From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.8 required=3.0 tests=DKIMWL_WL_HIGH,DKIM_SIGNED, DKIM_VALID,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI, SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 2A804C43331 for ; Tue, 24 Mar 2020 13:16:01 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id E9D212166E for ; Tue, 24 Mar 2020 13:16:00 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1585055761; bh=NKkceryTMuai4X1AFLt/xoV5nKReHREJqxrtUSrhY+0=; h=From:To:Cc:Subject:Date:In-Reply-To:References:List-ID:From; b=CzfMgGSB7VKaO6ga7C8BlsQCjkYlY/UvPH5sUjwsrei5Eh48xNUXZNkyvehC/IsZz emaBWNRrkQ42upElr1dXyfH6FaW9MrgzzaIi0Cl9ElyujJEkPgOkV84uFigW4mylgt scMid09N6//Uw4tTU6lgwbnZ93GGaWEE+t0pezeM= Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728339AbgCXNP7 (ORCPT ); Tue, 24 Mar 2020 09:15:59 -0400 Received: from mail.kernel.org ([198.145.29.99]:35168 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727843AbgCXNP6 (ORCPT ); Tue, 24 Mar 2020 09:15:58 -0400 Received: from localhost (83-86-89-107.cable.dynamic.v4.ziggo.nl [83.86.89.107]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id 4660E206F6; Tue, 24 Mar 2020 13:15:57 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1585055757; bh=NKkceryTMuai4X1AFLt/xoV5nKReHREJqxrtUSrhY+0=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=eUyEFEGdtl58MV3xIdzd/dQVz4DQfzDu4w6+6hpC7RLbGOaAir5y7CAQ8+kmyd0IN seDU87GfuvT63OZTGEV5JJk43Kn6Auxz7PeMRCA9Pb5ezdnb+8Zov+kSMvuJAwtlot eyqbSf/pWlDnRtz1i0O0Di2zI/xfQ9Zy/FM/1TJo= From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, yangerkun , NeilBrown , Jeff Layton , Linus Torvalds , Sasha Levin Subject: [PATCH 5.4 002/102] locks: reinstate locks_delete_block optimization Date: Tue, 24 Mar 2020 14:09:54 +0100 Message-Id: <20200324130806.734419667@linuxfoundation.org> X-Mailer: git-send-email 2.25.2 In-Reply-To: <20200324130806.544601211@linuxfoundation.org> References: <20200324130806.544601211@linuxfoundation.org> User-Agent: quilt/0.66 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sender: stable-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: stable@vger.kernel.org From: Linus Torvalds [ Upstream commit dcf23ac3e846ca0cf626c155a0e3fcbbcf4fae8a ] There is measurable performance impact in some synthetic tests due to commit 6d390e4b5d48 (locks: fix a potential use-after-free problem when wakeup a waiter). Fix the race condition instead by clearing the fl_blocker pointer after the wake_up, using explicit acquire/release semantics. This does mean that we can no longer use the clearing of fl_blocker as the wait condition, so switch the waiters over to checking whether the fl_blocked_member list_head is empty. Reviewed-by: yangerkun Reviewed-by: NeilBrown Fixes: 6d390e4b5d48 (locks: fix a potential use-after-free problem when wakeup a waiter) Signed-off-by: Jeff Layton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/cifs/file.c | 3 ++- fs/locks.c | 54 ++++++++++++++++++++++++++++++++++++++++++++------ 2 files changed, 50 insertions(+), 7 deletions(-) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 0dbe47e897208..35c55cf38a358 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1173,7 +1173,8 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock) rc = posix_lock_file(file, flock, NULL); up_write(&cinode->lock_sem); if (rc == FILE_LOCK_DEFERRED) { - rc = wait_event_interruptible(flock->fl_wait, !flock->fl_blocker); + rc = wait_event_interruptible(flock->fl_wait, + list_empty(&flock->fl_blocked_member)); if (!rc) goto try_again; locks_delete_block(flock); diff --git a/fs/locks.c b/fs/locks.c index 426b55d333d5b..b8a31c1c4fff3 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -725,7 +725,6 @@ static void __locks_delete_block(struct file_lock *waiter) { locks_delete_global_blocked(waiter); list_del_init(&waiter->fl_blocked_member); - waiter->fl_blocker = NULL; } static void __locks_wake_up_blocks(struct file_lock *blocker) @@ -740,6 +739,13 @@ static void __locks_wake_up_blocks(struct file_lock *blocker) waiter->fl_lmops->lm_notify(waiter); else wake_up(&waiter->fl_wait); + + /* + * The setting of fl_blocker to NULL marks the "done" + * point in deleting a block. Paired with acquire at the top + * of locks_delete_block(). + */ + smp_store_release(&waiter->fl_blocker, NULL); } } @@ -753,11 +759,42 @@ int locks_delete_block(struct file_lock *waiter) { int status = -ENOENT; + /* + * If fl_blocker is NULL, it won't be set again as this thread "owns" + * the lock and is the only one that might try to claim the lock. + * + * We use acquire/release to manage fl_blocker so that we can + * optimize away taking the blocked_lock_lock in many cases. + * + * The smp_load_acquire guarantees two things: + * + * 1/ that fl_blocked_requests can be tested locklessly. If something + * was recently added to that list it must have been in a locked region + * *before* the locked region when fl_blocker was set to NULL. + * + * 2/ that no other thread is accessing 'waiter', so it is safe to free + * it. __locks_wake_up_blocks is careful not to touch waiter after + * fl_blocker is released. + * + * If a lockless check of fl_blocker shows it to be NULL, we know that + * no new locks can be inserted into its fl_blocked_requests list, and + * can avoid doing anything further if the list is empty. + */ + if (!smp_load_acquire(&waiter->fl_blocker) && + list_empty(&waiter->fl_blocked_requests)) + return status; + spin_lock(&blocked_lock_lock); if (waiter->fl_blocker) status = 0; __locks_wake_up_blocks(waiter); __locks_delete_block(waiter); + + /* + * The setting of fl_blocker to NULL marks the "done" point in deleting + * a block. Paired with acquire at the top of this function. + */ + smp_store_release(&waiter->fl_blocker, NULL); spin_unlock(&blocked_lock_lock); return status; } @@ -1350,7 +1387,8 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) error = posix_lock_inode(inode, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; - error = wait_event_interruptible(fl->fl_wait, !fl->fl_blocker); + error = wait_event_interruptible(fl->fl_wait, + list_empty(&fl->fl_blocked_member)); if (error) break; } @@ -1435,7 +1473,8 @@ int locks_mandatory_area(struct inode *inode, struct file *filp, loff_t start, error = posix_lock_inode(inode, &fl, NULL); if (error != FILE_LOCK_DEFERRED) break; - error = wait_event_interruptible(fl.fl_wait, !fl.fl_blocker); + error = wait_event_interruptible(fl.fl_wait, + list_empty(&fl.fl_blocked_member)); if (!error) { /* * If we've been sleeping someone might have @@ -1638,7 +1677,8 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) locks_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->fl_wait, - !new_fl->fl_blocker, break_time); + list_empty(&new_fl->fl_blocked_member), + break_time); percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); @@ -2122,7 +2162,8 @@ static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) error = flock_lock_inode(inode, fl); if (error != FILE_LOCK_DEFERRED) break; - error = wait_event_interruptible(fl->fl_wait, !fl->fl_blocker); + error = wait_event_interruptible(fl->fl_wait, + list_empty(&fl->fl_blocked_member)); if (error) break; } @@ -2399,7 +2440,8 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd, error = vfs_lock_file(filp, cmd, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; - error = wait_event_interruptible(fl->fl_wait, !fl->fl_blocker); + error = wait_event_interruptible(fl->fl_wait, + list_empty(&fl->fl_blocked_member)); if (error) break; } -- 2.20.1