summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/helpers.c2
-rw-r--r--kernel/cgroup.c20
-rw-r--r--kernel/events/core.c20
-rw-r--r--kernel/power/hibernate.c1
-rw-r--r--kernel/sched/core.c1
-rw-r--r--kernel/sched/cputime.c14
-rw-r--r--kernel/sched/sched.h13
-rw-r--r--kernel/sysctl_binary.c2
-rw-r--r--kernel/trace/trace.c5
-rw-r--r--kernel/trace/trace_irqsoff.c8
-rw-r--r--kernel/trace/trace_printk.c3
-rw-r--r--kernel/watchdog.c9
12 files changed, 75 insertions, 23 deletions
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 4504ca66118d..50da680c479f 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -166,7 +166,7 @@ static u64 bpf_get_current_comm(u64 r1, u64 size, u64 r3, u64 r4, u64 r5)
if (!task)
return -EINVAL;
- memcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm)));
+ strlcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm)));
return 0;
}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index d5512e1e7138..e8d71110ed2a 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2498,6 +2498,14 @@ static void cgroup_migrate_add_src(struct css_set *src_cset,
lockdep_assert_held(&cgroup_mutex);
lockdep_assert_held(&css_set_lock);
+ /*
+ * If ->dead, @src_set is associated with one or more dead cgroups
+ * and doesn't contain any migratable tasks. Ignore it early so
+ * that the rest of migration path doesn't get confused by it.
+ */
+ if (src_cset->dead)
+ return;
+
src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
if (!list_empty(&src_cset->mg_preload_node))
@@ -5186,6 +5194,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
{
struct cgroup_subsys_state *css;
+ struct cgrp_cset_link *link;
int ssid;
lockdep_assert_held(&cgroup_mutex);
@@ -5206,11 +5215,18 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
return -EBUSY;
/*
- * Mark @cgrp dead. This prevents further task migration and child
- * creation by disabling cgroup_lock_live_group().
+ * Mark @cgrp and the associated csets dead. The former prevents
+ * further task migration and child creation by disabling
+ * cgroup_lock_live_group(). The latter makes the csets ignored by
+ * the migration path.
*/
cgrp->self.flags &= ~CSS_ONLINE;
+ spin_lock_bh(&css_set_lock);
+ list_for_each_entry(link, &cgrp->cset_links, cset_link)
+ link->cset->dead = true;
+ spin_unlock_bh(&css_set_lock);
+
/* initiate massacre of all css's */
for_each_css(css, ssid, cgrp)
kill_css(css);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1cb22d44ccbb..96100cc046c5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1584,14 +1584,14 @@ 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--;
@@ -8032,6 +8032,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
}
}
+ /* symmetric to unaccount_event() in _free_event() */
+ account_event(event);
+
return event;
err_per_task:
@@ -8398,8 +8401,6 @@ SYSCALL_DEFINE5(perf_event_open,
}
}
- account_event(event);
-
/*
* Special case software events and allow them to be part of
* any hardware group.
@@ -8638,7 +8639,12 @@ 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:
@@ -8682,8 +8688,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
/* Mark owner so we could distinguish it from user events. */
event->owner = EVENT_OWNER_KERNEL;
- account_event(event);
-
ctx = find_get_context(event->pmu, task, event);
if (IS_ERR(ctx)) {
err = PTR_ERR(ctx);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index b7342a24f559..b7dd5718836e 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -339,6 +339,7 @@ int hibernation_snapshot(int platform_mode)
pm_message_t msg;
int error;
+ pm_suspend_clear_flags();
error = platform_begin(platform_mode);
if (error)
goto Close;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f640c0e3c7ea..58303b3dc356 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8986,6 +8986,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
set_window_start(rq);
raw_spin_unlock_irqrestore(&rq->lock, flags);
rq->calc_load_update = calc_load_update;
+ account_reset_rq(rq);
break;
case CPU_ONLINE:
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 647f184f8aec..f29b132a9f8b 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -270,21 +270,21 @@ static __always_inline bool steal_account_process_tick(void)
#ifdef CONFIG_PARAVIRT
if (static_key_false(&paravirt_steal_enabled)) {
u64 steal;
- cputime_t steal_ct;
+ unsigned long steal_jiffies;
steal = paravirt_steal_clock(smp_processor_id());
steal -= this_rq()->prev_steal_time;
/*
- * cputime_t may be less precise than nsecs (eg: if it's
- * based on jiffies). Lets cast the result to cputime
+ * steal is in nsecs but our caller is expecting steal
+ * time in jiffies. Lets cast the result to jiffies
* granularity and account the rest on the next rounds.
*/
- steal_ct = nsecs_to_cputime(steal);
- this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct);
+ steal_jiffies = nsecs_to_jiffies(steal);
+ this_rq()->prev_steal_time += jiffies_to_nsecs(steal_jiffies);
- account_steal_time(steal_ct);
- return steal_ct;
+ account_steal_time(jiffies_to_cputime(steal_jiffies));
+ return steal_jiffies;
}
#endif
return false;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 45b76cfff1ec..b9566cf3ad37 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2363,3 +2363,16 @@ static inline u64 irq_time_read(int cpu)
}
#endif /* CONFIG_64BIT */
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+static inline void account_reset_rq(struct rq *rq)
+{
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+ rq->prev_irq_time = 0;
+#endif
+#ifdef CONFIG_PARAVIRT
+ rq->prev_steal_time = 0;
+#endif
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+ rq->prev_steal_time_rq = 0;
+#endif
+}
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index b65c78c15ab3..4a816bab38a2 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -1324,7 +1324,7 @@ static ssize_t binary_sysctl(const int *name, int nlen,
}
mnt = task_active_pid_ns(current)->proc_mnt;
- file = file_open_root(mnt->mnt_root, mnt, pathname, flags);
+ file = file_open_root(mnt->mnt_root, mnt, pathname, flags, 0);
result = PTR_ERR(file);
if (IS_ERR(file))
goto out_putname;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 530bbc44082c..ae68222c5a74 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5044,7 +5044,10 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
spd.nr_pages = i;
- ret = splice_to_pipe(pipe, &spd);
+ if (i)
+ ret = splice_to_pipe(pipe, &spd);
+ else
+ ret = 0;
out:
splice_shrink_spd(&spd);
return ret;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index e4e56589ec1d..be3222b7d72e 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -109,8 +109,12 @@ static int func_prolog_dec(struct trace_array *tr,
return 0;
local_save_flags(*flags);
- /* slight chance to get a false positive on tracing_cpu */
- if (!irqs_disabled_flags(*flags))
+ /*
+ * Slight chance to get a false positive on tracing_cpu,
+ * although I'm starting to think there isn't a chance.
+ * Leave this for now just to be paranoid.
+ */
+ if (!irqs_disabled_flags(*flags) && !preempt_count())
return 0;
*data = per_cpu_ptr(tr->trace_buffer.data, cpu);
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 060df67dbdd1..f96f0383f6c6 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -296,6 +296,9 @@ static int t_show(struct seq_file *m, void *v)
const char *str = *fmt;
int i;
+ if (!*fmt)
+ return 0;
+
seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt);
/*
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index b40f7f35413d..9472691c1eb0 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -1038,6 +1038,9 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write,
* both lockup detectors are disabled if proc_watchdog_update()
* returns an error.
*/
+ if (old == new)
+ goto out;
+
err = proc_watchdog_update();
}
out:
@@ -1082,7 +1085,7 @@ int proc_soft_watchdog(struct ctl_table *table, int write,
int proc_watchdog_thresh(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- int err, old;
+ int err, old, new;
get_online_cpus();
mutex_lock(&watchdog_proc_mutex);
@@ -1102,6 +1105,10 @@ int proc_watchdog_thresh(struct ctl_table *table, int write,
/*
* Update the sample period. Restore on failure.
*/
+ new = ACCESS_ONCE(watchdog_thresh);
+ if (old == new)
+ goto out;
+
set_sample_period();
err = proc_watchdog_update();
if (err) {
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-08 08:56:25 +0000