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: <20240816090159.1967650-5-dtatulea@nvidia.com>
Date: Fri, 16 Aug 2024 12:01:53 +0300
From: Dragos Tatulea <dtatulea@...dia.com>
To: "Michael S . Tsirkin" <mst@...hat.com>, Jason Wang <jasowang@...hat.com>,
	Eugenio Perez Martin <eperezma@...hat.com>,
	<virtualization@...ts.linux-foundation.org>
CC: Dragos Tatulea <dtatulea@...dia.com>, Si-Wei Liu <si-wei.liu@...cle.com>,
	Saeed Mahameed <saeedm@...dia.com>, Leon Romanovsky <leon@...nel.org>,
	<kvm@...r.kernel.org>, <linux-kernel@...r.kernel.org>, Gal Pressman
	<gal@...dia.com>, Parav Pandit <parav@...dia.com>, Xuan Zhuo
	<xuanzhuo@...ux.alibaba.com>, Tariq Toukan <tariqt@...dia.com>
Subject: [PATCH vhost v2 04/10] vdpa/mlx5: Use async API for vq query command

Switch firmware vq query command to be issued via the async API to
allow future parallelization.

For now the command is still serial but the infrastructure is there
to issue commands in parallel, including ratelimiting the number
of issued async commands to firmware.

A later patch will switch to issuing more commands at a time.

Signed-off-by: Dragos Tatulea <dtatulea@...dia.com>
Reviewed-by: Tariq Toukan <tariqt@...dia.com>
---
 drivers/vdpa/mlx5/core/mlx5_vdpa.h |   2 +
 drivers/vdpa/mlx5/net/mlx5_vnet.c  | 101 ++++++++++++++++++++++-------
 2 files changed, 78 insertions(+), 25 deletions(-)

diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index b34e9b93d56e..24fa00afb24f 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -103,6 +103,8 @@ struct mlx5_vdpa_dev {
 	struct workqueue_struct *wq;
 	unsigned int group2asid[MLX5_VDPA_NUMVQ_GROUPS];
 	bool suspended;
+
+	struct mlx5_async_ctx async_ctx;
 };
 
 struct mlx5_vdpa_async_cmd {
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 12133e5d1285..413b24398ef2 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1184,40 +1184,87 @@ struct mlx5_virtq_attr {
 	u16 used_index;
 };
 
-static int query_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq,
-			   struct mlx5_virtq_attr *attr)
-{
-	int outlen = MLX5_ST_SZ_BYTES(query_virtio_net_q_out);
-	u32 in[MLX5_ST_SZ_DW(query_virtio_net_q_in)] = {};
-	void *out;
-	void *obj_context;
-	void *cmd_hdr;
-	int err;
-
-	out = kzalloc(outlen, GFP_KERNEL);
-	if (!out)
-		return -ENOMEM;
+struct mlx5_virtqueue_query_mem {
+	u8 in[MLX5_ST_SZ_BYTES(query_virtio_net_q_in)];
+	u8 out[MLX5_ST_SZ_BYTES(query_virtio_net_q_out)];
+};
 
-	cmd_hdr = MLX5_ADDR_OF(query_virtio_net_q_in, in, general_obj_in_cmd_hdr);
+static void fill_query_virtqueue_cmd(struct mlx5_vdpa_net *ndev,
+				     struct mlx5_vdpa_virtqueue *mvq,
+				     struct mlx5_virtqueue_query_mem *cmd)
+{
+	void *cmd_hdr = MLX5_ADDR_OF(query_virtio_net_q_in, cmd->in, general_obj_in_cmd_hdr);
 
 	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, opcode, MLX5_CMD_OP_QUERY_GENERAL_OBJECT);
 	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_type, MLX5_OBJ_TYPE_VIRTIO_NET_Q);
 	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_id, mvq->virtq_id);
 	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid);
-	err = mlx5_cmd_exec(ndev->mvdev.mdev, in, sizeof(in), out, outlen);
-	if (err)
-		goto err_cmd;
+}
+
+static void query_virtqueue_end(struct mlx5_vdpa_net *ndev,
+				struct mlx5_virtqueue_query_mem *cmd,
+				struct mlx5_virtq_attr *attr)
+{
+	void *obj_context = MLX5_ADDR_OF(query_virtio_net_q_out, cmd->out, obj_context);
 
-	obj_context = MLX5_ADDR_OF(query_virtio_net_q_out, out, obj_context);
 	memset(attr, 0, sizeof(*attr));
 	attr->state = MLX5_GET(virtio_net_q_object, obj_context, state);
 	attr->available_index = MLX5_GET(virtio_net_q_object, obj_context, hw_available_index);
 	attr->used_index = MLX5_GET(virtio_net_q_object, obj_context, hw_used_index);
-	kfree(out);
-	return 0;
+}
 
-err_cmd:
-	kfree(out);
+static int query_virtqueues(struct mlx5_vdpa_net *ndev,
+			    int start_vq,
+			    int num_vqs,
+			    struct mlx5_virtq_attr *attrs)
+{
+	struct mlx5_vdpa_dev *mvdev = &ndev->mvdev;
+	struct mlx5_virtqueue_query_mem *cmd_mem;
+	struct mlx5_vdpa_async_cmd *cmds;
+	int err = 0;
+
+	WARN(start_vq + num_vqs > mvdev->max_vqs, "query vq range invalid [%d, %d), max_vqs: %u\n",
+	     start_vq, start_vq + num_vqs, mvdev->max_vqs);
+
+	cmds = kvcalloc(num_vqs, sizeof(*cmds), GFP_KERNEL);
+	cmd_mem = kvcalloc(num_vqs, sizeof(*cmd_mem), GFP_KERNEL);
+	if (!cmds || !cmd_mem) {
+		err = -ENOMEM;
+		goto done;
+	}
+
+	for (int i = 0; i < num_vqs; i++) {
+		cmds[i].in = &cmd_mem[i].in;
+		cmds[i].inlen = sizeof(cmd_mem[i].in);
+		cmds[i].out = &cmd_mem[i].out;
+		cmds[i].outlen = sizeof(cmd_mem[i].out);
+		fill_query_virtqueue_cmd(ndev, &ndev->vqs[start_vq + i], &cmd_mem[i]);
+	}
+
+	err = mlx5_vdpa_exec_async_cmds(&ndev->mvdev, cmds, num_vqs);
+	if (err) {
+		mlx5_vdpa_err(mvdev, "error issuing query cmd for vq range [%d, %d): %d\n",
+			      start_vq, start_vq + num_vqs, err);
+		goto done;
+	}
+
+	for (int i = 0; i < num_vqs; i++) {
+		struct mlx5_vdpa_async_cmd *cmd = &cmds[i];
+		int vq_idx = start_vq + i;
+
+		if (cmd->err) {
+			mlx5_vdpa_err(mvdev, "query vq %d failed, err: %d\n", vq_idx, err);
+			if (!err)
+				err = cmd->err;
+			continue;
+		}
+
+		query_virtqueue_end(ndev, &cmd_mem[i], &attrs[i]);
+	}
+
+done:
+	kvfree(cmd_mem);
+	kvfree(cmds);
 	return err;
 }
 
@@ -1542,7 +1589,7 @@ static int suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mv
 		return err;
 	}
 
-	err = query_virtqueue(ndev, mvq, &attr);
+	err = query_virtqueues(ndev, mvq->index, 1, &attr);
 	if (err) {
 		mlx5_vdpa_err(&ndev->mvdev, "failed to query virtqueue, err: %d\n", err);
 		return err;
@@ -2528,7 +2575,7 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa
 		return 0;
 	}
 
-	err = query_virtqueue(ndev, mvq, &attr);
+	err = query_virtqueues(ndev, mvq->index, 1, &attr);
 	if (err) {
 		mlx5_vdpa_err(mvdev, "failed to query virtqueue\n");
 		return err;
@@ -2879,7 +2926,7 @@ static int save_channel_info(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqu
 	int err;
 
 	if (mvq->initialized) {
-		err = query_virtqueue(ndev, mvq, &attr);
+		err = query_virtqueues(ndev, mvq->index, 1, &attr);
 		if (err)
 			return err;
 	}
@@ -3854,6 +3901,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 		ndev->rqt_size = 1;
 	}
 
+	mlx5_cmd_init_async_ctx(mdev, &mvdev->async_ctx);
+
 	ndev->mvdev.mlx_features = device_features;
 	mvdev->vdev.dma_dev = &mdev->pdev->dev;
 	err = mlx5_vdpa_alloc_resources(&ndev->mvdev);
@@ -3935,6 +3984,8 @@ static void mlx5_vdpa_dev_del(struct vdpa_mgmt_dev *v_mdev, struct vdpa_device *
 	mvdev->wq = NULL;
 	destroy_workqueue(wq);
 	mgtdev->ndev = NULL;
+
+	mlx5_cmd_cleanup_async_ctx(&mvdev->async_ctx);
 }
 
 static const struct vdpa_mgmtdev_ops mdev_ops = {
-- 
2.45.1


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ