Merge branch 'master' into pm-sleep
* master: (848 commits)
SELinux: Fix RCU deref check warning in sel_netport_insert()
binary_sysctl(): fix memory leak
mm/vmalloc.c: remove static declaration of va from __get_vm_area_node
ipmi_watchdog: restore settings when BMC reset
oom: fix integer overflow of points in oom_badness
memcg: keep root group unchanged if creation fails
nilfs2: potential integer overflow in nilfs_ioctl_clean_segments()
nilfs2: unbreak compat ioctl
cpusets: stall when updating mems_allowed for mempolicy or disjoint nodemask
evm: prevent racing during tfm allocation
evm: key must be set once during initialization
mmc: vub300: fix type of firmware_rom_wait_states module parameter
Revert "mmc: enable runtime PM by default"
mmc: sdhci: remove "state" argument from sdhci_suspend_host
x86, dumpstack: Fix code bytes breakage due to missing KERN_CONT
IB/qib: Correct sense on freectxts increment and decrement
RDMA/cma: Verify private data length
cgroups: fix a css_set not found bug in cgroup_attach_proc
oprofile: Fix uninitialized memory access when writing to writing to oprofilefs
Revert "xen/pv-on-hvm kexec: add xs_reset_watches to shutdown watches from old kernel"
...
Conflicts:
kernel/cgroup_freezer.c
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index d9d5648..a184470 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2098,11 +2098,6 @@
continue;
/* get old css_set pointer */
task_lock(tsk);
- if (tsk->flags & PF_EXITING) {
- /* ignore this task if it's going away */
- task_unlock(tsk);
- continue;
- }
oldcg = tsk->cgroups;
get_css_set(oldcg);
task_unlock(tsk);
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index e411a60..fcb93fc 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -152,6 +152,13 @@
kfree(freezer);
}
+/* task is frozen or will freeze immediately when next it gets woken */
+static bool is_task_frozen_enough(struct task_struct *task)
+{
+ return frozen(task) ||
+ (task_is_stopped_or_traced(task) && freezing(task));
+}
+
/*
* The call to cgroup_lock() in the freezer.state write method prevents
* a write to that file racing against an attach, and hence the
@@ -224,7 +231,7 @@
cgroup_iter_start(cgroup, &it);
while ((task = cgroup_iter_next(cgroup, &it))) {
ntotal++;
- if (freezing(task) && frozen(task))
+ if (freezing(task) && is_task_frozen_enough(task))
nfrozen++;
}
@@ -276,7 +283,7 @@
while ((task = cgroup_iter_next(cgroup, &it))) {
if (!freeze_task(task))
continue;
- if (frozen(task))
+ if (is_task_frozen_enough(task))
continue;
if (!freezing(task) && !freezer_should_skip(task))
num_cant_freeze_now++;
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 9fe58c4..0b1712d 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -123,6 +123,19 @@
struct cpuset, css);
}
+#ifdef CONFIG_NUMA
+static inline bool task_has_mempolicy(struct task_struct *task)
+{
+ return task->mempolicy;
+}
+#else
+static inline bool task_has_mempolicy(struct task_struct *task)
+{
+ return false;
+}
+#endif
+
+
/* bits in struct cpuset flags field */
typedef enum {
CS_CPU_EXCLUSIVE,
@@ -949,7 +962,7 @@
static void cpuset_change_task_nodemask(struct task_struct *tsk,
nodemask_t *newmems)
{
- bool masks_disjoint = !nodes_intersects(*newmems, tsk->mems_allowed);
+ bool need_loop;
repeat:
/*
@@ -962,6 +975,14 @@
return;
task_lock(tsk);
+ /*
+ * Determine if a loop is necessary if another thread is doing
+ * get_mems_allowed(). If at least one node remains unchanged and
+ * tsk does not have a mempolicy, then an empty nodemask will not be
+ * possible when mems_allowed is larger than a word.
+ */
+ need_loop = task_has_mempolicy(tsk) ||
+ !nodes_intersects(*newmems, tsk->mems_allowed);
nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
@@ -981,11 +1002,9 @@
/*
* Allocation of memory is very fast, we needn't sleep when waiting
- * for the read-side. No wait is necessary, however, if at least one
- * node remains unchanged.
+ * for the read-side.
*/
- while (masks_disjoint &&
- ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
+ while (need_loop && ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
task_unlock(tsk);
if (!task_curr(tsk))
yield();
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0e8457d..58690af 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -185,6 +185,9 @@
static void update_context_time(struct perf_event_context *ctx);
static u64 perf_event_time(struct perf_event *event);
+static void ring_buffer_attach(struct perf_event *event,
+ struct ring_buffer *rb);
+
void __weak perf_event_print_debug(void) { }
extern __weak const char *perf_pmu_name(void)
@@ -2171,9 +2174,10 @@
*/
cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
- perf_event_sched_in(cpuctx, ctx, task);
+ if (ctx->nr_events)
+ cpuctx->task_ctx = ctx;
- cpuctx->task_ctx = ctx;
+ perf_event_sched_in(cpuctx, cpuctx->task_ctx, task);
perf_pmu_enable(ctx->pmu);
perf_ctx_unlock(cpuctx, ctx);
@@ -3190,12 +3194,33 @@
struct ring_buffer *rb;
unsigned int events = POLL_HUP;
+ /*
+ * Race between perf_event_set_output() and perf_poll(): perf_poll()
+ * grabs the rb reference but perf_event_set_output() overrides it.
+ * Here is the timeline for two threads T1, T2:
+ * t0: T1, rb = rcu_dereference(event->rb)
+ * t1: T2, old_rb = event->rb
+ * t2: T2, event->rb = new rb
+ * t3: T2, ring_buffer_detach(old_rb)
+ * t4: T1, ring_buffer_attach(rb1)
+ * t5: T1, poll_wait(event->waitq)
+ *
+ * To avoid this problem, we grab mmap_mutex in perf_poll()
+ * thereby ensuring that the assignment of the new ring buffer
+ * and the detachment of the old buffer appear atomic to perf_poll()
+ */
+ mutex_lock(&event->mmap_mutex);
+
rcu_read_lock();
rb = rcu_dereference(event->rb);
- if (rb)
+ if (rb) {
+ ring_buffer_attach(event, rb);
events = atomic_xchg(&rb->poll, 0);
+ }
rcu_read_unlock();
+ mutex_unlock(&event->mmap_mutex);
+
poll_wait(file, &event->waitq, wait);
return events;
@@ -3496,6 +3521,53 @@
return ret;
}
+static void ring_buffer_attach(struct perf_event *event,
+ struct ring_buffer *rb)
+{
+ unsigned long flags;
+
+ if (!list_empty(&event->rb_entry))
+ return;
+
+ spin_lock_irqsave(&rb->event_lock, flags);
+ if (!list_empty(&event->rb_entry))
+ goto unlock;
+
+ list_add(&event->rb_entry, &rb->event_list);
+unlock:
+ spin_unlock_irqrestore(&rb->event_lock, flags);
+}
+
+static void ring_buffer_detach(struct perf_event *event,
+ struct ring_buffer *rb)
+{
+ unsigned long flags;
+
+ if (list_empty(&event->rb_entry))
+ return;
+
+ spin_lock_irqsave(&rb->event_lock, flags);
+ list_del_init(&event->rb_entry);
+ wake_up_all(&event->waitq);
+ spin_unlock_irqrestore(&rb->event_lock, flags);
+}
+
+static void ring_buffer_wakeup(struct perf_event *event)
+{
+ struct ring_buffer *rb;
+
+ rcu_read_lock();
+ rb = rcu_dereference(event->rb);
+ if (!rb)
+ goto unlock;
+
+ list_for_each_entry_rcu(event, &rb->event_list, rb_entry)
+ wake_up_all(&event->waitq);
+
+unlock:
+ rcu_read_unlock();
+}
+
static void rb_free_rcu(struct rcu_head *rcu_head)
{
struct ring_buffer *rb;
@@ -3521,9 +3593,19 @@
static void ring_buffer_put(struct ring_buffer *rb)
{
+ struct perf_event *event, *n;
+ unsigned long flags;
+
if (!atomic_dec_and_test(&rb->refcount))
return;
+ spin_lock_irqsave(&rb->event_lock, flags);
+ list_for_each_entry_safe(event, n, &rb->event_list, rb_entry) {
+ list_del_init(&event->rb_entry);
+ wake_up_all(&event->waitq);
+ }
+ spin_unlock_irqrestore(&rb->event_lock, flags);
+
call_rcu(&rb->rcu_head, rb_free_rcu);
}
@@ -3546,6 +3628,7 @@
atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
vma->vm_mm->pinned_vm -= event->mmap_locked;
rcu_assign_pointer(event->rb, NULL);
+ ring_buffer_detach(event, rb);
mutex_unlock(&event->mmap_mutex);
ring_buffer_put(rb);
@@ -3700,7 +3783,7 @@
void perf_event_wakeup(struct perf_event *event)
{
- wake_up_all(&event->waitq);
+ ring_buffer_wakeup(event);
if (event->pending_kill) {
kill_fasync(&event->fasync, SIGIO, event->pending_kill);
@@ -5822,6 +5905,8 @@
INIT_LIST_HEAD(&event->group_entry);
INIT_LIST_HEAD(&event->event_entry);
INIT_LIST_HEAD(&event->sibling_list);
+ INIT_LIST_HEAD(&event->rb_entry);
+
init_waitqueue_head(&event->waitq);
init_irq_work(&event->pending, perf_pending_event);
@@ -6028,6 +6113,8 @@
old_rb = event->rb;
rcu_assign_pointer(event->rb, rb);
+ if (old_rb)
+ ring_buffer_detach(event, old_rb);
ret = 0;
unlock:
mutex_unlock(&event->mmap_mutex);
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 09097dd..64568a6 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -22,6 +22,9 @@
local_t lost; /* nr records lost */
long watermark; /* wakeup watermark */
+ /* poll crap */
+ spinlock_t event_lock;
+ struct list_head event_list;
struct perf_event_mmap_page *user_page;
void *data_pages[0];
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index a2a2920..7f3011c 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -209,6 +209,9 @@
rb->writable = 1;
atomic_set(&rb->refcount, 1);
+
+ INIT_LIST_HEAD(&rb->event_list);
+ spin_lock_init(&rb->event_lock);
}
#ifndef CONFIG_PERF_USE_VMALLOC
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 422e567..ae34bf5 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -885,10 +885,13 @@
struct hrtimer_clock_base *base,
unsigned long newstate, int reprogram)
{
+ struct timerqueue_node *next_timer;
if (!(timer->state & HRTIMER_STATE_ENQUEUED))
goto out;
- if (&timer->node == timerqueue_getnext(&base->active)) {
+ next_timer = timerqueue_getnext(&base->active);
+ timerqueue_del(&base->active, &timer->node);
+ if (&timer->node == next_timer) {
#ifdef CONFIG_HIGH_RES_TIMERS
/* Reprogram the clock event device. if enabled */
if (reprogram && hrtimer_hres_active()) {
@@ -901,7 +904,6 @@
}
#endif
}
- timerqueue_del(&base->active, &timer->node);
if (!timerqueue_getnext(&base->active))
base->cpu_base->active_bases &= ~(1 << base->index);
out:
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 67ce837..1da999f 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -623,8 +623,9 @@
static int irq_wait_for_interrupt(struct irqaction *action)
{
+ set_current_state(TASK_INTERRUPTIBLE);
+
while (!kthread_should_stop()) {
- set_current_state(TASK_INTERRUPTIBLE);
if (test_and_clear_bit(IRQTF_RUNTHREAD,
&action->thread_flags)) {
@@ -632,7 +633,9 @@
return 0;
}
schedule();
+ set_current_state(TASK_INTERRUPTIBLE);
}
+ __set_current_state(TASK_RUNNING);
return -1;
}
@@ -1596,7 +1599,7 @@
return -ENOMEM;
action->handler = handler;
- action->flags = IRQF_PERCPU;
+ action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND;
action->name = devname;
action->percpu_dev_id = dev_id;
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index b5f4742..dc813a9 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -84,7 +84,9 @@
*/
action = desc->action;
if (!action || !(action->flags & IRQF_SHARED) ||
- (action->flags & __IRQF_TIMER) || !action->next)
+ (action->flags & __IRQF_TIMER) ||
+ (action->handler(irq, action->dev_id) == IRQ_HANDLED) ||
+ !action->next)
goto out;
/* Already running on another processor */
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index bbdfe2a..66ff710 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -66,8 +66,9 @@
return;
jump_label_lock();
- if (atomic_add_return(1, &key->enabled) == 1)
+ if (atomic_read(&key->enabled) == 0)
jump_label_update(key, JUMP_LABEL_ENABLE);
+ atomic_inc(&key->enabled);
jump_label_unlock();
}
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index e69434b..b2e08c9 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -44,6 +44,7 @@
#include <linux/stringify.h>
#include <linux/bitops.h>
#include <linux/gfp.h>
+#include <linux/kmemcheck.h>
#include <asm/sections.h>
@@ -2948,7 +2949,12 @@
void lockdep_init_map(struct lockdep_map *lock, const char *name,
struct lock_class_key *key, int subclass)
{
- memset(lock, 0, sizeof(*lock));
+ int i;
+
+ kmemcheck_mark_initialized(lock, sizeof(*lock));
+
+ for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++)
+ lock->class_cache[i] = NULL;
#ifdef CONFIG_LOCK_STAT
lock->cpu = raw_smp_processor_id();
diff --git a/kernel/printk.c b/kernel/printk.c
index 1455a0d..7982a0a 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -1293,10 +1293,11 @@
raw_spin_lock(&logbuf_lock);
if (con_start != log_end)
retry = 1;
+ raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+
if (retry && console_trylock())
goto again;
- raw_spin_unlock_irqrestore(&logbuf_lock, flags);
if (wake_klogd)
wake_up_klogd();
}
diff --git a/kernel/sched.c b/kernel/sched.c
index 0e9344a..d6b149c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -71,6 +71,7 @@
#include <linux/ctype.h>
#include <linux/ftrace.h>
#include <linux/slab.h>
+#include <linux/init_task.h>
#include <asm/tlb.h>
#include <asm/irq_regs.h>
@@ -4810,6 +4811,9 @@
* This waits for either a completion of a specific task to be signaled or for a
* specified timeout to expire. The timeout is in jiffies. It is not
* interruptible.
+ *
+ * The return value is 0 if timed out, and positive (at least 1, or number of
+ * jiffies left till timeout) if completed.
*/
unsigned long __sched
wait_for_completion_timeout(struct completion *x, unsigned long timeout)
@@ -4824,6 +4828,8 @@
*
* This waits for completion of a specific task to be signaled. It is
* interruptible.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if completed.
*/
int __sched wait_for_completion_interruptible(struct completion *x)
{
@@ -4841,6 +4847,9 @@
*
* This waits for either a completion of a specific task to be signaled or for a
* specified timeout to expire. It is interruptible. The timeout is in jiffies.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
+ * positive (at least 1, or number of jiffies left till timeout) if completed.
*/
long __sched
wait_for_completion_interruptible_timeout(struct completion *x,
@@ -4856,6 +4865,8 @@
*
* This waits to be signaled for completion of a specific task. It can be
* interrupted by a kill signal.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if completed.
*/
int __sched wait_for_completion_killable(struct completion *x)
{
@@ -4874,6 +4885,9 @@
* This waits for either a completion of a specific task to be
* signaled or for a specified timeout to expire. It can be
* interrupted by a kill signal. The timeout is in jiffies.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
+ * positive (at least 1, or number of jiffies left till timeout) if completed.
*/
long __sched
wait_for_completion_killable_timeout(struct completion *x,
@@ -6099,6 +6113,9 @@
*/
idle->sched_class = &idle_sched_class;
ftrace_graph_init_idle_task(idle, cpu);
+#if defined(CONFIG_SMP)
+ sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
+#endif
}
/*
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5c9e679..8a39fa3 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -772,19 +772,32 @@
list_del_leaf_cfs_rq(cfs_rq);
}
+static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
+{
+ long tg_weight;
+
+ /*
+ * Use this CPU's actual weight instead of the last load_contribution
+ * to gain a more accurate current total weight. See
+ * update_cfs_rq_load_contribution().
+ */
+ tg_weight = atomic_read(&tg->load_weight);
+ tg_weight -= cfs_rq->load_contribution;
+ tg_weight += cfs_rq->load.weight;
+
+ return tg_weight;
+}
+
static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
- long load_weight, load, shares;
+ long tg_weight, load, shares;
+ tg_weight = calc_tg_weight(tg, cfs_rq);
load = cfs_rq->load.weight;
- load_weight = atomic_read(&tg->load_weight);
- load_weight += load;
- load_weight -= cfs_rq->load_contribution;
-
shares = (tg->shares * load);
- if (load_weight)
- shares /= load_weight;
+ if (tg_weight)
+ shares /= tg_weight;
if (shares < MIN_SHARES)
shares = MIN_SHARES;
@@ -1743,7 +1756,7 @@
static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
- if (!cfs_rq->runtime_enabled || !cfs_rq->nr_running)
+ if (!cfs_rq->runtime_enabled || cfs_rq->nr_running)
return;
__return_cfs_rq_runtime(cfs_rq);
@@ -2036,36 +2049,100 @@
* Adding load to a group doesn't make a group heavier, but can cause movement
* of group shares between cpus. Assuming the shares were perfectly aligned one
* can calculate the shift in shares.
+ *
+ * Calculate the effective load difference if @wl is added (subtracted) to @tg
+ * on this @cpu and results in a total addition (subtraction) of @wg to the
+ * total group weight.
+ *
+ * Given a runqueue weight distribution (rw_i) we can compute a shares
+ * distribution (s_i) using:
+ *
+ * s_i = rw_i / \Sum rw_j (1)
+ *
+ * Suppose we have 4 CPUs and our @tg is a direct child of the root group and
+ * has 7 equal weight tasks, distributed as below (rw_i), with the resulting
+ * shares distribution (s_i):
+ *
+ * rw_i = { 2, 4, 1, 0 }
+ * s_i = { 2/7, 4/7, 1/7, 0 }
+ *
+ * As per wake_affine() we're interested in the load of two CPUs (the CPU the
+ * task used to run on and the CPU the waker is running on), we need to
+ * compute the effect of waking a task on either CPU and, in case of a sync
+ * wakeup, compute the effect of the current task going to sleep.
+ *
+ * So for a change of @wl to the local @cpu with an overall group weight change
+ * of @wl we can compute the new shares distribution (s'_i) using:
+ *
+ * s'_i = (rw_i + @wl) / (@wg + \Sum rw_j) (2)
+ *
+ * Suppose we're interested in CPUs 0 and 1, and want to compute the load
+ * differences in waking a task to CPU 0. The additional task changes the
+ * weight and shares distributions like:
+ *
+ * rw'_i = { 3, 4, 1, 0 }
+ * s'_i = { 3/8, 4/8, 1/8, 0 }
+ *
+ * We can then compute the difference in effective weight by using:
+ *
+ * dw_i = S * (s'_i - s_i) (3)
+ *
+ * Where 'S' is the group weight as seen by its parent.
+ *
+ * Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7)
+ * times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 -
+ * 4/7) times the weight of the group.
*/
static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
{
struct sched_entity *se = tg->se[cpu];
- if (!tg->parent)
+ if (!tg->parent) /* the trivial, non-cgroup case */
return wl;
for_each_sched_entity(se) {
- long lw, w;
+ long w, W;
tg = se->my_q->tg;
- w = se->my_q->load.weight;
- /* use this cpu's instantaneous contribution */
- lw = atomic_read(&tg->load_weight);
- lw -= se->my_q->load_contribution;
- lw += w + wg;
+ /*
+ * W = @wg + \Sum rw_j
+ */
+ W = wg + calc_tg_weight(tg, se->my_q);
- wl += w;
+ /*
+ * w = rw_i + @wl
+ */
+ w = se->my_q->load.weight + wl;
- if (lw > 0 && wl < lw)
- wl = (wl * tg->shares) / lw;
+ /*
+ * wl = S * s'_i; see (2)
+ */
+ if (W > 0 && w < W)
+ wl = (w * tg->shares) / W;
else
wl = tg->shares;
- /* zero point is MIN_SHARES */
+ /*
+ * Per the above, wl is the new se->load.weight value; since
+ * those are clipped to [MIN_SHARES, ...) do so now. See
+ * calc_cfs_shares().
+ */
if (wl < MIN_SHARES)
wl = MIN_SHARES;
+
+ /*
+ * wl = dw_i = S * (s'_i - s_i); see (3)
+ */
wl -= se->load.weight;
+
+ /*
+ * Recursively apply this logic to all parent groups to compute
+ * the final effective load change on the root group. Since
+ * only the @tg group gets extra weight, all parent groups can
+ * only redistribute existing shares. @wl is the shift in shares
+ * resulting from this level per the above.
+ */
wg = 0;
}
@@ -2249,7 +2326,8 @@
int cpu = smp_processor_id();
int prev_cpu = task_cpu(p);
struct sched_domain *sd;
- int i;
+ struct sched_group *sg;
+ int i, smt = 0;
/*
* If the task is going to be woken-up on this cpu and if it is
@@ -2269,25 +2347,40 @@
* Otherwise, iterate the domains and find an elegible idle cpu.
*/
rcu_read_lock();
+again:
for_each_domain(target, sd) {
+ if (!smt && (sd->flags & SD_SHARE_CPUPOWER))
+ continue;
+
+ if (smt && !(sd->flags & SD_SHARE_CPUPOWER))
+ break;
+
if (!(sd->flags & SD_SHARE_PKG_RESOURCES))
break;
- for_each_cpu_and(i, sched_domain_span(sd), tsk_cpus_allowed(p)) {
- if (idle_cpu(i)) {
- target = i;
- break;
- }
- }
+ sg = sd->groups;
+ do {
+ if (!cpumask_intersects(sched_group_cpus(sg),
+ tsk_cpus_allowed(p)))
+ goto next;
- /*
- * Lets stop looking for an idle sibling when we reached
- * the domain that spans the current cpu and prev_cpu.
- */
- if (cpumask_test_cpu(cpu, sched_domain_span(sd)) &&
- cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
- break;
+ for_each_cpu(i, sched_group_cpus(sg)) {
+ if (!idle_cpu(i))
+ goto next;
+ }
+
+ target = cpumask_first_and(sched_group_cpus(sg),
+ tsk_cpus_allowed(p));
+ goto done;
+next:
+ sg = sg->next;
+ } while (sg != sd->groups);
}
+ if (!smt) {
+ smt = 1;
+ goto again;
+ }
+done:
rcu_read_unlock();
return target;
@@ -3511,7 +3604,7 @@
}
/**
- * update_sd_lb_stats - Update sched_group's statistics for load balancing.
+ * update_sd_lb_stats - Update sched_domain's statistics for load balancing.
* @sd: sched_domain whose statistics are to be updated.
* @this_cpu: Cpu for which load balance is currently performed.
* @idle: Idle status of this_cpu
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index efa0a7b..8480224 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -67,3 +67,4 @@
SCHED_FEAT(TTWU_QUEUE, 1)
SCHED_FEAT(FORCE_SD_OVERLAP, 0)
+SCHED_FEAT(RT_RUNTIME_SHARE, 1)
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 056cbd2..583a136 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -560,6 +560,9 @@
{
int more = 0;
+ if (!sched_feat(RT_RUNTIME_SHARE))
+ return more;
+
if (rt_rq->rt_time > rt_rq->rt_runtime) {
raw_spin_unlock(&rt_rq->rt_runtime_lock);
more = do_balance_runtime(rt_rq);
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 6318b51..a650694 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -1354,7 +1354,7 @@
fput(file);
out_putname:
- putname(pathname);
+ __putname(pathname);
out:
return result;
}
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index c436e79..8a46f5d 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -195,7 +195,7 @@
struct alarm *alarm;
ktime_t expired = next->expires;
- if (expired.tv64 >= now.tv64)
+ if (expired.tv64 > now.tv64)
break;
alarm = container_of(next, struct alarm, node);
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 1ecd6ba..c4eb71c 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -387,6 +387,7 @@
* released list and do a notify add later.
*/
if (old) {
+ old->event_handler = clockevents_handle_noop;
clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
list_del(&old->list);
list_add(&old->list, &clockevents_released);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index cf52fda..d3ad022 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -492,6 +492,22 @@
}
/**
+ * clocksource_max_adjustment- Returns max adjustment amount
+ * @cs: Pointer to clocksource
+ *
+ */
+static u32 clocksource_max_adjustment(struct clocksource *cs)
+{
+ u64 ret;
+ /*
+ * We won't try to correct for more then 11% adjustments (110,000 ppm),
+ */
+ ret = (u64)cs->mult * 11;
+ do_div(ret,100);
+ return (u32)ret;
+}
+
+/**
* clocksource_max_deferment - Returns max time the clocksource can be deferred
* @cs: Pointer to clocksource
*
@@ -503,25 +519,28 @@
/*
* Calculate the maximum number of cycles that we can pass to the
* cyc2ns function without overflowing a 64-bit signed result. The
- * maximum number of cycles is equal to ULLONG_MAX/cs->mult which
- * is equivalent to the below.
- * max_cycles < (2^63)/cs->mult
- * max_cycles < 2^(log2((2^63)/cs->mult))
- * max_cycles < 2^(log2(2^63) - log2(cs->mult))
- * max_cycles < 2^(63 - log2(cs->mult))
- * max_cycles < 1 << (63 - log2(cs->mult))
+ * maximum number of cycles is equal to ULLONG_MAX/(cs->mult+cs->maxadj)
+ * which is equivalent to the below.
+ * max_cycles < (2^63)/(cs->mult + cs->maxadj)
+ * max_cycles < 2^(log2((2^63)/(cs->mult + cs->maxadj)))
+ * max_cycles < 2^(log2(2^63) - log2(cs->mult + cs->maxadj))
+ * max_cycles < 2^(63 - log2(cs->mult + cs->maxadj))
+ * max_cycles < 1 << (63 - log2(cs->mult + cs->maxadj))
* Please note that we add 1 to the result of the log2 to account for
* any rounding errors, ensure the above inequality is satisfied and
* no overflow will occur.
*/
- max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1));
+ max_cycles = 1ULL << (63 - (ilog2(cs->mult + cs->maxadj) + 1));
/*
* The actual maximum number of cycles we can defer the clocksource is
* determined by the minimum of max_cycles and cs->mask.
+ * Note: Here we subtract the maxadj to make sure we don't sleep for
+ * too long if there's a large negative adjustment.
*/
max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
- max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift);
+ max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult - cs->maxadj,
+ cs->shift);
/*
* To ensure that the clocksource does not wrap whilst we are idle,
@@ -529,7 +548,7 @@
* note a margin of 12.5% is used because this can be computed with
* a shift, versus say 10% which would require division.
*/
- return max_nsecs - (max_nsecs >> 5);
+ return max_nsecs - (max_nsecs >> 3);
}
#ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
@@ -628,7 +647,7 @@
/**
* __clocksource_updatefreq_scale - Used update clocksource with new freq
- * @t: clocksource to be registered
+ * @cs: clocksource to be registered
* @scale: Scale factor multiplied against freq to get clocksource hz
* @freq: clocksource frequency (cycles per second) divided by scale
*
@@ -640,7 +659,6 @@
void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
{
u64 sec;
-
/*
* Calc the maximum number of seconds which we can run before
* wrapping around. For clocksources which have a mask > 32bit
@@ -651,7 +669,7 @@
* ~ 0.06ppm granularity for NTP. We apply the same 12.5%
* margin as we do in clocksource_max_deferment()
*/
- sec = (cs->mask - (cs->mask >> 5));
+ sec = (cs->mask - (cs->mask >> 3));
do_div(sec, freq);
do_div(sec, scale);
if (!sec)
@@ -661,13 +679,27 @@
clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
NSEC_PER_SEC / scale, sec * scale);
+
+ /*
+ * for clocksources that have large mults, to avoid overflow.
+ * Since mult may be adjusted by ntp, add an safety extra margin
+ *
+ */
+ cs->maxadj = clocksource_max_adjustment(cs);
+ while ((cs->mult + cs->maxadj < cs->mult)
+ || (cs->mult - cs->maxadj > cs->mult)) {
+ cs->mult >>= 1;
+ cs->shift--;
+ cs->maxadj = clocksource_max_adjustment(cs);
+ }
+
cs->max_idle_ns = clocksource_max_deferment(cs);
}
EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
/**
* __clocksource_register_scale - Used to install new clocksources
- * @t: clocksource to be registered
+ * @cs: clocksource to be registered
* @scale: Scale factor multiplied against freq to get clocksource hz
* @freq: clocksource frequency (cycles per second) divided by scale
*
@@ -695,12 +727,18 @@
/**
* clocksource_register - Used to install new clocksources
- * @t: clocksource to be registered
+ * @cs: clocksource to be registered
*
* Returns -EBUSY if registration fails, zero otherwise.
*/
int clocksource_register(struct clocksource *cs)
{
+ /* calculate max adjustment for given mult/shift */
+ cs->maxadj = clocksource_max_adjustment(cs);
+ WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
+ "Clocksource %s might overflow on 11%% adjustment\n",
+ cs->name);
+
/* calculate max idle time permitted for this clocksource */
cs->max_idle_ns = clocksource_max_deferment(cs);
@@ -723,6 +761,8 @@
/**
* clocksource_change_rating - Change the rating of a registered clocksource
+ * @cs: clocksource to be changed
+ * @rating: new rating
*/
void clocksource_change_rating(struct clocksource *cs, int rating)
{
@@ -734,6 +774,7 @@
/**
* clocksource_unregister - remove a registered clocksource
+ * @cs: clocksource to be unregistered
*/
void clocksource_unregister(struct clocksource *cs)
{
@@ -749,6 +790,7 @@
/**
* sysfs_show_current_clocksources - sysfs interface for current clocksource
* @dev: unused
+ * @attr: unused
* @buf: char buffer to be filled with clocksource list
*
* Provides sysfs interface for listing current clocksource.
@@ -769,6 +811,7 @@
/**
* sysfs_override_clocksource - interface for manually overriding clocksource
* @dev: unused
+ * @attr: unused
* @buf: name of override clocksource
* @count: length of buffer
*
@@ -804,6 +847,7 @@
/**
* sysfs_show_available_clocksources - sysfs interface for listing clocksource
* @dev: unused
+ * @attr: unused
* @buf: char buffer to be filled with clocksource list
*
* Provides sysfs interface for listing registered clocksources
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index f954282..fd4a7b1 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -71,7 +71,7 @@
(dev->features & CLOCK_EVT_FEAT_C3STOP))
return 0;
- clockevents_exchange_device(NULL, dev);
+ clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
tick_broadcast_device.evtdev = dev;
if (!cpumask_empty(tick_get_broadcast_mask()))
tick_broadcast_start_periodic(dev);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 2b021b0e..2378413 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -249,6 +249,8 @@
secs = xtime.tv_sec + wall_to_monotonic.tv_sec;
nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec;
nsecs += timekeeping_get_ns();
+ /* If arch requires, add in gettimeoffset() */
+ nsecs += arch_gettimeoffset();
} while (read_seqretry(&xtime_lock, seq));
/*
@@ -280,6 +282,8 @@
*ts = xtime;
tomono = wall_to_monotonic;
nsecs = timekeeping_get_ns();
+ /* If arch requires, add in gettimeoffset() */
+ nsecs += arch_gettimeoffset();
} while (read_seqretry(&xtime_lock, seq));
@@ -802,14 +806,44 @@
s64 error, interval = timekeeper.cycle_interval;
int adj;
+ /*
+ * The point of this is to check if the error is greater then half
+ * an interval.
+ *
+ * First we shift it down from NTP_SHIFT to clocksource->shifted nsecs.
+ *
+ * Note we subtract one in the shift, so that error is really error*2.
+ * This "saves" dividing(shifting) intererval twice, but keeps the
+ * (error > interval) comparision as still measuring if error is
+ * larger then half an interval.
+ *
+ * Note: It does not "save" on aggrivation when reading the code.
+ */
error = timekeeper.ntp_error >> (timekeeper.ntp_error_shift - 1);
if (error > interval) {
+ /*
+ * We now divide error by 4(via shift), which checks if
+ * the error is greater then twice the interval.
+ * If it is greater, we need a bigadjust, if its smaller,
+ * we can adjust by 1.
+ */
error >>= 2;
+ /*
+ * XXX - In update_wall_time, we round up to the next
+ * nanosecond, and store the amount rounded up into
+ * the error. This causes the likely below to be unlikely.
+ *
+ * The properfix is to avoid rounding up by using
+ * the high precision timekeeper.xtime_nsec instead of
+ * xtime.tv_nsec everywhere. Fixing this will take some
+ * time.
+ */
if (likely(error <= interval))
adj = 1;
else
adj = timekeeping_bigadjust(error, &interval, &offset);
} else if (error < -interval) {
+ /* See comment above, this is just switched for the negative */
error >>= 2;
if (likely(error >= -interval)) {
adj = -1;
@@ -817,9 +851,65 @@
offset = -offset;
} else
adj = timekeeping_bigadjust(error, &interval, &offset);
- } else
+ } else /* No adjustment needed */
return;
+ WARN_ONCE(timekeeper.clock->maxadj &&
+ (timekeeper.mult + adj > timekeeper.clock->mult +
+ timekeeper.clock->maxadj),
+ "Adjusting %s more then 11%% (%ld vs %ld)\n",
+ timekeeper.clock->name, (long)timekeeper.mult + adj,
+ (long)timekeeper.clock->mult +
+ timekeeper.clock->maxadj);
+ /*
+ * So the following can be confusing.
+ *
+ * To keep things simple, lets assume adj == 1 for now.
+ *
+ * When adj != 1, remember that the interval and offset values
+ * have been appropriately scaled so the math is the same.
+ *
+ * The basic idea here is that we're increasing the multiplier
+ * by one, this causes the xtime_interval to be incremented by
+ * one cycle_interval. This is because:
+ * xtime_interval = cycle_interval * mult
+ * So if mult is being incremented by one:
+ * xtime_interval = cycle_interval * (mult + 1)
+ * Its the same as:
+ * xtime_interval = (cycle_interval * mult) + cycle_interval
+ * Which can be shortened to:
+ * xtime_interval += cycle_interval
+ *
+ * So offset stores the non-accumulated cycles. Thus the current
+ * time (in shifted nanoseconds) is:
+ * now = (offset * adj) + xtime_nsec
+ * Now, even though we're adjusting the clock frequency, we have
+ * to keep time consistent. In other words, we can't jump back
+ * in time, and we also want to avoid jumping forward in time.
+ *
+ * So given the same offset value, we need the time to be the same
+ * both before and after the freq adjustment.
+ * now = (offset * adj_1) + xtime_nsec_1
+ * now = (offset * adj_2) + xtime_nsec_2
+ * So:
+ * (offset * adj_1) + xtime_nsec_1 =
+ * (offset * adj_2) + xtime_nsec_2
+ * And we know:
+ * adj_2 = adj_1 + 1
+ * So:
+ * (offset * adj_1) + xtime_nsec_1 =
+ * (offset * (adj_1+1)) + xtime_nsec_2
+ * (offset * adj_1) + xtime_nsec_1 =
+ * (offset * adj_1) + offset + xtime_nsec_2
+ * Canceling the sides:
+ * xtime_nsec_1 = offset + xtime_nsec_2
+ * Which gives us:
+ * xtime_nsec_2 = xtime_nsec_1 - offset
+ * Which simplfies to:
+ * xtime_nsec -= offset
+ *
+ * XXX - TODO: Doc ntp_error calculation.
+ */
timekeeper.mult += adj;
timekeeper.xtime_interval += interval;
timekeeper.xtime_nsec -= offset;
diff --git a/kernel/timer.c b/kernel/timer.c
index dbaa624..9c3c62b 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1368,7 +1368,7 @@
int pid;
rcu_read_lock();
- pid = task_tgid_vnr(current->real_parent);
+ pid = task_tgid_vnr(rcu_dereference(current->real_parent));
rcu_read_unlock();
return pid;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 900b409..b1e8943 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -152,7 +152,6 @@
ftrace_pid_function = ftrace_stub;
}
-#undef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
/*
* For those archs that do not test ftrace_trace_stop in their
@@ -1212,7 +1211,9 @@
if (!src->count) {
free_ftrace_hash_rcu(*dst);
rcu_assign_pointer(*dst, EMPTY_HASH);
- return 0;
+ /* still need to update the function records */
+ ret = 0;
+ goto out;
}
/*
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 581876f..c212a7f 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1078,7 +1078,6 @@
/* First see if we did not already create this dir */
list_for_each_entry(system, &event_subsystems, list) {
if (strcmp(system->name, name) == 0) {
- __get_system(system);
system->nr_events++;
return system->entry;
}
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 816d3d0..95dc31e 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1649,7 +1649,9 @@
*/
err = replace_preds(call, NULL, ps, filter_string, true);
if (err)
- goto fail;
+ call->flags |= TRACE_EVENT_FL_NO_SET_FILTER;
+ else
+ call->flags &= ~TRACE_EVENT_FL_NO_SET_FILTER;
}
list_for_each_entry(call, &ftrace_events, list) {
@@ -1658,6 +1660,9 @@
if (strcmp(call->class->system, system->name) != 0)
continue;
+ if (call->flags & TRACE_EVENT_FL_NO_SET_FILTER)
+ continue;
+
filter_item = kzalloc(sizeof(*filter_item), GFP_KERNEL);
if (!filter_item)
goto fail_mem;
@@ -1686,7 +1691,7 @@
* replace the filter for the call.
*/
filter = call->filter;
- call->filter = filter_item->filter;
+ rcu_assign_pointer(call->filter, filter_item->filter);
filter_item->filter = filter;
fail = false;
@@ -1741,7 +1746,7 @@
filter = call->filter;
if (!filter)
goto out_unlock;
- call->filter = NULL;
+ RCU_INIT_POINTER(call->filter, NULL);
/* Make sure the filter is not being used */
synchronize_sched();
__free_filter(filter);
@@ -1782,7 +1787,7 @@
* string
*/
tmp = call->filter;
- call->filter = filter;
+ rcu_assign_pointer(call->filter, filter);
if (tmp) {
/* Make sure the call is done with the filter */
synchronize_sched();