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

Pull virtio,vhost,vdpa updates from Michael Tsirkin:

 - Doorbell remapping for ifcvf, mlx5

 - virtio_vdpa support for mlx5

 - Validate device input in several drivers (for SEV and friends)

 - ZONE_MOVABLE aware handling in virtio-mem

 - Misc fixes, cleanups

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (48 commits)
  virtio-mem: prioritize unplug from ZONE_MOVABLE in Big Block Mode
  virtio-mem: simplify high-level unplug handling in Big Block Mode
  virtio-mem: prioritize unplug from ZONE_MOVABLE in Sub Block Mode
  virtio-mem: simplify high-level unplug handling in Sub Block Mode
  virtio-mem: simplify high-level plug handling in Sub Block Mode
  virtio-mem: use page_zonenum() in virtio_mem_fake_offline()
  virtio-mem: don't read big block size in Sub Block Mode
  virtio/vdpa: clear the virtqueue state during probe
  vp_vdpa: allow set vq state to initial state after reset
  virtio-pci library: introduce vp_modern_get_driver_features()
  vdpa: support packed virtqueue for set/get_vq_state()
  virtio-ring: store DMA metadata in desc_extra for split virtqueue
  virtio: use err label in __vring_new_virtqueue()
  virtio_ring: introduce virtqueue_desc_add_split()
  virtio_ring: secure handling of mapping errors
  virtio-ring: factor out desc_extra allocation
  virtio_ring: rename vring_desc_extra_packed
  virtio-ring: maintain next in extra state for packed virtqueue
  vdpa/mlx5: Clear vq ready indication upon device reset
  vdpa/mlx5: Add support for doorbell bypassing
  ...

Author: torvalds

drivers/block/virtio_blk.c

@@ -21,6 +21,9 @@
 #define VQ_NAME_LEN 16
 #define MAX_DISCARD_SEGMENTS 256u
 
+/* The maximum number of sg elements that fit into a virtqueue */
+#define VIRTIO_BLK_MAX_SG_ELEMS 32768
+
 static int major;
 static DEFINE_IDA(vd_index_ida);
 
@@ -447,13 +450,6 @@ static void virtblk_update_capacity(struct virtio_blk *vblk, bool resize)
 	/* Host must always specify the capacity. */
 	virtio_cread(vdev, struct virtio_blk_config, capacity, &capacity);
 
-	/* If capacity is too big, truncate with warning. */
-	if ((sector_t)capacity != capacity) {
-		dev_warn(&vdev->dev, "Capacity %llu too large: truncating\n",
-			 (unsigned long long)capacity);
-		capacity = (sector_t)-1;
-	}
-
 	nblocks = DIV_ROUND_UP_ULL(capacity, queue_logical_block_size(q) >> 9);
 
 	string_get_size(nblocks, queue_logical_block_size(q),
@@ -728,7 +724,10 @@ static int virtblk_probe(struct virtio_device *vdev)
 	if (err || !sg_elems)
 		sg_elems = 1;
 
-	/* We need an extra sg elements at head and tail. */
+	/* Prevent integer overflows and honor max vq size */
+	sg_elems = min_t(u32, sg_elems, VIRTIO_BLK_MAX_SG_ELEMS - 2);
+
+	/* We need extra sg elements at head and tail. */
 	sg_elems += 2;
 	vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);
 	if (!vblk) {
@@ -936,6 +935,8 @@ static int virtblk_freeze(struct virtio_device *vdev)
 	blk_mq_quiesce_queue(vblk->disk->queue);
 
 	vdev->config->del_vqs(vdev);
+	kfree(vblk->vqs);
+
 	return 0;
 }
 

drivers/char/virtio_console.c

@@ -475,7 +475,7 @@ static struct port_buffer *get_inbuf(struct port *port)
 
 	buf = virtqueue_get_buf(port->in_vq, &len);
 	if (buf) {
-		buf->len = len;
+		buf->len = min_t(size_t, len, buf->size);
 		buf->offset = 0;
 		port->stats.bytes_received += len;
 	}
@@ -1709,7 +1709,7 @@ static void control_work_handler(struct work_struct *work)
 	while ((buf = virtqueue_get_buf(vq, &len))) {
 		spin_unlock(&portdev->c_ivq_lock);
 
-		buf->len = len;
+		buf->len = min_t(size_t, len, buf->size);
 		buf->offset = 0;
 
 		handle_control_message(vq->vdev, portdev, buf);

drivers/net/virtio_net.c

@@ -1516,12 +1516,16 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
 		return;
 
 	if (__netif_tx_trylock(txq)) {
-		free_old_xmit_skbs(sq, true);
+		do {
+			virtqueue_disable_cb(sq->vq);
+			free_old_xmit_skbs(sq, true);
+		} while (unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
+
+		if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
+			netif_tx_wake_queue(txq);
+
 		__netif_tx_unlock(txq);
 	}
-
-	if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
-		netif_tx_wake_queue(txq);
 }
 
 static int virtnet_poll(struct napi_struct *napi, int budget)
@@ -1592,6 +1596,8 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 	struct virtnet_info *vi = sq->vq->vdev->priv;
 	unsigned int index = vq2txq(sq->vq);
 	struct netdev_queue *txq;
+	int opaque;
+	bool done;
 
 	if (unlikely(is_xdp_raw_buffer_queue(vi, index))) {
 		/* We don't need to enable cb for XDP */
@@ -1601,14 +1607,32 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 
 	txq = netdev_get_tx_queue(vi->dev, index);
 	__netif_tx_lock(txq, raw_smp_processor_id());
+	virtqueue_disable_cb(sq->vq);
 	free_old_xmit_skbs(sq, true);
-	__netif_tx_unlock(txq);
-
-	virtqueue_napi_complete(napi, sq->vq, 0);
 
 	if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
 		netif_tx_wake_queue(txq);
 
+	opaque = virtqueue_enable_cb_prepare(sq->vq);
+
+	done = napi_complete_done(napi, 0);
+
+	if (!done)
+		virtqueue_disable_cb(sq->vq);
+
+	__netif_tx_unlock(txq);
+
+	if (done) {
+		if (unlikely(virtqueue_poll(sq->vq, opaque))) {
+			if (napi_schedule_prep(napi)) {
+				__netif_tx_lock(txq, raw_smp_processor_id());
+				virtqueue_disable_cb(sq->vq);
+				__netif_tx_unlock(txq);
+				__napi_schedule(napi);
+			}
+		}
+	}
+
 	return 0;
 }
 
@@ -1670,10 +1694,14 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	bool use_napi = sq->napi.weight;
 
 	/* Free up any pending old buffers before queueing new ones. */
-	free_old_xmit_skbs(sq, false);
+	do {
+		if (use_napi)
+			virtqueue_disable_cb(sq->vq);
+
+		free_old_xmit_skbs(sq, false);
 
-	if (use_napi && kick)
-		virtqueue_enable_cb_delayed(sq->vq);
+	} while (use_napi && kick &&
+	       unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
 
 	/* timestamp packet in software */
 	skb_tx_timestamp(skb);
@@ -3310,8 +3338,11 @@ static __maybe_unused int virtnet_restore(struct virtio_device *vdev)
 	virtnet_set_queues(vi, vi->curr_queue_pairs);
 
 	err = virtnet_cpu_notif_add(vi);
-	if (err)
+	if (err) {
+		virtnet_freeze_down(vdev);
+		remove_vq_common(vi);
 		return err;
+	}
 
 	return 0;
 }

drivers/vdpa/ifcvf/ifcvf_base.c

@@ -133,6 +133,8 @@ int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *pdev)
 					      &hw->notify_off_multiplier);
 			hw->notify_bar = cap.bar;
 			hw->notify_base = get_cap_addr(hw, &cap);
+			hw->notify_base_pa = pci_resource_start(pdev, cap.bar) +
+					le32_to_cpu(cap.offset);
 			IFCVF_DBG(pdev, "hw->notify_base = %p\n",
 				  hw->notify_base);
 			break;
@@ -161,6 +163,8 @@ int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *pdev)
 		notify_off = ifc_ioread16(&hw->common_cfg->queue_notify_off);
 		hw->vring[i].notify_addr = hw->notify_base +
 			notify_off * hw->notify_off_multiplier;
+		hw->vring[i].notify_pa = hw->notify_base_pa +
+			notify_off * hw->notify_off_multiplier;
 	}
 
 	hw->lm_cfg = hw->base[IFCVF_LM_BAR];

drivers/vdpa/ifcvf/ifcvf_base.h

@@ -19,21 +19,9 @@
 #include <uapi/linux/virtio_config.h>
 #include <uapi/linux/virtio_pci.h>
 
-#define N3000_VENDOR_ID		0x1AF4
 #define N3000_DEVICE_ID		0x1041
-#define N3000_SUBSYS_VENDOR_ID	0x8086
 #define N3000_SUBSYS_DEVICE_ID	0x001A
 
-#define C5000X_PL_VENDOR_ID		0x1AF4
-#define C5000X_PL_DEVICE_ID		0x1000
-#define C5000X_PL_SUBSYS_VENDOR_ID	0x8086
-#define C5000X_PL_SUBSYS_DEVICE_ID	0x0001
-
-#define C5000X_PL_BLK_VENDOR_ID		0x1AF4
-#define C5000X_PL_BLK_DEVICE_ID		0x1001
-#define C5000X_PL_BLK_SUBSYS_VENDOR_ID	0x8086
-#define C5000X_PL_BLK_SUBSYS_DEVICE_ID	0x0002
-
 #define IFCVF_NET_SUPPORTED_FEATURES \
 		((1ULL << VIRTIO_NET_F_MAC)			| \
 		 (1ULL << VIRTIO_F_ANY_LAYOUT)			| \
@@ -73,6 +61,7 @@ struct vring_info {
 	u16 last_avail_idx;
 	bool ready;
 	void __iomem *notify_addr;
+	phys_addr_t notify_pa;
 	u32 irq;
 	struct vdpa_callback cb;
 	char msix_name[256];
@@ -87,6 +76,7 @@ struct ifcvf_hw {
 	u8 notify_bar;
 	/* Notificaiton bar address */
 	void __iomem *notify_base;
+	phys_addr_t notify_base_pa;
 	u32 notify_off_multiplier;
 	u64 req_features;
 	u64 hw_features;

drivers/vdpa/ifcvf/ifcvf_main.c

@@ -264,7 +264,7 @@ static int ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid,
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
 
-	state->avail_index = ifcvf_get_vq_state(vf, qid);
+	state->split.avail_index = ifcvf_get_vq_state(vf, qid);
 	return 0;
 }
 
@@ -273,7 +273,7 @@ static int ifcvf_vdpa_set_vq_state(struct vdpa_device *vdpa_dev, u16 qid,
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
 
-	return ifcvf_set_vq_state(vf, qid, state->avail_index);
+	return ifcvf_set_vq_state(vf, qid, state->split.avail_index);
 }
 
 static void ifcvf_vdpa_set_vq_cb(struct vdpa_device *vdpa_dev, u16 qid,
@@ -413,6 +413,21 @@ static int ifcvf_vdpa_get_vq_irq(struct vdpa_device *vdpa_dev,
 	return vf->vring[qid].irq;
 }
 
+static struct vdpa_notification_area ifcvf_get_vq_notification(struct vdpa_device *vdpa_dev,
+							       u16 idx)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+	struct vdpa_notification_area area;
+
+	area.addr = vf->vring[idx].notify_pa;
+	if (!vf->notify_off_multiplier)
+		area.size = PAGE_SIZE;
+	else
+		area.size = vf->notify_off_multiplier;
+
+	return area;
+}
+
 /*
  * IFCVF currently does't have on-chip IOMMU, so not
  * implemented set_map()/dma_map()/dma_unmap()
@@ -440,6 +455,7 @@ static const struct vdpa_config_ops ifc_vdpa_ops = {
 	.get_config	= ifcvf_vdpa_get_config,
 	.set_config	= ifcvf_vdpa_set_config,
 	.set_config_cb  = ifcvf_vdpa_set_config_cb,
+	.get_vq_notification = ifcvf_get_vq_notification,
 };
 
 static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
@@ -536,18 +552,21 @@ static void ifcvf_remove(struct pci_dev *pdev)
 }
 
 static struct pci_device_id ifcvf_pci_ids[] = {
-	{ PCI_DEVICE_SUB(N3000_VENDOR_ID,
+	/* N3000 network device */
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_REDHAT_QUMRANET,
 			 N3000_DEVICE_ID,
-			 N3000_SUBSYS_VENDOR_ID,
+			 PCI_VENDOR_ID_INTEL,
 			 N3000_SUBSYS_DEVICE_ID) },
-	{ PCI_DEVICE_SUB(C5000X_PL_VENDOR_ID,
-			 C5000X_PL_DEVICE_ID,
-			 C5000X_PL_SUBSYS_VENDOR_ID,
-			 C5000X_PL_SUBSYS_DEVICE_ID) },
-	{ PCI_DEVICE_SUB(C5000X_PL_BLK_VENDOR_ID,
-			 C5000X_PL_BLK_DEVICE_ID,
-			 C5000X_PL_BLK_SUBSYS_VENDOR_ID,
-			 C5000X_PL_BLK_SUBSYS_DEVICE_ID) },
+	/* C5000X-PL network device */
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_REDHAT_QUMRANET,
+			 VIRTIO_TRANS_ID_NET,
+			 PCI_VENDOR_ID_INTEL,
+			 VIRTIO_ID_NET) },
+	/* C5000X-PL block device */
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_REDHAT_QUMRANET,
+			 VIRTIO_TRANS_ID_BLOCK,
+			 PCI_VENDOR_ID_INTEL,
+			 VIRTIO_ID_BLOCK) },
 
 	{ 0 },
 };

drivers/vdpa/mlx5/core/mlx5_vdpa.h

@@ -35,12 +35,14 @@ struct mlx5_vdpa_mr {
 
 	/* serialize mkey creation and destruction */
 	struct mutex mkey_mtx;
+	bool user_mr;
 };
 
 struct mlx5_vdpa_resources {
 	u32 pdn;
 	struct mlx5_uars_page *uar;
 	void __iomem *kick_addr;
+	u64 phys_kick_addr;
 	u16 uid;
 	u32 null_mkey;
 	bool valid;