virtio: fixes, features

9k mtu perf improvements
 vdpa feature provisioning
 virtio blk SECURE ERASE support
 
 Fixes, cleanups all over the place.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmNAvcMPHG1zdEByZWRo
 YXQuY29tAAoJECgfDbjSjVRpYaMH/0hv6q1D35lLinVn4DSz8ru754picK9Pg8Vv
 dJG8w0v3VN1lHLBQ63Gj9/M47odCq8JeeDwmkzVs3C2I3pwLdcO1Yd+fkqGVP7gd
 Fc7cyi87sk4heHEm6K5jC17gf3k39rS9BkFbYFyPQzr/+6HXx6O/6x7StxvY9EB0
 nst7yjPxKXptF5Sf3uUFk4YIFxSvkmvV292sLrWvkaMjn71oJXqsr8yNCFcqv/jk
 KM7C8ZCRuydatM+PEuJPcveJd04jYuoNS3OZDCCWD6XuzLROQ10PbLBBqoHLEWu7
 wZbY4WndJSqnRE3dx0Xm8LgKNPOBxVfDoD3RVejxW6JF9hmGcG8=
 =PIpt
 -----END PGP SIGNATURE-----

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

Pull virtio updates from Michael Tsirkin:

 - 9k mtu perf improvements

 - vdpa feature provisioning

 - virtio blk SECURE ERASE support

 - fixes and cleanups all over the place

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio_pci: don't try to use intxif pin is zero
  vDPA: conditionally read MTU and MAC in dev cfg space
  vDPA: fix spars cast warning in vdpa_dev_net_mq_config_fill
  vDPA: check virtio device features to detect MQ
  vDPA: check VIRTIO_NET_F_RSS for max_virtqueue_paris's presence
  vDPA: only report driver features if FEATURES_OK is set
  vDPA: allow userspace to query features of a vDPA device
  virtio_blk: add SECURE ERASE command support
  vp_vdpa: support feature provisioning
  vdpa_sim_net: support feature provisioning
  vdpa: device feature provisioning
  virtio-net: use mtu size as buffer length for big packets
  virtio-net: introduce and use helper function for guest gso support checks
  virtio: drop vp_legacy_set_queue_size
  virtio_ring: make vring_alloc_queue_packed prettier
  virtio_ring: split: Operators use unified style
  vhost: add __init/__exit annotations to module init/exit funcs

drivers/block/virtio_blk.c

@@ -130,7 +130,7 @@ static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr)
 	return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
 }
 
-static int virtblk_setup_discard_write_zeroes(struct request *req, bool unmap)
+static int virtblk_setup_discard_write_zeroes_erase(struct request *req, bool unmap)
 {
 	unsigned short segments = blk_rq_nr_discard_segments(req);
 	unsigned short n = 0;
@@ -240,6 +240,9 @@ static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev,
 		type = VIRTIO_BLK_T_WRITE_ZEROES;
 		unmap = !(req->cmd_flags & REQ_NOUNMAP);
 		break;
+	case REQ_OP_SECURE_ERASE:
+		type = VIRTIO_BLK_T_SECURE_ERASE;
+		break;
 	case REQ_OP_DRV_IN:
 		type = VIRTIO_BLK_T_GET_ID;
 		break;
@@ -251,8 +254,9 @@ static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev,
 	vbr->out_hdr.type = cpu_to_virtio32(vdev, type);
 	vbr->out_hdr.ioprio = cpu_to_virtio32(vdev, req_get_ioprio(req));
 
-	if (type == VIRTIO_BLK_T_DISCARD || type == VIRTIO_BLK_T_WRITE_ZEROES) {
+	if (type == VIRTIO_BLK_T_DISCARD || type == VIRTIO_BLK_T_WRITE_ZEROES ||
-		if (virtblk_setup_discard_write_zeroes(req, unmap))
+	    type == VIRTIO_BLK_T_SECURE_ERASE) {
+		if (virtblk_setup_discard_write_zeroes_erase(req, unmap))
 			return BLK_STS_RESOURCE;
 	}
 
@@ -886,6 +890,8 @@ static int virtblk_probe(struct virtio_device *vdev)
 	int err, index;
 
 	u32 v, blk_size, max_size, sg_elems, opt_io_size;
+	u32 max_discard_segs = 0;
+	u32 discard_granularity = 0;
 	u16 min_io_size;
 	u8 physical_block_exp, alignment_offset;
 	unsigned int queue_depth;
@@ -1043,27 +1049,14 @@ static int virtblk_probe(struct virtio_device *vdev)
 
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) {
 		virtio_cread(vdev, struct virtio_blk_config,
-			     discard_sector_alignment, &v);
+			     discard_sector_alignment, &discard_granularity);
-		if (v)
-			q->limits.discard_granularity = v << SECTOR_SHIFT;
-		else
-			q->limits.discard_granularity = blk_size;
 
 		virtio_cread(vdev, struct virtio_blk_config,
 			     max_discard_sectors, &v);
 		blk_queue_max_discard_sectors(q, v ? v : UINT_MAX);
 
 		virtio_cread(vdev, struct virtio_blk_config, max_discard_seg,
-			     &v);
+			     &max_discard_segs);
-
-		/*
-		 * max_discard_seg == 0 is out of spec but we always
-		 * handled it.
-		 */
-		if (!v)
-			v = sg_elems;
-		blk_queue_max_discard_segments(q,
-					       min(v, MAX_DISCARD_SEGMENTS));
 	}
 
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) {
@@ -1072,6 +1065,85 @@ static int virtblk_probe(struct virtio_device *vdev)
 		blk_queue_max_write_zeroes_sectors(q, v ? v : UINT_MAX);
 	}
 
+	/* The discard and secure erase limits are combined since the Linux
+	 * block layer uses the same limit for both commands.
+	 *
+	 * If both VIRTIO_BLK_F_SECURE_ERASE and VIRTIO_BLK_F_DISCARD features
+	 * are negotiated, we will use the minimum between the limits.
+	 *
+	 * discard sector alignment is set to the minimum between discard_sector_alignment
+	 * and secure_erase_sector_alignment.
+	 *
+	 * max discard sectors is set to the minimum between max_discard_seg and
+	 * max_secure_erase_seg.
+	 */
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_SECURE_ERASE)) {
+
+		virtio_cread(vdev, struct virtio_blk_config,
+			     secure_erase_sector_alignment, &v);
+
+		/* secure_erase_sector_alignment should not be zero, the device should set a
+		 * valid number of sectors.
+		 */
+		if (!v) {
+			dev_err(&vdev->dev,
+				"virtio_blk: secure_erase_sector_alignment can't be 0\n");
+			err = -EINVAL;
+			goto out_cleanup_disk;
+		}
+
+		discard_granularity = min_not_zero(discard_granularity, v);
+
+		virtio_cread(vdev, struct virtio_blk_config,
+			     max_secure_erase_sectors, &v);
+
+		/* max_secure_erase_sectors should not be zero, the device should set a
+		 * valid number of sectors.
+		 */
+		if (!v) {
+			dev_err(&vdev->dev,
+				"virtio_blk: max_secure_erase_sectors can't be 0\n");
+			err = -EINVAL;
+			goto out_cleanup_disk;
+		}
+
+		blk_queue_max_secure_erase_sectors(q, v);
+
+		virtio_cread(vdev, struct virtio_blk_config,
+			     max_secure_erase_seg, &v);
+
+		/* max_secure_erase_seg should not be zero, the device should set a
+		 * valid number of segments
+		 */
+		if (!v) {
+			dev_err(&vdev->dev,
+				"virtio_blk: max_secure_erase_seg can't be 0\n");
+			err = -EINVAL;
+			goto out_cleanup_disk;
+		}
+
+		max_discard_segs = min_not_zero(max_discard_segs, v);
+	}
+
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD) ||
+	    virtio_has_feature(vdev, VIRTIO_BLK_F_SECURE_ERASE)) {
+		/* max_discard_seg and discard_granularity will be 0 only
+		 * if max_discard_seg and discard_sector_alignment fields in the virtio
+		 * config are 0 and VIRTIO_BLK_F_SECURE_ERASE feature is not negotiated.
+		 * In this case, we use default values.
+		 */
+		if (!max_discard_segs)
+			max_discard_segs = sg_elems;
+
+		blk_queue_max_discard_segments(q,
+					       min(max_discard_segs, MAX_DISCARD_SEGMENTS));
+
+		if (discard_granularity)
+			q->limits.discard_granularity = discard_granularity << SECTOR_SHIFT;
+		else
+			q->limits.discard_granularity = blk_size;
+	}
+
 	virtblk_update_capacity(vblk, false);
 	virtio_device_ready(vdev);
 
@@ -1167,6 +1239,7 @@ static unsigned int features_legacy[] = {
 	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
 	VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
 	VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES,
+	VIRTIO_BLK_F_SECURE_ERASE,
 }
 ;
 static unsigned int features[] = {
@@ -1174,6 +1247,7 @@ static unsigned int features[] = {
 	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
 	VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
 	VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES,
+	VIRTIO_BLK_F_SECURE_ERASE,
 };
 
 static struct virtio_driver virtio_blk = {

drivers/net/virtio_net.c

@@ -225,6 +225,9 @@ struct virtnet_info {
 	/* I like... big packets and I cannot lie! */
 	bool big_packets;
 
+	/* number of sg entries allocated for big packets */
+	unsigned int big_packets_num_skbfrags;
+
 	/* Host will merge rx buffers for big packets (shake it! shake it!) */
 	bool mergeable_rx_bufs;
 
@@ -1331,10 +1334,10 @@ static int add_recvbuf_big(struct virtnet_info *vi, struct receive_queue *rq,
 	char *p;
 	int i, err, offset;
 
-	sg_init_table(rq->sg, MAX_SKB_FRAGS + 2);
+	sg_init_table(rq->sg, vi->big_packets_num_skbfrags + 2);
 
-	/* page in rq->sg[MAX_SKB_FRAGS + 1] is list tail */
+	/* page in rq->sg[vi->big_packets_num_skbfrags + 1] is list tail */
-	for (i = MAX_SKB_FRAGS + 1; i > 1; --i) {
+	for (i = vi->big_packets_num_skbfrags + 1; i > 1; --i) {
 		first = get_a_page(rq, gfp);
 		if (!first) {
 			if (list)
@@ -1365,7 +1368,7 @@ static int add_recvbuf_big(struct virtnet_info *vi, struct receive_queue *rq,
 
 	/* chain first in list head */
 	first->private = (unsigned long)list;
-	err = virtqueue_add_inbuf(rq->vq, rq->sg, MAX_SKB_FRAGS + 2,
+	err = virtqueue_add_inbuf(rq->vq, rq->sg, vi->big_packets_num_skbfrags + 2,
 				  first, gfp);
 	if (err < 0)
 		give_pages(rq, first);
@@ -3682,13 +3685,35 @@ static int virtnet_validate(struct virtio_device *vdev)
 	return 0;
 }
 
+static bool virtnet_check_guest_gso(const struct virtnet_info *vi)
+{
+	return virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) ||
+		virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) ||
+		virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) ||
+		virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO);
+}
+
+static void virtnet_set_big_packets(struct virtnet_info *vi, const int mtu)
+{
+	bool guest_gso = virtnet_check_guest_gso(vi);
+
+	/* If device can receive ANY guest GSO packets, regardless of mtu,
+	 * allocate packets of maximum size, otherwise limit it to only
+	 * mtu size worth only.
+	 */
+	if (mtu > ETH_DATA_LEN || guest_gso) {
+		vi->big_packets = true;
+		vi->big_packets_num_skbfrags = guest_gso ? MAX_SKB_FRAGS : DIV_ROUND_UP(mtu, PAGE_SIZE);
+	}
+}
+
 static int virtnet_probe(struct virtio_device *vdev)
 {
 	int i, err = -ENOMEM;
 	struct net_device *dev;
 	struct virtnet_info *vi;
 	u16 max_queue_pairs;
-	int mtu;
+	int mtu = 0;
 
 	/* Find if host supports multiqueue/rss virtio_net device */
 	max_queue_pairs = 1;
@@ -3776,13 +3801,6 @@ static int virtnet_probe(struct virtio_device *vdev)
 	INIT_WORK(&vi->config_work, virtnet_config_changed_work);
 	spin_lock_init(&vi->refill_lock);
 
-	/* If we can receive ANY GSO packets, we must allocate large ones. */
-	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
-	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) ||
-	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) ||
-	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO))
-		vi->big_packets = true;
-
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
 		vi->mergeable_rx_bufs = true;
 
@@ -3848,12 +3866,10 @@ static int virtnet_probe(struct virtio_device *vdev)
 
 		dev->mtu = mtu;
 		dev->max_mtu = mtu;
-
-		/* TODO: size buffers correctly in this case. */
-		if (dev->mtu > ETH_DATA_LEN)
-			vi->big_packets = true;
 	}
 
+	virtnet_set_big_packets(vi, mtu);
+
 	if (vi->any_header_sg)
 		dev->needed_headroom = vi->hdr_len;
 

drivers/vdpa/vdpa.c

@@ -600,6 +600,11 @@ static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *i
 		}
 		config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP);
 	}
+	if (nl_attrs[VDPA_ATTR_DEV_FEATURES]) {
+		config.device_features =
+			nla_get_u64(nl_attrs[VDPA_ATTR_DEV_FEATURES]);
+		config.mask |= BIT_ULL(VDPA_ATTR_DEV_FEATURES);
+	}
 
 	/* Skip checking capability if user didn't prefer to configure any
 	 * device networking attributes. It is likely that user might have used
@@ -799,51 +804,76 @@ static int vdpa_nl_cmd_dev_get_dumpit(struct sk_buff *msg, struct netlink_callba
 	return msg->len;
 }
 
-static int vdpa_dev_net_mq_config_fill(struct vdpa_device *vdev,
+static int vdpa_dev_net_mq_config_fill(struct sk_buff *msg, u64 features,
-				       struct sk_buff *msg, u64 features,
 				       const struct virtio_net_config *config)
 {
 	u16 val_u16;
 
-	if ((features & BIT_ULL(VIRTIO_NET_F_MQ)) == 0)
+	if ((features & BIT_ULL(VIRTIO_NET_F_MQ)) == 0 &&
+	    (features & BIT_ULL(VIRTIO_NET_F_RSS)) == 0)
 		return 0;
 
-	val_u16 = le16_to_cpu(config->max_virtqueue_pairs);
+	val_u16 = __virtio16_to_cpu(true, config->max_virtqueue_pairs);
+
 	return nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, val_u16);
 }
 
+static int vdpa_dev_net_mtu_config_fill(struct sk_buff *msg, u64 features,
+					const struct virtio_net_config *config)
+{
+	u16 val_u16;
+
+	if ((features & BIT_ULL(VIRTIO_NET_F_MTU)) == 0)
+		return 0;
+
+	val_u16 = __virtio16_to_cpu(true, config->mtu);
+
+	return nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MTU, val_u16);
+}
+
+static int vdpa_dev_net_mac_config_fill(struct sk_buff *msg, u64 features,
+					const struct virtio_net_config *config)
+{
+	if ((features & BIT_ULL(VIRTIO_NET_F_MAC)) == 0)
+		return 0;
+
+	return  nla_put(msg, VDPA_ATTR_DEV_NET_CFG_MACADDR,
+			sizeof(config->mac), config->mac);
+}
+
 static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *msg)
 {
 	struct virtio_net_config config = {};
-	u64 features;
+	u64 features_device;
 	u16 val_u16;
 
-	vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config));
+	vdev->config->get_config(vdev, 0, &config, sizeof(config));
-
-	if (nla_put(msg, VDPA_ATTR_DEV_NET_CFG_MACADDR, sizeof(config.mac),
-		    config.mac))
-		return -EMSGSIZE;
 
 	val_u16 = __virtio16_to_cpu(true, config.status);
 	if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_STATUS, val_u16))
 		return -EMSGSIZE;
 
-	val_u16 = __virtio16_to_cpu(true, config.mtu);
+	features_device = vdev->config->get_device_features(vdev);
-	if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MTU, val_u16))
-		return -EMSGSIZE;
 
-	features = vdev->config->get_driver_features(vdev);
+	if (nla_put_u64_64bit(msg, VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES, features_device,
-	if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES, features,
 			      VDPA_ATTR_PAD))
 		return -EMSGSIZE;
 
-	return vdpa_dev_net_mq_config_fill(vdev, msg, features, &config);
+	if (vdpa_dev_net_mtu_config_fill(msg, features_device, &config))
+		return -EMSGSIZE;
+
+	if (vdpa_dev_net_mac_config_fill(msg, features_device, &config))
+		return -EMSGSIZE;
+
+	return vdpa_dev_net_mq_config_fill(msg, features_device, &config);
 }
 
 static int
 vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq,
 		     int flags, struct netlink_ext_ack *extack)
 {
+	u64 features_driver;
+	u8 status = 0;
 	u32 device_id;
 	void *hdr;
 	int err;
@@ -867,6 +897,17 @@ vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid,
 		goto msg_err;
 	}
 
+	/* only read driver features after the feature negotiation is done */
+	status = vdev->config->get_status(vdev);
+	if (status & VIRTIO_CONFIG_S_FEATURES_OK) {
+		features_driver = vdev->config->get_driver_features(vdev);
+		if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES, features_driver,
+				      VDPA_ATTR_PAD)) {
+			err = -EMSGSIZE;
+			goto msg_err;
+		}
+	}
+
 	switch (device_id) {
 	case VIRTIO_ID_NET:
 		err = vdpa_dev_net_config_fill(vdev, msg);

drivers/vdpa/vdpa_sim/vdpa_sim.c

@@ -18,6 +18,7 @@
 #include <linux/vdpa.h>
 #include <linux/vhost_iotlb.h>
 #include <linux/iova.h>
+#include <uapi/linux/vdpa.h>
 
 #include "vdpa_sim.h"
 
@@ -245,13 +246,22 @@ static const struct dma_map_ops vdpasim_dma_ops = {
 static const struct vdpa_config_ops vdpasim_config_ops;
 static const struct vdpa_config_ops vdpasim_batch_config_ops;
 
-struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)
+struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr,
+			       const struct vdpa_dev_set_config *config)
 {
 	const struct vdpa_config_ops *ops;
 	struct vdpasim *vdpasim;
 	struct device *dev;
 	int i, ret = -ENOMEM;
 
+	if (config->mask & BIT_ULL(VDPA_ATTR_DEV_FEATURES)) {
+		if (config->device_features &
+		    ~dev_attr->supported_features)
+			return ERR_PTR(-EINVAL);
+		dev_attr->supported_features =
+			config->device_features;
+	}
+
 	if (batch_mapping)
 		ops = &vdpasim_batch_config_ops;
 	else

drivers/vdpa/vdpa_sim/vdpa_sim.h

@@ -71,7 +71,8 @@ struct vdpasim {
 	spinlock_t iommu_lock;
 };
 
-struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *attr);
+struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *attr,
+			       const struct vdpa_dev_set_config *config);
 
 /* TODO: cross-endian support */
 static inline bool vdpasim_is_little_endian(struct vdpasim *vdpasim)

drivers/vdpa/vdpa_sim/vdpa_sim_blk.c

@@ -383,7 +383,7 @@ static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
 	dev_attr.work_fn = vdpasim_blk_work;
 	dev_attr.buffer_size = VDPASIM_BLK_CAPACITY << SECTOR_SHIFT;
 
-	simdev = vdpasim_create(&dev_attr);
+	simdev = vdpasim_create(&dev_attr, config);
 	if (IS_ERR(simdev))
 		return PTR_ERR(simdev);
 

drivers/vdpa/vdpa_sim/vdpa_sim_net.c

@@ -254,7 +254,7 @@ static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
 	dev_attr.work_fn = vdpasim_net_work;
 	dev_attr.buffer_size = PAGE_SIZE;
 
-	simdev = vdpasim_create(&dev_attr);
+	simdev = vdpasim_create(&dev_attr, config);
 	if (IS_ERR(simdev))
 		return PTR_ERR(simdev);
 
@@ -294,7 +294,8 @@ static struct vdpa_mgmt_dev mgmt_dev = {
 	.id_table = id_table,
 	.ops = &vdpasim_net_mgmtdev_ops,
 	.config_attr_mask = (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR |
-			     1 << VDPA_ATTR_DEV_NET_CFG_MTU),
+			     1 << VDPA_ATTR_DEV_NET_CFG_MTU |
+		             1 << VDPA_ATTR_DEV_FEATURES),
 	.max_supported_vqs = VDPASIM_NET_VQ_NUM,
 	.supported_features = VDPASIM_NET_FEATURES,
 };

drivers/vdpa/virtio_pci/vp_vdpa.c

@@ -17,6 +17,7 @@
 #include <linux/virtio_ring.h>
 #include <linux/virtio_pci.h>
 #include <linux/virtio_pci_modern.h>
+#include <uapi/linux/vdpa.h>
 
 #define VP_VDPA_QUEUE_MAX 256
 #define VP_VDPA_DRIVER_NAME "vp_vdpa"
@@ -35,6 +36,7 @@ struct vp_vdpa {
 	struct virtio_pci_modern_device *mdev;
 	struct vp_vring *vring;
 	struct vdpa_callback config_cb;
+	u64 device_features;
 	char msix_name[VP_VDPA_NAME_SIZE];
 	int config_irq;
 	int queues;
@@ -66,9 +68,9 @@ static struct virtio_pci_modern_device *vp_vdpa_to_mdev(struct vp_vdpa *vp_vdpa)
 
 static u64 vp_vdpa_get_device_features(struct vdpa_device *vdpa)
 {
-	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
+	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
 
-	return vp_modern_get_features(mdev);
+	return vp_vdpa->device_features;
 }
 
 static int vp_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features)
@@ -475,6 +477,7 @@ static int vp_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 	struct pci_dev *pdev = mdev->pci_dev;
 	struct device *dev = &pdev->dev;
 	struct vp_vdpa *vp_vdpa = NULL;
+	u64 device_features;
 	int ret, i;
 
 	vp_vdpa = vdpa_alloc_device(struct vp_vdpa, vdpa,
@@ -491,6 +494,20 @@ static int vp_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 	vp_vdpa->queues = vp_modern_get_num_queues(mdev);
 	vp_vdpa->mdev = mdev;
 
+	device_features = vp_modern_get_features(mdev);
+	if (add_config->mask & BIT_ULL(VDPA_ATTR_DEV_FEATURES)) {
+		if (add_config->device_features & ~device_features) {
+			ret = -EINVAL;
+			dev_err(&pdev->dev, "Try to provision features "
+				"that are not supported by the device: "
+				"device_features 0x%llx provisioned 0x%llx\n",
+				device_features, add_config->device_features);
+			goto err;
+		}
+		device_features = add_config->device_features;
+	}
+	vp_vdpa->device_features = device_features;
+
 	ret = devm_add_action_or_reset(dev, vp_vdpa_free_irq_vectors, pdev);
 	if (ret) {
 		dev_err(&pdev->dev,
@@ -599,6 +616,7 @@ static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mgtdev->id_table = mdev_id;
 	mgtdev->max_supported_vqs = vp_modern_get_num_queues(mdev);
 	mgtdev->supported_features = vp_modern_get_features(mdev);
+	mgtdev->config_attr_mask = (1 << VDPA_ATTR_DEV_FEATURES);
 	pci_set_master(pdev);
 	pci_set_drvdata(pdev, vp_vdpa_mgtdev);
 

drivers/vhost/net.c

@@ -1782,7 +1782,7 @@ static struct miscdevice vhost_net_misc = {
 	.fops = &vhost_net_fops,
 };
 
-static int vhost_net_init(void)
+static int __init vhost_net_init(void)
 {
 	if (experimental_zcopytx)
 		vhost_net_enable_zcopy(VHOST_NET_VQ_TX);
@@ -1790,7 +1790,7 @@ static int vhost_net_init(void)
 }
 module_init(vhost_net_init);
 
-static void vhost_net_exit(void)
+static void __exit vhost_net_exit(void)
 {
 	misc_deregister(&vhost_net_misc);
 }

drivers/virtio/virtio_pci_common.c

@@ -409,6 +409,9 @@ int vp_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false, ctx, desc);
 	if (!err)
 		return 0;
+	/* Is there an interrupt pin? If not give up. */
+	if (!(to_vp_device(vdev)->pci_dev->pin))
+		return err;
 	/* Finally fall back to regular interrupts. */
 	return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names, ctx);
 }

include/linux/vdpa.h

@@ -104,6 +104,7 @@ struct vdpa_iova_range {
 };
 
 struct vdpa_dev_set_config {
+	u64 device_features;
 	struct {
 		u8 mac[ETH_ALEN];
 		u16 mtu;

include/linux/virtio_pci_legacy.h

@@ -32,8 +32,6 @@ void vp_legacy_set_queue_address(struct virtio_pci_legacy_device *ldev,
 			     u16 index, u32 queue_pfn);
 bool vp_legacy_get_queue_enable(struct virtio_pci_legacy_device *ldev,
 				u16 idx);
-void vp_legacy_set_queue_size(struct virtio_pci_legacy_device *ldev,
-			      u16 idx, u16 size);
 u16 vp_legacy_get_queue_size(struct virtio_pci_legacy_device *ldev,
 			     u16 idx);
 int vp_legacy_probe(struct virtio_pci_legacy_device *ldev);

include/uapi/linux/vdpa.h

@@ -46,12 +46,18 @@ enum vdpa_attr {
 
 	VDPA_ATTR_DEV_NEGOTIATED_FEATURES,	/* u64 */
 	VDPA_ATTR_DEV_MGMTDEV_MAX_VQS,		/* u32 */
+	/* virtio features that are supported by the vDPA management device */
 	VDPA_ATTR_DEV_SUPPORTED_FEATURES,	/* u64 */
 
 	VDPA_ATTR_DEV_QUEUE_INDEX,              /* u32 */
 	VDPA_ATTR_DEV_VENDOR_ATTR_NAME,		/* string */
 	VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,        /* u64 */
 
+	VDPA_ATTR_DEV_FEATURES,                 /* u64 */
+
+	/* virtio features that are supported by the vDPA device */
+	VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES,	/* u64 */
+
 	/* new attributes must be added above here */
 	VDPA_ATTR_MAX,
 };

include/uapi/linux/virtio_blk.h

@@ -40,6 +40,7 @@
 #define VIRTIO_BLK_F_MQ		12	/* support more than one vq */
 #define VIRTIO_BLK_F_DISCARD	13	/* DISCARD is supported */
 #define VIRTIO_BLK_F_WRITE_ZEROES	14	/* WRITE ZEROES is supported */
+#define VIRTIO_BLK_F_SECURE_ERASE	16 /* Secure Erase is supported */
 
 /* Legacy feature bits */
 #ifndef VIRTIO_BLK_NO_LEGACY
@@ -121,6 +122,21 @@ struct virtio_blk_config {
 	__u8 write_zeroes_may_unmap;
 
 	__u8 unused1[3];
+
+	/* the next 3 entries are guarded by VIRTIO_BLK_F_SECURE_ERASE */
+	/*
+	 * The maximum secure erase sectors (in 512-byte sectors) for
+	 * one segment.
+	 */
+	__virtio32 max_secure_erase_sectors;
+	/*
+	 * The maximum number of secure erase segments in a
+	 * secure erase command.
+	 */
+	__virtio32 max_secure_erase_seg;
+	/* Secure erase commands must be aligned to this number of sectors. */
+	__virtio32 secure_erase_sector_alignment;
+
 } __attribute__((packed));
 
 /*
@@ -155,6 +171,9 @@ struct virtio_blk_config {
 /* Write zeroes command */
 #define VIRTIO_BLK_T_WRITE_ZEROES	13
 
+/* Secure erase command */
+#define VIRTIO_BLK_T_SECURE_ERASE	14
+
 #ifndef VIRTIO_BLK_NO_LEGACY
 /* Barrier before this op. */
 #define VIRTIO_BLK_T_BARRIER	0x80000000