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
  ...

MAINTAINERS

@@ -20083,6 +20083,13 @@ S:	Maintained
 F:	drivers/i2c/busses/i2c-virtio.c
 F:	include/uapi/linux/virtio_i2c.h
 
+VIRTIO PMEM DRIVER
+M:	Pankaj Gupta <pankaj.gupta.linux@gmail.com>
+L:	virtualization@lists.linux-foundation.org
+S:	Maintained
+F:	drivers/nvdimm/virtio_pmem.c
+F:	drivers/nvdimm/nd_virtio.c
+
 VIRTUAL BOX GUEST DEVICE DRIVER
 M:	Hans de Goede <hdegoede@redhat.com>
 M:	Arnd Bergmann <arnd@arndb.de>

drivers/block/Kconfig

@@ -371,6 +371,7 @@ config XEN_BLKDEV_BACKEND
 config VIRTIO_BLK
 	tristate "Virtio block driver"
 	depends on VIRTIO
+	select SG_POOL
 	help
 	  This is the virtual block driver for virtio.  It can be used with
           QEMU based VMMs (like KVM or Xen).  Say Y or M.

drivers/block/virtio_blk.c

@@ -24,6 +24,19 @@
 /* The maximum number of sg elements that fit into a virtqueue */
 #define VIRTIO_BLK_MAX_SG_ELEMS 32768
 
+#ifdef CONFIG_ARCH_NO_SG_CHAIN
+#define VIRTIO_BLK_INLINE_SG_CNT	0
+#else
+#define VIRTIO_BLK_INLINE_SG_CNT	2
+#endif
+
+static unsigned int num_request_queues;
+module_param(num_request_queues, uint, 0644);
+MODULE_PARM_DESC(num_request_queues,
+		 "Limit the number of request queues to use for blk device. "
+		 "0 for no limit. "
+		 "Values > nr_cpu_ids truncated to nr_cpu_ids.");
+
 static int major;
 static DEFINE_IDA(vd_index_ida);
 
@@ -77,6 +90,7 @@ struct virtio_blk {
 struct virtblk_req {
 	struct virtio_blk_outhdr out_hdr;
 	u8 status;
+	struct sg_table sg_table;
 	struct scatterlist sg[];
 };
 
@@ -162,12 +176,93 @@ static int virtblk_setup_discard_write_zeroes(struct request *req, bool unmap)
 	return 0;
 }
 
-static inline void virtblk_request_done(struct request *req)
+static void virtblk_unmap_data(struct request *req, struct virtblk_req *vbr)
 {
-	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+	if (blk_rq_nr_phys_segments(req))
+		sg_free_table_chained(&vbr->sg_table,
+				      VIRTIO_BLK_INLINE_SG_CNT);
+}
+
+static int virtblk_map_data(struct blk_mq_hw_ctx *hctx, struct request *req,
+		struct virtblk_req *vbr)
+{
+	int err;
+
+	if (!blk_rq_nr_phys_segments(req))
+		return 0;
+
+	vbr->sg_table.sgl = vbr->sg;
+	err = sg_alloc_table_chained(&vbr->sg_table,
+				     blk_rq_nr_phys_segments(req),
+				     vbr->sg_table.sgl,
+				     VIRTIO_BLK_INLINE_SG_CNT);
+	if (unlikely(err))
+		return -ENOMEM;
 
+	return blk_rq_map_sg(hctx->queue, req, vbr->sg_table.sgl);
+}
+
+static void virtblk_cleanup_cmd(struct request *req)
+{
 	if (req->rq_flags & RQF_SPECIAL_PAYLOAD)
 		kfree(bvec_virt(&req->special_vec));
+}
+
+static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev,
+				      struct request *req,
+				      struct virtblk_req *vbr)
+{
+	bool unmap = false;
+	u32 type;
+
+	vbr->out_hdr.sector = 0;
+
+	switch (req_op(req)) {
+	case REQ_OP_READ:
+		type = VIRTIO_BLK_T_IN;
+		vbr->out_hdr.sector = cpu_to_virtio64(vdev,
+						      blk_rq_pos(req));
+		break;
+	case REQ_OP_WRITE:
+		type = VIRTIO_BLK_T_OUT;
+		vbr->out_hdr.sector = cpu_to_virtio64(vdev,
+						      blk_rq_pos(req));
+		break;
+	case REQ_OP_FLUSH:
+		type = VIRTIO_BLK_T_FLUSH;
+		break;
+	case REQ_OP_DISCARD:
+		type = VIRTIO_BLK_T_DISCARD;
+		break;
+	case REQ_OP_WRITE_ZEROES:
+		type = VIRTIO_BLK_T_WRITE_ZEROES;
+		unmap = !(req->cmd_flags & REQ_NOUNMAP);
+		break;
+	case REQ_OP_DRV_IN:
+		type = VIRTIO_BLK_T_GET_ID;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return BLK_STS_IOERR;
+	}
+
+	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))
+			return BLK_STS_RESOURCE;
+	}
+
+	return 0;
+}
+
+static inline void virtblk_request_done(struct request *req)
+{
+	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+
+	virtblk_unmap_data(req, vbr);
+	virtblk_cleanup_cmd(req);
 	blk_mq_end_request(req, virtblk_result(vbr));
 }
 
@@ -223,59 +318,26 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	unsigned long flags;
 	unsigned int num;
 	int qid = hctx->queue_num;
-	int err;
 	bool notify = false;
-	bool unmap = false;
-	u32 type;
+	blk_status_t status;
+	int err;
 
 	BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
 
-	switch (req_op(req)) {
-	case REQ_OP_READ:
-	case REQ_OP_WRITE:
-		type = 0;
-		break;
-	case REQ_OP_FLUSH:
-		type = VIRTIO_BLK_T_FLUSH;
-		break;
-	case REQ_OP_DISCARD:
-		type = VIRTIO_BLK_T_DISCARD;
-		break;
-	case REQ_OP_WRITE_ZEROES:
-		type = VIRTIO_BLK_T_WRITE_ZEROES;
-		unmap = !(req->cmd_flags & REQ_NOUNMAP);
-		break;
-	case REQ_OP_DRV_IN:
-		type = VIRTIO_BLK_T_GET_ID;
-		break;
-	default:
-		WARN_ON_ONCE(1);
-		return BLK_STS_IOERR;
-	}
-
-	vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, type);
-	vbr->out_hdr.sector = type ?
-		0 : cpu_to_virtio64(vblk->vdev, blk_rq_pos(req));
-	vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(req));
+	status = virtblk_setup_cmd(vblk->vdev, req, vbr);
+	if (unlikely(status))
+		return status;
 
 	blk_mq_start_request(req);
 
-	if (type == VIRTIO_BLK_T_DISCARD || type == VIRTIO_BLK_T_WRITE_ZEROES) {
-		err = virtblk_setup_discard_write_zeroes(req, unmap);
-		if (err)
-			return BLK_STS_RESOURCE;
-	}
-
-	num = blk_rq_map_sg(hctx->queue, req, vbr->sg);
-	if (num) {
-		if (rq_data_dir(req) == WRITE)
-			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_OUT);
-		else
-			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_IN);
+	num = virtblk_map_data(hctx, req, vbr);
+	if (unlikely(num < 0)) {
+		virtblk_cleanup_cmd(req);
+		return BLK_STS_RESOURCE;
 	}
 
 	spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
-	err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num);
+	err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg_table.sgl, num);
 	if (err) {
 		virtqueue_kick(vblk->vqs[qid].vq);
 		/* Don't stop the queue if -ENOMEM: we may have failed to
@@ -284,6 +346,8 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 		if (err == -ENOSPC)
 			blk_mq_stop_hw_queue(hctx);
 		spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
+		virtblk_unmap_data(req, vbr);
+		virtblk_cleanup_cmd(req);
 		switch (err) {
 		case -ENOSPC:
 			return BLK_STS_DEV_RESOURCE;
@@ -497,8 +561,14 @@ static int init_vq(struct virtio_blk *vblk)
 				   &num_vqs);
 	if (err)
 		num_vqs = 1;
+	if (!err && !num_vqs) {
+		dev_err(&vdev->dev, "MQ advertised but zero queues reported\n");
+		return -EINVAL;
+	}
 
-	num_vqs = min_t(unsigned int, nr_cpu_ids, num_vqs);
+	num_vqs = min_t(unsigned int,
+			min_not_zero(num_request_queues, nr_cpu_ids),
+			num_vqs);
 
 	vblk->vqs = kmalloc_array(num_vqs, sizeof(*vblk->vqs), GFP_KERNEL);
 	if (!vblk->vqs)
@@ -624,7 +694,7 @@ cache_type_show(struct device *dev, struct device_attribute *attr, char *buf)
 	u8 writeback = virtblk_get_cache_mode(vblk->vdev);
 
 	BUG_ON(writeback >= ARRAY_SIZE(virtblk_cache_types));
-	return snprintf(buf, 40, "%s\n", virtblk_cache_types[writeback]);
+	return sysfs_emit(buf, "%s\n", virtblk_cache_types[writeback]);
 }
 
 static DEVICE_ATTR_RW(cache_type);
@@ -660,16 +730,6 @@ static const struct attribute_group *virtblk_attr_groups[] = {
 	NULL,
 };
 
-static int virtblk_init_request(struct blk_mq_tag_set *set, struct request *rq,
-		unsigned int hctx_idx, unsigned int numa_node)
-{
-	struct virtio_blk *vblk = set->driver_data;
-	struct virtblk_req *vbr = blk_mq_rq_to_pdu(rq);
-
-	sg_init_table(vbr->sg, vblk->sg_elems);
-	return 0;
-}
-
 static int virtblk_map_queues(struct blk_mq_tag_set *set)
 {
 	struct virtio_blk *vblk = set->driver_data;
@@ -682,7 +742,6 @@ static const struct blk_mq_ops virtio_mq_ops = {
 	.queue_rq	= virtio_queue_rq,
 	.commit_rqs	= virtio_commit_rqs,
 	.complete	= virtblk_request_done,
-	.init_request	= virtblk_init_request,
 	.map_queues	= virtblk_map_queues,
 };
 
@@ -762,7 +821,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 	vblk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
 	vblk->tag_set.cmd_size =
 		sizeof(struct virtblk_req) +
-		sizeof(struct scatterlist) * sg_elems;
+		sizeof(struct scatterlist) * VIRTIO_BLK_INLINE_SG_CNT;
 	vblk->tag_set.driver_data = vblk;
 	vblk->tag_set.nr_hw_queues = vblk->num_vqs;
 
@@ -990,6 +1049,7 @@ static struct virtio_driver virtio_blk = {
 	.feature_table_size		= ARRAY_SIZE(features),
 	.feature_table_legacy		= features_legacy,
 	.feature_table_size_legacy	= ARRAY_SIZE(features_legacy),
+	.suppress_used_validation	= true,
 	.driver.name			= KBUILD_MODNAME,
 	.driver.owner			= THIS_MODULE,
 	.id_table			= id_table,

drivers/char/hw_random/virtio-rng.c

@@ -18,13 +18,20 @@ static DEFINE_IDA(rng_index_ida);
 struct virtrng_info {
 	struct hwrng hwrng;
 	struct virtqueue *vq;
-	struct completion have_data;
 	char name[25];
-	unsigned int data_avail;
 	int index;
-	bool busy;
 	bool hwrng_register_done;
 	bool hwrng_removed;
+	/* data transfer */
+	struct completion have_data;
+	unsigned int data_avail;
+	unsigned int data_idx;
+	/* minimal size returned by rng_buffer_size() */
+#if SMP_CACHE_BYTES < 32
+	u8 data[32];
+#else
+	u8 data[SMP_CACHE_BYTES];
+#endif
 };
 
 static void random_recv_done(struct virtqueue *vq)
@@ -35,54 +42,88 @@ static void random_recv_done(struct virtqueue *vq)
 	if (!virtqueue_get_buf(vi->vq, &vi->data_avail))
 		return;
 
+	vi->data_idx = 0;
+
 	complete(&vi->have_data);
 }
 
-/* The host will fill any buffer we give it with sweet, sweet randomness. */
-static void register_buffer(struct virtrng_info *vi, u8 *buf, size_t size)
+static void request_entropy(struct virtrng_info *vi)
 {
 	struct scatterlist sg;
 
-	sg_init_one(&sg, buf, size);
+	reinit_completion(&vi->have_data);
+	vi->data_avail = 0;
+	vi->data_idx = 0;
+
+	sg_init_one(&sg, vi->data, sizeof(vi->data));
 
 	/* There should always be room for one buffer. */
-	virtqueue_add_inbuf(vi->vq, &sg, 1, buf, GFP_KERNEL);
+	virtqueue_add_inbuf(vi->vq, &sg, 1, vi->data, GFP_KERNEL);
 
 	virtqueue_kick(vi->vq);
 }
 
+static unsigned int copy_data(struct virtrng_info *vi, void *buf,
+			      unsigned int size)
+{
+	size = min_t(unsigned int, size, vi->data_avail);
+	memcpy(buf, vi->data + vi->data_idx, size);
+	vi->data_idx += size;
+	vi->data_avail -= size;
+	if (vi->data_avail == 0)
+		request_entropy(vi);
+	return size;
+}
+
 static int virtio_read(struct hwrng *rng, void *buf, size_t size, bool wait)
 {
 	int ret;
 	struct virtrng_info *vi = (struct virtrng_info *)rng->priv;
+	unsigned int chunk;
+	size_t read;
 
 	if (vi->hwrng_removed)
 		return -ENODEV;
 
-	if (!vi->busy) {
-		vi->busy = true;
-		reinit_completion(&vi->have_data);
-		register_buffer(vi, buf, size);
+	read = 0;
+
+	/* copy available data */
+	if (vi->data_avail) {
+		chunk = copy_data(vi, buf, size);
+		size -= chunk;
+		read += chunk;
 	}
 
 	if (!wait)
-		return 0;
-
-	ret = wait_for_completion_killable(&vi->have_data);
-	if (ret < 0)
-		return ret;
+		return read;
+
+	/* We have already copied available entropy,
+	 * so either size is 0 or data_avail is 0
+	 */
+	while (size != 0) {
+		/* data_avail is 0 but a request is pending */
+		ret = wait_for_completion_killable(&vi->have_data);
+		if (ret < 0)
+			return ret;
+		/* if vi->data_avail is 0, we have been interrupted
+		 * by a cleanup, but buffer stays in the queue
+		 */
+		if (vi->data_avail == 0)
+			return read;
 
-	vi->busy = false;
+		chunk = copy_data(vi, buf + read, size);
+		size -= chunk;
+		read += chunk;
+	}
 
-	return vi->data_avail;
+	return read;
 }
 
 static void virtio_cleanup(struct hwrng *rng)
 {
 	struct virtrng_info *vi = (struct virtrng_info *)rng->priv;
 
-	if (vi->busy)
-		wait_for_completion(&vi->have_data);
+	complete(&vi->have_data);
 }
 
 static int probe_common(struct virtio_device *vdev)
@@ -118,6 +159,9 @@ static int probe_common(struct virtio_device *vdev)
 		goto err_find;
 	}
 
+	/* we always have a pending entropy request */
+	request_entropy(vi);
+
 	return 0;
 
 err_find:
@@ -133,9 +177,9 @@ static void remove_common(struct virtio_device *vdev)
 
 	vi->hwrng_removed = true;
 	vi->data_avail = 0;
+	vi->data_idx = 0;
 	complete(&vi->have_data);
 	vdev->config->reset(vdev);
-	vi->busy = false;
 	if (vi->hwrng_register_done)
 		hwrng_unregister(&vi->hwrng);
 	vdev->config->del_vqs(vdev);

drivers/char/virtio_console.c

@@ -28,6 +28,7 @@
 #include "../tty/hvc/hvc_console.h"
 
 #define is_rproc_enabled IS_ENABLED(CONFIG_REMOTEPROC)
+#define VIRTCONS_MAX_PORTS 0x8000
 
 /*
  * This is a global struct for storing common data for all the devices
@@ -2036,6 +2037,14 @@ static int virtcons_probe(struct virtio_device *vdev)
 	    virtio_cread_feature(vdev, VIRTIO_CONSOLE_F_MULTIPORT,
 				 struct virtio_console_config, max_nr_ports,
 				 &portdev->max_nr_ports) == 0) {
+		if (portdev->max_nr_ports == 0 ||
+		    portdev->max_nr_ports > VIRTCONS_MAX_PORTS) {
+			dev_err(&vdev->dev,
+				"Invalidate max_nr_ports %d",
+				portdev->max_nr_ports);
+			err = -EINVAL;
+			goto free;
+		}
 		multiport = true;
 	}
 

drivers/i2c/busses/i2c-virtio.c

@@ -62,35 +62,33 @@ static int virtio_i2c_prepare_reqs(struct virtqueue *vq,
 	for (i = 0; i < num; i++) {
 		int outcnt = 0, incnt = 0;
 
-		/*
-		 * We don't support 0 length messages and so filter out
-		 * 0 length transfers by using i2c_adapter_quirks.
-		 */
-		if (!msgs[i].len)
-			break;
-
 		/*
 		 * Only 7-bit mode supported for this moment. For the address
 		 * format, Please check the Virtio I2C Specification.
 		 */
 		reqs[i].out_hdr.addr = cpu_to_le16(msgs[i].addr << 1);
 
+		if (msgs[i].flags & I2C_M_RD)
+			reqs[i].out_hdr.flags |= cpu_to_le32(VIRTIO_I2C_FLAGS_M_RD);
+
 		if (i != num - 1)
-			reqs[i].out_hdr.flags = cpu_to_le32(VIRTIO_I2C_FLAGS_FAIL_NEXT);
+			reqs[i].out_hdr.flags |= cpu_to_le32(VIRTIO_I2C_FLAGS_FAIL_NEXT);
 
 		sg_init_one(&out_hdr, &reqs[i].out_hdr, sizeof(reqs[i].out_hdr));
 		sgs[outcnt++] = &out_hdr;
 
-		reqs[i].buf = i2c_get_dma_safe_msg_buf(&msgs[i], 1);
-		if (!reqs[i].buf)
-			break;
+		if (msgs[i].len) {
+			reqs[i].buf = i2c_get_dma_safe_msg_buf(&msgs[i], 1);
+			if (!reqs[i].buf)
+				break;
 
-		sg_init_one(&msg_buf, reqs[i].buf, msgs[i].len);
+			sg_init_one(&msg_buf, reqs[i].buf, msgs[i].len);
 
-		if (msgs[i].flags & I2C_M_RD)
-			sgs[outcnt + incnt++] = &msg_buf;
-		else
-			sgs[outcnt++] = &msg_buf;
+			if (msgs[i].flags & I2C_M_RD)
+				sgs[outcnt + incnt++] = &msg_buf;
+			else
+				sgs[outcnt++] = &msg_buf;
+		}
 
 		sg_init_one(&in_hdr, &reqs[i].in_hdr, sizeof(reqs[i].in_hdr));
 		sgs[outcnt + incnt++] = &in_hdr;
@@ -191,7 +189,7 @@ static int virtio_i2c_setup_vqs(struct virtio_i2c *vi)
 
 static u32 virtio_i2c_func(struct i2c_adapter *adap)
 {
-	return I2C_FUNC_I2C | (I2C_FUNC_SMBUS_EMUL & ~I2C_FUNC_SMBUS_QUICK);
+	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
 }
 
 static struct i2c_algorithm virtio_algorithm = {
@@ -199,15 +197,16 @@ static struct i2c_algorithm virtio_algorithm = {
 	.functionality = virtio_i2c_func,
 };
 
-static const struct i2c_adapter_quirks virtio_i2c_quirks = {
-	.flags = I2C_AQ_NO_ZERO_LEN,
-};
-
 static int virtio_i2c_probe(struct virtio_device *vdev)
 {
 	struct virtio_i2c *vi;
 	int ret;
 
+	if (!virtio_has_feature(vdev, VIRTIO_I2C_F_ZERO_LENGTH_REQUEST)) {
+		dev_err(&vdev->dev, "Zero-length request feature is mandatory\n");
+		return -EINVAL;
+	}
+
 	vi = devm_kzalloc(&vdev->dev, sizeof(*vi), GFP_KERNEL);
 	if (!vi)
 		return -ENOMEM;
@@ -225,7 +224,6 @@ static int virtio_i2c_probe(struct virtio_device *vdev)
 	snprintf(vi->adap.name, sizeof(vi->adap.name),
 		 "i2c_virtio at virtio bus %d", vdev->index);
 	vi->adap.algo = &virtio_algorithm;
-	vi->adap.quirks = &virtio_i2c_quirks;
 	vi->adap.dev.parent = &vdev->dev;
 	vi->adap.dev.of_node = vdev->dev.of_node;
 	i2c_set_adapdata(&vi->adap, vi);
@@ -270,11 +268,17 @@ static int virtio_i2c_restore(struct virtio_device *vdev)
 }
 #endif
 
+static const unsigned int features[] = {
+	VIRTIO_I2C_F_ZERO_LENGTH_REQUEST,
+};
+
 static struct virtio_driver virtio_i2c_driver = {
-	.id_table	= id_table,
-	.probe		= virtio_i2c_probe,
-	.remove		= virtio_i2c_remove,
-	.driver	= {
+	.feature_table		= features,
+	.feature_table_size	= ARRAY_SIZE(features),
+	.id_table		= id_table,
+	.probe			= virtio_i2c_probe,
+	.remove			= virtio_i2c_remove,
+	.driver			= {
 		.name	= "i2c_virtio",
 	},
 #ifdef CONFIG_PM_SLEEP

drivers/net/virtio_net.c

@@ -408,12 +408,13 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	 * add_recvbuf_mergeable() + get_mergeable_buf_len()
 	 */
 	truesize = headroom ? PAGE_SIZE : truesize;
-	tailroom = truesize - len - headroom - (hdr_padded_len - hdr_len);
+	tailroom = truesize - headroom;
 	buf = p - headroom;
 
 	len -= hdr_len;
 	offset += hdr_padded_len;
 	p += hdr_padded_len;
+	tailroom -= hdr_padded_len + len;
 
 	shinfo_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
@@ -3422,6 +3423,7 @@ static struct virtio_driver virtio_net_driver = {
 	.feature_table_size = ARRAY_SIZE(features),
 	.feature_table_legacy = features_legacy,
 	.feature_table_size_legacy = ARRAY_SIZE(features_legacy),
+	.suppress_used_validation = true,
 	.driver.name =	KBUILD_MODNAME,
 	.driver.owner =	THIS_MODULE,
 	.id_table =	id_table,

drivers/scsi/virtio_scsi.c

@@ -978,6 +978,7 @@ static unsigned int features[] = {
 static struct virtio_driver virtio_scsi_driver = {
 	.feature_table = features,
 	.feature_table_size = ARRAY_SIZE(features),
+	.suppress_used_validation = true,
 	.driver.name = KBUILD_MODNAME,
 	.driver.owner = THIS_MODULE,
 	.id_table = id_table,

drivers/vdpa/Kconfig

@@ -78,4 +78,12 @@ config VP_VDPA
 	help
 	  This kernel module bridges virtio PCI device to vDPA bus.
 
+config ALIBABA_ENI_VDPA
+	tristate "vDPA driver for Alibaba ENI"
+	select VIRTIO_PCI_LIB_LEGACY
+	depends on PCI_MSI && X86
+	help
+	  VDPA driver for Alibaba ENI (Elastic Network Interface) which is built upon
+	  virtio 0.9.5 specification.
+
 endif # VDPA

drivers/vdpa/Makefile

@@ -5,3 +5,4 @@ obj-$(CONFIG_VDPA_USER) += vdpa_user/
 obj-$(CONFIG_IFCVF)    += ifcvf/
 obj-$(CONFIG_MLX5_VDPA) += mlx5/
 obj-$(CONFIG_VP_VDPA)    += virtio_pci/
+obj-$(CONFIG_ALIBABA_ENI_VDPA) += alibaba/

drivers/vdpa/alibaba/Makefile

+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_ALIBABA_ENI_VDPA) += eni_vdpa.o
+

drivers/vdpa/ifcvf/ifcvf_main.c

@@ -499,7 +499,8 @@ static u32 get_dev_type(struct pci_dev *pdev)
 	return dev_type;
 }
 
-static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name)
+static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
+			      const struct vdpa_dev_set_config *config)
 {
 	struct ifcvf_vdpa_mgmt_dev *ifcvf_mgmt_dev;
 	struct ifcvf_adapter *adapter;

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;
 };

drivers/vdpa/vdpa_sim/vdpa_sim_blk.c

@@ -248,7 +248,8 @@ static struct device vdpasim_blk_mgmtdev = {
 	.release = vdpasim_blk_mgmtdev_release,
 };
 
-static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name)
+static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
+			       const struct vdpa_dev_set_config *config)
 {
 	struct vdpasim_dev_attr dev_attr = {};
 	struct vdpasim *simdev;

drivers/vdpa/vdpa_sim/vdpa_sim_net.c

@@ -16,6 +16,7 @@
 #include <linux/vringh.h>
 #include <linux/vdpa.h>
 #include <uapi/linux/virtio_net.h>
+#include <uapi/linux/vdpa.h>
 
 #include "vdpa_sim.h"
 
@@ -29,12 +30,6 @@
 
 #define VDPASIM_NET_VQ_NUM	2
 
-static char *macaddr;
-module_param(macaddr, charp, 0);
-MODULE_PARM_DESC(macaddr, "Ethernet MAC address");
-
-static u8 macaddr_buf[ETH_ALEN];
-
 static void vdpasim_net_work(struct work_struct *work)
 {
 	struct vdpasim *vdpasim = container_of(work, struct vdpasim, work);
@@ -112,9 +107,21 @@ static void vdpasim_net_get_config(struct vdpasim *vdpasim, void *config)
 {
 	struct virtio_net_config *net_config = config;
 
-	net_config->mtu = cpu_to_vdpasim16(vdpasim, 1500);
 	net_config->status = cpu_to_vdpasim16(vdpasim, VIRTIO_NET_S_LINK_UP);
-	memcpy(net_config->mac, macaddr_buf, ETH_ALEN);
+}
+
+static void vdpasim_net_setup_config(struct vdpasim *vdpasim,
+				     const struct vdpa_dev_set_config *config)
+{
+	struct virtio_net_config *vio_config = vdpasim->config;
+
+	if (config->mask & (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR))
+		memcpy(vio_config->mac, config->net.mac, ETH_ALEN);
+	if (config->mask & (1 << VDPA_ATTR_DEV_NET_CFG_MTU))
+		vio_config->mtu = cpu_to_vdpasim16(vdpasim, config->net.mtu);
+	else
+		/* Setup default MTU to be 1500 */
+		vio_config->mtu = cpu_to_vdpasim16(vdpasim, 1500);
 }
 
 static void vdpasim_net_mgmtdev_release(struct device *dev)
@@ -126,7 +133,8 @@ static struct device vdpasim_net_mgmtdev = {
 	.release = vdpasim_net_mgmtdev_release,
 };
 
-static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name)
+static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
+			       const struct vdpa_dev_set_config *config)
 {
 	struct vdpasim_dev_attr dev_attr = {};
 	struct vdpasim *simdev;
@@ -146,6 +154,8 @@ static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name)
 	if (IS_ERR(simdev))
 		return PTR_ERR(simdev);
 
+	vdpasim_net_setup_config(simdev, config);
+
 	ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_NET_VQ_NUM);
 	if (ret)
 		goto reg_err;
@@ -179,20 +189,14 @@ static struct vdpa_mgmt_dev mgmt_dev = {
 	.device = &vdpasim_net_mgmtdev,
 	.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),
 };
 
 static int __init vdpasim_net_init(void)
 {
 	int ret;
 
-	if (macaddr) {
-		mac_pton(macaddr, macaddr_buf);
-		if (!is_valid_ether_addr(macaddr_buf))
-			return -EADDRNOTAVAIL;
-	} else {
-		eth_random_addr(macaddr_buf);
-	}
-
 	ret = device_register(&vdpasim_net_mgmtdev);
 	if (ret)
 		return ret;

drivers/vdpa/vdpa_user/vduse_dev.c

@@ -1503,7 +1503,8 @@ static int vduse_dev_init_vdpa(struct vduse_dev *dev, const char *name)
 	return 0;
 }
 
-static int vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name)
+static int vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
+			const struct vdpa_dev_set_config *config)
 {
 	struct vduse_dev *dev;
 	int ret;

drivers/vdpa/virtio_pci/vp_vdpa.c

@@ -76,6 +76,17 @@ static u8 vp_vdpa_get_status(struct vdpa_device *vdpa)
 	return vp_modern_get_status(mdev);
 }
 
+static int vp_vdpa_get_vq_irq(struct vdpa_device *vdpa, u16 idx)
+{
+	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
+	int irq = vp_vdpa->vring[idx].irq;
+
+	if (irq == VIRTIO_MSI_NO_VECTOR)
+		return -EINVAL;
+
+	return irq;
+}
+
 static void vp_vdpa_free_irq(struct vp_vdpa *vp_vdpa)
 {
 	struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev;
@@ -427,6 +438,7 @@ static const struct vdpa_config_ops vp_vdpa_ops = {
 	.get_config	= vp_vdpa_get_config,
 	.set_config	= vp_vdpa_set_config,
 	.set_config_cb  = vp_vdpa_set_config_cb,
+	.get_vq_irq	= vp_vdpa_get_vq_irq,
 };
 
 static void vp_vdpa_free_irq_vectors(void *data)

drivers/vhost/vdpa.c

@@ -237,7 +237,6 @@ static long vhost_vdpa_set_config(struct vhost_vdpa *v,
 				  struct vhost_vdpa_config __user *c)
 {
 	struct vdpa_device *vdpa = v->vdpa;
-	const struct vdpa_config_ops *ops = vdpa->config;
 	struct vhost_vdpa_config config;
 	unsigned long size = offsetof(struct vhost_vdpa_config, buf);
 	u8 *buf;
@@ -251,7 +250,7 @@ static long vhost_vdpa_set_config(struct vhost_vdpa *v,
 	if (IS_ERR(buf))
 		return PTR_ERR(buf);
 
-	ops->set_config(vdpa, config.off, buf, config.len);
+	vdpa_set_config(vdpa, config.off, buf, config.len);
 
 	kvfree(buf);
 	return 0;

drivers/virtio/Kconfig

@@ -20,6 +20,15 @@ config VIRTIO_PCI_LIB
 	  PCI device with possible vendor specific extensions. Any
 	  module that selects this module must depend on PCI.
 
+config VIRTIO_PCI_LIB_LEGACY
+	tristate
+	help
+	  Legacy PCI device (Virtio PCI Card 0.9.x Draft and older device)
+	  implementation.
+	  This module implements the basic probe and control for devices
+	  which are based on legacy PCI device. Any module that selects this
+	  module must depend on PCI.
+
 menuconfig VIRTIO_MENU
 	bool "Virtio drivers"
 	default y
@@ -43,6 +52,7 @@ config VIRTIO_PCI_LEGACY
 	bool "Support for legacy virtio draft 0.9.X and older devices"
 	default y
 	depends on VIRTIO_PCI
+	select VIRTIO_PCI_LIB_LEGACY
 	help
           Virtio PCI Card 0.9.X Draft (circa 2014) and older device support.
 

drivers/virtio/Makefile

 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o
 obj-$(CONFIG_VIRTIO_PCI_LIB) += virtio_pci_modern_dev.o
+obj-$(CONFIG_VIRTIO_PCI_LIB_LEGACY) += virtio_pci_legacy_dev.o
 obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
 obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
 virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o

drivers/virtio/virtio_pci_common.c

@@ -24,17 +24,46 @@ MODULE_PARM_DESC(force_legacy,
 		 "Force legacy mode for transitional virtio 1 devices");
 #endif
 
-/* wait for pending irq handlers */
-void vp_synchronize_vectors(struct virtio_device *vdev)
+/* disable irq handlers */
+void vp_disable_cbs(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	int i;
 
-	if (vp_dev->intx_enabled)
+	if (vp_dev->intx_enabled) {
+		/*
+		 * The below synchronize() guarantees that any
+		 * interrupt for this line arriving after
+		 * synchronize_irq() has completed is guaranteed to see
+		 * intx_soft_enabled == false.
+		 */
+		WRITE_ONCE(vp_dev->intx_soft_enabled, false);
 		synchronize_irq(vp_dev->pci_dev->irq);
+	}
 
 	for (i = 0; i < vp_dev->msix_vectors; ++i)
-		synchronize_irq(pci_irq_vector(vp_dev->pci_dev, i));
+		disable_irq(pci_irq_vector(vp_dev->pci_dev, i));
+}
+
+/* enable irq handlers */
+void vp_enable_cbs(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	int i;
+
+	if (vp_dev->intx_enabled) {
+		disable_irq(vp_dev->pci_dev->irq);
+		/*
+		 * The above disable_irq() provides TSO ordering and
+		 * as such promotes the below store to store-release.
+		 */
+		WRITE_ONCE(vp_dev->intx_soft_enabled, true);
+		enable_irq(vp_dev->pci_dev->irq);
+		return;
+	}
+
+	for (i = 0; i < vp_dev->msix_vectors; ++i)
+		enable_irq(pci_irq_vector(vp_dev->pci_dev, i));
 }
 
 /* the notify function used when creating a virt queue */
@@ -84,6 +113,9 @@ static irqreturn_t vp_interrupt(int irq, void *opaque)
 	struct virtio_pci_device *vp_dev = opaque;
 	u8 isr;
 
+	if (!READ_ONCE(vp_dev->intx_soft_enabled))
+		return IRQ_NONE;
+
 	/* reading the ISR has the effect of also clearing it so it's very
 	 * important to save off the value. */
 	isr = ioread8(vp_dev->isr);
@@ -141,7 +173,8 @@ static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
 	snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
 		 "%s-config", name);
 	err = request_irq(pci_irq_vector(vp_dev->pci_dev, v),
-			  vp_config_changed, 0, vp_dev->msix_names[v],
+			  vp_config_changed, IRQF_NO_AUTOEN,
+			  vp_dev->msix_names[v],
 			  vp_dev);
 	if (err)
 		goto error;
@@ -160,7 +193,8 @@ static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
 		snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
 			 "%s-virtqueues", name);
 		err = request_irq(pci_irq_vector(vp_dev->pci_dev, v),
-				  vp_vring_interrupt, 0, vp_dev->msix_names[v],
+				  vp_vring_interrupt, IRQF_NO_AUTOEN,
+				  vp_dev->msix_names[v],
 				  vp_dev);
 		if (err)
 			goto error;
@@ -337,7 +371,7 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
 			 "%s-%s",
 			 dev_name(&vp_dev->vdev.dev), names[i]);
 		err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec),
-				  vring_interrupt, 0,
+				  vring_interrupt, IRQF_NO_AUTOEN,
 				  vp_dev->msix_names[msix_vec],
 				  vqs[i]);
 		if (err)
@@ -549,6 +583,8 @@ static int virtio_pci_probe(struct pci_dev *pci_dev,
 
 	pci_set_master(pci_dev);
 
+	vp_dev->is_legacy = vp_dev->ldev.ioaddr ? true : false;
+
 	rc = register_virtio_device(&vp_dev->vdev);
 	reg_dev = vp_dev;
 	if (rc)
@@ -557,10 +593,10 @@ static int virtio_pci_probe(struct pci_dev *pci_dev,
 	return 0;
 
 err_register:
-	if (vp_dev->ioaddr)
-	     virtio_pci_legacy_remove(vp_dev);
+	if (vp_dev->is_legacy)
+		virtio_pci_legacy_remove(vp_dev);
 	else
-	     virtio_pci_modern_remove(vp_dev);
+		virtio_pci_modern_remove(vp_dev);
 err_probe:
 	pci_disable_device(pci_dev);
 err_enable_device:
@@ -587,7 +623,7 @@ static void virtio_pci_remove(struct pci_dev *pci_dev)
 
 	unregister_virtio_device(&vp_dev->vdev);
 
-	if (vp_dev->ioaddr)
+	if (vp_dev->is_legacy)
 		virtio_pci_legacy_remove(vp_dev);
 	else
 		virtio_pci_modern_remove(vp_dev);

drivers/virtio/virtio_pci_common.h

@@ -25,6 +25,7 @@
 #include <linux/virtio_config.h>
 #include <linux/virtio_ring.h>
 #include <linux/virtio_pci.h>
+#include <linux/virtio_pci_legacy.h>
 #include <linux/virtio_pci_modern.h>
 #include <linux/highmem.h>
 #include <linux/spinlock.h>
@@ -44,16 +45,14 @@ struct virtio_pci_vq_info {
 struct virtio_pci_device {
 	struct virtio_device vdev;
 	struct pci_dev *pci_dev;
+	struct virtio_pci_legacy_device ldev;
 	struct virtio_pci_modern_device mdev;
 
-	/* In legacy mode, these two point to within ->legacy. */
+	bool is_legacy;
+
 	/* Where to read and clear interrupt */
 	u8 __iomem *isr;
 
-	/* Legacy only field */
-	/* the IO mapping for the PCI config space */
-	void __iomem *ioaddr;
-
 	/* a list of queues so we can dispatch IRQs */
 	spinlock_t lock;
 	struct list_head virtqueues;
@@ -64,6 +63,7 @@ struct virtio_pci_device {
 	/* MSI-X support */
 	int msix_enabled;
 	int intx_enabled;
+	bool intx_soft_enabled;
 	cpumask_var_t *msix_affinity_masks;
 	/* Name strings for interrupts. This size should be enough,
 	 * and I'm too lazy to allocate each name separately. */
@@ -102,8 +102,10 @@ static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
 	return container_of(vdev, struct virtio_pci_device, vdev);
 }
 
-/* wait for pending irq handlers */
-void vp_synchronize_vectors(struct virtio_device *vdev);
+/* disable irq handlers */
+void vp_disable_cbs(struct virtio_device *vdev);
+/* enable irq handlers */
+void vp_enable_cbs(struct virtio_device *vdev);
 /* the notify function used when creating a virt queue */
 bool vp_notify(struct virtqueue *vq);
 /* the config->del_vqs() implementation */

drivers/virtio/virtio_pci_legacy.c

@@ -14,6 +14,7 @@
  *  Michael S. Tsirkin <mst@redhat.com>
  */
 
+#include "linux/virtio_pci_legacy.h"
 #include "virtio_pci_common.h"
 
 /* virtio config->get_features() implementation */
@@ -23,7 +24,7 @@ static u64 vp_get_features(struct virtio_device *vdev)
 
 	/* When someone needs more than 32 feature bits, we'll need to
 	 * steal a bit to indicate that the rest are somewhere else. */
-	return ioread32(vp_dev->ioaddr + VIRTIO_PCI_HOST_FEATURES);
+	return vp_legacy_get_features(&vp_dev->ldev);
 }
 
 /* virtio config->finalize_features() implementation */
@@ -38,7 +39,7 @@ static int vp_finalize_features(struct virtio_device *vdev)
 	BUG_ON((u32)vdev->features != vdev->features);
 
 	/* We only support 32 feature bits. */
-	iowrite32(vdev->features, vp_dev->ioaddr + VIRTIO_PCI_GUEST_FEATURES);
+	vp_legacy_set_features(&vp_dev->ldev, vdev->features);
 
 	return 0;
 }
@@ -48,7 +49,7 @@ static void vp_get(struct virtio_device *vdev, unsigned offset,
 		   void *buf, unsigned len)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	void __iomem *ioaddr = vp_dev->ioaddr +
+	void __iomem *ioaddr = vp_dev->ldev.ioaddr +
 			VIRTIO_PCI_CONFIG_OFF(vp_dev->msix_enabled) +
 			offset;
 	u8 *ptr = buf;
@@ -64,7 +65,7 @@ static void vp_set(struct virtio_device *vdev, unsigned offset,
 		   const void *buf, unsigned len)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	void __iomem *ioaddr = vp_dev->ioaddr +
+	void __iomem *ioaddr = vp_dev->ldev.ioaddr +
 			VIRTIO_PCI_CONFIG_OFF(vp_dev->msix_enabled) +
 			offset;
 	const u8 *ptr = buf;
@@ -78,7 +79,7 @@ static void vp_set(struct virtio_device *vdev, unsigned offset,
 static u8 vp_get_status(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	return ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+	return vp_legacy_get_status(&vp_dev->ldev);
 }
 
 static void vp_set_status(struct virtio_device *vdev, u8 status)
@@ -86,28 +87,24 @@ static void vp_set_status(struct virtio_device *vdev, u8 status)
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	/* We should never be setting status to 0. */
 	BUG_ON(status == 0);
-	iowrite8(status, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+	vp_legacy_set_status(&vp_dev->ldev, status);
 }
 
 static void vp_reset(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	/* 0 status means a reset. */
-	iowrite8(0, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+	vp_legacy_set_status(&vp_dev->ldev, 0);
 	/* Flush out the status write, and flush in device writes,
 	 * including MSi-X interrupts, if any. */
-	ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
-	/* Flush pending VQ/configuration callbacks. */
-	vp_synchronize_vectors(vdev);
+	vp_legacy_get_status(&vp_dev->ldev);
+	/* Disable VQ/configuration callbacks. */
+	vp_disable_cbs(vdev);
 }
 
 static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 {
-	/* Setup the vector used for configuration events */
-	iowrite16(vector, vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
-	/* Verify we had enough resources to assign the vector */
-	/* Will also flush the write out to device */
-	return ioread16(vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+	return vp_legacy_config_vector(&vp_dev->ldev, vector);
 }
 
 static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
@@ -123,12 +120,9 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	int err;
 	u64 q_pfn;
 
-	/* Select the queue we're interested in */
-	iowrite16(index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
-
 	/* Check if queue is either not available or already active. */
-	num = ioread16(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NUM);
-	if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
+	num = vp_legacy_get_queue_size(&vp_dev->ldev, index);
+	if (!num || vp_legacy_get_queue_enable(&vp_dev->ldev, index))
 		return ERR_PTR(-ENOENT);
 
 	info->msix_vector = msix_vec;
@@ -151,13 +145,12 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	}
 
 	/* activate the queue */
-	iowrite32(q_pfn, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+	vp_legacy_set_queue_address(&vp_dev->ldev, index, q_pfn);
 
-	vq->priv = (void __force *)vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY;
+	vq->priv = (void __force *)vp_dev->ldev.ioaddr + VIRTIO_PCI_QUEUE_NOTIFY;
 
 	if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
-		iowrite16(msix_vec, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
-		msix_vec = ioread16(vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+		msix_vec = vp_legacy_queue_vector(&vp_dev->ldev, index, msix_vec);
 		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
 			err = -EBUSY;
 			goto out_deactivate;
@@ -167,7 +160,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	return vq;
 
 out_deactivate:
-	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+	vp_legacy_set_queue_address(&vp_dev->ldev, index, 0);
 out_del_vq:
 	vring_del_virtqueue(vq);
 	return ERR_PTR(err);
@@ -178,22 +171,21 @@ static void del_vq(struct virtio_pci_vq_info *info)
 	struct virtqueue *vq = info->vq;
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 
-	iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
-
 	if (vp_dev->msix_enabled) {
-		iowrite16(VIRTIO_MSI_NO_VECTOR,
-			  vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+		vp_legacy_queue_vector(&vp_dev->ldev, vq->index,
+				VIRTIO_MSI_NO_VECTOR);
 		/* Flush the write out to device */
-		ioread8(vp_dev->ioaddr + VIRTIO_PCI_ISR);
+		ioread8(vp_dev->ldev.ioaddr + VIRTIO_PCI_ISR);
 	}
 
 	/* Select and deactivate the queue */
-	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+	vp_legacy_set_queue_address(&vp_dev->ldev, vq->index, 0);
 
 	vring_del_virtqueue(vq);
 }
 
 static const struct virtio_config_ops virtio_pci_config_ops = {
+	.enable_cbs	= vp_enable_cbs,
 	.get		= vp_get,
 	.set		= vp_set,
 	.get_status	= vp_get_status,
@@ -211,51 +203,18 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 /* the PCI probing function */
 int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev)
 {
+	struct virtio_pci_legacy_device *ldev = &vp_dev->ldev;
 	struct pci_dev *pci_dev = vp_dev->pci_dev;
 	int rc;
 
-	/* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */
-	if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f)
-		return -ENODEV;
-
-	if (pci_dev->revision != VIRTIO_PCI_ABI_VERSION) {
-		printk(KERN_ERR "virtio_pci: expected ABI version %d, got %d\n",
-		       VIRTIO_PCI_ABI_VERSION, pci_dev->revision);
-		return -ENODEV;
-	}
-
-	rc = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(64));
-	if (rc) {
-		rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32));
-	} else {
-		/*
-		 * The virtio ring base address is expressed as a 32-bit PFN,
-		 * with a page size of 1 << VIRTIO_PCI_QUEUE_ADDR_SHIFT.
-		 */
-		dma_set_coherent_mask(&pci_dev->dev,
-				DMA_BIT_MASK(32 + VIRTIO_PCI_QUEUE_ADDR_SHIFT));
-	}
-
-	if (rc)
-		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
+	ldev->pci_dev = pci_dev;
 
-	rc = pci_request_region(pci_dev, 0, "virtio-pci-legacy");
+	rc = vp_legacy_probe(ldev);
 	if (rc)
 		return rc;
 
-	rc = -ENOMEM;
-	vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0);
-	if (!vp_dev->ioaddr)
-		goto err_iomap;
-
-	vp_dev->isr = vp_dev->ioaddr + VIRTIO_PCI_ISR;
-
-	/* we use the subsystem vendor/device id as the virtio vendor/device
-	 * id.  this allows us to use the same PCI vendor/device id for all
-	 * virtio devices and to identify the particular virtio driver by
-	 * the subsystem ids */
-	vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;
-	vp_dev->vdev.id.device = pci_dev->subsystem_device;
+	vp_dev->isr = ldev->isr;
+	vp_dev->vdev.id = ldev->id;
 
 	vp_dev->vdev.config = &virtio_pci_config_ops;
 
@@ -264,16 +223,11 @@ int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev)
 	vp_dev->del_vq = del_vq;
 
 	return 0;
-
-err_iomap:
-	pci_release_region(pci_dev, 0);
-	return rc;
 }
 
 void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
 {
-	struct pci_dev *pci_dev = vp_dev->pci_dev;
+	struct virtio_pci_legacy_device *ldev = &vp_dev->ldev;
 
-	pci_iounmap(pci_dev, vp_dev->ioaddr);
-	pci_release_region(pci_dev, 0);
+	vp_legacy_remove(ldev);
 }

drivers/virtio/virtio_pci_legacy_dev.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include "linux/virtio_pci.h"
+#include <linux/virtio_pci_legacy.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+
+/*
+ * vp_legacy_probe: probe the legacy virtio pci device, note that the
+ * caller is required to enable PCI device before calling this function.
+ * @ldev: the legacy virtio-pci device
+ *
+ * Return 0 on succeed otherwise fail
+ */
+int vp_legacy_probe(struct virtio_pci_legacy_device *ldev)
+{
+	struct pci_dev *pci_dev = ldev->pci_dev;
+	int rc;
+
+	/* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */
+	if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f)
+		return -ENODEV;
+
+	if (pci_dev->revision != VIRTIO_PCI_ABI_VERSION)
+		return -ENODEV;
+
+	rc = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(64));
+	if (rc) {
+		rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32));
+	} else {
+		/*
+		 * The virtio ring base address is expressed as a 32-bit PFN,
+		 * with a page size of 1 << VIRTIO_PCI_QUEUE_ADDR_SHIFT.
+		 */
+		dma_set_coherent_mask(&pci_dev->dev,
+				DMA_BIT_MASK(32 + VIRTIO_PCI_QUEUE_ADDR_SHIFT));
+	}
+
+	if (rc)
+		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
+
+	rc = pci_request_region(pci_dev, 0, "virtio-pci-legacy");
+	if (rc)
+		return rc;
+
+	ldev->ioaddr = pci_iomap(pci_dev, 0, 0);
+	if (!ldev->ioaddr)
+		goto err_iomap;
+
+	ldev->isr = ldev->ioaddr + VIRTIO_PCI_ISR;
+
+	ldev->id.vendor = pci_dev->subsystem_vendor;
+	ldev->id.device = pci_dev->subsystem_device;
+
+	return 0;
+err_iomap:
+	pci_release_region(pci_dev, 0);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(vp_legacy_probe);
+
+/*
+ * vp_legacy_probe: remove and cleanup the legacy virtio pci device
+ * @ldev: the legacy virtio-pci device
+ */
+void vp_legacy_remove(struct virtio_pci_legacy_device *ldev)
+{
+	struct pci_dev *pci_dev = ldev->pci_dev;
+
+	pci_iounmap(pci_dev, ldev->ioaddr);
+	pci_release_region(pci_dev, 0);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_remove);
+
+/*
+ * vp_legacy_get_features - get features from device
+ * @ldev: the legacy virtio-pci device
+ *
+ * Returns the features read from the device
+ */
+u64 vp_legacy_get_features(struct virtio_pci_legacy_device *ldev)
+{
+
+	return ioread32(ldev->ioaddr + VIRTIO_PCI_HOST_FEATURES);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_get_features);
+
+/*
+ * vp_legacy_get_driver_features - get driver features from device
+ * @ldev: the legacy virtio-pci device
+ *
+ * Returns the driver features read from the device
+ */
+u64 vp_legacy_get_driver_features(struct virtio_pci_legacy_device *ldev)
+{
+	return ioread32(ldev->ioaddr + VIRTIO_PCI_GUEST_FEATURES);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_get_driver_features);
+
+/*
+ * vp_legacy_set_features - set features to device
+ * @ldev: the legacy virtio-pci device
+ * @features: the features set to device
+ */
+void vp_legacy_set_features(struct virtio_pci_legacy_device *ldev,
+			    u32 features)
+{
+	iowrite32(features, ldev->ioaddr + VIRTIO_PCI_GUEST_FEATURES);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_set_features);
+
+/*
+ * vp_legacy_get_status - get the device status
+ * @ldev: the legacy virtio-pci device
+ *
+ * Returns the status read from device
+ */
+u8 vp_legacy_get_status(struct virtio_pci_legacy_device *ldev)
+{
+	return ioread8(ldev->ioaddr + VIRTIO_PCI_STATUS);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_get_status);
+
+/*
+ * vp_legacy_set_status - set status to device
+ * @ldev: the legacy virtio-pci device
+ * @status: the status set to device
+ */
+void vp_legacy_set_status(struct virtio_pci_legacy_device *ldev,
+				 u8 status)
+{
+	iowrite8(status, ldev->ioaddr + VIRTIO_PCI_STATUS);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_set_status);
+
+/*
+ * vp_legacy_queue_vector - set the MSIX vector for a specific virtqueue
+ * @ldev: the legacy virtio-pci device
+ * @index: queue index
+ * @vector: the config vector
+ *
+ * Returns the config vector read from the device
+ */
+u16 vp_legacy_queue_vector(struct virtio_pci_legacy_device *ldev,
+			   u16 index, u16 vector)
+{
+	iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+	iowrite16(vector, ldev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+	/* Flush the write out to device */
+	return ioread16(ldev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_queue_vector);
+
+/*
+ * vp_legacy_config_vector - set the vector for config interrupt
+ * @ldev: the legacy virtio-pci device
+ * @vector: the config vector
+ *
+ * Returns the config vector read from the device
+ */
+u16 vp_legacy_config_vector(struct virtio_pci_legacy_device *ldev,
+			    u16 vector)
+{
+	/* Setup the vector used for configuration events */
+	iowrite16(vector, ldev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+	/* Verify we had enough resources to assign the vector */
+	/* Will also flush the write out to device */
+	return ioread16(ldev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_config_vector);
+
+/*
+ * vp_legacy_set_queue_address - set the virtqueue address
+ * @ldev: the legacy virtio-pci device
+ * @index: the queue index
+ * @queue_pfn: pfn of the virtqueue
+ */
+void vp_legacy_set_queue_address(struct virtio_pci_legacy_device *ldev,
+			     u16 index, u32 queue_pfn)
+{
+	iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+	iowrite32(queue_pfn, ldev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_set_queue_address);
+
+/*
+ * vp_legacy_get_queue_enable - enable a virtqueue
+ * @ldev: the legacy virtio-pci device
+ * @index: the queue index
+ *
+ * Returns whether a virtqueue is enabled or not
+ */
+bool vp_legacy_get_queue_enable(struct virtio_pci_legacy_device *ldev,
+				u16 index)
+{
+	iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+	return ioread32(ldev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_get_queue_enable);
+
+/*
+ * vp_legacy_get_queue_size - get size for a virtqueue
+ * @ldev: the legacy virtio-pci device
+ * @index: the queue index
+ *
+ * Returns the size of the virtqueue
+ */
+u16 vp_legacy_get_queue_size(struct virtio_pci_legacy_device *ldev,
+			     u16 index)
+{
+	iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+	return ioread16(ldev->ioaddr + VIRTIO_PCI_QUEUE_NUM);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_get_queue_size);
+
+MODULE_VERSION("0.1");
+MODULE_DESCRIPTION("Legacy Virtio PCI Device");
+MODULE_AUTHOR("Wu Zongyong <wuzongyong@linux.alibaba.com>");
+MODULE_LICENSE("GPL");

drivers/virtio/virtio_pci_modern.c

@@ -172,8 +172,8 @@ static void vp_reset(struct virtio_device *vdev)
 	 */
 	while (vp_modern_get_status(mdev))
 		msleep(1);
-	/* Flush pending VQ/configuration callbacks. */
-	vp_synchronize_vectors(vdev);
+	/* Disable VQ/configuration callbacks. */
+	vp_disable_cbs(vdev);
 }
 
 static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
@@ -380,6 +380,7 @@ static bool vp_get_shm_region(struct virtio_device *vdev,
 }
 
 static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
+	.enable_cbs	= vp_enable_cbs,
 	.get		= NULL,
 	.set		= NULL,
 	.generation	= vp_generation,
@@ -397,6 +398,7 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 };
 
 static const struct virtio_config_ops virtio_pci_config_ops = {
+	.enable_cbs	= vp_enable_cbs,
 	.get		= vp_get,
 	.set		= vp_set,
 	.generation	= vp_generation,

drivers/virtio/virtio_ring.c

@@ -14,6 +14,9 @@
 #include <linux/spinlock.h>
 #include <xen/xen.h>
 
+static bool force_used_validation = false;
+module_param(force_used_validation, bool, 0444);
+
 #ifdef DEBUG
 /* For development, we want to crash whenever the ring is screwed. */
 #define BAD_RING(_vq, fmt, args...)				\
@@ -79,8 +82,8 @@ struct vring_desc_state_packed {
 };
 
 struct vring_desc_extra {
-	dma_addr_t addr;		/* Buffer DMA addr. */
-	u32 len;			/* Buffer length. */
+	dma_addr_t addr;		/* Descriptor DMA addr. */
+	u32 len;			/* Descriptor length. */
 	u16 flags;			/* Descriptor flags. */
 	u16 next;			/* The next desc state in a list. */
 };
@@ -182,6 +185,9 @@ struct vring_virtqueue {
 		} packed;
 	};
 
+	/* Per-descriptor in buffer length */
+	u32 *buflen;
+
 	/* How to notify other side. FIXME: commonalize hcalls! */
 	bool (*notify)(struct virtqueue *vq);
 
@@ -490,6 +496,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 	unsigned int i, n, avail, descs_used, prev, err_idx;
 	int head;
 	bool indirect;
+	u32 buflen = 0;
 
 	START_USE(vq);
 
@@ -571,6 +578,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 						     VRING_DESC_F_NEXT |
 						     VRING_DESC_F_WRITE,
 						     indirect);
+			buflen += sg->length;
 		}
 	}
 	/* Last one doesn't continue. */
@@ -610,6 +618,10 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 	else
 		vq->split.desc_state[head].indir_desc = ctx;
 
+	/* Store in buffer length if necessary */
+	if (vq->buflen)
+		vq->buflen[head] = buflen;
+
 	/* Put entry in available array (but don't update avail->idx until they
 	 * do sync). */
 	avail = vq->split.avail_idx_shadow & (vq->split.vring.num - 1);
@@ -784,6 +796,11 @@ static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq,
 		BAD_RING(vq, "id %u is not a head!\n", i);
 		return NULL;
 	}
+	if (vq->buflen && unlikely(*len > vq->buflen[i])) {
+		BAD_RING(vq, "used len %d is larger than in buflen %u\n",
+			*len, vq->buflen[i]);
+		return NULL;
+	}
 
 	/* detach_buf_split clears data, so grab it now. */
 	ret = vq->split.desc_state[i].data;
@@ -1050,21 +1067,24 @@ static struct vring_packed_desc *alloc_indirect_packed(unsigned int total_sg,
 }
 
 static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
-				       struct scatterlist *sgs[],
-				       unsigned int total_sg,
-				       unsigned int out_sgs,
-				       unsigned int in_sgs,
-				       void *data,
-				       gfp_t gfp)
+					 struct scatterlist *sgs[],
+					 unsigned int total_sg,
+					 unsigned int out_sgs,
+					 unsigned int in_sgs,
+					 void *data,
+					 gfp_t gfp)
 {
 	struct vring_packed_desc *desc;
 	struct scatterlist *sg;
 	unsigned int i, n, err_idx;
 	u16 head, id;
 	dma_addr_t addr;
+	u32 buflen = 0;
 
 	head = vq->packed.next_avail_idx;
 	desc = alloc_indirect_packed(total_sg, gfp);
+	if (!desc)
+		return -ENOMEM;
 
 	if (unlikely(vq->vq.num_free < 1)) {
 		pr_debug("Can't add buf len 1 - avail = 0\n");
@@ -1089,6 +1109,8 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
 			desc[i].addr = cpu_to_le64(addr);
 			desc[i].len = cpu_to_le32(sg->length);
 			i++;
+			if (n >= out_sgs)
+				buflen += sg->length;
 		}
 	}
 
@@ -1142,6 +1164,10 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
 	vq->packed.desc_state[id].indir_desc = desc;
 	vq->packed.desc_state[id].last = id;
 
+	/* Store in buffer length if necessary */
+	if (vq->buflen)
+		vq->buflen[id] = buflen;
+
 	vq->num_added += 1;
 
 	pr_debug("Added buffer head %i to %p\n", head, vq);
@@ -1176,6 +1202,8 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
 	unsigned int i, n, c, descs_used, err_idx;
 	__le16 head_flags, flags;
 	u16 head, id, prev, curr, avail_used_flags;
+	int err;
+	u32 buflen = 0;
 
 	START_USE(vq);
 
@@ -1191,9 +1219,14 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
 
 	BUG_ON(total_sg == 0);
 
-	if (virtqueue_use_indirect(_vq, total_sg))
-		return virtqueue_add_indirect_packed(vq, sgs, total_sg,
-				out_sgs, in_sgs, data, gfp);
+	if (virtqueue_use_indirect(_vq, total_sg)) {
+		err = virtqueue_add_indirect_packed(vq, sgs, total_sg, out_sgs,
+						    in_sgs, data, gfp);
+		if (err != -ENOMEM)
+			return err;
+
+		/* fall back on direct */
+	}
 
 	head = vq->packed.next_avail_idx;
 	avail_used_flags = vq->packed.avail_used_flags;
@@ -1250,6 +1283,8 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
 					1 << VRING_PACKED_DESC_F_AVAIL |
 					1 << VRING_PACKED_DESC_F_USED;
 			}
+			if (n >= out_sgs)
+				buflen += sg->length;
 		}
 	}
 
@@ -1269,6 +1304,10 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
 	vq->packed.desc_state[id].indir_desc = ctx;
 	vq->packed.desc_state[id].last = prev;
 
+	/* Store in buffer length if necessary */
+	if (vq->buflen)
+		vq->buflen[id] = buflen;
+
 	/*
 	 * A driver MUST NOT make the first descriptor in the list
 	 * available before all subsequent descriptors comprising
@@ -1455,6 +1494,11 @@ static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq,
 		BAD_RING(vq, "id %u is not a head!\n", id);
 		return NULL;
 	}
+	if (vq->buflen && unlikely(*len > vq->buflen[id])) {
+		BAD_RING(vq, "used len %d is larger than in buflen %u\n",
+			*len, vq->buflen[id]);
+		return NULL;
+	}
 
 	/* detach_buf_packed clears data, so grab it now. */
 	ret = vq->packed.desc_state[id].data;
@@ -1660,6 +1704,7 @@ static struct virtqueue *vring_create_virtqueue_packed(
 	struct vring_virtqueue *vq;
 	struct vring_packed_desc *ring;
 	struct vring_packed_desc_event *driver, *device;
+	struct virtio_driver *drv = drv_to_virtio(vdev->dev.driver);
 	dma_addr_t ring_dma_addr, driver_event_dma_addr, device_event_dma_addr;
 	size_t ring_size_in_bytes, event_size_in_bytes;
 
@@ -1749,6 +1794,15 @@ static struct virtqueue *vring_create_virtqueue_packed(
 	if (!vq->packed.desc_extra)
 		goto err_desc_extra;
 
+	if (!drv->suppress_used_validation || force_used_validation) {
+		vq->buflen = kmalloc_array(num, sizeof(*vq->buflen),
+					   GFP_KERNEL);
+		if (!vq->buflen)
+			goto err_buflen;
+	} else {
+		vq->buflen = NULL;
+	}
+
 	/* No callback?  Tell other side not to bother us. */
 	if (!callback) {
 		vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE;
@@ -1761,6 +1815,8 @@ static struct virtqueue *vring_create_virtqueue_packed(
 	spin_unlock(&vdev->vqs_list_lock);
 	return &vq->vq;
 
+err_buflen:
+	kfree(vq->packed.desc_extra);
 err_desc_extra:
 	kfree(vq->packed.desc_state);
 err_desc_state:
@@ -2168,6 +2224,7 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 					void (*callback)(struct virtqueue *),
 					const char *name)
 {
+	struct virtio_driver *drv = drv_to_virtio(vdev->dev.driver);
 	struct vring_virtqueue *vq;
 
 	if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED))
@@ -2227,6 +2284,15 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	if (!vq->split.desc_extra)
 		goto err_extra;
 
+	if (!drv->suppress_used_validation || force_used_validation) {
+		vq->buflen = kmalloc_array(vring.num, sizeof(*vq->buflen),
+					   GFP_KERNEL);
+		if (!vq->buflen)
+			goto err_buflen;
+	} else {
+		vq->buflen = NULL;
+	}
+
 	/* Put everything in free lists. */
 	vq->free_head = 0;
 	memset(vq->split.desc_state, 0, vring.num *
@@ -2237,6 +2303,8 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	spin_unlock(&vdev->vqs_list_lock);
 	return &vq->vq;
 
+err_buflen:
+	kfree(vq->split.desc_extra);
 err_extra:
 	kfree(vq->split.desc_state);
 err_state:

drivers/virtio/virtio_vdpa.c

@@ -65,9 +65,8 @@ static void virtio_vdpa_set(struct virtio_device *vdev, unsigned offset,
 			    const void *buf, unsigned len)
 {
 	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
-	const struct vdpa_config_ops *ops = vdpa->config;
 
-	ops->set_config(vdpa, offset, buf, len);
+	vdpa_set_config(vdpa, offset, buf, len);
 }
 
 static u32 virtio_vdpa_generation(struct virtio_device *vdev)
@@ -145,7 +144,8 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index,
 	/* Assume split virtqueue, switch to packed if necessary */
 	struct vdpa_vq_state state = {0};
 	unsigned long flags;
-	u32 align, num;
+	u32 align, max_num, min_num = 1;
+	bool may_reduce_num = true;
 	int err;
 
 	if (!name)
@@ -163,16 +163,21 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index,
 	if (!info)
 		return ERR_PTR(-ENOMEM);
 
-	num = ops->get_vq_num_max(vdpa);
-	if (num == 0) {
+	max_num = ops->get_vq_num_max(vdpa);
+	if (max_num == 0) {
 		err = -ENOENT;
 		goto error_new_virtqueue;
 	}
 
+	if (ops->get_vq_num_min)
+		min_num = ops->get_vq_num_min(vdpa);
+
+	may_reduce_num = (max_num == min_num) ? false : true;
+
 	/* Create the vring */
 	align = ops->get_vq_align(vdpa);
-	vq = vring_create_virtqueue(index, num, align, vdev,
-				    true, true, ctx,
+	vq = vring_create_virtqueue(index, max_num, align, vdev,
+				    true, may_reduce_num, ctx,
 				    virtio_vdpa_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;

include/linux/vdpa.h

@@ -6,6 +6,8 @@
 #include <linux/device.h>
 #include <linux/interrupt.h>
 #include <linux/vhost_iotlb.h>
+#include <linux/virtio_net.h>
+#include <linux/if_ether.h>
 
 /**
  * struct vdpa_calllback - vDPA callback definition.
@@ -63,6 +65,7 @@ struct vdpa_mgmt_dev;
  * @dev: underlying device
  * @dma_dev: the actual device that is performing DMA
  * @config: the configuration ops for this device.
+ * @cf_mutex: Protects get and set access to configuration layout.
  * @index: device index
  * @features_valid: were features initialized? for legacy guests
  * @use_va: indicate whether virtual address must be used by this device
@@ -74,6 +77,7 @@ struct vdpa_device {
 	struct device dev;
 	struct device *dma_dev;
 	const struct vdpa_config_ops *config;
+	struct mutex cf_mutex; /* Protects get/set config */
 	unsigned int index;
 	bool features_valid;
 	bool use_va;
@@ -91,6 +95,14 @@ struct vdpa_iova_range {
 	u64 last;
 };
 
+struct vdpa_dev_set_config {
+	struct {
+		u8 mac[ETH_ALEN];
+		u16 mtu;
+	} net;
+	u64 mask;
+};
+
 /**
  * Corresponding file area for device memory mapping
  * @file: vma->vm_file for the mapping
@@ -171,6 +183,9 @@ struct vdpa_map_file {
  * @get_vq_num_max:		Get the max size of virtqueue
  *				@vdev: vdpa device
  *				Returns u16: max size of virtqueue
+ * @get_vq_num_min:		Get the min size of virtqueue (optional)
+ *				@vdev: vdpa device
+ *				Returns u16: min size of virtqueue
  * @get_device_id:		Get virtio device id
  *				@vdev: vdpa device
  *				Returns u32: virtio device id
@@ -257,7 +272,7 @@ struct vdpa_config_ops {
 	struct vdpa_notification_area
 	(*get_vq_notification)(struct vdpa_device *vdev, u16 idx);
 	/* vq irq is not expected to be changed once DRIVER_OK is set */
-	int (*get_vq_irq)(struct vdpa_device *vdv, u16 idx);
+	int (*get_vq_irq)(struct vdpa_device *vdev, u16 idx);
 
 	/* Device ops */
 	u32 (*get_vq_align)(struct vdpa_device *vdev);
@@ -266,6 +281,7 @@ struct vdpa_config_ops {
 	void (*set_config_cb)(struct vdpa_device *vdev,
 			      struct vdpa_callback *cb);
 	u16 (*get_vq_num_max)(struct vdpa_device *vdev);
+	u16 (*get_vq_num_min)(struct vdpa_device *vdev);
 	u32 (*get_device_id)(struct vdpa_device *vdev);
 	u32 (*get_vendor_id)(struct vdpa_device *vdev);
 	u8 (*get_status)(struct vdpa_device *vdev);
@@ -382,26 +398,16 @@ static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features)
 	return ops->set_features(vdev, features);
 }
 
-static inline void vdpa_get_config(struct vdpa_device *vdev,
-				   unsigned int offset, void *buf,
-				   unsigned int len)
-{
-	const struct vdpa_config_ops *ops = vdev->config;
-
-	/*
-	 * Config accesses aren't supposed to trigger before features are set.
-	 * If it does happen we assume a legacy guest.
-	 */
-	if (!vdev->features_valid)
-		vdpa_set_features(vdev, 0);
-	ops->get_config(vdev, offset, buf, len);
-}
-
+void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset,
+		     void *buf, unsigned int len);
+void vdpa_set_config(struct vdpa_device *dev, unsigned int offset,
+		     const void *buf, unsigned int length);
 /**
  * struct vdpa_mgmtdev_ops - vdpa device ops
  * @dev_add: Add a vdpa device using alloc and register
  *	     @mdev: parent device to use for device addition
  *	     @name: name of the new vdpa device
+ *	     @config: config attributes to apply to the device under creation
  *	     Driver need to add a new device using _vdpa_register_device()
  *	     after fully initializing the vdpa device. Driver must return 0
  *	     on success or appropriate error code.
@@ -412,14 +418,25 @@ static inline void vdpa_get_config(struct vdpa_device *vdev,
  *	     _vdpa_unregister_device().
  */
 struct vdpa_mgmtdev_ops {
-	int (*dev_add)(struct vdpa_mgmt_dev *mdev, const char *name);
+	int (*dev_add)(struct vdpa_mgmt_dev *mdev, const char *name,
+		       const struct vdpa_dev_set_config *config);
 	void (*dev_del)(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev);
 };
 
+/**
+ * struct vdpa_mgmt_dev - vdpa management device
+ * @device: Management parent device
+ * @ops: operations supported by management device
+ * @id_table: Pointer to device id table of supported ids
+ * @config_attr_mask: bit mask of attributes of type enum vdpa_attr that
+ *		      management device support during dev_add callback
+ * @list: list entry
+ */
 struct vdpa_mgmt_dev {
 	struct device *device;
 	const struct vdpa_mgmtdev_ops *ops;
-	const struct virtio_device_id *id_table; /* supported ids */
+	const struct virtio_device_id *id_table;
+	u64 config_attr_mask;
 	struct list_head list;
 };
 

include/linux/virtio.h

@@ -152,6 +152,7 @@ size_t virtio_max_dma_size(struct virtio_device *vdev);
  * @feature_table_size: number of entries in the feature table array.
  * @feature_table_legacy: same as feature_table but when working in legacy mode.
  * @feature_table_size_legacy: number of entries in feature table legacy array.
+ * @suppress_used_validation: set to not have core validate used length
  * @probe: the function to call when a device is found.  Returns 0 or -errno.
  * @scan: optional function to call after successful probe; intended
  *    for virtio-scsi to invoke a scan.
@@ -168,6 +169,7 @@ struct virtio_driver {
 	unsigned int feature_table_size;
 	const unsigned int *feature_table_legacy;
 	unsigned int feature_table_size_legacy;
+	bool suppress_used_validation;
 	int (*validate)(struct virtio_device *dev);
 	int (*probe)(struct virtio_device *dev);
 	void (*scan)(struct virtio_device *dev);

include/linux/virtio_config.h

@@ -23,6 +23,8 @@ struct virtio_shm_region {
  *       any of @get/@set, @get_status/@set_status, or @get_features/
  *       @finalize_features are NOT safe to be called from an atomic
  *       context.
+ * @enable_cbs: enable the callbacks
+ *      vdev: the virtio_device
  * @get: read the value of a configuration field
  *	vdev: the virtio_device
  *	offset: the offset of the configuration field
@@ -75,6 +77,7 @@ struct virtio_shm_region {
  */
 typedef void vq_callback_t(struct virtqueue *);
 struct virtio_config_ops {
+	void (*enable_cbs)(struct virtio_device *vdev);
 	void (*get)(struct virtio_device *vdev, unsigned offset,
 		    void *buf, unsigned len);
 	void (*set)(struct virtio_device *vdev, unsigned offset,
@@ -229,6 +232,9 @@ void virtio_device_ready(struct virtio_device *dev)
 {
 	unsigned status = dev->config->get_status(dev);
 
+	if (dev->config->enable_cbs)
+                  dev->config->enable_cbs(dev);
+
 	BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK);
 	dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK);
 }

include/linux/virtio_pci_legacy.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_VIRTIO_PCI_LEGACY_H
+#define _LINUX_VIRTIO_PCI_LEGACY_H
+
+#include "linux/mod_devicetable.h"
+#include <linux/pci.h>
+#include <linux/virtio_pci.h>
+
+struct virtio_pci_legacy_device {
+	struct pci_dev *pci_dev;
+
+	/* Where to read and clear interrupt */
+	u8 __iomem *isr;
+	/* The IO mapping for the PCI config space (legacy mode only) */
+	void __iomem *ioaddr;
+
+	struct virtio_device_id id;
+};
+
+u64 vp_legacy_get_features(struct virtio_pci_legacy_device *ldev);
+u64 vp_legacy_get_driver_features(struct virtio_pci_legacy_device *ldev);
+void vp_legacy_set_features(struct virtio_pci_legacy_device *ldev,
+			u32 features);
+u8 vp_legacy_get_status(struct virtio_pci_legacy_device *ldev);
+void vp_legacy_set_status(struct virtio_pci_legacy_device *ldev,
+			u8 status);
+u16 vp_legacy_queue_vector(struct virtio_pci_legacy_device *ldev,
+			   u16 idx, u16 vector);
+u16 vp_legacy_config_vector(struct virtio_pci_legacy_device *ldev,
+		     u16 vector);
+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);
+void vp_legacy_remove(struct virtio_pci_legacy_device *ldev);
+
+#endif

include/uapi/linux/vdpa.h

@@ -17,6 +17,7 @@ enum vdpa_command {
 	VDPA_CMD_DEV_NEW,
 	VDPA_CMD_DEV_DEL,
 	VDPA_CMD_DEV_GET,		/* can dump */
+	VDPA_CMD_DEV_CONFIG_GET,	/* can dump */
 };
 
 enum vdpa_attr {
@@ -32,6 +33,12 @@ enum vdpa_attr {
 	VDPA_ATTR_DEV_VENDOR_ID,		/* u32 */
 	VDPA_ATTR_DEV_MAX_VQS,			/* u32 */
 	VDPA_ATTR_DEV_MAX_VQ_SIZE,		/* u16 */
+	VDPA_ATTR_DEV_MIN_VQ_SIZE,		/* u16 */
+
+	VDPA_ATTR_DEV_NET_CFG_MACADDR,		/* binary */
+	VDPA_ATTR_DEV_NET_STATUS,		/* u8 */
+	VDPA_ATTR_DEV_NET_CFG_MAX_VQP,		/* u16 */
+	VDPA_ATTR_DEV_NET_CFG_MTU,		/* u16 */
 
 	/* new attributes must be added above here */
 	VDPA_ATTR_MAX,

include/uapi/linux/virtio_i2c.h

@@ -11,9 +11,15 @@
 #include <linux/const.h>
 #include <linux/types.h>
 
+/* Virtio I2C Feature bits */
+#define VIRTIO_I2C_F_ZERO_LENGTH_REQUEST	0
+
 /* The bit 0 of the @virtio_i2c_out_hdr.@flags, used to group the requests */
 #define VIRTIO_I2C_FLAGS_FAIL_NEXT	_BITUL(0)
 
+/* The bit 1 of the @virtio_i2c_out_hdr.@flags, used to mark a buffer as read */
+#define VIRTIO_I2C_FLAGS_M_RD		_BITUL(1)
+
 /**
  * struct virtio_i2c_out_hdr - the virtio I2C message OUT header
  * @addr: the controlled device address