linux-stable.git/drivers/nvme, branch v4.19.166

nvme: free sq/cq dbbuf pointers when dbbuf set fails

2020-12-02T07:48:09+00:00

[ Upstream commit 0f0d2c876c96d4908a9ef40959a44bec21bdd6cf ]

If Doorbell Buffer Config command fails even 'dev->dbbuf_dbs != NULL'
which means OACS indicates that NVME_CTRL_OACS_DBBUF_SUPP is set,
nvme_dbbuf_update_and_check_event() will check event even it's not been
successfully set.

This patch fixes mismatch among dbbuf for sq/cqs in case that dbbuf
command fails.

Signed-off-by: Minwoo Im 
Signed-off-by: Christoph Hellwig 
Signed-off-by: Sasha Levin

nvme-rdma: fix crash when connect rejected

2020-11-05T10:08:45+00:00

[ Upstream commit 43efdb8e870ee0f58633fd579aa5b5185bf5d39e ]

A crash can happened when a connect is rejected.   The host establishes
the connection after received ConnectReply, and then continues to send
the fabrics Connect command.  If the controller does not receive the
ReadyToUse capsule, host may receive a ConnectReject reply.

Call nvme_rdma_destroy_queue_ib after the host received the
RDMA_CM_EVENT_REJECTED event.  Then when the fabrics Connect command
times out, nvme_rdma_timeout calls nvme_rdma_complete_rq to fail the
request.  A crash happenes due to use after free in
nvme_rdma_complete_rq.

nvme_rdma_destroy_queue_ib is redundant when handling the
RDMA_CM_EVENT_REJECTED event as nvme_rdma_destroy_queue_ib is already
called in connection failure handler.

Signed-off-by: Chao Leng 
Reviewed-by: Sagi Grimberg 
Signed-off-by: Christoph Hellwig 
Signed-off-by: Sasha Levin

nvmet: fix uninitialized work for zero kato

2020-10-30T09:38:25+00:00

[ Upstream commit 85bd23f3dc09a2ae9e56885420e52c54bf983713 ]

When connecting a controller with a zero kato value using the following
command line

   nvme connect -t tcp -n NQN -a ADDR -s PORT --keep-alive-tmo=0

the warning below can be reproduced:

WARNING: CPU: 1 PID: 241 at kernel/workqueue.c:1627 __queue_delayed_work+0x6d/0x90
with trace:
  mod_delayed_work_on+0x59/0x90
  nvmet_update_cc+0xee/0x100 [nvmet]
  nvmet_execute_prop_set+0x72/0x80 [nvmet]
  nvmet_tcp_try_recv_pdu+0x2f7/0x770 [nvmet_tcp]
  nvmet_tcp_io_work+0x63f/0xb2d [nvmet_tcp]
  ...

This is caused by queuing up an uninitialized work.  Althrough the
keep-alive timer is disabled during allocating the controller (fixed in
0d3b6a8d213a), ka_work still has a chance to run (called by
nvmet_start_ctrl).

Fixes: 0d3b6a8d213a ("nvmet: Disable keep-alive timer when kato is cleared to 0h")
Signed-off-by: zhenwei pi 
Signed-off-by: Christoph Hellwig 
Signed-off-by: Sasha Levin

nvme-core: put ctrl ref when module ref get fail

2020-10-14T08:31:22+00:00

commit 4bab69093044ca81f394bd0780be1b71c5a4d308 upstream.

When try_module_get() fails in the nvme_dev_open() it returns without
releasing the ctrl reference which was taken earlier.

Put the ctrl reference which is taken before calling the
try_module_get() in the error return code path.

Fixes: 52a3974feb1a "nvme-core: get/put ctrl and transport module in nvme_dev_open/release()"
Signed-off-by: Chaitanya Kulkarni 
Reviewed-by: Logan Gunthorpe 
Signed-off-by: Christoph Hellwig 
Signed-off-by: Greg Kroah-Hartman

nvme-fc: fail new connections to a deleted host or remote port

2020-10-07T06:00:07+00:00

[ Upstream commit 9e0e8dac985d4bd07d9e62922b9d189d3ca2fccf ]

The lldd may have made calls to delete a remote port or local port and
the delete is in progress when the cli then attempts to create a new
controller. Currently, this proceeds without error although it can't be
very successful.

Fix this by validating that both the host port and remote port are
present when a new controller is to be created.

Signed-off-by: James Smart 
Reviewed-by: Himanshu Madhani 
Signed-off-by: Christoph Hellwig 
Signed-off-by: Sasha Levin

nvme-core: get/put ctrl and transport module in nvme_dev_open/release()

2020-10-07T06:00:06+00:00

[ Upstream commit 52a3974feb1a3eec25d8836d37a508b67b0a9cd0 ]

Get and put the reference to the ctrl in the nvme_dev_open() and
nvme_dev_release() before and after module get/put for ctrl in char
device file operations.

Introduce char_dev relase function, get/put the controller and module
which allows us to fix the potential Oops which can be easily reproduced
with a passthru ctrl (although the problem also exists with pure user
access):

Entering kdb (current=0xffff8887f8290000, pid 3128) on processor 30 Oops: (null)
due to oops @ 0xffffffffa01019ad
CPU: 30 PID: 3128 Comm: bash Tainted: G        W  OE     5.8.0-rc4nvme-5.9+ #35
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.4
RIP: 0010:nvme_free_ctrl+0x234/0x285 [nvme_core]
Code: 57 10 a0 e8 73 bf 02 e1 ba 3d 11 00 00 48 c7 c6 98 33 10 a0 48 c7 c7 1d 57 10 a0 e8 5b bf 02 e1 8
RSP: 0018:ffffc90001d63de0 EFLAGS: 00010246
RAX: ffffffffa05c0440 RBX: ffff8888119e45a0 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffff8888177e9550 RDI: ffff8888119e43b0
RBP: ffff8887d4768000 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: ffffc90001d63c90 R12: ffff8888119e43b0
R13: ffff8888119e5108 R14: dead000000000100 R15: ffff8888119e5108
FS:  00007f1ef27b0740(0000) GS:ffff888817600000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffffffa05c0470 CR3: 00000007f6bee000 CR4: 00000000003406e0
Call Trace:
 device_release+0x27/0x80
 kobject_put+0x98/0x170
 nvmet_passthru_ctrl_disable+0x4a/0x70 [nvmet]
 nvmet_passthru_enable_store+0x4c/0x90 [nvmet]
 configfs_write_file+0xe6/0x150
 vfs_write+0xba/0x1e0
 ksys_write+0x5f/0xe0
 do_syscall_64+0x52/0xb0
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7f1ef1eb2840
Code: Bad RIP value.
RSP: 002b:00007fffdbff0eb8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007f1ef1eb2840
RDX: 0000000000000002 RSI: 00007f1ef27d2000 RDI: 0000000000000001
RBP: 00007f1ef27d2000 R08: 000000000000000a R09: 00007f1ef27b0740
R10: 0000000000000001 R11: 0000000000000246 R12: 00007f1ef2186400
R13: 0000000000000002 R14: 0000000000000001 R15: 0000000000000000

With this patch fix we take the module ref count in nvme_dev_open() and
release that ref count in newly introduced nvme_dev_release().

Signed-off-by: Chaitanya Kulkarni 
Signed-off-by: Christoph Hellwig 
Signed-off-by: Sasha Levin

nvme: explicitly update mpath disk capacity on revalidation

2020-10-01T11:14:49+00:00

[ Upstream commit 05b29021fba5e725dd385151ef00b6340229b500 ]

Commit 3b4b19721ec652 ("nvme: fix possible deadlock when I/O is
blocked") reverted multipath head disk revalidation due to deadlocks
caused by holding the bd_mutex during revalidate.

Updating the multipath disk blockdev size is still required though for
userspace to be able to observe any resizing while the device is
mounted. Directly update the bdev inode size to avoid unnecessarily
holding the bdev->bd_mutex.

Fixes: 3b4b19721ec652 ("nvme: fix possible deadlock when I/O is
blocked")

Signed-off-by: Anthony Iliopoulos 
Signed-off-by: Christoph Hellwig 
Signed-off-by: Sasha Levin

nvme: fix possible deadlock when I/O is blocked

2020-10-01T11:14:48+00:00

[ Upstream commit 3b4b19721ec652ad2c4fe51dfbe5124212b5f581 ]

Revert fab7772bfbcf ("nvme-multipath: revalidate nvme_ns_head gendisk
in nvme_validate_ns")

When adding a new namespace to the head disk (via nvme_mpath_set_live)
we will see partition scan which triggers I/O on the mpath device node.
This process will usually be triggered from the scan_work which holds
the scan_lock. If I/O blocks (if we got ana change currently have only
available paths but none are accessible) this can deadlock on the head
disk bd_mutex as both partition scan I/O takes it, and head disk revalidation
takes it to check for resize (also triggered from scan_work on a different
path). See trace [1].

The mpath disk revalidation was originally added to detect online disk
size change, but this is no longer needed since commit cb224c3af4df
("nvme: Convert to use set_capacity_revalidate_and_notify") which already
updates resize info without unnecessarily revalidating the disk (the
mpath disk doesn't even implement .revalidate_disk fop).

[1]:
--
kernel: INFO: task kworker/u65:9:494 blocked for more than 241 seconds.
kernel:       Tainted: G           OE     5.3.5-050305-generic #201910071830
kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
kernel: kworker/u65:9   D    0   494      2 0x80004000
kernel: Workqueue: nvme-wq nvme_scan_work [nvme_core]
kernel: Call Trace:
kernel:  __schedule+0x2b9/0x6c0
kernel:  schedule+0x42/0xb0
kernel:  schedule_preempt_disabled+0xe/0x10
kernel:  __mutex_lock.isra.0+0x182/0x4f0
kernel:  __mutex_lock_slowpath+0x13/0x20
kernel:  mutex_lock+0x2e/0x40
kernel:  revalidate_disk+0x63/0xa0
kernel:  __nvme_revalidate_disk+0xfe/0x110 [nvme_core]
kernel:  nvme_revalidate_disk+0xa4/0x160 [nvme_core]
kernel:  ? evict+0x14c/0x1b0
kernel:  revalidate_disk+0x2b/0xa0
kernel:  nvme_validate_ns+0x49/0x940 [nvme_core]
kernel:  ? blk_mq_free_request+0xd2/0x100
kernel:  ? __nvme_submit_sync_cmd+0xbe/0x1e0 [nvme_core]
kernel:  nvme_scan_work+0x24f/0x380 [nvme_core]
kernel:  process_one_work+0x1db/0x380
kernel:  worker_thread+0x249/0x400
kernel:  kthread+0x104/0x140
kernel:  ? process_one_work+0x380/0x380
kernel:  ? kthread_park+0x80/0x80
kernel:  ret_from_fork+0x1f/0x40
...
kernel: INFO: task kworker/u65:1:2630 blocked for more than 241 seconds.
kernel:       Tainted: G           OE     5.3.5-050305-generic #201910071830
kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
kernel: kworker/u65:1   D    0  2630      2 0x80004000
kernel: Workqueue: nvme-wq nvme_scan_work [nvme_core]
kernel: Call Trace:
kernel:  __schedule+0x2b9/0x6c0
kernel:  schedule+0x42/0xb0
kernel:  io_schedule+0x16/0x40
kernel:  do_read_cache_page+0x438/0x830
kernel:  ? __switch_to_asm+0x34/0x70
kernel:  ? file_fdatawait_range+0x30/0x30
kernel:  read_cache_page+0x12/0x20
kernel:  read_dev_sector+0x27/0xc0
kernel:  read_lba+0xc1/0x220
kernel:  ? kmem_cache_alloc_trace+0x19c/0x230
kernel:  efi_partition+0x1e6/0x708
kernel:  ? vsnprintf+0x39e/0x4e0
kernel:  ? snprintf+0x49/0x60
kernel:  check_partition+0x154/0x244
kernel:  rescan_partitions+0xae/0x280
kernel:  __blkdev_get+0x40f/0x560
kernel:  blkdev_get+0x3d/0x140
kernel:  __device_add_disk+0x388/0x480
kernel:  device_add_disk+0x13/0x20
kernel:  nvme_mpath_set_live+0x119/0x140 [nvme_core]
kernel:  nvme_update_ns_ana_state+0x5c/0x60 [nvme_core]
kernel:  nvme_set_ns_ana_state+0x1e/0x30 [nvme_core]
kernel:  nvme_parse_ana_log+0xa1/0x180 [nvme_core]
kernel:  ? nvme_update_ns_ana_state+0x60/0x60 [nvme_core]
kernel:  nvme_mpath_add_disk+0x47/0x90 [nvme_core]
kernel:  nvme_validate_ns+0x396/0x940 [nvme_core]
kernel:  ? blk_mq_free_request+0xd2/0x100
kernel:  nvme_scan_work+0x24f/0x380 [nvme_core]
kernel:  process_one_work+0x1db/0x380
kernel:  worker_thread+0x249/0x400
kernel:  kthread+0x104/0x140
kernel:  ? process_one_work+0x380/0x380
kernel:  ? kthread_park+0x80/0x80
kernel:  ret_from_fork+0x1f/0x40
--

Fixes: fab7772bfbcf ("nvme-multipath: revalidate nvme_ns_head gendisk
in nvme_validate_ns")
Signed-off-by: Anton Eidelman 
Signed-off-by: Sagi Grimberg 
Signed-off-by: Christoph Hellwig 
Signed-off-by: Sasha Levin

nvmet-rdma: fix double free of rdma queue

2020-10-01T11:14:41+00:00

[ Upstream commit 21f9024355e58772ec5d7fc3534aa5e29d72a8b6 ]

In case rdma accept fails at nvmet_rdma_queue_connect(), release work is
scheduled. Later on, a new RDMA CM event may arrive since we didn't
destroy the cm-id and call nvmet_rdma_queue_connect_fail(), which
schedule another release work. This will cause calling
nvmet_rdma_free_queue twice. To fix this we implicitly destroy the cm_id
with non-zero ret code, which guarantees that new rdma_cm events will
not arrive afterwards. Also add a qp pointer to nvmet_rdma_queue
structure, so we can use it when the cm_id pointer is NULL or was
destroyed.

Signed-off-by: Israel Rukshin 
Suggested-by: Sagi Grimberg 
Reviewed-by: Max Gurtovoy 
Reviewed-by: Sagi Grimberg 
Signed-off-by: Christoph Hellwig 
Signed-off-by: Sasha Levin

nvme: Fix controller creation races with teardown flow

2020-10-01T11:14:40+00:00

[ Upstream commit ce1518139e6976cf19c133b555083354fdb629b8 ]

Calling nvme_sysfs_delete() when the controller is in the middle of
creation may cause several bugs. If the controller is in NEW state we
remove delete_controller file and don't delete the controller. The user
will not be able to use nvme disconnect command on that controller again,
although the controller may be active. Other bugs may happen if the
controller is in the middle of create_ctrl callback and
nvme_do_delete_ctrl() starts. For example, freeing I/O tagset at
nvme_do_delete_ctrl() before it was allocated at create_ctrl callback.

To fix all those races don't allow the user to delete the controller
before it was fully created.

Signed-off-by: Israel Rukshin 
Reviewed-by: Max Gurtovoy 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Keith Busch 
Signed-off-by: Sasha Levin