srcu: Add srcu_read_lock_lite() and srcu_read_unlock_lite()

This patch adds srcu_read_lock_lite() and srcu_read_unlock_lite(), which
dispense with the read-side smp_mb() but also are restricted to code
regions that RCU is watching.  If a given srcu_struct structure uses
srcu_read_lock_lite() and srcu_read_unlock_lite(), it is not permitted
to use any other SRCU read-side marker, before, during, or after.

Another price of light-weight readers is heavier weight grace periods.
Such readers mean that SRCU grace periods on srcu_struct structures
used by light-weight readers will incur at least two calls to
synchronize_rcu().  In addition, normal SRCU grace periods for
light-weight-reader srcu_struct structures never auto-expedite.
Note that expedited SRCU grace periods for light-weight-reader
srcu_struct structures still invoke synchronize_rcu(), not
synchronize_srcu_expedited().  Something about wishing to keep
the IPIs down to a dull roar.

The srcu_read_lock_lite() and srcu_read_unlock_lite() functions may not
(repeat, *not*) be used from NMI handlers, but if this is needed, an
additional flavor of SRCU reader can be added by some future commit.

[ paulmck: Apply Alexei Starovoitov expediting feedback. ]
[ paulmck: Apply kernel test robot feedback. ]

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: kernel test robot <oliver.sang@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: <bpf@vger.kernel.org>
Reviewed-by: Neeraj Upadhyay <Neeraj.Upadhyay@amd.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>

1 files changed, 71 insertions, 11 deletions

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 602b4b8c4b89..8632a3caeb33 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -429,20 +429,29 @@ static bool srcu_gp_is_expedited(struct srcu_struct *ssp)
 }
 
 /*
- * Returns approximate total of the readers' ->srcu_lock_count[] values
- * for the rank of per-CPU counters specified by idx.
+ * 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 unsigned long srcu_readers_lock_idx(struct srcu_struct *ssp, int idx)
+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 *sdp = per_cpu_ptr(ssp->sda, cpu);
 
 		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;
 }
 
 /*
@@ -473,6 +482,7 @@ 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 = !!(raw_cpu_read(ssp->sda->srcu_reader_flavor) & SRCU_READ_FLAVOR_LITE);
 	unsigned long unlocks;
 
 	unlocks = srcu_readers_unlock_idx(ssp, idx);
@@ -482,13 +492,16 @@ static bool srcu_readers_active_idx_check(struct srcu_struct *ssp, int idx)
 	 * 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
@@ -546,7 +559,7 @@ 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);
 }
 
 /**
@@ -750,6 +763,47 @@ void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
+/*
+ * Counts the new reader in the appropriate per-CPU element of the
+ * srcu_struct.  Returns an index that must be passed to the matching
+ * srcu_read_unlock_lite().
+ *
+ * Note that this_cpu_inc() is an RCU read-side critical section either
+ * because it disables interrupts, because it is a single instruction,
+ * or because it is a read-modify-write atomic operation, depending on
+ * the whims of the architecture.
+ */
+int __srcu_read_lock_lite(struct srcu_struct *ssp)
+{
+	int idx;
+
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_lock_lite().");
+	idx = READ_ONCE(ssp->srcu_idx) & 0x1;
+	this_cpu_inc(ssp->sda->srcu_lock_count[idx].counter); /* Y */
+	barrier(); /* Avoid leaking the critical section. */
+	return idx;
+}
+EXPORT_SYMBOL_GPL(__srcu_read_lock_lite);
+
+/*
+ * Removes the count for the old reader from the appropriate
+ * per-CPU element of the srcu_struct.  Note that this may well be a
+ * different CPU than that which was incremented by the corresponding
+ * srcu_read_lock_lite(), but it must be within the same task.
+ *
+ * Note that this_cpu_inc() is an RCU read-side critical section either
+ * because it disables interrupts, because it is a single instruction,
+ * or because it is a read-modify-write atomic operation, depending on
+ * the whims of the architecture.
+ */
+void __srcu_read_unlock_lite(struct srcu_struct *ssp, int idx)
+{
+	barrier();  /* Avoid leaking the critical section. */
+	this_cpu_inc(ssp->sda->srcu_unlock_count[idx].counter);  /* Z */
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_unlock_lite().");
+}
+EXPORT_SYMBOL_GPL(__srcu_read_unlock_lite);
+
 #ifdef CONFIG_NEED_SRCU_NMI_SAFE
 
 /*
@@ -1134,6 +1188,8 @@ 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. */
 
@@ -1152,7 +1208,8 @@ static void srcu_flip(struct srcu_struct *ssp)
 
 /*
  * If SRCU is likely idle, in other words, the next SRCU grace period
- * should be expedited, return true, otherwise return false.
+ * 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
@@ -1181,6 +1238,9 @@ static bool srcu_should_expedite(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);