Commit ac1bea85781e (Make cond_resched() report RCU quiescent states)
fixed a problem where a CPU looping in the kernel with but one runnable
task would give RCU CPU stall warnings, even if the in-kernel loop
contained cond_resched() calls. Unfortunately, in so doing, it introduced
performance regressions in Anton Blanchard's will-it-scale "open1" test.
The problem appears to be not so much the increased cond_resched() path
length as an increase in the rate at which grace periods complete, which
increased per-update grace-period overhead.
This commit takes a different approach to fixing this bug, mainly by
moving the RCU-visible quiescent state from cond_resched() to
rcu_note_context_switch(), and by further reducing the check to a
simple non-zero test of a single per-CPU variable. However, this
approach requires that the force-quiescent-state processing send
resched IPIs to the offending CPUs. These will be sent only once
the grace period has reached an age specified by the boot/sysfs
parameter rcutree.jiffies_till_sched_qs, or once the grace period
reaches an age halfway to the point at which RCU CPU stall warnings
will be emitted, whichever comes first.
Reported-by: Dave Hansen <dave.han...@intel.com>
Signed-off-by: Paul E. McKenney <paul...@linux.vnet.ibm.com>
Cc: Josh Triplett <j...@joshtriplett.org>
Cc: Andi Kleen <a...@linux.intel.com>
Cc: Christoph Lameter <c...@gentwo.org>
Cc: Mike Galbraith <umgwanakikb...@gmail.com>
Cc: Eric Dumazet <eric.duma...@gmail.com>
---
b/Documentation/kernel-parameters.txt | 6 +
b/include/linux/rcupdate.h | 36 --------
b/kernel/rcu/tree.c | 140 +++++++++++++++++++++++++++-------
b/kernel/rcu/tree.h | 6 +
b/kernel/rcu/tree_plugin.h | 2
b/kernel/rcu/update.c | 18 ----
b/kernel/sched/core.c | 7 -
7 files changed, 125 insertions(+), 90 deletions(-)
diff --git a/Documentation/kernel-parameters.txt
b/Documentation/kernel-parameters.txt
index 6eaa9cdb7094..910c3829f81d 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2785,6 +2785,12 @@ bytes respectively. Such letter suffixes can also be
entirely omitted.
leaf rcu_node structure. Useful for very large
systems.
+ rcutree.jiffies_till_sched_qs= [KNL]
+ Set required age in jiffies for a
+ given grace period before RCU starts
+ soliciting quiescent-state help from
+ rcu_note_context_switch().
+
rcutree.jiffies_till_first_fqs= [KNL]
Set delay from grace-period initialization to
first attempt to force quiescent states.
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 5a75d19aa661..243aa4656cb7 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -44,7 +44,6 @@
#include <linux/debugobjects.h>
#include <linux/bug.h>
#include <linux/compiler.h>
-#include <linux/percpu.h>
#include <asm/barrier.h>
extern int rcu_expedited; /* for sysctl */
@@ -300,41 +299,6 @@ bool __rcu_is_watching(void);
#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) ||
defined(CONFIG_SMP) */
/*
- * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings.
- */
-
-#define RCU_COND_RESCHED_LIM 256 /* ms vs. 100s of ms. */
-DECLARE_PER_CPU(int, rcu_cond_resched_count);
-void rcu_resched(void);
-
-/*
- * Is it time to report RCU quiescent states?
- *
- * Note unsynchronized access to rcu_cond_resched_count. Yes, we might
- * increment some random CPU's count, and possibly also load the result from
- * yet another CPU's count. We might even clobber some other CPU's attempt
- * to zero its counter. This is all OK because the goal is not precision,
- * but rather reasonable amortization of rcu_note_context_switch() overhead
- * and extremely high probability of avoiding RCU CPU stall warnings.
- * Note that this function has to be preempted in just the wrong place,
- * many thousands of times in a row, for anything bad to happen.
- */
-static inline bool rcu_should_resched(void)
-{
- return raw_cpu_inc_return(rcu_cond_resched_count) >=
- RCU_COND_RESCHED_LIM;
-}
-
-/*
- * Report quiscent states to RCU if it is time to do so.
- */
-static inline void rcu_cond_resched(void)
-{
- if (unlikely(rcu_should_resched()))
- rcu_resched();
-}
-
-/*
* Infrastructure to implement the synchronize_() primitives in
* TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
*/
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f1ba77363fbb..7d711f9a2e86 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -206,6 +206,70 @@ void rcu_bh_qs(int cpu)
rdp->passed_quiesce = 1;
}
+static DEFINE_PER_CPU(int, rcu_sched_qs_mask);
+
+static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
+ .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
+ .dynticks = ATOMIC_INIT(1),
+#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
+ .dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE,
+ .dynticks_idle = ATOMIC_INIT(1),
+#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+};
+
+/*
+ * Let the RCU core know that this CPU has gone through the scheduler,
+ * which is a quiescent state. This is called when the need for a
+ * quiescent state is urgent, so we burn an atomic operation and full
+ * memory barriers to let the RCU core know about it, regardless of what
+ * this CPU might (or might not) do in the near future.
+ *
+ * We inform the RCU core by emulating a zero-duration dyntick-idle
+ * period, which we in turn do by incrementing the ->dynticks counter
+ * by two.
+ */
+void rcu_momentary_dyntick_idle(void)
+{
+ unsigned long flags;
+ struct rcu_data *rdp;
+ struct rcu_dynticks *rdtp;
+ int resched_mask;
+ struct rcu_state *rsp;
+
+ local_irq_save(flags);
+
+ /*
+ * Yes, we can lose flag-setting operations. This is OK, because
+ * the flag will be set again after some delay.
+ */
+ resched_mask = raw_cpu_read(rcu_sched_qs_mask);
+ raw_cpu_write(rcu_sched_qs_mask, 0);
+
+ /* Find the flavor that needs a quiescent state. */
+ for_each_rcu_flavor(rsp) {
+ rdp = raw_cpu_ptr(rsp->rda);
+ if (!(resched_mask & rsp->flavor_mask))
+ continue;
+ smp_mb(); /* ->flavor_mask before ->cond_resched_completed. */
+ if (ACCESS_ONCE(rdp->mynode->completed) !=
+ ACCESS_ONCE(rdp->cond_resched_completed))
+ continue;
+
+ /*
+ * Pretend to be momentarily idle for the quiescent state.
+ * This allows the grace-period kthread to record the
+ * quiescent state, with no need for this CPU to do anything
+ * further.
+ */
+ rdtp = this_cpu_ptr(&rcu_dynticks);
+ smp_mb__before_atomic(); /* Earlier stuff before QS. */
+ atomic_add(2, &rdtp->dynticks); /* QS. */
+ smp_mb__after_atomic(); /* Later stuff after QS. */
+ break;
+ }
+ local_irq_restore(flags);
+}
+
/*
* Note a context switch. This is a quiescent state for RCU-sched,
* and requires special handling for preemptible RCU.
@@ -216,19 +280,12 @@ void rcu_note_context_switch(int cpu)
trace_rcu_utilization(TPS("Start context switch"));
rcu_sched_qs(cpu);
rcu_preempt_note_context_switch(cpu);
+ if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
+ rcu_momentary_dyntick_idle();
trace_rcu_utilization(TPS("End context switch"));
}
EXPORT_SYMBOL_GPL(rcu_note_context_switch);
-static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
- .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
- .dynticks = ATOMIC_INIT(1),
-#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
- .dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE,
- .dynticks_idle = ATOMIC_INIT(1),
-#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
-};
-
static long blimit = 10; /* Maximum callbacks per rcu_do_batch. */
static long qhimark = 10000; /* If this many pending, ignore blimit. */
static long qlowmark = 100; /* Once only this many pending, use blimit. */
@@ -243,6 +300,13 @@ static ulong jiffies_till_next_fqs = ULONG_MAX;
module_param(jiffies_till_first_fqs, ulong, 0644);
module_param(jiffies_till_next_fqs, ulong, 0644);
+/*
+ * How long the grace period must be before we start recruiting
+ * quiescent-state help from rcu_note_context_switch().
+ */
+static ulong jiffies_till_sched_qs = HZ / 20;
+module_param(jiffies_till_sched_qs, ulong, 0644);
+
static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
struct rcu_data *rdp);
static void force_qs_rnp(struct rcu_state *rsp,
@@ -853,6 +917,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
bool *isidle, unsigned long *maxj)
{
unsigned int curr;
+ int *rcrmp;
unsigned int snap;
curr = (unsigned int)atomic_add_return(0, &rdp->dynticks->dynticks);
@@ -893,27 +958,43 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
}
/*
- * There is a possibility that a CPU in adaptive-ticks state
- * might run in the kernel with the scheduling-clock tick disabled
- * for an extended time period. Invoke rcu_kick_nohz_cpu() to
- * force the CPU to restart the scheduling-clock tick in this
- * CPU is in this state.
- */
- rcu_kick_nohz_cpu(rdp->cpu);
-
- /*
- * Alternatively, the CPU might be running in the kernel
- * for an extended period of time without a quiescent state.
- * Attempt to force the CPU through the scheduler to gain the
- * needed quiescent state, but only if the grace period has gone
- * on for an uncommonly long time. If there are many stuck CPUs,
- * we will beat on the first one until it gets unstuck, then move
- * to the next. Only do this for the primary flavor of RCU.
+ * A CPU running for an extended time within the kernel can
+ * delay RCU grace periods. When the CPU is in NO_HZ_FULL mode,
+ * even context-switching back and forth between a pair of
+ * in-kernel CPU-bound tasks cannot advance grace periods.
+ * So if the grace period is old enough, make the CPU pay attention.
+ * Note that the unsynchronized assignments to the per-CPU
+ * rcu_sched_qs_mask variable are safe. Yes, setting of
+ * bits can be lost, but they will be set again on the next
+ * force-quiescent-state pass. So lost bit sets do not result
+ * in incorrect behavior, merely in a grace period lasting
+ * a few jiffies longer than it might otherwise. Because
+ * there are at most four threads involved, and because the
+ * updates are only once every few jiffies, the probability of
+ * lossage (and thus of slight grace-period extension) is
+ * quite low.
+ *
+ * Note that if the jiffies_till_sched_qs boot/sysfs parameter
+ * is set too high, we override with half of the RCU CPU stall
+ * warning delay.
*/
- if (rdp->rsp == rcu_state_p &&
+ rcrmp = &per_cpu(rcu_sched_qs_mask, rdp->cpu);
+ if (ULONG_CMP_GE(jiffies,
+ rdp->rsp->gp_start + jiffies_till_sched_qs) ||
ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
- rdp->rsp->jiffies_resched += 5;
- resched_cpu(rdp->cpu);
+ if (!(ACCESS_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
+ ACCESS_ONCE(rdp->cond_resched_completed) =
+ ACCESS_ONCE(rdp->mynode->completed);
+ smp_mb(); /* ->cond_resched_completed before *rcrmp. */
+ ACCESS_ONCE(*rcrmp) =
+ ACCESS_ONCE(*rcrmp) + rdp->rsp->flavor_mask;
+ resched_cpu(rdp->cpu); /* Force CPU into scheduler. */
+ rdp->rsp->jiffies_resched += 5; /* Enable beating. */
+ } else if (ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
+ /* Time to beat on that CPU again! */
+ resched_cpu(rdp->cpu); /* Force CPU into scheduler. */
+ rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */
+ }
}
return 0;
@@ -3491,6 +3572,7 @@ static void __init rcu_init_one(struct rcu_state *rsp,
"rcu_node_fqs_1",
"rcu_node_fqs_2",
"rcu_node_fqs_3" }; /* Match MAX_RCU_LVLS */
+ static u8 fl_mask = 0x1;
int cpustride = 1;
int i;
int j;
@@ -3509,6 +3591,8 @@ static void __init rcu_init_one(struct rcu_state *rsp,
for (i = 1; i < rcu_num_lvls; i++)
rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1];
rcu_init_levelspread(rsp);
+ rsp->flavor_mask = fl_mask;
+ fl_mask <<= 1;
/* Initialize the elements themselves, starting from the leaves. */
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index bf2c1e669691..0f69a79c5b7d 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -307,6 +307,9 @@ struct rcu_data {
/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */
unsigned long offline_fqs; /* Kicked due to being offline. */
+ unsigned long cond_resched_completed;
+ /* Grace period that needs help */
+ /* from cond_resched(). */
/* 5) __rcu_pending() statistics. */
unsigned long n_rcu_pending; /* rcu_pending() calls since boot. */
@@ -392,6 +395,7 @@ struct rcu_state {
struct rcu_node *level[RCU_NUM_LVLS]; /* Hierarchy levels. */
u32 levelcnt[MAX_RCU_LVLS + 1]; /* # nodes in each level. */
u8 levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */
+ u8 flavor_mask; /* bit in flavor mask. */
struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */
void (*call)(struct rcu_head *head, /* call_rcu() flavor. */
void (*func)(struct rcu_head *head));
@@ -563,7 +567,7 @@ static bool rcu_nocb_need_deferred_wakeup(struct rcu_data
*rdp);
static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
-static void rcu_kick_nohz_cpu(int 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);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index cbc2c45265e2..02ac0fb186b8 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2404,7 +2404,7 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
* if an adaptive-ticks CPU is failing to respond to the current grace
* period and has not be idle from an RCU perspective, kick it.
*/
-static void rcu_kick_nohz_cpu(int cpu)
+static void __maybe_unused rcu_kick_nohz_cpu(int cpu)
{
#ifdef CONFIG_NO_HZ_FULL
if (tick_nohz_full_cpu(cpu))
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index a2aeb4df0f60..d22309cae9f5 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -350,21 +350,3 @@ static int __init check_cpu_stall_init(void)
early_initcall(check_cpu_stall_init);
#endif /* #ifdef CONFIG_RCU_STALL_COMMON */
-
-/*
- * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings.
- */
-
-DEFINE_PER_CPU(int, rcu_cond_resched_count);
-
-/*
- * Report a set of RCU quiescent states, for use by cond_resched()
- * and friends. Out of line due to being called infrequently.
- */
-void rcu_resched(void)
-{
- preempt_disable();
- __this_cpu_write(rcu_cond_resched_count, 0);
- rcu_note_context_switch(smp_processor_id());
- preempt_enable();
-}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3bdf01b494fe..bc1638b33449 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4147,7 +4147,6 @@ static void __cond_resched(void)
int __sched _cond_resched(void)
{
- rcu_cond_resched();
if (should_resched()) {
__cond_resched();
return 1;
@@ -4166,18 +4165,15 @@ EXPORT_SYMBOL(_cond_resched);
*/
int __cond_resched_lock(spinlock_t *lock)
{
- bool need_rcu_resched = rcu_should_resched();
int resched = should_resched();
int ret = 0;
lockdep_assert_held(lock);
- if (spin_needbreak(lock) || resched || need_rcu_resched) {
+ if (spin_needbreak(lock) || resched) {
spin_unlock(lock);
if (resched)
__cond_resched();
- else if (unlikely(need_rcu_resched))
- rcu_resched();
else
cpu_relax();
ret = 1;
@@ -4191,7 +4187,6 @@ int __sched __cond_resched_softirq(void)
{
BUG_ON(!in_softirq());
- rcu_cond_resched(); /* BH disabled OK, just recording QSes. */
if (should_resched()) {
local_bh_enable();
__cond_resched();
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
