From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga02.intel.com (mga02.intel.com [134.134.136.20]) by dpdk.org (Postfix) with ESMTP id E4314ADE6 for ; Mon, 23 Feb 2015 17:56:29 +0100 (CET) Received: from orsmga003.jf.intel.com ([10.7.209.27]) by orsmga101.jf.intel.com with ESMTP; 23 Feb 2015 08:56:04 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.09,631,1418112000"; d="scan'208";a="531534358" Received: from shvmail01.sh.intel.com ([10.239.29.42]) by orsmga003.jf.intel.com with ESMTP; 23 Feb 2015 08:47:04 -0800 Received: from shecgisg004.sh.intel.com (shecgisg004.sh.intel.com [10.239.29.89]) by shvmail01.sh.intel.com with ESMTP id t1NGu1rr013623; Tue, 24 Feb 2015 00:56:01 +0800 Received: from shecgisg004.sh.intel.com (localhost [127.0.0.1]) by shecgisg004.sh.intel.com (8.13.6/8.13.6/SuSE Linux 0.8) with ESMTP id t1NGtx5Y014708; Tue, 24 Feb 2015 00:56:01 +0800 Received: (from dyzhou@localhost) by shecgisg004.sh.intel.com (8.13.6/8.13.6/Submit) id t1NGtxLh014704; Tue, 24 Feb 2015 00:55:59 +0800 From: Zhou Danny To: dev@dpdk.org Date: Tue, 24 Feb 2015 00:55:41 +0800 Message-Id: <1424710542-14637-6-git-send-email-danny.zhou@intel.com> X-Mailer: git-send-email 1.7.4.1 In-Reply-To: <1424710542-14637-1-git-send-email-danny.zhou@intel.com> References: <1424710542-14637-1-git-send-email-danny.zhou@intel.com> Subject: [dpdk-dev] [PATCH v5 5/6] eal: add per rx queue interrupt handling based on VFIO X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 23 Feb 2015 16:56:30 -0000 v5 changes - Rebase the patchset onto the HEAD - Isolate ethdev from EAL for new-added wait-for-rx interrupt function - Export wait-for-rx interrupt function for shared libraries v4 changes: - Adjust position of new-added structure fields v3 changes: - Fix review comments v2 changes: - Fix compilation issue for a missed header file - Bug fix: free unreleased resources on the exception path before return - Consolidate coding style related review comments This patch does below: - Create multiple VFIO eventfd for rx queues. - Handle per rx queue interrupt. - Eliminate unnecessary suspended DPDK polling thread wakeup mechanism for rx interrupt by allowing polling thread epoll_wait rx queue interrupt notification. Signed-off-by: Danny Zhou Tested-by: Yong Liu --- lib/librte_eal/bsdapp/eal/rte_eal_version.map | 1 + lib/librte_eal/common/include/rte_eal.h | 1 + lib/librte_eal/common/include/rte_interrupts.h | 12 ++ lib/librte_eal/linuxapp/eal/eal_interrupts.c | 191 ++++++++++++++++++------ lib/librte_eal/linuxapp/eal/eal_pci_vfio.c | 12 +- lib/librte_eal/linuxapp/eal/rte_eal_version.map | 1 + 6 files changed, 174 insertions(+), 44 deletions(-) diff --git a/lib/librte_eal/bsdapp/eal/rte_eal_version.map b/lib/librte_eal/bsdapp/eal/rte_eal_version.map index 5ed6e4d..dd300ea 100644 --- a/lib/librte_eal/bsdapp/eal/rte_eal_version.map +++ b/lib/librte_eal/bsdapp/eal/rte_eal_version.map @@ -57,6 +57,7 @@ DPDK_2.0 { rte_intr_callback_unregister; rte_intr_disable; rte_intr_enable; + rte_intr_wait_rx_pkt; rte_log; rte_log_add_in_history; rte_log_cur_msg_loglevel; diff --git a/lib/librte_eal/common/include/rte_eal.h b/lib/librte_eal/common/include/rte_eal.h index f4ecd2e..b9d5230 100644 --- a/lib/librte_eal/common/include/rte_eal.h +++ b/lib/librte_eal/common/include/rte_eal.h @@ -150,6 +150,7 @@ int rte_eal_iopl_init(void); * - On failure, a negative error value. */ int rte_eal_init(int argc, char **argv); + /** * Usage function typedef used by the application usage function. * diff --git a/lib/librte_eal/common/include/rte_interrupts.h b/lib/librte_eal/common/include/rte_interrupts.h index 609c34b..1ba2421 100644 --- a/lib/librte_eal/common/include/rte_interrupts.h +++ b/lib/librte_eal/common/include/rte_interrupts.h @@ -113,6 +113,18 @@ int rte_intr_enable(struct rte_intr_handle *intr_handle); */ int rte_intr_disable(struct rte_intr_handle *intr_handle); +/** + * @param intr_handle + * pointer to the interrupt handle. + * @param queue_id + * the queue id + * @return + * - On success, return 0 + * - On failure, returns -1. + */ +int rte_intr_wait_rx_pkt(struct rte_intr_handle *intr_handle, + uint8_t queue_id); + #ifdef __cplusplus } #endif diff --git a/lib/librte_eal/linuxapp/eal/eal_interrupts.c b/lib/librte_eal/linuxapp/eal/eal_interrupts.c index 8c5b834..ee0f019 100644 --- a/lib/librte_eal/linuxapp/eal/eal_interrupts.c +++ b/lib/librte_eal/linuxapp/eal/eal_interrupts.c @@ -127,6 +127,9 @@ static pthread_t intr_thread; #ifdef VFIO_PRESENT #define IRQ_SET_BUF_LEN (sizeof(struct vfio_irq_set) + sizeof(int)) +/* irq set buffer length for queue interrupts and LSC interrupt */ +#define MSIX_IRQ_SET_BUF_LEN (sizeof(struct vfio_irq_set) + \ + sizeof(int) * (VFIO_MAX_QUEUE_ID + 1)) /* enable legacy (INTx) interrupts */ static int @@ -218,10 +221,10 @@ vfio_disable_intx(struct rte_intr_handle *intr_handle) { return 0; } -/* enable MSI-X interrupts */ +/* enable MSI interrupts */ static int vfio_enable_msi(struct rte_intr_handle *intr_handle) { - int len, ret; + int len, ret, max_intr; char irq_set_buf[IRQ_SET_BUF_LEN]; struct vfio_irq_set *irq_set; int *fd_ptr; @@ -230,12 +233,19 @@ vfio_enable_msi(struct rte_intr_handle *intr_handle) { irq_set = (struct vfio_irq_set *) irq_set_buf; irq_set->argsz = len; - irq_set->count = 1; + if ((!intr_handle->max_intr) || + (intr_handle->max_intr > VFIO_MAX_QUEUE_ID)) + max_intr = VFIO_MAX_QUEUE_ID + 1; + else + max_intr = intr_handle->max_intr; + + irq_set->count = max_intr; irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER; irq_set->index = VFIO_PCI_MSI_IRQ_INDEX; irq_set->start = 0; fd_ptr = (int *) &irq_set->data; - *fd_ptr = intr_handle->fd; + memcpy(fd_ptr, intr_handle->queue_fd, sizeof(intr_handle->queue_fd)); + fd_ptr[max_intr - 1] = intr_handle->fd; ret = ioctl(intr_handle->vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set); @@ -244,27 +254,10 @@ vfio_enable_msi(struct rte_intr_handle *intr_handle) { intr_handle->fd); return -1; } - - /* manually trigger interrupt to enable it */ - memset(irq_set, 0, len); - len = sizeof(struct vfio_irq_set); - irq_set->argsz = len; - irq_set->count = 1; - irq_set->flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER; - irq_set->index = VFIO_PCI_MSI_IRQ_INDEX; - irq_set->start = 0; - - ret = ioctl(intr_handle->vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set); - - if (ret) { - RTE_LOG(ERR, EAL, "Error triggering MSI interrupts for fd %d\n", - intr_handle->fd); - return -1; - } return 0; } -/* disable MSI-X interrupts */ +/* disable MSI interrupts */ static int vfio_disable_msi(struct rte_intr_handle *intr_handle) { struct vfio_irq_set *irq_set; @@ -292,8 +285,8 @@ vfio_disable_msi(struct rte_intr_handle *intr_handle) { /* enable MSI-X interrupts */ static int vfio_enable_msix(struct rte_intr_handle *intr_handle) { - int len, ret; - char irq_set_buf[IRQ_SET_BUF_LEN]; + int len, ret, max_intr; + char irq_set_buf[MSIX_IRQ_SET_BUF_LEN]; struct vfio_irq_set *irq_set; int *fd_ptr; @@ -301,12 +294,19 @@ vfio_enable_msix(struct rte_intr_handle *intr_handle) { irq_set = (struct vfio_irq_set *) irq_set_buf; irq_set->argsz = len; - irq_set->count = 1; + if ((!intr_handle->max_intr) || + (intr_handle->max_intr > VFIO_MAX_QUEUE_ID)) + max_intr = VFIO_MAX_QUEUE_ID + 1; + else + max_intr = intr_handle->max_intr; + + irq_set->count = max_intr; irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER; irq_set->index = VFIO_PCI_MSIX_IRQ_INDEX; irq_set->start = 0; fd_ptr = (int *) &irq_set->data; - *fd_ptr = intr_handle->fd; + memcpy(fd_ptr, intr_handle->queue_fd, sizeof(intr_handle->queue_fd)); + fd_ptr[max_intr - 1] = intr_handle->fd; ret = ioctl(intr_handle->vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set); @@ -316,22 +316,6 @@ vfio_enable_msix(struct rte_intr_handle *intr_handle) { return -1; } - /* manually trigger interrupt to enable it */ - memset(irq_set, 0, len); - len = sizeof(struct vfio_irq_set); - irq_set->argsz = len; - irq_set->count = 1; - irq_set->flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER; - irq_set->index = VFIO_PCI_MSIX_IRQ_INDEX; - irq_set->start = 0; - - ret = ioctl(intr_handle->vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set); - - if (ret) { - RTE_LOG(ERR, EAL, "Error triggering MSI-X interrupts for fd %d\n", - intr_handle->fd); - return -1; - } return 0; } @@ -339,7 +323,7 @@ vfio_enable_msix(struct rte_intr_handle *intr_handle) { static int vfio_disable_msix(struct rte_intr_handle *intr_handle) { struct vfio_irq_set *irq_set; - char irq_set_buf[IRQ_SET_BUF_LEN]; + char irq_set_buf[MSIX_IRQ_SET_BUF_LEN]; int len, ret; len = sizeof(struct vfio_irq_set); @@ -860,3 +844,124 @@ rte_eal_intr_init(void) return -ret; } +static void +eal_intr_process_rx_interrupts(struct rte_intr_handle *intr_handle, + struct epoll_event *events, int nfds) +{ + int n, bytes_read; + union rte_intr_read_buffer buf; + + for (n = 0; n < nfds; n++) { + /* set the length to be read for different handle type */ + switch (intr_handle->type) { + case RTE_INTR_HANDLE_UIO: + bytes_read = sizeof(buf.uio_intr_count); + break; + case RTE_INTR_HANDLE_ALARM: + bytes_read = sizeof(buf.timerfd_num); + break; +#ifdef VFIO_PRESENT + case RTE_INTR_HANDLE_VFIO_MSIX: + case RTE_INTR_HANDLE_VFIO_MSI: + case RTE_INTR_HANDLE_VFIO_LEGACY: + bytes_read = sizeof(buf.vfio_intr_count); + break; +#endif + default: + bytes_read = 1; + break; + } + + /** + * read out to clear the ready-to-be-read flag + * for epoll_wait. + */ + bytes_read = read(events[n].data.fd, &buf, bytes_read); + if (bytes_read < 0) + RTE_LOG(ERR, EAL, "Error reading from file " + "descriptor %d: %s\n", events[n].data.fd, + strerror(errno)); + else if (bytes_read == 0) + RTE_LOG(ERR, EAL, "Read nothing from file " + "descriptor %d\n", events[n].data.fd); + } +} + +static void +eal_intr_handle_rx_interrupts(struct rte_intr_handle *intr_handle, + int pfd, unsigned totalfds) +{ + struct epoll_event events[totalfds]; + int nfds = 0; + + do { + nfds = epoll_wait(pfd, events, totalfds, + EAL_INTR_EPOLL_WAIT_FOREVER); + /* epoll_wait fail */ + if (nfds < 0) { + RTE_LOG(ERR, EAL, + "epoll_wait returns with fail\n"); + return; + } + } while (nfds == 0); + + /* epoll_wait has at least one fd ready to read */ + eal_intr_process_rx_interrupts(intr_handle, events, nfds); +} + +int +rte_intr_wait_rx_pkt(struct rte_intr_handle *intr_handle, uint8_t queue_id) +{ + struct epoll_event ev; + unsigned numfds = 0; + + if (!intr_handle || intr_handle->fd < 0 || intr_handle->uio_cfg_fd < 0) + return -1; + if (queue_id >= VFIO_MAX_QUEUE_ID) + return -1; + + /* create epoll fd */ + int pfd = epoll_create(1); + if (pfd < 0) { + RTE_LOG(ERR, EAL, "Cannot create epoll instance\n"); + return -1; + } + + rte_spinlock_lock(&intr_lock); + + ev.events = EPOLLIN | EPOLLPRI; + switch (intr_handle->type) { + case RTE_INTR_HANDLE_UIO: + ev.data.fd = intr_handle->fd; + break; +#ifdef VFIO_PRESENT + case RTE_INTR_HANDLE_VFIO_MSIX: + case RTE_INTR_HANDLE_VFIO_MSI: + case RTE_INTR_HANDLE_VFIO_LEGACY: + ev.data.fd = intr_handle->queue_fd[queue_id]; + break; +#endif + default: + rte_spinlock_unlock(&intr_lock); + close(pfd); + return -1; + } + + if (epoll_ctl(pfd, EPOLL_CTL_ADD, ev.data.fd, &ev) < 0) { + RTE_LOG(ERR, EAL, "Error adding fd %d epoll_ctl, %s\n", + intr_handle->queue_fd[queue_id], strerror(errno)); + } else + numfds++; + + rte_spinlock_unlock(&intr_lock); + /* serve the interrupt */ + eal_intr_handle_rx_interrupts(intr_handle, pfd, numfds); + + /** + * when we return, we need to rebuild the + * list of fds to monitor. + */ + close(pfd); + + return 0; +} diff --git a/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c b/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c index 20e0977..0e5fa76 100644 --- a/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c +++ b/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c @@ -283,11 +283,21 @@ pci_vfio_setup_interrupts(struct rte_pci_device *dev, int vfio_dev_fd) dev->intr_handle.fd = fd; dev->intr_handle.vfio_dev_fd = vfio_dev_fd; - switch (i) { case VFIO_PCI_MSIX_IRQ_INDEX: internal_config.vfio_intr_mode = RTE_INTR_MODE_MSIX; dev->intr_handle.type = RTE_INTR_HANDLE_VFIO_MSIX; + for (i = 0; i < VFIO_MAX_QUEUE_ID; i++) { + fd = eventfd(0, 0); + if (fd < 0) { + RTE_LOG(ERR, EAL, + "cannot setup eventfd," + "error %i (%s)\n", + errno, strerror(errno)); + return -1; + } + dev->intr_handle.queue_fd[i] = fd; + } break; case VFIO_PCI_MSI_IRQ_INDEX: internal_config.vfio_intr_mode = RTE_INTR_MODE_MSI; diff --git a/lib/librte_eal/linuxapp/eal/rte_eal_version.map b/lib/librte_eal/linuxapp/eal/rte_eal_version.map index 5ed6e4d..dd300ea 100644 --- a/lib/librte_eal/linuxapp/eal/rte_eal_version.map +++ b/lib/librte_eal/linuxapp/eal/rte_eal_version.map @@ -57,6 +57,7 @@ DPDK_2.0 { rte_intr_callback_unregister; rte_intr_disable; rte_intr_enable; + rte_intr_wait_rx_pkt; rte_log; rte_log_add_in_history; rte_log_cur_msg_loglevel; -- 1.8.1.4