summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/locking/lockdep.c2
-rw-r--r--kernel/rcu/Kconfig.debug11
-rw-r--r--kernel/rcu/rcu.h1
-rw-r--r--kernel/rcu/rcu_segcblist.h21
-rw-r--r--kernel/rcu/rcuperf.c10
-rw-r--r--kernel/rcu/rcutorture.c29
-rw-r--r--kernel/rcu/srcutree.c5
-rw-r--r--kernel/rcu/tree_exp.h8
-rw-r--r--kernel/rcu/tree_plugin.h31
-rw-r--r--kernel/rcu/tree_stall.h4
-rw-r--r--kernel/rcu/update.c105
-rw-r--r--kernel/sched/core.c57
-rw-r--r--kernel/sched/idle.c5
-rw-r--r--kernel/torture.c2
-rw-r--r--kernel/trace/ftrace_internal.h8
-rw-r--r--kernel/trace/trace.c4
16 files changed, 193 insertions, 110 deletions
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 4861cf8e274b..4aca3f4379d2 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -620,7 +620,7 @@ static void print_lock(struct held_lock *hlock)
return;
}
- printk(KERN_CONT "%p", hlock->instance);
+ printk(KERN_CONT "%px", hlock->instance);
print_lock_name(lock);
printk(KERN_CONT ", at: %pS\n", (void *)hlock->acquire_ip);
}
diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug
index 5ec3ea4028e2..4aa02eee8f6c 100644
--- a/kernel/rcu/Kconfig.debug
+++ b/kernel/rcu/Kconfig.debug
@@ -8,6 +8,17 @@ menu "RCU Debugging"
config PROVE_RCU
def_bool PROVE_LOCKING
+config PROVE_RCU_LIST
+ bool "RCU list lockdep debugging"
+ depends on PROVE_RCU && RCU_EXPERT
+ default n
+ help
+ Enable RCU lockdep checking for list usages. By default it is
+ turned off since there are several list RCU users that still
+ need to be converted to pass a lockdep expression. To prevent
+ false-positive splats, we keep it default disabled but once all
+ users are converted, we can remove this config option.
+
config TORTURE_TEST
tristate
default n
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 5290b01de534..8fd4f82c9b3d 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -227,6 +227,7 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
#ifdef CONFIG_RCU_STALL_COMMON
+extern int rcu_cpu_stall_ftrace_dump;
extern int rcu_cpu_stall_suppress;
extern int rcu_cpu_stall_timeout;
int rcu_jiffies_till_stall_check(void);
diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
index 71b64648464e..822a39da0533 100644
--- a/kernel/rcu/rcu_segcblist.h
+++ b/kernel/rcu/rcu_segcblist.h
@@ -76,27 +76,6 @@ static inline bool rcu_segcblist_restempty(struct rcu_segcblist *rsclp, int seg)
return !*rsclp->tails[seg];
}
-/*
- * Interim function to return rcu_segcblist head pointer. Longer term, the
- * rcu_segcblist will be used more pervasively, removing the need for this
- * function.
- */
-static inline struct rcu_head *rcu_segcblist_head(struct rcu_segcblist *rsclp)
-{
- return rsclp->head;
-}
-
-/*
- * Interim function to return rcu_segcblist head pointer. Longer term, the
- * rcu_segcblist will be used more pervasively, removing the need for this
- * function.
- */
-static inline struct rcu_head **rcu_segcblist_tail(struct rcu_segcblist *rsclp)
-{
- WARN_ON_ONCE(rcu_segcblist_empty(rsclp));
- return rsclp->tails[RCU_NEXT_TAIL];
-}
-
void rcu_segcblist_init(struct rcu_segcblist *rsclp);
void rcu_segcblist_disable(struct rcu_segcblist *rsclp);
bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp);
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 7a6890b23c5f..5a879d073c1c 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -89,7 +89,7 @@ torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable
static char *perf_type = "rcu";
module_param(perf_type, charp, 0444);
-MODULE_PARM_DESC(perf_type, "Type of RCU to performance-test (rcu, rcu_bh, ...)");
+MODULE_PARM_DESC(perf_type, "Type of RCU to performance-test (rcu, srcu, ...)");
static int nrealreaders;
static int nrealwriters;
@@ -375,6 +375,14 @@ rcu_perf_writer(void *arg)
if (holdoff)
schedule_timeout_uninterruptible(holdoff * HZ);
+ /*
+ * Wait until rcu_end_inkernel_boot() is called for normal GP tests
+ * so that RCU is not always expedited for normal GP tests.
+ * The system_state test is approximate, but works well in practice.
+ */
+ while (!gp_exp && system_state != SYSTEM_RUNNING)
+ schedule_timeout_uninterruptible(1);
+
t = ktime_get_mono_fast_ns();
if (atomic_inc_return(&n_rcu_perf_writer_started) >= nrealwriters) {
t_rcu_perf_writer_started = t;
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index fce4e7e6f502..b22947324423 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -161,6 +161,7 @@ static atomic_long_t n_rcu_torture_timers;
static long n_barrier_attempts;
static long n_barrier_successes; /* did rcu_barrier test succeed? */
static struct list_head rcu_torture_removed;
+static unsigned long shutdown_jiffies;
static int rcu_torture_writer_state;
#define RTWS_FIXED_DELAY 0
@@ -228,6 +229,15 @@ static u64 notrace rcu_trace_clock_local(void)
}
#endif /* #else #ifdef CONFIG_RCU_TRACE */
+/*
+ * Stop aggressive CPU-hog tests a bit before the end of the test in order
+ * to avoid interfering with test shutdown.
+ */
+static bool shutdown_time_arrived(void)
+{
+ return shutdown_secs && time_after(jiffies, shutdown_jiffies - 30 * HZ);
+}
+
static unsigned long boost_starttime; /* jiffies of next boost test start. */
static DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */
/* and boost task create/destroy. */
@@ -1713,12 +1723,14 @@ static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp)
}
// Give the scheduler a chance, even on nohz_full CPUs.
-static void rcu_torture_fwd_prog_cond_resched(void)
+static void rcu_torture_fwd_prog_cond_resched(unsigned long iter)
{
if (IS_ENABLED(CONFIG_PREEMPT) && IS_ENABLED(CONFIG_NO_HZ_FULL)) {
- if (need_resched())
+ // Real call_rcu() floods hit userspace, so emulate that.
+ if (need_resched() || (iter & 0xfff))
schedule();
} else {
+ // No userspace emulation: CB invocation throttles call_rcu()
cond_resched();
}
}
@@ -1746,7 +1758,7 @@ static unsigned long rcu_torture_fwd_prog_cbfree(void)
spin_unlock_irqrestore(&rcu_fwd_lock, flags);
kfree(rfcp);
freed++;
- rcu_torture_fwd_prog_cond_resched();
+ rcu_torture_fwd_prog_cond_resched(freed);
}
return freed;
}
@@ -1785,15 +1797,17 @@ static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries)
WRITE_ONCE(rcu_fwd_startat, jiffies);
stopat = rcu_fwd_startat + dur;
while (time_before(jiffies, stopat) &&
+ !shutdown_time_arrived() &&
!READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
idx = cur_ops->readlock();
udelay(10);
cur_ops->readunlock(idx);
if (!fwd_progress_need_resched || need_resched())
- rcu_torture_fwd_prog_cond_resched();
+ rcu_torture_fwd_prog_cond_resched(1);
}
(*tested_tries)++;
if (!time_before(jiffies, stopat) &&
+ !shutdown_time_arrived() &&
!READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
(*tested)++;
cver = READ_ONCE(rcu_torture_current_version) - cver;
@@ -1852,6 +1866,7 @@ static void rcu_torture_fwd_prog_cr(void)
gps = cur_ops->get_gp_seq();
rcu_launder_gp_seq_start = gps;
while (time_before(jiffies, stopat) &&
+ !shutdown_time_arrived() &&
!READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
rfcp = READ_ONCE(rcu_fwd_cb_head);
rfcpn = NULL;
@@ -1875,7 +1890,7 @@ static void rcu_torture_fwd_prog_cr(void)
rfcp->rfc_gps = 0;
}
cur_ops->call(&rfcp->rh, rcu_torture_fwd_cb_cr);
- rcu_torture_fwd_prog_cond_resched();
+ rcu_torture_fwd_prog_cond_resched(n_launders + n_max_cbs);
}
stoppedat = jiffies;
n_launders_cb_snap = READ_ONCE(n_launders_cb);
@@ -1884,7 +1899,8 @@ static void rcu_torture_fwd_prog_cr(void)
cur_ops->cb_barrier(); /* Wait for callbacks to be invoked. */
(void)rcu_torture_fwd_prog_cbfree();
- if (!torture_must_stop() && !READ_ONCE(rcu_fwd_emergency_stop)) {
+ if (!torture_must_stop() && !READ_ONCE(rcu_fwd_emergency_stop) &&
+ !shutdown_time_arrived()) {
WARN_ON(n_max_gps < MIN_FWD_CBS_LAUNDERED);
pr_alert("%s Duration %lu barrier: %lu pending %ld n_launders: %ld n_launders_sa: %ld n_max_gps: %ld n_max_cbs: %ld cver %ld gps %ld\n",
__func__,
@@ -2465,6 +2481,7 @@ rcu_torture_init(void)
goto unwind;
rcutor_hp = firsterr;
}
+ shutdown_jiffies = jiffies + shutdown_secs * HZ;
firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
if (firsterr)
goto unwind;
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index cf0e886314f2..5dffade2d7cd 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -1279,8 +1279,9 @@ void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf)
c0 = l0 - u0;
c1 = l1 - u1;
- pr_cont(" %d(%ld,%ld %1p)",
- cpu, c0, c1, rcu_segcblist_head(&sdp->srcu_cblist));
+ pr_cont(" %d(%ld,%ld %c)",
+ cpu, c0, c1,
+ "C."[rcu_segcblist_empty(&sdp->srcu_cblist)]);
s0 += c0;
s1 += c1;
}
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index af7e7b9c86af..d632cd019597 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -781,7 +781,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
* other hand, if the CPU is not in an RCU read-side critical section,
* the IPI handler reports the quiescent state immediately.
*
- * Although this is a greate improvement over previous expedited
+ * Although this is a great improvement over previous expedited
* implementations, it is still unfriendly to real-time workloads, so is
* thus not recommended for any sort of common-case code. In fact, if
* you are using synchronize_rcu_expedited() in a loop, please restructure
@@ -792,6 +792,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
*/
void synchronize_rcu_expedited(void)
{
+ bool boottime = (rcu_scheduler_active == RCU_SCHEDULER_INIT);
struct rcu_exp_work rew;
struct rcu_node *rnp;
unsigned long s;
@@ -817,7 +818,7 @@ void synchronize_rcu_expedited(void)
return; /* Someone else did our work for us. */
/* Ensure that load happens before action based on it. */
- if (unlikely(rcu_scheduler_active == RCU_SCHEDULER_INIT)) {
+ if (unlikely(boottime)) {
/* Direct call during scheduler init and early_initcalls(). */
rcu_exp_sel_wait_wake(s);
} else {
@@ -835,5 +836,8 @@ void synchronize_rcu_expedited(void)
/* Let the next expedited grace period start. */
mutex_unlock(&rcu_state.exp_mutex);
+
+ if (likely(!boottime))
+ destroy_work_on_stack(&rew.rew_work);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index ce6ef345102b..99e9d952827b 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -288,7 +288,6 @@ void rcu_note_context_switch(bool preempt)
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
struct rcu_node *rnp;
- barrier(); /* Avoid RCU read-side critical sections leaking down. */
trace_rcu_utilization(TPS("Start context switch"));
lockdep_assert_irqs_disabled();
WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0);
@@ -331,7 +330,6 @@ void rcu_note_context_switch(bool preempt)
if (rdp->exp_deferred_qs)
rcu_report_exp_rdp(rdp);
trace_rcu_utilization(TPS("End context switch"));
- barrier(); /* Avoid RCU read-side critical sections leaking up. */
}
EXPORT_SYMBOL_GPL(rcu_note_context_switch);
@@ -815,11 +813,6 @@ static void rcu_qs(void)
* dyntick-idle quiescent state visible to other CPUs, which will in
* some cases serve for expedited as well as normal grace periods.
* Either way, register a lightweight quiescent state.
- *
- * The barrier() calls are redundant in the common case when this is
- * called externally, but just in case this is called from within this
- * file.
- *
*/
void rcu_all_qs(void)
{
@@ -834,14 +827,12 @@ void rcu_all_qs(void)
return;
}
this_cpu_write(rcu_data.rcu_urgent_qs, false);
- barrier(); /* Avoid RCU read-side critical sections leaking down. */
if (unlikely(raw_cpu_read(rcu_data.rcu_need_heavy_qs))) {
local_irq_save(flags);
rcu_momentary_dyntick_idle();
local_irq_restore(flags);
}
rcu_qs();
- barrier(); /* Avoid RCU read-side critical sections leaking up. */
preempt_enable();
}
EXPORT_SYMBOL_GPL(rcu_all_qs);
@@ -851,7 +842,6 @@ EXPORT_SYMBOL_GPL(rcu_all_qs);
*/
void rcu_note_context_switch(bool preempt)
{
- barrier(); /* Avoid RCU read-side critical sections leaking down. */
trace_rcu_utilization(TPS("Start context switch"));
rcu_qs();
/* Load rcu_urgent_qs before other flags. */
@@ -864,7 +854,6 @@ void rcu_note_context_switch(bool preempt)
rcu_tasks_qs(current);
out:
trace_rcu_utilization(TPS("End context switch"));
- barrier(); /* Avoid RCU read-side critical sections leaking up. */
}
EXPORT_SYMBOL_GPL(rcu_note_context_switch);
@@ -1121,7 +1110,7 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
* already exist. We only create this kthread for preemptible RCU.
* Returns zero if all is well, a negated errno otherwise.
*/
-static int rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
+static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
{
int rnp_index = rnp - rcu_get_root();
unsigned long flags;
@@ -1129,25 +1118,27 @@ static int rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
struct task_struct *t;
if (!IS_ENABLED(CONFIG_PREEMPT_RCU))
- return 0;
+ return;
if (!rcu_scheduler_fully_active || rcu_rnp_online_cpus(rnp) == 0)
- return 0;
+ return;
rcu_state.boost = 1;
+
if (rnp->boost_kthread_task != NULL)
- return 0;
+ return;
+
t = kthread_create(rcu_boost_kthread, (void *)rnp,
"rcub/%d", rnp_index);
- if (IS_ERR(t))
- return PTR_ERR(t);
+ if (WARN_ON_ONCE(IS_ERR(t)))
+ return;
+
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rnp->boost_kthread_task = t;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
sp.sched_priority = kthread_prio;
sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
- return 0;
}
/*
@@ -1188,7 +1179,7 @@ static void __init rcu_spawn_boost_kthreads(void)
struct rcu_node *rnp;
rcu_for_each_leaf_node(rnp)
- (void)rcu_spawn_one_boost_kthread(rnp);
+ rcu_spawn_one_boost_kthread(rnp);
}
static void rcu_prepare_kthreads(int cpu)
@@ -1198,7 +1189,7 @@ static void rcu_prepare_kthreads(int cpu)
/* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */
if (rcu_scheduler_fully_active)
- (void)rcu_spawn_one_boost_kthread(rnp);
+ rcu_spawn_one_boost_kthread(rnp);
}
#else /* #ifdef CONFIG_RCU_BOOST */
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 065183391f75..0627a66699a6 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -527,6 +527,8 @@ static void check_cpu_stall(struct rcu_data *rdp)
/* We haven't checked in, so go dump stack. */
print_cpu_stall();
+ if (rcu_cpu_stall_ftrace_dump)
+ rcu_ftrace_dump(DUMP_ALL);
} else if (rcu_gp_in_progress() &&
ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
@@ -534,6 +536,8 @@ static void check_cpu_stall(struct rcu_data *rdp)
/* They had a few time units to dump stack, so complain. */
print_other_cpu_stall(gs2);
+ if (rcu_cpu_stall_ftrace_dump)
+ rcu_ftrace_dump(DUMP_ALL);
}
}
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 61df2bf08563..1861103662db 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -61,9 +61,15 @@ module_param(rcu_normal_after_boot, int, 0);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/**
- * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
+ * rcu_read_lock_held_common() - might we be in RCU-sched read-side critical section?
+ * @ret: Best guess answer if lockdep cannot be relied on
*
- * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
+ * Returns true if lockdep must be ignored, in which case *ret contains
+ * the best guess described below. Otherwise returns false, in which
+ * case *ret tells the caller nothing and the caller should instead
+ * consult lockdep.
+ *
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, set *ret to nonzero iff in an
* RCU-sched read-side critical section. In absence of
* CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
* critical section unless it can prove otherwise. Note that disabling
@@ -75,35 +81,45 @@ module_param(rcu_normal_after_boot, int, 0);
* Check debug_lockdep_rcu_enabled() to prevent false positives during boot
* and while lockdep is disabled.
*
- * Note that if the CPU is in the idle loop from an RCU point of
- * view (ie: that we are in the section between rcu_idle_enter() and
- * rcu_idle_exit()) then rcu_read_lock_held() returns false even if the CPU
- * did an rcu_read_lock(). The reason for this is that RCU ignores CPUs
- * that are in such a section, considering these as in extended quiescent
- * state, so such a CPU is effectively never in an RCU read-side critical
- * section regardless of what RCU primitives it invokes. This state of
- * affairs is required --- we need to keep an RCU-free window in idle
- * where the CPU may possibly enter into low power mode. This way we can
- * notice an extended quiescent state to other CPUs that started a grace
- * period. Otherwise we would delay any grace period as long as we run in
- * the idle task.
+ * Note that if the CPU is in the idle loop from an RCU point of view (ie:
+ * that we are in the section between rcu_idle_enter() and rcu_idle_exit())
+ * then rcu_read_lock_held() sets *ret to false even if the CPU did an
+ * rcu_read_lock(). The reason for this is that RCU ignores CPUs that are
+ * in such a section, considering these as in extended quiescent state,
+ * so such a CPU is effectively never in an RCU read-side critical section
+ * regardless of what RCU primitives it invokes. This state of affairs is
+ * required --- we need to keep an RCU-free window in idle where the CPU may
+ * possibly enter into low power mode. This way we can notice an extended
+ * quiescent state to other CPUs that started a grace period. Otherwise
+ * we would delay any grace period as long as we run in the idle task.
*
- * Similarly, we avoid claiming an SRCU read lock held if the current
+ * Similarly, we avoid claiming an RCU read lock held if the current
* CPU is offline.
*/
+static bool rcu_read_lock_held_common(bool *ret)
+{
+ if (!debug_lockdep_rcu_enabled()) {
+ *ret = 1;
+ return true;
+ }
+ if (!rcu_is_watching()) {
+ *ret = 0;
+ return true;
+ }
+ if (!rcu_lockdep_current_cpu_online()) {
+ *ret = 0;
+ return true;
+ }
+ return false;
+}
+
int rcu_read_lock_sched_held(void)
{
- int lockdep_opinion = 0;
+ bool ret;
- if (!debug_lockdep_rcu_enabled())
- return 1;
- if (!rcu_is_watching())
- return 0;
- if (!rcu_lockdep_current_cpu_online())
- return 0;
- if (debug_locks)
- lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
- return lockdep_opinion || !preemptible();
+ if (rcu_read_lock_held_common(&ret))
+ return ret;
+ return lock_is_held(&rcu_sched_lock_map) || !preemptible();
}
EXPORT_SYMBOL(rcu_read_lock_sched_held);
#endif
@@ -136,8 +152,7 @@ static atomic_t rcu_expedited_nesting = ATOMIC_INIT(1);
*/
bool rcu_gp_is_expedited(void)
{
- return rcu_expedited || atomic_read(&rcu_expedited_nesting) ||
- rcu_scheduler_active == RCU_SCHEDULER_INIT;
+ return rcu_expedited || atomic_read(&rcu_expedited_nesting);
}
EXPORT_SYMBOL_GPL(rcu_gp_is_expedited);
@@ -261,12 +276,10 @@ NOKPROBE_SYMBOL(debug_lockdep_rcu_enabled);
*/
int rcu_read_lock_held(void)
{
- if (!debug_lockdep_rcu_enabled())
- return 1;
- if (!rcu_is_watching())
- return 0;
- if (!rcu_lockdep_current_cpu_online())
- return 0;
+ bool ret;
+
+ if (rcu_read_lock_held_common(&ret))
+ return ret;
return lock_is_held(&rcu_lock_map);
}
EXPORT_SYMBOL_GPL(rcu_read_lock_held);
@@ -288,16 +301,28 @@ EXPORT_SYMBOL_GPL(rcu_read_lock_held);
*/
int rcu_read_lock_bh_held(void)
{
- if (!debug_lockdep_rcu_enabled())
- return 1;
- if (!rcu_is_watching())
- return 0;
- if (!rcu_lockdep_current_cpu_online())
- return 0;
+ bool ret;
+
+ if (rcu_read_lock_held_common(&ret))
+ return ret;
return in_softirq() || irqs_disabled();
}
EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
+int rcu_read_lock_any_held(void)
+{
+ bool ret;
+
+ if (rcu_read_lock_held_common(&ret))
+ return ret;
+ if (lock_is_held(&rcu_lock_map) ||
+ lock_is_held(&rcu_bh_lock_map) ||
+ lock_is_held(&rcu_sched_lock_map))
+ return 1;
+ return !preemptible();
+}
+EXPORT_SYMBOL_GPL(rcu_read_lock_any_held);
+
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
/**
@@ -437,6 +462,8 @@ EXPORT_SYMBOL_GPL(rcutorture_sched_setaffinity);
#endif
#ifdef CONFIG_RCU_STALL_COMMON
+int rcu_cpu_stall_ftrace_dump __read_mostly;
+module_param(rcu_cpu_stall_ftrace_dump, int, 0644);
int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
module_param(rcu_cpu_stall_suppress, int, 0644);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2b037f195473..0b22e55cebe8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3486,8 +3486,36 @@ void scheduler_tick(void)
struct tick_work {
int cpu;
+ atomic_t state;
struct delayed_work work;
};
+/* Values for ->state, see diagram below. */
+#define TICK_SCHED_REMOTE_OFFLINE 0
+#define TICK_SCHED_REMOTE_OFFLINING 1
+#define TICK_SCHED_REMOTE_RUNNING 2
+
+/*
+ * State diagram for ->state:
+ *
+ *
+ * TICK_SCHED_REMOTE_OFFLINE
+ * | ^
+ * | |
+ * | | sched_tick_remote()
+ * | |
+ * | |
+ * +--TICK_SCHED_REMOTE_OFFLINING
+ * | ^
+ * | |
+ * sched_tick_start() | | sched_tick_stop()
+ * | |
+ * V |
+ * TICK_SCHED_REMOTE_RUNNING
+ *
+ *
+ * Other transitions get WARN_ON_ONCE(), except that sched_tick_remote()
+ * and sched_tick_start() are happy to leave the state in RUNNING.
+ */
static struct tick_work __percpu *tick_work_cpu;
@@ -3500,6 +3528,7 @@ static void sched_tick_remote(struct work_struct *work)
struct task_struct *curr;
struct rq_flags rf;
u64 delta;
+ int os;
/*
* Handle the tick only if it appears the remote CPU is running in full
@@ -3513,7 +3542,7 @@ static void sched_tick_remote(struct work_struct *work)
rq_lock_irq(rq, &rf);
curr = rq->curr;
- if (is_idle_task(curr))
+ if (is_idle_task(curr) || cpu_is_offline(cpu))
goto out_unlock;
update_rq_clock(rq);
@@ -3533,13 +3562,18 @@ out_requeue:
/*
* Run the remote tick once per second (1Hz). This arbitrary
* frequency is large enough to avoid overload but short enough
- * to keep scheduler internal stats reasonably up to date.
+ * to keep scheduler internal stats reasonably up to date. But
+ * first update state to reflect hotplug activity if required.
*/
- queue_delayed_work(system_unbound_wq, dwork, HZ);
+ os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING);
+ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE);
+ if (os == TICK_SCHED_REMOTE_RUNNING)
+ queue_delayed_work(system_unbound_wq, dwork, HZ);
}
static void sched_tick_start(int cpu)
{
+ int os;
struct tick_work *twork;
if (housekeeping_cpu(cpu, HK_FLAG_TICK))
@@ -3548,15 +3582,20 @@ static void sched_tick_start(int cpu)
WARN_ON_ONCE(!tick_work_cpu);
twork = per_cpu_ptr(tick_work_cpu, cpu);
- twork->cpu = cpu;
- INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
- queue_delayed_work(system_unbound_wq, &twork->work, HZ);
+ os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING);
+ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING);
+ if (os == TICK_SCHED_REMOTE_OFFLINE) {
+ twork->cpu = cpu;
+ INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
+ queue_delayed_work(system_unbound_wq, &twork->work, HZ);
+ }
}
#ifdef CONFIG_HOTPLUG_CPU
static void sched_tick_stop(int cpu)
{
struct tick_work *twork;
+ int os;
if (housekeeping_cpu(cpu, HK_FLAG_TICK))
return;
@@ -3564,7 +3603,10 @@ static void sched_tick_stop(int cpu)
WARN_ON_ONCE(!tick_work_cpu);
twork = per_cpu_ptr(tick_work_cpu, cpu);
- cancel_delayed_work_sync(&twork->work);
+ /* There cannot be competing actions, but don't rely on stop-machine. */
+ os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_OFFLINING);
+ WARN_ON_ONCE(os != TICK_SCHED_REMOTE_RUNNING);
+ /* Don't cancel, as this would mess up the state machine. */
}
#endif /* CONFIG_HOTPLUG_CPU */
@@ -3572,7 +3614,6 @@ int __init sched_tick_offload_init(void)
{
tick_work_cpu = alloc_percpu(struct tick_work);
BUG_ON(!tick_work_cpu);
-
return 0;
}
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 80940939b733..e4bc4aa739b8 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -241,13 +241,14 @@ static void do_idle(void)
check_pgt_cache();
rmb();
+ local_irq_disable();
+
if (cpu_is_offline(cpu)) {
- tick_nohz_idle_stop_tick_protected();
+ tick_nohz_idle_stop_tick();
cpuhp_report_idle_dead();
arch_cpu_idle_dead();
}
- local_irq_disable();
arch_cpu_idle_enter();
/*
diff --git a/kernel/torture.c b/kernel/torture.c
index a8d9bdfba7c3..7c13f5558b71 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -263,7 +263,6 @@ static void torture_onoff_cleanup(void)
onoff_task = NULL;
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
}
-EXPORT_SYMBOL_GPL(torture_onoff_cleanup);
/*
* Print online/offline testing statistics.
@@ -449,7 +448,6 @@ static void torture_shuffle_cleanup(void)
}
shuffler_task = NULL;
}
-EXPORT_SYMBOL_GPL(torture_shuffle_cleanup);
/*
* Variables for auto-shutdown. This allows "lights out" torture runs
diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h
index 0515a2096f90..0456e0a3dab1 100644
--- a/kernel/trace/ftrace_internal.h
+++ b/kernel/trace/ftrace_internal.h
@@ -6,22 +6,22 @@
/*
* Traverse the ftrace_global_list, invoking all entries. The reason that we
- * can use rcu_dereference_raw_notrace() is that elements removed from this list
+ * can use rcu_dereference_raw_check() is that elements removed from this list
* are simply leaked, so there is no need to interact with a grace-period
- * mechanism. The rcu_dereference_raw_notrace() calls are needed to handle
+ * mechanism. The rcu_dereference_raw_check() calls are needed to handle
* concurrent insertions into the ftrace_global_list.
*
* Silly Alpha and silly pointer-speculation compiler optimizations!
*/
#define do_for_each_ftrace_op(op, list) \
- op = rcu_dereference_raw_notrace(list); \
+ op = rcu_dereference_raw_check(list); \
do
/*
* Optimized for just a single item in the list (as that is the normal case).
*/
#define while_for_each_ftrace_op(op) \
- while (likely(op = rcu_dereference_raw_notrace((op)->next)) && \
+ while (likely(op = rcu_dereference_raw_check((op)->next)) && \
unlikely((op) != &ftrace_list_end))
extern struct ftrace_ops __rcu *ftrace_ops_list;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 525a97fbbc60..642474b26ba7 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2642,10 +2642,10 @@ static void ftrace_exports(struct ring_buffer_event *event)
preempt_disable_notrace();
- export = rcu_dereference_raw_notrace(ftrace_exports_list);
+ export = rcu_dereference_raw_check(ftrace_exports_list);
while (export) {
trace_process_export(export, event);
- export = rcu_dereference_raw_notrace(export->next);
+ export = rcu_dereference_raw_check(export->next);
}
preempt_enable_notrace();
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-27 18:05:53 +0000