_pid_array(cp);
return seq_release(inode, file);
}
@@ -2324,6 +2365,8 @@ static struct file_operations cgroup_tasks_operations = {
static int cgroup_tasks_open(struct inode *unused, struct file *file)
{
struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
+ struct pid_namespace *ns = current->nsproxy->pid_ns;
+ struct cgroup_pids *cp;
pid_t *pidarray;
int npids;
int retval;
@@ -2350,20 +2393,37 @@ static int cgroup_tasks_open(struct inode *unused, struct file *file)
* array if necessary
*/
down_write(&cgrp->pids_mutex);
- kfree(cgrp->tasks_pids);
- cgrp->tasks_pids = pidarray;
- cgrp->pids_length = npids;
- cgrp->pids_use_count++;
+
+ list_for_each_entry(cp, &cgrp->pids_list, list) {
+ if (ns == cp->ns)
+ goto found;
+ }
+
+ cp = kzalloc(sizeof(*cp), GFP_KERNEL);
+ if (!cp) {
+ up_write(&cgrp->pids_mutex);
+ kfree(pidarray);
+ return -ENOMEM;
+ }
+ cp->cgrp = cgrp;
+ cp->ns = ns;
+ get_pid_ns(ns);
+ list_add(&cp->list, &cgrp->pids_list);
+found:
+ kfree(cp->tasks_pids);
+ cp->tasks_pids = pidarray;
+ cp->length = npids;
+ cp->use_count++;
up_write(&cgrp->pids_mutex);
file->f_op = &cgroup_tasks_operations;
retval = seq_open(file, &cgroup_tasks_seq_operations);
if (retval) {
- release_cgroup_pid_array(cgrp);
+ release_cgroup_pid_array(cp);
return retval;
}
- ((struct seq_file *)file->private_data)->private = cgrp;
+ ((struct seq_file *)file->private_data)->private = cp;
return 0;
}
@@ -2696,33 +2756,42 @@ again:
mutex_unlock(&cgroup_mutex);
/*
+ * In general, subsystem has no css->refcnt after pre_destroy(). But
+ * in racy cases, subsystem may have to get css->refcnt after
+ * pre_destroy() and it makes rmdir return with -EBUSY. This sometimes
+ * make rmdir return -EBUSY too often. To avoid that, we use waitqueue
+ * for cgroup's rmdir. CGRP_WAIT_ON_RMDIR is for synchronizing rmdir
+ * and subsystem's reference count handling. Please see css_get/put
+ * and css_tryget() and cgroup_wakeup_rmdir_waiter() implementation.
+ */
+ set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
+
+ /*
* Call pre_destroy handlers of subsys. Notify subsystems
* that rmdir() request comes.
*/
ret = cgroup_call_pre_destroy(cgrp);
- if (ret)
+ if (ret) {
+ clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
return ret;
+ }
mutex_lock(&cgroup_mutex);
parent = cgrp->parent;
if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
+ clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
mutex_unlock(&cgroup_mutex);
return -EBUSY;
}
- /*
- * css_put/get is provided for subsys to grab refcnt to css. In typical
- * case, subsystem has no reference after pre_destroy(). But, under
- * hierarchy management, some *temporal* refcnt can be hold.
- * To avoid returning -EBUSY to a user, waitqueue is used. If subsys
- * is really busy, it should return -EBUSY at pre_destroy(). wake_up
- * is called when css_put() is called and refcnt goes down to 0.
- */
- set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE);
-
if (!cgroup_clear_css_refs(cgrp)) {
mutex_unlock(&cgroup_mutex);
- schedule();
+ /*
+ * Because someone may call cgroup_wakeup_rmdir_waiter() before
+ * prepare_to_wait(), we need to check this flag.
+ */
+ if (test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags))
+ schedule();
finish_wait(&cgroup_rmdir_waitq, &wait);
clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
if (signal_pending(current))
@@ -3294,7 +3363,7 @@ void __css_put(struct cgroup_subsys_state *css)
set_bit(CGRP_RELEASABLE, &cgrp->flags);
check_for_release(cgrp);
}
- cgroup_wakeup_rmdir_waiters(cgrp);
+ cgroup_wakeup_rmdir_waiter(cgrp);
}
rcu_read_unlock();
}
diff --git a/kernel/exit.c b/kernel/exit.c
index 628d41f0dd5..869dc221733 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -12,7 +12,6 @@
#include <linux/completion.h>
#include <linux/personality.h>
#include <linux/tty.h>
-#include <linux/mnt_namespace.h>
#include <linux/iocontext.h>
#include <linux/key.h>
#include <linux/security.h>
diff --git a/kernel/fork.c b/kernel/fork.c
index 467746b3f0a..466531eb92c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -17,7 +17,6 @@
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/completion.h>
-#include <linux/mnt_namespace.h>
#include <linux/personality.h>
#include <linux/mempolicy.h>
#include <linux/sem.h>
@@ -427,6 +426,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
init_rwsem(&mm->mmap_sem);
INIT_LIST_HEAD(&mm->mmlist);
mm->flags = (current->mm) ? current->mm->flags : default_dump_filter;
+ mm->oom_adj = (current->mm) ? current->mm->oom_adj : 0;
mm->core_state = NULL;
mm->nr_ptes = 0;
set_mm_counter(mm, file_rss, 0);
@@ -1269,6 +1269,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
write_unlock_irq(&tasklist_lock);
proc_fork_connector(p);
cgroup_post_fork(p);
+ perf_counter_fork(p);
return p;
bad_fork_free_pid:
@@ -1408,12 +1409,6 @@ long do_fork(unsigned long clone_flags,
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
- } else if (!(clone_flags & CLONE_VM)) {
- /*
- * vfork will do an exec which will call
- * set_task_comm()
- */
- perf_counter_fork(p);
}
audit_finish_fork(p);
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 2f4936cf708..bd1d42b17cb 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -44,12 +44,19 @@ void refrigerator(void)
recalc_sigpending(); /* We sent fake signal, clean it up */
spin_unlock_irq(&current->sighand->siglock);
+ /* prevent accounting of that task to load */
+ current->flags |= PF_FREEZING;
+
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (!frozen(current))
break;
schedule();
}
+
+ /* Remove the accounting blocker */
+ current->flags &= ~PF_FREEZING;
+
pr_debug("%s left refrigerator\n", current->comm);
__set_current_state(save);
}
diff --git a/kernel/futex.c b/kernel/futex.c
index 1c337112335..0672ff88f15 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -247,6 +247,7 @@ again:
if (err < 0)
return err;
+ page = compound_head(page);
lock_page(page);
if (!page->mapping) {
unlock_page(page);
@@ -299,7 +300,7 @@ void put_futex_key(int fshared, union futex_key *key)
static int fault_in_user_writeable(u32 __user *uaddr)
{
int ret = get_user_pages(current, current->mm, (unsigned long)uaddr,
- sizeof(*uaddr), 1, 0, NULL, NULL);
+ 1, 1, 0, NULL, NULL);
return ret < 0 ? ret : 0;
}
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 9002958a96e..49da79ab848 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -191,6 +191,46 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
}
}
+
+/*
+ * Get the preferred target CPU for NOHZ
+ */
+static int hrtimer_get_target(int this_cpu, int pinned)
+{
+#ifdef CONFIG_NO_HZ
+ if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) {
+ int preferred_cpu = get_nohz_load_balancer();
+
+ if (preferred_cpu >= 0)
+ return preferred_cpu;
+ }
+#endif
+ return this_cpu;
+}
+
+/*
+ * With HIGHRES=y we do not migrate the timer when it is expiring
+ * before the next event on the target cpu because we cannot reprogram
+ * the target cpu hardware and we would cause it to fire late.
+ *
+ * Called with cpu_base->lock of target cpu held.
+ */
+static int
+hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
+{
+#ifdef CONFIG_HIGH_RES_TIMERS
+ ktime_t expires;
+
+ if (!new_base->cpu_base->hres_active)
+ return 0;
+
+ expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
+ return expires.tv64 <= new_base->cpu_base->expires_next.tv64;
+#else
+ return 0;
+#endif
+}
+
/*
* Switch the timer base to the current CPU when possible.
*/
@@ -200,16 +240,8 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
{
struct hrtimer_clock_base *new_base;
struct hrtimer_cpu_base *new_cpu_base;
- int cpu, preferred_cpu = -1;
-
- cpu = smp_processor_id();
-#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
- if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) {
- preferred_cpu = get_nohz_load_balancer();
- if (preferred_cpu >= 0)
- cpu = preferred_cpu;
- }
-#endif
+ int this_cpu = smp_processor_id();
+ int cpu = hrtimer_get_target(this_cpu, pinned);
again:
new_cpu_base = &per_cpu(hrtimer_bases, cpu);
@@ -217,7 +249,7 @@ again:
if (base != new_base) {
/*
- * We are trying to schedule the timer on the local CPU.
+ * We are trying to move timer to new_base.
* However we can't change timer's base while it is running,
* so we keep it on the same CPU. No hassle vs. reprogramming
* the event source in the high resolution case. The softirq
@@ -233,38 +265,12 @@ again:
spin_unlock(&base->cpu_base->lock);
spin_lock(&new_base->cpu_base->lock);
- /* Optimized away for NOHZ=n SMP=n */
- if (cpu == preferred_cpu) {
- /* Calculate clock monotonic expiry time */
-#ifdef CONFIG_HIGH_RES_TIMERS
- ktime_t expires = ktime_sub(hrtimer_get_expires(timer),
- new_base->offset);
-#else
- ktime_t expires = hrtimer_get_expires(timer);
-#endif
-
- /*
- * Get the next event on target cpu from the
- * clock events layer.
- * This covers the highres=off nohz=on case as well.
- */
- ktime_t next = clockevents_get_next_event(cpu);
-
- ktime_t delta = ktime_sub(expires, next);
-
- /*
- * We do not migrate the timer when it is expiring
- * before the next event on the target cpu because
- * we cannot reprogram the target cpu hardware and
- * we would cause it to fire late.
- */
- if (delta.tv64 < 0) {
- cpu = smp_processor_id();
- spin_unlock(&new_base->cpu_base->lock);
- spin_lock(&base->cpu_base->lock);
- timer->base = base;
- goto again;
- }
+ if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
+ cpu = this_cpu;
+ spin_unlock(&new_base->cpu_base->lock);
+ spin_lock(&base->cpu_base->lock);
+ timer->base = base;
+ goto again;
}
timer->base = new_base;
}
@@ -1276,14 +1282,22 @@ void hrtimer_interrupt(struct clock_event_device *dev)
expires_next.tv64 = KTIME_MAX;
+ spin_lock(&cpu_base->lock);
+ /*
+ * We set expires_next to KTIME_MAX here with cpu_base->lock
+ * held to prevent that a timer is enqueued in our queue via
+ * the migration code. This does not affect enqueueing of
+ * timers which run their callback and need to be requeued on
+ * this CPU.
+ */
+ cpu_base->expires_next.tv64 = KTIME_MAX;
+
base = cpu_base->clock_base;
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
ktime_t basenow;
struct rb_node *node;
- spin_lock(&cpu_base->lock);
-
basenow = ktime_add(now, base->offset);
while ((node = base->first)) {
@@ -1316,11 +1330,15 @@ void hrtimer_interrupt(struct clock_event_device *dev)
__run_hrtimer(timer);
}
- spin_unlock(&cpu_base->lock);
base++;
}
+ /*
+ * Store the new expiry value so the migration code can verify
+ * against it.
+ */
cpu_base->expires_next = expires_next;
+ spin_unlock(&cpu_base->lock);
/* Reprogramming necessary ? */
if (expires_next.tv64 != KTIME_MAX) {
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 73468253143..e70ed5592eb 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -42,8 +42,7 @@ static inline void unregister_handler_proc(unsigned int irq,
extern int irq_select_affinity_usr(unsigned int irq);
-extern void
-irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask);
+extern void irq_set_thread_affinity(struct irq_desc *desc);
/*
* Debugging printout:
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 50da6767290..61c679db468 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -80,14 +80,22 @@ int irq_can_set_affinity(unsigned int irq)
return 1;
}
-void
-irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask)
+/**
+ * irq_set_thread_affinity - Notify irq threads to adjust affinity
+ * @desc: irq descriptor which has affitnity changed
+ *
+ * We just set IRQTF_AFFINITY and delegate the affinity setting
+ * to the interrupt thread itself. We can not call
+ * set_cpus_allowed_ptr() here as we hold desc->lock and this
+ * code can be called from hard interrupt context.
+ */
+void irq_set_thread_affinity(struct irq_desc *desc)
{
struct irqaction *action = desc->action;
while (action) {
if (action->thread)
- set_cpus_allowed_ptr(action->thread, cpumask);
+ set_bit(IRQTF_AFFINITY, &action->thread_flags);
action = action->next;
}
}
@@ -112,7 +120,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
if (desc->status & IRQ_MOVE_PCNTXT) {
if (!desc->chip->set_affinity(irq, cpumask)) {
cpumask_copy(desc->affinity, cpumask);
- irq_set_thread_affinity(desc, cpumask);
+ irq_set_thread_affinity(desc);
}
}
else {
@@ -122,7 +130,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
#else
if (!desc->chip->set_affinity(irq, cpumask)) {
cpumask_copy(desc->affinity, cpumask);
- irq_set_thread_affinity(desc, cpumask);
+ irq_set_thread_affinity(desc);
}
#endif
desc->status |= IRQ_AFFINITY_SET;
@@ -176,7 +184,7 @@ int irq_select_affinity_usr(unsigned int irq)
spin_lock_irqsave(&desc->lock, flags);
ret = setup_affinity(irq, desc);
if (!ret)
- irq_set_thread_affinity(desc, desc->affinity);
+ irq_set_thread_affinity(desc);
spin_unlock_irqrestore(&desc->lock, flags);
return ret;
@@ -443,6 +451,39 @@ static int irq_wait_for_interrupt(struct irqaction *action)
return -1;
}
+#ifdef CONFIG_SMP
+/*
+ * Check whether we need to change the affinity of the interrupt thread.
+ */
+static void
+irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
+{
+ cpumask_var_t mask;
+
+ if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags))
+ return;
+
+ /*
+ * In case we are out of memory we set IRQTF_AFFINITY again and
+ * try again next time
+ */
+ if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
+ set_bit(IRQTF_AFFINITY, &action->thread_flags);
+ return;
+ }
+
+ spin_lock_irq(&desc->lock);
+ cpumask_copy(mask, desc->affinity);
+ spin_unlock_irq(&desc->lock);
+
+ set_cpus_allowed_ptr(current, mask);
+ free_cpumask_var(mask);
+}
+#else
+static inline void
+irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
+#endif
+
/*
* Interrupt handler thread
*/
@@ -458,6 +499,8 @@ static int irq_thread(void *data)
while (!irq_wait_for_interrupt(action)) {
+ irq_thread_check_affinity(desc, action);
+
atomic_inc(&desc->threads_active);
spin_lock_irq(&desc->lock);
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index cfe767ca154..fcb6c96f262 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -45,7 +45,7 @@ void move_masked_irq(int irq)
< nr_cpu_ids))
if (!desc->chip->set_affinity(irq, desc->pending_mask)) {
cpumask_copy(desc->affinity, desc->pending_mask);
- irq_set_thread_affinity(desc, desc->pending_mask);
+ irq_set_thread_affinity(desc);
}
cpumask_clear(desc->pending_mask);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index ae1c35201cc..f336e2107f9 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1228,7 +1228,7 @@ static int __init parse_crashkernel_mem(char *cmdline,
} while (*cur++ == ',');
if (*crash_size > 0) {
- while (*cur != ' ' && *cur != '@')
+ while (*cur && *cur != ' ' && *cur != '@')
cur++;
if (*cur == '@') {
cur++;
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 7e95bedb2bf..385c31a1bdb 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -24,7 +24,6 @@
#include <linux/unistd.h>
#include <linux/kmod.h>
#include <linux/slab.h>
-#include <linux/mnt_namespace.h>
#include <linux/completion.h>
#include <linux/file.h>
#include <linux/fdtable.h>
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index c0fa54b276d..0540948e29a 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -237,13 +237,9 @@ static int __kprobes collect_garbage_slots(void)
{
struct kprobe_insn_page *kip;
struct hlist_node *pos, *next;
- int safety;
/* Ensure no-one is preepmted on the garbages */
- mutex_unlock(&kprobe_insn_mutex);
- safety = check_safety();
- mutex_lock(&kprobe_insn_mutex);
- if (safety != 0)
+ if (check_safety())
return -EAGAIN;
hlist_for_each_entry_safe(kip, pos, next, &kprobe_insn_pages, hlist) {
@@ -698,7 +694,7 @@ int __kprobes register_kprobe(struct kprobe *p)
p->addr = addr;
preempt_disable();
- if (!__kernel_text_address((unsigned long) p->addr) ||
+ if (!kernel_text_address((unsigned long) p->addr) ||
in_kprobes_functions((unsigned long) p->addr)) {
preempt_enable();
return -EINVAL;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 9b1a7de2697..eb8751aa041 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -180,10 +180,12 @@ EXPORT_SYMBOL(kthread_bind);
* @k: thread created by kthread_create().
*
* Sets kthread_should_stop() for @k to return true, wakes it, and
- * waits for it to exit. Your threadfn() must not call do_exit()
- * itself if you use this function! This can also be called after
- * kthread_create() instead of calling wake_up_process(): the thread
- * will exit without calling threadfn().
+ * waits for it to exit. This can also be called after kthread_create()
+ * instead of calling wake_up_process(): the thread will exit without
+ * calling threadfn().
+ *
+ * If threadfn() may call do_exit() itself, the caller must ensure
+ * task_struct can't go away.
*
* Returns the result of threadfn(), or %-EINTR if wake_up_process()
* was never called.
diff --git a/kernel/module.c b/kernel/module.c
index 38928fcaff2..fd141140355 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1068,7 +1068,8 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs,
{
const unsigned long *crc;
- if (!find_symbol("module_layout", NULL, &crc, true, false))
+ if (!find_symbol(MODULE_SYMBOL_PREFIX "module_layout", NULL,
+ &crc, true, false))
BUG();
return check_version(sechdrs, versindex, "module_layout", mod, crc);
}
@@ -2451,9 +2452,9 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
return ret;
}
if (ret > 0) {
- printk(KERN_WARNING "%s: '%s'->init suspiciously returned %d, "
- "it should follow 0/-E convention\n"
- KERN_WARNING "%s: loading module anyway...\n",
+ printk(KERN_WARNING
+"%s: '%s'->init suspiciously returned %d, it should follow 0/-E convention\n"
+"%s: loading module anyway...\n",
__func__, mod->name, ret,
__func__);
dump_stack();
diff --git a/kernel/panic.c b/kernel/panic.c
index 984b3ecbd72..512ab73b0ca 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -301,6 +301,7 @@ int oops_may_print(void)
*/
void oops_enter(void)
{
+ tracing_off();
/* can't trust the integrity of the kernel anymore: */
debug_locks_off();
do_oops_enter_exit();
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 1a933a221ea..199ed477131 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -42,6 +42,7 @@ static int perf_overcommit __read_mostly = 1;
static atomic_t nr_counters __read_mostly;
static atomic_t nr_mmap_counters __read_mostly;
static atomic_t nr_comm_counters __read_mostly;
+static atomic_t nr_task_counters __read_mostly;
/*
* perf counter paranoia level:
@@ -146,6 +147,28 @@ static void put_ctx(struct perf_counter_context *ctx)
}
}
+static void unclone_ctx(struct perf_counter_context *ctx)
+{
+ if (ctx->parent_ctx) {
+ put_ctx(ctx->parent_ctx);
+ ctx->parent_ctx = NULL;
+ }
+}
+
+/*
+ * If we inherit counters we want to return the parent counter id
+ * to userspace.
+ */
+static u64 primary_counter_id(struct perf_counter *counter)
+{
+ u64 id = counter->id;
+
+ if (counter->parent)
+ id = counter->parent->id;
+
+ return id;
+}
+
/*
* Get the perf_counter_context for a task and lock it.
* This has to cope with with the fact that until it is locked,
@@ -236,6 +259,8 @@ list_add_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
list_add_rcu(&counter->event_entry, &ctx->event_list);
ctx->nr_counters++;
+ if (counter->attr.inherit_stat)
+ ctx->nr_stat++;
}
/*
@@ -250,6 +275,8 @@ list_del_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
if (list_empty(&counter->list_entry))
return;
ctx->nr_counters--;
+ if (counter->attr.inherit_stat)
+ ctx->nr_stat--;
list_del_init(&counter->list_entry);
list_del_rcu(&counter->event_entry);
@@ -1006,6 +1033,81 @@ static int context_equiv(struct perf_counter_context *ctx1,
&& !ctx1->pin_count && !ctx2->pin_count;
}
+static void __perf_counter_read(void *counter);
+
+static void __perf_counter_sync_stat(struct perf_counter *counter,
+ struct perf_counter *next_counter)
+{
+ u64 value;
+
+ if (!counter->attr.inherit_stat)
+ return;
+
+ /*
+ * Update the counter value, we cannot use perf_counter_read()
+ * because we're in the middle of a context switch and have IRQs
+ * disabled, which upsets smp_call_function_single(), however
+ * we know the counter must be on the current CPU, therefore we
+ * don't need to use it.
+ */
+ switch (counter->state) {
+ case PERF_COUNTER_STATE_ACTIVE:
+ __perf_counter_read(counter);
+ break;
+
+ case PERF_COUNTER_STATE_INACTIVE:
+ update_counter_times(counter);
+ break;
+
+ default:
+ break;
+ }
+
+ /*
+ * In order to keep per-task stats reliable we need to flip the counter
+ * values when we flip the contexts.
+ */
+ value = atomic64_read(&next_counter->count);
+ value = atomic64_xchg(&counter->count, value);
+ atomic64_set(&next_counter->count, value);
+
+ swap(counter->total_time_enabled, next_counter->total_time_enabled);
+ swap(counter->total_time_running, next_counter->total_time_running);
+
+ /*
+ * Since we swizzled the values, update the user visible data too.
+ */
+ perf_counter_update_userpage(counter);
+ perf_counter_update_userpage(next_counter);
+}
+
+#define list_next_entry(pos, member) \
+ list_entry(pos->member.next, typeof(*pos), member)
+
+static void perf_counter_sync_stat(struct perf_counter_context *ctx,
+ struct perf_counter_context *next_ctx)
+{
+ struct perf_counter *counter, *next_counter;
+
+ if (!ctx->nr_stat)
+ return;
+
+ counter = list_first_entry(&ctx->event_list,
+ struct perf_counter, event_entry);
+
+ next_counter = list_first_entry(&next_ctx->event_list,
+ struct perf_counter, event_entry);
+
+ while (&counter->event_entry != &ctx->event_list &&
+ &next_counter->event_entry != &next_ctx->event_list) {
+
+ __perf_counter_sync_stat(counter, next_counter);
+
+ counter = list_next_entry(counter, event_entry);
+ next_counter = list_next_entry(counter, event_entry);
+ }
+}
+
/*
* Called from scheduler to remove the counters of the current task,
* with interrupts disabled.
@@ -1061,6 +1163,8 @@ void perf_counter_task_sched_out(struct task_struct *task,
ctx->task = next;
next_ctx->task = task;
do_switch = 0;
+
+ perf_counter_sync_stat(ctx, next_ctx);
}
spin_unlock(&next_ctx->lock);
spin_unlock(&ctx->lock);
@@ -1207,7 +1311,6 @@ static void perf_counter_cpu_sched_in(struct perf_cpu_context *cpuctx, int cpu)
#define MAX_INTERRUPTS (~0ULL)
static void perf_log_throttle(struct perf_counter *counter, int enable);
-static void perf_log_period(struct perf_counter *counter, u64 period);
static void perf_adjust_period(struct perf_counter *counter, u64 events)
{
@@ -1226,8 +1329,6 @@ static void perf_adjust_period(struct perf_counter *counter, u64 events)
if (!sample_period)
sample_period = 1;
- perf_log_period(counter, sample_period);
-
hwc->sample_period = sample_period;
}
@@ -1348,9 +1449,54 @@ void perf_counter_task_tick(struct task_struct *curr, int cpu)
}
/*
+ * Enable all of a task's counters that have been marked enable-on-exec.
+ * This expects task == current.
+ */
+static void perf_counter_enable_on_exec(struct task_struct *task)
+{
+ struct perf_counter_context *ctx;
+ struct perf_counter *counter;
+ unsigned long flags;
+ int enabled = 0;
+
+ local_irq_save(flags);
+ ctx = task->perf_counter_ctxp;
+ if (!ctx || !ctx->nr_counters)
+ goto out;
+
+ __perf_counter_task_sched_out(ctx);
+
+ spin_lock(&ctx->lock);
+
+ list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+ if (!counter->attr.enable_on_exec)
+ continue;
+ counter->attr.enable_on_exec = 0;
+ if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
+ continue;
+ counter->state = PERF_COUNTER_STATE_INACTIVE;
+ counter->tstamp_enabled =
+ ctx->time - counter->total_time_enabled;
+ enabled = 1;
+ }
+
+ /*
+ * Unclone this context if we enabled any counter.
+ */
+ if (enabled)
+ unclone_ctx(ctx);
+
+ spin_unlock(&ctx->lock);
+
+ perf_counter_task_sched_in(task, smp_processor_id());
+ out:
+ local_irq_restore(flags);
+}
+
+/*
* Cross CPU call to read the hardware counter
*/
-static void __read(void *info)
+static void __perf_counter_read(void *info)
{
struct perf_counter *counter = info;
struct perf_counter_context *ctx = counter->ctx;
@@ -1372,7 +1518,7 @@ static u64 perf_counter_read(struct perf_counter *counter)
*/
if (counter->state == PERF_COUNTER_STATE_ACTIVE) {
smp_call_function_single(counter->oncpu,
- __read, counter, 1);
+ __perf_counter_read, counter, 1);
} else if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
update_counter_times(counter);
}
@@ -1398,7 +1544,6 @@ __perf_counter_init_context(struct perf_counter_context *ctx,
static struct perf_counter_context *find_get_context(pid_t pid, int cpu)
{
- struct perf_counter_context *parent_ctx;
struct perf_counter_context *ctx;
struct perf_cpu_context *cpuctx;
struct task_struct *task;
@@ -1458,11 +1603,7 @@ static struct perf_counter_context *find_get_context(pid_t pid, int cpu)
retry:
ctx = perf_lock_task_context(task, &flags);
if (ctx) {
- parent_ctx = ctx->parent_ctx;
- if (parent_ctx) {
- put_ctx(parent_ctx);
- ctx->parent_ctx = NULL; /* no longer a clone */
- }
+ unclone_ctx(ctx);
spin_unlock_irqrestore(&ctx->lock, flags);
}
@@ -1508,11 +1649,15 @@ static void free_counter(struct perf_counter *counter)
{
perf_pending_sync(counter);
- atomic_dec(&nr_counters);
- if (counter->attr.mmap)
- atomic_dec(&nr_mmap_counters);
- if (counter->attr.comm)
- atomic_dec(&nr_comm_counters);
+ if (!counter->parent) {
+ atomic_dec(&nr_counters);
+ if (counter->attr.mmap)
+ atomic_dec(&nr_mmap_counters);
+ if (counter->attr.comm)
+ atomic_dec(&nr_comm_counters);
+ if (counter->attr.task)
+ atomic_dec(&nr_task_counters);
+ }
if (counter->destroy)
counter->destroy(counter);
@@ -1546,6 +1691,18 @@ static int perf_release(struct inode *inode, struct file *file)
return 0;
}
+static u64 perf_counter_read_tree(struct perf_counter *counter)
+{
+ struct perf_counter *child;
+ u64 total = 0;
+
+ total += perf_counter_read(counter);
+ list_for_each_entry(child, &counter->child_list, child_list)
+ total += perf_counter_read(child);
+
+ return total;
+}
+
/*
* Read the performance counter - simple non blocking version for now
*/
@@ -1565,7 +1722,7 @@ perf_read_hw(struct perf_counter *counter, char __user *buf, size_t count)
WARN_ON_ONCE(counter->ctx->parent_ctx);
mutex_lock(&counter->child_mutex);
- values[0] = perf_counter_read(counter);
+ values[0] = perf_counter_read_tree(counter);
n = 1;
if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
values[n++] = counter->total_time_enabled +
@@ -1574,7 +1731,7 @@ perf_read_hw(struct perf_counter *counter, char __user *buf, size_t count)
values[n++] = counter->total_time_running +
atomic64_read(&counter->child_total_time_running);
if (counter->attr.read_format & PERF_FORMAT_ID)
- values[n++] = counter->id;
+ values[n++] = primary_counter_id(counter);
mutex_unlock(&counter->child_mutex);
if (count < n * sizeof(u64))
@@ -1681,8 +1838,6 @@ static int perf_counter_period(struct perf_counter *counter, u64 __user *arg)
counter->attr.sample_freq = value;
} else {
- perf_log_period(counter, value);
-
counter->attr.sample_period = value;
counter->hw.sample_period = value;
}
@@ -1751,6 +1906,14 @@ int perf_counter_task_disable(void)
return 0;
}
+static int perf_counter_index(struct perf_counter *counter)
+{
+ if (counter->state != PERF_COUNTER_STATE_ACTIVE)
+ return 0;
+
+ return counter->hw.idx + 1 - PERF_COUNTER_INDEX_OFFSET;
+}
+
/*
* Callers need to ensure there can be no nesting of this function, otherwise
* the seqlock logic goes bad. We can not serialize this because the arch
@@ -1775,11 +1938,17 @@ void perf_counter_update_userpage(struct perf_counter *counter)
preempt_disable();
++userpg->lock;
barrier();
- userpg->index = counter->hw.idx;
+ userpg->index = perf_counter_index(counter);
userpg->offset = atomic64_read(&counter->count);
if (counter->state == PERF_COUNTER_STATE_ACTIVE)
userpg->offset -= atomic64_read(&counter->hw.prev_count);
+ userpg->time_enabled = counter->total_time_enabled +
+ atomic64_read(&counter->child_total_time_enabled);
+
+ userpg->time_running = counter->total_time_running +
+ atomic64_read(&counter->child_total_time_running);
+
barrier();
++userpg->lock;
preempt_enable();
@@ -1876,7 +2045,7 @@ fail:
static void perf_mmap_free_page(unsigned long addr)
{
- struct page *page = virt_to_page(addr);
+ struct page *page = virt_to_page((void *)addr);
page->mapping = NULL;
__free_page(page);
@@ -2483,15 +2652,14 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
u32 cpu, reserved;
} cpu_entry;
- header.type = 0;
+ header.type = PERF_EVENT_SAMPLE;
header.size = sizeof(header);
- header.misc = PERF_EVENT_MISC_OVERFLOW;
+ header.misc = 0;
header.misc |= perf_misc_flags(data->regs);
if (sample_type & PERF_SAMPLE_IP) {
ip = perf_instruction_pointer(data->regs);
- header.type |= PERF_SAMPLE_IP;
header.size += sizeof(ip);
}
@@ -2500,7 +2668,6 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
tid_entry.pid = perf_counter_pid(counter, current);
tid_entry.tid = perf_counter_tid(counter, current);
- header.type |= PERF_SAMPLE_TID;
header.size += sizeof(tid_entry);
}
@@ -2510,34 +2677,29 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
*/
time = sched_clock();
- header.type |= PERF_SAMPLE_TIME;
header.size += sizeof(u64);
}
- if (sample_type & PERF_SAMPLE_ADDR) {
- header.type |= PERF_SAMPLE_ADDR;
+ if (sample_type & PERF_SAMPLE_ADDR)
+ header.size += sizeof(u64);
+
+ if (sample_type & PERF_SAMPLE_ID)
header.size += sizeof(u64);
- }
- if (sample_type & PERF_SAMPLE_ID) {
- header.type |= PERF_SAMPLE_ID;
+ if (sample_type & PERF_SAMPLE_STREAM_ID)
header.size += sizeof(u64);
- }
if (sample_type & PERF_SAMPLE_CPU) {
- header.type |= PERF_SAMPLE_CPU;
header.size += sizeof(cpu_entry);
cpu_entry.cpu = raw_smp_processor_id();
+ cpu_entry.reserved = 0;
}
- if (sample_type & PERF_SAMPLE_PERIOD) {
- header.type |= PERF_SAMPLE_PERIOD;
+ if (sample_type & PERF_SAMPLE_PERIOD)
header.size += sizeof(u64);
- }
if (sample_type & PERF_SAMPLE_GROUP) {
- header.type |= PERF_SAMPLE_GROUP;
header.size += sizeof(u64) +
counter->nr_siblings * sizeof(group_entry);
}
@@ -2547,10 +2709,9 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
if (callchain) {
callchain_size = (1 + callchain->nr) * sizeof(u64);
-
- header.type |= PERF_SAMPLE_CALLCHAIN;
header.size += callchain_size;
- }
+ } else
+ header.size += sizeof(u64);
}
ret = perf_output_begin(&handle, counter, header.size, nmi, 1);
@@ -2571,7 +2732,13 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
if (sample_type & PERF_SAMPLE_ADDR)
perf_output_put(&handle, data->addr);
- if (sample_type & PERF_SAMPLE_ID)
+ if (sample_type & PERF_SAMPLE_ID) {
+ u64 id = primary_counter_id(counter);
+
+ perf_output_put(&handle, id);
+ }
+
+ if (sample_type & PERF_SAMPLE_STREAM_ID)
perf_output_put(&handle, counter->id);
if (sample_type & PERF_SAMPLE_CPU)
@@ -2594,24 +2761,85 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
if (sub != counter)
sub->pmu->read(sub);
- group_entry.id = sub->id;
+ group_entry.id = primary_counter_id(sub);
group_entry.counter = atomic64_read(&sub->count);
perf_output_put(&handle, group_entry);
}
}
- if (callchain)
- perf_output_copy(&handle, callchain, callchain_size);
+ if (sample_type & PERF_SAMPLE_CALLCHAIN) {
+ if (callchain)
+ perf_output_copy(&handle, callchain, callchain_size);
+ else {
+ u64 nr = 0;
+ perf_output_put(&handle, nr);
+ }
+ }
+
+ perf_output_end(&handle);
+}
+
+/*
+ * read event
+ */
+
+struct perf_read_event {
+ struct perf_event_header header;
+
+ u32 pid;
+ u32 tid;
+ u64 value;
+ u64 format[3];
+};
+
+static void
+perf_counter_read_event(struct perf_counter *counter,
+ struct task_struct *task)
+{
+ struct perf_output_handle handle;
+ struct perf_read_event event = {
+ .header = {
+ .type = PERF_EVENT_READ,
+ .misc = 0,
+ .size = sizeof(event) - sizeof(event.format),
+ },
+ .pid = perf_counter_pid(counter, task),
+ .tid = perf_counter_tid(counter, task),
+ .value = atomic64_read(&counter->count),
+ };
+ int ret, i = 0;
+
+ if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+ event.header.size += sizeof(u64);
+ event.format[i++] = counter->total_time_enabled;
+ }
+
+ if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+ event.header.size += sizeof(u64);
+ event.format[i++] = counter->total_time_running;
+ }
+
+ if (counter->attr.read_format & PERF_FORMAT_ID) {
+ event.header.size += sizeof(u64);
+ event.format[i++] = primary_counter_id(counter);
+ }
+ ret = perf_output_begin(&handle, counter, event.header.size, 0, 0);
+ if (ret)
+ return;
+
+ perf_output_copy(&handle, &event, event.header.size);
perf_output_end(&handle);
}
/*
- * fork tracking
+ * task tracking -- fork/exit
+ *
+ * enabled by: attr.comm | attr.mmap | attr.task
*/
-struct perf_fork_event {
+struct perf_task_event {
struct task_struct *task;
struct {
@@ -2619,37 +2847,42 @@ struct perf_fork_event {
u32 pid;
u32 ppid;
+ u32 tid;
+ u32 ptid;
} event;
};
-static void perf_counter_fork_output(struct perf_counter *counter,
- struct perf_fork_event *fork_event)
+static void perf_counter_task_output(struct perf_counter *counter,
+ struct perf_task_event *task_event)
{
struct perf_output_handle handle;
- int size = fork_event->event.header.size;
- struct task_struct *task = fork_event->task;
+ int size = task_event->event.header.size;
+ struct task_struct *task = task_event->task;
int ret = perf_output_begin(&handle, counter, size, 0, 0);
if (ret)
return;
- fork_event->event.pid = perf_counter_pid(counter, task);
- fork_event->event.ppid = perf_counter_pid(counter, task->real_parent);
+ task_event->event.pid = perf_counter_pid(counter, task);
+ task_event->event.ppid = perf_counter_pid(counter, task->real_parent);
- perf_output_put(&handle, fork_event->event);
+ task_event->event.tid = perf_counter_tid(counter, task);
+ task_event->event.ptid = perf_counter_tid(counter, task->real_parent);
+
+ perf_output_put(&handle, task_event->event);
perf_output_end(&handle);
}
-static int perf_counter_fork_match(struct perf_counter *counter)
+static int perf_counter_task_match(struct perf_counter *counter)
{
- if (counter->attr.comm || counter->attr.mmap)
+ if (counter->attr.comm || counter->attr.mmap || counter->attr.task)
return 1;
return 0;
}
-static void perf_counter_fork_ctx(struct perf_counter_context *ctx,
- struct perf_fork_event *fork_event)
+static void perf_counter_task_ctx(struct perf_counter_context *ctx,
+ struct perf_task_event *task_event)
{
struct perf_counter *counter;
@@ -2658,19 +2891,19 @@ static void perf_counter_fork_ctx(struct perf_counter_context *ctx,
rcu_read_lock();
list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
- if (perf_counter_fork_match(counter))
- perf_counter_fork_output(counter, fork_event);
+ if (perf_counter_task_match(counter))
+ perf_counter_task_output(counter, task_event);
}
rcu_read_unlock();
}
-static void perf_counter_fork_event(struct perf_fork_event *fork_event)
+static void perf_counter_task_event(struct perf_task_event *task_event)
{
struct perf_cpu_context *cpuctx;
struct perf_counter_context *ctx;
cpuctx = &get_cpu_var(perf_cpu_context);
- perf_counter_fork_ctx(&cpuctx->ctx, fork_event);
+ perf_counter_task_ctx(&cpuctx->ctx, task_event);
put_cpu_var(perf_cpu_context);
rcu_read_lock();
@@ -2680,29 +2913,40 @@ static void perf_counter_fork_event(struct perf_fork_event *fork_event)
*/
ctx = rcu_dereference(current->perf_counter_ctxp);
if (ctx)
- perf_counter_fork_ctx(ctx, fork_event);
+ perf_counter_task_ctx(ctx, task_event);
rcu_read_unlock();
}
-void perf_counter_fork(struct task_struct *task)
+static void perf_counter_task(struct task_struct *task, int new)
{
- struct perf_fork_event fork_event;
+ struct perf_task_event task_event;
if (!atomic_read(&nr_comm_counters) &&
- !atomic_read(&nr_mmap_counters))
+ !atomic_read(&nr_mmap_counters) &&
+ !atomic_read(&nr_task_counters))
return;
- fork_event = (struct perf_fork_event){
+ task_event = (struct perf_task_event){
.task = task,
.event = {
.header = {
- .type = PERF_EVENT_FORK,
- .size = sizeof(fork_event.event),
+ .type = new ? PERF_EVENT_FORK : PERF_EVENT_EXIT,
+ .misc = 0,
+ .size = sizeof(task_event.event),
},
+ /* .pid */
+ /* .ppid */
+ /* .tid */
+ /* .ptid */
},
};
- perf_counter_fork_event(&fork_event);
+ perf_counter_task_event(&task_event);
+}
+
+void perf_counter_fork(struct task_struct *task)
+{
+ perf_counter_task(task, 1);
}
/*
@@ -2770,8 +3014,10 @@ static void perf_counter_comm_event(struct perf_comm_event *comm_event)
struct perf_cpu_context *cpuctx;
struct perf_counter_context *ctx;
unsigned int size;
- char *comm = comm_event->task->comm;
+ char comm[TASK_COMM_LEN];
+ memset(comm, 0, sizeof(comm));
+ strncpy(comm, comm_event->task->comm, sizeof(comm));
size = ALIGN(strlen(comm)+1, sizeof(u64));
comm_event->comm = comm;
@@ -2798,13 +3044,24 @@ void perf_counter_comm(struct task_struct *task)
{
struct perf_comm_event comm_event;
+ if (task->perf_counter_ctxp)
+ perf_counter_enable_on_exec(task);
+
if (!atomic_read(&nr_comm_counters))
return;
comm_event = (struct perf_comm_event){
.task = task,
+ /* .comm */
+ /* .comm_size */
.event = {
- .header = { .type = PERF_EVENT_COMM, },
+ .header = {
+ .type = PERF_EVENT_COMM,
+ .misc = 0,
+ /* .size */
+ },
+ /* .pid */
+ /* .tid */
},
};
@@ -2887,8 +3144,15 @@ static void perf_counter_mmap_event(struct perf_mmap_event *mmap_event)
char *buf = NULL;
const char *name;
+ memset(tmp, 0, sizeof(tmp));
+
if (file) {
- buf = kzalloc(PATH_MAX, GFP_KERNEL);
+ /*
+ * d_path works from the end of the buffer backwards, so we
+ * need to add enough zero bytes after the string to handle
+ * the 64bit alignment we do later.
+ */
+ buf = kzalloc(PATH_MAX + sizeof(u64), GFP_KERNEL);
if (!buf) {
name = strncpy(tmp, "//enomem", sizeof(tmp));
goto got_name;
@@ -2899,9 +3163,11 @@ static void perf_counter_mmap_event(struct perf_mmap_event *mmap_event)
goto got_name;
}
} else {
- name = arch_vma_name(mmap_event->vma);
- if (name)
+ if (arch_vma_name(mmap_event->vma)) {
+ name = strncpy(tmp, arch_vma_name(mmap_event->vma),
+ sizeof(tmp));
goto got_name;
+ }
if (!vma->vm_mm) {
name = strncpy(tmp, "[vdso]", sizeof(tmp));
@@ -2946,8 +3212,16 @@ void __perf_counter_mmap(struct vm_area_struct *vma)
mmap_event = (struct perf_mmap_event){
.vma = vma,
+ /* .file_name */
+ /* .file_size */
.event = {
- .header = { .type = PERF_EVENT_MMAP, },
+ .header = {
+ .type = PERF_EVENT_MMAP,
+ .misc = 0,
+ /* .size */
+ },
+ /* .pid */
+ /* .tid */
.start = vma->vm_start,
.len = vma->vm_end - vma->vm_start,
.pgoff = vma->vm_pgoff,
@@ -2958,49 +3232,6 @@ void __perf_counter_mmap(struct vm_area_struct *vma)
}
/*
- * Log sample_period changes so that analyzing tools can re-normalize the
- * event flow.
- */
-
-struct freq_event {
- struct perf_event_header header;
- u64 time;
- u64 id;
- u64 period;
-};
-
-static void perf_log_period(struct perf_counter *counter, u64 period)
-{
- struct perf_output_handle handle;
- struct freq_event event;
- int ret;
-
- if (counter->hw.sample_period == period)
- return;
-
- if (counter->attr.sample_type & PERF_SAMPLE_PERIOD)
- return;
-
- event = (struct freq_event) {
- .header = {
- .type = PERF_EVENT_PERIOD,
- .misc = 0,
- .size = sizeof(event),
- },
- .time = sched_clock(),
- .id = counter->id,
- .period = period,
- };
-
- ret = perf_output_begin(&handle, counter, sizeof(event), 1, 0);
- if (ret)
- return;
-
- perf_output_put(&handle, event);
- perf_output_end(&handle);
-}
-
-/*
* IRQ throttle logging
*/
@@ -3013,16 +3244,21 @@ static void perf_log_throttle(struct perf_counter *counter, int enable)
struct perf_event_header header;
u64 time;
u64 id;
+ u64 stream_id;
} throttle_event = {
.header = {
- .type = PERF_EVENT_THROTTLE + 1,
+ .type = PERF_EVENT_THROTTLE,
.misc = 0,
.size = sizeof(throttle_event),
},
- .time = sched_clock(),
- .id = counter->id,
+ .time = sched_clock(),
+ .id = primary_counter_id(counter),
+ .stream_id = counter->id,
};
+ if (enable)
+ throttle_event.header.type = PERF_EVENT_UNTHROTTLE;
+
ret = perf_output_begin(&handle, counter, sizeof(throttle_event), 1, 0);
if (ret)
return;
@@ -3317,8 +3553,8 @@ out:
put_cpu_var(perf_cpu_context);
}
-void
-perf_swcounter_event(u32 event, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
+void __perf_swcounter_event(u32 event, u64 nr, int nmi,
+ struct pt_regs *regs, u64 addr)
{
struct perf_sample_data data = {
.regs = regs,
@@ -3470,7 +3706,7 @@ static const struct pmu perf_ops_task_clock = {
void perf_tpcounter_event(int event_id)
{
struct perf_sample_data data = {
- .regs = get_irq_regs();
+ .regs = get_irq_regs(),
.addr = 0,
};
@@ -3486,16 +3722,12 @@ extern void ftrace_profile_disable(int);
static void tp_perf_counter_destroy(struct perf_counter *counter)
{
- ftrace_profile_disable(perf_event_id(&counter->attr));
+ ftrace_profile_disable(counter->attr.config);
}
static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
{
- int event_id = perf_event_id(&counter->attr);
- int ret;
-
- ret = ftrace_profile_enable(event_id);
- if (ret)
+ if (ftrace_profile_enable(counter->attr.config))
return NULL;
counter->destroy = tp_perf_counter_destroy;
@@ -3509,9 +3741,21 @@ static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
}
#endif
+atomic_t perf_swcounter_enabled[PERF_COUNT_SW_MAX];
+
+static void sw_perf_counter_destroy(struct perf_counter *counter)
+{
+ u64 event = counter->attr.config;
+
+ WARN_ON(counter->parent);
+
+ atomic_dec(&perf_swcounter_enabled[event]);
+}
+
static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
{
const struct pmu *pmu = NULL;
+ u64 event = counter->attr.config;
/*
* Software counters (currently) can't in general distinguish
@@ -3520,7 +3764,7 @@ static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
* to be kernel events, and page faults are never hypervisor
* events.
*/
- switch (counter->attr.config) {
+ switch (event) {
case PERF_COUNT_SW_CPU_CLOCK:
pmu = &perf_ops_cpu_clock;
@@ -3541,6 +3785,10 @@ static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
case PERF_COUNT_SW_CONTEXT_SWITCHES:
case PERF_COUNT_SW_CPU_MIGRATIONS:
+ if (!counter->parent) {
+ atomic_inc(&perf_swcounter_enabled[event]);
+ counter->destroy = sw_perf_counter_destroy;
+ }
pmu = &perf_ops_generic;
break;
}
@@ -3556,6 +3804,7 @@ perf_counter_alloc(struct perf_counter_attr *attr,
int cpu,
struct perf_counter_context *ctx,
struct perf_counter *group_leader,
+ struct perf_counter *parent_counter,
gfp_t gfpflags)
{
const struct pmu *pmu;
@@ -3591,6 +3840,8 @@ perf_counter_alloc(struct perf_counter_attr *attr,
counter->ctx = ctx;
counter->oncpu = -1;
+ counter->parent = parent_counter;
+
counter->ns = get_pid_ns(current->nsproxy->pid_ns);
counter->id = atomic64_inc_return(&perf_counter_id);
@@ -3648,11 +3899,15 @@ done:
counter->pmu = pmu;
- atomic_inc(&nr_counters);
- if (counter->attr.mmap)
- atomic_inc(&nr_mmap_counters);
- if (counter->attr.comm)
- atomic_inc(&nr_comm_counters);
+ if (!counter->parent) {
+ atomic_inc(&nr_counters);
+ if (counter->attr.mmap)
+ atomic_inc(&nr_mmap_counters);
+ if (counter->attr.comm)
+ atomic_inc(&nr_comm_counters);
+ if (counter->attr.task)
+ atomic_inc(&nr_task_counters);
+ }
return counter;
}
@@ -3815,7 +4070,7 @@ SYSCALL_DEFINE5(perf_counter_open,
}
counter = perf_counter_alloc(&attr, cpu, ctx, group_leader,
- GFP_KERNEL);
+ NULL, GFP_KERNEL);
ret = PTR_ERR(counter);
if (IS_ERR(counter))
goto err_put_context;
@@ -3881,7 +4136,8 @@ inherit_counter(struct perf_counter *parent_counter,
child_counter = perf_counter_alloc(&parent_counter->attr,
parent_counter->cpu, child_ctx,
- group_leader, GFP_KERNEL);
+ group_leader, parent_counter,
+ GFP_KERNEL);
if (IS_ERR(child_counter))
return child_counter;
get_ctx(child_ctx);
@@ -3904,12 +4160,6 @@ inherit_counter(struct perf_counter *parent_counter,
*/
add_counter_to_ctx(child_counter, child_ctx);
- child_counter->parent = parent_counter;
- /*
- * inherit into child's child as well:
- */
- child_counter->attr.inherit = 1;
-
/*
* Get a reference to the parent filp - we will fput it
* when the child counter exits. This is safe to do because
@@ -3953,10 +4203,14 @@ static int inherit_group(struct perf_counter *parent_counter,
}
static void sync_child_counter(struct perf_counter *child_counter,
- struct perf_counter *parent_counter)
+ struct task_struct *child)
{
+ struct perf_counter *parent_counter = child_counter->parent;
u64 child_val;
+ if (child_counter->attr.inherit_stat)
+ perf_counter_read_event(child_counter, child);
+
child_val = atomic64_read(&child_counter->count);
/*
@@ -3985,7 +4239,8 @@ static void sync_child_counter(struct perf_counter *child_counter,
static void
__perf_counter_exit_task(struct perf_counter *child_counter,
- struct perf_counter_context *child_ctx)
+ struct perf_counter_context *child_ctx,
+ struct task_struct *child)
{
struct perf_counter *parent_counter;
@@ -3999,7 +4254,7 @@ __perf_counter_exit_task(struct perf_counter *child_counter,
* counters need to be zapped - but otherwise linger.
*/
if (parent_counter) {
- sync_child_counter(child_counter, parent_counter);
+ sync_child_counter(child_counter, child);
free_counter(child_counter);
}
}
@@ -4013,8 +4268,10 @@ void perf_counter_exit_task(struct task_struct *child)
struct perf_counter_context *child_ctx;
unsigned long flags;
- if (likely(!child->perf_counter_ctxp))
+ if (likely(!child->perf_counter_ctxp)) {
+ perf_counter_task(child, 0);
return;
+ }
local_irq_save(flags);
/*
@@ -4032,18 +4289,22 @@ void perf_counter_exit_task(struct task_struct *child)
* incremented the context's refcount before we do put_ctx below.
*/
spin_lock(&child_ctx->lock);
+ /*
+ * If this context is a clone; unclone it so it can't get
+ * swapped to another process while we're removing all
+ * the counters from it.
+ */
+ unclone_ctx(child_ctx);
+ spin_unlock_irqrestore(&child_ctx->lock, flags);
+
+ /*
+ * Report the task dead after unscheduling the counters so that we
+ * won't get any samples after PERF_EVENT_EXIT. We can however still
+ * get a few PERF_EVENT_READ events.
+ */
+ perf_counter_task(child, 0);
+
child->perf_counter_ctxp = NULL;
- if (child_ctx->parent_ctx) {
- /*
- * This context is a clone; unclone it so it can't get
- * swapped to another process while we're removing all
- * the counters from it.
- */
- put_ctx(child_ctx->parent_ctx);
- child_ctx->parent_ctx = NULL;
- }
- spin_unlock(&child_ctx->lock);
- local_irq_restore(flags);
/*
* We can recurse on the same lock type through:
@@ -4061,7 +4322,7 @@ void perf_counter_exit_task(struct task_struct *child)
again:
list_for_each_entry_safe(child_counter, tmp, &child_ctx->counter_list,
list_entry)
- __perf_counter_exit_task(child_counter, child_ctx);
+ __perf_counter_exit_task(child_counter, child_ctx, child);
/*
* If the last counter was a group counter, it will have appended all
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 052ec4d195c..d089d052c4a 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -202,6 +202,12 @@ static int no_timer_create(struct k_itimer *new_timer)
return -EOPNOTSUPP;
}
+static int no_nsleep(const clockid_t which_clock, int flags,
+ struct timespec *tsave, struct timespec __user *rmtp)
+{
+ return -EOPNOTSUPP;
+}
+
/*
* Return nonzero if we know a priori this clockid_t value is bogus.
*/
@@ -254,6 +260,7 @@ static __init int init_posix_timers(void)
.clock_get = posix_get_monotonic_raw,
.clock_set = do_posix_clock_nosettime,
.timer_create = no_timer_create,
+ .nsleep = no_nsleep,
};
register_posix_clock(CLOCK_REALTIME, &clock_realtime);
diff --git a/kernel/power/user.c b/kernel/power/user.c
index ed97375daae..bf0014d6a5f 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -23,7 +23,6 @@
#include <linux/console.h>
#include <linux/cpu.h>
#include <linux/freezer.h>
-#include <linux/smp_lock.h>
#include <scsi/scsi_scan.h>
#include <asm/uaccess.h>
diff --git a/kernel/profile.c b/kernel/profile.c
index 69911b5745e..419250ebec4 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -117,11 +117,12 @@ int __ref profile_init(void)
cpumask_copy(prof_cpu_mask, cpu_possible_mask);
- prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL);
+ prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL|__GFP_NOWARN);
if (prof_buffer)
return 0;
- prof_buffer = alloc_pages_exact(buffer_bytes, GFP_KERNEL|__GFP_ZERO);
+ prof_buffer = alloc_pages_exact(buffer_bytes,
+ GFP_KERNEL|__GFP_ZERO|__GFP_NOWARN);
if (prof_buffer)
return 0;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 61c78b2c07b..082c320e4db 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -181,8 +181,8 @@ int ptrace_attach(struct task_struct *task)
* interference; SUID, SGID and LSM creds get determined differently
* under ptrace.
*/
- retval = mutex_lock_interruptible(&task->cred_guard_mutex);
- if (retval < 0)
+ retval = -ERESTARTNOINTR;
+ if (mutex_lock_interruptible(&task->cred_guard_mutex))
goto out;
task_lock(task);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 0dccfbba6d2..7717b95c202 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1533,7 +1533,7 @@ void __init __rcu_init(void)
int j;
struct rcu_node *rnp;
- printk(KERN_WARNING "Experimental hierarchical RCU implementation.\n");
+ printk(KERN_INFO "Hierarchical RCU implementation.\n");
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
@@ -1546,7 +1546,6 @@ void __init __rcu_init(void)
rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE, (void *)(long)i);
/* Register notifier for non-boot CPUs */
register_cpu_notifier(&rcu_nb);
- printk(KERN_WARNING "Experimental hierarchical RCU init done.\n");
}
module_param(blimit, int, 0);
diff --git a/kernel/resource.c b/kernel/resource.c
index ac5f3a36923..78b087221c1 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -787,7 +787,7 @@ static int __init reserve_setup(char *str)
static struct resource reserve[MAXRESERVE];
for (;;) {
- int io_start, io_num;
+ unsigned int io_start, io_num;
int x = reserved;
if (get_option (&str, &io_start) != 2)
diff --git a/kernel/sched.c b/kernel/sched.c
index 7c9098d186e..1b59e265273 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -493,6 +493,7 @@ struct rt_rq {
#endif
#ifdef CONFIG_SMP
unsigned long rt_nr_migratory;
+ unsigned long rt_nr_total;
int overloaded;
struct plist_head pushable_tasks;
#endif
@@ -2571,15 +2572,37 @@ static void __sched_fork(struct task_struct *p)
p->se.avg_wakeup = sysctl_sched_wakeup_granularity;
#ifdef CONFIG_SCHEDSTATS
- p->se.wait_start = 0;
- p->se.sum_sleep_runtime = 0;
- p->se.sleep_start = 0;
- p->se.block_start = 0;
- p->se.sleep_max = 0;
- p->se.block_max = 0;
- p->se.exec_max = 0;
- p->se.slice_max = 0;
- p->se.wait_max = 0;
+ p->se.wait_start = 0;
+ p->se.wait_max = 0;
+ p->se.wait_count = 0;
+ p->se.wait_sum = 0;
+
+ p->se.sleep_start = 0;
+ p->se.sleep_max = 0;
+ p->se.sum_sleep_runtime = 0;
+
+ p->se.block_start = 0;
+ p->se.block_max = 0;
+ p->se.exec_max = 0;
+ p->se.slice_max = 0;
+
+ p->se.nr_migrations_cold = 0;
+ p->se.nr_failed_migrations_affine = 0;
+ p->se.nr_failed_migrations_running = 0;
+ p->se.nr_failed_migrations_hot = 0;
+ p->se.nr_forced_migrations = 0;
+ p->se.nr_forced2_migrations = 0;
+
+ p->se.nr_wakeups = 0;
+ p->se.nr_wakeups_sync = 0;
+ p->se.nr_wakeups_migrate = 0;
+ p->se.nr_wakeups_local = 0;
+ p->se.nr_wakeups_remote = 0;
+ p->se.nr_wakeups_affine = 0;
+ p->se.nr_wakeups_affine_attempts = 0;
+ p->se.nr_wakeups_passive = 0;
+ p->se.nr_wakeups_idle = 0;
+
#endif
INIT_LIST_HEAD(&p->rt.run_list);
@@ -6541,6 +6564,11 @@ SYSCALL_DEFINE0(sched_yield)
return 0;
}
+static inline int should_resched(void)
+{
+ return need_resched() && !(preempt_count() & PREEMPT_ACTIVE);
+}
+
static void __cond_resched(void)
{
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
@@ -6560,8 +6588,7 @@ static void __cond_resched(void)
int __sched _cond_resched(void)
{
- if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) &&
- system_state == SYSTEM_RUNNING) {
+ if (should_resched()) {
__cond_resched();
return 1;
}
@@ -6579,12 +6606,12 @@ EXPORT_SYMBOL(_cond_resched);
*/
int cond_resched_lock(spinlock_t *lock)
{
- int resched = need_resched() && system_state == SYSTEM_RUNNING;
+ int resched = should_resched();
int ret = 0;
if (spin_needbreak(lock) || resched) {
spin_unlock(lock);
- if (resched && need_resched())
+ if (resched)
__cond_resched();
else
cpu_relax();
@@ -6599,7 +6626,7 @@ int __sched cond_resched_softirq(void)
{
BUG_ON(!in_softirq());
- if (need_resched() && system_state == SYSTEM_RUNNING) {
+ if (should_resched()) {
local_bh_enable();
__cond_resched();
local_bh_disable();
@@ -7262,6 +7289,7 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
static void calc_global_load_remove(struct rq *rq)
{
atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
+ rq->calc_load_active = 0;
}
#endif /* CONFIG_HOTPLUG_CPU */
@@ -7488,6 +7516,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
task_rq_unlock(rq, &flags);
get_task_struct(p);
cpu_rq(cpu)->migration_thread = p;
+ rq->calc_load_update = calc_load_update;
break;
case CPU_ONLINE:
@@ -7498,8 +7527,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
/* Update our root-domain */
rq = cpu_rq(cpu);
spin_lock_irqsave(&rq->lock, flags);
- rq->calc_load_update = calc_load_update;
- rq->calc_load_active = 0;
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
@@ -9070,7 +9097,7 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
#ifdef CONFIG_SMP
rt_rq->rt_nr_migratory = 0;
rt_rq->overloaded = 0;
- plist_head_init(&rq->rt.pushable_tasks, &rq->lock);
+ plist_head_init(&rt_rq->pushable_tasks, &rq->lock);
#endif
rt_rq->rt_time = 0;
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index e6c251790dd..d014efbf947 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -81,8 +81,21 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
continue;
- if (lowest_mask)
+ if (lowest_mask) {
cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
+
+ /*
+ * We have to ensure that we have at least one bit
+ * still set in the array, since the map could have
+ * been concurrently emptied between the first and
+ * second reads of vec->mask. If we hit this
+ * condition, simply act as though we never hit this
+ * priority level and continue on.
+ */
+ if (cpumask_any(lowest_mask) >= nr_cpu_ids)
+ continue;
+ }
+
return 1;
}
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index ba7fd6e9556..652e8bdef9a 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -266,6 +266,12 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
return min_vruntime;
}
+static inline int entity_before(struct sched_entity *a,
+ struct sched_entity *b)
+{
+ return (s64)(a->vruntime - b->vruntime) < 0;
+}
+
static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
return se->vruntime - cfs_rq->min_vruntime;
@@ -605,9 +611,13 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_SCHEDSTATS
+ struct task_struct *tsk = NULL;
+
+ if (entity_is_task(se))
+ tsk = task_of(se);
+
if (se->sleep_start) {
u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
- struct task_struct *tsk = task_of(se);
if ((s64)delta < 0)
delta = 0;
@@ -618,11 +628,11 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
se->sleep_start = 0;
se->sum_sleep_runtime += delta;
- account_scheduler_latency(tsk, delta >> 10, 1);
+ if (tsk)
+ account_scheduler_latency(tsk, delta >> 10, 1);
}
if (se->block_start) {
u64 delta = rq_of(cfs_rq)->clock - se->block_start;
- struct task_struct *tsk = task_of(se);
if ((s64)delta < 0)
delta = 0;
@@ -633,17 +643,19 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
se->block_start = 0;
se->sum_sleep_runtime += delta;
- /*
- * Blocking time is in units of nanosecs, so shift by 20 to
- * get a milliseconds-range estimation of the amount of
- * time that the task spent sleeping:
- */
- if (unlikely(prof_on == SLEEP_PROFILING)) {
-
- profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
- delta >> 20);
+ if (tsk) {
+ /*
+ * Blocking time is in units of nanosecs, so shift by
+ * 20 to get a milliseconds-range estimation of the
+ * amount of time that the task spent sleeping:
+ */
+ if (unlikely(prof_on == SLEEP_PROFILING)) {
+ profile_hits(SLEEP_PROFILING,
+ (void *)get_wchan(tsk),
+ delta >> 20);
+ }
+ account_scheduler_latency(tsk, delta >> 10, 0);
}
- account_scheduler_latency(tsk, delta >> 10, 0);
}
#endif
}
@@ -687,7 +699,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
* all of which have the same weight.
*/
if (sched_feat(NORMALIZED_SLEEPER) &&
- task_of(se)->policy != SCHED_IDLE)
+ (!entity_is_task(se) ||
+ task_of(se)->policy != SCHED_IDLE))
thresh = calc_delta_fair(thresh, se);
vruntime -= thresh;
@@ -1016,7 +1029,7 @@ static void yield_task_fair(struct rq *rq)
/*
* Already in the rightmost position?
*/
- if (unlikely(!rightmost || rightmost->vruntime < se->vruntime))
+ if (unlikely(!rightmost || entity_before(rightmost, se)))
return;
/*
@@ -1712,7 +1725,7 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
/* 'curr' will be NULL if the child belongs to a different group */
if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) &&
- curr && curr->vruntime < se->vruntime) {
+ curr && entity_before(curr, se)) {
/*
* Upon rescheduling, sched_class::put_prev_task() will place
* 'current' within the tree based on its new key value.
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 9bf0d2a7304..3918e01994e 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -10,6 +10,8 @@ static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
#ifdef CONFIG_RT_GROUP_SCHED
+#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)
+
static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
{
return rt_rq->rq;
@@ -22,6 +24,8 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
#else /* CONFIG_RT_GROUP_SCHED */
+#define rt_entity_is_task(rt_se) (1)
+
static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
{
return container_of(rt_rq, struct rq, rt);
@@ -73,7 +77,7 @@ static inline void rt_clear_overload(struct rq *rq)
static void update_rt_migration(struct rt_rq *rt_rq)
{
- if (rt_rq->rt_nr_migratory && (rt_rq->rt_nr_running > 1)) {
+ if (rt_rq->rt_nr_migratory && rt_rq->rt_nr_total > 1) {
if (!rt_rq->overloaded) {
rt_set_overload(rq_of_rt_rq(rt_rq));
rt_rq->overloaded = 1;
@@ -86,6 +90,12 @@ static void update_rt_migration(struct rt_rq *rt_rq)
static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
+ if (!rt_entity_is_task(rt_se))
+ return;
+
+ rt_rq = &rq_of_rt_rq(rt_rq)->rt;
+
+ rt_rq->rt_nr_total++;
if (rt_se->nr_cpus_allowed > 1)
rt_rq->rt_nr_migratory++;
@@ -94,6 +104,12 @@ static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
+ if (!rt_entity_is_task(rt_se))
+ return;
+
+ rt_rq = &rq_of_rt_rq(rt_rq)->rt;
+
+ rt_rq->rt_nr_total--;
if (rt_se->nr_cpus_allowed > 1)
rt_rq->rt_nr_migratory--;
diff --git a/kernel/signal.c b/kernel/signal.c
index ccf1ceedaeb..64c5deeaca5 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2454,11 +2454,9 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s
stack_t oss;
int error;
- if (uoss) {
- oss.ss_sp = (void __user *) current->sas_ss_sp;
- oss.ss_size = current->sas_ss_size;
- oss.ss_flags = sas_ss_flags(sp);
- }
+ oss.ss_sp = (void __user *) current->sas_ss_sp;
+ oss.ss_size = current->sas_ss_size;
+ oss.ss_flags = sas_ss_flags(sp);
if (uss) {
void __user *ss_sp;
@@ -2466,10 +2464,12 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s
int ss_flags;
error = -EFAULT;
- if (!access_ok(VERIFY_READ, uss, sizeof(*uss))
- || __get_user(ss_sp, &uss->ss_sp)
- || __get_user(ss_flags, &uss->ss_flags)
- || __get_user(ss_size, &uss->ss_size))
+ if (!access_ok(VERIFY_READ, uss, sizeof(*uss)))
+ goto out;
+ error = __get_user(ss_sp, &uss->ss_sp) |
+ __get_user(ss_flags, &uss->ss_flags) |
+ __get_user(ss_size, &uss->ss_size);
+ if (error)
goto out;
error = -EPERM;
@@ -2501,13 +2501,16 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s
current->sas_ss_size = ss_size;
}
+ error = 0;
if (uoss) {
error = -EFAULT;
- if (copy_to_user(uoss, &oss, sizeof(oss)))
+ if (!access_ok(VERIFY_WRITE, uoss, sizeof(*uoss)))
goto out;
+ error = __put_user(oss.ss_sp, &uoss->ss_sp) |
+ __put_user(oss.ss_size, &uoss->ss_size) |
+ __put_user(oss.ss_flags, &uoss->ss_flags);
}
- error = 0;
out:
return error;
}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 3a94905fa5d..eb5e131a048 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -345,7 +345,9 @@ void open_softirq(int nr, void (*action)(struct softirq_action *))
softirq_vec[nr].action = action;
}
-/* Tasklets */
+/*
+ * Tasklets
+ */
struct tasklet_head
{
struct tasklet_struct *head;
@@ -493,6 +495,66 @@ void tasklet_kill(struct tasklet_struct *t)
EXPORT_SYMBOL(tasklet_kill);
+/*
+ * tasklet_hrtimer
+ */
+
+/*
+ * The trampoline is called when the hrtimer expires. If this is
+ * called from the hrtimer interrupt then we schedule the tasklet as
+ * the timer callback function expects to run in softirq context. If
+ * it's called in softirq context anyway (i.e. high resolution timers
+ * disabled) then the hrtimer callback is called right away.
+ */
+static enum hrtimer_restart __hrtimer_tasklet_trampoline(struct hrtimer *timer)
+{
+ struct tasklet_hrtimer *ttimer =
+ container_of(timer, struct tasklet_hrtimer, timer);
+
+ if (hrtimer_is_hres_active(timer)) {
+ tasklet_hi_schedule(&ttimer->tasklet);
+ return HRTIMER_NORESTART;
+ }
+ return ttimer->function(timer);
+}
+
+/*
+ * Helper function which calls the hrtimer callback from
+ * tasklet/softirq context
+ */
+static void __tasklet_hrtimer_trampoline(unsigned long data)
+{
+ struct tasklet_hrtimer *ttimer = (void *)data;
+ enum hrtimer_restart restart;
+
+ restart = ttimer->function(&ttimer->timer);
+ if (restart != HRTIMER_NORESTART)
+ hrtimer_restart(&ttimer->timer);
+}
+
+/**
+ * tasklet_hrtimer_init - Init a tasklet/hrtimer combo for softirq callbacks
+ * @ttimer: tasklet_hrtimer which is initialized
+ * @function: hrtimer callback funtion which gets called from softirq context
+ * @which_clock: clock id (CLOCK_MONOTONIC/CLOCK_REALTIME)
+ * @mode: hrtimer mode (HRTIMER_MODE_ABS/HRTIMER_MODE_REL)
+ */
+void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
+ enum hrtimer_restart (*function)(struct hrtimer *),
+ clockid_t which_clock, enum hrtimer_mode mode)
+{
+ hrtimer_init(&ttimer->timer, which_clock, mode);
+ ttimer->timer.function = __hrtimer_tasklet_trampoline;
+ tasklet_init(&ttimer->tasklet, __tasklet_hrtimer_trampoline,
+ (unsigned long)ttimer);
+ ttimer->function = function;
+}
+EXPORT_SYMBOL_GPL(tasklet_hrtimer_init);
+
+/*
+ * Remote softirq bits
+ */
+
DEFINE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
EXPORT_PER_CPU_SYMBOL(softirq_work_list);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 62e4ff9968b..98e02328c67 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -335,7 +335,10 @@ static struct ctl_table kern_table[] = {
.data = &sysctl_timer_migration,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_dointvec_minmax,
+ .strategy = &sysctl_intvec,
+ .extra1 = &zero,
+ .extra2 = &one,
},
#endif
{
@@ -744,6 +747,14 @@ static struct ctl_table kern_table[] = {
.proc_handler = &proc_dointvec,
},
{
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "panic_on_io_nmi",
+ .data = &panic_on_io_nmi,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
+ {
.ctl_name = KERN_BOOTLOADER_TYPE,
.procname = "bootloader_type",
.data = &bootloader_type,
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 1ad6dd46111..a6dcd67b041 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -254,15 +254,4 @@ void clockevents_notify(unsigned long reason, void *arg)
spin_unlock(&clockevents_lock);
}
EXPORT_SYMBOL_GPL(clockevents_notify);
-
-ktime_t clockevents_get_next_event(int cpu)
-{
- struct tick_device *td;
- struct clock_event_device *dev;
-
- td = &per_cpu(tick_cpu_device, cpu);
- dev = td->evtdev;
-
- return dev->next_event;
-}
#endif
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 592bf584d1d..7466cb81125 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -513,7 +513,7 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev,
* Check to make sure we don't switch to a non-highres capable
* clocksource if the tick code is in oneshot mode (highres or nohz)
*/
- if (tick_oneshot_mode_active() &&
+ if (tick_oneshot_mode_active() && ovr &&
!(ovr->flags & CLOCK_SOURCE_VALID_FOR_HRES)) {
printk(KERN_WARNING "%s clocksource is not HRT compatible. "
"Cannot switch while in HRT/NOHZ mode\n", ovr->name);
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
index c994530d166..4cde8b9c716 100644
--- a/kernel/time/timer_stats.c
+++ b/kernel/time/timer_stats.c
@@ -96,7 +96,7 @@ static DEFINE_MUTEX(show_mutex);
/*
* Collection status, active/inactive:
*/
-static int __read_mostly active;
+int __read_mostly timer_stats_active;
/*
* Beginning/end timestamps of measurement:
@@ -242,7 +242,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
struct entry *entry, input;
unsigned long flags;
- if (likely(!active))
+ if (likely(!timer_stats_active))
return;
lock = &per_cpu(lookup_lock, raw_smp_processor_id());
@@ -254,7 +254,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
input.timer_flag = timer_flag;
spin_lock_irqsave(lock, flags);
- if (!active)
+ if (!timer_stats_active)
goto out_unlock;
entry = tstat_lookup(&input, comm);
@@ -290,7 +290,7 @@ static int tstats_show(struct seq_file *m, void *v)
/*
* If still active then calculate up to now:
*/
- if (active)
+ if (timer_stats_active)
time_stop = ktime_get();
time = ktime_sub(time_stop, time_start);
@@ -368,18 +368,18 @@ static ssize_t tstats_write(struct file *file, const char __user *buf,
mutex_lock(&show_mutex);
switch (ctl[0]) {
case '0':
- if (active) {
- active = 0;
+ if (timer_stats_active) {
+ timer_stats_active = 0;
time_stop = ktime_get();
sync_access();
}
break;
case '1':
- if (!active) {
+ if (!timer_stats_active) {
reset_entries();
time_start = ktime_get();
smp_mb();
- active = 1;
+ timer_stats_active = 1;
}
break;
default:
diff --git a/kernel/timer.c b/kernel/timer.c
index 54d3912f8ca..a7f07d5a624 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -380,6 +380,8 @@ static void timer_stats_account_timer(struct timer_list *timer)
{
unsigned int flag = 0;
+ if (likely(!timer->start_site))
+ return;
if (unlikely(tbase_get_deferrable(timer->base)))
flag |= TIMER_STATS_FLAG_DEFERRABLE;
@@ -712,7 +714,7 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
* networking code - if the timer is re-modified
* to be the same thing then just return:
*/
- if (timer->expires == expires && timer_pending(timer))
+ if (timer_pending(timer) && timer->expires == expires)
return 1;
return __mod_timer(timer, expires, false, TIMER_NOT_PINNED);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 1551f47e766..019f380fd76 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -226,13 +226,13 @@ config BOOT_TRACER
the timings of the initcalls and traces key events and the identity
of tasks that can cause boot delays, such as context-switches.
- Its aim is to be parsed by the /scripts/bootgraph.pl tool to
+ Its aim is to be parsed by the scripts/bootgraph.pl tool to
produce pretty graphics about boot inefficiencies, giving a visual
representation of the delays during initcalls - but the raw
/debug/tracing/trace text output is readable too.
- You must pass in ftrace=initcall to the kernel command line
- to enable this on bootup.
+ You must pass in initcall_debug and ftrace=initcall to the kernel
+ command line to enable this on bootup.
config TRACE_BRANCH_PROFILING
bool
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 39af8af6fc3..1090b0aed9b 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -22,6 +22,7 @@
#include <linux/init.h>
#include <linux/mutex.h>
#include <linux/debugfs.h>
+#include <linux/smp_lock.h>
#include <linux/time.h>
#include <linux/uaccess.h>
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 3718d55fb4c..1e1d23c2630 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -291,7 +291,9 @@ function_stat_next(void *v, int idx)
pg = (struct ftrace_profile_page *)((unsigned long)rec & PAGE_MASK);
again:
- rec++;
+ if (idx != 0)
+ rec++;
+
if ((void *)rec >= (void *)&pg->records[pg->index]) {
pg = pg->next;
if (!pg)
@@ -766,7 +768,7 @@ static struct tracer_stat function_stats __initdata = {
.stat_show = function_stat_show
};
-static void ftrace_profile_debugfs(struct dentry *d_tracer)
+static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
{
struct ftrace_profile_stat *stat;
struct dentry *entry;
@@ -784,7 +786,6 @@ static void ftrace_profile_debugfs(struct dentry *d_tracer)
* The files created are permanent, if something happens
* we still do not free memory.
*/
- kfree(stat);
WARN(1,
"Could not allocate stat file for cpu %d\n",
cpu);
@@ -811,7 +812,7 @@ static void ftrace_profile_debugfs(struct dentry *d_tracer)
}
#else /* CONFIG_FUNCTION_PROFILER */
-static void ftrace_profile_debugfs(struct dentry *d_tracer)
+static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
{
}
#endif /* CONFIG_FUNCTION_PROFILER */
@@ -1417,10 +1418,20 @@ static void *t_hash_start(struct seq_file *m, loff_t *pos)
{
struct ftrace_iterator *iter = m->private;
void *p = NULL;
+ loff_t l;
+
+ if (!(iter->flags & FTRACE_ITER_HASH))
+ *pos = 0;
iter->flags |= FTRACE_ITER_HASH;
- return t_hash_next(m, p, pos);
+ iter->hidx = 0;
+ for (l = 0; l <= *pos; ) {
+ p = t_hash_next(m, p, &l);
+ if (!p)
+ break;
+ }
+ return p;
}
static int t_hash_show(struct seq_file *m, void *v)
@@ -1467,8 +1478,6 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
iter->pg = iter->pg->next;
iter->idx = 0;
goto retry;
- } else {
- iter->idx = -1;
}
} else {
rec = &iter->pg->records[iter->idx++];
@@ -1497,6 +1506,7 @@ static void *t_start(struct seq_file *m, loff_t *pos)
{
struct ftrace_iterator *iter = m->private;
void *p = NULL;
+ loff_t l;
mutex_lock(&ftrace_lock);
/*
@@ -1508,23 +1518,21 @@ static void *t_start(struct seq_file *m, loff_t *pos)
if (*pos > 0)
return t_hash_start(m, pos);
iter->flags |= FTRACE_ITER_PRINTALL;
- (*pos)++;
return iter;
}
if (iter->flags & FTRACE_ITER_HASH)
return t_hash_start(m, pos);
- if (*pos > 0) {
- if (iter->idx < 0)
- return p;
- (*pos)--;
- iter->idx--;
+ iter->pg = ftrace_pages_start;
+ iter->idx = 0;
+ for (l = 0; l <= *pos; ) {
+ p = t_next(m, p, &l);
+ if (!p)
+ break;
}
- p = t_next(m, p, pos);
-
- if (!p)
+ if (!p && iter->flags & FTRACE_ITER_FILTER)
return t_hash_start(m, pos);
return p;
@@ -1654,7 +1662,7 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable)
mutex_lock(&ftrace_regex_lock);
if ((file->f_mode & FMODE_WRITE) &&
- !(file->f_flags & O_APPEND))
+ (file->f_flags & O_TRUNC))
ftrace_filter_reset(enable);
if (file->f_mode & FMODE_READ) {
@@ -2500,32 +2508,31 @@ int ftrace_graph_count;
unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
static void *
-g_next(struct seq_file *m, void *v, loff_t *pos)
+__g_next(struct seq_file *m, loff_t *pos)
{
unsigned long *array = m->private;
- int index = *pos;
-
- (*pos)++;
- if (index >= ftrace_graph_count)
+ if (*pos >= ftrace_graph_count)
return NULL;
+ return &array[*pos];
+}
- return &array[index];
+static void *
+g_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ (*pos)++;
+ return __g_next(m, pos);
}
static void *g_start(struct seq_file *m, loff_t *pos)
{
- void *p = NULL;
-
mutex_lock(&graph_lock);
/* Nothing, tell g_show to print all functions are enabled */
if (!ftrace_graph_count && !*pos)
return (void *)1;
- p = g_next(m, p, pos);
-
- return p;
+ return __g_next(m, pos);
}
static void g_stop(struct seq_file *m, void *p)
@@ -2570,7 +2577,7 @@ ftrace_graph_open(struct inode *inode, struct file *file)
mutex_lock(&graph_lock);
if ((file->f_mode & FMODE_WRITE) &&
- !(file->f_flags & O_APPEND)) {
+ (file->f_flags & O_TRUNC)) {
ftrace_graph_count = 0;
memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs));
}
@@ -2589,6 +2596,14 @@ ftrace_graph_open(struct inode *inode, struct file *file)
}
static int
+ftrace_graph_release(struct inode *inode, struct file *file)
+{
+ if (file->f_mode & FMODE_READ)
+ seq_release(inode, file);
+ return 0;
+}
+
+static int
ftrace_set_func(unsigned long *array, int *idx, char *buffer)
{
struct dyn_ftrace *rec;
@@ -2717,9 +2732,10 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
}
static const struct file_operations ftrace_graph_fops = {
- .open = ftrace_graph_open,
- .read = seq_read,
- .write = ftrace_graph_write,
+ .open = ftrace_graph_open,
+ .read = seq_read,
+ .write = ftrace_graph_write,
+ .release = ftrace_graph_release,
};
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@@ -3152,10 +3168,10 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
ret = proc_dointvec(table, write, file, buffer, lenp, ppos);
- if (ret || !write || (last_ftrace_enabled == ftrace_enabled))
+ if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled))
goto out;
- last_ftrace_enabled = ftrace_enabled;
+ last_ftrace_enabled = !!ftrace_enabled;
if (ftrace_enabled) {
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 04dac263825..bf27bb7a63e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1563,6 +1563,8 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
return NULL;
}
+#ifdef CONFIG_TRACING
+
#define TRACE_RECURSIVE_DEPTH 16
static int trace_recursive_lock(void)
@@ -1593,6 +1595,13 @@ static void trace_recursive_unlock(void)
current->trace_recursion--;
}
+#else
+
+#define trace_recursive_lock() (0)
+#define trace_recursive_unlock() do { } while (0)
+
+#endif
+
static DEFINE_PER_CPU(int, rb_need_resched);
/**
@@ -3104,6 +3113,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
}
EXPORT_SYMBOL_GPL(ring_buffer_read_page);
+#ifdef CONFIG_TRACING
static ssize_t
rb_simple_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
@@ -3171,6 +3181,7 @@ static __init int rb_init_debugfs(void)
}
fs_initcall(rb_init_debugfs);
+#endif
#ifdef CONFIG_HOTPLUG_CPU
static int rb_cpu_notify(struct notifier_block *self,
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 076fa6f0ee4..8930e39b9d8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -17,6 +17,7 @@
#include <linux/writeback.h>
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
+#include <linux/smp_lock.h>
#include <linux/notifier.h>
#include <linux/irqflags.h>
#include <linux/debugfs.h>
@@ -284,13 +285,12 @@ void trace_wake_up(void)
static int __init set_buf_size(char *str)
{
unsigned long buf_size;
- int ret;
if (!str)
return 0;
- ret = strict_strtoul(str, 0, &buf_size);
+ buf_size = memparse(str, &str);
/* nr_entries can not be zero */
- if (ret < 0 || buf_size == 0)
+ if (buf_size == 0)
return 0;
trace_buf_size = buf_size;
return 1;
@@ -2031,7 +2031,7 @@ static int tracing_open(struct inode *inode, struct file *file)
/* If this file was open for write, then erase contents */
if ((file->f_mode & FMODE_WRITE) &&
- !(file->f_flags & O_APPEND)) {
+ (file->f_flags & O_TRUNC)) {
long cpu = (long) inode->i_private;
if (cpu == TRACE_PIPE_ALL_CPU)
@@ -2053,25 +2053,23 @@ static int tracing_open(struct inode *inode, struct file *file)
static void *
t_next(struct seq_file *m, void *v, loff_t *pos)
{
- struct tracer *t = m->private;
+ struct tracer *t = v;
(*pos)++;
if (t)
t = t->next;
- m->private = t;
-
return t;
}
static void *t_start(struct seq_file *m, loff_t *pos)
{
- struct tracer *t = m->private;
+ struct tracer *t;
loff_t l = 0;
mutex_lock(&trace_types_lock);
- for (; t && l < *pos; t = t_next(m, t, &l))
+ for (t = trace_types; t && l < *pos; t = t_next(m, t, &l))
;
return t;
@@ -2107,18 +2105,10 @@ static struct seq_operations show_traces_seq_ops = {
static int show_traces_open(struct inode *inode, struct file *file)
{
- int ret;
-
if (tracing_disabled)
return -ENODEV;
- ret = seq_open(file, &show_traces_seq_ops);
- if (!ret) {
- struct seq_file *m = file->private_data;
- m->private = trace_types;
- }
-
- return ret;
+ return seq_open(file, &show_traces_seq_ops);
}
static ssize_t
@@ -3095,7 +3085,8 @@ tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter)
break;
}
- trace_consume(iter);
+ if (ret != TRACE_TYPE_NO_CONSUME)
+ trace_consume(iter);
rem -= count;
if (!find_next_entry_inc(iter)) {
rem = 0;
@@ -4243,8 +4234,11 @@ static void __ftrace_dump(bool disable_tracing)
iter.pos = -1;
if (find_next_entry_inc(&iter) != NULL) {
- print_trace_line(&iter);
- trace_consume(&iter);
+ int ret;
+
+ ret = print_trace_line(&iter);
+ if (ret != TRACE_TYPE_NO_CONSUME)
+ trace_consume(&iter);
}
trace_printk_seq(&iter.seq);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6e735d4771f..3548ae5cc78 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -597,6 +597,7 @@ print_graph_function(struct trace_iterator *iter)
extern struct pid *ftrace_pid_trace;
+#ifdef CONFIG_FUNCTION_TRACER
static inline int ftrace_trace_task(struct task_struct *task)
{
if (!ftrace_pid_trace)
@@ -604,6 +605,12 @@ static inline int ftrace_trace_task(struct task_struct *task)
return test_tsk_trace_trace(task);
}
+#else
+static inline int ftrace_trace_task(struct task_struct *task)
+{
+ return 1;
+}
+#endif
/*
* trace_iterator_flags is an enumeration that defines bit
diff --git a/kernel/trace/trace_event_types.h b/kernel/trace/trace_event_types.h
index 5e32e375134..6db005e1248 100644
--- a/kernel/trace/trace_event_types.h
+++ b/kernel/trace/trace_event_types.h
@@ -26,6 +26,9 @@ TRACE_EVENT_FORMAT(funcgraph_exit, TRACE_GRAPH_RET,
ftrace_graph_ret_entry, ignore,
TRACE_STRUCT(
TRACE_FIELD(unsigned long, ret.func, func)
+ TRACE_FIELD(unsigned long long, ret.calltime, calltime)
+ TRACE_FIELD(unsigned long long, ret.rettime, rettime)
+ TRACE_FIELD(unsigned long, ret.overrun, overrun)
TRACE_FIELD(int, ret.depth, depth)
),
TP_RAW_FMT("<-- %lx (%d)")
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index aa08be69a1b..23d2972b22d 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -300,10 +300,18 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
static void *t_start(struct seq_file *m, loff_t *pos)
{
+ struct ftrace_event_call *call = NULL;
+ loff_t l;
+
mutex_lock(&event_mutex);
- if (*pos == 0)
- m->private = ftrace_events.next;
- return t_next(m, NULL, pos);
+
+ m->private = ftrace_events.next;
+ for (l = 0; l <= *pos; ) {
+ call = t_next(m, NULL, &l);
+ if (!call)
+ break;
+ }
+ return call;
}
static void *
@@ -332,10 +340,18 @@ s_next(struct seq_file *m, void *v, loff_t *pos)
static void *s_start(struct seq_file *m, loff_t *pos)
{
+ struct ftrace_event_call *call = NULL;
+ loff_t l;
+
mutex_lock(&event_mutex);
- if (*pos == 0)
- m->private = ftrace_events.next;
- return s_next(m, NULL, pos);
+
+ m->private = ftrace_events.next;
+ for (l = 0; l <= *pos; ) {
+ call = s_next(m, NULL, &l);
+ if (!call)
+ break;
+ }
+ return call;
}
static int t_show(struct seq_file *m, void *v)
@@ -360,7 +376,7 @@ ftrace_event_seq_open(struct inode *inode, struct file *file)
const struct seq_operations *seq_ops;
if ((file->f_mode & FMODE_WRITE) &&
- !(file->f_flags & O_APPEND))
+ (file->f_flags & O_TRUNC))
ftrace_clear_events();
seq_ops = inode->i_private;
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 90f13476483..75ef000613c 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -302,8 +302,7 @@ ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
if (count == -1)
seq_printf(m, ":unlimited\n");
else
- seq_printf(m, ":count=%ld", count);
- seq_putc(m, '\n');
+ seq_printf(m, ":count=%ld\n", count);
return 0;
}
@@ -364,7 +363,7 @@ ftrace_trace_onoff_callback(char *glob, char *cmd, char *param, int enable)
out_reg:
ret = register_ftrace_function_probe(glob, ops, count);
- return ret;
+ return ret < 0 ? ret : 0;
}
static struct ftrace_func_command ftrace_traceon_cmd = {
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index d2249abafb5..420ec348757 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -843,9 +843,16 @@ print_graph_function(struct trace_iterator *iter)
switch (entry->type) {
case TRACE_GRAPH_ENT: {
- struct ftrace_graph_ent_entry *field;
+ /*
+ * print_graph_entry() may consume the current event,
+ * thus @field may become invalid, so we need to save it.
+ * sizeof(struct ftrace_graph_ent_entry) is very small,
+ * it can be safely saved at the stack.
+ */
+ struct ftrace_graph_ent_entry *field, saved;
trace_assign_type(field, entry);
- return print_graph_entry(field, s, iter);
+ saved = *field;
+ return print_graph_entry(&saved, s, iter);
}
case TRACE_GRAPH_RET: {
struct ftrace_graph_ret_entry *field;
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 7938f3ae93e..e0c2545622e 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -27,8 +27,7 @@ void trace_print_seq(struct seq_file *m, struct trace_seq *s)
{
int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
- s->buffer[len] = 0;
- seq_puts(m, s->buffer);
+ seq_write(m, s->buffer, len);
trace_seq_init(s);
}
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 9bece9687b6..687699d365a 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -155,25 +155,19 @@ int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap)
EXPORT_SYMBOL_GPL(__ftrace_vprintk);
static void *
-t_next(struct seq_file *m, void *v, loff_t *pos)
+t_start(struct seq_file *m, loff_t *pos)
{
- const char **fmt = m->private;
- const char **next = fmt;
-
- (*pos)++;
+ const char **fmt = __start___trace_bprintk_fmt + *pos;
if ((unsigned long)fmt >= (unsigned long)__stop___trace_bprintk_fmt)
return NULL;
-
- next = fmt;
- m->private = ++next;
-
return fmt;
}
-static void *t_start(struct seq_file *m, loff_t *pos)
+static void *t_next(struct seq_file *m, void * v, loff_t *pos)
{
- return t_next(m, NULL, pos);
+ (*pos)++;
+ return t_start(m, pos);
}
static int t_show(struct seq_file *m, void *v)
@@ -182,7 +176,7 @@ static int t_show(struct seq_file *m, void *v)
const char *str = *fmt;
int i;
- seq_printf(m, "0x%lx : \"", (unsigned long)fmt);
+ seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt);
/*
* Tabs and new lines need to be converted.
@@ -224,15 +218,7 @@ static const struct seq_operations show_format_seq_ops = {
static int
ftrace_formats_open(struct inode *inode, struct file *file)
{
- int ret;
-
- ret = seq_open(file, &show_format_seq_ops);
- if (!ret) {
- struct seq_file *m = file->private_data;
-
- m->private = __start___trace_bprintk_fmt;
- }
- return ret;
+ return seq_open(file, &show_format_seq_ops);
}
static const struct file_operations ftrace_formats_fops = {
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 2d7aebd71db..6a2a9d484cd 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -301,17 +301,14 @@ static const struct seq_operations stack_trace_seq_ops = {
static int stack_trace_open(struct inode *inode, struct file *file)
{
- int ret;
-
- ret = seq_open(file, &stack_trace_seq_ops);
-
- return ret;
+ return seq_open(file, &stack_trace_seq_ops);
}
static const struct file_operations stack_trace_fops = {
.open = stack_trace_open,
.read = seq_read,
.llseek = seq_lseek,
+ .release = seq_release,
};
int
@@ -326,10 +323,10 @@ stack_trace_sysctl(struct ctl_table *table, int write,
ret = proc_dointvec(table, write, file, buffer, lenp, ppos);
if (ret || !write ||
- (last_stack_tracer_enabled == stack_tracer_enabled))
+ (last_stack_tracer_enabled == !!stack_tracer_enabled))
goto out;
- last_stack_tracer_enabled = stack_tracer_enabled;
+ last_stack_tracer_enabled = !!stack_tracer_enabled;
if (stack_tracer_enabled)
register_ftrace_function(&trace_ops);
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index c00643733f4..aea321c82fa 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -73,7 +73,7 @@ static struct rb_node *release_next(struct rb_node *node)
}
}
-static void reset_stat_session(struct stat_session *session)
+static void __reset_stat_session(struct stat_session *session)
{
struct rb_node *node = session->stat_root.rb_node;
@@ -83,10 +83,17 @@ static void reset_stat_session(struct stat_session *session)
session->stat_root = RB_ROOT;
}
+static void reset_stat_session(struct stat_session *session)
+{
+ mutex_lock(&session->stat_mutex);
+ __reset_stat_session(session);
+ mutex_unlock(&session->stat_mutex);
+}
+
static void destroy_session(struct stat_session *session)
{
debugfs_remove(session->file);
- reset_stat_session(session);
+ __reset_stat_session(session);
mutex_destroy(&session->stat_mutex);
kfree(session);
}
@@ -150,7 +157,7 @@ static int stat_seq_init(struct stat_session *session)
int i;
mutex_lock(&session->stat_mutex);
- reset_stat_session(session);
+ __reset_stat_session(session);
if (!ts->stat_cmp)
ts->stat_cmp = dummy_cmp;
@@ -183,7 +190,7 @@ exit:
return ret;
exit_free_rbtree:
- reset_stat_session(session);
+ __reset_stat_session(session);
mutex_unlock(&session->stat_mutex);
return ret;
}
@@ -199,17 +206,13 @@ static void *stat_seq_start(struct seq_file *s, loff_t *pos)
mutex_lock(&session->stat_mutex);
/* If we are in the beginning of the file, print the headers */
- if (!*pos && session->ts->stat_headers) {
- (*pos)++;
+ if (!*pos && session->ts->stat_headers)
return SEQ_START_TOKEN;
- }
node = rb_first(&session->stat_root);
for (i = 0; node && i < *pos; i++)
node = rb_next(node);
- (*pos)++;
-
return node;
}
@@ -254,16 +257,21 @@ static const struct seq_operations trace_stat_seq_ops = {
static int tracing_stat_open(struct inode *inode, struct file *file)
{
int ret;
-
+ struct seq_file *m;
struct stat_session *session = inode->i_private;
+ ret = stat_seq_init(session);
+ if (ret)
+ return ret;
+
ret = seq_open(file, &trace_stat_seq_ops);
- if (!ret) {
- struct seq_file *m = file->private_data;
- m->private = session;
- ret = stat_seq_init(session);
+ if (ret) {
+ reset_stat_session(session);
+ return ret;
}
+ m = file->private_data;
+ m->private = session;
return ret;
}
@@ -274,11 +282,9 @@ static int tracing_stat_release(struct inode *i, struct file *f)
{
struct stat_session *session = i->i_private;
- mutex_lock(&session->stat_mutex);
reset_stat_session(session);
- mutex_unlock(&session->stat_mutex);
- return 0;
+ return seq_release(i, f);
}
static const struct file_operations tracing_stat_fops = {