diff options
| author | Lalithambika Krishnakumar <lalithambika.krishnakumar@intel.com> | 2020-12-24 01:09:00 +0300 |
|---|---|---|
| committer | Christoph Hellwig <hch@lst.de> | 2021-01-06 12:30:37 +0300 |
| commit | 62df80165d7f197c9c0652e7416164f294a96661 (patch) | |
| tree | 9d613daac28ccc1da9bcfc7e581293b7a9c3c3c5 /drivers/nvme/host | |
| parent | 5c11f7d9f843bdd24cd29b95401938bc3f168070 (diff) | |
| download | linux-62df80165d7f197c9c0652e7416164f294a96661.tar.xz | |
nvme: avoid possible double fetch in handling CQE
While handling the completion queue, keep a local copy of the command id
from the DMA-accessible completion entry. This silences a time-of-check
to time-of-use (TOCTOU) warning from KF/x[1], with respect to a
Thunderclap[2] vulnerability analysis. The double-read impact appears
benign.
There may be a theoretical window for @command_id to be used as an
adversary-controlled array-index-value for mounting a speculative
execution attack, but that mitigation is saved for a potential follow-on.
A man-in-the-middle attack on the data payload is out of scope for this
analysis and is hopefully mitigated by filesystem integrity mechanisms.
[1] https://github.com/intel/kernel-fuzzer-for-xen-project
[2] http://thunderclap.io/thunderclap-paper-ndss2019.pdf
Signed-off-by: Lalithambika Krishna Kumar <lalithambika.krishnakumar@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Diffstat (limited to 'drivers/nvme/host')
| -rw-r--r-- | drivers/nvme/host/pci.c | 7 |
1 files changed, 4 insertions, 3 deletions
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 553871e6962b..50d9a20568a2 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -967,6 +967,7 @@ static inline struct blk_mq_tags *nvme_queue_tagset(struct nvme_queue *nvmeq) static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) { struct nvme_completion *cqe = &nvmeq->cqes[idx]; + __u16 command_id = READ_ONCE(cqe->command_id); struct request *req; /* @@ -975,17 +976,17 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) * aborts. We don't even bother to allocate a struct request * for them but rather special case them here. */ - if (unlikely(nvme_is_aen_req(nvmeq->qid, cqe->command_id))) { + if (unlikely(nvme_is_aen_req(nvmeq->qid, command_id))) { nvme_complete_async_event(&nvmeq->dev->ctrl, cqe->status, &cqe->result); return; } - req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), cqe->command_id); + req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), command_id); if (unlikely(!req)) { dev_warn(nvmeq->dev->ctrl.device, "invalid id %d completed on queue %d\n", - cqe->command_id, le16_to_cpu(cqe->sq_id)); + command_id, le16_to_cpu(cqe->sq_id)); return; } |