[PATCH v4 4/6] srcu: Make Tiny call_srcu() safe to call from any context

Puranjay Mohan <[email protected]>
Newsgroups org.kernel.vger.rcu,dev.linux.lists.linux-rt-devel,org.kernel.vger.bpf,org.kernel.vger.linux-kernel
Message-ID <[email protected]>
Give Tiny call_srcu() the same treatment as Tree SRCU.  When interrupts
are disabled and the scheduler is up, stage the callback on the
srcu_struct's lockless list for an irq_work to re-issue later.  Tiny SRCU
is uniprocessor, so there is no CPU-offline drain.  A draining flag drops
a deferring call_srcu() that re-enters mid-drain (unless from an NMI), as
in Tree SRCU; such a drop can strand state the caller tied to the callback,
not just the callback itself.

Interrupts stay off for the whole batch.  TINY_SRCU implies !SMP, where
arch_irq_work_has_interrupt() is false, so the drain always waits for the
tick and a batch is whatever one tick's worth of interrupts-disabled
call_srcu()s staged.  Unlike the other three flavors srcu_do_enqueue() here
has no debug_rcu_head_queue(), so nothing reports a double call_srcu();
termination of the drain rests on srcu_do_enqueue() clearing ->next, and
the callback list self-links at the tail exactly as a double call_srcu()
made it before.

srcu_barrier() (now out of line) and cleanup_srcu_struct() drain the
deferred list first, so a deferred callback is re-issued onto the callback
list and invoked by the grace-period work that cleanup_srcu_struct()
flushes, rather than stranded on a soon-to-be-freed srcu_struct.
cleanup_srcu_struct() also syncs ->defer_iw, since that irq_work is
embedded in the srcu_struct the caller is about to free.

The draining flag is global rather than per-srcu_struct: a re-entrant
call_srcu(B) inside a drain of A raises B's own ->defer_iw, whose drain can
stage back onto A, so a per-srcu_struct flag would not break the chain.
The cost is that a drain of A also drops a non-NMI call_srcu() to any
other srcu_struct for its duration.

Gated by CONFIG_RCU_DEFER like Tree SRCU, though the srcu_struct members
are unconditional.

Suggested-by: Paul E. McKenney <[email protected]>
Signed-off-by: Puranjay Mohan <[email protected]>
---
 include/linux/srcutiny.h | 12 ++++--
 kernel/rcu/srcutiny.c    | 93 ++++++++++++++++++++++++++++++++++++++--
 2 files changed, 97 insertions(+), 8 deletions(-)

diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h
index fbcf13bc12d15..85b5de438450b 100644
--- a/include/linux/srcutiny.h
+++ b/include/linux/srcutiny.h
@@ -12,6 +12,7 @@
 #define _LINUX_SRCU_TINY_H
 
 #include <linux/irq_work_types.h>
+#include <linux/llist.h>
 #include <linux/swait.h>
 
 struct srcu_struct {
@@ -26,6 +27,8 @@ struct srcu_struct {
 	struct rcu_head **srcu_cb_tail;	/* Pending callbacks: Tail. */
 	struct work_struct srcu_work;	/* For driving grace periods. */
 	struct irq_work srcu_irq_work;	/* Defer schedule_work() to irq work. */
+	struct llist_head defer_cbs;	/* Callbacks deferred on re-entry. */
+	struct irq_work defer_iw;	/* Re-issues defer_cbs later. */
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map dep_map;
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
@@ -33,6 +36,7 @@ struct srcu_struct {
 
 void srcu_drive_gp(struct work_struct *wp);
 void srcu_tiny_irq_work(struct irq_work *irq_work);
+void srcu_defer_drain(struct irq_work *irq_work);
 
 #define __SRCU_STRUCT_INIT(name, __ignored, ___ignored, ____ignored)	\
 {									\
@@ -40,6 +44,9 @@ void srcu_tiny_irq_work(struct irq_work *irq_work);
 	.srcu_cb_tail = &name.srcu_cb_head,				\
 	.srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp),	\
 	.srcu_irq_work = { .func = srcu_tiny_irq_work },		\
+	.defer_cbs = LLIST_HEAD_INIT(name.defer_cbs),			\
+	.defer_iw = { .node = { .u_flags = IRQ_WORK_HARD_IRQ },		\
+		      .func = srcu_defer_drain },			\
 	__SRCU_DEP_MAP_INIT(name)					\
 }
 
@@ -131,10 +138,7 @@ static inline void synchronize_srcu_expedited(struct srcu_struct *ssp)
 	synchronize_srcu(ssp);
 }
 
-static inline void srcu_barrier(struct srcu_struct *ssp)
-{
-	synchronize_srcu(ssp);
-}
+void srcu_barrier(struct srcu_struct *ssp);
 
 static inline void srcu_expedite_current(struct srcu_struct *ssp) { }
 #define srcu_check_read_flavor(ssp, read_flavor) do { } while (0)
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index f9c498ae75df2..32b37d63d58aa 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -10,6 +10,7 @@
 
 #include <linux/export.h>
 #include <linux/irq_work.h>
+#include <linux/llist.h>
 #include <linux/mutex.h>
 #include <linux/preempt.h>
 #include <linux/rcupdate_wait.h>
@@ -29,6 +30,8 @@ extern int rcu_scheduler_active;
 static LIST_HEAD(srcu_boot_list);
 static bool srcu_init_done;
 
+static void __srcu_defer_drain(struct srcu_struct *ssp);
+
 static int init_srcu_struct_fields(struct srcu_struct *ssp)
 {
 	ssp->srcu_lock_nesting[0] = 0;
@@ -43,6 +46,8 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp)
 	INIT_WORK(&ssp->srcu_work, srcu_drive_gp);
 	INIT_LIST_HEAD(&ssp->srcu_work.entry);
 	init_irq_work(&ssp->srcu_irq_work, srcu_tiny_irq_work);
+	init_llist_head(&ssp->defer_cbs);
+	ssp->defer_iw = IRQ_WORK_INIT_HARD(srcu_defer_drain);
 	return 0;
 }
 
@@ -86,6 +91,16 @@ EXPORT_SYMBOL_GPL(init_srcu_struct_generic);
 void cleanup_srcu_struct(struct srcu_struct *ssp)
 {
 	WARN_ON(srcu_readers_active(ssp));
+	/*
+	 * Re-issue any deferred callbacks, then wait out ->defer_iw before it is
+	 * freed.  Skipped entirely with CONFIG_RCU_DEFER=n: irq_work_sync() ends
+	 * in an unconditional synchronize_rcu() wherever
+	 * arch_irq_work_has_interrupt() is false, which is every !SMP target.
+	 */
+	if (IS_ENABLED(CONFIG_RCU_DEFER)) {
+		__srcu_defer_drain(ssp);
+		irq_work_sync(&ssp->defer_iw);
+	}
 	irq_work_sync(&ssp->srcu_irq_work);
 	flush_work(&ssp->srcu_work);
 	WARN_ON(ssp->srcu_gp_running);
@@ -215,11 +230,11 @@ static void srcu_gp_start_if_needed(struct srcu_struct *ssp)
 }
 
 /*
- * Enqueue an SRCU callback on the specified srcu_struct structure,
- * initiating grace-period processing if it is not already running.
+ * Also called by __srcu_defer_drain() to re-issue a deferred callback, so it
+ * must not re-check the deferral condition.
  */
-void call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
-	       rcu_callback_t func)
+static void srcu_do_enqueue(struct srcu_struct *ssp, struct rcu_head *rhp,
+			    rcu_callback_t func)
 {
 	unsigned long flags;
 
@@ -233,6 +248,68 @@ void call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
 	srcu_gp_start_if_needed(ssp);
 	preempt_enable();
 }
+
+/*
+ * Set only by the irq_work drain, the one drain its own re-issue can re-feed;
+ * a callback staged during a direct drain is taken by ->defer_iw afterwards.
+ * Global rather than per-srcu_struct: a re-entrant call_srcu(B) inside a drain
+ * of A raises B's own ->defer_iw, whose drain can stage back onto A.
+ */
+static bool srcu_defer_draining;
+
+static void __srcu_defer_drain(struct srcu_struct *ssp)
+{
+	struct llist_node *node, *next;
+	unsigned long flags;
+
+	if (!IS_ENABLED(CONFIG_RCU_DEFER))
+		return;
+
+	/* Re-issued newest-first; nothing depends on call_srcu() ordering. */
+	local_irq_save(flags);
+	llist_for_each_safe(node, next, llist_del_all(&ssp->defer_cbs)) {
+		struct rcu_head *rhp = (struct rcu_head *)node;
+
+		srcu_do_enqueue(ssp, rhp, rhp->func);
+	}
+	local_irq_restore(flags);
+}
+
+/* Only the irq_work drain can be re-fed by its own re-issue; see Tree SRCU. */
+void srcu_defer_drain(struct irq_work *iw)
+{
+	struct srcu_struct *ssp = container_of(iw, struct srcu_struct, defer_iw);
+
+	WRITE_ONCE(srcu_defer_draining, true);
+	__srcu_defer_drain(ssp);
+	WRITE_ONCE(srcu_defer_draining, false);
+}
+EXPORT_SYMBOL_GPL(srcu_defer_drain);
+
+void call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
+	       rcu_callback_t func)
+{
+	if (should_rcu_defer()) {
+		/* A re-entrant call_srcu() during the drain would livelock it. */
+		if (READ_ONCE(srcu_defer_draining) && !in_nmi()) {
+			WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU),
+				  "call_srcu() re-entered during callback drain; leaking callback\n");
+			return;
+		}
+		rhp->func = func;
+		if (llist_add((struct llist_node *)rhp, &ssp->defer_cbs))
+			irq_work_queue(&ssp->defer_iw);
+		return;
+	}
+
+	/*
+	 * Only reachable from an NMI when deferral is off: before the scheduler
+	 * is up, or with CONFIG_RCU_DEFER=n.  The enqueue can then race.
+	 */
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && in_nmi());
+
+	srcu_do_enqueue(ssp, rhp, func);
+}
 EXPORT_SYMBOL_GPL(call_srcu);
 
 /*
@@ -262,6 +339,14 @@ void synchronize_srcu(struct srcu_struct *ssp)
 }
 EXPORT_SYMBOL_GPL(synchronize_srcu);
 
+/* Register any deferred callbacks, then wait for all in-flight ones. */
+void srcu_barrier(struct srcu_struct *ssp)
+{
+	__srcu_defer_drain(ssp);
+	synchronize_srcu(ssp);
+}
+EXPORT_SYMBOL_GPL(srcu_barrier);
+
 /*
  * get_state_synchronize_srcu - Provide an end-of-grace-period cookie
  */
-- 
2.53.0-Meta
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.