From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp.tuxdriver.com (charlotte.tuxdriver.com [70.61.120.58]) by dpdk.org (Postfix) with ESMTP id EA90BB64B for ; Tue, 17 Feb 2015 16:59:03 +0100 (CET) Received: from [67.210.173.2] (helo=localhost) by smtp.tuxdriver.com with esmtpsa (TLSv1:AES128-SHA:128) (Exim 4.63) (envelope-from ) id 1YNkY6-0003oZ-LN; Tue, 17 Feb 2015 10:59:02 -0500 Date: Tue, 17 Feb 2015 10:58:52 -0500 From: Neil Horman To: Zhou Danny Message-ID: <20150217155852.GD6309@neilslaptop.think-freely.org> References: <1424180839-24483-1-git-send-email-danny.zhou@intel.com> <1424180839-24483-5-git-send-email-danny.zhou@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1424180839-24483-5-git-send-email-danny.zhou@intel.com> User-Agent: Mutt/1.5.23 (2014-03-12) X-Spam-Score: -2.9 (--) X-Spam-Status: No Cc: dev@dpdk.org Subject: Re: [dpdk-dev] [PATCH v3 4/5] 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: , X-List-Received-Date: Tue, 17 Feb 2015 15:59:04 -0000 On Tue, Feb 17, 2015 at 09:47:18PM +0800, Zhou Danny wrote: > 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/common/include/rte_eal.h | 12 ++ > lib/librte_eal/linuxapp/eal/Makefile | 1 + > lib/librte_eal/linuxapp/eal/eal_interrupts.c | 190 ++++++++++++++++----- > lib/librte_eal/linuxapp/eal/eal_pci_vfio.c | 12 +- > .../linuxapp/eal/include/exec-env/rte_interrupts.h | 4 + > 5 files changed, 175 insertions(+), 44 deletions(-) > > diff --git a/lib/librte_eal/common/include/rte_eal.h b/lib/librte_eal/common/include/rte_eal.h > index f4ecd2e..d81331f 100644 > --- a/lib/librte_eal/common/include/rte_eal.h > +++ b/lib/librte_eal/common/include/rte_eal.h > @@ -150,6 +150,18 @@ 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 > + * @param queue_id > + * the queue id > + * @return > + * - On success, return 0 > + * - On failure, returns -1. > + */ > +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/Makefile b/lib/librte_eal/linuxapp/eal/Makefile > index e117cec..c593dfa 100644 > --- a/lib/librte_eal/linuxapp/eal/Makefile > +++ b/lib/librte_eal/linuxapp/eal/Makefile > @@ -43,6 +43,7 @@ CFLAGS += -I$(SRCDIR)/include > CFLAGS += -I$(RTE_SDK)/lib/librte_eal/common > CFLAGS += -I$(RTE_SDK)/lib/librte_eal/common/include > CFLAGS += -I$(RTE_SDK)/lib/librte_ring > +CFLAGS += -I$(RTE_SDK)/lib/librte_mbuf > CFLAGS += -I$(RTE_SDK)/lib/librte_mempool > CFLAGS += -I$(RTE_SDK)/lib/librte_malloc > CFLAGS += -I$(RTE_SDK)/lib/librte_ether > diff --git a/lib/librte_eal/linuxapp/eal/eal_interrupts.c b/lib/librte_eal/linuxapp/eal/eal_interrupts.c > index dc2668a..97215ad 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 +128,9 @@ 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 +222,10 @@ 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 +234,19 @@ 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 +255,10 @@ 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 +286,8 @@ 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 +295,19 @@ 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 +317,6 @@ 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 +324,7 @@ 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 +809,122 @@ rte_eal_intr_init(void) > return -ret; > } > > +static void > +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 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(uint8_t port_id, 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(port_id, events, nfds); > +} > + > +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_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(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..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/include/exec-env/rte_interrupts.h b/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h > index 23eafd9..c6982cf 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 +54,8 @@ enum rte_intr_handle_type { > struct rte_intr_handle { > int vfio_dev_fd; /**< VFIO device file descriptor */ > int fd; /**< file descriptor */ > + int max_intr; /**< max interrupt requested */ > + int queue_fd[VFIO_MAX_QUEUE_ID]; /**< rx and tx queue interrupt file descriptor */ This is used outside of this library, you need to move these new fields to the end of the structure. neil > enum rte_intr_handle_type type; /**< handle type */ > }; > > -- > 1.8.1.4 > >