From patchwork Tue Jan 20 09:53:58 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Zhou, Danny" X-Patchwork-Id: 2392 Return-Path: X-Original-To: patchwork@dpdk.org Delivered-To: patchwork@dpdk.org Received: from [92.243.14.124] (localhost [IPv6:::1]) by dpdk.org (Postfix) with ESMTP id 211895A99; Tue, 20 Jan 2015 10:54:21 +0100 (CET) Received: from mga02.intel.com (mga02.intel.com [134.134.136.20]) by dpdk.org (Postfix) with ESMTP id DE8EC5A70 for ; Tue, 20 Jan 2015 10:54:18 +0100 (CET) Received: from fmsmga001.fm.intel.com ([10.253.24.23]) by orsmga101.jf.intel.com with ESMTP; 20 Jan 2015 01:54:17 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.09,433,1418112000"; d="scan'208";a="653618708" Received: from shvmail01.sh.intel.com ([10.239.29.42]) by fmsmga001.fm.intel.com with ESMTP; 20 Jan 2015 01:54:17 -0800 Received: from shecgisg004.sh.intel.com (shecgisg004.sh.intel.com [10.239.29.89]) by shvmail01.sh.intel.com with ESMTP id t0K9sF4d000486; Tue, 20 Jan 2015 17:54:15 +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 t0K9sCP4021035; Tue, 20 Jan 2015 17:54:14 +0800 Received: (from dyzhou@localhost) by shecgisg004.sh.intel.com (8.13.6/8.13.6/Submit) id t0K9sBcG021031; Tue, 20 Jan 2015 17:54:11 +0800 From: Danny Zhou To: dev@dpdk.org Date: Tue, 20 Jan 2015 17:53:58 +0800 Message-Id: <1421747640-20978-4-git-send-email-danny.zhou@intel.com> X-Mailer: git-send-email 1.7.4.1 In-Reply-To: <1421747640-20978-1-git-send-email-danny.zhou@intel.com> References: <1421747640-20978-1-git-send-email-danny.zhou@intel.com> Subject: [dpdk-dev] [RFC PATCH 3/5] 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: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Signed-off-by: Danny Zhou --- lib/librte_eal/common/include/rte_eal.h | 9 ++ lib/librte_eal/linuxapp/eal/eal_interrupts.c | 120 ++++++++++++++++++++- lib/librte_eal/linuxapp/eal/eal_pci_vfio.c | 11 +- .../linuxapp/eal/include/exec-env/rte_interrupts.h | 3 + 4 files changed, 137 insertions(+), 6 deletions(-) diff --git a/lib/librte_eal/common/include/rte_eal.h b/lib/librte_eal/common/include/rte_eal.h index f4ecd2e..5f31aa5 100644 --- a/lib/librte_eal/common/include/rte_eal.h +++ b/lib/librte_eal/common/include/rte_eal.h @@ -150,6 +150,15 @@ int rte_eal_iopl_init(void); * - On failure, a negative error value. */ int rte_eal_init(int argc, char **argv); + +/** + * @param port_id + * the port id + * @return + * - On success, return 0 + */ +int rte_eal_wait_rx_intr(uint8_t port_id, uint8_t queue_id); + /** * Usage function typedef used by the application usage function. * diff --git a/lib/librte_eal/linuxapp/eal/eal_interrupts.c b/lib/librte_eal/linuxapp/eal/eal_interrupts.c index dc2668a..1be4ba7 100644 --- a/lib/librte_eal/linuxapp/eal/eal_interrupts.c +++ b/lib/librte_eal/linuxapp/eal/eal_interrupts.c @@ -64,6 +64,7 @@ #include #include #include +#include #include "eal_private.h" #include "eal_vfio.h" @@ -127,6 +128,7 @@ static pthread_t intr_thread; #ifdef VFIO_PRESENT #define IRQ_SET_BUF_LEN (sizeof(struct vfio_irq_set) + sizeof(int)) +#define MSIX_IRQ_SET_BUF_LEN (sizeof(struct vfio_irq_set) + sizeof(int) * (VFIO_MAX_QUEUE_ID + 1)) /* enable legacy (INTx) interrupts */ static int @@ -293,7 +295,7 @@ vfio_disable_msi(struct rte_intr_handle *intr_handle) { static int vfio_enable_msix(struct rte_intr_handle *intr_handle) { int len, ret; - char irq_set_buf[IRQ_SET_BUF_LEN]; + char irq_set_buf[MSIX_IRQ_SET_BUF_LEN]; struct vfio_irq_set *irq_set; int *fd_ptr; @@ -301,12 +303,13 @@ 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; + irq_set->count = VFIO_MAX_QUEUE_ID + 1; 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[VFIO_MAX_QUEUE_ID] = intr_handle->fd; ret = ioctl(intr_handle->vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set); @@ -323,7 +326,7 @@ vfio_enable_msix(struct rte_intr_handle *intr_handle) { 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; + irq_set->start = VFIO_MAX_QUEUE_ID; ret = ioctl(intr_handle->vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set); @@ -332,6 +335,7 @@ vfio_enable_msix(struct rte_intr_handle *intr_handle) { intr_handle->fd); return -1; } + return 0; } @@ -339,7 +343,7 @@ 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); @@ -824,3 +828,109 @@ rte_eal_intr_init(void) return -ret; } +static int +eal_intr_process_rx_interrupts(uint8_t port_id, struct epoll_event *events, int nfds) +{ + int n, bytes_read; + union rte_intr_read_buffer buf; + struct rte_intr_handle intr_handle = rte_eth_devices[port_id].pci_dev->intr_handle; + + for (n = 0; n < nfds; n++) { + /* set the length to be read dor 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); + } + + return 0; +} + +static void +eal_intr_handle_rx_interrupts(uint8_t port_id, int pfd, unsigned totalfds) +{ + struct epoll_event events[totalfds]; + int nfds = 0; + +m_wait: + nfds = epoll_wait(pfd, events, totalfds, + EAL_INTR_EPOLL_WAIT_FOREVER); + /* epoll_wait fail */ + if (nfds < 0) { + if (errno == EINTR) + goto m_wait;/*continue;*/ + RTE_LOG(ERR, EAL, + "epoll_wait returns with fail\n"); + return; + } + /* epoll_wait timeout, will never happens here */ + else if (nfds == 0) + goto m_wait;/*continue;*/ + /* epoll_wait has at least one fd ready to read */ + if (eal_intr_process_rx_interrupts(port_id, events, nfds) < 0) + return; +} + +int +rte_eal_wait_rx_intr(uint8_t port_id, uint8_t queue_id) +{ + struct rte_intr_handle intr_handle = rte_eth_devices[port_id].pci_dev->intr_handle; + struct epoll_event ev; + unsigned numfds = 0; + + /* create epoll fd */ + int pfd = epoll_create(1); + if (pfd < 0) + rte_panic("Cannot create epoll instance\n"); + + rte_spinlock_lock(&intr_lock); + + ev.events = EPOLLIN | EPOLLPRI; + ev.data.fd = intr_handle.queue_fd[queue_id]; + + if (epoll_ctl(pfd, EPOLL_CTL_ADD, + intr_handle.queue_fd[queue_id], &ev) < 0){ + rte_panic("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(port_id, 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..63d0ae8 100644 --- a/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c +++ b/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c @@ -283,7 +283,6 @@ 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; @@ -302,6 +301,16 @@ pci_vfio_setup_interrupts(struct rte_pci_device *dev, int vfio_dev_fd) return -1; } + for (i = 0; i < VFIO_MAX_QUEUE_ID; i++) { + fd = eventfd(0, 0); + if (fd < 0) { + RTE_LOG(ERR, EAL, " cannot set up eventfd, " + "error %i (%s)\n", errno, strerror(errno)); + return -1; + } + dev->intr_handle.queue_fd[i] = fd; + } + 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 23eafd9..83b717c 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 @@ -38,6 +38,8 @@ #ifndef _RTE_LINUXAPP_INTERRUPTS_H_ #define _RTE_LINUXAPP_INTERRUPTS_H_ +#define VFIO_MAX_QUEUE_ID 32 + enum rte_intr_handle_type { RTE_INTR_HANDLE_UNKNOWN = 0, RTE_INTR_HANDLE_UIO, /**< uio device handle */ @@ -52,6 +54,7 @@ enum rte_intr_handle_type { struct rte_intr_handle { int vfio_dev_fd; /**< VFIO device file descriptor */ int fd; /**< file descriptor */ + int queue_fd[VFIO_MAX_QUEUE_ID]; /**< rx and tx queue interrupt file descriptor */ enum rte_intr_handle_type type; /**< handle type */ };