From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga03.intel.com (mga03.intel.com [134.134.136.65]) by dpdk.org (Postfix) with ESMTP id 76256567C for ; Sun, 28 May 2017 17:52:54 +0200 (CEST) Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by orsmga103.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 28 May 2017 08:52:53 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.38,410,1491289200"; d="scan'208";a="1175412087" Received: from dpdk4.bj.intel.com ([172.16.182.85]) by fmsmga002.fm.intel.com with ESMTP; 28 May 2017 08:52:50 -0700 From: Jeff Guo To: helin.zhang@intel.com, jingjing.wu@intel.com, bruce.richardson@intel.com, konstantin.ananyev@intel.com, yuanhan.liu@intel.com, gaetan.rivet@6wind.com Cc: dev@dpdk.org, jia.guo@intel.com Date: Sun, 28 May 2017 23:44:40 +0800 Message-Id: <1495986280-26207-1-git-send-email-jia.guo@intel.com> X-Mailer: git-send-email 2.7.4 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Subject: [dpdk-dev] [RFC] Add hot plug event in rte eal interrupt and inplement it in i40e driver. 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: , X-List-Received-Date: Sun, 28 May 2017 15:52:55 -0000 For HW hotplug feature, we had already got upstream that removal event adding from 6wind as bellow. dependency of “add device removal event” patch set: http://dpdk.org/dev/patchwork/patch/23693/ [dpdk-dev,v2,1/5] ethdev: introduce device removal event http://dpdk.org/dev/patchwork/patch/23694/ [dpdk-dev,v2,2/5] net/mlx4: device removal event support http://dpdk.org/dev/patchwork/patch/23695/ [dpdk-dev,v2,3/5] app/testpmd: generic event handler http://dpdk.org/dev/patchwork/patch/23696/ [dpdk-dev,v2,4/5] app/testpmd: request link status interrupt http://dpdk.org/dev/patchwork/patch/23697/ [dpdk-dev,v2,5/5] app/testpmd: request device removal interrupt >>From the patches, we can see a new event type “RTE_ETH_DEV_INTR_RMV” has been added into the ethdev, and the event has been implemented in mlx4 driver, and Testpmd be use for testing purposes and as a practical usage example for how to use these event. The progress is use the mlx4 driver to register interrupt callback function to rte eal interrupt source, and when rte epolling detect the IBV_EVENT_DEVICE_FATAL , which is identify the device remove behavior, it will callback into the driver’s interrupt handle to handle it, and then callback to the user app, such as testpmd, to detach the pci device. So far, except the mlx4 driver, other driver like i40, that not have the remove interrupt from hw, will not be able to monitoring the remove behavior, so in order to expand the hot plug feature for all driver cases, something must be done ot detect the remove event at the kernel level and offer a new line of interrupt to the userland. The idea is coming as below. Use I40e as example, we know that the rmv interrupt is not added in hw, but we could monitor the uio file descriptor to catch the device remove event as bellow. The info of uevent form FD monitoring: remove@/devices/pci0000:80/0000:80:02.2/0000:82:00.0/0000:83:03.0/0000:84:00.2/uio/uio2 ACTION=remove DEVPATH=/devices/pci0000:80/0000:80:02.2/0000:82:00.0/0000:83:03.0/0000:84:00.2/uio/uio2 SUBSYSTEM=uio MAJOR=243 MINOR=2 DEVNAME=uio2 SEQNUM=11366 Firstly, in order to monitor the uio file descriptor, we need to create socket to monitor the uio fd, that is defined as “hotplug_fd”, and then add the uio fd into the epoll fd list, rte eal could epoll all of the interrupt event from hw interrupt and also include the uevent from hotplug_fd. Secondly, in order to read out the uevent that monitoring, we need to add uevent API in rte layer. We plan add 2 , rte_uevent_connect and rte_get_uevent. All driver interrupt handler could use these API to enable the uevent monitoring, and read out the uevent type , then corresponding to handle these uevent, such as detach the device when get the remove type. Signed-off-by: Jeff Guo --- drivers/net/i40e/i40e_ethdev.c | 15 +++ lib/librte_eal/linuxapp/eal/eal_interrupts.c | 146 ++++++++++++++++++++- .../linuxapp/eal/include/exec-env/rte_interrupts.h | 32 +++++ 3 files changed, 191 insertions(+), 2 deletions(-) diff --git a/drivers/net/i40e/i40e_ethdev.c b/drivers/net/i40e/i40e_ethdev.c index 4c49673..0336f82 100644 --- a/drivers/net/i40e/i40e_ethdev.c +++ b/drivers/net/i40e/i40e_ethdev.c @@ -66,6 +66,8 @@ #include "i40e_pf.h" #include "i40e_regs.h" +extern int hotplug_fd; + #define ETH_I40E_FLOATING_VEB_ARG "enable_floating_veb" #define ETH_I40E_FLOATING_VEB_LIST_ARG "floating_veb_list" @@ -5808,8 +5810,21 @@ i40e_dev_interrupt_handler(void *param) { struct rte_eth_dev *dev = (struct rte_eth_dev *)param; struct i40e_hw *hw = I40E_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct rte_uevent event; uint32_t icr0; + /* check device uevent */ + while (rte_get_uevent(hotplug_fd, &event) > 0) { + if (event.subsystem == 1) { + if (event.action == RTE_UEVENT_ADD) { + //do nothing here + } else if (event.action == RTE_UEVENT_REMOVE) { + _rte_eth_dev_callback_process(dev, + RTE_ETH_EVENT_INTR_RMV, NULL); + } + } + } + /* Disable interrupt */ i40e_pf_disable_irq0(hw); diff --git a/lib/librte_eal/linuxapp/eal/eal_interrupts.c b/lib/librte_eal/linuxapp/eal/eal_interrupts.c index 2e3bd12..873ab5f 100644 --- a/lib/librte_eal/linuxapp/eal/eal_interrupts.c +++ b/lib/librte_eal/linuxapp/eal/eal_interrupts.c @@ -65,6 +65,10 @@ #include #include +#include +#include +#include + #include "eal_private.h" #include "eal_vfio.h" #include "eal_thread.h" @@ -74,6 +78,11 @@ static RTE_DEFINE_PER_LCORE(int, _epfd) = -1; /**< epoll fd per thread */ +#define RTE_UEVENT_MSG_LEN 4096 +#define RTE_UEVENT_SUBSYSTEM_UIO 1 + +int hotplug_fd = -1; + /** * union for pipe fds. */ @@ -669,10 +678,13 @@ eal_intr_process_interrupts(struct epoll_event *events, int nfds) RTE_SET_USED(r); return -1; } + rte_spinlock_lock(&intr_lock); TAILQ_FOREACH(src, &intr_sources, next) - if (src->intr_handle.fd == - events[n].data.fd) + if ((src->intr_handle.fd == + events[n].data.fd) || + (hotplug_fd == + events[n].data.fd)) break; if (src == NULL){ rte_spinlock_unlock(&intr_lock); @@ -858,7 +870,24 @@ eal_intr_thread_main(__rte_unused void *arg) } else numfds++; + + /** + * add device uevent file descriptor + * into wait list for hot plug. + */ + ev.events = EPOLLIN | EPOLLPRI | EPOLLRDHUP | EPOLLHUP; + ev.data.fd = hotplug_fd; + if (epoll_ctl(pfd, EPOLL_CTL_ADD, + hotplug_fd, &ev) < 0){ + rte_panic("Error adding hotplug_fd %d epoll_ctl, %s\n", + hotplug_fd, strerror(errno)); + } + else + numfds++; + } + + rte_spinlock_unlock(&intr_lock); /* serve the interrupt */ eal_intr_handle_interrupts(pfd, numfds); @@ -877,6 +906,9 @@ rte_eal_intr_init(void) int ret = 0, ret_1 = 0; char thread_name[RTE_MAX_THREAD_NAME_LEN]; + /* connect to monitor device uevent */ + rte_uevent_connect(); + /* init the global interrupt source head */ TAILQ_INIT(&intr_sources); @@ -1255,3 +1287,113 @@ rte_intr_cap_multiple(struct rte_intr_handle *intr_handle) return 0; } + +int +rte_uevent_connect(void) +{ + struct sockaddr_nl addr; + int ret; + int netlink_fd; + int size = 64 * 1024; + int nonblock = 1; + memset(&addr, 0, sizeof(addr)); + addr.nl_family = AF_NETLINK; + addr.nl_pid = getpid(); + addr.nl_groups = 0xffffffff; + + netlink_fd = socket(PF_NETLINK, SOCK_DGRAM, NETLINK_KOBJECT_UEVENT); + if (netlink_fd < 0) + return -1; + + setsockopt(netlink_fd, SOL_SOCKET, SO_RCVBUFFORCE, &size, sizeof(size)); + + ret = ioctl(netlink_fd, FIONBIO, &nonblock); + if (ret != 0) { + RTE_LOG(ERR, EAL, + "ioctl(FIONBIO) failed\n"); + close(netlink_fd); + return -1; + } + + if (bind(netlink_fd, (struct sockaddr *) &addr, sizeof(addr)) < 0) { + close(netlink_fd); + return -1; + } + + hotplug_fd = netlink_fd; + + return netlink_fd; +} + +static int +parse_event(const char *buf, struct rte_uevent *event) +{ + char action[RTE_UEVENT_MSG_LEN]; + char subsystem[RTE_UEVENT_MSG_LEN]; + char dev_path[RTE_UEVENT_MSG_LEN]; + + memset(action, 0, RTE_UEVENT_MSG_LEN); + memset(subsystem, 0, RTE_UEVENT_MSG_LEN); + memset(dev_path, 0, RTE_UEVENT_MSG_LEN); + + while (*buf) { + if (!strncmp(buf, "ACTION=", 7)) { + buf += 7; + snprintf(action, sizeof(action), "%s", buf); + } else if (!strncmp(buf, "DEVPATH=", 8)) { + buf += 8; + snprintf(dev_path, sizeof(dev_path), "%s", buf); + } else if (!strncmp(buf, "SUBSYSTEM=", 10)) { + buf += 10; + snprintf(subsystem, sizeof(subsystem), "%s", buf); + } + while (*buf++) + ; + } + + if (!strncmp(subsystem, "uio", 3)) { + + event->subsystem = RTE_UEVENT_SUBSYSTEM_UIO; + if (!strncmp(action, "add", 3)) { + event->action = RTE_UEVENT_ADD; + } + if (!strncmp(action, "remove", 6)) { + event->action = RTE_UEVENT_REMOVE; + } + return 1; + } + + return -1; +} + +int +rte_get_uevent(int fd, struct rte_uevent *uevent) +{ + int ret; + char buf[RTE_UEVENT_MSG_LEN]; + + memset(uevent, 0, sizeof(struct rte_uevent)); + memset(buf, 0, RTE_UEVENT_MSG_LEN); + + ret = recv(fd, buf, RTE_UEVENT_MSG_LEN - 1, MSG_DONTWAIT); + if (ret > 0) { + return parse_event(buf, uevent); + } + + if (ret < 0) { + if (errno == EAGAIN || errno == EWOULDBLOCK) { + return 0; + } else { + RTE_LOG(ERR, EAL, + "Socket read error(%d): %s\n", + errno, strerror(errno)); + } + } + + /* connection closed */ + if (ret == 0) { + return -1; + } + + return 0; +} diff --git a/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h b/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h index 6daffeb..d32ba01 100644 --- a/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h +++ b/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h @@ -99,6 +99,16 @@ struct rte_intr_handle { int *intr_vec; /**< intr vector number array */ }; +enum rte_uevent_action { + RTE_UEVENT_ADD = 0, /**< uevent type of device add */ + RTE_UEVENT_REMOVE = 1, /**< uevent type of device remove*/ +}; + +struct rte_uevent { + enum rte_uevent_action action; /**< uevent action type */ + int subsystem; /**< subsystem id */ +}; + #define RTE_EPOLL_PER_THREAD -1 /**< to hint using per thread epfd */ /** @@ -236,4 +246,26 @@ rte_intr_allow_others(struct rte_intr_handle *intr_handle); int rte_intr_cap_multiple(struct rte_intr_handle *intr_handle); +/** + * It read out the uevent from the specific file descriptor. + * + * @param fd + * The fd which the uevent associated to + * @param uevent + * Pointer to the uevent which read from the monitoring fd. + * @return + * - On success, one. + * - On failure, zeor or a negative value. + */ +int +rte_get_uevent(int fd, struct rte_uevent *uevent); + +/** + * Connect to the device uevent file descriptor. + * @return + * return the connected uevent fd. + */ +int +rte_uevent_connect(void); + #endif /* _RTE_LINUXAPP_INTERRUPTS_H_ */ -- 2.7.4