search for: tun_pcpu_stat

...ged, 70 insertions(+), 6 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 8c1d3bd..13890ac 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -218,6 +218,7 @@ struct tun_struct { struct list_head disabled; void *security; u32 flow_count; + u32 rx_batched; struct tun_pcpu_stats __percpu *pcpu_stats; }; @@ -522,6 +523,7 @@ static void tun_queue_purge(struct tun_file *tfile) while ((skb = skb_array_consume(&tfile->tx_array)) != NULL) kfree_skb(skb); + skb_queue_purge(&tfile->sk.sk_write_queue); skb_queue_purge(&tfile->sk.sk_error_queue); }...

...ged, 70 insertions(+), 6 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index cd8e02c..6c93926 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -218,6 +218,7 @@ struct tun_struct { struct list_head disabled; void *security; u32 flow_count; + u32 rx_batched; struct tun_pcpu_stats __percpu *pcpu_stats; }; @@ -522,6 +523,7 @@ static void tun_queue_purge(struct tun_file *tfile) while ((skb = skb_array_consume(&tfile->tx_array)) != NULL) kfree_skb(skb); + skb_queue_purge(&tfile->sk.sk_write_queue); skb_queue_purge(&tfile->sk.sk_error_queue); }...

Hi: This series tries to implement tx batching support for vhost. This was done by using MSG_MORE as a hint for under layer socket. The backend (e.g tap) can then batch the packets temporarily in a list and submit it all once the number of bacthed exceeds a limitation. Tests shows obvious improvement on guest pktgen over over mlx4(noqueue) on host: Mpps -+%

Hi: This series tries to implement tx batching support for vhost. This was done by using MSG_MORE as a hint for under layer socket. The backend (e.g tap) can then batch the packets temporarily in a list and submit it all once the number of bacthed exceeds a limitation. Tests shows obvious improvement on guest pktgen over over mlx4(noqueue) on host: Mpps -+%

Hi: This series tries to implement tx batching support for vhost. This was done by using MSG_MORE as a hint for under layer socket. The backend (e.g tap) can then batch the packets temporarily in a list and submit it all once the number of bacthed exceeds a limitation. Tests shows obvious improvement on guest pktgen over over mlx4(noqueue) on host: Mpps -+%

Hi: This series tries to implement tx batching support for vhost. This was done by using MSG_MORE as a hint for under layer socket. The backend (e.g tap) can then batch the packets temporarily in a list and submit it all once the number of bacthed exceeds a limitation. Tests shows obvious improvement on guest pktgen over over mlx4(noqueue) on host: Mpps -+%

...-git a/drivers/net/tun.c b/drivers/net/tun.c > index cd8e02c..6c93926 100644 > --- a/drivers/net/tun.c > +++ b/drivers/net/tun.c > @@ -218,6 +218,7 @@ struct tun_struct { > struct list_head disabled; > void *security; > u32 flow_count; > + u32 rx_batched; > struct tun_pcpu_stats __percpu *pcpu_stats; > }; > > @@ -522,6 +523,7 @@ static void tun_queue_purge(struct tun_file *tfile) > while ((skb = skb_array_consume(&tfile->tx_array)) != NULL) > kfree_skb(skb); > > + skb_queue_purge(&tfile->sk.sk_write_queue); > skb_queue_pur...

...-git a/drivers/net/tun.c b/drivers/net/tun.c > index cd8e02c..6c93926 100644 > --- a/drivers/net/tun.c > +++ b/drivers/net/tun.c > @@ -218,6 +218,7 @@ struct tun_struct { > struct list_head disabled; > void *security; > u32 flow_count; > + u32 rx_batched; > struct tun_pcpu_stats __percpu *pcpu_stats; > }; > > @@ -522,6 +523,7 @@ static void tun_queue_purge(struct tun_file *tfile) > while ((skb = skb_array_consume(&tfile->tx_array)) != NULL) > kfree_skb(skb); > > + skb_queue_purge(&tfile->sk.sk_write_queue); > skb_queue_pur...

...ck_write_space(struct sock *sk) kill_fasync(&tfile->fasync, SIGIO, POLL_OUT); } +static int tun_xdp_one(struct tun_struct *tun, + struct tun_file *tfile, + struct xdp_buff *xdp, int *flush) +{ + struct virtio_net_hdr *gso = xdp->data_hard_start + sizeof(int); + struct tun_pcpu_stats *stats; + struct bpf_prog *xdp_prog; + struct sk_buff *skb = NULL; + u32 rxhash = 0, act; + int buflen = *(int *)xdp->data_hard_start; + int err = 0; + bool skb_xdp = false; + + xdp_prog = rcu_dereference(tun->xdp_prog); + if (xdp_prog) { + if (gso->gso_type) { + skb_xdp = true; + go...

...async(&tfile->fasync, SIGIO, POLL_OUT); > } > > +static int tun_xdp_one(struct tun_struct *tun, > + struct tun_file *tfile, > + struct xdp_buff *xdp, int *flush) > +{ > + struct virtio_net_hdr *gso = xdp->data_hard_start + sizeof(int); > + struct tun_pcpu_stats *stats; > + struct bpf_prog *xdp_prog; > + struct sk_buff *skb = NULL; > + u32 rxhash = 0, act; > + int buflen = *(int *)xdp->data_hard_start; > + int err = 0; > + bool skb_xdp = false; > + > + xdp_prog = rcu_dereference(tun->xdp_prog); > + if (xdp_prog) { > +...

...#include <linux/uio.h> > +#include <linux/skb_array.h> > > #include <asm/uaccess.h> > > @@ -130,6 +131,7 @@ struct tap_filter { > #define MAX_TAP_FLOWS 4096 > > #define TUN_FLOW_EXPIRE (3 * HZ) > +#define TUN_RING_SIZE 256 > > struct tun_pcpu_stats { > u64 rx_packets; > @@ -167,6 +169,7 @@ struct tun_file { > }; > struct list_head next; > struct tun_struct *detached; > + struct skb_array tx_array; > }; > > struct tun_flow_entry { > @@ -513,8 +516,15 @@ static struct tun_struct *tun_enable_queue(struc...

...e <net/sock.h> #include <linux/seq_file.h> #include <linux/uio.h> +#include <linux/skb_array.h> #include <asm/uaccess.h> @@ -130,6 +131,7 @@ struct tap_filter { #define MAX_TAP_FLOWS 4096 #define TUN_FLOW_EXPIRE (3 * HZ) +#define TUN_RING_SIZE 256 struct tun_pcpu_stats { u64 rx_packets; @@ -167,6 +169,7 @@ struct tun_file { }; struct list_head next; struct tun_struct *detached; + struct skb_array tx_array; }; struct tun_flow_entry { @@ -513,8 +516,15 @@ static struct tun_struct *tun_enable_queue(struct tun_file *tfile) return tun; } -static void...

...e <net/sock.h> #include <linux/seq_file.h> #include <linux/uio.h> +#include <linux/skb_array.h> #include <asm/uaccess.h> @@ -130,6 +131,7 @@ struct tap_filter { #define MAX_TAP_FLOWS 4096 #define TUN_FLOW_EXPIRE (3 * HZ) +#define TUN_RING_SIZE 256 struct tun_pcpu_stats { u64 rx_packets; @@ -167,6 +169,7 @@ struct tun_file { }; struct list_head next; struct tun_struct *detached; + struct skb_array tx_array; }; struct tun_flow_entry { @@ -513,8 +516,15 @@ static struct tun_struct *tun_enable_queue(struct tun_file *tfile) return tun; } -static void...

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: 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: 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