Linux-Fsdevel Archive on lore.kernel.org
 help / color / Atom feed
From: Waiman Long <longman@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>, Will Deacon <will.deacon@arm.com>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Mike Kravetz <mike.kravetz@oracle.com>
Cc: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-mm@kvack.org, Davidlohr Bueso <dave@stgolabs.net>,
	Waiman Long <longman@redhat.com>
Subject: [PATCH 3/5] locking/osq: Allow early break from OSQ
Date: Wed, 11 Sep 2019 16:05:35 +0100
Message-ID: <20190911150537.19527-4-longman@redhat.com> (raw)
In-Reply-To: <20190911150537.19527-1-longman@redhat.com>

The current osq_lock() function will spin until it gets the lock or
when its time slice has been used up. There may be other reasons that
a task may want to back out from the OSQ before getting the lock. This
patch extends the osq_lock() function by adding two new arguments - a
break function pointer and its argument.  That break function will be
called, if defined, in each iteration of the loop to see if it should
break out early.

The optimistic_spin_node structure in osq_lock.h isn't needed by callers,
so it is moved into osq_lock.c.

Signed-off-by: Waiman Long <longman@redhat.com>
---
 include/linux/osq_lock.h  | 13 ++-----------
 kernel/locking/mutex.c    |  2 +-
 kernel/locking/osq_lock.c | 12 +++++++++++-
 kernel/locking/rwsem.c    |  2 +-
 4 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h
index 5581dbd3bd34..161eb6b26d6d 100644
--- a/include/linux/osq_lock.h
+++ b/include/linux/osq_lock.h
@@ -2,16 +2,6 @@
 #ifndef __LINUX_OSQ_LOCK_H
 #define __LINUX_OSQ_LOCK_H
 
-/*
- * An MCS like lock especially tailored for optimistic spinning for sleeping
- * lock implementations (mutex, rwsem, etc).
- */
-struct optimistic_spin_node {
-	struct optimistic_spin_node *next, *prev;
-	int locked; /* 1 if lock acquired */
-	int cpu; /* encoded CPU # + 1 value */
-};
-
 struct optimistic_spin_queue {
 	/*
 	 * Stores an encoded value of the CPU # of the tail node in the queue.
@@ -30,7 +20,8 @@ static inline void osq_lock_init(struct optimistic_spin_queue *lock)
 	atomic_set(&lock->tail, OSQ_UNLOCKED_VAL);
 }
 
-extern bool osq_lock(struct optimistic_spin_queue *lock);
+extern bool osq_lock(struct optimistic_spin_queue *lock,
+		     bool (*break_fn)(void *), void *break_arg);
 extern void osq_unlock(struct optimistic_spin_queue *lock);
 
 static inline bool osq_is_locked(struct optimistic_spin_queue *lock)
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 468a9b8422e3..8a1df82fd71a 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -654,7 +654,7 @@ mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
 		 * acquire the mutex all at once, the spinners need to take a
 		 * MCS (queued) lock first before spinning on the owner field.
 		 */
-		if (!osq_lock(&lock->osq))
+		if (!osq_lock(&lock->osq, NULL, NULL))
 			goto fail;
 	}
 
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index 6ef600aa0f47..40c94380a485 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -11,6 +11,12 @@
  * called from interrupt context and we have preemption disabled while
  * spinning.
  */
+struct optimistic_spin_node {
+	struct optimistic_spin_node *next, *prev;
+	int locked; /* 1 if lock acquired */
+	int cpu; /* encoded CPU # + 1 value */
+};
+
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);
 
 /*
@@ -87,7 +93,8 @@ osq_wait_next(struct optimistic_spin_queue *lock,
 	return next;
 }
 
-bool osq_lock(struct optimistic_spin_queue *lock)
+bool osq_lock(struct optimistic_spin_queue *lock,
+	      bool (*break_fn)(void *), void *break_arg)
 {
 	struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
 	struct optimistic_spin_node *prev, *next;
@@ -143,6 +150,9 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 		if (need_resched() || vcpu_is_preempted(node_cpu(node->prev)))
 			goto unqueue;
 
+		if (unlikely(break_fn) && break_fn(break_arg))
+			goto unqueue;
+
 		cpu_relax();
 	}
 	return true;
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 49f052d68404..c15926ecb21e 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -807,7 +807,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem, bool wlock,
 	preempt_disable();
 
 	/* sem->wait_lock should not be held when doing optimistic spinning */
-	if (!osq_lock(&sem->osq))
+	if (!osq_lock(&sem->osq, NULL, NULL))
 		goto done;
 
 	curtime = timeout ? sched_clock() : 0;
-- 
2.18.1


  parent reply index

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-09-11 15:05 [PATCH 0/5] hugetlbfs: Disable PMD sharing for large systems Waiman Long
2019-09-11 15:05 ` [PATCH 1/5] locking/rwsem: Add down_write_timedlock() Waiman Long
2019-09-11 15:05 ` [PATCH 2/5] locking/rwsem: Enable timeout check when spinning on owner Waiman Long
2019-09-11 15:05 ` Waiman Long [this message]
2019-09-11 15:05 ` [PATCH 4/5] locking/rwsem: Enable timeout check when staying in the OSQ Waiman Long
2019-09-11 15:05 ` [PATCH 5/5] hugetlbfs: Limit wait time when trying to share huge PMD Waiman Long
2019-09-11 15:14   ` Matthew Wilcox
2019-09-11 15:44     ` Waiman Long
2019-09-11 17:03       ` Mike Kravetz
2019-09-11 17:15         ` Waiman Long
2019-09-11 17:22           ` Qian Cai
2019-09-11 17:28           ` Waiman Long
2019-09-11 16:01   ` Qian Cai
2019-09-11 16:34     ` Waiman Long
2019-09-11 19:42       ` Qian Cai
2019-09-11 20:54         ` Waiman Long
2019-09-11 21:57           ` Qian Cai
2019-09-11 19:57   ` Matthew Wilcox
2019-09-11 20:51     ` Waiman Long
2019-09-12  3:26   ` Mike Kravetz
2019-09-12  3:41     ` Matthew Wilcox
2019-09-12  4:40       ` Davidlohr Bueso
2019-09-16 13:53         ` Waiman Long
2019-09-12  9:06     ` Waiman Long
2019-09-12 16:43       ` Mike Kravetz
2019-09-13 18:23         ` Waiman Long
2019-09-13  1:50 ` [PATCH 0/5] hugetlbfs: Disable PMD sharing for large systems Dave Chinner
2019-09-25  8:35   ` Peter Zijlstra

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190911150537.19527-4-longman@redhat.com \
    --to=longman@redhat.com \
    --cc=dave@stgolabs.net \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mike.kravetz@oracle.com \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=viro@zeniv.linux.org.uk \
    --cc=will.deacon@arm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-Fsdevel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-fsdevel linux-fsdevel/ https://lore.kernel.org/linux-fsdevel \
		linux-fsdevel@vger.kernel.org
	public-inbox-index linux-fsdevel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-fsdevel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git