From 1877db75589a895bbdc4c4c3f23558e57b521141 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 5 Feb 2014 12:17:01 +1100 Subject: md/raid1: restore ability for check and repair to fix read errors. commit 30bc9b53878a9921b02e3b5bc4283ac1c6de102a md/raid1: fix bio handling problems in process_checks() Move the bio_reset() to a point before where BIO_UPTODATE is checked, so that check now always report that the bio is uptodate, even if it is not. This causes process_check() to sometimes treat read-errors as successful matches so the good data isn't written out. This patch preserves the flag until it is needed. Bug was introduced in 3.11, but backported to 3.10-stable (as it fixed an even worse bug). So suitable for any -stable since 3.10. Reported-and-tested-by: Michael Tokarev Cc: stable@vger.kernel.org (3.10+) Fixed: 30bc9b53878a9921b02e3b5bc4283ac1c6de102a Signed-off-by: NeilBrown --- drivers/md/raid1.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index fd3a2a14b587..4a6ca1cb2e78 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1953,11 +1953,15 @@ static int process_checks(struct r1bio *r1_bio) for (i = 0; i < conf->raid_disks * 2; i++) { int j; int size; + int uptodate; struct bio *b = r1_bio->bios[i]; if (b->bi_end_io != end_sync_read) continue; - /* fixup the bio for reuse */ + /* fixup the bio for reuse, but preserve BIO_UPTODATE */ + uptodate = test_bit(BIO_UPTODATE, &b->bi_flags); bio_reset(b); + if (!uptodate) + clear_bit(BIO_UPTODATE, &b->bi_flags); b->bi_vcnt = vcnt; b->bi_iter.bi_size = r1_bio->sectors << 9; b->bi_iter.bi_sector = r1_bio->sector + @@ -1990,11 +1994,14 @@ static int process_checks(struct r1bio *r1_bio) int j; struct bio *pbio = r1_bio->bios[primary]; struct bio *sbio = r1_bio->bios[i]; + int uptodate = test_bit(BIO_UPTODATE, &sbio->bi_flags); if (sbio->bi_end_io != end_sync_read) continue; + /* Now we can 'fixup' the BIO_UPTODATE flag */ + set_bit(BIO_UPTODATE, &sbio->bi_flags); - if (test_bit(BIO_UPTODATE, &sbio->bi_flags)) { + if (uptodate) { for (j = vcnt; j-- ; ) { struct page *p, *s; p = pbio->bi_io_vec[j].bv_page; @@ -2009,7 +2016,7 @@ static int process_checks(struct r1bio *r1_bio) if (j >= 0) atomic64_add(r1_bio->sectors, &mddev->resync_mismatches); if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery) - && test_bit(BIO_UPTODATE, &sbio->bi_flags))) { + && uptodate)) { /* No need to write to this device. */ sbio->bi_end_io = NULL; rdev_dec_pending(conf->mirrors[i].rdev, mddev); -- cgit v1.2.3 From 789b5e0315284463617e106baad360cb9e8db3ac Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 6 Feb 2014 03:42:45 +0530 Subject: md/raid5: Fix CPU hotplug callback registration Subsystems that want to register CPU hotplug callbacks, as well as perform initialization for the CPUs that are already online, often do it as shown below: get_online_cpus(); for_each_online_cpu(cpu) init_cpu(cpu); register_cpu_notifier(&foobar_cpu_notifier); put_online_cpus(); This is wrong, since it is prone to ABBA deadlocks involving the cpu_add_remove_lock and the cpu_hotplug.lock (when running concurrently with CPU hotplug operations). Interestingly, the raid5 code can actually prevent double initialization and hence can use the following simplified form of callback registration: register_cpu_notifier(&foobar_cpu_notifier); get_online_cpus(); for_each_online_cpu(cpu) init_cpu(cpu); put_online_cpus(); A hotplug operation that occurs between registering the notifier and calling get_online_cpus(), won't disrupt anything, because the code takes care to perform the memory allocations only once. So reorganize the code in raid5 this way to fix the deadlock with callback registration. Cc: linux-raid@vger.kernel.org Cc: stable@vger.kernel.org (v2.6.32+) Fixes: 36d1c6476be51101778882897b315bd928c8c7b5 Signed-off-by: Oleg Nesterov [Srivatsa: Fixed the unregister_cpu_notifier() deadlock, added the free_scratch_buffer() helper to condense code further and wrote the changelog.] Signed-off-by: Srivatsa S. Bhat Signed-off-by: NeilBrown --- drivers/md/raid5.c | 90 ++++++++++++++++++++++++++---------------------------- 1 file changed, 44 insertions(+), 46 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index f1feadeb7bb2..16f5c21963db 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5514,23 +5514,43 @@ raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks) return sectors * (raid_disks - conf->max_degraded); } +static void free_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu) +{ + safe_put_page(percpu->spare_page); + kfree(percpu->scribble); + percpu->spare_page = NULL; + percpu->scribble = NULL; +} + +static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu) +{ + if (conf->level == 6 && !percpu->spare_page) + percpu->spare_page = alloc_page(GFP_KERNEL); + if (!percpu->scribble) + percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL); + + if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) { + free_scratch_buffer(conf, percpu); + return -ENOMEM; + } + + return 0; +} + static void raid5_free_percpu(struct r5conf *conf) { - struct raid5_percpu *percpu; unsigned long cpu; if (!conf->percpu) return; - get_online_cpus(); - for_each_possible_cpu(cpu) { - percpu = per_cpu_ptr(conf->percpu, cpu); - safe_put_page(percpu->spare_page); - kfree(percpu->scribble); - } #ifdef CONFIG_HOTPLUG_CPU unregister_cpu_notifier(&conf->cpu_notify); #endif + + get_online_cpus(); + for_each_possible_cpu(cpu) + free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu)); put_online_cpus(); free_percpu(conf->percpu); @@ -5557,15 +5577,7 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action, switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: - if (conf->level == 6 && !percpu->spare_page) - percpu->spare_page = alloc_page(GFP_KERNEL); - if (!percpu->scribble) - percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL); - - if (!percpu->scribble || - (conf->level == 6 && !percpu->spare_page)) { - safe_put_page(percpu->spare_page); - kfree(percpu->scribble); + if (alloc_scratch_buffer(conf, percpu)) { pr_err("%s: failed memory allocation for cpu%ld\n", __func__, cpu); return notifier_from_errno(-ENOMEM); @@ -5573,10 +5585,7 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action, break; case CPU_DEAD: case CPU_DEAD_FROZEN: - safe_put_page(percpu->spare_page); - kfree(percpu->scribble); - percpu->spare_page = NULL; - percpu->scribble = NULL; + free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu)); break; default: break; @@ -5588,40 +5597,29 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action, static int raid5_alloc_percpu(struct r5conf *conf) { unsigned long cpu; - struct page *spare_page; - struct raid5_percpu __percpu *allcpus; - void *scribble; - int err; + int err = 0; - allcpus = alloc_percpu(struct raid5_percpu); - if (!allcpus) + conf->percpu = alloc_percpu(struct raid5_percpu); + if (!conf->percpu) return -ENOMEM; - conf->percpu = allcpus; + +#ifdef CONFIG_HOTPLUG_CPU + conf->cpu_notify.notifier_call = raid456_cpu_notify; + conf->cpu_notify.priority = 0; + err = register_cpu_notifier(&conf->cpu_notify); + if (err) + return err; +#endif get_online_cpus(); - err = 0; for_each_present_cpu(cpu) { - if (conf->level == 6) { - spare_page = alloc_page(GFP_KERNEL); - if (!spare_page) { - err = -ENOMEM; - break; - } - per_cpu_ptr(conf->percpu, cpu)->spare_page = spare_page; - } - scribble = kmalloc(conf->scribble_len, GFP_KERNEL); - if (!scribble) { - err = -ENOMEM; + err = alloc_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu)); + if (err) { + pr_err("%s: failed memory allocation for cpu%ld\n", + __func__, cpu); break; } - per_cpu_ptr(conf->percpu, cpu)->scribble = scribble; } -#ifdef CONFIG_HOTPLUG_CPU - conf->cpu_notify.notifier_call = raid456_cpu_notify; - conf->cpu_notify.priority = 0; - if (err == 0) - err = register_cpu_notifier(&conf->cpu_notify); -#endif put_online_cpus(); return err; -- cgit v1.2.3