1 files changed, 124 insertions, 45 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index da6f5213fb74..8e78b2430c16 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -156,6 +156,7 @@ static void invoke_rcu_core(void);
 static void rcu_report_exp_rdp(struct rcu_data *rdp);
 static void sync_sched_exp_online_cleanup(int cpu);
 static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp);
+static bool rcu_rdp_is_offloaded(struct rcu_data *rdp);
 
 /* rcuc/rcub kthread realtime priority */
 static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
@@ -648,7 +649,6 @@ static noinstr void rcu_eqs_enter(bool user)
 	instrumentation_begin();
 	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
-	rdp = this_cpu_ptr(&rcu_data);
 	rcu_prepare_for_idle();
 	rcu_preempt_deferred_qs(current);
 
@@ -1077,7 +1077,6 @@ noinstr void rcu_nmi_enter(void)
 	} else if (!in_nmi()) {
 		instrumentation_begin();
 		rcu_irq_enter_check_tick();
-		instrumentation_end();
 	} else  {
 		instrumentation_begin();
 	}
@@ -1672,7 +1671,7 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	bool ret = false;
 	bool need_qs;
-	const bool offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
+	const bool offloaded = rcu_rdp_is_offloaded(rdp);
 
 	raw_lockdep_assert_held_rcu_node(rnp);
 
@@ -2128,7 +2127,7 @@ static void rcu_gp_cleanup(void)
 		needgp = true;
 	}
 	/* Advance CBs to reduce false positives below. */
-	offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
+	offloaded = rcu_rdp_is_offloaded(rdp);
 	if ((offloaded || !rcu_accelerate_cbs(rnp, rdp)) && needgp) {
 		WRITE_ONCE(rcu_state.gp_flags, RCU_GP_FLAG_INIT);
 		WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
@@ -2327,7 +2326,7 @@ rcu_report_qs_rdp(struct rcu_data *rdp)
 	unsigned long flags;
 	unsigned long mask;
 	bool needwake = false;
-	const bool offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
+	const bool offloaded = rcu_rdp_is_offloaded(rdp);
 	struct rcu_node *rnp;
 
 	WARN_ON_ONCE(rdp->cpu != smp_processor_id());
@@ -2414,7 +2413,7 @@ int rcutree_dying_cpu(unsigned int cpu)
 
 	blkd = !!(rnp->qsmask & rdp->grpmask);
 	trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
-			       blkd ? TPS("cpuofl") : TPS("cpuofl-bgp"));
+			       blkd ? TPS("cpuofl-bgp") : TPS("cpuofl"));
 	return 0;
 }
 
@@ -2497,7 +2496,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	int div;
 	bool __maybe_unused empty;
 	unsigned long flags;
-	const bool offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
+	const bool offloaded = rcu_rdp_is_offloaded(rdp);
 	struct rcu_head *rhp;
 	struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl);
 	long bl, count = 0;
@@ -3066,7 +3065,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
 	trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCBQueued"));
 
 	/* Go handle any RCU core processing required. */
-	if (unlikely(rcu_segcblist_is_offloaded(&rdp->cblist))) {
+	if (unlikely(rcu_rdp_is_offloaded(rdp))) {
 		__call_rcu_nocb_wake(rdp, was_alldone, flags); /* unlocks */
 	} else {
 		__call_rcu_core(rdp, head, flags);
@@ -3229,8 +3228,7 @@ krc_this_cpu_lock(unsigned long *flags)
 static inline void
 krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags)
 {
-	raw_spin_unlock(&krcp->lock);
-	local_irq_restore(flags);
+	raw_spin_unlock_irqrestore(&krcp->lock, flags);
 }
 
 static inline struct kvfree_rcu_bulk_data *
@@ -3464,7 +3462,7 @@ static void fill_page_cache_func(struct work_struct *work)
 
 	for (i = 0; i < rcu_min_cached_objs; i++) {
 		bnode = (struct kvfree_rcu_bulk_data *)
-			__get_free_page(GFP_KERNEL | __GFP_NOWARN);
+			__get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
 
 		if (bnode) {
 			raw_spin_lock_irqsave(&krcp->lock, flags);
@@ -3493,37 +3491,62 @@ run_page_cache_worker(struct kfree_rcu_cpu *krcp)
 	}
 }
 
+// Record ptr in a page managed by krcp, with the pre-krc_this_cpu_lock()
+// state specified by flags.  If can_alloc is true, the caller must
+// be schedulable and not be holding any locks or mutexes that might be
+// acquired by the memory allocator or anything that it might invoke.
+// Returns true if ptr was successfully recorded, else the caller must
+// use a fallback.
 static inline bool
-kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
+add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp,
+	unsigned long *flags, void *ptr, bool can_alloc)
 {
 	struct kvfree_rcu_bulk_data *bnode;
 	int idx;
 
-	if (unlikely(!krcp->initialized))
+	*krcp = krc_this_cpu_lock(flags);
+	if (unlikely(!(*krcp)->initialized))
 		return false;
 
-	lockdep_assert_held(&krcp->lock);
 	idx = !!is_vmalloc_addr(ptr);
 
 	/* Check if a new block is required. */
-	if (!krcp->bkvhead[idx] ||
-			krcp->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
-		bnode = get_cached_bnode(krcp);
-		/* Switch to emergency path. */
+	if (!(*krcp)->bkvhead[idx] ||
+			(*krcp)->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
+		bnode = get_cached_bnode(*krcp);
+		if (!bnode && can_alloc) {
+			krc_this_cpu_unlock(*krcp, *flags);
+
+			// __GFP_NORETRY - allows a light-weight direct reclaim
+			// what is OK from minimizing of fallback hitting point of
+			// view. Apart of that it forbids any OOM invoking what is
+			// also beneficial since we are about to release memory soon.
+			//
+			// __GFP_NOMEMALLOC - prevents from consuming of all the
+			// memory reserves. Please note we have a fallback path.
+			//
+			// __GFP_NOWARN - it is supposed that an allocation can
+			// be failed under low memory or high memory pressure
+			// scenarios.
+			bnode = (struct kvfree_rcu_bulk_data *)
+				__get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
+			*krcp = krc_this_cpu_lock(flags);
+		}
+
 		if (!bnode)
 			return false;
 
 		/* Initialize the new block. */
 		bnode->nr_records = 0;
-		bnode->next = krcp->bkvhead[idx];
+		bnode->next = (*krcp)->bkvhead[idx];
 
 		/* Attach it to the head. */
-		krcp->bkvhead[idx] = bnode;
+		(*krcp)->bkvhead[idx] = bnode;
 	}
 
 	/* Finally insert. */
-	krcp->bkvhead[idx]->records
-		[krcp->bkvhead[idx]->nr_records++] = ptr;
+	(*krcp)->bkvhead[idx]->records
+		[(*krcp)->bkvhead[idx]->nr_records++] = ptr;
 
 	return true;
 }
@@ -3561,8 +3584,6 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 		ptr = (unsigned long *) func;
 	}
 
-	krcp = krc_this_cpu_lock(&flags);
-
 	// Queue the object but don't yet schedule the batch.
 	if (debug_rcu_head_queue(ptr)) {
 		// Probable double kfree_rcu(), just leak.
@@ -3570,12 +3591,11 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 			  __func__, head);
 
 		// Mark as success and leave.
-		success = true;
-		goto unlock_return;
+		return;
 	}
 
 	kasan_record_aux_stack(ptr);
-	success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr);
+	success = add_ptr_to_bulk_krc_lock(&krcp, &flags, ptr, !head);
 	if (!success) {
 		run_page_cache_worker(krcp);
 
@@ -3774,8 +3794,8 @@ EXPORT_SYMBOL_GPL(synchronize_rcu);
  * get_state_synchronize_rcu - Snapshot current RCU state
  *
  * Returns a cookie that is used by a later call to cond_synchronize_rcu()
- * to determine whether or not a full grace period has elapsed in the
- * meantime.
+ * or poll_state_synchronize_rcu() to determine whether or not a full
+ * grace period has elapsed in the meantime.
  */
 unsigned long get_state_synchronize_rcu(void)
 {
@@ -3789,13 +3809,76 @@ unsigned long get_state_synchronize_rcu(void)
 EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
 
 /**
+ * start_poll_synchronize_rcu - Snapshot and start RCU grace period
+ *
+ * Returns a cookie that is used by a later call to cond_synchronize_rcu()
+ * or poll_state_synchronize_rcu() to determine whether or not a full
+ * grace period has elapsed in the meantime.  If the needed grace period
+ * is not already slated to start, notifies RCU core of the need for that
+ * grace period.
+ *
+ * Interrupts must be enabled for the case where it is necessary to awaken
+ * the grace-period kthread.
+ */
+unsigned long start_poll_synchronize_rcu(void)
+{
+	unsigned long flags;
+	unsigned long gp_seq = get_state_synchronize_rcu();
+	bool needwake;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+
+	lockdep_assert_irqs_enabled();
+	local_irq_save(flags);
+	rdp = this_cpu_ptr(&rcu_data);
+	rnp = rdp->mynode;
+	raw_spin_lock_rcu_node(rnp); // irqs already disabled.
+	needwake = rcu_start_this_gp(rnp, rdp, gp_seq);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	if (needwake)
+		rcu_gp_kthread_wake();
+	return gp_seq;
+}
+EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
+
+/**
+ * poll_state_synchronize_rcu - Conditionally wait for an RCU grace period
+ *
+ * @oldstate: return from call to get_state_synchronize_rcu() or start_poll_synchronize_rcu()
+ *
+ * If a full RCU grace period has elapsed since the earlier call from
+ * which oldstate was obtained, return @true, otherwise return @false.
+ * If @false is returned, it is the caller's responsibilty to invoke this
+ * function later on until it does return @true.  Alternatively, the caller
+ * can explicitly wait for a grace period, for example, by passing @oldstate
+ * to cond_synchronize_rcu() or by directly invoking synchronize_rcu().
+ *
+ * Yes, this function does not take counter wrap into account.
+ * But counter wrap is harmless.  If the counter wraps, we have waited for
+ * more than 2 billion grace periods (and way more on a 64-bit system!).
+ * Those needing to keep oldstate values for very long time periods
+ * (many hours even on 32-bit systems) should check them occasionally
+ * and either refresh them or set a flag indicating that the grace period
+ * has completed.
+ */
+bool poll_state_synchronize_rcu(unsigned long oldstate)
+{
+	if (rcu_seq_done(&rcu_state.gp_seq, oldstate)) {
+		smp_mb(); /* Ensure GP ends before subsequent accesses. */
+		return true;
+	}
+	return false;
+}
+EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu);
+
+/**
  * cond_synchronize_rcu - Conditionally wait for an RCU grace period
  *
  * @oldstate: return value from earlier call to get_state_synchronize_rcu()
  *
  * If a full RCU grace period has elapsed since the earlier call to
- * get_state_synchronize_rcu(), just return.  Otherwise, invoke
- * synchronize_rcu() to wait for a full grace period.
+ * get_state_synchronize_rcu() or start_poll_synchronize_rcu(), just return.
+ * Otherwise, invoke synchronize_rcu() to wait for a full grace period.
  *
  * Yes, this function does not take counter wrap into account.  But
  * counter wrap is harmless.  If the counter wraps, we have waited for
@@ -3804,10 +3887,8 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
  */
 void cond_synchronize_rcu(unsigned long oldstate)
 {
-	if (!rcu_seq_done(&rcu_state.gp_seq, oldstate))
+	if (!poll_state_synchronize_rcu(oldstate))
 		synchronize_rcu();
-	else
-		smp_mb(); /* Ensure GP ends before subsequent accesses. */
 }
 EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
 
@@ -3843,13 +3924,13 @@ static int rcu_pending(int user)
 		return 1;
 
 	/* Does this CPU have callbacks ready to invoke? */
-	if (!rcu_segcblist_is_offloaded(&rdp->cblist) &&
+	if (!rcu_rdp_is_offloaded(rdp) &&
 	    rcu_segcblist_ready_cbs(&rdp->cblist))
 		return 1;
 
 	/* Has RCU gone idle with this CPU needing another grace period? */
 	if (!gp_in_progress && rcu_segcblist_is_enabled(&rdp->cblist) &&
-	    !rcu_segcblist_is_offloaded(&rdp->cblist) &&
+	    !rcu_rdp_is_offloaded(rdp) &&
 	    !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
 		return 1;
 
@@ -3968,7 +4049,7 @@ void rcu_barrier(void)
 	for_each_possible_cpu(cpu) {
 		rdp = per_cpu_ptr(&rcu_data, cpu);
 		if (cpu_is_offline(cpu) &&
-		    !rcu_segcblist_is_offloaded(&rdp->cblist))
+		    !rcu_rdp_is_offloaded(rdp))
 			continue;
 		if (rcu_segcblist_n_cbs(&rdp->cblist) && cpu_online(cpu)) {
 			rcu_barrier_trace(TPS("OnlineQ"), cpu,
@@ -4083,15 +4164,13 @@ int rcutree_prepare_cpu(unsigned int cpu)
 	rdp->dynticks_nesting = 1;	/* CPU not up, no tearing. */
 	rcu_dynticks_eqs_online();
 	raw_spin_unlock_rcu_node(rnp);		/* irqs remain disabled. */
+
 	/*
-	 * Lock in case the CB/GP kthreads are still around handling
-	 * old callbacks (longer term we should flush all callbacks
-	 * before completing CPU offline)
+	 * Only non-NOCB CPUs that didn't have early-boot callbacks need to be
+	 * (re-)initialized.
 	 */
-	rcu_nocb_lock(rdp);
-	if (rcu_segcblist_empty(&rdp->cblist)) /* No early-boot CBs? */
+	if (!rcu_segcblist_is_enabled(&rdp->cblist))
 		rcu_segcblist_init(&rdp->cblist);  /* Re-enable callbacks. */
-	rcu_nocb_unlock(rdp);
 
 	/*
 	 * Add CPU to leaf rcu_node pending-online bitmask.  Any needed
@@ -4291,7 +4370,7 @@ void rcutree_migrate_callbacks(int cpu)
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	bool needwake;
 
-	if (rcu_segcblist_is_offloaded(&rdp->cblist) ||
+	if (rcu_rdp_is_offloaded(rdp) ||
 	    rcu_segcblist_empty(&rdp->cblist))
 		return;  /* No callbacks to migrate. */
 
@@ -4309,7 +4388,7 @@ void rcutree_migrate_callbacks(int cpu)
 	rcu_segcblist_disable(&rdp->cblist);
 	WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) !=
 		     !rcu_segcblist_n_cbs(&my_rdp->cblist));
-	if (rcu_segcblist_is_offloaded(&my_rdp->cblist)) {
+	if (rcu_rdp_is_offloaded(my_rdp)) {
 		raw_spin_unlock_rcu_node(my_rnp); /* irqs remain disabled. */
 		__call_rcu_nocb_wake(my_rdp, true, flags);
 	} else {