From 9bbf5feecc7eab2c370496c1c161bbfe62084028 Mon Sep 17 00:00:00 2001 From: Coly Li Date: Mon, 27 Feb 2023 23:23:17 +0800 Subject: [PATCH 1/4] dm thin: fix deadlock when swapping to thin device This is an already known issue that dm-thin volume cannot be used as swap, otherwise a deadlock may happen when dm-thin internal memory demand triggers swap I/O on the dm-thin volume itself. But thanks to commit a666e5c05e7c ("dm: fix deadlock when swapping to encrypted device"), the limit_swap_bios target flag can also be used for dm-thin to avoid the recursive I/O when it is used as swap. Fix is to simply set ti->limit_swap_bios to true in both pool_ctr() and thin_ctr(). In my test, I create a dm-thin volume /dev/vg/swap and use it as swap device. Then I run fio on another dm-thin volume /dev/vg/main and use large --blocksize to trigger swap I/O onto /dev/vg/swap. The following fio command line is used in my test, fio --name recursive-swap-io --lockmem 1 --iodepth 128 \ --ioengine libaio --filename /dev/vg/main --rw randrw \ --blocksize 1M --numjobs 32 --time_based --runtime=12h Without this fix, the whole system can be locked up within 15 seconds. With this fix, there is no any deadlock or hung task observed after 2 hours of running fio. Furthermore, if blocksize is changed from 1M to 128M, after around 30 seconds fio has no visible I/O, and the out-of-memory killer message shows up in kernel message. After around 20 minutes all fio processes are killed and the whole system is back to being alive. This is exactly what is expected when recursive I/O happens on dm-thin volume when it is used as swap. Depends-on: a666e5c05e7c ("dm: fix deadlock when swapping to encrypted device") Cc: stable@vger.kernel.org Signed-off-by: Coly Li Acked-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- drivers/md/dm-thin.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 6cd105c1cef3..13d4677baafd 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -3369,6 +3369,7 @@ static int pool_ctr(struct dm_target *ti, unsigned int argc, char **argv) pt->low_water_blocks = low_water_blocks; pt->adjusted_pf = pt->requested_pf = pf; ti->num_flush_bios = 1; + ti->limit_swap_bios = true; /* * Only need to enable discards if the pool should pass @@ -4249,6 +4250,7 @@ static int thin_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; ti->num_flush_bios = 1; + ti->limit_swap_bios = true; ti->flush_supported = true; ti->accounts_remapped_io = true; ti->per_io_data_size = sizeof(struct dm_thin_endio_hook); From fb294b1c0ba982144ca467a75e7d01ff26304e2b Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Mon, 6 Mar 2023 11:17:58 -0500 Subject: [PATCH 2/4] dm crypt: add cond_resched() to dmcrypt_write() The loop in dmcrypt_write may be running for unbounded amount of time, thus we need cond_resched() in it. This commit fixes the following warning: [ 3391.153255][ C12] watchdog: BUG: soft lockup - CPU#12 stuck for 23s! [dmcrypt_write/2:2897] ... [ 3391.387210][ C12] Call trace: [ 3391.390338][ C12] blk_attempt_bio_merge.part.6+0x38/0x158 [ 3391.395970][ C12] blk_attempt_plug_merge+0xc0/0x1b0 [ 3391.401085][ C12] blk_mq_submit_bio+0x398/0x550 [ 3391.405856][ C12] submit_bio_noacct+0x308/0x380 [ 3391.410630][ C12] dmcrypt_write+0x1e4/0x208 [dm_crypt] [ 3391.416005][ C12] kthread+0x130/0x138 [ 3391.419911][ C12] ret_from_fork+0x10/0x18 Reported-by: yangerkun Fixes: dc2676210c42 ("dm crypt: offload writes to thread") Cc: stable@vger.kernel.org Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- drivers/md/dm-crypt.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 87c5706131f2..faba1be572f9 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1937,6 +1937,7 @@ pop_from_list: io = crypt_io_from_node(rb_first(&write_tree)); rb_erase(&io->rb_node, &write_tree); kcryptd_io_write(io); + cond_resched(); } while (!RB_EMPTY_ROOT(&write_tree)); blk_finish_plug(&plug); } From d9a02e016aaf5a57fb44e9a5e6da8ccd3b9e2e70 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 8 Mar 2023 14:39:54 -0500 Subject: [PATCH 3/4] dm crypt: avoid accessing uninitialized tasklet When neither "no_read_workqueue" nor "no_write_workqueue" are enabled, tasklet_trylock() in crypt_dec_pending() may still return false due to an uninitialized state, and dm-crypt will unnecessarily do io completion in io_queue workqueue instead of current context. Fix this by adding an 'in_tasklet' flag to dm_crypt_io struct and initialize it to false in crypt_io_init(). Set this flag to true in kcryptd_queue_crypt() before calling tasklet_schedule(). If set crypt_dec_pending() will punt io completion to a workqueue. This also nicely avoids the tasklet_trylock/unlock hack when tasklets aren't in use. Fixes: 8e14f610159d ("dm crypt: do not call bio_endio() from the dm-crypt tasklet") Cc: stable@vger.kernel.org Reported-by: Hou Tao Suggested-by: Ignat Korchagin Reviewed-by: Ignat Korchagin Signed-off-by: Mike Snitzer --- drivers/md/dm-crypt.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index faba1be572f9..2764b4ea18a3 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -72,7 +72,9 @@ struct dm_crypt_io { struct crypt_config *cc; struct bio *base_bio; u8 *integrity_metadata; - bool integrity_metadata_from_pool; + bool integrity_metadata_from_pool:1; + bool in_tasklet:1; + struct work_struct work; struct tasklet_struct tasklet; @@ -1731,6 +1733,7 @@ static void crypt_io_init(struct dm_crypt_io *io, struct crypt_config *cc, io->ctx.r.req = NULL; io->integrity_metadata = NULL; io->integrity_metadata_from_pool = false; + io->in_tasklet = false; atomic_set(&io->io_pending, 0); } @@ -1777,14 +1780,13 @@ static void crypt_dec_pending(struct dm_crypt_io *io) * our tasklet. In this case we need to delay bio_endio() * execution to after the tasklet is done and dequeued. */ - if (tasklet_trylock(&io->tasklet)) { - tasklet_unlock(&io->tasklet); - bio_endio(base_bio); + if (io->in_tasklet) { + INIT_WORK(&io->work, kcryptd_io_bio_endio); + queue_work(cc->io_queue, &io->work); return; } - INIT_WORK(&io->work, kcryptd_io_bio_endio); - queue_work(cc->io_queue, &io->work); + bio_endio(base_bio); } /* @@ -2233,6 +2235,7 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io) * it is being executed with irqs disabled. */ if (in_hardirq() || irqs_disabled()) { + io->in_tasklet = true; tasklet_init(&io->tasklet, kcryptd_crypt_tasklet, (unsigned long)&io->work); tasklet_schedule(&io->tasklet); return; From d3aa3e060c4a80827eb801fc448debc9daa7c46b Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Thu, 16 Mar 2023 14:55:06 +0800 Subject: [PATCH 4/4] dm stats: check for and propagate alloc_percpu failure Check alloc_precpu()'s return value and return an error from dm_stats_init() if it fails. Update alloc_dev() to fail if dm_stats_init() does. Otherwise, a NULL pointer dereference will occur in dm_stats_cleanup() even if dm-stats isn't being actively used. Fixes: fd2ed4d25270 ("dm: add statistics support") Cc: stable@vger.kernel.org Signed-off-by: Jiasheng Jiang Signed-off-by: Mike Snitzer --- drivers/md/dm-stats.c | 7 ++++++- drivers/md/dm-stats.h | 2 +- drivers/md/dm.c | 4 +++- 3 files changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index c21a19ab73f7..db2d997a6c18 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -188,7 +188,7 @@ static int dm_stat_in_flight(struct dm_stat_shared *shared) atomic_read(&shared->in_flight[WRITE]); } -void dm_stats_init(struct dm_stats *stats) +int dm_stats_init(struct dm_stats *stats) { int cpu; struct dm_stats_last_position *last; @@ -197,11 +197,16 @@ void dm_stats_init(struct dm_stats *stats) INIT_LIST_HEAD(&stats->list); stats->precise_timestamps = false; stats->last = alloc_percpu(struct dm_stats_last_position); + if (!stats->last) + return -ENOMEM; + for_each_possible_cpu(cpu) { last = per_cpu_ptr(stats->last, cpu); last->last_sector = (sector_t)ULLONG_MAX; last->last_rw = UINT_MAX; } + + return 0; } void dm_stats_cleanup(struct dm_stats *stats) diff --git a/drivers/md/dm-stats.h b/drivers/md/dm-stats.h index 0bc152c8e4f3..c6728c8b4159 100644 --- a/drivers/md/dm-stats.h +++ b/drivers/md/dm-stats.h @@ -21,7 +21,7 @@ struct dm_stats_aux { unsigned long long duration_ns; }; -void dm_stats_init(struct dm_stats *st); +int dm_stats_init(struct dm_stats *st); void dm_stats_cleanup(struct dm_stats *st); struct mapped_device; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index eace45a18d45..b6ace995b9ca 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2097,7 +2097,9 @@ static struct mapped_device *alloc_dev(int minor) if (!md->pending_io) goto bad; - dm_stats_init(&md->stats); + r = dm_stats_init(&md->stats); + if (r < 0) + goto bad; /* Populate the mapping, nobody knows we exist yet */ spin_lock(&_minor_lock);