summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit_watch.c2
-rw-r--r--kernel/cgroup/cgroup.c5
-rw-r--r--kernel/cpu.c27
-rw-r--r--kernel/events/core.c23
-rw-r--r--kernel/power/qos.c8
-rw-r--r--kernel/power/snapshot.c9
-rw-r--r--kernel/sched/core.c5
-rw-r--r--kernel/sched/fair.c29
-rw-r--r--kernel/sched/idle.c24
-rw-r--r--kernel/signal.c2
-rw-r--r--kernel/time/ntp.c2
11 files changed, 104 insertions, 32 deletions
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 1f31c2f1e6fc..4508d5e0cf69 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -351,12 +351,12 @@ static int audit_get_nd(struct audit_watch *watch, struct path *parent)
struct dentry *d = kern_path_locked(watch->path, parent);
if (IS_ERR(d))
return PTR_ERR(d);
- inode_unlock(d_backing_inode(parent->dentry));
if (d_is_positive(d)) {
/* update watch filter fields */
watch->dev = d->d_sb->s_dev;
watch->ino = d_backing_inode(d)->i_ino;
}
+ inode_unlock(d_backing_inode(parent->dentry));
dput(d);
return 0;
}
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 080561bb8a4b..ef4242e5d4bc 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2119,11 +2119,12 @@ int cgroup_do_get_tree(struct fs_context *fc)
nsdentry = kernfs_node_dentry(cgrp->kn, sb);
dput(fc->root);
- fc->root = nsdentry;
if (IS_ERR(nsdentry)) {
- ret = PTR_ERR(nsdentry);
deactivate_locked_super(sb);
+ ret = PTR_ERR(nsdentry);
+ nsdentry = NULL;
}
+ fc->root = nsdentry;
}
if (!ctx->kfc.new_sb_created)
diff --git a/kernel/cpu.c b/kernel/cpu.c
index fc28e17940e0..e2cad3ee2ead 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2373,7 +2373,18 @@ void __init boot_cpu_hotplug_init(void)
this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
}
-enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO;
+/*
+ * These are used for a global "mitigations=" cmdline option for toggling
+ * optional CPU mitigations.
+ */
+enum cpu_mitigations {
+ CPU_MITIGATIONS_OFF,
+ CPU_MITIGATIONS_AUTO,
+ CPU_MITIGATIONS_AUTO_NOSMT,
+};
+
+static enum cpu_mitigations cpu_mitigations __ro_after_init =
+ CPU_MITIGATIONS_AUTO;
static int __init mitigations_parse_cmdline(char *arg)
{
@@ -2390,3 +2401,17 @@ static int __init mitigations_parse_cmdline(char *arg)
return 0;
}
early_param("mitigations", mitigations_parse_cmdline);
+
+/* mitigations=off */
+bool cpu_mitigations_off(void)
+{
+ return cpu_mitigations == CPU_MITIGATIONS_OFF;
+}
+EXPORT_SYMBOL_GPL(cpu_mitigations_off);
+
+/* mitigations=auto,nosmt */
+bool cpu_mitigations_auto_nosmt(void)
+{
+ return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT;
+}
+EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index aec8dba2bea4..00a014670ed0 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1031,7 +1031,7 @@ perf_cgroup_set_timestamp(struct task_struct *task,
{
}
-void
+static inline void
perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
{
}
@@ -10535,6 +10535,15 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
goto err_ns;
}
+ /*
+ * Disallow uncore-cgroup events, they don't make sense as the cgroup will
+ * be different on other CPUs in the uncore mask.
+ */
+ if (pmu->task_ctx_nr == perf_invalid_context && cgroup_fd != -1) {
+ err = -EINVAL;
+ goto err_pmu;
+ }
+
if (event->attr.aux_output &&
!(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
err = -EOPNOTSUPP;
@@ -11323,8 +11332,11 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
int err;
/*
- * Get the target context (task or percpu):
+ * Grouping is not supported for kernel events, neither is 'AUX',
+ * make sure the caller's intentions are adjusted.
*/
+ if (attr->aux_output)
+ return ERR_PTR(-EINVAL);
event = perf_event_alloc(attr, cpu, task, NULL, NULL,
overflow_handler, context, -1);
@@ -11336,6 +11348,9 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
/* Mark owner so we could distinguish it from user events. */
event->owner = TASK_TOMBSTONE;
+ /*
+ * Get the target context (task or percpu):
+ */
ctx = find_get_context(event->pmu, task, event);
if (IS_ERR(ctx)) {
err = PTR_ERR(ctx);
@@ -11787,7 +11802,7 @@ inherit_event(struct perf_event *parent_event,
GFP_KERNEL);
if (!child_ctx->task_ctx_data) {
free_event(child_event);
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
}
@@ -11890,7 +11905,7 @@ static int inherit_group(struct perf_event *parent_event,
if (IS_ERR(child_ctr))
return PTR_ERR(child_ctr);
- if (sub->aux_event == parent_event &&
+ if (sub->aux_event == parent_event && child_ctr &&
!perf_get_aux_event(child_ctr, leader))
return -EINVAL;
}
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 04e83fdfbe80..a45cba7df0ae 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -814,6 +814,8 @@ EXPORT_SYMBOL_GPL(freq_qos_update_request);
*/
int freq_qos_remove_request(struct freq_qos_request *req)
{
+ int ret;
+
if (!req)
return -EINVAL;
@@ -821,7 +823,11 @@ int freq_qos_remove_request(struct freq_qos_request *req)
"%s() called for unknown object\n", __func__))
return -EINVAL;
- return freq_qos_apply(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
+ ret = freq_qos_apply(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
+ req->qos = NULL;
+ req->type = 0;
+
+ return ret;
}
EXPORT_SYMBOL_GPL(freq_qos_remove_request);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 83105874f255..26b9168321e7 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -734,8 +734,15 @@ zone_found:
* We have found the zone. Now walk the radix tree to find the leaf node
* for our PFN.
*/
+
+ /*
+ * If the zone we wish to scan is the the current zone and the
+ * pfn falls into the current node then we do not need to walk
+ * the tree.
+ */
node = bm->cur.node;
- if (((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn)
+ if (zone == bm->cur.zone &&
+ ((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn)
goto node_found;
node = zone->rtree;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0f2eb3629070..44123b4d14e8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1065,7 +1065,7 @@ uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
* affecting a valid clamp bucket, the next time it's enqueued,
* it will already see the updated clamp bucket value.
*/
- if (!p->uclamp[clamp_id].active) {
+ if (p->uclamp[clamp_id].active) {
uclamp_rq_dec_id(rq, p, clamp_id);
uclamp_rq_inc_id(rq, p, clamp_id);
}
@@ -6019,10 +6019,11 @@ void init_idle(struct task_struct *idle, int cpu)
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
+ __sched_fork(0, idle);
+
raw_spin_lock_irqsave(&idle->pi_lock, flags);
raw_spin_lock(&rq->lock);
- __sched_fork(0, idle);
idle->state = TASK_RUNNING;
idle->se.exec_start = sched_clock();
idle->flags |= PF_IDLE;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 22a2fed29054..69a81a5709ff 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7548,6 +7548,19 @@ static void update_blocked_averages(int cpu)
update_rq_clock(rq);
/*
+ * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure
+ * that RT, DL and IRQ signals have been updated before updating CFS.
+ */
+ curr_class = rq->curr->sched_class;
+ update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
+ update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
+ update_irq_load_avg(rq, 0);
+
+ /* Don't need periodic decay once load/util_avg are null */
+ if (others_have_blocked(rq))
+ done = false;
+
+ /*
* Iterates the task_group tree in a bottom up fashion, see
* list_add_leaf_cfs_rq() for details.
*/
@@ -7574,14 +7587,6 @@ static void update_blocked_averages(int cpu)
done = false;
}
- curr_class = rq->curr->sched_class;
- update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
- update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
- update_irq_load_avg(rq, 0);
- /* Don't need periodic decay once load/util_avg are null */
- if (others_have_blocked(rq))
- done = false;
-
update_blocked_load_status(rq, !done);
rq_unlock_irqrestore(rq, &rf);
}
@@ -7642,12 +7647,18 @@ static inline void update_blocked_averages(int cpu)
rq_lock_irqsave(rq, &rf);
update_rq_clock(rq);
- update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
+ /*
+ * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure
+ * that RT, DL and IRQ signals have been updated before updating CFS.
+ */
curr_class = rq->curr->sched_class;
update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
update_irq_load_avg(rq, 0);
+
+ update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
+
update_blocked_load_status(rq, cfs_rq_has_blocked(cfs_rq) || others_have_blocked(rq));
rq_unlock_irqrestore(rq, &rf);
}
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index f65ef1e2f204..80167b1bd98a 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -104,7 +104,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
* update no idle residency and return.
*/
if (current_clr_polling_and_test()) {
- dev->last_residency = 0;
+ dev->last_residency_ns = 0;
local_irq_enable();
return -EBUSY;
}
@@ -165,7 +165,9 @@ static void cpuidle_idle_call(void)
* until a proper wakeup interrupt happens.
*/
- if (idle_should_enter_s2idle() || dev->use_deepest_state) {
+ if (idle_should_enter_s2idle() || dev->forced_idle_latency_limit_ns) {
+ u64 max_latency_ns;
+
if (idle_should_enter_s2idle()) {
rcu_idle_enter();
@@ -176,12 +178,16 @@ static void cpuidle_idle_call(void)
}
rcu_idle_exit();
+
+ max_latency_ns = U64_MAX;
+ } else {
+ max_latency_ns = dev->forced_idle_latency_limit_ns;
}
tick_nohz_idle_stop_tick();
rcu_idle_enter();
- next_state = cpuidle_find_deepest_state(drv, dev);
+ next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns);
call_cpuidle(drv, dev, next_state);
} else {
bool stop_tick = true;
@@ -311,7 +317,7 @@ static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
return HRTIMER_NORESTART;
}
-void play_idle(unsigned long duration_us)
+void play_idle_precise(u64 duration_ns, u64 latency_ns)
{
struct idle_timer it;
@@ -323,29 +329,29 @@ void play_idle(unsigned long duration_us)
WARN_ON_ONCE(current->nr_cpus_allowed != 1);
WARN_ON_ONCE(!(current->flags & PF_KTHREAD));
WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY));
- WARN_ON_ONCE(!duration_us);
+ WARN_ON_ONCE(!duration_ns);
rcu_sleep_check();
preempt_disable();
current->flags |= PF_IDLE;
- cpuidle_use_deepest_state(true);
+ cpuidle_use_deepest_state(latency_ns);
it.done = 0;
hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
it.timer.function = idle_inject_timer_fn;
- hrtimer_start(&it.timer, ns_to_ktime(duration_us * NSEC_PER_USEC),
+ hrtimer_start(&it.timer, ns_to_ktime(duration_ns),
HRTIMER_MODE_REL_PINNED);
while (!READ_ONCE(it.done))
do_idle();
- cpuidle_use_deepest_state(false);
+ cpuidle_use_deepest_state(0);
current->flags &= ~PF_IDLE;
preempt_fold_need_resched();
preempt_enable();
}
-EXPORT_SYMBOL_GPL(play_idle);
+EXPORT_SYMBOL_GPL(play_idle_precise);
void cpu_startup_entry(enum cpuhp_state state)
{
diff --git a/kernel/signal.c b/kernel/signal.c
index c4da1ef56fdf..bcd46f547db3 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2205,8 +2205,8 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t
*/
preempt_disable();
read_unlock(&tasklist_lock);
- preempt_enable_no_resched();
cgroup_enter_frozen();
+ preempt_enable_no_resched();
freezable_schedule();
cgroup_leave_frozen(true);
} else {
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 65eb796610dc..069ca78fb0bf 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -771,7 +771,7 @@ int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts,
/* fill PPS status fields */
pps_fill_timex(txc);
- txc->time.tv_sec = (time_t)ts->tv_sec;
+ txc->time.tv_sec = ts->tv_sec;
txc->time.tv_usec = ts->tv_nsec;
if (!(time_status & STA_NANO))
txc->time.tv_usec = ts->tv_nsec / NSEC_PER_USEC;