nvme: code command_id with a genctr for use-after-free validation

We cannot detect a (perhaps buggy) controller that is sending us
a completion for a request that was already completed (for example
sending a completion twice), this phenomenon was seen in the wild
a few times.

So to protect against this, we use the upper 4 msbits of the nvme sqe
command_id to use as a 4-bit generation counter and verify it matches
the existing request generation that is incrementing on every execution.

The 16-bit command_id structure now is constructed by:
| xxxx | xxxxxxxxxxxx |
  gen    request tag

This means that we are giving up some possible queue depth as 12 bits
allow for a maximum queue depth of 4095 instead of 65536, however we
never create such long queues anyways so no real harm done.

Suggested-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Acked-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Tested-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>

1 files changed, 46 insertions, 1 deletions

diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index ab803f91ace1..57d2ac00a6bd 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -152,6 +152,7 @@ enum nvme_quirks {
 struct nvme_request {
 	struct nvme_command	*cmd;
 	union nvme_result	result;
+	u8			genctr;
 	u8			retries;
 	u8			flags;
 	u16			status;
@@ -491,6 +492,49 @@ struct nvme_ctrl_ops {
 	int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
 };
 
+/*
+ * nvme command_id is constructed as such:
+ * | xxxx | xxxxxxxxxxxx |
+ *   gen    request tag
+ */
+#define nvme_genctr_mask(gen)			(gen & 0xf)
+#define nvme_cid_install_genctr(gen)		(nvme_genctr_mask(gen) << 12)
+#define nvme_genctr_from_cid(cid)		((cid & 0xf000) >> 12)
+#define nvme_tag_from_cid(cid)			(cid & 0xfff)
+
+static inline u16 nvme_cid(struct request *rq)
+{
+	return nvme_cid_install_genctr(nvme_req(rq)->genctr) | rq->tag;
+}
+
+static inline struct request *nvme_find_rq(struct blk_mq_tags *tags,
+		u16 command_id)
+{
+	u8 genctr = nvme_genctr_from_cid(command_id);
+	u16 tag = nvme_tag_from_cid(command_id);
+	struct request *rq;
+
+	rq = blk_mq_tag_to_rq(tags, tag);
+	if (unlikely(!rq)) {
+		pr_err("could not locate request for tag %#x\n",
+			tag);
+		return NULL;
+	}
+	if (unlikely(nvme_genctr_mask(nvme_req(rq)->genctr) != genctr)) {
+		dev_err(nvme_req(rq)->ctrl->device,
+			"request %#x genctr mismatch (got %#x expected %#x)\n",
+			tag, genctr, nvme_genctr_mask(nvme_req(rq)->genctr));
+		return NULL;
+	}
+	return rq;
+}
+
+static inline struct request *nvme_cid_to_rq(struct blk_mq_tags *tags,
+                u16 command_id)
+{
+	return blk_mq_tag_to_rq(tags, nvme_tag_from_cid(command_id));
+}
+
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
 void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj,
 			    const char *dev_name);
@@ -588,7 +632,8 @@ static inline void nvme_put_ctrl(struct nvme_ctrl *ctrl)
 
 static inline bool nvme_is_aen_req(u16 qid, __u16 command_id)
 {
-	return !qid && command_id >= NVME_AQ_BLK_MQ_DEPTH;
+	return !qid &&
+		nvme_tag_from_cid(command_id) >= NVME_AQ_BLK_MQ_DEPTH;
 }
 
 void nvme_complete_rq(struct request *req);