LKML Archive on lore.kernel.org
 help / color / Atom feed
From: NeilBrown <neilb@suse.com>
To: Jeff Layton <jlayton@kernel.org>,
	Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "J. Bruce Fields" <bfields@fieldses.org>,
	Martin Wilck <mwilck@suse.de>,
	linux-fsdevel@vger.kernel.org,
	Frank Filz <ffilzlnx@mindspring.com>,
	linux-kernel@vger.kernel.org
Subject: [PATCH 2/5] fs/locks: allow a lock request to block other requests.
Date: Thu, 09 Aug 2018 12:04:41 +1000
Message-ID: <153378028110.1220.8149340480666080233.stgit@noble> (raw)
In-Reply-To: <153378012255.1220.6754153662007899557.stgit@noble>

Currently, a lock can block pending requests, but all pending
requests are equal.  If lots of pending requests are
mutually exclusive, this means they will all be woken up
and all but one will fail.  This can hurt performance.

So we will allow pending requests to block other requests.
Only the first request will be woken, and it will wake the others.

This patch doesn't implement this fully, but prepares the way.

- It acknowledges that a request might be blocking other requests,
  and when the request is converted to a lock, those blocked
  requests are moved across.
- When a request is removed, all blocked requests are woken.
- When deadlock-detection looks for the lock which blocks a
  given request, we follow the chain of ->fl_blocker all
  the way to the top.

Signed-off-by: NeilBrown <neilb@suse.com>
---
 fs/locks.c |   58 ++++++++++++++++++++++++++++++++++++++++------------------
 1 file changed, 40 insertions(+), 18 deletions(-)

diff --git a/fs/locks.c b/fs/locks.c
index 322491e70e41..b4812da2a374 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -408,9 +408,19 @@ void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
 			fl->fl_ops->fl_copy_lock(new, fl);
 	}
 }
-
 EXPORT_SYMBOL(locks_copy_lock);
 
+static void locks_move_blocks(struct file_lock *new, struct file_lock *fl)
+{
+	struct file_lock *f;
+
+	spin_lock(&blocked_lock_lock);
+	list_splice_init(&fl->fl_blocked, &new->fl_blocked);
+	list_for_each_entry(f, &fl->fl_blocked, fl_block)
+		f->fl_blocker = new;
+	spin_unlock(&blocked_lock_lock);
+}
+
 static inline int flock_translate_cmd(int cmd) {
 	if (cmd & LOCK_MAND)
 		return cmd & (LOCK_MAND | LOCK_RW);
@@ -681,9 +691,25 @@ static void __locks_delete_block(struct file_lock *waiter)
 	waiter->fl_blocker = NULL;
 }
 
+static void __locks_wake_up_blocks(struct file_lock *blocker)
+{
+	while (!list_empty(&blocker->fl_blocked)) {
+		struct file_lock *waiter;
+
+		waiter = list_first_entry(&blocker->fl_blocked,
+				struct file_lock, fl_block);
+		__locks_delete_block(waiter);
+		if (waiter->fl_lmops && waiter->fl_lmops->lm_notify)
+			waiter->fl_lmops->lm_notify(waiter);
+		else
+			wake_up(&waiter->fl_wait);
+	}
+}
+
 static void locks_delete_block(struct file_lock *waiter)
 {
 	spin_lock(&blocked_lock_lock);
+	__locks_wake_up_blocks(waiter);
 	__locks_delete_block(waiter);
 	spin_unlock(&blocked_lock_lock);
 }
@@ -735,17 +761,7 @@ static void locks_wake_up_blocks(struct file_lock *blocker)
 		return;
 
 	spin_lock(&blocked_lock_lock);
-	while (!list_empty(&blocker->fl_blocked)) {
-		struct file_lock *waiter;
-
-		waiter = list_first_entry(&blocker->fl_blocked,
-				struct file_lock, fl_block);
-		__locks_delete_block(waiter);
-		if (waiter->fl_lmops && waiter->fl_lmops->lm_notify)
-			waiter->fl_lmops->lm_notify(waiter);
-		else
-			wake_up(&waiter->fl_wait);
-	}
+	__locks_wake_up_blocks(blocker);
 	spin_unlock(&blocked_lock_lock);
 }
 
@@ -888,8 +904,11 @@ static struct file_lock *what_owner_is_waiting_for(struct file_lock *block_fl)
 	struct file_lock *fl;
 
 	hash_for_each_possible(blocked_hash, fl, fl_link, posix_owner_key(block_fl)) {
-		if (posix_same_owner(fl, block_fl))
-			return fl->fl_blocker;
+		if (posix_same_owner(fl, block_fl)) {
+			while (fl->fl_blocker)
+				fl = fl->fl_blocker;
+			return fl;
+		}
 	}
 	return NULL;
 }
@@ -982,6 +1001,7 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request)
 	if (request->fl_flags & FL_ACCESS)
 		goto out;
 	locks_copy_lock(new_fl, request);
+	locks_move_blocks(new_fl, request);
 	locks_insert_lock_ctx(new_fl, &ctx->flc_flock);
 	new_fl = NULL;
 	error = 0;
@@ -1174,6 +1194,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
 			goto out;
 		}
 		locks_copy_lock(new_fl, request);
+		locks_move_blocks(new_fl, request);
 		locks_insert_lock_ctx(new_fl, &fl->fl_list);
 		fl = new_fl;
 		new_fl = NULL;
@@ -2582,13 +2603,14 @@ void locks_remove_file(struct file *filp)
 int
 posix_unblock_lock(struct file_lock *waiter)
 {
-	int status = 0;
+	int status = -ENOENT;
 
 	spin_lock(&blocked_lock_lock);
-	if (waiter->fl_blocker)
+	if (waiter->fl_blocker) {
+		__locks_wake_up_blocks(waiter);
 		__locks_delete_block(waiter);
-	else
-		status = -ENOENT;
+		status = 0;
+	}
 	spin_unlock(&blocked_lock_lock);
 	return status;
 }



  parent reply index

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-08-09  2:04 [PATCH 0/5 - V2] locks: avoid thundering-herd wake-ups NeilBrown
2018-08-09  2:04 ` [PATCH 1/5] fs/locks: rename some lists and pointers NeilBrown
2018-08-09  2:04 ` NeilBrown [this message]
2018-08-09  2:04 ` [PATCH 3/5] fs/locks: change all *_conflict() functions to return a new enum NeilBrown
2018-08-09 11:09   ` Jeff Layton
2018-08-09 13:09   ` J. Bruce Fields
2018-08-09 23:40     ` NeilBrown
2018-08-10  0:56       ` J. Bruce Fields
2018-08-09  2:04 ` [PATCH 4/5] fs/locks: split out __locks_wake_one() NeilBrown
2018-08-09  2:04 ` [PATCH 5/5] fs/locks: create a tree of dependent requests NeilBrown
2018-08-09 11:17   ` Jeff Layton
2018-08-09 23:25     ` NeilBrown
2018-08-09 14:13   ` J. Bruce Fields
2018-08-09 22:19     ` NeilBrown
2018-08-10  0:36       ` J. Bruce Fields
2018-08-09 17:32 ` [PATCH 0/5 - V2] locks: avoid thundering-herd wake-ups J. Bruce Fields
2018-08-09 22:12   ` NeilBrown
2018-08-10  0:29     ` J. Bruce Fields
2018-08-10  1:50       ` NeilBrown
2018-08-10  2:52         ` J. Bruce Fields
2018-08-10  3:17           ` NeilBrown
2018-08-10 15:47             ` J. Bruce Fields
2018-08-11 11:56               ` Jeff Layton
2018-08-11 12:35                 ` J. Bruce Fields
2018-08-11 11:51       ` Jeff Layton
2018-08-11 12:21         ` J. Bruce Fields
2018-08-11 13:15           ` Jeff Layton

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=153378028110.1220.8149340480666080233.stgit@noble \
    --to=neilb@suse.com \
    --cc=bfields@fieldses.org \
    --cc=ffilzlnx@mindspring.com \
    --cc=jlayton@kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mwilck@suse.de \
    --cc=viro@zeniv.linux.org.uk \
    /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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git

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


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


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