1 files changed, 83 insertions, 50 deletions

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 31706e3293bc..5e2e53464794 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -128,7 +128,7 @@ static void init_srcu_struct_data(struct srcu_struct *ssp)
 	 * Initialize the per-CPU srcu_data array, which feeds into the
 	 * leaves of the srcu_node tree.
 	 */
-	WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) !=
+	BUILD_BUG_ON(ARRAY_SIZE(sdp->srcu_lock_count) !=
 		     ARRAY_SIZE(sdp->srcu_unlock_count));
 	for_each_possible_cpu(cpu) {
 		sdp = per_cpu_ptr(ssp->sda, cpu);
@@ -187,7 +187,7 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags)
 	/* Each pass through this loop initializes one srcu_node structure. */
 	srcu_for_each_node_breadth_first(ssp, snp) {
 		spin_lock_init(&ACCESS_PRIVATE(snp, lock));
-		WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) !=
+		BUILD_BUG_ON(ARRAY_SIZE(snp->srcu_have_cbs) !=
 			     ARRAY_SIZE(snp->srcu_data_have_cbs));
 		for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) {
 			snp->srcu_have_cbs[i] = SRCU_SNP_INIT_SEQ;
@@ -419,41 +419,60 @@ static void check_init_srcu_struct(struct srcu_struct *ssp)
 }
 
 /*
- * Returns approximate total of the readers' ->srcu_lock_count[] values
- * for the rank of per-CPU counters specified by idx.
+ * Is the current or any upcoming grace period to be expedited?
  */
-static unsigned long srcu_readers_lock_idx(struct srcu_struct *ssp, int idx)
+static bool srcu_gp_is_expedited(struct srcu_struct *ssp)
+{
+	struct srcu_usage *sup = ssp->srcu_sup;
+
+	return ULONG_CMP_LT(READ_ONCE(sup->srcu_gp_seq), READ_ONCE(sup->srcu_gp_seq_needed_exp));
+}
+
+/*
+ * Computes approximate total of the readers' ->srcu_lock_count[] values
+ * for the rank of per-CPU counters specified by idx, and returns true if
+ * the caller did the proper barrier (gp), and if the count of the locks
+ * matches that of the unlocks passed in.
+ */
+static bool srcu_readers_lock_idx(struct srcu_struct *ssp, int idx, bool gp, unsigned long unlocks)
 {
 	int cpu;
+	unsigned long mask = 0;
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
+		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
 
-		sum += atomic_long_read(&cpuc->srcu_lock_count[idx]);
+		sum += atomic_long_read(&sdp->srcu_lock_count[idx]);
+		if (IS_ENABLED(CONFIG_PROVE_RCU))
+			mask = mask | READ_ONCE(sdp->srcu_reader_flavor);
 	}
-	return sum;
+	WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && (mask & (mask - 1)),
+		  "Mixed reader flavors for srcu_struct at %ps.\n", ssp);
+	if (mask & SRCU_READ_FLAVOR_LITE && !gp)
+		return false;
+	return sum == unlocks;
 }
 
 /*
  * Returns approximate total of the readers' ->srcu_unlock_count[] values
  * for the rank of per-CPU counters specified by idx.
  */
-static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx)
+static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx, unsigned long *rdm)
 {
 	int cpu;
 	unsigned long mask = 0;
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
+		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
 
-		sum += atomic_long_read(&cpuc->srcu_unlock_count[idx]);
-		if (IS_ENABLED(CONFIG_PROVE_RCU))
-			mask = mask | READ_ONCE(cpuc->srcu_nmi_safety);
+		sum += atomic_long_read(&sdp->srcu_unlock_count[idx]);
+		mask = mask | READ_ONCE(sdp->srcu_reader_flavor);
 	}
-	WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && (mask & (mask >> 1)),
-		  "Mixed NMI-safe readers for srcu_struct at %ps.\n", ssp);
+	WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && (mask & (mask - 1)),
+		  "Mixed reader flavors for srcu_struct at %ps.\n", ssp);
+	*rdm = mask;
 	return sum;
 }
 
@@ -463,22 +482,28 @@ static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx)
  */
 static bool srcu_readers_active_idx_check(struct srcu_struct *ssp, int idx)
 {
+	bool did_gp;
+	unsigned long rdm;
 	unsigned long unlocks;
 
-	unlocks = srcu_readers_unlock_idx(ssp, idx);
+	unlocks = srcu_readers_unlock_idx(ssp, idx, &rdm);
+	did_gp = !!(rdm & SRCU_READ_FLAVOR_LITE);
 
 	/*
 	 * Make sure that a lock is always counted if the corresponding
 	 * unlock is counted. Needs to be a smp_mb() as the read side may
 	 * contain a read from a variable that is written to before the
 	 * synchronize_srcu() in the write side. In this case smp_mb()s
-	 * A and B act like the store buffering pattern.
+	 * A and B (or X and Y) act like the store buffering pattern.
 	 *
-	 * This smp_mb() also pairs with smp_mb() C to prevent accesses
-	 * after the synchronize_srcu() from being executed before the
-	 * grace period ends.
+	 * This smp_mb() also pairs with smp_mb() C (or, in the case of X,
+	 * Z) to prevent accesses after the synchronize_srcu() from being
+	 * executed before the grace period ends.
 	 */
-	smp_mb(); /* A */
+	if (!did_gp)
+		smp_mb(); /* A */
+	else
+		synchronize_rcu(); /* X */
 
 	/*
 	 * If the locks are the same as the unlocks, then there must have
@@ -536,7 +561,7 @@ static bool srcu_readers_active_idx_check(struct srcu_struct *ssp, int idx)
 	 * which are unlikely to be configured with an address space fully
 	 * populated with memory, at least not anytime soon.
 	 */
-	return srcu_readers_lock_idx(ssp, idx) == unlocks;
+	return srcu_readers_lock_idx(ssp, idx, did_gp, unlocks);
 }
 
 /**
@@ -554,12 +579,12 @@ static bool srcu_readers_active(struct srcu_struct *ssp)
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
+		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
 
-		sum += atomic_long_read(&cpuc->srcu_lock_count[0]);
-		sum += atomic_long_read(&cpuc->srcu_lock_count[1]);
-		sum -= atomic_long_read(&cpuc->srcu_unlock_count[0]);
-		sum -= atomic_long_read(&cpuc->srcu_unlock_count[1]);
+		sum += atomic_long_read(&sdp->srcu_lock_count[0]);
+		sum += atomic_long_read(&sdp->srcu_lock_count[1]);
+		sum -= atomic_long_read(&sdp->srcu_unlock_count[0]);
+		sum -= atomic_long_read(&sdp->srcu_unlock_count[1]);
 	}
 	return sum;
 }
@@ -622,7 +647,7 @@ static unsigned long srcu_get_delay(struct srcu_struct *ssp)
 	unsigned long jbase = SRCU_INTERVAL;
 	struct srcu_usage *sup = ssp->srcu_sup;
 
-	if (ULONG_CMP_LT(READ_ONCE(sup->srcu_gp_seq), READ_ONCE(sup->srcu_gp_seq_needed_exp)))
+	if (srcu_gp_is_expedited(ssp))
 		jbase = 0;
 	if (rcu_seq_state(READ_ONCE(sup->srcu_gp_seq))) {
 		j = jiffies - 1;
@@ -687,28 +712,28 @@ void cleanup_srcu_struct(struct srcu_struct *ssp)
 }
 EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
 
-#ifdef CONFIG_PROVE_RCU
 /*
- * Check for consistent NMI safety.
+ * Check for consistent reader flavor.
  */
-void srcu_check_nmi_safety(struct srcu_struct *ssp, bool nmi_safe)
+void __srcu_check_read_flavor(struct srcu_struct *ssp, int read_flavor)
 {
-	int nmi_safe_mask = 1 << nmi_safe;
-	int old_nmi_safe_mask;
+	int old_read_flavor;
 	struct srcu_data *sdp;
 
-	/* NMI-unsafe use in NMI is a bad sign */
-	WARN_ON_ONCE(!nmi_safe && in_nmi());
+	/* NMI-unsafe use in NMI is a bad sign, as is multi-bit read_flavor values. */
+	WARN_ON_ONCE((read_flavor != SRCU_READ_FLAVOR_NMI) && in_nmi());
+	WARN_ON_ONCE(read_flavor & (read_flavor - 1));
+
 	sdp = raw_cpu_ptr(ssp->sda);
-	old_nmi_safe_mask = READ_ONCE(sdp->srcu_nmi_safety);
-	if (!old_nmi_safe_mask) {
-		WRITE_ONCE(sdp->srcu_nmi_safety, nmi_safe_mask);
-		return;
+	old_read_flavor = READ_ONCE(sdp->srcu_reader_flavor);
+	if (!old_read_flavor) {
+		old_read_flavor = cmpxchg(&sdp->srcu_reader_flavor, 0, read_flavor);
+		if (!old_read_flavor)
+			return;
 	}
-	WARN_ONCE(old_nmi_safe_mask != nmi_safe_mask, "CPU %d old state %d new state %d\n", sdp->cpu, old_nmi_safe_mask, nmi_safe_mask);
+	WARN_ONCE(old_read_flavor != read_flavor, "CPU %d old state %d new state %d\n", sdp->cpu, old_read_flavor, read_flavor);
 }
-EXPORT_SYMBOL_GPL(srcu_check_nmi_safety);
-#endif /* CONFIG_PROVE_RCU */
+EXPORT_SYMBOL_GPL(__srcu_check_read_flavor);
 
 /*
  * Counts the new reader in the appropriate per-CPU element of the
@@ -867,7 +892,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 	spin_lock_irq_rcu_node(sup);
 	idx = rcu_seq_state(sup->srcu_gp_seq);
 	WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
-	if (ULONG_CMP_LT(READ_ONCE(sup->srcu_gp_seq), READ_ONCE(sup->srcu_gp_seq_needed_exp)))
+	if (srcu_gp_is_expedited(ssp))
 		cbdelay = 0;
 
 	WRITE_ONCE(sup->srcu_last_gp_end, ktime_get_mono_fast_ns());
@@ -1122,6 +1147,8 @@ static void srcu_flip(struct srcu_struct *ssp)
 	 * it stays until either (1) Compilers learn about this sort of
 	 * control dependency or (2) Some production workload running on
 	 * a production system is unduly delayed by this slowpath smp_mb().
+	 * Except for _lite() readers, where it is inoperative, which
+	 * means that it is a good thing that it is redundant.
 	 */
 	smp_mb(); /* E */  /* Pairs with B and C. */
 
@@ -1139,7 +1166,9 @@ static void srcu_flip(struct srcu_struct *ssp)
 }
 
 /*
- * If SRCU is likely idle, return true, otherwise return false.
+ * If SRCU is likely idle, in other words, the next SRCU grace period
+ * should be expedited, return true, otherwise return false.  Except that
+ * in the presence of _lite() readers, always return false.
  *
  * Note that it is OK for several current from-idle requests for a new
  * grace period from idle to specify expediting because they will all end
@@ -1159,7 +1188,7 @@ static void srcu_flip(struct srcu_struct *ssp)
  * negligible when amortized over that time period, and the extra latency
  * of a needlessly non-expedited grace period is similarly negligible.
  */
-static bool srcu_might_be_idle(struct srcu_struct *ssp)
+static bool srcu_should_expedite(struct srcu_struct *ssp)
 {
 	unsigned long curseq;
 	unsigned long flags;
@@ -1168,6 +1197,9 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp)
 	unsigned long tlast;
 
 	check_init_srcu_struct(ssp);
+	/* If _lite() readers, don't do unsolicited expediting. */
+	if (this_cpu_read(ssp->sda->srcu_reader_flavor) & SRCU_READ_FLAVOR_LITE)
+		return false;
 	/* If the local srcu_data structure has callbacks, not idle.  */
 	sdp = raw_cpu_ptr(ssp->sda);
 	spin_lock_irqsave_rcu_node(sdp, flags);
@@ -1469,14 +1501,15 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
  * Implementation of these memory-ordering guarantees is similar to
  * that of synchronize_rcu().
  *
- * If SRCU is likely idle, expedite the first request.  This semantic
- * was provided by Classic SRCU, and is relied upon by its users, so TREE
- * SRCU must also provide it.  Note that detecting idleness is heuristic
- * and subject to both false positives and negatives.
+ * If SRCU is likely idle as determined by srcu_should_expedite(),
+ * expedite the first request.  This semantic was provided by Classic SRCU,
+ * and is relied upon by its users, so TREE SRCU must also provide it.
+ * Note that detecting idleness is heuristic and subject to both false
+ * positives and negatives.
  */
 void synchronize_srcu(struct srcu_struct *ssp)
 {
-	if (srcu_might_be_idle(ssp) || rcu_gp_is_expedited())
+	if (srcu_should_expedite(ssp) || rcu_gp_is_expedited())
 		synchronize_srcu_expedited(ssp);
 	else
 		__synchronize_srcu(ssp, true);