summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit.c4
-rw-r--r--kernel/events/core.c147
-rw-r--r--kernel/hrtimer.c22
-rw-r--r--kernel/irq/irqdesc.c7
-rw-r--r--kernel/irq/manage.c17
-rw-r--r--kernel/module.c6
-rw-r--r--kernel/power/suspend.c3
-rw-r--r--kernel/softirq.c5
-rw-r--r--kernel/timer.c2
-rw-r--r--kernel/trace/ftrace.c27
-rw-r--r--kernel/trace/trace_events_trigger.c2
11 files changed, 135 insertions, 107 deletions
diff --git a/kernel/audit.c b/kernel/audit.c
index 7c2893602d06..47845c57eb19 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -643,13 +643,13 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
if ((task_active_pid_ns(current) != &init_pid_ns))
return -EPERM;
- if (!capable(CAP_AUDIT_CONTROL))
+ if (!netlink_capable(skb, CAP_AUDIT_CONTROL))
err = -EPERM;
break;
case AUDIT_USER:
case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG:
case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
- if (!capable(CAP_AUDIT_WRITE))
+ if (!netlink_capable(skb, CAP_AUDIT_WRITE))
err = -EPERM;
break;
default: /* bad msg */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5129b1201050..ed50b0943213 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1444,6 +1444,11 @@ group_sched_out(struct perf_event *group_event,
cpuctx->exclusive = 0;
}
+struct remove_event {
+ struct perf_event *event;
+ bool detach_group;
+};
+
/*
* Cross CPU call to remove a performance event
*
@@ -1452,12 +1457,15 @@ group_sched_out(struct perf_event *group_event,
*/
static int __perf_remove_from_context(void *info)
{
- struct perf_event *event = info;
+ struct remove_event *re = info;
+ struct perf_event *event = re->event;
struct perf_event_context *ctx = event->ctx;
struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
raw_spin_lock(&ctx->lock);
event_sched_out(event, cpuctx, ctx);
+ if (re->detach_group)
+ perf_group_detach(event);
list_del_event(event, ctx);
if (!ctx->nr_events && cpuctx->task_ctx == ctx) {
ctx->is_active = 0;
@@ -1482,10 +1490,14 @@ static int __perf_remove_from_context(void *info)
* When called from perf_event_exit_task, it's OK because the
* context has been detached from its task.
*/
-static void perf_remove_from_context(struct perf_event *event)
+static void perf_remove_from_context(struct perf_event *event, bool detach_group)
{
struct perf_event_context *ctx = event->ctx;
struct task_struct *task = ctx->task;
+ struct remove_event re = {
+ .event = event,
+ .detach_group = detach_group,
+ };
lockdep_assert_held(&ctx->mutex);
@@ -1494,12 +1506,12 @@ static void perf_remove_from_context(struct perf_event *event)
* Per cpu events are removed via an smp call and
* the removal is always successful.
*/
- cpu_function_call(event->cpu, __perf_remove_from_context, event);
+ cpu_function_call(event->cpu, __perf_remove_from_context, &re);
return;
}
retry:
- if (!task_function_call(task, __perf_remove_from_context, event))
+ if (!task_function_call(task, __perf_remove_from_context, &re))
return;
raw_spin_lock_irq(&ctx->lock);
@@ -1516,6 +1528,8 @@ retry:
* Since the task isn't running, its safe to remove the event, us
* holding the ctx->lock ensures the task won't get scheduled in.
*/
+ if (detach_group)
+ perf_group_detach(event);
list_del_event(event, ctx);
raw_spin_unlock_irq(&ctx->lock);
}
@@ -1664,6 +1678,8 @@ event_sched_in(struct perf_event *event,
u64 tstamp = perf_event_time(event);
int ret = 0;
+ lockdep_assert_held(&ctx->lock);
+
if (event->state <= PERF_EVENT_STATE_OFF)
return 0;
@@ -3235,7 +3251,8 @@ static void __free_event(struct perf_event *event)
call_rcu(&event->rcu_head, free_event_rcu);
}
-static void free_event(struct perf_event *event)
+
+static void _free_event(struct perf_event *event)
{
irq_work_sync(&event->pending);
@@ -3263,45 +3280,31 @@ static void free_event(struct perf_event *event)
if (is_cgroup_event(event))
perf_detach_cgroup(event);
-
__free_event(event);
}
-int perf_event_release_kernel(struct perf_event *event)
+/*
+ * Used to free events which have a known refcount of 1, such as in error paths
+ * where the event isn't exposed yet and inherited events.
+ */
+static void free_event(struct perf_event *event)
{
- struct perf_event_context *ctx = event->ctx;
-
- WARN_ON_ONCE(ctx->parent_ctx);
- /*
- * There are two ways this annotation is useful:
- *
- * 1) there is a lock recursion from perf_event_exit_task
- * see the comment there.
- *
- * 2) there is a lock-inversion with mmap_sem through
- * perf_event_read_group(), which takes faults while
- * holding ctx->mutex, however this is called after
- * the last filedesc died, so there is no possibility
- * to trigger the AB-BA case.
- */
- mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
- raw_spin_lock_irq(&ctx->lock);
- perf_group_detach(event);
- raw_spin_unlock_irq(&ctx->lock);
- perf_remove_from_context(event);
- mutex_unlock(&ctx->mutex);
-
- free_event(event);
+ if (WARN(atomic_long_cmpxchg(&event->refcount, 1, 0) != 1,
+ "unexpected event refcount: %ld; ptr=%p\n",
+ atomic_long_read(&event->refcount), event)) {
+ /* leak to avoid use-after-free */
+ return;
+ }
- return 0;
+ _free_event(event);
}
-EXPORT_SYMBOL_GPL(perf_event_release_kernel);
/*
* Called when the last reference to the file is gone.
*/
static void put_event(struct perf_event *event)
{
+ struct perf_event_context *ctx = event->ctx;
struct task_struct *owner;
if (!atomic_long_dec_and_test(&event->refcount))
@@ -3340,8 +3343,32 @@ static void put_event(struct perf_event *event)
put_task_struct(owner);
}
- perf_event_release_kernel(event);
+ WARN_ON_ONCE(ctx->parent_ctx);
+ /*
+ * There are two ways this annotation is useful:
+ *
+ * 1) there is a lock recursion from perf_event_exit_task
+ * see the comment there.
+ *
+ * 2) there is a lock-inversion with mmap_sem through
+ * perf_event_read_group(), which takes faults while
+ * holding ctx->mutex, however this is called after
+ * the last filedesc died, so there is no possibility
+ * to trigger the AB-BA case.
+ */
+ mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
+ perf_remove_from_context(event, true);
+ mutex_unlock(&ctx->mutex);
+
+ _free_event(event);
+}
+
+int perf_event_release_kernel(struct perf_event *event)
+{
+ put_event(event);
+ return 0;
}
+EXPORT_SYMBOL_GPL(perf_event_release_kernel);
static int perf_release(struct inode *inode, struct file *file)
{
@@ -7070,20 +7097,26 @@ SYSCALL_DEFINE5(perf_event_open,
}
}
+ if (task && group_leader &&
+ group_leader->attr.inherit != attr.inherit) {
+ err = -EINVAL;
+ goto err_task;
+ }
+
get_online_cpus();
event = perf_event_alloc(&attr, cpu, task, group_leader, NULL,
NULL, NULL);
if (IS_ERR(event)) {
err = PTR_ERR(event);
- goto err_task;
+ goto err_cpus;
}
if (flags & PERF_FLAG_PID_CGROUP) {
err = perf_cgroup_connect(pid, event, &attr, group_leader);
if (err) {
__free_event(event);
- goto err_task;
+ goto err_cpus;
}
}
@@ -7180,7 +7213,7 @@ SYSCALL_DEFINE5(perf_event_open,
struct perf_event_context *gctx = group_leader->ctx;
mutex_lock(&gctx->mutex);
- perf_remove_from_context(group_leader);
+ perf_remove_from_context(group_leader, false);
/*
* Removing from the context ends up with disabled
@@ -7190,7 +7223,7 @@ SYSCALL_DEFINE5(perf_event_open,
perf_event__state_init(group_leader);
list_for_each_entry(sibling, &group_leader->sibling_list,
group_entry) {
- perf_remove_from_context(sibling);
+ perf_remove_from_context(sibling, false);
perf_event__state_init(sibling);
put_ctx(gctx);
}
@@ -7245,8 +7278,9 @@ err_context:
put_ctx(ctx);
err_alloc:
free_event(event);
-err_task:
+err_cpus:
put_online_cpus();
+err_task:
if (task)
put_task_struct(task);
err_group_fd:
@@ -7320,7 +7354,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
mutex_lock(&src_ctx->mutex);
list_for_each_entry_safe(event, tmp, &src_ctx->event_list,
event_entry) {
- perf_remove_from_context(event);
+ perf_remove_from_context(event, false);
unaccount_event_cpu(event, src_cpu);
put_ctx(src_ctx);
list_add(&event->migrate_entry, &events);
@@ -7382,13 +7416,7 @@ __perf_event_exit_task(struct perf_event *child_event,
struct perf_event_context *child_ctx,
struct task_struct *child)
{
- if (child_event->parent) {
- raw_spin_lock_irq(&child_ctx->lock);
- perf_group_detach(child_event);
- raw_spin_unlock_irq(&child_ctx->lock);
- }
-
- perf_remove_from_context(child_event);
+ perf_remove_from_context(child_event, true);
/*
* It can happen that the parent exits first, and has events
@@ -7403,7 +7431,7 @@ __perf_event_exit_task(struct perf_event *child_event,
static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
{
- struct perf_event *child_event, *tmp;
+ struct perf_event *child_event;
struct perf_event_context *child_ctx;
unsigned long flags;
@@ -7457,24 +7485,9 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
*/
mutex_lock(&child_ctx->mutex);
-again:
- list_for_each_entry_safe(child_event, tmp, &child_ctx->pinned_groups,
- group_entry)
+ list_for_each_entry_rcu(child_event, &child_ctx->event_list, event_entry)
__perf_event_exit_task(child_event, child_ctx, child);
- list_for_each_entry_safe(child_event, tmp, &child_ctx->flexible_groups,
- group_entry)
- __perf_event_exit_task(child_event, child_ctx, child);
-
- /*
- * If the last event was a group event, it will have appended all
- * its siblings to the list, but we obtained 'tmp' before that which
- * will still point to the list head terminating the iteration.
- */
- if (!list_empty(&child_ctx->pinned_groups) ||
- !list_empty(&child_ctx->flexible_groups))
- goto again;
-
mutex_unlock(&child_ctx->mutex);
put_ctx(child_ctx);
@@ -7739,6 +7752,8 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
* swapped under us.
*/
parent_ctx = perf_pin_task_context(parent, ctxn);
+ if (!parent_ctx)
+ return 0;
/*
* No need to check if parent_ctx != NULL here; since we saw
@@ -7872,14 +7887,14 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
static void __perf_event_exit_context(void *__info)
{
+ struct remove_event re = { .detach_group = false };
struct perf_event_context *ctx = __info;
- struct perf_event *event;
perf_pmu_rotate_stop(ctx->pmu);
rcu_read_lock();
- list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
- __perf_remove_from_context(event);
+ list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry)
+ __perf_remove_from_context(&re);
rcu_read_unlock();
}
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 53d26829cd4d..d10eba8089d1 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -234,6 +234,11 @@ again:
goto again;
}
timer->base = new_base;
+ } else {
+ if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
+ cpu = this_cpu;
+ goto again;
+ }
}
return new_base;
}
@@ -569,6 +574,23 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
cpu_base->expires_next.tv64 = expires_next.tv64;
+ /*
+ * If a hang was detected in the last timer interrupt then we
+ * leave the hang delay active in the hardware. We want the
+ * system to make progress. That also prevents the following
+ * scenario:
+ * T1 expires 50ms from now
+ * T2 expires 5s from now
+ *
+ * T1 is removed, so this code is called and would reprogram
+ * the hardware to 5s from now. Any hrtimer_start after that
+ * will not reprogram the hardware due to hang_detected being
+ * set. So we'd effectivly block all timers until the T2 event
+ * fires.
+ */
+ if (cpu_base->hang_detected)
+ return;
+
if (cpu_base->expires_next.tv64 != KTIME_MAX)
tick_program_event(cpu_base->expires_next, 1);
}
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index a7174617616b..bb07f2928f4b 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -363,6 +363,13 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
if (from > irq)
return -EINVAL;
from = irq;
+ } else {
+ /*
+ * For interrupts which are freely allocated the
+ * architecture can force a lower bound to the @from
+ * argument. x86 uses this to exclude the GSI space.
+ */
+ from = arch_dynirq_lower_bound(from);
}
mutex_lock(&sparse_irq_lock);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 2486a4c1a710..d34131ca372b 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -180,7 +180,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
struct irq_chip *chip = irq_data_get_irq_chip(data);
int ret;
- ret = chip->irq_set_affinity(data, mask, false);
+ ret = chip->irq_set_affinity(data, mask, force);
switch (ret) {
case IRQ_SET_MASK_OK:
cpumask_copy(data->affinity, mask);
@@ -192,7 +192,8 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
return ret;
}
-int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
+int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
+ bool force)
{
struct irq_chip *chip = irq_data_get_irq_chip(data);
struct irq_desc *desc = irq_data_to_desc(data);
@@ -202,7 +203,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
return -EINVAL;
if (irq_can_move_pcntxt(data)) {
- ret = irq_do_set_affinity(data, mask, false);
+ ret = irq_do_set_affinity(data, mask, force);
} else {
irqd_set_move_pending(data);
irq_copy_pending(desc, mask);
@@ -217,13 +218,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
return ret;
}
-/**
- * irq_set_affinity - Set the irq affinity of a given irq
- * @irq: Interrupt to set affinity
- * @mask: cpumask
- *
- */
-int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
+int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force)
{
struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
@@ -233,7 +228,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
return -EINVAL;
raw_spin_lock_irqsave(&desc->lock, flags);
- ret = __irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask);
+ ret = irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force);
raw_spin_unlock_irqrestore(&desc->lock, flags);
return ret;
}
diff --git a/kernel/module.c b/kernel/module.c
index 11869408f79b..079c4615607d 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -815,9 +815,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
return -EFAULT;
name[MODULE_NAME_LEN-1] = '\0';
- if (!(flags & O_NONBLOCK))
- pr_warn("waiting module removal not supported: please upgrade\n");
-
if (mutex_lock_interruptible(&module_mutex) != 0)
return -EINTR;
@@ -3271,6 +3268,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
dynamic_debug_setup(info->debug, info->num_debug);
+ /* Ftrace init must be called in the MODULE_STATE_UNFORMED state */
+ ftrace_module_init(mod);
+
/* Finally it's fully formed, ready to start executing. */
err = complete_formation(mod, info);
if (err)
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index c3ad9cafe930..8233cd4047d7 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -14,6 +14,7 @@
#include <linux/init.h>
#include <linux/console.h>
#include <linux/cpu.h>
+#include <linux/cpuidle.h>
#include <linux/syscalls.h>
#include <linux/gfp.h>
#include <linux/io.h>
@@ -53,7 +54,9 @@ static void freeze_begin(void)
static void freeze_enter(void)
{
+ cpuidle_resume();
wait_event(suspend_freeze_wait_head, suspend_freeze_wake);
+ cpuidle_pause();
}
void freeze_wake(void)
diff --git a/kernel/softirq.c b/kernel/softirq.c
index b50990a5bea0..33e4648ae0e7 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -779,3 +779,8 @@ int __init __weak arch_early_irq_init(void)
{
return 0;
}
+
+unsigned int __weak arch_dynirq_lower_bound(unsigned int from)
+{
+ return from;
+}
diff --git a/kernel/timer.c b/kernel/timer.c
index 87bd529879c2..3bb01a323b2a 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -838,7 +838,7 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
bit = find_last_bit(&mask, BITS_PER_LONG);
- mask = (1 << bit) - 1;
+ mask = (1UL << bit) - 1;
expires_limit = expires_limit & ~(mask);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1fd4b9479210..4a54a25afa2f 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4330,16 +4330,11 @@ static void ftrace_init_module(struct module *mod,
ftrace_process_locs(mod, start, end);
}
-static int ftrace_module_notify_enter(struct notifier_block *self,
- unsigned long val, void *data)
+void ftrace_module_init(struct module *mod)
{
- struct module *mod = data;
-
- if (val == MODULE_STATE_COMING)
- ftrace_init_module(mod, mod->ftrace_callsites,
- mod->ftrace_callsites +
- mod->num_ftrace_callsites);
- return 0;
+ ftrace_init_module(mod, mod->ftrace_callsites,
+ mod->ftrace_callsites +
+ mod->num_ftrace_callsites);
}
static int ftrace_module_notify_exit(struct notifier_block *self,
@@ -4353,11 +4348,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self,
return 0;
}
#else
-static int ftrace_module_notify_enter(struct notifier_block *self,
- unsigned long val, void *data)
-{
- return 0;
-}
static int ftrace_module_notify_exit(struct notifier_block *self,
unsigned long val, void *data)
{
@@ -4365,11 +4355,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self,
}
#endif /* CONFIG_MODULES */
-struct notifier_block ftrace_module_enter_nb = {
- .notifier_call = ftrace_module_notify_enter,
- .priority = INT_MAX, /* Run before anything that can use kprobes */
-};
-
struct notifier_block ftrace_module_exit_nb = {
.notifier_call = ftrace_module_notify_exit,
.priority = INT_MIN, /* Run after anything that can remove kprobes */
@@ -4403,10 +4388,6 @@ void __init ftrace_init(void)
__start_mcount_loc,
__stop_mcount_loc);
- ret = register_module_notifier(&ftrace_module_enter_nb);
- if (ret)
- pr_warning("Failed to register trace ftrace module enter notifier\n");
-
ret = register_module_notifier(&ftrace_module_exit_nb);
if (ret)
pr_warning("Failed to register trace ftrace module exit notifier\n");
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 925f537f07d1..4747b476a030 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -77,7 +77,7 @@ event_triggers_call(struct ftrace_event_file *file, void *rec)
data->ops->func(data);
continue;
}
- filter = rcu_dereference(data->filter);
+ filter = rcu_dereference_sched(data->filter);
if (filter && !filter_match_preds(filter, rec))
continue;
if (data->cmd_ops->post_trigger) {
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-07 19:30:02 +0100