Introduce preferred busy-polling
Subsystems (32)
v4 cover Introduce preferred busy-polling
This series introduces three new features:
1. A new "heavy traffic" busy-polling variant that works in concert with the existing napi_defer_hard_irqs and gro_flush_timeout knobs.
2. A new socket option that let a user change the busy-polling NAPI budget.
3. Allow busy-polling to be performed on XDP sockets.
The existing busy-polling mode, enabled by the SO_BUSY_POLL socket option or system-wide using the /proc/sys/net/core/busy_read knob, is an opportunistic. That means that if the NAPI context is not scheduled, it will poll it. If, after busy-polling, the budget is exceeded the busy-polling logic will schedule the NAPI onto the regular softirq handling.
One implication of the behavior above is that a busy/heavy loaded NAPI context will never enter/allow for busy-polling. Some applications prefer that most NAPI processing would be done by busy-polling.
This series adds a new socket option, SO_PREFER_BUSY_POLL, that works in concert with the napi_defer_hard_irqs and gro_flush_timeout knobs. The napi_defer_hard_irqs and gro_flush_timeout knobs were introduced in commit 6f8b12d661d0 ("net: napi: add hard irqs deferral feature"), and allows for a user to defer interrupts to be enabled and instead schedule the NAPI context from a watchdog timer. When a user enables the SO_PREFER_BUSY_POLL, again with the other knobs enabled, and the NAPI context is being processed by a softirq, the softirq NAPI processing will exit early to allow the busy-polling to be performed.
If the application stops performing busy-polling via a system call, the watchdog timer defined by gro_flush_timeout will timeout, and regular softirq handling will resume.
In summary; Heavy traffic applications that prefer busy-polling over softirq processing should use this option.
Patch 6 touches a lot of drivers, so the Cc: list is grossly long.
Example usage:
$ echo 2 | sudo tee /sys/class/net/ens785f1/napi_defer_hard_irqs $ echo 200000 | sudo tee /sys/class/net/ens785f1/gro_flush_timeout
Note that the timeout should be larger than the userspace processing window, otherwise the watchdog will timeout and fall back to regular softirq processing.
Enable the SO_BUSY_POLL/SO_PREFER_BUSY_POLL options on your socket.
Performance simple UDP ping-pong:
A packet generator blasts UDP packets from a packet generator to a certain {src,dst}IP/port, so a dedicated ksoftirq will be busy handling the packets at a certain core.
A simple UDP test program that simply does recvfrom/sendto is running at the host end. Throughput in pps and RTT latency is measured at the packet generator.
/proc/sys/net/core/busy_read is set (20).
Min Max Avg (usec)
1. Blocking 2-cores: 490Kpps
1218.192 1335.427 1271.083
2. Blocking, 1-core: 155Kpps
1327.195 17294.855 4761.367
3. Non-blocking, 2-cores: 475Kpps
1221.197 1330.465 1270.740
4. Non-blocking, 1-core: 3Kpps
29006.482 37260.465 33128.367
5. Non-blocking, prefer busy-poll, 1-core: 420Kpps 1202.535 5494.052 4885.443
Scenario 2 and 5 shows when the new option should be used. Throughput go from 155 to 420Kpps, average latency are similar, but the tail latencies are much better for the latter.
Performance XDP sockets:
Again, a packet generator blasts UDP packets from a packet generator to a certain {src,dst}IP/port.
Today, running XDP sockets sample on the same core as the softirq handling, performance tanks mainly because we do not yield to user-space when the XDP socket Rx queue is full.
# taskset -c 5 ./xdpsock -i ens785f1 -q 5 -n 1 -r Rx: 64Kpps
# # preferred busy-polling, budget 8
# taskset -c 5 ./xdpsock -i ens785f1 -q 5 -n 1 -r -B -b 8 Rx 9.9Mpps # # preferred busy-polling, budget 64 # taskset -c 5 ./xdpsock -i ens785f1 -q 5 -n 1 -r -B -b 64 Rx: 19.3Mpps # # preferred busy-polling, budget 256 # taskset -c 5 ./xdpsock -i ens785f1 -q 5 -n 1 -r -B -b 256 Rx: 21.4Mpps # # preferred busy-polling, budget 512 # taskset -c 5 ./xdpsock -i ens785f1 -q 5 -n 1 -r -B -b 512 Rx: 21.7Mpps
Compared to the two-core case:
# taskset -c 4 ./xdpsock -i ens785f1 -q 20 -n 1 -r Rx: 20.7Mpps
We're getting better single-core performance than two, for this naïve drop scenario.
Performance netperf UDP_RR:
Note that netperf UDP_RR is not a heavy traffic tests, and preferred busy-polling is not typically something we want to use here.
$ echo 20 | sudo tee /proc/sys/net/core/busy_read
$ netperf -H 192.168.1.1 -l 30 -t UDP_RR -v 2 -- \
-o min_latency,mean_latency,max_latency,stddev_latency,transaction_ratebusy-polling blocking sockets: 12,13.33,224,0.63,74731.177
I hacked netperf to use non-blocking sockets and re-ran:
busy-polling non-blocking sockets: 12,13.46,218,0.72,73991.172
prefer busy-polling non-blocking sockets: 12,13.62,221,0.59,73138.448
Using the preferred busy-polling mode does not impact performance.
The above tests was done for the 'ice' driver.
Thanks to Jakub for suggesting this busy-polling addition [1], and Eric for all input/review!
Changes:
rfc-v1 [2] -> rfc-v2:
* Changed name from bias to prefer.
* Base the work on Eric's/Luigi's defer irq/gro timeout work.
* Proper GRO flushing.
* Build issues for some XDP drivers.
rfc-v2 [3] -> v1:
* Fixed broken qlogic build.
* Do not trigger an IPI (XDP socket wakeup) when busy-polling is enabled.
v1 [4] -> v2:
* Added napi_id to socionext driver, and added Ilias Acked-by:. (Ilias)
* Added a samples patch to improve busy-polling for xdpsock/l2fwd.
* Correctly mark atomic operations with {WRITE,READ}_ONCE, to make KCSAN and the code readers happy. (Eric)
* Check NAPI budget not to exceed U16_MAX. (Eric)
* Added kdoc.
v2 [5] -> v3:
* Collected Acked-by.
* Check NAPI disable prior prefer busy-polling. (Jakub)
* Added napi_id registration for virtio-net. (Michael)
* Added napi_id registration for veth.
v3 [6] -> v4:
* Collected Acked-by/Reviewed-by.
[1] https://lore.kernel.org/netdev/20200925120652.10b8d7c5@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com/
[2] https://lore.kernel.org/bpf/[email protected]/
[3] https://lore.kernel.org/bpf/[email protected]/
[4] https://lore.kernel.org/bpf/[email protected]/
[5] https://lore.kernel.org/bpf/[email protected]/
[6] https://lore.kernel.org/bpf/[email protected]/
Björn Töpel (10):
net: introduce preferred busy-polling
net: add SO_BUSY_POLL_BUDGET socket option
xsk: add support for recvmsg()
xsk: check need wakeup flag in sendmsg()
xsk: add busy-poll support for {recv,send}msg()
xsk: propagate napi_id to XDP socket Rx path samples/bpf: use recvfrom() in xdpsock/rxdrop samples/bpf: use recvfrom() in xdpsock/l2fwd samples/bpf: add busy-poll support to xdpsock samples/bpf: add option to set the busy-poll budget
arch/alpha/include/uapi/asm/socket.h | 3 + arch/mips/include/uapi/asm/socket.h | 3 + arch/parisc/include/uapi/asm/socket.h | 3 + arch/sparc/include/uapi/asm/socket.h | 3 + drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- .../ethernet/cavium/thunder/nicvf_queues.c | 2 +- .../net/ethernet/freescale/dpaa2/dpaa2-eth.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 2 +- drivers/net/ethernet/intel/ice/ice_base.c | 4 +- drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- .../net/ethernet/intel/ixgbevf/ixgbevf_main.c | 2 +- drivers/net/ethernet/marvell/mvneta.c | 2 +- .../net/ethernet/marvell/mvpp2/mvpp2_main.c | 4 +- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 +- .../net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- .../ethernet/netronome/nfp/nfp_net_common.c | 2 +- drivers/net/ethernet/qlogic/qede/qede_main.c | 2 +- drivers/net/ethernet/sfc/rx_common.c | 2 +- drivers/net/ethernet/socionext/netsec.c | 2 +- drivers/net/ethernet/ti/cpsw_priv.c | 2 +- drivers/net/hyperv/netvsc.c | 2 +- drivers/net/tun.c | 2 +- drivers/net/veth.c | 12 ++- drivers/net/virtio_net.c | 2 +- drivers/net/xen-netfront.c | 2 +- fs/eventpoll.c | 3 +- include/linux/netdevice.h | 35 +++++--- include/net/busy_poll.h | 27 ++++-- include/net/sock.h | 6 ++ include/net/xdp.h | 3 +- include/uapi/asm-generic/socket.h | 3 + net/core/dev.c | 89 ++++++++++++++----- net/core/sock.c | 19 ++++ net/core/xdp.c | 3 +- net/xdp/xsk.c | 53 ++++++++++- net/xdp/xsk_buff_pool.c | 13 ++- samples/bpf/xdpsock_user.c | 79 ++++++++++------ 40 files changed, 300 insertions(+), 107 deletions(-)
base-commit: bb1b25cab04324d0749f7ae22653aff58157bf83
Signature · 1 line
2.27.0
PATCH v4 1/10 net: introduce preferred busy-polling
From: Björn Töpel <[email protected]>
The existing busy-polling mode, enabled by the SO_BUSY_POLL socket option or system-wide using the /proc/sys/net/core/busy_read knob, is an opportunistic. That means that if the NAPI context is not scheduled, it will poll it. If, after busy-polling, the budget is exceeded the busy-polling logic will schedule the NAPI onto the regular softirq handling.
One implication of the behavior above is that a busy/heavy loaded NAPI context will never enter/allow for busy-polling. Some applications prefer that most NAPI processing would be done by busy-polling.
This series adds a new socket option, SO_PREFER_BUSY_POLL, that works in concert with the napi_defer_hard_irqs and gro_flush_timeout knobs. The napi_defer_hard_irqs and gro_flush_timeout knobs were introduced in commit 6f8b12d661d0 ("net: napi: add hard irqs deferral feature"), and allows for a user to defer interrupts to be enabled and instead schedule the NAPI context from a watchdog timer. When a user enables the SO_PREFER_BUSY_POLL, again with the other knobs enabled, and the NAPI context is being processed by a softirq, the softirq NAPI processing will exit early to allow the busy-polling to be performed.
If the application stops performing busy-polling via a system call, the watchdog timer defined by gro_flush_timeout will timeout, and regular softirq handling will resume.
In summary; Heavy traffic applications that prefer busy-polling over softirq processing should use this option.
Example usage:
$ echo 2 | sudo tee /sys/class/net/ens785f1/napi_defer_hard_irqs $ echo 200000 | sudo tee /sys/class/net/ens785f1/gro_flush_timeout
Note that the timeout should be larger than the userspace processing window, otherwise the watchdog will timeout and fall back to regular softirq processing.
Enable the SO_BUSY_POLL/SO_PREFER_BUSY_POLL options on your socket.
--- arch/alpha/include/uapi/asm/socket.h | 2 + arch/mips/include/uapi/asm/socket.h | 2 + arch/parisc/include/uapi/asm/socket.h | 2 + arch/sparc/include/uapi/asm/socket.h | 2 + fs/eventpoll.c | 2 +- include/linux/netdevice.h | 35 +++++++----- include/net/busy_poll.h | 5 +- include/net/sock.h | 4 ++ include/uapi/asm-generic/socket.h | 2 + net/core/dev.c | 78 +++++++++++++++++++++------ net/core/sock.c | 9 ++++ 11 files changed, 111 insertions(+), 32 deletions(-)
arch/alpha/include/uapi/asm/socket.h +2 -0
@@ -124,6 +124,8 @@#define SO_DETACH_REUSEPORT_BPF 68 +#define SO_PREFER_BUSY_POLL 69 +#if !defined(__KERNEL__)#if __BITS_PER_LONG ==64
arch/mips/include/uapi/asm/socket.h +2 -0
@@ -135,6 +135,8 @@#define SO_DETACH_REUSEPORT_BPF 68 +#define SO_PREFER_BUSY_POLL 69 +#if !defined(__KERNEL__)#if __BITS_PER_LONG ==64
arch/parisc/include/uapi/asm/socket.h +2 -0
@@ -116,6 +116,8 @@#define SO_DETACH_REUSEPORT_BPF 0x4042 +#define SO_PREFER_BUSY_POLL 0x4043 +#if !defined(__KERNEL__)#if __BITS_PER_LONG ==64
arch/sparc/include/uapi/asm/socket.h +2 -0
@@ -117,6 +117,8 @@#define SO_DETACH_REUSEPORT_BPF 0x0047 +#define SO_PREFER_BUSY_POLL 0x0048 +#if !defined(__KERNEL__)
fs/eventpoll.c +1 -1
@@ -397,7 +397,7 @@ static void ep_busy_loop(struct eventpoll *ep, int nonblock)unsigned int napi_id =READ_ONCE (ep->napi_id);if ((napi_id >=MIN_NAPI_ID ) &&net_busy_loop_on ()) -napi_busy_loop (napi_id, nonblock ?NULL : ep_busy_loop_end, ep); +napi_busy_loop (napi_id, nonblock ?NULL : ep_busy_loop_end, ep, false); }static inline void ep_reset_busy_poll_napi_id (struct eventpoll *ep)
include/linux/netdevice.h +21 -14
@@ -350,23 +350,25 @@ struct napi_struct { };enum { -NAPI_STATE_SCHED ,/* Poll is scheduled */ -NAPI_STATE_MISSED ,/* reschedule a napi */ -NAPI_STATE_DISABLE ,/* Disable pending */ -NAPI_STATE_NPSVC ,/* Netpoll - don't dequeue from poll_list */ -NAPI_STATE_LISTED ,/* NAPI added to system lists */ -NAPI_STATE_NO_BUSY_POLL ,/* Do not add in napi_hash, no busy polling */ -NAPI_STATE_IN_BUSY_POLL ,/* sk_busy_loop() owns this NAPI */ +NAPI_STATE_SCHED ,/* Poll is scheduled */ +NAPI_STATE_MISSED ,/* reschedule a napi */ +NAPI_STATE_DISABLE ,/* Disable pending */ +NAPI_STATE_NPSVC ,/* Netpoll - don't dequeue from poll_list */ +NAPI_STATE_LISTED ,/* NAPI added to system lists */ +NAPI_STATE_NO_BUSY_POLL ,/* Do not add in napi_hash, no busy polling */ +NAPI_STATE_IN_BUSY_POLL ,/* sk_busy_loop() owns this NAPI */ +NAPI_STATE_PREFER_BUSY_POLL ,/* prefer busy-polling over softirq processing*/ };enum { -NAPIF_STATE_SCHED =BIT (NAPI_STATE_SCHED ), -NAPIF_STATE_MISSED =BIT (NAPI_STATE_MISSED ), -NAPIF_STATE_DISABLE =BIT (NAPI_STATE_DISABLE ), -NAPIF_STATE_NPSVC =BIT (NAPI_STATE_NPSVC ), -NAPIF_STATE_LISTED =BIT (NAPI_STATE_LISTED ), -NAPIF_STATE_NO_BUSY_POLL =BIT (NAPI_STATE_NO_BUSY_POLL ), -NAPIF_STATE_IN_BUSY_POLL =BIT (NAPI_STATE_IN_BUSY_POLL ), +NAPIF_STATE_SCHED =BIT (NAPI_STATE_SCHED ), +NAPIF_STATE_MISSED =BIT (NAPI_STATE_MISSED ), +NAPIF_STATE_DISABLE =BIT (NAPI_STATE_DISABLE ), +NAPIF_STATE_NPSVC =BIT (NAPI_STATE_NPSVC ), +NAPIF_STATE_LISTED =BIT (NAPI_STATE_LISTED ), +NAPIF_STATE_NO_BUSY_POLL =BIT (NAPI_STATE_NO_BUSY_POLL ), +NAPIF_STATE_IN_BUSY_POLL =BIT (NAPI_STATE_IN_BUSY_POLL ), +NAPIF_STATE_PREFER_BUSY_POLL =BIT (NAPI_STATE_PREFER_BUSY_POLL ), };enum gro_result {
@@ -437,6 +439,11 @@ static inline bool napi_disable_pending(struct napi_struct *n)return test_bit (NAPI_STATE_DISABLE , &n->state); } +static inline bool napi_prefer_busy_poll (struct napi_struct *n) +{ +return test_bit (NAPI_STATE_PREFER_BUSY_POLL , &n->state); +} +bool napi_schedule_prep (struct napi_struct *n);/**
include/net/busy_poll.h +3 -2
@@ -43,7 +43,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time);void napi_busy_loop (unsigned int napi_id,bool (*loop_end)(void *,unsigned long ), -void *loop_end_arg); +void *loop_end_arg,bool prefer_busy_poll);#else /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long net_busy_loop_on (void )
@@ -105,7 +105,8 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock)unsigned int napi_id =READ_ONCE (sk->sk_napi_id);if (napi_id >=MIN_NAPI_ID ) -napi_busy_loop (napi_id, nonblock ?NULL : sk_busy_loop_end, sk); +napi_busy_loop (napi_id, nonblock ?NULL : sk_busy_loop_end, sk, +READ_ONCE (sk->sk_prefer_busy_poll));#endif }
include/net/sock.h +4 -0
@@ -301,6 +301,7 @@ struct bpf_local_storage;* @sk_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() * @sk_uid: user id of owner +* @sk_prefer_busy_poll: prefer busypolling over softirq processing * @sk_priority: %SO_PRIORITY setting * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family
@@ -479,6 +480,9 @@ struct sock {u32 sk_ack_backlog;u32 sk_max_ack_backlog;kuid_t sk_uid; +#ifdef CONFIG_NET_RX_BUSY_POLL +u8 sk_prefer_busy_poll; +#endif struct pid *sk_peer_pid;const struct cred *sk_peer_cred;long sk_rcvtimeo;
include/uapi/asm-generic/socket.h +2 -0
@@ -119,6 +119,8 @@#define SO_DETACH_REUSEPORT_BPF 68 +#define SO_PREFER_BUSY_POLL 69 +#if !defined(__KERNEL__)#if __BITS_PER_LONG ==64 || (defined(__x86_64__) && defined(__ILP32__))
net/core/dev.c +63 -15
149 lines not on this page · raw message
net/core/sock.c +9 -0
@@ -1159,6 +1159,12 @@ int sock_setsockopt(struct socket *sock, int level, int optname, sk->sk_ll_usec = val; }break ; +case SO_PREFER_BUSY_POLL : +if (valbool && !capable (CAP_NET_ADMIN )) + ret = -EPERM ; +else +WRITE_ONCE (sk->sk_prefer_busy_poll, valbool); +break ;#endif case SO_MAX_PACING_RATE :
@@ -1523,6 +1529,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname,case SO_BUSY_POLL : v.val = sk->sk_ll_usec;break ; +case SO_PREFER_BUSY_POLL : + v.val =READ_ONCE (sk->sk_prefer_busy_poll); +break ;#endif case SO_MAX_PACING_RATE :
Signature · 1 line
2.27.0
PATCH v4 2/10 net: add SO_BUSY_POLL_BUDGET socket option
In reply to Björn TöpelFrom: Björn Töpel <[email protected]>
This option lets a user set a per socket NAPI budget for busy-polling. If the options is not set, it will use the default of 8.
--- arch/alpha/include/uapi/asm/socket.h | 1 + arch/mips/include/uapi/asm/socket.h | 1 + arch/parisc/include/uapi/asm/socket.h | 1 + arch/sparc/include/uapi/asm/socket.h | 1 + fs/eventpoll.c | 3 ++- include/net/busy_poll.h | 7 +++++-- include/net/sock.h | 2 ++ include/uapi/asm-generic/socket.h | 1 + net/core/dev.c | 21 ++++++++++----------- net/core/sock.c | 10 ++++++++++ 10 files changed, 34 insertions(+), 14 deletions(-)
arch/alpha/include/uapi/asm/socket.h +1 -0
@@ -125,6 +125,7 @@#define SO_DETACH_REUSEPORT_BPF 68#define SO_PREFER_BUSY_POLL 69 +#define SO_BUSY_POLL_BUDGET 70#if !defined(__KERNEL__)
arch/mips/include/uapi/asm/socket.h +1 -0
@@ -136,6 +136,7 @@#define SO_DETACH_REUSEPORT_BPF 68#define SO_PREFER_BUSY_POLL 69 +#define SO_BUSY_POLL_BUDGET 70#if !defined(__KERNEL__)
arch/parisc/include/uapi/asm/socket.h +1 -0
@@ -117,6 +117,7 @@#define SO_DETACH_REUSEPORT_BPF 0x4042#define SO_PREFER_BUSY_POLL 0x4043 +#define SO_BUSY_POLL_BUDGET 0x4044#if !defined(__KERNEL__)
arch/sparc/include/uapi/asm/socket.h +1 -0
@@ -118,6 +118,7 @@#define SO_DETACH_REUSEPORT_BPF 0x0047#define SO_PREFER_BUSY_POLL 0x0048 +#define SO_BUSY_POLL_BUDGET 0x0049#if !defined(__KERNEL__)
fs/eventpoll.c +2 -1
@@ -397,7 +397,8 @@ static void ep_busy_loop(struct eventpoll *ep, int nonblock)unsigned int napi_id =READ_ONCE (ep->napi_id);if ((napi_id >=MIN_NAPI_ID ) &&net_busy_loop_on ()) -napi_busy_loop (napi_id, nonblock ?NULL : ep_busy_loop_end, ep, false); +napi_busy_loop (napi_id, nonblock ?NULL : ep_busy_loop_end, ep, false, +BUSY_POLL_BUDGET ); }static inline void ep_reset_busy_poll_napi_id (struct eventpoll *ep)
include/net/busy_poll.h +5 -2
@@ -23,6 +23,8 @@*/ #define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1)) +#define BUSY_POLL_BUDGET 8 +#ifdef CONFIG_NET_RX_BUSY_POLL struct napi_struct ;
@@ -43,7 +45,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time);void napi_busy_loop (unsigned int napi_id,bool (*loop_end)(void *,unsigned long ), -void *loop_end_arg,bool prefer_busy_poll); +void *loop_end_arg,bool prefer_busy_poll,u16 budget);#else /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long net_busy_loop_on (void )
@@ -106,7 +108,8 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock)if (napi_id >=MIN_NAPI_ID )napi_busy_loop (napi_id, nonblock ?NULL : sk_busy_loop_end, sk, -READ_ONCE (sk->sk_prefer_busy_poll)); +READ_ONCE (sk->sk_prefer_busy_poll), +READ_ONCE (sk->sk_busy_poll_budget) ?:BUSY_POLL_BUDGET );#endif }
include/net/sock.h +2 -0
@@ -302,6 +302,7 @@ struct bpf_local_storage;* @sk_max_ack_backlog: listen backlog set in listen() * @sk_uid: user id of owner * @sk_prefer_busy_poll: prefer busypolling over softirq processing +* @sk_busy_poll_budget: napi processing budget when busypolling * @sk_priority: %SO_PRIORITY setting * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family
@@ -482,6 +483,7 @@ struct sock {kuid_t sk_uid;#ifdef CONFIG_NET_RX_BUSY_POLL u8 sk_prefer_busy_poll; +u16 sk_busy_poll_budget;#endif struct pid *sk_peer_pid;const struct cred *sk_peer_cred;
include/uapi/asm-generic/socket.h +1 -0
@@ -120,6 +120,7 @@#define SO_DETACH_REUSEPORT_BPF 68#define SO_PREFER_BUSY_POLL 69 +#define SO_BUSY_POLL_BUDGET 70#if !defined(__KERNEL__)
net/core/dev.c +10 -11
@@ -6496,8 +6496,6 @@ static struct napi_struct *napi_by_id(unsigned int napi_id)#if defined(CONFIG_NET_RX_BUSY_POLL ) -#define BUSY_POLL_BUDGET 8 -static void __busy_poll_stop (struct napi_struct *napi,bool skip_schedule) {if (!skip_schedule) {
@@ -6517,7 +6515,8 @@ static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)clear_bit (NAPI_STATE_SCHED , &napi->state); } -static void busy_poll_stop (struct napi_struct *napi,void *have_poll_lock,bool prefer_busy_poll) +static void busy_poll_stop (struct napi_struct *napi,void *have_poll_lock,bool prefer_busy_poll, +u16 budget) {bool skip_schedule = false;unsigned long timeout;
@@ -6549,21 +6548,21 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool/* All we really want here is to re-enable device interrupts. * Ideally, a new ndo_busy_poll_stop() could avoid another round. */ - rc = napi->poll (napi,BUSY_POLL_BUDGET ); + rc = napi->poll (napi, budget);/* We can't gro_normal_list() here, because napi->poll() might have * rearmed the napi (napi_complete_done()) in which case it could * already be running on another CPU. */ -trace_napi_poll (napi, rc,BUSY_POLL_BUDGET ); +trace_napi_poll (napi, rc, budget);netpoll_poll_unlock (have_poll_lock); -if (rc ==BUSY_POLL_BUDGET ) +if (rc == budget)__busy_poll_stop (napi, skip_schedule);local_bh_enable (); }void napi_busy_loop (unsigned int napi_id,bool (*loop_end)(void *,unsigned long ), -void *loop_end_arg,bool prefer_busy_poll) +void *loop_end_arg,bool prefer_busy_poll,u16 budget) {unsigned long start_time = loop_end ?busy_loop_current_time () :0 ;int (*napi_poll)(struct napi_struct *napi,int budget);
@@ -6606,8 +6605,8 @@ void napi_busy_loop(unsigned int napi_id, have_poll_lock =netpoll_poll_lock (napi); napi_poll = napi->poll; } - work =napi_poll (napi,BUSY_POLL_BUDGET ); -trace_napi_poll (napi, work,BUSY_POLL_BUDGET ); + work =napi_poll (napi, budget); +trace_napi_poll (napi, work, budget);gro_normal_list (napi); count:if (work >0 )
@@ -6620,7 +6619,7 @@ void napi_busy_loop(unsigned int napi_id,if (unlikely (need_resched ())) {if (napi_poll) -busy_poll_stop (napi, have_poll_lock, prefer_busy_poll); +busy_poll_stop (napi, have_poll_lock, prefer_busy_poll, budget);preempt_enable ();rcu_read_unlock ();cond_resched ();
@@ -6631,7 +6630,7 @@ void napi_busy_loop(unsigned int napi_id,cpu_relax (); }if (napi_poll) -busy_poll_stop (napi, have_poll_lock, prefer_busy_poll); +busy_poll_stop (napi, have_poll_lock, prefer_busy_poll, budget);preempt_enable (); out:rcu_read_unlock ();
net/core/sock.c +10 -0
@@ -1165,6 +1165,16 @@ int sock_setsockopt(struct socket *sock, int level, int optname, else WRITE_ONCE(sk->sk_prefer_busy_poll, valbool);break ; +case SO_BUSY_POLL_BUDGET : +if (val >READ_ONCE (sk->sk_busy_poll_budget) && !capable (CAP_NET_ADMIN )) { + ret = -EPERM ; + }else { +if (val <0 || val >U16_MAX ) + ret = -EINVAL ; +else +WRITE_ONCE (sk->sk_busy_poll_budget, val); + } +break ;#endif case SO_MAX_PACING_RATE :
Signature · 1 line
2.27.0
PATCH v4 3/10 xsk: add support for recvmsg()
In reply to Björn TöpelFrom: Björn Töpel <[email protected]>
Add support for non-blocking recvmsg() to XDP sockets. Previously, only sendmsg() was supported by XDP socket. Now, for symmetry and the upcoming busy-polling support, recvmsg() is added.
--- net/xdp/xsk.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-)
net/xdp/xsk.c +21 -1
@@ -531,6 +531,26 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)return __xsk_sendmsg (sk); } +static int xsk_recvmsg (struct socket *sock,struct msghdr *m,size_t len,int flags) +{ +bool need_wait = !(flags &MSG_DONTWAIT ); +struct sock *sk = sock->sk; +struct xdp_sock *xs =xdp_sk (sk); + +if (unlikely (!(xs->dev->flags &IFF_UP ))) +return -ENETDOWN ; +if (unlikely (!xs->rx)) +return -ENOBUFS ; +if (unlikely (!xsk_is_bound (xs))) +return -ENXIO ; +if (unlikely (need_wait)) +return -EOPNOTSUPP ; + +if (xs->pool->cached_need_wakeup &XDP_WAKEUP_RX && xs->zc) +return xsk_wakeup (xs,XDP_WAKEUP_RX ); +return 0 ; +} +static __poll_t xsk_poll (struct file *file,struct socket *sock,struct poll_table_struct *wait) {
@@ -1191,7 +1211,7 @@ static const struct proto_ops xsk_proto_ops = { .setsockopt = xsk_setsockopt, .getsockopt = xsk_getsockopt, .sendmsg = xsk_sendmsg, - .recvmsg = sock_no_recvmsg, + .recvmsg = xsk_recvmsg, .mmap = xsk_mmap, .sendpage = sock_no_sendpage, };
Signature · 1 line
2.27.0
PATCH v4 4/10 xsk: check need wakeup flag in sendmsg()
In reply to Björn TöpelFrom: Björn Töpel <[email protected]>
Add a check for need wake up in sendmsg(), so that if a user calls sendmsg() when no wakeup is needed, do not trigger a wakeup.
To simplify the need wakeup check in the syscall, unconditionally enable the need wakeup flag for Tx. This has a side-effect for poll(); If poll() is called for a socket without enabled need wakeup, a Tx wakeup is unconditionally performed.
The wakeup matrix for AF_XDP now looks like:
need wakeup | poll() | sendmsg() | recvmsg()
------------+--------------+-------------+------------
disabled | wake Tx | wake Tx | nop
enabled | check flag; | check flag; | check flag;
| wake Tx/Rx | wake Tx | wake Rx--- net/xdp/xsk.c | 6 +++++- net/xdp/xsk_buff_pool.c | 13 ++++++------- 2 files changed, 11 insertions(+), 8 deletions(-)
net/xdp/xsk.c +5 -1
@@ -522,13 +522,17 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)bool need_wait = !(m->msg_flags &MSG_DONTWAIT );struct sock *sk = sock->sk;struct xdp_sock *xs =xdp_sk (sk); +struct xsk_buff_pool *pool;if (unlikely (!xsk_is_bound (xs)))return -ENXIO ;if (unlikely (need_wait))return -EOPNOTSUPP ; -return __xsk_sendmsg (sk); + pool = xs->pool; +if (pool->cached_need_wakeup &XDP_WAKEUP_TX ) +return __xsk_sendmsg (sk); +return 0 ; }static int xsk_recvmsg (struct socket *sock,struct msghdr *m,size_t len,int flags)
net/xdp/xsk_buff_pool.c +6 -7
@@ -144,14 +144,13 @@ static int __xp_assign_dev(struct xsk_buff_pool *pool,if (err)return err; -if (flags &XDP_USE_NEED_WAKEUP ) { +if (flags &XDP_USE_NEED_WAKEUP ) pool->uses_need_wakeup = true; -/* Tx needs to be explicitly woken up the first time. -* Also for supporting drivers that do not implement this -* feature. They will always have to call sendto(). -*/ - pool->cached_need_wakeup =XDP_WAKEUP_TX ; - } +/* Tx needs to be explicitly woken up the first time. Also +* for supporting drivers that do not implement this +* feature. They will always have to call sendto() or poll(). +*/ + pool->cached_need_wakeup =XDP_WAKEUP_TX ;dev_hold (netdev);
Signature · 1 line
2.27.0
PATCH v4 5/10 xsk: add busy-poll support for {recv,send}msg()
In reply to Björn TöpelFrom: Björn Töpel <[email protected]>
Wire-up XDP socket busy-poll support for recvmsg() and sendmsg(). If the XDP socket prefers busy-polling, make sure that no wakeup/IPI is performed.
--- net/xdp/xsk.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+)
net/xdp/xsk.c +24 -0
@@ -23,6 +23,7 @@#include <linux/netdevice.h> #include <linux/rculist.h> #include <net/xdp_sock_drv.h> +#include <net/busy_poll.h> #include <net/xdp.h> #include "xsk_queue.h"
@@ -517,6 +518,17 @@ static int __xsk_sendmsg(struct sock *sk)return xs->zc ?xsk_zc_xmit (xs) :xsk_generic_xmit (sk); } +static bool xsk_no_wakeup (struct sock *sk) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL +/* Prefer busy-polling, skip the wakeup. */ +return READ_ONCE (sk->sk_prefer_busy_poll) &&READ_ONCE (sk->sk_ll_usec) && +READ_ONCE (sk->sk_napi_id) >=MIN_NAPI_ID ; +#else +return false; +#endif +} +static int xsk_sendmsg (struct socket *sock,struct msghdr *m,size_t total_len) {bool need_wait = !(m->msg_flags &MSG_DONTWAIT );
@@ -529,6 +541,12 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)if (unlikely (need_wait))return -EOPNOTSUPP ; +if (sk_can_busy_loop (sk)) +sk_busy_loop (sk,1 );/* only support non-blocking sockets */ + +if (xsk_no_wakeup (sk)) +return 0 ; + pool = xs->pool;if (pool->cached_need_wakeup &XDP_WAKEUP_TX )return __xsk_sendmsg (sk);
@@ -550,6 +568,12 @@ static int xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flif (unlikely (need_wait))return -EOPNOTSUPP ; +if (sk_can_busy_loop (sk)) +sk_busy_loop (sk,1 );/* only support non-blocking sockets */ + +if (xsk_no_wakeup (sk)) +return 0 ; +if (xs->pool->cached_need_wakeup &XDP_WAKEUP_RX && xs->zc)return xsk_wakeup (xs,XDP_WAKEUP_RX );return 0 ;
Signature · 1 line
2.27.0
PATCH v4 6/10 xsk: propagate napi_id to XDP socket Rx path
In reply to Björn TöpelFrom: Bj?rn T?pel <[email protected]>
Add napi_id to the xdp_rxq_info structure, and make sure the XDP socket pick up the napi_id in the Rx path. The napi_id is used to find the corresponding NAPI structure for socket busy polling.
--- drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- .../ethernet/cavium/thunder/nicvf_queues.c | 2 +- .../net/ethernet/freescale/dpaa2/dpaa2-eth.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 2 +- drivers/net/ethernet/intel/ice/ice_base.c | 4 ++-- drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- .../net/ethernet/intel/ixgbevf/ixgbevf_main.c | 2 +- drivers/net/ethernet/marvell/mvneta.c | 2 +- .../net/ethernet/marvell/mvpp2/mvpp2_main.c | 4 ++-- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 +- .../net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- .../ethernet/netronome/nfp/nfp_net_common.c | 2 +- drivers/net/ethernet/qlogic/qede/qede_main.c | 2 +- drivers/net/ethernet/sfc/rx_common.c | 2 +- drivers/net/ethernet/socionext/netsec.c | 2 +- drivers/net/ethernet/ti/cpsw_priv.c | 2 +- drivers/net/hyperv/netvsc.c | 2 +- drivers/net/tun.c | 2 +- drivers/net/veth.c | 12 ++++++++---- drivers/net/virtio_net.c | 2 +- drivers/net/xen-netfront.c | 2 +- include/net/busy_poll.h | 19 +++++++++++++++---- include/net/xdp.h | 3 ++- net/core/dev.c | 2 +- net/core/xdp.c | 3 ++- net/xdp/xsk.c | 1 + 29 files changed, 54 insertions(+), 36 deletions(-)
drivers/net/ethernet/amazon/ena/ena_netdev.c +1 -1
@@ -416,7 +416,7 @@ static int ena_xdp_register_rxq_info(struct ena_ring *rx_ring) {int rc; - rc =xdp_rxq_info_reg (&rx_ring->xdp_rxq, rx_ring->netdev, rx_ring->qid); + rc =xdp_rxq_info_reg (&rx_ring->xdp_rxq, rx_ring->netdev, rx_ring->qid,0 );if (rc) { netif_err(rx_ring->adapter, ifup, rx_ring->netdev,
drivers/net/ethernet/broadcom/bnxt/bnxt.c +1 -1
@@ -2884,7 +2884,7 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp)if (rc)return rc; - rc =xdp_rxq_info_reg (&rxr->xdp_rxq, bp->dev, i); + rc =xdp_rxq_info_reg (&rxr->xdp_rxq, bp->dev, i,0 );if (rc <0 )return rc;
drivers/net/ethernet/cavium/thunder/nicvf_queues.c +1 -1
@@ -770,7 +770,7 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs, rq->caching =1 ;/* Driver have no proper error path for failed XDP RX-queue info reg */ -WARN_ON (xdp_rxq_info_reg (&rq->xdp_rxq, nic->netdev, qidx) <0 ); +WARN_ON (xdp_rxq_info_reg (&rq->xdp_rxq, nic->netdev, qidx,0 ) <0 );/* Send a mailbox msg to PF to config RQ */ mbx.rq.msg =NIC_MBOX_MSG_RQ_CFG ;
drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +1 -1
@@ -3334,7 +3334,7 @@ static int dpaa2_eth_setup_rx_flow(struct dpaa2_eth_priv *priv,return 0 ; err =xdp_rxq_info_reg (&fq->channel->xdp_rxq, priv->net_dev, - fq->flowid); + fq->flowid,0 );if (err) {dev_err (dev,"xdp_rxq_info_reg failed\n" );return err;
drivers/net/ethernet/intel/i40e/i40e_txrx.c +1 -1
@@ -1447,7 +1447,7 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)/* XDP RX-queue info only needed for RX rings exposed to XDP */ if (rx_ring->vsi->type ==I40E_VSI_MAIN ) { err =xdp_rxq_info_reg (&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->queue_index); + rx_ring->queue_index, rx_ring->q_vector->napi.napi_id);if (err <0 )return err; }
drivers/net/ethernet/intel/ice/ice_base.c +2 -2
@@ -306,7 +306,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)if (!xdp_rxq_info_is_reg (&ring->xdp_rxq))/* coverity[check_return] */ xdp_rxq_info_reg (&ring->xdp_rxq, ring->netdev, - ring->q_index); + ring->q_index, ring->q_vector->napi.napi_id); ring->xsk_pool =ice_xsk_pool (ring);if (ring->xsk_pool) {
@@ -333,7 +333,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)/* coverity[check_return] */ xdp_rxq_info_reg (&ring->xdp_rxq, ring->netdev, - ring->q_index); + ring->q_index, ring->q_vector->napi.napi_id); err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED,
drivers/net/ethernet/intel/ice/ice_txrx.c +1 -1
@@ -483,7 +483,7 @@ int ice_setup_rx_ring(struct ice_ring *rx_ring)if (rx_ring->vsi->type ==ICE_VSI_PF && !xdp_rxq_info_is_reg (&rx_ring->xdp_rxq))if (xdp_rxq_info_reg (&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->q_index)) + rx_ring->q_index, rx_ring->q_vector->napi.napi_id)) goto err;return 0 ;
drivers/net/ethernet/intel/igb/igb_main.c +1 -1
@@ -4352,7 +4352,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)/* XDP RX-queue info */ if (xdp_rxq_info_reg (&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->queue_index) <0 ) + rx_ring->queue_index,0 ) <0 ) goto err;return 0 ;
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +1 -1
@@ -6577,7 +6577,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,/* XDP RX-queue info */ if (xdp_rxq_info_reg (&rx_ring->xdp_rxq, adapter->netdev, - rx_ring->queue_index) <0 ) + rx_ring->queue_index, rx_ring->q_vector->napi.napi_id) <0 ) goto err; rx_ring->xdp_prog = adapter->xdp_prog;
drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +1 -1
@@ -3493,7 +3493,7 @@ int ixgbevf_setup_rx_resources(struct ixgbevf_adapter *adapter,/* XDP RX-queue info */ if (xdp_rxq_info_reg (&rx_ring->xdp_rxq, adapter->netdev, - rx_ring->queue_index) <0 ) + rx_ring->queue_index,0 ) <0 ) goto err; rx_ring->xdp_prog = adapter->xdp_prog;
drivers/net/ethernet/marvell/mvneta.c +1 -1
@@ -3227,7 +3227,7 @@ static int mvneta_create_page_pool(struct mvneta_port *pp,return err; } - err =xdp_rxq_info_reg (&rxq->xdp_rxq, pp->dev, rxq->id); + err =xdp_rxq_info_reg (&rxq->xdp_rxq, pp->dev, rxq->id,0 );if (err <0 ) goto err_free_pp;
drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +2 -2
@@ -2614,11 +2614,11 @@ static int mvpp2_rxq_init(struct mvpp2_port *port,mvpp2_rxq_status_update (port, rxq->id,0 , rxq->size);if (priv->percpu_pools) { - err =xdp_rxq_info_reg (&rxq->xdp_rxq_short, port->dev, rxq->id); + err =xdp_rxq_info_reg (&rxq->xdp_rxq_short, port->dev, rxq->id,0 );if (err <0 ) goto err_free_dma; - err =xdp_rxq_info_reg (&rxq->xdp_rxq_long, port->dev, rxq->id); + err =xdp_rxq_info_reg (&rxq->xdp_rxq_long, port->dev, rxq->id,0 );if (err <0 ) goto err_unregister_rxq_short;
drivers/net/ethernet/mellanox/mlx4/en_rx.c +1 -1
@@ -283,7 +283,7 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv, ring->log_stride =ffs (ring->stride) -1 ; ring->buf_size = ring->size * ring->stride +TXBB_SIZE ; -if (xdp_rxq_info_reg (&ring->xdp_rxq, priv->dev, queue_index) <0 ) +if (xdp_rxq_info_reg (&ring->xdp_rxq, priv->dev, queue_index,0 ) <0 ) goto err_ring; tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
drivers/net/ethernet/mellanox/mlx5/core/en_main.c +1 -1
@@ -434,7 +434,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq_xdp_ix = rq->ix;if (xsk) rq_xdp_ix += params->num_channels *MLX5E_RQ_GROUP_XSK ; - err =xdp_rxq_info_reg (&rq->xdp_rxq, rq->netdev, rq_xdp_ix); + err =xdp_rxq_info_reg (&rq->xdp_rxq, rq->netdev, rq_xdp_ix,0 );if (err <0 ) goto err_rq_xdp_prog;
drivers/net/ethernet/netronome/nfp/nfp_net_common.c +1 -1
@@ -2533,7 +2533,7 @@ nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring)if (dp->netdev) { err =xdp_rxq_info_reg (&rx_ring->xdp_rxq, dp->netdev, - rx_ring->idx); + rx_ring->idx, rx_ring->r_vec->napi.napi_id);if (err <0 )return err; }
drivers/net/ethernet/qlogic/qede/qede_main.c +1 -1
@@ -1762,7 +1762,7 @@ static void qede_init_fp(struct qede_dev *edev)/* Driver have no error path from here */ WARN_ON (xdp_rxq_info_reg (&fp->rxq->xdp_rxq, edev->ndev, - fp->rxq->rxq_id) <0 ); + fp->rxq->rxq_id,0 ) <0 ); if (xdp_rxq_info_reg_mem_model(&fp->rxq->xdp_rxq, MEM_TYPE_PAGE_ORDER0,
drivers/net/ethernet/sfc/rx_common.c +1 -1
@@ -262,7 +262,7 @@ void efx_init_rx_queue(struct efx_rx_queue *rx_queue)/* Initialise XDP queue information */ rc =xdp_rxq_info_reg (&rx_queue->xdp_rxq_info, efx->net_dev, - rx_queue->core_index); + rx_queue->core_index,0 );if (rc) { netif_err(efx, rx_err, efx->net_dev,
drivers/net/ethernet/socionext/netsec.c +1 -1
@@ -1304,7 +1304,7 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv) goto err_out; } - err =xdp_rxq_info_reg (&dring->xdp_rxq, priv->ndev,0 ); + err =xdp_rxq_info_reg (&dring->xdp_rxq, priv->ndev,0 , priv->napi.napi_id);if (err) goto err_out;
drivers/net/ethernet/ti/cpsw_priv.c +1 -1
@@ -1186,7 +1186,7 @@ static int cpsw_ndev_create_xdp_rxq(struct cpsw_priv *priv, int ch) pool = cpsw->page_pool[ch]; rxq = &priv->xdp_rxq[ch]; - ret =xdp_rxq_info_reg (rxq, priv->ndev, ch); + ret =xdp_rxq_info_reg (rxq, priv->ndev, ch,0 );if (ret)return ret;
drivers/net/hyperv/netvsc.c +1 -1
@@ -1499,7 +1499,7 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,u64_stats_init (&nvchan->tx_stats.syncp);u64_stats_init (&nvchan->rx_stats.syncp); - ret =xdp_rxq_info_reg (&nvchan->xdp_rxq, ndev, i); + ret =xdp_rxq_info_reg (&nvchan->xdp_rxq, ndev, i,0 );if (ret) {netdev_err (ndev,"xdp_rxq_info_reg fail: %d\n" , ret);
drivers/net/tun.c +1 -1
@@ -780,7 +780,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file, }else {/* Setup XDP RX-queue info, for new tfile getting attached */ err =xdp_rxq_info_reg (&tfile->xdp_rxq, - tun->dev, tfile->queue_index); + tun->dev, tfile->queue_index,0 );if (err <0 ) goto out; err = xdp_rxq_info_reg_mem_model(&tfile->xdp_rxq,
drivers/net/veth.c +8 -4
@@ -884,7 +884,6 @@ static int veth_napi_add(struct net_device *dev)for (i =0 ; i < dev->real_num_rx_queues; i++) {struct veth_rq *rq = &priv->rq[i]; -netif_napi_add (dev, &rq->xdp_napi, veth_poll,NAPI_POLL_WEIGHT );napi_enable (&rq->xdp_napi); }
@@ -926,7 +925,8 @@ static int veth_enable_xdp(struct net_device *dev)for (i =0 ; i < dev->real_num_rx_queues; i++) {struct veth_rq *rq = &priv->rq[i]; - err =xdp_rxq_info_reg (&rq->xdp_rxq, dev, i); +netif_napi_add (dev, &rq->xdp_napi, veth_poll,NAPI_POLL_WEIGHT ); + err =xdp_rxq_info_reg (&rq->xdp_rxq, dev, i, rq->xdp_napi.napi_id);if (err <0 ) goto err_rxq_reg;
@@ -952,8 +952,12 @@ static int veth_enable_xdp(struct net_device *dev) err_reg_mem:xdp_rxq_info_unreg (&priv->rq[i].xdp_rxq); err_rxq_reg: -for (i--; i >=0 ; i--) -xdp_rxq_info_unreg (&priv->rq[i].xdp_rxq); +for (i--; i >=0 ; i--) { +struct veth_rq *rq = &priv->rq[i]; + +xdp_rxq_info_unreg (&rq->xdp_rxq); +netif_napi_del (&rq->xdp_napi); + }return err; }
drivers/net/virtio_net.c +1 -1
@@ -1485,7 +1485,7 @@ static int virtnet_open(struct net_device *dev)if (!try_fill_recv (vi, &vi->rq[i],GFP_KERNEL ))schedule_delayed_work (&vi->refill,0 ); - err =xdp_rxq_info_reg (&vi->rq[i].xdp_rxq, dev, i); + err =xdp_rxq_info_reg (&vi->rq[i].xdp_rxq, dev, i, vi->rq[i].napi.napi_id);if (err <0 )return err;
drivers/net/xen-netfront.c +1 -1
@@ -2014,7 +2014,7 @@ static int xennet_create_page_pool(struct netfront_queue *queue) } err =xdp_rxq_info_reg (&queue->xdp_rxq, queue->info->netdev, - queue->id); + queue->id,0 );if (err) {netdev_err (queue->info->netdev,"xdp_rxq_info_reg failed\n" ); goto err_free_pp;
include/net/busy_poll.h +15 -4
@@ -135,14 +135,25 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) sk_rx_queue_set(sk, skb); } -/* variant used for unconnected sockets */ -static inline void sk_mark_napi_id_once (struct sock *sk, -const struct sk_buff *skb) +static inline void __sk_mark_napi_id_once_xdp (struct sock *sk,unsigned int napi_id) {#ifdef CONFIG_NET_RX_BUSY_POLL if (!READ_ONCE (sk->sk_napi_id)) -WRITE_ONCE (sk->sk_napi_id, skb->napi_id); +WRITE_ONCE (sk->sk_napi_id, napi_id);#endif } +/* variant used for unconnected sockets */ +static inline void sk_mark_napi_id_once (struct sock *sk, +const struct sk_buff *skb) +{ +__sk_mark_napi_id_once_xdp (sk, skb->napi_id); +} + +static inline void sk_mark_napi_id_once_xdp (struct sock *sk, +const struct xdp_buff *xdp) +{ +__sk_mark_napi_id_once_xdp (sk, xdp->rxq->napi_id); +} +#endif /* _LINUX_NET_BUSY_POLL_H */
include/net/xdp.h +2 -1
@@ -59,6 +59,7 @@ struct xdp_rxq_info {u32 queue_index;u32 reg_state;struct xdp_mem_info mem; +unsigned int napi_id; }____cacheline_aligned ;/* perf critical, avoid false-sharing */ struct xdp_txq_info {
@@ -226,7 +227,7 @@ static inline void xdp_release_frame(struct xdp_frame *xdpf) }int xdp_rxq_info_reg (struct xdp_rxq_info *xdp_rxq, -struct net_device *dev,u32 queue_index); +struct net_device *dev,u32 queue_index,unsigned int napi_id);void xdp_rxq_info_unreg (struct xdp_rxq_info *xdp_rxq);void xdp_rxq_info_unused (struct xdp_rxq_info *xdp_rxq);bool xdp_rxq_info_is_reg (struct xdp_rxq_info *xdp_rxq);
net/core/dev.c +1 -1
@@ -9810,7 +9810,7 @@ static int netif_alloc_rx_queues(struct net_device *dev) rx[i].dev = dev;/* XDP RX-queue setup */ - err =xdp_rxq_info_reg (&rx[i].xdp_rxq, dev, i); + err =xdp_rxq_info_reg (&rx[i].xdp_rxq, dev, i,0 );if (err <0 ) goto err_rxq_info; }
net/core/xdp.c +2 -1
@@ -158,7 +158,7 @@ static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq)/* Returns 0 on success, negative on failure */ int xdp_rxq_info_reg (struct xdp_rxq_info *xdp_rxq, -struct net_device *dev,u32 queue_index) +struct net_device *dev,u32 queue_index,unsigned int napi_id) {if (xdp_rxq->reg_state ==REG_STATE_UNUSED ) {WARN (1 ,"Driver promised not to register this" );
@@ -179,6 +179,7 @@ int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,xdp_rxq_info_init (xdp_rxq); xdp_rxq->dev = dev; xdp_rxq->queue_index = queue_index; + xdp_rxq->napi_id = napi_id; xdp_rxq->reg_state =REG_STATE_REGISTERED ;return 0 ;
net/xdp/xsk.c +1 -0
@@ -233,6 +233,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp,if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)return -EINVAL ; +sk_mark_napi_id_once_xdp (&xs->sk, xdp); len = xdp->data_end - xdp->data; return xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL ?
Signature · 1 line
2.27.0
PATCH v4 7/10 samples/bpf: use recvfrom() in xdpsock/rxdrop
In reply to Björn TöpelFrom: Björn Töpel <[email protected]>
Start using recvfrom() the rxdrop scenario.
--- samples/bpf/xdpsock_user.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
samples/bpf/xdpsock_user.c +4 -4
@@ -1170,7 +1170,7 @@ static inline void complete_tx_only(struct xsk_socket_info *xsk, } } -static void rx_drop (struct xsk_socket_info *xsk,struct pollfd *fds) +static void rx_drop (struct xsk_socket_info *xsk) {unsigned int rcvd, i;u32 idx_rx =0 , idx_fq =0 ;
@@ -1180,7 +1180,7 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds)if (!rcvd) {if (xsk_ring_prod__needs_wakeup (&xsk->umem->fq)) { xsk->app_stats.rx_empty_polls++; - ret =poll (fds, num_socks, opt_timeout); +recvfrom (xsk_socket__fd (xsk->xsk),NULL ,0 ,MSG_DONTWAIT ,NULL ,NULL ); }return ; }
@@ -1191,7 +1191,7 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds)exit_with_error (-ret);if (xsk_ring_prod__needs_wakeup (&xsk->umem->fq)) { xsk->app_stats.fill_fail_polls++; - ret =poll (fds, num_socks, opt_timeout); +recvfrom (xsk_socket__fd (xsk->xsk),NULL ,0 ,MSG_DONTWAIT ,NULL ,NULL ); } ret =xsk_ring_prod__reserve (&xsk->umem->fq, rcvd, &idx_fq); }
@@ -1233,7 +1233,7 @@ static void rx_drop_all(void) }for (i =0 ; i < num_socks; i++) -rx_drop (xsks[i], fds); +rx_drop (xsks[i]);if (benchmark_done)break ;
Signature · 1 line
2.27.0
PATCH v4 8/10 samples/bpf: use recvfrom() in xdpsock/l2fwd
In reply to Björn TöpelFrom: Björn Töpel <[email protected]>
Start using recvfrom() the l2fwd scenario, instead of poll() which is more expensive and need additional knobs for busy-polling.
--- samples/bpf/xdpsock_user.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-)
samples/bpf/xdpsock_user.c +12 -14
@@ -1098,8 +1098,7 @@ static void kick_tx(struct xsk_socket_info *xsk)exit_with_error (errno); } -static inline void complete_tx_l2fwd (struct xsk_socket_info *xsk, -struct pollfd *fds) +static inline void complete_tx_l2fwd (struct xsk_socket_info *xsk) {struct xsk_umem_info *umem = xsk->umem;u32 idx_cq =0 , idx_fq =0 ;
@@ -1134,7 +1133,8 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk,exit_with_error (-ret);if (xsk_ring_prod__needs_wakeup (&umem->fq)) { xsk->app_stats.fill_fail_polls++; - ret =poll (fds, num_socks, opt_timeout); +recvfrom (xsk_socket__fd (xsk->xsk),NULL ,0 ,MSG_DONTWAIT ,NULL , +NULL ); } ret =xsk_ring_prod__reserve (&umem->fq, rcvd, &idx_fq); }
@@ -1331,19 +1331,19 @@ static void tx_only_all(void)complete_tx_only_all (); } -static void l2fwd (struct xsk_socket_info *xsk,struct pollfd *fds) +static void l2fwd (struct xsk_socket_info *xsk) {unsigned int rcvd, i;u32 idx_rx =0 , idx_tx =0 ;int ret; -complete_tx_l2fwd (xsk, fds); +complete_tx_l2fwd (xsk); rcvd =xsk_ring_cons__peek (&xsk->rx, opt_batch_size, &idx_rx);if (!rcvd) {if (xsk_ring_prod__needs_wakeup (&xsk->umem->fq)) { xsk->app_stats.rx_empty_polls++; - ret =poll (fds, num_socks, opt_timeout); +recvfrom (xsk_socket__fd (xsk->xsk),NULL ,0 ,MSG_DONTWAIT ,NULL ,NULL ); }return ; }
@@ -1353,7 +1353,7 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds)while (ret != rcvd) {if (ret <0 )exit_with_error (-ret); -complete_tx_l2fwd (xsk, fds); +complete_tx_l2fwd (xsk);if (xsk_ring_prod__needs_wakeup (&xsk->tx)) { xsk->app_stats.tx_wakeup_sendtos++;kick_tx (xsk);
@@ -1388,22 +1388,20 @@ static void l2fwd_all(void)struct pollfd fds[MAX_SOCKS ] = {};int i, ret; -for (i =0 ; i < num_socks; i++) { - fds[i].fd =xsk_socket__fd (xsks[i]->xsk); - fds[i].events =POLLOUT |POLLIN ; - } -for (;;) {if (opt_poll) { -for (i =0 ; i < num_socks; i++) +for (i =0 ; i < num_socks; i++) { + fds[i].fd =xsk_socket__fd (xsks[i]->xsk); + fds[i].events =POLLOUT |POLLIN ; xsks[i]->app_stats.opt_polls++; + } ret =poll (fds, num_socks, opt_timeout);if (ret <=0 )continue ; }for (i =0 ; i < num_socks; i++) -l2fwd (xsks[i], fds); +l2fwd (xsks[i]);if (benchmark_done)break ;
Signature · 1 line
2.27.0
PATCH v4 9/10 samples/bpf: add busy-poll support to xdpsock
In reply to Björn TöpelFrom: Björn Töpel <[email protected]>
Add a new option to xdpsock, 'B', for busy-polling. This option will also set the batching size, 'b' option, to the busy-poll budget.
--- samples/bpf/xdpsock_user.c | 40 +++++++++++++++++++++++++++++++------- 1 file changed, 33 insertions(+), 7 deletions(-)
samples/bpf/xdpsock_user.c +33 -7
@@ -95,6 +95,7 @@ static int opt_timeout = 1000;static bool opt_need_wakeup = true;static u32 opt_num_xsks =1 ;static u32 prog_id; +static bool opt_busy_poll;struct xsk_ring_stats {unsigned long rx_npkts;
@@ -911,6 +912,7 @@ static struct option long_options[] = { {"quiet", no_argument, 0, 'Q'}, {"app-stats", no_argument, 0, 'a'}, {"irq-string", no_argument, 0, 'I'}, + {"busy-poll", no_argument, 0, 'B'}, {0, 0, 0, 0} };
@@ -949,6 +951,7 @@ static void usage(const char *prog)" -Q, --quiet Do not display any stats.\n" " -a, --app-stats Display application (syscall) statistics.\n" " -I, --irq-string Display driver interrupt statistics for interface associated with irq-string.\n" +" -B, --busy-poll Busy poll.\n" "\n" ; fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE, opt_batch_size, MIN_PKT_SIZE, MIN_PKT_SIZE,
@@ -964,7 +967,7 @@ static void parse_command_line(int argc, char **argv) opterr =0 ;for (;;) { - c =getopt_long (argc, argv,"Frtli:q:pSNn:czf:muMd:b:C:s:P:xQaI:" , + c =getopt_long (argc, argv,"Frtli:q:pSNn:czf:muMd:b:C:s:P:xQaI:B" , long_options, &option_index);if (c ==-1 )break ;
@@ -1062,7 +1065,9 @@ static void parse_command_line(int argc, char **argv)fprintf (stderr,"ERROR: Failed to get irqs for %s\n" , opt_irq_str);usage (basename (argv[0 ])); } - +break ; +case 'B' : + opt_busy_poll =1 ;break ;default :usage (basename (argv[0 ]));
@@ -1131,7 +1136,7 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk)while (ret != rcvd) {if (ret <0 )exit_with_error (-ret); -if (xsk_ring_prod__needs_wakeup (&umem->fq)) { +if (opt_busy_poll ||xsk_ring_prod__needs_wakeup (&umem->fq)) { xsk->app_stats.fill_fail_polls++;recvfrom (xsk_socket__fd (xsk->xsk),NULL ,0 ,MSG_DONTWAIT ,NULL ,NULL );
@@ -1178,7 +1183,7 @@ static void rx_drop(struct xsk_socket_info *xsk) rcvd =xsk_ring_cons__peek (&xsk->rx, opt_batch_size, &idx_rx);if (!rcvd) { -if (xsk_ring_prod__needs_wakeup (&xsk->umem->fq)) { +if (opt_busy_poll ||xsk_ring_prod__needs_wakeup (&xsk->umem->fq)) { xsk->app_stats.rx_empty_polls++;recvfrom (xsk_socket__fd (xsk->xsk),NULL ,0 ,MSG_DONTWAIT ,NULL ,NULL ); }
@@ -1189,7 +1194,7 @@ static void rx_drop(struct xsk_socket_info *xsk)while (ret != rcvd) {if (ret <0 )exit_with_error (-ret); -if (xsk_ring_prod__needs_wakeup (&xsk->umem->fq)) { +if (opt_busy_poll ||xsk_ring_prod__needs_wakeup (&xsk->umem->fq)) { xsk->app_stats.fill_fail_polls++;recvfrom (xsk_socket__fd (xsk->xsk),NULL ,0 ,MSG_DONTWAIT ,NULL ,NULL ); }
@@ -1341,7 +1346,7 @@ static void l2fwd(struct xsk_socket_info *xsk) rcvd =xsk_ring_cons__peek (&xsk->rx, opt_batch_size, &idx_rx);if (!rcvd) { -if (xsk_ring_prod__needs_wakeup (&xsk->umem->fq)) { +if (opt_busy_poll ||xsk_ring_prod__needs_wakeup (&xsk->umem->fq)) { xsk->app_stats.rx_empty_polls++;recvfrom (xsk_socket__fd (xsk->xsk),NULL ,0 ,MSG_DONTWAIT ,NULL ,NULL ); }
@@ -1354,7 +1359,7 @@ static void l2fwd(struct xsk_socket_info *xsk)if (ret <0 )exit_with_error (-ret);complete_tx_l2fwd (xsk); -if (xsk_ring_prod__needs_wakeup (&xsk->tx)) { +if (opt_busy_poll ||xsk_ring_prod__needs_wakeup (&xsk->tx)) { xsk->app_stats.tx_wakeup_sendtos++;kick_tx (xsk); }
@@ -1459,6 +1464,24 @@ static void enter_xsks_into_map(struct bpf_object *obj) } } +static void apply_setsockopt (struct xsk_socket_info *xsk) +{ +int sock_opt; + +if (!opt_busy_poll) +return ; + + sock_opt =1 ; +if (setsockopt (xsk_socket__fd (xsk->xsk),SOL_SOCKET ,SO_PREFER_BUSY_POLL , + (void *)&sock_opt,sizeof (sock_opt)) <0 ) +exit_with_error (errno); + + sock_opt =20 ; +if (setsockopt (xsk_socket__fd (xsk->xsk),SOL_SOCKET ,SO_BUSY_POLL , + (void *)&sock_opt,sizeof (sock_opt)) <0 ) +exit_with_error (errno); +} +int main (int argc,char **argv) {struct rlimit r = {RLIM_INFINITY ,RLIM_INFINITY };
@@ -1500,6 +1523,9 @@ int main(int argc, char **argv)for (i =0 ; i < opt_num_xsks; i++) xsks[num_socks++] =xsk_configure_socket (umem, rx, tx); +for (i =0 ; i < opt_num_xsks; i++) +apply_setsockopt (xsks[i]); +if (opt_bench ==BENCH_TXONLY ) {gen_eth_hdr_data ();
Signature · 1 line
2.27.0
PATCH v4 10/10 samples/bpf: add option to set the busy-poll budget
In reply to Björn TöpelFrom: Björn Töpel <[email protected]>
Support for the SO_BUSY_POLL_BUDGET setsockopt, via the batching option ('b').
--- samples/bpf/xdpsock_user.c | 5 +++++ 1 file changed, 5 insertions(+)
samples/bpf/xdpsock_user.c +5 -0
@@ -1480,6 +1480,11 @@ static void apply_setsockopt(struct xsk_socket_info *xsk)if (setsockopt (xsk_socket__fd (xsk->xsk),SOL_SOCKET ,SO_BUSY_POLL , (void *)&sock_opt,sizeof (sock_opt)) <0 )exit_with_error (errno); + + sock_opt = opt_batch_size; +if (setsockopt (xsk_socket__fd (xsk->xsk),SOL_SOCKET ,SO_BUSY_POLL_BUDGET , + (void *)&sock_opt,sizeof (sock_opt)) <0 ) +exit_with_error (errno); }int main (int argc,char **argv)
Signature · 1 line
2.27.0
This series was applied to bpf/bpf-next.git (refs/heads/master):
Hello:
This series was applied to bpf/bpf-next.git (refs/heads/master):
Quoted 9 lines · On Mon, 30 Nov 2020 19:51:55 +0100 you wrote:
This series introduces three new features:
1. A new "heavy traffic" busy-polling variant that works in concert with the existing
napi_defer_hard_irqsandgro_flush_timeoutknobs.2. A new socket option that let a user change the busy-polling NAPI budget.
[...]
Here is the summary with links:
- [bpf-next,v4,01/10] net: introduce preferred busy-polling
https://git.kernel.org/bpf/bpf-next/c/7fd3253a7de6 - [bpf-next,v4,02/10] net: add SO_BUSY_POLL_BUDGET socket option https://git.kernel.org/bpf/bpf-next/c/7c951cafc0cb - [bpf-next,v4,03/10] xsk: add support for recvmsg() https://git.kernel.org/bpf/bpf-next/c/45a86681844e - [bpf-next,v4,04/10] xsk: check need wakeup flag in sendmsg() https://git.kernel.org/bpf/bpf-next/c/e39208183728 - [bpf-next,v4,05/10] xsk: add busy-poll support for {recv,send}msg() https://git.kernel.org/bpf/bpf-next/c/a0731952d9cd - [bpf-next,v4,06/10] xsk: propagate napi_id to XDP socket Rx path https://git.kernel.org/bpf/bpf-next/c/b02e5a0ebb17 - [bpf-next,v4,07/10] samples/bpf: use recvfrom() in xdpsock/rxdrop https://git.kernel.org/bpf/bpf-next/c/f2d2728220ac - [bpf-next,v4,08/10] samples/bpf: use recvfrom() in xdpsock/l2fwd https://git.kernel.org/bpf/bpf-next/c/284cbc61f851 - [bpf-next,v4,09/10] samples/bpf: add busy-poll support to xdpsock https://git.kernel.org/bpf/bpf-next/c/b35fc1482ceb - [bpf-next,v4,10/10] samples/bpf: add option to set the busy-poll budget https://git.kernel.org/bpf/bpf-next/c/41bf900fe2a0
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html