summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/cgroup.c33
-rw-r--r--kernel/bpf/core.c29
-rw-r--r--kernel/bpf/hashtab.c2
-rw-r--r--kernel/bpf/syscall.c7
-rw-r--r--kernel/bpf/verifier.c4
-rw-r--r--kernel/cgroup/cgroup.c2
-rw-r--r--kernel/cgroup/cpuset.c6
-rw-r--r--kernel/events/core.c83
-rw-r--r--kernel/events/hw_breakpoint.c5
-rw-r--r--kernel/events/ring_buffer.c1
-rw-r--r--kernel/fork.c9
-rw-r--r--kernel/padata.c3
-rw-r--r--kernel/power/hibernate.c5
-rw-r--r--kernel/power/main.c3
-rw-r--r--kernel/power/power.h4
-rw-r--r--kernel/power/wakelock.c3
-rw-r--r--kernel/printk/printk.c14
-rw-r--r--kernel/rcu/tree.c10
-rw-r--r--kernel/rcu/tree.h2
-rw-r--r--kernel/rcu/tree_plugin.h22
-rw-r--r--kernel/rcu/tree_stall.h4
-rw-r--r--kernel/sched/fair.c6
-rw-r--r--kernel/softirq.c18
-rw-r--r--kernel/time/hrtimer.c103
-rw-r--r--kernel/time/posix-cpu-timers.c9
-rw-r--r--kernel/time/posix-timers.c1
-rw-r--r--kernel/time/timer_list.c4
-rw-r--r--kernel/trace/bpf_trace.c2
-rw-r--r--kernel/trace/trace.c13
-rw-r--r--kernel/trace/trace.h24
-rw-r--r--kernel/trace/trace_dynevent.c16
-rw-r--r--kernel/trace/trace_dynevent.h1
-rw-r--r--kernel/trace/trace_events_hist.c122
-rw-r--r--kernel/trace/trace_events_trigger.c22
-rw-r--r--kernel/trace/trace_functions.c6
-rw-r--r--kernel/trace/trace_kprobe.c2
-rw-r--r--kernel/trace/trace_probe.c9
-rw-r--r--kernel/trace/trace_uprobe.c2
38 files changed, 451 insertions, 160 deletions
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index cf2eb0895d40..684fb450ad08 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -369,7 +369,7 @@ static struct bpf_prog *prog_list_prog(struct bpf_prog_list *pl)
/* count number of elements in the list.
* it's slow but the list cannot be long
*/
-static u32 prog_list_length(struct hlist_head *head)
+static u32 prog_list_length(struct hlist_head *head, int *preorder_cnt)
{
struct bpf_prog_list *pl;
u32 cnt = 0;
@@ -377,6 +377,8 @@ static u32 prog_list_length(struct hlist_head *head)
hlist_for_each_entry(pl, head, node) {
if (!prog_list_prog(pl))
continue;
+ if (preorder_cnt && (pl->flags & BPF_F_PREORDER))
+ (*preorder_cnt)++;
cnt++;
}
return cnt;
@@ -400,7 +402,7 @@ static bool hierarchy_allows_attach(struct cgroup *cgrp,
if (flags & BPF_F_ALLOW_MULTI)
return true;
- cnt = prog_list_length(&p->bpf.progs[atype]);
+ cnt = prog_list_length(&p->bpf.progs[atype], NULL);
WARN_ON_ONCE(cnt > 1);
if (cnt == 1)
return !!(flags & BPF_F_ALLOW_OVERRIDE);
@@ -423,12 +425,12 @@ static int compute_effective_progs(struct cgroup *cgrp,
struct bpf_prog_array *progs;
struct bpf_prog_list *pl;
struct cgroup *p = cgrp;
- int cnt = 0;
+ int i, j, cnt = 0, preorder_cnt = 0, fstart, bstart, init_bstart;
/* count number of effective programs by walking parents */
do {
if (cnt == 0 || (p->bpf.flags[atype] & BPF_F_ALLOW_MULTI))
- cnt += prog_list_length(&p->bpf.progs[atype]);
+ cnt += prog_list_length(&p->bpf.progs[atype], &preorder_cnt);
p = cgroup_parent(p);
} while (p);
@@ -439,20 +441,34 @@ static int compute_effective_progs(struct cgroup *cgrp,
/* populate the array with effective progs */
cnt = 0;
p = cgrp;
+ fstart = preorder_cnt;
+ bstart = preorder_cnt - 1;
do {
if (cnt > 0 && !(p->bpf.flags[atype] & BPF_F_ALLOW_MULTI))
continue;
+ init_bstart = bstart;
hlist_for_each_entry(pl, &p->bpf.progs[atype], node) {
if (!prog_list_prog(pl))
continue;
- item = &progs->items[cnt];
+ if (pl->flags & BPF_F_PREORDER) {
+ item = &progs->items[bstart];
+ bstart--;
+ } else {
+ item = &progs->items[fstart];
+ fstart++;
+ }
item->prog = prog_list_prog(pl);
bpf_cgroup_storages_assign(item->cgroup_storage,
pl->storage);
cnt++;
}
+
+ /* reverse pre-ordering progs at this cgroup level */
+ for (i = bstart + 1, j = init_bstart; i < j; i++, j--)
+ swap(progs->items[i], progs->items[j]);
+
} while ((p = cgroup_parent(p)));
*array = progs;
@@ -663,7 +679,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp,
*/
return -EPERM;
- if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS)
+ if (prog_list_length(progs, NULL) >= BPF_CGROUP_MAX_PROGS)
return -E2BIG;
pl = find_attach_entry(progs, prog, link, replace_prog,
@@ -698,6 +714,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp,
pl->prog = prog;
pl->link = link;
+ pl->flags = flags;
bpf_cgroup_storages_assign(pl->storage, storage);
cgrp->bpf.flags[atype] = saved_flags;
@@ -1073,7 +1090,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
lockdep_is_held(&cgroup_mutex));
total_cnt += bpf_prog_array_length(effective);
} else {
- total_cnt += prog_list_length(&cgrp->bpf.progs[atype]);
+ total_cnt += prog_list_length(&cgrp->bpf.progs[atype], NULL);
}
}
@@ -1105,7 +1122,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
u32 id;
progs = &cgrp->bpf.progs[atype];
- cnt = min_t(int, prog_list_length(progs), total_cnt);
+ cnt = min_t(int, prog_list_length(progs, NULL), total_cnt);
i = 0;
hlist_for_each_entry(pl, progs, node) {
prog = prog_list_prog(pl);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 81fd1bb99416..5eaaf95048ab 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2258,8 +2258,8 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx,
}
#endif
-bool bpf_prog_map_compatible(struct bpf_map *map,
- const struct bpf_prog *fp)
+static bool __bpf_prog_map_compatible(struct bpf_map *map,
+ const struct bpf_prog *fp)
{
enum bpf_prog_type prog_type = resolve_prog_type(fp);
bool ret;
@@ -2268,14 +2268,6 @@ bool bpf_prog_map_compatible(struct bpf_map *map,
if (fp->kprobe_override)
return false;
- /* XDP programs inserted into maps are not guaranteed to run on
- * a particular netdev (and can run outside driver context entirely
- * in the case of devmap and cpumap). Until device checks
- * are implemented, prohibit adding dev-bound programs to program maps.
- */
- if (bpf_prog_is_dev_bound(aux))
- return false;
-
spin_lock(&map->owner.lock);
if (!map->owner.type) {
/* There's no owner yet where we could check for
@@ -2309,6 +2301,19 @@ bool bpf_prog_map_compatible(struct bpf_map *map,
return ret;
}
+bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp)
+{
+ /* XDP programs inserted into maps are not guaranteed to run on
+ * a particular netdev (and can run outside driver context entirely
+ * in the case of devmap and cpumap). Until device checks
+ * are implemented, prohibit adding dev-bound programs to program maps.
+ */
+ if (bpf_prog_is_dev_bound(fp->aux))
+ return false;
+
+ return __bpf_prog_map_compatible(map, fp);
+}
+
static int bpf_check_tail_call(const struct bpf_prog *fp)
{
struct bpf_prog_aux *aux = fp->aux;
@@ -2321,7 +2326,7 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
if (!map_type_contains_progs(map))
continue;
- if (!bpf_prog_map_compatible(map, fp)) {
+ if (!__bpf_prog_map_compatible(map, fp)) {
ret = -EINVAL;
goto out;
}
@@ -2359,7 +2364,7 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
/* In case of BPF to BPF calls, verifier did all the prep
* work with regards to JITing, etc.
*/
- bool jit_needed = false;
+ bool jit_needed = fp->jit_requested;
if (fp->bpf_func)
goto finalize;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index fc34f72702cc..8a3eadf17f78 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -2212,7 +2212,7 @@ static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_
b = &htab->buckets[i];
rcu_read_lock();
head = &b->head;
- hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) {
+ hlist_nulls_for_each_entry_safe(elem, n, head, hash_node) {
key = elem->key;
if (is_percpu) {
/* current cpu value for percpu map */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index f089a6163011..b66349f892f2 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3900,7 +3900,8 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
#define BPF_F_ATTACH_MASK_BASE \
(BPF_F_ALLOW_OVERRIDE | \
BPF_F_ALLOW_MULTI | \
- BPF_F_REPLACE)
+ BPF_F_REPLACE | \
+ BPF_F_PREORDER)
#define BPF_F_ATTACH_MASK_MPROG \
(BPF_F_REPLACE | \
@@ -4442,6 +4443,8 @@ static int bpf_prog_get_info_by_fd(struct file *file,
info.recursion_misses = stats.misses;
info.verified_insns = prog->aux->verified_insns;
+ if (prog->aux->btf)
+ info.btf_id = btf_obj_id(prog->aux->btf);
if (!bpf_capable()) {
info.jited_prog_len = 0;
@@ -4588,8 +4591,6 @@ static int bpf_prog_get_info_by_fd(struct file *file,
}
}
- if (prog->aux->btf)
- info.btf_id = btf_obj_id(prog->aux->btf);
info.attach_btf_id = prog->aux->attach_btf_id;
if (attach_btf)
info.attach_btf_obj_id = btf_obj_id(attach_btf);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 756e179a1efe..1f9ae600e445 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -16014,12 +16014,16 @@ static void clean_verifier_state(struct bpf_verifier_env *env,
static void clean_live_states(struct bpf_verifier_env *env, int insn,
struct bpf_verifier_state *cur)
{
+ struct bpf_verifier_state *loop_entry;
struct bpf_verifier_state_list *sl;
sl = *explored_state(env, insn);
while (sl) {
if (sl->state.branches)
goto next;
+ loop_entry = get_loop_entry(&sl->state);
+ if (loop_entry && loop_entry->branches)
+ goto next;
if (sl->state.insn_idx != insn ||
!same_callsites(&sl->state, cur))
goto next;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 3ccf80dfa587..e8ef062f6ca0 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -90,7 +90,7 @@
DEFINE_MUTEX(cgroup_mutex);
DEFINE_SPINLOCK(css_set_lock);
-#ifdef CONFIG_PROVE_RCU
+#if (defined CONFIG_PROVE_RCU || defined CONFIG_LOCKDEP)
EXPORT_SYMBOL_GPL(cgroup_mutex);
EXPORT_SYMBOL_GPL(css_set_lock);
#endif
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 3646426c69e2..ad8b62202bdc 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1229,9 +1229,11 @@ static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
if (top_cs) {
/*
- * Percpu kthreads in top_cpuset are ignored
+ * PF_NO_SETAFFINITY tasks are ignored.
+ * All per cpu kthreads should have PF_NO_SETAFFINITY
+ * flag set, see kthread_set_per_cpu().
*/
- if (kthread_is_per_cpu(task))
+ if (task->flags & PF_NO_SETAFFINITY)
continue;
cpumask_andnot(new_cpus, possible_mask, cs->subparts_cpus);
} else {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 987807b1040a..563f39518f7f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1163,6 +1163,12 @@ static void perf_assert_pmu_disabled(struct pmu *pmu)
WARN_ON_ONCE(*this_cpu_ptr(pmu->pmu_disable_count) == 0);
}
+static inline void perf_pmu_read(struct perf_event *event)
+{
+ if (event->state == PERF_EVENT_STATE_ACTIVE)
+ event->pmu->read(event);
+}
+
static void get_ctx(struct perf_event_context *ctx)
{
refcount_inc(&ctx->refcount);
@@ -3397,8 +3403,7 @@ static void __perf_event_sync_stat(struct perf_event *event,
* we know the event must be on the current CPU, therefore we
* don't need to use it.
*/
- if (event->state == PERF_EVENT_STATE_ACTIVE)
- event->pmu->read(event);
+ perf_pmu_read(event);
perf_event_update_time(event);
@@ -4524,15 +4529,8 @@ static void __perf_event_read(void *info)
pmu->read(event);
- for_each_sibling_event(sub, event) {
- if (sub->state == PERF_EVENT_STATE_ACTIVE) {
- /*
- * Use sibling's PMU rather than @event's since
- * sibling could be on different (eg: software) PMU.
- */
- sub->pmu->read(sub);
- }
- }
+ for_each_sibling_event(sub, event)
+ perf_pmu_read(sub);
data->ret = pmu->commit_txn(pmu);
@@ -5915,6 +5913,9 @@ static int perf_event_set_output(struct perf_event *event,
static int perf_event_set_filter(struct perf_event *event, void __user *arg);
static int perf_copy_attr(struct perf_event_attr __user *uattr,
struct perf_event_attr *attr);
+static int __perf_event_set_bpf_prog(struct perf_event *event,
+ struct bpf_prog *prog,
+ u64 bpf_cookie);
static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned long arg)
{
@@ -5983,7 +5984,7 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon
if (IS_ERR(prog))
return PTR_ERR(prog);
- err = perf_event_set_bpf_prog(event, prog, 0);
+ err = __perf_event_set_bpf_prog(event, prog, 0);
if (err) {
bpf_prog_put(prog);
return err;
@@ -7297,9 +7298,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
values[n++] = running;
- if ((leader != event) &&
- (leader->state == PERF_EVENT_STATE_ACTIVE))
- leader->pmu->read(leader);
+ if ((leader != event) && !handle->skip_read)
+ perf_pmu_read(leader);
values[n++] = perf_event_count(leader);
if (read_format & PERF_FORMAT_ID)
@@ -7312,9 +7312,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
for_each_sibling_event(sub, leader) {
n = 0;
- if ((sub != event) &&
- (sub->state == PERF_EVENT_STATE_ACTIVE))
- sub->pmu->read(sub);
+ if ((sub != event) && !handle->skip_read)
+ perf_pmu_read(sub);
values[n++] = perf_event_count(sub);
if (read_format & PERF_FORMAT_ID)
@@ -7369,6 +7368,9 @@ void perf_output_sample(struct perf_output_handle *handle,
{
u64 sample_type = data->type;
+ if (data->sample_flags & PERF_SAMPLE_READ)
+ handle->skip_read = 1;
+
perf_output_put(handle, *header);
if (sample_type & PERF_SAMPLE_IDENTIFIER)
@@ -9554,14 +9556,14 @@ __perf_event_account_interrupt(struct perf_event *event, int throttle)
hwc->interrupts = 1;
} else {
hwc->interrupts++;
- if (unlikely(throttle &&
- hwc->interrupts > max_samples_per_tick)) {
- __this_cpu_inc(perf_throttled_count);
- tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS);
- hwc->interrupts = MAX_INTERRUPTS;
- perf_log_throttle(event, 0);
- ret = 1;
- }
+ }
+
+ if (unlikely(throttle && hwc->interrupts >= max_samples_per_tick)) {
+ __this_cpu_inc(perf_throttled_count);
+ tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS);
+ hwc->interrupts = MAX_INTERRUPTS;
+ perf_log_throttle(event, 0);
+ ret = 1;
}
if (event->attr.freq) {
@@ -10584,8 +10586,9 @@ static inline bool perf_event_is_tracing(struct perf_event *event)
return false;
}
-int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog,
- u64 bpf_cookie)
+static int __perf_event_set_bpf_prog(struct perf_event *event,
+ struct bpf_prog *prog,
+ u64 bpf_cookie)
{
bool is_kprobe, is_uprobe, is_tracepoint, is_syscall_tp;
@@ -10623,6 +10626,20 @@ int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog,
return perf_event_attach_bpf_prog(event, prog, bpf_cookie);
}
+int perf_event_set_bpf_prog(struct perf_event *event,
+ struct bpf_prog *prog,
+ u64 bpf_cookie)
+{
+ struct perf_event_context *ctx;
+ int ret;
+
+ ctx = perf_event_ctx_lock(event);
+ ret = __perf_event_set_bpf_prog(event, prog, bpf_cookie);
+ perf_event_ctx_unlock(event, ctx);
+
+ return ret;
+}
+
void perf_event_free_bpf_prog(struct perf_event *event)
{
if (!perf_event_is_tracing(event)) {
@@ -10642,7 +10659,15 @@ static void perf_event_free_filter(struct perf_event *event)
{
}
-int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog,
+static int __perf_event_set_bpf_prog(struct perf_event *event,
+ struct bpf_prog *prog,
+ u64 bpf_cookie)
+{
+ return -ENOENT;
+}
+
+int perf_event_set_bpf_prog(struct perf_event *event,
+ struct bpf_prog *prog,
u64 bpf_cookie)
{
return -ENOENT;
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 6c2cb4e4f48d..8f3f624419aa 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -950,9 +950,10 @@ static int hw_breakpoint_event_init(struct perf_event *bp)
return -ENOENT;
/*
- * no branch sampling for breakpoint events
+ * Check if breakpoint type is supported before proceeding.
+ * Also, no branch sampling for breakpoint events.
*/
- if (has_branch_stack(bp))
+ if (!hw_breakpoint_slots_cached(find_slot_idx(bp->attr.bp_type)) || has_branch_stack(bp))
return -EOPNOTSUPP;
err = register_perf_hw_breakpoint(bp);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 52de76ef8723..dc1193b779c0 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -181,6 +181,7 @@ __perf_output_begin(struct perf_output_handle *handle,
handle->rb = rb;
handle->event = event;
+ handle->flags = 0;
have_lost = local_read(&rb->lost);
if (unlikely(have_lost)) {
diff --git a/kernel/fork.c b/kernel/fork.c
index 97f433fb4b5e..7966c9a1c163 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -518,10 +518,6 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
vma_numab_state_init(new);
dup_anon_vma_name(orig, new);
- /* track_pfn_copy() will later take care of copying internal state. */
- if (unlikely(new->vm_flags & VM_PFNMAP))
- untrack_pfn_clear(new);
-
return new;
}
@@ -715,6 +711,11 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
tmp = vm_area_dup(mpnt);
if (!tmp)
goto fail_nomem;
+
+ /* track_pfn_copy() will later take care of copying internal state. */
+ if (unlikely(tmp->vm_flags & VM_PFNMAP))
+ untrack_pfn_clear(tmp);
+
retval = vma_dup_policy(mpnt, tmp);
if (retval)
goto fail_nomem_policy;
diff --git a/kernel/padata.c b/kernel/padata.c
index 071d8cad8078..93cd7704ab63 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -358,7 +358,8 @@ static void padata_reorder(struct parallel_data *pd)
* To avoid UAF issue, add pd ref here, and put pd ref after reorder_work finish.
*/
padata_get_pd(pd);
- queue_work(pinst->serial_wq, &pd->reorder_work);
+ if (!queue_work(pinst->serial_wq, &pd->reorder_work))
+ padata_put_pd(pd);
}
}
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index c2fc58938dee..76dcf2e28427 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -80,6 +80,11 @@ void hibernate_release(void)
atomic_inc(&hibernate_atomic);
}
+bool hibernation_in_progress(void)
+{
+ return !atomic_read(&hibernate_atomic);
+}
+
bool hibernation_available(void)
{
return nohibernate == 0 &&
diff --git a/kernel/power/main.c b/kernel/power/main.c
index f6425ae3e8b0..a3543bd2d25a 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -585,7 +585,8 @@ bool pm_debug_messages_on __read_mostly;
bool pm_debug_messages_should_print(void)
{
- return pm_debug_messages_on && pm_suspend_target_state != PM_SUSPEND_ON;
+ return pm_debug_messages_on && (hibernation_in_progress() ||
+ pm_suspend_target_state != PM_SUSPEND_ON);
}
EXPORT_SYMBOL_GPL(pm_debug_messages_should_print);
diff --git a/kernel/power/power.h b/kernel/power/power.h
index a98f95e309a3..62a7cb452a4b 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -66,10 +66,14 @@ extern void enable_restore_image_protection(void);
static inline void enable_restore_image_protection(void) {}
#endif /* CONFIG_STRICT_KERNEL_RWX */
+extern bool hibernation_in_progress(void);
+
#else /* !CONFIG_HIBERNATION */
static inline void hibernate_reserved_size_init(void) {}
static inline void hibernate_image_size_init(void) {}
+
+static inline bool hibernation_in_progress(void) { return false; }
#endif /* !CONFIG_HIBERNATION */
#define power_attr(_name) \
diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c
index 52571dcad768..4e941999a53b 100644
--- a/kernel/power/wakelock.c
+++ b/kernel/power/wakelock.c
@@ -49,6 +49,9 @@ ssize_t pm_show_wakelocks(char *buf, bool show_active)
len += sysfs_emit_at(buf, len, "%s ", wl->name);
}
+ if (len > 0)
+ --len;
+
len += sysfs_emit_at(buf, len, "\n");
mutex_unlock(&wakelocks_lock);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index dcdf449615bd..51c43e0f9b29 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -3119,7 +3119,12 @@ void console_unblank(void)
*/
cookie = console_srcu_read_lock();
for_each_console_srcu(c) {
- if ((console_srcu_read_flags(c) & CON_ENABLED) && c->unblank) {
+ short flags = console_srcu_read_flags(c);
+
+ if (flags & CON_SUSPENDED)
+ continue;
+
+ if ((flags & CON_ENABLED) && c->unblank) {
found_unblank = true;
break;
}
@@ -3156,7 +3161,12 @@ void console_unblank(void)
cookie = console_srcu_read_lock();
for_each_console_srcu(c) {
- if ((console_srcu_read_flags(c) & CON_ENABLED) && c->unblank)
+ short flags = console_srcu_read_flags(c);
+
+ if (flags & CON_SUSPENDED)
+ continue;
+
+ if ((flags & CON_ENABLED) && c->unblank)
c->unblank();
}
console_srcu_read_unlock(cookie);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index fda08520c75c..1fb3b7a0ed5d 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -754,6 +754,10 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
return 0;
}
+#ifndef arch_irq_stat_cpu
+#define arch_irq_stat_cpu(cpu) 0
+#endif
+
/*
* Returns positive if the specified CPU has passed through a quiescent state
* by virtue of being in or having passed through an dynticks idle state since
@@ -889,9 +893,9 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
rsrp->cputime_irq = kcpustat_field(kcsp, CPUTIME_IRQ, cpu);
rsrp->cputime_softirq = kcpustat_field(kcsp, CPUTIME_SOFTIRQ, cpu);
rsrp->cputime_system = kcpustat_field(kcsp, CPUTIME_SYSTEM, cpu);
- rsrp->nr_hardirqs = kstat_cpu_irqs_sum(rdp->cpu);
- rsrp->nr_softirqs = kstat_cpu_softirqs_sum(rdp->cpu);
- rsrp->nr_csw = nr_context_switches_cpu(rdp->cpu);
+ rsrp->nr_hardirqs = kstat_cpu_irqs_sum(cpu) + arch_irq_stat_cpu(cpu);
+ rsrp->nr_softirqs = kstat_cpu_softirqs_sum(cpu);
+ rsrp->nr_csw = nr_context_switches_cpu(cpu);
rsrp->jiffies = jiffies;
rsrp->gp_seq = rdp->gp_seq;
}
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 9eb43b501ff5..ac8cc756920d 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -169,7 +169,7 @@ struct rcu_snap_record {
u64 cputime_irq; /* Accumulated cputime of hard irqs */
u64 cputime_softirq;/* Accumulated cputime of soft irqs */
u64 cputime_system; /* Accumulated cputime of kernel tasks */
- unsigned long nr_hardirqs; /* Accumulated number of hard irqs */
+ u64 nr_hardirqs; /* Accumulated number of hard irqs */
unsigned int nr_softirqs; /* Accumulated number of soft irqs */
unsigned long long nr_csw; /* Accumulated number of task switches */
unsigned long jiffies; /* Track jiffies value */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 41021080ad25..94b715139f52 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -821,8 +821,17 @@ void rcu_read_unlock_strict(void)
{
struct rcu_data *rdp;
- if (irqs_disabled() || preempt_count() || !rcu_state.gp_kthread)
+ if (irqs_disabled() || in_atomic_preempt_off() || !rcu_state.gp_kthread)
return;
+
+ /*
+ * rcu_report_qs_rdp() can only be invoked with a stable rdp and
+ * from the local CPU.
+ *
+ * The in_atomic_preempt_off() check ensures that we come here holding
+ * the last preempt_count (which will get dropped once we return to
+ * __rcu_read_unlock().
+ */
rdp = this_cpu_ptr(&rcu_data);
rdp->cpu_no_qs.b.norm = false;
rcu_report_qs_rdp(rdp);
@@ -963,13 +972,16 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
*/
static void rcu_flavor_sched_clock_irq(int user)
{
- if (user || rcu_is_cpu_rrupt_from_idle()) {
+ if (user || rcu_is_cpu_rrupt_from_idle() ||
+ (IS_ENABLED(CONFIG_PREEMPT_COUNT) &&
+ (preempt_count() == HARDIRQ_OFFSET))) {
/*
* Get here if this CPU took its interrupt from user
- * mode or from the idle loop, and if this is not a
- * nested interrupt. In this case, the CPU is in
- * a quiescent state, so note it.
+ * mode, from the idle loop without this being a nested
+ * interrupt, or while not holding the task preempt count
+ * (with PREEMPT_COUNT=y). In this case, the CPU is in a
+ * quiescent state, so note it.
*
* No memory barrier is required here because rcu_qs()
* references only CPU-local variables that other CPUs
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 11a1fac3a589..aab91040b83b 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -452,8 +452,8 @@ static void print_cpu_stat_info(int cpu)
rsr.cputime_system = kcpustat_field(kcsp, CPUTIME_SYSTEM, cpu);
pr_err("\t hardirqs softirqs csw/system\n");
- pr_err("\t number: %8ld %10d %12lld\n",
- kstat_cpu_irqs_sum(cpu) - rsrp->nr_hardirqs,
+ pr_err("\t number: %8lld %10d %12lld\n",
+ kstat_cpu_irqs_sum(cpu) + arch_irq_stat_cpu(cpu) - rsrp->nr_hardirqs,
kstat_cpu_softirqs_sum(cpu) - rsrp->nr_softirqs,
nr_context_switches_cpu(cpu) - rsrp->nr_csw);
pr_err("\tcputime: %8lld %10lld %12lld ==> %d(ms)\n",
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 268e2a49b964..6ce3028e6e85 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -73,10 +73,10 @@ unsigned int sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_LOG;
/*
* Minimal preemption granularity for CPU-bound tasks:
*
- * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 0.70 msec * (1 + ilog(ncpus)), units: nanoseconds)
*/
-unsigned int sysctl_sched_base_slice = 750000ULL;
-static unsigned int normalized_sysctl_sched_base_slice = 750000ULL;
+unsigned int sysctl_sched_base_slice = 700000ULL;
+static unsigned int normalized_sysctl_sched_base_slice = 700000ULL;
/*
* After fork, child runs first. If set to 0 (default) then
diff --git a/kernel/softirq.c b/kernel/softirq.c
index f24d80cf20bd..d9e37f3fa130 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -125,6 +125,18 @@ static DEFINE_PER_CPU(struct softirq_ctrl, softirq_ctrl) = {
.lock = INIT_LOCAL_LOCK(softirq_ctrl.lock),
};
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static struct lock_class_key bh_lock_key;
+struct lockdep_map bh_lock_map = {
+ .name = "local_bh",
+ .key = &bh_lock_key,
+ .wait_type_outer = LD_WAIT_FREE,
+ .wait_type_inner = LD_WAIT_CONFIG, /* PREEMPT_RT makes BH preemptible. */
+ .lock_type = LD_LOCK_PERCPU,
+};
+EXPORT_SYMBOL_GPL(bh_lock_map);
+#endif
+
/**
* local_bh_blocked() - Check for idle whether BH processing is blocked
*
@@ -147,6 +159,8 @@ void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
WARN_ON_ONCE(in_hardirq());
+ lock_map_acquire_read(&bh_lock_map);
+
/* First entry of a task into a BH disabled section? */
if (!current->softirq_disable_cnt) {
if (preemptible()) {
@@ -210,6 +224,8 @@ void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
WARN_ON_ONCE(in_hardirq());
lockdep_assert_irqs_enabled();
+ lock_map_release(&bh_lock_map);
+
local_irq_save(flags);
curcnt = __this_cpu_read(softirq_ctrl.cnt);
@@ -260,6 +276,8 @@ static inline void ksoftirqd_run_begin(void)
/* Counterpart to ksoftirqd_run_begin() */
static inline void ksoftirqd_run_end(void)
{
+ /* pairs with the lock_map_acquire_read() in ksoftirqd_run_begin() */
+ lock_map_release(&bh_lock_map);
__local_bh_enable(SOFTIRQ_OFFSET, true);
WARN_ON_ONCE(in_interrupt());
local_irq_enable();
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 877535b06e73..6d9da768604d 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -58,6 +58,8 @@
#define HRTIMER_ACTIVE_SOFT (HRTIMER_ACTIVE_HARD << MASK_SHIFT)
#define HRTIMER_ACTIVE_ALL (HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD)
+static void retrigger_next_event(void *arg);
+
/*
* The timer bases:
*
@@ -111,7 +113,8 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
.clockid = CLOCK_TAI,
.get_time = &ktime_get_clocktai,
},
- }
+ },
+ .csd = CSD_INIT(retrigger_next_event, NULL)
};
static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
@@ -124,6 +127,14 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
[CLOCK_TAI] = HRTIMER_BASE_TAI,
};
+static inline bool hrtimer_base_is_online(struct hrtimer_cpu_base *base)
+{
+ if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+ return true;
+ else
+ return likely(base->online);
+}
+
/*
* Functions and macros which are different for UP/SMP systems are kept in a
* single place
@@ -178,27 +189,54 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
}
/*
- * We do not migrate the timer when it is expiring before the next
- * event on the target cpu. When high resolution is enabled, we cannot
- * reprogram the target cpu hardware and we would cause it to fire
- * late. To keep it simple, we handle the high resolution enabled and
- * disabled case similar.
+ * Check if the elected target is suitable considering its next
+ * event and the hotplug state of the current CPU.
+ *
+ * If the elected target is remote and its next event is after the timer
+ * to queue, then a remote reprogram is necessary. However there is no
+ * guarantee the IPI handling the operation would arrive in time to meet
+ * the high resolution deadline. In this case the local CPU becomes a
+ * preferred target, unless it is offline.
+ *
+ * High and low resolution modes are handled the same way for simplicity.
*
* Called with cpu_base->lock of target cpu held.
*/
-static int
-hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
+static bool hrtimer_suitable_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base,
+ struct hrtimer_cpu_base *new_cpu_base,
+ struct hrtimer_cpu_base *this_cpu_base)
{
ktime_t expires;
+ /*
+ * The local CPU clockevent can be reprogrammed. Also get_target_base()
+ * guarantees it is online.
+ */
+ if (new_cpu_base == this_cpu_base)
+ return true;
+
+ /*
+ * The offline local CPU can't be the default target if the
+ * next remote target event is after this timer. Keep the
+ * elected new base. An IPI will we issued to reprogram
+ * it as a last resort.
+ */
+ if (!hrtimer_base_is_online(this_cpu_base))
+ return true;
+
expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
- return expires < new_base->cpu_base->expires_next;
+
+ return expires >= new_base->cpu_base->expires_next;
}
-static inline
-struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
- int pinned)
+static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned)
{
+ if (!hrtimer_base_is_online(base)) {
+ int cpu = cpumask_any_and(cpu_online_mask, housekeeping_cpumask(HK_TYPE_TIMER));
+
+ return &per_cpu(hrtimer_bases, cpu);
+ }
+
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
if (static_branch_likely(&timers_migration_enabled) && !pinned)
return &per_cpu(hrtimer_bases, get_nohz_timer_target());
@@ -249,8 +287,8 @@ again:
raw_spin_unlock(&base->cpu_base->lock);
raw_spin_lock(&new_base->cpu_base->lock);
- if (new_cpu_base != this_cpu_base &&
- hrtimer_check_target(timer, new_base)) {
+ if (!hrtimer_suitable_target(timer, new_base, new_cpu_base,
+ this_cpu_base)) {
raw_spin_unlock(&new_base->cpu_base->lock);
raw_spin_lock(&base->cpu_base->lock);
new_cpu_base = this_cpu_base;
@@ -259,8 +297,7 @@ again:
}
WRITE_ONCE(timer->base, new_base);
} else {
- if (new_cpu_base != this_cpu_base &&
- hrtimer_check_target(timer, new_base)) {
+ if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, this_cpu_base)) {
new_cpu_base = this_cpu_base;
goto again;
}
@@ -720,8 +757,6 @@ static inline int hrtimer_is_hres_enabled(void)
return hrtimer_hres_enabled;
}
-static void retrigger_next_event(void *arg);
-
/*
* Switch to high resolution mode
*/
@@ -1208,6 +1243,7 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
u64 delta_ns, const enum hrtimer_mode mode,
struct hrtimer_clock_base *base)
{
+ struct hrtimer_cpu_base *this_cpu_base = this_cpu_ptr(&hrtimer_bases);
struct hrtimer_clock_base *new_base;
bool force_local, first;
@@ -1219,10 +1255,16 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
* and enforce reprogramming after it is queued no matter whether
* it is the new first expiring timer again or not.
*/
- force_local = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
+ force_local = base->cpu_base == this_cpu_base;
force_local &= base->cpu_base->next_timer == timer;
/*
+ * Don't force local queuing if this enqueue happens on a unplugged
+ * CPU after hrtimer_cpu_dying() has been invoked.
+ */
+ force_local &= this_cpu_base->online;
+
+ /*
* Remove an active timer from the queue. In case it is not queued
* on the current CPU, make sure that remove_hrtimer() updates the
* remote data correctly.
@@ -1251,8 +1293,27 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
}
first = enqueue_hrtimer(timer, new_base, mode);
- if (!force_local)
- return first;
+ if (!force_local) {
+ /*
+ * If the current CPU base is online, then the timer is
+ * never queued on a remote CPU if it would be the first
+ * expiring timer there.
+ */
+ if (hrtimer_base_is_online(this_cpu_base))
+ return first;
+
+ /*
+ * Timer was enqueued remote because the current base is
+ * already offline. If the timer is the first to expire,
+ * kick the remote CPU to reprogram the clock event.
+ */
+ if (first) {
+ struct hrtimer_cpu_base *new_cpu_base = new_base->cpu_base;
+
+ smp_call_function_single_async(new_cpu_base->cpu, &new_cpu_base->csd);
+ }
+ return 0;
+ }
/*
* Timer was forced to stay on the current CPU to avoid
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index e9c6f9d0e42c..9af1f2a72a0a 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1438,6 +1438,15 @@ void run_posix_cpu_timers(void)
lockdep_assert_irqs_disabled();
/*
+ * Ensure that release_task(tsk) can't happen while
+ * handle_posix_cpu_timers() is running. Otherwise, a concurrent
+ * posix_cpu_timer_del() may fail to lock_task_sighand(tsk) and
+ * miss timer->it.cpu.firing != 0.
+ */
+ if (tsk->exit_state)
+ return;
+
+ /*
* If the actual expiry is deferred to task work context and the
* work is already scheduled there is no point to do anything here.
*/
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index b924f0f096fa..7534069f6033 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -118,6 +118,7 @@ static int posix_timer_add(struct k_itimer *timer)
return id;
}
spin_unlock(&hash_lock);
+ cond_resched();
}
/* POSIX return code when no timer ID could be allocated */
return -EAGAIN;
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index ed7d6ad694fb..20a5e6962b69 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -46,7 +46,7 @@ static void
print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer,
int idx, u64 now)
{
- SEQ_printf(m, " #%d: <%pK>, %ps", idx, taddr, timer->function);
+ SEQ_printf(m, " #%d: <%p>, %ps", idx, taddr, timer->function);
SEQ_printf(m, ", S:%02x", timer->state);
SEQ_printf(m, "\n");
SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n",
@@ -98,7 +98,7 @@ next_one:
static void
print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
{
- SEQ_printf(m, " .base: %pK\n", base);
+ SEQ_printf(m, " .base: %p\n", base);
SEQ_printf(m, " .index: %d\n", base->index);
SEQ_printf(m, " .resolution: %u nsecs\n", hrtimer_resolution);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 97f660a8ddc7..8903db0b5960 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1834,7 +1834,7 @@ static struct pt_regs *get_bpf_raw_tp_regs(void)
struct bpf_raw_tp_regs *tp_regs = this_cpu_ptr(&bpf_raw_tp_regs);
int nest_level = this_cpu_inc_return(bpf_raw_tp_nest_level);
- if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(tp_regs->regs))) {
+ if (nest_level > ARRAY_SIZE(tp_regs->regs)) {
this_cpu_dec(bpf_raw_tp_nest_level);
return ERR_PTR(-EBUSY);
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 95868c315730..946350c98b53 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3487,10 +3487,9 @@ out_nobuffer:
}
EXPORT_SYMBOL_GPL(trace_vbprintk);
-__printf(3, 0)
-static int
-__trace_array_vprintk(struct trace_buffer *buffer,
- unsigned long ip, const char *fmt, va_list args)
+static __printf(3, 0)
+int __trace_array_vprintk(struct trace_buffer *buffer,
+ unsigned long ip, const char *fmt, va_list args)
{
struct trace_event_call *call = &event_print;
struct ring_buffer_event *event;
@@ -3543,7 +3542,6 @@ out_nobuffer:
return len;
}
-__printf(3, 0)
int trace_array_vprintk(struct trace_array *tr,
unsigned long ip, const char *fmt, va_list args)
{
@@ -3573,7 +3571,6 @@ int trace_array_vprintk(struct trace_array *tr,
* Note, trace_array_init_printk() must be called on @tr before this
* can be used.
*/
-__printf(3, 0)
int trace_array_printk(struct trace_array *tr,
unsigned long ip, const char *fmt, ...)
{
@@ -3618,7 +3615,6 @@ int trace_array_init_printk(struct trace_array *tr)
}
EXPORT_SYMBOL_GPL(trace_array_init_printk);
-__printf(3, 4)
int trace_array_printk_buf(struct trace_buffer *buffer,
unsigned long ip, const char *fmt, ...)
{
@@ -3634,7 +3630,6 @@ int trace_array_printk_buf(struct trace_buffer *buffer,
return ret;
}
-__printf(2, 0)
int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
{
return trace_array_vprintk(&global_trace, ip, fmt, args);
@@ -7028,7 +7023,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
ret = trace_seq_to_buffer(&iter->seq,
page_address(spd.pages[i]),
min((size_t)trace_seq_used(&iter->seq),
- PAGE_SIZE));
+ (size_t)PAGE_SIZE));
if (ret < 0) {
__free_page(spd.pages[i]);
break;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index db0d2641125e..e3afb830fbcc 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -800,13 +800,15 @@ static inline void __init disable_tracing_selftest(const char *reason)
extern void *head_page(struct trace_array_cpu *data);
extern unsigned long long ns2usecs(u64 nsec);
-extern int
-trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
-extern int
-trace_vprintk(unsigned long ip, const char *fmt, va_list args);
-extern int
-trace_array_vprintk(struct trace_array *tr,
- unsigned long ip, const char *fmt, va_list args);
+
+__printf(2, 0)
+int trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
+__printf(2, 0)
+int trace_vprintk(unsigned long ip, const char *fmt, va_list args);
+__printf(3, 0)
+int trace_array_vprintk(struct trace_array *tr,
+ unsigned long ip, const char *fmt, va_list args);
+__printf(3, 4)
int trace_array_printk_buf(struct trace_buffer *buffer,
unsigned long ip, const char *fmt, ...);
void trace_printk_seq(struct trace_seq *s);
@@ -1641,6 +1643,9 @@ extern int event_enable_register_trigger(char *glob,
extern void event_enable_unregister_trigger(char *glob,
struct event_trigger_data *test,
struct trace_event_file *file);
+extern struct event_trigger_data *
+trigger_data_alloc(struct event_command *cmd_ops, char *cmd, char *param,
+ void *private_data);
extern void trigger_data_free(struct event_trigger_data *data);
extern int event_trigger_init(struct event_trigger_data *data);
extern int trace_event_trigger_enable_disable(struct trace_event_file *file,
@@ -1667,11 +1672,6 @@ extern bool event_trigger_check_remove(const char *glob);
extern bool event_trigger_empty_param(const char *param);
extern int event_trigger_separate_filter(char *param_and_filter, char **param,
char **filter, bool param_required);
-extern struct event_trigger_data *
-event_trigger_alloc(struct event_command *cmd_ops,
- char *cmd,
- char *param,
- void *private_data);
extern int event_trigger_parse_num(char *trigger,
struct event_trigger_data *trigger_data);
extern int event_trigger_set_filter(struct event_command *cmd_ops,
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index 4376887e0d8a..c9b0533407ed 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -16,7 +16,7 @@
#include "trace_output.h" /* for trace_event_sem */
#include "trace_dynevent.h"
-static DEFINE_MUTEX(dyn_event_ops_mutex);
+DEFINE_MUTEX(dyn_event_ops_mutex);
static LIST_HEAD(dyn_event_ops_list);
bool trace_event_dyn_try_get_ref(struct trace_event_call *dyn_call)
@@ -125,6 +125,20 @@ out:
return ret;
}
+/*
+ * Locked version of event creation. The event creation must be protected by
+ * dyn_event_ops_mutex because of protecting trace_probe_log.
+ */
+int dyn_event_create(const char *raw_command, struct dyn_event_operations *type)
+{
+ int ret;
+
+ mutex_lock(&dyn_event_ops_mutex);
+ ret = type->create(raw_command);
+ mutex_unlock(&dyn_event_ops_mutex);
+ return ret;
+}
+
static int create_dyn_event(const char *raw_command)
{
struct dyn_event_operations *ops;
diff --git a/kernel/trace/trace_dynevent.h b/kernel/trace/trace_dynevent.h
index 936477a111d3..beee3f8d7544 100644
--- a/kernel/trace/trace_dynevent.h
+++ b/kernel/trace/trace_dynevent.h
@@ -100,6 +100,7 @@ void *dyn_event_seq_next(struct seq_file *m, void *v, loff_t *pos);
void dyn_event_seq_stop(struct seq_file *m, void *v);
int dyn_events_release_all(struct dyn_event_operations *type);
int dyn_event_release(const char *raw_command, struct dyn_event_operations *type);
+int dyn_event_create(const char *raw_command, struct dyn_event_operations *type);
/*
* for_each_dyn_event - iterate over the dyn_event list
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index e6f9cbc622c7..88985aefb71f 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -5257,17 +5257,94 @@ hist_trigger_actions(struct hist_trigger_data *hist_data,
}
}
+/*
+ * The hist_pad structure is used to save information to create
+ * a histogram from the histogram trigger. It's too big to store
+ * on the stack, so when the histogram trigger is initialized
+ * a percpu array of 4 hist_pad structures is allocated.
+ * This will cover every context from normal, softirq, irq and NMI
+ * in the very unlikely event that a tigger happens at each of
+ * these contexts and interrupts a currently active trigger.
+ */
+struct hist_pad {
+ unsigned long entries[HIST_STACKTRACE_DEPTH];
+ u64 var_ref_vals[TRACING_MAP_VARS_MAX];
+ char compound_key[HIST_KEY_SIZE_MAX];
+};
+
+static struct hist_pad __percpu *hist_pads;
+static DEFINE_PER_CPU(int, hist_pad_cnt);
+static refcount_t hist_pad_ref;
+
+/* One hist_pad for every context (normal, softirq, irq, NMI) */
+#define MAX_HIST_CNT 4
+
+static int alloc_hist_pad(void)
+{
+ lockdep_assert_held(&event_mutex);
+
+ if (refcount_read(&hist_pad_ref)) {
+ refcount_inc(&hist_pad_ref);
+ return 0;
+ }
+
+ hist_pads = __alloc_percpu(sizeof(struct hist_pad) * MAX_HIST_CNT,
+ __alignof__(struct hist_pad));
+ if (!hist_pads)
+ return -ENOMEM;
+
+ refcount_set(&hist_pad_ref, 1);
+ return 0;
+}
+
+static void free_hist_pad(void)
+{
+ lockdep_assert_held(&event_mutex);
+
+ if (!refcount_dec_and_test(&hist_pad_ref))
+ return;
+
+ free_percpu(hist_pads);
+ hist_pads = NULL;
+}
+
+static struct hist_pad *get_hist_pad(void)
+{
+ struct hist_pad *hist_pad;
+ int cnt;
+
+ if (WARN_ON_ONCE(!hist_pads))
+ return NULL;
+
+ preempt_disable();
+
+ hist_pad = per_cpu_ptr(hist_pads, smp_processor_id());
+
+ if (this_cpu_read(hist_pad_cnt) == MAX_HIST_CNT) {
+ preempt_enable();
+ return NULL;
+ }
+
+ cnt = this_cpu_inc_return(hist_pad_cnt) - 1;
+
+ return &hist_pad[cnt];
+}
+
+static void put_hist_pad(void)
+{
+ this_cpu_dec(hist_pad_cnt);
+ preempt_enable();
+}
+
static void event_hist_trigger(struct event_trigger_data *data,
struct trace_buffer *buffer, void *rec,
struct ring_buffer_event *rbe)
{
struct hist_trigger_data *hist_data = data->private_data;
bool use_compound_key = (hist_data->n_keys > 1);
- unsigned long entries[HIST_STACKTRACE_DEPTH];
- u64 var_ref_vals[TRACING_MAP_VARS_MAX];
- char compound_key[HIST_KEY_SIZE_MAX];
struct tracing_map_elt *elt = NULL;
struct hist_field *key_field;
+ struct hist_pad *hist_pad;
u64 field_contents;
void *key = NULL;
unsigned int i;
@@ -5275,12 +5352,18 @@ static void event_hist_trigger(struct event_trigger_data *data,
if (unlikely(!rbe))
return;
- memset(compound_key, 0, hist_data->key_size);
+ hist_pad = get_hist_pad();
+ if (!hist_pad)
+ return;
+
+ memset(hist_pad->compound_key, 0, hist_data->key_size);
for_each_hist_key_field(i, hist_data) {
key_field = hist_data->fields[i];
if (key_field->flags & HIST_FIELD_FL_STACKTRACE) {
+ unsigned long *entries = hist_pad->entries;
+
memset(entries, 0, HIST_STACKTRACE_SIZE);
if (key_field->field) {
unsigned long *stack, n_entries;
@@ -5304,26 +5387,31 @@ static void event_hist_trigger(struct event_trigger_data *data,
}
if (use_compound_key)
- add_to_key(compound_key, key, key_field, rec);
+ add_to_key(hist_pad->compound_key, key, key_field, rec);
}
if (use_compound_key)
- key = compound_key;
+ key = hist_pad->compound_key;
if (hist_data->n_var_refs &&
- !resolve_var_refs(hist_data, key, var_ref_vals, false))
- return;
+ !resolve_var_refs(hist_data, key, hist_pad->var_ref_vals, false))
+ goto out;
elt = tracing_map_insert(hist_data->map, key);
if (!elt)
- return;
+ goto out;
- hist_trigger_elt_update(hist_data, elt, buffer, rec, rbe, var_ref_vals);
+ hist_trigger_elt_update(hist_data, elt, buffer, rec, rbe, hist_pad->var_ref_vals);
- if (resolve_var_refs(hist_data, key, var_ref_vals, true))
- hist_trigger_actions(hist_data, elt, buffer, rec, rbe, key, var_ref_vals);
+ if (resolve_var_refs(hist_data, key, hist_pad->var_ref_vals, true)) {
+ hist_trigger_actions(hist_data, elt, buffer, rec, rbe,
+ key, hist_pad->var_ref_vals);
+ }
hist_poll_wakeup();
+
+ out:
+ put_hist_pad();
}
static void hist_trigger_stacktrace_print(struct seq_file *m,
@@ -6168,6 +6256,9 @@ static int event_hist_trigger_init(struct event_trigger_data *data)
{
struct hist_trigger_data *hist_data = data->private_data;
+ if (alloc_hist_pad() < 0)
+ return -ENOMEM;
+
if (!data->ref && hist_data->attrs->name)
save_named_trigger(hist_data->attrs->name, data);
@@ -6212,6 +6303,7 @@ static void event_hist_trigger_free(struct event_trigger_data *data)
destroy_hist_data(hist_data);
}
+ free_hist_pad();
}
static struct event_trigger_ops event_hist_trigger_ops = {
@@ -6227,9 +6319,7 @@ static int event_hist_trigger_named_init(struct event_trigger_data *data)
save_named_trigger(data->named_data->name, data);
- event_hist_trigger_init(data->named_data);
-
- return 0;
+ return event_hist_trigger_init(data->named_data);
}
static void event_hist_trigger_named_free(struct event_trigger_data *data)
@@ -6716,7 +6806,7 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
return PTR_ERR(hist_data);
}
- trigger_data = event_trigger_alloc(cmd_ops, cmd, param, hist_data);
+ trigger_data = trigger_data_alloc(cmd_ops, cmd, param, hist_data);
if (!trigger_data) {
ret = -ENOMEM;
goto out_free;
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 76abc9a45f97..fe079ff82ef1 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -809,7 +809,7 @@ out:
}
/**
- * event_trigger_alloc - allocate and init event_trigger_data for a trigger
+ * trigger_data_alloc - allocate and init event_trigger_data for a trigger
* @cmd_ops: The event_command operations for the trigger
* @cmd: The cmd string
* @param: The param string
@@ -820,14 +820,14 @@ out:
* trigger_ops to assign to the event_trigger_data. @private_data can
* also be passed in and associated with the event_trigger_data.
*
- * Use event_trigger_free() to free an event_trigger_data object.
+ * Use trigger_data_free() to free an event_trigger_data object.
*
* Return: The trigger_data object success, NULL otherwise
*/
-struct event_trigger_data *event_trigger_alloc(struct event_command *cmd_ops,
- char *cmd,
- char *param,
- void *private_data)
+struct event_trigger_data *trigger_data_alloc(struct event_command *cmd_ops,
+ char *cmd,
+ char *param,
+ void *private_data)
{
struct event_trigger_data *trigger_data;
struct event_trigger_ops *trigger_ops;
@@ -994,13 +994,13 @@ event_trigger_parse(struct event_command *cmd_ops,
return ret;
ret = -ENOMEM;
- trigger_data = event_trigger_alloc(cmd_ops, cmd, param, file);
+ trigger_data = trigger_data_alloc(cmd_ops, cmd, param, file);
if (!trigger_data)
goto out;
if (remove) {
event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
- kfree(trigger_data);
+ trigger_data_free(trigger_data);
ret = 0;
goto out;
}
@@ -1027,7 +1027,7 @@ event_trigger_parse(struct event_command *cmd_ops,
out_free:
event_trigger_reset_filter(cmd_ops, trigger_data);
- kfree(trigger_data);
+ trigger_data_free(trigger_data);
goto out;
}
@@ -1554,7 +1554,7 @@ stacktrace_trigger(struct event_trigger_data *data,
struct trace_event_file *file = data->private_data;
if (file)
- __trace_stack(file->tr, tracing_gen_ctx(), STACK_SKIP);
+ __trace_stack(file->tr, tracing_gen_ctx_dec(), STACK_SKIP);
else
trace_dump_stack(STACK_SKIP);
}
@@ -1787,7 +1787,7 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
enable_data->enable = enable;
enable_data->file = event_enable_file;
- trigger_data = event_trigger_alloc(cmd_ops, cmd, param, enable_data);
+ trigger_data = trigger_data_alloc(cmd_ops, cmd, param, enable_data);
if (!trigger_data) {
kfree(enable_data);
goto out;
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 69e92c7359fb..44ae51d1dc45 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -561,11 +561,7 @@ ftrace_traceoff(unsigned long ip, unsigned long parent_ip,
static __always_inline void trace_stack(struct trace_array *tr)
{
- unsigned int trace_ctx;
-
- trace_ctx = tracing_gen_ctx();
-
- __trace_stack(tr, trace_ctx, FTRACE_STACK_SKIP);
+ __trace_stack(tr, tracing_gen_ctx_dec(), FTRACE_STACK_SKIP);
}
static void
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 508c10414a93..46491f3c1569 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1004,7 +1004,7 @@ static int create_or_delete_trace_kprobe(const char *raw_command)
if (raw_command[0] == '-')
return dyn_event_release(raw_command, &trace_kprobe_ops);
- ret = trace_kprobe_create(raw_command);
+ ret = dyn_event_create(raw_command, &trace_kprobe_ops);
return ret == -ECANCELED ? -EINVAL : ret;
}
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 606190239c87..694f32d843d9 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -153,9 +153,12 @@ fail:
}
static struct trace_probe_log trace_probe_log;
+extern struct mutex dyn_event_ops_mutex;
void trace_probe_log_init(const char *subsystem, int argc, const char **argv)
{
+ lockdep_assert_held(&dyn_event_ops_mutex);
+
trace_probe_log.subsystem = subsystem;
trace_probe_log.argc = argc;
trace_probe_log.argv = argv;
@@ -164,11 +167,15 @@ void trace_probe_log_init(const char *subsystem, int argc, const char **argv)
void trace_probe_log_clear(void)
{
+ lockdep_assert_held(&dyn_event_ops_mutex);
+
memset(&trace_probe_log, 0, sizeof(trace_probe_log));
}
void trace_probe_log_set_index(int index)
{
+ lockdep_assert_held(&dyn_event_ops_mutex);
+
trace_probe_log.index = index;
}
@@ -177,6 +184,8 @@ void __trace_probe_log_err(int offset, int err_type)
char *command, *p;
int i, len = 0, pos = 0;
+ lockdep_assert_held(&dyn_event_ops_mutex);
+
if (!trace_probe_log.argv)
return;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 79f8da7e3cd4..ecf04e81ddf7 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -730,7 +730,7 @@ static int create_or_delete_trace_uprobe(const char *raw_command)
if (raw_command[0] == '-')
return dyn_event_release(raw_command, &trace_uprobe_ops);
- ret = trace_uprobe_create(raw_command);
+ ret = dyn_event_create(raw_command, &trace_uprobe_ops);
return ret == -ECANCELED ? -EINVAL : ret;
}