linux/drivers/block, branch v6.4

Revert "virtio-blk: support completion batching for the IRQ path"

2023-06-21T08:14:28Z

This reverts commit 07b679f70d73483930e8d3c293942416d9cd5c13. This change appears to have broken things... We now see applications hanging during disk accesses. e.g. multi-port virtio-blk device running in h/w (FPGA) Host running a simple 'fio' test. [global] thread=1 direct=1 ioengine=libaio norandommap=1 group_reporting=1 bs=4K rw=read iodepth=128 runtime=1 numjobs=4 time_based [job0] filename=/dev/vda [job1] filename=/dev/vdb [job2] filename=/dev/vdc ... [job15] filename=/dev/vdp i.e. 16 disks; 4 queues per disk; simple burst of 4KB reads This is repeatedly run in a loop. After a few, normally <10 seconds, fio hangs. With 64 queues (16 disks), failure occurs within a few seconds; with 8 queues (2 disks) it may take ~hour before hanging. Last message: fio-3.19 Starting 8 threads Jobs: 1 (f=1): [_(7),R(1)][68.3%][eta 03h:11m:06s] I think this means at the end of the run 1 queue was left incomplete. 'diskstats' (run while fio is hung) shows no outstanding transactions. e.g. $ cat /proc/diskstats ... 252 0 vda 1843140071 0 14745120568 712568645 0 0 0 0 0 3117947 712568645 0 0 0 0 0 0 252 16 vdb 1816291511 0 14530332088 704905623 0 0 0 0 0 3117711 704905623 0 0 0 0 0 0 ... Other stats (in the h/w, and added to the virtio-blk driver ([a]virtio_queue_rq(), [b]virtblk_handle_req(), [c]virtblk_request_done()) all agree, and show every request had a completion, and that virtblk_request_done() never gets called. e.g. PF= 0 vq=0 1 2 3 [a]request_count - 839416590 813148916 105586179 84988123 [b]completion1_count - 839416590 813148916 105586179 84988123 [c]completion2_count - 0 0 0 0 PF= 1 vq=0 1 2 3 [a]request_count - 823335887 812516140 104582672 75856549 [b]completion1_count - 823335887 812516140 104582672 75856549 [c]completion2_count - 0 0 0 0 i.e. the issue is after the virtio-blk driver. This change was introduced in kernel 6.3.0. I am seeing this using 6.3.3. If I run with an earlier kernel (5.15), it does not occur. If I make a simple patch to the 6.3.3 virtio-blk driver, to skip the blk_mq_add_to_batch()call, it does not fail. e.g. kernel 5.15 - this is OK virtio_blk.c,virtblk_done() [irq handler] if (likely(!blk_should_fake_timeout(req->q))) { blk_mq_complete_request(req); } kernel 6.3.3 - this fails virtio_blk.c,virtblk_handle_req() [irq handler] if (likely(!blk_should_fake_timeout(req->q))) { if (!blk_mq_complete_request_remote(req)) { if (!blk_mq_add_to_batch(req, iob, virtblk_vbr_status(vbr), virtblk_complete_batch)) { virtblk_request_done(req); //this never gets called... so blk_mq_add_to_batch() must always succeed } } } If I do, kernel 6.3.3 - this is OK virtio_blk.c,virtblk_handle_req() [irq handler] if (likely(!blk_should_fake_timeout(req->q))) { if (!blk_mq_complete_request_remote(req)) { virtblk_request_done(req); //force this here... if (!blk_mq_add_to_batch(req, iob, virtblk_vbr_status(vbr), virtblk_complete_batch)) { virtblk_request_done(req); //this never gets called... so blk_mq_add_to_batch() must always succeed } } } Perhaps you might like to fix/test/revert this change... Martin Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202306090826.C1fZmdMe-lkp@intel.com/ Cc: Suwan Kim Tested-by: edliaw@google.com Reported-by: "Roberts, Martin" Message-Id: <336455b4f630f329380a8f53ee8cad3868764d5c.1686295549.git.mst@redhat.com> Signed-off-by: Michael S. Tsirkin

Merge tag 'block-6.4-2023-06-09' of git://git.kernel.dk/linux

2023-06-09T21:21:20Z

Pull block fixes from Jens Axboe: - Fix an issue with the hardware queue nr_active, causing it to become imbalanced (Tian) - Fix an issue with null_blk not releasing pages if configured as memory backed (Nitesh) - Fix a locking issue in dasd (Jan) * tag 'block-6.4-2023-06-09' of git://git.kernel.dk/linux: s390/dasd: Use correct lock while counting channel queue length null_blk: Fix: memory release when memory_backed=1 blk-mq: fix blk_mq_hw_ctx active request accounting

rbd: get snapshot context after exclusive lock is ensured to be held

2023-06-06T07:54:27Z

Move capturing the snapshot context into the image request state machine, after exclusive lock is ensured to be held for the duration of dealing with the image request. This is needed to ensure correctness of fast-diff states (OBJECT_EXISTS vs OBJECT_EXISTS_CLEAN) and object deltas computed based off of them. Otherwise the object map that is forked for the snapshot isn't guaranteed to accurately reflect the contents of the snapshot when the snapshot is taken under I/O. This breaks differential backup and snapshot-based mirroring use cases with fast-diff enabled: since some object deltas may be incomplete, the destination image may get corrupted. Cc: stable@vger.kernel.org Link: https://tracker.ceph.com/issues/61472 Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang

rbd: move RBD_OBJ_FLAG_COPYUP_ENABLED flag setting

2023-06-06T07:53:59Z

Move RBD_OBJ_FLAG_COPYUP_ENABLED flag setting into the object request state machine to allow for the snapshot context to be captured in the image request state machine rather than in rbd_queue_workfn(). Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang

null_blk: Fix: memory release when memory_backed=1

2023-06-05T22:15:35Z

Memory/pages are not freed, when unloading nullblk driver. Steps to reproduce issue 1.free -h total used free shared buff/cache available Mem: 7.8Gi 260Mi 7.1Gi 3.0Mi 395Mi 7.3Gi Swap: 0B 0B 0B 2.modprobe null_blk memory_backed=1 3.dd if=/dev/urandom of=/dev/nullb0 oflag=direct bs=1M count=1000 4.modprobe -r null_blk 5.free -h total used free shared buff/cache available Mem: 7.8Gi 1.2Gi 6.1Gi 3.0Mi 398Mi 6.3Gi Swap: 0B 0B 0B Signed-off-by: Anuj Gupta Signed-off-by: Nitesh Shetty Link: https://lore.kernel.org/r/20230605062354.24785-1-nj.shetty@samsung.com Signed-off-by: Jens Axboe

Merge tag 'for-linus-6.4-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

2023-05-27T16:42:56Z

Pull xen fixes from Juergen Gross: - a double free fix in the Xen pvcalls backend driver - a fix for a regression causing the MSI related sysfs entries to not being created in Xen PV guests - a fix in the Xen blkfront driver for handling insane input data better * tag 'for-linus-6.4-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip: x86/pci/xen: populate MSI sysfs entries xen/pvcalls-back: fix double frees with pvcalls_new_active_socket() xen/blkfront: Only check REQ_FUA for writes

xen/blkfront: Only check REQ_FUA for writes

2023-05-24T14:35:39Z

The existing code silently converts read operations with the REQ_FUA bit set into write-barrier operations. This results in data loss as the backend scribbles zeroes over the data instead of returning it. While the REQ_FUA bit doesn't make sense on a read operation, at least one well-known out-of-tree kernel module does set it and since it results in data loss, let's be safe here and only look at REQ_FUA for writes. Signed-off-by: Ross Lagerwall Acked-by: Juergen Gross Link: https://lore.kernel.org/r/20230426164005.2213139-1-ross.lagerwall@citrix.com Signed-off-by: Juergen Gross

ublk: fix AB-BA lockdep warning

2023-05-18T13:59:08Z

When handling UBLK_IO_FETCH_REQ, ctx->uring_lock is grabbed first, then ub->mutex is acquired. When handling UBLK_CMD_STOP_DEV or UBLK_CMD_DEL_DEV, ub->mutex is grabbed first, then calling io_uring_cmd_done() for canceling uring command, in which ctx->uring_lock may be required. Real deadlock only happens when all the above commands are issued from same uring context, and in reality different uring contexts are often used for handing control command and IO command. Fix the issue by using io_uring_cmd_complete_in_task() to cancel command in ublk_cancel_dev(ublk_cancel_queue). Reported-by: Shinichiro Kawasaki Closes: https://lore.kernel.org/linux-block/becol2g7sawl4rsjq2dztsbc7mqypfqko6wzsyoyazqydoasml@rcxarzwidrhk Cc: Ziyang Zhang Signed-off-by: Ming Lei Tested-by: Shinichiro Kawasaki Link: https://lore.kernel.org/r/20230517133408.210944-1-ming.lei@redhat.com Signed-off-by: Jens Axboe

ublk: fix command op code check

2023-05-12T15:09:06Z

In case of CONFIG_BLKDEV_UBLK_LEGACY_OPCODES, type of cmd opcode could be 0 or 'u'; and type can only be 'u' if CONFIG_BLKDEV_UBLK_LEGACY_OPCODES isn't set. So fix the wrong check. Fixes: 2d786e66c966 ("block: ublk: switch to ioctl command encoding") Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20230505153142.1258336-1-ming.lei@redhat.com Signed-off-by: Jens Axboe

block/rnbd: replace REQ_OP_FLUSH with REQ_OP_WRITE

2023-05-12T14:56:42Z

Since flush bios are implemented as writes with no data and the preflush flag per Christoph's comment [1]. And we need to change it in rnbd accordingly. Otherwise, I got splatting when create fs from rnbd client. [ 464.028545] ------------[ cut here ]------------ [ 464.028553] WARNING: CPU: 0 PID: 65 at block/blk-core.c:751 submit_bio_noacct+0x32c/0x5d0 [ ... ] [ 464.028668] CPU: 0 PID: 65 Comm: kworker/0:1H Tainted: G OE 6.4.0-rc1 #9 [ 464.028671] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.15.0-0-g2dd4b9b-rebuilt.opensuse.org 04/01/2014 [ 464.028673] Workqueue: ib-comp-wq ib_cq_poll_work [ib_core] [ 464.028717] RIP: 0010:submit_bio_noacct+0x32c/0x5d0 [ 464.028720] Code: 03 0f 85 51 fe ff ff 48 8b 43 18 8b 88 04 03 00 00 85 c9 0f 85 3f fe ff ff e9 be fd ff ff 0f b6 d0 3c 0d 74 26 83 fa 01 74 21 <0f> 0b b8 0a 00 00 00 e9 56 fd ff ff 4c 89 e7 e8 70 a1 03 00 84 c0 [ 464.028722] RSP: 0018:ffffaf3680b57c68 EFLAGS: 00010202 [ 464.028724] RAX: 0000000000060802 RBX: ffffa09dcc18bf00 RCX: 0000000000000000 [ 464.028726] RDX: 0000000000000002 RSI: 0000000000000000 RDI: ffffa09dde081d00 [ 464.028727] RBP: ffffaf3680b57c98 R08: ffffa09dde081d00 R09: ffffa09e38327200 [ 464.028729] R10: 0000000000000000 R11: 0000000000000000 R12: ffffa09dde081d00 [ 464.028730] R13: ffffa09dcb06e1e8 R14: 0000000000000000 R15: 0000000000200000 [ 464.028733] FS: 0000000000000000(0000) GS:ffffa09e3bc00000(0000) knlGS:0000000000000000 [ 464.028735] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 464.028736] CR2: 000055a4e8206c40 CR3: 0000000119f06000 CR4: 00000000003506f0 [ 464.028738] Call Trace: [ 464.028740] [ 464.028746] submit_bio+0x1b/0x80 [ 464.028748] rnbd_srv_rdma_ev+0x50d/0x10c0 [rnbd_server] [ 464.028754] ? percpu_ref_get_many.constprop.0+0x55/0x140 [rtrs_server] [ 464.028760] ? __this_cpu_preempt_check+0x13/0x20 [ 464.028769] process_io_req+0x1dc/0x450 [rtrs_server] [ 464.028775] rtrs_srv_inv_rkey_done+0x67/0xb0 [rtrs_server] [ 464.028780] __ib_process_cq+0xbc/0x1f0 [ib_core] [ 464.028793] ib_cq_poll_work+0x2b/0xa0 [ib_core] [ 464.028804] process_one_work+0x2a9/0x580 [1]. https://lore.kernel.org/all/ZFHgefWofVt24tRl@infradead.org/ Signed-off-by: Guoqing Jiang Reviewed-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20230512034631.28686-1-guoqing.jiang@linux.dev Signed-off-by: Jens Axboe