diff options
Diffstat (limited to 'hw/virtio')
| -rw-r--r-- | hw/virtio/Kconfig | 11 | ||||
| -rw-r--r-- | hw/virtio/Makefile.objs | 3 | ||||
| -rw-r--r-- | hw/virtio/trace-events | 10 | ||||
| -rw-r--r-- | hw/virtio/vhost-backend.c | 6 | ||||
| -rw-r--r-- | hw/virtio/vhost-vdpa.c | 475 | ||||
| -rw-r--r-- | hw/virtio/vhost.c | 52 | ||||
| -rw-r--r-- | hw/virtio/virtio-balloon.c | 36 | ||||
| -rw-r--r-- | hw/virtio/virtio-mem-pci.c | 157 | ||||
| -rw-r--r-- | hw/virtio/virtio-mem-pci.h | 34 | ||||
| -rw-r--r-- | hw/virtio/virtio-mem.c | 873 | ||||
| -rw-r--r-- | hw/virtio/virtio-pci.c | 13 | ||||
| -rw-r--r-- | hw/virtio/virtio.c | 6 |
12 files changed, 1655 insertions, 21 deletions
diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig index 83122424fa..0eda25c4e1 100644 --- a/hw/virtio/Kconfig +++ b/hw/virtio/Kconfig @@ -47,3 +47,14 @@ config VIRTIO_PMEM depends on VIRTIO depends on VIRTIO_PMEM_SUPPORTED select MEM_DEVICE + +config VIRTIO_MEM_SUPPORTED + bool + +config VIRTIO_MEM + bool + default y + depends on VIRTIO + depends on LINUX + depends on VIRTIO_MEM_SUPPORTED + select MEM_DEVICE diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs index 13e75f171f..fc91719b4a 100644 --- a/hw/virtio/Makefile.objs +++ b/hw/virtio/Makefile.objs @@ -5,6 +5,7 @@ obj-y += virtio.o obj-$(CONFIG_VHOST) += vhost.o vhost-backend.o common-obj-$(call lnot,$(CONFIG_VHOST)) += vhost-stub.o obj-$(CONFIG_VHOST_USER) += vhost-user.o +obj-$(CONFIG_VHOST_VDPA) += vhost-vdpa.o common-obj-$(CONFIG_VIRTIO_RNG) += virtio-rng.o common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o @@ -19,6 +20,8 @@ obj-$(call land,$(CONFIG_VHOST_USER_FS),$(CONFIG_VIRTIO_PCI)) += vhost-user-fs-p obj-$(CONFIG_VIRTIO_IOMMU) += virtio-iommu.o obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock-common.o vhost-vsock.o obj-$(CONFIG_VHOST_USER_VSOCK) += vhost-vsock-common.o vhost-user-vsock.o +obj-$(CONFIG_VIRTIO_MEM) += virtio-mem.o +common-obj-$(call land,$(CONFIG_VIRTIO_MEM),$(CONFIG_VIRTIO_PCI)) += virtio-mem-pci.o ifeq ($(CONFIG_VIRTIO_PCI),y) obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock-pci.o diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events index 23109f69bb..045e89cae6 100644 --- a/hw/virtio/trace-events +++ b/hw/virtio/trace-events @@ -75,3 +75,13 @@ virtio_iommu_put_domain(uint32_t domain_id) "Free domain=%d" virtio_iommu_translate_out(uint64_t virt_addr, uint64_t phys_addr, uint32_t sid) "0x%"PRIx64" -> 0x%"PRIx64 " for sid=%d" virtio_iommu_report_fault(uint8_t reason, uint32_t flags, uint32_t endpoint, uint64_t addr) "FAULT reason=%d flags=%d endpoint=%d address =0x%"PRIx64 virtio_iommu_fill_resv_property(uint32_t devid, uint8_t subtype, uint64_t start, uint64_t end) "dev= %d, type=%d start=0x%"PRIx64" end=0x%"PRIx64 + +# virtio-mem.c +virtio_mem_send_response(uint16_t type) "type=%" PRIu16 +virtio_mem_plug_request(uint64_t addr, uint16_t nb_blocks) "addr=0x%" PRIx64 " nb_blocks=%" PRIu16 +virtio_mem_unplug_request(uint64_t addr, uint16_t nb_blocks) "addr=0x%" PRIx64 " nb_blocks=%" PRIu16 +virtio_mem_unplugged_all(void) "" +virtio_mem_unplug_all_request(void) "" +virtio_mem_resized_usable_region(uint64_t old_size, uint64_t new_size) "old_size=0x%" PRIx64 "new_size=0x%" PRIx64 +virtio_mem_state_request(uint64_t addr, uint16_t nb_blocks) "addr=0x%" PRIx64 " nb_blocks=%" PRIu16 +virtio_mem_state_response(uint16_t state) "state=%" PRIu16 diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c index 48905383f8..782b1d67d9 100644 --- a/hw/virtio/vhost-backend.c +++ b/hw/virtio/vhost-backend.c @@ -15,6 +15,7 @@ #include "qemu/main-loop.h" #include "standard-headers/linux/vhost_types.h" +#include "hw/virtio/vhost-vdpa.h" #ifdef CONFIG_VHOST_KERNEL #include <linux/vhost.h> #include <sys/ioctl.h> @@ -286,6 +287,11 @@ int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type) dev->vhost_ops = &user_ops; break; #endif +#ifdef CONFIG_VHOST_VDPA + case VHOST_BACKEND_TYPE_VDPA: + dev->vhost_ops = &vdpa_ops; + break; +#endif default: error_report("Unknown vhost backend type"); r = -1; diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c new file mode 100644 index 0000000000..a3d17fe0f9 --- /dev/null +++ b/hw/virtio/vhost-vdpa.c @@ -0,0 +1,475 @@ +/* + * vhost-vdpa + * + * Copyright(c) 2017-2018 Intel Corporation. + * Copyright(c) 2020 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include <linux/vhost.h> +#include <linux/vfio.h> +#include <sys/eventfd.h> +#include <sys/ioctl.h> +#include "hw/virtio/vhost.h" +#include "hw/virtio/vhost-backend.h" +#include "hw/virtio/virtio-net.h" +#include "hw/virtio/vhost-vdpa.h" +#include "qemu/main-loop.h" +#include <linux/kvm.h> +#include "sysemu/kvm.h" + +static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section) +{ + return (!memory_region_is_ram(section->mr) && + !memory_region_is_iommu(section->mr)) || + /* + * Sizing an enabled 64-bit BAR can cause spurious mappings to + * addresses in the upper part of the 64-bit address space. These + * are never accessed by the CPU and beyond the address width of + * some IOMMU hardware. TODO: VDPA should tell us the IOMMU width. + */ + section->offset_within_address_space & (1ULL << 63); +} + +static int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size, + void *vaddr, bool readonly) +{ + struct vhost_msg_v2 msg; + int fd = v->device_fd; + int ret = 0; + + msg.type = v->msg_type; + msg.iotlb.iova = iova; + msg.iotlb.size = size; + msg.iotlb.uaddr = (uint64_t)(uintptr_t)vaddr; + msg.iotlb.perm = readonly ? VHOST_ACCESS_RO : VHOST_ACCESS_RW; + msg.iotlb.type = VHOST_IOTLB_UPDATE; + + if (write(fd, &msg, sizeof(msg)) != sizeof(msg)) { + error_report("failed to write, fd=%d, errno=%d (%s)", + fd, errno, strerror(errno)); + return -EIO ; + } + + return ret; +} + +static int vhost_vdpa_dma_unmap(struct vhost_vdpa *v, hwaddr iova, + hwaddr size) +{ + struct vhost_msg_v2 msg; + int fd = v->device_fd; + int ret = 0; + + msg.type = v->msg_type; + msg.iotlb.iova = iova; + msg.iotlb.size = size; + msg.iotlb.type = VHOST_IOTLB_INVALIDATE; + + if (write(fd, &msg, sizeof(msg)) != sizeof(msg)) { + error_report("failed to write, fd=%d, errno=%d (%s)", + fd, errno, strerror(errno)); + return -EIO ; + } + + return ret; +} + +static void vhost_vdpa_listener_region_add(MemoryListener *listener, + MemoryRegionSection *section) +{ + struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener); + hwaddr iova; + Int128 llend, llsize; + void *vaddr; + int ret; + + if (vhost_vdpa_listener_skipped_section(section)) { + return; + } + + if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) != + (section->offset_within_region & ~TARGET_PAGE_MASK))) { + error_report("%s received unaligned region", __func__); + return; + } + + iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); + llend = int128_make64(section->offset_within_address_space); + llend = int128_add(llend, section->size); + llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK)); + + if (int128_ge(int128_make64(iova), llend)) { + return; + } + + memory_region_ref(section->mr); + + /* Here we assume that memory_region_is_ram(section->mr)==true */ + + vaddr = memory_region_get_ram_ptr(section->mr) + + section->offset_within_region + + (iova - section->offset_within_address_space); + + llsize = int128_sub(llend, int128_make64(iova)); + + ret = vhost_vdpa_dma_map(v, iova, int128_get64(llsize), + vaddr, section->readonly); + if (ret) { + error_report("vhost vdpa map fail!"); + if (memory_region_is_ram_device(section->mr)) { + /* Allow unexpected mappings not to be fatal for RAM devices */ + error_report("map ram fail!"); + return ; + } + goto fail; + } + + return; + +fail: + if (memory_region_is_ram_device(section->mr)) { + error_report("failed to vdpa_dma_map. pci p2p may not work"); + return; + + } + /* + * On the initfn path, store the first error in the container so we + * can gracefully fail. Runtime, there's not much we can do other + * than throw a hardware error. + */ + error_report("vhost-vdpa: DMA mapping failed, unable to continue"); + return; + +} + +static void vhost_vdpa_listener_region_del(MemoryListener *listener, + MemoryRegionSection *section) +{ + struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener); + hwaddr iova; + Int128 llend, llsize; + int ret; + bool try_unmap = true; + + if (vhost_vdpa_listener_skipped_section(section)) { + return; + } + + if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) != + (section->offset_within_region & ~TARGET_PAGE_MASK))) { + error_report("%s received unaligned region", __func__); + return; + } + + iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); + llend = int128_make64(section->offset_within_address_space); + llend = int128_add(llend, section->size); + llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK)); + + if (int128_ge(int128_make64(iova), llend)) { + return; + } + + llsize = int128_sub(llend, int128_make64(iova)); + + if (try_unmap) { + ret = vhost_vdpa_dma_unmap(v, iova, int128_get64(llsize)); + if (ret) { + error_report("vhost_vdpa dma unmap error!"); + } + } + + memory_region_unref(section->mr); +} +/* + * IOTLB API is used by vhost-vpda which requires incremental updating + * of the mapping. So we can not use generic vhost memory listener which + * depends on the addnop(). + */ +static const MemoryListener vhost_vdpa_memory_listener = { + .region_add = vhost_vdpa_listener_region_add, + .region_del = vhost_vdpa_listener_region_del, +}; + +static int vhost_vdpa_call(struct vhost_dev *dev, unsigned long int request, + void *arg) +{ + struct vhost_vdpa *v = dev->opaque; + int fd = v->device_fd; + + assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_VDPA); + + return ioctl(fd, request, arg); +} + +static void vhost_vdpa_add_status(struct vhost_dev *dev, uint8_t status) +{ + uint8_t s; + + if (vhost_vdpa_call(dev, VHOST_VDPA_GET_STATUS, &s)) { + return; + } + + s |= status; + + vhost_vdpa_call(dev, VHOST_VDPA_SET_STATUS, &s); +} + +static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque) +{ + struct vhost_vdpa *v; + uint64_t features; + assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_VDPA); + + v = opaque; + dev->opaque = opaque ; + vhost_vdpa_call(dev, VHOST_GET_FEATURES, &features); + dev->backend_features = features; + v->listener = vhost_vdpa_memory_listener; + v->msg_type = VHOST_IOTLB_MSG_V2; + + vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE | + VIRTIO_CONFIG_S_DRIVER); + + return 0; +} + +static int vhost_vdpa_cleanup(struct vhost_dev *dev) +{ + struct vhost_vdpa *v; + assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_VDPA); + v = dev->opaque; + memory_listener_unregister(&v->listener); + + dev->opaque = NULL; + return 0; +} + +static int vhost_vdpa_memslots_limit(struct vhost_dev *dev) +{ + return INT_MAX; +} + +static int vhost_vdpa_set_mem_table(struct vhost_dev *dev, + struct vhost_memory *mem) +{ + + if (mem->padding) { + return -1; + } + + return 0; +} + +static int vhost_vdpa_set_features(struct vhost_dev *dev, + uint64_t features) +{ + int ret; + ret = vhost_vdpa_call(dev, VHOST_SET_FEATURES, &features); + uint8_t status = 0; + if (ret) { + return ret; + } + vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_FEATURES_OK); + vhost_vdpa_call(dev, VHOST_VDPA_GET_STATUS, &status); + + return !(status & VIRTIO_CONFIG_S_FEATURES_OK); +} + +int vhost_vdpa_get_device_id(struct vhost_dev *dev, + uint32_t *device_id) +{ + return vhost_vdpa_call(dev, VHOST_VDPA_GET_DEVICE_ID, device_id); +} + +static int vhost_vdpa_reset_device(struct vhost_dev *dev) +{ + uint8_t status = 0; + + return vhost_vdpa_call(dev, VHOST_VDPA_SET_STATUS, &status); +} + +static int vhost_vdpa_get_vq_index(struct vhost_dev *dev, int idx) +{ + assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs); + + return idx - dev->vq_index; +} + +static int vhost_vdpa_set_vring_ready(struct vhost_dev *dev) +{ + int i; + for (i = 0; i < dev->nvqs; ++i) { + struct vhost_vring_state state = { + .index = dev->vq_index + i, + .num = 1, + }; + vhost_vdpa_call(dev, VHOST_VDPA_SET_VRING_ENABLE, &state); + } + return 0; +} + +static int vhost_vdpa_set_config(struct vhost_dev *dev, const uint8_t *data, + uint32_t offset, uint32_t size, + uint32_t flags) +{ + struct vhost_vdpa_config *config; + int ret; + unsigned long config_size = offsetof(struct vhost_vdpa_config, buf); + config = g_malloc(size + config_size); + if (config == NULL) { + return -1; + } + config->off = offset; + config->len = size; + memcpy(config->buf, data, size); + ret = vhost_vdpa_call(dev, VHOST_VDPA_SET_CONFIG, config); + g_free(config); + return ret; +} + +static int vhost_vdpa_get_config(struct vhost_dev *dev, uint8_t *config, + uint32_t config_len) +{ + struct vhost_vdpa_config *v_config; + unsigned long config_size = offsetof(struct vhost_vdpa_config, buf); + int ret; + + v_config = g_malloc(config_len + config_size); + if (v_config == NULL) { + return -1; + } + v_config->len = config_len; + v_config->off = 0; + ret = vhost_vdpa_call(dev, VHOST_VDPA_GET_CONFIG, v_config); + memcpy(config, v_config->buf, config_len); + g_free(v_config); + return ret; + } + +static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) +{ + struct vhost_vdpa *v = dev->opaque; + if (started) { + uint8_t status = 0; + memory_listener_register(&v->listener, &address_space_memory); + vhost_vdpa_set_vring_ready(dev); + vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK); + vhost_vdpa_call(dev, VHOST_VDPA_GET_STATUS, &status); + + return !(status & VIRTIO_CONFIG_S_DRIVER_OK); + } else { + vhost_vdpa_reset_device(dev); + vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE | + VIRTIO_CONFIG_S_DRIVER); + memory_listener_unregister(&v->listener); + + return 0; + } +} + +static int vhost_vdpa_set_log_base(struct vhost_dev *dev, uint64_t base, + struct vhost_log *log) +{ + return vhost_vdpa_call(dev, VHOST_SET_LOG_BASE, &base); +} + +static int vhost_vdpa_set_vring_addr(struct vhost_dev *dev, + struct vhost_vring_addr *addr) +{ + return vhost_vdpa_call(dev, VHOST_SET_VRING_ADDR, addr); +} + +static int vhost_vdpa_set_vring_num(struct vhost_dev *dev, + struct vhost_vring_state *ring) +{ + return vhost_vdpa_call(dev, VHOST_SET_VRING_NUM, ring); +} + +static int vhost_vdpa_set_vring_base(struct vhost_dev *dev, + struct vhost_vring_state *ring) +{ + return vhost_vdpa_call(dev, VHOST_SET_VRING_BASE, ring); +} + +static int vhost_vdpa_get_vring_base(struct vhost_dev *dev, + struct vhost_vring_state *ring) +{ + return vhost_vdpa_call(dev, VHOST_GET_VRING_BASE, ring); +} + +static int vhost_vdpa_set_vring_kick(struct vhost_dev *dev, + struct vhost_vring_file *file) +{ + return vhost_vdpa_call(dev, VHOST_SET_VRING_KICK, file); +} + +static int vhost_vdpa_set_vring_call(struct vhost_dev *dev, + struct vhost_vring_file *file) +{ + return vhost_vdpa_call(dev, VHOST_SET_VRING_CALL, file); +} + +static int vhost_vdpa_get_features(struct vhost_dev *dev, + uint64_t *features) +{ + return vhost_vdpa_call(dev, VHOST_GET_FEATURES, features); +} + +static int vhost_vdpa_set_owner(struct vhost_dev *dev) +{ + return vhost_vdpa_call(dev, VHOST_SET_OWNER, NULL); +} + +static int vhost_vdpa_vq_get_addr(struct vhost_dev *dev, + struct vhost_vring_addr *addr, struct vhost_virtqueue *vq) +{ + assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_VDPA); + addr->desc_user_addr = (uint64_t)(unsigned long)vq->desc_phys; + addr->avail_user_addr = (uint64_t)(unsigned long)vq->avail_phys; + addr->used_user_addr = (uint64_t)(unsigned long)vq->used_phys; + return 0; +} + +static bool vhost_vdpa_force_iommu(struct vhost_dev *dev) +{ + return true; +} + +const VhostOps vdpa_ops = { + .backend_type = VHOST_BACKEND_TYPE_VDPA, + .vhost_backend_init = vhost_vdpa_init, + .vhost_backend_cleanup = vhost_vdpa_cleanup, + .vhost_set_log_base = vhost_vdpa_set_log_base, + .vhost_set_vring_addr = vhost_vdpa_set_vring_addr, + .vhost_set_vring_num = vhost_vdpa_set_vring_num, + .vhost_set_vring_base = vhost_vdpa_set_vring_base, + .vhost_get_vring_base = vhost_vdpa_get_vring_base, + .vhost_set_vring_kick = vhost_vdpa_set_vring_kick, + .vhost_set_vring_call = vhost_vdpa_set_vring_call, + .vhost_get_features = vhost_vdpa_get_features, + .vhost_set_owner = vhost_vdpa_set_owner, + .vhost_set_vring_endian = NULL, + .vhost_backend_memslots_limit = vhost_vdpa_memslots_limit, + .vhost_set_mem_table = vhost_vdpa_set_mem_table, + .vhost_set_features = vhost_vdpa_set_features, + .vhost_reset_device = vhost_vdpa_reset_device, + .vhost_get_vq_index = vhost_vdpa_get_vq_index, + .vhost_get_config = vhost_vdpa_get_config, + .vhost_set_config = vhost_vdpa_set_config, + .vhost_requires_shm_log = NULL, + .vhost_migration_done = NULL, + .vhost_backend_can_merge = NULL, + .vhost_net_set_mtu = NULL, + .vhost_set_iotlb_callback = NULL, + .vhost_send_device_iotlb_msg = NULL, + .vhost_dev_start = vhost_vdpa_dev_start, + .vhost_get_device_id = vhost_vdpa_get_device_id, + .vhost_vq_get_addr = vhost_vdpa_vq_get_addr, + .vhost_force_iommu = vhost_vdpa_force_iommu, +}; diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index 5fd25fe520..1a1384e7a6 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -773,15 +773,25 @@ static int vhost_virtqueue_set_addr(struct vhost_dev *dev, struct vhost_virtqueue *vq, unsigned idx, bool enable_log) { - struct vhost_vring_addr addr = { - .index = idx, - .desc_user_addr = (uint64_t)(unsigned long)vq->desc, - .avail_user_addr = (uint64_t)(unsigned long)vq->avail, - .used_user_addr = (uint64_t)(unsigned long)vq->used, - .log_guest_addr = vq->used_phys, - .flags = enable_log ? (1 << VHOST_VRING_F_LOG) : 0, - }; - int r = dev->vhost_ops->vhost_set_vring_addr(dev, &addr); + struct vhost_vring_addr addr; + int r; + memset(&addr, 0, sizeof(struct vhost_vring_addr)); + + if (dev->vhost_ops->vhost_vq_get_addr) { + r = dev->vhost_ops->vhost_vq_get_addr(dev, &addr, vq); + if (r < 0) { + VHOST_OPS_DEBUG("vhost_vq_get_addr failed"); + return -errno; + } + } else { + addr.desc_user_addr = (uint64_t)(unsigned long)vq->desc; + addr.avail_user_addr = (uint64_t)(unsigned long)vq->avail; + addr.used_user_addr = (uint64_t)(unsigned long)vq->used; + } + addr.index = idx; + addr.log_guest_addr = vq->used_phys; + addr.flags = enable_log ? (1 << VHOST_VRING_F_LOG) : 0; + r = dev->vhost_ops->vhost_set_vring_addr(dev, &addr); if (r < 0) { VHOST_OPS_DEBUG("vhost_set_vring_addr failed"); return -errno; @@ -800,6 +810,11 @@ static int vhost_dev_set_features(struct vhost_dev *dev, if (!vhost_dev_has_iommu(dev)) { features &= ~(0x1ULL << VIRTIO_F_IOMMU_PLATFORM); } + if (dev->vhost_ops->vhost_force_iommu) { + if (dev->vhost_ops->vhost_force_iommu(dev) == true) { + features |= 0x1ULL << VIRTIO_F_IOMMU_PLATFORM; + } + } r = dev->vhost_ops->vhost_set_features(dev, features); if (r < 0) { VHOST_OPS_DEBUG("vhost_set_features failed"); @@ -1685,9 +1700,15 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) goto fail_log; } } - - if (vhost_dev_has_iommu(hdev)) { - hdev->vhost_ops->vhost_set_iotlb_callback(hdev, true); + if (hdev->vhost_ops->vhost_dev_start) { + r = hdev->vhost_ops->vhost_dev_start(hdev, true); + if (r) { + goto fail_log; + } + } + if (vhost_dev_has_iommu(hdev) && + hdev->vhost_ops->vhost_set_iotlb_callback) { + hdev->vhost_ops->vhost_set_iotlb_callback(hdev, true); /* Update used ring information for IOTLB to work correctly, * vhost-kernel code requires for this.*/ @@ -1722,6 +1743,9 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev) /* should only be called after backend is connected */ assert(hdev->vhost_ops); + if (hdev->vhost_ops->vhost_dev_start) { + hdev->vhost_ops->vhost_dev_start(hdev, false); + } for (i = 0; i < hdev->nvqs; ++i) { vhost_virtqueue_stop(hdev, vdev, @@ -1730,7 +1754,9 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev) } if (vhost_dev_has_iommu(hdev)) { - hdev->vhost_ops->vhost_set_iotlb_callback(hdev, false); + if (hdev->vhost_ops->vhost_set_iotlb_callback) { + hdev->vhost_ops->vhost_set_iotlb_callback(hdev, false); + } memory_listener_unregister(&hdev->iommu_listener); } vhost_log_put(hdev, true); diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c index 10507b2a43..ae31f0817a 100644 --- a/hw/virtio/virtio-balloon.c +++ b/hw/virtio/virtio-balloon.c @@ -63,6 +63,12 @@ static bool virtio_balloon_pbp_matches(PartiallyBalloonedPage *pbp, return pbp->base_gpa == base_gpa; } +static bool virtio_balloon_inhibited(void) +{ + /* Postcopy cannot deal with concurrent discards, so it's special. */ + return ram_block_discard_is_disabled() || migration_in_incoming_postcopy(); +} + static void balloon_inflate_page(VirtIOBalloon *balloon, MemoryRegion *mr, hwaddr mr_offset, PartiallyBalloonedPage *pbp) @@ -336,7 +342,7 @@ static void virtio_balloon_handle_report(VirtIODevice *vdev, VirtQueue *vq) * accessible by another device or process, or if the guest is * expecting it to retain a non-zero value. */ - if (qemu_balloon_is_inhibited() || dev->poison_val) { + if (virtio_balloon_inhibited() || dev->poison_val) { goto skip_element; } @@ -421,7 +427,7 @@ static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq) trace_virtio_balloon_handle_output(memory_region_name(section.mr), pa); - if (!qemu_balloon_is_inhibited()) { + if (!virtio_balloon_inhibited()) { if (vq == s->ivq) { balloon_inflate_page(s, section.mr, section.offset_within_region, &pbp); @@ -628,8 +634,13 @@ static void virtio_balloon_free_page_done(VirtIOBalloon *s) { VirtIODevice *vdev = VIRTIO_DEVICE(s); - s->free_page_report_status = FREE_PAGE_REPORT_S_DONE; - virtio_notify_config(vdev); + if (s->free_page_report_status != FREE_PAGE_REPORT_S_DONE) { + /* See virtio_balloon_free_page_stop() */ + qemu_mutex_lock(&s->free_page_lock); + s->free_page_report_status = FREE_PAGE_REPORT_S_DONE; + qemu_mutex_unlock(&s->free_page_lock); + virtio_notify_config(vdev); + } } static int @@ -653,17 +664,26 @@ virtio_balloon_free_page_report_notify(NotifierWithReturn *n, void *data) case PRECOPY_NOTIFY_SETUP: precopy_enable_free_page_optimization(); break; - case PRECOPY_NOTIFY_COMPLETE: - case PRECOPY_NOTIFY_CLEANUP: case PRECOPY_NOTIFY_BEFORE_BITMAP_SYNC: virtio_balloon_free_page_stop(dev); break; case PRECOPY_NOTIFY_AFTER_BITMAP_SYNC: if (vdev->vm_running) { virtio_balloon_free_page_start(dev); - } else { - virtio_balloon_free_page_done(dev); + break; } + /* + * Set S_DONE before migrating the vmstate, so the guest will reuse + * all hinted pages once running on the destination. Fall through. + */ + case PRECOPY_NOTIFY_CLEANUP: + /* + * Especially, if something goes wrong during precopy or if migration + * is canceled, we have to properly communicate S_DONE to the VM. + */ + virtio_balloon_free_page_done(dev); + break; + case PRECOPY_NOTIFY_COMPLETE: break; default: virtio_error(vdev, "%s: %d reason unknown", __func__, pnd->reason); diff --git a/hw/virtio/virtio-mem-pci.c b/hw/virtio/virtio-mem-pci.c new file mode 100644 index 0000000000..1a8e854123 --- /dev/null +++ b/hw/virtio/virtio-mem-pci.c @@ -0,0 +1,157 @@ +/* + * Virtio MEM PCI device + * + * Copyright (C) 2020 Red Hat, Inc. + * + * Authors: + * David Hildenbrand <david@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "virtio-mem-pci.h" +#include "hw/mem/memory-device.h" +#include "qapi/error.h" +#include "qapi/qapi-events-misc.h" + +static void virtio_mem_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VirtIOMEMPCI *mem_pci = VIRTIO_MEM_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&mem_pci->vdev); + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static void virtio_mem_pci_set_addr(MemoryDeviceState *md, uint64_t addr, + Error **errp) +{ + object_property_set_uint(OBJECT(md), addr, VIRTIO_MEM_ADDR_PROP, errp); +} + +static uint64_t virtio_mem_pci_get_addr(const MemoryDeviceState *md) +{ + return object_property_get_uint(OBJECT(md), VIRTIO_MEM_ADDR_PROP, + &error_abort); +} + +static MemoryRegion *virtio_mem_pci_get_memory_region(MemoryDeviceState *md, + Error **errp) +{ + VirtIOMEMPCI *pci_mem = VIRTIO_MEM_PCI(md); + VirtIOMEM *vmem = VIRTIO_MEM(&pci_mem->vdev); + VirtIOMEMClass *vmc = VIRTIO_MEM_GET_CLASS(vmem); + + return vmc->get_memory_region(vmem, errp); +} + +static uint64_t virtio_mem_pci_get_plugged_size(const MemoryDeviceState *md, + Error **errp) +{ + return object_property_get_uint(OBJECT(md), VIRTIO_MEM_SIZE_PROP, + errp); +} + +static void virtio_mem_pci_fill_device_info(const MemoryDeviceState *md, + MemoryDeviceInfo *info) +{ + VirtioMEMDeviceInfo *vi = g_new0(VirtioMEMDeviceInfo, 1); + VirtIOMEMPCI *pci_mem = VIRTIO_MEM_PCI(md); + VirtIOMEM *vmem = VIRTIO_MEM(&pci_mem->vdev); + VirtIOMEMClass *vpc = VIRTIO_MEM_GET_CLASS(vmem); + DeviceState *dev = DEVICE(md); + + if (dev->id) { + vi->has_id = true; + vi->id = g_strdup(dev->id); + } + + /* let the real device handle everything else */ + vpc->fill_device_info(vmem, vi); + + info->u.virtio_mem.data = vi; + info->type = MEMORY_DEVICE_INFO_KIND_VIRTIO_MEM; +} + +static void virtio_mem_pci_size_change_notify(Notifier *notifier, void *data) +{ + VirtIOMEMPCI *pci_mem = container_of(notifier, VirtIOMEMPCI, + size_change_notifier); + DeviceState *dev = DEVICE(pci_mem); + const uint64_t * const size_p = data; + const char *id = NULL; + + if (dev->id) { + id = g_strdup(dev->id); + } + + qapi_event_send_memory_device_size_change(!!id, id, *size_p); +} + +static void virtio_mem_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + MemoryDeviceClass *mdc = MEMORY_DEVICE_CLASS(klass); + + k->realize = virtio_mem_pci_realize; + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_MEM; + pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; + pcidev_k->class_id = PCI_CLASS_OTHERS; + + mdc->get_addr = virtio_mem_pci_get_addr; + mdc->set_addr = virtio_mem_pci_set_addr; + mdc->get_plugged_size = virtio_mem_pci_get_plugged_size; + mdc->get_memory_region = virtio_mem_pci_get_memory_region; + mdc->fill_device_info = virtio_mem_pci_fill_device_info; +} + +static void virtio_mem_pci_instance_init(Object *obj) +{ + VirtIOMEMPCI *dev = VIRTIO_MEM_PCI(obj); + VirtIOMEMClass *vmc; + VirtIOMEM *vmem; + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_MEM); + + dev->size_change_notifier.notify = virtio_mem_pci_size_change_notify; + vmem = VIRTIO_MEM(&dev->vdev); + vmc = VIRTIO_MEM_GET_CLASS(vmem); + /* + * We never remove the notifier again, as we expect both devices to + * disappear at the same time. + */ + vmc->add_size_change_notifier(vmem, &dev->size_change_notifier); + + object_property_add_alias(obj, VIRTIO_MEM_BLOCK_SIZE_PROP, + OBJECT(&dev->vdev), VIRTIO_MEM_BLOCK_SIZE_PROP); + object_property_add_alias(obj, VIRTIO_MEM_SIZE_PROP, OBJECT(&dev->vdev), + VIRTIO_MEM_SIZE_PROP); + object_property_add_alias(obj, VIRTIO_MEM_REQUESTED_SIZE_PROP, + OBJECT(&dev->vdev), + VIRTIO_MEM_REQUESTED_SIZE_PROP); +} + +static const VirtioPCIDeviceTypeInfo virtio_mem_pci_info = { + .base_name = TYPE_VIRTIO_MEM_PCI, + .generic_name = "virtio-mem-pci", + .instance_size = sizeof(VirtIOMEMPCI), + .instance_init = virtio_mem_pci_instance_init, + .class_init = virtio_mem_pci_class_init, + .interfaces = (InterfaceInfo[]) { + { TYPE_MEMORY_DEVICE }, + { } + }, +}; + +static void virtio_mem_pci_register_types(void) +{ + virtio_pci_types_register(&virtio_mem_pci_info); +} +type_init(virtio_mem_pci_register_types) diff --git a/hw/virtio/virtio-mem-pci.h b/hw/virtio/virtio-mem-pci.h new file mode 100644 index 0000000000..b51a28b275 --- /dev/null +++ b/hw/virtio/virtio-mem-pci.h @@ -0,0 +1,34 @@ +/* + * Virtio MEM PCI device + * + * Copyright (C) 2020 Red Hat, Inc. + * + * Authors: + * David Hildenbrand <david@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. + * See the COPYING file in the top-level directory. + */ + +#ifndef QEMU_VIRTIO_MEM_PCI_H +#define QEMU_VIRTIO_MEM_PCI_H + +#include "hw/virtio/virtio-pci.h" +#include "hw/virtio/virtio-mem.h" + +typedef struct VirtIOMEMPCI VirtIOMEMPCI; + +/* + * virtio-mem-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VIRTIO_MEM_PCI "virtio-mem-pci-base" +#define VIRTIO_MEM_PCI(obj) \ + OBJECT_CHECK(VirtIOMEMPCI, (obj), TYPE_VIRTIO_MEM_PCI) + +struct VirtIOMEMPCI { + VirtIOPCIProxy parent_obj; + VirtIOMEM vdev; + Notifier size_change_notifier; +}; + +#endif /* QEMU_VIRTIO_MEM_PCI_H */ diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c new file mode 100644 index 0000000000..65850530e7 --- /dev/null +++ b/hw/virtio/virtio-mem.c @@ -0,0 +1,873 @@ +/* + * Virtio MEM device + * + * Copyright (C) 2020 Red Hat, Inc. + * + * Authors: + * David Hildenbrand <david@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/iov.h" +#include "qemu/cutils.h" +#include "qemu/error-report.h" +#include "qemu/units.h" +#include "sysemu/numa.h" +#include "sysemu/sysemu.h" +#include "sysemu/reset.h" +#include "hw/virtio/virtio.h" +#include "hw/virtio/virtio-bus.h" +#include "hw/virtio/virtio-access.h" +#include "hw/virtio/virtio-mem.h" +#include "qapi/error.h" +#include "qapi/visitor.h" +#include "exec/ram_addr.h" +#include "migration/misc.h" +#include "hw/boards.h" +#include "hw/qdev-properties.h" +#include "config-devices.h" +#include "trace.h" + +/* + * Use QEMU_VMALLOC_ALIGN, so no THP will have to be split when unplugging + * memory (e.g., 2MB on x86_64). + */ +#define VIRTIO_MEM_MIN_BLOCK_SIZE QEMU_VMALLOC_ALIGN +/* + * Size the usable region bigger than the requested size if possible. Esp. + * Linux guests will only add (aligned) memory blocks in case they fully + * fit into the usable region, but plug+online only a subset of the pages. + * The memory block size corresponds mostly to the section size. + * + * This allows e.g., to add 20MB with a section size of 128MB on x86_64, and + * a section size of 1GB on arm64 (as long as the start address is properly + * aligned, similar to ordinary DIMMs). + * + * We can change this at any time and maybe even make it configurable if + * necessary (as the section size can change). But it's more likely that the + * section size will rather get smaller and not bigger over time. + */ +#if defined(TARGET_X86_64) || defined(TARGET_I386) +#define VIRTIO_MEM_USABLE_EXTENT (2 * (128 * MiB)) +#else +#error VIRTIO_MEM_USABLE_EXTENT not defined +#endif + +static bool virtio_mem_is_busy(void) +{ + /* + * Postcopy cannot handle concurrent discards and we don't want to migrate + * pages on-demand with stale content when plugging new blocks. + * + * For precopy, we don't want unplugged blocks in our migration stream, and + * when plugging new blocks, the page content might differ between source + * and destination (observable by the guest when not initializing pages + * after plugging them) until we're running on the destination (as we didn't + * migrate these blocks when they were unplugged). + */ + return migration_in_incoming_postcopy() || !migration_is_idle(); +} + +static bool virtio_mem_test_bitmap(VirtIOMEM *vmem, uint64_t start_gpa, + uint64_t size, bool plugged) +{ + const unsigned long first_bit = (start_gpa - vmem->addr) / vmem->block_size; + const unsigned long last_bit = first_bit + (size / vmem->block_size) - 1; + unsigned long found_bit; + + /* We fake a shorter bitmap to avoid searching too far. */ + if (plugged) { + found_bit = find_next_zero_bit(vmem->bitmap, last_bit + 1, first_bit); + } else { + found_bit = find_next_bit(vmem->bitmap, last_bit + 1, first_bit); + } + return found_bit > last_bit; +} + +static void virtio_mem_set_bitmap(VirtIOMEM *vmem, uint64_t start_gpa, + uint64_t size, bool plugged) +{ + const unsigned long bit = (start_gpa - vmem->addr) / vmem->block_size; + const unsigned long nbits = size / vmem->block_size; + + if (plugged) { + bitmap_set(vmem->bitmap, bit, nbits); + } else { + bitmap_clear(vmem->bitmap, bit, nbits); + } +} + +static void virtio_mem_send_response(VirtIOMEM *vmem, VirtQueueElement *elem, + struct virtio_mem_resp *resp) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(vmem); + VirtQueue *vq = vmem->vq; + + trace_virtio_mem_send_response(le16_to_cpu(resp->type)); + iov_from_buf(elem->in_sg, elem->in_num, 0, resp, sizeof(*resp)); + + virtqueue_push(vq, elem, sizeof(*resp)); + virtio_notify(vdev, vq); +} + +static void virtio_mem_send_response_simple(VirtIOMEM *vmem, + VirtQueueElement *elem, + uint16_t type) +{ + struct virtio_mem_resp resp = { + .type = cpu_to_le16(type), + }; + + virtio_mem_send_response(vmem, elem, &resp); +} + +static bool virtio_mem_valid_range(VirtIOMEM *vmem, uint64_t gpa, uint64_t size) +{ + if (!QEMU_IS_ALIGNED(gpa, vmem->block_size)) { + return false; + } + if (gpa + size < gpa || !size) { + return false; + } + if (gpa < vmem->addr || gpa >= vmem->addr + vmem->usable_region_size) { + return false; + } + if (gpa + size > vmem->addr + vmem->usable_region_size) { + return false; + } + return true; +} + +static int virtio_mem_set_block_state(VirtIOMEM *vmem, uint64_t start_gpa, + uint64_t size, bool plug) +{ + const uint64_t offset = start_gpa - vmem->addr; + int ret; + + if (virtio_mem_is_busy()) { + return -EBUSY; + } + + if (!plug) { + ret = ram_block_discard_range(vmem->memdev->mr.ram_block, offset, size); + if (ret) { + error_report("Unexpected error discarding RAM: %s", + strerror(-ret)); + return -EBUSY; + } + } + virtio_mem_set_bitmap(vmem, start_gpa, size, plug); + return 0; +} + +static int virtio_mem_state_change_request(VirtIOMEM *vmem, uint64_t gpa, + uint16_t nb_blocks, bool plug) +{ + const uint64_t size = nb_blocks * vmem->block_size; + int ret; + + if (!virtio_mem_valid_range(vmem, gpa, size)) { + return VIRTIO_MEM_RESP_ERROR; + } + + if (plug && (vmem->size + size > vmem->requested_size)) { + return VIRTIO_MEM_RESP_NACK; + } + + /* test if really all blocks are in the opposite state */ + if (!virtio_mem_test_bitmap(vmem, gpa, size, !plug)) { + return VIRTIO_MEM_RESP_ERROR; + } + + ret = virtio_mem_set_block_state(vmem, gpa, size, plug); + if (ret) { + return VIRTIO_MEM_RESP_BUSY; + } + if (plug) { + vmem->size += size; + } else { + vmem->size -= size; + } + notifier_list_notify(&vmem->size_change_notifiers, &vmem->size); + return VIRTIO_MEM_RESP_ACK; +} + +static void virtio_mem_plug_request(VirtIOMEM *vmem, VirtQueueElement *elem, + struct virtio_mem_req *req) +{ + const uint64_t gpa = le64_to_cpu(req->u.plug.addr); + const uint16_t nb_blocks = le16_to_cpu(req->u.plug.nb_blocks); + uint16_t type; + + trace_virtio_mem_plug_request(gpa, nb_blocks); + type = virtio_mem_state_change_request(vmem, gpa, nb_blocks, true); + virtio_mem_send_response_simple(vmem, elem, type); +} + +static void virtio_mem_unplug_request(VirtIOMEM *vmem, VirtQueueElement *elem, + struct virtio_mem_req *req) +{ + const uint64_t gpa = le64_to_cpu(req->u.unplug.addr); + const uint16_t nb_blocks = le16_to_cpu(req->u.unplug.nb_blocks); + uint16_t type; + + trace_virtio_mem_unplug_request(gpa, nb_blocks); + type = virtio_mem_state_change_request(vmem, gpa, nb_blocks, false); + virtio_mem_send_response_simple(vmem, elem, type); +} + +static void virtio_mem_resize_usable_region(VirtIOMEM *vmem, + uint64_t requested_size, + bool can_shrink) +{ + uint64_t newsize = MIN(memory_region_size(&vmem->memdev->mr), + requested_size + VIRTIO_MEM_USABLE_EXTENT); + + if (!requested_size) { + newsize = 0; + } + + if (newsize < vmem->usable_region_size && !can_shrink) { + return; + } + + trace_virtio_mem_resized_usable_region(vmem->usable_region_size, newsize); + vmem->usable_region_size = newsize; +} + +static int virtio_mem_unplug_all(VirtIOMEM *vmem) +{ + RAMBlock *rb = vmem->memdev->mr.ram_block; + int ret; + + if (virtio_mem_is_busy()) { + return -EBUSY; + } + + ret = ram_block_discard_range(rb, 0, qemu_ram_get_used_length(rb)); + if (ret) { + error_report("Unexpected error discarding RAM: %s", strerror(-ret)); + return -EBUSY; + } + bitmap_clear(vmem->bitmap, 0, vmem->bitmap_size); + if (vmem->size) { + vmem->size = 0; + notifier_list_notify(&vmem->size_change_notifiers, &vmem->size); + } + trace_virtio_mem_unplugged_all(); + virtio_mem_resize_usable_region(vmem, vmem->requested_size, true); + return 0; +} + +static void virtio_mem_unplug_all_request(VirtIOMEM *vmem, + VirtQueueElement *elem) +{ + trace_virtio_mem_unplug_all_request(); + if (virtio_mem_unplug_all(vmem)) { + virtio_mem_send_response_simple(vmem, elem, VIRTIO_MEM_RESP_BUSY); + } else { + virtio_mem_send_response_simple(vmem, elem, VIRTIO_MEM_RESP_ACK); + } +} + +static void virtio_mem_state_request(VirtIOMEM *vmem, VirtQueueElement *elem, + struct virtio_mem_req *req) +{ + const uint16_t nb_blocks = le16_to_cpu(req->u.state.nb_blocks); + const uint64_t gpa = le64_to_cpu(req->u.state.addr); + const uint64_t size = nb_blocks * vmem->block_size; + struct virtio_mem_resp resp = { + .type = cpu_to_le16(VIRTIO_MEM_RESP_ACK), + }; + + trace_virtio_mem_state_request(gpa, nb_blocks); + if (!virtio_mem_valid_range(vmem, gpa, size)) { + virtio_mem_send_response_simple(vmem, elem, VIRTIO_MEM_RESP_ERROR); + return; + } + + if (virtio_mem_test_bitmap(vmem, gpa, size, true)) { + resp.u.state.state = cpu_to_le16(VIRTIO_MEM_STATE_PLUGGED); + } else if (virtio_mem_test_bitmap(vmem, gpa, size, false)) { + resp.u.state.state = cpu_to_le16(VIRTIO_MEM_STATE_UNPLUGGED); + } else { + resp.u.state.state = cpu_to_le16(VIRTIO_MEM_STATE_MIXED); + } + trace_virtio_mem_state_response(le16_to_cpu(resp.u.state.state)); + virtio_mem_send_response(vmem, elem, &resp); +} + +static void virtio_mem_handle_request(VirtIODevice *vdev, VirtQueue *vq) +{ + const int len = sizeof(struct virtio_mem_req); + VirtIOMEM *vmem = VIRTIO_MEM(vdev); + VirtQueueElement *elem; + struct virtio_mem_req req; + uint16_t type; + + while (true) { + elem = virtqueue_pop(vq, sizeof(VirtQueueElement)); + if (!elem) { + return; + } + + if (iov_to_buf(elem->out_sg, elem->out_num, 0, &req, len) < len) { + virtio_error(vdev, "virtio-mem protocol violation: invalid request" + " size: %d", len); + g_free(elem); + return; + } + + if (iov_size(elem->in_sg, elem->in_num) < + sizeof(struct virtio_mem_resp)) { + virtio_error(vdev, "virtio-mem protocol violation: not enough space" + " for response: %zu", + iov_size(elem->in_sg, elem->in_num)); + g_free(elem); + return; + } + + type = le16_to_cpu(req.type); + switch (type) { + case VIRTIO_MEM_REQ_PLUG: + virtio_mem_plug_request(vmem, elem, &req); + break; + case VIRTIO_MEM_REQ_UNPLUG: + virtio_mem_unplug_request(vmem, elem, &req); + break; + case VIRTIO_MEM_REQ_UNPLUG_ALL: + virtio_mem_unplug_all_request(vmem, elem); + break; + case VIRTIO_MEM_REQ_STATE: + virtio_mem_state_request(vmem, elem, &req); + break; + default: + virtio_error(vdev, "virtio-mem protocol violation: unknown request" + " type: %d", type); + g_free(elem); + return; + } + + g_free(elem); + } +} + +static void virtio_mem_get_config(VirtIODevice *vdev, uint8_t *config_data) +{ + VirtIOMEM *vmem = VIRTIO_MEM(vdev); + struct virtio_mem_config *config = (void *) config_data; + + config->block_size = cpu_to_le64(vmem->block_size); + config->node_id = cpu_to_le16(vmem->node); + config->requested_size = cpu_to_le64(vmem->requested_size); + config->plugged_size = cpu_to_le64(vmem->size); + config->addr = cpu_to_le64(vmem->addr); + config->region_size = cpu_to_le64(memory_region_size(&vmem->memdev->mr)); + config->usable_region_size = cpu_to_le64(vmem->usable_region_size); +} + +static uint64_t virtio_mem_get_features(VirtIODevice *vdev, uint64_t features, + Error **errp) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + + if (ms->numa_state) { +#if defined(CONFIG_ACPI) + virtio_add_feature(&features, VIRTIO_MEM_F_ACPI_PXM); +#endif + } + return features; +} + +static void virtio_mem_system_reset(void *opaque) +{ + VirtIOMEM *vmem = VIRTIO_MEM(opaque); + + /* + * During usual resets, we will unplug all memory and shrink the usable + * region size. This is, however, not possible in all scenarios. Then, + * the guest has to deal with this manually (VIRTIO_MEM_REQ_UNPLUG_ALL). + */ + virtio_mem_unplug_all(vmem); +} + +static void virtio_mem_device_realize(DeviceState *dev, Error **errp) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + int nb_numa_nodes = ms->numa_state ? ms->numa_state->num_nodes : 0; + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VirtIOMEM *vmem = VIRTIO_MEM(dev); + uint64_t page_size; + RAMBlock *rb; + int ret; + + if (!vmem->memdev) { + error_setg(errp, "'%s' property is not set", VIRTIO_MEM_MEMDEV_PROP); + return; + } else if (host_memory_backend_is_mapped(vmem->memdev)) { + char *path = object_get_canonical_path_component(OBJECT(vmem->memdev)); + + error_setg(errp, "'%s' property specifies a busy memdev: %s", + VIRTIO_MEM_MEMDEV_PROP, path); + g_free(path); + return; + } else if (!memory_region_is_ram(&vmem->memdev->mr) || + memory_region_is_rom(&vmem->memdev->mr) || + !vmem->memdev->mr.ram_block) { + error_setg(errp, "'%s' property specifies an unsupported memdev", + VIRTIO_MEM_MEMDEV_PROP); + return; + } + + if ((nb_numa_nodes && vmem->node >= nb_numa_nodes) || + (!nb_numa_nodes && vmem->node)) { + error_setg(errp, "'%s' property has value '%" PRIu32 "', which exceeds" + "the number of numa nodes: %d", VIRTIO_MEM_NODE_PROP, + vmem->node, nb_numa_nodes ? nb_numa_nodes : 1); + return; + } + + if (enable_mlock) { + error_setg(errp, "Incompatible with mlock"); + return; + } + + rb = vmem->memdev->mr.ram_block; + page_size = qemu_ram_pagesize(rb); + + if (vmem->block_size < page_size) { + error_setg(errp, "'%s' property has to be at least the page size (0x%" + PRIx64 ")", VIRTIO_MEM_BLOCK_SIZE_PROP, page_size); + return; + } else if (!QEMU_IS_ALIGNED(vmem->requested_size, vmem->block_size)) { + error_setg(errp, "'%s' property has to be multiples of '%s' (0x%" PRIx64 + ")", VIRTIO_MEM_REQUESTED_SIZE_PROP, + VIRTIO_MEM_BLOCK_SIZE_PROP, vmem->block_size); + return; + } else if (!QEMU_IS_ALIGNED(memory_region_size(&vmem->memdev->mr), + vmem->block_size)) { + error_setg(errp, "'%s' property memdev size has to be multiples of" + "'%s' (0x%" PRIx64 ")", VIRTIO_MEM_MEMDEV_PROP, + VIRTIO_MEM_BLOCK_SIZE_PROP, vmem->block_size); + return; + } + + if (ram_block_discard_require(true)) { + error_setg(errp, "Discarding RAM is disabled"); + return; + } + + ret = ram_block_discard_range(rb, 0, qemu_ram_get_used_length(rb)); + if (ret) { + error_setg_errno(errp, -ret, "Unexpected error discarding RAM"); + ram_block_discard_require(false); + return; + } + + virtio_mem_resize_usable_region(vmem, vmem->requested_size, true); + + vmem->bitmap_size = memory_region_size(&vmem->memdev->mr) / + vmem->block_size; + vmem->bitmap = bitmap_new(vmem->bitmap_size); + + virtio_init(vdev, TYPE_VIRTIO_MEM, VIRTIO_ID_MEM, + sizeof(struct virtio_mem_config)); + vmem->vq = virtio_add_queue(vdev, 128, virtio_mem_handle_request); + + host_memory_backend_set_mapped(vmem->memdev, true); + vmstate_register_ram(&vmem->memdev->mr, DEVICE(vmem)); + qemu_register_reset(virtio_mem_system_reset, vmem); + precopy_add_notifier(&vmem->precopy_notifier); +} + +static void virtio_mem_device_unrealize(DeviceState *dev) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VirtIOMEM *vmem = VIRTIO_MEM(dev); + + precopy_remove_notifier(&vmem->precopy_notifier); + qemu_unregister_reset(virtio_mem_system_reset, vmem); + vmstate_unregister_ram(&vmem->memdev->mr, DEVICE(vmem)); + host_memory_backend_set_mapped(vmem->memdev, false); + virtio_del_queue(vdev, 0); + virtio_cleanup(vdev); + g_free(vmem->bitmap); + ram_block_discard_require(false); +} + +static int virtio_mem_restore_unplugged(VirtIOMEM *vmem) +{ + RAMBlock *rb = vmem->memdev->mr.ram_block; + unsigned long first_zero_bit, last_zero_bit; + uint64_t offset, length; + int ret; + + /* Find consecutive unplugged blocks and discard the consecutive range. */ + first_zero_bit = find_first_zero_bit(vmem->bitmap, vmem->bitmap_size); + while (first_zero_bit < vmem->bitmap_size) { + offset = first_zero_bit * vmem->block_size; + last_zero_bit = find_next_bit(vmem->bitmap, vmem->bitmap_size, + first_zero_bit + 1) - 1; + length = (last_zero_bit - first_zero_bit + 1) * vmem->block_size; + + ret = ram_block_discard_range(rb, offset, length); + if (ret) { + error_report("Unexpected error discarding RAM: %s", + strerror(-ret)); + return -EINVAL; + } + first_zero_bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size, + last_zero_bit + 2); + } + return 0; +} + +static int virtio_mem_post_load(void *opaque, int version_id) +{ + if (migration_in_incoming_postcopy()) { + return 0; + } + + return virtio_mem_restore_unplugged(VIRTIO_MEM(opaque)); +} + +typedef struct VirtIOMEMMigSanityChecks { + VirtIOMEM *parent; + uint64_t addr; + uint64_t region_size; + uint64_t block_size; + uint32_t node; +} VirtIOMEMMigSanityChecks; + +static int virtio_mem_mig_sanity_checks_pre_save(void *opaque) +{ + VirtIOMEMMigSanityChecks *tmp = opaque; + VirtIOMEM *vmem = tmp->parent; + + tmp->addr = vmem->addr; + tmp->region_size = memory_region_size(&vmem->memdev->mr); + tmp->block_size = vmem->block_size; + tmp->node = vmem->node; + return 0; +} + +static int virtio_mem_mig_sanity_checks_post_load(void *opaque, int version_id) +{ + VirtIOMEMMigSanityChecks *tmp = opaque; + VirtIOMEM *vmem = tmp->parent; + const uint64_t new_region_size = memory_region_size(&vmem->memdev->mr); + + if (tmp->addr != vmem->addr) { + error_report("Property '%s' changed from 0x%" PRIx64 " to 0x%" PRIx64, + VIRTIO_MEM_ADDR_PROP, tmp->addr, vmem->addr); + return -EINVAL; + } + /* + * Note: Preparation for resizeable memory regions. The maximum size + * of the memory region must not change during migration. + */ + if (tmp->region_size != new_region_size) { + error_report("Property '%s' size changed from 0x%" PRIx64 " to 0x%" + PRIx64, VIRTIO_MEM_MEMDEV_PROP, tmp->region_size, + new_region_size); + return -EINVAL; + } + if (tmp->block_size != vmem->block_size) { + error_report("Property '%s' changed from 0x%" PRIx64 " to 0x%" PRIx64, + VIRTIO_MEM_BLOCK_SIZE_PROP, tmp->block_size, + vmem->block_size); + return -EINVAL; + } + if (tmp->node != vmem->node) { + error_report("Property '%s' changed from %" PRIu32 " to %" PRIu32, + VIRTIO_MEM_NODE_PROP, tmp->node, vmem->node); + return -EINVAL; + } + return 0; +} + +static const VMStateDescription vmstate_virtio_mem_sanity_checks = { + .name = "virtio-mem-device/sanity-checks", + .pre_save = virtio_mem_mig_sanity_checks_pre_save, + .post_load = virtio_mem_mig_sanity_checks_post_load, + .fields = (VMStateField[]) { + VMSTATE_UINT64(addr, VirtIOMEMMigSanityChecks), + VMSTATE_UINT64(region_size, VirtIOMEMMigSanityChecks), + VMSTATE_UINT64(block_size, VirtIOMEMMigSanityChecks), + VMSTATE_UINT32(node, VirtIOMEMMigSanityChecks), + VMSTATE_END_OF_LIST(), + }, +}; + +static const VMStateDescription vmstate_virtio_mem_device = { + .name = "virtio-mem-device", + .minimum_version_id = 1, + .version_id = 1, + .post_load = virtio_mem_post_load, + .fields = (VMStateField[]) { + VMSTATE_WITH_TMP(VirtIOMEM, VirtIOMEMMigSanityChecks, + vmstate_virtio_mem_sanity_checks), + VMSTATE_UINT64(usable_region_size, VirtIOMEM), + VMSTATE_UINT64(size, VirtIOMEM), + VMSTATE_UINT64(requested_size, VirtIOMEM), + VMSTATE_BITMAP(bitmap, VirtIOMEM, 0, bitmap_size), + VMSTATE_END_OF_LIST() + }, +}; + +static const VMStateDescription vmstate_virtio_mem = { + .name = "virtio-mem", + .minimum_version_id = 1, + .version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_VIRTIO_DEVICE, + VMSTATE_END_OF_LIST() + }, +}; + +static void virtio_mem_fill_device_info(const VirtIOMEM *vmem, + VirtioMEMDeviceInfo *vi) +{ + vi->memaddr = vmem->addr; + vi->node = vmem->node; + vi->requested_size = vmem->requested_size; + vi->size = vmem->size; + vi->max_size = memory_region_size(&vmem->memdev->mr); + vi->block_size = vmem->block_size; + vi->memdev = object_get_canonical_path(OBJECT(vmem->memdev)); +} + +static MemoryRegion *virtio_mem_get_memory_region(VirtIOMEM *vmem, Error **errp) +{ + if (!vmem->memdev) { + error_setg(errp, "'%s' property must be set", VIRTIO_MEM_MEMDEV_PROP); + return NULL; + } + + return &vmem->memdev->mr; +} + +static void virtio_mem_add_size_change_notifier(VirtIOMEM *vmem, + Notifier *notifier) +{ + notifier_list_add(&vmem->size_change_notifiers, notifier); +} + +static void virtio_mem_remove_size_change_notifier(VirtIOMEM *vmem, + Notifier *notifier) +{ + notifier_remove(notifier); +} + +static void virtio_mem_get_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + const VirtIOMEM *vmem = VIRTIO_MEM(obj); + uint64_t value = vmem->size; + + visit_type_size(v, name, &value, errp); +} + +static void virtio_mem_get_requested_size(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + const VirtIOMEM *vmem = VIRTIO_MEM(obj); + uint64_t value = vmem->requested_size; + + visit_type_size(v, name, &value, errp); +} + +static void virtio_mem_set_requested_size(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + VirtIOMEM *vmem = VIRTIO_MEM(obj); + Error *err = NULL; + uint64_t value; + + visit_type_size(v, name, &value, &err); + if (err) { + error_propagate(errp, err); + return; + } + + /* + * The block size and memory backend are not fixed until the device was + * realized. realize() will verify these properties then. + */ + if (DEVICE(obj)->realized) { + if (!QEMU_IS_ALIGNED(value, vmem->block_size)) { + error_setg(errp, "'%s' has to be multiples of '%s' (0x%" PRIx64 + ")", name, VIRTIO_MEM_BLOCK_SIZE_PROP, + vmem->block_size); + return; + } else if (value > memory_region_size(&vmem->memdev->mr)) { + error_setg(errp, "'%s' cannot exceed the memory backend size" + "(0x%" PRIx64 ")", name, + memory_region_size(&vmem->memdev->mr)); + return; + } + + if (value != vmem->requested_size) { + virtio_mem_resize_usable_region(vmem, value, false); + vmem->requested_size = value; + } + /* + * Trigger a config update so the guest gets notified. We trigger + * even if the size didn't change (especially helpful for debugging). + */ + virtio_notify_config(VIRTIO_DEVICE(vmem)); + } else { + vmem->requested_size = value; + } +} + +static void virtio_mem_get_block_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + const VirtIOMEM *vmem = VIRTIO_MEM(obj); + uint64_t value = vmem->block_size; + + visit_type_size(v, name, &value, errp); +} + +static void virtio_mem_set_block_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + VirtIOMEM *vmem = VIRTIO_MEM(obj); + Error *err = NULL; + uint64_t value; + + if (DEVICE(obj)->realized) { + error_setg(errp, "'%s' cannot be changed", name); + return; + } + + visit_type_size(v, name, &value, &err); + if (err) { + error_propagate(errp, err); + return; + } + + if (value < VIRTIO_MEM_MIN_BLOCK_SIZE) { + error_setg(errp, "'%s' property has to be at least 0x%" PRIx32, name, + VIRTIO_MEM_MIN_BLOCK_SIZE); + return; + } else if (!is_power_of_2(value)) { + error_setg(errp, "'%s' property has to be a power of two", name); + return; + } + vmem->block_size = value; +} + +static void virtio_mem_precopy_exclude_unplugged(VirtIOMEM *vmem) +{ + void * const host = qemu_ram_get_host_addr(vmem->memdev->mr.ram_block); + unsigned long first_zero_bit, last_zero_bit; + uint64_t offset, length; + + /* + * Find consecutive unplugged blocks and exclude them from migration. + * + * Note: Blocks cannot get (un)plugged during precopy, no locking needed. + */ + first_zero_bit = find_first_zero_bit(vmem->bitmap, vmem->bitmap_size); + while (first_zero_bit < vmem->bitmap_size) { + offset = first_zero_bit * vmem->block_size; + last_zero_bit = find_next_bit(vmem->bitmap, vmem->bitmap_size, + first_zero_bit + 1) - 1; + length = (last_zero_bit - first_zero_bit + 1) * vmem->block_size; + + qemu_guest_free_page_hint(host + offset, length); + first_zero_bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size, + last_zero_bit + 2); + } +} + +static int virtio_mem_precopy_notify(NotifierWithReturn *n, void *data) +{ + VirtIOMEM *vmem = container_of(n, VirtIOMEM, precopy_notifier); + PrecopyNotifyData *pnd = data; + + switch (pnd->reason) { + case PRECOPY_NOTIFY_SETUP: + precopy_enable_free_page_optimization(); + break; + case PRECOPY_NOTIFY_AFTER_BITMAP_SYNC: + virtio_mem_precopy_exclude_unplugged(vmem); + break; + default: + break; + } + + return 0; +} + +static void virtio_mem_instance_init(Object *obj) +{ + VirtIOMEM *vmem = VIRTIO_MEM(obj); + + vmem->block_size = VIRTIO_MEM_MIN_BLOCK_SIZE; + notifier_list_init(&vmem->size_change_notifiers); + vmem->precopy_notifier.notify = virtio_mem_precopy_notify; + + object_property_add(obj, VIRTIO_MEM_SIZE_PROP, "size", virtio_mem_get_size, + NULL, NULL, NULL); + object_property_add(obj, VIRTIO_MEM_REQUESTED_SIZE_PROP, "size", + virtio_mem_get_requested_size, + virtio_mem_set_requested_size, NULL, NULL); + object_property_add(obj, VIRTIO_MEM_BLOCK_SIZE_PROP, "size", + virtio_mem_get_block_size, virtio_mem_set_block_size, + NULL, NULL); +} + +static Property virtio_mem_properties[] = { + DEFINE_PROP_UINT64(VIRTIO_MEM_ADDR_PROP, VirtIOMEM, addr, 0), + DEFINE_PROP_UINT32(VIRTIO_MEM_NODE_PROP, VirtIOMEM, node, 0), + DEFINE_PROP_LINK(VIRTIO_MEM_MEMDEV_PROP, VirtIOMEM, memdev, + TYPE_MEMORY_BACKEND, HostMemoryBackend *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void virtio_mem_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); + VirtIOMEMClass *vmc = VIRTIO_MEM_CLASS(klass); + + device_class_set_props(dc, virtio_mem_properties); + dc->vmsd = &vmstate_virtio_mem; + + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + vdc->realize = virtio_mem_device_realize; + vdc->unrealize = virtio_mem_device_unrealize; + vdc->get_config = virtio_mem_get_config; + vdc->get_features = virtio_mem_get_features; + vdc->vmsd = &vmstate_virtio_mem_device; + + vmc->fill_device_info = virtio_mem_fill_device_info; + vmc->get_memory_region = virtio_mem_get_memory_region; + vmc->add_size_change_notifier = virtio_mem_add_size_change_notifier; + vmc->remove_size_change_notifier = virtio_mem_remove_size_change_notifier; +} + +static const TypeInfo virtio_mem_info = { + .name = TYPE_VIRTIO_MEM, + .parent = TYPE_VIRTIO_DEVICE, + .instance_size = sizeof(VirtIOMEM), + .instance_init = virtio_mem_instance_init, + .class_init = virtio_mem_class_init, + .class_size = sizeof(VirtIOMEMClass), +}; + +static void virtio_register_types(void) +{ + type_register_static(&virtio_mem_info); +} + +type_init(virtio_register_types) diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index 7bc8c1c056..8554cf2a03 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -1107,6 +1107,18 @@ static AddressSpace *virtio_pci_get_dma_as(DeviceState *d) return pci_get_address_space(dev); } +static bool virtio_pci_queue_enabled(DeviceState *d, int n) +{ + VirtIOPCIProxy *proxy = VIRTIO_PCI(d); + VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus); + + if (virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1)) { + return proxy->vqs[vdev->queue_sel].enabled; + } + + return virtio_queue_enabled(vdev, n); +} + static int virtio_pci_add_mem_cap(VirtIOPCIProxy *proxy, struct virtio_pci_cap *cap) { @@ -2064,6 +2076,7 @@ static void virtio_pci_bus_class_init(ObjectClass *klass, void *data) k->ioeventfd_enabled = virtio_pci_ioeventfd_enabled; k->ioeventfd_assign = virtio_pci_ioeventfd_assign; k->get_dma_as = virtio_pci_get_dma_as; + k->queue_enabled = virtio_pci_queue_enabled; } static const TypeInfo virtio_pci_bus_info = { diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index cc9c9dc162..5bd2a2f621 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -3286,6 +3286,12 @@ hwaddr virtio_queue_get_desc_addr(VirtIODevice *vdev, int n) bool virtio_queue_enabled(VirtIODevice *vdev, int n) { + BusState *qbus = qdev_get_parent_bus(DEVICE(vdev)); + VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); + + if (k->queue_enabled) { + return k->queue_enabled(qbus->parent, n); + } return virtio_queue_get_desc_addr(vdev, n) != 0; } |