summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/syscall.c35
-rw-r--r--kernel/bpf/verifier.c3
-rw-r--r--kernel/kprobes.c18
-rw-r--r--kernel/power/suspend.c6
-rw-r--r--kernel/time/tick-sched.c18
-rw-r--r--kernel/time/tick-sched.h2
-rw-r--r--kernel/time/timer.c22
-rw-r--r--kernel/time/timer_migration.c32
-rw-r--r--kernel/trace/Kconfig2
-rw-r--r--kernel/trace/bpf_trace.c10
-rw-r--r--kernel/trace/ring_buffer.c6
-rw-r--r--kernel/trace/trace_events.c4
12 files changed, 124 insertions, 34 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ae2ff73bde7e..c287925471f6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3024,17 +3024,46 @@ void bpf_link_inc(struct bpf_link *link)
atomic64_inc(&link->refcnt);
}
+static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu)
+{
+ struct bpf_link *link = container_of(rcu, struct bpf_link, rcu);
+
+ /* free bpf_link and its containing memory */
+ link->ops->dealloc_deferred(link);
+}
+
+static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu)
+{
+ if (rcu_trace_implies_rcu_gp())
+ bpf_link_defer_dealloc_rcu_gp(rcu);
+ else
+ call_rcu(rcu, bpf_link_defer_dealloc_rcu_gp);
+}
+
/* bpf_link_free is guaranteed to be called from process context */
static void bpf_link_free(struct bpf_link *link)
{
+ bool sleepable = false;
+
bpf_link_free_id(link->id);
if (link->prog) {
+ sleepable = link->prog->sleepable;
/* detach BPF program, clean up used resources */
link->ops->release(link);
bpf_prog_put(link->prog);
}
- /* free bpf_link and its containing memory */
- link->ops->dealloc(link);
+ if (link->ops->dealloc_deferred) {
+ /* schedule BPF link deallocation; if underlying BPF program
+ * is sleepable, we need to first wait for RCU tasks trace
+ * sync, then go through "classic" RCU grace period
+ */
+ if (sleepable)
+ call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp);
+ else
+ call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp);
+ }
+ if (link->ops->dealloc)
+ link->ops->dealloc(link);
}
static void bpf_link_put_deferred(struct work_struct *work)
@@ -3544,7 +3573,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
static const struct bpf_link_ops bpf_raw_tp_link_lops = {
.release = bpf_raw_tp_link_release,
- .dealloc = bpf_raw_tp_link_dealloc,
+ .dealloc_deferred = bpf_raw_tp_link_dealloc,
.show_fdinfo = bpf_raw_tp_link_show_fdinfo,
.fill_link_info = bpf_raw_tp_link_fill_link_info,
};
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 353985b2b6a2..98188379d5c7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -18379,15 +18379,18 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
}
if (!env->prog->jit_requested) {
verbose(env, "JIT is required to use arena\n");
+ fdput(f);
return -EOPNOTSUPP;
}
if (!bpf_jit_supports_arena()) {
verbose(env, "JIT doesn't support arena\n");
+ fdput(f);
return -EOPNOTSUPP;
}
env->prog->aux->arena = (void *)map;
if (!bpf_arena_get_user_vm_start(env->prog->aux->arena)) {
verbose(env, "arena's user address must be set via map_extra or mmap()\n");
+ fdput(f);
return -EINVAL;
}
}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 9d9095e81792..65adc815fc6e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1567,10 +1567,17 @@ static int check_kprobe_address_safe(struct kprobe *p,
jump_label_lock();
preempt_disable();
- /* Ensure it is not in reserved area nor out of text */
- if (!(core_kernel_text((unsigned long) p->addr) ||
- is_module_text_address((unsigned long) p->addr)) ||
- in_gate_area_no_mm((unsigned long) p->addr) ||
+ /* Ensure the address is in a text area, and find a module if exists. */
+ *probed_mod = NULL;
+ if (!core_kernel_text((unsigned long) p->addr)) {
+ *probed_mod = __module_text_address((unsigned long) p->addr);
+ if (!(*probed_mod)) {
+ ret = -EINVAL;
+ goto out;
+ }
+ }
+ /* Ensure it is not in reserved area. */
+ if (in_gate_area_no_mm((unsigned long) p->addr) ||
within_kprobe_blacklist((unsigned long) p->addr) ||
jump_label_text_reserved(p->addr, p->addr) ||
static_call_text_reserved(p->addr, p->addr) ||
@@ -1580,8 +1587,7 @@ static int check_kprobe_address_safe(struct kprobe *p,
goto out;
}
- /* Check if 'p' is probing a module. */
- *probed_mod = __module_text_address((unsigned long) p->addr);
+ /* Get module refcount and reject __init functions for loaded modules. */
if (*probed_mod) {
/*
* We must hold a refcount of the probed module while updating
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index e3ae93bbcb9b..09f8397bae15 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -106,6 +106,12 @@ static void s2idle_enter(void)
swait_event_exclusive(s2idle_wait_head,
s2idle_state == S2IDLE_STATE_WAKE);
+ /*
+ * Kick all CPUs to ensure that they resume their timers and restore
+ * consistent system state.
+ */
+ wake_up_all_idle_cpus();
+
cpus_read_unlock();
raw_spin_lock_irq(&s2idle_lock);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 269e21590df5..1331216a9cae 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -697,6 +697,7 @@ bool tick_nohz_tick_stopped_cpu(int cpu)
/**
* tick_nohz_update_jiffies - update jiffies when idle was interrupted
+ * @now: current ktime_t
*
* Called from interrupt entry when the CPU was idle
*
@@ -794,7 +795,7 @@ static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime,
* This time is measured via accounting rather than sampling,
* and is as accurate as ktime_get() is.
*
- * This function returns -1 if NOHZ is not enabled.
+ * Return: -1 if NOHZ is not enabled, else total idle time of the @cpu
*/
u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
{
@@ -820,7 +821,7 @@ EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
* This time is measured via accounting rather than sampling,
* and is as accurate as ktime_get() is.
*
- * This function returns -1 if NOHZ is not enabled.
+ * Return: -1 if NOHZ is not enabled, else total iowait time of @cpu
*/
u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
{
@@ -1287,6 +1288,8 @@ void tick_nohz_irq_exit(void)
/**
* tick_nohz_idle_got_tick - Check whether or not the tick handler has run
+ *
+ * Return: %true if the tick handler has run, otherwise %false
*/
bool tick_nohz_idle_got_tick(void)
{
@@ -1305,6 +1308,8 @@ bool tick_nohz_idle_got_tick(void)
* stopped, it returns the next hrtimer.
*
* Called from power state control code with interrupts disabled
+ *
+ * Return: the next expiration time
*/
ktime_t tick_nohz_get_next_hrtimer(void)
{
@@ -1320,6 +1325,8 @@ ktime_t tick_nohz_get_next_hrtimer(void)
* The return value of this function and/or the value returned by it through the
* @delta_next pointer can be negative which must be taken into account by its
* callers.
+ *
+ * Return: the expected length of the current sleep
*/
ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
{
@@ -1357,8 +1364,11 @@ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
/**
* tick_nohz_get_idle_calls_cpu - return the current idle calls counter value
* for a particular CPU.
+ * @cpu: target CPU number
*
* Called from the schedutil frequency scaling governor in scheduler context.
+ *
+ * Return: the current idle calls counter value for @cpu
*/
unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
{
@@ -1371,6 +1381,8 @@ unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
* tick_nohz_get_idle_calls - return the current idle calls counter value
*
* Called from the schedutil frequency scaling governor in scheduler context.
+ *
+ * Return: the current idle calls counter value for the current CPU
*/
unsigned long tick_nohz_get_idle_calls(void)
{
@@ -1559,7 +1571,7 @@ early_param("skew_tick", skew_tick);
/**
* tick_setup_sched_timer - setup the tick emulation timer
- * @mode: tick_nohz_mode to setup for
+ * @hrtimer: whether to use the hrtimer or not
*/
void tick_setup_sched_timer(bool hrtimer)
{
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index e11c4dc65bcb..b4a7822f495d 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -46,8 +46,8 @@ struct tick_device {
* @next_tick: Next tick to be fired when in dynticks mode.
* @idle_jiffies: jiffies at the entry to idle for idle time accounting
* @idle_waketime: Time when the idle was interrupted
+ * @idle_sleeptime_seq: sequence counter for data consistency
* @idle_entrytime: Time when the idle call was entered
- * @nohz_mode: Mode - one state of tick_nohz_mode
* @last_jiffies: Base jiffies snapshot when next event was last computed
* @timer_expires_base: Base time clock monotonic for @timer_expires
* @timer_expires: Anticipated timer expiration time (in case sched tick is stopped)
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index dee29f1f5b75..3baf2fbe6848 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -64,15 +64,15 @@ EXPORT_SYMBOL(jiffies_64);
/*
* The timer wheel has LVL_DEPTH array levels. Each level provides an array of
- * LVL_SIZE buckets. Each level is driven by its own clock and therefor each
+ * LVL_SIZE buckets. Each level is driven by its own clock and therefore each
* level has a different granularity.
*
- * The level granularity is: LVL_CLK_DIV ^ lvl
+ * The level granularity is: LVL_CLK_DIV ^ level
* The level clock frequency is: HZ / (LVL_CLK_DIV ^ level)
*
* The array level of a newly armed timer depends on the relative expiry
* time. The farther the expiry time is away the higher the array level and
- * therefor the granularity becomes.
+ * therefore the granularity becomes.
*
* Contrary to the original timer wheel implementation, which aims for 'exact'
* expiry of the timers, this implementation removes the need for recascading
@@ -207,7 +207,7 @@ EXPORT_SYMBOL(jiffies_64);
* struct timer_base - Per CPU timer base (number of base depends on config)
* @lock: Lock protecting the timer_base
* @running_timer: When expiring timers, the lock is dropped. To make
- * sure not to race agains deleting/modifying a
+ * sure not to race against deleting/modifying a
* currently running timer, the pointer is set to the
* timer, which expires at the moment. If no timer is
* running, the pointer is NULL.
@@ -737,7 +737,7 @@ static bool timer_is_static_object(void *addr)
}
/*
- * fixup_init is called when:
+ * timer_fixup_init is called when:
* - an active object is initialized
*/
static bool timer_fixup_init(void *addr, enum debug_obj_state state)
@@ -761,7 +761,7 @@ static void stub_timer(struct timer_list *unused)
}
/*
- * fixup_activate is called when:
+ * timer_fixup_activate is called when:
* - an active object is activated
* - an unknown non-static object is activated
*/
@@ -783,7 +783,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state)
}
/*
- * fixup_free is called when:
+ * timer_fixup_free is called when:
* - an active object is freed
*/
static bool timer_fixup_free(void *addr, enum debug_obj_state state)
@@ -801,7 +801,7 @@ static bool timer_fixup_free(void *addr, enum debug_obj_state state)
}
/*
- * fixup_assert_init is called when:
+ * timer_fixup_assert_init is called when:
* - an untracked/uninit-ed object is found
*/
static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state)
@@ -914,7 +914,7 @@ static void do_init_timer(struct timer_list *timer,
* @key: lockdep class key of the fake lock used for tracking timer
* sync lock dependencies
*
- * init_timer_key() must be done to a timer prior calling *any* of the
+ * init_timer_key() must be done to a timer prior to calling *any* of the
* other timer functions.
*/
void init_timer_key(struct timer_list *timer,
@@ -1417,7 +1417,7 @@ static int __timer_delete(struct timer_list *timer, bool shutdown)
* If @shutdown is set then the lock has to be taken whether the
* timer is pending or not to protect against a concurrent rearm
* which might hit between the lockless pending check and the lock
- * aquisition. By taking the lock it is ensured that such a newly
+ * acquisition. By taking the lock it is ensured that such a newly
* enqueued timer is dequeued and cannot end up with
* timer->function == NULL in the expiry code.
*
@@ -2306,7 +2306,7 @@ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem,
/*
* When timer base is not set idle, undo the effect of
- * tmigr_cpu_deactivate() to prevent inconsitent states - active
+ * tmigr_cpu_deactivate() to prevent inconsistent states - active
* timer base but inactive timer migration hierarchy.
*
* When timer base was already marked idle, nothing will be
diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c
index c63a0afdcebe..ccba875d2234 100644
--- a/kernel/time/timer_migration.c
+++ b/kernel/time/timer_migration.c
@@ -751,6 +751,33 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
first_childevt = evt = data->evt;
+ /*
+ * Walking the hierarchy is required in any case when a
+ * remote expiry was done before. This ensures to not lose
+ * already queued events in non active groups (see section
+ * "Required event and timerqueue update after a remote
+ * expiry" in the documentation at the top).
+ *
+ * The two call sites which are executed without a remote expiry
+ * before, are not prevented from propagating changes through
+ * the hierarchy by the return:
+ * - When entering this path by tmigr_new_timer(), @evt->ignore
+ * is never set.
+ * - tmigr_inactive_up() takes care of the propagation by
+ * itself and ignores the return value. But an immediate
+ * return is possible if there is a parent, sparing group
+ * locking at this level, because the upper walking call to
+ * the parent will take care about removing this event from
+ * within the group and update next_expiry accordingly.
+ *
+ * However if there is no parent, ie: the hierarchy has only a
+ * single level so @group is the top level group, make sure the
+ * first event information of the group is updated properly and
+ * also handled properly, so skip this fast return path.
+ */
+ if (evt->ignore && !remote && group->parent)
+ return true;
+
raw_spin_lock(&group->lock);
childstate.state = 0;
@@ -762,8 +789,11 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
* queue when the expiry time changed only or when it could be ignored.
*/
if (timerqueue_node_queued(&evt->nextevt)) {
- if ((evt->nextevt.expires == nextexp) && !evt->ignore)
+ if ((evt->nextevt.expires == nextexp) && !evt->ignore) {
+ /* Make sure not to miss a new CPU event with the same expiry */
+ evt->cpu = first_childevt->cpu;
goto check_toplvl;
+ }
if (!timerqueue_del(&group->events, &evt->nextevt))
WRITE_ONCE(group->next_expiry, KTIME_MAX);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 61c541c36596..47345bf1d4a9 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -965,7 +965,7 @@ config FTRACE_RECORD_RECURSION
config FTRACE_RECORD_RECURSION_SIZE
int "Max number of recursed functions to record"
- default 128
+ default 128
depends on FTRACE_RECORD_RECURSION
help
This defines the limit of number of functions that can be
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 0a5c4efc73c3..9dc605f08a23 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2728,7 +2728,7 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link,
static const struct bpf_link_ops bpf_kprobe_multi_link_lops = {
.release = bpf_kprobe_multi_link_release,
- .dealloc = bpf_kprobe_multi_link_dealloc,
+ .dealloc_deferred = bpf_kprobe_multi_link_dealloc,
.fill_link_info = bpf_kprobe_multi_link_fill_link_info,
};
@@ -3157,6 +3157,9 @@ static void bpf_uprobe_multi_link_release(struct bpf_link *link)
umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt);
+ if (umulti_link->task)
+ put_task_struct(umulti_link->task);
+ path_put(&umulti_link->path);
}
static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
@@ -3164,9 +3167,6 @@ static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
struct bpf_uprobe_multi_link *umulti_link;
umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
- if (umulti_link->task)
- put_task_struct(umulti_link->task);
- path_put(&umulti_link->path);
kvfree(umulti_link->uprobes);
kfree(umulti_link);
}
@@ -3242,7 +3242,7 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link,
static const struct bpf_link_ops bpf_uprobe_multi_link_lops = {
.release = bpf_uprobe_multi_link_release,
- .dealloc = bpf_uprobe_multi_link_dealloc,
+ .dealloc_deferred = bpf_uprobe_multi_link_dealloc,
.fill_link_info = bpf_uprobe_multi_link_fill_link_info,
};
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 25476ead681b..6511dc3a00da 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1393,7 +1393,6 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write);
old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries);
- local_inc(&cpu_buffer->pages_touched);
/*
* Just make sure we have seen our old_write and synchronize
* with any interrupts that come in.
@@ -1430,8 +1429,9 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
*/
local_set(&next_page->page->commit, 0);
- /* Again, either we update tail_page or an interrupt does */
- (void)cmpxchg(&cpu_buffer->tail_page, tail_page, next_page);
+ /* Either we update tail_page or an interrupt does */
+ if (try_cmpxchg(&cpu_buffer->tail_page, &tail_page, next_page))
+ local_inc(&cpu_buffer->pages_touched);
}
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 7c364b87352e..52f75c36bbca 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1670,6 +1670,7 @@ static int trace_format_open(struct inode *inode, struct file *file)
return 0;
}
+#ifdef CONFIG_PERF_EVENTS
static ssize_t
event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
{
@@ -1684,6 +1685,7 @@ event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
return simple_read_from_buffer(ubuf, cnt, ppos, buf, len);
}
+#endif
static ssize_t
event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
@@ -2152,10 +2154,12 @@ static const struct file_operations ftrace_event_format_fops = {
.release = seq_release,
};
+#ifdef CONFIG_PERF_EVENTS
static const struct file_operations ftrace_event_id_fops = {
.read = event_id_read,
.llseek = default_llseek,
};
+#endif
static const struct file_operations ftrace_event_filter_fops = {
.open = tracing_open_file_tr,
generated by cgit (git 2.34.1) at 2024-05-19 00:09:39 +0000