On 2020-11-12 15:38, Eric Dumazet wrote:
On Thu, Nov 12, 2020 at 12:41 PM Björn Töpel <bjorn.topel@xxxxxxxxx> wrote:From: Björn Töpel <bjorn.topel@xxxxxxxxx> 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. Signed-off-by: Björn Töpel <bjorn.topel@xxxxxxxxx>...diff --git a/net/core/sock.c b/net/core/sock.c index 727ea1cc633c..248f6a763661 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -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 + sk->sk_prefer_busy_poll = valbool;WRITE_ONCE(sk->sk_prefer_busy_poll, valbool); So that KCSAN is happy while readers read this field while socket is not locked.
Thanks Eric, I'll fix that! Also, in patch 5, READ_ONCE is missing. I'll address that as well.
