srcu: Create an SRCU-fast-updown API

This commit creates an SRCU-fast-updown API, including
DEFINE_SRCU_FAST_UPDOWN(), DEFINE_STATIC_SRCU_FAST_UPDOWN(),
__init_srcu_struct_fast_updown(), init_srcu_struct_fast_updown(),
srcu_read_lock_fast_updown(), srcu_read_unlock_fast_updown(),
__srcu_read_lock_fast_updown(), and __srcu_read_unlock_fast_updown().

These are initially identical to their SRCU-fast counterparts, but both
SRCU-fast and SRCU-fast-updown will be optimized in different directions
by later commits. SRCU-fast will lack any sort of srcu_down_read() and
srcu_up_read() APIs, which will enable extremely efficient NMI safety.
For its part, SRCU-fast-updown will not be NMI safe, which will enable
reasonably efficient implementations of srcu_down_read_fast() and
srcu_up_read_fast().

This API fork happens to meet two different future use cases.

* SRCU-fast will become the reimplementation basis for RCU-TASK-TRACE
  for consolidation. Since RCU-TASK-TRACE must be NMI safe, SRCU-fast
  must be as well.

* SRCU-fast-updown will be needed for uretprobes code in order to get
  rid of the read-side memory barriers while still allowing entering the
  reader at task level while exiting it in a timer handler.

This commit also adds rcutorture tests for the new APIs.  This
(annoyingly) needs to be in the same commit for bisectability.  With this
commit, the 0x8 value tests SRCU-fast-updown.  However, most SRCU-fast
testing will be via the RCU Tasks Trace wrappers.

[ paulmck: Apply s/0x8/0x4/ missing change per Boqun Feng feedback. ]
[ paulmck: Apply Akira Yokosawa feedback. ]

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <bpf@vger.kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>

1 files changed, 53 insertions, 2 deletions

diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 6080a9094618..d6f978b50472 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -199,8 +199,15 @@ struct srcu_struct {
  *
  * See include/linux/percpu-defs.h for the rules on per-CPU variables.
  *
- * DEFINE_SRCU_FAST() creates an srcu_struct and associated structures
- * whose readers must be of the SRCU-fast variety.
+ * DEFINE_SRCU_FAST() and DEFINE_STATIC_SRCU_FAST create an srcu_struct
+ * and associated structures whose readers must be of the SRCU-fast variety.
+ * DEFINE_SRCU_FAST_UPDOWN() and DEFINE_STATIC_SRCU_FAST_UPDOWN() create
+ * an srcu_struct and associated structures whose readers must be of the
+ * SRCU-fast-updown variety.  The key point (aside from error checking) with
+ * both varieties is that the grace periods must use synchronize_rcu()
+ * instead of smp_mb(), and given that the first (for example)
+ * srcu_read_lock_fast() might race with the first synchronize_srcu(),
+ * this different must be specified at initialization time.
  */
 #ifdef MODULE
 # define __DEFINE_SRCU(name, fast, is_static)							\
@@ -221,6 +228,10 @@ struct srcu_struct {
 #define DEFINE_STATIC_SRCU(name)	__DEFINE_SRCU(name, 0, static)
 #define DEFINE_SRCU_FAST(name)		__DEFINE_SRCU(name, SRCU_READ_FLAVOR_FAST, /* not static */)
 #define DEFINE_STATIC_SRCU_FAST(name)	__DEFINE_SRCU(name, SRCU_READ_FLAVOR_FAST, static)
+#define DEFINE_SRCU_FAST_UPDOWN(name)	__DEFINE_SRCU(name, SRCU_READ_FLAVOR_FAST_UPDOWN, \
+						      /* not static */)
+#define DEFINE_STATIC_SRCU_FAST_UPDOWN(name) \
+					__DEFINE_SRCU(name, SRCU_READ_FLAVOR_FAST_UPDOWN, static)
 
 int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp);
 void synchronize_srcu_expedited(struct srcu_struct *ssp);
@@ -305,6 +316,46 @@ __srcu_read_unlock_fast(struct srcu_struct *ssp, struct srcu_ctr __percpu *scp)
 		atomic_long_inc(raw_cpu_ptr(&scp->srcu_unlocks));  // Z, and implicit RCU reader.
 }
 
+/*
+ * Counts the new reader in the appropriate per-CPU element of the
+ * srcu_struct.  Returns a pointer that must be passed to the matching
+ * srcu_read_unlock_fast_updown().  This type of reader is compatible
+ * with srcu_down_read_fast() and srcu_up_read_fast().
+ *
+ * See the __srcu_read_lock_fast() comment for more details.
+ */
+static inline
+struct srcu_ctr __percpu notrace *__srcu_read_lock_fast_updown(struct srcu_struct *ssp)
+{
+	struct srcu_ctr __percpu *scp = READ_ONCE(ssp->srcu_ctrp);
+
+	if (!IS_ENABLED(CONFIG_NEED_SRCU_NMI_SAFE))
+		this_cpu_inc(scp->srcu_locks.counter); // Y, and implicit RCU reader.
+	else
+		atomic_long_inc(raw_cpu_ptr(&scp->srcu_locks));  // Y, and implicit RCU reader.
+	barrier(); /* Avoid leaking the critical section. */
+	return scp;
+}
+
+/*
+ * 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_fast(), but it must be within the same task.
+ *
+ * Please see the __srcu_read_lock_fast() function's header comment for
+ * information on implicit RCU readers and NMI safety.
+ */
+static inline void notrace
+__srcu_read_unlock_fast_updown(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, and implicit RCU reader.
+	else
+		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);
 
 // Record SRCU-reader usage type only for CONFIG_PROVE_RCU=y kernels.