vfio/mlx5: Align the page tracking max message size with the device c…

…apability

Align the page tracking maximum message size with the device's
capability instead of relying on PAGE_SIZE.

This adjustment resolves a mismatch on systems where PAGE_SIZE is 64K,
but the firmware only supports a maximum message size of 4K.

Now that we rely on the device's capability for max_message_size, we
must account for potential future increases in its value.

Key considerations include:
- Supporting message sizes that exceed a single system page (e.g., an 8K
  message on a 4K system).
- Ensuring the RQ size is adjusted to accommodate at least 4
  WQEs/messages, in line with the device specification.

The above has been addressed as part of the patch.

Fixes: 79c3cf2 ("vfio/mlx5: Init QP based resources for dirty tracking")
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Tested-by: Yingshun Cui <yicui@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20241205122654.235619-1-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

drivers/vfio/pci/mlx5/cmd.c

@@ -1517,7 +1517,8 @@ int mlx5vf_start_page_tracker(struct vfio_device *vdev,
 	struct mlx5_vhca_qp *host_qp;
 	struct mlx5_vhca_qp *fw_qp;
 	struct mlx5_core_dev *mdev;
-	u32 max_msg_size = PAGE_SIZE;
+	u32 log_max_msg_size;
+	u32 max_msg_size;
 	u64 rq_size = SZ_2M;
 	u32 max_recv_wr;
 	int err;
@@ -1534,6 +1535,12 @@ int mlx5vf_start_page_tracker(struct vfio_device *vdev,
 	}
 
 	mdev = mvdev->mdev;
+	log_max_msg_size = MLX5_CAP_ADV_VIRTUALIZATION(mdev, pg_track_log_max_msg_size);
+	max_msg_size = (1ULL << log_max_msg_size);
+	/* The RQ must hold at least 4 WQEs/messages for successful QP creation */
+	if (rq_size < 4 * max_msg_size)
+		rq_size = 4 * max_msg_size;
+
 	memset(tracker, 0, sizeof(*tracker));
 	tracker->uar = mlx5_get_uars_page(mdev);
 	if (IS_ERR(tracker->uar)) {
@@ -1623,25 +1630,41 @@ set_report_output(u32 size, int index, struct mlx5_vhca_qp *qp,
 {
 	u32 entry_size = MLX5_ST_SZ_BYTES(page_track_report_entry);
 	u32 nent = size / entry_size;
+	u32 nent_in_page;
+	u32 nent_to_set;
 	struct page *page;
+	u32 page_offset;
+	u32 page_index;
+	u32 buf_offset;
+	void *kaddr;
 	u64 addr;
 	u64 *buf;
 	int i;
 
-	if (WARN_ON(index >= qp->recv_buf.npages ||
+	buf_offset = index * qp->max_msg_size;
+	if (WARN_ON(buf_offset + size >= qp->recv_buf.npages * PAGE_SIZE ||
 		    (nent > qp->max_msg_size / entry_size)))
 		return;
 
-	page = qp->recv_buf.page_list[index];
-	buf = kmap_local_page(page);
-	for (i = 0; i < nent; i++) {
-		addr = MLX5_GET(page_track_report_entry, buf + i,
-				dirty_address_low);
-		addr |= (u64)MLX5_GET(page_track_report_entry, buf + i,
-				      dirty_address_high) << 32;
-		iova_bitmap_set(dirty, addr, qp->tracked_page_size);
-	}
-	kunmap_local(buf);
+	do {
+		page_index = buf_offset / PAGE_SIZE;
+		page_offset = buf_offset % PAGE_SIZE;
+		nent_in_page = (PAGE_SIZE - page_offset) / entry_size;
+		page = qp->recv_buf.page_list[page_index];
+		kaddr = kmap_local_page(page);
+		buf = kaddr + page_offset;
+		nent_to_set = min(nent, nent_in_page);
+		for (i = 0; i < nent_to_set; i++) {
+			addr = MLX5_GET(page_track_report_entry, buf + i,
+					dirty_address_low);
+			addr |= (u64)MLX5_GET(page_track_report_entry, buf + i,
+					      dirty_address_high) << 32;
+			iova_bitmap_set(dirty, addr, qp->tracked_page_size);
+		}
+		kunmap_local(kaddr);
+		buf_offset += (nent_to_set * entry_size);
+		nent -= nent_to_set;
+	} while (nent);
 }
 
 static void