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

Pull vhost,virtio,vdpa bugfixes from Michael Tsirkin:
 "Misc fixes all over the place.

  Revert of virtio used length validation series: the approach taken
  does not seem to work, breaking too many guests in the process. We'll
  need to do length validation using some other approach"

[ This merge also ends up reverting commit f7a36b0 ("vsock/virtio:
  suppress used length validation"), which came in through the
  networking tree in the meantime, and was part of that whole used
  length validation series   - Linus ]

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  vdpa_sim: avoid putting an uninitialized iova_domain
  vhost-vdpa: clean irqs before reseting vdpa device
  virtio-blk: modify the value type of num in virtio_queue_rq()
  vhost/vsock: cleanup removing `len` variable
  vhost/vsock: fix incorrect used length reported to the guest
  Revert "virtio_ring: validate used buffer length"
  Revert "virtio-net: don't let virtio core to validate used length"
  Revert "virtio-blk: don't let virtio core to validate used length"
  Revert "virtio-scsi: don't let virtio core to validate used buffer length"

Author: torvalds

drivers/block/virtio_blk.c

@@ -316,7 +316,7 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct request *req = bd->rq;
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
 	unsigned long flags;
-	unsigned int num;
+	int num;
 	int qid = hctx->queue_num;
 	bool notify = false;
 	blk_status_t status;
@@ -1049,7 +1049,6 @@ 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/net/virtio_net.c

@@ -3423,7 +3423,6 @@ 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

@@ -977,7 +977,6 @@ 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/vdpa_sim/vdpa_sim.c

@@ -591,8 +591,11 @@ static void vdpasim_free(struct vdpa_device *vdpa)
 		vringh_kiov_cleanup(&vdpasim->vqs[i].in_iov);
 	}
 
-	put_iova_domain(&vdpasim->iova);
-	iova_cache_put();
+	if (vdpa_get_dma_dev(vdpa)) {
+		put_iova_domain(&vdpasim->iova);
+		iova_cache_put();
+	}
+
 	kvfree(vdpasim->buffer);
 	if (vdpasim->iommu)
 		vhost_iotlb_free(vdpasim->iommu);

drivers/vhost/vdpa.c

@@ -1014,12 +1014,12 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep)
 
 	mutex_lock(&d->mutex);
 	filep->private_data = NULL;
+	vhost_vdpa_clean_irq(v);
 	vhost_vdpa_reset(v);
 	vhost_dev_stop(&v->vdev);
 	vhost_vdpa_iotlb_free(v);
 	vhost_vdpa_free_domain(v);
 	vhost_vdpa_config_put(v);
-	vhost_vdpa_clean_irq(v);
 	vhost_dev_cleanup(&v->vdev);
 	kfree(v->vdev.vqs);
 	mutex_unlock(&d->mutex);

drivers/vhost/vsock.c

@@ -511,8 +511,6 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 
 	vhost_disable_notify(&vsock->dev, vq);
 	do {
-		u32 len;
-
 		if (!vhost_vsock_more_replies(vsock)) {
 			/* Stop tx until the device processes already
 			 * pending replies.  Leave tx virtqueue
@@ -540,7 +538,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 			continue;
 		}
 
-		len = pkt->len;
+		total_len += sizeof(pkt->hdr) + pkt->len;
 
 		/* Deliver to monitoring devices all received packets */
 		virtio_transport_deliver_tap_pkt(pkt);
@@ -553,9 +551,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 		else
 			virtio_transport_free_pkt(pkt);
 
-		len += sizeof(pkt->hdr);
-		vhost_add_used(vq, head, len);
-		total_len += len;
+		vhost_add_used(vq, head, 0);
 		added = true;
 	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));
 

drivers/virtio/virtio_ring.c

@@ -14,9 +14,6 @@
 #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...)				\
@@ -185,9 +182,6 @@ struct vring_virtqueue {
 		} packed;
 	};
 
-	/* Per-descriptor in buffer length */
-	u32 *buflen;
-
 	/* How to notify other side. FIXME: commonalize hcalls! */
 	bool (*notify)(struct virtqueue *vq);
 
@@ -496,7 +490,6 @@ 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);
 
@@ -578,7 +571,6 @@ 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. */
@@ -618,10 +610,6 @@ 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);
@@ -796,11 +784,6 @@ 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;
@@ -1079,7 +1062,6 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
 	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);
@@ -1109,8 +1091,6 @@ 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;
 		}
 	}
 
@@ -1164,10 +1144,6 @@ 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);
@@ -1203,7 +1179,6 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
 	__le16 head_flags, flags;
 	u16 head, id, prev, curr, avail_used_flags;
 	int err;
-	u32 buflen = 0;
 
 	START_USE(vq);
 
@@ -1283,8 +1258,6 @@ 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;
 		}
 	}
 
@@ -1304,10 +1277,6 @@ 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
@@ -1494,11 +1463,6 @@ 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;
@@ -1704,7 +1668,6 @@ 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;
 
@@ -1794,15 +1757,6 @@ 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;
@@ -1815,8 +1769,6 @@ 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:
@@ -2224,7 +2176,6 @@ 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))
@@ -2284,15 +2235,6 @@ 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 *
@@ -2303,8 +2245,6 @@ 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:

include/linux/virtio.h

@@ -152,7 +152,6 @@ 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.
@@ -169,7 +168,6 @@ 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);

net/vmw_vsock/virtio_transport.c

@@ -731,7 +731,6 @@ static unsigned int features[] = {
 static struct virtio_driver virtio_vsock_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,