The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable@xxxxxxxxxxxxxxx>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From f6c367585d0d851349d3a9e607c43e5bea993fa1 Mon Sep 17 00:00:00 2001 From: Mike Snitzer <snitzer@xxxxxxxxxx> Date: Tue, 11 Dec 2018 13:31:40 -0500 Subject: [PATCH] dm thin: send event about thin-pool state change _after_ making it Sending a DM event before a thin-pool state change is about to happen is a bug. It wasn't realized until it became clear that userspace response to the event raced with the actual state change that the event was meant to notify about. Fix this by first updating internal thin-pool state to reflect what the DM event is being issued about. This fixes a long-standing racey/buggy userspace device-mapper-test-suite 'resize_io' test that would get an event but not find the state it was looking for -- so it would just go on to hang because no other events caused the test to reevaluate the thin-pool's state. Cc: stable@xxxxxxxxxxxxxxx Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx> diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 0bd8d498b3b9..53f8d03f76f7 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -195,7 +195,7 @@ static void throttle_unlock(struct throttle *t) struct dm_thin_new_mapping; /* - * The pool runs in 4 modes. Ordered in degraded order for comparisons. + * The pool runs in various modes. Ordered in degraded order for comparisons. */ enum pool_mode { PM_WRITE, /* metadata may be changed */ @@ -282,9 +282,38 @@ struct pool { mempool_t mapping_pool; }; -static enum pool_mode get_pool_mode(struct pool *pool); static void metadata_operation_failed(struct pool *pool, const char *op, int r); +static enum pool_mode get_pool_mode(struct pool *pool) +{ + return pool->pf.mode; +} + +static void notify_of_pool_mode_change(struct pool *pool) +{ + const char *descs[] = { + "write", + "out-of-data-space", + "read-only", + "read-only", + "fail" + }; + const char *extra_desc = NULL; + enum pool_mode mode = get_pool_mode(pool); + + if (mode == PM_OUT_OF_DATA_SPACE) { + if (!pool->pf.error_if_no_space) + extra_desc = " (queue IO)"; + else + extra_desc = " (error IO)"; + } + + dm_table_event(pool->ti->table); + DMINFO("%s: switching pool to %s%s mode", + dm_device_name(pool->pool_md), + descs[(int)mode], extra_desc ? : ""); +} + /* * Target context for a pool. */ @@ -2351,8 +2380,6 @@ static void do_waker(struct work_struct *ws) queue_delayed_work(pool->wq, &pool->waker, COMMIT_PERIOD); } -static void notify_of_pool_mode_change_to_oods(struct pool *pool); - /* * We're holding onto IO to allow userland time to react. After the * timeout either the pool will have been resized (and thus back in @@ -2365,7 +2392,7 @@ static void do_no_space_timeout(struct work_struct *ws) if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) { pool->pf.error_if_no_space = true; - notify_of_pool_mode_change_to_oods(pool); + notify_of_pool_mode_change(pool); error_retry_list_with_code(pool, BLK_STS_NOSPC); } } @@ -2433,26 +2460,6 @@ static void noflush_work(struct thin_c *tc, void (*fn)(struct work_struct *)) /*----------------------------------------------------------------*/ -static enum pool_mode get_pool_mode(struct pool *pool) -{ - return pool->pf.mode; -} - -static void notify_of_pool_mode_change(struct pool *pool, const char *new_mode) -{ - dm_table_event(pool->ti->table); - DMINFO("%s: switching pool to %s mode", - dm_device_name(pool->pool_md), new_mode); -} - -static void notify_of_pool_mode_change_to_oods(struct pool *pool) -{ - if (!pool->pf.error_if_no_space) - notify_of_pool_mode_change(pool, "out-of-data-space (queue IO)"); - else - notify_of_pool_mode_change(pool, "out-of-data-space (error IO)"); -} - static bool passdown_enabled(struct pool_c *pt) { return pt->adjusted_pf.discard_passdown; @@ -2501,8 +2508,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) switch (new_mode) { case PM_FAIL: - if (old_mode != new_mode) - notify_of_pool_mode_change(pool, "failure"); dm_pool_metadata_read_only(pool->pmd); pool->process_bio = process_bio_fail; pool->process_discard = process_bio_fail; @@ -2516,8 +2521,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) case PM_OUT_OF_METADATA_SPACE: case PM_READ_ONLY: - if (!is_read_only_pool_mode(old_mode)) - notify_of_pool_mode_change(pool, "read-only"); dm_pool_metadata_read_only(pool->pmd); pool->process_bio = process_bio_read_only; pool->process_discard = process_bio_success; @@ -2538,8 +2541,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) * alarming rate. Adjust your low water mark if you're * frequently seeing this mode. */ - if (old_mode != new_mode) - notify_of_pool_mode_change_to_oods(pool); pool->out_of_data_space = true; pool->process_bio = process_bio_read_only; pool->process_discard = process_discard_bio; @@ -2552,8 +2553,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) break; case PM_WRITE: - if (old_mode != new_mode) - notify_of_pool_mode_change(pool, "write"); if (old_mode == PM_OUT_OF_DATA_SPACE) cancel_delayed_work_sync(&pool->no_space_timeout); pool->out_of_data_space = false; @@ -2573,6 +2572,9 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) * doesn't cause an unexpected mode transition on resume. */ pt->adjusted_pf.mode = new_mode; + + if (old_mode != new_mode) + notify_of_pool_mode_change(pool); } static void abort_transaction(struct pool *pool)