summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit.c2
-rw-r--r--kernel/audit_tree.c1
-rw-r--r--kernel/cpu.c19
-rw-r--r--kernel/events/uprobes.c1
-rw-r--r--kernel/fork.c5
-rw-r--r--kernel/panic.c1
-rw-r--r--kernel/power/suspend.c4
-rw-r--r--kernel/rcu/Makefile2
-rw-r--r--kernel/rcu/rcu.h2
-rw-r--r--kernel/rcu/rcutorture.c1
-rw-r--r--kernel/rcu/tiny.c6
-rw-r--r--kernel/rcu/tree.c97
-rw-r--r--kernel/rcu/tree.h22
-rw-r--r--kernel/rcu/tree_plugin.h111
-rw-r--r--kernel/rcu/update.c89
-rw-r--r--kernel/sched/core.c73
-rw-r--r--kernel/sched/deadline.c2
-rw-r--r--kernel/sched/fair.c14
-rw-r--r--kernel/sched/idle_task.c5
-rw-r--r--kernel/sched/rt.c2
-rw-r--r--kernel/sched/sched.h2
-rw-r--r--kernel/sched/stop_task.c5
-rw-r--r--kernel/signal.c42
-rw-r--r--kernel/softirq.c2
-rw-r--r--kernel/time/posix-cpu-timers.c2
-rw-r--r--kernel/time/tick-sched.c2
-rw-r--r--kernel/time/timer.c3
-rw-r--r--kernel/trace/ring_buffer.c81
-rw-r--r--kernel/trace/trace.c33
29 files changed, 400 insertions, 231 deletions
diff --git a/kernel/audit.c b/kernel/audit.c
index 80983df92cd4..cebb11db4d34 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -739,7 +739,7 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE);
audit_log_task_info(ab, current);
- audit_log_format(ab, "feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d",
+ audit_log_format(ab, " feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d",
audit_feature_names[which], !!old_feature, !!new_feature,
!!old_lock, !!new_lock, res);
audit_log_end(ab);
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index e242e3a9864a..80f29e015570 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -154,6 +154,7 @@ static struct audit_chunk *alloc_chunk(int count)
chunk->owners[i].index = i;
}
fsnotify_init_mark(&chunk->mark, audit_tree_destroy_watch);
+ chunk->mark.mask = FS_IN_IGNORED;
return chunk;
}
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 90a3d017b90c..5d220234b3ca 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -86,6 +86,16 @@ static struct {
#define cpuhp_lock_acquire() lock_map_acquire(&cpu_hotplug.dep_map)
#define cpuhp_lock_release() lock_map_release(&cpu_hotplug.dep_map)
+static void apply_puts_pending(int max)
+{
+ int delta;
+
+ if (atomic_read(&cpu_hotplug.puts_pending) >= max) {
+ delta = atomic_xchg(&cpu_hotplug.puts_pending, 0);
+ cpu_hotplug.refcount -= delta;
+ }
+}
+
void get_online_cpus(void)
{
might_sleep();
@@ -93,6 +103,7 @@ void get_online_cpus(void)
return;
cpuhp_lock_acquire_read();
mutex_lock(&cpu_hotplug.lock);
+ apply_puts_pending(65536);
cpu_hotplug.refcount++;
mutex_unlock(&cpu_hotplug.lock);
}
@@ -105,6 +116,7 @@ bool try_get_online_cpus(void)
if (!mutex_trylock(&cpu_hotplug.lock))
return false;
cpuhp_lock_acquire_tryread();
+ apply_puts_pending(65536);
cpu_hotplug.refcount++;
mutex_unlock(&cpu_hotplug.lock);
return true;
@@ -161,12 +173,7 @@ void cpu_hotplug_begin(void)
cpuhp_lock_acquire();
for (;;) {
mutex_lock(&cpu_hotplug.lock);
- if (atomic_read(&cpu_hotplug.puts_pending)) {
- int delta;
-
- delta = atomic_xchg(&cpu_hotplug.puts_pending, 0);
- cpu_hotplug.refcount -= delta;
- }
+ apply_puts_pending(1);
if (likely(!cpu_hotplug.refcount))
break;
__set_current_state(TASK_UNINTERRUPTIBLE);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 1d0af8a2c646..ed8f2cde34c5 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1640,7 +1640,6 @@ bool uprobe_deny_signal(void)
if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) {
utask->state = UTASK_SSTEP_TRAPPED;
set_tsk_thread_flag(t, TIF_UPROBE);
- set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
}
}
diff --git a/kernel/fork.c b/kernel/fork.c
index 9b7d746d6d62..9ca84189cfc2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1022,11 +1022,14 @@ void __cleanup_sighand(struct sighand_struct *sighand)
{
if (atomic_dec_and_test(&sighand->count)) {
signalfd_cleanup(sighand);
+ /*
+ * sighand_cachep is SLAB_DESTROY_BY_RCU so we can free it
+ * without an RCU grace period, see __lock_task_sighand().
+ */
kmem_cache_free(sighand_cachep, sighand);
}
}
-
/*
* Initialize POSIX timer handling for a thread group.
*/
diff --git a/kernel/panic.c b/kernel/panic.c
index d09dc5c32c67..cf80672b7924 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -244,6 +244,7 @@ static const struct tnt tnts[] = {
* 'I' - Working around severe firmware bug.
* 'O' - Out-of-tree module has been loaded.
* 'E' - Unsigned module has been loaded.
+ * 'L' - A soft lockup has previously occurred.
*
* The string is overwritten by the next call to print_tainted().
*/
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 4ca9a33ff620..c347e3ce3a55 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -146,7 +146,7 @@ static int platform_suspend_prepare(suspend_state_t state)
static int platform_suspend_prepare_late(suspend_state_t state)
{
- return state == PM_SUSPEND_FREEZE && freeze_ops->prepare ?
+ return state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->prepare ?
freeze_ops->prepare() : 0;
}
@@ -164,7 +164,7 @@ static void platform_resume_noirq(suspend_state_t state)
static void platform_resume_early(suspend_state_t state)
{
- if (state == PM_SUSPEND_FREEZE && freeze_ops->restore)
+ if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->restore)
freeze_ops->restore();
}
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 807ccfbf69b3..e6fae503d1bc 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -1,6 +1,6 @@
obj-y += update.o srcu.o
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
obj-$(CONFIG_TREE_RCU) += tree.o
-obj-$(CONFIG_TREE_PREEMPT_RCU) += tree.o
+obj-$(CONFIG_PREEMPT_RCU) += tree.o
obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o
obj-$(CONFIG_TINY_RCU) += tiny.o
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index ff1a6de62f17..07bb02eda844 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -135,4 +135,6 @@ int rcu_jiffies_till_stall_check(void);
*/
#define TPS(x) tracepoint_string(x)
+void rcu_early_boot_tests(void);
+
#endif /* __LINUX_RCU_H */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 240fa9094f83..4d559baf06e0 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -812,6 +812,7 @@ rcu_torture_cbflood(void *arg)
cur_ops->cb_barrier();
stutter_wait("rcu_torture_cbflood");
} while (!torture_must_stop());
+ vfree(rhp);
torture_kthread_stopping("rcu_torture_cbflood");
return 0;
}
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index c0623fc47125..0db5649f8817 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -247,7 +247,7 @@ void rcu_bh_qs(void)
* be called from hardirq context. It is normally called from the
* scheduling-clock interrupt.
*/
-void rcu_check_callbacks(int cpu, int user)
+void rcu_check_callbacks(int user)
{
RCU_TRACE(check_cpu_stalls());
if (user || rcu_is_cpu_rrupt_from_idle())
@@ -380,7 +380,9 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
}
EXPORT_SYMBOL_GPL(call_rcu_bh);
-void rcu_init(void)
+void __init rcu_init(void)
{
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+
+ rcu_early_boot_tests();
}
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 9815447d22e0..7680fc275036 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -105,7 +105,7 @@ struct rcu_state sname##_state = { \
.name = RCU_STATE_NAME(sname), \
.abbr = sabbr, \
}; \
-DEFINE_PER_CPU(struct rcu_data, sname##_data)
+DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data)
RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
@@ -152,19 +152,6 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active);
*/
static int rcu_scheduler_fully_active __read_mostly;
-#ifdef CONFIG_RCU_BOOST
-
-/*
- * Control variables for per-CPU and per-rcu_node kthreads. These
- * handle all flavors of RCU.
- */
-static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
-DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
-DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
-DEFINE_PER_CPU(char, rcu_cpu_has_work);
-
-#endif /* #ifdef CONFIG_RCU_BOOST */
-
static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
static void invoke_rcu_core(void);
static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
@@ -286,11 +273,11 @@ static void rcu_momentary_dyntick_idle(void)
* and requires special handling for preemptible RCU.
* The caller must have disabled preemption.
*/
-void rcu_note_context_switch(int cpu)
+void rcu_note_context_switch(void)
{
trace_rcu_utilization(TPS("Start context switch"));
rcu_sched_qs();
- rcu_preempt_note_context_switch(cpu);
+ rcu_preempt_note_context_switch();
if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
rcu_momentary_dyntick_idle();
trace_rcu_utilization(TPS("End context switch"));
@@ -325,7 +312,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
unsigned long *maxj),
bool *isidle, unsigned long *maxj);
static void force_quiescent_state(struct rcu_state *rsp);
-static int rcu_pending(int cpu);
+static int rcu_pending(void);
/*
* Return the number of RCU-sched batches processed thus far for debug & stats.
@@ -510,11 +497,11 @@ cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
* we really have entered idle, and must do the appropriate accounting.
* The caller must have disabled interrupts.
*/
-static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
- bool user)
+static void rcu_eqs_enter_common(long long oldval, bool user)
{
struct rcu_state *rsp;
struct rcu_data *rdp;
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
if (!user && !is_idle_task(current)) {
@@ -531,7 +518,7 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
rdp = this_cpu_ptr(rsp->rda);
do_nocb_deferred_wakeup(rdp);
}
- rcu_prepare_for_idle(smp_processor_id());
+ rcu_prepare_for_idle();
/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
smp_mb__before_atomic(); /* See above. */
atomic_inc(&rdtp->dynticks);
@@ -565,7 +552,7 @@ static void rcu_eqs_enter(bool user)
WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
rdtp->dynticks_nesting = 0;
- rcu_eqs_enter_common(rdtp, oldval, user);
+ rcu_eqs_enter_common(oldval, user);
} else {
rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
}
@@ -589,7 +576,7 @@ void rcu_idle_enter(void)
local_irq_save(flags);
rcu_eqs_enter(false);
- rcu_sysidle_enter(this_cpu_ptr(&rcu_dynticks), 0);
+ rcu_sysidle_enter(0);
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(rcu_idle_enter);
@@ -639,8 +626,8 @@ void rcu_irq_exit(void)
if (rdtp->dynticks_nesting)
trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting);
else
- rcu_eqs_enter_common(rdtp, oldval, true);
- rcu_sysidle_enter(rdtp, 1);
+ rcu_eqs_enter_common(oldval, true);
+ rcu_sysidle_enter(1);
local_irq_restore(flags);
}
@@ -651,16 +638,17 @@ void rcu_irq_exit(void)
* we really have exited idle, and must do the appropriate accounting.
* The caller must have disabled interrupts.
*/
-static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval,
- int user)
+static void rcu_eqs_exit_common(long long oldval, int user)
{
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+
rcu_dynticks_task_exit();
smp_mb__before_atomic(); /* Force ordering w/previous sojourn. */
atomic_inc(&rdtp->dynticks);
/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
smp_mb__after_atomic(); /* See above. */
WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
- rcu_cleanup_after_idle(smp_processor_id());
+ rcu_cleanup_after_idle();
trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting);
if (!user && !is_idle_task(current)) {
struct task_struct *idle __maybe_unused =
@@ -691,7 +679,7 @@ static void rcu_eqs_exit(bool user)
rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
} else {
rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
- rcu_eqs_exit_common(rdtp, oldval, user);
+ rcu_eqs_exit_common(oldval, user);
}
}
@@ -712,7 +700,7 @@ void rcu_idle_exit(void)
local_irq_save(flags);
rcu_eqs_exit(false);
- rcu_sysidle_exit(this_cpu_ptr(&rcu_dynticks), 0);
+ rcu_sysidle_exit(0);
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(rcu_idle_exit);
@@ -763,8 +751,8 @@ void rcu_irq_enter(void)
if (oldval)
trace_rcu_dyntick(TPS("++="), oldval, rdtp->dynticks_nesting);
else
- rcu_eqs_exit_common(rdtp, oldval, true);
- rcu_sysidle_exit(rdtp, 1);
+ rcu_eqs_exit_common(oldval, true);
+ rcu_sysidle_exit(1);
local_irq_restore(flags);
}
@@ -2387,7 +2375,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
* invoked from the scheduling-clock interrupt. If rcu_pending returns
* false, there is no point in invoking rcu_check_callbacks().
*/
-void rcu_check_callbacks(int cpu, int user)
+void rcu_check_callbacks(int user)
{
trace_rcu_utilization(TPS("Start scheduler-tick"));
increment_cpu_stall_ticks();
@@ -2419,8 +2407,8 @@ void rcu_check_callbacks(int cpu, int user)
rcu_bh_qs();
}
- rcu_preempt_check_callbacks(cpu);
- if (rcu_pending(cpu))
+ rcu_preempt_check_callbacks();
+ if (rcu_pending())
invoke_rcu_core();
if (user)
rcu_note_voluntary_context_switch(current);
@@ -2963,6 +2951,9 @@ static int synchronize_sched_expedited_cpu_stop(void *data)
*/
void synchronize_sched_expedited(void)
{
+ cpumask_var_t cm;
+ bool cma = false;
+ int cpu;
long firstsnap, s, snap;
int trycount = 0;
struct rcu_state *rsp = &rcu_sched_state;
@@ -2997,11 +2988,26 @@ void synchronize_sched_expedited(void)
}
WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id()));
+ /* Offline CPUs, idle CPUs, and any CPU we run on are quiescent. */
+ cma = zalloc_cpumask_var(&cm, GFP_KERNEL);
+ if (cma) {
+ cpumask_copy(cm, cpu_online_mask);
+ cpumask_clear_cpu(raw_smp_processor_id(), cm);
+ for_each_cpu(cpu, cm) {
+ struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+ if (!(atomic_add_return(0, &rdtp->dynticks) & 0x1))
+ cpumask_clear_cpu(cpu, cm);
+ }
+ if (cpumask_weight(cm) == 0)
+ goto all_cpus_idle;
+ }
+
/*
* Each pass through the following loop attempts to force a
* context switch on each CPU.
*/
- while (try_stop_cpus(cpu_online_mask,
+ while (try_stop_cpus(cma ? cm : cpu_online_mask,
synchronize_sched_expedited_cpu_stop,
NULL) == -EAGAIN) {
put_online_cpus();
@@ -3013,6 +3019,7 @@ void synchronize_sched_expedited(void)
/* ensure test happens before caller kfree */
smp_mb__before_atomic(); /* ^^^ */
atomic_long_inc(&rsp->expedited_workdone1);
+ free_cpumask_var(cm);
return;
}
@@ -3022,6 +3029,7 @@ void synchronize_sched_expedited(void)
} else {
wait_rcu_gp(call_rcu_sched);
atomic_long_inc(&rsp->expedited_normal);
+ free_cpumask_var(cm);
return;
}
@@ -3031,6 +3039,7 @@ void synchronize_sched_expedited(void)
/* ensure test happens before caller kfree */
smp_mb__before_atomic(); /* ^^^ */
atomic_long_inc(&rsp->expedited_workdone2);
+ free_cpumask_var(cm);
return;
}
@@ -3045,6 +3054,7 @@ void synchronize_sched_expedited(void)
/* CPU hotplug operation in flight, use normal GP. */
wait_rcu_gp(call_rcu_sched);
atomic_long_inc(&rsp->expedited_normal);
+ free_cpumask_var(cm);
return;
}
snap = atomic_long_read(&rsp->expedited_start);
@@ -3052,6 +3062,9 @@ void synchronize_sched_expedited(void)
}
atomic_long_inc(&rsp->expedited_stoppedcpus);
+all_cpus_idle:
+ free_cpumask_var(cm);
+
/*
* Everyone up to our most recent fetch is covered by our grace
* period. Update the counter, but only if our work is still
@@ -3143,12 +3156,12 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
* by the current CPU, returning 1 if so. This function is part of the
* RCU implementation; it is -not- an exported member of the RCU API.
*/
-static int rcu_pending(int cpu)
+static int rcu_pending(void)
{
struct rcu_state *rsp;
for_each_rcu_flavor(rsp)
- if (__rcu_pending(rsp, per_cpu_ptr(rsp->rda, cpu)))
+ if (__rcu_pending(rsp, this_cpu_ptr(rsp->rda)))
return 1;
return 0;
}
@@ -3158,7 +3171,7 @@ static int rcu_pending(int cpu)
* non-NULL, store an indication of whether all callbacks are lazy.
* (If there are no callbacks, all of them are deemed to be lazy.)
*/
-static int __maybe_unused rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
+static int __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
{
bool al = true;
bool hc = false;
@@ -3166,7 +3179,7 @@ static int __maybe_unused rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
struct rcu_state *rsp;
for_each_rcu_flavor(rsp) {
- rdp = per_cpu_ptr(rsp->rda, cpu);
+ rdp = this_cpu_ptr(rsp->rda);
if (!rdp->nxtlist)
continue;
hc = true;
@@ -3485,8 +3498,10 @@ static int rcu_cpu_notify(struct notifier_block *self,
case CPU_DEAD_FROZEN:
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
- for_each_rcu_flavor(rsp)
+ for_each_rcu_flavor(rsp) {
rcu_cleanup_dead_cpu(cpu, rsp);
+ do_nocb_deferred_wakeup(per_cpu_ptr(rsp->rda, cpu));
+ }
break;
default:
break;
@@ -3766,6 +3781,8 @@ void __init rcu_init(void)
pm_notifier(rcu_pm_notify, 0);
for_each_online_cpu(cpu)
rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
+
+ rcu_early_boot_tests();
}
#include "tree_plugin.h"
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index bbdc45d8d74f..8e7b1843896e 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -139,7 +139,7 @@ struct rcu_node {
unsigned long expmask; /* Groups that have ->blkd_tasks */
/* elements that need to drain to allow the */
/* current expedited grace period to */
- /* complete (only for TREE_PREEMPT_RCU). */
+ /* complete (only for PREEMPT_RCU). */
unsigned long qsmaskinit;
/* Per-GP initial value for qsmask & expmask. */
unsigned long grpmask; /* Mask to apply to parent qsmask. */
@@ -530,10 +530,10 @@ DECLARE_PER_CPU(struct rcu_data, rcu_sched_data);
extern struct rcu_state rcu_bh_state;
DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
extern struct rcu_state rcu_preempt_state;
DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
-#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST
DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
@@ -547,7 +547,7 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work);
/* Forward declarations for rcutree_plugin.h */
static void rcu_bootup_announce(void);
long rcu_batches_completed(void);
-static void rcu_preempt_note_context_switch(int cpu);
+static void rcu_preempt_note_context_switch(void);
static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
#ifdef CONFIG_HOTPLUG_CPU
static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
@@ -561,12 +561,12 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
struct rcu_node *rnp,
struct rcu_data *rdp);
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-static void rcu_preempt_check_callbacks(int cpu);
+static void rcu_preempt_check_callbacks(void);
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
-#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU)
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PREEMPT_RCU)
static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
bool wake);
-#endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */
+#endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PREEMPT_RCU) */
static void __init __rcu_init_preempt(void);
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
@@ -579,8 +579,8 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
#endif /* #ifdef CONFIG_RCU_BOOST */
static void __init rcu_spawn_boost_kthreads(void);
static void rcu_prepare_kthreads(int cpu);
-static void rcu_cleanup_after_idle(int cpu);
-static void rcu_prepare_for_idle(int cpu);
+static void rcu_cleanup_after_idle(void);
+static void rcu_prepare_for_idle(void);
static void rcu_idle_count_callbacks_posted(void);
static void print_cpu_stall_info_begin(void);
static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
@@ -606,8 +606,8 @@ static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp);
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
static void __maybe_unused rcu_kick_nohz_cpu(int cpu);
static bool init_nocb_callback_list(struct rcu_data *rdp);
-static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq);
-static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq);
+static void rcu_sysidle_enter(int irq);
+static void rcu_sysidle_exit(int irq);
static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
unsigned long *maxj);
static bool is_sysidle_rcu_state(struct rcu_state *rsp);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index c1d7f27bd38f..3ec85cb5d544 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -30,14 +30,24 @@
#include <linux/smpboot.h>
#include "../time/tick-internal.h"
-#define RCU_KTHREAD_PRIO 1
-
#ifdef CONFIG_RCU_BOOST
+
#include "../locking/rtmutex_common.h"
-#define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO
-#else
-#define RCU_BOOST_PRIO RCU_KTHREAD_PRIO
-#endif
+
+/* rcuc/rcub kthread realtime priority */
+static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO;
+module_param(kthread_prio, int, 0644);
+
+/*
+ * Control variables for per-CPU and per-rcu_node kthreads. These
+ * handle all flavors of RCU.
+ */
+static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
+DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
+DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
+DEFINE_PER_CPU(char, rcu_cpu_has_work);
+
+#endif /* #ifdef CONFIG_RCU_BOOST */
#ifdef CONFIG_RCU_NOCB_CPU
static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
@@ -72,9 +82,6 @@ static void __init rcu_bootup_announce_oddness(void)
#ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE
pr_info("\tRCU torture testing starts during boot.\n");
#endif
-#if defined(CONFIG_TREE_PREEMPT_RCU) && !defined(CONFIG_RCU_CPU_STALL_VERBOSE)
- pr_info("\tDump stacks of tasks blocking RCU-preempt GP.\n");
-#endif
#if defined(CONFIG_RCU_CPU_STALL_INFO)
pr_info("\tAdditional per-CPU info printed with stalls.\n");
#endif
@@ -85,9 +92,12 @@ static void __init rcu_bootup_announce_oddness(void)
pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
if (nr_cpu_ids != NR_CPUS)
pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
+#ifdef CONFIG_RCU_BOOST
+ pr_info("\tRCU kthread priority: %d.\n", kthread_prio);
+#endif
}
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu);
static struct rcu_state *rcu_state_p = &rcu_preempt_state;
@@ -156,7 +166,7 @@ static void rcu_preempt_qs(void)
*
* Caller must disable preemption.
*/
-static void rcu_preempt_note_context_switch(int cpu)
+static void rcu_preempt_note_context_switch(void)
{
struct task_struct *t = current;
unsigned long flags;
@@ -167,7 +177,7 @@ static void rcu_preempt_note_context_switch(int cpu)
!t->rcu_read_unlock_special.b.blocked) {
/* Possibly blocking in an RCU read-side critical section. */
- rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
+ rdp = this_cpu_ptr(rcu_preempt_state.rda);
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
@@ -415,8 +425,6 @@ void rcu_read_unlock_special(struct task_struct *t)
}
}
-#ifdef CONFIG_RCU_CPU_STALL_VERBOSE
-
/*
* Dump detailed information for all tasks blocking the current RCU
* grace period on the specified rcu_node structure.
@@ -451,14 +459,6 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp)
rcu_print_detail_task_stall_rnp(rnp);
}
-#else /* #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */
-
-static void rcu_print_detail_task_stall(struct rcu_state *rsp)
-{
-}
-
-#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */
-
#ifdef CONFIG_RCU_CPU_STALL_INFO
static void rcu_print_task_stall_begin(struct rcu_node *rnp)
@@ -621,7 +621,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
*
* Caller must disable hard irqs.
*/
-static void rcu_preempt_check_callbacks(int cpu)
+static void rcu_preempt_check_callbacks(void)
{
struct task_struct *t = current;
@@ -630,8 +630,8 @@ static void rcu_preempt_check_callbacks(int cpu)
return;
}
if (t->rcu_read_lock_nesting > 0 &&
- per_cpu(rcu_preempt_data, cpu).qs_pending &&
- !per_cpu(rcu_preempt_data, cpu).passed_quiesce)
+ __this_cpu_read(rcu_preempt_data.qs_pending) &&
+ !__this_cpu_read(rcu_preempt_data.passed_quiesce))
t->rcu_read_unlock_special.b.need_qs = true;
}
@@ -919,7 +919,7 @@ void exit_rcu(void)
__rcu_read_unlock();
}
-#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+#else /* #ifdef CONFIG_PREEMPT_RCU */
static struct rcu_state *rcu_state_p = &rcu_sched_state;
@@ -945,7 +945,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed);
* Because preemptible RCU does not exist, we never have to check for
* CPUs being in quiescent states.
*/
-static void rcu_preempt_note_context_switch(int cpu)
+static void rcu_preempt_note_context_switch(void)
{
}
@@ -1017,7 +1017,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
* Because preemptible RCU does not exist, it never has any callbacks
* to check.
*/
-static void rcu_preempt_check_callbacks(int cpu)
+static void rcu_preempt_check_callbacks(void)
{
}
@@ -1070,7 +1070,7 @@ void exit_rcu(void)
{
}
-#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST
@@ -1326,7 +1326,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
smp_mb__after_unlock_lock();
rnp->boost_kthread_task = t;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
- sp.sched_priority = RCU_BOOST_PRIO;
+ sp.sched_priority = kthread_prio;
sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
return 0;
@@ -1343,7 +1343,7 @@ static void rcu_cpu_kthread_setup(unsigned int cpu)
{
struct sched_param sp;
- sp.sched_priority = RCU_KTHREAD_PRIO;
+ sp.sched_priority = kthread_prio;
sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
}
@@ -1512,10 +1512,10 @@ static void rcu_prepare_kthreads(int cpu)
* any flavor of RCU.
*/
#ifndef CONFIG_RCU_NOCB_CPU_ALL
-int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
+int rcu_needs_cpu(unsigned long *delta_jiffies)
{
*delta_jiffies = ULONG_MAX;
- return rcu_cpu_has_callbacks(cpu, NULL);
+ return rcu_cpu_has_callbacks(NULL);
}
#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
@@ -1523,7 +1523,7 @@ int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
* Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
* after it.
*/
-static void rcu_cleanup_after_idle(int cpu)
+static void rcu_cleanup_after_idle(void)
{
}
@@ -1531,7 +1531,7 @@ static void rcu_cleanup_after_idle(int cpu)
* Do the idle-entry grace-period work, which, because CONFIG_RCU_FAST_NO_HZ=n,
* is nothing.
*/
-static void rcu_prepare_for_idle(int cpu)
+static void rcu_prepare_for_idle(void)
{
}
@@ -1624,15 +1624,15 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
* The caller must have disabled interrupts.
*/
#ifndef CONFIG_RCU_NOCB_CPU_ALL
-int rcu_needs_cpu(int cpu, unsigned long *dj)
+int rcu_needs_cpu(unsigned long *dj)
{
- struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
/* Snapshot to detect later posting of non-lazy callback. */
rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
/* If no callbacks, RCU doesn't need the CPU. */
- if (!rcu_cpu_has_callbacks(cpu, &rdtp->all_lazy)) {
+ if (!rcu_cpu_has_callbacks(&rdtp->all_lazy)) {
*dj = ULONG_MAX;
return 0;
}
@@ -1666,12 +1666,12 @@ int rcu_needs_cpu(int cpu, unsigned long *dj)
*
* The caller must have disabled interrupts.
*/
-static void rcu_prepare_for_idle(int cpu)
+static void rcu_prepare_for_idle(void)
{
#ifndef CONFIG_RCU_NOCB_CPU_ALL
bool needwake;
struct rcu_data *rdp;
- struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
struct rcu_node *rnp;
struct rcu_state *rsp;
int tne;
@@ -1679,7 +1679,7 @@ static void rcu_prepare_for_idle(int cpu)
/* Handle nohz enablement switches conservatively. */
tne = ACCESS_ONCE(tick_nohz_active);
if (tne != rdtp->tick_nohz_enabled_snap) {
- if (rcu_cpu_has_callbacks(cpu, NULL))
+ if (rcu_cpu_has_callbacks(NULL))
invoke_rcu_core(); /* force nohz to see update. */
rdtp->tick_nohz_enabled_snap = tne;
return;
@@ -1688,7 +1688,7 @@ static void rcu_prepare_for_idle(int cpu)
return;
/* If this is a no-CBs CPU, no callbacks, just return. */
- if (rcu_is_nocb_cpu(cpu))
+ if (rcu_is_nocb_cpu(smp_processor_id()))
return;
/*
@@ -1712,7 +1712,7 @@ static void rcu_prepare_for_idle(int cpu)
return;
rdtp->last_accelerate = jiffies;
for_each_rcu_flavor(rsp) {
- rdp = per_cpu_ptr(rsp->rda, cpu);
+ rdp = this_cpu_ptr(rsp->rda);
if (!*rdp->nxttail[RCU_DONE_TAIL])
continue;
rnp = rdp->mynode;
@@ -1731,10 +1731,10 @@ static void rcu_prepare_for_idle(int cpu)
* any grace periods that elapsed while the CPU was idle, and if any
* callbacks are now ready to invoke, initiate invocation.
*/
-static void rcu_cleanup_after_idle(int cpu)
+static void rcu_cleanup_after_idle(void)
{
#ifndef CONFIG_RCU_NOCB_CPU_ALL
- if (rcu_is_nocb_cpu(cpu))
+ if (rcu_is_nocb_cpu(smp_processor_id()))
return;
if (rcu_try_advance_all_cbs())
invoke_rcu_core();
@@ -2573,9 +2573,13 @@ static void rcu_spawn_one_nocb_kthread(struct rcu_state *rsp, int cpu)
rdp->nocb_leader = rdp_spawn;
if (rdp_last && rdp != rdp_spawn)
rdp_last->nocb_next_follower = rdp;
- rdp_last = rdp;
- rdp = rdp->nocb_next_follower;
- rdp_last->nocb_next_follower = NULL;
+ if (rdp == rdp_spawn) {
+ rdp = rdp->nocb_next_follower;
+ } else {
+ rdp_last = rdp;
+ rdp = rdp->nocb_next_follower;
+ rdp_last->nocb_next_follower = NULL;
+ }
} while (rdp);
rdp_spawn->nocb_next_follower = rdp_old_leader;
}
@@ -2761,9 +2765,10 @@ static int full_sysidle_state; /* Current system-idle state. */
* to detect full-system idle states, not RCU quiescent states and grace
* periods. The caller must have disabled interrupts.
*/
-static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq)
+static void rcu_sysidle_enter(int irq)
{
unsigned long j;
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
/* If there are no nohz_full= CPUs, no need to track this. */
if (!tick_nohz_full_enabled())
@@ -2832,8 +2837,10 @@ void rcu_sysidle_force_exit(void)
* usermode execution does -not- count as idle here! The caller must
* have disabled interrupts.
*/
-static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq)
+static void rcu_sysidle_exit(int irq)
{
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+
/* If there are no nohz_full= CPUs, no need to track this. */
if (!tick_nohz_full_enabled())
return;
@@ -3127,11 +3134,11 @@ static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp)
#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
-static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq)
+static void rcu_sysidle_enter(int irq)
{
}
-static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq)
+static void rcu_sysidle_exit(int irq)
{
}
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 3ef8ba58694e..e0d31a345ee6 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -306,7 +306,7 @@ struct debug_obj_descr rcuhead_debug_descr = {
EXPORT_SYMBOL_GPL(rcuhead_debug_descr);
#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE)
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE)
void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp,
unsigned long secs,
unsigned long c_old, unsigned long c)
@@ -531,7 +531,8 @@ static int __noreturn rcu_tasks_kthread(void *arg)
struct rcu_head *next;
LIST_HEAD(rcu_tasks_holdouts);
- /* FIXME: Add housekeeping affinity. */
+ /* Run on housekeeping CPUs by default. Sysadm can move if desired. */
+ housekeeping_affine(current);
/*
* Each pass through the following loop makes one check for
@@ -690,3 +691,87 @@ static void rcu_spawn_tasks_kthread(void)
}
#endif /* #ifdef CONFIG_TASKS_RCU */
+
+#ifdef CONFIG_PROVE_RCU
+
+/*
+ * Early boot self test parameters, one for each flavor
+ */
+static bool rcu_self_test;
+static bool rcu_self_test_bh;
+static bool rcu_self_test_sched;
+
+module_param(rcu_self_test, bool, 0444);
+module_param(rcu_self_test_bh, bool, 0444);
+module_param(rcu_self_test_sched, bool, 0444);
+
+static int rcu_self_test_counter;
+
+static void test_callback(struct rcu_head *r)
+{
+ rcu_self_test_counter++;
+ pr_info("RCU test callback executed %d\n", rcu_self_test_counter);
+}
+
+static void early_boot_test_call_rcu(void)
+{
+ static struct rcu_head head;
+
+ call_rcu(&head, test_callback);
+}
+
+static void early_boot_test_call_rcu_bh(void)
+{
+ static struct rcu_head head;
+
+ call_rcu_bh(&head, test_callback);
+}
+
+static void early_boot_test_call_rcu_sched(void)
+{
+ static struct rcu_head head;
+
+ call_rcu_sched(&head, test_callback);
+}
+
+void rcu_early_boot_tests(void)
+{
+ pr_info("Running RCU self tests\n");
+
+ if (rcu_self_test)
+ early_boot_test_call_rcu();
+ if (rcu_self_test_bh)
+ early_boot_test_call_rcu_bh();
+ if (rcu_self_test_sched)
+ early_boot_test_call_rcu_sched();
+}
+
+static int rcu_verify_early_boot_tests(void)
+{
+ int ret = 0;
+ int early_boot_test_counter = 0;
+
+ if (rcu_self_test) {
+ early_boot_test_counter++;
+ rcu_barrier();
+ }
+ if (rcu_self_test_bh) {
+ early_boot_test_counter++;
+ rcu_barrier_bh();
+ }
+ if (rcu_self_test_sched) {
+ early_boot_test_counter++;
+ rcu_barrier_sched();
+ }
+
+ if (rcu_self_test_counter != early_boot_test_counter) {
+ WARN_ON(1);
+ ret = -1;
+ }
+
+ return ret;
+}
+late_initcall(rcu_verify_early_boot_tests);
+#else
+void rcu_early_boot_tests(void) {}
+#endif /* CONFIG_PROVE_RCU */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 240157c13ddc..e67a6e88e125 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2475,44 +2475,6 @@ EXPORT_PER_CPU_SYMBOL(kstat);
EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
/*
- * Return any ns on the sched_clock that have not yet been accounted in
- * @p in case that task is currently running.
- *
- * Called with task_rq_lock() held on @rq.
- */
-static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
-{
- u64 ns = 0;
-
- /*
- * Must be ->curr _and_ ->on_rq. If dequeued, we would
- * project cycles that may never be accounted to this
- * thread, breaking clock_gettime().
- */
- if (task_current(rq, p) && task_on_rq_queued(p)) {
- update_rq_clock(rq);
- ns = rq_clock_task(rq) - p->se.exec_start;
- if ((s64)ns < 0)
- ns = 0;
- }
-
- return ns;
-}
-
-unsigned long long task_delta_exec(struct task_struct *p)
-{
- unsigned long flags;
- struct rq *rq;
- u64 ns = 0;
-
- rq = task_rq_lock(p, &flags);
- ns = do_task_delta_exec(p, rq);
- task_rq_unlock(rq, p, &flags);
-
- return ns;
-}
-
-/*
* Return accounted runtime for the task.
* In case the task is currently running, return the runtime plus current's
* pending runtime that have not been accounted yet.
@@ -2521,7 +2483,7 @@ unsigned long long task_sched_runtime(struct task_struct *p)
{
unsigned long flags;
struct rq *rq;
- u64 ns = 0;
+ u64 ns;
#if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
/*
@@ -2540,7 +2502,16 @@ unsigned long long task_sched_runtime(struct task_struct *p)
#endif
rq = task_rq_lock(p, &flags);
- ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq);
+ /*
+ * Must be ->curr _and_ ->on_rq. If dequeued, we would
+ * project cycles that may never be accounted to this
+ * thread, breaking clock_gettime().
+ */
+ if (task_current(rq, p) && task_on_rq_queued(p)) {
+ update_rq_clock(rq);
+ p->sched_class->update_curr(rq);
+ }
+ ns = p->se.sum_exec_runtime;
task_rq_unlock(rq, p, &flags);
return ns;
@@ -2802,7 +2773,7 @@ need_resched:
preempt_disable();
cpu = smp_processor_id();
rq = cpu_rq(cpu);
- rcu_note_context_switch(cpu);
+ rcu_note_context_switch();
prev = rq->curr;
schedule_debug(prev);
@@ -2903,10 +2874,14 @@ asmlinkage __visible void __sched schedule_user(void)
* or we have been woken up remotely but the IPI has not yet arrived,
* we haven't yet exited the RCU idle mode. Do it here manually until
* we find a better solution.
+ *
+ * NB: There are buggy callers of this function. Ideally we
+ * should warn if prev_state != IN_USER, but that will trigger
+ * too frequently to make sense yet.
*/
- user_exit();
+ enum ctx_state prev_state = exception_enter();
schedule();
- user_enter();
+ exception_exit(prev_state);
}
#endif
@@ -6368,6 +6343,10 @@ static void sched_init_numa(void)
if (!sched_debug())
break;
}
+
+ if (!level)
+ return;
+
/*
* 'level' contains the number of unique distances, excluding the
* identity distance node_distance(i,i).
@@ -7444,8 +7423,12 @@ void sched_move_task(struct task_struct *tsk)
if (unlikely(running))
put_prev_task(rq, tsk);
- tg = container_of(task_css_check(tsk, cpu_cgrp_id,
- lockdep_is_held(&tsk->sighand->siglock)),
+ /*
+ * All callers are synchronized by task_rq_lock(); we do not use RCU
+ * which is pointless here. Thus, we pass "true" to task_css_check()
+ * to prevent lockdep warnings.
+ */
+ tg = container_of(task_css_check(tsk, cpu_cgrp_id, true),
struct task_group, css);
tg = autogroup_task_group(tsk, tg);
tsk->sched_task_group = tg;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 5285332392d5..28fa9d9e9201 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1701,4 +1701,6 @@ const struct sched_class dl_sched_class = {
.prio_changed = prio_changed_dl,
.switched_from = switched_from_dl,
.switched_to = switched_to_dl,
+
+ .update_curr = update_curr_dl,
};
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 34baa60f8a7b..ef2b104b254c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -726,6 +726,11 @@ static void update_curr(struct cfs_rq *cfs_rq)
account_cfs_rq_runtime(cfs_rq, delta_exec);
}
+static void update_curr_fair(struct rq *rq)
+{
+ update_curr(cfs_rq_of(&rq->curr->se));
+}
+
static inline void
update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
@@ -1180,6 +1185,13 @@ static void task_numa_compare(struct task_numa_env *env,
raw_spin_unlock_irq(&dst_rq->lock);
/*
+ * Because we have preemption enabled we can get migrated around and
+ * end try selecting ourselves (current == env->p) as a swap candidate.
+ */
+ if (cur == env->p)
+ goto unlock;
+
+ /*
* "imp" is the fault differential for the source task between the
* source and destination node. Calculate the total differential for
* the source task and potential destination task. The more negative
@@ -7949,6 +7961,8 @@ const struct sched_class fair_sched_class = {
.get_rr_interval = get_rr_interval_fair,
+ .update_curr = update_curr_fair,
+
#ifdef CONFIG_FAIR_GROUP_SCHED
.task_move_group = task_move_group_fair,
#endif
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 67ad4e7f506a..c65dac8c97cd 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -75,6 +75,10 @@ static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task
return 0;
}
+static void update_curr_idle(struct rq *rq)
+{
+}
+
/*
* Simple, special scheduling class for the per-CPU idle tasks:
*/
@@ -101,4 +105,5 @@ const struct sched_class idle_sched_class = {
.prio_changed = prio_changed_idle,
.switched_to = switched_to_idle,
+ .update_curr = update_curr_idle,
};
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index d024e6ce30ba..20bca398084a 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2128,6 +2128,8 @@ const struct sched_class rt_sched_class = {
.prio_changed = prio_changed_rt,
.switched_to = switched_to_rt,
+
+ .update_curr = update_curr_rt,
};
#ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 24156c8434d1..2df8ef067cc5 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1135,6 +1135,8 @@ struct sched_class {
unsigned int (*get_rr_interval) (struct rq *rq,
struct task_struct *task);
+ void (*update_curr) (struct rq *rq);
+
#ifdef CONFIG_FAIR_GROUP_SCHED
void (*task_move_group) (struct task_struct *p, int on_rq);
#endif
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 67426e529f59..79ffec45a6ac 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -102,6 +102,10 @@ get_rr_interval_stop(struct rq *rq, struct task_struct *task)
return 0;
}
+static void update_curr_stop(struct rq *rq)
+{
+}
+
/*
* Simple, special scheduling class for the per-CPU stop tasks:
*/
@@ -128,4 +132,5 @@ const struct sched_class stop_sched_class = {
.prio_changed = prio_changed_stop,
.switched_to = switched_to_stop,
+ .update_curr = update_curr_stop,
};
diff --git a/kernel/signal.c b/kernel/signal.c
index 8f0876f9f6dd..19e35135fc60 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1275,7 +1275,17 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
local_irq_restore(*flags);
break;
}
-
+ /*
+ * This sighand can be already freed and even reused, but
+ * we rely on SLAB_DESTROY_BY_RCU and sighand_ctor() which
+ * initializes ->siglock: this slab can't go away, it has
+ * the same object type, ->siglock can't be reinitialized.
+ *
+ * We need to ensure that tsk->sighand is still the same
+ * after we take the lock, we can race with de_thread() or
+ * __exit_signal(). In the latter case the next iteration
+ * must see ->sighand == NULL.
+ */
spin_lock(&sighand->siglock);
if (likely(sighand == tsk->sighand)) {
rcu_read_unlock();
@@ -1331,23 +1341,21 @@ int kill_pid_info(int sig, struct siginfo *info, struct pid *pid)
int error = -ESRCH;
struct task_struct *p;
- rcu_read_lock();
-retry:
- p = pid_task(pid, PIDTYPE_PID);
- if (p) {
- error = group_send_sig_info(sig, info, p);
- if (unlikely(error == -ESRCH))
- /*
- * The task was unhashed in between, try again.
- * If it is dead, pid_task() will return NULL,
- * if we race with de_thread() it will find the
- * new leader.
- */
- goto retry;
- }
- rcu_read_unlock();
+ for (;;) {
+ rcu_read_lock();
+ p = pid_task(pid, PIDTYPE_PID);
+ if (p)
+ error = group_send_sig_info(sig, info, p);
+ rcu_read_unlock();
+ if (likely(!p || error != -ESRCH))
+ return error;
- return error;
+ /*
+ * The task was unhashed in between, try again. If it
+ * is dead, pid_task() will return NULL, if we race with
+ * de_thread() it will find the new leader.
+ */
+ }
}
int kill_proc_info(int sig, struct siginfo *info, pid_t pid)
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 0699add19164..501baa9ac1be 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -656,7 +656,7 @@ static void run_ksoftirqd(unsigned int cpu)
* in the task stack here.
*/
__do_softirq();
- rcu_note_context_switch(cpu);
+ rcu_note_context_switch();
local_irq_enable();
cond_resched();
return;
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 492b986195d5..a16b67859e2a 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -553,7 +553,7 @@ static int cpu_timer_sample_group(const clockid_t which_clock,
*sample = cputime_to_expires(cputime.utime);
break;
case CPUCLOCK_SCHED:
- *sample = cputime.sum_exec_runtime + task_delta_exec(p);
+ *sample = cputime.sum_exec_runtime;
break;
}
return 0;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 7b5741fc4110..1f4356037a7d 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -585,7 +585,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
last_jiffies = jiffies;
} while (read_seqretry(&jiffies_lock, seq));
- if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) ||
+ if (rcu_needs_cpu(&rcu_delta_jiffies) ||
arch_needs_cpu() || irq_work_needs_cpu()) {
next_jiffies = last_jiffies + 1;
delta_jiffies = 1;
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 3260ffdb368f..2d3f5c504939 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1377,12 +1377,11 @@ unsigned long get_next_timer_interrupt(unsigned long now)
void update_process_times(int user_tick)
{
struct task_struct *p = current;
- int cpu = smp_processor_id();
/* Note: this timer irq context must be accounted for as well. */
account_process_tick(p, user_tick);
run_local_timers();
- rcu_check_callbacks(cpu, user_tick);
+ rcu_check_callbacks(user_tick);
#ifdef CONFIG_IRQ_WORK
if (in_irq())
irq_work_tick();
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 2d75c94ae87d..a56e07c8d15b 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -538,16 +538,18 @@ static void rb_wake_up_waiters(struct irq_work *work)
* ring_buffer_wait - wait for input to the ring buffer
* @buffer: buffer to wait on
* @cpu: the cpu buffer to wait on
+ * @full: wait until a full page is available, if @cpu != RING_BUFFER_ALL_CPUS
*
* If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
* as data is added to any of the @buffer's cpu buffers. Otherwise
* it will wait for data to be added to a specific cpu buffer.
*/
-int ring_buffer_wait(struct ring_buffer *buffer, int cpu)
+int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full)
{
- struct ring_buffer_per_cpu *cpu_buffer;
+ struct ring_buffer_per_cpu *uninitialized_var(cpu_buffer);
DEFINE_WAIT(wait);
struct rb_irq_work *work;
+ int ret = 0;
/*
* Depending on what the caller is waiting for, either any
@@ -564,36 +566,61 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu)
}
- prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
+ while (true) {
+ prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
- /*
- * The events can happen in critical sections where
- * checking a work queue can cause deadlocks.
- * After adding a task to the queue, this flag is set
- * only to notify events to try to wake up the queue
- * using irq_work.
- *
- * We don't clear it even if the buffer is no longer
- * empty. The flag only causes the next event to run
- * irq_work to do the work queue wake up. The worse
- * that can happen if we race with !trace_empty() is that
- * an event will cause an irq_work to try to wake up
- * an empty queue.
- *
- * There's no reason to protect this flag either, as
- * the work queue and irq_work logic will do the necessary
- * synchronization for the wake ups. The only thing
- * that is necessary is that the wake up happens after
- * a task has been queued. It's OK for spurious wake ups.
- */
- work->waiters_pending = true;
+ /*
+ * The events can happen in critical sections where
+ * checking a work queue can cause deadlocks.
+ * After adding a task to the queue, this flag is set
+ * only to notify events to try to wake up the queue
+ * using irq_work.
+ *
+ * We don't clear it even if the buffer is no longer
+ * empty. The flag only causes the next event to run
+ * irq_work to do the work queue wake up. The worse
+ * that can happen if we race with !trace_empty() is that
+ * an event will cause an irq_work to try to wake up
+ * an empty queue.
+ *
+ * There's no reason to protect this flag either, as
+ * the work queue and irq_work logic will do the necessary
+ * synchronization for the wake ups. The only thing
+ * that is necessary is that the wake up happens after
+ * a task has been queued. It's OK for spurious wake ups.
+ */
+ work->waiters_pending = true;
+
+ if (signal_pending(current)) {
+ ret = -EINTR;
+ break;
+ }
+
+ if (cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer))
+ break;
+
+ if (cpu != RING_BUFFER_ALL_CPUS &&
+ !ring_buffer_empty_cpu(buffer, cpu)) {
+ unsigned long flags;
+ bool pagebusy;
+
+ if (!full)
+ break;
+
+ raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
+ raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ if (!pagebusy)
+ break;
+ }
- if ((cpu == RING_BUFFER_ALL_CPUS && ring_buffer_empty(buffer)) ||
- (cpu != RING_BUFFER_ALL_CPUS && ring_buffer_empty_cpu(buffer, cpu)))
schedule();
+ }
finish_wait(&work->waiters, &wait);
- return 0;
+
+ return ret;
}
/**
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8a528392b1f4..92f4a6cee172 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1076,13 +1076,14 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
}
#endif /* CONFIG_TRACER_MAX_TRACE */
-static int wait_on_pipe(struct trace_iterator *iter)
+static int wait_on_pipe(struct trace_iterator *iter, bool full)
{
/* Iterators are static, they should be filled or empty */
if (trace_buffer_iter(iter, iter->cpu_file))
return 0;
- return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
+ return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file,
+ full);
}
#ifdef CONFIG_FTRACE_STARTUP_TEST
@@ -4434,15 +4435,12 @@ static int tracing_wait_pipe(struct file *filp)
mutex_unlock(&iter->mutex);
- ret = wait_on_pipe(iter);
+ ret = wait_on_pipe(iter, false);
mutex_lock(&iter->mutex);
if (ret)
return ret;
-
- if (signal_pending(current))
- return -EINTR;
}
return 1;
@@ -5372,16 +5370,12 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
goto out_unlock;
}
mutex_unlock(&trace_types_lock);
- ret = wait_on_pipe(iter);
+ ret = wait_on_pipe(iter, false);
mutex_lock(&trace_types_lock);
if (ret) {
size = ret;
goto out_unlock;
}
- if (signal_pending(current)) {
- size = -EINTR;
- goto out_unlock;
- }
goto again;
}
size = 0;
@@ -5500,7 +5494,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
};
struct buffer_ref *ref;
int entries, size, i;
- ssize_t ret;
+ ssize_t ret = 0;
mutex_lock(&trace_types_lock);
@@ -5538,13 +5532,16 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
int r;
ref = kzalloc(sizeof(*ref), GFP_KERNEL);
- if (!ref)
+ if (!ref) {
+ ret = -ENOMEM;
break;
+ }
ref->ref = 1;
ref->buffer = iter->trace_buffer->buffer;
ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file);
if (!ref->page) {
+ ret = -ENOMEM;
kfree(ref);
break;
}
@@ -5582,19 +5579,19 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
/* did we read anything? */
if (!spd.nr_pages) {
+ if (ret)
+ goto out;
+
if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) {
ret = -EAGAIN;
goto out;
}
mutex_unlock(&trace_types_lock);
- ret = wait_on_pipe(iter);
+ ret = wait_on_pipe(iter, true);
mutex_lock(&trace_types_lock);
if (ret)
goto out;
- if (signal_pending(current)) {
- ret = -EINTR;
- goto out;
- }
+
goto again;
}
generated by cgit v1.2.3-70-g09d2 (git 2.47.1) at 2025-01-16 00:37:23 +0000