@@ -841,7 +841,7 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset)
/* See the kfree_rcu() header comment. */
BUILD_BUG_ON(!__is_kfree_rcu_offset(offset));
- call_rcu(head, (rcu_callback)offset);
+ kfree_call_rcu(head, (rcu_callback)offset);
}
/**
@@ -83,6 +83,12 @@ static inline void synchronize_sched_expedited(void)
synchronize_sched();
}
+static inline void kfree_call_rcu(struct rcu_head *head,
+ void (*func)(struct rcu_head *rcu))
+{
+ call_rcu(head, func);
+}
+
#ifdef CONFIG_TINY_RCU
static inline void rcu_preempt_note_context_switch(void)
@@ -61,6 +61,8 @@ extern void synchronize_rcu_bh(void);
extern void synchronize_sched_expedited(void);
extern void synchronize_rcu_expedited(void);
+void kfree_call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
+
static inline void synchronize_rcu_bh_expedited(void)
{
synchronize_sched_expedited();
@@ -313,19 +313,22 @@ TRACE_EVENT(rcu_prep_idle,
/*
* Tracepoint for the registration of a single RCU callback function.
* The first argument is the type of RCU, the second argument is
- * a pointer to the RCU callback itself, and the third element is the
- * new RCU callback queue length for the current CPU.
+ * a pointer to the RCU callback itself, the third element is the
+ * number of lazy callbacks queued, and the fourth element is the
+ * total number of callbacks queued.
*/
TRACE_EVENT(rcu_callback,
- TP_PROTO(char *rcuname, struct rcu_head *rhp, long qlen),
+ TP_PROTO(char *rcuname, struct rcu_head *rhp, long qlen_lazy,
+ long qlen),
- TP_ARGS(rcuname, rhp, qlen),
+ TP_ARGS(rcuname, rhp, qlen_lazy, qlen),
TP_STRUCT__entry(
__field(char *, rcuname)
__field(void *, rhp)
__field(void *, func)
+ __field(long, qlen_lazy)
__field(long, qlen)
),
@@ -333,11 +336,13 @@ TRACE_EVENT(rcu_callback,
__entry->rcuname = rcuname;
__entry->rhp = rhp;
__entry->func = rhp->func;
+ __entry->qlen_lazy = qlen_lazy;
__entry->qlen = qlen;
),
- TP_printk("%s rhp=%p func=%pf %ld",
- __entry->rcuname, __entry->rhp, __entry->func, __entry->qlen)
+ TP_printk("%s rhp=%p func=%pf %ld/%ld",
+ __entry->rcuname, __entry->rhp, __entry->func,
+ __entry->qlen_lazy, __entry->qlen)
);
/*
@@ -345,20 +350,21 @@ TRACE_EVENT(rcu_callback,
* kfree() form. The first argument is the RCU type, the second argument
* is a pointer to the RCU callback, the third argument is the offset
* of the callback within the enclosing RCU-protected data structure,
- * and the fourth argument is the new RCU callback queue length for the
- * current CPU.
+ * the fourth argument is the number of lazy callbacks queued, and the
+ * fifth argument is the total number of callbacks queued.
*/
TRACE_EVENT(rcu_kfree_callback,
TP_PROTO(char *rcuname, struct rcu_head *rhp, unsigned long offset,
- long qlen),
+ long qlen_lazy, long qlen),
- TP_ARGS(rcuname, rhp, offset, qlen),
+ TP_ARGS(rcuname, rhp, offset, qlen_lazy, qlen),
TP_STRUCT__entry(
__field(char *, rcuname)
__field(void *, rhp)
__field(unsigned long, offset)
+ __field(long, qlen_lazy)
__field(long, qlen)
),
@@ -366,41 +372,45 @@ TRACE_EVENT(rcu_kfree_callback,
__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",
+ TP_printk("%s rhp=%p func=%ld %ld/%ld",
__entry->rcuname, __entry->rhp, __entry->offset,
- __entry->qlen)
+ __entry->qlen_lazy, __entry->qlen)
);
/*
* Tracepoint for marking the beginning rcu_do_batch, performed to start
* RCU callback invocation. The first argument is the RCU flavor,
- * the second is the total number of callbacks (including those that
- * are not yet ready to be invoked), and the third argument is the
- * current RCU-callback batch limit.
+ * the second is the number of lazy callbacks queued, the third is
+ * the total number of callbacks queued, and the fourth argument is
+ * the current RCU-callback batch limit.
*/
TRACE_EVENT(rcu_batch_start,
- TP_PROTO(char *rcuname, long qlen, int blimit),
+ TP_PROTO(char *rcuname, long qlen_lazy, long qlen, int blimit),
- TP_ARGS(rcuname, qlen, blimit),
+ TP_ARGS(rcuname, qlen_lazy, qlen, blimit),
TP_STRUCT__entry(
__field(char *, rcuname)
+ __field(long, qlen_lazy)
__field(long, qlen)
__field(int, blimit)
),
TP_fast_assign(
__entry->rcuname = rcuname;
+ __entry->qlen_lazy = qlen_lazy;
__entry->qlen = qlen;
__entry->blimit = blimit;
),
- TP_printk("%s CBs=%ld bl=%d",
- __entry->rcuname, __entry->qlen, __entry->blimit)
+ TP_printk("%s CBs=%ld/%ld bl=%d",
+ __entry->rcuname, __entry->qlen_lazy, __entry->qlen,
+ __entry->blimit)
);
/*
@@ -531,16 +541,21 @@ TRACE_EVENT(rcu_torture_read,
#else /* #ifdef CONFIG_RCU_TRACE */
#define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0)
-#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, qsmask) do { } while (0)
+#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \
+ qsmask) do { } while (0)
#define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0)
#define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0)
-#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks) do { } while (0)
+#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \
+ grplo, grphi, gp_tasks) do { } \
+ while (0)
#define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0)
#define trace_rcu_dyntick(polarity, oldnesting, newnesting) do { } while (0)
#define trace_rcu_prep_idle(reason) do { } while (0)
-#define trace_rcu_callback(rcuname, rhp, qlen) do { } while (0)
-#define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen) do { } while (0)
-#define trace_rcu_batch_start(rcuname, qlen, blimit) do { } while (0)
+#define trace_rcu_callback(rcuname, rhp, qlen_lazy, qlen) do { } while (0)
+#define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen_lazy, qlen) \
+ do { } while (0)
+#define trace_rcu_batch_start(rcuname, qlen_lazy, qlen, blimit) \
+ do { } while (0)
#define trace_rcu_invoke_callback(rcuname, rhp) do { } while (0)
#define trace_rcu_invoke_kfree_callback(rcuname, rhp, offset) do { } while (0)
#define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \
@@ -76,16 +76,18 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
extern void kfree(const void *);
-static inline void __rcu_reclaim(char *rn, struct rcu_head *head)
+static inline bool __rcu_reclaim(char *rn, struct rcu_head *head)
{
unsigned long offset = (unsigned long)head->func;
if (__is_kfree_rcu_offset(offset)) {
RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset));
kfree((void *)head - offset);
+ return 1;
} else {
RCU_TRACE(trace_rcu_invoke_callback(rn, head));
head->func(head);
+ return 0;
}
}
@@ -258,7 +258,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
/* If no RCU callbacks ready to invoke, just return. */
if (&rcp->rcucblist == rcp->donetail) {
- RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, -1));
+ RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, 0, -1));
RCU_TRACE(trace_rcu_batch_end(rcp->name, 0,
ACCESS_ONCE(rcp->rcucblist),
need_resched(),
@@ -269,7 +269,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
/* Move the ready-to-invoke callbacks to a local list. */
local_irq_save(flags);
- RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, -1));
+ RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1));
list = rcp->rcucblist;
rcp->rcucblist = *rcp->donetail;
*rcp->donetail = NULL;
@@ -1261,6 +1261,7 @@ static void rcu_send_cbs_to_online(struct rcu_state *rsp)
*receive_rdp->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist;
receive_rdp->nxttail[RCU_NEXT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+ receive_rdp->qlen_lazy += rdp->qlen_lazy;
receive_rdp->qlen += rdp->qlen;
receive_rdp->n_cbs_adopted += rdp->qlen;
rdp->n_cbs_orphaned += rdp->qlen;
@@ -1268,6 +1269,7 @@ static void rcu_send_cbs_to_online(struct rcu_state *rsp)
rdp->nxtlist = NULL;
for (i = 0; i < RCU_NEXT_SIZE; i++)
rdp->nxttail[i] = &rdp->nxtlist;
+ rdp->qlen_lazy = 0;
rdp->qlen = 0;
}
@@ -1368,11 +1370,11 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
{
unsigned long flags;
struct rcu_head *next, *list, **tail;
- int bl, count;
+ int bl, count, count_lazy;
/* If no callbacks are ready, just return.*/
if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
- trace_rcu_batch_start(rsp->name, 0, 0);
+ trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0);
trace_rcu_batch_end(rsp->name, 0, !!ACCESS_ONCE(rdp->nxtlist),
need_resched(), is_idle_task(current),
rcu_is_callbacks_kthread());
@@ -1385,7 +1387,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
*/
local_irq_save(flags);
bl = rdp->blimit;
- trace_rcu_batch_start(rsp->name, rdp->qlen, bl);
+ trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, bl);
list = rdp->nxtlist;
rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL];
*rdp->nxttail[RCU_DONE_TAIL] = NULL;
@@ -1396,12 +1398,13 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
local_irq_restore(flags);
/* Invoke callbacks. */
- count = 0;
+ count = count_lazy = 0;
while (list) {
next = list->next;
prefetch(next);
debug_rcu_head_unqueue(list);
- __rcu_reclaim(rsp->name, list);
+ if (__rcu_reclaim(rsp->name, list))
+ count_lazy++;
list = next;
/* Stop only if limit reached and CPU has something to do. */
if (++count >= bl &&
@@ -1416,6 +1419,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
rcu_is_callbacks_kthread());
/* Update count, and requeue any remaining callbacks. */
+ rdp->qlen_lazy -= count_lazy;
rdp->qlen -= count;
rdp->n_cbs_invoked += count;
if (list != NULL) {
@@ -1702,7 +1706,7 @@ static void invoke_rcu_core(void)
static void
__call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
- struct rcu_state *rsp)
+ struct rcu_state *rsp, bool lazy)
{
unsigned long flags;
struct rcu_data *rdp;
@@ -1727,12 +1731,14 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
*rdp->nxttail[RCU_NEXT_TAIL] = head;
rdp->nxttail[RCU_NEXT_TAIL] = &head->next;
rdp->qlen++;
+ if (lazy)
+ rdp->qlen_lazy++;
if (__is_kfree_rcu_offset((unsigned long)func))
trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func,
- rdp->qlen);
+ rdp->qlen_lazy, rdp->qlen);
else
- trace_rcu_callback(rsp->name, head, rdp->qlen);
+ trace_rcu_callback(rsp->name, head, rdp->qlen_lazy, rdp->qlen);
/* If interrupts were disabled, don't dive into RCU core. */
if (irqs_disabled_flags(flags)) {
@@ -1779,16 +1785,16 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
*/
void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
- __call_rcu(head, func, &rcu_sched_state);
+ __call_rcu(head, func, &rcu_sched_state, 0);
}
EXPORT_SYMBOL_GPL(call_rcu_sched);
/*
- * Queue an RCU for invocation after a quicker grace period.
+ * Queue an RCU callback for invocation after a quicker grace period.
*/
void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
- __call_rcu(head, func, &rcu_bh_state);
+ __call_rcu(head, func, &rcu_bh_state, 0);
}
EXPORT_SYMBOL_GPL(call_rcu_bh);
@@ -2036,6 +2042,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
rdp->nxtlist = NULL;
for (i = 0; i < RCU_NEXT_SIZE; i++)
rdp->nxttail[i] = &rdp->nxtlist;
+ rdp->qlen_lazy = 0;
rdp->qlen = 0;
rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_NESTING);
@@ -265,7 +265,8 @@ struct rcu_data {
*/
struct rcu_head *nxtlist;
struct rcu_head **nxttail[RCU_NEXT_SIZE];
- long qlen; /* # of queued callbacks */
+ long qlen_lazy; /* # of lazy queued callbacks */
+ long qlen; /* # of queued callbacks, incl lazy */
long qlen_last_fqs_check;
/* qlen at last check for QS forcing */
unsigned long n_cbs_invoked; /* count of RCU cbs invoked. */
@@ -671,10 +671,24 @@ static void rcu_preempt_do_callbacks(void)
*/
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
- __call_rcu(head, func, &rcu_preempt_state);
+ __call_rcu(head, func, &rcu_preempt_state, 0);
}
EXPORT_SYMBOL_GPL(call_rcu);
+/*
+ * Queue an RCU callback for lazy invocation after a grace period.
+ * This will likely be later named something like "call_rcu_lazy()",
+ * but this change will require some way of tagging the lazy RCU
+ * callbacks in the list of pending callbacks. Until then, this
+ * function may only be called from __kfree_rcu().
+ */
+void kfree_call_rcu(struct rcu_head *head,
+ void (*func)(struct rcu_head *rcu))
+{
+ __call_rcu(head, func, &rcu_preempt_state, 1);
+}
+EXPORT_SYMBOL_GPL(kfree_call_rcu);
+
/**
* synchronize_rcu - wait until a grace period has elapsed.
*
@@ -1065,6 +1079,22 @@ static void rcu_preempt_process_callbacks(void)
}
/*
+ * Queue an RCU callback for lazy invocation after a grace period.
+ * This will likely be later named something like "call_rcu_lazy()",
+ * but this change will require some way of tagging the lazy RCU
+ * callbacks in the list of pending callbacks. Until then, this
+ * function may only be called from __kfree_rcu().
+ *
+ * Because there is no preemptible RCU, we use RCU-sched instead.
+ */
+void kfree_call_rcu(struct rcu_head *head,
+ void (*func)(struct rcu_head *rcu))
+{
+ __call_rcu(head, func, &rcu_sched_state, 1);
+}
+EXPORT_SYMBOL_GPL(kfree_call_rcu);
+
+/*
* Wait for an rcu-preempt grace period, but make it happen quickly.
* But because preemptible RCU does not exist, map to rcu-sched.
*/
@@ -2052,6 +2082,48 @@ int rcu_needs_cpu(int cpu)
}
/*
+ * Does the specified flavor of RCU have non-lazy callbacks pending on
+ * the specified CPU? Both RCU flavor and CPU are specified by the
+ * rcu_data structure.
+ */
+static bool __rcu_cpu_has_nonlazy_callbacks(struct rcu_data *rdp)
+{
+ return rdp->qlen != rdp->qlen_lazy;
+}
+
+#ifdef CONFIG_TREE_PREEMPT_RCU
+
+/*
+ * Are there non-lazy RCU-preempt callbacks? (There cannot be if there
+ * is no RCU-preempt in the kernel.)
+ */
+static bool rcu_preempt_cpu_has_nonlazy_callbacks(int cpu)
+{
+ struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
+
+ return __rcu_cpu_has_nonlazy_callbacks(rdp);
+}
+
+#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+
+static bool rcu_preempt_cpu_has_nonlazy_callbacks(int cpu)
+{
+ return 0;
+}
+
+#endif /* else #ifdef CONFIG_TREE_PREEMPT_RCU */
+
+/*
+ * Does any flavor of RCU have non-lazy callbacks on the specified CPU?
+ */
+static bool rcu_cpu_has_nonlazy_callbacks(int cpu)
+{
+ return __rcu_cpu_has_nonlazy_callbacks(&per_cpu(rcu_sched_data, cpu)) ||
+ __rcu_cpu_has_nonlazy_callbacks(&per_cpu(rcu_bh_data, cpu)) ||
+ rcu_preempt_cpu_has_nonlazy_callbacks(cpu);
+}
+
+/*
* Timer handler used to force CPU to start pushing its remaining RCU
* callbacks in the case where it entered dyntick-idle mode with callbacks
* pending. The hander doesn't really need to do anything because the
@@ -2149,8 +2221,9 @@ static void rcu_prepare_for_idle(int cpu)
trace_rcu_prep_idle("Dyntick with callbacks");
per_cpu(rcu_dyntick_drain, cpu) = 0;
per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
- hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu),
- rcu_idle_gp_wait, HRTIMER_MODE_REL);
+ if (rcu_cpu_has_nonlazy_callbacks(cpu))
+ hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu),
+ rcu_idle_gp_wait, HRTIMER_MODE_REL);
return; /* Nothing more to do immediately. */
} else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) {
/* We have hit the limit, so time to give up. */
@@ -73,8 +73,8 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
rdp->dynticks->dynticks_nmi_nesting,
rdp->dynticks_fqs);
seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
- seq_printf(m, " ql=%ld qs=%c%c%c%c",
- rdp->qlen,
+ seq_printf(m, " ql=%ld/%ld qs=%c%c%c%c",
+ rdp->qlen_lazy, rdp->qlen,
".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
rdp->nxttail[RCU_NEXT_TAIL]],
".R"[rdp->nxttail[RCU_WAIT_TAIL] !=
@@ -145,7 +145,7 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
rdp->dynticks->dynticks_nmi_nesting,
rdp->dynticks_fqs);
seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi);
- seq_printf(m, ",%ld,\"%c%c%c%c\"", rdp->qlen,
+ seq_printf(m, ",%ld,%ld,\"%c%c%c%c\"", rdp->qlen_lazy, rdp->qlen,
".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
rdp->nxttail[RCU_NEXT_TAIL]],
".R"[rdp->nxttail[RCU_WAIT_TAIL] !=
@@ -168,7 +168,7 @@ static int show_rcudata_csv(struct seq_file *m, void *unused)
{
seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pgp\",\"pq\",");
seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\",");
- seq_puts(m, "\"of\",\"ri\",\"ql\",\"qs\"");
+ seq_puts(m, "\"of\",\"ri\",\"qll\",\"ql\",\"qs\"");
#ifdef CONFIG_RCU_BOOST
seq_puts(m, "\"kt\",\"ktl\"");
#endif /* #ifdef CONFIG_RCU_BOOST */