From patchwork Mon Jan 26 03:20:40 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Huawei Xie X-Patchwork-Id: 2514 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 CDA105A7F; Mon, 26 Jan 2015 04:21:54 +0100 (CET) Received: from mga01.intel.com (mga01.intel.com [192.55.52.88]) by dpdk.org (Postfix) with ESMTP id 54EA15ACD for ; Mon, 26 Jan 2015 04:21:51 +0100 (CET) Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga101.fm.intel.com with ESMTP; 25 Jan 2015 19:21:49 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.09,466,1418112000"; d="scan'208";a="667415838" Received: from shvmail01.sh.intel.com ([10.239.29.42]) by fmsmga002.fm.intel.com with ESMTP; 25 Jan 2015 19:21:48 -0800 Received: from shecgisg003.sh.intel.com (shecgisg003.sh.intel.com [10.239.29.90]) by shvmail01.sh.intel.com with ESMTP id t0Q3Lj67015824; Mon, 26 Jan 2015 11:21:45 +0800 Received: from shecgisg003.sh.intel.com (localhost [127.0.0.1]) by shecgisg003.sh.intel.com (8.13.6/8.13.6/SuSE Linux 0.8) with ESMTP id t0Q3LhZq029081; Mon, 26 Jan 2015 11:21:45 +0800 Received: (from hxie5@localhost) by shecgisg003.sh.intel.com (8.13.6/8.13.6/Submit) id t0Q3Lh9h029077; Mon, 26 Jan 2015 11:21:43 +0800 From: Huawei Xie To: dev@dpdk.org Date: Mon, 26 Jan 2015 11:20:40 +0800 Message-Id: <1422242440-28948-15-git-send-email-huawei.xie@intel.com> X-Mailer: git-send-email 1.7.4.1 In-Reply-To: <1422242440-28948-1-git-send-email-huawei.xie@intel.com> References: <1422242440-28948-1-git-send-email-huawei.xie@intel.com> Subject: [dpdk-dev] [RFC PATCH v2 14/14] vhost user ifr_name support 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: Huawei Xie --- lib/librte_vhost/Makefile | 2 +- lib/librte_vhost/rte_virtio_net.h | 3 +- lib/librte_vhost/vhost-net.h | 3 + lib/librte_vhost/vhost_cuse/eventfd_copy.c | 89 +++++++++++++++++++++++++++ lib/librte_vhost/vhost_cuse/eventfd_copy.h | 40 ++++++++++++ lib/librte_vhost/vhost_cuse/vhost-net-cdev.c | 51 ++------------- lib/librte_vhost/vhost_cuse/virtio-net-cdev.c | 53 ++++++++++++++++ lib/librte_vhost/vhost_cuse/virtio-net-cdev.h | 3 + lib/librte_vhost/vhost_user/vhost-net-user.c | 7 +++ lib/librte_vhost/virtio-net.c | 63 ++++++------------- 10 files changed, 223 insertions(+), 91 deletions(-) create mode 100644 lib/librte_vhost/vhost_cuse/eventfd_copy.c create mode 100644 lib/librte_vhost/vhost_cuse/eventfd_copy.h diff --git a/lib/librte_vhost/Makefile b/lib/librte_vhost/Makefile index b2f14a0..c9017d5 100644 --- a/lib/librte_vhost/Makefile +++ b/lib/librte_vhost/Makefile @@ -37,7 +37,7 @@ LIB = librte_vhost.a CFLAGS += $(WERROR_FLAGS) -I$(SRCDIR) -I vhost_cuse -I vhost_user -O3 -D_FILE_OFFSET_BITS=64 -lfuse LDFLAGS += -lfuse # all source are stored in SRCS-y -#SRCS-$(CONFIG_RTE_LIBRTE_VHOST) := vhost_cuse/vhost-net-cdev.c vhost_cuse/virtio-net-cdev.c virtio-net.c vhost_rxtx.c +#SRCS-$(CONFIG_RTE_LIBRTE_VHOST) := vhost_cuse/vhost-net-cdev.c vhost_cuse/virtio-net-cdev.c vhost_cuse/eventfd_copy.c virtio-net.c vhost_rxtx.c SRCS-$(CONFIG_RTE_LIBRTE_VHOST) := vhost_user/vhost-net-user.c vhost_user/virtio-net-user.c vhost_user/fd_man.c virtio-net.c vhost_rxtx.c # install includes diff --git a/lib/librte_vhost/rte_virtio_net.h b/lib/librte_vhost/rte_virtio_net.h index 46c2072..611a3d4 100644 --- a/lib/librte_vhost/rte_virtio_net.h +++ b/lib/librte_vhost/rte_virtio_net.h @@ -100,7 +100,8 @@ struct virtio_net { uint64_t features; /**< Negotiated feature set. */ uint64_t device_fh; /**< device identifier. */ uint32_t flags; /**< Device flags. Only used to check if device is running on data core. */ - char ifname[IFNAMSIZ]; /**< Name of the tap device. */ +#define IF_NAME_SZ (PATH_MAX > IFNAMSIZ ? PATH_MAX : IFNAMSIZ) + char ifname[IF_NAME_SZ]; /**< Name of the tap device or socket path. */ void *priv; /**< private context */ } __rte_cache_aligned; diff --git a/lib/librte_vhost/vhost-net.h b/lib/librte_vhost/vhost-net.h index 94b359f..d125a05 100644 --- a/lib/librte_vhost/vhost-net.h +++ b/lib/librte_vhost/vhost-net.h @@ -93,6 +93,9 @@ struct vhost_net_device_ops { int (*new_device)(struct vhost_device_ctx); void (*destroy_device)(struct vhost_device_ctx); + void (*set_ifname)(struct vhost_device_ctx, + const char *if_name, unsigned int if_len); + int (*get_features)(struct vhost_device_ctx, uint64_t *); int (*set_features)(struct vhost_device_ctx, uint64_t *); diff --git a/lib/librte_vhost/vhost_cuse/eventfd_copy.c b/lib/librte_vhost/vhost_cuse/eventfd_copy.c new file mode 100644 index 0000000..f2ed04e --- /dev/null +++ b/lib/librte_vhost/vhost_cuse/eventfd_copy.c @@ -0,0 +1,89 @@ +/*- + * BSD LICENSE + * + * Copyright(c) 2010-2014 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include +#include +#include +#include +#include +#include + +#include + +#include "eventfd_link/eventfd_link.h" +#include "eventfd_copy.h" +#include "vhost-net.h" + +static const char eventfd_cdev[] = "/dev/eventfd-link"; + +/* + * This function uses the eventfd_link kernel module to copy an eventfd file + * descriptor provided by QEMU in to our process space. + */ +int +eventfd_copy(int target_fd, int target_pid) +{ + int eventfd_link, ret; + struct eventfd_copy eventfd_copy; + int fd = eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC); + + if (fd == -1) + return -1; + + /* Open the character device to the kernel module. */ + /* TODO: check this earlier rather than fail until VM boots! */ + eventfd_link = open(eventfd_cdev, O_RDWR); + if (eventfd_link < 0) { + RTE_LOG(ERR, VHOST_CONFIG, + "eventfd_link module is not loaded\n"); + close(fd); + return -1; + } + + eventfd_copy.source_fd = fd; + eventfd_copy.target_fd = target_fd; + eventfd_copy.target_pid = target_pid; + /* Call the IOCTL to copy the eventfd. */ + ret = ioctl(eventfd_link, EVENTFD_COPY, &eventfd_copy); + close(eventfd_link); + + if (ret < 0) { + RTE_LOG(ERR, VHOST_CONFIG, + "EVENTFD_COPY ioctl failed\n"); + close(fd); + return -1; + } + + return fd; +} + diff --git a/lib/librte_vhost/vhost_cuse/eventfd_copy.h b/lib/librte_vhost/vhost_cuse/eventfd_copy.h new file mode 100644 index 0000000..5f7307c --- /dev/null +++ b/lib/librte_vhost/vhost_cuse/eventfd_copy.h @@ -0,0 +1,40 @@ +/*- + * BSD LICENSE + * + * Copyright(c) 2010-2014 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ +#ifndef _EVENTFD_H +#define _EVENTFD_H + +int +eventfd_copy(int target_fd, int target_pid); + +#endif + diff --git a/lib/librte_vhost/vhost_cuse/vhost-net-cdev.c b/lib/librte_vhost/vhost_cuse/vhost-net-cdev.c index 2ddd6e0..228da43 100644 --- a/lib/librte_vhost/vhost_cuse/vhost-net-cdev.c +++ b/lib/librte_vhost/vhost_cuse/vhost-net-cdev.c @@ -38,8 +38,6 @@ #include #include #include -#include -#include #include #include @@ -48,7 +46,7 @@ #include "virtio-net-cdev.h" #include "vhost-net.h" -#include "eventfd_link/eventfd_link.h" +#include "eventfd_copy.h" #define FUSE_OPT_DUMMY "\0\0" #define FUSE_OPT_FORE "-f\0\0" @@ -58,7 +56,7 @@ static const uint32_t default_major = 231; static const uint32_t default_minor = 1; static const char cuse_device_name[] = "/dev/cuse"; static const char default_cdev[] = "vhost-net"; -static const char eventfd_cdev[] = "/dev/eventfd-link"; + static struct fuse_session *session; struct vhost_net_device_ops const *ops; @@ -178,47 +176,6 @@ vhost_net_release(fuse_req_t req, struct fuse_file_info *fi) } while (0) /* - * This function uses the eventfd_link kernel module to copy an eventfd file - * descriptor provided by QEMU in to our process space. - */ -static int -eventfd_copy(int target_fd, int target_pid) -{ - int eventfd_link, ret; - struct eventfd_copy eventfd_copy; - int fd = eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC); - - if (fd == -1) - return -1; - - /* Open the character device to the kernel module. */ - /* TODO: check this earlier rather than fail until VM boots! */ - eventfd_link = open(eventfd_cdev, O_RDWR); - if (eventfd_link < 0) { - RTE_LOG(ERR, VHOST_CONFIG, - "eventfd_link module is not loaded\n"); - close(fd); - return -1; - } - - eventfd_copy.source_fd = fd; - eventfd_copy.target_fd = target_fd; - eventfd_copy.target_pid = target_pid; - /* Call the IOCTL to copy the eventfd. */ - ret = ioctl(eventfd_link, EVENTFD_COPY, &eventfd_copy); - close(eventfd_link); - - if (ret < 0) { - RTE_LOG(ERR, VHOST_CONFIG, - "EVENTFD_COPY ioctl failed\n"); - close(fd); - return -1; - } - - return fd; -} - -/* * The IOCTLs are handled using CUSE/FUSE in userspace. Depending on the type * of IOCTL a buffer is requested to read or to write. This request is handled * by FUSE and the buffer is then given to CUSE. @@ -240,7 +197,9 @@ vhost_net_ioctl(fuse_req_t req, int cmd, void *arg, case VHOST_NET_SET_BACKEND: LOG_DEBUG(VHOST_CONFIG, "(%"PRIu64") IOCTL: VHOST_NET_SET_BACKEND\n", ctx.fh); - VHOST_IOCTL_R(struct vhost_vring_file, file, ops->set_backend); + file = *(const struct vhost_vring_file *)in_buf; + result = cuse_set_backend(ctx, &file); + fuse_reply_ioctl(req, result, NULL, 0); break; case VHOST_GET_FEATURES: diff --git a/lib/librte_vhost/vhost_cuse/virtio-net-cdev.c b/lib/librte_vhost/vhost_cuse/virtio-net-cdev.c index 1d2c403..6f7f4da 100644 --- a/lib/librte_vhost/vhost_cuse/virtio-net-cdev.c +++ b/lib/librte_vhost/vhost_cuse/virtio-net-cdev.c @@ -43,6 +43,10 @@ #include #include #include +#include +#include +#include +#include #include #include @@ -51,6 +55,7 @@ #include "vhost-net.h" #include "virtio-net-cdev.h" #include "virtio-net.h" +#include "eventfd_copy.h" /* Line size for reading maps file. */ static const uint32_t BUFSIZE = PATH_MAX; @@ -346,3 +351,51 @@ cuse_set_mem_table(struct vhost_device_ctx ctx, ops->set_mem_table(ctx, ®ions[0], valid_regions); return 0; } + +/* + * Function to get the tap device name from the provided file descriptor and + * save it in the device structure. + */ +static int +get_ifname(struct vhost_device_ctx ctx, struct virtio_net *dev, int tap_fd, int pid) +{ + int fd_tap; + struct ifreq ifr; + uint32_t ifr_size; + int ret; + + fd_tap = eventfd_copy(tap_fd, pid); + if (fd_tap < 0) + return -1; + + ret = ioctl(fd_tap, TUNGETIFF, &ifr); + + if (close(fd_tap) < 0) + RTE_LOG(ERR, VHOST_CONFIG, + "(%"PRIu64") fd close failed\n", + dev->device_fh); + + if (ret >= 0) { + ifr_size = strnlen(ifr.ifr_name, sizeof(ifr.ifr_name)); + ops->set_ifname(ctx, ifr.ifr_name, ifr_size); + } else + RTE_LOG(ERR, VHOST_CONFIG, + "(%"PRIu64") TUNGETIFF ioctl failed\n", + dev->device_fh); + + return 0; +} + +int cuse_set_backend(struct vhost_device_ctx ctx, struct vhost_vring_file *file) +{ + struct virtio_net *dev; + + dev = get_device(ctx); + if (dev == NULL) + return -1; + + if (!(dev->flags & VIRTIO_DEV_RUNNING)) + get_ifname(ctx, dev, file->fd, ctx.pid); + + return ops->set_backend(ctx, file); +} diff --git a/lib/librte_vhost/vhost_cuse/virtio-net-cdev.h b/lib/librte_vhost/vhost_cuse/virtio-net-cdev.h index 5ee81b1..eb6b0ba 100644 --- a/lib/librte_vhost/vhost_cuse/virtio-net-cdev.h +++ b/lib/librte_vhost/vhost_cuse/virtio-net-cdev.h @@ -42,4 +42,7 @@ int cuse_set_mem_table(struct vhost_device_ctx ctx, const struct vhost_memory *mem_regions_addr, uint32_t nregions); +int +cuse_set_backend(struct vhost_device_ctx ctx, struct vhost_vring_file *); + #endif diff --git a/lib/librte_vhost/vhost_user/vhost-net-user.c b/lib/librte_vhost/vhost_user/vhost-net-user.c index 3a45a5e..38fef83 100644 --- a/lib/librte_vhost/vhost_user/vhost-net-user.c +++ b/lib/librte_vhost/vhost_user/vhost-net-user.c @@ -265,6 +265,7 @@ vserver_new_vq_conn(int fd, void *dat) struct connfd_ctx *ctx; int fh; struct vhost_device_ctx vdev_ctx = { 0 }; + unsigned int size; conn_fd = accept(fd, NULL, NULL); RTE_LOG(INFO, VHOST_CONFIG, @@ -284,6 +285,12 @@ vserver_new_vq_conn(int fd, void *dat) close(conn_fd); return; } + + vdev_ctx.fh = fh; + size = strnlen(vserver->path, PATH_MAX); + ops->set_ifname(vdev_ctx, vserver->path, + size); + RTE_LOG(INFO, VHOST_CONFIG, "new device, handle is %d\n", fh); ctx->vserver = vserver; diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_vhost/virtio-net.c index c458ed9..c45bccc 100644 --- a/lib/librte_vhost/virtio-net.c +++ b/lib/librte_vhost/virtio-net.c @@ -40,8 +40,6 @@ #include #include -#include -#include #include #include @@ -354,6 +352,24 @@ destroy_device(struct vhost_device_ctx ctx) } } +static void +set_ifname(struct vhost_device_ctx ctx, + const char *if_name, unsigned int if_len) +{ + struct virtio_net *dev; + unsigned int len; + + dev = get_device(ctx); + if (dev == NULL) + return; + + len = if_len > sizeof(dev->ifname) ? + sizeof(dev->ifname) : if_len; + + strncpy(dev->ifname, if_name, len); +} + + /* * Called from CUSE IOCTL: VHOST_SET_OWNER * This function just returns success at the moment unless @@ -660,46 +676,6 @@ set_vring_kick(struct vhost_device_ctx ctx, struct vhost_vring_file *file) } /* - * Function to get the tap device name from the provided file descriptor and - * save it in the device structure. - */ -static int -get_ifname(struct virtio_net *dev, int tap_fd, int pid) -{ - struct eventfd_copy fd_tap; - struct ifreq ifr; - uint32_t size, ifr_size; - int ret; - - fd_tap.source_fd = eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC); - fd_tap.target_fd = tap_fd; - fd_tap.target_pid = pid; - - if (eventfd_copy(dev, &fd_tap)) - return -1; - - ret = ioctl(fd_tap.source_fd, TUNGETIFF, &ifr); - - if (close(fd_tap.source_fd) < 0) - RTE_LOG(ERR, VHOST_CONFIG, - "(%"PRIu64") fd close failed\n", - dev->device_fh); - - if (ret >= 0) { - ifr_size = strnlen(ifr.ifr_name, sizeof(ifr.ifr_name)); - size = ifr_size > sizeof(dev->ifname) ? - sizeof(dev->ifname) : ifr_size; - - strncpy(dev->ifname, ifr.ifr_name, size); - } else - RTE_LOG(ERR, VHOST_CONFIG, - "(%"PRIu64") TUNGETIFF ioctl failed\n", - dev->device_fh); - - return 0; -} - -/* * Called from CUSE IOCTL: VHOST_NET_SET_BACKEND * To complete device initialisation when the virtio driver is loaded, * we are provided with a valid fd for a tap device (not used by us). @@ -727,7 +703,6 @@ set_backend(struct vhost_device_ctx ctx, struct vhost_vring_file *file) if (!(dev->flags & VIRTIO_DEV_RUNNING)) { if (((int)dev->virtqueue[VIRTIO_TXQ]->backend != VIRTIO_DEV_STOPPED) && ((int)dev->virtqueue[VIRTIO_RXQ]->backend != VIRTIO_DEV_STOPPED)) { - get_ifname(dev, file->fd, ctx.pid); return notify_ops->new_device(dev); } /* Otherwise we remove it. */ @@ -745,6 +720,8 @@ static const struct vhost_net_device_ops vhost_device_ops = { .new_device = new_device, .destroy_device = destroy_device, + .set_ifname = set_ifname, + .get_features = get_features, .set_features = set_features,