summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorIngo Molnar <mingo@kernel.org>2016-02-29 09:42:07 +0100
committerIngo Molnar <mingo@kernel.org>2016-02-29 09:42:07 +0100
commit6aa447bcbb444cd1b738613a20627f288d631665 (patch)
tree62030bb14be0006248181305ac1fe377a99e5b65 /kernel
parentabedf8e2419fb873d919dd74de2e84b510259339 (diff)
parent48be3a67da7413d62e5efbcf2c73a9dddf61fb96 (diff)
downloadop-kernel-dev-6aa447bcbb444cd1b738613a20627f288d631665.zip
op-kernel-dev-6aa447bcbb444cd1b738613a20627f288d631665.tar.gz
Merge branch 'sched/urgent' into sched/core, to pick up fixes before applying new changes
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/verifier.c2
-rw-r--r--kernel/cgroup.c31
-rw-r--r--kernel/cpuset.c71
-rw-r--r--kernel/events/core.c372
-rw-r--r--kernel/locking/lockdep.c58
-rw-r--r--kernel/memremap.c8
-rw-r--r--kernel/module.c124
-rw-r--r--kernel/resource.c5
-rw-r--r--kernel/sched/core.c4
-rw-r--r--kernel/sched/deadline.c24
-rw-r--r--kernel/sched/fair.c37
-rw-r--r--kernel/sched/sched.h2
-rw-r--r--kernel/signal.c6
-rw-r--r--kernel/trace/ftrace.c36
-rw-r--r--kernel/trace/trace_events.c3
-rw-r--r--kernel/trace/trace_stack.c6
-rw-r--r--kernel/workqueue.c74
17 files changed, 546 insertions, 317 deletions
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d1d3e8f..2e7f7ab 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2082,7 +2082,7 @@ static void adjust_branches(struct bpf_prog *prog, int pos, int delta)
/* adjust offset of jmps if necessary */
if (i < pos && i + insn->off + 1 > pos)
insn->off += delta;
- else if (i > pos && i + insn->off + 1 < pos)
+ else if (i > pos + delta && i + insn->off + 1 <= pos + delta)
insn->off -= delta;
}
}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c03a640..d27904c 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -58,6 +58,7 @@
#include <linux/kthread.h>
#include <linux/delay.h>
#include <linux/atomic.h>
+#include <linux/cpuset.h>
#include <net/sock.h>
/*
@@ -2739,6 +2740,7 @@ out_unlock_rcu:
out_unlock_threadgroup:
percpu_up_write(&cgroup_threadgroup_rwsem);
cgroup_kn_unlock(of->kn);
+ cpuset_post_attach_flush();
return ret ?: nbytes;
}
@@ -4655,14 +4657,15 @@ static void css_free_work_fn(struct work_struct *work)
if (ss) {
/* css free path */
+ struct cgroup_subsys_state *parent = css->parent;
int id = css->id;
- if (css->parent)
- css_put(css->parent);
-
ss->css_free(css);
cgroup_idr_remove(&ss->css_idr, id);
cgroup_put(cgrp);
+
+ if (parent)
+ css_put(parent);
} else {
/* cgroup free path */
atomic_dec(&cgrp->root->nr_cgrps);
@@ -4758,6 +4761,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
INIT_LIST_HEAD(&css->sibling);
INIT_LIST_HEAD(&css->children);
css->serial_nr = css_serial_nr_next++;
+ atomic_set(&css->online_cnt, 0);
if (cgroup_parent(cgrp)) {
css->parent = cgroup_css(cgroup_parent(cgrp), ss);
@@ -4780,6 +4784,10 @@ static int online_css(struct cgroup_subsys_state *css)
if (!ret) {
css->flags |= CSS_ONLINE;
rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
+
+ atomic_inc(&css->online_cnt);
+ if (css->parent)
+ atomic_inc(&css->parent->online_cnt);
}
return ret;
}
@@ -5017,10 +5025,15 @@ static void css_killed_work_fn(struct work_struct *work)
container_of(work, struct cgroup_subsys_state, destroy_work);
mutex_lock(&cgroup_mutex);
- offline_css(css);
- mutex_unlock(&cgroup_mutex);
- css_put(css);
+ do {
+ offline_css(css);
+ css_put(css);
+ /* @css can't go away while we're holding cgroup_mutex */
+ css = css->parent;
+ } while (css && atomic_dec_and_test(&css->online_cnt));
+
+ mutex_unlock(&cgroup_mutex);
}
/* css kill confirmation processing requires process context, bounce */
@@ -5029,8 +5042,10 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
struct cgroup_subsys_state *css =
container_of(ref, struct cgroup_subsys_state, refcnt);
- INIT_WORK(&css->destroy_work, css_killed_work_fn);
- queue_work(cgroup_destroy_wq, &css->destroy_work);
+ if (atomic_dec_and_test(&css->online_cnt)) {
+ INIT_WORK(&css->destroy_work, css_killed_work_fn);
+ queue_work(cgroup_destroy_wq, &css->destroy_work);
+ }
}
/**
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 3e945fc..41989ab 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -287,6 +287,8 @@ static struct cpuset top_cpuset = {
static DEFINE_MUTEX(cpuset_mutex);
static DEFINE_SPINLOCK(callback_lock);
+static struct workqueue_struct *cpuset_migrate_mm_wq;
+
/*
* CPU / memory hotplug is handled asynchronously.
*/
@@ -972,31 +974,51 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
}
/*
- * cpuset_migrate_mm
- *
- * Migrate memory region from one set of nodes to another.
- *
- * Temporarilly set tasks mems_allowed to target nodes of migration,
- * so that the migration code can allocate pages on these nodes.
- *
- * While the mm_struct we are migrating is typically from some
- * other task, the task_struct mems_allowed that we are hacking
- * is for our current task, which must allocate new pages for that
- * migrating memory region.
+ * Migrate memory region from one set of nodes to another. This is
+ * performed asynchronously as it can be called from process migration path
+ * holding locks involved in process management. All mm migrations are
+ * performed in the queued order and can be waited for by flushing
+ * cpuset_migrate_mm_wq.
*/
+struct cpuset_migrate_mm_work {
+ struct work_struct work;
+ struct mm_struct *mm;
+ nodemask_t from;
+ nodemask_t to;
+};
+
+static void cpuset_migrate_mm_workfn(struct work_struct *work)
+{
+ struct cpuset_migrate_mm_work *mwork =
+ container_of(work, struct cpuset_migrate_mm_work, work);
+
+ /* on a wq worker, no need to worry about %current's mems_allowed */
+ do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL);
+ mmput(mwork->mm);
+ kfree(mwork);
+}
+
static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
const nodemask_t *to)
{
- struct task_struct *tsk = current;
-
- tsk->mems_allowed = *to;
+ struct cpuset_migrate_mm_work *mwork;
- do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
+ mwork = kzalloc(sizeof(*mwork), GFP_KERNEL);
+ if (mwork) {
+ mwork->mm = mm;
+ mwork->from = *from;
+ mwork->to = *to;
+ INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn);
+ queue_work(cpuset_migrate_mm_wq, &mwork->work);
+ } else {
+ mmput(mm);
+ }
+}
- rcu_read_lock();
- guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed);
- rcu_read_unlock();
+void cpuset_post_attach_flush(void)
+{
+ flush_workqueue(cpuset_migrate_mm_wq);
}
/*
@@ -1097,7 +1119,8 @@ static void update_tasks_nodemask(struct cpuset *cs)
mpol_rebind_mm(mm, &cs->mems_allowed);
if (migrate)
cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems);
- mmput(mm);
+ else
+ mmput(mm);
}
css_task_iter_end(&it);
@@ -1545,11 +1568,11 @@ static void cpuset_attach(struct cgroup_taskset *tset)
* @old_mems_allowed is the right nodesets that we
* migrate mm from.
*/
- if (is_memory_migrate(cs)) {
+ if (is_memory_migrate(cs))
cpuset_migrate_mm(mm, &oldcs->old_mems_allowed,
&cpuset_attach_nodemask_to);
- }
- mmput(mm);
+ else
+ mmput(mm);
}
}
@@ -1714,6 +1737,7 @@ out_unlock:
mutex_unlock(&cpuset_mutex);
kernfs_unbreak_active_protection(of->kn);
css_put(&cs->css);
+ flush_workqueue(cpuset_migrate_mm_wq);
return retval ?: nbytes;
}
@@ -2359,6 +2383,9 @@ void __init cpuset_init_smp(void)
top_cpuset.effective_mems = node_states[N_MEMORY];
register_hotmemory_notifier(&cpuset_track_online_nodes_nb);
+
+ cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0);
+ BUG_ON(!cpuset_migrate_mm_wq);
}
/**
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5946460..6146148 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -64,8 +64,17 @@ static void remote_function(void *data)
struct task_struct *p = tfc->p;
if (p) {
- tfc->ret = -EAGAIN;
- if (task_cpu(p) != smp_processor_id() || !task_curr(p))
+ /* -EAGAIN */
+ if (task_cpu(p) != smp_processor_id())
+ return;
+
+ /*
+ * Now that we're on right CPU with IRQs disabled, we can test
+ * if we hit the right task without races.
+ */
+
+ tfc->ret = -ESRCH; /* No such (running) process */
+ if (p != current)
return;
}
@@ -92,13 +101,17 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info)
.p = p,
.func = func,
.info = info,
- .ret = -ESRCH, /* No such (running) process */
+ .ret = -EAGAIN,
};
+ int ret;
- if (task_curr(p))
- smp_call_function_single(task_cpu(p), remote_function, &data, 1);
+ do {
+ ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1);
+ if (!ret)
+ ret = data.ret;
+ } while (ret == -EAGAIN);
- return data.ret;
+ return ret;
}
/**
@@ -169,19 +182,6 @@ static bool is_kernel_event(struct perf_event *event)
* rely on ctx->is_active and therefore cannot use event_function_call().
* See perf_install_in_context().
*
- * This is because we need a ctx->lock serialized variable (ctx->is_active)
- * to reliably determine if a particular task/context is scheduled in. The
- * task_curr() use in task_function_call() is racy in that a remote context
- * switch is not a single atomic operation.
- *
- * As is, the situation is 'safe' because we set rq->curr before we do the
- * actual context switch. This means that task_curr() will fail early, but
- * we'll continue spinning on ctx->is_active until we've passed
- * perf_event_task_sched_out().
- *
- * Without this ctx->lock serialized variable we could have race where we find
- * the task (and hence the context) would not be active while in fact they are.
- *
* If ctx->nr_events, then ctx->is_active and cpuctx->task_ctx are set.
*/
@@ -212,7 +212,7 @@ static int event_function(void *info)
*/
if (ctx->task) {
if (ctx->task != current) {
- ret = -EAGAIN;
+ ret = -ESRCH;
goto unlock;
}
@@ -276,10 +276,10 @@ static void event_function_call(struct perf_event *event, event_f func, void *da
return;
}
-again:
if (task == TASK_TOMBSTONE)
return;
+again:
if (!task_function_call(task, event_function, &efs))
return;
@@ -289,13 +289,15 @@ again:
* a concurrent perf_event_context_sched_out().
*/
task = ctx->task;
- if (task != TASK_TOMBSTONE) {
- if (ctx->is_active) {
- raw_spin_unlock_irq(&ctx->lock);
- goto again;
- }
- func(event, NULL, ctx, data);
+ if (task == TASK_TOMBSTONE) {
+ raw_spin_unlock_irq(&ctx->lock);
+ return;
}
+ if (ctx->is_active) {
+ raw_spin_unlock_irq(&ctx->lock);
+ goto again;
+ }
+ func(event, NULL, ctx, data);
raw_spin_unlock_irq(&ctx->lock);
}
@@ -314,6 +316,7 @@ again:
enum event_type_t {
EVENT_FLEXIBLE = 0x1,
EVENT_PINNED = 0x2,
+ EVENT_TIME = 0x4,
EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
};
@@ -321,7 +324,13 @@ enum event_type_t {
* perf_sched_events : >0 events exist
* perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
*/
-struct static_key_deferred perf_sched_events __read_mostly;
+
+static void perf_sched_delayed(struct work_struct *work);
+DEFINE_STATIC_KEY_FALSE(perf_sched_events);
+static DECLARE_DELAYED_WORK(perf_sched_work, perf_sched_delayed);
+static DEFINE_MUTEX(perf_sched_mutex);
+static atomic_t perf_sched_count;
+
static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
static DEFINE_PER_CPU(int, perf_sched_cb_usages);
@@ -1288,16 +1297,18 @@ static u64 perf_event_time(struct perf_event *event)
/*
* Update the total_time_enabled and total_time_running fields for a event.
- * The caller of this function needs to hold the ctx->lock.
*/
static void update_event_times(struct perf_event *event)
{
struct perf_event_context *ctx = event->ctx;
u64 run_end;
+ lockdep_assert_held(&ctx->lock);
+
if (event->state < PERF_EVENT_STATE_INACTIVE ||
event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
return;
+
/*
* in cgroup mode, time_enabled represents
* the time the event was enabled AND active
@@ -1645,7 +1656,7 @@ out:
static bool is_orphaned_event(struct perf_event *event)
{
- return event->state == PERF_EVENT_STATE_EXIT;
+ return event->state == PERF_EVENT_STATE_DEAD;
}
static inline int pmu_filter_match(struct perf_event *event)
@@ -1690,14 +1701,14 @@ event_sched_out(struct perf_event *event,
perf_pmu_disable(event->pmu);
+ event->tstamp_stopped = tstamp;
+ event->pmu->del(event, 0);
+ event->oncpu = -1;
event->state = PERF_EVENT_STATE_INACTIVE;
if (event->pending_disable) {
event->pending_disable = 0;
event->state = PERF_EVENT_STATE_OFF;
}
- event->tstamp_stopped = tstamp;
- event->pmu->del(event, 0);
- event->oncpu = -1;
if (!is_software_event(event))
cpuctx->active_oncpu--;
@@ -1732,7 +1743,6 @@ group_sched_out(struct perf_event *group_event,
}
#define DETACH_GROUP 0x01UL
-#define DETACH_STATE 0x02UL
/*
* Cross CPU call to remove a performance event
@@ -1752,8 +1762,6 @@ __perf_remove_from_context(struct perf_event *event,
if (flags & DETACH_GROUP)
perf_group_detach(event);
list_del_event(event, ctx);
- if (flags & DETACH_STATE)
- event->state = PERF_EVENT_STATE_EXIT;
if (!ctx->nr_events && ctx->is_active) {
ctx->is_active = 0;
@@ -2063,14 +2071,27 @@ static void add_event_to_ctx(struct perf_event *event,
event->tstamp_stopped = tstamp;
}
-static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
- struct perf_event_context *ctx);
+static void ctx_sched_out(struct perf_event_context *ctx,
+ struct perf_cpu_context *cpuctx,
+ enum event_type_t event_type);
static void
ctx_sched_in(struct perf_event_context *ctx,
struct perf_cpu_context *cpuctx,
enum event_type_t event_type,
struct task_struct *task);
+static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
+ struct perf_event_context *ctx)
+{
+ if (!cpuctx->task_ctx)
+ return;
+
+ if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
+ return;
+
+ ctx_sched_out(ctx, cpuctx, EVENT_ALL);
+}
+
static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
struct perf_event_context *ctx,
struct task_struct *task)
@@ -2097,49 +2118,68 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
/*
* Cross CPU call to install and enable a performance event
*
- * Must be called with ctx->mutex held
+ * Very similar to remote_function() + event_function() but cannot assume that
+ * things like ctx->is_active and cpuctx->task_ctx are set.
*/
static int __perf_install_in_context(void *info)
{
- struct perf_event_context *ctx = info;
+ struct perf_event *event = info;
+ struct perf_event_context *ctx = event->ctx;
struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
struct perf_event_context *task_ctx = cpuctx->task_ctx;
+ bool activate = true;
+ int ret = 0;
raw_spin_lock(&cpuctx->ctx.lock);
if (ctx->task) {
raw_spin_lock(&ctx->lock);
- /*
- * If we hit the 'wrong' task, we've since scheduled and
- * everything should be sorted, nothing to do!
- */
task_ctx = ctx;
- if (ctx->task != current)
+
+ /* If we're on the wrong CPU, try again */
+ if (task_cpu(ctx->task) != smp_processor_id()) {
+ ret = -ESRCH;
goto unlock;
+ }
/*
- * If task_ctx is set, it had better be to us.
+ * If we're on the right CPU, see if the task we target is
+ * current, if not we don't have to activate the ctx, a future
+ * context switch will do that for us.
*/
- WARN_ON_ONCE(cpuctx->task_ctx != ctx && cpuctx->task_ctx);
+ if (ctx->task != current)
+ activate = false;
+ else
+ WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx);
+
} else if (task_ctx) {
raw_spin_lock(&task_ctx->lock);
}
- ctx_resched(cpuctx, task_ctx);
+ if (activate) {
+ ctx_sched_out(ctx, cpuctx, EVENT_TIME);
+ add_event_to_ctx(event, ctx);
+ ctx_resched(cpuctx, task_ctx);
+ } else {
+ add_event_to_ctx(event, ctx);
+ }
+
unlock:
perf_ctx_unlock(cpuctx, task_ctx);
- return 0;
+ return ret;
}
/*
- * Attach a performance event to a context
+ * Attach a performance event to a context.
+ *
+ * Very similar to event_function_call, see comment there.
*/
static void
perf_install_in_context(struct perf_event_context *ctx,
struct perf_event *event,
int cpu)
{
- struct task_struct *task = NULL;
+ struct task_struct *task = READ_ONCE(ctx->task);
lockdep_assert_held(&ctx->mutex);
@@ -2147,40 +2187,46 @@ perf_install_in_context(struct perf_event_context *ctx,
if (event->cpu != -1)
event->cpu = cpu;
+ if (!task) {
+ cpu_function_call(cpu, __perf_install_in_context, event);
+ return;
+ }
+
+ /*
+ * Should not happen, we validate the ctx is still alive before calling.
+ */
+ if (WARN_ON_ONCE(task == TASK_TOMBSTONE))
+ return;
+
/*
* Installing events is tricky because we cannot rely on ctx->is_active
* to be set in case this is the nr_events 0 -> 1 transition.
- *
- * So what we do is we add the event to the list here, which will allow
- * a future context switch to DTRT and then send a racy IPI. If the IPI
- * fails to hit the right task, this means a context switch must have
- * happened and that will have taken care of business.
*/
- raw_spin_lock_irq(&ctx->lock);
- task = ctx->task;
+again:
/*
- * Worse, we cannot even rely on the ctx actually existing anymore. If
- * between find_get_context() and perf_install_in_context() the task
- * went through perf_event_exit_task() its dead and we should not be
- * adding new events.
+ * Cannot use task_function_call() because we need to run on the task's
+ * CPU regardless of whether its current or not.
*/
- if (task == TASK_TOMBSTONE) {
+ if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event))
+ return;
+
+ raw_spin_lock_irq(&ctx->lock);
+ task = ctx->task;
+ if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) {
+ /*
+ * Cannot happen because we already checked above (which also
+ * cannot happen), and we hold ctx->mutex, which serializes us
+ * against perf_event_exit_task_context().
+ */
raw_spin_unlock_irq(&ctx->lock);
return;
}
- update_context_time(ctx);
+ raw_spin_unlock_irq(&ctx->lock);
/*
- * Update cgrp time only if current cgrp matches event->cgrp.
- * Must be done before calling add_event_to_ctx().
+ * Since !ctx->is_active doesn't mean anything, we must IPI
+ * unconditionally.
*/
- update_cgrp_time_from_event(event);
- add_event_to_ctx(event, ctx);
- raw_spin_unlock_irq(&ctx->lock);
-
- if (task)
- task_function_call(task, __perf_install_in_context, ctx);
- else
- cpu_function_call(cpu, __perf_install_in_context, ctx);
+ goto again;
}
/*
@@ -2219,17 +2265,18 @@ static void __perf_event_enable(struct perf_event *event,
event->state <= PERF_EVENT_STATE_ERROR)
return;
- update_context_time(ctx);
+ if (ctx->is_active)
+ ctx_sched_out(ctx, cpuctx, EVENT_TIME);
+
__perf_event_mark_enabled(event);
if (!ctx->is_active)
return;
if (!event_filter_match(event)) {
- if (is_cgroup_event(event)) {
- perf_cgroup_set_timestamp(current, ctx); // XXX ?
+ if (is_cgroup_event(event))
perf_cgroup_defer_enabled(event);
- }
+ ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
return;
}
@@ -2237,8 +2284,10 @@ static void __perf_event_enable(struct perf_event *event,
* If the event is in a group and isn't the group leader,
* then don't put it on unless the group is on.
*/
- if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE)
+ if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) {
+ ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
return;
+ }
task_ctx = cpuctx->task_ctx;
if (ctx->task)
@@ -2344,24 +2393,33 @@ static void ctx_sched_out(struct perf_event_context *ctx,
}
ctx->is_active &= ~event_type;
+ if (!(ctx->is_active & EVENT_ALL))
+ ctx->is_active = 0;
+
if (ctx->task) {
WARN_ON_ONCE(cpuctx->task_ctx != ctx);
if (!ctx->is_active)
cpuctx->task_ctx = NULL;
}
- update_context_time(ctx);
- update_cgrp_time_from_cpuctx(cpuctx);
- if (!ctx->nr_active)
+ is_active ^= ctx->is_active; /* changed bits */
+
+ if (is_active & EVENT_TIME) {
+ /* update (and stop) ctx time */
+ update_context_time(ctx);
+ update_cgrp_time_from_cpuctx(cpuctx);
+ }
+
+ if (!ctx->nr_active || !(is_active & EVENT_ALL))
return;
perf_pmu_disable(ctx->pmu);
- if ((is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) {
+ if (is_active & EVENT_PINNED) {
list_for_each_entry(event, &ctx->pinned_groups, group_entry)
group_sched_out(event, cpuctx, ctx);
}
- if ((is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) {
+ if (is_active & EVENT_FLEXIBLE) {
list_for_each_entry(event, &ctx->flexible_groups, group_entry)
group_sched_out(event, cpuctx, ctx);
}
@@ -2641,18 +2699,6 @@ void __perf_event_task_sched_out(struct task_struct *task,
perf_cgroup_sched_out(task, next);
}
-static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
- struct perf_event_context *ctx)
-{
- if (!cpuctx->task_ctx)
- return;
-
- if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
- return;
-
- ctx_sched_out(ctx, cpuctx, EVENT_ALL);
-}
-
/*
* Called with IRQs disabled
*/
@@ -2735,7 +2781,7 @@ ctx_sched_in(struct perf_event_context *ctx,
if (likely(!ctx->nr_events))
return;
- ctx->is_active |= event_type;
+ ctx->is_active |= (event_type | EVENT_TIME);
if (ctx->task) {
if (!is_active)
cpuctx->task_ctx = ctx;
@@ -2743,18 +2789,24 @@ ctx_sched_in(struct perf_event_context *ctx,
WARN_ON_ONCE(cpuctx->task_ctx != ctx);
}
- now = perf_clock();
- ctx->timestamp = now;
- perf_cgroup_set_timestamp(task, ctx);
+ is_active ^= ctx->is_active; /* changed bits */
+
+ if (is_active & EVENT_TIME) {
+ /* start ctx time */
+ now = perf_clock();
+ ctx->timestamp = now;
+ perf_cgroup_set_timestamp(task, ctx);
+ }
+
/*
* First go through the list and put on any pinned groups
* in order to give them the best chance of going on.
*/
- if (!(is_active & EVENT_PINNED) && (event_type & EVENT_PINNED))
+ if (is_active & EVENT_PINNED)
ctx_pinned_sched_in(ctx, cpuctx);
/* Then walk through the lower prio flexible groups */
- if (!(is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE))
+ if (is_active & EVENT_FLEXIBLE)
ctx_flexible_sched_in(ctx, cpuctx);
}
@@ -3120,6 +3172,7 @@ static void perf_event_enable_on_exec(int ctxn)
cpuctx = __get_cpu_context(ctx);
perf_ctx_lock(cpuctx, ctx);
+ ctx_sched_out(ctx, cpuctx, EVENT_TIME);
list_for_each_entry(event, &ctx->event_list, event_entry)
enabled |= event_enable_on_exec(event, ctx);
@@ -3537,12 +3590,22 @@ static void unaccount_event(struct perf_event *event)
if (has_branch_stack(event))
dec = true;
- if (dec)
- static_key_slow_dec_deferred(&perf_sched_events);
+ if (dec) {
+ if (!atomic_add_unless(&perf_sched_count, -1, 1))
+ schedule_delayed_work(&perf_sched_work, HZ);
+ }
unaccount_event_cpu(event, event->cpu);
}
+static void perf_sched_delayed(struct work_struct *work)
+{
+ mutex_lock(&perf_sched_mutex);
+ if (atomic_dec_and_test(&perf_sched_count))
+ static_branch_disable(&perf_sched_events);
+ mutex_unlock(&perf_sched_mutex);
+}
+
/*
* The following implement mutual exclusion of events on "exclusive" pmus
* (PERF_PMU_CAP_EXCLUSIVE). Such pmus can only have one event scheduled
@@ -3752,30 +3815,42 @@ static void put_event(struct perf_event *event)
*/
int perf_event_release_kernel(struct perf_event *event)
{
- struct perf_event_context *ctx;
+ struct perf_event_context *ctx = event->ctx;
struct perf_event *child, *tmp;
+ /*
+ * If we got here through err_file: fput(event_file); we will not have
+ * attached to a context yet.
+ */
+ if (!ctx) {
+ WARN_ON_ONCE(event->attach_state &
+ (PERF_ATTACH_CONTEXT|PERF_ATTACH_GROUP));
+ goto no_ctx;
+ }
+
if (!is_kernel_event(event))
perf_remove_from_owner(event);
ctx = perf_event_ctx_lock(event);
WARN_ON_ONCE(ctx->parent_ctx);
- perf_remove_from_context(event, DETACH_GROUP | DETACH_STATE);
- perf_event_ctx_unlock(event, ctx);
+ perf_remove_from_context(event, DETACH_GROUP);
+ raw_spin_lock_irq(&ctx->lock);
/*
- * At this point we must have event->state == PERF_EVENT_STATE_EXIT,
- * either from the above perf_remove_from_context() or through
- * perf_event_exit_event().
+ * Mark this even as STATE_DEAD, there is no external reference to it
+ * anymore.
*
- * Therefore, anybody acquiring event->child_mutex after the below
- * loop _must_ also see this, most importantly inherit_event() which
- * will avoid placing more children on the list.
+ * Anybody acquiring event->child_mutex after the below loop _must_
+ * also see this, most importantly inherit_event() which will avoid
+ * placing more children on the list.
*
* Thus this guarantees that we will in fact observe and kill _ALL_
* child events.
*/
- WARN_ON_ONCE(event->state != PERF_EVENT_STATE_EXIT);
+ event->state = PERF_EVENT_STATE_DEAD;
+ raw_spin_unlock_irq(&ctx->lock);
+
+ perf_event_ctx_unlock(event, ctx);
again:
mutex_lock(&event->child_mutex);
@@ -3830,8 +3905,8 @@ again:
}
mutex_unlock(&event->child_mutex);
- /* Must be the last reference */
- put_event(event);
+no_ctx:
+ put_event(event); /* Must be the 'last' reference */
return 0;
}
EXPORT_SYMBOL_GPL(perf_event_release_kernel);
@@ -3988,7 +4063,7 @@ static bool is_event_hup(struct perf_event *event)
{
bool no_children;
- if (event->state != PERF_EVENT_STATE_EXIT)
+ if (event->state > PERF_EVENT_STATE_EXIT)
return false;
mutex_lock(&event->child_mutex);
@@ -7769,8 +7844,28 @@ static void account_event(struct perf_event *event)
if (is_cgroup_event(event))
inc = true;
- if (inc)
- static_key_slow_inc(&perf_sched_events.key);
+ if (inc) {
+ if (atomic_inc_not_zero(&perf_sched_count))
+ goto enabled;
+
+ mutex_lock(&perf_sched_mutex);
+ if (!atomic_read(&perf_sched_count)) {
+ static_branch_enable(&perf_sched_events);
+ /*
+ * Guarantee that all CPUs observe they key change and
+ * call the perf scheduling hooks before proceeding to
+ * install events that need them.
+ */
+ synchronize_sched();
+ }
+ /*
+ * Now that we have waited for the sync_sched(), allow further
+ * increments to by-pass the mutex.
+ */
+ atomic_inc(&perf_sched_count);
+ mutex_unlock(&perf_sched_mutex);
+ }
+enabled:
account_event_cpu(event, event->cpu);
}
@@ -8389,10 +8484,19 @@ SYSCALL_DEFINE5(perf_event_open,
if (move_group) {
gctx = group_leader->ctx;
mutex_lock_double(&gctx->mutex, &ctx->mutex);
+ if (gctx->task == TASK_TOMBSTONE) {
+ err = -ESRCH;
+ goto err_locked;
+ }
} else {
mutex_lock(&ctx->mutex);
}
+ if (ctx->task == TASK_TOMBSTONE) {
+ err = -ESRCH;
+ goto err_locked;
+ }
+
if (!perf_event_validate_size(event)) {
err = -E2BIG;
goto err_locked;
@@ -8509,7 +8613,12 @@ err_context:
perf_unpin_context(ctx);
put_ctx(ctx);
err_alloc:
- free_event(event);
+ /*
+ * If event_file is set, the fput() above will have called ->release()
+ * and that will take care of freeing the event.
+ */
+ if (!event_file)
+ free_event(event);
err_cpus:
put_online_cpus();
err_task:
@@ -8563,12 +8672,14 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
WARN_ON_ONCE(ctx->parent_ctx);
mutex_lock(&ctx->mutex);
+ if (ctx->task == TASK_TOMBSTONE) {
+ err = -ESRCH;
+ goto err_unlock;
+ }
+
if (!exclusive_event_installable(event, ctx)) {
- mutex_unlock(&ctx->mutex);
- perf_unpin_context(ctx);
- put_ctx(ctx);
err = -EBUSY;
- goto err_free;
+ goto err_unlock;
}
perf_install_in_context(ctx, event, cpu);
@@ -8577,6 +8688,10 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
return event;
+err_unlock:
+ mutex_unlock(&ctx->mutex);
+ perf_unpin_context(ctx);
+ put_ctx(ctx);
err_free:
free_event(event);
err:
@@ -8695,7 +8810,7 @@ perf_event_exit_event(struct perf_event *child_event,
if (parent_event)
perf_group_detach(child_event);
list_del_event(child_event, child_ctx);
- child_event->state = PERF_EVENT_STATE_EXIT; /* see perf_event_release_kernel() */
+ child_event->state = PERF_EVENT_STATE_EXIT; /* is_event_hup() */
raw_spin_unlock_irq(&child_ctx->lock);
/*
@@ -9206,7 +9321,7 @@ static void perf_event_init_cpu(int cpu)
struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
mutex_lock(&swhash->hlist_mutex);
- if (swhash->hlist_refcount > 0) {
+ if (swhash->hlist_refcount > 0 && !swevent_hlist_deref(swhash)) {
struct swevent_hlist *hlist;
hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu));
@@ -9282,11 +9397,9 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_UP_PREPARE:
- case CPU_DOWN_FAILED:
perf_event_init_cpu(cpu);
break;
- case CPU_UP_CANCELED:
case CPU_DOWN_PREPARE:
perf_event_exit_cpu(cpu);
break;
@@ -9315,9 +9428,6 @@ void __init perf_event_init(void)
ret = init_hw_breakpoint();
WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
- /* do not patch jump label more than once per second */
- jump_label_rate_limit(&perf_sched_events, HZ);
-
/*
* Build time assertion that we keep the data_head at the intended
* location. IOW, validation we got the __reserved[] size right.
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 60ace56..716547f 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -292,7 +292,7 @@ LIST_HEAD(all_lock_classes);
#define __classhashfn(key) hash_long((unsigned long)key, CLASSHASH_BITS)
#define classhashentry(key) (classhash_table + __classhashfn((key)))
-static struct list_head classhash_table[CLASSHASH_SIZE];
+static struct hlist_head classhash_table[CLASSHASH_SIZE];
/*
* We put the lock dependency chains into a hash-table as well, to cache
@@ -303,7 +303,7 @@ static struct list_head classhash_table[CLASSHASH_SIZE];
#define __chainhashfn(chain) hash_long(chain, CHAINHASH_BITS)
#define chainhashentry(chain) (chainhash_table + __chainhashfn((chain)))
-static struct list_head chainhash_table[CHAINHASH_SIZE];
+static struct hlist_head chainhash_table[CHAINHASH_SIZE];
/*
* The hash key of the lock dependency chains is a hash itself too:
@@ -666,7 +666,7 @@ static inline struct lock_class *
look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
{
struct lockdep_subclass_key *key;
- struct list_head *hash_head;
+ struct hlist_head *hash_head;
struct lock_class *class;
#ifdef CONFIG_DEBUG_LOCKDEP
@@ -719,7 +719,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
return NULL;
- list_for_each_entry_rcu(class, hash_head, hash_entry) {
+ hlist_for_each_entry_rcu(class, hash_head, hash_entry) {
if (class->key == key) {
/*
* Huh! same key, different name? Did someone trample
@@ -742,7 +742,7 @@ static inline struct lock_class *
register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
{
struct lockdep_subclass_key *key;
- struct list_head *hash_head;
+ struct hlist_head *hash_head;
struct lock_class *class;
DEBUG_LOCKS_WARN_ON(!irqs_disabled());
@@ -774,7 +774,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
* We have to do the hash-walk again, to avoid races
* with another CPU:
*/
- list_for_each_entry_rcu(class, hash_head, hash_entry) {
+ hlist_for_each_entry_rcu(class, hash_head, hash_entry) {
if (class->key == key)
goto out_unlock_set;
}
@@ -805,7 +805,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
* We use RCU's safe list-add method to make
* parallel walking of the hash-list safe:
*/
- list_add_tail_rcu(&class->hash_entry, hash_head);
+ hlist_add_head_rcu(&class->hash_entry, hash_head);
/*
* Add it to the global list of classes:
*/
@@ -1822,7 +1822,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next,
*/
static int
check_prev_add(struct task_struct *curr, struct held_lock *prev,
- struct held_lock *next, int distance, int trylock_loop)
+ struct held_lock *next, int distance, int *stack_saved)
{
struct lock_list *entry;
int ret;
@@ -1883,8 +1883,11 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
}
}
- if (!trylock_loop && !save_trace(&trace))
- return 0;
+ if (!*stack_saved) {
+ if (!save_trace(&trace))
+ return 0;
+ *stack_saved = 1;
+ }
/*
* Ok, all validations passed, add the new lock
@@ -1907,6 +1910,8 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
* Debugging printouts:
*/
if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) {
+ /* We drop graph lock, so another thread can overwrite trace. */
+ *stack_saved = 0;
graph_unlock();
printk("\n new dependency: ");
print_lock_name(hlock_class(prev));
@@ -1929,7 +1934,7 @@ static int
check_prevs_add(struct task_struct *curr, struct held_lock *next)
{
int depth = curr->lockdep_depth;
- int trylock_loop = 0;
+ int stack_saved = 0;
struct held_lock *hlock;
/*
@@ -1956,7 +1961,7 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
*/
if (hlock->read != 2 && hlock->check) {
if (!check_prev_add(curr, hlock, next,
- distance, trylock_loop))
+ distance, &stack_saved))
return 0;
/*
* Stop after the first non-trylock entry,
@@ -1979,7 +1984,6 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
if (curr->held_locks[depth].irq_context !=
curr->held_locks[depth-1].irq_context)
break;
- trylock_loop = 1;
}
return 1;
out_bug:
@@ -2017,7 +2021,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
u64 chain_key)
{
struct lock_class *class = hlock_class(hlock);
- struct list_head *hash_head = chainhashentry(chain_key);
+ struct hlist_head *hash_head = chainhashentry(chain_key);
struct lock_chain *chain;
struct held_lock *hlock_curr;
int i, j;
@@ -2033,7 +2037,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
* We can walk it lock-free, because entries only get added
* to the hash:
*/
- list_for_each_entry_rcu(chain, hash_head, entry) {
+ hlist_for_each_entry_rcu(chain, hash_head, entry) {
if (chain->chain_key == chain_key) {
cache_hit:
debug_atomic_inc(chain_lookup_hits);
@@ -2057,7 +2061,7 @@ cache_hit:
/*
* We have to walk the chain again locked - to avoid duplicates:
*/
- list_for_each_entry(chain, hash_head, entry) {
+ hlist_for_each_entry(chain, hash_head, entry) {
if (chain->chain_key == chain_key) {
graph_unlock();
goto cache_hit;
@@ -2091,7 +2095,7 @@ cache_hit:
}
chain_hlocks[chain->base + j] = class - lock_classes;
}
- list_add_tail_rcu(&chain->entry, hash_head);
+ hlist_add_head_rcu(&chain->entry, hash_head);
debug_atomic_inc(chain_lookup_misses);
inc_chains();
@@ -3875,7 +3879,7 @@ void lockdep_reset(void)
nr_process_chains = 0;
debug_locks = 1;
for (i = 0; i < CHAINHASH_SIZE; i++)
- INIT_LIST_HEAD(chainhash_table + i);
+ INIT_HLIST_HEAD(chainhash_table + i);
raw_local_irq_restore(flags);
}
@@ -3894,7 +3898,7 @@ static void zap_class(struct lock_class *class)
/*
* Unhash the class and remove it from the all_lock_classes list:
*/
- list_del_rcu(&class->hash_entry);
+ hlist_del_rcu(&class->hash_entry);
list_del_rcu(&class->lock_entry);
RCU_INIT_POINTER(class->key, NULL);
@@ -3917,7 +3921,7 @@ static inline int within(const void *addr, void *start, unsigned long size)
void lockdep_free_key_range(void *start, unsigned long size)
{
struct lock_class *class;
- struct list_head *head;
+ struct hlist_head *head;
unsigned long flags;
int i;
int locked;
@@ -3930,9 +3934,7 @@ void lockdep_free_key_range(void *start, unsigned long size)
*/
for (i = 0; i < CLASSHASH_SIZE; i++) {
head = classhash_table + i;
- if (list_empty(head))
- continue;
- list_for_each_entry_rcu(class, head, hash_entry) {
+ hlist_for_each_entry_rcu(class, head, hash_entry) {
if (within(class->key, start, size))
zap_class(class);
else if (within(class->name, start, size))
@@ -3962,7 +3964,7 @@ void lockdep_free_key_range(void *start, unsigned long size)
void lockdep_reset_lock(struct lockdep_map *lock)
{
struct lock_class *class;
- struct list_head *head;
+ struct hlist_head *head;
unsigned long flags;
int i, j;
int locked;
@@ -3987,9 +3989,7 @@ void lockdep_reset_lock(struct lockdep_map *lock)
locked = graph_lock();
for (i = 0; i < CLASSHASH_SIZE; i++) {
head = classhash_table + i;
- if (list_empty(head))
- continue;
- list_for_each_entry_rcu(class, head, hash_entry) {
+ hlist_for_each_entry_rcu(class, head, hash_entry) {
int match = 0;
for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
@@ -4027,10 +4027,10 @@ void lockdep_init(void)
return;
for (i = 0; i < CLASSHASH_SIZE; i++)
- INIT_LIST_HEAD(classhash_table + i);
+ INIT_HLIST_HEAD(classhash_table + i);
for (i = 0; i < CHAINHASH_SIZE; i++)
- INIT_LIST_HEAD(chainhash_table + i);
+ INIT_HLIST_HEAD(chainhash_table + i);
lockdep_initialized = 1;
}
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 70ee377..b981a7b 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -114,7 +114,7 @@ EXPORT_SYMBOL(memunmap);
static void devm_memremap_release(struct device *dev, void *res)
{
- memunmap(res);
+ memunmap(*(void **)res);
}
static int devm_memremap_match(struct device *dev, void *res, void *match_data)
@@ -136,8 +136,10 @@ void *devm_memremap(struct device *dev, resource_size_t offset,
if (addr) {
*ptr = addr;
devres_add(dev, ptr);
- } else
+ } else {
devres_free(ptr);
+ return ERR_PTR(-ENXIO);
+ }
return addr;
}
@@ -150,7 +152,7 @@ void devm_memunmap(struct device *dev, void *addr)
}
EXPORT_SYMBOL(devm_memunmap);
-pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags)
+pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags)
{
return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags);
}
diff --git a/kernel/module.c b/kernel/module.c
index 8358f46..794ebe8 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -303,6 +303,9 @@ struct load_info {
struct _ddebug *debug;
unsigned int num_debug;
bool sig_ok;
+#ifdef CONFIG_KALLSYMS
+ unsigned long mod_kallsyms_init_off;
+#endif
struct {
unsigned int sym, str, mod, vers, info, pcpu;
} index;
@@ -981,6 +984,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
mod->exit();
blocking_notifier_call_chain(&module_notify_list,
MODULE_STATE_GOING, mod);
+ ftrace_release_mod(mod);
+
async_synchronize_full();
/* Store the name of the last unloaded module for diagnostic purposes */
@@ -2480,10 +2485,21 @@ static void layout_symtab(struct module *mod, struct load_info *info)
strsect->sh_flags |= SHF_ALLOC;
strsect->sh_entsize = get_offset(mod, &mod->init_layout.size, strsect,
info->index.str) | INIT_OFFSET_MASK;
- mod->init_layout.size = debug_align(mod->init_layout.size);
pr_debug("\t%s\n", info->secstrings + strsect->sh_name);
+
+ /* We'll tack temporary mod_kallsyms on the end. */
+ mod->init_layout.size = ALIGN(mod->init_layout.size,
+ __alignof__(struct mod_kallsyms));
+ info->mod_kallsyms_init_off = mod->init_layout.size;
+ mod->init_layout.size += sizeof(struct mod_kallsyms);
+ mod->init_layout.size = debug_align(mod->init_layout.size);
}
+/*
+ * We use the full symtab and strtab which layout_symtab arranged to
+ * be appended to the init section. Later we switch to the cut-down
+ * core-only ones.
+ */
static void add_kallsyms(struct module *mod, const struct load_info *info)
{
unsigned int i, ndst;
@@ -2492,29 +2508,34 @@ static void add_kallsyms(struct module *mod, const struct load_info *info)
char *s;
Elf_Shdr *symsec = &info->sechdrs[info->index.sym];
- mod->symtab = (void *)symsec->sh_addr;
- mod->num_symtab = symsec->sh_size / sizeof(Elf_Sym);
+ /* Set up to point into init section. */
+ mod->kallsyms = mod->init_layout.base + info->mod_kallsyms_init_off;
+
+ mod->kallsyms->symtab = (void *)symsec->sh_addr;
+ mod->kallsyms->num_symtab = symsec->sh_size / sizeof(Elf_Sym);
/* Make sure we get permanent strtab: don't use info->strtab. */
- mod->strtab = (void *)info->sechdrs[info->index.str].sh_addr;
+ mod->kallsyms->strtab = (void *)info->sechdrs[info->index.str].sh_addr;
/* Set types up while we still have access to sections. */
- for (i = 0; i < mod->num_symtab; i++)
- mod->symtab[i].st_info = elf_type(&mod->symtab[i], info);
-
- mod->core_symtab = dst = mod->core_layout.base + info->symoffs;
- mod->core_strtab = s = mod->core_layout.base + info->stroffs;
- src = mod->symtab;
- for (ndst = i = 0; i < mod->num_symtab; i++) {
+ for (i = 0; i < mod->kallsyms->num_symtab; i++)
+ mod->kallsyms->symtab[i].st_info
+ = elf_type(&mod->kallsyms->symtab[i], info);
+
+ /* Now populate the cut down core kallsyms for after init. */
+ mod->core_kallsyms.symtab = dst = mod->core_layout.base + info->symoffs;
+ mod->core_kallsyms.strtab = s = mod->core_layout.base + info->stroffs;
+ src = mod->kallsyms->symtab;
+ for (ndst = i = 0; i < mod->kallsyms->num_symtab; i++) {
if (i == 0 ||
is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum,
info->index.pcpu)) {
dst[ndst] = src[i];
- dst[ndst++].st_name = s - mod->core_strtab;
- s += strlcpy(s, &mod->strtab[src[i].st_name],
+ dst[ndst++].st_name = s - mod->core_kallsyms.strtab;
+ s += strlcpy(s, &mod->kallsyms->strtab[src[i].st_name],
KSYM_NAME_LEN) + 1;
}
}
- mod->core_num_syms = ndst;
+ mod->core_kallsyms.num_symtab = ndst;
}
#else
static inline void layout_symtab(struct module *mod, struct load_info *info)
@@ -3263,9 +3284,8 @@ static noinline int do_init_module(struct module *mod)
module_put(mod);
trim_init_extable(mod);
#ifdef CONFIG_KALLSYMS
- mod->num_symtab = mod->core_num_syms;
- mod->symtab = mod->core_symtab;
- mod->strtab = mod->core_strtab;
+ /* Switch to core kallsyms now init is done: kallsyms may be walking! */
+ rcu_assign_pointer(mod->kallsyms, &mod->core_kallsyms);
#endif
mod_tree_remove_init(mod);
disable_ro_nx(&mod->init_layout);
@@ -3295,6 +3315,7 @@ fail:
module_put(mod);
blocking_notifier_call_chain(&module_notify_list,
MODULE_STATE_GOING, mod);
+ ftrace_release_mod(mod);
free_module(mod);
wake_up_all(&module_wq);
return ret;
@@ -3371,6 +3392,7 @@ static int complete_formation(struct module *mod, struct load_info *info)
mod->state = MODULE_STATE_COMING;
mutex_unlock(&module_mutex);
+ ftrace_module_enable(mod);
blocking_notifier_call_chain(&module_notify_list,
MODULE_STATE_COMING, mod);
return 0;
@@ -3496,7 +3518,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
/* Module is ready to execute: parsing args may do that. */
after_dashes = parse_args(mod->name, mod->args, mod->kp, mod->num_kp,
- -32768, 32767, NULL,
+ -32768, 32767, mod,
unknown_module_param_cb);
if (IS_ERR(after_dashes)) {
err = PTR_ERR(after_dashes);
@@ -3627,6 +3649,11 @@ static inline int is_arm_mapping_symbol(const char *str)
&& (str[2] == '\0' || str[2] == '.');
}
+static const char *symname(struct mod_kallsyms *kallsyms, unsigned int symnum)
+{
+ return kallsyms->strtab + kallsyms->symtab[symnum].st_name;
+}
+
static const char *get_ksymbol(struct module *mod,
unsigned long addr,
unsigned long *size,
@@ -3634,6 +3661,7 @@ static const char *get_ksymbol(struct module *mod,
{
unsigned int i, best = 0;
unsigned long nextval;
+ struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms);
/* At worse, next value is at end of module */
if (within_module_init(addr, mod))
@@ -3643,32 +3671,32 @@ static const char *get_ksymbol(struct module *mod,
/* Scan for closest preceding symbol, and next symbol. (ELF
starts real symbols at 1). */
- for (i = 1; i < mod->num_symtab; i++) {
- if (mod->symtab[i].st_shndx == SHN_UNDEF)
+ for (i = 1; i < kallsyms->num_symtab; i++) {
+ if (kallsyms->symtab[i].st_shndx == SHN_UNDEF)
continue;
/* We ignore unnamed symbols: they're uninformative
* and inserted at a whim. */
- if (mod->symtab[i].st_value <= addr
- && mod->symtab[i].st_value > mod->symtab[best].st_value
- && *(mod->strtab + mod->symtab[i].st_name) != '\0'
- && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name))
+ if (*symname(kallsyms, i) == '\0'
+ || is_arm_mapping_symbol(symname(kallsyms, i)))
+ continue;
+
+ if (kallsyms->symtab[i].st_value <= addr
+ && kallsyms->symtab[i].st_value > kallsyms->symtab[best].st_value)
best = i;
- if (mod->symtab[i].st_value > addr
- && mod->symtab[i].st_value < nextval
- && *(mod->strtab + mod->symtab[i].st_name) != '\0'
- && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name))
- nextval = mod->symtab[i].st_value;
+ if (kallsyms->symtab[i].st_value > addr
+ && kallsyms->symtab[i].st_value < nextval)
+ nextval = kallsyms->symtab[i].st_value;
}
if (!best)
return NULL;
if (size)
- *size = nextval - mod->symtab[best].st_value;
+ *size = nextval - kallsyms->symtab[best].st_value;
if (offset)
- *offset = addr - mod->symtab[best].st_value;
- return mod->strtab + mod->symtab[best].st_name;
+ *offset = addr - kallsyms->symtab[best].st_value;
+ return symname(kallsyms, best);
}
/* For kallsyms to ask for address resolution. NULL means not found. Careful
@@ -3758,19 +3786,21 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
preempt_disable();
list_for_each_entry_rcu(mod, &modules, list) {
+ struct mod_kallsyms *kallsyms;
+
if (mod->state == MODULE_STATE_UNFORMED)
continue;
- if (symnum < mod->num_symtab) {
- *value = mod->symtab[symnum].st_value;
- *type = mod->symtab[symnum].st_info;
- strlcpy(name, mod->strtab + mod->symtab[symnum].st_name,
- KSYM_NAME_LEN);
+ kallsyms = rcu_dereference_sched(mod->kallsyms);
+ if (symnum < kallsyms->num_symtab) {
+ *value = kallsyms->symtab[symnum].st_value;
+ *type = kallsyms->symtab[symnum].st_info;
+ strlcpy(name, symname(kallsyms, symnum), KSYM_NAME_LEN);
strlcpy(module_name, mod->name, MODULE_NAME_LEN);
*exported = is_exported(name, *value, mod);
preempt_enable();
return 0;
}
- symnum -= mod->num_symtab;
+ symnum -= kallsyms->num_symtab;
}
preempt_enable();
return -ERANGE;
@@ -3779,11 +3809,12 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
static unsigned long mod_find_symname(struct module *mod, const char *name)
{
unsigned int i;
+ struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms);
- for (i = 0; i < mod->num_symtab; i++)
- if (strcmp(name, mod->strtab+mod->symtab[i].st_name) == 0 &&
- mod->symtab[i].st_info != 'U')
- return mod->symtab[i].st_value;
+ for (i = 0; i < kallsyms->num_symtab; i++)
+ if (strcmp(name, symname(kallsyms, i)) == 0 &&
+ kallsyms->symtab[i].st_info != 'U')
+ return kallsyms->symtab[i].st_value;
return 0;
}
@@ -3822,11 +3853,14 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
module_assert_mutex();
list_for_each_entry(mod, &modules, list) {
+ /* We hold module_mutex: no need for rcu_dereference_sched */
+ struct mod_kallsyms *kallsyms = mod->kallsyms;
+
if (mod->state == MODULE_STATE_UNFORMED)
continue;
- for (i = 0; i < mod->num_symtab; i++) {
- ret = fn(data, mod->strtab + mod->symtab[i].st_name,
- mod, mod->symtab[i].st_value);
+ for (i = 0; i < kallsyms->num_symtab; i++) {
+ ret = fn(data, symname(kallsyms, i),
+ mod, kallsyms->symtab[i].st_value);
if (ret != 0)
return ret;
}
diff --git a/kernel/resource.c b/kernel/resource.c
index 09c0597..3669d1b 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1083,9 +1083,10 @@ struct resource * __request_region(struct resource *parent,
if (!conflict)
break;
if (conflict != parent) {
- parent = conflict;
- if (!(conflict->flags & IORESOURCE_BUSY))
+ if (!(conflict->flags & IORESOURCE_BUSY)) {
+ parent = conflict;
continue;
+ }
}
if (conflict->flags & flags & IORESOURCE_MUXED) {
add_wait_queue(&muxed_resource_wait, &wait);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 87ca0be..291552b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7930,11 +7930,9 @@ void sched_destroy_group(struct task_group *tg)
void sched_offline_group(struct task_group *tg)
{
unsigned long flags;
- int i;
/* end participation in shares distribution */
- for_each_possible_cpu(i)
- unregister_fair_sched_group(tg, i);
+ unregister_fair_sched_group(tg);
spin_lock_irqsave(&task_group_lock, flags);
list_del_rcu(&tg->list);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index cd64c97..04a569c 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -399,6 +399,9 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
dl_se->runtime = pi_se->dl_runtime;
}
+ if (dl_se->dl_yielded && dl_se->runtime > 0)
+ dl_se->runtime = 0;
+
/*
* We keep moving the deadline away until we get some
* available runtime for the entity. This ensures correct
@@ -420,7 +423,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
* entity.
*/
if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
- printk_deferred_once("sched: DL replenish lagged to much\n");
+ printk_deferred_once("sched: DL replenish lagged too much\n");
dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
dl_se->runtime = pi_se->dl_runtime;
}
@@ -735,8 +738,11 @@ static void update_curr_dl(struct rq *rq)
* approach need further study.
*/
delta_exec = rq_clock_task(rq) - curr->se.exec_start;
- if (unlikely((s64)delta_exec <= 0))
+ if (unlikely((s64)delta_exec <= 0)) {
+ if (unlikely(dl_se->dl_yielded))
+ goto throttle;
return;
+ }
schedstat_set(curr->se.statistics.exec_max,
max(curr->se.statistics.exec_max, delta_exec));
@@ -749,8 +755,10 @@ static void update_curr_dl(struct rq *rq)
sched_rt_avg_update(rq, delta_exec);
- dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec;
- if (dl_runtime_exceeded(dl_se)) {
+ dl_se->runtime -= delta_exec;
+
+throttle:
+ if (dl_runtime_exceeded(dl_se) || dl_se->dl_yielded) {
dl_se->dl_throttled = 1;
__dequeue_task_dl(rq, curr, 0);
if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr)))
@@ -994,18 +1002,14 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
*/
static void yield_task_dl(struct rq *rq)
{
- struct task_struct *p = rq->curr;
-
/*
* We make the task go to sleep until its current deadline by
* forcing its runtime to zero. This way, update_curr_dl() stops
* it and the bandwidth timer will wake it up and will give it
* new scheduling parameters (thanks to dl_yielded=1).
*/
- if (p->dl.runtime > 0) {
- rq->curr->dl.dl_yielded = 1;
- p->dl.runtime = 0;
- }
+ rq->curr->dl.dl_yielded = 1;
+
update_rq_clock(rq);
update_curr_dl(rq);
/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7ce24a4..5641042 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8284,11 +8284,8 @@ void free_fair_sched_group(struct task_group *tg)
for_each_possible_cpu(i) {
if (tg->cfs_rq)
kfree(tg->cfs_rq[i]);
- if (tg->se) {
- if (tg->se[i])
- remove_entity_load_avg(tg->se[i]);
+ if (tg->se)
kfree(tg->se[i]);
- }
}
kfree(tg->cfs_rq);
@@ -8336,21 +8333,29 @@ err:
return 0;
}
-void unregister_fair_sched_group(struct task_group *tg, int cpu)
+void unregister_fair_sched_group(struct task_group *tg)
{
- struct rq *rq = cpu_rq(cpu);
unsigned long flags;
+ struct rq *rq;
+ int cpu;
- /*
- * Only empty task groups can be destroyed; so we can speculatively
- * check on_list without danger of it being re-added.
- */
- if (!tg->cfs_rq[cpu]->on_list)
- return;
+ for_each_possible_cpu(cpu) {
+ if (tg->se[cpu])
+ remove_entity_load_avg(tg->se[cpu]);
- raw_spin_lock_irqsave(&rq->lock, flags);
- list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
- raw_spin_unlock_irqrestore(&rq->lock, flags);
+ /*
+ * Only empty task groups can be destroyed; so we can speculatively
+ * check on_list without danger of it being re-added.
+ */
+ if (!tg->cfs_rq[cpu]->on_list)
+ continue;
+
+ rq = cpu_rq(cpu);
+
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+ }
}
void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
@@ -8432,7 +8437,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
return 1;
}
-void unregister_fair_sched_group(struct task_group *tg, int cpu) { }
+void unregister_fair_sched_group(struct task_group *tg) { }
#endif /* CONFIG_FAIR_GROUP_SCHED */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 1d58387..91f0a77 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -313,7 +313,7 @@ extern int tg_nop(struct task_group *tg, void *data);
extern void free_fair_sched_group(struct task_group *tg);
extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent);
-extern void unregister_fair_sched_group(struct task_group *tg, int cpu);
+extern void unregister_fair_sched_group(struct task_group *tg);
extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
struct sched_entity *se, int cpu,
struct sched_entity *parent);
diff --git a/kernel/signal.c b/kernel/signal.c
index f3f1f7a..0508544 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -3508,8 +3508,10 @@ static int sigsuspend(sigset_t *set)
current->saved_sigmask = current->blocked;
set_current_blocked(set);
- __set_current_state(TASK_INTERRUPTIBLE);
- schedule();
+ while (!signal_pending(current)) {
+ __set_current_state(TASK_INTERRUPTIBLE);
+ schedule();
+ }
set_restore_sigmask();
return -ERESTARTNOHAND;
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index eca592f..57a6eea 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4961,7 +4961,7 @@ void ftrace_release_mod(struct module *mod)
mutex_unlock(&ftrace_lock);
}
-static void ftrace_module_enable(struct module *mod)
+void ftrace_module_enable(struct module *mod)
{
struct dyn_ftrace *rec;
struct ftrace_page *pg;
@@ -5038,38 +5038,8 @@ void ftrace_module_init(struct module *mod)
ftrace_process_locs(mod, mod->ftrace_callsites,
mod->ftrace_callsites + mod->num_ftrace_callsites);
}
-
-static int ftrace_module_notify(struct notifier_block *self,
- unsigned long val, void *data)
-{
- struct module *mod = data;
-
- switch (val) {
- case MODULE_STATE_COMING:
- ftrace_module_enable(mod);
- break;
- case MODULE_STATE_GOING:
- ftrace_release_mod(mod);
- break;
- default:
- break;
- }
-
- return 0;
-}
-#else
-static int ftrace_module_notify(struct notifier_block *self,
- unsigned long val, void *data)
-{
- return 0;
-}
#endif /* CONFIG_MODULES */
-struct notifier_block ftrace_module_nb = {
- .notifier_call = ftrace_module_notify,
- .priority = INT_MIN, /* Run after anything that can remove kprobes */
-};
-
void __init ftrace_init(void)
{
extern unsigned long __start_mcount_loc[];
@@ -5098,10 +5068,6 @@ void __init ftrace_init(void)
__start_mcount_loc,
__stop_mcount_loc);
- ret = register_module_notifier(&ftrace_module_nb);
- if (ret)
- pr_warning("Failed to register trace ftrace module exit notifier\n");
-
set_ftrace_early_filters();
return;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f333e57..ab09829 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -869,7 +869,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
* The ftrace subsystem is for showing formats only.
* They can not be enabled or disabled via the event files.
*/
- if (call->class && call->class->reg)
+ if (call->class && call->class->reg &&
+ !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
return file;
}
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 202df6c..2a1abba 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -156,7 +156,11 @@ check_stack(unsigned long ip, unsigned long *stack)
for (; p < top && i < stack_trace_max.nr_entries; p++) {
if (stack_dump_trace[i] == ULONG_MAX)
break;
- if (*p == stack_dump_trace[i]) {
+ /*
+ * The READ_ONCE_NOCHECK is used to let KASAN know that
+ * this is not a stack-out-of-bounds error.
+ */
+ if ((READ_ONCE_NOCHECK(*p)) == stack_dump_trace[i]) {
stack_dump_trace[x] = stack_dump_trace[i++];
this_size = stack_trace_index[x++] =
(top - p) * sizeof(unsigned long);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 61a0264..7ff5dc7 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -301,7 +301,23 @@ static DEFINE_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */
static LIST_HEAD(workqueues); /* PR: list of all workqueues */
static bool workqueue_freezing; /* PL: have wqs started freezing? */
-static cpumask_var_t wq_unbound_cpumask; /* PL: low level cpumask for all unbound wqs */
+/* PL: allowable cpus for unbound wqs and work items */
+static cpumask_var_t wq_unbound_cpumask;
+
+/* CPU where unbound work was last round robin scheduled from this CPU */
+static DEFINE_PER_CPU(int, wq_rr_cpu_last);
+
+/*
+ * Local execution of unbound work items is no longer guaranteed. The
+ * following always forces round-robin CPU selection on unbound work items
+ * to uncover usages which depend on it.
+ */
+#ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU
+static bool wq_debug_force_rr_cpu = true;
+#else
+static bool wq_debug_force_rr_cpu = false;
+#endif
+module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644);
/* the per-cpu worker pools */
static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS],
@@ -570,6 +586,16 @@ static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq,
int node)
{
assert_rcu_or_wq_mutex_or_pool_mutex(wq);
+
+ /*
+ * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a
+ * delayed item is pending. The plan is to keep CPU -> NODE
+ * mapping valid and stable across CPU on/offlines. Once that
+ * happens, this workaround can be removed.
+ */
+ if (unlikely(node == NUMA_NO_NODE))
+ return wq->dfl_pwq;
+
return rcu_dereference_raw(wq->numa_pwq_tbl[node]);
}
@@ -1298,6 +1324,39 @@ static bool is_chained_work(struct workqueue_struct *wq)
return worker && worker->current_pwq->wq == wq;
}
+/*
+ * When queueing an unbound work item to a wq, prefer local CPU if allowed
+ * by wq_unbound_cpumask. Otherwise, round robin among the allowed ones to
+ * avoid perturbing sensitive tasks.
+ */
+static int wq_select_unbound_cpu(int cpu)
+{
+ static bool printed_dbg_warning;
+ int new_cpu;
+
+ if (likely(!wq_debug_force_rr_cpu)) {
+ if (cpumask_test_cpu(cpu, wq_unbound_cpumask))
+ return cpu;
+ } else if (!printed_dbg_warning) {
+ pr_warn("workqueue: round-robin CPU selection forced, expect performance impact\n");
+ printed_dbg_warning = true;
+ }
+
+ if (cpumask_empty(wq_unbound_cpumask))
+ return cpu;
+
+ new_cpu = __this_cpu_read(wq_rr_cpu_last);
+ new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask);
+ if (unlikely(new_cpu >= nr_cpu_ids)) {
+ new_cpu = cpumask_first_and(wq_unbound_cpumask, cpu_online_mask);
+ if (unlikely(new_cpu >= nr_cpu_ids))
+ return cpu;
+ }
+ __this_cpu_write(wq_rr_cpu_last, new_cpu);
+
+ return new_cpu;
+}
+
static void __queue_work(int cpu, struct workqueue_struct *wq,
struct work_struct *work)
{
@@ -1323,7 +1382,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
return;
retry:
if (req_cpu == WORK_CPU_UNBOUND)
- cpu = raw_smp_processor_id();
+ cpu = wq_select_unbound_cpu(raw_smp_processor_id());
/* pwq which will be used unless @work is executing elsewhere */
if (!(wq->flags & WQ_UNBOUND))
@@ -1464,13 +1523,13 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
timer_stats_timer_set_start_info(&dwork->timer);
dwork->wq = wq;
- /* timer isn't guaranteed to run in this cpu, record earlier */
- if (cpu == WORK_CPU_UNBOUND)
- cpu = raw_smp_processor_id();
dwork->cpu = cpu;
timer->expires = jiffies + delay;
- add_timer_on(timer, cpu);
+ if (unlikely(cpu != WORK_CPU_UNBOUND))
+ add_timer_on(timer, cpu);
+ else
+ add_timer(timer);
}
/**
@@ -2355,7 +2414,8 @@ static void check_flush_dependency(struct workqueue_struct *target_wq,
WARN_ONCE(current->flags & PF_MEMALLOC,
"workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%pf",
current->pid, current->comm, target_wq->name, target_func);
- WARN_ONCE(worker && (worker->current_pwq->wq->flags & WQ_MEM_RECLAIM),
+ WARN_ONCE(worker && ((worker->current_pwq->wq->flags &
+ (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM),
"workqueue: WQ_MEM_RECLAIM %s:%pf is flushing !WQ_MEM_RECLAIM %s:%pf",
worker->current_pwq->wq->name, worker->current_func,
target_wq->name, target_func);
OpenPOWER on IntegriCloud