Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:
 "vhost and virtio fixes and features:

   - Hardening work by Jason

   - vdpa driver for Alibaba ENI

   - Performance tweaks for virtio blk

   - virtio rng rework using an internal buffer

   - mac/mtu programming for mlx5 vdpa

   - Misc fixes, cleanups"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (45 commits)
  vdpa/mlx5: Forward only packets with allowed MAC address
  vdpa/mlx5: Support configuration of MAC
  vdpa/mlx5: Fix clearing of VIRTIO_NET_F_MAC feature bit
  vdpa_sim_net: Enable user to set mac address and mtu
  vdpa: Enable user to set mac and mtu of vdpa device
  vdpa: Use kernel coding style for structure comments
  vdpa: Introduce query of device config layout
  vdpa: Introduce and use vdpa device get, set config helpers
  virtio-scsi: don't let virtio core to validate used buffer length
  virtio-blk: don't let virtio core to validate used length
  virtio-net: don't let virtio core to validate used length
  virtio_ring: validate used buffer length
  virtio_blk: correct types for status handling
  virtio_blk: allow 0 as num_request_queues
  i2c: virtio: Add support for zero-length requests
  virtio-blk: fixup coccinelle warnings
  virtio_ring: fix typos in vring_desc_extra
  virtio-pci: harden INTX interrupts
  virtio_pci: harden MSI-X interrupts
  virtio_config: introduce a new .enable_cbs method
  ...

2 files changed, 170 insertions, 34 deletions

diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index 3163b313a470..daaf7b503677 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -63,7 +63,7 @@ struct mlx5_control_vq {
 	unsigned short head;
 };
 
-struct mlx5_ctrl_wq_ent {
+struct mlx5_vdpa_wq_ent {
 	struct work_struct work;
 	struct mlx5_vdpa_dev *mvdev;
 };
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 5c7d2a953dbd..63813fbb5f62 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -6,6 +6,7 @@
 #include <linux/vringh.h>
 #include <uapi/linux/virtio_net.h>
 #include <uapi/linux/virtio_ids.h>
+#include <uapi/linux/vdpa.h>
 #include <linux/virtio_config.h>
 #include <linux/auxiliary_bus.h>
 #include <linux/mlx5/cq.h>
@@ -157,10 +158,12 @@ struct mlx5_vdpa_net {
 	struct mutex reslock;
 	struct mlx5_flow_table *rxft;
 	struct mlx5_fc *rx_counter;
-	struct mlx5_flow_handle *rx_rule;
+	struct mlx5_flow_handle *rx_rule_ucast;
+	struct mlx5_flow_handle *rx_rule_mcast;
 	bool setup;
-	u16 mtu;
 	u32 cur_num_vqs;
+	struct notifier_block nb;
+	struct vdpa_callback config_cb;
 };
 
 static void free_resources(struct mlx5_vdpa_net *ndev);
@@ -1381,21 +1384,33 @@ static int add_fwd_to_tir(struct mlx5_vdpa_net *ndev)
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_act flow_act = {};
 	struct mlx5_flow_namespace *ns;
+	struct mlx5_flow_spec *spec;
+	void *headers_c;
+	void *headers_v;
+	u8 *dmac_c;
+	u8 *dmac_v;
 	int err;
 
-	/* for now, one entry, match all, forward to tir */
-	ft_attr.max_fte = 1;
-	ft_attr.autogroup.max_num_groups = 1;
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	ft_attr.max_fte = 2;
+	ft_attr.autogroup.max_num_groups = 2;
 
 	ns = mlx5_get_flow_namespace(ndev->mvdev.mdev, MLX5_FLOW_NAMESPACE_BYPASS);
 	if (!ns) {
-		mlx5_vdpa_warn(&ndev->mvdev, "get flow namespace\n");
-		return -EOPNOTSUPP;
+		mlx5_vdpa_warn(&ndev->mvdev, "failed to get flow namespace\n");
+		err = -EOPNOTSUPP;
+		goto err_ns;
 	}
 
 	ndev->rxft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
-	if (IS_ERR(ndev->rxft))
-		return PTR_ERR(ndev->rxft);
+	if (IS_ERR(ndev->rxft)) {
+		err = PTR_ERR(ndev->rxft);
+		goto err_ns;
+	}
 
 	ndev->rx_counter = mlx5_fc_create(ndev->mvdev.mdev, false);
 	if (IS_ERR(ndev->rx_counter)) {
@@ -1403,37 +1418,64 @@ static int add_fwd_to_tir(struct mlx5_vdpa_net *ndev)
 		goto err_fc;
 	}
 
+	headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, outer_headers);
+	dmac_c = MLX5_ADDR_OF(fte_match_param, headers_c, outer_headers.dmac_47_16);
+	memset(dmac_c, 0xff, ETH_ALEN);
+	headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers);
+	dmac_v = MLX5_ADDR_OF(fte_match_param, headers_v, outer_headers.dmac_47_16);
+	ether_addr_copy(dmac_v, ndev->config.mac);
+
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT;
 	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_TIR;
 	dest[0].tir_num = ndev->res.tirn;
 	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
 	dest[1].counter_id = mlx5_fc_id(ndev->rx_counter);
-	ndev->rx_rule = mlx5_add_flow_rules(ndev->rxft, NULL, &flow_act, dest, 2);
-	if (IS_ERR(ndev->rx_rule)) {
-		err = PTR_ERR(ndev->rx_rule);
-		ndev->rx_rule = NULL;
-		goto err_rule;
+	ndev->rx_rule_ucast = mlx5_add_flow_rules(ndev->rxft, spec, &flow_act, dest, 2);
+
+	if (IS_ERR(ndev->rx_rule_ucast)) {
+		err = PTR_ERR(ndev->rx_rule_ucast);
+		ndev->rx_rule_ucast = NULL;
+		goto err_rule_ucast;
 	}
 
+	memset(dmac_c, 0, ETH_ALEN);
+	memset(dmac_v, 0, ETH_ALEN);
+	dmac_c[0] = 1;
+	dmac_v[0] = 1;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	ndev->rx_rule_mcast = mlx5_add_flow_rules(ndev->rxft, spec, &flow_act, dest, 1);
+	if (IS_ERR(ndev->rx_rule_mcast)) {
+		err = PTR_ERR(ndev->rx_rule_mcast);
+		ndev->rx_rule_mcast = NULL;
+		goto err_rule_mcast;
+	}
+
+	kvfree(spec);
 	return 0;
 
-err_rule:
+err_rule_mcast:
+	mlx5_del_flow_rules(ndev->rx_rule_ucast);
+	ndev->rx_rule_ucast = NULL;
+err_rule_ucast:
 	mlx5_fc_destroy(ndev->mvdev.mdev, ndev->rx_counter);
 err_fc:
 	mlx5_destroy_flow_table(ndev->rxft);
+err_ns:
+	kvfree(spec);
 	return err;
 }
 
 static void remove_fwd_to_tir(struct mlx5_vdpa_net *ndev)
 {
-	if (!ndev->rx_rule)
+	if (!ndev->rx_rule_ucast)
 		return;
 
-	mlx5_del_flow_rules(ndev->rx_rule);
+	mlx5_del_flow_rules(ndev->rx_rule_mcast);
+	ndev->rx_rule_mcast = NULL;
+	mlx5_del_flow_rules(ndev->rx_rule_ucast);
+	ndev->rx_rule_ucast = NULL;
 	mlx5_fc_destroy(ndev->mvdev.mdev, ndev->rx_counter);
 	mlx5_destroy_flow_table(ndev->rxft);
-
-	ndev->rx_rule = NULL;
 }
 
 static virtio_net_ctrl_ack handle_ctrl_mac(struct mlx5_vdpa_dev *mvdev, u8 cmd)
@@ -1557,14 +1599,14 @@ static void mlx5_cvq_kick_handler(struct work_struct *work)
 {
 	virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
 	struct virtio_net_ctrl_hdr ctrl;
-	struct mlx5_ctrl_wq_ent *wqent;
+	struct mlx5_vdpa_wq_ent *wqent;
 	struct mlx5_vdpa_dev *mvdev;
 	struct mlx5_control_vq *cvq;
 	struct mlx5_vdpa_net *ndev;
 	size_t read, write;
 	int err;
 
-	wqent = container_of(work, struct mlx5_ctrl_wq_ent, work);
+	wqent = container_of(work, struct mlx5_vdpa_wq_ent, work);
 	mvdev = wqent->mvdev;
 	ndev = to_mlx5_vdpa_ndev(mvdev);
 	cvq = &mvdev->cvq;
@@ -1616,7 +1658,7 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx)
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
 	struct mlx5_vdpa_virtqueue *mvq;
-	struct mlx5_ctrl_wq_ent *wqent;
+	struct mlx5_vdpa_wq_ent *wqent;
 
 	if (!is_index_valid(mvdev, idx))
 		return;
@@ -1852,6 +1894,7 @@ static u64 mlx5_vdpa_get_features(struct vdpa_device *vdev)
 	ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_CTRL_VQ);
 	ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR);
 	ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_MQ);
+	ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_STATUS);
 
 	print_features(mvdev, ndev->mvdev.mlx_features, false);
 	return ndev->mvdev.mlx_features;
@@ -1942,16 +1985,16 @@ static int mlx5_vdpa_set_features(struct vdpa_device *vdev, u64 features)
 		return err;
 
 	ndev->mvdev.actual_features = features & ndev->mvdev.mlx_features;
-	ndev->config.mtu = cpu_to_mlx5vdpa16(mvdev, ndev->mtu);
-	ndev->config.status |= cpu_to_mlx5vdpa16(mvdev, VIRTIO_NET_S_LINK_UP);
 	update_cvq_info(mvdev);
 	return err;
 }
 
 static void mlx5_vdpa_set_config_cb(struct vdpa_device *vdev, struct vdpa_callback *cb)
 {
-	/* not implemented */
-	mlx5_vdpa_warn(to_mvdev(vdev), "set config callback not supported\n");
+	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+
+	ndev->config_cb = *cb;
 }
 
 #define MLX5_VDPA_MAX_VQ_ENTRIES 256
@@ -2192,7 +2235,6 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
 	clear_vqs_ready(ndev);
 	mlx5_vdpa_destroy_mr(&ndev->mvdev);
 	ndev->mvdev.status = 0;
-	ndev->mvdev.mlx_features = 0;
 	memset(ndev->event_cbs, 0, sizeof(ndev->event_cbs));
 	ndev->mvdev.actual_features = 0;
 	++mvdev->generation;
@@ -2404,7 +2446,84 @@ struct mlx5_vdpa_mgmtdev {
 	struct mlx5_vdpa_net *ndev;
 };
 
-static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name)
+static u8 query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport)
+{
+	u32 out[MLX5_ST_SZ_DW(query_vport_state_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_vport_state_in)] = {};
+	int err;
+
+	MLX5_SET(query_vport_state_in, in, opcode, MLX5_CMD_OP_QUERY_VPORT_STATE);
+	MLX5_SET(query_vport_state_in, in, op_mod, opmod);
+	MLX5_SET(query_vport_state_in, in, vport_number, vport);
+	if (vport)
+		MLX5_SET(query_vport_state_in, in, other_vport, 1);
+
+	err = mlx5_cmd_exec_inout(mdev, query_vport_state, in, out);
+	if (err)
+		return 0;
+
+	return MLX5_GET(query_vport_state_out, out, state);
+}
+
+static bool get_link_state(struct mlx5_vdpa_dev *mvdev)
+{
+	if (query_vport_state(mvdev->mdev, MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT, 0) ==
+	    VPORT_STATE_UP)
+		return true;
+
+	return false;
+}
+
+static void update_carrier(struct work_struct *work)
+{
+	struct mlx5_vdpa_wq_ent *wqent;
+	struct mlx5_vdpa_dev *mvdev;
+	struct mlx5_vdpa_net *ndev;
+
+	wqent = container_of(work, struct mlx5_vdpa_wq_ent, work);
+	mvdev = wqent->mvdev;
+	ndev = to_mlx5_vdpa_ndev(mvdev);
+	if (get_link_state(mvdev))
+		ndev->config.status |= cpu_to_mlx5vdpa16(mvdev, VIRTIO_NET_S_LINK_UP);
+	else
+		ndev->config.status &= cpu_to_mlx5vdpa16(mvdev, ~VIRTIO_NET_S_LINK_UP);
+
+	if (ndev->config_cb.callback)
+		ndev->config_cb.callback(ndev->config_cb.private);
+
+	kfree(wqent);
+}
+
+static int event_handler(struct notifier_block *nb, unsigned long event, void *param)
+{
+	struct mlx5_vdpa_net *ndev = container_of(nb, struct mlx5_vdpa_net, nb);
+	struct mlx5_eqe *eqe = param;
+	int ret = NOTIFY_DONE;
+	struct mlx5_vdpa_wq_ent *wqent;
+
+	if (event == MLX5_EVENT_TYPE_PORT_CHANGE) {
+		switch (eqe->sub_type) {
+		case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+		case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
+			wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC);
+			if (!wqent)
+				return NOTIFY_DONE;
+
+			wqent->mvdev = &ndev->mvdev;
+			INIT_WORK(&wqent->work, update_carrier);
+			queue_work(ndev->mvdev.wq, &wqent->work);
+			ret = NOTIFY_OK;
+			break;
+		default:
+			return NOTIFY_DONE;
+		}
+		return ret;
+	}
+	return ret;
+}
+
+static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
+			     const struct vdpa_dev_set_config *add_config)
 {
 	struct mlx5_vdpa_mgmtdev *mgtdev = container_of(v_mdev, struct mlx5_vdpa_mgmtdev, mgtdev);
 	struct virtio_net_config *config;
@@ -2413,6 +2532,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name)
 	struct mlx5_vdpa_net *ndev;
 	struct mlx5_core_dev *mdev;
 	u32 max_vqs;
+	u16 mtu;
 	int err;
 
 	if (mgtdev->ndev)
@@ -2440,13 +2560,24 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name)
 	init_mvqs(ndev);
 	mutex_init(&ndev->reslock);
 	config = &ndev->config;
-	err = query_mtu(mdev, &ndev->mtu);
+	err = query_mtu(mdev, &mtu);
 	if (err)
 		goto err_mtu;
 
-	err = mlx5_query_nic_vport_mac_address(mdev, 0, 0, config->mac);
-	if (err)
-		goto err_mtu;
+	ndev->config.mtu = cpu_to_mlx5vdpa16(mvdev, mtu);
+
+	if (get_link_state(mvdev))
+		ndev->config.status |= cpu_to_mlx5vdpa16(mvdev, VIRTIO_NET_S_LINK_UP);
+	else
+		ndev->config.status &= cpu_to_mlx5vdpa16(mvdev, ~VIRTIO_NET_S_LINK_UP);
+
+	if (add_config->mask & (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR)) {
+		memcpy(ndev->config.mac, add_config->net.mac, ETH_ALEN);
+	} else {
+		err = mlx5_query_nic_vport_mac_address(mdev, 0, 0, config->mac);
+		if (err)
+			goto err_mtu;
+	}
 
 	if (!is_zero_ether_addr(config->mac)) {
 		pfmdev = pci_get_drvdata(pci_physfn(mdev->pdev));
@@ -2473,12 +2604,14 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name)
 	if (err)
 		goto err_mr;
 
-	mvdev->wq = create_singlethread_workqueue("mlx5_vdpa_ctrl_wq");
+	mvdev->wq = create_singlethread_workqueue("mlx5_vdpa_wq");
 	if (!mvdev->wq) {
 		err = -ENOMEM;
 		goto err_res2;
 	}
 
+	ndev->nb.notifier_call = event_handler;
+	mlx5_notifier_register(mdev, &ndev->nb);
 	ndev->cur_num_vqs = 2 * mlx5_vdpa_max_qps(max_vqs);
 	mvdev->vdev.mdev = &mgtdev->mgtdev;
 	err = _vdpa_register_device(&mvdev->vdev, ndev->cur_num_vqs + 1);
@@ -2509,7 +2642,9 @@ static void mlx5_vdpa_dev_del(struct vdpa_mgmt_dev *v_mdev, struct vdpa_device *
 {
 	struct mlx5_vdpa_mgmtdev *mgtdev = container_of(v_mdev, struct mlx5_vdpa_mgmtdev, mgtdev);
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(dev);
+	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
 
+	mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
 	destroy_workqueue(mvdev->wq);
 	_vdpa_unregister_device(dev);
 	mgtdev->ndev = NULL;
@@ -2541,6 +2676,7 @@ static int mlx5v_probe(struct auxiliary_device *adev,
 	mgtdev->mgtdev.ops = &mdev_ops;
 	mgtdev->mgtdev.device = mdev->device;
 	mgtdev->mgtdev.id_table = id_table;
+	mgtdev->mgtdev.config_attr_mask = (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR);
 	mgtdev->madev = madev;
 
 	err = vdpa_mgmtdev_register(&mgtdev->mgtdev);