From 88ce2a530cc9865a894454b2e40eba5957a60e1a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Sep 2020 16:15:06 +0200 Subject: block: restore a specific error code in bdev_del_partition mdadm relies on the fact that deleting an invalid partition returns -ENXIO or -ENOTTY to detect if a block device is a partition or a whole device. Fixes: 08fc1ab6d748 ("block: fix locking in bdev_del_partition") Reported-by: kernel test robot Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/partitions/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'block') diff --git a/block/partitions/core.c b/block/partitions/core.c index 5b4869c08fb3..722406b841df 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -537,7 +537,7 @@ int bdev_del_partition(struct block_device *bdev, int partno) bdevp = bdget_disk(bdev->bd_disk, partno); if (!bdevp) - return -ENOMEM; + return -ENXIO; mutex_lock(&bdevp->bd_mutex); mutex_lock_nested(&bdev->bd_mutex, 1); -- cgit From e8a8a185051a460e3eb0617dca33f996f4e31516 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Tue, 8 Sep 2020 13:46:37 -0700 Subject: block: only call sched requeue_request() for scheduled requests Yang Yang reported the following crash caused by requeueing a flush request in Kyber: [ 2.517297] Unable to handle kernel paging request at virtual address ffffffd8071c0b00 ... [ 2.517468] pc : clear_bit+0x18/0x2c [ 2.517502] lr : sbitmap_queue_clear+0x40/0x228 [ 2.517503] sp : ffffff800832bc60 pstate : 00c00145 ... [ 2.517599] Process ksoftirqd/5 (pid: 51, stack limit = 0xffffff8008328000) [ 2.517602] Call trace: [ 2.517606] clear_bit+0x18/0x2c [ 2.517619] kyber_finish_request+0x74/0x80 [ 2.517627] blk_mq_requeue_request+0x3c/0xc0 [ 2.517637] __scsi_queue_insert+0x11c/0x148 [ 2.517640] scsi_softirq_done+0x114/0x130 [ 2.517643] blk_done_softirq+0x7c/0xb0 [ 2.517651] __do_softirq+0x208/0x3bc [ 2.517657] run_ksoftirqd+0x34/0x60 [ 2.517663] smpboot_thread_fn+0x1c4/0x2c0 [ 2.517667] kthread+0x110/0x120 [ 2.517669] ret_from_fork+0x10/0x18 This happens because Kyber doesn't track flush requests, so kyber_finish_request() reads a garbage domain token. Only call the scheduler's requeue_request() hook if RQF_ELVPRIV is set (like we do for the finish_request() hook in blk_mq_free_request()). Now that we're handling it in blk-mq, also remove the check from BFQ. Reported-by: Yang Yang Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/bfq-iosched.c | 12 ------------ block/blk-mq-sched.h | 2 +- 2 files changed, 1 insertion(+), 13 deletions(-) (limited to 'block') diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index a4c0bec920cb..ee767fa000e4 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5895,18 +5895,6 @@ static void bfq_finish_requeue_request(struct request *rq) struct bfq_queue *bfqq = RQ_BFQQ(rq); struct bfq_data *bfqd; - /* - * Requeue and finish hooks are invoked in blk-mq without - * checking whether the involved request is actually still - * referenced in the scheduler. To handle this fact, the - * following two checks make this function exit in case of - * spurious invocations, for which there is nothing to do. - * - * First, check whether rq has nothing to do with an elevator. - */ - if (unlikely(!(rq->rq_flags & RQF_ELVPRIV))) - return; - /* * rq either is not associated with any icq, or is an already * requeued request that has not (yet) been re-inserted into diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 126021fc3a11..e81ca1bf6e10 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -66,7 +66,7 @@ static inline void blk_mq_sched_requeue_request(struct request *rq) struct request_queue *q = rq->q; struct elevator_queue *e = q->elevator; - if (e && e->type->ops.requeue_request) + if ((rq->rq_flags & RQF_ELVPRIV) && e && e->type->ops.requeue_request) e->type->ops.requeue_request(rq); } -- cgit From 2cd896a5e86fc326bda8614b96c0401dcc145868 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Wed, 9 Sep 2020 08:44:25 +0530 Subject: block: Set same_page to false in __bio_try_merge_page if ret is false If we hit the UINT_MAX limit of bio->bi_iter.bi_size and so we are anyway not merging this page in this bio, then it make sense to make same_page also as false before returning. Without this patch, we hit below WARNING in iomap. This mostly happens with very large memory system and / or after tweaking vm dirty threshold params to delay writeback of dirty data. WARNING: CPU: 18 PID: 5130 at fs/iomap/buffered-io.c:74 iomap_page_release+0x120/0x150 CPU: 18 PID: 5130 Comm: fio Kdump: loaded Tainted: G W 5.8.0-rc3 #6 Call Trace: __remove_mapping+0x154/0x320 (unreliable) iomap_releasepage+0x80/0x180 try_to_release_page+0x94/0xe0 invalidate_inode_page+0xc8/0x110 invalidate_mapping_pages+0x1dc/0x540 generic_fadvise+0x3c8/0x450 xfs_file_fadvise+0x2c/0xe0 [xfs] vfs_fadvise+0x3c/0x60 ksys_fadvise64_64+0x68/0xe0 sys_fadvise64+0x28/0x40 system_call_exception+0xf8/0x1c0 system_call_common+0xf0/0x278 Fixes: cc90bc68422 ("block: fix "check bi_size overflow before merge"") Reported-by: Shivaprasad G Bhat Suggested-by: Christoph Hellwig Signed-off-by: Anju T Sudhakar Signed-off-by: Ritesh Harjani Reviewed-by: Ming Lei Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/bio.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'block') diff --git a/block/bio.c b/block/bio.c index a9931f23d933..e865ea55b9f9 100644 --- a/block/bio.c +++ b/block/bio.c @@ -879,8 +879,10 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page, struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; if (page_is_mergeable(bv, page, len, off, same_page)) { - if (bio->bi_iter.bi_size > UINT_MAX - len) + if (bio->bi_iter.bi_size > UINT_MAX - len) { + *same_page = false; return false; + } bv->bv_len += len; bio->bi_iter.bi_size += len; return true; -- cgit