| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1429898069-28907-1-git-send-email-Waiman.Long@hp.com>
Date: Fri, 24 Apr 2015 13:54:29 -0400
From: Waiman Long <Waiman.Long@...com>
To: Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...nel.org>
Cc: linux-kernel@...r.kernel.org, Jason Low <jason.low2@...com>,
Davidlohr Bueso <dave@...olabs.net>,
Scott J Norton <scott.norton@...com>,
Douglas Hatch <doug.hatch@...com>,
Waiman Long <Waiman.Long@...com>
Subject: [PATCH v3] locking/rwsem: reduce spinlock contention in wakeup after up_read/up_write
In up_write()/up_read(), rwsem_wake() will be called whenever it
detects that some writers/readers are waiting. The rwsem_wake()
function will take the wait_lock and call __rwsem_do_wake() to do the
real wakeup. For a heavily contended rwsem, doing a spin_lock() on
wait_lock will cause further contention on the heavily contended rwsem
cacheline resulting in delay in the completion of the up_read/up_write
operations.
This patch makes the wait_lock taking and the call to __rwsem_do_wake()
optional if at least one spinning writer is present. The spinning
writer will be able to take the rwsem and call rwsem_wake() later
when it calls up_write(). With the presence of a spinning writer,
rwsem_wake() will now try to acquire the lock using trylock. If that
fails, it will just quit.
This patch also checks one more time in __rwsem_do_wake() to see if
the rwsem was stolen just before doing the expensive wakeup operation
which will be unnecessary if the lock was stolen.
On an 8-socket Westmere-EX server (80 cores, HT off), running AIM7's
high_systime workload (1000 users) on a vanilla 4.0 kernel produced
the following perf profile for spinlock contention:
9.23% reaim [kernel.kallsyms] [k] _raw_spin_lock_irqsave
|--97.39%-- rwsem_wake
|--0.69%-- try_to_wake_up
|--0.52%-- release_pages
--1.40%-- [...]
1.70% reaim [kernel.kallsyms] [k] _raw_spin_lock_irq
|--96.61%-- rwsem_down_write_failed
|--2.03%-- __schedule
|--0.50%-- run_timer_softirq
--0.86%-- [...]
Here the contended rwsems are the mmap_sem (mm_struct) and the
i_mmap_rwsem (address_space) with mostly write locking. With a
patched 4.0 kernel, the perf profile became:
1.87% reaim [kernel.kallsyms] [k] _raw_spin_lock_irqsave
|--87.64%-- rwsem_wake
|--2.80%-- release_pages
|--2.56%-- try_to_wake_up
|--1.10%-- __wake_up
|--1.06%-- pagevec_lru_move_fn
|--0.93%-- prepare_to_wait_exclusive
|--0.71%-- free_pid
|--0.58%-- get_page_from_freelist
|--0.57%-- add_device_randomness
--2.04%-- [...]
0.80% reaim [kernel.kallsyms] [k] _raw_spin_lock_irq
|--92.49%-- rwsem_down_write_failed
|--4.24%-- __schedule
|--1.37%-- run_timer_softirq
--1.91%-- [...]
The table below shows the % improvement in throughput (1100-2000 users)
in the various AIM7's workloads:
Workload % increase in throughput
-------- ------------------------
custom 3.8%
five-sec 3.5%
fserver 4.1%
high_systime 22.2%
shared 2.1%
short 10.1%
Signed-off-by: Waiman Long <Waiman.Long@...com>
---
include/linux/osq_lock.h | 5 +++
kernel/locking/rwsem-xadd.c | 72 ++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 76 insertions(+), 1 deletions(-)
v2->v3:
- Fix errors in commit log.
v1->v2:
- Add a memory barrier before calling spin_trylock for proper memory
ordering.
diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h
index 3a6490e..703ea5c 100644
--- a/include/linux/osq_lock.h
+++ b/include/linux/osq_lock.h
@@ -32,4 +32,9 @@ static inline void osq_lock_init(struct optimistic_spin_queue *lock)
extern bool osq_lock(struct optimistic_spin_queue *lock);
extern void osq_unlock(struct optimistic_spin_queue *lock);
+static inline bool osq_is_locked(struct optimistic_spin_queue *lock)
+{
+ return atomic_read(&lock->tail) != OSQ_UNLOCKED_VAL;
+}
+
#endif
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 2f7cc40..f52c69a 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -107,6 +107,35 @@ enum rwsem_wake_type {
RWSEM_WAKE_READ_OWNED /* Waker thread holds the read lock */
};
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+/*
+ * return true if there is an active writer by checking the owner field which
+ * should be set if there is one.
+ */
+static inline bool rwsem_has_active_writer(struct rw_semaphore *sem)
+{
+ return READ_ONCE(sem->owner) != NULL;
+}
+
+/*
+ * Return true if the rwsem has active spinner
+ */
+static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
+{
+ return osq_is_locked(&sem->osq);
+}
+#else /* CONFIG_RWSEM_SPIN_ON_OWNER */
+static inline bool rwsem_has_active_writer(struct rw_semaphore *sem)
+{
+ return false; /* Assume it has no active writer */
+}
+
+static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
+{
+ return false;
+}
+#endif /* CONFIG_RWSEM_SPIN_ON_OWNER */
+
/*
* handle the lock release when processes blocked on it that can now run
* - if we come here from up_xxxx(), then:
@@ -125,6 +154,14 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
struct list_head *next;
long oldcount, woken, loop, adjustment;
+ /*
+ * up_write() cleared the owner field before calling this function.
+ * If that field is now set, a writer must have stolen the lock and
+ * the wakeup operation should be aborted.
+ */
+ if (rwsem_has_active_writer(sem))
+ goto out;
+
waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
if (wake_type == RWSEM_WAKE_ANY)
@@ -478,7 +515,40 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
{
unsigned long flags;
- raw_spin_lock_irqsave(&sem->wait_lock, flags);
+ /*
+ * If a spinner is present, it is not necessary to do the wakeup.
+ * Try to do wakeup only if the trylock succeeds to minimize
+ * spinlock contention which may introduce too much delay in the
+ * unlock operation.
+ *
+ * spinning writer up_write/up_read caller
+ * --------------- -----------------------
+ * [S] osq_unlock() [L] osq
+ * MB MB
+ * [RmW] rwsem_try_write_lock() [RmW] spin_trylock(wait_lock)
+ *
+ * Here, it is important to make sure that there won't be a missed
+ * wakeup while the rwsem is free and the only spinning writer goes
+ * to sleep without taking the rwsem. In case the spinning writer is
+ * just going to break out of the waiting loop, it will still do a
+ * trylock in rwsem_down_write_failed() before sleeping. IOW, if
+ * rwsem_has_spinner() is true, it will guarantee at least one
+ * trylock attempt on the rwsem.
+ */
+ if (!rwsem_has_spinner(sem)) {
+ raw_spin_lock_irqsave(&sem->wait_lock, flags);
+ } else {
+ /*
+ * rwsem_has_spinner() is an atomic read while spin_trylock
+ * does not guarantee a full memory barrier. Insert a memory
+ * barrier here to make sure that wait_lock isn't read until
+ * after osq.
+ * Note: smp_rmb__after_atomic() should be used if available.
+ */
+ smp_mb__after_atomic();
+ if (!raw_spin_trylock_irqsave(&sem->wait_lock, flags))
+ return sem;
+ }
/* do nothing if list empty */
if (!list_empty(&sem->wait_list))
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists