linux-kernel - [PATCH vhost v4 12/15] vdpa/mlx5: Mark vq state for modification in hw vq

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20231219180858.120898-13-dtatulea@nvidia.com>
Date: Tue, 19 Dec 2023 20:08:55 +0200
From: Dragos Tatulea <dtatulea@...dia.com>
To: "Michael S . Tsirkin" <mst@...hat.com>, Jason Wang <jasowang@...hat.com>,
	Eugenio Perez Martin <eperezma@...hat.com>, Si-Wei Liu
	<si-wei.liu@...cle.com>, Saeed Mahameed <saeedm@...dia.com>, Leon Romanovsky
	<leon@...nel.org>, <virtualization@...ts.linux-foundation.org>, Gal Pressman
	<gal@...dia.com>
CC: Dragos Tatulea <dtatulea@...dia.com>, <kvm@...r.kernel.org>,
	<linux-kernel@...r.kernel.org>, Parav Pandit <parav@...dia.com>, Xuan Zhuo
	<xuanzhuo@...ux.alibaba.com>
Subject: [PATCH vhost v4 12/15] vdpa/mlx5: Mark vq state for modification in hw vq

.set_vq_state will set the indices and mark the fields to be modified in
the hw vq.

Advertise that the device supports changing the vq state when the device
is in DRIVER_OK state and suspended.

Reviewed-by: Gal Pressman <gal@...dia.com>
Signed-off-by: Dragos Tatulea <dtatulea@...dia.com>
---
 drivers/vdpa/mlx5/net/mlx5_vnet.c  | 11 ++++++++++-
 include/linux/mlx5/mlx5_ifc_vdpa.h |  2 ++
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 93812683c88c..b760005e2920 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1249,6 +1249,12 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 		MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr);
 	}
 
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX)
+		MLX5_SET(virtio_net_q_object, obj_context, hw_available_index, mvq->avail_idx);
+
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX)
+		MLX5_SET(virtio_net_q_object, obj_context, hw_used_index, mvq->used_idx);
+
 	MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select, mvq->modified_fields);
 	err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
 	if (err)
@@ -2328,6 +2334,8 @@ static int mlx5_vdpa_set_vq_state(struct vdpa_device *vdev, u16 idx,
 
 	mvq->used_idx = state->split.avail_index;
 	mvq->avail_idx = state->split.avail_index;
+	mvq->modified_fields |= MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX |
+				MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX;
 	return 0;
 }
 
@@ -2639,7 +2647,8 @@ static u64 mlx5_vdpa_get_backend_features(const struct vdpa_device *vdpa)
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdpa);
 
 	if (MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, freeze_to_rdy_supported))
-		features |= BIT_ULL(VHOST_BACKEND_F_CHANGEABLE_VQ_ADDR_IN_SUSPEND);
+		features |= BIT_ULL(VHOST_BACKEND_F_CHANGEABLE_VQ_ADDR_IN_SUSPEND) |
+			    BIT_ULL(VHOST_BACKEND_F_CHANGEABLE_VQ_STATE_IN_SUSPEND);
 
 	return features;
 }
diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h
index 9594ac405740..32e712106e68 100644
--- a/include/linux/mlx5/mlx5_ifc_vdpa.h
+++ b/include/linux/mlx5/mlx5_ifc_vdpa.h
@@ -146,6 +146,8 @@ enum {
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_PARAMS      = (u64)1 << 3,
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_DUMP_ENABLE = (u64)1 << 4,
 	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS           = (u64)1 << 6,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX       = (u64)1 << 7,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX        = (u64)1 << 8,
 	MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY          = (u64)1 << 14,
 };
 
-- 
2.43.0