kernel/linux.git/drivers/nvme/host/core.c, branch linux-4.16.y

nvme: fix use-after-free in nvme_free_ns_head

2018-06-20T19:01:38+00:00

[ Upstream commit 12d9f07022dcde261ad16e9a11f45096dc68b03c ] Currently only nvme_ctrl will take a reference counter of nvme_subsystem, nvme_ns_head also needs it. Otherwise nvme_free_ns_head will access the nvme_subsystem.ns_ida which has been freed by __nvme_release_subsystem after all the reference of nvme_subsystem have been released by nvme_free_ctrl. This could cause memory corruption. BUG: KASAN: use-after-free in radix_tree_next_chunk+0x9f/0x4b0 Read of size 8 at addr ffff88036494d2e8 by task fio/1815 CPU: 1 PID: 1815 Comm: fio Kdump: loaded Tainted: G W 4.17.0-rc1+ #18 Hardware name: LENOVO 10MLS0E339/3106, BIOS M1AKT22A 06/27/2017 Call Trace: dump_stack+0x91/0xeb print_address_description+0x6b/0x290 kasan_report+0x261/0x360 radix_tree_next_chunk+0x9f/0x4b0 ida_remove+0x8b/0x180 ida_simple_remove+0x26/0x40 nvme_free_ns_head+0x58/0xc0 __blkdev_put+0x30a/0x3a0 blkdev_close+0x44/0x50 __fput+0x184/0x380 task_work_run+0xaf/0xe0 do_exit+0x501/0x1440 do_group_exit+0x89/0x140 __x64_sys_exit_group+0x28/0x30 do_syscall_64+0x72/0x230 Signed-off-by: Jianchao Wang Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

nvme/multipath: Fix multipath disabled naming collisions

2018-06-20T19:01:34+00:00

[ Upstream commit a785dbccd95c37606c720580714f5a7a8b3255f1 ] When CONFIG_NVME_MULTIPATH is set, but we're not using nvme to multipath, namespaces with multiple paths were not creating unique names due to reusing the same instance number from the namespace's head. This patch fixes this by falling back to the non-multipath naming method when the parameter disabled using multipath. Reported-by: Mike Snitzer Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

nvme: Set integrity flag for user passthrough commands

2018-06-20T19:01:34+00:00

[ Upstream commit f31a21103c03bb62846409fdc60cc9faf2398cfb ] If the command a separate metadata buffer attached, the request needs to have the integrity flag set so the driver knows to map it. Signed-off-by: Keith Busch Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

nvme: fix extended data LBA supported setting

2018-06-05T09:46:11+00:00

commit c97f414c54a255f4f05a50a2625efaeee406e134 upstream. This value depands on the metadata support value, so reorder the initialization to fit. Fixes: b5be3b392 ("nvme: always unregister the integrity profile in __nvme_revalidate_disk") Signed-off-by: Max Gurtovoy Signed-off-by: Christoph Hellwig Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

nvme: expand nvmf_check_if_ready checks

2018-05-30T06:17:20+00:00

[ Upstream commit bb06ec31452fb2da1594f88035c2ecea4e0652f4 ] The nvmf_check_if_ready() checks that were added are very simplistic. As such, the routine allows a lot of cases to fail ios during windows of reset or re-connection. In cases where there are not multi-path options present, the error goes back to the callee - the filesystem or application. Not good. The common routine was rewritten and calling syntax slightly expanded so that per-transport is_ready routines don't need to be present. The transports now call the routine directly. The routine is now a fabrics routine rather than an inline function. The routine now looks at controller state to decide the action to take. Some states mandate io failure. Others define the condition where a command can be accepted. When the decision is unclear, a generic queue-or-reject check is made to look for failfast or multipath ios and only fails the io if it is so marked. Otherwise, the io will be queued and wait for the controller state to resolve. Admin commands issued via ioctl share a live admin queue with commands from the transport for controller init. The ioctls could be intermixed with the initialization commands. It's possible for the ioctl cmd to be issued prior to the controller being enabled. To block this, the ioctl admin commands need to be distinguished from admin commands used for controller init. Added a USERCMD nvme_req(req)->rq_flags bit to reflect this division and set it on ioctls requests. As the nvmf_check_if_ready() routine is called prior to nvme_setup_cmd(), ensure that commands allocated by the ioctl path (actually anything in core.c) preps the nvme_req(req) before starting the io. This will preserve the USERCMD flag during execution and/or retry. Signed-off-by: James Smart Reviewed-by: Sagi Grimberg Reviewed-by: Johannes Thumshirn Signed-off-by: Keith Busch Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

nvme: Fix sync controller reset return

2018-05-16T08:12:35+00:00

commit 4e50d9ebaeaa3c6761d2b513ef7039510c8cf213 upstream. If a controller reset is requested while the device has no namespaces, we were incorrectly returning ENETRESET. This patch adds the check for ADMIN_ONLY controller state to indicate a successful reset. Fixes: 8000d1fdb0 ("nvme-rdma: fix sysfs invoked reset_ctrl error flow ") Cc: Signed-off-by: Charles Machalow [changelog] Signed-off-by: Keith Busch Signed-off-by: Greg Kroah-Hartman

nvme: Skip checking heads without namespaces

2018-04-19T06:54:08+00:00

commit 2079699c10c8c60a9572540c2f77d045abf036eb upstream. If a task is holding a reference to a namespace on a removed controller, the head will not be released. If the same controller is added again later, its namespaces may not be successfully added. Instead, the user will see kernel message "Duplicate IDs for nsid ". This patch fixes that by skipping heads that don't have namespaces when considering if a new namespace is safe to add. Reported-by: Alex Gagniuc Cc: stable@vger.kernel.org Signed-off-by: Keith Busch Reviewed-by: Max Gurtovoy Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman

Revert "nvme: create 'slaves' and 'holders' entries for hidden controllers"

2018-03-07T10:22:28+00:00

This reverts commit e9a48034d7d1318ece7d4a235838a86c94db9d68. The slaves and holders link for the hidden gendisks confuse lsblk so that it errors out on, or doesn't report the nvme multipath devices. Given that we don't need holder relationships for something that can't even be directly accessed we should just stop creating those links. Signed-off-by: Christoph Hellwig Reported-by: Potnuri Bharat Teja Cc: stable@vger.kernel.org Signed-off-by: Keith Busch

Merge branch 'for-jens' of git://git.infradead.org/nvme into for-linus

2018-02-28T19:18:58+00:00

Pull NVMe fixes from Keith for 4.16-rc. * 'for-jens' of git://git.infradead.org/nvme: nvmet: fix PSDT field check in command format nvme-multipath: fix sysfs dangerously created links nvme-pci: Fix nvme queue cleanup if IRQ setup fails nvmet-loop: use blk_rq_payload_bytes for sgl selection nvme-rdma: use blk_rq_payload_bytes instead of blk_rq_bytes nvme-fabrics: don't check for non-NULL module in nvmf_register_transport

nvme-multipath: fix sysfs dangerously created links

2018-02-28T09:46:48+00:00

If multipathing is enabled, each NVMe subsystem creates a head namespace (e.g., nvme0n1) and multiple private namespaces (e.g., nvme0c0n1 and nvme0c1n1) in sysfs. When creating links for private namespaces, links of head namespace are used, so the namespace creation order must be followed (e.g., nvme0n1 -> nvme0c1n1). If the order is not followed, links of sysfs will be incomplete or kernel panic will occur. The kernel panic was: kernel BUG at fs/sysfs/symlink.c:27! Call Trace: nvme_mpath_add_disk_links+0x5d/0x80 [nvme_core] nvme_validate_ns+0x5c2/0x850 [nvme_core] nvme_scan_work+0x1af/0x2d0 [nvme_core] Correct order Context A Context B nvme0n1 nvme0c0n1 nvme0c1n1 Incorrect order Context A Context B nvme0c1n1 nvme0n1 nvme0c0n1 The nvme_mpath_add_disk (for creating head namespace) is called just before the nvme_mpath_add_disk_links (for creating private namespaces). In nvme_mpath_add_disk, the first context acquires the lock of subsystem and creates a head namespace, and other contexts do nothing by checking GENHD_FL_UP of a head namespace after waiting to acquire the lock. We verified the code with or without multipathing using three vendors of dual-port NVMe SSDs. Signed-off-by: Baegjae Sung Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch