aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile4
-rw-r--r--kernel/audit_tree.c48
-rw-r--r--kernel/cgroup.c3
-rw-r--r--kernel/cgroup_freezer.c51
-rw-r--r--kernel/cpu.c3
-rw-r--r--kernel/exec_domain.c33
-rw-r--r--kernel/fork.c2
-rw-r--r--kernel/freezer.c20
-rw-r--r--kernel/futex.c11
-rw-r--r--kernel/hrtimer.c206
-rw-r--r--kernel/irq/chip.c3
-rw-r--r--kernel/irq/proc.c2
-rw-r--r--kernel/lockdep.c17
-rw-r--r--kernel/module.c343
-rw-r--r--kernel/panic.c17
-rw-r--r--kernel/params.c276
-rw-r--r--kernel/posix-timers.c10
-rw-r--r--kernel/power/Kconfig2
-rw-r--r--kernel/power/disk.c2
-rw-r--r--kernel/power/power.h2
-rw-r--r--kernel/power/swap.c14
-rw-r--r--kernel/printk.c39
-rw-r--r--kernel/profile.c2
-rw-r--r--kernel/rcupdate.c19
-rw-r--r--kernel/resource.c8
-rw-r--r--kernel/rtmutex.c3
-rw-r--r--kernel/sched.c75
-rw-r--r--kernel/sched_debug.c2
-rw-r--r--kernel/sched_fair.c301
-rw-r--r--kernel/sched_features.h3
-rw-r--r--kernel/sched_idletask.c5
-rw-r--r--kernel/sched_rt.c5
-rw-r--r--kernel/sched_stats.h11
-rw-r--r--kernel/signal.c3
-rw-r--r--kernel/smp.c18
-rw-r--r--kernel/stop_machine.c120
-rw-r--r--kernel/sys.c10
-rw-r--r--kernel/sysctl.c12
-rw-r--r--kernel/time.c18
-rw-r--r--kernel/time/ntp.c3
-rw-r--r--kernel/time/tick-sched.c35
-rw-r--r--kernel/time/timer_list.c8
-rw-r--r--kernel/timer.c129
-rw-r--r--kernel/trace/Kconfig31
-rw-r--r--kernel/trace/Makefile6
-rw-r--r--kernel/trace/ftrace.c608
-rw-r--r--kernel/trace/ring_buffer.c62
-rw-r--r--kernel/trace/trace.c63
-rw-r--r--kernel/trace/trace.h22
-rw-r--r--kernel/trace/trace_functions.c2
-rw-r--r--kernel/trace/trace_irqsoff.c4
-rw-r--r--kernel/trace/trace_sched_wakeup.c4
-rw-r--r--kernel/trace/trace_selftest.c18
-rw-r--r--kernel/trace/trace_stack.c4
-rw-r--r--kernel/tracepoint.c8
-rw-r--r--kernel/workqueue.c52
56 files changed, 1424 insertions, 1358 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 305f11dbef2..9a3ec66a9d8 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -13,7 +13,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \
CFLAGS_REMOVE_sched.o = -mno-spe
-ifdef CONFIG_FTRACE
+ifdef CONFIG_FUNCTION_TRACER
# Do not trace debug files and internal ftrace files
CFLAGS_REMOVE_lockdep.o = -pg
CFLAGS_REMOVE_lockdep_proc.o = -pg
@@ -88,7 +88,7 @@ obj-$(CONFIG_MARKERS) += marker.o
obj-$(CONFIG_TRACEPOINTS) += tracepoint.o
obj-$(CONFIG_LATENCYTOP) += latencytop.o
obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
-obj-$(CONFIG_FTRACE) += trace/
+obj-$(CONFIG_FUNCTION_TRACER) += trace/
obj-$(CONFIG_TRACING) += trace/
obj-$(CONFIG_SMP) += sched_cpupri.o
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index f7921a2ecf1..8ba0e0d934f 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -532,7 +532,7 @@ void audit_trim_trees(void)
list_add(&cursor, &tree_list);
while (cursor.next != &tree_list) {
struct audit_tree *tree;
- struct nameidata nd;
+ struct path path;
struct vfsmount *root_mnt;
struct node *node;
struct list_head list;
@@ -544,12 +544,12 @@ void audit_trim_trees(void)
list_add(&cursor, &tree->list);
mutex_unlock(&audit_filter_mutex);
- err = path_lookup(tree->pathname, 0, &nd);
+ err = kern_path(tree->pathname, 0, &path);
if (err)
goto skip_it;
- root_mnt = collect_mounts(nd.path.mnt, nd.path.dentry);
- path_put(&nd.path);
+ root_mnt = collect_mounts(path.mnt, path.dentry);
+ path_put(&path);
if (!root_mnt)
goto skip_it;
@@ -580,19 +580,19 @@ skip_it:
}
static int is_under(struct vfsmount *mnt, struct dentry *dentry,
- struct nameidata *nd)
+ struct path *path)
{
- if (mnt != nd->path.mnt) {
+ if (mnt != path->mnt) {
for (;;) {
if (mnt->mnt_parent == mnt)
return 0;
- if (mnt->mnt_parent == nd->path.mnt)
+ if (mnt->mnt_parent == path->mnt)
break;
mnt = mnt->mnt_parent;
}
dentry = mnt->mnt_mountpoint;
}
- return is_subdir(dentry, nd->path.dentry);
+ return is_subdir(dentry, path->dentry);
}
int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op)
@@ -618,7 +618,7 @@ void audit_put_tree(struct audit_tree *tree)
int audit_add_tree_rule(struct audit_krule *rule)
{
struct audit_tree *seed = rule->tree, *tree;
- struct nameidata nd;
+ struct path path;
struct vfsmount *mnt, *p;
struct list_head list;
int err;
@@ -637,11 +637,11 @@ int audit_add_tree_rule(struct audit_krule *rule)
/* do not set rule->tree yet */
mutex_unlock(&audit_filter_mutex);
- err = path_lookup(tree->pathname, 0, &nd);
+ err = kern_path(tree->pathname, 0, &path);
if (err)
goto Err;
- mnt = collect_mounts(nd.path.mnt, nd.path.dentry);
- path_put(&nd.path);
+ mnt = collect_mounts(path.mnt, path.dentry);
+ path_put(&path);
if (!mnt) {
err = -ENOMEM;
goto Err;
@@ -690,29 +690,29 @@ int audit_tag_tree(char *old, char *new)
{
struct list_head cursor, barrier;
int failed = 0;
- struct nameidata nd;
+ struct path path;
struct vfsmount *tagged;
struct list_head list;
struct vfsmount *mnt;
struct dentry *dentry;
int err;
- err = path_lookup(new, 0, &nd);
+ err = kern_path(new, 0, &path);
if (err)
return err;
- tagged = collect_mounts(nd.path.mnt, nd.path.dentry);
- path_put(&nd.path);
+ tagged = collect_mounts(path.mnt, path.dentry);
+ path_put(&path);
if (!tagged)
return -ENOMEM;
- err = path_lookup(old, 0, &nd);
+ err = kern_path(old, 0, &path);
if (err) {
drop_collected_mounts(tagged);
return err;
}
- mnt = mntget(nd.path.mnt);
- dentry = dget(nd.path.dentry);
- path_put(&nd.path);
+ mnt = mntget(path.mnt);
+ dentry = dget(path.dentry);
+ path_put(&path);
if (dentry == tagged->mnt_root && dentry == mnt->mnt_root)
follow_up(&mnt, &dentry);
@@ -733,7 +733,7 @@ int audit_tag_tree(char *old, char *new)
list_add(&cursor, &tree->list);
mutex_unlock(&audit_filter_mutex);
- err = path_lookup(tree->pathname, 0, &nd);
+ err = kern_path(tree->pathname, 0, &path);
if (err) {
put_tree(tree);
mutex_lock(&audit_filter_mutex);
@@ -741,15 +741,15 @@ int audit_tag_tree(char *old, char *new)
}
spin_lock(&vfsmount_lock);
- if (!is_under(mnt, dentry, &nd)) {
+ if (!is_under(mnt, dentry, &path)) {
spin_unlock(&vfsmount_lock);
- path_put(&nd.path);
+ path_put(&path);
put_tree(tree);
mutex_lock(&audit_filter_mutex);
continue;
}
spin_unlock(&vfsmount_lock);
- path_put(&nd.path);
+ path_put(&path);
list_for_each_entry(p, &list, mnt_list) {
failed = tag_chunk(p->mnt_root->d_inode, tree);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 046c1609606..358e77564e6 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2104,7 +2104,7 @@ static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
down_read(&cgrp->pids_mutex);
if (pid) {
int end = cgrp->pids_length;
- int i;
+
while (index < end) {
int mid = (index + end) / 2;
if (cgrp->tasks_pids[mid] == pid) {
@@ -2497,7 +2497,6 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
list_del(&cgrp->sibling);
spin_lock(&cgrp->dentry->d_lock);
d = dget(cgrp->dentry);
- cgrp->dentry = NULL;
spin_unlock(&d->d_lock);
cgroup_d_remove_dir(d);
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index e9505695449..7fa476f01d0 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -162,9 +162,13 @@ static int freezer_can_attach(struct cgroup_subsys *ss,
struct task_struct *task)
{
struct freezer *freezer;
- int retval;
- /* Anything frozen can't move or be moved to/from */
+ /*
+ * Anything frozen can't move or be moved to/from.
+ *
+ * Since orig_freezer->state == FROZEN means that @task has been
+ * frozen, so it's sufficient to check the latter condition.
+ */
if (is_task_frozen_enough(task))
return -EBUSY;
@@ -173,13 +177,7 @@ static int freezer_can_attach(struct cgroup_subsys *ss,
if (freezer->state == CGROUP_FROZEN)
return -EBUSY;
- retval = 0;
- task_lock(task);
- freezer = task_freezer(task);
- if (freezer->state == CGROUP_FROZEN)
- retval = -EBUSY;
- task_unlock(task);
- return retval;
+ return 0;
}
static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
@@ -190,8 +188,9 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
freezer = task_freezer(task);
task_unlock(task);
- BUG_ON(freezer->state == CGROUP_FROZEN);
spin_lock_irq(&freezer->lock);
+ BUG_ON(freezer->state == CGROUP_FROZEN);
+
/* Locking avoids race with FREEZING -> THAWED transitions. */
if (freezer->state == CGROUP_FREEZING)
freeze_task(task, true);
@@ -276,25 +275,18 @@ static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
return num_cant_freeze_now ? -EBUSY : 0;
}
-static int unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
+static void unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
{
struct cgroup_iter it;
struct task_struct *task;
cgroup_iter_start(cgroup, &it);
while ((task = cgroup_iter_next(cgroup, &it))) {
- int do_wake;
-
- task_lock(task);
- do_wake = __thaw_process(task);
- task_unlock(task);
- if (do_wake)
- wake_up_process(task);
+ thaw_process(task);
}
cgroup_iter_end(cgroup, &it);
- freezer->state = CGROUP_THAWED;
- return 0;
+ freezer->state = CGROUP_THAWED;
}
static int freezer_change_state(struct cgroup *cgroup,
@@ -304,27 +296,22 @@ static int freezer_change_state(struct cgroup *cgroup,
int retval = 0;
freezer = cgroup_freezer(cgroup);
+
spin_lock_irq(&freezer->lock);
+
update_freezer_state(cgroup, freezer);
if (goal_state == freezer->state)
goto out;
- switch (freezer->state) {
+
+ switch (goal_state) {
case CGROUP_THAWED:
- retval = try_to_freeze_cgroup(cgroup, freezer);
+ unfreeze_cgroup(cgroup, freezer);
break;
- case CGROUP_FREEZING:
- if (goal_state == CGROUP_FROZEN) {
- /* Userspace is retrying after
- * "/bin/echo FROZEN > freezer.state" returned -EBUSY */
- retval = try_to_freeze_cgroup(cgroup, freezer);
- break;
- }
- /* state == FREEZING and goal_state == THAWED, so unfreeze */
case CGROUP_FROZEN:
- retval = unfreeze_cgroup(cgroup, freezer);
+ retval = try_to_freeze_cgroup(cgroup, freezer);
break;
default:
- break;
+ BUG();
}
out:
spin_unlock_irq(&freezer->lock);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 86d49045dae..5a732c5ef08 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -499,3 +499,6 @@ const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {
#endif
};
EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
+
+const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
+EXPORT_SYMBOL(cpu_all_bits);
diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c
index 0d407e88673..0511716e942 100644
--- a/kernel/exec_domain.c
+++ b/kernel/exec_domain.c
@@ -12,7 +12,9 @@
#include <linux/kmod.h>
#include <linux/module.h>
#include <linux/personality.h>
+#include <linux/proc_fs.h>
#include <linux/sched.h>
+#include <linux/seq_file.h>
#include <linux/syscalls.h>
#include <linux/sysctl.h>
#include <linux/types.h>
@@ -173,20 +175,39 @@ __set_personality(u_long personality)
return 0;
}
-int
-get_exec_domain_list(char *page)
+#ifdef CONFIG_PROC_FS
+static int execdomains_proc_show(struct seq_file *m, void *v)
{
struct exec_domain *ep;
- int len = 0;
read_lock(&exec_domains_lock);
- for (ep = exec_domains; ep && len < PAGE_SIZE - 80; ep = ep->next)
- len += sprintf(page + len, "%d-%d\t%-16s\t[%s]\n",
+ for (ep = exec_domains; ep; ep = ep->next)
+ seq_printf(m, "%d-%d\t%-16s\t[%s]\n",
ep->pers_low, ep->pers_high, ep->name,
module_name(ep->module));
read_unlock(&exec_domains_lock);
- return (len);
+ return 0;
+}
+
+static int execdomains_proc_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, execdomains_proc_show, NULL);
+}
+
+static const struct file_operations execdomains_proc_fops = {
+ .open = execdomains_proc_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int __init proc_execdomains_init(void)
+{
+ proc_create("execdomains", 0, NULL, &execdomains_proc_fops);
+ return 0;
}
+module_init(proc_execdomains_init);
+#endif
asmlinkage long
sys_personality(u_long personality)
diff --git a/kernel/fork.c b/kernel/fork.c
index 4d093552dd6..f6083561dfe 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1018,6 +1018,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->prev_utime = cputime_zero;
p->prev_stime = cputime_zero;
+ p->default_timer_slack_ns = current->timer_slack_ns;
+
#ifdef CONFIG_DETECT_SOFTLOCKUP
p->last_switch_count = 0;
p->last_switch_timestamp = 0;
diff --git a/kernel/freezer.c b/kernel/freezer.c
index ba6248b323e..2f4936cf708 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -121,16 +121,7 @@ void cancel_freezing(struct task_struct *p)
}
}
-/*
- * Wake up a frozen process
- *
- * task_lock() is needed to prevent the race with refrigerator() which may
- * occur if the freezing of tasks fails. Namely, without the lock, if the
- * freezing of tasks failed, thaw_tasks() might have run before a task in
- * refrigerator() could call frozen_process(), in which case the task would be
- * frozen and no one would thaw it.
- */
-int __thaw_process(struct task_struct *p)
+static int __thaw_process(struct task_struct *p)
{
if (frozen(p)) {
p->flags &= ~PF_FROZEN;
@@ -140,6 +131,15 @@ int __thaw_process(struct task_struct *p)
return 0;
}
+/*
+ * Wake up a frozen process
+ *
+ * task_lock() is needed to prevent the race with refrigerator() which may
+ * occur if the freezing of tasks fails. Namely, without the lock, if the
+ * freezing of tasks failed, thaw_tasks() might have run before a task in
+ * refrigerator() could call frozen_process(), in which case the task would be
+ * frozen and no one would thaw it.
+ */
int thaw_process(struct task_struct *p)
{
task_lock(p);
diff --git a/kernel/futex.c b/kernel/futex.c
index 7d1136e97c1..8af10027514 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1296,13 +1296,16 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
if (!abs_time)
schedule();
else {
+ unsigned long slack;
+ slack = current->timer_slack_ns;
+ if (rt_task(current))
+ slack = 0;
hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC,
HRTIMER_MODE_ABS);
hrtimer_init_sleeper(&t, current);
- t.timer.expires = *abs_time;
+ hrtimer_set_expires_range_ns(&t.timer, *abs_time, slack);
- hrtimer_start(&t.timer, t.timer.expires,
- HRTIMER_MODE_ABS);
+ hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS);
if (!hrtimer_active(&t.timer))
t.task = NULL;
@@ -1404,7 +1407,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
hrtimer_init_on_stack(&to->timer, CLOCK_REALTIME,
HRTIMER_MODE_ABS);
hrtimer_init_sleeper(to, current);
- to->timer.expires = *time;
+ hrtimer_set_expires(&to->timer, *time);
}
q.pi_state = NULL;
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 95978f48e03..2b465dfde42 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -517,7 +517,7 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
if (!base->first)
continue;
timer = rb_entry(base->first, struct hrtimer, node);
- expires = ktime_sub(timer->expires, base->offset);
+ expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
if (expires.tv64 < cpu_base->expires_next.tv64)
cpu_base->expires_next = expires;
}
@@ -539,10 +539,10 @@ static int hrtimer_reprogram(struct hrtimer *timer,
struct hrtimer_clock_base *base)
{
ktime_t *expires_next = &__get_cpu_var(hrtimer_bases).expires_next;
- ktime_t expires = ktime_sub(timer->expires, base->offset);
+ ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
int res;
- WARN_ON_ONCE(timer->expires.tv64 < 0);
+ WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
/*
* When the callback is running, we do not reprogram the clock event
@@ -795,7 +795,7 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
u64 orun = 1;
ktime_t delta;
- delta = ktime_sub(now, timer->expires);
+ delta = ktime_sub(now, hrtimer_get_expires(timer));
if (delta.tv64 < 0)
return 0;
@@ -807,8 +807,8 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
s64 incr = ktime_to_ns(interval);
orun = ktime_divns(delta, incr);
- timer->expires = ktime_add_ns(timer->expires, incr * orun);
- if (timer->expires.tv64 > now.tv64)
+ hrtimer_add_expires_ns(timer, incr * orun);
+ if (hrtimer_get_expires_tv64(timer) > now.tv64)
return orun;
/*
* This (and the ktime_add() below) is the
@@ -816,7 +816,7 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
*/
orun++;
}
- timer->expires = ktime_add_safe(timer->expires, interval);
+ hrtimer_add_expires(timer, interval);
return orun;
}
@@ -848,7 +848,8 @@ static void enqueue_hrtimer(struct hrtimer *timer,
* We dont care about collisions. Nodes with
* the same expiry time stay together.
*/
- if (timer->expires.tv64 < entry->expires.tv64) {
+ if (hrtimer_get_expires_tv64(timer) <
+ hrtimer_get_expires_tv64(entry)) {
link = &(*link)->rb_left;
} else {
link = &(*link)->rb_right;
@@ -945,9 +946,10 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
}
/**
- * hrtimer_start - (re)start an relative timer on the current CPU
+ * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
* @timer: the timer to be added
* @tim: expiry time
+ * @delta_ns: "slack" range for the timer
* @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
*
* Returns:
@@ -955,7 +957,8 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
* 1 when the timer was active
*/
int
-hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
+hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_ns,
+ const enum hrtimer_mode mode)
{
struct hrtimer_clock_base *base, *new_base;
unsigned long flags;
@@ -983,7 +986,7 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
#endif
}
- timer->expires = tim;
+ hrtimer_set_expires_range_ns(timer, tim, delta_ns);
timer_stats_hrtimer_set_start_info(timer);
@@ -1016,8 +1019,26 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
return ret;
}
+EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
+
+/**
+ * hrtimer_start - (re)start an hrtimer on the current CPU
+ * @timer: the timer to be added
+ * @tim: expiry time
+ * @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
+ *
+ * Returns:
+ * 0 on success
+ * 1 when the timer was active
+ */
+int
+hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
+{
+ return hrtimer_start_range_ns(timer, tim, 0, mode);
+}
EXPORT_SYMBOL_GPL(hrtimer_start);
+
/**
* hrtimer_try_to_cancel - try to deactivate a timer
* @timer: hrtimer to stop
@@ -1077,7 +1098,7 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
ktime_t rem;
base = lock_hrtimer_base(timer, &flags);
- rem = ktime_sub(timer->expires, base->get_time());
+ rem = hrtimer_expires_remaining(timer);
unlock_hrtimer_base(timer, &flags);
return rem;
@@ -1109,7 +1130,7 @@ ktime_t hrtimer_get_next_event(void)
continue;
timer = rb_entry(base->first, struct hrtimer, node);
- delta.tv64 = timer->expires.tv64;
+ delta.tv64 = hrtimer_get_expires_tv64(timer);
delta = ktime_sub(delta, base->get_time());
if (delta.tv64 < mindelta.tv64)
mindelta.tv64 = delta.tv64;
@@ -1310,10 +1331,23 @@ void hrtimer_interrupt(struct clock_event_device *dev)
timer = rb_entry(node, struct hrtimer, node);
- if (basenow.tv64 < timer->expires.tv64) {
+ /*
+ * The immediate goal for using the softexpires is
+ * minimizing wakeups, not running timers at the
+ * earliest interrupt after their soft expiration.
+ * This allows us to avoid using a Priority Search
+ * Tree, which can answer a stabbing querry for
+ * overlapping intervals and instead use the simple
+ * BST we already have.
+ * We don't add extra wakeups by delaying timers that
+ * are right-of a not yet expired timer, because that
+ * timer will have to trigger a wakeup anyway.
+ */
+
+ if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
ktime_t expires;
- expires = ktime_sub(timer->expires,
+ expires = ktime_sub(hrtimer_get_expires(timer),
base->offset);
if (expires.tv64 < expires_next.tv64)
expires_next = expires;
@@ -1349,6 +1383,30 @@ void