[RFC PATCH V2 7/8] vhost: packed ring support
Signed-off-by: Jason Wang--- drivers/vhost/net.c | 5 +- drivers/vhost/vhost.c | 530 ++ drivers/vhost/vhost.h | 7 +- 3 files changed, 505 insertions(+), 37 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 7be8b55..84905d5 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -67,7 +67,8 @@ enum { VHOST_NET_FEATURES = VHOST_FEATURES | (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) | (1ULL << VIRTIO_NET_F_MRG_RXBUF) | -(1ULL << VIRTIO_F_IOMMU_PLATFORM) +(1ULL << VIRTIO_F_IOMMU_PLATFORM) | +(1ULL << VIRTIO_F_RING_PACKED) }; enum { @@ -706,6 +707,8 @@ static void handle_rx(struct vhost_net *net) vq_log = unlikely(vhost_has_feature(vq, VHOST_F_LOG_ALL)) ? vq->log : NULL; mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF); + /* FIXME: workaround for current dpdk prototype */ + mergeable = false; while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk))) { sock_len += sock_hlen; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index dcac4d4..6177e4d 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -324,6 +324,7 @@ static void vhost_vq_reset(struct vhost_dev *dev, vhost_reset_is_le(vq); vhost_disable_cross_endian(vq); vq->busyloop_timeout = 0; + vq->used_wrap_counter = true; vq->umem = NULL; vq->iotlb = NULL; __vhost_vq_meta_reset(vq); @@ -1136,10 +1137,22 @@ static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access) return 0; } -static int vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, - struct vring_desc __user *desc, - struct vring_avail __user *avail, - struct vring_used __user *used) +static int vq_access_ok_packed(struct vhost_virtqueue *vq, unsigned int num, + struct vring_desc __user *desc, + struct vring_avail __user *avail, + struct vring_used __user *used) +{ + struct vring_desc_packed *packed = (struct vring_desc_packed *)desc; + + /* FIXME: check device area and driver area */ + return access_ok(VERIFY_READ, packed, num * sizeof(*packed)) && + access_ok(VERIFY_WRITE, packed, num * sizeof(*packed)); +} + +static int vq_access_ok_split(struct vhost_virtqueue *vq, unsigned int num, + struct vring_desc __user *desc, + struct vring_avail __user *avail, + struct vring_used __user *used) { size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; @@ -1151,6 +1164,17 @@ static int vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, sizeof *used + num * sizeof *used->ring + s); } +static int vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, + struct vring_desc __user *desc, + struct vring_avail __user *avail, + struct vring_used __user *used) +{ + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) + return vq_access_ok_packed(vq, num, desc, avail, used); + else + return vq_access_ok_split(vq, num, desc, avail, used); +} + static void vhost_vq_meta_update(struct vhost_virtqueue *vq, const struct vhost_umem_node *node, int type) @@ -1763,6 +1787,9 @@ int vhost_vq_init_access(struct vhost_virtqueue *vq) vhost_init_is_le(vq); + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) + return 0; + r = vhost_update_used_flags(vq); if (r) goto err; @@ -1836,7 +1863,8 @@ static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len, /* Each buffer in the virtqueues is actually a chain of descriptors. This * function returns the next descriptor in the chain, * or -1U if we're at the end. */ -static unsigned next_desc(struct vhost_virtqueue *vq, struct vring_desc *desc) +static unsigned next_desc_split(struct vhost_virtqueue *vq, + struct vring_desc *desc) { unsigned int next; @@ -1849,11 +1877,17 @@ static unsigned next_desc(struct vhost_virtqueue *vq, struct vring_desc *desc) return next; } -static int get_indirect(struct vhost_virtqueue *vq, - struct iovec iov[], unsigned int iov_size, - unsigned int *out_num, unsigned int *in_num, - struct vhost_log *log, unsigned int *log_num, - struct vring_desc *indirect) +static unsigned next_desc_packed(struct vhost_virtqueue *vq, +
[RFC PATCH V2 7/8] vhost: packed ring support
Signed-off-by: Jason Wang --- drivers/vhost/net.c | 5 +- drivers/vhost/vhost.c | 530 ++ drivers/vhost/vhost.h | 7 +- 3 files changed, 505 insertions(+), 37 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 7be8b55..84905d5 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -67,7 +67,8 @@ enum { VHOST_NET_FEATURES = VHOST_FEATURES | (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) | (1ULL << VIRTIO_NET_F_MRG_RXBUF) | -(1ULL << VIRTIO_F_IOMMU_PLATFORM) +(1ULL << VIRTIO_F_IOMMU_PLATFORM) | +(1ULL << VIRTIO_F_RING_PACKED) }; enum { @@ -706,6 +707,8 @@ static void handle_rx(struct vhost_net *net) vq_log = unlikely(vhost_has_feature(vq, VHOST_F_LOG_ALL)) ? vq->log : NULL; mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF); + /* FIXME: workaround for current dpdk prototype */ + mergeable = false; while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk))) { sock_len += sock_hlen; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index dcac4d4..6177e4d 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -324,6 +324,7 @@ static void vhost_vq_reset(struct vhost_dev *dev, vhost_reset_is_le(vq); vhost_disable_cross_endian(vq); vq->busyloop_timeout = 0; + vq->used_wrap_counter = true; vq->umem = NULL; vq->iotlb = NULL; __vhost_vq_meta_reset(vq); @@ -1136,10 +1137,22 @@ static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access) return 0; } -static int vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, - struct vring_desc __user *desc, - struct vring_avail __user *avail, - struct vring_used __user *used) +static int vq_access_ok_packed(struct vhost_virtqueue *vq, unsigned int num, + struct vring_desc __user *desc, + struct vring_avail __user *avail, + struct vring_used __user *used) +{ + struct vring_desc_packed *packed = (struct vring_desc_packed *)desc; + + /* FIXME: check device area and driver area */ + return access_ok(VERIFY_READ, packed, num * sizeof(*packed)) && + access_ok(VERIFY_WRITE, packed, num * sizeof(*packed)); +} + +static int vq_access_ok_split(struct vhost_virtqueue *vq, unsigned int num, + struct vring_desc __user *desc, + struct vring_avail __user *avail, + struct vring_used __user *used) { size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; @@ -1151,6 +1164,17 @@ static int vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, sizeof *used + num * sizeof *used->ring + s); } +static int vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, + struct vring_desc __user *desc, + struct vring_avail __user *avail, + struct vring_used __user *used) +{ + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) + return vq_access_ok_packed(vq, num, desc, avail, used); + else + return vq_access_ok_split(vq, num, desc, avail, used); +} + static void vhost_vq_meta_update(struct vhost_virtqueue *vq, const struct vhost_umem_node *node, int type) @@ -1763,6 +1787,9 @@ int vhost_vq_init_access(struct vhost_virtqueue *vq) vhost_init_is_le(vq); + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) + return 0; + r = vhost_update_used_flags(vq); if (r) goto err; @@ -1836,7 +1863,8 @@ static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len, /* Each buffer in the virtqueues is actually a chain of descriptors. This * function returns the next descriptor in the chain, * or -1U if we're at the end. */ -static unsigned next_desc(struct vhost_virtqueue *vq, struct vring_desc *desc) +static unsigned next_desc_split(struct vhost_virtqueue *vq, + struct vring_desc *desc) { unsigned int next; @@ -1849,11 +1877,17 @@ static unsigned next_desc(struct vhost_virtqueue *vq, struct vring_desc *desc) return next; } -static int get_indirect(struct vhost_virtqueue *vq, - struct iovec iov[], unsigned int iov_size, - unsigned int *out_num, unsigned int *in_num, - struct vhost_log *log, unsigned int *log_num, - struct vring_desc *indirect) +static unsigned next_desc_packed(struct vhost_virtqueue *vq, +