diff options
Diffstat (limited to 'hw/virtio/vhost-user.c')
| -rw-r--r-- | hw/virtio/vhost-user.c | 581 |
1 files changed, 378 insertions, 203 deletions
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index b11c0d21a0..78442ba980 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -10,11 +10,13 @@ #include "hw/virtio/vhost.h" #include "hw/virtio/vhost-backend.h" +#include "hw/virtio/virtio-net.h" #include "sysemu/char.h" #include "sysemu/kvm.h" #include "qemu/error-report.h" #include "qemu/sockets.h" #include "exec/ram_addr.h" +#include "migration/migration.h" #include <fcntl.h> #include <unistd.h> @@ -25,9 +27,16 @@ #define VHOST_MEMORY_MAX_NREGIONS 8 #define VHOST_USER_F_PROTOCOL_FEATURES 30 -#define VHOST_USER_PROTOCOL_FEATURE_MASK 0x1ULL -#define VHOST_USER_PROTOCOL_F_MQ 0 +enum VhostUserProtocolFeature { + VHOST_USER_PROTOCOL_F_MQ = 0, + VHOST_USER_PROTOCOL_F_LOG_SHMFD = 1, + VHOST_USER_PROTOCOL_F_RARP = 2, + + VHOST_USER_PROTOCOL_F_MAX +}; + +#define VHOST_USER_PROTOCOL_FEATURE_MASK ((1 << VHOST_USER_PROTOCOL_F_MAX) - 1) typedef enum VhostUserRequest { VHOST_USER_NONE = 0, @@ -49,6 +58,7 @@ typedef enum VhostUserRequest { VHOST_USER_SET_PROTOCOL_FEATURES = 16, VHOST_USER_GET_QUEUE_NUM = 17, VHOST_USER_SET_VRING_ENABLE = 18, + VHOST_USER_SEND_RARP = 19, VHOST_USER_MAX } VhostUserRequest; @@ -97,37 +107,6 @@ static bool ioeventfd_enabled(void) return kvm_enabled() && kvm_eventfds_enabled(); } -static unsigned long int ioctl_to_vhost_user_request[VHOST_USER_MAX] = { - -1, /* VHOST_USER_NONE */ - VHOST_GET_FEATURES, /* VHOST_USER_GET_FEATURES */ - VHOST_SET_FEATURES, /* VHOST_USER_SET_FEATURES */ - VHOST_SET_OWNER, /* VHOST_USER_SET_OWNER */ - VHOST_RESET_DEVICE, /* VHOST_USER_RESET_DEVICE */ - VHOST_SET_MEM_TABLE, /* VHOST_USER_SET_MEM_TABLE */ - VHOST_SET_LOG_BASE, /* VHOST_USER_SET_LOG_BASE */ - VHOST_SET_LOG_FD, /* VHOST_USER_SET_LOG_FD */ - VHOST_SET_VRING_NUM, /* VHOST_USER_SET_VRING_NUM */ - VHOST_SET_VRING_ADDR, /* VHOST_USER_SET_VRING_ADDR */ - VHOST_SET_VRING_BASE, /* VHOST_USER_SET_VRING_BASE */ - VHOST_GET_VRING_BASE, /* VHOST_USER_GET_VRING_BASE */ - VHOST_SET_VRING_KICK, /* VHOST_USER_SET_VRING_KICK */ - VHOST_SET_VRING_CALL, /* VHOST_USER_SET_VRING_CALL */ - VHOST_SET_VRING_ERR /* VHOST_USER_SET_VRING_ERR */ -}; - -static VhostUserRequest vhost_user_request_translate(unsigned long int request) -{ - VhostUserRequest idx; - - for (idx = 0; idx < VHOST_USER_MAX; idx++) { - if (ioctl_to_vhost_user_request[idx] == request) { - break; - } - } - - return (idx == VHOST_USER_MAX) ? VHOST_USER_NONE : idx; -} - static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg) { CharDriverState *chr = dev->opaque; @@ -174,12 +153,35 @@ fail: return -1; } +static bool vhost_user_one_time_request(VhostUserRequest request) +{ + switch (request) { + case VHOST_USER_SET_OWNER: + case VHOST_USER_RESET_DEVICE: + case VHOST_USER_SET_MEM_TABLE: + case VHOST_USER_GET_QUEUE_NUM: + return true; + default: + return false; + } +} + +/* most non-init callers ignore the error */ static int vhost_user_write(struct vhost_dev *dev, VhostUserMsg *msg, int *fds, int fd_num) { CharDriverState *chr = dev->opaque; int size = VHOST_USER_HDR_SIZE + msg->size; + /* + * For non-vring specific requests, like VHOST_USER_SET_MEM_TABLE, + * we just need send it once in the first time. For later such + * request, we just ignore it. + */ + if (vhost_user_one_time_request(msg->request) && dev->vq_index != 0) { + return 0; + } + if (fd_num) { qemu_chr_fe_set_msgfds(chr, fds, fd_num); } @@ -188,195 +190,321 @@ static int vhost_user_write(struct vhost_dev *dev, VhostUserMsg *msg, 0 : -1; } -static bool vhost_user_one_time_request(VhostUserRequest request) +static int vhost_user_set_log_base(struct vhost_dev *dev, uint64_t base, + struct vhost_log *log) { - switch (request) { - case VHOST_USER_SET_OWNER: - case VHOST_USER_RESET_DEVICE: - case VHOST_USER_SET_MEM_TABLE: - case VHOST_USER_GET_QUEUE_NUM: - return true; - default: - return false; + int fds[VHOST_MEMORY_MAX_NREGIONS]; + size_t fd_num = 0; + bool shmfd = virtio_has_feature(dev->protocol_features, + VHOST_USER_PROTOCOL_F_LOG_SHMFD); + VhostUserMsg msg = { + .request = VHOST_USER_SET_LOG_BASE, + .flags = VHOST_USER_VERSION, + .u64 = base, + .size = sizeof(m.u64), + }; + + if (shmfd && log->fd != -1) { + fds[fd_num++] = log->fd; } + + vhost_user_write(dev, &msg, fds, fd_num); + + if (shmfd) { + msg.size = 0; + if (vhost_user_read(dev, &msg) < 0) { + return 0; + } + + if (msg.request != VHOST_USER_SET_LOG_BASE) { + error_report("Received unexpected msg type. " + "Expected %d received %d", + VHOST_USER_SET_LOG_BASE, msg.request); + return -1; + } + } + + return 0; } -static int vhost_user_call(struct vhost_dev *dev, unsigned long int request, - void *arg) +static int vhost_user_set_mem_table(struct vhost_dev *dev, + struct vhost_memory *mem) { - VhostUserMsg msg; - VhostUserRequest msg_request; - struct vhost_vring_file *file = 0; - int need_reply = 0; int fds[VHOST_MEMORY_MAX_NREGIONS]; int i, fd; size_t fd_num = 0; + VhostUserMsg msg = { + .request = VHOST_USER_SET_MEM_TABLE, + .flags = VHOST_USER_VERSION, + }; - assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER); - - /* only translate vhost ioctl requests */ - if (request > VHOST_USER_MAX) { - msg_request = vhost_user_request_translate(request); - } else { - msg_request = request; + for (i = 0; i < dev->mem->nregions; ++i) { + struct vhost_memory_region *reg = dev->mem->regions + i; + ram_addr_t ram_addr; + + assert((uintptr_t)reg->userspace_addr == reg->userspace_addr); + qemu_ram_addr_from_host((void *)(uintptr_t)reg->userspace_addr, + &ram_addr); + fd = qemu_get_ram_fd(ram_addr); + if (fd > 0) { + msg.memory.regions[fd_num].userspace_addr = reg->userspace_addr; + msg.memory.regions[fd_num].memory_size = reg->memory_size; + msg.memory.regions[fd_num].guest_phys_addr = reg->guest_phys_addr; + msg.memory.regions[fd_num].mmap_offset = reg->userspace_addr - + (uintptr_t) qemu_get_ram_block_host_ptr(ram_addr); + assert(fd_num < VHOST_MEMORY_MAX_NREGIONS); + fds[fd_num++] = fd; + } } - /* - * For non-vring specific requests, like VHOST_USER_SET_MEM_TABLE, - * we just need send it once in the first time. For later such - * request, we just ignore it. - */ - if (vhost_user_one_time_request(msg_request) && dev->vq_index != 0) { - return 0; + msg.memory.nregions = fd_num; + + if (!fd_num) { + error_report("Failed initializing vhost-user memory map, " + "consider using -object memory-backend-file share=on"); + return -1; } - msg.request = msg_request; - msg.flags = VHOST_USER_VERSION; - msg.size = 0; + msg.size = sizeof(m.memory.nregions); + msg.size += sizeof(m.memory.padding); + msg.size += fd_num * sizeof(VhostUserMemoryRegion); - switch (msg_request) { - case VHOST_USER_GET_FEATURES: - case VHOST_USER_GET_PROTOCOL_FEATURES: - case VHOST_USER_GET_QUEUE_NUM: - need_reply = 1; - break; + vhost_user_write(dev, &msg, fds, fd_num); - case VHOST_USER_SET_FEATURES: - case VHOST_USER_SET_LOG_BASE: - case VHOST_USER_SET_PROTOCOL_FEATURES: - msg.u64 = *((__u64 *) arg); - msg.size = sizeof(m.u64); - break; + return 0; +} - case VHOST_USER_SET_OWNER: - case VHOST_USER_RESET_DEVICE: - break; +static int vhost_user_set_vring_addr(struct vhost_dev *dev, + struct vhost_vring_addr *addr) +{ + VhostUserMsg msg = { + .request = VHOST_USER_SET_VRING_ADDR, + .flags = VHOST_USER_VERSION, + .addr = *addr, + .size = sizeof(*addr), + }; - case VHOST_USER_SET_MEM_TABLE: - for (i = 0; i < dev->mem->nregions; ++i) { - struct vhost_memory_region *reg = dev->mem->regions + i; - ram_addr_t ram_addr; - - assert((uintptr_t)reg->userspace_addr == reg->userspace_addr); - qemu_ram_addr_from_host((void *)(uintptr_t)reg->userspace_addr, &ram_addr); - fd = qemu_get_ram_fd(ram_addr); - if (fd > 0) { - msg.memory.regions[fd_num].userspace_addr = reg->userspace_addr; - msg.memory.regions[fd_num].memory_size = reg->memory_size; - msg.memory.regions[fd_num].guest_phys_addr = reg->guest_phys_addr; - msg.memory.regions[fd_num].mmap_offset = reg->userspace_addr - - (uintptr_t) qemu_get_ram_block_host_ptr(ram_addr); - assert(fd_num < VHOST_MEMORY_MAX_NREGIONS); - fds[fd_num++] = fd; - } - } + vhost_user_write(dev, &msg, NULL, 0); - msg.memory.nregions = fd_num; + return 0; +} - if (!fd_num) { - error_report("Failed initializing vhost-user memory map, " - "consider using -object memory-backend-file share=on"); - return -1; - } +static int vhost_user_set_vring_endian(struct vhost_dev *dev, + struct vhost_vring_state *ring) +{ + error_report("vhost-user trying to send unhandled ioctl"); + return -1; +} - msg.size = sizeof(m.memory.nregions); - msg.size += sizeof(m.memory.padding); - msg.size += fd_num * sizeof(VhostUserMemoryRegion); - - 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.state, arg, sizeof(struct vhost_vring_state)); - msg.size = sizeof(m.state); - break; - - case VHOST_USER_GET_VRING_BASE: - memcpy(&msg.state, arg, sizeof(struct vhost_vring_state)); - msg.size = sizeof(m.state); - need_reply = 1; - break; - - case VHOST_USER_SET_VRING_ADDR: - memcpy(&msg.addr, arg, sizeof(struct vhost_vring_addr)); - msg.size = sizeof(m.addr); - break; - - case VHOST_USER_SET_VRING_KICK: - case VHOST_USER_SET_VRING_CALL: - case VHOST_USER_SET_VRING_ERR: - file = arg; - msg.u64 = file->index & VHOST_USER_VRING_IDX_MASK; - msg.size = sizeof(m.u64); - if (ioeventfd_enabled() && file->fd > 0) { - fds[fd_num++] = file->fd; - } else { - msg.u64 |= VHOST_USER_VRING_NOFD_MASK; - } - break; - default: - error_report("vhost-user trying to send unhandled ioctl"); +static int vhost_set_vring(struct vhost_dev *dev, + unsigned long int request, + struct vhost_vring_state *ring) +{ + VhostUserMsg msg = { + .request = request, + .flags = VHOST_USER_VERSION, + .state = *ring, + .size = sizeof(*ring), + }; + + vhost_user_write(dev, &msg, NULL, 0); + + return 0; +} + +static int vhost_user_set_vring_num(struct vhost_dev *dev, + struct vhost_vring_state *ring) +{ + return vhost_set_vring(dev, VHOST_USER_SET_VRING_NUM, ring); +} + +static int vhost_user_set_vring_base(struct vhost_dev *dev, + struct vhost_vring_state *ring) +{ + return vhost_set_vring(dev, VHOST_USER_SET_VRING_BASE, ring); +} + +static int vhost_user_set_vring_enable(struct vhost_dev *dev, int enable) +{ + struct vhost_vring_state state = { + .index = dev->vq_index, + .num = enable, + }; + + if (!(dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ))) { return -1; - break; } - if (vhost_user_write(dev, &msg, fds, fd_num) < 0) { + return vhost_set_vring(dev, VHOST_USER_SET_VRING_ENABLE, &state); +} + + +static int vhost_user_get_vring_base(struct vhost_dev *dev, + struct vhost_vring_state *ring) +{ + VhostUserMsg msg = { + .request = VHOST_USER_GET_VRING_BASE, + .flags = VHOST_USER_VERSION, + .state = *ring, + .size = sizeof(*ring), + }; + + vhost_user_write(dev, &msg, NULL, 0); + + if (vhost_user_read(dev, &msg) < 0) { return 0; } - if (need_reply) { - if (vhost_user_read(dev, &msg) < 0) { - return 0; - } + if (msg.request != VHOST_USER_GET_VRING_BASE) { + error_report("Received unexpected msg type. Expected %d received %d", + VHOST_USER_GET_VRING_BASE, msg.request); + return -1; + } - if (msg_request != msg.request) { - error_report("Received unexpected msg type." - " Expected %d received %d", msg_request, msg.request); - return -1; - } + if (msg.size != sizeof(m.state)) { + error_report("Received bad msg size."); + return -1; + } - switch (msg_request) { - case VHOST_USER_GET_FEATURES: - case VHOST_USER_GET_PROTOCOL_FEATURES: - case VHOST_USER_GET_QUEUE_NUM: - if (msg.size != sizeof(m.u64)) { - error_report("Received bad msg size."); - return -1; - } - *((__u64 *) arg) = msg.u64; - break; - case VHOST_USER_GET_VRING_BASE: - if (msg.size != sizeof(m.state)) { - error_report("Received bad msg size."); - return -1; - } - memcpy(arg, &msg.state, sizeof(struct vhost_vring_state)); - break; - default: - error_report("Received unexpected msg type."); - return -1; - break; - } + *ring = msg.state; + + return 0; +} + +static int vhost_set_vring_file(struct vhost_dev *dev, + VhostUserRequest request, + struct vhost_vring_file *file) +{ + int fds[VHOST_MEMORY_MAX_NREGIONS]; + size_t fd_num = 0; + VhostUserMsg msg = { + .request = request, + .flags = VHOST_USER_VERSION, + .u64 = file->index & VHOST_USER_VRING_IDX_MASK, + .size = sizeof(m.u64), + }; + + if (ioeventfd_enabled() && file->fd > 0) { + fds[fd_num++] = file->fd; + } else { + msg.u64 |= VHOST_USER_VRING_NOFD_MASK; + } + + vhost_user_write(dev, &msg, fds, fd_num); + + return 0; +} + +static int vhost_user_set_vring_kick(struct vhost_dev *dev, + struct vhost_vring_file *file) +{ + return vhost_set_vring_file(dev, VHOST_USER_SET_VRING_KICK, file); +} + +static int vhost_user_set_vring_call(struct vhost_dev *dev, + struct vhost_vring_file *file) +{ + return vhost_set_vring_file(dev, VHOST_USER_SET_VRING_CALL, file); +} + +static int vhost_user_set_u64(struct vhost_dev *dev, int request, uint64_t u64) +{ + VhostUserMsg msg = { + .request = request, + .flags = VHOST_USER_VERSION, + .u64 = u64, + .size = sizeof(m.u64), + }; + + vhost_user_write(dev, &msg, NULL, 0); + + return 0; +} + +static int vhost_user_set_features(struct vhost_dev *dev, + uint64_t features) +{ + return vhost_user_set_u64(dev, VHOST_USER_SET_FEATURES, features); +} + +static int vhost_user_set_protocol_features(struct vhost_dev *dev, + uint64_t features) +{ + return vhost_user_set_u64(dev, VHOST_USER_SET_PROTOCOL_FEATURES, features); +} + +static int vhost_user_get_u64(struct vhost_dev *dev, int request, uint64_t *u64) +{ + VhostUserMsg msg = { + .request = request, + .flags = VHOST_USER_VERSION, + }; + + if (vhost_user_one_time_request(request) && dev->vq_index != 0) { + return 0; + } + + vhost_user_write(dev, &msg, NULL, 0); + + if (vhost_user_read(dev, &msg) < 0) { + return 0; + } + + if (msg.request != request) { + error_report("Received unexpected msg type. Expected %d received %d", + request, msg.request); + return -1; } + if (msg.size != sizeof(m.u64)) { + error_report("Received bad msg size."); + return -1; + } + + *u64 = msg.u64; + + return 0; +} + +static int vhost_user_get_features(struct vhost_dev *dev, uint64_t *features) +{ + return vhost_user_get_u64(dev, VHOST_USER_GET_FEATURES, features); +} + +static int vhost_user_set_owner(struct vhost_dev *dev) +{ + VhostUserMsg msg = { + .request = VHOST_USER_SET_OWNER, + .flags = VHOST_USER_VERSION, + }; + + vhost_user_write(dev, &msg, NULL, 0); + + return 0; +} + +static int vhost_user_reset_device(struct vhost_dev *dev) +{ + VhostUserMsg msg = { + .request = VHOST_USER_RESET_DEVICE, + .flags = VHOST_USER_VERSION, + }; + + vhost_user_write(dev, &msg, NULL, 0); + return 0; } static int vhost_user_init(struct vhost_dev *dev, void *opaque) { - unsigned long long features; + uint64_t features; int err; assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER); dev->opaque = opaque; - err = vhost_user_call(dev, VHOST_USER_GET_FEATURES, &features); + err = vhost_user_get_features(dev, &features); if (err < 0) { return err; } @@ -384,44 +512,37 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque) if (virtio_has_feature(features, VHOST_USER_F_PROTOCOL_FEATURES)) { dev->backend_features |= 1ULL << VHOST_USER_F_PROTOCOL_FEATURES; - err = vhost_user_call(dev, VHOST_USER_GET_PROTOCOL_FEATURES, &features); + err = vhost_user_get_u64(dev, VHOST_USER_GET_PROTOCOL_FEATURES, + &features); if (err < 0) { return err; } dev->protocol_features = features & VHOST_USER_PROTOCOL_FEATURE_MASK; - err = vhost_user_call(dev, VHOST_USER_SET_PROTOCOL_FEATURES, - &dev->protocol_features); + err = vhost_user_set_protocol_features(dev, dev->protocol_features); if (err < 0) { return err; } /* query the max queues we support if backend supports Multiple Queue */ if (dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ)) { - err = vhost_user_call(dev, VHOST_USER_GET_QUEUE_NUM, &dev->max_queues); + err = vhost_user_get_u64(dev, VHOST_USER_GET_QUEUE_NUM, + &dev->max_queues); if (err < 0) { return err; } } } - return 0; -} - -static int vhost_user_set_vring_enable(struct vhost_dev *dev, int enable) -{ - struct vhost_vring_state state = { - .index = dev->vq_index, - .num = enable, - }; - - assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER); - - if (!(dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ))) { - return -1; + if (dev->migration_blocker == NULL && + !virtio_has_feature(dev->protocol_features, + VHOST_USER_PROTOCOL_F_LOG_SHMFD)) { + error_setg(&dev->migration_blocker, + "Migration disabled: vhost-user backend lacks " + "VHOST_USER_PROTOCOL_F_LOG_SHMFD feature."); } - return vhost_user_call(dev, VHOST_USER_SET_VRING_ENABLE, &state); + return 0; } static int vhost_user_cleanup(struct vhost_dev *dev) @@ -440,11 +561,65 @@ static int vhost_user_get_vq_index(struct vhost_dev *dev, int idx) return idx; } +static int vhost_user_memslots_limit(struct vhost_dev *dev) +{ + return VHOST_MEMORY_MAX_NREGIONS; +} + +static bool vhost_user_requires_shm_log(struct vhost_dev *dev) +{ + assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER); + + return virtio_has_feature(dev->protocol_features, + VHOST_USER_PROTOCOL_F_LOG_SHMFD); +} + +static int vhost_user_migration_done(struct vhost_dev *dev, char* mac_addr) +{ + VhostUserMsg msg = { 0 }; + int err; + + assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER); + + /* If guest supports GUEST_ANNOUNCE do nothing */ + if (virtio_has_feature(dev->acked_features, VIRTIO_NET_F_GUEST_ANNOUNCE)) { + return 0; + } + + /* if backend supports VHOST_USER_PROTOCOL_F_RARP ask it to send the RARP */ + if (virtio_has_feature(dev->protocol_features, + VHOST_USER_PROTOCOL_F_RARP)) { + msg.request = VHOST_USER_SEND_RARP; + msg.flags = VHOST_USER_VERSION; + memcpy((char *)&msg.u64, mac_addr, 6); + msg.size = sizeof(m.u64); + + err = vhost_user_write(dev, &msg, NULL, 0); + return err; + } + return -1; +} + const VhostOps user_ops = { .backend_type = VHOST_BACKEND_TYPE_USER, - .vhost_call = vhost_user_call, .vhost_backend_init = vhost_user_init, .vhost_backend_cleanup = vhost_user_cleanup, - .vhost_backend_get_vq_index = vhost_user_get_vq_index, - .vhost_backend_set_vring_enable = vhost_user_set_vring_enable, + .vhost_backend_memslots_limit = vhost_user_memslots_limit, + .vhost_set_log_base = vhost_user_set_log_base, + .vhost_set_mem_table = vhost_user_set_mem_table, + .vhost_set_vring_addr = vhost_user_set_vring_addr, + .vhost_set_vring_endian = vhost_user_set_vring_endian, + .vhost_set_vring_num = vhost_user_set_vring_num, + .vhost_set_vring_base = vhost_user_set_vring_base, + .vhost_get_vring_base = vhost_user_get_vring_base, + .vhost_set_vring_kick = vhost_user_set_vring_kick, + .vhost_set_vring_call = vhost_user_set_vring_call, + .vhost_set_features = vhost_user_set_features, + .vhost_get_features = vhost_user_get_features, + .vhost_set_owner = vhost_user_set_owner, + .vhost_reset_device = vhost_user_reset_device, + .vhost_get_vq_index = vhost_user_get_vq_index, + .vhost_set_vring_enable = vhost_user_set_vring_enable, + .vhost_requires_shm_log = vhost_user_requires_shm_log, + .vhost_migration_done = vhost_user_migration_done, }; |