From nobody Wed Dec 24 20:09:34 2025 Received: from mail-il1-f173.google.com (mail-il1-f173.google.com [209.85.166.173]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 6B310A3D for ; Thu, 25 Jan 2024 00:30:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.166.173 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706142626; cv=none; b=GeMWGzMkdkYvnva9lqimrBrjJFgpYZG6+9N7+pjO1jCMbq0y/Vf8mjH0pTQ2PMaf5cFpn1N2bJHp870bAc0kyIT0pB7bjPAbCUtjYd7ffCbN2HUdKn9OpnS4L4Q0TtbovdmC3JlX1Jq4f40GfkpHU8LiP6clhmlKohIQ8kmPl1Y= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706142626; c=relaxed/simple; bh=qkngexUKlfn+hMPunN78J4XlCpnaY0JzFvOY2CvOwFw=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=dNooLMln2mIiQIRwZ2DFzKoRd+EMBrOEkRcBL/FAHJmu8nio+EMrCrj2kfI6p8nJsbtQqt50yb5jsgB6PeAvPwQaxsKC+yTfXxAi6d1opEZNa1lGaRQiV0xea5YeudbPWEm1yr7DtqEkDc7yCySJUoccIJ0RCHPfPuWOM03cfiQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=fastly.com; spf=pass smtp.mailfrom=fastly.com; dkim=pass (1024-bit key) header.d=fastly.com header.i=@fastly.com header.b=RrRYhH/i; arc=none smtp.client-ip=209.85.166.173 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=fastly.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=fastly.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=fastly.com header.i=@fastly.com header.b="RrRYhH/i" Received: by mail-il1-f173.google.com with SMTP id e9e14a558f8ab-3627e9f1b40so18328715ab.1 for ; Wed, 24 Jan 2024 16:30:23 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=fastly.com; s=google; t=1706142622; x=1706747422; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=VV39OAkRpCVAHLKUI3lU3BvBDLbvOa7qJKwdNWq/qLo=; b=RrRYhH/iEsRHUmKTquV2y95C9aRsKyCGxgflWpj0V8QQpjBruF+BKUVz0LDlNsI313 8aI4+U3ixR45wYg8g3NTlExvkD//EWmymdG7TeA4zAT0wedY0BX8zsZUlPWuKfQoeszg uTrztf7SZyKmfaLyL7opJRTMLitGJKRVxeNEs= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1706142622; x=1706747422; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=VV39OAkRpCVAHLKUI3lU3BvBDLbvOa7qJKwdNWq/qLo=; b=ObL84/esDSLVDZalGJ5g1RIVRBxhZpZpDig+dQqroJnCSawCbsXaeioF6QRhp6/EmF ks4ogfmL1egb+J1GWY7m57OhLdx8sORfPmaIbNtcHVPO0oquz5Dp4npEilan4DlO0lc8 k/fmviaG50igEI0520rvbHODQ6c5QoLDkWT7rLDMi0s+HYjfnR9HHTPAOMyzNQdL+vam iy5cEu/dJMt9gyU7farEcOQL9hZdX6BFubSxw8tzCzqe3qGCqV0sk7Y4SJuEhXtA7kU7 z8UYnRj4InlGzBhKKMbJQe6gx0EX4F7anTRaxMuzZbW4oE5qlqaHo3SDZCmZfnjvgP0+ p0Gg== X-Gm-Message-State: AOJu0YzbuaaH0iOWeBp5ZE2D/bgVQEV2OU0bSmyZv+KOxGDfd5JUh0ft RsC0jOkPtJl1j3qQww8VmXCUecoCfjeE9S85EiBgxVXhOxQZ6Arnsdvrk3QTSUk= X-Google-Smtp-Source: AGHT+IGnYPOifsV33or2bBeZeQG6+k6OkdXKBZqmsoPyQU14DL3OI0VG4LUd5evkY/JboI23hyOIDQ== X-Received: by 2002:a92:cec9:0:b0:361:ac44:150a with SMTP id z9-20020a92cec9000000b00361ac44150amr285943ilq.57.1706142622585; Wed, 24 Jan 2024 16:30:22 -0800 (PST) Received: from localhost.localdomain ([2620:11a:c018:0:ea8:be91:8d1:f59b]) by smtp.gmail.com with ESMTPSA id w10-20020a63d74a000000b005cd945c0399sm12550486pgi.80.2024.01.24.16.30.21 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 24 Jan 2024 16:30:21 -0800 (PST) From: Joe Damato To: netdev@vger.kernel.org, linux-kernel@vger.kernel.org Cc: chuck.lever@oracle.com, jlayton@kernel.org, linux-api@vger.kernel.org, brauner@kernel.org, edumazet@google.com, davem@davemloft.net, alexander.duyck@gmail.com, sridhar.samudrala@intel.com, kuba@kernel.org, weiwan@google.com, Joe Damato Subject: [net-next v2 1/4] eventpoll: support busy poll per epoll instance Date: Thu, 25 Jan 2024 00:30:11 +0000 Message-Id: <20240125003014.43103-2-jdamato@fastly.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20240125003014.43103-1-jdamato@fastly.com> References: <20240125003014.43103-1-jdamato@fastly.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Allow busy polling on a per-epoll context basis. The per-epoll context usec timeout value is preferred, but the pre-existing system wide sysctl value is still supported if it specified. Note that this change uses an xor: either per epoll instance busy polling is enabled on the epoll instance or system wide epoll is enabled. Enabling both is disallowed. Signed-off-by: Joe Damato --- fs/eventpoll.c | 49 +++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 45 insertions(+), 4 deletions(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 3534d36a1474..4503fec01278 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -227,6 +227,8 @@ struct eventpoll { #ifdef CONFIG_NET_RX_BUSY_POLL /* used to track busy poll napi_id */ unsigned int napi_id; + /* busy poll timeout */ + u64 busy_poll_usecs; #endif =20 #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -386,12 +388,44 @@ static inline int ep_events_available(struct eventpol= l *ep) READ_ONCE(ep->ovflist) !=3D EP_UNACTIVE_PTR; } =20 +/** + * busy_loop_ep_timeout - check if busy poll has timed out. The timeout va= lue + * from the epoll instance ep is preferred, but if it is not set fallback = to + * the system-wide global via busy_loop_timeout. + * + * @start_time: The start time used to compute the remaining time until ti= meout. + * @ep: Pointer to the eventpoll context. + * + * Return: true if the timeout has expired, false otherwise. + */ +static inline bool busy_loop_ep_timeout(unsigned long start_time, struct e= ventpoll *ep) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + unsigned long bp_usec =3D READ_ONCE(ep->busy_poll_usecs); + + if (bp_usec) { + unsigned long end_time =3D start_time + bp_usec; + unsigned long now =3D busy_loop_current_time(); + + return time_after(now, end_time); + } else { + return busy_loop_timeout(start_time); + } +#endif + return true; +} + #ifdef CONFIG_NET_RX_BUSY_POLL +static bool ep_busy_loop_on(struct eventpoll *ep) +{ + return !!ep->busy_poll_usecs ^ net_busy_loop_on(); +} + static bool ep_busy_loop_end(void *p, unsigned long start_time) { struct eventpoll *ep =3D p; =20 - return ep_events_available(ep) || busy_loop_timeout(start_time); + return ep_events_available(ep) || busy_loop_ep_timeout(start_time, ep); } =20 /* @@ -404,7 +438,7 @@ static bool ep_busy_loop(struct eventpoll *ep, int nonb= lock) { unsigned int napi_id =3D READ_ONCE(ep->napi_id); =20 - if ((napi_id >=3D MIN_NAPI_ID) && net_busy_loop_on()) { + if ((napi_id >=3D MIN_NAPI_ID) && ep_busy_loop_on(ep)) { napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep, false, BUSY_POLL_BUDGET); if (ep_events_available(ep)) @@ -430,7 +464,8 @@ static inline void ep_set_busy_poll_napi_id(struct epit= em *epi) struct socket *sock; struct sock *sk; =20 - if (!net_busy_loop_on()) + ep =3D epi->ep; + if (!ep_busy_loop_on(ep)) return; =20 sock =3D sock_from_file(epi->ffd.file); @@ -442,7 +477,6 @@ static inline void ep_set_busy_poll_napi_id(struct epit= em *epi) return; =20 napi_id =3D READ_ONCE(sk->sk_napi_id); - ep =3D epi->ep; =20 /* Non-NAPI IDs can be rejected * or @@ -466,6 +500,10 @@ static inline void ep_set_busy_poll_napi_id(struct epi= tem *epi) { } =20 +static inline bool ep_busy_loop_on(struct eventpoll *ep) +{ + return false; +} #endif /* CONFIG_NET_RX_BUSY_POLL */ =20 /* @@ -2058,6 +2096,9 @@ static int do_epoll_create(int flags) error =3D PTR_ERR(file); goto out_free_fd; } +#ifdef CONFIG_NET_RX_BUSY_POLL + ep->busy_poll_usecs =3D 0; +#endif ep->file =3D file; fd_install(fd, file); return fd; --=20 2.25.1