From b76b4014f9d988d2412b873e4d4c13c7f9afc4e4 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sat, 28 Aug 2010 08:52:10 +0200 Subject: writeback: Fix lost wake-up shutting down writeback thread Setting the task state here may cause us to miss the wake up from kthread_stop(), so we need to recheck kthread_should_stop() or risk sleeping forever in the following schedule(). Symptom was an indefinite hang on an NFSv4 mount. (NFSv4 may create multiple mounts in a temporary namespace while traversing the mount path, and since the temporary namespace is immediately destroyed, it may end up destroying a mount very soon after it was created, possibly making this race more likely.) INFO: task mount.nfs4:4314 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. mount.nfs4 D 0000000000000000 2880 4314 4313 0x00000000 ffff88001ed6da28 0000000000000046 ffff88001ed6dfd8 ffff88001ed6dfd8 ffff88001ed6c000 ffff88001ed6c000 ffff88001ed6c000 ffff88001e5003a0 ffff88001ed6dfd8 ffff88001e5003a8 ffff88001ed6c000 ffff88001ed6dfd8 Call Trace: [] schedule_timeout+0x1cd/0x2e0 [] ? mark_held_locks+0x6c/0xa0 [] ? _raw_spin_unlock_irq+0x30/0x60 [] ? trace_hardirqs_on_caller+0x14d/0x190 [] ? sub_preempt_count+0xe/0xd0 [] wait_for_common+0x120/0x190 [] ? default_wake_function+0x0/0x20 [] wait_for_completion+0x1d/0x20 [] kthread_stop+0x4a/0x150 [] ? thaw_process+0x70/0x80 [] bdi_unregister+0x10a/0x1a0 [] nfs_put_super+0x19/0x20 [] generic_shutdown_super+0x54/0xe0 [] kill_anon_super+0x16/0x60 [] nfs4_kill_super+0x39/0x90 [] deactivate_locked_super+0x45/0x60 [] deactivate_super+0x49/0x70 [] mntput_no_expire+0x84/0xe0 [] release_mounts+0x9f/0xc0 [] put_mnt_ns+0x65/0x80 [] nfs_follow_remote_path+0x1e6/0x420 [] nfs4_try_mount+0x6f/0xd0 [] nfs4_get_sb+0xa2/0x360 [] vfs_kern_mount+0x88/0x1f0 [] do_kern_mount+0x52/0x130 [] ? _lock_kernel+0x6a/0x170 [] do_mount+0x26e/0x7f0 [] ? copy_mount_options+0xea/0x190 [] sys_mount+0x98/0xf0 [] system_call_fastpath+0x16/0x1b 1 lock held by mount.nfs4/4314: #0: (&type->s_umount_key#24){+.+...}, at: [] deactivate_super+0x41/0x70 Signed-off-by: J. Bruce Fields Signed-off-by: Jens Axboe Acked-by: Artem Bityutskiy --- fs/fs-writeback.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/fs-writeback.c') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 7d9d06ba184b..81e086d8aa57 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -808,7 +808,7 @@ int bdi_writeback_thread(void *data) wb->last_active = jiffies; set_current_state(TASK_INTERRUPTIBLE); - if (!list_empty(&bdi->work_list)) { + if (!list_empty(&bdi->work_list) || kthread_should_stop()) { __set_current_state(TASK_RUNNING); continue; } -- cgit v1.2.3-58-ga151 From 692ebd17c2905313fff3c504c249c6a0faad16ec Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 21 Sep 2010 11:51:01 +0200 Subject: bdi: Fix warnings in __mark_inode_dirty for /dev/zero and friends Inodes of devices such as /dev/zero can get dirty for example via utime(2) syscall or due to atime update. Backing device of such inodes (zero_bdi, etc.) is however unable to handle dirty inodes and thus __mark_inode_dirty complains. In fact, inode should be rather dirtied against backing device of the filesystem holding it. This is generally a good rule except for filesystems such as 'bdev' or 'mtd_inodefs'. Inodes in these pseudofilesystems are referenced from ordinary filesystem inodes and carry mapping with real data of the device. Thus for these inodes we have to use inode->i_mapping->backing_dev_info as we did so far. We distinguish these filesystems by checking whether sb->s_bdi points to a non-trivial backing device or not. Example: Assume we have an ext3 filesystem on /dev/sda1 mounted on /. There's a device inode A described by a path "/dev/sdb" on this filesystem. This inode will be dirtied against backing device "8:0" after this patch. bdev filesystem contains block device inode B coupled with our inode A. When someone modifies a page of /dev/sdb, it's B that gets dirtied and the dirtying happens against the backing device "8:16". Thus both inodes get filed to a correct bdi list. Cc: stable@kernel.org Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) (limited to 'fs/fs-writeback.c') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 81e086d8aa57..5581122bd2c0 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -52,8 +52,6 @@ struct wb_writeback_work { #define CREATE_TRACE_POINTS #include -#define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info) - /* * We don't actually have pdflush, but this one is exported though /proc... */ @@ -71,6 +69,27 @@ int writeback_in_progress(struct backing_dev_info *bdi) return test_bit(BDI_writeback_running, &bdi->state); } +static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info; + + /* + * For inodes on standard filesystems, we use superblock's bdi. For + * inodes on virtual filesystems, we want to use inode mapping's bdi + * because they can possibly point to something useful (think about + * block_dev filesystem). + */ + if (sb->s_bdi && sb->s_bdi != &noop_backing_dev_info) { + /* Some device inodes could play dirty tricks. Catch them... */ + WARN(bdi != sb->s_bdi && bdi_cap_writeback_dirty(bdi), + "Dirtiable inode bdi %s != sb bdi %s\n", + bdi->name, sb->s_bdi->name); + return sb->s_bdi; + } + return bdi; +} + static void bdi_queue_work(struct backing_dev_info *bdi, struct wb_writeback_work *work) { -- cgit v1.2.3-58-ga151 From aaead25b954879e1a708ff2f3602f494c18d20b5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 Oct 2010 14:25:33 +0200 Subject: writeback: always use sb->s_bdi for writeback purposes We currently use struct backing_dev_info for various different purposes. Originally it was introduced to describe a backing device which includes an unplug and congestion function and various bits of readahead information and VM-relevant flags. We're also using for tracking dirty inodes for writeback. To make writeback properly find all inodes we need to only access the per-filesystem backing_device pointed to by the superblock in ->s_bdi inside the writeback code, and not the instances pointeded to by inode->i_mapping->backing_dev which can be overriden by special devices or might not be set at all by some filesystems. Long term we should split out the writeback-relevant bits of struct backing_device_info (which includes more than the current bdi_writeback) and only point to it from the superblock while leaving the traditional backing device as a separate structure that can be overriden by devices. The one exception for now is the block device filesystem which really wants different writeback contexts for it's different (internal) inodes to handle the writeout more efficiently. For now we do this with a hack in fs-writeback.c because we're so late in the cycle, but in the future I plan to replace this with a superblock method that allows for multiple writeback contexts per filesystem. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) (limited to 'fs/fs-writeback.c') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 5581122bd2c0..ab38fef1c9a1 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -72,22 +72,11 @@ int writeback_in_progress(struct backing_dev_info *bdi) static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) { struct super_block *sb = inode->i_sb; - struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info; - /* - * For inodes on standard filesystems, we use superblock's bdi. For - * inodes on virtual filesystems, we want to use inode mapping's bdi - * because they can possibly point to something useful (think about - * block_dev filesystem). - */ - if (sb->s_bdi && sb->s_bdi != &noop_backing_dev_info) { - /* Some device inodes could play dirty tricks. Catch them... */ - WARN(bdi != sb->s_bdi && bdi_cap_writeback_dirty(bdi), - "Dirtiable inode bdi %s != sb bdi %s\n", - bdi->name, sb->s_bdi->name); - return sb->s_bdi; - } - return bdi; + if (strcmp(sb->s_type->name, "bdev") == 0) + return inode->i_mapping->backing_dev_info; + + return sb->s_bdi; } static void bdi_queue_work(struct backing_dev_info *bdi, -- cgit v1.2.3-58-ga151