In kernels with CONFIG_RCU_FAST_NO_HZ, more information is printed
for each CPU:
- 0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 softirq=82/543 last_accelerate: a345/d342 Nonlazy posted: ..D
+ 0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 softirq=82/543 last_accelerate: a345/d342 dyntick_enabled: 1
The "last_accelerate:" prints the low-order 16 bits (in hex) of the
jiffies counter when this CPU last invoked rcu_try_advance_all_cbs()
from rcu_needs_cpu() or last invoked rcu_accelerate_cbs() from
-rcu_prepare_for_idle(). The "Nonlazy posted:" indicates lazy-callback
-status, so that an "l" indicates that all callbacks were lazy at the start
-of the last idle period and an "L" indicates that there are currently
-no non-lazy callbacks (in both cases, "." is printed otherwise, as
-shown above) and "D" indicates that dyntick-idle processing is enabled
-("." is printed otherwise, for example, if disabled via the "nohz="
-kernel boot parameter).
+rcu_prepare_for_idle(). "dyntick_enabled: 1" indicates that dyntick-idle
+processing is enabled.
If the grace period ends just as the stall warning starts printing,
there will be a spurious stall-warning message, which will include
struct rcu_head *head;
struct rcu_head **tail;
long len;
- long len_lazy;
};
#define RCU_CBLIST_INITIALIZER(n) { .head = NULL, .tail = &n.head }
#else
long len;
#endif
- long len_lazy;
u8 enabled;
u8 offloaded;
};
*/
TRACE_EVENT_RCU(rcu_callback,
- TP_PROTO(const char *rcuname, struct rcu_head *rhp, long qlen_lazy,
- long qlen),
+ TP_PROTO(const char *rcuname, struct rcu_head *rhp, long qlen),
- TP_ARGS(rcuname, rhp, qlen_lazy, qlen),
+ TP_ARGS(rcuname, rhp, qlen),
TP_STRUCT__entry(
__field(const char *, rcuname)
__field(void *, rhp)
__field(void *, func)
- __field(long, qlen_lazy)
__field(long, qlen)
),
__entry->rcuname = rcuname;
__entry->rhp = rhp;
__entry->func = rhp->func;
- __entry->qlen_lazy = qlen_lazy;
__entry->qlen = qlen;
),
- TP_printk("%s rhp=%p func=%ps %ld/%ld",
+ TP_printk("%s rhp=%p func=%ps %ld",
__entry->rcuname, __entry->rhp, __entry->func,
- __entry->qlen_lazy, __entry->qlen)
+ __entry->qlen)
);
/*
TRACE_EVENT_RCU(rcu_kfree_callback,
TP_PROTO(const char *rcuname, struct rcu_head *rhp, unsigned long offset,
- long qlen_lazy, long qlen),
+ long qlen),
- TP_ARGS(rcuname, rhp, offset, qlen_lazy, qlen),
+ TP_ARGS(rcuname, rhp, offset, qlen),
TP_STRUCT__entry(
__field(const char *, rcuname)
__field(void *, rhp)
__field(unsigned long, offset)
- __field(long, qlen_lazy)
__field(long, qlen)
),
__entry->rcuname = rcuname;
__entry->rhp = rhp;
__entry->offset = offset;
- __entry->qlen_lazy = qlen_lazy;
__entry->qlen = qlen;
),
- TP_printk("%s rhp=%p func=%ld %ld/%ld",
+ TP_printk("%s rhp=%p func=%ld %ld",
__entry->rcuname, __entry->rhp, __entry->offset,
- __entry->qlen_lazy, __entry->qlen)
+ __entry->qlen)
);
/*
*/
TRACE_EVENT_RCU(rcu_batch_start,
- TP_PROTO(const char *rcuname, long qlen_lazy, long qlen, long blimit),
+ TP_PROTO(const char *rcuname, long qlen, long blimit),
- TP_ARGS(rcuname, qlen_lazy, qlen, blimit),
+ TP_ARGS(rcuname, qlen, blimit),
TP_STRUCT__entry(
__field(const char *, rcuname)
- __field(long, qlen_lazy)
__field(long, qlen)
__field(long, blimit)
),
TP_fast_assign(
__entry->rcuname = rcuname;
- __entry->qlen_lazy = qlen_lazy;
__entry->qlen = qlen;
__entry->blimit = blimit;
),
- TP_printk("%s CBs=%ld/%ld bl=%ld",
- __entry->rcuname, __entry->qlen_lazy, __entry->qlen,
- __entry->blimit)
+ TP_printk("%s CBs=%ld bl=%ld",
+ __entry->rcuname, __entry->qlen, __entry->blimit)
);
/*
}
#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-void kfree(const void *);
-
-/*
- * Reclaim the specified callback, either by invoking it (non-lazy case)
- * or freeing it directly (lazy case). Return true if lazy, false otherwise.
- */
-static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
-{
- rcu_callback_t f;
- unsigned long offset = (unsigned long)head->func;
-
- rcu_lock_acquire(&rcu_callback_map);
- if (__is_kfree_rcu_offset(offset)) {
- trace_rcu_invoke_kfree_callback(rn, head, offset);
- kfree((void *)head - offset);
- rcu_lock_release(&rcu_callback_map);
- return true;
- } else {
- trace_rcu_invoke_callback(rn, head);
- f = head->func;
- WRITE_ONCE(head->func, (rcu_callback_t)0L);
- f(head);
- rcu_lock_release(&rcu_callback_map);
- return false;
- }
-}
-
#ifdef CONFIG_RCU_STALL_COMMON
extern int rcu_cpu_stall_ftrace_dump;
rclp->head = NULL;
rclp->tail = &rclp->head;
rclp->len = 0;
- rclp->len_lazy = 0;
}
/*
* Enqueue an rcu_head structure onto the specified callback list.
- * This function assumes that the callback is non-lazy because it
- * is intended for use by no-CBs CPUs, which do not distinguish
- * between lazy and non-lazy RCU callbacks.
*/
void rcu_cblist_enqueue(struct rcu_cblist *rclp, struct rcu_head *rhp)
{
else
drclp->tail = &drclp->head;
drclp->len = srclp->len;
- drclp->len_lazy = srclp->len_lazy;
if (!rhp) {
rcu_cblist_init(srclp);
} else {
srclp->head = rhp;
srclp->tail = &rhp->next;
WRITE_ONCE(srclp->len, 1);
- srclp->len_lazy = 0;
}
}
/*
* Dequeue the oldest rcu_head structure from the specified callback
- * list. This function assumes that the callback is non-lazy, but
- * the caller can later invoke rcu_cblist_dequeued_lazy() if it
- * finds otherwise (and if it cares about laziness). This allows
- * different users to have different ways of determining laziness.
+ * list.
*/
struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp)
{
for (i = 0; i < RCU_CBLIST_NSEGS; i++)
rsclp->tails[i] = &rsclp->head;
rcu_segcblist_set_len(rsclp, 0);
- rsclp->len_lazy = 0;
rsclp->enabled = 1;
}
{
WARN_ON_ONCE(!rcu_segcblist_empty(rsclp));
WARN_ON_ONCE(rcu_segcblist_n_cbs(rsclp));
- WARN_ON_ONCE(rcu_segcblist_n_lazy_cbs(rsclp));
rsclp->enabled = 0;
}
* absolutely not OK for it to ever miss posting a callback.
*/
void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
- struct rcu_head *rhp, bool lazy)
+ struct rcu_head *rhp)
{
rcu_segcblist_inc_len(rsclp);
- if (lazy)
- rsclp->len_lazy++;
smp_mb(); /* Ensure counts are updated before callback is enqueued. */
rhp->next = NULL;
WRITE_ONCE(*rsclp->tails[RCU_NEXT_TAIL], rhp);
* period. You have been warned.
*/
bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
- struct rcu_head *rhp, bool lazy)
+ struct rcu_head *rhp)
{
int i;
if (rcu_segcblist_n_cbs(rsclp) == 0)
return false;
rcu_segcblist_inc_len(rsclp);
- if (lazy)
- rsclp->len_lazy++;
smp_mb(); /* Ensure counts are updated before callback is entrained. */
rhp->next = NULL;
for (i = RCU_NEXT_TAIL; i > RCU_DONE_TAIL; i--)
void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
- rclp->len_lazy += rsclp->len_lazy;
- rsclp->len_lazy = 0;
rclp->len = rcu_segcblist_xchg_len(rsclp, 0);
}
void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
- rsclp->len_lazy += rclp->len_lazy;
rcu_segcblist_add_len(rsclp, rclp->len);
- rclp->len_lazy = 0;
rclp->len = 0;
}
return READ_ONCE(rclp->len);
}
-/*
- * Account for the fact that a previously dequeued callback turned out
- * to be marked as lazy.
- */
-static inline void rcu_cblist_dequeued_lazy(struct rcu_cblist *rclp)
-{
- rclp->len_lazy--;
-}
-
void rcu_cblist_init(struct rcu_cblist *rclp);
void rcu_cblist_enqueue(struct rcu_cblist *rclp, struct rcu_head *rhp);
void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp,
#endif
}
-/* Return number of lazy callbacks in segmented callback list. */
-static inline long rcu_segcblist_n_lazy_cbs(struct rcu_segcblist *rsclp)
-{
- return rsclp->len_lazy;
-}
-
-/* Return number of lazy callbacks in segmented callback list. */
-static inline long rcu_segcblist_n_nonlazy_cbs(struct rcu_segcblist *rsclp)
-{
- return rcu_segcblist_n_cbs(rsclp) - rsclp->len_lazy;
-}
-
/*
* Is the specified rcu_segcblist enabled, for example, not corresponding
* to an offline CPU?
struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp);
bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, unsigned long *lp);
void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
- struct rcu_head *rhp, bool lazy);
+ struct rcu_head *rhp);
bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
- struct rcu_head *rhp, bool lazy);
+ struct rcu_head *rhp);
void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp);
void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp,
local_irq_save(flags);
sdp = this_cpu_ptr(ssp->sda);
spin_lock_rcu_node(sdp);
- rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false);
+ rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
rcu_segcblist_advance(&sdp->srcu_cblist,
rcu_seq_current(&ssp->srcu_gp_seq));
s = rcu_seq_snap(&ssp->srcu_gp_seq);
sdp->srcu_barrier_head.func = srcu_barrier_cb;
debug_rcu_head_queue(&sdp->srcu_barrier_head);
if (!rcu_segcblist_entrain(&sdp->srcu_cblist,
- &sdp->srcu_barrier_head, 0)) {
+ &sdp->srcu_barrier_head)) {
debug_rcu_head_unqueue(&sdp->srcu_barrier_head);
atomic_dec(&ssp->srcu_barrier_cpu_cnt);
}
#include <linux/time.h>
#include <linux/cpu.h>
#include <linux/prefetch.h>
+#include <linux/slab.h>
#include "rcu.h"
}
}
+/*
+ * Reclaim the specified callback, either by invoking it for non-kfree cases or
+ * freeing it directly (for kfree). Return true if kfreeing, false otherwise.
+ */
+static inline bool rcu_reclaim_tiny(struct rcu_head *head)
+{
+ rcu_callback_t f;
+ unsigned long offset = (unsigned long)head->func;
+
+ rcu_lock_acquire(&rcu_callback_map);
+ if (__is_kfree_rcu_offset(offset)) {
+ trace_rcu_invoke_kfree_callback("", head, offset);
+ kfree((void *)head - offset);
+ rcu_lock_release(&rcu_callback_map);
+ return true;
+ }
+
+ trace_rcu_invoke_callback("", head);
+ f = head->func;
+ WRITE_ONCE(head->func, (rcu_callback_t)0L);
+ f(head);
+ rcu_lock_release(&rcu_callback_map);
+ return false;
+}
+
/* Invoke the RCU callbacks whose grace period has elapsed. */
static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused)
{
prefetch(next);
debug_rcu_head_unqueue(list);
local_bh_disable();
- __rcu_reclaim("", list);
+ rcu_reclaim_tiny(list);
local_bh_enable();
list = next;
}
#include <linux/oom.h>
#include <linux/smpboot.h>
#include <linux/jiffies.h>
+#include <linux/slab.h>
#include <linux/sched/isolation.h>
#include <linux/sched/clock.h>
#include "../time/tick-internal.h"
/* If no callbacks are ready, just return. */
if (!rcu_segcblist_ready_cbs(&rdp->cblist)) {
trace_rcu_batch_start(rcu_state.name,
- rcu_segcblist_n_lazy_cbs(&rdp->cblist),
rcu_segcblist_n_cbs(&rdp->cblist), 0);
trace_rcu_batch_end(rcu_state.name, 0,
!rcu_segcblist_empty(&rdp->cblist),
if (unlikely(bl > 100))
tlimit = local_clock() + rcu_resched_ns;
trace_rcu_batch_start(rcu_state.name,
- rcu_segcblist_n_lazy_cbs(&rdp->cblist),
rcu_segcblist_n_cbs(&rdp->cblist), bl);
rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl);
if (offloaded)
tick_dep_set_task(current, TICK_DEP_BIT_RCU);
rhp = rcu_cblist_dequeue(&rcl);
for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) {
+ rcu_callback_t f;
+
debug_rcu_head_unqueue(rhp);
- if (__rcu_reclaim(rcu_state.name, rhp))
- rcu_cblist_dequeued_lazy(&rcl);
+
+ rcu_lock_acquire(&rcu_callback_map);
+ trace_rcu_invoke_callback(rcu_state.name, rhp);
+
+ f = rhp->func;
+ WRITE_ONCE(rhp->func, (rcu_callback_t)0L);
+ f(rhp);
+
+ rcu_lock_release(&rcu_callback_map);
+
/*
* Stop only if limit reached and CPU has something to do.
* Note: The rcl structure counts down from zero.
* is expected to specify a CPU.
*/
static void
-__call_rcu(struct rcu_head *head, rcu_callback_t func, bool lazy)
+__call_rcu(struct rcu_head *head, rcu_callback_t func)
{
unsigned long flags;
struct rcu_data *rdp;
if (rcu_segcblist_empty(&rdp->cblist))
rcu_segcblist_init(&rdp->cblist);
}
+
if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags))
return; // Enqueued onto ->nocb_bypass, so just leave.
/* If we get here, rcu_nocb_try_bypass() acquired ->nocb_lock. */
- rcu_segcblist_enqueue(&rdp->cblist, head, lazy);
+ rcu_segcblist_enqueue(&rdp->cblist, head);
if (__is_kfree_rcu_offset((unsigned long)func))
trace_rcu_kfree_callback(rcu_state.name, head,
(unsigned long)func,
- rcu_segcblist_n_lazy_cbs(&rdp->cblist),
rcu_segcblist_n_cbs(&rdp->cblist));
else
trace_rcu_callback(rcu_state.name, head,
- rcu_segcblist_n_lazy_cbs(&rdp->cblist),
rcu_segcblist_n_cbs(&rdp->cblist));
/* Go handle any RCU core processing required. */
*/
void call_rcu(struct rcu_head *head, rcu_callback_t func)
{
- __call_rcu(head, func, 0);
+ __call_rcu(head, func);
}
EXPORT_SYMBOL_GPL(call_rcu);
// List "head" is now private, so traverse locklessly.
for (; head; head = next) {
+ unsigned long offset = (unsigned long)head->func;
+
next = head->next;
// Potentially optimize with kfree_bulk in future.
debug_rcu_head_unqueue(head);
- __rcu_reclaim(rcu_state.name, head);
+ rcu_lock_acquire(&rcu_callback_map);
+ trace_rcu_invoke_kfree_callback(rcu_state.name, head, offset);
+
+ /* Could be possible to optimize with kfree_bulk in future */
+ kfree((void *)head - offset);
+
+ rcu_lock_release(&rcu_callback_map);
cond_resched_tasks_rcu_qs();
}
}
*/
void kfree_call_rcu_nobatch(struct rcu_head *head, rcu_callback_t func)
{
- __call_rcu(head, func, 1);
+ __call_rcu(head, func);
}
EXPORT_SYMBOL_GPL(kfree_call_rcu_nobatch);
debug_rcu_head_queue(&rdp->barrier_head);
rcu_nocb_lock(rdp);
WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies));
- if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head, 0)) {
+ if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head)) {
atomic_inc(&rcu_state.barrier_cpu_count);
} else {
debug_rcu_head_unqueue(&rdp->barrier_head);
bool rcu_urgent_qs; /* GP old need light quiescent state. */
bool rcu_forced_tick; /* Forced tick to provide QS. */
#ifdef CONFIG_RCU_FAST_NO_HZ
- bool all_lazy; /* All CPU's CBs lazy at idle start? */
unsigned long last_accelerate; /* Last jiffy CBs were accelerated. */
unsigned long last_advance_all; /* Last jiffy CBs were all advanced. */
int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */
/*
* This code is invoked when a CPU goes idle, at which point we want
* to have the CPU do everything required for RCU so that it can enter
- * the energy-efficient dyntick-idle mode. This is handled by a
- * state machine implemented by rcu_prepare_for_idle() below.
+ * the energy-efficient dyntick-idle mode.
*
- * The following three proprocessor symbols control this state machine:
+ * The following preprocessor symbol controls this:
*
* RCU_IDLE_GP_DELAY gives the number of jiffies that a CPU is permitted
* to sleep in dyntick-idle mode with RCU callbacks pending. This
* number, be warned: Setting RCU_IDLE_GP_DELAY too high can hang your
* system. And if you are -that- concerned about energy efficiency,
* just power the system down and be done with it!
- * RCU_IDLE_LAZY_GP_DELAY gives the number of jiffies that a CPU is
- * permitted to sleep in dyntick-idle mode with only lazy RCU
- * callbacks pending. Setting this too high can OOM your system.
*
- * The values below work well in practice. If future workloads require
+ * The value below works well in practice. If future workloads require
* adjustment, they can be converted into kernel config parameters, though
* making the state machine smarter might be a better option.
*/
#define RCU_IDLE_GP_DELAY 4 /* Roughly one grace period. */
-#define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */
static int rcu_idle_gp_delay = RCU_IDLE_GP_DELAY;
module_param(rcu_idle_gp_delay, int, 0644);
-static int rcu_idle_lazy_gp_delay = RCU_IDLE_LAZY_GP_DELAY;
-module_param(rcu_idle_lazy_gp_delay, int, 0644);
/*
* Try to advance callbacks on the current CPU, but only if it has been
/*
* Allow the CPU to enter dyntick-idle mode unless it has callbacks ready
* to invoke. If the CPU has callbacks, try to advance them. Tell the
- * caller to set the timeout based on whether or not there are non-lazy
- * callbacks.
+ * caller about what to set the timeout.
*
* The caller must have disabled interrupts.
*/
}
rdp->last_accelerate = jiffies;
- /* Request timer delay depending on laziness, and round. */
- rdp->all_lazy = !rcu_segcblist_n_nonlazy_cbs(&rdp->cblist);
- if (rdp->all_lazy) {
- dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
- } else {
- dj = round_up(rcu_idle_gp_delay + jiffies,
- rcu_idle_gp_delay) - jiffies;
- }
+ /* Request timer and round. */
+ dj = round_up(rcu_idle_gp_delay + jiffies, rcu_idle_gp_delay) - jiffies;
+
*nextevt = basemono + dj * TICK_NSEC;
return 0;
}
/*
- * Prepare a CPU for idle from an RCU perspective. The first major task
- * is to sense whether nohz mode has been enabled or disabled via sysfs.
- * The second major task is to check to see if a non-lazy callback has
- * arrived at a CPU that previously had only lazy callbacks. The third
- * major task is to accelerate (that is, assign grace-period numbers to)
- * any recently arrived callbacks.
+ * Prepare a CPU for idle from an RCU perspective. The first major task is to
+ * sense whether nohz mode has been enabled or disabled via sysfs. The second
+ * major task is to accelerate (that is, assign grace-period numbers to) any
+ * recently arrived callbacks.
*
* The caller must have disabled interrupts.
*/
if (!tne)
return;
- /*
- * If a non-lazy callback arrived at a CPU having only lazy
- * callbacks, invoke RCU core for the side-effect of recalculating
- * idle duration on re-entry to idle.
- */
- if (rdp->all_lazy && rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)) {
- rdp->all_lazy = false;
- invoke_rcu_core();
- return;
- }
-
/*
* If we have not yet accelerated this jiffy, accelerate all
* callbacks on this CPU.
{
struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
- sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c",
+ sprintf(cp, "last_accelerate: %04lx/%04lx dyntick_enabled: %d",
rdp->last_accelerate & 0xffff, jiffies & 0xffff,
- ".l"[rdp->all_lazy],
- ".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)],
- ".D"[!!rdp->tick_nohz_enabled_snap]);
+ !!rdp->tick_nohz_enabled_snap);
}
#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
projects / linux.git / commitdiff