aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/cgroup/cgroup.c15
-rw-r--r--kernel/cgroup/pids.c4
-rw-r--r--kernel/cpu.c9
-rw-r--r--kernel/exit.c1
-rw-r--r--kernel/irq/chip.c16
-rw-r--r--kernel/irq/internals.h8
-rw-r--r--kernel/irq/irqdesc.c8
-rw-r--r--kernel/sched/debug.c4
-rw-r--r--kernel/sched/fair.c6
-rw-r--r--kernel/sched/topology.c2
-rw-r--r--kernel/sysctl.c3
-rw-r--r--kernel/time/alarmtimer.c2
-rw-r--r--kernel/trace/ring_buffer.c5
-rw-r--r--kernel/trace/trace.c6
-rw-r--r--kernel/trace/trace_kdb.c6
15 files changed, 72 insertions, 23 deletions
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 7e79358b4473..694b1cc8d144 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -187,7 +187,7 @@ static u64 css_serial_nr_next = 1;
*/
static u16 have_fork_callback __read_mostly;
static u16 have_exit_callback __read_mostly;
-static u16 have_free_callback __read_mostly;
+static u16 have_release_callback __read_mostly;
static u16 have_canfork_callback __read_mostly;
/* cgroup namespace for init task */
@@ -5112,7 +5112,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
have_fork_callback |= (bool)ss->fork << ss->id;
have_exit_callback |= (bool)ss->exit << ss->id;
- have_free_callback |= (bool)ss->free << ss->id;
+ have_release_callback |= (bool)ss->release << ss->id;
have_canfork_callback |= (bool)ss->can_fork << ss->id;
/* At system boot, before all subsystems have been
@@ -5546,16 +5546,19 @@ void cgroup_exit(struct task_struct *tsk)
} while_each_subsys_mask();
}
-void cgroup_free(struct task_struct *task)
+void cgroup_release(struct task_struct *task)
{
- struct css_set *cset = task_css_set(task);
struct cgroup_subsys *ss;
int ssid;
- do_each_subsys_mask(ss, ssid, have_free_callback) {
- ss->free(task);
+ do_each_subsys_mask(ss, ssid, have_release_callback) {
+ ss->release(task);
} while_each_subsys_mask();
+}
+void cgroup_free(struct task_struct *task)
+{
+ struct css_set *cset = task_css_set(task);
put_css_set(cset);
}
diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c
index 9829c67ebc0a..c9960baaa14f 100644
--- a/kernel/cgroup/pids.c
+++ b/kernel/cgroup/pids.c
@@ -247,7 +247,7 @@ static void pids_cancel_fork(struct task_struct *task)
pids_uncharge(pids, 1);
}
-static void pids_free(struct task_struct *task)
+static void pids_release(struct task_struct *task)
{
struct pids_cgroup *pids = css_pids(task_css(task, pids_cgrp_id));
@@ -342,7 +342,7 @@ struct cgroup_subsys pids_cgrp_subsys = {
.cancel_attach = pids_cancel_attach,
.can_fork = pids_can_fork,
.cancel_fork = pids_cancel_fork,
- .free = pids_free,
+ .release = pids_release,
.legacy_cftypes = pids_files,
.dfl_cftypes = pids_files,
.threaded = true,
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 32f0432f0c26..8c350dd81581 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -314,6 +314,15 @@ void cpus_write_unlock(void)
void lockdep_assert_cpus_held(void)
{
+ /*
+ * We can't have hotplug operations before userspace starts running,
+ * and some init codepaths will knowingly not take the hotplug lock.
+ * This is all valid, so mute lockdep until it makes sense to report
+ * unheld locks.
+ */
+ if (system_state < SYSTEM_RUNNING)
+ return;
+
percpu_rwsem_assert_held(&cpu_hotplug_lock);
}
diff --git a/kernel/exit.c b/kernel/exit.c
index 5523fb0c20c8..95ce231ff5e2 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -218,6 +218,7 @@ repeat:
}
write_unlock_irq(&tasklist_lock);
+ cgroup_release(p);
release_thread(p);
call_rcu(&p->rcu, delayed_put_task_struct);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 5a2ef92c2782..317fc759de76 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -834,7 +834,11 @@ void handle_percpu_irq(struct irq_desc *desc)
{
struct irq_chip *chip = irq_desc_get_chip(desc);
- kstat_incr_irqs_this_cpu(desc);
+ /*
+ * PER CPU interrupts are not serialized. Do not touch
+ * desc->tot_count.
+ */
+ __kstat_incr_irqs_this_cpu(desc);
if (chip->irq_ack)
chip->irq_ack(&desc->irq_data);
@@ -863,7 +867,11 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
unsigned int irq = irq_desc_get_irq(desc);
irqreturn_t res;
- kstat_incr_irqs_this_cpu(desc);
+ /*
+ * PER CPU interrupts are not serialized. Do not touch
+ * desc->tot_count.
+ */
+ __kstat_incr_irqs_this_cpu(desc);
if (chip->irq_ack)
chip->irq_ack(&desc->irq_data);
@@ -1355,6 +1363,10 @@ int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info)
int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on)
{
data = data->parent_data;
+
+ if (data->chip->flags & IRQCHIP_SKIP_SET_WAKE)
+ return 0;
+
if (data->chip->irq_set_wake)
return data->chip->irq_set_wake(data, on);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 44ed5f8c8759..4ef7f3b820ce 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -240,12 +240,18 @@ static inline void irq_state_set_masked(struct irq_desc *desc)
#undef __irqd_to_state
-static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
+static inline void __kstat_incr_irqs_this_cpu(struct irq_desc *desc)
{
__this_cpu_inc(*desc->kstat_irqs);
__this_cpu_inc(kstat.irqs_sum);
}
+static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
+{
+ __kstat_incr_irqs_this_cpu(desc);
+ desc->tot_count++;
+}
+
static inline int irq_desc_get_node(struct irq_desc *desc)
{
return irq_common_data_get_node(&desc->irq_common_data);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index e97bbae947f0..aa08d4184608 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -119,6 +119,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
desc->depth = 1;
desc->irq_count = 0;
desc->irqs_unhandled = 0;
+ desc->tot_count = 0;
desc->name = NULL;
desc->owner = owner;
for_each_possible_cpu(cpu)
@@ -534,6 +535,7 @@ int __init early_irq_init(void)
alloc_masks(&desc[i], node);
raw_spin_lock_init(&desc[i].lock);
lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
+ mutex_init(&desc[i].request_mutex);
desc_set_defaults(i, &desc[i], node, NULL, NULL);
}
return arch_early_irq_init();
@@ -895,11 +897,15 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
unsigned int kstat_irqs(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
- int cpu;
unsigned int sum = 0;
+ int cpu;
if (!desc || !desc->kstat_irqs)
return 0;
+ if (!irq_settings_is_per_cpu_devid(desc) &&
+ !irq_settings_is_per_cpu(desc))
+ return desc->tot_count;
+
for_each_possible_cpu(cpu)
sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
return sum;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 2f93e4a2d9f6..187c04a34ba1 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -339,6 +339,7 @@ void register_sched_domain_sysctl(void)
{
static struct ctl_table *cpu_entries;
static struct ctl_table **cpu_idx;
+ static bool init_done = false;
char buf[32];
int i;
@@ -368,7 +369,10 @@ void register_sched_domain_sysctl(void)
if (!cpumask_available(sd_sysctl_cpus)) {
if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
return;
+ }
+ if (!init_done) {
+ init_done = true;
/* init to possible to not have holes in @cpu_entries */
cpumask_copy(sd_sysctl_cpus, cpu_possible_mask);
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4d54c1fe9623..9829ede00498 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7018,10 +7018,10 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
if (cfs_rq->last_h_load_update == now)
return;
- cfs_rq->h_load_next = NULL;
+ WRITE_ONCE(cfs_rq->h_load_next, NULL);
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
- cfs_rq->h_load_next = se;
+ WRITE_ONCE(cfs_rq->h_load_next, se);
if (cfs_rq->last_h_load_update == now)
break;
}
@@ -7031,7 +7031,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
cfs_rq->last_h_load_update = now;
}
- while ((se = cfs_rq->h_load_next) != NULL) {
+ while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) {
load = cfs_rq->h_load;
load = div64_ul(load * se->avg.load_avg,
cfs_rq_load_avg(cfs_rq) + 1);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 659e075ef70b..9dcd80ed9d4c 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -499,7 +499,7 @@ static int __init isolated_cpu_setup(char *str)
__setup("isolcpus=", isolated_cpu_setup);
struct s_data {
- struct sched_domain ** __percpu sd;
+ struct sched_domain * __percpu *sd;
struct root_domain *rd;
};
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index a7acb058b776..34a3b8a262a9 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -125,6 +125,7 @@ static int __maybe_unused one = 1;
static int __maybe_unused two = 2;
static int __maybe_unused four = 4;
static unsigned long one_ul = 1;
+static unsigned long long_max = LONG_MAX;
static int one_hundred = 100;
static int one_thousand = 1000;
#ifdef CONFIG_PRINTK
@@ -1681,6 +1682,8 @@ static struct ctl_table fs_table[] = {
.maxlen = sizeof(files_stat.max_files),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &long_max,
},
{
.procname = "nr_open",
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index fa5de5e8de61..fdeb9bc6affb 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -597,7 +597,7 @@ static ktime_t alarm_timer_remaining(struct k_itimer *timr, ktime_t now)
{
struct alarm *alarm = &timr->it.alarm.alarmtimer;
- return ktime_sub(now, alarm->node.expires);
+ return ktime_sub(alarm->node.expires, now);
}
/**
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a1d5e0949dcf..5f7f4f07499f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -4010,6 +4010,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume);
* ring_buffer_read_prepare - Prepare for a non consuming read of the buffer
* @buffer: The ring buffer to read from
* @cpu: The cpu buffer to iterate over
+ * @flags: gfp flags to use for memory allocation
*
* This performs the initial preparations necessary to iterate
* through the buffer. Memory is allocated, buffer recording
@@ -4027,7 +4028,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume);
* This overall must be paired with ring_buffer_read_finish.
*/
struct ring_buffer_iter *
-ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu)
+ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu, gfp_t flags)
{
struct ring_buffer_per_cpu *cpu_buffer;
struct ring_buffer_iter *iter;
@@ -4035,7 +4036,7 @@ ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu)
if (!cpumask_test_cpu(cpu, buffer->cpumask))
return NULL;
- iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+ iter = kmalloc(sizeof(*iter), flags);
if (!iter)
return NULL;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 287e61aba57c..ffddb5ac255c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3901,7 +3901,8 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
if (iter->cpu_file == RING_BUFFER_ALL_CPUS) {
for_each_tracing_cpu(cpu) {
iter->buffer_iter[cpu] =
- ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu);
+ ring_buffer_read_prepare(iter->trace_buffer->buffer,
+ cpu, GFP_KERNEL);
}
ring_buffer_read_prepare_sync();
for_each_tracing_cpu(cpu) {
@@ -3911,7 +3912,8 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
} else {
cpu = iter->cpu_file;
iter->buffer_iter[cpu] =
- ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu);
+ ring_buffer_read_prepare(iter->trace_buffer->buffer,
+ cpu, GFP_KERNEL);
ring_buffer_read_prepare_sync();
ring_buffer_read_start(iter->buffer_iter[cpu]);
tracing_iter_reset(iter, cpu);
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index d953c163a079..810d78a8d14c 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -51,14 +51,16 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file)
if (cpu_file == RING_BUFFER_ALL_CPUS) {
for_each_tracing_cpu(cpu) {
iter.buffer_iter[cpu] =
- ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu);
+ ring_buffer_read_prepare(iter.trace_buffer->buffer,
+ cpu, GFP_ATOMIC);
ring_buffer_read_start(iter.buffer_iter[cpu]);
tracing_iter_reset(&iter, cpu);
}
} else {
iter.cpu_file = cpu_file;
iter.buffer_iter[cpu_file] =
- ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu_file);
+ ring_buffer_read_prepare(iter.trace_buffer->buffer,
+ cpu_file, GFP_ATOMIC);
ring_buffer_read_start(iter.buffer_iter[cpu_file]);
tracing_iter_reset(&iter, cpu_file);
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-01 01:33:01 +0000