nvme-pci: use sgls for all user requests if possible

If the device supports SGLs, use these for all user requests. This
format encodes the expected transfer length so it can catch short buffer
errors in a user command, whether it occurred accidently or maliciously.

For controllers that support SGL data mode, this is a viable mitigation
to CVE-2023-6238. For controllers that don't support SGLs, log a warning
in the passthrough path since not having the capability can corrupt
data if the interface is not used correctly.

Reviewed-by: Christoph Hellwig <[email protected]>
Signed-off-by: Keith Busch <[email protected]>

Author: keithbusch

drivers/nvme/host/ioctl.c

@@ -120,12 +120,20 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 	struct nvme_ns *ns = q->queuedata;
 	struct block_device *bdev = ns ? ns->disk->part0 : NULL;
 	bool supports_metadata = bdev && blk_get_integrity(bdev->bd_disk);
+	struct nvme_ctrl *ctrl = nvme_req(req)->ctrl;
 	bool has_metadata = meta_buffer && meta_len;
 	struct bio *bio = NULL;
 	int ret;
 
-	if (has_metadata && !supports_metadata)
-		return -EINVAL;
+	if (!nvme_ctrl_sgl_supported(ctrl))
+		dev_warn_once(ctrl->device, "using unchecked data buffer\n");
+	if (has_metadata) {
+		if (!supports_metadata)
+			return -EINVAL;
+		if (!nvme_ctrl_meta_sgl_supported(ctrl))
+			dev_warn_once(ctrl->device,
+				      "using unchecked metadata buffer\n");
+	}
 
 	if (ioucmd && (ioucmd->flags & IORING_URING_CMD_FIXED)) {
 		struct iov_iter iter;

drivers/nvme/host/pci.c

@@ -515,7 +515,8 @@ static inline bool nvme_pci_metadata_use_sgls(struct nvme_dev *dev,
 {
 	if (!nvme_ctrl_meta_sgl_supported(&dev->ctrl))
 		return false;
-	return req->nr_integrity_segments > 1;
+	return req->nr_integrity_segments > 1 ||
+		nvme_req(req)->flags & NVME_REQ_USERCMD;
 }
 
 static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req,
@@ -533,7 +534,7 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req,
 	if (nvme_pci_metadata_use_sgls(dev, req))
 		return true;
 	if (!sgl_threshold || avg_seg_size < sgl_threshold)
-		return false;
+		return nvme_req(req)->flags & NVME_REQ_USERCMD;
 	return true;
 }