locking/rwsem: Support optimistic spinning

We have reached the point where our mutexes are quite fine tuned
for a number of situations. This includes the use of heuristics
and optimistic spinning, based on MCS locking techniques.

Exclusive ownership of read-write semaphores are, conceptually,
just about the same as mutexes, making them close cousins. To
this end we need to make them both perform similarly, and
right now, rwsems are simply not up to it. This was discovered
by both reverting commit 4fc3f1d6 (mm/rmap, migration: Make
rmap_walk_anon() and try_to_unmap_anon() more scalable) and
similarly, converting some other mutexes (ie: i_mmap_mutex) to
rwsems. This creates a situation where users have to choose
between a rwsem and mutex taking into account this important
performance difference. Specifically, biggest difference between
both locks is when we fail to acquire a mutex in the fastpath,
optimistic spinning comes in to play and we can avoid a large
amount of unnecessary sleeping and overhead of moving tasks in
and out of wait queue. Rwsems do not have such logic.

This patch, based on the work from Tim Chen and I, adds support
for write-side optimistic spinning when the lock is contended.
It also includes support for the recently added cancelable MCS
locking for adaptive spinning. Note that is is only applicable
to the xadd method, and the spinlock rwsem variant remains intact.

Allowing optimistic spinning before putting the writer on the wait
queue reduces wait queue contention and provided greater chance
for the rwsem to get acquired. With these changes, rwsem is on par
with mutex. The performance benefits can be seen on a number of
workloads. For instance, on a 8 socket, 80 core 64bit Westmere box,
aim7 shows the following improvements in throughput:

 +--------------+---------------------+-----------------+
 |   Workload   | throughput-increase | number of users |
 +--------------+---------------------+-----------------+
 | alltests     | 20%                 | >1000           |
 | custom       | 27%, 60%            | 10-100, >1000   |
 | high_systime | 36%, 30%            | >100, >1000     |
 | shared       | 58%, 29%            | 10-100, >1000   |
 +--------------+---------------------+-----------------+

There was also improvement on smaller systems, such as a quad-core
x86-64 laptop running a 30Gb PostgreSQL (pgbench) workload for up
to +60% in throughput for over 50 clients. Additionally, benefits
were also noticed in exim (mail server) workloads. Furthermore, no
performance regression have been seen at all.

Based-on-work-from: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
[peterz: rej fixup due to comment patches, sched/rt.h header]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Alex Shi <alex.shi@linaro.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Michel Lespinasse <walken@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Hurley <peter@hurleysoftware.com>
Cc: "Paul E.McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: "Scott J Norton" <scott.norton@hp.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Chris Mason <clm@fb.com>
Cc: Josef Bacik <jbacik@fusionio.com>
Link: http://lkml.kernel.org/r/1399055055.6275.15.camel@buesod1.americas.hpqcorp.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 22 insertions, 3 deletions

diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 03f3b05..3e108f1 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -16,6 +16,7 @@
 
 #include <linux/atomic.h>
 
+struct optimistic_spin_queue;
 struct rw_semaphore;
 
 #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
@@ -23,9 +24,17 @@ struct rw_semaphore;
 #else
 /* All arch specific implementations share the same struct */
 struct rw_semaphore {
-	long			count;
-	raw_spinlock_t		wait_lock;
-	struct list_head	wait_list;
+	long count;
+	raw_spinlock_t wait_lock;
+	struct list_head wait_list;
+#ifdef CONFIG_SMP
+	/*
+	 * Write owner. Used as a speculative check to see
+	 * if the owner is running on the cpu.
+	 */
+	struct task_struct *owner;
+	struct optimistic_spin_queue *osq; /* spinner MCS lock */
+#endif
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 #endif
@@ -55,11 +64,21 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 # define __RWSEM_DEP_MAP_INIT(lockname)
 #endif
 
+#ifdef CONFIG_SMP
+#define __RWSEM_INITIALIZER(name)			\
+	{ RWSEM_UNLOCKED_VALUE,				\
+	  __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),	\
+	  LIST_HEAD_INIT((name).wait_list),		\
+	  NULL, /* owner */				\
+	  NULL /* mcs lock */                           \
+	  __RWSEM_DEP_MAP_INIT(name) }
+#else
 #define __RWSEM_INITIALIZER(name)			\
 	{ RWSEM_UNLOCKED_VALUE,				\
 	  __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),	\
 	  LIST_HEAD_INIT((name).wait_list)		\
 	  __RWSEM_DEP_MAP_INIT(name) }
+#endif
 
 #define DECLARE_RWSEM(name) \
 	struct rw_semaphore name = __RWSEM_INITIALIZER(name)