From patchwork Fri Jul 18 14:20:40 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Ming Lei X-Patchwork-Id: 371558 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from huckleberry.canonical.com (huckleberry.canonical.com [91.189.94.19]) by ozlabs.org (Postfix) with ESMTP id B427F14010C; Sat, 19 Jul 2014 00:21:33 +1000 (EST) Received: from localhost ([127.0.0.1] helo=huckleberry.canonical.com) by huckleberry.canonical.com with esmtp (Exim 4.76) (envelope-from ) id 1X892M-0003QV-OJ; Fri, 18 Jul 2014 14:21:26 +0000 Received: from mail-pd0-f179.google.com ([209.85.192.179]) by huckleberry.canonical.com with esmtp (Exim 4.76) (envelope-from ) id 1X892F-0003OP-BL for kernel-team@lists.ubuntu.com; Fri, 18 Jul 2014 14:21:19 +0000 Received: by mail-pd0-f179.google.com with SMTP id ft15so5121928pdb.38 for ; Fri, 18 Jul 2014 07:21:18 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-type:content-transfer-encoding; bh=q1CqtRyBAvHpdrrdpKpTsujvRNBKSg2UJnFscUU37Jw=; b=TRbmgipYTm2FVt6ix7ee1R4i6dVvIHncF99VXdQYFGGOriqh5yiSdPcRfo4C9fXNop BLvlqtGz2bNGhYT4InKQhQd6zQPXpAdy2zkWYBkygGbu/T5KM+wxdIIn4WxmIk3Dh6oP KVklkNpPhXdrMEJ9exS510yQyJptnticAjGpvWlH2zlqXYamPPxA5WNC8YjdZzlcZaUT hKfPGc23H6eWsSKWD9q8xlvNY9xM0NSQ+pG9hgedEU3CSYpSW5tSp9bktR7B39n70Urd cImUC8gIAwLVIqHi6RNQKbz066o5TeXOvLfA6XDgPBhqyhwrJcl6QPhPFiOsRCJWmvz0 U1dQ== X-Received: by 10.68.223.1 with SMTP id qq1mr5649687pbc.62.1405693278470; Fri, 18 Jul 2014 07:21:18 -0700 (PDT) Received: from localhost ([183.14.17.82]) by mx.google.com with ESMTPSA id n2sm7674795pdr.15.2014.07.18.07.21.15 for (version=TLSv1.2 cipher=RC4-SHA bits=128/128); Fri, 18 Jul 2014 07:21:17 -0700 (PDT) From: Ming Lei To: kernel-team@lists.ubuntu.com Subject: [PATCH trusty SRU 3/5] net/mlx4_en: Use affinity hint Date: Fri, 18 Jul 2014 22:20:40 +0800 Message-Id: <1405693242-3929-4-git-send-email-ming.lei@canonical.com> X-Mailer: git-send-email 1.7.9.5 In-Reply-To: <1405693242-3929-1-git-send-email-ming.lei@canonical.com> References: <1405693242-3929-1-git-send-email-ming.lei@canonical.com> MIME-Version: 1.0 X-BeenThere: kernel-team@lists.ubuntu.com X-Mailman-Version: 2.1.14 Precedence: list List-Id: Kernel team discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: kernel-team-bounces@lists.ubuntu.com Sender: kernel-team-bounces@lists.ubuntu.com From: Yuval Atias The “affinity hint” mechanism is used by the user space daemon, irqbalancer, to indicate a preferred CPU mask for irqs. Irqbalancer can use this hint to balance the irqs between the cpus indicated by the mask. We wish the HCA to preferentially map the IRQs it uses to numa cores close to it. To accomplish this, we use cpumask_set_cpu_local_first(), that sets the affinity hint according the following policy: First it maps IRQs to “close” numa cores. If these are exhausted, the remaining IRQs are mapped to “far” numa cores. Signed-off-by: Yuval Atias Signed-off-by: Amir Vadai Signed-off-by: David S. Miller (cherry picked from commit 9e311e77a85e37b5caec3d64c3593cd52b2cdb71) (add #include for fixing compiling failure) Signed-off-by: Ming Lei --- drivers/net/ethernet/mellanox/mlx4/en_cq.c | 13 ++++++++- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 35 +++++++++++++++++++++++- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 1 + 3 files changed, 47 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index c2cd8d3..12bef3e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -34,6 +34,7 @@ #include #include #include +#include #include "mlx4_en.h" @@ -164,6 +165,13 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_tx_cq, NAPI_POLL_WEIGHT); } else { + struct mlx4_en_rx_ring *ring = priv->rx_ring[cq->ring]; + + err = irq_set_affinity_hint(cq->mcq.irq, + ring->affinity_mask); + if (err) + mlx4_warn(mdev, "Failed setting affinity hint\n"); + netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_rx_cq, 64); napi_hash_add(&cq->napi); } @@ -180,8 +188,11 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq) mlx4_en_unmap_buffer(&cq->wqres.buf); mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size); - if (priv->mdev->dev->caps.comp_pool && cq->vector) + if (priv->mdev->dev->caps.comp_pool && cq->vector) { + if (!cq->is_tx) + irq_set_affinity_hint(cq->mcq.irq, NULL); mlx4_release_eq(priv->mdev->dev, cq->vector); + } cq->vector = 0; cq->buf_size = 0; cq->buf = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 19a08de..d71e4cf 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1526,6 +1526,27 @@ static void mlx4_en_linkstate(struct work_struct *work) mutex_unlock(&mdev->state_lock); } +static int mlx4_en_init_affinity_hint(struct mlx4_en_priv *priv, int ring_idx) +{ + struct mlx4_en_rx_ring *ring = priv->rx_ring[ring_idx]; + int numa_node = priv->mdev->dev->numa_node; + int ret = 0; + + if (!zalloc_cpumask_var(&ring->affinity_mask, GFP_KERNEL)) + return -ENOMEM; + + ret = cpumask_set_cpu_local_first(ring_idx, numa_node, + ring->affinity_mask); + if (ret) + free_cpumask_var(ring->affinity_mask); + + return ret; +} + +static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx) +{ + free_cpumask_var(priv->rx_ring[ring_idx]->affinity_mask); +} int mlx4_en_start_port(struct net_device *dev) { @@ -1567,9 +1588,16 @@ int mlx4_en_start_port(struct net_device *dev) mlx4_en_cq_init_lock(cq); + err = mlx4_en_init_affinity_hint(priv, i); + if (err) { + en_err(priv, "Failed preparing IRQ affinity hint\n"); + goto cq_err; + } + err = mlx4_en_activate_cq(priv, cq, i); if (err) { en_err(priv, "Failed activating Rx CQ\n"); + mlx4_en_free_affinity_hint(priv, i); goto cq_err; } for (j = 0; j < cq->size; j++) @@ -1578,6 +1606,7 @@ int mlx4_en_start_port(struct net_device *dev) if (err) { en_err(priv, "Failed setting cq moderation parameters"); mlx4_en_deactivate_cq(priv, cq); + mlx4_en_free_affinity_hint(priv, i); goto cq_err; } mlx4_en_arm_cq(priv, cq); @@ -1715,8 +1744,10 @@ rss_err: mac_err: mlx4_en_put_qp(priv); cq_err: - while (rx_index--) + while (rx_index--) { mlx4_en_deactivate_cq(priv, priv->rx_cq[rx_index]); + mlx4_en_free_affinity_hint(priv, i); + } for (i = 0; i < priv->rx_ring_num; i++) mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]); @@ -1847,6 +1878,8 @@ void mlx4_en_stop_port(struct net_device *dev, int detach) msleep(1); mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]); mlx4_en_deactivate_cq(priv, cq); + + mlx4_en_free_affinity_hint(priv, i); } } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 04d9b6fe..75271dc 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -313,6 +313,7 @@ struct mlx4_en_rx_ring { unsigned long csum_ok; unsigned long csum_none; int hwtstamp_rx_filter; + cpumask_var_t affinity_mask; }; struct mlx4_en_cq {