From 2dffdc0724004f38f5e39907747b53e4b0d80e59 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Tue, 16 May 2017 14:01:25 +0800 Subject: [PATCH 1/4] md-cluster: fix potential lock issue in add_new_disk The add_new_disk returns with communication locked if __sendmsg returns failure, fix it with call unlock_comm before return. Reported-by: Dan Carpenter CC: Goldwyn Rodrigues Signed-off-by: Guoqing Jiang Signed-off-by: Shaohua Li --- drivers/md/md-cluster.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 7299ce2f08a8..03082e17c65c 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -1311,8 +1311,10 @@ static int add_new_disk(struct mddev *mddev, struct md_rdev *rdev) cmsg.raid_slot = cpu_to_le32(rdev->desc_nr); lock_comm(cinfo, 1); ret = __sendmsg(cinfo, &cmsg); - if (ret) + if (ret) { + unlock_comm(cinfo); return ret; + } cinfo->no_new_dev_lockres->flags |= DLM_LKF_NOQUEUE; ret = dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_EX); cinfo->no_new_dev_lockres->flags &= ~DLM_LKF_NOQUEUE; From 4179bc30b2fe85f827d93e0ae7ae8f49ad3afc02 Mon Sep 17 00:00:00 2001 From: Kyungchan Koh Date: Wed, 24 May 2017 10:16:27 -0700 Subject: [PATCH 2/4] md: uuid debug statement now in processor byte order. Previously, the uuid debug statements were printed in little-endian format, which wasn't consistent in machines that might not be in little-endian byte order. With this change, the output will be consistent for all machines with different byte-ordering. Signed-off-by: Kyungchan Koh Signed-off-by: Shaohua Li --- drivers/md/bitmap.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index bf7419a56454..f4eace5ea184 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -485,10 +485,10 @@ void bitmap_print_sb(struct bitmap *bitmap) pr_debug(" magic: %08x\n", le32_to_cpu(sb->magic)); pr_debug(" version: %d\n", le32_to_cpu(sb->version)); pr_debug(" uuid: %08x.%08x.%08x.%08x\n", - *(__u32 *)(sb->uuid+0), - *(__u32 *)(sb->uuid+4), - *(__u32 *)(sb->uuid+8), - *(__u32 *)(sb->uuid+12)); + le32_to_cpu(*(__u32 *)(sb->uuid+0)), + le32_to_cpu(*(__u32 *)(sb->uuid+4)), + le32_to_cpu(*(__u32 *)(sb->uuid+8)), + le32_to_cpu(*(__u32 *)(sb->uuid+12))); pr_debug(" events: %llu\n", (unsigned long long) le64_to_cpu(sb->events)); pr_debug("events cleared: %llu\n", From e153903686deac9ea8c499b49516126f1a844fdb Mon Sep 17 00:00:00 2001 From: Nix Date: Tue, 16 May 2017 10:13:31 +0100 Subject: [PATCH 3/4] md: report sector of stripes with check mismatches This makes it possible, with appropriate filesystem support, for a sysadmin to tell what is affected by the mismatch, and whether it should be ignored (if it's inside a swap partition, for instance). We ratelimit to prevent log flooding: if there are so many mismatches that ratelimiting is necessary, the individual messages are relatively unlikely to be important (either the machine is swapping like crazy or something is very wrong with the disk). Signed-off-by: Nick Alcock Signed-off-by: Shaohua Li --- drivers/md/raid5.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 9c4f7659f8b1..722064689e82 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -4085,10 +4085,15 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh, set_bit(STRIPE_INSYNC, &sh->state); else { atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches); - if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) + if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) { /* don't try to repair!! */ set_bit(STRIPE_INSYNC, &sh->state); - else { + pr_warn_ratelimited("%s: mismatch sector in range " + "%llu-%llu\n", mdname(conf->mddev), + (unsigned long long) sh->sector, + (unsigned long long) sh->sector + + STRIPE_SECTORS); + } else { sh->check_state = check_state_compute_run; set_bit(STRIPE_COMPUTE_RUN, &sh->state); set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request); @@ -4237,10 +4242,15 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, } } else { atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches); - if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) + if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) { /* don't try to repair!! */ set_bit(STRIPE_INSYNC, &sh->state); - else { + pr_warn_ratelimited("%s: mismatch sector in range " + "%llu-%llu\n", mdname(conf->mddev), + (unsigned long long) sh->sector, + (unsigned long long) sh->sector + + STRIPE_SECTORS); + } else { int *target = &sh->ops.target; sh->ops.target = -1; From 5a8948f8a32ba56c17b3fb75d318ac98157f3ba5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 31 May 2017 09:44:33 +0200 Subject: [PATCH 4/4] md: Make flush bios explicitely sync Commit b685d3d65ac7 "block: treat REQ_FUA and REQ_PREFLUSH as synchronous" removed REQ_SYNC flag from WRITE_{FUA|PREFLUSH|...} definitions. generic_make_request_checks() however strips REQ_FUA and REQ_PREFLUSH flags from a bio when the storage doesn't report volatile write cache and thus write effectively becomes asynchronous which can lead to performance regressions Fix the problem by making sure all bios which are synchronous are properly marked with REQ_SYNC. CC: linux-raid@vger.kernel.org CC: Shaohua Li Fixes: b685d3d65ac791406e0dfd8779cc9b3707fea5a3 CC: stable@vger.kernel.org Signed-off-by: Jan Kara Signed-off-by: Shaohua Li --- drivers/md/md.c | 2 +- drivers/md/raid5-cache.c | 4 ++-- drivers/md/raid5-ppl.c | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 10367ffe92e3..212a6777ff31 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -765,7 +765,7 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev, test_bit(FailFast, &rdev->flags) && !test_bit(LastDev, &rdev->flags)) ff = MD_FAILFAST; - bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_FUA | ff; + bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA | ff; atomic_inc(&mddev->pending_writes); submit_bio(bio); diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 4c00bc248287..0a7af8b0a80a 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -1782,7 +1782,7 @@ static int r5l_log_write_empty_meta_block(struct r5l_log *log, sector_t pos, mb->checksum = cpu_to_le32(crc32c_le(log->uuid_checksum, mb, PAGE_SIZE)); if (!sync_page_io(log->rdev, pos, PAGE_SIZE, page, REQ_OP_WRITE, - REQ_FUA, false)) { + REQ_SYNC | REQ_FUA, false)) { __free_page(page); return -EIO; } @@ -2388,7 +2388,7 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log, mb->checksum = cpu_to_le32(crc32c_le(log->uuid_checksum, mb, PAGE_SIZE)); sync_page_io(log->rdev, ctx->pos, PAGE_SIZE, page, - REQ_OP_WRITE, REQ_FUA, false); + REQ_OP_WRITE, REQ_SYNC | REQ_FUA, false); sh->log_start = ctx->pos; list_add_tail(&sh->r5c, &log->stripe_in_journal_list); atomic_inc(&log->stripe_in_journal_count); diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index 5d25bebf3328..ccce92e68d7f 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -907,8 +907,8 @@ static int ppl_write_empty_header(struct ppl_log *log) pplhdr->checksum = cpu_to_le32(~crc32c_le(~0, pplhdr, PAGE_SIZE)); if (!sync_page_io(rdev, rdev->ppl.sector - rdev->data_offset, - PPL_HEADER_SIZE, page, REQ_OP_WRITE | REQ_FUA, 0, - false)) { + PPL_HEADER_SIZE, page, REQ_OP_WRITE | REQ_SYNC | + REQ_FUA, 0, false)) { md_error(rdev->mddev, rdev); ret = -EIO; }