linux.git/drivers/nvme, branch v5.12.5 Clone of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git nvme: do not try to reconfigure APST when the controller is not live 2021-05-19T08:56:45+00:00 Christoph Hellwig hch@lst.de 2021-04-09T09:46:12+00:00 6e3a85b8aa01f5752813ee865eea517c97953830 commit 53fe2a30bc168db9700e00206d991ff934973cf1 upstream. Do not call nvme_configure_apst when the controller is not live, given that nvme_configure_apst will fail due the lack of an admin queue when the controller is being torn down and nvme_set_latency_tolerance is called from dev_pm_qos_hide_latency_tolerance. Fixes: 510a405d945b("nvme: fix memory leak for power latency tolerance") Reported-by: Peng Liu <liupeng17@lenovo.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <kbusch@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 53fe2a30bc168db9700e00206d991ff934973cf1 upstream.

Do not call nvme_configure_apst when the controller is not live, given
that nvme_configure_apst will fail due the lack of an admin queue when
the controller is being torn down and nvme_set_latency_tolerance is
called from dev_pm_qos_hide_latency_tolerance.

Fixes: 510a405d945b("nvme: fix memory leak for power latency tolerance")
Reported-by: Peng Liu <liupeng17@lenovo.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
nvmet-rdma: Fix NULL deref when SEND is completed with error 2021-05-19T08:56:38+00:00 Michal Kalderon michal.kalderon@marvell.com 2021-05-06T07:08:19+00:00 5bdb34466ad8370546dfa0497594fb1d6f2fed90 [ Upstream commit 8cc365f9559b86802afc0208389f5c8d46b4ad61 ] When running some traffic and taking down the link on peer, a retry counter exceeded error is received. This leads to nvmet_rdma_error_comp which tried accessing the cq_context to obtain the queue. The cq_context is no longer valid after the fix to use shared CQ mechanism and should be obtained similar to how it is obtained in other functions from the wc->qp. [ 905.786331] nvmet_rdma: SEND for CQE 0x00000000e3337f90 failed with status transport retry counter exceeded (12). [ 905.832048] BUG: unable to handle kernel NULL pointer dereference at 0000000000000048 [ 905.839919] PGD 0 P4D 0 [ 905.842464] Oops: 0000 1 SMP NOPTI [ 905.846144] CPU: 13 PID: 1557 Comm: kworker/13:1H Kdump: loaded Tainted: G OE --------- - - 4.18.0-304.el8.x86_64 #1 [ 905.872135] RIP: 0010:nvmet_rdma_error_comp+0x5/0x1b [nvmet_rdma] [ 905.878259] Code: 19 4f c0 e8 89 b3 a5 f6 e9 5b e0 ff ff 0f b7 75 14 4c 89 ea 48 c7 c7 08 1a 4f c0 e8 71 b3 a5 f6 e9 4b e0 ff ff 0f 1f 44 00 00 <48> 8b 47 48 48 85 c0 74 08 48 89 c7 e9 98 bf 49 00 e9 c3 e3 ff ff [ 905.897135] RSP: 0018:ffffab601c45fe28 EFLAGS: 00010246 [ 905.902387] RAX: 0000000000000065 RBX: ffff9e729ea2f800 RCX: 0000000000000000 [ 905.909558] RDX: 0000000000000000 RSI: ffff9e72df9567c8 RDI: 0000000000000000 [ 905.916731] RBP: ffff9e729ea2b400 R08: 000000000000074d R09: 0000000000000074 [ 905.923903] R10: 0000000000000000 R11: ffffab601c45fcc0 R12: 0000000000000010 [ 905.931074] R13: 0000000000000000 R14: 0000000000000010 R15: ffff9e729ea2f400 [ 905.938247] FS: 0000000000000000(0000) GS:ffff9e72df940000(0000) knlGS:0000000000000000 [ 905.938249] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 905.950067] nvmet_rdma: SEND for CQE 0x00000000c7356cca failed with status transport retry counter exceeded (12). [ 905.961855] CR2: 0000000000000048 CR3: 000000678d010004 CR4: 00000000007706e0 [ 905.961855] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 905.961856] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 905.961857] PKRU: 55555554 [ 906.010315] Call Trace: [ 906.012778] __ib_process_cq+0x89/0x170 [ib_core] [ 906.017509] ib_cq_poll_work+0x26/0x80 [ib_core] [ 906.022152] process_one_work+0x1a7/0x360 [ 906.026182] ? create_worker+0x1a0/0x1a0 [ 906.030123] worker_thread+0x30/0x390 [ 906.033802] ? create_worker+0x1a0/0x1a0 [ 906.037744] kthread+0x116/0x130 [ 906.040988] ? kthread_flush_work_fn+0x10/0x10 [ 906.045456] ret_from_fork+0x1f/0x40 Fixes: ca0f1a8055be2 ("nvmet-rdma: use new shared CQ mechanism") Signed-off-by: Shai Malin <smalin@marvell.com> Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 8cc365f9559b86802afc0208389f5c8d46b4ad61 ]

When running some traffic and taking down the link on peer, a
retry counter exceeded error is received. This leads to
nvmet_rdma_error_comp which tried accessing the cq_context to
obtain the queue. The cq_context is no longer valid after the
fix to use shared CQ mechanism and should be obtained similar
to how it is obtained in other functions from the wc->qp.

[ 905.786331] nvmet_rdma: SEND for CQE 0x00000000e3337f90 failed with status transport retry counter exceeded (12).
[ 905.832048] BUG: unable to handle kernel NULL pointer dereference at 0000000000000048
[ 905.839919] PGD 0 P4D 0
[ 905.842464] Oops: 0000 1 SMP NOPTI
[ 905.846144] CPU: 13 PID: 1557 Comm: kworker/13:1H Kdump: loaded Tainted: G OE --------- - - 4.18.0-304.el8.x86_64 #1
[ 905.872135] RIP: 0010:nvmet_rdma_error_comp+0x5/0x1b [nvmet_rdma]
[ 905.878259] Code: 19 4f c0 e8 89 b3 a5 f6 e9 5b e0 ff ff 0f b7 75 14 4c 89 ea 48 c7 c7 08 1a 4f c0 e8 71 b3 a5 f6 e9 4b e0 ff ff 0f 1f 44 00 00 <48> 8b 47 48 48 85 c0 74 08 48 89 c7 e9 98 bf 49 00 e9 c3 e3 ff ff
[ 905.897135] RSP: 0018:ffffab601c45fe28 EFLAGS: 00010246
[ 905.902387] RAX: 0000000000000065 RBX: ffff9e729ea2f800 RCX: 0000000000000000
[ 905.909558] RDX: 0000000000000000 RSI: ffff9e72df9567c8 RDI: 0000000000000000
[ 905.916731] RBP: ffff9e729ea2b400 R08: 000000000000074d R09: 0000000000000074
[ 905.923903] R10: 0000000000000000 R11: ffffab601c45fcc0 R12: 0000000000000010
[ 905.931074] R13: 0000000000000000 R14: 0000000000000010 R15: ffff9e729ea2f400
[ 905.938247] FS: 0000000000000000(0000) GS:ffff9e72df940000(0000) knlGS:0000000000000000
[ 905.938249] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 905.950067] nvmet_rdma: SEND for CQE 0x00000000c7356cca failed with status transport retry counter exceeded (12).
[ 905.961855] CR2: 0000000000000048 CR3: 000000678d010004 CR4: 00000000007706e0
[ 905.961855] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 905.961856] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 905.961857] PKRU: 55555554
[ 906.010315] Call Trace:
[ 906.012778] __ib_process_cq+0x89/0x170 [ib_core]
[ 906.017509] ib_cq_poll_work+0x26/0x80 [ib_core]
[ 906.022152] process_one_work+0x1a7/0x360
[ 906.026182] ? create_worker+0x1a0/0x1a0
[ 906.030123] worker_thread+0x30/0x390
[ 906.033802] ? create_worker+0x1a0/0x1a0
[ 906.037744] kthread+0x116/0x130
[ 906.040988] ? kthread_flush_work_fn+0x10/0x10
[ 906.045456] ret_from_fork+0x1f/0x40

Fixes: ca0f1a8055be2 ("nvmet-rdma: use new shared CQ mechanism")
Signed-off-by: Shai Malin <smalin@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
nvmet: fix inline bio check for passthru 2021-05-19T08:56:38+00:00 Chaitanya Kulkarni chaitanya.kulkarni@wdc.com 2021-05-07T01:51:36+00:00 03fce793a991fa2f3a32b836d8b975249d6bfa37 [ Upstream commit ab96de5def854d8fc51280b6a20597e64b14ac31 ] When handling passthru commands, for inline bio allocation we only consider the transfer size. This works well when req->sg_cnt fits into the req->inline_bvec, but it will result in the early return from bio_add_hw_page() when req->sg_cnt > NVMET_MAX_INLINE_BVEC. Consider an I/O of size 32768 and first buffer is not aligned to the page boundary, then I/O is split in following manner :- [ 2206.256140] nvmet: sg->length 3440 sg->offset 656 [ 2206.256144] nvmet: sg->length 4096 sg->offset 0 [ 2206.256148] nvmet: sg->length 4096 sg->offset 0 [ 2206.256152] nvmet: sg->length 4096 sg->offset 0 [ 2206.256155] nvmet: sg->length 4096 sg->offset 0 [ 2206.256159] nvmet: sg->length 4096 sg->offset 0 [ 2206.256163] nvmet: sg->length 4096 sg->offset 0 [ 2206.256166] nvmet: sg->length 4096 sg->offset 0 [ 2206.256170] nvmet: sg->length 656 sg->offset 0 Now the req->transfer_size == NVMET_MAX_INLINE_DATA_LEN i.e. 32768, but the req->sg_cnt is (9) > NVMET_MAX_INLINE_BIOVEC which is (8). This will result in early return in the following code path :- nvmet_bdev_execute_rw() bio_add_pc_page() bio_add_hw_page() if (bio_full(bio, len)) return 0; Use previously introduced helper nvmet_use_inline_bvec() to consider req->sg_cnt when using inline bio. This only affects nvme-loop transport. Fixes: dab3902b19a0 ("nvmet: use inline bio for passthru fast path") Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit ab96de5def854d8fc51280b6a20597e64b14ac31 ]

When handling passthru commands, for inline bio allocation we only
consider the transfer size. This works well when req->sg_cnt fits into
the req->inline_bvec, but it will result in the early return from
bio_add_hw_page() when req->sg_cnt > NVMET_MAX_INLINE_BVEC.

Consider an I/O of size 32768 and first buffer is not aligned to the
page boundary, then I/O is split in following manner :-

[ 2206.256140] nvmet: sg->length 3440 sg->offset 656
[ 2206.256144] nvmet: sg->length 4096 sg->offset 0
[ 2206.256148] nvmet: sg->length 4096 sg->offset 0
[ 2206.256152] nvmet: sg->length 4096 sg->offset 0
[ 2206.256155] nvmet: sg->length 4096 sg->offset 0
[ 2206.256159] nvmet: sg->length 4096 sg->offset 0
[ 2206.256163] nvmet: sg->length 4096 sg->offset 0
[ 2206.256166] nvmet: sg->length 4096 sg->offset 0
[ 2206.256170] nvmet: sg->length 656 sg->offset 0

Now the req->transfer_size == NVMET_MAX_INLINE_DATA_LEN i.e. 32768, but
the req->sg_cnt is (9) > NVMET_MAX_INLINE_BIOVEC which is (8).
This will result in early return in the following code path :-

nvmet_bdev_execute_rw()
	bio_add_pc_page()
		bio_add_hw_page()
			if (bio_full(bio, len))
				return 0;

Use previously introduced helper nvmet_use_inline_bvec() to consider
req->sg_cnt when using inline bio. This only affects nvme-loop
transport.

Fixes: dab3902b19a0 ("nvmet: use inline bio for passthru fast path")
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
nvmet: fix inline bio check for bdev-ns 2021-05-19T08:56:38+00:00 Chaitanya Kulkarni chaitanya.kulkarni@wdc.com 2021-05-07T01:51:35+00:00 3df867719031392c259999dc6f21e28a935200cb [ Upstream commit 608a969046e6e0567d05a166be66c77d2dd8220b ] When handling rw commands, for inline bio case we only consider transfer size. This works well when req->sg_cnt fits into the req->inline_bvec, but it will result in the warning in __bio_add_page() when req->sg_cnt > NVMET_MAX_INLINE_BVEC. Consider an I/O size 32768 and first page is not aligned to the page boundary, then I/O is split in following manner :- [ 2206.256140] nvmet: sg->length 3440 sg->offset 656 [ 2206.256144] nvmet: sg->length 4096 sg->offset 0 [ 2206.256148] nvmet: sg->length 4096 sg->offset 0 [ 2206.256152] nvmet: sg->length 4096 sg->offset 0 [ 2206.256155] nvmet: sg->length 4096 sg->offset 0 [ 2206.256159] nvmet: sg->length 4096 sg->offset 0 [ 2206.256163] nvmet: sg->length 4096 sg->offset 0 [ 2206.256166] nvmet: sg->length 4096 sg->offset 0 [ 2206.256170] nvmet: sg->length 656 sg->offset 0 Now the req->transfer_size == NVMET_MAX_INLINE_DATA_LEN i.e. 32768, but the req->sg_cnt is (9) > NVMET_MAX_INLINE_BIOVEC which is (8). This will result in the following warning message :- nvmet_bdev_execute_rw() bio_add_page() __bio_add_page() WARN_ON_ONCE(bio_full(bio, len)); This scenario is very hard to reproduce on the nvme-loop transport only with rw commands issued with the passthru IOCTL interface from the host application and the data buffer is allocated with the malloc() and not the posix_memalign(). Fixes: 73383adfad24 ("nvmet: don't split large I/Os unconditionally") Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 608a969046e6e0567d05a166be66c77d2dd8220b ]

When handling rw commands, for inline bio case we only consider
transfer size. This works well when req->sg_cnt fits into the
req->inline_bvec, but it will result in the warning in
__bio_add_page() when req->sg_cnt > NVMET_MAX_INLINE_BVEC.

Consider an I/O size 32768 and first page is not aligned to the page
boundary, then I/O is split in following manner :-

[ 2206.256140] nvmet: sg->length 3440 sg->offset 656
[ 2206.256144] nvmet: sg->length 4096 sg->offset 0
[ 2206.256148] nvmet: sg->length 4096 sg->offset 0
[ 2206.256152] nvmet: sg->length 4096 sg->offset 0
[ 2206.256155] nvmet: sg->length 4096 sg->offset 0
[ 2206.256159] nvmet: sg->length 4096 sg->offset 0
[ 2206.256163] nvmet: sg->length 4096 sg->offset 0
[ 2206.256166] nvmet: sg->length 4096 sg->offset 0
[ 2206.256170] nvmet: sg->length 656 sg->offset 0

Now the req->transfer_size == NVMET_MAX_INLINE_DATA_LEN i.e. 32768, but
the req->sg_cnt is (9) > NVMET_MAX_INLINE_BIOVEC which is (8).
This will result in the following warning message :-

nvmet_bdev_execute_rw()
	bio_add_page()
		__bio_add_page()
			WARN_ON_ONCE(bio_full(bio, len));

This scenario is very hard to reproduce on the nvme-loop transport only
with rw commands issued with the passthru IOCTL interface from the host
application and the data buffer is allocated with the malloc() and not
the posix_memalign().

Fixes: 73383adfad24 ("nvmet: don't split large I/Os unconditionally")
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
nvme-pci: don't simple map sgl when sgls are disabled 2021-05-14T08:52:42+00:00 Niklas Cassel niklas.cassel@wdc.com 2021-04-09T18:12:55+00:00 3709013f59ae15d2ce0e08f68d03077b05dcdde3 [ Upstream commit e51183be1fa96dc6d3cd11b3c25a0f595807315e ] According to the module parameter description for sgl_threshold, a value of 0 means that SGLs are disabled. If SGLs are disabled, we should respect that, even for the case where the request is made up of a single physical segment. Fixes: 297910571f08 ("nvme-pci: optimize mapping single segment requests using SGLs") Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit e51183be1fa96dc6d3cd11b3c25a0f595807315e ]

According to the module parameter description for sgl_threshold,
a value of 0 means that SGLs are disabled.

If SGLs are disabled, we should respect that, even for the case
where the request is made up of a single physical segment.

Fixes: 297910571f08 ("nvme-pci: optimize mapping single segment requests using SGLs")
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
nvmet-tcp: fix a segmentation fault during io parsing error 2021-05-14T08:52:42+00:00 Elad Grupi elad.grupi@dell.com 2021-03-31T09:13:14+00:00 8d14cda3129233d7bb3b3d860a681b7a8e7be3d5 [ Upstream commit bdaf13279192c60b2b1fc99badef53b494fec055 ] In case there is an io that contains inline data and it goes to parsing error flow, command response will free command and iov before clearing the data on the socket buffer. This will delay the command response until receive flow is completed. Fixes: 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver") Signed-off-by: Elad Grupi <elad.grupi@dell.com> Signed-off-by: Hou Pu <houpu.main@gmail.com> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit bdaf13279192c60b2b1fc99badef53b494fec055 ]

In case there is an io that contains inline data and it goes to
parsing error flow, command response will free command and iov
before clearing the data on the socket buffer.
This will delay the command response until receive flow is completed.

Fixes: 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver")
Signed-off-by: Elad Grupi <elad.grupi@dell.com>
Signed-off-by: Hou Pu <houpu.main@gmail.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
nvme: retrigger ANA log update if group descriptor isn't found 2021-05-14T08:52:38+00:00 Hannes Reinecke hare@suse.de 2020-12-05T15:29:01+00:00 1b71d5587fa7c794031a5bf2830dc1af892a26ca [ Upstream commit dd8f7fa908f66dd44abcd83cbb50410524b9f8ef ] If ANA is enabled but no ANA group descriptor is found when creating a new namespace the ANA log is most likely out of date, so trigger a re-read. The namespace will be tagged with the NS_ANA_PENDING flag to exclude it from path selection until the ANA log has been re-read. Fixes: 32acab3181c7 ("nvme: implement multipath access to nvme subsystems") Reported-by: Martin George <marting@netapp.com> Signed-off-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit dd8f7fa908f66dd44abcd83cbb50410524b9f8ef ]

If ANA is enabled but no ANA group descriptor is found when creating
a new namespace the ANA log is most likely out of date, so trigger
a re-read. The namespace will be tagged with the NS_ANA_PENDING flag
to exclude it from path selection until the ANA log has been re-read.

Fixes: 32acab3181c7 ("nvme: implement multipath access to nvme subsystems")
Reported-by: Martin George <marting@netapp.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
nvmet-tcp: fix incorrect locking in state_change sk callback 2021-05-14T08:52:38+00:00 Sagi Grimberg sagi@grimberg.me 2021-03-21T07:08:49+00:00 906c538340dde6d891df89fe7dac8eaa724e40da [ Upstream commit b5332a9f3f3d884a1b646ce155e664cc558c1722 ] We are not changing anything in the TCP connection state so we should not take a write_lock but rather a read lock. This caused a deadlock when running nvmet-tcp and nvme-tcp on the same system, where state_change callbacks on the host and on the controller side have causal relationship and made lockdep report on this with blktests: ================================ WARNING: inconsistent lock state 5.12.0-rc3 #1 Tainted: G I -------------------------------- inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-R} usage. nvme/1324 [HC0[0]:SC0[0]:HE1:SE1] takes: ffff888363151000 (clock-AF_INET){++-?}-{2:2}, at: nvme_tcp_state_change+0x21/0x150 [nvme_tcp] {IN-SOFTIRQ-W} state was registered at: __lock_acquire+0x79b/0x18d0 lock_acquire+0x1ca/0x480 _raw_write_lock_bh+0x39/0x80 nvmet_tcp_state_change+0x21/0x170 [nvmet_tcp] tcp_fin+0x2a8/0x780 tcp_data_queue+0xf94/0x1f20 tcp_rcv_established+0x6ba/0x1f00 tcp_v4_do_rcv+0x502/0x760 tcp_v4_rcv+0x257e/0x3430 ip_protocol_deliver_rcu+0x69/0x6a0 ip_local_deliver_finish+0x1e2/0x2f0 ip_local_deliver+0x1a2/0x420 ip_rcv+0x4fb/0x6b0 __netif_receive_skb_one_core+0x162/0x1b0 process_backlog+0x1ff/0x770 __napi_poll.constprop.0+0xa9/0x5c0 net_rx_action+0x7b3/0xb30 __do_softirq+0x1f0/0x940 do_softirq+0xa1/0xd0 __local_bh_enable_ip+0xd8/0x100 ip_finish_output2+0x6b7/0x18a0 __ip_queue_xmit+0x706/0x1aa0 __tcp_transmit_skb+0x2068/0x2e20 tcp_write_xmit+0xc9e/0x2bb0 __tcp_push_pending_frames+0x92/0x310 inet_shutdown+0x158/0x300 __nvme_tcp_stop_queue+0x36/0x270 [nvme_tcp] nvme_tcp_stop_queue+0x87/0xb0 [nvme_tcp] nvme_tcp_teardown_admin_queue+0x69/0xe0 [nvme_tcp] nvme_do_delete_ctrl+0x100/0x10c [nvme_core] nvme_sysfs_delete.cold+0x8/0xd [nvme_core] kernfs_fop_write_iter+0x2c7/0x460 new_sync_write+0x36c/0x610 vfs_write+0x5c0/0x870 ksys_write+0xf9/0x1d0 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae irq event stamp: 10687 hardirqs last enabled at (10687): [<ffffffff9ec376bd>] _raw_spin_unlock_irqrestore+0x2d/0x40 hardirqs last disabled at (10686): [<ffffffff9ec374d8>] _raw_spin_lock_irqsave+0x68/0x90 softirqs last enabled at (10684): [<ffffffff9f000608>] __do_softirq+0x608/0x940 softirqs last disabled at (10649): [<ffffffff9cdedd31>] do_softirq+0xa1/0xd0 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(clock-AF_INET); <Interrupt> lock(clock-AF_INET); *** DEADLOCK *** 5 locks held by nvme/1324: #0: ffff8884a01fe470 (sb_writers#4){.+.+}-{0:0}, at: ksys_write+0xf9/0x1d0 #1: ffff8886e435c090 (&of->mutex){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x216/0x460 #2: ffff888104d90c38 (kn->active#255){++++}-{0:0}, at: kernfs_remove_self+0x22d/0x330 #3: ffff8884634538d0 (&queue->queue_lock){+.+.}-{3:3}, at: nvme_tcp_stop_queue+0x52/0xb0 [nvme_tcp] #4: ffff888363150d30 (sk_lock-AF_INET){+.+.}-{0:0}, at: inet_shutdown+0x59/0x300 stack backtrace: CPU: 26 PID: 1324 Comm: nvme Tainted: G I 5.12.0-rc3 #1 Hardware name: Dell Inc. PowerEdge R640/06NR82, BIOS 2.10.0 11/12/2020 Call Trace: dump_stack+0x93/0xc2 mark_lock_irq.cold+0x2c/0xb3 ? verify_lock_unused+0x390/0x390 ? stack_trace_consume_entry+0x160/0x160 ? lock_downgrade+0x100/0x100 ? save_trace+0x88/0x5e0 ? _raw_spin_unlock_irqrestore+0x2d/0x40 mark_lock+0x530/0x1470 ? mark_lock_irq+0x1d10/0x1d10 ? enqueue_timer+0x660/0x660 mark_usage+0x215/0x2a0 __lock_acquire+0x79b/0x18d0 ? tcp_schedule_loss_probe.part.0+0x38c/0x520 lock_acquire+0x1ca/0x480 ? nvme_tcp_state_change+0x21/0x150 [nvme_tcp] ? rcu_read_unlock+0x40/0x40 ? tcp_mtu_probe+0x1ae0/0x1ae0 ? kmalloc_reserve+0xa0/0xa0 ? sysfs_file_ops+0x170/0x170 _raw_read_lock+0x3d/0xa0 ? nvme_tcp_state_change+0x21/0x150 [nvme_tcp] nvme_tcp_state_change+0x21/0x150 [nvme_tcp] ? sysfs_file_ops+0x170/0x170 inet_shutdown+0x189/0x300 __nvme_tcp_stop_queue+0x36/0x270 [nvme_tcp] nvme_tcp_stop_queue+0x87/0xb0 [nvme_tcp] nvme_tcp_teardown_admin_queue+0x69/0xe0 [nvme_tcp] nvme_do_delete_ctrl+0x100/0x10c [nvme_core] nvme_sysfs_delete.cold+0x8/0xd [nvme_core] kernfs_fop_write_iter+0x2c7/0x460 new_sync_write+0x36c/0x610 ? new_sync_read+0x600/0x600 ? lock_acquire+0x1ca/0x480 ? rcu_read_unlock+0x40/0x40 ? lock_is_held_type+0x9a/0x110 vfs_write+0x5c0/0x870 ksys_write+0xf9/0x1d0 ? __ia32_sys_read+0xa0/0xa0 ? lockdep_hardirqs_on_prepare.part.0+0x198/0x340 ? syscall_enter_from_user_mode+0x27/0x70 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae Fixes: 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver") Reported-by: Yi Zhang <yi.zhang@redhat.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit b5332a9f3f3d884a1b646ce155e664cc558c1722 ]

We are not changing anything in the TCP connection state so
we should not take a write_lock but rather a read lock.

This caused a deadlock when running nvmet-tcp and nvme-tcp
on the same system, where state_change callbacks on the
host and on the controller side have causal relationship
and made lockdep report on this with blktests:

================================
WARNING: inconsistent lock state
5.12.0-rc3 #1 Tainted: G          I
--------------------------------
inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-R} usage.
nvme/1324 [HC0[0]:SC0[0]:HE1:SE1] takes:
ffff888363151000 (clock-AF_INET){++-?}-{2:2}, at: nvme_tcp_state_change+0x21/0x150 [nvme_tcp]
{IN-SOFTIRQ-W} state was registered at:
  __lock_acquire+0x79b/0x18d0
  lock_acquire+0x1ca/0x480
  _raw_write_lock_bh+0x39/0x80
  nvmet_tcp_state_change+0x21/0x170 [nvmet_tcp]
  tcp_fin+0x2a8/0x780
  tcp_data_queue+0xf94/0x1f20
  tcp_rcv_established+0x6ba/0x1f00
  tcp_v4_do_rcv+0x502/0x760
  tcp_v4_rcv+0x257e/0x3430
  ip_protocol_deliver_rcu+0x69/0x6a0
  ip_local_deliver_finish+0x1e2/0x2f0
  ip_local_deliver+0x1a2/0x420
  ip_rcv+0x4fb/0x6b0
  __netif_receive_skb_one_core+0x162/0x1b0
  process_backlog+0x1ff/0x770
  __napi_poll.constprop.0+0xa9/0x5c0
  net_rx_action+0x7b3/0xb30
  __do_softirq+0x1f0/0x940
  do_softirq+0xa1/0xd0
  __local_bh_enable_ip+0xd8/0x100
  ip_finish_output2+0x6b7/0x18a0
  __ip_queue_xmit+0x706/0x1aa0
  __tcp_transmit_skb+0x2068/0x2e20
  tcp_write_xmit+0xc9e/0x2bb0
  __tcp_push_pending_frames+0x92/0x310
  inet_shutdown+0x158/0x300
  __nvme_tcp_stop_queue+0x36/0x270 [nvme_tcp]
  nvme_tcp_stop_queue+0x87/0xb0 [nvme_tcp]
  nvme_tcp_teardown_admin_queue+0x69/0xe0 [nvme_tcp]
  nvme_do_delete_ctrl+0x100/0x10c [nvme_core]
  nvme_sysfs_delete.cold+0x8/0xd [nvme_core]
  kernfs_fop_write_iter+0x2c7/0x460
  new_sync_write+0x36c/0x610
  vfs_write+0x5c0/0x870
  ksys_write+0xf9/0x1d0
  do_syscall_64+0x33/0x40
  entry_SYSCALL_64_after_hwframe+0x44/0xae
irq event stamp: 10687
hardirqs last  enabled at (10687): [<ffffffff9ec376bd>] _raw_spin_unlock_irqrestore+0x2d/0x40
hardirqs last disabled at (10686): [<ffffffff9ec374d8>] _raw_spin_lock_irqsave+0x68/0x90
softirqs last  enabled at (10684): [<ffffffff9f000608>] __do_softirq+0x608/0x940
softirqs last disabled at (10649): [<ffffffff9cdedd31>] do_softirq+0xa1/0xd0

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(clock-AF_INET);
  <Interrupt>
    lock(clock-AF_INET);

 *** DEADLOCK ***

5 locks held by nvme/1324:
 #0: ffff8884a01fe470 (sb_writers#4){.+.+}-{0:0}, at: ksys_write+0xf9/0x1d0
 #1: ffff8886e435c090 (&of->mutex){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x216/0x460
 #2: ffff888104d90c38 (kn->active#255){++++}-{0:0}, at: kernfs_remove_self+0x22d/0x330
 #3: ffff8884634538d0 (&queue->queue_lock){+.+.}-{3:3}, at: nvme_tcp_stop_queue+0x52/0xb0 [nvme_tcp]
 #4: ffff888363150d30 (sk_lock-AF_INET){+.+.}-{0:0}, at: inet_shutdown+0x59/0x300

stack backtrace:
CPU: 26 PID: 1324 Comm: nvme Tainted: G          I       5.12.0-rc3 #1
Hardware name: Dell Inc. PowerEdge R640/06NR82, BIOS 2.10.0 11/12/2020
Call Trace:
 dump_stack+0x93/0xc2
 mark_lock_irq.cold+0x2c/0xb3
 ? verify_lock_unused+0x390/0x390
 ? stack_trace_consume_entry+0x160/0x160
 ? lock_downgrade+0x100/0x100
 ? save_trace+0x88/0x5e0
 ? _raw_spin_unlock_irqrestore+0x2d/0x40
 mark_lock+0x530/0x1470
 ? mark_lock_irq+0x1d10/0x1d10
 ? enqueue_timer+0x660/0x660
 mark_usage+0x215/0x2a0
 __lock_acquire+0x79b/0x18d0
 ? tcp_schedule_loss_probe.part.0+0x38c/0x520
 lock_acquire+0x1ca/0x480
 ? nvme_tcp_state_change+0x21/0x150 [nvme_tcp]
 ? rcu_read_unlock+0x40/0x40
 ? tcp_mtu_probe+0x1ae0/0x1ae0
 ? kmalloc_reserve+0xa0/0xa0
 ? sysfs_file_ops+0x170/0x170
 _raw_read_lock+0x3d/0xa0
 ? nvme_tcp_state_change+0x21/0x150 [nvme_tcp]
 nvme_tcp_state_change+0x21/0x150 [nvme_tcp]
 ? sysfs_file_ops+0x170/0x170
 inet_shutdown+0x189/0x300
 __nvme_tcp_stop_queue+0x36/0x270 [nvme_tcp]
 nvme_tcp_stop_queue+0x87/0xb0 [nvme_tcp]
 nvme_tcp_teardown_admin_queue+0x69/0xe0 [nvme_tcp]
 nvme_do_delete_ctrl+0x100/0x10c [nvme_core]
 nvme_sysfs_delete.cold+0x8/0xd [nvme_core]
 kernfs_fop_write_iter+0x2c7/0x460
 new_sync_write+0x36c/0x610
 ? new_sync_read+0x600/0x600
 ? lock_acquire+0x1ca/0x480
 ? rcu_read_unlock+0x40/0x40
 ? lock_is_held_type+0x9a/0x110
 vfs_write+0x5c0/0x870
 ksys_write+0xf9/0x1d0
 ? __ia32_sys_read+0xa0/0xa0
 ? lockdep_hardirqs_on_prepare.part.0+0x198/0x340
 ? syscall_enter_from_user_mode+0x27/0x70
 do_syscall_64+0x33/0x40
 entry_SYSCALL_64_after_hwframe+0x44/0xae

Fixes: 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver")
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
nvme-tcp: block BH in sk state_change sk callback 2021-05-14T08:52:38+00:00 Sagi Grimberg sagi@grimberg.me 2021-03-21T07:08:48+00:00 c7dee3feee3fdbca68235e4e6041edd6e7ed65c7 [ Upstream commit 8b73b45d54a14588f86792869bfb23098ea254cb ] The TCP stack can run from process context for a long time so we should disable BH here. Fixes: 3f2304f8c6d6 ("nvme-tcp: add NVMe over TCP host driver") Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 8b73b45d54a14588f86792869bfb23098ea254cb ]

The TCP stack can run from process context for a long time
so we should disable BH here.

Fixes: 3f2304f8c6d6 ("nvme-tcp: add NVMe over TCP host driver")
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
nvmet: avoid queuing keep-alive timer if it is disabled 2021-05-12T06:39:53+00:00 Hou Pu houpu.main@gmail.com 2021-04-16T02:45:21+00:00 284d899d90004213794f45c5506020d7782e9150 [ Upstream commit 8f864c595bed20ef85fef3e7314212b73800d51d ] Issue following command: nvme set-feature -f 0xf -v 0 /dev/nvme1n1 # disable keep-alive timer nvme admin-passthru -o 0x18 /dev/nvme1n1 # send keep-alive command will make keep-alive timer fired and thus delete the controller like below: [247459.907635] nvmet: ctrl 1 keep-alive timer (0 seconds) expired! [247459.930294] nvmet: ctrl 1 fatal error occurred! Avoid this by not queuing delayed keep-alive if it is disabled when keep-alive command is received from the admin queue. Signed-off-by: Hou Pu <houpu.main@gmail.com> Tested-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 8f864c595bed20ef85fef3e7314212b73800d51d ]

Issue following command:
nvme set-feature -f 0xf -v 0 /dev/nvme1n1 # disable keep-alive timer
nvme admin-passthru -o 0x18 /dev/nvme1n1  # send keep-alive command
will make keep-alive timer fired and thus delete the controller like
below:

[247459.907635] nvmet: ctrl 1 keep-alive timer (0 seconds) expired!
[247459.930294] nvmet: ctrl 1 fatal error occurred!

Avoid this by not queuing delayed keep-alive if it is disabled when
keep-alive command is received from the admin queue.

Signed-off-by: Hou Pu <houpu.main@gmail.com>
Tested-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>