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

Author: torvalds

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 (virtblk_setup_discard_write_zeroes(req, unmap))
+	if (type == VIRTIO_BLK_T_DISCARD || type == VIRTIO_BLK_T_WRITE_ZEROES ||
+	    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);
-		if (v)
-			q->limits.discard_granularity = v << SECTOR_SHIFT;
-		else
-			q->limits.discard_granularity = blk_size;
+			     discard_sector_alignment, &discard_granularity);
 
 		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_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));
+			     &max_discard_segs);
 	}
 
 	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);
 
@@ -1167,13 +1239,15 @@ 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[] = {
 	VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
 	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 */
-	for (i = MAX_SKB_FRAGS + 1; i > 1; --i) {
+	/* page in rq->sg[vi->big_packets_num_skbfrags + 1] is list tail */
+	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,
-				       struct sk_buff *msg, u64 features,
+static int vdpa_dev_net_mq_config_fill(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));
-
-	if (nla_put(msg, VDPA_ATTR_DEV_NET_CFG_MACADDR, sizeof(config.mac),
-		    config.mac))
-		return -EMSGSIZE;
+	vdev->config->get_config(vdev, 0, &config, sizeof(config));
 
 	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);
-	if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MTU, val_u16))
-		return -EMSGSIZE;
+	features_device = vdev->config->get_device_features(vdev);
 
-	features = vdev->config->get_driver_features(vdev);
-	if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES, features,
+	if (nla_put_u64_64bit(msg, VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES, features_device,
 			      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);