search for: tun_msg_ctl

On Thu, Sep 06, 2018 at 12:05:23PM +0800, Jason Wang wrote: > This patch introduces to a new tun/tap specific msg_control: > > #define TUN_MSG_UBUF 1 > #define TUN_MSG_PTR 2 > struct tun_msg_ctl { > int type; > void *ptr; > }; > > This allows us to pass different kinds of msg_control through > sendmsg(). The first supported type is ubuf (TUN_MSG_UBUF) which will > be used by the existed vhost_net zerocopy code. The second is XDP > buff, which allows v...

This patch introduces to a new tun/tap specific msg_control: #define TUN_MSG_UBUF 1 #define TUN_MSG_PTR 2 struct tun_msg_ctl { int type; void *ptr; }; This allows us to pass different kinds of msg_control through sendmsg(). The first supported type is ubuf (TUN_MSG_UBUF) which will be used by the existed vhost_net zerocopy code. The second is XDP buff, which allows vhost_net to pass XDP buff to TUN. This c...

...out: - rcu_read_unlock(); - preempt_enable(); - return err; } static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { - int ret; + int ret, i; struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); struct tun_msg_ctl *ctl = m->msg_control; @@ -2477,10 +2469,28 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) if (!tun) return -EBADFD; - if (ctl && ctl->type == TUN_MSG_PTR) { - ret = tun_xdp_one(tun, tfile, ctl->ptr); - if (!ret) - ret = total_len; + i...

...hanges from V1: - don't hold page refcnt for XDP_DROP - release page if build_skb() fails - introduce a helper to build skb for the path of no batching mode - rename tun_do_xdp() as tun_xdp_act() and use negative for reporting errors instead of a pointer to integer - introduce a num field in tun_msg_ctl - introduce a new structure for storing metadata in the head of XDP packet - do not store batche XDP inside vhoet_net_virtqueue Jason Wang (11): net: sock: introduce SOCK_XDP tuntap: switch to use XDP_PACKET_HEADROOM tuntap: enable bh early during processing XDP tuntap: simplify error ha...

...hanges from V1: - don't hold page refcnt for XDP_DROP - release page if build_skb() fails - introduce a helper to build skb for the path of no batching mode - rename tun_do_xdp() as tun_xdp_act() and use negative for reporting errors instead of a pointer to integer - introduce a num field in tun_msg_ctl - introduce a new structure for storing metadata in the head of XDP packet - do not store batche XDP inside vhoet_net_virtqueue Jason Wang (11): net: sock: introduce SOCK_XDP tuntap: switch to use XDP_PACKET_HEADROOM tuntap: enable bh early during processing XDP tuntap: simplify error ha...

On Wed, Sep 12, 2018 at 11:17:09AM +0800, Jason Wang wrote: > +static void vhost_tx_batch(struct vhost_net *net, > + struct vhost_net_virtqueue *nvq, > + struct socket *sock, > + struct msghdr *msghdr) > +{ > + struct tun_msg_ctl ctl = { > + .type = TUN_MSG_PTR, > + .num = nvq->batched_xdp, > + .ptr = nvq->xdp, > + }; > + int err; > + > + if (nvq->batched_xdp == 0) > + goto signal_used; > + > + msghdr->msg_control = &ctl; > + err = sock->ops->sendmsg(sock, msghdr, 0...

Hi all: This series tries to batch submitting packets to underlayer socket through msg_control during sendmsg(). This is done by: 1) Doing userspace copy inside vhost_net 2) Build XDP buff 3) Batch at most 64 (VHOST_NET_BATCH) XDP buffs and submit them once through msg_control during sendmsg(). 4) Underlayer sockets can use XDP buffs directly when XDP is enalbed, or build skb based on XDP

Hi all: We do not support XDP batching for TUN since it can only receive one packet a time from vhost_net. This series tries to remove this limitation by: - introduce a TUN specific msg_control that can hold a pointer to an array of XDP buffs - try copy and build XDP buff in vhost_net - store XDP buffs in an array and submit them once for every N packets from vhost_net - since TUN can only

...ped) > + tap->count_tx_dropped(tap); > + rcu_read_unlock(); > + return err; > +} > + > static int tap_sendmsg(struct socket *sock, struct msghdr *m, > size_t total_len) > { > struct tap_queue *q = container_of(sock, struct tap_queue, sock); > struct tun_msg_ctl *ctl = m->msg_control; > + struct xdp_buff *xdp; > + int i; > > - if (ctl && ctl->type != TUN_MSG_UBUF) > - return -EINVAL; > + if (ctl && ((ctl->type & 0xF) == TUN_MSG_PTR)) { > + for (i = 0; i < ctl->type >> 16; i++) { > + xdp...

...t;tap); + if (tap && tap->count_tx_dropped) + tap->count_tx_dropped(tap); + rcu_read_unlock(); + return err; +} + static int tap_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { struct tap_queue *q = container_of(sock, struct tap_queue, sock); struct tun_msg_ctl *ctl = m->msg_control; + struct xdp_buff *xdp; + int i; - if (ctl && ctl->type != TUN_MSG_UBUF) - return -EINVAL; + if (ctl && ((ctl->type & 0xF) == TUN_MSG_PTR)) { + for (i = 0; i < ctl->type >> 16; i++) { + xdp = &((struct xdp_buff *)ctl->ptr)...

...+ tun_flow_update(tun, rxhash, tfile); + +out: + return err; +} + static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { - int ret; + int ret, i; struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); struct tun_msg_ctl *ctl = m->msg_control; + struct xdp_buff *xdp; if (!tun) return -EBADFD; - if (ctl && ctl->type != TUN_MSG_UBUF) - return -EINVAL; + if (ctl && ((ctl->type & 0xF) == TUN_MSG_PTR)) { + int n = ctl->type >> 16; + int flush = 0; + + local_bh_disable()...

...t; + return err; > +} > + > static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) > { > - int ret; > + int ret, i; > struct tun_file *tfile = container_of(sock, struct tun_file, socket); > struct tun_struct *tun = tun_get(tfile); > struct tun_msg_ctl *ctl = m->msg_control; > + struct xdp_buff *xdp; > > if (!tun) > return -EBADFD; > > - if (ctl && ctl->type != TUN_MSG_UBUF) > - return -EINVAL; > + if (ctl && ((ctl->type & 0xF) == TUN_MSG_PTR)) { > + int n = ctl->type >>...

...atic void vhost_net_signal_used(struct vhost_net_virtqueue *nvq) > nvq->done_idx = 0; > } > > +static void vhost_tx_batch(struct vhost_net *net, > + struct vhost_net_virtqueue *nvq, > + struct socket *sock, > + struct msghdr *msghdr) > +{ > + struct tun_msg_ctl ctl = { > + .type = nvq->batched_xdp << 16 | TUN_MSG_PTR, > + .ptr = nvq->xdp, > + }; > + int err; > + > + if (nvq->batched_xdp == 0) > + goto signal_used; > + > + msghdr->msg_control = &ctl; > + err = sock->ops->sendmsg(sock, msghdr, 0);...

...atic void vhost_net_signal_used(struct vhost_net_virtqueue *nvq) > nvq->done_idx = 0; > } > > +static void vhost_tx_batch(struct vhost_net *net, > + struct vhost_net_virtqueue *nvq, > + struct socket *sock, > + struct msghdr *msghdr) > +{ > + struct tun_msg_ctl ctl = { > + .type = nvq->batched_xdp << 16 | TUN_MSG_PTR, > + .ptr = nvq->xdp, > + }; > + int err; > + > + if (nvq->batched_xdp == 0) > + goto signal_used; > + > + msghdr->msg_control = &ctl; > + err = sock->ops->sendmsg(sock, msghdr, 0);...

..., we will signal KVM @@ -444,10 +451,36 @@ static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq) nvq->done_idx = 0; } +static void vhost_tx_batch(struct vhost_net *net, + struct vhost_net_virtqueue *nvq, + struct socket *sock, + struct msghdr *msghdr) +{ + struct tun_msg_ctl ctl = { + .type = nvq->batched_xdp << 16 | TUN_MSG_PTR, + .ptr = nvq->xdp, + }; + int err; + + if (nvq->batched_xdp == 0) + goto signal_used; + + msghdr->msg_control = &ctl; + err = sock->ops->sendmsg(sock, msghdr, 0); + if (unlikely(err < 0)) { + vq_err(&nvq-...

..., we will signal KVM @@ -444,10 +453,37 @@ static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq) nvq->done_idx = 0; } +static void vhost_tx_batch(struct vhost_net *net, + struct vhost_net_virtqueue *nvq, + struct socket *sock, + struct msghdr *msghdr) +{ + struct tun_msg_ctl ctl = { + .type = TUN_MSG_PTR, + .num = nvq->batched_xdp, + .ptr = nvq->xdp, + }; + int err; + + if (nvq->batched_xdp == 0) + goto signal_used; + + msghdr->msg_control = &ctl; + err = sock->ops->sendmsg(sock, msghdr, 0); + if (unlikely(err < 0)) { + vq_err(&nvq-&gt...

...vhost_net_virtqueue *nvq) >> nvq->done_idx = 0; >> } >> >> +static void vhost_tx_batch(struct vhost_net *net, >> + struct vhost_net_virtqueue *nvq, >> + struct socket *sock, >> + struct msghdr *msghdr) >> +{ >> + struct tun_msg_ctl ctl = { >> + .type = nvq->batched_xdp << 16 | TUN_MSG_PTR, >> + .ptr = nvq->xdp, >> + }; >> + int err; >> + >> + if (nvq->batched_xdp == 0) >> + goto signal_used; >> + >> + msghdr->msg_control = &ctl; >> + err = so...

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