[PATCH 5.10 086/152] nvme: avoid possible double fetch in handling CQE

From: Greg Kroah-Hartman
Date: Mon Jan 18 2021 - 09:31:14 EST

From: Lalithambika Krishnakumar <lalithambika.krishnakumar@xxxxxxxxx>

[ Upstream commit 62df80165d7f197c9c0652e7416164f294a96661 ]

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

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@xxxxxxxxx>
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
drivers/nvme/host/pci.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 143f16a9f8d7e..a89d74c5cd1a7 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))) {
cqe->status, &cqe->result);

- 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)) {
"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));