From patchwork Tue Sep 25 07:02:34 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Hemant Agrawal X-Patchwork-Id: 147399 Delivered-To: patch@linaro.org Received: by 2002:a2e:8595:0:0:0:0:0 with SMTP id b21-v6csp373275lji; Tue, 25 Sep 2018 00:04:41 -0700 (PDT) X-Google-Smtp-Source: ACcGV635Z0DwhasDgXkOHIJYcQ2TVWxLd49tpXKC3NPybZi0J+aMXSlcVnubIX9v4OoGyoP4IeWy X-Received: by 2002:a1c:1bca:: with SMTP id b193-v6mr733130wmb.6.1537859081540; Tue, 25 Sep 2018 00:04:41 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1537859081; cv=none; d=google.com; s=arc-20160816; b=gT6ABMo8Ho9EDjsrwWrpUv2+bh5fR5/846iznHfPHUMFq7l/jQrqxnx5g4sadwQsfR PQIFTOtORooFLzfPvHBijx7SpcpOPv11z4pq0q2D0OYKZ2SH3aSEyD2g89+lRmzy6zfg UKB9VOA0giRUt7vSGtEzWCXkiH6vUmy40eeg6riwBEJfaansf6jPtxxC4+knR11wipfV gLECC0yMjQXza3BFIzNz7/pxwyxLDcCAGEMp3RJj0xZBkUBtc10ZptdZUddxWrFxVxmL dJCPgrJjET4+GGSdYXMI8WbT8pFq42YywCxRu2mpYDXvDX9+6BNqAQAWRgkwYKmHp2lm qqNQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:subject:references:in-reply-to :message-id:date:cc:to:from; bh=bslINFZMqGbfDjQZFSNq12hVMpiG+bmi1CvljQ3+eq0=; b=BK00U2+qZwjMKY+JAAV6eZqzkZQ+j5rpFybe1F2ncnHTJMA9w2sEk/vPQgNCm2lpAO 9iirWaY7OnMTZHHykFgPhp9BK8eAfqaGE+65H521Ici/CS8m8KvpZZm0XYLah1vfvbpw AgIZsVfQ2bp+7muD+G19br9MF/AIxpNe8thPDdgosJl8mKsvE69JXkY1hWZYkSHxeI+4 taT3lgRDN8DKMJLF5rk3/5Bo6aMLcD4xLdxU5kYixr8Mc7sP6OTt2K/4pMy/FoL1POF5 b2iNY+HOAkhTenp8O1uWur2J9Loga18iaQHRQe44ytK3KM9U5HoIJcZcnFBPmWeicvOv s95A== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: domain of dev-bounces@dpdk.org designates 92.243.14.124 as permitted sender) smtp.mailfrom=dev-bounces@dpdk.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=nxp.com Return-Path: Received: from dpdk.org (dpdk.org. [92.243.14.124]) by mx.google.com with ESMTP id i14-v6si1403523wrq.178.2018.09.25.00.04.41; Tue, 25 Sep 2018 00:04:41 -0700 (PDT) Received-SPF: pass (google.com: domain of dev-bounces@dpdk.org designates 92.243.14.124 as permitted sender) client-ip=92.243.14.124; Authentication-Results: mx.google.com; spf=pass (google.com: domain of dev-bounces@dpdk.org designates 92.243.14.124 as permitted sender) smtp.mailfrom=dev-bounces@dpdk.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=nxp.com Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 6FBA81E34; Tue, 25 Sep 2018 09:04:40 +0200 (CEST) Received: from inva020.nxp.com (inva020.nxp.com [92.121.34.13]) by dpdk.org (Postfix) with ESMTP id 231F51AFF for ; Tue, 25 Sep 2018 09:04:39 +0200 (CEST) Received: from inva020.nxp.com (localhost [127.0.0.1]) by inva020.eu-rdc02.nxp.com (Postfix) with ESMTP id 994341A0099; Tue, 25 Sep 2018 09:04:38 +0200 (CEST) Received: from invc005.ap-rdc01.nxp.com (invc005.ap-rdc01.nxp.com [165.114.16.14]) by inva020.eu-rdc02.nxp.com (Postfix) with ESMTP id BC4DD1A006A; Tue, 25 Sep 2018 09:04:36 +0200 (CEST) Received: from bf-netperf1.ap.freescale.net (bf-netperf1.ap.freescale.net [10.232.134.28]) by invc005.ap-rdc01.nxp.com (Postfix) with ESMTP id 3AC32402D8; Tue, 25 Sep 2018 15:04:34 +0800 (SGT) From: Hemant Agrawal To: dev@dpdk.org Cc: jerin.jacob@caviumnetworks.com Date: Tue, 25 Sep 2018 12:32:34 +0530 Message-Id: <1537858955-6884-1-git-send-email-hemant.agrawal@nxp.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1535607196-26782-1-git-send-email-hemant.agrawal@nxp.com> References: <1535607196-26782-1-git-send-email-hemant.agrawal@nxp.com> X-Virus-Scanned: ClamAV using ClamSMTP Subject: [dpdk-dev] [PATCH v2 1/2] event/dpaa: remove duplicate log macros X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" align and cleanup the debug log prints Signed-off-by: Hemant Agrawal --- Note: This patch has a dependency on following patch series: http://mails.dpdk.org/archives/dev/2018-September/112433.html which is now part of dpdk-next-net tree. drivers/event/dpaa/dpaa_eventdev.c | 58 +++++++++++++++++++------------------- drivers/event/dpaa/dpaa_eventdev.h | 7 ----- 2 files changed, 29 insertions(+), 36 deletions(-) -- 2.7.4 diff --git a/drivers/event/dpaa/dpaa_eventdev.c b/drivers/event/dpaa/dpaa_eventdev.c index 5443ef5..9ddaf30 100644 --- a/drivers/event/dpaa/dpaa_eventdev.c +++ b/drivers/event/dpaa/dpaa_eventdev.c @@ -49,7 +49,7 @@ dpaa_event_dequeue_timeout_ticks(struct rte_eventdev *dev, uint64_t ns, { uint64_t cycles_per_second; - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); RTE_SET_USED(dev); @@ -175,7 +175,7 @@ static void dpaa_event_dev_info_get(struct rte_eventdev *dev, struct rte_event_dev_info *dev_info) { - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); RTE_SET_USED(dev); dev_info->driver_name = "event_dpaa"; @@ -220,8 +220,7 @@ dpaa_event_dev_configure(const struct rte_eventdev *dev) int ret, i; uint32_t *ch_id; - EVENTDEV_DRV_FUNC_TRACE(); - + EVENTDEV_INIT_FUNC_TRACE(); priv->dequeue_timeout_ns = conf->dequeue_timeout_ns; priv->nb_events_limit = conf->nb_events_limit; priv->nb_event_queues = conf->nb_event_queues; @@ -244,13 +243,14 @@ dpaa_event_dev_configure(const struct rte_eventdev *dev) sizeof(uint32_t) * priv->nb_event_queues, RTE_CACHE_LINE_SIZE); if (ch_id == NULL) { - EVENTDEV_DRV_ERR("Fail to allocate memory for dpaa channels\n"); + DPAA_EVENTDEV_ERR("Fail to allocate memory for dpaa channels\n"); return -ENOMEM; } /* Create requested event queues within the given event device */ ret = qman_alloc_pool_range(ch_id, priv->nb_event_queues, 1, 0); if (ret < 0) { - EVENTDEV_DRV_ERR("Failed to create internal channel\n"); + DPAA_EVENTDEV_ERR("qman_alloc_pool_range %u, err =%d\n", + priv->nb_event_queues, ret); rte_free(ch_id); return ret; } @@ -283,7 +283,7 @@ dpaa_event_dev_configure(const struct rte_eventdev *dev) * can be created equals to number of lcore. */ rte_free(ch_id); - EVENTDEV_DRV_LOG("Configured eventdev devid=%d", dev->data->dev_id); + DPAA_EVENTDEV_INFO("Configured eventdev devid=%d", dev->data->dev_id); return 0; } @@ -291,7 +291,7 @@ dpaa_event_dev_configure(const struct rte_eventdev *dev) static int dpaa_event_dev_start(struct rte_eventdev *dev) { - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); RTE_SET_USED(dev); return 0; @@ -300,14 +300,14 @@ dpaa_event_dev_start(struct rte_eventdev *dev) static void dpaa_event_dev_stop(struct rte_eventdev *dev) { - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); RTE_SET_USED(dev); } static int dpaa_event_dev_close(struct rte_eventdev *dev) { - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); RTE_SET_USED(dev); return 0; @@ -317,7 +317,7 @@ static void dpaa_event_queue_def_conf(struct rte_eventdev *dev, uint8_t queue_id, struct rte_event_queue_conf *queue_conf) { - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); RTE_SET_USED(dev); RTE_SET_USED(queue_id); @@ -334,14 +334,14 @@ dpaa_event_queue_setup(struct rte_eventdev *dev, uint8_t queue_id, struct dpaa_eventdev *priv = dev->data->dev_private; struct dpaa_eventq *evq_info = &priv->evq_info[queue_id]; - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); switch (queue_conf->schedule_type) { case RTE_SCHED_TYPE_PARALLEL: case RTE_SCHED_TYPE_ATOMIC: break; case RTE_SCHED_TYPE_ORDERED: - EVENTDEV_DRV_ERR("Schedule type is not supported."); + DPAA_EVENTDEV_ERR("Schedule type is not supported."); return -1; } evq_info->event_queue_cfg = queue_conf->event_queue_cfg; @@ -353,7 +353,7 @@ dpaa_event_queue_setup(struct rte_eventdev *dev, uint8_t queue_id, static void dpaa_event_queue_release(struct rte_eventdev *dev, uint8_t queue_id) { - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); RTE_SET_USED(dev); RTE_SET_USED(queue_id); @@ -363,7 +363,7 @@ static void dpaa_event_port_default_conf_get(struct rte_eventdev *dev, uint8_t port_id, struct rte_event_port_conf *port_conf) { - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); RTE_SET_USED(dev); RTE_SET_USED(port_id); @@ -379,7 +379,7 @@ dpaa_event_port_setup(struct rte_eventdev *dev, uint8_t port_id, { struct dpaa_eventdev *eventdev = dev->data->dev_private; - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); RTE_SET_USED(port_conf); dev->data->ports[port_id] = &eventdev->ports[port_id]; @@ -390,7 +390,7 @@ dpaa_event_port_setup(struct rte_eventdev *dev, uint8_t port_id, static void dpaa_event_port_release(void *port) { - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); RTE_SET_USED(port); } @@ -466,7 +466,7 @@ dpaa_event_eth_rx_adapter_caps_get(const struct rte_eventdev *dev, { const char *ethdev_driver = eth_dev->device->driver->name; - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); RTE_SET_USED(dev); @@ -491,14 +491,14 @@ dpaa_event_eth_rx_adapter_queue_add( struct dpaa_if *dpaa_intf = eth_dev->data->dev_private; int ret, i; - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); if (rx_queue_id == -1) { for (i = 0; i < dpaa_intf->nb_rx_queues; i++) { ret = dpaa_eth_eventq_attach(eth_dev, i, ch_id, queue_conf); if (ret) { - EVENTDEV_DRV_ERR( + DPAA_EVENTDEV_ERR( "Event Queue attach failed:%d\n", ret); goto detach_configured_queues; } @@ -508,7 +508,7 @@ dpaa_event_eth_rx_adapter_queue_add( ret = dpaa_eth_eventq_attach(eth_dev, rx_queue_id, ch_id, queue_conf); if (ret) - EVENTDEV_DRV_ERR("dpaa_eth_eventq_attach failed:%d\n", ret); + DPAA_EVENTDEV_ERR("dpaa_eth_eventq_attach failed:%d\n", ret); return ret; detach_configured_queues: @@ -527,14 +527,14 @@ dpaa_event_eth_rx_adapter_queue_del(const struct rte_eventdev *dev, int ret, i; struct dpaa_if *dpaa_intf = eth_dev->data->dev_private; - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); RTE_SET_USED(dev); if (rx_queue_id == -1) { for (i = 0; i < dpaa_intf->nb_rx_queues; i++) { ret = dpaa_eth_eventq_detach(eth_dev, i); if (ret) - EVENTDEV_DRV_ERR( + DPAA_EVENTDEV_ERR( "Event Queue detach failed:%d\n", ret); } @@ -543,7 +543,7 @@ dpaa_event_eth_rx_adapter_queue_del(const struct rte_eventdev *dev, ret = dpaa_eth_eventq_detach(eth_dev, rx_queue_id); if (ret) - EVENTDEV_DRV_ERR("dpaa_eth_eventq_detach failed:%d\n", ret); + DPAA_EVENTDEV_ERR("dpaa_eth_eventq_detach failed:%d\n", ret); return ret; } @@ -551,7 +551,7 @@ static int dpaa_event_eth_rx_adapter_start(const struct rte_eventdev *dev, const struct rte_eth_dev *eth_dev) { - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); RTE_SET_USED(dev); RTE_SET_USED(eth_dev); @@ -563,7 +563,7 @@ static int dpaa_event_eth_rx_adapter_stop(const struct rte_eventdev *dev, const struct rte_eth_dev *eth_dev) { - EVENTDEV_DRV_FUNC_TRACE(); + EVENTDEV_INIT_FUNC_TRACE(); RTE_SET_USED(dev); RTE_SET_USED(eth_dev); @@ -603,7 +603,7 @@ dpaa_event_dev_create(const char *name) sizeof(struct dpaa_eventdev), rte_socket_id()); if (eventdev == NULL) { - EVENTDEV_DRV_ERR("Failed to create eventdev vdev %s", name); + DPAA_EVENTDEV_ERR("Failed to create eventdev vdev %s", name); goto fail; } @@ -631,7 +631,7 @@ dpaa_event_dev_probe(struct rte_vdev_device *vdev) const char *name; name = rte_vdev_device_name(vdev); - EVENTDEV_DRV_LOG("Initializing %s", name); + DPAA_EVENTDEV_INFO("Initializing %s", name); return dpaa_event_dev_create(name); } @@ -642,7 +642,7 @@ dpaa_event_dev_remove(struct rte_vdev_device *vdev) const char *name; name = rte_vdev_device_name(vdev); - EVENTDEV_DRV_LOG("Closing %s", name); + DPAA_EVENTDEV_INFO("Closing %s", name); return rte_event_pmd_vdev_uninit(name); } diff --git a/drivers/event/dpaa/dpaa_eventdev.h b/drivers/event/dpaa/dpaa_eventdev.h index 583e46c..3994bd6 100644 --- a/drivers/event/dpaa/dpaa_eventdev.h +++ b/drivers/event/dpaa/dpaa_eventdev.h @@ -12,13 +12,6 @@ #define EVENTDEV_NAME_DPAA_PMD event_dpaa1 -#define EVENTDEV_DRV_LOG(fmt, args...) \ - DPAA_EVENTDEV_INFO(fmt, ## args) -#define EVENTDEV_DRV_FUNC_TRACE() \ - DPAA_EVENTDEV_DEBUG("%s() Called:\n", __func__) -#define EVENTDEV_DRV_ERR(fmt, args...) \ - DPAA_EVENTDEV_ERR("%s(): " fmt "\n", __func__, ## args) - #define DPAA_EVENT_MAX_PORTS 8 #define DPAA_EVENT_MAX_QUEUES 16 #define DPAA_EVENT_MIN_DEQUEUE_TIMEOUT 1 From patchwork Tue Sep 25 07:02:35 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Hemant Agrawal X-Patchwork-Id: 147400 Delivered-To: patch@linaro.org Received: by 2002:a2e:8595:0:0:0:0:0 with SMTP id b21-v6csp373399lji; Tue, 25 Sep 2018 00:04:49 -0700 (PDT) X-Google-Smtp-Source: ACcGV60/AR2z2/5GFn2dEOL/TgSxu2mOYOsShXsi336cbEByVBBmk4wPVeoyVGbHFvH/1ViPN8CV X-Received: by 2002:a1c:4c0c:: with SMTP id z12-v6mr692486wmf.57.1537859089104; Tue, 25 Sep 2018 00:04:49 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1537859089; cv=none; d=google.com; s=arc-20160816; b=Zxeo31DhzSYwTAHQy2fLm/+8FoSDlxQpFcsCLxOq2MqNtkT9QH/e2iM7Bh/p9/Za1x YBBKVoreCAkrimDkMk8JYs5afNQaPy/k4amKN2Vic0WAnjXyrjj+h3VkSvrpGnbOP2qh 29YVezHkCrvmfZvAeG9L2X+1QKl/7MtOsfDtEA+PQJ7uPQL8oYLNxexq+VgpmVFlFP94 psoQ5W/Wsc/xXzZbcVAJbWD47UZIHLYtBjZcL5DEhNJbF+LhI1YM1JlXiXvCcvXFIIaD VCBDSit/m1t5Kue1YWJDG8QbUv46NxYRbnZdH/UtROrHYSaXJUALBWMfDDY2ElQv1Na6 Xb3Q== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:subject:references:in-reply-to :message-id:date:cc:to:from; bh=Uaww1daoH4YFXEw27Jku/yymu5U8NPFv5MsQTvs6Xnw=; b=UF2LGnkEqc12a3EBq/XrsFHWI2Ds+R0dyGrFBH3Hk8S3dVdJ57GsR0tI8mmkPOfjcU xZFqRCmGYA1u/8eHUQbdkIL7SwkCb2LD3j62CXTbqpvg2+YHTelK0QUSoYpBfG7DJM+F x/MQl/qL7pR6cM0X1ECu6r7HWlqGWSXHMr4TG3/MAZpqbxjdlod+f7LDqdEXnUtohkoj Ganmwy2k9IOE5xK+KD/Sl5njwgcx5DQzlcPbJjWFYTHDOM1J0IMVPeqbBjx51quG+gM6 YFRUqu2Zy5wg+IoHS52CyUouVhabu8clVflxupBgfBHn8YeyGFSOmv0iMSC2z+YUCbfE Fbow== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: domain of dev-bounces@dpdk.org designates 92.243.14.124 as permitted sender) smtp.mailfrom=dev-bounces@dpdk.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=nxp.com Return-Path: Received: from dpdk.org (dpdk.org. [92.243.14.124]) by mx.google.com with ESMTP id 66-v6si1567233wra.32.2018.09.25.00.04.48; Tue, 25 Sep 2018 00:04:49 -0700 (PDT) Received-SPF: pass (google.com: domain of dev-bounces@dpdk.org designates 92.243.14.124 as permitted sender) client-ip=92.243.14.124; Authentication-Results: mx.google.com; spf=pass (google.com: domain of dev-bounces@dpdk.org designates 92.243.14.124 as permitted sender) smtp.mailfrom=dev-bounces@dpdk.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=nxp.com Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id BF9AB44BE; Tue, 25 Sep 2018 09:04:42 +0200 (CEST) Received: from inva020.nxp.com (inva020.nxp.com [92.121.34.13]) by dpdk.org (Postfix) with ESMTP id 802A01AFF for ; Tue, 25 Sep 2018 09:04:39 +0200 (CEST) Received: from inva020.nxp.com (localhost [127.0.0.1]) by inva020.eu-rdc02.nxp.com (Postfix) with ESMTP id 4BC381A0006; Tue, 25 Sep 2018 09:04:39 +0200 (CEST) Received: from invc005.ap-rdc01.nxp.com (invc005.ap-rdc01.nxp.com [165.114.16.14]) by inva020.eu-rdc02.nxp.com (Postfix) with ESMTP id 6D4CA1A0179; Tue, 25 Sep 2018 09:04:37 +0200 (CEST) Received: from bf-netperf1.ap.freescale.net (bf-netperf1.ap.freescale.net [10.232.134.28]) by invc005.ap-rdc01.nxp.com (Postfix) with ESMTP id D4675402E2; Tue, 25 Sep 2018 15:04:34 +0800 (SGT) From: Hemant Agrawal To: dev@dpdk.org Cc: jerin.jacob@caviumnetworks.com Date: Tue, 25 Sep 2018 12:32:35 +0530 Message-Id: <1537858955-6884-2-git-send-email-hemant.agrawal@nxp.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1537858955-6884-1-git-send-email-hemant.agrawal@nxp.com> References: <1535607196-26782-1-git-send-email-hemant.agrawal@nxp.com> <1537858955-6884-1-git-send-email-hemant.agrawal@nxp.com> X-Virus-Scanned: ClamAV using ClamSMTP Subject: [dpdk-dev] [PATCH v2 2/2] event/dpaa: add select based event support X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" This patch add support to use select call with qman portal fd for timeout based dequeue request for eventdev. If there is a event available qman portal fd will be set and the function will be awakened. If no event is available, it will only wait till the given timeout value. In case of interrupt the timeout ticks are used as usecs. Signed-off-by: Hemant Agrawal --- Note: This patch has a dependency on following patch series: http://mails.dpdk.org/archives/dev/2018-September/112433.html which is now part of dpdk-next-net tree. doc/guides/eventdevs/dpaa.rst | 2 + drivers/event/dpaa/dpaa_eventdev.c | 283 +++++++++++++++++++++++++++++++------ drivers/event/dpaa/dpaa_eventdev.h | 10 +- 3 files changed, 247 insertions(+), 48 deletions(-) -- 2.7.4 diff --git a/doc/guides/eventdevs/dpaa.rst b/doc/guides/eventdevs/dpaa.rst index 7383295..2f356d3 100644 --- a/doc/guides/eventdevs/dpaa.rst +++ b/doc/guides/eventdevs/dpaa.rst @@ -122,6 +122,8 @@ Example: ./your_eventdev_application --vdev="event_dpaa1" +* Use dev arg option ``disable_intr=1`` to disable the interrupt mode + Limitations ----------- diff --git a/drivers/event/dpaa/dpaa_eventdev.c b/drivers/event/dpaa/dpaa_eventdev.c index 9ddaf30..1e247e4 100644 --- a/drivers/event/dpaa/dpaa_eventdev.c +++ b/drivers/event/dpaa/dpaa_eventdev.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include "dpaa_eventdev.h" @@ -43,22 +44,34 @@ * 1 Eventdev can have N Eventqueue */ +#define DISABLE_INTR_MODE "disable_intr" + static int dpaa_event_dequeue_timeout_ticks(struct rte_eventdev *dev, uint64_t ns, uint64_t *timeout_ticks) { - uint64_t cycles_per_second; - EVENTDEV_INIT_FUNC_TRACE(); RTE_SET_USED(dev); + uint64_t cycles_per_second; + cycles_per_second = rte_get_timer_hz(); - *timeout_ticks = ns * (cycles_per_second / NS_PER_S); + *timeout_ticks = (ns * cycles_per_second) / NS_PER_S; return 0; } +static int +dpaa_event_dequeue_timeout_ticks_intr(struct rte_eventdev *dev, uint64_t ns, + uint64_t *timeout_ticks) +{ + RTE_SET_USED(dev); + + *timeout_ticks = ns/1000; + return 0; +} + static void dpaa_eventq_portal_add(u16 ch_id) { @@ -100,6 +113,56 @@ dpaa_event_enqueue(void *port, const struct rte_event *ev) return dpaa_event_enqueue_burst(port, ev, 1); } +static void drain_4_bytes(int fd, fd_set *fdset) +{ + if (FD_ISSET(fd, fdset)) { + /* drain 4 bytes */ + uint32_t junk; + ssize_t sjunk = read(qman_thread_fd(), &junk, sizeof(junk)); + if (sjunk != sizeof(junk)) + DPAA_EVENTDEV_ERR("UIO irq read error"); + } +} + +static inline int +dpaa_event_dequeue_wait(uint64_t timeout_ticks) +{ + int fd_qman, nfds; + int ret; + fd_set readset; + + /* Go into (and back out of) IRQ mode for each select, + * it simplifies exit-path considerations and other + * potential nastiness. + */ + struct timeval tv = { + .tv_sec = timeout_ticks / 1000000, + .tv_usec = timeout_ticks % 1000000 + }; + + fd_qman = qman_thread_fd(); + nfds = fd_qman + 1; + FD_ZERO(&readset); + FD_SET(fd_qman, &readset); + + qman_irqsource_add(QM_PIRQ_DQRI); + + ret = select(nfds, &readset, NULL, NULL, &tv); + if (ret < 0) + return ret; + /* Calling irqsource_remove() prior to thread_irq() + * means thread_irq() will not process whatever caused + * the interrupts, however it does ensure that, once + * thread_irq() re-enables interrupts, they won't fire + * again immediately. + */ + qman_irqsource_remove(~0); + drain_4_bytes(fd_qman, &readset); + qman_thread_irq(); + + return ret; +} + static uint16_t dpaa_event_dequeue_burst(void *port, struct rte_event ev[], uint16_t nb_events, uint64_t timeout_ticks) @@ -107,8 +170,8 @@ dpaa_event_dequeue_burst(void *port, struct rte_event ev[], int ret; u16 ch_id; void *buffers[8]; - u32 num_frames, i; - uint64_t wait_time, cur_ticks, start_ticks; + u32 num_frames, i, irq = 0; + uint64_t cur_ticks = 0, wait_time_ticks = 0; struct dpaa_port *portal = (struct dpaa_port *)port; struct rte_mbuf *mbuf; @@ -147,20 +210,21 @@ dpaa_event_dequeue_burst(void *port, struct rte_event ev[], } DPAA_PER_LCORE_DQRR_HELD = 0; - if (portal->timeout == DPAA_EVENT_PORT_DEQUEUE_TIMEOUT_INVALID) - wait_time = timeout_ticks; + if (timeout_ticks) + wait_time_ticks = timeout_ticks; else - wait_time = portal->timeout; + wait_time_ticks = portal->timeout_us; - /* Lets dequeue the frames */ - start_ticks = rte_get_timer_cycles(); - wait_time += start_ticks; + wait_time_ticks += rte_get_timer_cycles(); do { + /* Lets dequeue the frames */ num_frames = qman_portal_dequeue(ev, nb_events, buffers); - if (num_frames != 0) + if (irq) + irq = 0; + if (num_frames) break; cur_ticks = rte_get_timer_cycles(); - } while (cur_ticks < wait_time); + } while (cur_ticks < wait_time_ticks); return num_frames; } @@ -171,6 +235,86 @@ dpaa_event_dequeue(void *port, struct rte_event *ev, uint64_t timeout_ticks) return dpaa_event_dequeue_burst(port, ev, 1, timeout_ticks); } +static uint16_t +dpaa_event_dequeue_burst_intr(void *port, struct rte_event ev[], + uint16_t nb_events, uint64_t timeout_ticks) +{ + int ret; + u16 ch_id; + void *buffers[8]; + u32 num_frames, i, irq = 0; + uint64_t cur_ticks = 0, wait_time_ticks = 0; + struct dpaa_port *portal = (struct dpaa_port *)port; + struct rte_mbuf *mbuf; + + if (unlikely(!RTE_PER_LCORE(dpaa_io))) { + /* Affine current thread context to a qman portal */ + ret = rte_dpaa_portal_init((void *)0); + if (ret) { + DPAA_EVENTDEV_ERR("Unable to initialize portal"); + return ret; + } + } + + if (unlikely(!portal->is_port_linked)) { + /* + * Affine event queue for current thread context + * to a qman portal. + */ + for (i = 0; i < portal->num_linked_evq; i++) { + ch_id = portal->evq_info[i].ch_id; + dpaa_eventq_portal_add(ch_id); + } + portal->is_port_linked = true; + } + + /* Check if there are atomic contexts to be released */ + i = 0; + while (DPAA_PER_LCORE_DQRR_SIZE) { + if (DPAA_PER_LCORE_DQRR_HELD & (1 << i)) { + qman_dca_index(i, 0); + mbuf = DPAA_PER_LCORE_DQRR_MBUF(i); + mbuf->seqn = DPAA_INVALID_MBUF_SEQN; + DPAA_PER_LCORE_DQRR_HELD &= ~(1 << i); + DPAA_PER_LCORE_DQRR_SIZE--; + } + i++; + } + DPAA_PER_LCORE_DQRR_HELD = 0; + + if (timeout_ticks) + wait_time_ticks = timeout_ticks; + else + wait_time_ticks = portal->timeout_us; + + do { + /* Lets dequeue the frames */ + num_frames = qman_portal_dequeue(ev, nb_events, buffers); + if (irq) + irq = 0; + if (num_frames) + break; + if (wait_time_ticks) { /* wait for time */ + if (dpaa_event_dequeue_wait(wait_time_ticks) > 0) { + irq = 1; + continue; + } + break; /* no event after waiting */ + } + cur_ticks = rte_get_timer_cycles(); + } while (cur_ticks < wait_time_ticks); + + return num_frames; +} + +static uint16_t +dpaa_event_dequeue_intr(void *port, + struct rte_event *ev, + uint64_t timeout_ticks) +{ + return dpaa_event_dequeue_burst_intr(port, ev, 1, timeout_ticks); +} + static void dpaa_event_dev_info_get(struct rte_eventdev *dev, struct rte_event_dev_info *dev_info) @@ -184,7 +328,7 @@ dpaa_event_dev_info_get(struct rte_eventdev *dev, dev_info->max_dequeue_timeout_ns = DPAA_EVENT_MAX_DEQUEUE_TIMEOUT; dev_info->dequeue_timeout_ns = - DPAA_EVENT_MIN_DEQUEUE_TIMEOUT; + DPAA_EVENT_PORT_DEQUEUE_TIMEOUT_NS; dev_info->max_event_queues = DPAA_EVENT_MAX_QUEUES; dev_info->max_event_queue_flows = @@ -230,15 +374,6 @@ dpaa_event_dev_configure(const struct rte_eventdev *dev) priv->nb_event_port_enqueue_depth = conf->nb_event_port_enqueue_depth; priv->event_dev_cfg = conf->event_dev_cfg; - /* Check dequeue timeout method is per dequeue or global */ - if (priv->event_dev_cfg & RTE_EVENT_DEV_CFG_PER_DEQUEUE_TIMEOUT) { - /* - * Use timeout value as given in dequeue operation. - * So invalidating this timetout value. - */ - priv->dequeue_timeout_ns = 0; - } - ch_id = rte_malloc("dpaa-channels", sizeof(uint32_t) * priv->nb_event_queues, RTE_CACHE_LINE_SIZE); @@ -260,24 +395,35 @@ dpaa_event_dev_configure(const struct rte_eventdev *dev) /* Lets prepare event ports */ memset(&priv->ports[0], 0, sizeof(struct dpaa_port) * priv->nb_event_ports); + + /* Check dequeue timeout method is per dequeue or global */ if (priv->event_dev_cfg & RTE_EVENT_DEV_CFG_PER_DEQUEUE_TIMEOUT) { - for (i = 0; i < priv->nb_event_ports; i++) { - priv->ports[i].timeout = - DPAA_EVENT_PORT_DEQUEUE_TIMEOUT_INVALID; - } - } else if (priv->dequeue_timeout_ns == 0) { - for (i = 0; i < priv->nb_event_ports; i++) { - dpaa_event_dequeue_timeout_ticks(NULL, - DPAA_EVENT_PORT_DEQUEUE_TIMEOUT_NS, - &priv->ports[i].timeout); - } + /* + * Use timeout value as given in dequeue operation. + * So invalidating this timeout value. + */ + priv->dequeue_timeout_ns = 0; + + } else if (conf->dequeue_timeout_ns == 0) { + priv->dequeue_timeout_ns = DPAA_EVENT_PORT_DEQUEUE_TIMEOUT_NS; } else { - for (i = 0; i < priv->nb_event_ports; i++) { - dpaa_event_dequeue_timeout_ticks(NULL, - priv->dequeue_timeout_ns, - &priv->ports[i].timeout); + priv->dequeue_timeout_ns = conf->dequeue_timeout_ns; + } + + for (i = 0; i < priv->nb_event_ports; i++) { + if (priv->intr_mode) { + priv->ports[i].timeout_us = + priv->dequeue_timeout_ns/1000; + } else { + uint64_t cycles_per_second; + + cycles_per_second = rte_get_timer_hz(); + priv->ports[i].timeout_us = + (priv->dequeue_timeout_ns * cycles_per_second) + / NS_PER_S; } } + /* * TODO: Currently portals are affined with threads. Maximum threads * can be created equals to number of lcore. @@ -454,7 +600,8 @@ dpaa_event_port_unlink(struct rte_eventdev *dev, void *port, event_queue->event_port = NULL; } - event_port->num_linked_evq = event_port->num_linked_evq - i; + if (event_port->num_linked_evq) + event_port->num_linked_evq = event_port->num_linked_evq - i; return (int)i; } @@ -593,8 +740,44 @@ static struct rte_eventdev_ops dpaa_eventdev_ops = { .eth_rx_adapter_stop = dpaa_event_eth_rx_adapter_stop, }; +static int flag_check_handler(__rte_unused const char *key, + const char *value, __rte_unused void *opaque) +{ + if (strcmp(value, "1")) + return -1; + + return 0; +} + +static int +dpaa_event_check_flags(const char *params) +{ + struct rte_kvargs *kvlist; + + if (params == NULL || params[0] == '\0') + return 0; + + kvlist = rte_kvargs_parse(params, NULL); + if (kvlist == NULL) + return 0; + + if (!rte_kvargs_count(kvlist, DISABLE_INTR_MODE)) { + rte_kvargs_free(kvlist); + return 0; + } + /* INTR MODE is disabled when there's key-value pair: disable_intr = 1*/ + if (rte_kvargs_process(kvlist, DISABLE_INTR_MODE, + flag_check_handler, NULL) < 0) { + rte_kvargs_free(kvlist); + return 0; + } + rte_kvargs_free(kvlist); + + return 1; +} + static int -dpaa_event_dev_create(const char *name) +dpaa_event_dev_create(const char *name, const char *params) { struct rte_eventdev *eventdev; struct dpaa_eventdev *priv; @@ -606,18 +789,27 @@ dpaa_event_dev_create(const char *name) DPAA_EVENTDEV_ERR("Failed to create eventdev vdev %s", name); goto fail; } + priv = eventdev->data->dev_private; eventdev->dev_ops = &dpaa_eventdev_ops; eventdev->enqueue = dpaa_event_enqueue; eventdev->enqueue_burst = dpaa_event_enqueue_burst; - eventdev->dequeue = dpaa_event_dequeue; - eventdev->dequeue_burst = dpaa_event_dequeue_burst; + + if (dpaa_event_check_flags(params)) { + eventdev->dequeue = dpaa_event_dequeue; + eventdev->dequeue_burst = dpaa_event_dequeue_burst; + } else { + priv->intr_mode = 1; + eventdev->dev_ops->timeout_ticks = + dpaa_event_dequeue_timeout_ticks_intr; + eventdev->dequeue = dpaa_event_dequeue_intr; + eventdev->dequeue_burst = dpaa_event_dequeue_burst_intr; + } /* For secondary processes, the primary has done all the work */ if (rte_eal_process_type() != RTE_PROC_PRIMARY) return 0; - priv = eventdev->data->dev_private; priv->max_event_queues = DPAA_EVENT_MAX_QUEUES; return 0; @@ -629,11 +821,14 @@ static int dpaa_event_dev_probe(struct rte_vdev_device *vdev) { const char *name; + const char *params; name = rte_vdev_device_name(vdev); DPAA_EVENTDEV_INFO("Initializing %s", name); - return dpaa_event_dev_create(name); + params = rte_vdev_device_args(vdev); + + return dpaa_event_dev_create(name, params); } static int @@ -653,3 +848,5 @@ static struct rte_vdev_driver vdev_eventdev_dpaa_pmd = { }; RTE_PMD_REGISTER_VDEV(EVENTDEV_NAME_DPAA_PMD, vdev_eventdev_dpaa_pmd); +RTE_PMD_REGISTER_PARAM_STRING(EVENTDEV_NAME_DPAA_PMD, + DISABLE_INTR_MODE "="); diff --git a/drivers/event/dpaa/dpaa_eventdev.h b/drivers/event/dpaa/dpaa_eventdev.h index 3994bd6..8134e6b 100644 --- a/drivers/event/dpaa/dpaa_eventdev.h +++ b/drivers/event/dpaa/dpaa_eventdev.h @@ -12,8 +12,8 @@ #define EVENTDEV_NAME_DPAA_PMD event_dpaa1 -#define DPAA_EVENT_MAX_PORTS 8 -#define DPAA_EVENT_MAX_QUEUES 16 +#define DPAA_EVENT_MAX_PORTS 4 +#define DPAA_EVENT_MAX_QUEUES 8 #define DPAA_EVENT_MIN_DEQUEUE_TIMEOUT 1 #define DPAA_EVENT_MAX_DEQUEUE_TIMEOUT (UINT32_MAX - 1) #define DPAA_EVENT_MAX_QUEUE_FLOWS 2048 @@ -21,7 +21,7 @@ #define DPAA_EVENT_MAX_EVENT_PRIORITY_LEVELS 0 #define DPAA_EVENT_MAX_EVENT_PORT RTE_MIN(RTE_MAX_LCORE, INT8_MAX) #define DPAA_EVENT_MAX_PORT_DEQUEUE_DEPTH 8 -#define DPAA_EVENT_PORT_DEQUEUE_TIMEOUT_NS 100UL +#define DPAA_EVENT_PORT_DEQUEUE_TIMEOUT_NS 100000UL #define DPAA_EVENT_PORT_DEQUEUE_TIMEOUT_INVALID ((uint64_t)-1) #define DPAA_EVENT_MAX_PORT_ENQUEUE_DEPTH 1 #define DPAA_EVENT_MAX_NUM_EVENTS (INT32_MAX - 1) @@ -54,7 +54,7 @@ struct dpaa_port { struct dpaa_eventq evq_info[DPAA_EVENT_MAX_QUEUES]; uint8_t num_linked_evq; uint8_t is_port_linked; - uint64_t timeout; + uint64_t timeout_us; }; struct dpaa_eventdev { @@ -65,7 +65,7 @@ struct dpaa_eventdev { uint8_t max_event_queues; uint8_t nb_event_queues; uint8_t nb_event_ports; - uint8_t resvd; + uint8_t intr_mode; uint32_t nb_event_queue_flows; uint32_t nb_event_port_dequeue_depth; uint32_t nb_event_port_enqueue_depth;