| { |
| "containers": { |
| "cna": { |
| "providerMetadata": { |
| "orgId": "f4215fc3-5b6b-47ff-a258-f7189bd81038" |
| }, |
| "descriptions": [ |
| { |
| "lang": "en", |
| "value": "In the Linux kernel, the following vulnerability has been resolved:\n\nnvme-fabrics: fix kernel crash while shutting down controller\n\nThe nvme keep-alive operation, which executes at a periodic interval,\ncould potentially sneak in while shutting down a fabric controller.\nThis may lead to a race between the fabric controller admin queue\ndestroy code path (invoked while shutting down controller) and hw/hctx\nqueue dispatcher called from the nvme keep-alive async request queuing\noperation. This race could lead to the kernel crash shown below:\n\nCall Trace:\n autoremove_wake_function+0x0/0xbc (unreliable)\n __blk_mq_sched_dispatch_requests+0x114/0x24c\n blk_mq_sched_dispatch_requests+0x44/0x84\n blk_mq_run_hw_queue+0x140/0x220\n nvme_keep_alive_work+0xc8/0x19c [nvme_core]\n process_one_work+0x200/0x4e0\n worker_thread+0x340/0x504\n kthread+0x138/0x140\n start_kernel_thread+0x14/0x18\n\nWhile shutting down fabric controller, if nvme keep-alive request sneaks\nin then it would be flushed off. The nvme_keep_alive_end_io function is\nthen invoked to handle the end of the keep-alive operation which\ndecrements the admin->q_usage_counter and assuming this is the last/only\nrequest in the admin queue then the admin->q_usage_counter becomes zero.\nIf that happens then blk-mq destroy queue operation (blk_mq_destroy_\nqueue()) which could be potentially running simultaneously on another\ncpu (as this is the controller shutdown code path) would forward\nprogress and deletes the admin queue. So, now from this point onward\nwe are not supposed to access the admin queue resources. However the\nissue here's that the nvme keep-alive thread running hw/hctx queue\ndispatch operation hasn't yet finished its work and so it could still\npotentially access the admin queue resource while the admin queue had\nbeen already deleted and that causes the above crash.\n\nThe above kernel crash is regression caused due to changes implemented\nin commit a54a93d0e359 (\"nvme: move stopping keep-alive into\nnvme_uninit_ctrl()\"). Ideally we should stop keep-alive before destroyin\ng the admin queue and freeing the admin tagset so that it wouldn't sneak\nin during the shutdown operation. However we removed the keep alive stop\noperation from the beginning of the controller shutdown code path in commit\na54a93d0e359 (\"nvme: move stopping keep-alive into nvme_uninit_ctrl()\")\nand added it under nvme_uninit_ctrl() which executes very late in the\nshutdown code path after the admin queue is destroyed and its tagset is\nremoved. So this change created the possibility of keep-alive sneaking in\nand interfering with the shutdown operation and causing observed kernel\ncrash.\n\nTo fix the observed crash, we decided to move nvme_stop_keep_alive() from\nnvme_uninit_ctrl() to nvme_remove_admin_tag_set(). This change would ensure\nthat we don't forward progress and delete the admin queue until the keep-\nalive operation is finished (if it's in-flight) or cancelled and that would\nhelp contain the race condition explained above and hence avoid the crash.\n\nMoving nvme_stop_keep_alive() to nvme_remove_admin_tag_set() instead of\nadding nvme_stop_keep_alive() to the beginning of the controller shutdown\ncode path in nvme_stop_ctrl(), as was the case earlier before commit\na54a93d0e359 (\"nvme: move stopping keep-alive into nvme_uninit_ctrl()\"),\nwould help save one callsite of nvme_stop_keep_alive()." |
| } |
| ], |
| "affected": [ |
| { |
| "product": "Linux", |
| "vendor": "Linux", |
| "defaultStatus": "unaffected", |
| "repo": "https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git", |
| "programFiles": [ |
| "drivers/nvme/host/core.c" |
| ], |
| "versions": [ |
| { |
| "version": "a54a93d0e3599b05856971734e15418ac551a14c", |
| "lessThan": "30794f4952decb2ec8efa42f704cac5304499a41", |
| "status": "affected", |
| "versionType": "git" |
| }, |
| { |
| "version": "a54a93d0e3599b05856971734e15418ac551a14c", |
| "lessThan": "5416b76a8156c1b8491f78f8a728f422104bb919", |
| "status": "affected", |
| "versionType": "git" |
| }, |
| { |
| "version": "a54a93d0e3599b05856971734e15418ac551a14c", |
| "lessThan": "e9869c85c81168a1275f909d5972a3fc435304be", |
| "status": "affected", |
| "versionType": "git" |
| }, |
| { |
| "version": "4101af98ab573554c4225e328d506fec2a74bc54", |
| "status": "affected", |
| "versionType": "git" |
| } |
| ] |
| }, |
| { |
| "product": "Linux", |
| "vendor": "Linux", |
| "defaultStatus": "affected", |
| "repo": "https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git", |
| "programFiles": [ |
| "drivers/nvme/host/core.c" |
| ], |
| "versions": [ |
| { |
| "version": "6.11", |
| "status": "affected" |
| }, |
| { |
| "version": "0", |
| "lessThan": "6.11", |
| "status": "unaffected", |
| "versionType": "semver" |
| }, |
| { |
| "version": "6.11.11", |
| "lessThanOrEqual": "6.11.*", |
| "status": "unaffected", |
| "versionType": "semver" |
| }, |
| { |
| "version": "6.12.2", |
| "lessThanOrEqual": "6.12.*", |
| "status": "unaffected", |
| "versionType": "semver" |
| }, |
| { |
| "version": "6.13", |
| "lessThanOrEqual": "*", |
| "status": "unaffected", |
| "versionType": "original_commit_for_fix" |
| } |
| ] |
| } |
| ], |
| "cpeApplicability": [ |
| { |
| "nodes": [ |
| { |
| "operator": "OR", |
| "negate": false, |
| "cpeMatch": [ |
| { |
| "vulnerable": true, |
| "criteria": "cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*", |
| "versionStartIncluding": "6.11", |
| "versionEndExcluding": "6.11.11" |
| }, |
| { |
| "vulnerable": true, |
| "criteria": "cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*", |
| "versionStartIncluding": "6.11", |
| "versionEndExcluding": "6.12.2" |
| }, |
| { |
| "vulnerable": true, |
| "criteria": "cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*", |
| "versionStartIncluding": "6.11", |
| "versionEndExcluding": "6.13" |
| }, |
| { |
| "vulnerable": true, |
| "criteria": "cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*", |
| "versionStartIncluding": "6.10.7" |
| } |
| ] |
| } |
| ] |
| } |
| ], |
| "references": [ |
| { |
| "url": "https://git.kernel.org/stable/c/30794f4952decb2ec8efa42f704cac5304499a41" |
| }, |
| { |
| "url": "https://git.kernel.org/stable/c/5416b76a8156c1b8491f78f8a728f422104bb919" |
| }, |
| { |
| "url": "https://git.kernel.org/stable/c/e9869c85c81168a1275f909d5972a3fc435304be" |
| } |
| ], |
| "title": "nvme-fabrics: fix kernel crash while shutting down controller", |
| "x_generator": { |
| "engine": "bippy-1.2.0" |
| } |
| } |
| }, |
| "cveMetadata": { |
| "assignerOrgId": "f4215fc3-5b6b-47ff-a258-f7189bd81038", |
| "cveID": "CVE-2024-53169", |
| "requesterUserId": "gregkh@kernel.org", |
| "serial": "1", |
| "state": "PUBLISHED" |
| }, |
| "dataType": "CVE_RECORD", |
| "dataVersion": "5.0" |
| } |
