summaryrefslogtreecommitdiffstats
path: root/drivers/net/virtio/virtio_user
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/virtio/virtio_user')
-rw-r--r--drivers/net/virtio/virtio_user/vhost.h146
-rw-r--r--drivers/net/virtio/virtio_user/vhost_user.c426
-rw-r--r--drivers/net/virtio/virtio_user/virtio_user_dev.c333
-rw-r--r--drivers/net/virtio/virtio_user/virtio_user_dev.h62
4 files changed, 967 insertions, 0 deletions
diff --git a/drivers/net/virtio/virtio_user/vhost.h b/drivers/net/virtio/virtio_user/vhost.h
new file mode 100644
index 00000000..7adb55f5
--- /dev/null
+++ b/drivers/net/virtio/virtio_user/vhost.h
@@ -0,0 +1,146 @@
+/*-
+ * BSD LICENSE
+ *
+ * Copyright(c) 2010-2016 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 _VHOST_NET_USER_H
+#define _VHOST_NET_USER_H
+
+#include <stdint.h>
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#include "../virtio_pci.h"
+#include "../virtio_logs.h"
+#include "../virtqueue.h"
+
+#define VHOST_MEMORY_MAX_NREGIONS 8
+
+struct vhost_vring_state {
+ unsigned int index;
+ unsigned int num;
+};
+
+struct vhost_vring_file {
+ unsigned int index;
+ int fd;
+};
+
+struct vhost_vring_addr {
+ unsigned int index;
+ /* Option flags. */
+ unsigned int flags;
+ /* Flag values: */
+ /* Whether log address is valid. If set enables logging. */
+#define VHOST_VRING_F_LOG 0
+
+ /* Start of array of descriptors (virtually contiguous) */
+ uint64_t desc_user_addr;
+ /* Used structure address. Must be 32 bit aligned */
+ uint64_t used_user_addr;
+ /* Available structure address. Must be 16 bit aligned */
+ uint64_t avail_user_addr;
+ /* Logging support. */
+ /* Log writes to used structure, at offset calculated from specified
+ * address. Address must be 32 bit aligned.
+ */
+ uint64_t log_guest_addr;
+};
+
+enum vhost_user_request {
+ VHOST_USER_NONE = 0,
+ VHOST_USER_GET_FEATURES = 1,
+ VHOST_USER_SET_FEATURES = 2,
+ VHOST_USER_SET_OWNER = 3,
+ VHOST_USER_RESET_OWNER = 4,
+ VHOST_USER_SET_MEM_TABLE = 5,
+ VHOST_USER_SET_LOG_BASE = 6,
+ VHOST_USER_SET_LOG_FD = 7,
+ VHOST_USER_SET_VRING_NUM = 8,
+ VHOST_USER_SET_VRING_ADDR = 9,
+ VHOST_USER_SET_VRING_BASE = 10,
+ VHOST_USER_GET_VRING_BASE = 11,
+ VHOST_USER_SET_VRING_KICK = 12,
+ VHOST_USER_SET_VRING_CALL = 13,
+ VHOST_USER_SET_VRING_ERR = 14,
+ VHOST_USER_GET_PROTOCOL_FEATURES = 15,
+ VHOST_USER_SET_PROTOCOL_FEATURES = 16,
+ VHOST_USER_GET_QUEUE_NUM = 17,
+ VHOST_USER_SET_VRING_ENABLE = 18,
+ VHOST_USER_MAX
+};
+
+struct vhost_memory_region {
+ uint64_t guest_phys_addr;
+ uint64_t memory_size; /* bytes */
+ uint64_t userspace_addr;
+ uint64_t mmap_offset;
+};
+
+struct vhost_memory {
+ uint32_t nregions;
+ uint32_t padding;
+ struct vhost_memory_region regions[VHOST_MEMORY_MAX_NREGIONS];
+};
+
+struct vhost_user_msg {
+ enum vhost_user_request request;
+
+#define VHOST_USER_VERSION_MASK 0x3
+#define VHOST_USER_REPLY_MASK (0x1 << 2)
+ uint32_t flags;
+ uint32_t size; /* the following payload size */
+ union {
+#define VHOST_USER_VRING_IDX_MASK 0xff
+#define VHOST_USER_VRING_NOFD_MASK (0x1 << 8)
+ uint64_t u64;
+ struct vhost_vring_state state;
+ struct vhost_vring_addr addr;
+ struct vhost_memory memory;
+ } payload;
+ int fds[VHOST_MEMORY_MAX_NREGIONS];
+} __attribute((packed));
+
+#define VHOST_USER_HDR_SIZE offsetof(struct vhost_user_msg, payload.u64)
+#define VHOST_USER_PAYLOAD_SIZE \
+ (sizeof(struct vhost_user_msg) - VHOST_USER_HDR_SIZE)
+
+/* The version of the protocol we support */
+#define VHOST_USER_VERSION 0x1
+
+#define VHOST_USER_F_PROTOCOL_FEATURES 30
+#define VHOST_USER_MQ (1ULL << VHOST_USER_F_PROTOCOL_FEATURES)
+
+int vhost_user_sock(int vhostfd, enum vhost_user_request req, void *arg);
+int vhost_user_setup(const char *path);
+int vhost_user_enable_queue_pair(int vhostfd, uint16_t pair_idx, int enable);
+
+#endif
diff --git a/drivers/net/virtio/virtio_user/vhost_user.c b/drivers/net/virtio/virtio_user/vhost_user.c
new file mode 100644
index 00000000..a2b0687f
--- /dev/null
+++ b/drivers/net/virtio/virtio_user/vhost_user.c
@@ -0,0 +1,426 @@
+/*-
+ * BSD LICENSE
+ *
+ * Copyright(c) 2010-2016 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 <sys/socket.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/un.h>
+#include <string.h>
+#include <errno.h>
+
+#include "vhost.h"
+
+static int
+vhost_user_write(int fd, void *buf, int len, int *fds, int fd_num)
+{
+ int r;
+ struct msghdr msgh;
+ struct iovec iov;
+ size_t fd_size = fd_num * sizeof(int);
+ char control[CMSG_SPACE(fd_size)];
+ struct cmsghdr *cmsg;
+
+ memset(&msgh, 0, sizeof(msgh));
+ memset(control, 0, sizeof(control));
+
+ iov.iov_base = (uint8_t *)buf;
+ iov.iov_len = len;
+
+ msgh.msg_iov = &iov;
+ msgh.msg_iovlen = 1;
+ msgh.msg_control = control;
+ msgh.msg_controllen = sizeof(control);
+
+ cmsg = CMSG_FIRSTHDR(&msgh);
+ cmsg->cmsg_len = CMSG_LEN(fd_size);
+ cmsg->cmsg_level = SOL_SOCKET;
+ cmsg->cmsg_type = SCM_RIGHTS;
+ memcpy(CMSG_DATA(cmsg), fds, fd_size);
+
+ do {
+ r = sendmsg(fd, &msgh, 0);
+ } while (r < 0 && errno == EINTR);
+
+ return r;
+}
+
+static int
+vhost_user_read(int fd, struct vhost_user_msg *msg)
+{
+ uint32_t valid_flags = VHOST_USER_REPLY_MASK | VHOST_USER_VERSION;
+ int ret, sz_hdr = VHOST_USER_HDR_SIZE, sz_payload;
+
+ ret = recv(fd, (void *)msg, sz_hdr, 0);
+ if (ret < sz_hdr) {
+ PMD_DRV_LOG(ERR, "Failed to recv msg hdr: %d instead of %d.",
+ ret, sz_hdr);
+ goto fail;
+ }
+
+ /* validate msg flags */
+ if (msg->flags != (valid_flags)) {
+ PMD_DRV_LOG(ERR, "Failed to recv msg: flags %x instead of %x.",
+ msg->flags, valid_flags);
+ goto fail;
+ }
+
+ sz_payload = msg->size;
+ if (sz_payload) {
+ ret = recv(fd, (void *)((char *)msg + sz_hdr), sz_payload, 0);
+ if (ret < sz_payload) {
+ PMD_DRV_LOG(ERR,
+ "Failed to recv msg payload: %d instead of %d.",
+ ret, msg->size);
+ goto fail;
+ }
+ }
+
+ return 0;
+
+fail:
+ return -1;
+}
+
+struct hugepage_file_info {
+ uint64_t addr; /**< virtual addr */
+ size_t size; /**< the file size */
+ char path[PATH_MAX]; /**< path to backing file */
+};
+
+/* Two possible options:
+ * 1. Match HUGEPAGE_INFO_FMT to find the file storing struct hugepage_file
+ * array. This is simple but cannot be used in secondary process because
+ * secondary process will close and munmap that file.
+ * 2. Match HUGEFILE_FMT to find hugepage files directly.
+ *
+ * We choose option 2.
+ */
+static int
+get_hugepage_file_info(struct hugepage_file_info huges[], int max)
+{
+ int idx;
+ FILE *f;
+ char buf[BUFSIZ], *tmp, *tail;
+ char *str_underline, *str_start;
+ int huge_index;
+ uint64_t v_start, v_end;
+
+ f = fopen("/proc/self/maps", "r");
+ if (!f) {
+ PMD_DRV_LOG(ERR, "cannot open /proc/self/maps");
+ return -1;
+ }
+
+ idx = 0;
+ while (fgets(buf, sizeof(buf), f) != NULL) {
+ if (sscanf(buf, "%" PRIx64 "-%" PRIx64, &v_start, &v_end) < 2) {
+ PMD_DRV_LOG(ERR, "Failed to parse address");
+ goto error;
+ }
+
+ tmp = strchr(buf, ' ') + 1; /** skip address */
+ tmp = strchr(tmp, ' ') + 1; /** skip perm */
+ tmp = strchr(tmp, ' ') + 1; /** skip offset */
+ tmp = strchr(tmp, ' ') + 1; /** skip dev */
+ tmp = strchr(tmp, ' ') + 1; /** skip inode */
+ while (*tmp == ' ') /** skip spaces */
+ tmp++;
+ tail = strrchr(tmp, '\n'); /** remove newline if exists */
+ if (tail)
+ *tail = '\0';
+
+ /* Match HUGEFILE_FMT, aka "%s/%smap_%d",
+ * which is defined in eal_filesystem.h
+ */
+ str_underline = strrchr(tmp, '_');
+ if (!str_underline)
+ continue;
+
+ str_start = str_underline - strlen("map");
+ if (str_start < tmp)
+ continue;
+
+ if (sscanf(str_start, "map_%d", &huge_index) != 1)
+ continue;
+
+ if (idx >= max) {
+ PMD_DRV_LOG(ERR, "Exceed maximum of %d", max);
+ goto error;
+ }
+ huges[idx].addr = v_start;
+ huges[idx].size = v_end - v_start;
+ strcpy(huges[idx].path, tmp);
+ idx++;
+ }
+
+ fclose(f);
+ return idx;
+
+error:
+ fclose(f);
+ return -1;
+}
+
+static int
+prepare_vhost_memory_user(struct vhost_user_msg *msg, int fds[])
+{
+ int i, num;
+ struct hugepage_file_info huges[VHOST_MEMORY_MAX_NREGIONS];
+ struct vhost_memory_region *mr;
+
+ num = get_hugepage_file_info(huges, VHOST_MEMORY_MAX_NREGIONS);
+ if (num < 0) {
+ PMD_INIT_LOG(ERR, "Failed to prepare memory for vhost-user");
+ return -1;
+ }
+
+ for (i = 0; i < num; ++i) {
+ mr = &msg->payload.memory.regions[i];
+ mr->guest_phys_addr = huges[i].addr; /* use vaddr! */
+ mr->userspace_addr = huges[i].addr;
+ mr->memory_size = huges[i].size;
+ mr->mmap_offset = 0;
+ fds[i] = open(huges[i].path, O_RDWR);
+ }
+
+ msg->payload.memory.nregions = num;
+ msg->payload.memory.padding = 0;
+
+ return 0;
+}
+
+static struct vhost_user_msg m;
+
+static const char * const vhost_msg_strings[] = {
+ [VHOST_USER_SET_OWNER] = "VHOST_USER_SET_OWNER",
+ [VHOST_USER_RESET_OWNER] = "VHOST_USER_RESET_OWNER",
+ [VHOST_USER_SET_FEATURES] = "VHOST_USER_SET_FEATURES",
+ [VHOST_USER_GET_FEATURES] = "VHOST_USER_GET_FEATURES",
+ [VHOST_USER_SET_VRING_CALL] = "VHOST_USER_SET_VRING_CALL",
+ [VHOST_USER_SET_VRING_NUM] = "VHOST_USER_SET_VRING_NUM",
+ [VHOST_USER_SET_VRING_BASE] = "VHOST_USER_SET_VRING_BASE",
+ [VHOST_USER_GET_VRING_BASE] = "VHOST_USER_GET_VRING_BASE",
+ [VHOST_USER_SET_VRING_ADDR] = "VHOST_USER_SET_VRING_ADDR",
+ [VHOST_USER_SET_VRING_KICK] = "VHOST_USER_SET_VRING_KICK",
+ [VHOST_USER_SET_MEM_TABLE] = "VHOST_USER_SET_MEM_TABLE",
+ [VHOST_USER_SET_VRING_ENABLE] = "VHOST_USER_SET_VRING_ENABLE",
+ NULL,
+};
+
+int
+vhost_user_sock(int vhostfd, enum vhost_user_request req, void *arg)
+{
+ struct vhost_user_msg msg;
+ struct vhost_vring_file *file = 0;
+ int need_reply = 0;
+ int fds[VHOST_MEMORY_MAX_NREGIONS];
+ int fd_num = 0;
+ int i, len;
+
+ RTE_SET_USED(m);
+ RTE_SET_USED(vhost_msg_strings);
+
+ PMD_DRV_LOG(INFO, "%s", vhost_msg_strings[req]);
+
+ msg.request = req;
+ msg.flags = VHOST_USER_VERSION;
+ msg.size = 0;
+
+ switch (req) {
+ case VHOST_USER_GET_FEATURES:
+ need_reply = 1;
+ break;
+
+ case VHOST_USER_SET_FEATURES:
+ case VHOST_USER_SET_LOG_BASE:
+ msg.payload.u64 = *((__u64 *)arg);
+ msg.size = sizeof(m.payload.u64);
+ break;
+
+ case VHOST_USER_SET_OWNER:
+ case VHOST_USER_RESET_OWNER:
+ break;
+
+ case VHOST_USER_SET_MEM_TABLE:
+ if (prepare_vhost_memory_user(&msg, fds) < 0)
+ return -1;
+ fd_num = msg.payload.memory.nregions;
+ msg.size = sizeof(m.payload.memory.nregions);
+ msg.size += sizeof(m.payload.memory.padding);
+ msg.size += fd_num * sizeof(struct vhost_memory_region);
+ break;
+
+ case VHOST_USER_SET_LOG_FD:
+ fds[fd_num++] = *((int *)arg);
+ break;
+
+ case VHOST_USER_SET_VRING_NUM:
+ case VHOST_USER_SET_VRING_BASE:
+ case VHOST_USER_SET_VRING_ENABLE:
+ memcpy(&msg.payload.state, arg, sizeof(msg.payload.state));
+ msg.size = sizeof(m.payload.state);
+ break;
+
+ case VHOST_USER_GET_VRING_BASE:
+ memcpy(&msg.payload.state, arg, sizeof(msg.payload.state));
+ msg.size = sizeof(m.payload.state);
+ need_reply = 1;
+ break;
+
+ case VHOST_USER_SET_VRING_ADDR:
+ memcpy(&msg.payload.addr, arg, sizeof(msg.payload.addr));
+ msg.size = sizeof(m.payload.addr);
+ break;
+
+ case VHOST_USER_SET_VRING_KICK:
+ case VHOST_USER_SET_VRING_CALL:
+ case VHOST_USER_SET_VRING_ERR:
+ file = arg;
+ msg.payload.u64 = file->index & VHOST_USER_VRING_IDX_MASK;
+ msg.size = sizeof(m.payload.u64);
+ if (file->fd > 0)
+ fds[fd_num++] = file->fd;
+ else
+ msg.payload.u64 |= VHOST_USER_VRING_NOFD_MASK;
+ break;
+
+ default:
+ PMD_DRV_LOG(ERR, "trying to send unhandled msg type");
+ return -1;
+ }
+
+ len = VHOST_USER_HDR_SIZE + msg.size;
+ if (vhost_user_write(vhostfd, &msg, len, fds, fd_num) < 0) {
+ PMD_DRV_LOG(ERR, "%s failed: %s",
+ vhost_msg_strings[req], strerror(errno));
+ return -1;
+ }
+
+ if (req == VHOST_USER_SET_MEM_TABLE)
+ for (i = 0; i < fd_num; ++i)
+ close(fds[i]);
+
+ if (need_reply) {
+ if (vhost_user_read(vhostfd, &msg) < 0) {
+ PMD_DRV_LOG(ERR, "Received msg failed: %s",
+ strerror(errno));
+ return -1;
+ }
+
+ if (req != msg.request) {
+ PMD_DRV_LOG(ERR, "Received unexpected msg type");
+ return -1;
+ }
+
+ switch (req) {
+ case VHOST_USER_GET_FEATURES:
+ if (msg.size != sizeof(m.payload.u64)) {
+ PMD_DRV_LOG(ERR, "Received bad msg size");
+ return -1;
+ }
+ *((__u64 *)arg) = msg.payload.u64;
+ break;
+ case VHOST_USER_GET_VRING_BASE:
+ if (msg.size != sizeof(m.payload.state)) {
+ PMD_DRV_LOG(ERR, "Received bad msg size");
+ return -1;
+ }
+ memcpy(arg, &msg.payload.state,
+ sizeof(struct vhost_vring_state));
+ break;
+ default:
+ PMD_DRV_LOG(ERR, "Received unexpected msg type");
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * Set up environment to talk with a vhost user backend.
+ * @param path
+ * - The path to vhost user unix socket file.
+ *
+ * @return
+ * - (-1) if fail to set up;
+ * - (>=0) if successful, and it is the fd to vhostfd.
+ */
+int
+vhost_user_setup(const char *path)
+{
+ int fd;
+ int flag;
+ struct sockaddr_un un;
+
+ fd = socket(AF_UNIX, SOCK_STREAM, 0);
+ if (fd < 0) {
+ PMD_DRV_LOG(ERR, "socket() error, %s", strerror(errno));
+ return -1;
+ }
+
+ flag = fcntl(fd, F_GETFD);
+ fcntl(fd, F_SETFD, flag | FD_CLOEXEC);
+
+ memset(&un, 0, sizeof(un));
+ un.sun_family = AF_UNIX;
+ snprintf(un.sun_path, sizeof(un.sun_path), "%s", path);
+ if (connect(fd, (struct sockaddr *)&un, sizeof(un)) < 0) {
+ PMD_DRV_LOG(ERR, "connect error, %s", strerror(errno));
+ close(fd);
+ return -1;
+ }
+
+ return fd;
+}
+
+int
+vhost_user_enable_queue_pair(int vhostfd, uint16_t pair_idx, int enable)
+{
+ int i;
+
+ for (i = 0; i < 2; ++i) {
+ struct vhost_vring_state state = {
+ .index = pair_idx * 2 + i,
+ .num = enable,
+ };
+
+ if (vhost_user_sock(vhostfd,
+ VHOST_USER_SET_VRING_ENABLE, &state))
+ return -1;
+ }
+
+ return 0;
+}
diff --git a/drivers/net/virtio/virtio_user/virtio_user_dev.c b/drivers/net/virtio/virtio_user/virtio_user_dev.c
new file mode 100644
index 00000000..3d12a320
--- /dev/null
+++ b/drivers/net/virtio/virtio_user/virtio_user_dev.c
@@ -0,0 +1,333 @@
+/*-
+ * BSD LICENSE
+ *
+ * Copyright(c) 2010-2016 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 <stdint.h>
+#include <stdio.h>
+#include <fcntl.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/mman.h>
+#include <unistd.h>
+#include <sys/eventfd.h>
+
+#include "vhost.h"
+#include "virtio_user_dev.h"
+#include "../virtio_ethdev.h"
+
+static int
+virtio_user_kick_queue(struct virtio_user_dev *dev, uint32_t queue_sel)
+{
+ int callfd, kickfd;
+ struct vhost_vring_file file;
+ struct vhost_vring_state state;
+ struct vring *vring = &dev->vrings[queue_sel];
+ struct vhost_vring_addr addr = {
+ .index = queue_sel,
+ .desc_user_addr = (uint64_t)(uintptr_t)vring->desc,
+ .avail_user_addr = (uint64_t)(uintptr_t)vring->avail,
+ .used_user_addr = (uint64_t)(uintptr_t)vring->used,
+ .log_guest_addr = 0,
+ .flags = 0, /* disable log */
+ };
+
+ /* May use invalid flag, but some backend leverages kickfd and callfd as
+ * criteria to judge if dev is alive. so finally we use real event_fd.
+ */
+ callfd = eventfd(0, O_CLOEXEC | O_NONBLOCK);
+ if (callfd < 0) {
+ PMD_DRV_LOG(ERR, "callfd error, %s\n", strerror(errno));
+ return -1;
+ }
+ kickfd = eventfd(0, O_CLOEXEC | O_NONBLOCK);
+ if (kickfd < 0) {
+ close(callfd);
+ PMD_DRV_LOG(ERR, "kickfd error, %s\n", strerror(errno));
+ return -1;
+ }
+
+ /* Of all per virtqueue MSGs, make sure VHOST_SET_VRING_CALL come
+ * firstly because vhost depends on this msg to allocate virtqueue
+ * pair.
+ */
+ file.index = queue_sel;
+ file.fd = callfd;
+ vhost_user_sock(dev->vhostfd, VHOST_USER_SET_VRING_CALL, &file);
+ dev->callfds[queue_sel] = callfd;
+
+ state.index = queue_sel;
+ state.num = vring->num;
+ vhost_user_sock(dev->vhostfd, VHOST_USER_SET_VRING_NUM, &state);
+
+ state.num = 0; /* no reservation */
+ vhost_user_sock(dev->vhostfd, VHOST_USER_SET_VRING_BASE, &state);
+
+ vhost_user_sock(dev->vhostfd, VHOST_USER_SET_VRING_ADDR, &addr);
+
+ /* Of all per virtqueue MSGs, make sure VHOST_USER_SET_VRING_KICK comes
+ * lastly because vhost depends on this msg to judge if
+ * virtio is ready.
+ */
+ file.fd = kickfd;
+ vhost_user_sock(dev->vhostfd, VHOST_USER_SET_VRING_KICK, &file);
+ dev->kickfds[queue_sel] = kickfd;
+
+ return 0;
+}
+
+int
+virtio_user_start_device(struct virtio_user_dev *dev)
+{
+ uint64_t features;
+ uint32_t i, queue_sel;
+ int ret;
+
+ /* construct memory region inside each implementation */
+ ret = vhost_user_sock(dev->vhostfd, VHOST_USER_SET_MEM_TABLE, NULL);
+ if (ret < 0)
+ goto error;
+
+ for (i = 0; i < dev->max_queue_pairs; ++i) {
+ queue_sel = 2 * i + VTNET_SQ_RQ_QUEUE_IDX;
+ if (virtio_user_kick_queue(dev, queue_sel) < 0) {
+ PMD_DRV_LOG(INFO, "kick rx vq fails: %u", i);
+ goto error;
+ }
+ }
+ for (i = 0; i < dev->max_queue_pairs; ++i) {
+ queue_sel = 2 * i + VTNET_SQ_TQ_QUEUE_IDX;
+ if (virtio_user_kick_queue(dev, queue_sel) < 0) {
+ PMD_DRV_LOG(INFO, "kick tx vq fails: %u", i);
+ goto error;
+ }
+ }
+
+ /* After setup all virtqueues, we need to set_features so that these
+ * features can be set into each virtqueue in vhost side. And before
+ * that, make sure VHOST_USER_F_PROTOCOL_FEATURES is added if mq is
+ * enabled, and VIRTIO_NET_F_MAC is stripped.
+ */
+ features = dev->features;
+ if (dev->max_queue_pairs > 1)
+ features |= VHOST_USER_MQ;
+ features &= ~(1ull << VIRTIO_NET_F_MAC);
+ ret = vhost_user_sock(dev->vhostfd, VHOST_USER_SET_FEATURES, &features);
+ if (ret < 0)
+ goto error;
+ PMD_DRV_LOG(INFO, "set features: %" PRIx64, features);
+
+ return 0;
+error:
+ /* TODO: free resource here or caller to check */
+ return -1;
+}
+
+int virtio_user_stop_device(struct virtio_user_dev *dev)
+{
+ return vhost_user_sock(dev->vhostfd, VHOST_USER_RESET_OWNER, NULL);
+}
+
+static inline void
+parse_mac(struct virtio_user_dev *dev, const char *mac)
+{
+ int i, r;
+ uint32_t tmp[ETHER_ADDR_LEN];
+
+ if (!mac)
+ return;
+
+ r = sscanf(mac, "%x:%x:%x:%x:%x:%x", &tmp[0],
+ &tmp[1], &tmp[2], &tmp[3], &tmp[4], &tmp[5]);
+ if (r == ETHER_ADDR_LEN) {
+ for (i = 0; i < ETHER_ADDR_LEN; ++i)
+ dev->mac_addr[i] = (uint8_t)tmp[i];
+ dev->mac_specified = 1;
+ } else {
+ /* ignore the wrong mac, use random mac */
+ PMD_DRV_LOG(ERR, "wrong format of mac: %s", mac);
+ }
+}
+
+int
+virtio_user_dev_init(struct virtio_user_dev *dev, char *path, int queues,
+ int cq, int queue_size, const char *mac)
+{
+ strncpy(dev->path, path, PATH_MAX);
+ dev->max_queue_pairs = queues;
+ dev->queue_pairs = 1; /* mq disabled by default */
+ dev->queue_size = queue_size;
+ dev->mac_specified = 0;
+ parse_mac(dev, mac);
+ dev->vhostfd = -1;
+
+ dev->vhostfd = vhost_user_setup(dev->path);
+ if (dev->vhostfd < 0) {
+ PMD_INIT_LOG(ERR, "backend set up fails");
+ return -1;
+ }
+ if (vhost_user_sock(dev->vhostfd, VHOST_USER_SET_OWNER, NULL) < 0) {
+ PMD_INIT_LOG(ERR, "set_owner fails: %s", strerror(errno));
+ return -1;
+ }
+
+ if (vhost_user_sock(dev->vhostfd, VHOST_USER_GET_FEATURES,
+ &dev->features) < 0) {
+ PMD_INIT_LOG(ERR, "get_features failed: %s", strerror(errno));
+ return -1;
+ }
+ if (dev->mac_specified)
+ dev->features |= (1ull << VIRTIO_NET_F_MAC);
+
+ if (!cq) {
+ dev->features &= ~(1ull << VIRTIO_NET_F_CTRL_VQ);
+ /* Also disable features depends on VIRTIO_NET_F_CTRL_VQ */
+ dev->features &= ~(1ull << VIRTIO_NET_F_CTRL_RX);
+ dev->features &= ~(1ull << VIRTIO_NET_F_CTRL_VLAN);
+ dev->features &= ~(1ull << VIRTIO_NET_F_GUEST_ANNOUNCE);
+ dev->features &= ~(1ull << VIRTIO_NET_F_MQ);
+ dev->features &= ~(1ull << VIRTIO_NET_F_CTRL_MAC_ADDR);
+ } else {
+ /* vhost user backend does not need to know ctrl-q, so
+ * actually we need add this bit into features. However,
+ * DPDK vhost-user does send features with this bit, so we
+ * check it instead of OR it for now.
+ */
+ if (!(dev->features & (1ull << VIRTIO_NET_F_CTRL_VQ)))
+ PMD_INIT_LOG(INFO, "vhost does not support ctrl-q");
+ }
+
+ if (dev->max_queue_pairs > 1) {
+ if (!(dev->features & VHOST_USER_MQ)) {
+ PMD_INIT_LOG(ERR, "MQ not supported by the backend");
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+void
+virtio_user_dev_uninit(struct virtio_user_dev *dev)
+{
+ uint32_t i;
+
+ for (i = 0; i < dev->max_queue_pairs * 2; ++i) {
+ close(dev->callfds[i]);
+ close(dev->kickfds[i]);
+ }
+
+ close(dev->vhostfd);
+}
+
+static uint8_t
+virtio_user_handle_mq(struct virtio_user_dev *dev, uint16_t q_pairs)
+{
+ uint16_t i;
+ uint8_t ret = 0;
+
+ if (q_pairs > dev->max_queue_pairs) {
+ PMD_INIT_LOG(ERR, "multi-q config %u, but only %u supported",
+ q_pairs, dev->max_queue_pairs);
+ return -1;
+ }
+
+ for (i = 0; i < q_pairs; ++i)
+ ret |= vhost_user_enable_queue_pair(dev->vhostfd, i, 1);
+ for (i = q_pairs; i < dev->max_queue_pairs; ++i)
+ ret |= vhost_user_enable_queue_pair(dev->vhostfd, i, 0);
+
+ dev->queue_pairs = q_pairs;
+
+ return ret;
+}
+
+static uint32_t
+virtio_user_handle_ctrl_msg(struct virtio_user_dev *dev, struct vring *vring,
+ uint16_t idx_hdr)
+{
+ struct virtio_net_ctrl_hdr *hdr;
+ virtio_net_ctrl_ack status = ~0;
+ uint16_t i, idx_data, idx_status;
+ uint32_t n_descs = 0;
+
+ /* locate desc for header, data, and status */
+ idx_data = vring->desc[idx_hdr].next;
+ n_descs++;
+
+ i = idx_data;
+ while (vring->desc[i].flags == VRING_DESC_F_NEXT) {
+ i = vring->desc[i].next;
+ n_descs++;
+ }
+
+ /* locate desc for status */
+ idx_status = i;
+ n_descs++;
+
+ hdr = (void *)(uintptr_t)vring->desc[idx_hdr].addr;
+ if (hdr->class == VIRTIO_NET_CTRL_MQ &&
+ hdr->cmd == VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET) {
+ uint16_t queues;
+
+ queues = *(uint16_t *)(uintptr_t)vring->desc[idx_data].addr;
+ status = virtio_user_handle_mq(dev, queues);
+ }
+
+ /* Update status */
+ *(virtio_net_ctrl_ack *)(uintptr_t)vring->desc[idx_status].addr = status;
+
+ return n_descs;
+}
+
+void
+virtio_user_handle_cq(struct virtio_user_dev *dev, uint16_t queue_idx)
+{
+ uint16_t avail_idx, desc_idx;
+ struct vring_used_elem *uep;
+ uint32_t n_descs;
+ struct vring *vring = &dev->vrings[queue_idx];
+
+ /* Consume avail ring, using used ring idx as first one */
+ while (vring->used->idx != vring->avail->idx) {
+ avail_idx = (vring->used->idx) & (vring->num - 1);
+ desc_idx = vring->avail->ring[avail_idx];
+
+ n_descs = virtio_user_handle_ctrl_msg(dev, vring, desc_idx);
+
+ /* Update used ring */
+ uep = &vring->used->ring[avail_idx];
+ uep->id = avail_idx;
+ uep->len = n_descs;
+
+ vring->used->idx++;
+ }
+}
diff --git a/drivers/net/virtio/virtio_user/virtio_user_dev.h b/drivers/net/virtio/virtio_user/virtio_user_dev.h
new file mode 100644
index 00000000..33690b5c
--- /dev/null
+++ b/drivers/net/virtio/virtio_user/virtio_user_dev.h
@@ -0,0 +1,62 @@
+/*-
+ * BSD LICENSE
+ *
+ * Copyright(c) 2010-2016 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 _VIRTIO_USER_DEV_H
+#define _VIRTIO_USER_DEV_H
+
+#include <limits.h>
+#include "../virtio_pci.h"
+#include "../virtio_ring.h"
+
+struct virtio_user_dev {
+ int vhostfd;
+ int callfds[VIRTIO_MAX_VIRTQUEUES * 2 + 1];
+ int kickfds[VIRTIO_MAX_VIRTQUEUES * 2 + 1];
+ int mac_specified;
+ uint32_t max_queue_pairs;
+ uint32_t queue_pairs;
+ uint32_t queue_size;
+ uint64_t features;
+ uint8_t status;
+ uint8_t mac_addr[ETHER_ADDR_LEN];
+ char path[PATH_MAX];
+ struct vring vrings[VIRTIO_MAX_VIRTQUEUES * 2 + 1];
+};
+
+int virtio_user_start_device(struct virtio_user_dev *dev);
+int virtio_user_stop_device(struct virtio_user_dev *dev);
+int virtio_user_dev_init(struct virtio_user_dev *dev, char *path, int queues,
+ int cq, int queue_size, const char *mac);
+void virtio_user_dev_uninit(struct virtio_user_dev *dev);
+void virtio_user_handle_cq(struct virtio_user_dev *dev, uint16_t queue_idx);
+#endif