This commit moves __srcu_read_lock_lite() and __srcu_read_unlock_lite()
into include/linux/srcu.h and marks them "static inline" so that they
can be inlined into srcu_read_lock_lite() and srcu_read_unlock_lite(),
respectively.  They are not hand-inlined due to Tree SRCU and Tiny SRCU
having different implementations.

The earlier removal of smp_mb() combined with the inlining produce
significant single-percentage performance wins.

Link: https://lore.kernel.org/all/CAEf4BzYgiNmSb=ZKQ65tm6nJDi1UX2Gq26cdHSH1mPwXJYZj5g@mail.gmail.com/

Reported-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
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>
---
 include/linux/srcutree.h | 39 ++++++++++++++++++++++++++++++++++++++
 kernel/rcu/srcutree.c    | 41 ----------------------------------------
 2 files changed, 39 insertions(+), 41 deletions(-)

diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 8074138cbd624..778eb61542e18 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -209,4 +209,43 @@ void synchronize_srcu_expedited(struct srcu_struct *ssp);
 void srcu_barrier(struct srcu_struct *ssp);
 void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf);
 
+/*
+ * 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.
+ */
+static inline 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;
+}
+
+/*
+ * 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.
+ */
+static inline 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().");
+}
+
 #endif
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index bf51758cf4a64..07147efcb64d3 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -763,47 +763,6 @@ 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
 
 /*
-- 
2.40.1