summaryrefslogtreecommitdiffstats
path: root/drivers/vhost
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/vhost')
-rw-r--r--drivers/vhost/net.c8
-rw-r--r--drivers/vhost/scsi.c27
-rw-r--r--drivers/vhost/test.c3
-rw-r--r--drivers/vhost/vdpa.c43
-rw-r--r--drivers/vhost/vhost.c5
-rw-r--r--drivers/vhost/vhost.h3
-rw-r--r--drivers/vhost/vringh.c5
-rw-r--r--drivers/vhost/vsock.c216
8 files changed, 162 insertions, 148 deletions
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 9af19b0cf3b7..07181cd8d52e 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -73,7 +73,8 @@ enum {
VHOST_NET_FEATURES = VHOST_FEATURES |
(1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
(1ULL << VIRTIO_NET_F_MRG_RXBUF) |
- (1ULL << VIRTIO_F_ACCESS_PLATFORM)
+ (1ULL << VIRTIO_F_ACCESS_PLATFORM) |
+ (1ULL << VIRTIO_F_RING_RESET)
};
enum {
@@ -1511,6 +1512,9 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
nvq = &n->vqs[index];
mutex_lock(&vq->mutex);
+ if (fd == -1)
+ vhost_clear_msg(&n->dev);
+
/* Verify that ring has been setup correctly. */
if (!vhost_vq_access_ok(vq)) {
r = -EFAULT;
@@ -1642,7 +1646,7 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
goto out_unlock;
if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) {
- if (vhost_init_device_iotlb(&n->dev, true))
+ if (vhost_init_device_iotlb(&n->dev))
goto out_unlock;
}
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index dca6346d75b3..b244e7c0f514 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -80,7 +80,7 @@ struct vhost_scsi_cmd {
struct scatterlist *tvc_prot_sgl;
struct page **tvc_upages;
/* Pointer to response header iovec */
- struct iovec tvc_resp_iov;
+ struct iovec *tvc_resp_iov;
/* Pointer to vhost_scsi for our device */
struct vhost_scsi *tvc_vhost;
/* Pointer to vhost_virtqueue for the cmd */
@@ -563,7 +563,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
memcpy(v_rsp.sense, cmd->tvc_sense_buf,
se_cmd->scsi_sense_length);
- iov_iter_init(&iov_iter, ITER_DEST, &cmd->tvc_resp_iov,
+ iov_iter_init(&iov_iter, ITER_DEST, cmd->tvc_resp_iov,
cmd->tvc_in_iovs, sizeof(v_rsp));
ret = copy_to_iter(&v_rsp, sizeof(v_rsp), &iov_iter);
if (likely(ret == sizeof(v_rsp))) {
@@ -594,6 +594,7 @@ vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
struct vhost_scsi_cmd *cmd;
struct vhost_scsi_nexus *tv_nexus;
struct scatterlist *sg, *prot_sg;
+ struct iovec *tvc_resp_iov;
struct page **pages;
int tag;
@@ -613,6 +614,7 @@ vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
sg = cmd->tvc_sgl;
prot_sg = cmd->tvc_prot_sgl;
pages = cmd->tvc_upages;
+ tvc_resp_iov = cmd->tvc_resp_iov;
memset(cmd, 0, sizeof(*cmd));
cmd->tvc_sgl = sg;
cmd->tvc_prot_sgl = prot_sg;
@@ -625,6 +627,7 @@ vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
cmd->tvc_data_direction = data_direction;
cmd->tvc_nexus = tv_nexus;
cmd->inflight = vhost_scsi_get_inflight(vq);
+ cmd->tvc_resp_iov = tvc_resp_iov;
memcpy(cmd->tvc_cdb, cdb, VHOST_SCSI_MAX_CDB_SIZE);
@@ -935,7 +938,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
struct iov_iter in_iter, prot_iter, data_iter;
u64 tag;
u32 exp_data_len, data_direction;
- int ret, prot_bytes, c = 0;
+ int ret, prot_bytes, i, c = 0;
u16 lun;
u8 task_attr;
bool t10_pi = vhost_has_feature(vq, VIRTIO_SCSI_F_T10_PI);
@@ -1092,7 +1095,8 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
}
cmd->tvc_vhost = vs;
cmd->tvc_vq = vq;
- cmd->tvc_resp_iov = vq->iov[vc.out];
+ for (i = 0; i < vc.in ; i++)
+ cmd->tvc_resp_iov[i] = vq->iov[vc.out + i];
cmd->tvc_in_iovs = vc.in;
pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n",
@@ -1461,6 +1465,7 @@ static void vhost_scsi_destroy_vq_cmds(struct vhost_virtqueue *vq)
kfree(tv_cmd->tvc_sgl);
kfree(tv_cmd->tvc_prot_sgl);
kfree(tv_cmd->tvc_upages);
+ kfree(tv_cmd->tvc_resp_iov);
}
sbitmap_free(&svq->scsi_tags);
@@ -1508,6 +1513,14 @@ static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds)
goto out;
}
+ tv_cmd->tvc_resp_iov = kcalloc(UIO_MAXIOV,
+ sizeof(struct iovec),
+ GFP_KERNEL);
+ if (!tv_cmd->tvc_resp_iov) {
+ pr_err("Unable to allocate tv_cmd->tvc_resp_iov\n");
+ goto out;
+ }
+
tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS,
sizeof(struct scatterlist),
GFP_KERNEL);
@@ -2092,7 +2105,7 @@ static ssize_t vhost_scsi_tpg_attrib_fabric_prot_type_show(
struct vhost_scsi_tpg *tpg = container_of(se_tpg,
struct vhost_scsi_tpg, se_tpg);
- return sprintf(page, "%d\n", tpg->tv_fabric_prot_type);
+ return sysfs_emit(page, "%d\n", tpg->tv_fabric_prot_type);
}
CONFIGFS_ATTR(vhost_scsi_tpg_attrib_, fabric_prot_type);
@@ -2202,7 +2215,7 @@ static ssize_t vhost_scsi_tpg_nexus_show(struct config_item *item, char *page)
mutex_unlock(&tpg->tv_tpg_mutex);
return -ENODEV;
}
- ret = snprintf(page, PAGE_SIZE, "%s\n",
+ ret = sysfs_emit(page, "%s\n",
tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
mutex_unlock(&tpg->tv_tpg_mutex);
@@ -2427,7 +2440,7 @@ static void vhost_scsi_drop_tport(struct se_wwn *wwn)
static ssize_t
vhost_scsi_wwn_version_show(struct config_item *item, char *page)
{
- return sprintf(page, "TCM_VHOST fabric module %s on %s/%s"
+ return sysfs_emit(page, "TCM_VHOST fabric module %s on %s/%s"
"on "UTS_RELEASE"\n", VHOST_SCSI_VERSION, utsname()->sysname,
utsname()->machine);
}
diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c
index bc8e7fb1e635..42c955a5b211 100644
--- a/drivers/vhost/test.c
+++ b/drivers/vhost/test.c
@@ -333,13 +333,10 @@ static long vhost_test_ioctl(struct file *f, unsigned int ioctl,
return -EFAULT;
return 0;
case VHOST_SET_FEATURES:
- printk(KERN_ERR "1\n");
if (copy_from_user(&features, featurep, sizeof features))
return -EFAULT;
- printk(KERN_ERR "2\n");
if (features & ~VHOST_FEATURES)
return -EOPNOTSUPP;
- printk(KERN_ERR "3\n");
return vhost_test_set_features(n, features);
case VHOST_RESET_OWNER:
return vhost_test_reset_owner(n);
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index ec32f785dfde..dc12dbd5b43b 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -359,6 +359,14 @@ static bool vhost_vdpa_can_suspend(const struct vhost_vdpa *v)
return ops->suspend;
}
+static bool vhost_vdpa_can_resume(const struct vhost_vdpa *v)
+{
+ struct vdpa_device *vdpa = v->vdpa;
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ return ops->resume;
+}
+
static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep)
{
struct vdpa_device *vdpa = v->vdpa;
@@ -498,6 +506,21 @@ static long vhost_vdpa_suspend(struct vhost_vdpa *v)
return ops->suspend(vdpa);
}
+/* After a successful return of this ioctl the device resumes processing
+ * virtqueue descriptors. The device becomes fully operational the same way it
+ * was before it was suspended.
+ */
+static long vhost_vdpa_resume(struct vhost_vdpa *v)
+{
+ struct vdpa_device *vdpa = v->vdpa;
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ if (!ops->resume)
+ return -EOPNOTSUPP;
+
+ return ops->resume(vdpa);
+}
+
static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
void __user *argp)
{
@@ -606,11 +629,15 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
if (copy_from_user(&features, featurep, sizeof(features)))
return -EFAULT;
if (features & ~(VHOST_VDPA_BACKEND_FEATURES |
- BIT_ULL(VHOST_BACKEND_F_SUSPEND)))
+ BIT_ULL(VHOST_BACKEND_F_SUSPEND) |
+ BIT_ULL(VHOST_BACKEND_F_RESUME)))
return -EOPNOTSUPP;
if ((features & BIT_ULL(VHOST_BACKEND_F_SUSPEND)) &&
!vhost_vdpa_can_suspend(v))
return -EOPNOTSUPP;
+ if ((features & BIT_ULL(VHOST_BACKEND_F_RESUME)) &&
+ !vhost_vdpa_can_resume(v))
+ return -EOPNOTSUPP;
vhost_set_backend_features(&v->vdev, features);
return 0;
}
@@ -662,6 +689,8 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
features = VHOST_VDPA_BACKEND_FEATURES;
if (vhost_vdpa_can_suspend(v))
features |= BIT_ULL(VHOST_BACKEND_F_SUSPEND);
+ if (vhost_vdpa_can_resume(v))
+ features |= BIT_ULL(VHOST_BACKEND_F_RESUME);
if (copy_to_user(featurep, &features, sizeof(features)))
r = -EFAULT;
break;
@@ -677,6 +706,9 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
case VHOST_VDPA_SUSPEND:
r = vhost_vdpa_suspend(v);
break;
+ case VHOST_VDPA_RESUME:
+ r = vhost_vdpa_resume(v);
+ break;
default:
r = vhost_dev_ioctl(&v->vdev, cmd, argp);
if (r == -ENOIOCTLCMD)
@@ -792,7 +824,7 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
r = ops->set_map(vdpa, asid, iotlb);
} else {
r = iommu_map(v->domain, iova, pa, size,
- perm_to_iommu_flags(perm));
+ perm_to_iommu_flags(perm), GFP_KERNEL);
}
if (r) {
vhost_iotlb_del_range(iotlb, iova, iova + size - 1);
@@ -1119,8 +1151,11 @@ static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v)
if (!bus)
return -EFAULT;
- if (!device_iommu_capable(dma_dev, IOMMU_CAP_CACHE_COHERENCY))
+ if (!device_iommu_capable(dma_dev, IOMMU_CAP_CACHE_COHERENCY)) {
+ dev_warn_once(&v->dev,
+ "Failed to allocate domain, device is not IOMMU cache coherent capable\n");
return -ENOTSUPP;
+ }
v->domain = iommu_domain_alloc(bus);
if (!v->domain)
@@ -1315,7 +1350,7 @@ static int vhost_vdpa_mmap(struct file *file, struct vm_area_struct *vma)
if (vma->vm_end - vma->vm_start != notify.size)
return -ENOTSUPP;
- vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
+ vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
vma->vm_ops = &vhost_vdpa_vm_ops;
return 0;
}
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index cbe72bfd2f1f..f11bdbe4c2c5 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -661,7 +661,7 @@ void vhost_dev_stop(struct vhost_dev *dev)
}
EXPORT_SYMBOL_GPL(vhost_dev_stop);
-static void vhost_clear_msg(struct vhost_dev *dev)
+void vhost_clear_msg(struct vhost_dev *dev)
{
struct vhost_msg_node *node, *n;
@@ -679,6 +679,7 @@ static void vhost_clear_msg(struct vhost_dev *dev)
spin_unlock(&dev->iotlb_lock);
}
+EXPORT_SYMBOL_GPL(vhost_clear_msg);
void vhost_dev_cleanup(struct vhost_dev *dev)
{
@@ -1729,7 +1730,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
}
EXPORT_SYMBOL_GPL(vhost_vring_ioctl);
-int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled)
+int vhost_init_device_iotlb(struct vhost_dev *d)
{
struct vhost_iotlb *niotlb, *oiotlb;
int i;
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index d9109107af08..1647b750169c 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -181,6 +181,7 @@ long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, void __user *argp);
long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp);
bool vhost_vq_access_ok(struct vhost_virtqueue *vq);
bool vhost_log_access_ok(struct vhost_dev *);
+void vhost_clear_msg(struct vhost_dev *dev);
int vhost_get_vq_desc(struct vhost_virtqueue *,
struct iovec iov[], unsigned int iov_count,
@@ -221,7 +222,7 @@ ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to,
int noblock);
ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
struct iov_iter *from);
-int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled);
+int vhost_init_device_iotlb(struct vhost_dev *d);
void vhost_iotlb_map_free(struct vhost_iotlb *iotlb,
struct vhost_iotlb_map *map);
diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c
index 33eb941fcf15..a1e27da54481 100644
--- a/drivers/vhost/vringh.c
+++ b/drivers/vhost/vringh.c
@@ -1126,9 +1126,8 @@ static int iotlb_translate(const struct vringh *vrh,
size = map->size - addr + map->start;
pa = map->addr + addr - map->start;
pfn = pa >> PAGE_SHIFT;
- iov[ret].bv_page = pfn_to_page(pfn);
- iov[ret].bv_len = min(len - s, size);
- iov[ret].bv_offset = pa & (PAGE_SIZE - 1);
+ bvec_set_page(&iov[ret], pfn_to_page(pfn), min(len - s, size),
+ pa & (PAGE_SIZE - 1));
s += size;
addr += size;
++ret;
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index a2b374372363..c8e6087769a1 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -51,8 +51,7 @@ struct vhost_vsock {
struct hlist_node hash;
struct vhost_work send_pkt_work;
- spinlock_t send_pkt_list_lock;
- struct list_head send_pkt_list; /* host->guest pending packets */
+ struct sk_buff_head send_pkt_queue; /* host->guest pending packets */
atomic_t queued_replies;
@@ -108,40 +107,31 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
vhost_disable_notify(&vsock->dev, vq);
do {
- struct virtio_vsock_pkt *pkt;
+ struct virtio_vsock_hdr *hdr;
+ size_t iov_len, payload_len;
struct iov_iter iov_iter;
+ u32 flags_to_restore = 0;
+ struct sk_buff *skb;
unsigned out, in;
size_t nbytes;
- size_t iov_len, payload_len;
int head;
- u32 flags_to_restore = 0;
- spin_lock_bh(&vsock->send_pkt_list_lock);
- if (list_empty(&vsock->send_pkt_list)) {
- spin_unlock_bh(&vsock->send_pkt_list_lock);
+ skb = virtio_vsock_skb_dequeue(&vsock->send_pkt_queue);
+
+ if (!skb) {
vhost_enable_notify(&vsock->dev, vq);
break;
}
- pkt = list_first_entry(&vsock->send_pkt_list,
- struct virtio_vsock_pkt, list);
- list_del_init(&pkt->list);
- spin_unlock_bh(&vsock->send_pkt_list_lock);
-
head = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
&out, &in, NULL, NULL);
if (head < 0) {
- spin_lock_bh(&vsock->send_pkt_list_lock);
- list_add(&pkt->list, &vsock->send_pkt_list);
- spin_unlock_bh(&vsock->send_pkt_list_lock);
+ virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb);
break;
}
if (head == vq->num) {
- spin_lock_bh(&vsock->send_pkt_list_lock);
- list_add(&pkt->list, &vsock->send_pkt_list);
- spin_unlock_bh(&vsock->send_pkt_list_lock);
-
+ virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb);
/* We cannot finish yet if more buffers snuck in while
* re-enabling notify.
*/
@@ -153,26 +143,27 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
}
if (out) {
- virtio_transport_free_pkt(pkt);
+ kfree_skb(skb);
vq_err(vq, "Expected 0 output buffers, got %u\n", out);
break;
}
iov_len = iov_length(&vq->iov[out], in);
- if (iov_len < sizeof(pkt->hdr)) {
- virtio_transport_free_pkt(pkt);
+ if (iov_len < sizeof(*hdr)) {
+ kfree_skb(skb);
vq_err(vq, "Buffer len [%zu] too small\n", iov_len);
break;
}
iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[out], in, iov_len);
- payload_len = pkt->len - pkt->off;
+ payload_len = skb->len;
+ hdr = virtio_vsock_hdr(skb);
/* If the packet is greater than the space available in the
* buffer, we split it using multiple buffers.
*/
- if (payload_len > iov_len - sizeof(pkt->hdr)) {
- payload_len = iov_len - sizeof(pkt->hdr);
+ if (payload_len > iov_len - sizeof(*hdr)) {
+ payload_len = iov_len - sizeof(*hdr);
/* As we are copying pieces of large packet's buffer to
* small rx buffers, headers of packets in rx queue are
@@ -185,31 +176,30 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
* bits set. After initialized header will be copied to
* rx buffer, these required bits will be restored.
*/
- if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOM) {
- pkt->hdr.flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM);
+ if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) {
+ hdr->flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM);
flags_to_restore |= VIRTIO_VSOCK_SEQ_EOM;
- if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) {
- pkt->hdr.flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR);
+ if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOR) {
+ hdr->flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR);
flags_to_restore |= VIRTIO_VSOCK_SEQ_EOR;
}
}
}
/* Set the correct length in the header */
- pkt->hdr.len = cpu_to_le32(payload_len);
+ hdr->len = cpu_to_le32(payload_len);
- nbytes = copy_to_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter);
- if (nbytes != sizeof(pkt->hdr)) {
- virtio_transport_free_pkt(pkt);
+ nbytes = copy_to_iter(hdr, sizeof(*hdr), &iov_iter);
+ if (nbytes != sizeof(*hdr)) {
+ kfree_skb(skb);
vq_err(vq, "Faulted on copying pkt hdr\n");
break;
}
- nbytes = copy_to_iter(pkt->buf + pkt->off, payload_len,
- &iov_iter);
+ nbytes = copy_to_iter(skb->data, payload_len, &iov_iter);
if (nbytes != payload_len) {
- virtio_transport_free_pkt(pkt);
+ kfree_skb(skb);
vq_err(vq, "Faulted on copying pkt buf\n");
break;
}
@@ -217,31 +207,28 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
/* Deliver to monitoring devices all packets that we
* will transmit.
*/
- virtio_transport_deliver_tap_pkt(pkt);
+ virtio_transport_deliver_tap_pkt(skb);
- vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len);
+ vhost_add_used(vq, head, sizeof(*hdr) + payload_len);
added = true;
- pkt->off += payload_len;
+ skb_pull(skb, payload_len);
total_len += payload_len;
/* If we didn't send all the payload we can requeue the packet
* to send it with the next available buffer.
*/
- if (pkt->off < pkt->len) {
- pkt->hdr.flags |= cpu_to_le32(flags_to_restore);
+ if (skb->len > 0) {
+ hdr->flags |= cpu_to_le32(flags_to_restore);
- /* We are queueing the same virtio_vsock_pkt to handle
+ /* We are queueing the same skb to handle
* the remaining bytes, and we want to deliver it
* to monitoring devices in the next iteration.
*/
- pkt->tap_delivered = false;
-
- spin_lock_bh(&vsock->send_pkt_list_lock);
- list_add(&pkt->list, &vsock->send_pkt_list);
- spin_unlock_bh(&vsock->send_pkt_list_lock);
+ virtio_vsock_skb_clear_tap_delivered(skb);
+ virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb);
} else {
- if (pkt->reply) {
+ if (virtio_vsock_skb_reply(skb)) {
int val;
val = atomic_dec_return(&vsock->queued_replies);
@@ -253,7 +240,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
restart_tx = true;
}
- virtio_transport_free_pkt(pkt);
+ consume_skb(skb);
}
} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));
if (added)
@@ -278,28 +265,26 @@ static void vhost_transport_send_pkt_work(struct vhost_work *work)
}
static int
-vhost_transport_send_pkt(struct virtio_vsock_pkt *pkt)
+vhost_transport_send_pkt(struct sk_buff *skb)
{
+ struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb);
struct vhost_vsock *vsock;
- int len = pkt->len;
+ int len = skb->len;
rcu_read_lock();
/* Find the vhost_vsock according to guest context id */
- vsock = vhost_vsock_get(le64_to_cpu(pkt->hdr.dst_cid));
+ vsock = vhost_vsock_get(le64_to_cpu(hdr->dst_cid));
if (!vsock) {
rcu_read_unlock();
- virtio_transport_free_pkt(pkt);
+ kfree_skb(skb);
return -ENODEV;
}
- if (pkt->reply)
+ if (virtio_vsock_skb_reply(skb))
atomic_inc(&vsock->queued_replies);
- spin_lock_bh(&vsock->send_pkt_list_lock);
- list_add_tail(&pkt->list, &vsock->send_pkt_list);
- spin_unlock_bh(&vsock->send_pkt_list_lock);
-
+ virtio_vsock_skb_queue_tail(&vsock->send_pkt_queue, skb);
vhost_work_queue(&vsock->dev, &vsock->send_pkt_work);
rcu_read_unlock();
@@ -310,10 +295,8 @@ static int
vhost_transport_cancel_pkt(struct vsock_sock *vsk)
{
struct vhost_vsock *vsock;
- struct virtio_vsock_pkt *pkt, *n;
int cnt = 0;
int ret = -ENODEV;
- LIST_HEAD(freeme);
rcu_read_lock();
@@ -322,20 +305,7 @@ vhost_transport_cancel_pkt(struct vsock_sock *vsk)
if (!vsock)
goto out;
- spin_lock_bh(&vsock->send_pkt_list_lock);
- list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) {
- if (pkt->vsk != vsk)
- continue;
- list_move(&pkt->list, &freeme);
- }
- spin_unlock_bh(&vsock->send_pkt_list_lock);
-
- list_for_each_entry_safe(pkt, n, &freeme, list) {
- if (pkt->reply)
- cnt++;
- list_del(&pkt->list);
- virtio_transport_free_pkt(pkt);
- }
+ cnt = virtio_transport_purge_skbs(vsk, &vsock->send_pkt_queue);
if (cnt) {
struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX];
@@ -352,12 +322,14 @@ out:
return ret;
}
-static struct virtio_vsock_pkt *
-vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
+static struct sk_buff *
+vhost_vsock_alloc_skb(struct vhost_virtqueue *vq,
unsigned int out, unsigned int in)
{
- struct virtio_vsock_pkt *pkt;
+ struct virtio_vsock_hdr *hdr;
struct iov_iter iov_iter;
+ struct sk_buff *skb;
+ size_t payload_len;
size_t nbytes;
size_t len;
@@ -366,50 +338,48 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
return NULL;
}
- pkt = kzalloc(sizeof(*pkt), GFP_KERNEL);
- if (!pkt)
+ len = iov_length(vq->iov, out);
+
+ /* len contains both payload and hdr */
+ skb = virtio_vsock_alloc_skb(len, GFP_KERNEL);
+ if (!skb)
return NULL;
- len = iov_length(vq->iov, out);
iov_iter_init(&iov_iter, ITER_SOURCE, vq->iov, out, len);
- nbytes = copy_from_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter);
- if (nbytes != sizeof(pkt->hdr)) {
+ hdr = virtio_vsock_hdr(skb);
+ nbytes = copy_from_iter(hdr, sizeof(*hdr), &iov_iter);
+ if (nbytes != sizeof(*hdr)) {
vq_err(vq, "Expected %zu bytes for pkt->hdr, got %zu bytes\n",
- sizeof(pkt->hdr), nbytes);
- kfree(pkt);
+ sizeof(*hdr), nbytes);
+ kfree_skb(skb);
return NULL;
}
- pkt->len = le32_to_cpu(pkt->hdr.len);
+ payload_len = le32_to_cpu(hdr->len);
/* No payload */
- if (!pkt->len)
- return pkt;
+ if (!payload_len)
+ return skb;
- /* The pkt is too big */
- if (pkt->len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) {
- kfree(pkt);
+ /* The pkt is too big or the length in the header is invalid */
+ if (payload_len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE ||
+ payload_len + sizeof(*hdr) > len) {
+ kfree_skb(skb);
return NULL;
}
- pkt->buf = kvmalloc(pkt->len, GFP_KERNEL);
- if (!pkt->buf) {
- kfree(pkt);
- return NULL;
- }
+ virtio_vsock_skb_rx_put(skb);
- pkt->buf_len = pkt->len;
-
- nbytes = copy_from_iter(pkt->buf, pkt->len, &iov_iter);
- if (nbytes != pkt->len) {
- vq_err(vq, "Expected %u byte payload, got %zu bytes\n",
- pkt->len, nbytes);
- virtio_transport_free_pkt(pkt);
+ nbytes = copy_from_iter(skb->data, payload_len, &iov_iter);
+ if (nbytes != payload_len) {
+ vq_err(vq, "Expected %zu byte payload, got %zu bytes\n",
+ payload_len, nbytes);
+ kfree_skb(skb);
return NULL;
}
- return pkt;
+ return skb;
}
/* Is there space left for replies to rx packets? */
@@ -496,9 +466,9 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
poll.work);
struct vhost_vsock *vsock = container_of(vq->dev, struct vhost_vsock,
dev);
- struct virtio_vsock_pkt *pkt;
int head, pkts = 0, total_len = 0;
unsigned int out, in;
+ struct sk_buff *skb;
bool added = false;
mutex_lock(&vq->mutex);
@@ -511,6 +481,8 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
vhost_disable_notify(&vsock->dev, vq);
do {
+ struct virtio_vsock_hdr *hdr;
+
if (!vhost_vsock_more_replies(vsock)) {
/* Stop tx until the device processes already
* pending replies. Leave tx virtqueue
@@ -532,24 +504,26 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
break;
}
- pkt = vhost_vsock_alloc_pkt(vq, out, in);
- if (!pkt) {
+ skb = vhost_vsock_alloc_skb(vq, out, in);
+ if (!skb) {
vq_err(vq, "Faulted on pkt\n");
continue;
}
- total_len += sizeof(pkt->hdr) + pkt->len;
+ total_len += sizeof(*hdr) + skb->len;
/* Deliver to monitoring devices all received packets */
- virtio_transport_deliver_tap_pkt(pkt);
+ virtio_transport_deliver_tap_pkt(skb);
+
+ hdr = virtio_vsock_hdr(skb);
/* Only accept correctly addressed packets */
- if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid &&
- le64_to_cpu(pkt->hdr.dst_cid) ==
+ if (le64_to_cpu(hdr->src_cid) == vsock->guest_cid &&
+ le64_to_cpu(hdr->dst_cid) ==
vhost_transport_get_local_cid())
- virtio_transport_recv_pkt(&vhost_transport, pkt);
+ virtio_transport_recv_pkt(&vhost_transport, skb);
else
- virtio_transport_free_pkt(pkt);
+ kfree_skb(skb);
vhost_add_used(vq, head, 0);
added = true;
@@ -693,8 +667,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
VHOST_VSOCK_WEIGHT, true, NULL);
file->private_data = vsock;
- spin_lock_init(&vsock->send_pkt_list_lock);
- INIT_LIST_HEAD(&vsock->send_pkt_list);
+ skb_queue_head_init(&vsock->send_pkt_queue);
vhost_work_init(&vsock->send_pkt_work, vhost_transport_send_pkt_work);
return 0;
@@ -760,16 +733,7 @@ static int vhost_vsock_dev_release(struct inode *inode, struct file *file)
vhost_vsock_flush(vsock);
vhost_dev_stop(&vsock->dev);
- spin_lock_bh(&vsock->send_pkt_list_lock);
- while (!list_empty(&vsock->send_pkt_list)) {
- struct virtio_vsock_pkt *pkt;
-
- pkt = list_first_entry(&vsock->send_pkt_list,
- struct virtio_vsock_pkt, list);
- list_del_init(&pkt->list);
- virtio_transport_free_pkt(pkt);
- }
- spin_unlock_bh(&vsock->send_pkt_list_lock);
+ virtio_vsock_skb_queue_purge(&vsock->send_pkt_queue);
vhost_dev_cleanup(&vsock->dev);
kfree(vsock->dev.vqs);
@@ -829,7 +793,7 @@ static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features)
}
if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) {
- if (vhost_init_device_iotlb(&vsock->dev, true))
+ if (vhost_init_device_iotlb(&vsock->dev))
goto err;
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-09-19 04:22:48 +0000