kernel/drivers/md, branch linux-4.16.y

bcache: stop dc->writeback_rate_update properly

2018-05-30T06:17:32Z

[ Upstream commit 3fd47bfe55b00d5ac7b0a44c9301c07be39b1082 ] struct delayed_work writeback_rate_update in struct cache_dev is a delayed worker to call function update_writeback_rate() in period (the interval is defined by dc->writeback_rate_update_seconds). When a metadate I/O error happens on cache device, bcache error handling routine bch_cache_set_error() will call bch_cache_set_unregister() to retire whole cache set. On the unregister code path, this delayed work is stopped by calling cancel_delayed_work_sync(&dc->writeback_rate_update). dc->writeback_rate_update is a special delayed work from others in bcache. In its routine update_writeback_rate(), this delayed work is re-armed itself. That means when cancel_delayed_work_sync() returns, this delayed work can still be executed after several seconds defined by dc->writeback_rate_update_seconds. The problem is, after cancel_delayed_work_sync() returns, the cache set unregister code path will continue and release memory of struct cache set. Then the delayed work is scheduled to run, __update_writeback_rate() will reference the already released cache_set memory, and trigger a NULL pointer deference fault. This patch introduces two more bcache device flags, - BCACHE_DEV_WB_RUNNING bit set: bcache device is in writeback mode and running, it is OK for dc->writeback_rate_update to re-arm itself. bit clear:bcache device is trying to stop dc->writeback_rate_update, this delayed work should not re-arm itself and quit. - BCACHE_DEV_RATE_DW_RUNNING bit set: routine update_writeback_rate() is executing. bit clear: routine update_writeback_rate() quits. This patch also adds a function cancel_writeback_rate_update_dwork() to wait for dc->writeback_rate_update quits before cancel it by calling cancel_delayed_work_sync(). In order to avoid a deadlock by unexpected quit dc->writeback_rate_update, after time_out seconds this function will give up and continue to call cancel_delayed_work_sync(). And here I explain how this patch stops self re-armed delayed work properly with the above stuffs. update_writeback_rate() sets BCACHE_DEV_RATE_DW_RUNNING at its beginning and clears BCACHE_DEV_RATE_DW_RUNNING at its end. Before calling cancel_writeback_rate_update_dwork() clear flag BCACHE_DEV_WB_RUNNING. Before calling cancel_delayed_work_sync() wait utill flag BCACHE_DEV_RATE_DW_RUNNING is clear. So when calling cancel_delayed_work_sync(), dc->writeback_rate_update must be already re- armed, or quite by seeing BCACHE_DEV_WB_RUNNING cleared. In both cases delayed work routine update_writeback_rate() won't be executed after cancel_delayed_work_sync() returns. Inside update_writeback_rate() before calling schedule_delayed_work(), flag BCACHE_DEV_WB_RUNNING is checked before. If this flag is cleared, it means someone is about to stop the delayed work. Because flag BCACHE_DEV_RATE_DW_RUNNING is set already and cancel_delayed_work_sync() has to wait for this flag to be cleared, we don't need to worry about race condition here. If update_writeback_rate() is scheduled to run after checking BCACHE_DEV_RATE_DW_RUNNING and before calling cancel_delayed_work_sync() in cancel_writeback_rate_update_dwork(), it is also safe. Because at this moment BCACHE_DEV_WB_RUNNING is cleared with memory barrier. As I mentioned previously, update_writeback_rate() will see BCACHE_DEV_WB_RUNNING is clear and quit immediately. Because there are more dependences inside update_writeback_rate() to struct cache_set memory, dc->writeback_rate_update is not a simple self re-arm delayed work. After trying many different methods (e.g. hold dc->count, or use locks), this is the only way I can find which works to properly stop dc->writeback_rate_update delayed work. Changelog: v3: change values of BCACHE_DEV_WB_RUNNING and BCACHE_DEV_RATE_DW_RUNNING to bit index, for test_bit(). v2: Try to fix the race issue which is pointed out by Junhui. v1: The initial version for review Signed-off-by: Coly Li Reviewed-by: Junhui Tang Reviewed-by: Michael Lyle Cc: Michael Lyle Cc: Hannes Reinecke Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

bcache: fix cached_dev->count usage for bch_cache_set_error()

2018-05-30T06:17:32Z

[ Upstream commit 804f3c6981f5e4a506a8f14dc284cb218d0659ae ] When bcache metadata I/O fails, bcache will call bch_cache_set_error() to retire the whole cache set. The expected behavior to retire a cache set is to unregister the cache set, and unregister all backing device attached to this cache set, then remove sysfs entries of the cache set and all attached backing devices, finally release memory of structs cache_set, cache, cached_dev and bcache_device. In my testing when journal I/O failure triggered by disconnected cache device, sometimes the cache set cannot be retired, and its sysfs entry /sys/fs/bcache/ still exits and the backing device also references it. This is not expected behavior. When metadata I/O failes, the call senquence to retire whole cache set is, bch_cache_set_error() bch_cache_set_unregister() bch_cache_set_stop() __cache_set_unregister() <- called as callback by calling clousre_queue(&c->caching) cache_set_flush() <- called as a callback when refcount of cache_set->caching is 0 cache_set_free() <- called as a callback when refcount of catch_set->cl is 0 bch_cache_set_release() <- called as a callback when refcount of catch_set->kobj is 0 I find if kernel thread bch_writeback_thread() quits while-loop when kthread_should_stop() is true and searched_full_index is false, clousre callback cache_set_flush() set by continue_at() will never be called. The result is, bcache fails to retire whole cache set. cache_set_flush() will be called when refcount of closure c->caching is 0, and in function bcache_device_detach() refcount of closure c->caching is released to 0 by clousre_put(). In metadata error code path, function bcache_device_detach() is called by cached_dev_detach_finish(). This is a callback routine being called when cached_dev->count is 0. This refcount is decreased by cached_dev_put(). The above dependence indicates, cache_set_flush() will be called when refcount of cache_set->cl is 0, and refcount of cache_set->cl to be 0 when refcount of cache_dev->count is 0. The reason why sometimes cache_dev->count is not 0 (when metadata I/O fails and bch_cache_set_error() called) is, in bch_writeback_thread(), refcount of cache_dev is not decreased properly. In bch_writeback_thread(), cached_dev_put() is called only when searched_full_index is true and cached_dev->writeback_keys is empty, a.k.a there is no dirty data on cache. In most of run time it is correct, but when bch_writeback_thread() quits the while-loop while cache is still dirty, current code forget to call cached_dev_put() before this kernel thread exits. This is why sometimes cache_set_flush() is not executed and cache set fails to be retired. The reason to call cached_dev_put() in bch_writeback_rate() is, when the cache device changes from clean to dirty, cached_dev_get() is called, to make sure during writeback operatiions both backing and cache devices won't be released. Adding following code in bch_writeback_thread() does not work, static int bch_writeback_thread(void *arg) } + if (atomic_read(&dc->has_dirty)) + cached_dev_put() + return 0; } because writeback kernel thread can be waken up and start via sysfs entry: echo 1 > /sys/block/bcache/bcache/writeback_running It is difficult to check whether backing device is dirty without race and extra lock. So the above modification will introduce potential refcount underflow in some conditions. The correct fix is, to take cached dev refcount when creating the kernel thread, and put it before the kernel thread exits. Then bcache does not need to take a cached dev refcount when cache turns from clean to dirty, or to put a cached dev refcount when cache turns from ditry to clean. The writeback kernel thread is alwasy safe to reference data structure from cache set, cache and cached device (because a refcount of cache device is taken for it already), and no matter the kernel thread is stopped by I/O errors or system reboot, cached_dev->count can always be used correctly. The patch is simple, but understanding how it works is quite complicated. Changelog: v2: set dc->writeback_thread to NULL in this patch, as suggested by Hannes. v1: initial version for review. Signed-off-by: Coly Li Reviewed-by: Hannes Reinecke Reviewed-by: Michael Lyle Cc: Michael Lyle Cc: Junhui Tang Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

bcache: quit dc->writeback_thread when BCACHE_DEV_DETACHING is set

2018-05-30T06:17:31Z

[ Upstream commit fadd94e05c02afec7b70b0b14915624f1782f578 ] In patch "bcache: fix cached_dev->count usage for bch_cache_set_error()", cached_dev_get() is called when creating dc->writeback_thread, and cached_dev_put() is called when exiting dc->writeback_thread. This modification works well unless people detach the bcache device manually by 'echo 1 > /sys/block/bcache/bcache/detach' Because this sysfs interface only calls bch_cached_dev_detach() which wakes up dc->writeback_thread but does not stop it. The reason is, before patch "bcache: fix cached_dev->count usage for bch_cache_set_error()", inside bch_writeback_thread(), if cache is not dirty after writeback, cached_dev_put() will be called here. And in cached_dev_make_request() when a new write request makes cache from clean to dirty, cached_dev_get() will be called there. Since we don't operate dc->count in these locations, refcount d->count cannot be dropped after cache becomes clean, and cached_dev_detach_finish() won't be called to detach bcache device. This patch fixes the issue by checking whether BCACHE_DEV_DETACHING is set inside bch_writeback_thread(). If this bit is set and cache is clean (no existing writeback_keys), break the while-loop, call cached_dev_put() and quit the writeback thread. Please note if cache is still dirty, even BCACHE_DEV_DETACHING is set the writeback thread should continue to perform writeback, this is the original design of manually detach. It is safe to do the following check without locking, let me explain why, + if (!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) && + (!atomic_read(&dc->has_dirty) || !dc->writeback_running)) { If the kenrel thread does not sleep and continue to run due to conditions are not updated in time on the running CPU core, it just consumes more CPU cycles and has no hurt. This should-sleep-but-run is safe here. We just focus on the should-run-but-sleep condition, which means the writeback thread goes to sleep in mistake while it should continue to run. 1, First of all, no matter the writeback thread is hung or not, kthread_stop() from cached_dev_detach_finish() will wake up it and terminate by making kthread_should_stop() return true. And in normal run time, bit on index BCACHE_DEV_DETACHING is always cleared, the condition !test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) is always true and can be ignored as constant value. 2, If one of the following conditions is true, the writeback thread should go to sleep, "!atomic_read(&dc->has_dirty)" or "!dc->writeback_running)" each of them independently controls the writeback thread should sleep or not, let's analyse them one by one. 2.1 condition "!atomic_read(&dc->has_dirty)" If dc->has_dirty is set from 0 to 1 on another CPU core, bcache will call bch_writeback_queue() immediately or call bch_writeback_add() which indirectly calls bch_writeback_queue() too. In bch_writeback_queue(), wake_up_process(dc->writeback_thread) is called. It sets writeback thread's task state to TASK_RUNNING and following an implicit memory barrier, then tries to wake up the writeback thread. In writeback thread, its task state is set to TASK_INTERRUPTIBLE before doing the condition check. If other CPU core sets the TASK_RUNNING state after writeback thread setting TASK_INTERRUPTIBLE, the writeback thread will be scheduled to run very soon because its state is not TASK_INTERRUPTIBLE. If other CPU core sets the TASK_RUNNING state before writeback thread setting TASK_INTERRUPTIBLE, the implict memory barrier of wake_up_process() will make sure modification of dc->has_dirty on other CPU core is updated and observed on the CPU core of writeback thread. Therefore the condition check will correctly be false, and continue writeback code without sleeping. 2.2 condition "!dc->writeback_running)" dc->writeback_running can be changed via sysfs file, every time it is modified, a following bch_writeback_queue() is alwasy called. So the change is always observed on the CPU core of writeback thread. If dc->writeback_running is changed from 0 to 1 on other CPU core, this condition check will observe the modification and allow writeback thread to continue to run without sleeping. Now we can see, even without a locking protection, multiple conditions check is safe here, no deadlock or process hang up will happen. I compose a separte patch because that patch "bcache: fix cached_dev->count usage for bch_cache_set_error()" already gets a "Reviewed-by:" from Hannes Reinecke. Also this fix is not trivial and good for a separate patch. Signed-off-by: Coly Li Reviewed-by: Michael Lyle Cc: Hannes Reinecke Cc: Huijun Tang Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

bcache: return 0 from bch_debug_init() if CONFIG_DEBUG_FS=n

2018-05-22T16:56:24Z

commit 1c1a2ee1b53b006754073eefc65d2b2cedb5264b upstream. Commit 539d39eb2708 ("bcache: fix wrong return value in bch_debug_init()") returns the return value of debugfs_create_dir() to bcache_init(). When CONFIG_DEBUG_FS=n, bch_debug_init() always returns 1 and makes bcache_init() failedi. This patch makes bch_debug_init() always returns 0 if CONFIG_DEBUG_FS=n, so bcache can continue to work for the kernels which don't have debugfs enanbled. Changelog: v4: Add Acked-by from Kent Overstreet. v3: Use IS_ENABLED(CONFIG_DEBUG_FS) to replace #ifdef DEBUG_FS. v2: Remove a warning information v1: Initial version. Fixes: Commit 539d39eb2708 ("bcache: fix wrong return value in bch_debug_init()") Cc: stable@vger.kernel.org Signed-off-by: Coly Li Reported-by: Massimo B. Reported-by: Kai Krakow Tested-by: Kai Krakow Acked-by: Kent Overstreet Signed-off-by: Jens Axboe Signed-off-by: Kai Krakow Signed-off-by: Greg Kroah-Hartman

dm integrity: use kvfree for kvmalloc'd memory

2018-05-16T08:12:29Z

commit fc8cec113904a47396bf0a1afc62920d66319d36 upstream. Use kvfree instead of kfree because the array is allocated with kvmalloc. Fixes: 7eada909bfd7a ("dm: add integrity target") Cc: stable@vger.kernel.org # v4.12+ Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman

dm raid: fix nosync status

2018-04-24T07:43:01Z

commit 880bcce0dcc3172fe865352b492c41d85290cb8d upstream. Fix a race for "nosync" activations providing "aa.." device health characters and "0/N" sync ratio rather than "AA..." and "N/N". Occurs when status for the raid set is retrieved during resume before the MD sync thread starts and clears the MD_RECOVERY_NEEDED flag. Cc: stable@vger.kernel.org # 4.16+ Signed-off-by: Heinz Mauelshagen Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman

dm crypt: limit the number of allocated pages

2018-04-24T07:42:59Z

commit 5059353df86e2573ccd9d43fd9d9396dcec47ca2 upstream. dm-crypt consumes an excessive amount memory when the user attempts to zero a dm-crypt device with "blkdiscard -z". The command "blkdiscard -z" calls the BLKZEROOUT ioctl, it goes to the function __blkdev_issue_zeroout, __blkdev_issue_zeroout sends a large amount of write bios that contain the zero page as their payload. For each incoming page, dm-crypt allocates another page that holds the encrypted data, so when processing "blkdiscard -z", dm-crypt tries to allocate the amount of memory that is equal to the size of the device. This can trigger OOM killer or cause system crash. Fix this by limiting the amount of memory that dm-crypt allocates to 2% of total system memory. This limit is system-wide and is divided by the number of active dm-crypt devices and each device receives an equal share. Cc: stable@vger.kernel.org Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman

dm: backfill abnormal IO support to non-splitting IO submission

2018-04-24T07:42:59Z

commit 0519c71e8d461ac3ef9a555bb7339243c9128d37 upstream. Otherwise, these abnormal IOs would be sent to the DM target regardless of whether the target advertised support for them. Factor out __process_abnormal_io() from __split_and_process_non_flush() so that discards, write same, etc may be conditionally processed. Fixes: 978e51ba3 ("dm: optimize bio-based NVMe IO submission") Cc: stable@vger.kernel.org # 4.16 Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman

dm: fix dropped return code from dm_get_bdev_for_ioctl

2018-03-30T03:31:32Z

dm_get_bdev_for_ioctl()'s return of 0 or 1 must be the result from prepare_ioctl (1 means the ioctl was issued to a partition, 0 means it wasn't). Unfortunately commit 519049afea ("dm: use blkdev_get rather than bdgrab when issuing pass-through ioctl") reused the variable 'r' to store the return from blkdev_get() that follows prepare_ioctl() -- whereby dropping prepare_ioctl()'s result on the floor. This can lead to an ioctl or persistent reservation being issued to a partition going unnoticed, which implies the extra permission check for CAP_SYS_RAWIO is skipped. Fix this by using a different variable to store blkdev_get()'s return. Fixes: 519049afea ("dm: use blkdev_get rather than bdgrab when issuing pass-through ioctl") Reported-by: Alasdair G Kergon Signed-off-by: Mike Snitzer

dm mpath: fix support for loading scsi_dh modules during table load

2018-03-29T21:00:44Z

The ability to have multipath dynamically attach a scsi_dh, that the user specified in the multipath table, was broken by commit e8f74a0f00 ("dm mpath: eliminate need to use scsi_device_from_queue"). Restore the ability to load, and attach, a particular scsi_dh module if one is specified (as noticed by checking m->hw_handler_name). Fixes: e8f74a0f00 ("dm mpath: eliminate need to use scsi_device_from_queue") Reported-by: Paul Mackerras Signed-off-by: Mike Snitzer