From ce7d363aaf1e28be8406a2976220944ca487e8ca Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 4 Mar 2013 12:37:14 +1100 Subject: md/raid5: schedule_construction should abort if nothing to do. Since commit 1ed850f356a0a422013846b5291acff08815008b md/raid5: make sure to_read and to_write never go negative. It has been possible for handle_stripe_dirtying to be called when there isn't actually any work to do. It then calls schedule_reconstruction() which will set R5_LOCKED on the parity block(s) even when nothing else is happening. This then causes problems in do_release_stripe(). So add checks to schedule_reconstruction() so that if it doesn't find anything to do, it just aborts. This bug was introduced in v3.7, so the patch is suitable for -stable kernels since then. Cc: stable@vger.kernel.org (v3.7+) Reported-by: majianpeng Signed-off-by: NeilBrown --- drivers/md/raid5.c | 38 ++++++++++++++++++++++---------------- 1 file changed, 22 insertions(+), 16 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 35031c8b2d0..5601dda1bc4 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2283,17 +2283,6 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, int level = conf->level; if (rcw) { - /* if we are not expanding this is a proper write request, and - * there will be bios with new data to be drained into the - * stripe cache - */ - if (!expand) { - sh->reconstruct_state = reconstruct_state_drain_run; - set_bit(STRIPE_OP_BIODRAIN, &s->ops_request); - } else - sh->reconstruct_state = reconstruct_state_run; - - set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request); for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; @@ -2306,6 +2295,21 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, s->locked++; } } + /* if we are not expanding this is a proper write request, and + * there will be bios with new data to be drained into the + * stripe cache + */ + if (!expand) { + if (!s->locked) + /* False alarm, nothing to do */ + return; + sh->reconstruct_state = reconstruct_state_drain_run; + set_bit(STRIPE_OP_BIODRAIN, &s->ops_request); + } else + sh->reconstruct_state = reconstruct_state_run; + + set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request); + if (s->locked + conf->max_degraded == disks) if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state)) atomic_inc(&conf->pending_full_writes); @@ -2314,11 +2318,6 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) || test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags))); - sh->reconstruct_state = reconstruct_state_prexor_drain_run; - set_bit(STRIPE_OP_PREXOR, &s->ops_request); - set_bit(STRIPE_OP_BIODRAIN, &s->ops_request); - set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request); - for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; if (i == pd_idx) @@ -2333,6 +2332,13 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, s->locked++; } } + if (!s->locked) + /* False alarm - nothing to do */ + return; + sh->reconstruct_state = reconstruct_state_prexor_drain_run; + set_bit(STRIPE_OP_PREXOR, &s->ops_request); + set_bit(STRIPE_OP_BIODRAIN, &s->ops_request); + set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request); } /* keep the parity disk(s) locked while asynchronous operations -- cgit v1.2.3-18-g5258 From e3620a3ad52609f64a2402e4b59300afb4b83b77 Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Thu, 7 Mar 2013 16:22:01 -0600 Subject: MD RAID5: Avoid accessing gendisk or queue structs when not available MD RAID5: Fix kernel oops when RAID4/5/6 is used via device-mapper Commit a9add5d (v3.8-rc1) added blktrace calls to the RAID4/5/6 driver. However, when device-mapper is used to create RAID4/5/6 arrays, the mddev->gendisk and mddev->queue fields are not setup. Therefore, calling things like trace_block_bio_remap will cause a kernel oops. This patch conditionalizes those calls on whether the proper fields exist to make the calls. (Device-mapper will call trace_block_bio_remap on its own.) This patch is suitable for the 3.8.y stable kernel. Cc: stable@vger.kernel.org (v3.8+) Signed-off-by: Jonathan Brassow Signed-off-by: NeilBrown --- drivers/md/raid5.c | 33 ++++++++++++++++++++------------- 1 file changed, 20 insertions(+), 13 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 5601dda1bc4..52ba88a1066 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -674,9 +674,11 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) bi->bi_next = NULL; if (rrdev) set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags); - trace_block_bio_remap(bdev_get_queue(bi->bi_bdev), - bi, disk_devt(conf->mddev->gendisk), - sh->dev[i].sector); + + if (conf->mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(bi->bi_bdev), + bi, disk_devt(conf->mddev->gendisk), + sh->dev[i].sector); generic_make_request(bi); } if (rrdev) { @@ -704,9 +706,10 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) rbi->bi_io_vec[0].bv_offset = 0; rbi->bi_size = STRIPE_SIZE; rbi->bi_next = NULL; - trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev), - rbi, disk_devt(conf->mddev->gendisk), - sh->dev[i].sector); + if (conf->mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev), + rbi, disk_devt(conf->mddev->gendisk), + sh->dev[i].sector); generic_make_request(rbi); } if (!rdev && !rrdev) { @@ -2835,8 +2838,10 @@ static void handle_stripe_dirtying(struct r5conf *conf, set_bit(STRIPE_HANDLE, &sh->state); if (rmw < rcw && rmw > 0) { /* prefer read-modify-write, but need to get some data */ - blk_add_trace_msg(conf->mddev->queue, "raid5 rmw %llu %d", - (unsigned long long)sh->sector, rmw); + if (conf->mddev->queue) + blk_add_trace_msg(conf->mddev->queue, + "raid5 rmw %llu %d", + (unsigned long long)sh->sector, rmw); for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; if ((dev->towrite || i == sh->pd_idx) && @@ -2886,7 +2891,7 @@ static void handle_stripe_dirtying(struct r5conf *conf, } } } - if (rcw) + if (rcw && conf->mddev->queue) blk_add_trace_msg(conf->mddev->queue, "raid5 rcw %llu %d %d %d", (unsigned long long)sh->sector, rcw, qread, test_bit(STRIPE_DELAYED, &sh->state)); @@ -3993,9 +3998,10 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) atomic_inc(&conf->active_aligned_reads); spin_unlock_irq(&conf->device_lock); - trace_block_bio_remap(bdev_get_queue(align_bi->bi_bdev), - align_bi, disk_devt(mddev->gendisk), - raid_bio->bi_sector); + if (mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(align_bi->bi_bdev), + align_bi, disk_devt(mddev->gendisk), + raid_bio->bi_sector); generic_make_request(align_bi); return 1; } else { @@ -4089,7 +4095,8 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule) } spin_unlock_irq(&conf->device_lock); } - trace_block_unplug(mddev->queue, cnt, !from_schedule); + if (mddev->queue) + trace_block_unplug(mddev->queue, cnt, !from_schedule); kfree(cb); } -- cgit v1.2.3-18-g5258 From 90584fc93d461520a888f691144f0879283b3624 Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Thu, 7 Mar 2013 16:24:26 -0600 Subject: MD: Prevent sysfs operations on uninitialized kobjects MD: Prevent sysfs operations on uninitialized kobjects Device-mapper does not use sysfs; but when device-mapper is leveraging MD's RAID personalities, MD sometimes attempts to update sysfs. This patch adds checks for 'mddev-kobj.sd' in sysfs_[un]link_rdev to ensure it is about to operate on something valid. This patch also checks for 'mddev->kobj.sd' before calling 'sysfs_notify' in 'remove_and_add_spares'. Although 'sysfs_notify' already makes this check, doing so in 'remove_and_add_spares' prevents an additional mutex operation. Signed-off-by: Jonathan Brassow Signed-off-by: NeilBrown --- drivers/md/md.c | 6 ++---- drivers/md/md.h | 4 ++-- 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index fcb878f8879..aeceedfc530 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -7663,10 +7663,8 @@ static int remove_and_add_spares(struct mddev *mddev) removed++; } } - if (removed) - sysfs_notify(&mddev->kobj, NULL, - "degraded"); - + if (removed && mddev->kobj.sd) + sysfs_notify(&mddev->kobj, NULL, "degraded"); rdev_for_each(rdev, mddev) { if (rdev->raid_disk >= 0 && diff --git a/drivers/md/md.h b/drivers/md/md.h index eca59c3074e..d90fb1a879e 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -506,7 +506,7 @@ static inline char * mdname (struct mddev * mddev) static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; - if (!test_bit(Replacement, &rdev->flags)) { + if (!test_bit(Replacement, &rdev->flags) && mddev->kobj.sd) { sprintf(nm, "rd%d", rdev->raid_disk); return sysfs_create_link(&mddev->kobj, &rdev->kobj, nm); } else @@ -516,7 +516,7 @@ static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev) static inline void sysfs_unlink_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; - if (!test_bit(Replacement, &rdev->flags)) { + if (!test_bit(Replacement, &rdev->flags) && mddev->kobj.sd) { sprintf(nm, "rd%d", rdev->raid_disk); sysfs_remove_link(&mddev->kobj, nm); } -- cgit v1.2.3-18-g5258 From f8dfcffd0472a0f353f34a567ad3f53568914d04 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 12 Mar 2013 12:18:06 +1100 Subject: md/raid5: ensure sync and DISCARD don't happen at the same time. A number of problems can occur due to races between resync/recovery and discard. - if sync_request calls handle_stripe() while a discard is happening on the stripe, it might call handle_stripe_clean_event before all of the individual discard requests have completed (so some devices are still locked, but not all). Since commit ca64cae96037de16e4af92678814f5d4bf0c1c65 md/raid5: Make sure we clear R5_Discard when discard is finished. this will cause R5_Discard to be cleared for the parity device, so handle_stripe_clean_event() will not be called when the other devices do become unlocked, so their ->written will not be cleared. This ultimately leads to a WARN_ON in init_stripe and a lock-up. - If handle_stripe_clean_event() does clear R5_UPTODATE at an awkward time for resync, it can lead to s->uptodate being less than disks in handle_parity_checks5(), which triggers a BUG (because it is one). So: - keep R5_Discard on the parity device until all other devices have completed their discard request - make sure we don't try to have a 'discard' and a 'sync' action at the same time. This involves a new stripe flag to we know when a 'discard' is happening, and the use of R5_Overlap on the parity disk so when a discard is wanted while a sync is active, so we know to wake up the discard at the appropriate time. Discard support for RAID5 was added in 3.7, so this is suitable for any -stable kernel since 3.7. Cc: stable@vger.kernel.org (v3.7+) Reported-by: Jes Sorensen Tested-by: Jes Sorensen Signed-off-by: NeilBrown --- drivers/md/raid5.c | 45 +++++++++++++++++++++++++++++++++++++++------ drivers/md/raid5.h | 1 + 2 files changed, 40 insertions(+), 6 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 52ba88a1066..42a89972874 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2576,6 +2576,8 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh, int i; clear_bit(STRIPE_SYNCING, &sh->state); + if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags)) + wake_up(&conf->wait_for_overlap); s->syncing = 0; s->replacing = 0; /* There is nothing more to do for sync/check/repair. @@ -2749,6 +2751,7 @@ static void handle_stripe_clean_event(struct r5conf *conf, { int i; struct r5dev *dev; + int discard_pending = 0; for (i = disks; i--; ) if (sh->dev[i].written) { @@ -2777,9 +2780,23 @@ static void handle_stripe_clean_event(struct r5conf *conf, STRIPE_SECTORS, !test_bit(STRIPE_DEGRADED, &sh->state), 0); - } - } else if (test_bit(R5_Discard, &sh->dev[i].flags)) - clear_bit(R5_Discard, &sh->dev[i].flags); + } else if (test_bit(R5_Discard, &dev->flags)) + discard_pending = 1; + } + if (!discard_pending && + test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) { + clear_bit(R5_Discard, &sh->dev[sh->pd_idx].flags); + clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags); + if (sh->qd_idx >= 0) { + clear_bit(R5_Discard, &sh->dev[sh->qd_idx].flags); + clear_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags); + } + /* now that discard is done we can proceed with any sync */ + clear_bit(STRIPE_DISCARD, &sh->state); + if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) + set_bit(STRIPE_HANDLE, &sh->state); + + } if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state)) if (atomic_dec_and_test(&conf->pending_full_writes)) @@ -3431,9 +3448,15 @@ static void handle_stripe(struct stripe_head *sh) return; } - if (test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) { - set_bit(STRIPE_SYNCING, &sh->state); - clear_bit(STRIPE_INSYNC, &sh->state); + if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) { + spin_lock(&sh->stripe_lock); + /* Cannot process 'sync' concurrently with 'discard' */ + if (!test_bit(STRIPE_DISCARD, &sh->state) && + test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) { + set_bit(STRIPE_SYNCING, &sh->state); + clear_bit(STRIPE_INSYNC, &sh->state); + } + spin_unlock(&sh->stripe_lock); } clear_bit(STRIPE_DELAYED, &sh->state); @@ -3593,6 +3616,8 @@ static void handle_stripe(struct stripe_head *sh) test_bit(STRIPE_INSYNC, &sh->state)) { md_done_sync(conf->mddev, STRIPE_SECTORS, 1); clear_bit(STRIPE_SYNCING, &sh->state); + if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags)) + wake_up(&conf->wait_for_overlap); } /* If the failed drives are just a ReadError, then we might need @@ -4159,6 +4184,13 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi) sh = get_active_stripe(conf, logical_sector, 0, 0, 0); prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE); + set_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags); + if (test_bit(STRIPE_SYNCING, &sh->state)) { + release_stripe(sh); + schedule(); + goto again; + } + clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags); spin_lock_irq(&sh->stripe_lock); for (d = 0; d < conf->raid_disks; d++) { if (d == sh->pd_idx || d == sh->qd_idx) @@ -4171,6 +4203,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi) goto again; } } + set_bit(STRIPE_DISCARD, &sh->state); finish_wait(&conf->wait_for_overlap, &w); for (d = 0; d < conf->raid_disks; d++) { if (d == sh->pd_idx || d == sh->qd_idx) diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 18b2c4a8a1f..050a334e89c 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -323,6 +323,7 @@ enum { STRIPE_COMPUTE_RUN, STRIPE_OPS_REQ_PENDING, STRIPE_ON_UNPLUG_LIST, + STRIPE_DISCARD, }; /* -- cgit v1.2.3-18-g5258 From 238f5908bd48f9e2f4668e0289e88cba969d710c Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Mon, 11 Mar 2013 11:27:44 +0100 Subject: md: remove CONFIG_MULTICORE_RAID456 entirely Once instance of this Kconfig macro remained after commit 51acbcec6c42b24482bac18e42befc822524535d ("md: remove CONFIG_MULTICORE_RAID456"). Remove that one too. And, while we're at it, also remove it from the defconfig files that carry it. Signed-off-by: Paul Bolle Signed-off-by: NeilBrown --- arch/tile/configs/tilegx_defconfig | 1 - arch/tile/configs/tilepro_defconfig | 1 - drivers/md/raid5.h | 4 ---- 3 files changed, 6 deletions(-) diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig index 8c5eff6d6df..47684815e5c 100644 --- a/arch/tile/configs/tilegx_defconfig +++ b/arch/tile/configs/tilegx_defconfig @@ -330,7 +330,6 @@ CONFIG_MD_RAID0=m CONFIG_MD_RAID1=m CONFIG_MD_RAID10=m CONFIG_MD_RAID456=m -CONFIG_MULTICORE_RAID456=y CONFIG_MD_FAULTY=m CONFIG_BLK_DEV_DM=m CONFIG_DM_DEBUG=y diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig index e7a3dfcbcda..dd2b8f0c631 100644 --- a/arch/tile/configs/tilepro_defconfig +++ b/arch/tile/configs/tilepro_defconfig @@ -324,7 +324,6 @@ CONFIG_MD_RAID0=m CONFIG_MD_RAID1=m CONFIG_MD_RAID10=m CONFIG_MD_RAID456=m -CONFIG_MULTICORE_RAID456=y CONFIG_MD_FAULTY=m CONFIG_BLK_DEV_DM=m CONFIG_DM_DEBUG=y diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 050a334e89c..b0b663b119a 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -221,10 +221,6 @@ struct stripe_head { struct stripe_operations { int target, target2; enum sum_check_flags zero_sum_result; - #ifdef CONFIG_MULTICORE_RAID456 - unsigned long request; - wait_queue_head_t wait_for_ops; - #endif } ops; struct r5dev { /* rreq and rvec are used for the replacement device when -- cgit v1.2.3-18-g5258