From 03b3bcd319b3ab5182bc9aaa0421351572c78ac0 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 4 Nov 2025 14:48:30 -0800 Subject: [PATCH 1/5] nvme: fix admin request_queue lifetime The namespaces can access the controller's admin request_queue, and stale references on the namespaces may exist after tearing down the controller. Ensure the admin request_queue is active by moving the controller's 'put' to after all controller references have been released to ensure no one is can access the request_queue. This fixes a reported use-after-free bug: BUG: KASAN: slab-use-after-free in blk_queue_enter+0x41c/0x4a0 Read of size 8 at addr ffff88c0a53819f8 by task nvme/3287 CPU: 67 UID: 0 PID: 3287 Comm: nvme Tainted: G E 6.13.2-ga1582f1a031e #15 Tainted: [E]=UNSIGNED_MODULE Hardware name: Jabil /EGS 2S MB1, BIOS 1.00 06/18/2025 Call Trace: dump_stack_lvl+0x4f/0x60 print_report+0xc4/0x620 ? _raw_spin_lock_irqsave+0x70/0xb0 ? _raw_read_unlock_irqrestore+0x30/0x30 ? blk_queue_enter+0x41c/0x4a0 kasan_report+0xab/0xe0 ? blk_queue_enter+0x41c/0x4a0 blk_queue_enter+0x41c/0x4a0 ? __irq_work_queue_local+0x75/0x1d0 ? blk_queue_start_drain+0x70/0x70 ? irq_work_queue+0x18/0x20 ? vprintk_emit.part.0+0x1cc/0x350 ? wake_up_klogd_work_func+0x60/0x60 blk_mq_alloc_request+0x2b7/0x6b0 ? __blk_mq_alloc_requests+0x1060/0x1060 ? __switch_to+0x5b7/0x1060 nvme_submit_user_cmd+0xa9/0x330 nvme_user_cmd.isra.0+0x240/0x3f0 ? force_sigsegv+0xe0/0xe0 ? nvme_user_cmd64+0x400/0x400 ? vfs_fileattr_set+0x9b0/0x9b0 ? cgroup_update_frozen_flag+0x24/0x1c0 ? cgroup_leave_frozen+0x204/0x330 ? nvme_ioctl+0x7c/0x2c0 blkdev_ioctl+0x1a8/0x4d0 ? blkdev_common_ioctl+0x1930/0x1930 ? fdget+0x54/0x380 __x64_sys_ioctl+0x129/0x190 do_syscall_64+0x5b/0x160 entry_SYSCALL_64_after_hwframe+0x4b/0x53 RIP: 0033:0x7f765f703b0b Code: ff ff ff 85 c0 79 9b 49 c7 c4 ff ff ff ff 5b 5d 4c 89 e0 41 5c c3 66 0f 1f 84 00 00 00 00 00 f3 0f 1e fa b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d dd 52 0f 00 f7 d8 64 89 01 48 RSP: 002b:00007ffe2cefe808 EFLAGS: 00000202 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007ffe2cefe860 RCX: 00007f765f703b0b RDX: 00007ffe2cefe860 RSI: 00000000c0484e41 RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000000000003 R09: 0000000000000000 R10: 00007f765f611d50 R11: 0000000000000202 R12: 0000000000000003 R13: 00000000c0484e41 R14: 0000000000000001 R15: 00007ffe2cefea60 Reported-by: Casey Chen Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Ming Lei Reviewed-by: Chaitanya Kulkarni Signed-off-by: Keith Busch --- drivers/nvme/host/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index fa4181d7de73..f1f719351f3f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4901,7 +4901,6 @@ void nvme_remove_admin_tag_set(struct nvme_ctrl *ctrl) */ nvme_stop_keep_alive(ctrl); blk_mq_destroy_queue(ctrl->admin_q); - blk_put_queue(ctrl->admin_q); if (ctrl->ops->flags & NVME_F_FABRICS) { blk_mq_destroy_queue(ctrl->fabrics_q); blk_put_queue(ctrl->fabrics_q); @@ -5045,6 +5044,8 @@ static void nvme_free_ctrl(struct device *dev) container_of(dev, struct nvme_ctrl, ctrl_device); struct nvme_subsystem *subsys = ctrl->subsys; + if (ctrl->admin_q) + blk_put_queue(ctrl->admin_q); if (!subsys || ctrl->instance != subsys->instance) ida_free(&nvme_instance_ida, ctrl->instance); nvme_free_cels(ctrl); From 159de7a825aea4242d3f8d32de5853d269dbe72f Mon Sep 17 00:00:00 2001 From: Alistair Francis Date: Fri, 7 Nov 2025 09:17:11 +1000 Subject: [PATCH 2/5] nvmet-auth: update sc_c in target host hash calculation Commit 7e091add9c43 "nvme-auth: update sc_c in host response" added the sc_c variable to the dhchap queue context structure which is appropriately set during negotiate and then used in the host response. This breaks secure concat connections with a Linux target as the target code wasn't updated at the same time. This patch fixes this by adding a new sc_c variable to the host hash calculations. Fixes: 7e091add9c43 ("nvme-auth: update sc_c in host response") Tested-by: Shin'ichiro Kawasaki Tested-by: Yi Zhang Reviewed-by: Martin George Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Alistair Francis Signed-off-by: Keith Busch --- drivers/nvme/target/auth.c | 4 ++-- drivers/nvme/target/fabrics-cmd-auth.c | 1 + drivers/nvme/target/nvmet.h | 1 + 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c index ceba21684e82..300d5e032f6d 100644 --- a/drivers/nvme/target/auth.c +++ b/drivers/nvme/target/auth.c @@ -298,7 +298,7 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, const char *hash_name; u8 *challenge = req->sq->dhchap_c1; struct nvme_dhchap_key *transformed_key; - u8 buf[4], sc_c = ctrl->concat ? 1 : 0; + u8 buf[4]; int ret; hash_name = nvme_auth_hmac_name(ctrl->shash_id); @@ -367,7 +367,7 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, ret = crypto_shash_update(shash, buf, 2); if (ret) goto out; - *buf = sc_c; + *buf = req->sq->sc_c; ret = crypto_shash_update(shash, buf, 1); if (ret) goto out; diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c index bf01ec414c55..5946681cb0e3 100644 --- a/drivers/nvme/target/fabrics-cmd-auth.c +++ b/drivers/nvme/target/fabrics-cmd-auth.c @@ -43,6 +43,7 @@ static u8 nvmet_auth_negotiate(struct nvmet_req *req, void *d) data->auth_protocol[0].dhchap.halen, data->auth_protocol[0].dhchap.dhlen); req->sq->dhchap_tid = le16_to_cpu(data->t_id); + req->sq->sc_c = data->sc_c; if (data->sc_c != NVME_AUTH_SECP_NOSC) { if (!IS_ENABLED(CONFIG_NVME_TARGET_TCP_TLS)) return NVME_AUTH_DHCHAP_FAILURE_CONCAT_MISMATCH; diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 51df72f5e89b..f3b09f4099f0 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -159,6 +159,7 @@ struct nvmet_sq { bool authenticated; struct delayed_work auth_expired_work; u16 dhchap_tid; + u8 sc_c; u8 dhchap_status; u8 dhchap_step; u8 *dhchap_c1; From 6d87cd5335784351280f82c47cc8a657271929c3 Mon Sep 17 00:00:00 2001 From: Shin'ichiro Kawasaki Date: Mon, 17 Nov 2025 11:23:39 +0900 Subject: [PATCH 3/5] nvme-multipath: fix lockdep WARN due to partition scan work Blktests test cases nvme/014, 057 and 058 fail occasionally due to a lockdep WARN. As reported in the Closes tag URL, the WARN indicates that a deadlock can happen due to the dependency among disk->open_mutex, kblockd workqueue completion and partition_scan_work completion. To avoid the lockdep WARN and the potential deadlock, cut the dependency by running the partition_scan_work not by kblockd workqueue but by nvme_wq. Reported-by: Yi Zhang Closes: https://lore.kernel.org/linux-block/CAHj4cs8mJ+R_GmQm9R8ebResKAWUE8kF5+_WVg0v8zndmqd6BQ@mail.gmail.com/ Link: https://lore.kernel.org/linux-block/oeyzci6ffshpukpfqgztsdeke5ost5hzsuz4rrsjfmvpqcevax@5nhnwbkzbrpa/ Fixes: 1f021341eef4 ("nvme-multipath: defer partition scanning") Signed-off-by: Shin'ichiro Kawasaki Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Keith Busch --- drivers/nvme/host/multipath.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 543e17aead12..e35eccacee8c 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -793,7 +793,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns) return; } nvme_add_ns_head_cdev(head); - kblockd_schedule_work(&head->partition_scan_work); + queue_work(nvme_wq, &head->partition_scan_work); } nvme_mpath_add_sysfs_link(ns->head); From ea3442efabd0aa3930c5bab73c3901ef38ef6ac3 Mon Sep 17 00:00:00 2001 From: "Ewan D. Milne" Date: Mon, 10 Nov 2025 16:20:00 -0500 Subject: [PATCH 4/5] nvme: nvme-fc: move tagset removal to nvme_fc_delete_ctrl() Now target is removed from nvme_fc_ctrl_free() which is the ctrl->ref release handler. And even admin queue is unquiesced there, this way is definitely wrong because the ctr->ref is grabbed when submitting command. And Marco observed that nvme_fc_ctrl_free() can be called from request completion code path, and trigger kernel warning since request completes from softirq context. Fix the issue by moveing target removal into nvme_fc_delete_ctrl(), which is also aligned with nvme-tcp and nvme-rdma. Patch originally proposed by Ming Lei, then modified to move the tagset removal down to after nvme_fc_delete_association() after further testing. Cc: Marco Patalano Cc: Ewan Milne Cc: James Smart Cc: Sagi Grimberg Signed-off-by: Ming Lei Cc: stable@vger.kernel.org Tested-by: Marco Patalano Reviewed-by: Justin Tee Signed-off-by: Ewan D. Milne Signed-off-by: Keith Busch --- drivers/nvme/host/fc.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 03987f497a5b..2dd8adf1139e 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2355,17 +2355,11 @@ nvme_fc_ctrl_free(struct kref *ref) container_of(ref, struct nvme_fc_ctrl, ref); unsigned long flags; - if (ctrl->ctrl.tagset) - nvme_remove_io_tag_set(&ctrl->ctrl); - /* remove from rport list */ spin_lock_irqsave(&ctrl->rport->lock, flags); list_del(&ctrl->ctrl_list); spin_unlock_irqrestore(&ctrl->rport->lock, flags); - nvme_unquiesce_admin_queue(&ctrl->ctrl); - nvme_remove_admin_tag_set(&ctrl->ctrl); - kfree(ctrl->queues); put_device(ctrl->dev); @@ -3261,11 +3255,18 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl) cancel_work_sync(&ctrl->ioerr_work); cancel_delayed_work_sync(&ctrl->connect_work); + /* * kill the association on the link side. this will block * waiting for io to terminate */ nvme_fc_delete_association(ctrl); + + if (ctrl->ctrl.tagset) + nvme_remove_io_tag_set(&ctrl->ctrl); + + nvme_unquiesce_admin_queue(&ctrl->ctrl); + nvme_remove_admin_tag_set(&ctrl->ctrl); } static void From 0a2c5495b6d1ecb0fa18ef6631450f391a888256 Mon Sep 17 00:00:00 2001 From: "Ewan D. Milne" Date: Mon, 10 Nov 2025 16:20:01 -0500 Subject: [PATCH 5/5] nvme: nvme-fc: Ensure ->ioerr_work is cancelled in nvme_fc_delete_ctrl() nvme_fc_delete_assocation() waits for pending I/O to complete before returning, and an error can cause ->ioerr_work to be queued after cancel_work_sync() had been called. Move the call to cancel_work_sync() to be after nvme_fc_delete_association() to ensure ->ioerr_work is not running when the nvme_fc_ctrl object is freed. Otherwise the following can occur: [ 1135.911754] list_del corruption, ff2d24c8093f31f8->next is NULL [ 1135.917705] ------------[ cut here ]------------ [ 1135.922336] kernel BUG at lib/list_debug.c:52! [ 1135.926784] Oops: invalid opcode: 0000 [#1] SMP NOPTI [ 1135.931851] CPU: 48 UID: 0 PID: 726 Comm: kworker/u449:23 Kdump: loaded Not tainted 6.12.0 #1 PREEMPT(voluntary) [ 1135.943490] Hardware name: Dell Inc. PowerEdge R660/0HGTK9, BIOS 2.5.4 01/16/2025 [ 1135.950969] Workqueue: 0x0 (nvme-wq) [ 1135.954673] RIP: 0010:__list_del_entry_valid_or_report.cold+0xf/0x6f [ 1135.961041] Code: c7 c7 98 68 72 94 e8 26 45 fe ff 0f 0b 48 c7 c7 70 68 72 94 e8 18 45 fe ff 0f 0b 48 89 fe 48 c7 c7 80 69 72 94 e8 07 45 fe ff <0f> 0b 48 89 d1 48 c7 c7 a0 6a 72 94 48 89 c2 e8 f3 44 fe ff 0f 0b [ 1135.979788] RSP: 0018:ff579b19482d3e50 EFLAGS: 00010046 [ 1135.985015] RAX: 0000000000000033 RBX: ff2d24c8093f31f0 RCX: 0000000000000000 [ 1135.992148] RDX: 0000000000000000 RSI: ff2d24d6bfa1d0c0 RDI: ff2d24d6bfa1d0c0 [ 1135.999278] RBP: ff2d24c8093f31f8 R08: 0000000000000000 R09: ffffffff951e2b08 [ 1136.006413] R10: ffffffff95122ac8 R11: 0000000000000003 R12: ff2d24c78697c100 [ 1136.013546] R13: fffffffffffffff8 R14: 0000000000000000 R15: ff2d24c78697c0c0 [ 1136.020677] FS: 0000000000000000(0000) GS:ff2d24d6bfa00000(0000) knlGS:0000000000000000 [ 1136.028765] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1136.034510] CR2: 00007fd207f90b80 CR3: 000000163ea22003 CR4: 0000000000f73ef0 [ 1136.041641] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1136.048776] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400 [ 1136.055910] PKRU: 55555554 [ 1136.058623] Call Trace: [ 1136.061074] [ 1136.063179] ? show_trace_log_lvl+0x1b0/0x2f0 [ 1136.067540] ? show_trace_log_lvl+0x1b0/0x2f0 [ 1136.071898] ? move_linked_works+0x4a/0xa0 [ 1136.075998] ? __list_del_entry_valid_or_report.cold+0xf/0x6f [ 1136.081744] ? __die_body.cold+0x8/0x12 [ 1136.085584] ? die+0x2e/0x50 [ 1136.088469] ? do_trap+0xca/0x110 [ 1136.091789] ? do_error_trap+0x65/0x80 [ 1136.095543] ? __list_del_entry_valid_or_report.cold+0xf/0x6f [ 1136.101289] ? exc_invalid_op+0x50/0x70 [ 1136.105127] ? __list_del_entry_valid_or_report.cold+0xf/0x6f [ 1136.110874] ? asm_exc_invalid_op+0x1a/0x20 [ 1136.115059] ? __list_del_entry_valid_or_report.cold+0xf/0x6f [ 1136.120806] move_linked_works+0x4a/0xa0 [ 1136.124733] worker_thread+0x216/0x3a0 [ 1136.128485] ? __pfx_worker_thread+0x10/0x10 [ 1136.132758] kthread+0xfa/0x240 [ 1136.135904] ? __pfx_kthread+0x10/0x10 [ 1136.139657] ret_from_fork+0x31/0x50 [ 1136.143236] ? __pfx_kthread+0x10/0x10 [ 1136.146988] ret_from_fork_asm+0x1a/0x30 [ 1136.150915] Fixes: 19fce0470f05 ("nvme-fc: avoid calling _nvme_fc_abort_outstanding_ios from interrupt context") Cc: stable@vger.kernel.org Tested-by: Marco Patalano Reviewed-by: Justin Tee Signed-off-by: Ewan D. Milne Signed-off-by: Keith Busch --- drivers/nvme/host/fc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 2dd8adf1139e..2c903729b0b9 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3253,7 +3253,6 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl) { struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl); - cancel_work_sync(&ctrl->ioerr_work); cancel_delayed_work_sync(&ctrl->connect_work); /* @@ -3261,6 +3260,7 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl) * waiting for io to terminate */ nvme_fc_delete_association(ctrl); + cancel_work_sync(&ctrl->ioerr_work); if (ctrl->ctrl.tagset) nvme_remove_io_tag_set(&ctrl->ctrl);