search for: get_tx_buf

...NULL, NULL); > + r = vhost_get_avail_buf(tvq, buf, tvq->iov, ARRAY_SIZE(tvq->iov), > + out_num, in_num, NULL, NULL); > } > > return r; > @@ -607,6 +620,7 @@ static size_t init_iov_iter(struct vhost_virtqueue *vq, struct iov_iter *iter, > > static int get_tx_bufs(struct vhost_net *net, > struct vhost_net_virtqueue *nvq, > + struct vhost_buf *buf, > struct msghdr *msg, > unsigned int *out, unsigned int *in, > size_t *len, bool *busyloop_intr) > @@ -614,9 +628,9 @@ static int get_tx_bufs(s...

...ZE(tvq->iov), - out_num, in_num, NULL, NULL); + r = vhost_get_avail_buf(tvq, buf, tvq->iov, ARRAY_SIZE(tvq->iov), + out_num, in_num, NULL, NULL); } return r; @@ -607,6 +620,7 @@ static size_t init_iov_iter(struct vhost_virtqueue *vq, struct iov_iter *iter, static int get_tx_bufs(struct vhost_net *net, struct vhost_net_virtqueue *nvq, + struct vhost_buf *buf, struct msghdr *msg, unsigned int *out, unsigned int *in, size_t *len, bool *busyloop_intr) @@ -614,9 +628,9 @@ static int get_tx_bufs(struct vhost_net *net, struct vho...

...he split of datapath will also be helpful for future implementation like in order completion. Please review. Thanks Jason Wang (9): vhost_net: drop unnecessary parameter vhost_net: introduce helper to initialize tx iov iter vhost_net: introduce vhost_exceeds_weight() vhost_net: introduce get_tx_bufs() vhost_net: introduce tx_can_batch() vhost_net: split out datacopy logic vhost_net: rename vhost_rx_signal_used() to vhost_net_signal_used() vhost_net: rename VHOST_RX_BATCH to VHOST_NET_BATCH vhost_net: batch update used ring for datacopy TX drivers/vhost/net.c | 249 ++++++++++++++++...

...he split of datapath will also be helpful for future implementation like in order completion. Please review. Thanks Jason Wang (9): vhost_net: drop unnecessary parameter vhost_net: introduce helper to initialize tx iov iter vhost_net: introduce vhost_exceeds_weight() vhost_net: introduce get_tx_bufs() vhost_net: introduce tx_can_batch() vhost_net: split out datacopy logic vhost_net: rename vhost_rx_signal_used() to vhost_net_signal_used() vhost_net: rename VHOST_RX_BATCH to VHOST_NET_BATCH vhost_net: batch update used ring for datacopy TX drivers/vhost/net.c | 249 ++++++++++++++++...

...ot INT_MAX. But what does batching have to do with sndbuf? > > > for (;;) { > > > bool busyloop_intr = false; > > > + if (nvq->done_idx == VHOST_NET_BATCH) > > > + vhost_tx_batch(net, nvq, sock, &msg); > > > + > > > head = get_tx_bufs(net, nvq, &msg, &out, &in, &len, > > > &busyloop_intr); > > > /* On error, stop handling until the next kick. */ > > > @@ -577,14 +692,34 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) > > > break;...

...ck_zcopy(vq->private_data)) > - vhost_net_signal_used(nvq); > + vhost_tx_batch(net, nvq, vq->private_data, msghdr); > preempt_disable(); > endtime = busy_clock() + vq->busyloop_timeout; > while (vhost_can_busy_poll(endtime)) { > @@ -512,7 +546,7 @@ static int get_tx_bufs(struct vhost_net *net, > struct vhost_virtqueue *vq = &nvq->vq; > int ret; > > - ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, busyloop_intr); > + ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, msg, busyloop_intr); > > if (ret < 0 || ret == vq->nu...

...ck_zcopy(vq->private_data)) > - vhost_net_signal_used(nvq); > + vhost_tx_batch(net, nvq, vq->private_data, msghdr); > preempt_disable(); > endtime = busy_clock() + vq->busyloop_timeout; > while (vhost_can_busy_poll(endtime)) { > @@ -512,7 +546,7 @@ static int get_tx_bufs(struct vhost_net *net, > struct vhost_virtqueue *vq = &nvq->vq; > int ret; > > - ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, busyloop_intr); > + ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, msg, busyloop_intr); > > if (ret < 0 || ret == vq->nu...

...kets first */ if (!vhost_sock_zcopy(vq->private_data)) - vhost_net_signal_used(nvq); + vhost_tx_batch(net, nvq, vq->private_data, msghdr); preempt_disable(); endtime = busy_clock() + vq->busyloop_timeout; while (vhost_can_busy_poll(endtime)) { @@ -512,7 +546,7 @@ static int get_tx_bufs(struct vhost_net *net, struct vhost_virtqueue *vq = &nvq->vq; int ret; - ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, busyloop_intr); + ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, msg, busyloop_intr); if (ret < 0 || ret == vq->num) return ret; @@ -540,6 +574,83...

...kets first */ if (!vhost_sock_zcopy(vq->private_data)) - vhost_net_signal_used(nvq); + vhost_tx_batch(net, nvq, vq->private_data, msghdr); preempt_disable(); endtime = busy_clock() + vq->busyloop_timeout; while (vhost_can_busy_poll(endtime)) { @@ -512,7 +549,7 @@ static int get_tx_bufs(struct vhost_net *net, struct vhost_virtqueue *vq = &nvq->vq; int ret; - ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, busyloop_intr); + ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, msg, busyloop_intr); if (ret < 0 || ret == vq->num) return ret; @@ -540,6 +577,80...

...a)) >> - vhost_net_signal_used(nvq); >> + vhost_tx_batch(net, nvq, vq->private_data, msghdr); >> preempt_disable(); >> endtime = busy_clock() + vq->busyloop_timeout; >> while (vhost_can_busy_poll(endtime)) { >> @@ -512,7 +546,7 @@ static int get_tx_bufs(struct vhost_net *net, >> struct vhost_virtqueue *vq = &nvq->vq; >> int ret; >> >> - ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, busyloop_intr); >> + ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, msg, busyloop_intr); >> >> i...

We let the specifics of the ring format seep through to vhost API callers - mostly because there was only one format so it was hard to imagine what an independent API would look like. Now that there's an alternative in form of the packed ring, it's easier to see the issues, and fixing them is perhaps the cleanest way to add support for more formats. This patchset does this by indtroducing

...hat.com> I'm very happy with the split, the mixed data path became hard to maintain. > Jason Wang (9): > vhost_net: drop unnecessary parameter > vhost_net: introduce helper to initialize tx iov iter > vhost_net: introduce vhost_exceeds_weight() > vhost_net: introduce get_tx_bufs() > vhost_net: introduce tx_can_batch() > vhost_net: split out datacopy logic > vhost_net: rename vhost_rx_signal_used() to vhost_net_signal_used() > vhost_net: rename VHOST_RX_BATCH to VHOST_NET_BATCH > vhost_net: batch update used ring for datacopy TX > > drivers...

This adds infrastructure required for supporting multiple ring formats. The idea is as follows: we convert descriptors to an independent format first, and process that converting to iov later. Used ring is similar: we fetch into an independent struct first, convert that to IOV later. The point is that we have a tight loop that fetches descriptors, which is good for cache utilization. This will

...ael > > Thanks for your fast reply. > > As the following code, the 2nd branch of iov_iter_advance() does not check if i->count < size, when this happens, i->count -= size may cause len exceed INT_MAX, and then total_len exceed INT_MAX. > > handle_tx_copy() -> > get_tx_bufs(..., &len, ...) -> > init_iov_iter() -> > iov_iter_advance(iter, ...) // has 3 branches: > pipe_advance() // has checked the size: if (unlikely(i->count < size)) size = i->count; > iov_iter_is_discard() ... // no check. Yes, but I don't th...

This adds infrastructure required for supporting multiple ring formats. The idea is as follows: we convert descriptors to an independent format first, and process that converting to iov later. Used ring is similar: we fetch into an independent struct first, convert that to IOV later. The point is that we have a tight loop that fetches descriptors, which is good for cache utilization. This will

...-604,12 +604,6 @@ static size_t init_iov_iter(struct vhost_virtqueue *vq, struct iov_iter *iter, return iov_iter_count(iter); } -static bool vhost_exceeds_weight(int pkts, int total_len) -{ - return total_len >= VHOST_NET_WEIGHT || - pkts >= VHOST_NET_PKT_WEIGHT; -} - static int get_tx_bufs(struct vhost_net *net, struct vhost_net_virtqueue *nvq, struct msghdr *msg, @@ -845,10 +839,8 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head); vq->heads[nvq->done_idx].len = 0;...

This intentionally leaves "fixup" changes separate - hopefully that is enough to fix vhost-net crashes reported here, but it helps me keep track of what changed. I will naturally squash them later when we are done. This adds infrastructure required for supporting multiple ring formats. The idea is as follows: we convert descriptors to an independent format first, and process that

This intentionally leaves "fixup" changes separate - hopefully that is enough to fix vhost-net crashes reported here, but it helps me keep track of what changed. I will naturally squash them later when we are done. This adds infrastructure required for supporting multiple ring formats. The idea is as follows: we convert descriptors to an independent format first, and process that

Hi all: This series implements packed virtqueues which were described at [1]. In this version we try to address the performance regression saw by V2. The root cause is packed virtqueue need more times of userspace memory accesssing which turns out to be very expensive. Thanks to the help of 7f466032dc9e ("vhost: access vq metadata through kernel virtual address"), such overhead cold be

Hi all: This series implements packed virtqueues which were described at [1]. In this version we try to address the performance regression saw by V2. The root cause is packed virtqueue need more times of userspace memory accesssing which turns out to be very expensive. Thanks to the help of 7f466032dc9e ("vhost: access vq metadata through kernel virtual address"), such overhead cold be