Merge branches 'rcutorture.2026.05.24' and 'misc.2026.05.24' into rcu-merge.2026.05.24

rcutorture.2026.05.24: Torture-test updates
misc.2026.05.24: Miscellaneous RCU updates

Author: urezki

Documentation/admin-guide/kernel-parameters.txt

@@ -5862,13 +5862,13 @@ Kernel parameters
 			use a call_rcu[_hurry]() path. Please note, this is for a
 			normal grace period.
 
-			How to enable it:
+			How to disable it:
 
-			echo 1 > /sys/module/rcutree/parameters/rcu_normal_wake_from_gp
-			or pass a boot parameter "rcutree.rcu_normal_wake_from_gp=1"
+			echo 0 > /sys/module/rcutree/parameters/rcu_normal_wake_from_gp
+			or pass a boot parameter "rcutree.rcu_normal_wake_from_gp=0"
 
-			Default is 1 if num_possible_cpus() <= 16 and it is not explicitly
-			disabled by the boot parameter passing 0.
+			Default is 1 if it is not explicitly disabled by the boot parameter
+			passing 0.
 
 	rcuscale.gp_async= [KNL]
 			Measure performance of asynchronous

include/linux/rcupdate.h

@@ -592,11 +592,13 @@ context_unsafe(							      \
  * lockdep checks for being in an RCU read-side critical section.  This is
  * useful when the value of this pointer is accessed, but the pointer is
  * not dereferenced, for example, when testing an RCU-protected pointer
- * against NULL.  Although rcu_access_pointer() may also be used in cases
- * where update-side locks prevent the value of the pointer from changing,
- * you should instead use rcu_dereference_protected() for this use case.
- * Within an RCU read-side critical section, there is little reason to
- * use rcu_access_pointer().
+ * against NULL.  Within an RCU read-side critical section, there is little
+ * reason to use rcu_access_pointer().  Although rcu_access_pointer() may
+ * also be used in cases where update-side locks prevent the value of the
+ * pointer from changing, you should instead use rcu_dereference_protected()
+ * for this use case.  It is also permissible to use rcu_access_pointer()
+ * within lockless updaters to obtain the old value for an atomic operation,
+ * for example, for cmpxchg().
  *
  * It is usually best to test the rcu_access_pointer() return value
  * directly in order to avoid accidental dereferences being introduced

include/linux/srcu.h

@@ -397,7 +397,7 @@ static inline struct srcu_ctr __percpu *srcu_read_lock_fast_notrace(struct srcu_
  *
  * The same srcu_struct may be used concurrently by srcu_down_read_fast()
  * and srcu_read_lock_fast().  However, the same definition/initialization
- * requirements called out for srcu_read_lock_safe() apply.
+ * requirements called out for srcu_read_lock_fast_updown() apply.
  */
 static inline struct srcu_ctr __percpu *srcu_down_read_fast(struct srcu_struct *ssp) __acquires_shared(ssp)
 {

kernel/rcu/tasks.h

@@ -373,7 +373,8 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
 	// Queuing callbacks before initialization not yet supported.
 	if (WARN_ON_ONCE(!rcu_segcblist_is_enabled(&rtpcp->cblist)))
 		rcu_segcblist_init(&rtpcp->cblist);
-	needwake = (func == wakeme_after_rcu) ||
+	needwake = (!havekthread && rcu_segcblist_empty(&rtpcp->cblist)) ||
+		   (func == wakeme_after_rcu) ||
 		   (rcu_segcblist_n_cbs(&rtpcp->cblist) == rcu_task_lazy_lim);
 	if (havekthread && !needwake && !timer_pending(&rtpcp->lazy_timer)) {
 		if (rtp->lazy_jiffies)

kernel/rcu/tree.c

@@ -492,7 +492,7 @@ static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param
 	int ret = kstrtoul(val, 0, &j);
 
 	if (!ret) {
-		WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : (j ?: 1));
+		WRITE_ONCE(*(ulong *)kp->arg, clamp_val(j, 1, HZ));
 		adjust_jiffies_till_sched_qs();
 	}
 	return ret;
@@ -1632,24 +1632,37 @@ static void rcu_sr_put_wait_head(struct llist_node *node)
 	atomic_set_release(&sr_wn->inuse, 0);
 }
 
-/* Enable rcu_normal_wake_from_gp automatically on small systems. */
-#define WAKE_FROM_GP_CPU_THRESHOLD 16
-
-static int rcu_normal_wake_from_gp = -1;
+static int rcu_normal_wake_from_gp = 1;
 module_param(rcu_normal_wake_from_gp, int, 0644);
 static struct workqueue_struct *sync_wq;
 
+#define RCU_SR_NORMAL_LATCH_THR 64
+
+/* Number of in-flight synchronize_rcu() calls queued on srs_next. */
+static atomic_long_t rcu_sr_normal_count;
+static int rcu_sr_normal_latched; /* 0/1 */
+
 static void rcu_sr_normal_complete(struct llist_node *node)
 {
 	struct rcu_synchronize *rs = container_of(
 		(struct rcu_head *) node, struct rcu_synchronize, head);
+	long nr;
 
 	WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) &&
 		!poll_state_synchronize_rcu_full(&rs->oldstate),
 		"A full grace period is not passed yet!\n");
 
 	/* Finally. */
 	complete(&rs->completion);
+	nr = atomic_long_dec_return(&rcu_sr_normal_count);
+	WARN_ON_ONCE(nr < 0);
+
+	/*
+	 * Unlatch: switch back to normal path when fully
+	 * drained and if it has been latched.
+	 */
+	if (nr == 0)
+		(void)cmpxchg_relaxed(&rcu_sr_normal_latched, 1, 0);
 }
 
 static void rcu_sr_normal_gp_cleanup_work(struct work_struct *work)
@@ -1795,6 +1808,24 @@ static bool rcu_sr_normal_gp_init(void)
 
 static void rcu_sr_normal_add_req(struct rcu_synchronize *rs)
 {
+	/*
+	 * Increment before publish to avoid a complete
+	 * vs enqueue race on latch.
+	 */
+	long nr = atomic_long_inc_return(&rcu_sr_normal_count);
+
+	/*
+	 * Latch when threshold is reached. Checking for an exact match
+	 * restricts cmpxchg() to a single context.
+	 *
+	 * This latch is intentionally relaxed and best-effort. Concurrent
+	 * set/clear can race and temporarily lose the latch, which is OK
+	 * because it only selects between the fast and fallback paths.
+	 */
+	if (nr == RCU_SR_NORMAL_LATCH_THR)
+		(void)cmpxchg_relaxed(&rcu_sr_normal_latched, 0, 1);
+
+	/* Publish for the GP kthread/worker. */
 	llist_add((struct llist_node *) &rs->head, &rcu_state.srs_next);
 }
 
@@ -2584,7 +2615,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 		const long npj = NSEC_PER_SEC / HZ;
 		long rrn = READ_ONCE(rcu_resched_ns);
 
-		rrn = rrn < NSEC_PER_MSEC ? NSEC_PER_MSEC : rrn > NSEC_PER_SEC ? NSEC_PER_SEC : rrn;
+		rrn = clamp(rrn, NSEC_PER_MSEC, NSEC_PER_SEC);
 		tlimit = local_clock() + rrn;
 		jlimit = jiffies + (rrn + npj + 1) / npj;
 		jlimit_check = true;
@@ -3278,14 +3309,15 @@ static void synchronize_rcu_normal(void)
 {
 	struct rcu_synchronize rs;
 
+	init_rcu_head_on_stack(&rs.head);
 	trace_rcu_sr_normal(rcu_state.name, &rs.head, TPS("request"));
 
-	if (READ_ONCE(rcu_normal_wake_from_gp) < 1) {
+	if (READ_ONCE(rcu_normal_wake_from_gp) < 1 ||
+			READ_ONCE(rcu_sr_normal_latched)) {
 		wait_rcu_gp(call_rcu_hurry);
 		goto trace_complete_out;
 	}
 
-	init_rcu_head_on_stack(&rs.head);
 	init_completion(&rs.completion);
 
 	/*
@@ -3302,10 +3334,10 @@ static void synchronize_rcu_normal(void)
 
 	/* Now we can wait. */
 	wait_for_completion(&rs.completion);
-	destroy_rcu_head_on_stack(&rs.head);
 
 trace_complete_out:
 	trace_rcu_sr_normal(rcu_state.name, &rs.head, TPS("complete"));
+	destroy_rcu_head_on_stack(&rs.head);
 }
 
 /**
@@ -4904,12 +4936,6 @@ void __init rcu_init(void)
 	sync_wq = alloc_workqueue("sync_wq", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
 	WARN_ON(!sync_wq);
 
-	/* Respect if explicitly disabled via a boot parameter. */
-	if (rcu_normal_wake_from_gp < 0) {
-		if (num_possible_cpus() <= WAKE_FROM_GP_CPU_THRESHOLD)
-			rcu_normal_wake_from_gp = 1;
-	}
-
 	/* Fill in default value for rcutree.qovld boot parameter. */
 	/* -After- the rcu_node ->lock fields are initialized! */
 	if (qovld < 0)

kernel/rcu/tree_nocb.h

@@ -655,7 +655,7 @@ static void nocb_gp_sleep(struct rcu_data *my_rdp, int cpu)
  * No-CBs GP kthreads come here to wait for additional callbacks to show up
  * or for grace periods to end.
  */
-static void nocb_gp_wait(struct rcu_data *my_rdp)
+static noinline_for_stack void nocb_gp_wait(struct rcu_data *my_rdp)
 {
 	bool bypass = false;
 	int __maybe_unused cpu = my_rdp->cpu;

scripts/checkpatch.pl

@@ -865,8 +865,6 @@ sub find_standard_signature {
 	"DEFINE_IDR"				=> "DEFINE_XARRAY",
 	"idr_init"				=> "xa_init",
 	"idr_init_base"				=> "xa_init_flags",
-	"rcu_read_lock_trace"			=> "rcu_read_lock_tasks_trace",
-	"rcu_read_unlock_trace"			=> "rcu_read_unlock_tasks_trace",
 );
 
 #Create a search pattern for all these strings to speed up a loop below
@@ -7596,12 +7594,15 @@ sub process {
 
 # Complain about RCU Tasks Trace used outside of BPF (and of course, RCU).
 		our $rcu_trace_funcs = qr{(?x:
+			rcu_read_lock_tasks_trace |
 			rcu_read_lock_trace |
 			rcu_read_lock_trace_held |
 			rcu_read_unlock_trace |
+			rcu_read_unlock_tasks_trace |
 			call_rcu_tasks_trace |
 			synchronize_rcu_tasks_trace |
 			rcu_barrier_tasks_trace |
+			rcu_tasks_trace_expedite_current |
 			rcu_request_urgent_qs_task
 		)};
 		our $rcu_trace_paths = qr{(?x: