xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branches 'consolidate.2019.04.09a', 'doc.2019.03.26b', 'fixes.2019.03.26b', 'srcu.2019.03.26b', 'stall.2019.03.26b' and 'torture.2019.03.26b' into HEAD

Browse Source 
consolidate.2019.04.09a: Lingering RCU flavor consolidation cleanups.
doc.2019.03.26b: Documentation updates.
fixes.2019.03.26b: Miscellaneous fixes.
srcu.2019.03.26b: SRCU updates.
stall.2019.03.26b: RCU CPU stall warning updates.
torture.2019.03.26b: Torture-test updates.
This commit is contained in:
Paul E. McKenney
2019-04-09 08:08:13 -07:00
parent bee58fe346 884b429ae6 add0d37b4f f5ad399149 6c70e9cd5f 164a4daaea
commit 6cdbc07a5a
51 changed files with 1081 additions and 1272 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
kernel/locking/locktorture.c
View File

@@ -829,7 +829,9 @@ static void lock_torture_cleanup(void)
"End of test: SUCCESS");
kfree(cxt.lwsa);
cxt.lwsa = NULL;
kfree(cxt.lrsa);
cxt.lrsa = NULL;
end:
torture_cleanup_end();

1
kernel/rcu/rcu.h
View File

@@ -233,6 +233,7 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
#ifdef CONFIG_RCU_STALL_COMMON
extern int rcu_cpu_stall_suppress;
extern int rcu_cpu_stall_timeout;
int rcu_jiffies_till_stall_check(void);
#define rcu_ftrace_dump_stall_suppress() \

5
kernel/rcu/rcuperf.c
View File

@@ -494,6 +494,10 @@ rcu_perf_cleanup(void)
if (torture_cleanup_begin())
return;
if (!cur_ops) {
torture_cleanup_end();
return;
}
if (reader_tasks) {
for (i = 0; i < nrealreaders; i++)
@@ -614,6 +618,7 @@ rcu_perf_init(void)
pr_cont("\n");
WARN_ON(!IS_MODULE(CONFIG_RCU_PERF_TEST));
firsterr = -EINVAL;
cur_ops = NULL;
goto unwind;
}
if (cur_ops->init)

21
kernel/rcu/rcutorture.c
View File

@@ -299,7 +299,6 @@ struct rcu_torture_ops {
int irq_capable;
int can_boost;
int extendables;
int ext_irq_conflict;
const char *name;
};
@@ -592,12 +591,7 @@ static void srcu_torture_init(void)
static void srcu_torture_cleanup(void)
{
static DEFINE_TORTURE_RANDOM(rand);
if (torture_random(&rand) & 0x800)
cleanup_srcu_struct(&srcu_ctld);
else
cleanup_srcu_struct_quiesced(&srcu_ctld);
cleanup_srcu_struct(&srcu_ctld);
srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */
}
@@ -1160,7 +1154,7 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
unsigned long randmask2 = randmask1 >> 3;
WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT);
/* Most of the time lots of bits, half the time only one bit. */
/* Mostly only one bit (need preemption!), sometimes lots of bits. */
if (!(randmask1 & 0x7))
mask = mask & randmask2;
else
@@ -1170,10 +1164,6 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
((!(mask & RCUTORTURE_RDR_BH) && (oldmask & RCUTORTURE_RDR_BH)) ||
(!(mask & RCUTORTURE_RDR_RBH) && (oldmask & RCUTORTURE_RDR_RBH))))
mask |= RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH;
if ((mask & RCUTORTURE_RDR_IRQ) &&
!(mask & cur_ops->ext_irq_conflict) &&
(oldmask & cur_ops->ext_irq_conflict))
mask |= cur_ops->ext_irq_conflict; /* Or if readers object. */
return mask ?: RCUTORTURE_RDR_RCU;
}
@@ -1848,7 +1838,7 @@ static int rcutorture_oom_notify(struct notifier_block *self,
WARN(1, "%s invoked upon OOM during forward-progress testing.\n",
__func__);
rcu_torture_fwd_cb_hist();
rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat) / 2));
rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat)) / 2);
WRITE_ONCE(rcu_fwd_emergency_stop, true);
smp_mb(); /* Emergency stop before free and wait to avoid hangs. */
pr_info("%s: Freed %lu RCU callbacks.\n",
@@ -2094,6 +2084,10 @@ rcu_torture_cleanup(void)
cur_ops->cb_barrier();
return;
}
if (!cur_ops) {
torture_cleanup_end();
return;
}
rcu_torture_barrier_cleanup();
torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task);
@@ -2267,6 +2261,7 @@ rcu_torture_init(void)
pr_cont("\n");
WARN_ON(!IS_MODULE(CONFIG_RCU_TORTURE_TEST));
firsterr = -EINVAL;
cur_ops = NULL;
goto unwind;
}
if (cur_ops->fqs == NULL && fqs_duration != 0) {

9
kernel/rcu/srcutiny.c
View File

@@ -76,19 +76,16 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
* Must invoke this after you are finished using a given srcu_struct that
* was initialized via init_srcu_struct(), else you leak memory.
*/
void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
void cleanup_srcu_struct(struct srcu_struct *ssp)
{
WARN_ON(ssp->srcu_lock_nesting[0] || ssp->srcu_lock_nesting[1]);
if (quiesced)
WARN_ON(work_pending(&ssp->srcu_work));
else
flush_work(&ssp->srcu_work);
flush_work(&ssp->srcu_work);
WARN_ON(ssp->srcu_gp_running);
WARN_ON(ssp->srcu_gp_waiting);
WARN_ON(ssp->srcu_cb_head);
WARN_ON(&ssp->srcu_cb_head != ssp->srcu_cb_tail);
}
EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
/*
* Removes the count for the old reader from the appropriate element of

32
kernel/rcu/srcutree.c
View File

@@ -360,8 +360,14 @@ static unsigned long srcu_get_delay(struct srcu_struct *ssp)
return SRCU_INTERVAL;
}
/* Helper for cleanup_srcu_struct() and cleanup_srcu_struct_quiesced(). */
void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
/**
* cleanup_srcu_struct - deconstruct a sleep-RCU structure
* @ssp: structure to clean up.
*
* Must invoke this after you are finished using a given srcu_struct that
* was initialized via init_srcu_struct(), else you leak memory.
*/
void cleanup_srcu_struct(struct srcu_struct *ssp)
{
int cpu;
@@ -369,24 +375,14 @@ void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
return; /* Just leak it! */
if (WARN_ON(srcu_readers_active(ssp)))
return; /* Just leak it! */
if (quiesced) {
if (WARN_ON(delayed_work_pending(&ssp->work)))
return; /* Just leak it! */
} else {
flush_delayed_work(&ssp->work);
}
flush_delayed_work(&ssp->work);
for_each_possible_cpu(cpu) {
struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
if (quiesced) {
if (WARN_ON(timer_pending(&sdp->delay_work)))
return; /* Just leak it! */
if (WARN_ON(work_pending(&sdp->work)))
return; /* Just leak it! */
} else {
del_timer_sync(&sdp->delay_work);
flush_work(&sdp->work);
}
del_timer_sync(&sdp->delay_work);
flush_work(&sdp->work);
if (WARN_ON(rcu_segcblist_n_cbs(&sdp->srcu_cblist)))
return; /* Forgot srcu_barrier(), so just leak it! */
}
if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
WARN_ON(srcu_readers_active(ssp))) {
@@ -397,7 +393,7 @@ void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
free_percpu(ssp->sda);
ssp->sda = NULL;
}
EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
/*
* Counts the new reader in the appropriate per-CPU element of the

2
kernel/rcu/tiny.c
View File

@@ -52,7 +52,7 @@ void rcu_qs(void)
local_irq_save(flags);
if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) {
rcu_ctrlblk.donetail = rcu_ctrlblk.curtail;
raise_softirq(RCU_SOFTIRQ);
raise_softirq_irqoff(RCU_SOFTIRQ);
}
local_irq_restore(flags);
}

508
kernel/rcu/tree.c
View File

@@ -102,11 +102,6 @@ int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
/* Number of rcu_nodes at specified level. */
int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
/* panic() on RCU Stall sysctl. */
int sysctl_panic_on_rcu_stall __read_mostly;
/* Commandeer a sysrq key to dump RCU's tree. */
static bool sysrq_rcu;
module_param(sysrq_rcu, bool, 0444);
/*
* The rcu_scheduler_active variable is initialized to the value
@@ -149,7 +144,7 @@ static void sync_sched_exp_online_cleanup(int cpu);
/* rcuc/rcub kthread realtime priority */
static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
module_param(kthread_prio, int, 0644);
module_param(kthread_prio, int, 0444);
/* Delay in jiffies for grace-period initialization delays, debug only. */
@@ -406,7 +401,7 @@ static bool rcu_kick_kthreads;
*/
static ulong jiffies_till_sched_qs = ULONG_MAX;
module_param(jiffies_till_sched_qs, ulong, 0444);
static ulong jiffies_to_sched_qs; /* Adjusted version of above if not default */
static ulong jiffies_to_sched_qs; /* See adjust_jiffies_till_sched_qs(). */
module_param(jiffies_to_sched_qs, ulong, 0444); /* Display only! */
/*
@@ -424,6 +419,7 @@ static void adjust_jiffies_till_sched_qs(void)
WRITE_ONCE(jiffies_to_sched_qs, jiffies_till_sched_qs);
return;
}
/* Otherwise, set to third fqs scan, but bound below on large system. */
j = READ_ONCE(jiffies_till_first_fqs) +
2 * READ_ONCE(jiffies_till_next_fqs);
if (j < HZ / 10 + nr_cpu_ids / RCU_JIFFIES_FQS_DIV)
@@ -512,74 +508,6 @@ static const char *gp_state_getname(short gs)
return gp_state_names[gs];
}
/*
* Show the state of the grace-period kthreads.
*/
void show_rcu_gp_kthreads(void)
{
int cpu;
unsigned long j;
unsigned long ja;
unsigned long jr;
unsigned long jw;
struct rcu_data *rdp;
struct rcu_node *rnp;
j = jiffies;
ja = j - READ_ONCE(rcu_state.gp_activity);
jr = j - READ_ONCE(rcu_state.gp_req_activity);
jw = j - READ_ONCE(rcu_state.gp_wake_time);
pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
rcu_state.name, gp_state_getname(rcu_state.gp_state),
rcu_state.gp_state,
rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL,
ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
(long)READ_ONCE(rcu_state.gp_seq),
(long)READ_ONCE(rcu_get_root()->gp_seq_needed),
READ_ONCE(rcu_state.gp_flags));
rcu_for_each_node_breadth_first(rnp) {
if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
continue;
pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
rnp->grplo, rnp->grphi, (long)rnp->gp_seq,
(long)rnp->gp_seq_needed);
if (!rcu_is_leaf_node(rnp))
continue;
for_each_leaf_node_possible_cpu(rnp, cpu) {
rdp = per_cpu_ptr(&rcu_data, cpu);
if (rdp->gpwrap ||
ULONG_CMP_GE(rcu_state.gp_seq,
rdp->gp_seq_needed))
continue;
pr_info("\tcpu %d ->gp_seq_needed %ld\n",
cpu, (long)rdp->gp_seq_needed);
}
}
/* sched_show_task(rcu_state.gp_kthread); */
}
EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
/* Dump grace-period-request information due to commandeered sysrq. */
static void sysrq_show_rcu(int key)
{
show_rcu_gp_kthreads();
}
static struct sysrq_key_op sysrq_rcudump_op = {
.handler = sysrq_show_rcu,
.help_msg = "show-rcu(y)",
.action_msg = "Show RCU tree",
.enable_mask = SYSRQ_ENABLE_DUMP,
};
static int __init rcu_sysrq_init(void)
{
if (sysrq_rcu)
return register_sysrq_key('y', &sysrq_rcudump_op);
return 0;
}
early_initcall(rcu_sysrq_init);
/*
* Send along grace-period-related data for rcutorture diagnostics.
*/
@@ -1033,27 +961,6 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
return 0;
}
/*
* Handler for the irq_work request posted when a grace period has
* gone on for too long, but not yet long enough for an RCU CPU
* stall warning. Set state appropriately, but just complain if
* there is unexpected state on entry.
*/
static void rcu_iw_handler(struct irq_work *iwp)
{
struct rcu_data *rdp;
struct rcu_node *rnp;
rdp = container_of(iwp, struct rcu_data, rcu_iw);
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp);
if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) {
rdp->rcu_iw_gp_seq = rnp->gp_seq;
rdp->rcu_iw_pending = false;
}
raw_spin_unlock_rcu_node(rnp);
}
/*
* Return true if the specified CPU has passed through a quiescent
* state by virtue of being in or having passed through an dynticks
@@ -1167,295 +1074,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
return 0;
}
static void record_gp_stall_check_time(void)
{
unsigned long j = jiffies;
unsigned long j1;
rcu_state.gp_start = j;
j1 = rcu_jiffies_till_stall_check();
/* Record ->gp_start before ->jiffies_stall. */
smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */
rcu_state.jiffies_resched = j + j1 / 2;
rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs);
}
/*
* Complain about starvation of grace-period kthread.
*/
static void rcu_check_gp_kthread_starvation(void)
{
struct task_struct *gpk = rcu_state.gp_kthread;
unsigned long j;
j = jiffies - READ_ONCE(rcu_state.gp_activity);
if (j > 2 * HZ) {
pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
rcu_state.name, j,
(long)rcu_seq_current(&rcu_state.gp_seq),
READ_ONCE(rcu_state.gp_flags),
gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
if (gpk) {
pr_err("RCU grace-period kthread stack dump:\n");
sched_show_task(gpk);
wake_up_process(gpk);
}
}
}
/*
* Dump stacks of all tasks running on stalled CPUs. First try using
* NMIs, but fall back to manual remote stack tracing on architectures
* that don't support NMI-based stack dumps. The NMI-triggered stack
* traces are more accurate because they are printed by the target CPU.
*/
static void rcu_dump_cpu_stacks(void)
{
int cpu;
unsigned long flags;
struct rcu_node *rnp;
rcu_for_each_leaf_node(rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
for_each_leaf_node_possible_cpu(rnp, cpu)
if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
if (!trigger_single_cpu_backtrace(cpu))
dump_cpu_task(cpu);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
}
/*
* If too much time has passed in the current grace period, and if
* so configured, go kick the relevant kthreads.
*/
static void rcu_stall_kick_kthreads(void)
{
unsigned long j;
if (!rcu_kick_kthreads)
return;
j = READ_ONCE(rcu_state.jiffies_kick_kthreads);
if (time_after(jiffies, j) && rcu_state.gp_kthread &&
(rcu_gp_in_progress() || READ_ONCE(rcu_state.gp_flags))) {
WARN_ONCE(1, "Kicking %s grace-period kthread\n",
rcu_state.name);
rcu_ftrace_dump(DUMP_ALL);
wake_up_process(rcu_state.gp_kthread);
WRITE_ONCE(rcu_state.jiffies_kick_kthreads, j + HZ);
}
}
static void panic_on_rcu_stall(void)
{
if (sysctl_panic_on_rcu_stall)
panic("RCU Stall\n");
}
static void print_other_cpu_stall(unsigned long gp_seq)
{
int cpu;
unsigned long flags;
unsigned long gpa;
unsigned long j;
int ndetected = 0;
struct rcu_node *rnp = rcu_get_root();
long totqlen = 0;
/* Kick and suppress, if so configured. */
rcu_stall_kick_kthreads();
if (rcu_cpu_stall_suppress)
return;
/*
* OK, time to rat on our buddy...
* See Documentation/RCU/stallwarn.txt for info on how to debug
* RCU CPU stall warnings.
*/
pr_err("INFO: %s detected stalls on CPUs/tasks:", rcu_state.name);
print_cpu_stall_info_begin();
rcu_for_each_leaf_node(rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
ndetected += rcu_print_task_stall(rnp);
if (rnp->qsmask != 0) {
for_each_leaf_node_possible_cpu(rnp, cpu)
if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
print_cpu_stall_info(cpu);
ndetected++;
}
}
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
print_cpu_stall_info_end();
for_each_possible_cpu(cpu)
totqlen += rcu_get_n_cbs_cpu(cpu);
pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
smp_processor_id(), (long)(jiffies - rcu_state.gp_start),
(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
if (ndetected) {
rcu_dump_cpu_stacks();
/* Complain about tasks blocking the grace period. */
rcu_print_detail_task_stall();
} else {
if (rcu_seq_current(&rcu_state.gp_seq) != gp_seq) {
pr_err("INFO: Stall ended before state dump start\n");
} else {
j = jiffies;
gpa = READ_ONCE(rcu_state.gp_activity);
pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
rcu_state.name, j - gpa, j, gpa,
READ_ONCE(jiffies_till_next_fqs),
rcu_get_root()->qsmask);
/* In this case, the current CPU might be at fault. */
sched_show_task(current);
}
}
/* Rewrite if needed in case of slow consoles. */
if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
WRITE_ONCE(rcu_state.jiffies_stall,
jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
rcu_check_gp_kthread_starvation();
panic_on_rcu_stall();
rcu_force_quiescent_state(); /* Kick them all. */
}
static void print_cpu_stall(void)
{
int cpu;
unsigned long flags;
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rcu_get_root();
long totqlen = 0;
/* Kick and suppress, if so configured. */
rcu_stall_kick_kthreads();
if (rcu_cpu_stall_suppress)
return;
/*
* OK, time to rat on ourselves...
* See Documentation/RCU/stallwarn.txt for info on how to debug
* RCU CPU stall warnings.
*/
pr_err("INFO: %s self-detected stall on CPU", rcu_state.name);
print_cpu_stall_info_begin();
raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags);
print_cpu_stall_info(smp_processor_id());
raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags);
print_cpu_stall_info_end();
for_each_possible_cpu(cpu)
totqlen += rcu_get_n_cbs_cpu(cpu);
pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n",
jiffies - rcu_state.gp_start,
(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
rcu_check_gp_kthread_starvation();
rcu_dump_cpu_stacks();
raw_spin_lock_irqsave_rcu_node(rnp, flags);
/* Rewrite if needed in case of slow consoles. */
if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
WRITE_ONCE(rcu_state.jiffies_stall,
jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
panic_on_rcu_stall();
/*
* Attempt to revive the RCU machinery by forcing a context switch.
*
* A context switch would normally allow the RCU state machine to make
* progress and it could be we're stuck in kernel space without context
* switches for an entirely unreasonable amount of time.
*/
set_tsk_need_resched(current);
set_preempt_need_resched();
}
static void check_cpu_stall(struct rcu_data *rdp)
{
unsigned long gs1;
unsigned long gs2;
unsigned long gps;
unsigned long j;
unsigned long jn;
unsigned long js;
struct rcu_node *rnp;
if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) ||
!rcu_gp_in_progress())
return;
rcu_stall_kick_kthreads();
j = jiffies;
/*
* Lots of memory barriers to reject false positives.
*
* The idea is to pick up rcu_state.gp_seq, then
* rcu_state.jiffies_stall, then rcu_state.gp_start, and finally
* another copy of rcu_state.gp_seq. These values are updated in
* the opposite order with memory barriers (or equivalent) during
* grace-period initialization and cleanup. Now, a false positive
* can occur if we get an new value of rcu_state.gp_start and a old
* value of rcu_state.jiffies_stall. But given the memory barriers,
* the only way that this can happen is if one grace period ends
* and another starts between these two fetches. This is detected
* by comparing the second fetch of rcu_state.gp_seq with the
* previous fetch from rcu_state.gp_seq.
*
* Given this check, comparisons of jiffies, rcu_state.jiffies_stall,
* and rcu_state.gp_start suffice to forestall false positives.
*/
gs1 = READ_ONCE(rcu_state.gp_seq);
smp_rmb(); /* Pick up ->gp_seq first... */
js = READ_ONCE(rcu_state.jiffies_stall);
smp_rmb(); /* ...then ->jiffies_stall before the rest... */
gps = READ_ONCE(rcu_state.gp_start);
smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */
gs2 = READ_ONCE(rcu_state.gp_seq);
if (gs1 != gs2 ||
ULONG_CMP_LT(j, js) ||
ULONG_CMP_GE(gps, js))
return; /* No stall or GP completed since entering function. */
rnp = rdp->mynode;
jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
if (rcu_gp_in_progress() &&
(READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
/* We haven't checked in, so go dump stack. */
print_cpu_stall();
} else if (rcu_gp_in_progress() &&
ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
/* They had a few time units to dump stack, so complain. */
print_other_cpu_stall(gs2);
}
}
/**
* rcu_cpu_stall_reset - prevent further stall warnings in current grace period
*
* Set the stall-warning timeout way off into the future, thus preventing
* any RCU CPU stall-warning messages from appearing in the current set of
* RCU grace periods.
*
* The caller must disable hard irqs.
*/
void rcu_cpu_stall_reset(void)
{
WRITE_ONCE(rcu_state.jiffies_stall, jiffies + ULONG_MAX / 2);
}
/* Trace-event wrapper function for trace_rcu_future_grace_period. */
static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
unsigned long gp_seq_req, const char *s)
@@ -1585,7 +1203,7 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
static void rcu_gp_kthread_wake(void)
{
if ((current == rcu_state.gp_kthread &&
!in_interrupt() && !in_serving_softirq()) ||
!in_irq() && !in_serving_softirq()) ||
!READ_ONCE(rcu_state.gp_flags) ||
!rcu_state.gp_kthread)
return;
@@ -2295,11 +1913,10 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
return;
}
mask = rdp->grpmask;
rdp->core_needs_qs = false;
if ((rnp->qsmask & mask) == 0) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
} else {
rdp->core_needs_qs = false;
/*
* This GP can't end until cpu checks in, so all of our
* callbacks can be processed during the next GP.
@@ -2548,11 +2165,11 @@ void rcu_sched_clock_irq(int user)
}
/*
* Scan the leaf rcu_node structures, processing dyntick state for any that
* have not yet encountered a quiescent state, using the function specified.
* Also initiate boosting for any threads blocked on the root rcu_node.
*
* The caller must have suppressed start of new grace periods.
* Scan the leaf rcu_node structures. For each structure on which all
* CPUs have reported a quiescent state and on which there are tasks
* blocking the current grace period, initiate RCU priority boosting.
* Otherwise, invoke the specified function to check dyntick state for
* each CPU that has not yet reported a quiescent state.
*/
static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
{
@@ -2635,101 +2252,6 @@ void rcu_force_quiescent_state(void)
}
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
/*
* This function checks for grace-period requests that fail to motivate
* RCU to come out of its idle mode.
*/
void
rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
const unsigned long gpssdelay)
{
unsigned long flags;
unsigned long j;
struct rcu_node *rnp_root = rcu_get_root();
static atomic_t warned = ATOMIC_INIT(0);
if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress() ||
ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
return;
j = jiffies; /* Expensive access, and in common case don't get here. */
if (time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
atomic_read(&warned))
return;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
j = jiffies;
if (rcu_gp_in_progress() ||
ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
atomic_read(&warned)) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
/* Hold onto the leaf lock to make others see warned==1. */
if (rnp_root != rnp)
raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
j = jiffies;
if (rcu_gp_in_progress() ||
ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
time_before(j, rcu_state.gp_req_activity + gpssdelay) ||
time_before(j, rcu_state.gp_activity + gpssdelay) ||
atomic_xchg(&warned, 1)) {
raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
WARN_ON(1);
if (rnp_root != rnp)
raw_spin_unlock_rcu_node(rnp_root);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
show_rcu_gp_kthreads();
}
/*
* Do a forward-progress check for rcutorture. This is normally invoked
* due to an OOM event. The argument "j" gives the time period during
* which rcutorture would like progress to have been made.
*/
void rcu_fwd_progress_check(unsigned long j)
{
unsigned long cbs;
int cpu;
unsigned long max_cbs = 0;
int max_cpu = -1;
struct rcu_data *rdp;
if (rcu_gp_in_progress()) {
pr_info("%s: GP age %lu jiffies\n",
__func__, jiffies - rcu_state.gp_start);
show_rcu_gp_kthreads();
} else {
pr_info("%s: Last GP end %lu jiffies ago\n",
__func__, jiffies - rcu_state.gp_end);
preempt_disable();
rdp = this_cpu_ptr(&rcu_data);
rcu_check_gp_start_stall(rdp->mynode, rdp, j);
preempt_enable();
}
for_each_possible_cpu(cpu) {
cbs = rcu_get_n_cbs_cpu(cpu);
if (!cbs)
continue;
if (max_cpu < 0)
pr_info("%s: callbacks", __func__);
pr_cont(" %d: %lu", cpu, cbs);
if (cbs <= max_cbs)
continue;
max_cbs = cbs;
max_cpu = cpu;
}
if (max_cpu >= 0)
pr_cont("\n");
}
EXPORT_SYMBOL_GPL(rcu_fwd_progress_check);
/* Perform RCU core processing work for the current CPU. */
static __latent_entropy void rcu_core(struct softirq_action *unused)
{
@@ -3559,13 +3081,11 @@ static int rcu_pm_notify(struct notifier_block *self,
switch (action) {
case PM_HIBERNATION_PREPARE:
case PM_SUSPEND_PREPARE:
if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
rcu_expedite_gp();
rcu_expedite_gp();
break;
case PM_POST_HIBERNATION:
case PM_POST_SUSPEND:
if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
rcu_unexpedite_gp();
rcu_unexpedite_gp();
break;
default:
break;
@@ -3742,8 +3262,7 @@ static void __init rcu_init_geometry(void)
jiffies_till_first_fqs = d;
if (jiffies_till_next_fqs == ULONG_MAX)
jiffies_till_next_fqs = d;
if (jiffies_till_sched_qs == ULONG_MAX)
adjust_jiffies_till_sched_qs();
adjust_jiffies_till_sched_qs();
/* If the compile-time values are accurate, just leave. */
if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
@@ -3858,5 +3377,6 @@ void __init rcu_init(void)
srcu_init();
}
#include "tree_stall.h"
#include "tree_exp.h"
#include "tree_plugin.h"

14
kernel/rcu/tree.h
View File

@@ -393,15 +393,13 @@ static const char *tp_rcu_varname __used __tracepoint_string = rcu_name;
int rcu_dynticks_snap(struct rcu_data *rdp);
/* Forward declarations for rcutree_plugin.h */
/* Forward declarations for tree_plugin.h */
static void rcu_bootup_announce(void);
static void rcu_qs(void);
static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
#ifdef CONFIG_HOTPLUG_CPU
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
static void rcu_print_detail_task_stall(void);
static int rcu_print_task_stall(struct rcu_node *rnp);
static int rcu_print_task_exp_stall(struct rcu_node *rnp);
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
static void rcu_flavor_sched_clock_irq(int user);
@@ -418,9 +416,6 @@ static void rcu_prepare_for_idle(void);
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
static void rcu_preempt_deferred_qs(struct task_struct *t);
static void print_cpu_stall_info_begin(void);
static void print_cpu_stall_info(int cpu);
static void print_cpu_stall_info_end(void);
static void zero_cpu_stall_ticks(struct rcu_data *rdp);
static bool rcu_nocb_cpu_needs_barrier(int cpu);
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
@@ -445,3 +440,10 @@ static void rcu_bind_gp_kthread(void);
static bool rcu_nohz_full_cpu(void);
static void rcu_dynticks_task_enter(void);
static void rcu_dynticks_task_exit(void);
/* Forward declarations for tree_stall.h */
static void record_gp_stall_check_time(void);
static void rcu_iw_handler(struct irq_work *iwp);
static void check_cpu_stall(struct rcu_data *rdp);
static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
const unsigned long gpssdelay);

36
kernel/rcu/tree_exp.h
View File

@@ -10,6 +10,7 @@
#include <linux/lockdep.h>
static void rcu_exp_handler(void *unused);
static int rcu_print_task_exp_stall(struct rcu_node *rnp);
/*
* Record the start of an expedited grace period.
@@ -633,7 +634,7 @@ static void rcu_exp_handler(void *unused)
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (rnp->expmask & rdp->grpmask) {
rdp->deferred_qs = true;
WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, true);
t->rcu_read_unlock_special.b.exp_hint = true;
}
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
@@ -648,7 +649,7 @@ static void rcu_exp_handler(void *unused)
*
* If the CPU is fully enabled (or if some buggy RCU-preempt
* read-side critical section is being used from idle), just
* invoke rcu_preempt_defer_qs() to immediately report the
* invoke rcu_preempt_deferred_qs() to immediately report the
* quiescent state. We cannot use rcu_read_unlock_special()
* because we are in an interrupt handler, which will cause that
* function to take an early exit without doing anything.
@@ -670,6 +671,27 @@ static void sync_sched_exp_online_cleanup(int cpu)
{
}
/*
* Scan the current list of tasks blocked within RCU read-side critical
* sections, printing out the tid of each that is blocking the current
* expedited grace period.
*/
static int rcu_print_task_exp_stall(struct rcu_node *rnp)
{
struct task_struct *t;
int ndetected = 0;
if (!rnp->exp_tasks)
return 0;
t = list_entry(rnp->exp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
pr_cont(" P%d", t->pid);
ndetected++;
}
return ndetected;
}
#else /* #ifdef CONFIG_PREEMPT_RCU */
/* Invoked on each online non-idle CPU for expedited quiescent state. */
@@ -709,6 +731,16 @@ static void sync_sched_exp_online_cleanup(int cpu)
WARN_ON_ONCE(ret);
}
/*
* Because preemptible RCU does not exist, we never have to check for
* tasks blocked within RCU read-side critical sections that are
* blocking the current expedited grace period.
*/
static int rcu_print_task_exp_stall(struct rcu_node *rnp)
{
return 0;
}
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
/**

257
kernel/rcu/tree_plugin.h
View File

@@ -285,7 +285,7 @@ static void rcu_qs(void)
TPS("cpuqs"));
__this_cpu_write(rcu_data.cpu_no_qs.b.norm, false);
barrier(); /* Coordinate with rcu_flavor_sched_clock_irq(). */
current->rcu_read_unlock_special.b.need_qs = false;
WRITE_ONCE(current->rcu_read_unlock_special.b.need_qs, false);
}
}
@@ -642,100 +642,6 @@ static void rcu_read_unlock_special(struct task_struct *t)
rcu_preempt_deferred_qs_irqrestore(t, flags);
}
/*
* Dump detailed information for all tasks blocking the current RCU
* grace period on the specified rcu_node structure.
*/
static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
{
unsigned long flags;
struct task_struct *t;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (!rcu_preempt_blocked_readers_cgp(rnp)) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
t = list_entry(rnp->gp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
/*
* We could be printing a lot while holding a spinlock.
* Avoid triggering hard lockup.
*/
touch_nmi_watchdog();
sched_show_task(t);
}
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
/*
* Dump detailed information for all tasks blocking the current RCU
* grace period.
*/
static void rcu_print_detail_task_stall(void)
{
struct rcu_node *rnp = rcu_get_root();
rcu_print_detail_task_stall_rnp(rnp);
rcu_for_each_leaf_node(rnp)
rcu_print_detail_task_stall_rnp(rnp);
}
static void rcu_print_task_stall_begin(struct rcu_node *rnp)
{
pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
rnp->level, rnp->grplo, rnp->grphi);
}
static void rcu_print_task_stall_end(void)
{
pr_cont("\n");
}
/*
* Scan the current list of tasks blocked within RCU read-side critical
* sections, printing out the tid of each.
*/
static int rcu_print_task_stall(struct rcu_node *rnp)
{
struct task_struct *t;
int ndetected = 0;
if (!rcu_preempt_blocked_readers_cgp(rnp))
return 0;
rcu_print_task_stall_begin(rnp);
t = list_entry(rnp->gp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
pr_cont(" P%d", t->pid);
ndetected++;
}
rcu_print_task_stall_end();
return ndetected;
}
/*
* Scan the current list of tasks blocked within RCU read-side critical
* sections, printing out the tid of each that is blocking the current
* expedited grace period.
*/
static int rcu_print_task_exp_stall(struct rcu_node *rnp)
{
struct task_struct *t;
int ndetected = 0;
if (!rnp->exp_tasks)
return 0;
t = list_entry(rnp->exp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
pr_cont(" P%d", t->pid);
ndetected++;
}
return ndetected;
}
/*
* Check that the list of blocked tasks for the newly completed grace
* period is in fact empty. It is a serious bug to complete a grace
@@ -804,19 +710,25 @@ static void rcu_flavor_sched_clock_irq(int user)
/*
* Check for a task exiting while in a preemptible-RCU read-side
* critical section, clean up if so. No need to issue warnings,
* as debug_check_no_locks_held() already does this if lockdep
* is enabled.
* critical section, clean up if so. No need to issue warnings, as
* debug_check_no_locks_held() already does this if lockdep is enabled.
* Besides, if this function does anything other than just immediately
* return, there was a bug of some sort. Spewing warnings from this
* function is like as not to simply obscure important prior warnings.
*/
void exit_rcu(void)
{
struct task_struct *t = current;
if (likely(list_empty(&current->rcu_node_entry)))
if (unlikely(!list_empty(&current->rcu_node_entry))) {
t->rcu_read_lock_nesting = 1;
barrier();
WRITE_ONCE(t->rcu_read_unlock_special.b.blocked, true);
} else if (unlikely(t->rcu_read_lock_nesting)) {
t->rcu_read_lock_nesting = 1;
} else {
return;
t->rcu_read_lock_nesting = 1;
barrier();
t->rcu_read_unlock_special.b.blocked = true;
}
__rcu_read_unlock();
rcu_preempt_deferred_qs(current);
}
@@ -979,33 +891,6 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
}
static void rcu_preempt_deferred_qs(struct task_struct *t) { }
/*
* Because preemptible RCU does not exist, we never have to check for
* tasks blocked within RCU read-side critical sections.
*/
static void rcu_print_detail_task_stall(void)
{
}
/*
* Because preemptible RCU does not exist, we never have to check for
* tasks blocked within RCU read-side critical sections.
*/
static int rcu_print_task_stall(struct rcu_node *rnp)
{
return 0;
}
/*
* Because preemptible RCU does not exist, we never have to check for
* tasks blocked within RCU read-side critical sections that are
* blocking the current expedited grace period.
*/
static int rcu_print_task_exp_stall(struct rcu_node *rnp)
{
return 0;
}
/*
* Because there is no preemptible RCU, there can be no readers blocked,
* so there is no need to check for blocked tasks. So check only for
@@ -1185,8 +1070,6 @@ static int rcu_boost_kthread(void *arg)
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
__releases(rnp->lock)
{
struct task_struct *t;
raw_lockdep_assert_held_rcu_node(rnp);
if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -1200,9 +1083,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
if (rnp->exp_tasks == NULL)
rnp->boost_tasks = rnp->gp_tasks;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
t = rnp->boost_kthread_task;
if (t)
rcu_wake_cond(t, rnp->boost_kthread_status);
rcu_wake_cond(rnp->boost_kthread_task,
rnp->boost_kthread_status);
} else {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
@@ -1649,98 +1531,6 @@ static void rcu_cleanup_after_idle(void)
#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
#ifdef CONFIG_RCU_FAST_NO_HZ
static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
{
struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c",
rdp->last_accelerate & 0xffff, jiffies & 0xffff,
".l"[rdp->all_lazy],
".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)],
".D"[!rdp->tick_nohz_enabled_snap]);
}
#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
{
*cp = '\0';
}
#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */
/* Initiate the stall-info list. */
static void print_cpu_stall_info_begin(void)
{
pr_cont("\n");
}
/*
* Print out diagnostic information for the specified stalled CPU.
*
* If the specified CPU is aware of the current RCU grace period, then
* print the number of scheduling clock interrupts the CPU has taken
* during the time that it has been aware. Otherwise, print the number
* of RCU grace periods that this CPU is ignorant of, for example, "1"
* if the CPU was aware of the previous grace period.
*
* Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info.
*/
static void print_cpu_stall_info(int cpu)
{
unsigned long delta;
char fast_no_hz[72];
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
char *ticks_title;
unsigned long ticks_value;
/*
* We could be printing a lot while holding a spinlock. Avoid
* triggering hard lockup.
*/
touch_nmi_watchdog();
ticks_value = rcu_seq_ctr(rcu_state.gp_seq - rdp->gp_seq);
if (ticks_value) {
ticks_title = "GPs behind";
} else {
ticks_title = "ticks this GP";
ticks_value = rdp->ticks_this_gp;
}
print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
cpu,
"O."[!!cpu_online(cpu)],
"o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
"N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)],
!IS_ENABLED(CONFIG_IRQ_WORK) ? '?' :
rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' :
"!."[!delta],
ticks_value, ticks_title,
rcu_dynticks_snap(rdp) & 0xfff,
rdp->dynticks_nesting, rdp->dynticks_nmi_nesting,
rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
READ_ONCE(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
fast_no_hz);
}
/* Terminate the stall-info list. */
static void print_cpu_stall_info_end(void)
{
pr_err("\t");
}
/* Zero ->ticks_this_gp and snapshot the number of RCU softirq handlers. */
static void zero_cpu_stall_ticks(struct rcu_data *rdp)
{
rdp->ticks_this_gp = 0;
rdp->softirq_snap = kstat_softirqs_cpu(RCU_SOFTIRQ, smp_processor_id());
WRITE_ONCE(rdp->last_fqs_resched, jiffies);
}
#ifdef CONFIG_RCU_NOCB_CPU
/*
@@ -1766,11 +1556,22 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp)
*/
/* Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters. */
/*
* Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters.
* The string after the "rcu_nocbs=" is either "all" for all CPUs, or a
* comma-separated list of CPUs and/or CPU ranges. If an invalid list is
* given, a warning is emitted and all CPUs are offloaded.
*/
static int __init rcu_nocb_setup(char *str)
{
alloc_bootmem_cpumask_var(&rcu_nocb_mask);
cpulist_parse(str, rcu_nocb_mask);
if (!strcasecmp(str, "all"))
cpumask_setall(rcu_nocb_mask);
else
if (cpulist_parse(str, rcu_nocb_mask)) {
pr_warn("rcu_nocbs= bad CPU range, all CPUs set\n");
cpumask_setall(rcu_nocb_mask);
}
return 1;
}
__setup("rcu_nocbs=", rcu_nocb_setup);

709
kernel/rcu/tree_stall.h Normal file
View File

@@ -0,0 +1,709 @@
// SPDX-License-Identifier: GPL-2.0+
/*
* RCU CPU stall warnings for normal RCU grace periods
*
* Copyright IBM Corporation, 2019
*
* Author: Paul E. McKenney <paulmck@linux.ibm.com>
*/
//////////////////////////////////////////////////////////////////////////////
//
// Controlling CPU stall warnings, including delay calculation.
/* panic() on RCU Stall sysctl. */
int sysctl_panic_on_rcu_stall __read_mostly;
#ifdef CONFIG_PROVE_RCU
#define RCU_STALL_DELAY_DELTA (5 * HZ)
#else
#define RCU_STALL_DELAY_DELTA 0
#endif
/* Limit-check stall timeouts specified at boottime and runtime. */
int rcu_jiffies_till_stall_check(void)
{
int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout);
/*
* Limit check must be consistent with the Kconfig limits
* for CONFIG_RCU_CPU_STALL_TIMEOUT.
*/
if (till_stall_check < 3) {
WRITE_ONCE(rcu_cpu_stall_timeout, 3);
till_stall_check = 3;
} else if (till_stall_check > 300) {
WRITE_ONCE(rcu_cpu_stall_timeout, 300);
till_stall_check = 300;
}
return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
}
EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check);
/* Don't do RCU CPU stall warnings during long sysrq printouts. */
void rcu_sysrq_start(void)
{
if (!rcu_cpu_stall_suppress)
rcu_cpu_stall_suppress = 2;
}
void rcu_sysrq_end(void)
{
if (rcu_cpu_stall_suppress == 2)
rcu_cpu_stall_suppress = 0;
}
/* Don't print RCU CPU stall warnings during a kernel panic. */
static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
{
rcu_cpu_stall_suppress = 1;
return NOTIFY_DONE;
}
static struct notifier_block rcu_panic_block = {
.notifier_call = rcu_panic,
};
static int __init check_cpu_stall_init(void)
{
atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
return 0;
}
early_initcall(check_cpu_stall_init);
/* If so specified via sysctl, panic, yielding cleaner stall-warning output. */
static void panic_on_rcu_stall(void)
{
if (sysctl_panic_on_rcu_stall)
panic("RCU Stall\n");
}
/**
* rcu_cpu_stall_reset - prevent further stall warnings in current grace period
*
* Set the stall-warning timeout way off into the future, thus preventing
* any RCU CPU stall-warning messages from appearing in the current set of
* RCU grace periods.
*
* The caller must disable hard irqs.
*/
void rcu_cpu_stall_reset(void)
{
WRITE_ONCE(rcu_state.jiffies_stall, jiffies + ULONG_MAX / 2);
}
//////////////////////////////////////////////////////////////////////////////
//
// Interaction with RCU grace periods
/* Start of new grace period, so record stall time (and forcing times). */
static void record_gp_stall_check_time(void)
{
unsigned long j = jiffies;
unsigned long j1;
rcu_state.gp_start = j;
j1 = rcu_jiffies_till_stall_check();
/* Record ->gp_start before ->jiffies_stall. */
smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */
rcu_state.jiffies_resched = j + j1 / 2;
rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs);
}
/* Zero ->ticks_this_gp and snapshot the number of RCU softirq handlers. */
static void zero_cpu_stall_ticks(struct rcu_data *rdp)
{
rdp->ticks_this_gp = 0;
rdp->softirq_snap = kstat_softirqs_cpu(RCU_SOFTIRQ, smp_processor_id());
WRITE_ONCE(rdp->last_fqs_resched, jiffies);
}
/*
* If too much time has passed in the current grace period, and if
* so configured, go kick the relevant kthreads.
*/
static void rcu_stall_kick_kthreads(void)
{
unsigned long j;
if (!rcu_kick_kthreads)
return;
j = READ_ONCE(rcu_state.jiffies_kick_kthreads);
if (time_after(jiffies, j) && rcu_state.gp_kthread &&
(rcu_gp_in_progress() || READ_ONCE(rcu_state.gp_flags))) {
WARN_ONCE(1, "Kicking %s grace-period kthread\n",
rcu_state.name);
rcu_ftrace_dump(DUMP_ALL);
wake_up_process(rcu_state.gp_kthread);
WRITE_ONCE(rcu_state.jiffies_kick_kthreads, j + HZ);
}
}
/*
* Handler for the irq_work request posted about halfway into the RCU CPU
* stall timeout, and used to detect excessive irq disabling. Set state
* appropriately, but just complain if there is unexpected state on entry.
*/
static void rcu_iw_handler(struct irq_work *iwp)
{
struct rcu_data *rdp;
struct rcu_node *rnp;
rdp = container_of(iwp, struct rcu_data, rcu_iw);
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp);
if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) {
rdp->rcu_iw_gp_seq = rnp->gp_seq;
rdp->rcu_iw_pending = false;
}
raw_spin_unlock_rcu_node(rnp);
}
//////////////////////////////////////////////////////////////////////////////
//
// Printing RCU CPU stall warnings
#ifdef CONFIG_PREEMPT
/*
* Dump detailed information for all tasks blocking the current RCU
* grace period on the specified rcu_node structure.
*/
static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
{
unsigned long flags;
struct task_struct *t;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (!rcu_preempt_blocked_readers_cgp(rnp)) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
t = list_entry(rnp->gp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
/*
* We could be printing a lot while holding a spinlock.
* Avoid triggering hard lockup.
*/
touch_nmi_watchdog();
sched_show_task(t);
}
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
/*
* Scan the current list of tasks blocked within RCU read-side critical
* sections, printing out the tid of each.
*/
static int rcu_print_task_stall(struct rcu_node *rnp)
{
struct task_struct *t;
int ndetected = 0;
if (!rcu_preempt_blocked_readers_cgp(rnp))
return 0;
pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
rnp->level, rnp->grplo, rnp->grphi);
t = list_entry(rnp->gp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
pr_cont(" P%d", t->pid);
ndetected++;
}
pr_cont("\n");
return ndetected;
}
#else /* #ifdef CONFIG_PREEMPT */
/*
* Because preemptible RCU does not exist, we never have to check for
* tasks blocked within RCU read-side critical sections.
*/
static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
{
}
/*
* Because preemptible RCU does not exist, we never have to check for
* tasks blocked within RCU read-side critical sections.
*/
static int rcu_print_task_stall(struct rcu_node *rnp)
{
return 0;
}
#endif /* #else #ifdef CONFIG_PREEMPT */
/*
* Dump stacks of all tasks running on stalled CPUs. First try using
* NMIs, but fall back to manual remote stack tracing on architectures
* that don't support NMI-based stack dumps. The NMI-triggered stack
* traces are more accurate because they are printed by the target CPU.
*/
static void rcu_dump_cpu_stacks(void)
{
int cpu;
unsigned long flags;
struct rcu_node *rnp;
rcu_for_each_leaf_node(rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
for_each_leaf_node_possible_cpu(rnp, cpu)
if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
if (!trigger_single_cpu_backtrace(cpu))
dump_cpu_task(cpu);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
}
#ifdef CONFIG_RCU_FAST_NO_HZ
static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
{
struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c",
rdp->last_accelerate & 0xffff, jiffies & 0xffff,
".l"[rdp->all_lazy],
".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)],
".D"[!!rdp->tick_nohz_enabled_snap]);
}
#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
{
*cp = '\0';
}
#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */
/*
* Print out diagnostic information for the specified stalled CPU.
*
* If the specified CPU is aware of the current RCU grace period, then
* print the number of scheduling clock interrupts the CPU has taken
* during the time that it has been aware. Otherwise, print the number
* of RCU grace periods that this CPU is ignorant of, for example, "1"
* if the CPU was aware of the previous grace period.
*
* Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info.
*/
static void print_cpu_stall_info(int cpu)
{
unsigned long delta;
char fast_no_hz[72];
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
char *ticks_title;
unsigned long ticks_value;
/*
* We could be printing a lot while holding a spinlock. Avoid
* triggering hard lockup.
*/
touch_nmi_watchdog();
ticks_value = rcu_seq_ctr(rcu_state.gp_seq - rdp->gp_seq);
if (ticks_value) {
ticks_title = "GPs behind";
} else {
ticks_title = "ticks this GP";
ticks_value = rdp->ticks_this_gp;
}
print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
cpu,
"O."[!!cpu_online(cpu)],
"o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
"N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)],
!IS_ENABLED(CONFIG_IRQ_WORK) ? '?' :
rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' :
"!."[!delta],
ticks_value, ticks_title,
rcu_dynticks_snap(rdp) & 0xfff,
rdp->dynticks_nesting, rdp->dynticks_nmi_nesting,
rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
READ_ONCE(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
fast_no_hz);
}
/* Complain about starvation of grace-period kthread. */
static void rcu_check_gp_kthread_starvation(void)
{
struct task_struct *gpk = rcu_state.gp_kthread;
unsigned long j;
j = jiffies - READ_ONCE(rcu_state.gp_activity);
if (j > 2 * HZ) {
pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
rcu_state.name, j,
(long)rcu_seq_current(&rcu_state.gp_seq),
READ_ONCE(rcu_state.gp_flags),
gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
if (gpk) {
pr_err("RCU grace-period kthread stack dump:\n");
sched_show_task(gpk);
wake_up_process(gpk);
}
}
}
static void print_other_cpu_stall(unsigned long gp_seq)
{
int cpu;
unsigned long flags;
unsigned long gpa;
unsigned long j;
int ndetected = 0;
struct rcu_node *rnp;
long totqlen = 0;
/* Kick and suppress, if so configured. */
rcu_stall_kick_kthreads();
if (rcu_cpu_stall_suppress)
return;
/*
* OK, time to rat on our buddy...
* See Documentation/RCU/stallwarn.txt for info on how to debug
* RCU CPU stall warnings.
*/
pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name);
rcu_for_each_leaf_node(rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
ndetected += rcu_print_task_stall(rnp);
if (rnp->qsmask != 0) {
for_each_leaf_node_possible_cpu(rnp, cpu)
if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
print_cpu_stall_info(cpu);
ndetected++;
}
}
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
for_each_possible_cpu(cpu)
totqlen += rcu_get_n_cbs_cpu(cpu);
pr_cont("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
smp_processor_id(), (long)(jiffies - rcu_state.gp_start),
(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
if (ndetected) {
rcu_dump_cpu_stacks();
/* Complain about tasks blocking the grace period. */
rcu_for_each_leaf_node(rnp)
rcu_print_detail_task_stall_rnp(rnp);
} else {
if (rcu_seq_current(&rcu_state.gp_seq) != gp_seq) {
pr_err("INFO: Stall ended before state dump start\n");
} else {
j = jiffies;
gpa = READ_ONCE(rcu_state.gp_activity);
pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
rcu_state.name, j - gpa, j, gpa,
READ_ONCE(jiffies_till_next_fqs),
rcu_get_root()->qsmask);
/* In this case, the current CPU might be at fault. */
sched_show_task(current);
}
}
/* Rewrite if needed in case of slow consoles. */
if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
WRITE_ONCE(rcu_state.jiffies_stall,
jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
rcu_check_gp_kthread_starvation();
panic_on_rcu_stall();
rcu_force_quiescent_state(); /* Kick them all. */
}
static void print_cpu_stall(void)
{
int cpu;
unsigned long flags;
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rcu_get_root();
long totqlen = 0;
/* Kick and suppress, if so configured. */
rcu_stall_kick_kthreads();
if (rcu_cpu_stall_suppress)
return;
/*
* OK, time to rat on ourselves...
* See Documentation/RCU/stallwarn.txt for info on how to debug
* RCU CPU stall warnings.
*/
pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name);
raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags);
print_cpu_stall_info(smp_processor_id());
raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags);
for_each_possible_cpu(cpu)
totqlen += rcu_get_n_cbs_cpu(cpu);
pr_cont("\t(t=%lu jiffies g=%ld q=%lu)\n",
jiffies - rcu_state.gp_start,
(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
rcu_check_gp_kthread_starvation();
rcu_dump_cpu_stacks();
raw_spin_lock_irqsave_rcu_node(rnp, flags);
/* Rewrite if needed in case of slow consoles. */
if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
WRITE_ONCE(rcu_state.jiffies_stall,
jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
panic_on_rcu_stall();
/*
* Attempt to revive the RCU machinery by forcing a context switch.
*
* A context switch would normally allow the RCU state machine to make
* progress and it could be we're stuck in kernel space without context
* switches for an entirely unreasonable amount of time.
*/
set_tsk_need_resched(current);
set_preempt_need_resched();
}
static void check_cpu_stall(struct rcu_data *rdp)
{
unsigned long gs1;
unsigned long gs2;
unsigned long gps;
unsigned long j;
unsigned long jn;
unsigned long js;
struct rcu_node *rnp;
if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) ||
!rcu_gp_in_progress())
return;
rcu_stall_kick_kthreads();
j = jiffies;
/*
* Lots of memory barriers to reject false positives.
*
* The idea is to pick up rcu_state.gp_seq, then
* rcu_state.jiffies_stall, then rcu_state.gp_start, and finally
* another copy of rcu_state.gp_seq. These values are updated in
* the opposite order with memory barriers (or equivalent) during
* grace-period initialization and cleanup. Now, a false positive
* can occur if we get an new value of rcu_state.gp_start and a old
* value of rcu_state.jiffies_stall. But given the memory barriers,
* the only way that this can happen is if one grace period ends
* and another starts between these two fetches. This is detected
* by comparing the second fetch of rcu_state.gp_seq with the
* previous fetch from rcu_state.gp_seq.
*
* Given this check, comparisons of jiffies, rcu_state.jiffies_stall,
* and rcu_state.gp_start suffice to forestall false positives.
*/
gs1 = READ_ONCE(rcu_state.gp_seq);
smp_rmb(); /* Pick up ->gp_seq first... */
js = READ_ONCE(rcu_state.jiffies_stall);
smp_rmb(); /* ...then ->jiffies_stall before the rest... */
gps = READ_ONCE(rcu_state.gp_start);
smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */
gs2 = READ_ONCE(rcu_state.gp_seq);
if (gs1 != gs2 ||
ULONG_CMP_LT(j, js) ||
ULONG_CMP_GE(gps, js))
return; /* No stall or GP completed since entering function. */
rnp = rdp->mynode;
jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
if (rcu_gp_in_progress() &&
(READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
/* We haven't checked in, so go dump stack. */
print_cpu_stall();
} else if (rcu_gp_in_progress() &&
ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
/* They had a few time units to dump stack, so complain. */
print_other_cpu_stall(gs2);
}
}
//////////////////////////////////////////////////////////////////////////////
//
// RCU forward-progress mechanisms, including of callback invocation.
/*
* Show the state of the grace-period kthreads.
*/
void show_rcu_gp_kthreads(void)
{
int cpu;
unsigned long j;
unsigned long ja;
unsigned long jr;
unsigned long jw;
struct rcu_data *rdp;
struct rcu_node *rnp;
j = jiffies;
ja = j - READ_ONCE(rcu_state.gp_activity);
jr = j - READ_ONCE(rcu_state.gp_req_activity);
jw = j - READ_ONCE(rcu_state.gp_wake_time);
pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
rcu_state.name, gp_state_getname(rcu_state.gp_state),
rcu_state.gp_state,
rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL,
ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
(long)READ_ONCE(rcu_state.gp_seq),
(long)READ_ONCE(rcu_get_root()->gp_seq_needed),
READ_ONCE(rcu_state.gp_flags));
rcu_for_each_node_breadth_first(rnp) {
if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
continue;
pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
rnp->grplo, rnp->grphi, (long)rnp->gp_seq,
(long)rnp->gp_seq_needed);
if (!rcu_is_leaf_node(rnp))
continue;
for_each_leaf_node_possible_cpu(rnp, cpu) {
rdp = per_cpu_ptr(&rcu_data, cpu);
if (rdp->gpwrap ||
ULONG_CMP_GE(rcu_state.gp_seq,
rdp->gp_seq_needed))
continue;
pr_info("\tcpu %d ->gp_seq_needed %ld\n",
cpu, (long)rdp->gp_seq_needed);
}
}
/* sched_show_task(rcu_state.gp_kthread); */
}
EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
/*
* This function checks for grace-period requests that fail to motivate
* RCU to come out of its idle mode.
*/
static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
const unsigned long gpssdelay)
{
unsigned long flags;
unsigned long j;
struct rcu_node *rnp_root = rcu_get_root();
static atomic_t warned = ATOMIC_INIT(0);
if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress() ||
ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
return;
j = jiffies; /* Expensive access, and in common case don't get here. */
if (time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
atomic_read(&warned))
return;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
j = jiffies;
if (rcu_gp_in_progress() ||
ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
atomic_read(&warned)) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
/* Hold onto the leaf lock to make others see warned==1. */
if (rnp_root != rnp)
raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
j = jiffies;
if (rcu_gp_in_progress() ||
ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
time_before(j, rcu_state.gp_req_activity + gpssdelay) ||
time_before(j, rcu_state.gp_activity + gpssdelay) ||
atomic_xchg(&warned, 1)) {
raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
WARN_ON(1);
if (rnp_root != rnp)
raw_spin_unlock_rcu_node(rnp_root);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
show_rcu_gp_kthreads();
}
/*
* Do a forward-progress check for rcutorture. This is normally invoked
* due to an OOM event. The argument "j" gives the time period during
* which rcutorture would like progress to have been made.
*/
void rcu_fwd_progress_check(unsigned long j)
{
unsigned long cbs;
int cpu;
unsigned long max_cbs = 0;
int max_cpu = -1;
struct rcu_data *rdp;
if (rcu_gp_in_progress()) {
pr_info("%s: GP age %lu jiffies\n",
__func__, jiffies - rcu_state.gp_start);
show_rcu_gp_kthreads();
} else {
pr_info("%s: Last GP end %lu jiffies ago\n",
__func__, jiffies - rcu_state.gp_end);
preempt_disable();
rdp = this_cpu_ptr(&rcu_data);
rcu_check_gp_start_stall(rdp->mynode, rdp, j);
preempt_enable();
}
for_each_possible_cpu(cpu) {
cbs = rcu_get_n_cbs_cpu(cpu);
if (!cbs)
continue;
if (max_cpu < 0)
pr_info("%s: callbacks", __func__);
pr_cont(" %d: %lu", cpu, cbs);
if (cbs <= max_cbs)
continue;
max_cbs = cbs;
max_cpu = cpu;
}
if (max_cpu >= 0)
pr_cont("\n");
}
EXPORT_SYMBOL_GPL(rcu_fwd_progress_check);
/* Commandeer a sysrq key to dump RCU's tree. */
static bool sysrq_rcu;
module_param(sysrq_rcu, bool, 0444);
/* Dump grace-period-request information due to commandeered sysrq. */
static void sysrq_show_rcu(int key)
{
show_rcu_gp_kthreads();
}
static struct sysrq_key_op sysrq_rcudump_op = {
.handler = sysrq_show_rcu,
.help_msg = "show-rcu(y)",
.action_msg = "Show RCU tree",
.enable_mask = SYSRQ_ENABLE_DUMP,
};
static int __init rcu_sysrq_init(void)
{
if (sysrq_rcu)
return register_sysrq_key('y', &sysrq_rcudump_op);
return 0;
}
early_initcall(rcu_sysrq_init);

59
kernel/rcu/update.c
View File

@@ -424,68 +424,11 @@ EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read);
#endif
#ifdef CONFIG_RCU_STALL_COMMON
#ifdef CONFIG_PROVE_RCU
#define RCU_STALL_DELAY_DELTA (5 * HZ)
#else
#define RCU_STALL_DELAY_DELTA 0
#endif
int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
static int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
module_param(rcu_cpu_stall_suppress, int, 0644);
int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
module_param(rcu_cpu_stall_timeout, int, 0644);
int rcu_jiffies_till_stall_check(void)
{
int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout);
/*
* Limit check must be consistent with the Kconfig limits
* for CONFIG_RCU_CPU_STALL_TIMEOUT.
*/
if (till_stall_check < 3) {
WRITE_ONCE(rcu_cpu_stall_timeout, 3);
till_stall_check = 3;
} else if (till_stall_check > 300) {
WRITE_ONCE(rcu_cpu_stall_timeout, 300);
till_stall_check = 300;
}
return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
}
EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check);
void rcu_sysrq_start(void)
{
if (!rcu_cpu_stall_suppress)
rcu_cpu_stall_suppress = 2;
}
void rcu_sysrq_end(void)
{
if (rcu_cpu_stall_suppress == 2)
rcu_cpu_stall_suppress = 0;
}
static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
{
rcu_cpu_stall_suppress = 1;
return NOTIFY_DONE;
}
static struct notifier_block rcu_panic_block = {
.notifier_call = rcu_panic,
};
static int __init check_cpu_stall_init(void)
{
atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
return 0;
}
early_initcall(check_cpu_stall_init);
#endif /* #ifdef CONFIG_RCU_STALL_COMMON */
#ifdef CONFIG_TASKS_RCU

2
kernel/torture.c
View File

@@ -88,6 +88,8 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
return false;
if (num_online_cpus() <= 1)
return false; /* Can't offline the last CPU. */
if (verbose > 1)
pr_alert("%s" TORTURE_FLAG