Merge branch 'srcu-next.2025.08.21a' into HEAD

SRCU updates:
* Create srcu_read_{,un}lock_fast_notrace()
* Add srcu_read_lock_fast_notrace() and srcu_read_unlock_fast_notrace()
* Add guards for notrace variants of SRCU-fast readers
* Document srcu_read_{,un}lock_fast() use of implicit RCU readers
* Document srcu_flip() memory-barrier D relation to SRCU-fast
* Remove preempt_disable/enable() in Tiny SRCU srcu_gp_start_if_needed()

Author: paulmckrcu

include/linux/srcu.h

@@ -275,12 +275,27 @@ static inline struct srcu_ctr __percpu *srcu_read_lock_fast(struct srcu_struct *
 {
 	struct srcu_ctr __percpu *retval;
 
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_lock_fast().");
 	srcu_check_read_flavor_force(ssp, SRCU_READ_FLAVOR_FAST);
 	retval = __srcu_read_lock_fast(ssp);
 	rcu_try_lock_acquire(&ssp->dep_map);
 	return retval;
 }
 
+/*
+ * Used by tracing, cannot be traced and cannot call lockdep.
+ * See srcu_read_lock_fast() for more information.
+ */
+static inline struct srcu_ctr __percpu *srcu_read_lock_fast_notrace(struct srcu_struct *ssp)
+	__acquires(ssp)
+{
+	struct srcu_ctr __percpu *retval;
+
+	srcu_check_read_flavor_force(ssp, SRCU_READ_FLAVOR_FAST);
+	retval = __srcu_read_lock_fast(ssp);
+	return retval;
+}
+
 /**
  * srcu_down_read_fast - register a new reader for an SRCU-protected structure.
  * @ssp: srcu_struct in which to register the new reader.
@@ -295,6 +310,7 @@ static inline struct srcu_ctr __percpu *srcu_read_lock_fast(struct srcu_struct *
 static inline struct srcu_ctr __percpu *srcu_down_read_fast(struct srcu_struct *ssp) __acquires(ssp)
 {
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && in_nmi());
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_down_read_fast().");
 	srcu_check_read_flavor_force(ssp, SRCU_READ_FLAVOR_FAST);
 	return __srcu_read_lock_fast(ssp);
 }
@@ -389,6 +405,18 @@ static inline void srcu_read_unlock_fast(struct srcu_struct *ssp, struct srcu_ct
 	srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST);
 	srcu_lock_release(&ssp->dep_map);
 	__srcu_read_unlock_fast(ssp, scp);
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_unlock_fast().");
+}
+
+/*
+ * Used by tracing, cannot be traced and cannot call lockdep.
+ * See srcu_read_unlock_fast() for more information.
+ */
+static inline void srcu_read_unlock_fast_notrace(struct srcu_struct *ssp,
+						 struct srcu_ctr __percpu *scp) __releases(ssp)
+{
+	srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST);
+	__srcu_read_unlock_fast(ssp, scp);
 }
 
 /**
@@ -405,6 +433,7 @@ static inline void srcu_up_read_fast(struct srcu_struct *ssp, struct srcu_ctr __
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && in_nmi());
 	srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST);
 	__srcu_read_unlock_fast(ssp, scp);
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_up_read_fast().");
 }
 
 /**
@@ -486,4 +515,9 @@ DEFINE_LOCK_GUARD_1(srcu_fast, struct srcu_struct,
 		    srcu_read_unlock_fast(_T->lock, _T->scp),
 		    struct srcu_ctr __percpu *scp)
 
+DEFINE_LOCK_GUARD_1(srcu_fast_notrace, struct srcu_struct,
+		    _T->scp = srcu_read_lock_fast_notrace(_T->lock),
+		    srcu_read_unlock_fast_notrace(_T->lock, _T->scp),
+		    struct srcu_ctr __percpu *scp)
+
 #endif

include/linux/srcutree.h

@@ -232,23 +232,40 @@ static inline struct srcu_ctr __percpu *__srcu_ctr_to_ptr(struct srcu_struct *ss
  * srcu_read_unlock_fast().
  *
  * Note that both this_cpu_inc() and atomic_long_inc() are RCU read-side
- * critical sections either because they disables interrupts, because they
- * are a single instruction, or because they are a read-modify-write atomic
- * operation, depending on the whims of the architecture.
+ * critical sections either because they disables interrupts, because
+ * they are a single instruction, or because they are read-modify-write
+ * atomic operations, depending on the whims of the architecture.
+ * This matters because the SRCU-fast grace-period mechanism uses either
+ * synchronize_rcu() or synchronize_rcu_expedited(), that is, RCU,
+ * *not* SRCU, in order to eliminate the need for the read-side smp_mb()
+ * invocations that are used by srcu_read_lock() and srcu_read_unlock().
+ * The __srcu_read_unlock_fast() function also relies on this same RCU
+ * (again, *not* SRCU) trick to eliminate the need for smp_mb().
+ *
+ * The key point behind this RCU trick is that if any part of a given
+ * RCU reader precedes the beginning of a given RCU grace period, then
+ * the entirety of that RCU reader and everything preceding it happens
+ * before the end of that same RCU grace period.  Similarly, if any part
+ * of a given RCU reader follows the end of a given RCU grace period,
+ * then the entirety of that RCU reader and everything following it
+ * happens after the beginning of that same RCU grace period.  Therefore,
+ * the operations labeled Y in __srcu_read_lock_fast() and those labeled Z
+ * in __srcu_read_unlock_fast() are ordered against the corresponding SRCU
+ * read-side critical section from the viewpoint of the SRCU grace period.
+ * This is all the ordering that is required, hence no calls to smp_mb().
  *
  * This means that __srcu_read_lock_fast() is not all that fast
  * on architectures that support NMIs but do not supply NMI-safe
  * implementations of this_cpu_inc().
  */
-static inline struct srcu_ctr __percpu *__srcu_read_lock_fast(struct srcu_struct *ssp)
+static inline struct srcu_ctr __percpu notrace *__srcu_read_lock_fast(struct srcu_struct *ssp)
 {
 	struct srcu_ctr __percpu *scp = READ_ONCE(ssp->srcu_ctrp);
 
-	RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_lock_fast().");
 	if (!IS_ENABLED(CONFIG_NEED_SRCU_NMI_SAFE))
-		this_cpu_inc(scp->srcu_locks.counter); /* Y */
+		this_cpu_inc(scp->srcu_locks.counter); // Y, and implicit RCU reader.
 	else
-		atomic_long_inc(raw_cpu_ptr(&scp->srcu_locks));  /* Z */
+		atomic_long_inc(raw_cpu_ptr(&scp->srcu_locks));  // Y, and implicit RCU reader.
 	barrier(); /* Avoid leaking the critical section. */
 	return scp;
 }
@@ -259,23 +276,17 @@ static inline struct srcu_ctr __percpu *__srcu_read_lock_fast(struct srcu_struct
  * different CPU than that which was incremented by the corresponding
  * srcu_read_lock_fast(), but it must be within the same task.
  *
- * Note that both this_cpu_inc() and atomic_long_inc() are RCU read-side
- * critical sections either because they disables interrupts, because they
- * are a single instruction, or because they are a read-modify-write atomic
- * operation, depending on the whims of the architecture.
- *
- * This means that __srcu_read_unlock_fast() is not all that fast
- * on architectures that support NMIs but do not supply NMI-safe
- * implementations of this_cpu_inc().
+ * Please see the __srcu_read_lock_fast() function's header comment for
+ * information on implicit RCU readers and NMI safety.
  */
-static inline void __srcu_read_unlock_fast(struct srcu_struct *ssp, struct srcu_ctr __percpu *scp)
+static inline void notrace
+__srcu_read_unlock_fast(struct srcu_struct *ssp, struct srcu_ctr __percpu *scp)
 {
 	barrier();  /* Avoid leaking the critical section. */
 	if (!IS_ENABLED(CONFIG_NEED_SRCU_NMI_SAFE))
-		this_cpu_inc(scp->srcu_unlocks.counter);  /* Z */
+		this_cpu_inc(scp->srcu_unlocks.counter);  // Z, and implicit RCU reader.
 	else
-		atomic_long_inc(raw_cpu_ptr(&scp->srcu_unlocks));  /* Z */
-	RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_unlock_fast().");
+		atomic_long_inc(raw_cpu_ptr(&scp->srcu_unlocks));  // Z, and implicit RCU reader.
 }
 
 void __srcu_check_read_flavor(struct srcu_struct *ssp, int read_flavor);

kernel/rcu/srcutiny.c

@@ -176,10 +176,9 @@ static void srcu_gp_start_if_needed(struct srcu_struct *ssp)
 {
 	unsigned long cookie;
 
-	preempt_disable();  // Needed for PREEMPT_LAZY
+	lockdep_assert_preemption_disabled(); // Needed for PREEMPT_LAZY
 	cookie = get_state_synchronize_srcu(ssp);
 	if (ULONG_CMP_GE(READ_ONCE(ssp->srcu_idx_max), cookie)) {
-		preempt_enable();
 		return;
 	}
 	WRITE_ONCE(ssp->srcu_idx_max, cookie);
@@ -189,7 +188,6 @@ static void srcu_gp_start_if_needed(struct srcu_struct *ssp)
 		else if (list_empty(&ssp->srcu_work.entry))
 			list_add(&ssp->srcu_work.entry, &srcu_boot_list);
 	}
-	preempt_enable();
 }
 
 /*

kernel/rcu/srcutree.c

@@ -1168,6 +1168,16 @@ static void srcu_flip(struct srcu_struct *ssp)
 	 * counter update.  Note that both this memory barrier and the
 	 * one in srcu_readers_active_idx_check() provide the guarantee
 	 * for __srcu_read_lock().
+	 *
+	 * Note that this is a performance optimization, in which we spend
+	 * an otherwise unnecessary smp_mb() in order to reduce the number
+	 * of full per-CPU-variable scans in srcu_readers_lock_idx() and
+	 * srcu_readers_unlock_idx().  But this performance optimization
+	 * is not so optimal for SRCU-fast, where we would be spending
+	 * not smp_mb(), but rather synchronize_rcu().  At the same time,
+	 * the overhead of the smp_mb() is in the noise, so there is no
+	 * point in omitting it in the SRCU-fast case.  So the same code
+	 * is executed either way.
 	 */
 	smp_mb(); /* D */  /* Pairs with C. */
 }