rcu: Remove kfree_rcu() special casing and lazy-callback handling

This commit removes kfree_rcu() special-casing and the lazy-callback handling from Tree RCU. It moves some of this special casing to Tiny RCU, the removal of which will be the subject of later commits. This results in a nice negative delta. Suggested-by: Paul E. McKenney <[email protected]> Signed-off-by: Joel Fernandes (Google) <[email protected]> [ paulmck: Add slab.h #include, thanks to kbuild test robot <[email protected]>. ] Signed-off-by: Paul E. McKenney <[email protected]>
josf · Jan 24, 2020 · 77a40f9 · 77a40f9
1 parent e99637b
commit 77a40f9
Show file tree

Hide file tree

Showing 12 changed files with 90 additions and 159 deletions.
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
@@ -225,18 +225,13 @@ an estimate of the total number of RCU callbacks queued across all CPUs
 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

diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h
@@ -22,7 +22,6 @@ struct rcu_cblist {
 	struct rcu_head *head;
 	struct rcu_head **tail;
 	long len;
-	long len_lazy;
 };
 
 #define RCU_CBLIST_INITIALIZER(n) { .head = NULL, .tail = &n.head }
@@ -73,7 +72,6 @@ struct rcu_segcblist {
 #else
 	long len;
 #endif
-	long len_lazy;
 	u8 enabled;
 	u8 offloaded;
 };

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
@@ -481,30 +481,27 @@ TRACE_EVENT_RCU(rcu_dyntick,
  */
 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)
 	),
 
 	TP_fast_assign(
 		__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)
 );
 
 /*
@@ -518,29 +515,27 @@ TRACE_EVENT_RCU(rcu_callback,
 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)
 	),
 
 	TP_fast_assign(
 		__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)
 );
 
 /*
@@ -552,27 +547,24 @@ TRACE_EVENT_RCU(rcu_kfree_callback,
  */
 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)
 );
 
 /*

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
@@ -198,33 +198,6 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 }
 #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;

diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
@@ -20,14 +20,10 @@ void rcu_cblist_init(struct rcu_cblist *rclp)
 	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)
 {
@@ -54,24 +50,19 @@ void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp,
 	else
 		drclp->tail = &drclp->head;
 	drclp->len = srclp->len;
-	drclp->len_lazy = srclp->len_lazy;
 	if (!rhp) {
 		rcu_cblist_init(srclp);
 	} else {
 		rhp->next = NULL;
 		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)
 {
@@ -161,7 +152,6 @@ void rcu_segcblist_init(struct rcu_segcblist *rsclp)
 	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;
 }
 
@@ -173,7 +163,6 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp)
 {
 	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;
 }
 
@@ -253,11 +242,9 @@ bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, unsigned long *lp)
  * 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);
@@ -275,15 +262,13 @@ void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
  * 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--)
@@ -307,8 +292,6 @@ bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
 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);
 }
 
@@ -361,9 +344,7 @@ void rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp,
 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;
 }
 

diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
@@ -15,15 +15,6 @@ static inline long rcu_cblist_n_cbs(struct rcu_cblist *rclp)
 	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,
@@ -59,18 +50,6 @@ static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp)
 #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?
@@ -106,9 +85,9 @@ struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp);
 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,

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
@@ -853,7 +853,7 @@ static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
 	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);
@@ -1052,7 +1052,7 @@ void srcu_barrier(struct srcu_struct *ssp)
 		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);
 		}

diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
@@ -22,6 +22,7 @@
 #include <linux/time.h>
 #include <linux/cpu.h>
 #include <linux/prefetch.h>
+#include <linux/slab.h>
 
 #include "rcu.h"
 
@@ -73,6 +74,31 @@ void rcu_sched_clock_irq(int user)
 	}
 }
 
+/*
+ * 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)
 {
@@ -100,7 +126,7 @@ 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;
 	}