From 5c3c7e64bbcb60db39d0d55c8fab39ef41d41c30 Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Sat, 10 Apr 2010 02:10:09 +0200 Subject: drbd: don't expose failed local READ to upper layers fix regression introduced in 8.3.3: commit a9b17323f2875f5d9b132c2b476a750bf44b10c7 Author: Lars Ellenberg Date: Wed Aug 12 15:18:33 2009 +0200 out-of-spinlock completion of master bio : (bio_rw(bio) == READA) ? read_completed_with_error : read_ahead_completed_with_error; is obviously not what was intended. No one noticed because of * page-cache at work, * local RAIDs Impact: Failed local READs are not retried remotely, but errored to upper layers, causing filesystems to remount read-only, or worse. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- drivers/block/drbd/drbd_worker.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 44bf6d11197..d48a1dfd7b2 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -235,7 +235,7 @@ void drbd_endio_pri(struct bio *bio, int error) if (unlikely(error)) { what = (bio_data_dir(bio) == WRITE) ? write_completed_with_error - : (bio_rw(bio) == READA) + : (bio_rw(bio) == READ) ? read_completed_with_error : read_ahead_completed_with_error; } else -- cgit v1.2.3-70-g09d2 From dcf097b247affd8b88ad410a92298590c5600f44 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Thu, 22 Apr 2010 11:54:52 -0400 Subject: blk-cgroup: Fix RCU correctness warning in cfq_init_queue() It is necessary to be in an RCU read-side critical section when invoking css_id(), so this patch adds one to blkiocg_add_blkio_group(). This is actually a false positive, because this is called at initialization time and hence always refers to the root cgroup, which cannot go away. [ 103.790505] =================================================== [ 103.790509] [ INFO: suspicious rcu_dereference_check() usage. ] [ 103.790511] --------------------------------------------------- [ 103.790514] kernel/cgroup.c:4432 invoked rcu_dereference_check() without protection! [ 103.790517] [ 103.790517] other info that might help us debug this: [ 103.790519] [ 103.790521] [ 103.790521] rcu_scheduler_active = 1, debug_locks = 1 [ 103.790524] 4 locks held by bash/4422: [ 103.790526] #0: (&buffer->mutex){+.+.+.}, at: [] sysfs_write_file+0x3c/0x144 [ 103.790537] #1: (s_active#102){.+.+.+}, at: [] sysfs_write_file+0xe7/0x144 [ 103.790544] #2: (&q->sysfs_lock){+.+.+.}, at: [] queue_attr_store+0x49/0x8f [ 103.790552] #3: (&(&blkcg->lock)->rlock){......}, at: [] blkiocg_add_blkio_group+0x2b/0xad [ 103.790560] [ 103.790561] stack backtrace: [ 103.790564] Pid: 4422, comm: bash Not tainted 2.6.34-rc4-blkio-second-crash #81 [ 103.790567] Call Trace: [ 103.790572] [] lockdep_rcu_dereference+0x9d/0xa5 [ 103.790577] [] css_id+0x44/0x57 [ 103.790581] [] blkiocg_add_blkio_group+0x53/0xad [ 103.790586] [] cfq_init_queue+0x139/0x32c [ 103.790591] [] elv_iosched_store+0xbf/0x1bf [ 103.790595] [] queue_attr_store+0x70/0x8f [ 103.790599] [] ? sysfs_write_file+0xe7/0x144 [ 103.790603] [] sysfs_write_file+0x108/0x144 [ 103.790609] [] vfs_write+0xae/0x10b [ 103.790612] [] ? trace_hardirqs_on_caller+0x10c/0x130 [ 103.790616] [] sys_write+0x4a/0x6e [ 103.790622] [] system_call_fastpath+0x16/0x1b [ 103.790625] Located-by: Miles Lane Signed-off-by: Vivek Goyal Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar Signed-off-by: Jens Axboe --- block/cfq-iosched.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 838834be115..5f127cfb2e9 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -3694,8 +3694,10 @@ static void *cfq_init_queue(struct request_queue *q) * to make sure that cfq_put_cfqg() does not try to kfree root group */ atomic_set(&cfqg->ref, 1); + rcu_read_lock(); blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg, (void *)cfqd, 0); + rcu_read_unlock(); #endif /* * Not strictly needed (since RB_ROOT just clears the node and we -- cgit v1.2.3-70-g09d2 From 0341509fdfc9519f7de6aabc5dd23217cef72b73 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 7 May 2010 08:57:00 +0200 Subject: blk-cgroup: Fix an RCU warning in blkiocg_create() with CONFIG_PROVE_RCU=y, a warning can be triggered: # mount -t cgroup -o blkio xxx /mnt # mkdir /mnt/subgroup ... kernel/cgroup.c:4442 invoked rcu_dereference_check() without protection! ... To fix this, we avoid caling css_depth() here, which is a bit simpler than the original code. Signed-off-by: Li Zefan Acked-by: Vivek Goyal Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 5fe03def34b..2cc682b860e 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -286,16 +286,16 @@ done: static struct cgroup_subsys_state * blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup) { - struct blkio_cgroup *blkcg, *parent_blkcg; + struct blkio_cgroup *blkcg; + struct cgroup *parent = cgroup->parent; - if (!cgroup->parent) { + if (!parent) { blkcg = &blkio_root_cgroup; goto done; } /* Currently we do not support hierarchy deeper than two level (0,1) */ - parent_blkcg = cgroup_to_blkio_cgroup(cgroup->parent); - if (css_depth(&parent_blkcg->css) > 0) + if (parent != cgroup->top_cgroup) return ERR_PTR(-EINVAL); blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL); -- cgit v1.2.3-70-g09d2