diff options
Diffstat (limited to 'hw/virtio/virtio.c')
-rw-r--r-- | hw/virtio/virtio.c | 982 |
1 files changed, 637 insertions, 345 deletions
diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index 3a1f6c520c..fb6b4ccd83 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -13,13 +13,17 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" +#include "qapi/qapi-commands-virtio.h" #include "trace.h" +#include "qemu/defer-call.h" #include "qemu/error-report.h" #include "qemu/log.h" #include "qemu/main-loop.h" #include "qemu/module.h" +#include "qom/object_interfaces.h" +#include "hw/core/cpu.h" #include "hw/virtio/virtio.h" +#include "hw/virtio/vhost.h" #include "migration/qemu-file-types.h" #include "qemu/atomic.h" #include "hw/virtio/virtio-bus.h" @@ -27,7 +31,25 @@ #include "hw/virtio/virtio-access.h" #include "sysemu/dma.h" #include "sysemu/runstate.h" +#include "virtio-qmp.h" + #include "standard-headers/linux/virtio_ids.h" +#include "standard-headers/linux/vhost_types.h" +#include "standard-headers/linux/virtio_blk.h" +#include "standard-headers/linux/virtio_console.h" +#include "standard-headers/linux/virtio_gpu.h" +#include "standard-headers/linux/virtio_net.h" +#include "standard-headers/linux/virtio_scsi.h" +#include "standard-headers/linux/virtio_i2c.h" +#include "standard-headers/linux/virtio_balloon.h" +#include "standard-headers/linux/virtio_iommu.h" +#include "standard-headers/linux/virtio_mem.h" +#include "standard-headers/linux/virtio_vsock.h" + +/* + * Maximum size of virtio device config space + */ +#define VHOST_USER_MAX_CONFIG_SIZE 256 /* * The alignment to use between consumer and producer parts of vring. @@ -125,7 +147,6 @@ struct VirtQueue uint16_t vector; VirtIOHandleOutput handle_output; - VirtIOHandleAIOOutput handle_aio_output; VirtIODevice *vdev; EventNotifier guest_notifier; EventNotifier host_notifier; @@ -133,6 +154,56 @@ struct VirtQueue QLIST_ENTRY(VirtQueue) node; }; +const char *virtio_device_names[] = { + [VIRTIO_ID_NET] = "virtio-net", + [VIRTIO_ID_BLOCK] = "virtio-blk", + [VIRTIO_ID_CONSOLE] = "virtio-serial", + [VIRTIO_ID_RNG] = "virtio-rng", + [VIRTIO_ID_BALLOON] = "virtio-balloon", + [VIRTIO_ID_IOMEM] = "virtio-iomem", + [VIRTIO_ID_RPMSG] = "virtio-rpmsg", + [VIRTIO_ID_SCSI] = "virtio-scsi", + [VIRTIO_ID_9P] = "virtio-9p", + [VIRTIO_ID_MAC80211_WLAN] = "virtio-mac-wlan", + [VIRTIO_ID_RPROC_SERIAL] = "virtio-rproc-serial", + [VIRTIO_ID_CAIF] = "virtio-caif", + [VIRTIO_ID_MEMORY_BALLOON] = "virtio-mem-balloon", + [VIRTIO_ID_GPU] = "virtio-gpu", + [VIRTIO_ID_CLOCK] = "virtio-clk", + [VIRTIO_ID_INPUT] = "virtio-input", + [VIRTIO_ID_VSOCK] = "vhost-vsock", + [VIRTIO_ID_CRYPTO] = "virtio-crypto", + [VIRTIO_ID_SIGNAL_DIST] = "virtio-signal", + [VIRTIO_ID_PSTORE] = "virtio-pstore", + [VIRTIO_ID_IOMMU] = "virtio-iommu", + [VIRTIO_ID_MEM] = "virtio-mem", + [VIRTIO_ID_SOUND] = "virtio-sound", + [VIRTIO_ID_FS] = "virtio-user-fs", + [VIRTIO_ID_PMEM] = "virtio-pmem", + [VIRTIO_ID_RPMB] = "virtio-rpmb", + [VIRTIO_ID_MAC80211_HWSIM] = "virtio-mac-hwsim", + [VIRTIO_ID_VIDEO_ENCODER] = "virtio-vid-encoder", + [VIRTIO_ID_VIDEO_DECODER] = "virtio-vid-decoder", + [VIRTIO_ID_SCMI] = "virtio-scmi", + [VIRTIO_ID_NITRO_SEC_MOD] = "virtio-nitro-sec-mod", + [VIRTIO_ID_I2C_ADAPTER] = "vhost-user-i2c", + [VIRTIO_ID_WATCHDOG] = "virtio-watchdog", + [VIRTIO_ID_CAN] = "virtio-can", + [VIRTIO_ID_DMABUF] = "virtio-dmabuf", + [VIRTIO_ID_PARAM_SERV] = "virtio-param-serv", + [VIRTIO_ID_AUDIO_POLICY] = "virtio-audio-pol", + [VIRTIO_ID_BT] = "virtio-bluetooth", + [VIRTIO_ID_GPIO] = "virtio-gpio" +}; + +static const char *virtio_id_to_name(uint16_t device_id) +{ + assert(device_id < G_N_ELEMENTS(virtio_device_names)); + const char *name = virtio_device_names[device_id]; + assert(name != NULL); + return name; +} + /* Called within call_rcu(). */ static void virtio_free_region_cache(VRingMemoryRegionCaches *caches) { @@ -154,7 +225,7 @@ static void virtio_virtqueue_reset_region_cache(struct VirtQueue *vq) } } -static void virtio_init_region_cache(VirtIODevice *vdev, int n) +void virtio_init_region_cache(VirtIODevice *vdev, int n) { VirtQueue *vq = &vdev->vq[n]; VRingMemoryRegionCaches *old = vq->vring.caches; @@ -247,13 +318,10 @@ static void vring_packed_event_read(VirtIODevice *vdev, hwaddr off_off = offsetof(VRingPackedDescEvent, off_wrap); hwaddr off_flags = offsetof(VRingPackedDescEvent, flags); - address_space_read_cached(cache, off_flags, &e->flags, - sizeof(e->flags)); + e->flags = virtio_lduw_phys_cached(vdev, cache, off_flags); /* Make sure flags is seen before off_wrap */ smp_rmb(); - address_space_read_cached(cache, off_off, &e->off_wrap, - sizeof(e->off_wrap)); - virtio_tswap16s(vdev, &e->off_wrap); + e->off_wrap = virtio_lduw_phys_cached(vdev, cache, off_off); virtio_tswap16s(vdev, &e->flags); } @@ -263,8 +331,7 @@ static void vring_packed_off_wrap_write(VirtIODevice *vdev, { hwaddr off = offsetof(VRingPackedDescEvent, off_wrap); - virtio_tswap16s(vdev, &off_wrap); - address_space_write_cached(cache, off, &off_wrap, sizeof(off_wrap)); + virtio_stw_phys_cached(vdev, cache, off, off_wrap); address_space_cache_invalidate(cache, off, sizeof(off_wrap)); } @@ -273,8 +340,7 @@ static void vring_packed_flags_write(VirtIODevice *vdev, { hwaddr off = offsetof(VRingPackedDescEvent, flags); - virtio_tswap16s(vdev, &flags); - address_space_write_cached(cache, off, &flags, sizeof(flags)); + virtio_stw_phys_cached(vdev, cache, off, flags); address_space_cache_invalidate(cache, off, sizeof(flags)); } @@ -347,6 +413,19 @@ static inline void vring_used_write(VirtQueue *vq, VRingUsedElem *uelem, address_space_cache_invalidate(&caches->used, pa, sizeof(VRingUsedElem)); } +/* Called within rcu_read_lock(). */ +static inline uint16_t vring_used_flags(VirtQueue *vq) +{ + VRingMemoryRegionCaches *caches = vring_get_region_caches(vq); + hwaddr pa = offsetof(VRingUsed, flags); + + if (!caches) { + return 0; + } + + return virtio_lduw_phys_cached(vq->vdev, &caches->used, pa); +} + /* Called within rcu_read_lock(). */ static uint16_t vring_used_idx(VirtQueue *vq) { @@ -507,11 +586,9 @@ static void vring_packed_desc_read_flags(VirtIODevice *vdev, MemoryRegionCache *cache, int i) { - address_space_read_cached(cache, - i * sizeof(VRingPackedDesc) + - offsetof(VRingPackedDesc, flags), - flags, sizeof(*flags)); - virtio_tswap16s(vdev, flags); + hwaddr off = i * sizeof(VRingPackedDesc) + offsetof(VRingPackedDesc, flags); + + *flags = virtio_lduw_phys_cached(vdev, cache, off); } static void vring_packed_desc_read(VirtIODevice *vdev, @@ -564,8 +641,7 @@ static void vring_packed_desc_write_flags(VirtIODevice *vdev, { hwaddr off = i * sizeof(VRingPackedDesc) + offsetof(VRingPackedDesc, flags); - virtio_tswap16s(vdev, &desc->flags); - address_space_write_cached(cache, off, &desc->flags, sizeof(desc->flags)); + virtio_stw_phys_cached(vdev, cache, off, desc->flags); address_space_cache_invalidate(cache, off, sizeof(desc->flags)); } @@ -893,6 +969,7 @@ static void virtqueue_packed_flush(VirtQueue *vq, unsigned int count) if (vq->used_idx >= vq->vring.num) { vq->used_idx -= vq->vring.num; vq->used_wrap_counter ^= 1; + vq->signalled_used_valid = false; } } @@ -921,7 +998,12 @@ void virtqueue_push(VirtQueue *vq, const VirtQueueElement *elem, /* Called within rcu_read_lock(). */ static int virtqueue_num_heads(VirtQueue *vq, unsigned int idx) { - uint16_t num_heads = vring_avail_idx(vq) - idx; + uint16_t avail_idx, num_heads; + + /* Use shadow index whenever possible. */ + avail_idx = (vq->shadow_avail_idx != idx) ? vq->shadow_avail_idx + : vring_avail_idx(vq); + num_heads = avail_idx - idx; /* Check it isn't doing very strange things with descriptor numbers. */ if (num_heads > vq->vring.num) { @@ -929,8 +1011,15 @@ static int virtqueue_num_heads(VirtQueue *vq, unsigned int idx) idx, vq->shadow_avail_idx); return -EINVAL; } - /* On success, callers read a descriptor at vq->last_avail_idx. - * Make sure descriptor read does not bypass avail index read. */ + /* + * On success, callers read a descriptor at vq->last_avail_idx. + * Make sure descriptor read does not bypass avail index read. + * + * This is necessary even if we are using a shadow index, since + * the shadow index could have been initialized by calling + * vring_avail_idx() outside of this function, i.e., by a guest + * memory read not accompanied by a barrier. + */ if (num_heads) { smp_rmb(); } @@ -961,9 +1050,10 @@ enum { VIRTQUEUE_READ_DESC_MORE = 1, /* more buffers in chain */ }; +/* Reads the 'desc->next' descriptor into '*desc'. */ static int virtqueue_split_read_next_desc(VirtIODevice *vdev, VRingDesc *desc, MemoryRegionCache *desc_cache, - unsigned int max, unsigned int *next) + unsigned int max) { /* If this descriptor says it doesn't chain, we're done. */ if (!(desc->flags & VRING_DESC_F_NEXT)) { @@ -971,47 +1061,39 @@ static int virtqueue_split_read_next_desc(VirtIODevice *vdev, VRingDesc *desc, } /* Check they're not leading us off end of descriptors. */ - *next = desc->next; - /* Make sure compiler knows to grab that: we don't want it changing! */ - smp_wmb(); - - if (*next >= max) { - virtio_error(vdev, "Desc next is %u", *next); + if (desc->next >= max) { + virtio_error(vdev, "Desc next is %u", desc->next); return VIRTQUEUE_READ_DESC_ERROR; } - vring_split_desc_read(vdev, desc, desc_cache, *next); + vring_split_desc_read(vdev, desc, desc_cache, desc->next); return VIRTQUEUE_READ_DESC_MORE; } +/* Called within rcu_read_lock(). */ static void virtqueue_split_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes, unsigned int *out_bytes, - unsigned max_in_bytes, unsigned max_out_bytes) + unsigned max_in_bytes, unsigned max_out_bytes, + VRingMemoryRegionCaches *caches) { VirtIODevice *vdev = vq->vdev; - unsigned int max, idx; + unsigned int idx; unsigned int total_bufs, in_total, out_total; - VRingMemoryRegionCaches *caches; - MemoryRegionCache indirect_desc_cache = MEMORY_REGION_CACHE_INVALID; + MemoryRegionCache indirect_desc_cache; int64_t len = 0; int rc; - RCU_READ_LOCK_GUARD(); + address_space_cache_init_empty(&indirect_desc_cache); idx = vq->last_avail_idx; total_bufs = in_total = out_total = 0; - max = vq->vring.num; - caches = vring_get_region_caches(vq); - if (!caches) { - goto err; - } - while ((rc = virtqueue_num_heads(vq, idx)) > 0) { MemoryRegionCache *desc_cache = &caches->desc; unsigned int num_bufs; VRingDesc desc; unsigned int i; + unsigned int max = vq->vring.num; num_bufs = total_bufs; @@ -1064,7 +1146,7 @@ static void virtqueue_split_get_avail_bytes(VirtQueue *vq, goto done; } - rc = virtqueue_split_read_next_desc(vdev, &desc, desc_cache, max, &i); + rc = virtqueue_split_read_next_desc(vdev, &desc, desc_cache, max); } while (rc == VIRTQUEUE_READ_DESC_MORE); if (rc == VIRTQUEUE_READ_DESC_ERROR) { @@ -1124,39 +1206,37 @@ static int virtqueue_packed_read_next_desc(VirtQueue *vq, return VIRTQUEUE_READ_DESC_MORE; } +/* Called within rcu_read_lock(). */ static void virtqueue_packed_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes, unsigned int *out_bytes, unsigned max_in_bytes, - unsigned max_out_bytes) + unsigned max_out_bytes, + VRingMemoryRegionCaches *caches) { VirtIODevice *vdev = vq->vdev; - unsigned int max, idx; + unsigned int idx; unsigned int total_bufs, in_total, out_total; + MemoryRegionCache indirect_desc_cache; MemoryRegionCache *desc_cache; - VRingMemoryRegionCaches *caches; - MemoryRegionCache indirect_desc_cache = MEMORY_REGION_CACHE_INVALID; int64_t len = 0; VRingPackedDesc desc; bool wrap_counter; - RCU_READ_LOCK_GUARD(); + address_space_cache_init_empty(&indirect_desc_cache); + idx = vq->last_avail_idx; wrap_counter = vq->last_avail_wrap_counter; total_bufs = in_total = out_total = 0; - max = vq->vring.num; - caches = vring_get_region_caches(vq); - if (!caches) { - goto err; - } - for (;;) { unsigned int num_bufs = total_bufs; unsigned int i = idx; int rc; + unsigned int max = vq->vring.num; desc_cache = &caches->desc; + vring_packed_desc_read(vdev, &desc, desc_cache, idx, true); if (!is_desc_avail(desc.flags, wrap_counter)) { break; @@ -1250,6 +1330,8 @@ void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes, uint16_t desc_size; VRingMemoryRegionCaches *caches; + RCU_READ_LOCK_GUARD(); + if (unlikely(!vq->vring.desc)) { goto err; } @@ -1268,10 +1350,12 @@ void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes, if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) { virtqueue_packed_get_avail_bytes(vq, in_bytes, out_bytes, - max_in_bytes, max_out_bytes); + max_in_bytes, max_out_bytes, + caches); } else { virtqueue_split_get_avail_bytes(vq, in_bytes, out_bytes, - max_in_bytes, max_out_bytes); + max_in_bytes, max_out_bytes, + caches); } return; @@ -1319,7 +1403,8 @@ static bool virtqueue_map_desc(VirtIODevice *vdev, unsigned int *p_num_sg, iov[num_sg].iov_base = dma_memory_map(vdev->dma_as, pa, &len, is_write ? DMA_DIRECTION_FROM_DEVICE : - DMA_DIRECTION_TO_DEVICE); + DMA_DIRECTION_TO_DEVICE, + MEMTXATTRS_UNSPECIFIED); if (!iov[num_sg].iov_base) { virtio_error(vdev, "virtio: bogus descriptor or out of resources"); goto out; @@ -1368,7 +1453,8 @@ static void virtqueue_map_iovec(VirtIODevice *vdev, struct iovec *sg, sg[i].iov_base = dma_memory_map(vdev->dma_as, addr[i], &len, is_write ? DMA_DIRECTION_FROM_DEVICE : - DMA_DIRECTION_TO_DEVICE); + DMA_DIRECTION_TO_DEVICE, + MEMTXATTRS_UNSPECIFIED); if (!sg[i].iov_base) { error_report("virtio: error trying to map MMIO memory"); exit(1); @@ -1413,7 +1499,7 @@ static void *virtqueue_split_pop(VirtQueue *vq, size_t sz) { unsigned int i, head, max; VRingMemoryRegionCaches *caches; - MemoryRegionCache indirect_desc_cache = MEMORY_REGION_CACHE_INVALID; + MemoryRegionCache indirect_desc_cache; MemoryRegionCache *desc_cache; int64_t len; VirtIODevice *vdev = vq->vdev; @@ -1424,6 +1510,8 @@ static void *virtqueue_split_pop(VirtQueue *vq, size_t sz) VRingDesc desc; int rc; + address_space_cache_init_empty(&indirect_desc_cache); + RCU_READ_LOCK_GUARD(); if (virtio_queue_empty_rcu(vq)) { goto done; @@ -1513,7 +1601,7 @@ static void *virtqueue_split_pop(VirtQueue *vq, size_t sz) goto err_undo_map; } - rc = virtqueue_split_read_next_desc(vdev, &desc, desc_cache, max, &i); + rc = virtqueue_split_read_next_desc(vdev, &desc, desc_cache, max); } while (rc == VIRTQUEUE_READ_DESC_MORE); if (rc == VIRTQUEUE_READ_DESC_ERROR) { @@ -1550,7 +1638,7 @@ static void *virtqueue_packed_pop(VirtQueue *vq, size_t sz) { unsigned int i, max; VRingMemoryRegionCaches *caches; - MemoryRegionCache indirect_desc_cache = MEMORY_REGION_CACHE_INVALID; + MemoryRegionCache indirect_desc_cache; MemoryRegionCache *desc_cache; int64_t len; VirtIODevice *vdev = vq->vdev; @@ -1562,6 +1650,8 @@ static void *virtqueue_packed_pop(VirtQueue *vq, size_t sz) uint16_t id; int rc; + address_space_cache_init_empty(&indirect_desc_cache); + RCU_READ_LOCK_GUARD(); if (virtio_queue_packed_empty_rcu(vq)) { goto done; @@ -1703,6 +1793,8 @@ static unsigned int virtqueue_packed_drop_all(VirtQueue *vq) VirtIODevice *vdev = vq->vdev; VRingPackedDesc desc; + RCU_READ_LOCK_GUARD(); + caches = vring_get_region_caches(vq); if (!caches) { return 0; @@ -1978,6 +2070,58 @@ static enum virtio_device_endian virtio_current_cpu_endian(void) } } +static void __virtio_queue_reset(VirtIODevice *vdev, uint32_t i) +{ + vdev->vq[i].vring.desc = 0; + vdev->vq[i].vring.avail = 0; + vdev->vq[i].vring.used = 0; + vdev->vq[i].last_avail_idx = 0; + vdev->vq[i].shadow_avail_idx = 0; + vdev->vq[i].used_idx = 0; + vdev->vq[i].last_avail_wrap_counter = true; + vdev->vq[i].shadow_avail_wrap_counter = true; + vdev->vq[i].used_wrap_counter = true; + virtio_queue_set_vector(vdev, i, VIRTIO_NO_VECTOR); + vdev->vq[i].signalled_used = 0; + vdev->vq[i].signalled_used_valid = false; + vdev->vq[i].notification = true; + vdev->vq[i].vring.num = vdev->vq[i].vring.num_default; + vdev->vq[i].inuse = 0; + virtio_virtqueue_reset_region_cache(&vdev->vq[i]); +} + +void virtio_queue_reset(VirtIODevice *vdev, uint32_t queue_index) +{ + VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev); + + if (k->queue_reset) { + k->queue_reset(vdev, queue_index); + } + + __virtio_queue_reset(vdev, queue_index); +} + +void virtio_queue_enable(VirtIODevice *vdev, uint32_t queue_index) +{ + VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev); + + /* + * TODO: Seabios is currently out of spec and triggering this error. + * So this needs to be fixed in Seabios, then this can + * be re-enabled for new machine types only, and also after + * being converted to LOG_GUEST_ERROR. + * + if (!virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1)) { + error_report("queue_enable is only supported in devices of virtio " + "1.0 or later."); + } + */ + + if (k->queue_enable) { + k->queue_enable(vdev, queue_index); + } +} + void virtio_reset(void *opaque) { VirtIODevice *vdev = opaque; @@ -1993,6 +2137,10 @@ void virtio_reset(void *opaque) vdev->device_endian = virtio_default_endian(); } + if (vdev->vhost_started && k->get_vhost) { + vhost_reset_device(k->get_vhost(vdev)); + } + if (k->reset) { k->reset(vdev); } @@ -2009,211 +2157,7 @@ void virtio_reset(void *opaque) virtio_notify_vector(vdev, vdev->config_vector); for(i = 0; i < VIRTIO_QUEUE_MAX; i++) { - vdev->vq[i].vring.desc = 0; - vdev->vq[i].vring.avail = 0; - vdev->vq[i].vring.used = 0; - vdev->vq[i].last_avail_idx = 0; - vdev->vq[i].shadow_avail_idx = 0; - vdev->vq[i].used_idx = 0; - vdev->vq[i].last_avail_wrap_counter = true; - vdev->vq[i].shadow_avail_wrap_counter = true; - vdev->vq[i].used_wrap_counter = true; - virtio_queue_set_vector(vdev, i, VIRTIO_NO_VECTOR); - vdev->vq[i].signalled_used = 0; - vdev->vq[i].signalled_used_valid = false; - vdev->vq[i].notification = true; - vdev->vq[i].vring.num = vdev->vq[i].vring.num_default; - vdev->vq[i].inuse = 0; - virtio_virtqueue_reset_region_cache(&vdev->vq[i]); - } -} - -uint32_t virtio_config_readb(VirtIODevice *vdev, uint32_t addr) -{ - VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev); - uint8_t val; - - if (addr + sizeof(val) > vdev->config_len) { - return (uint32_t)-1; - } - - k->get_config(vdev, vdev->config); - - val = ldub_p(vdev->config + addr); - return val; -} - -uint32_t virtio_config_readw(VirtIODevice *vdev, uint32_t addr) -{ - VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev); - uint16_t val; - - if (addr + sizeof(val) > vdev->config_len) { - return (uint32_t)-1; - } - - k->get_config(vdev, vdev->config); - - val = lduw_p(vdev->config + addr); - return val; -} - -uint32_t virtio_config_readl(VirtIODevice *vdev, uint32_t addr) -{ - VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev); - uint32_t val; - - if (addr + sizeof(val) > vdev->config_len) { - return (uint32_t)-1; - } - - k->get_config(vdev, vdev->config); - - val = ldl_p(vdev->config + addr); - return val; -} - -void virtio_config_writeb(VirtIODevice *vdev, uint32_t addr, uint32_t data) -{ - VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev); - uint8_t val = data; - - if (addr + sizeof(val) > vdev->config_len) { - return; - } - - stb_p(vdev->config + addr, val); - - if (k->set_config) { - k->set_config(vdev, vdev->config); - } -} - -void virtio_config_writew(VirtIODevice *vdev, uint32_t addr, uint32_t data) -{ - VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev); - uint16_t val = data; - - if (addr + sizeof(val) > vdev->config_len) { - return; - } - - stw_p(vdev->config + addr, val); - - if (k->set_config) { - k->set_config(vdev, vdev->config); - } -} - -void virtio_config_writel(VirtIODevice *vdev, uint32_t addr, uint32_t data) -{ - VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev); - uint32_t val = data; - - if (addr + sizeof(val) > vdev->config_len) { - return; - } - - stl_p(vdev->config + addr, val); - - if (k->set_config) { - k->set_config(vdev, vdev->config); - } -} - -uint32_t virtio_config_modern_readb(VirtIODevice *vdev, uint32_t addr) -{ - VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev); - uint8_t val; - - if (addr + sizeof(val) > vdev->config_len) { - return (uint32_t)-1; - } - - k->get_config(vdev, vdev->config); - - val = ldub_p(vdev->config + addr); - return val; -} - -uint32_t virtio_config_modern_readw(VirtIODevice *vdev, uint32_t addr) -{ - VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev); - uint16_t val; - - if (addr + sizeof(val) > vdev->config_len) { - return (uint32_t)-1; - } - - k->get_config(vdev, vdev->config); - - val = lduw_le_p(vdev->config + addr); - return val; -} - -uint32_t virtio_config_modern_readl(VirtIODevice *vdev, uint32_t addr) -{ - VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev); - uint32_t val; - - if (addr + sizeof(val) > vdev->config_len) { - return (uint32_t)-1; - } - - k->get_config(vdev, vdev->config); - - val = ldl_le_p(vdev->config + addr); - return val; -} - -void virtio_config_modern_writeb(VirtIODevice *vdev, - uint32_t addr, uint32_t data) -{ - VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev); - uint8_t val = data; - - if (addr + sizeof(val) > vdev->config_len) { - return; - } - - stb_p(vdev->config + addr, val); - - if (k->set_config) { - k->set_config(vdev, vdev->config); - } -} - -void virtio_config_modern_writew(VirtIODevice *vdev, - uint32_t addr, uint32_t data) -{ - VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev); - uint16_t val = data; - - if (addr + sizeof(val) > vdev->config_len) { - return; - } - - stw_le_p(vdev->config + addr, val); - - if (k->set_config) { - k->set_config(vdev, vdev->config); - } -} - -void virtio_config_modern_writel(VirtIODevice *vdev, - uint32_t addr, uint32_t data) -{ - VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev); - uint32_t val = data; - - if (addr + sizeof(val) > vdev->config_len) { - return; - } - - stl_le_p(vdev->config + addr, val); - - if (k->set_config) { - k->set_config(vdev, vdev->config); + __virtio_queue_reset(vdev, i); } } @@ -2311,24 +2255,6 @@ void virtio_queue_set_align(VirtIODevice *vdev, int n, int align) } } -static bool virtio_queue_notify_aio_vq(VirtQueue *vq) -{ - bool ret = false; - - if (vq->vring.desc && vq->handle_aio_output) { - VirtIODevice *vdev = vq->vdev; - - trace_virtio_queue_notify(vdev, vq - vdev->vq, vq); - ret = vq->handle_aio_output(vdev, vq); - - if (unlikely(vdev->start_on_kick)) { - virtio_set_started(vdev, true); - } - } - - return ret; -} - static void virtio_queue_notify_vq(VirtQueue *vq) { if (vq->vring.desc && vq->handle_output) { @@ -2407,9 +2333,7 @@ VirtQueue *virtio_add_queue(VirtIODevice *vdev, int queue_size, vdev->vq[i].vring.num_default = queue_size; vdev->vq[i].vring.align = VIRTIO_PCI_VRING_ALIGN; vdev->vq[i].handle_output = handle_output; - vdev->vq[i].handle_aio_output = NULL; - vdev->vq[i].used_elems = g_malloc0(sizeof(VirtQueueElement) * - queue_size); + vdev->vq[i].used_elems = g_new0(VirtQueueElement, queue_size); return &vdev->vq[i]; } @@ -2419,7 +2343,6 @@ void virtio_delete_queue(VirtQueue *vq) vq->vring.num = 0; vq->vring.num_default = 0; vq->handle_output = NULL; - vq->handle_aio_output = NULL; g_free(vq->used_elems); vq->used_elems = NULL; virtio_virtqueue_reset_region_cache(vq); @@ -2523,6 +2446,16 @@ static bool virtio_should_notify(VirtIODevice *vdev, VirtQueue *vq) } } +/* Batch irqs while inside a defer_call_begin()/defer_call_end() section */ +static void virtio_notify_irqfd_deferred_fn(void *opaque) +{ + EventNotifier *notifier = opaque; + VirtQueue *vq = container_of(notifier, VirtQueue, guest_notifier); + + trace_virtio_notify_irqfd_deferred_fn(vq->vdev, vq); + event_notifier_set(notifier); +} + void virtio_notify_irqfd(VirtIODevice *vdev, VirtQueue *vq) { WITH_RCU_READ_LOCK_GUARD() { @@ -2549,7 +2482,7 @@ void virtio_notify_irqfd(VirtIODevice *vdev, VirtQueue *vq) * to an atomic operation. */ virtio_set_isr(vq->vdev, 0x1); - event_notifier_set(&vq->guest_notifier); + defer_call(virtio_notify_irqfd_deferred_fn, &vq->guest_notifier); } static void virtio_irq(VirtQueue *vq) @@ -2661,7 +2594,7 @@ static const VMStateDescription vmstate_virtqueue = { .name = "virtqueue_state", .version_id = 1, .minimum_version_id = 1, - .fields = (VMStateField[]) { + .fields = (const VMStateField[]) { VMSTATE_UINT64(vring.avail, struct VirtQueue), VMSTATE_UINT64(vring.used, struct VirtQueue), VMSTATE_END_OF_LIST() @@ -2672,7 +2605,7 @@ static const VMStateDescription vmstate_packed_virtqueue = { .name = "packed_virtqueue_state", .version_id = 1, .minimum_version_id = 1, - .fields = (VMStateField[]) { + .fields = (const VMStateField[]) { VMSTATE_UINT16(last_avail_idx, struct VirtQueue), VMSTATE_BOOL(last_avail_wrap_counter, struct VirtQueue), VMSTATE_UINT16(used_idx, struct VirtQueue), @@ -2687,7 +2620,7 @@ static const VMStateDescription vmstate_virtio_virtqueues = { .version_id = 1, .minimum_version_id = 1, .needed = &virtio_virtqueue_needed, - .fields = (VMStateField[]) { + .fields = (const VMStateField[]) { VMSTATE_STRUCT_VARRAY_POINTER_KNOWN(vq, struct VirtIODevice, VIRTIO_QUEUE_MAX, 0, vmstate_virtqueue, VirtQueue), VMSTATE_END_OF_LIST() @@ -2699,7 +2632,7 @@ static const VMStateDescription vmstate_virtio_packed_virtqueues = { .version_id = 1, .minimum_version_id = 1, .needed = &virtio_packed_virtqueue_needed, - .fields = (VMStateField[]) { + .fields = (const VMStateField[]) { VMSTATE_STRUCT_VARRAY_POINTER_KNOWN(vq, struct VirtIODevice, VIRTIO_QUEUE_MAX, 0, vmstate_packed_virtqueue, VirtQueue), VMSTATE_END_OF_LIST() @@ -2710,7 +2643,7 @@ static const VMStateDescription vmstate_ringsize = { .name = "ringsize_state", .version_id = 1, .minimum_version_id = 1, - .fields = (VMStateField[]) { + .fields = (const VMStateField[]) { VMSTATE_UINT32(vring.num_default, struct VirtQueue), VMSTATE_END_OF_LIST() } @@ -2721,7 +2654,7 @@ static const VMStateDescription vmstate_virtio_ringsize = { .version_id = 1, .minimum_version_id = 1, .needed = &virtio_ringsize_needed, - .fields = (VMStateField[]) { + .fields = (const VMStateField[]) { VMSTATE_STRUCT_VARRAY_POINTER_KNOWN(vq, struct VirtIODevice, VIRTIO_QUEUE_MAX, 0, vmstate_ringsize, VirtQueue), VMSTATE_END_OF_LIST() @@ -2764,7 +2697,7 @@ static const VMStateDescription vmstate_virtio_extra_state = { .version_id = 1, .minimum_version_id = 1, .needed = &virtio_extra_state_needed, - .fields = (VMStateField[]) { + .fields = (const VMStateField[]) { { .name = "extra_state", .version_id = 0, @@ -2783,7 +2716,7 @@ static const VMStateDescription vmstate_virtio_device_endian = { .version_id = 1, .minimum_version_id = 1, .needed = &virtio_device_endian_needed, - .fields = (VMStateField[]) { + .fields = (const VMStateField[]) { VMSTATE_UINT8(device_endian, VirtIODevice), VMSTATE_END_OF_LIST() } @@ -2794,7 +2727,7 @@ static const VMStateDescription vmstate_virtio_64bit_features = { .version_id = 1, .minimum_version_id = 1, .needed = &virtio_64bit_features_needed, - .fields = (VMStateField[]) { + .fields = (const VMStateField[]) { VMSTATE_UINT64(guest_features, VirtIODevice), VMSTATE_END_OF_LIST() } @@ -2805,7 +2738,7 @@ static const VMStateDescription vmstate_virtio_broken = { .version_id = 1, .minimum_version_id = 1, .needed = &virtio_broken_needed, - .fields = (VMStateField[]) { + .fields = (const VMStateField[]) { VMSTATE_BOOL(broken, VirtIODevice), VMSTATE_END_OF_LIST() } @@ -2816,7 +2749,7 @@ static const VMStateDescription vmstate_virtio_started = { .version_id = 1, .minimum_version_id = 1, .needed = &virtio_started_needed, - .fields = (VMStateField[]) { + .fields = (const VMStateField[]) { VMSTATE_BOOL(started, VirtIODevice), VMSTATE_END_OF_LIST() } @@ -2827,7 +2760,7 @@ static const VMStateDescription vmstate_virtio_disabled = { .version_id = 1, .minimum_version_id = 1, .needed = &virtio_disabled_needed, - .fields = (VMStateField[]) { + .fields = (const VMStateField[]) { VMSTATE_BOOL(disabled, VirtIODevice), VMSTATE_END_OF_LIST() } @@ -2837,11 +2770,10 @@ static const VMStateDescription vmstate_virtio = { .name = "virtio", .version_id = 1, .minimum_version_id = 1, - .minimum_version_id_old = 1, - .fields = (VMStateField[]) { + .fields = (const VMStateField[]) { VMSTATE_END_OF_LIST() }, - .subsections = (const VMStateDescription*[]) { + .subsections = (const VMStateDescription * const []) { &vmstate_virtio_device_endian, &vmstate_virtio_64bit_features, &vmstate_virtio_virtqueues, @@ -2923,8 +2855,9 @@ static int virtio_device_put(QEMUFile *f, void *opaque, size_t size, } /* A wrapper for use as a VMState .get function */ -static int virtio_device_get(QEMUFile *f, void *opaque, size_t size, - const VMStateField *field) +static int coroutine_mixed_fn +virtio_device_get(QEMUFile *f, void *opaque, size_t size, + const VMStateField *field) { VirtIODevice *vdev = VIRTIO_DEVICE(opaque); DeviceClass *dc = DEVICE_CLASS(VIRTIO_DEVICE_GET_CLASS(vdev)); @@ -2951,6 +2884,39 @@ static int virtio_set_features_nocheck(VirtIODevice *vdev, uint64_t val) return bad ? -1 : 0; } +typedef struct VirtioSetFeaturesNocheckData { + Coroutine *co; + VirtIODevice *vdev; + uint64_t val; + int ret; +} VirtioSetFeaturesNocheckData; + +static void virtio_set_features_nocheck_bh(void *opaque) +{ + VirtioSetFeaturesNocheckData *data = opaque; + + data->ret = virtio_set_features_nocheck(data->vdev, data->val); + aio_co_wake(data->co); +} + +static int coroutine_mixed_fn +virtio_set_features_nocheck_maybe_co(VirtIODevice *vdev, uint64_t val) +{ + if (qemu_in_coroutine()) { + VirtioSetFeaturesNocheckData data = { + .co = qemu_coroutine_self(), + .vdev = vdev, + .val = val, + }; + aio_bh_schedule_oneshot(qemu_get_current_aio_context(), + virtio_set_features_nocheck_bh, &data); + qemu_coroutine_yield(); + return data.ret; + } else { + return virtio_set_features_nocheck(vdev, val); + } +} + int virtio_set_features(VirtIODevice *vdev, uint64_t val) { int ret; @@ -2961,6 +2927,13 @@ int virtio_set_features(VirtIODevice *vdev, uint64_t val) if (vdev->status & VIRTIO_CONFIG_S_FEATURES_OK) { return -EINVAL; } + + if (val & (1ull << VIRTIO_F_BAD_FEATURE)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: guest driver for %s has enabled UNUSED(30) feature bit!\n", + __func__, vdev->name); + } + ret = virtio_set_features_nocheck(vdev, val); if (virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) { /* VIRTIO_RING_F_EVENT_IDX changes the size of the caches. */ @@ -2980,11 +2953,12 @@ int virtio_set_features(VirtIODevice *vdev, uint64_t val) return ret; } -size_t virtio_feature_get_config_size(const VirtIOFeature *feature_sizes, - uint64_t host_features) +size_t virtio_get_config_size(const VirtIOConfigSizeParams *params, + uint64_t host_features) { - size_t config_size = 0; - int i; + size_t config_size = params->min_size; + const VirtIOFeature *feature_sizes = params->feature_sizes; + size_t i; for (i = 0; feature_sizes[i].flags != 0; i++) { if (host_features & feature_sizes[i].flags) { @@ -2992,10 +2966,12 @@ size_t virtio_feature_get_config_size(const VirtIOFeature *feature_sizes, } } + assert(config_size <= params->max_size); return config_size; } -int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id) +int coroutine_mixed_fn +virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id) { int i, ret; int32_t config_len; @@ -3112,14 +3088,14 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id) * host_features. */ uint64_t features64 = vdev->guest_features; - if (virtio_set_features_nocheck(vdev, features64) < 0) { + if (virtio_set_features_nocheck_maybe_co(vdev, features64) < 0) { error_report("Features 0x%" PRIx64 " unsupported. " "Allowed features: 0x%" PRIx64, features64, vdev->host_features); return -1; } } else { - if (virtio_set_features_nocheck(vdev, features) < 0) { + if (virtio_set_features_nocheck_maybe_co(vdev, features) < 0) { error_report("Features 0x%x unsupported. " "Allowed features: 0x%" PRIx64, features, vdev->host_features); @@ -3238,8 +3214,7 @@ void virtio_instance_init_common(Object *proxy_obj, void *data, qdev_alias_all_properties(vdev, proxy_obj); } -void virtio_init(VirtIODevice *vdev, const char *name, - uint16_t device_id, size_t config_size) +void virtio_init(VirtIODevice *vdev, uint16_t device_id, size_t config_size) { BusState *qbus = qdev_get_parent_bus(DEVICE(vdev)); VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); @@ -3253,12 +3228,13 @@ void virtio_init(VirtIODevice *vdev, const char *name, vdev->start_on_kick = false; vdev->started = false; + vdev->vhost_started = false; vdev->device_id = device_id; vdev->status = 0; qatomic_set(&vdev->isr, 0); vdev->queue_sel = 0; vdev->config_vector = VIRTIO_NO_VECTOR; - vdev->vq = g_malloc0(sizeof(VirtQueue) * VIRTIO_QUEUE_MAX); + vdev->vq = g_new0(VirtQueue, VIRTIO_QUEUE_MAX); vdev->vm_running = runstate_is_running(); vdev->broken = false; for (i = 0; i < VIRTIO_QUEUE_MAX; i++) { @@ -3268,7 +3244,7 @@ void virtio_init(VirtIODevice *vdev, const char *name, vdev->vq[i].host_notifier_enabled = false; } - vdev->name = name; + vdev->name = virtio_id_to_name(device_id); vdev->config_len = config_size; if (vdev->config_len) { vdev->config = g_malloc0(config_size); @@ -3392,6 +3368,18 @@ static uint16_t virtio_queue_split_get_last_avail_idx(VirtIODevice *vdev, return vdev->vq[n].last_avail_idx; } +static uint32_t virtio_queue_split_get_vring_states(VirtIODevice *vdev, + int n) +{ + struct VirtQueue *vq = &vdev->vq[n]; + uint16_t avail, used; + + avail = vq->last_avail_idx; + used = vq->used_idx; + + return avail | (uint32_t)used << 16; +} + unsigned int virtio_queue_get_last_avail_idx(VirtIODevice *vdev, int n) { if (virtio_vdev_has_feature(vdev, VIRTIO_F_RING_PACKED)) { @@ -3401,6 +3389,33 @@ unsigned int virtio_queue_get_last_avail_idx(VirtIODevice *vdev, int n) } } +unsigned int virtio_queue_get_vring_states(VirtIODevice *vdev, int n) +{ + if (virtio_vdev_has_feature(vdev, VIRTIO_F_RING_PACKED)) { + return -1; + } else { + return virtio_queue_split_get_vring_states(vdev, n); + } +} + +static void virtio_queue_split_set_vring_states(VirtIODevice *vdev, + int n, uint32_t idx) +{ + struct VirtQueue *vq = &vdev->vq[n]; + vq->last_avail_idx = (uint16_t)(idx & 0xffff); + vq->shadow_avail_idx = (uint16_t)(idx & 0xffff); + vq->used_idx = (uint16_t)(idx >> 16); +} + +void virtio_queue_set_vring_states(VirtIODevice *vdev, int n, uint32_t idx) +{ + if (virtio_vdev_has_feature(vdev, VIRTIO_F_RING_PACKED)) { + return; + } else { + virtio_queue_split_set_vring_states(vdev, n, idx); + } +} + static void virtio_queue_packed_set_last_avail_idx(VirtIODevice *vdev, int n, unsigned int idx) { @@ -3410,7 +3425,7 @@ static void virtio_queue_packed_set_last_avail_idx(VirtIODevice *vdev, vq->last_avail_wrap_counter = vq->shadow_avail_wrap_counter = !!(idx & 0x8000); idx >>= 16; - vq->used_idx = idx & 0x7ffff; + vq->used_idx = idx & 0x7fff; vq->used_wrap_counter = !!(idx & 0x8000); } @@ -3502,7 +3517,14 @@ static void virtio_queue_guest_notifier_read(EventNotifier *n) virtio_irq(vq); } } +static void virtio_config_guest_notifier_read(EventNotifier *n) +{ + VirtIODevice *vdev = container_of(n, VirtIODevice, config_notifier); + if (event_notifier_test_and_clear(n)) { + virtio_notify_config(vdev); + } +} void virtio_queue_set_guest_notifier_fd_handler(VirtQueue *vq, bool assign, bool with_irqfd) { @@ -3519,17 +3541,26 @@ void virtio_queue_set_guest_notifier_fd_handler(VirtQueue *vq, bool assign, } } -EventNotifier *virtio_queue_get_guest_notifier(VirtQueue *vq) +void virtio_config_set_guest_notifier_fd_handler(VirtIODevice *vdev, + bool assign, bool with_irqfd) { - return &vq->guest_notifier; + EventNotifier *n; + n = &vdev->config_notifier; + if (assign && !with_irqfd) { + event_notifier_set_handler(n, virtio_config_guest_notifier_read); + } else { + event_notifier_set_handler(n, NULL); + } + if (!assign) { + /* Test and clear notifier before closing it,*/ + /* in case poll callback didn't have time to run. */ + virtio_config_guest_notifier_read(n); + } } -static void virtio_queue_host_notifier_aio_read(EventNotifier *n) +EventNotifier *virtio_queue_get_guest_notifier(VirtQueue *vq) { - VirtQueue *vq = container_of(n, VirtQueue, host_notifier); - if (event_notifier_test_and_clear(n)) { - virtio_queue_notify_aio_vq(vq); - } + return &vq->guest_notifier; } static void virtio_queue_host_notifier_aio_poll_begin(EventNotifier *n) @@ -3544,11 +3575,14 @@ static bool virtio_queue_host_notifier_aio_poll(void *opaque) EventNotifier *n = opaque; VirtQueue *vq = container_of(n, VirtQueue, host_notifier); - if (!vq->vring.desc || virtio_queue_empty(vq)) { - return false; - } + return vq->vring.desc && !virtio_queue_empty(vq); +} + +static void virtio_queue_host_notifier_aio_poll_ready(EventNotifier *n) +{ + VirtQueue *vq = container_of(n, VirtQueue, host_notifier); - return virtio_queue_notify_aio_vq(vq); + virtio_queue_notify_vq(vq); } static void virtio_queue_host_notifier_aio_poll_end(EventNotifier *n) @@ -3559,24 +3593,75 @@ static void virtio_queue_host_notifier_aio_poll_end(EventNotifier *n) virtio_queue_set_notification(vq, 1); } -void virtio_queue_aio_set_host_notifier_handler(VirtQueue *vq, AioContext *ctx, - VirtIOHandleAIOOutput handle_output) +void virtio_queue_aio_attach_host_notifier(VirtQueue *vq, AioContext *ctx) { - if (handle_output) { - vq->handle_aio_output = handle_output; - aio_set_event_notifier(ctx, &vq->host_notifier, true, - virtio_queue_host_notifier_aio_read, - virtio_queue_host_notifier_aio_poll); - aio_set_event_notifier_poll(ctx, &vq->host_notifier, - virtio_queue_host_notifier_aio_poll_begin, - virtio_queue_host_notifier_aio_poll_end); - } else { - aio_set_event_notifier(ctx, &vq->host_notifier, true, NULL, NULL); - /* Test and clear notifier before after disabling event, - * in case poll callback didn't have time to run. */ - virtio_queue_host_notifier_aio_read(&vq->host_notifier); - vq->handle_aio_output = NULL; + /* + * virtio_queue_aio_detach_host_notifier() can leave notifications disabled. + * Re-enable them. (And if detach has not been used before, notifications + * being enabled is still the default state while a notifier is attached; + * see virtio_queue_host_notifier_aio_poll_end(), which will always leave + * notifications enabled once the polling section is left.) + */ + if (!virtio_queue_get_notification(vq)) { + virtio_queue_set_notification(vq, 1); } + + aio_set_event_notifier(ctx, &vq->host_notifier, + virtio_queue_host_notifier_read, + virtio_queue_host_notifier_aio_poll, + virtio_queue_host_notifier_aio_poll_ready); + aio_set_event_notifier_poll(ctx, &vq->host_notifier, + virtio_queue_host_notifier_aio_poll_begin, + virtio_queue_host_notifier_aio_poll_end); + + /* + * We will have ignored notifications about new requests from the guest + * while no notifiers were attached, so "kick" the virt queue to process + * those requests now. + */ + event_notifier_set(&vq->host_notifier); +} + +/* + * Same as virtio_queue_aio_attach_host_notifier() but without polling. Use + * this for rx virtqueues and similar cases where the virtqueue handler + * function does not pop all elements. When the virtqueue is left non-empty + * polling consumes CPU cycles and should not be used. + */ +void virtio_queue_aio_attach_host_notifier_no_poll(VirtQueue *vq, AioContext *ctx) +{ + /* See virtio_queue_aio_attach_host_notifier() */ + if (!virtio_queue_get_notification(vq)) { + virtio_queue_set_notification(vq, 1); + } + + aio_set_event_notifier(ctx, &vq->host_notifier, + virtio_queue_host_notifier_read, + NULL, NULL); + + /* + * See virtio_queue_aio_attach_host_notifier(). + * Note that this may be unnecessary for the type of virtqueues this + * function is used for. Still, it will not hurt to have a quick look into + * whether we can/should process any of the virtqueue elements. + */ + event_notifier_set(&vq->host_notifier); +} + +void virtio_queue_aio_detach_host_notifier(VirtQueue *vq, AioContext *ctx) +{ + aio_set_event_notifier(ctx, &vq->host_notifier, NULL, NULL, NULL); + + /* + * aio_set_event_notifier_poll() does not guarantee whether io_poll_end() + * will run after io_poll_begin(), so by removing the notifier, we do not + * know whether virtio_queue_host_notifier_aio_poll_end() has run after a + * previous virtio_queue_host_notifier_aio_poll_begin(), i.e. whether + * notifications are enabled or disabled. It does not really matter anyway; + * we just removed the notifier, so we do not care about notifications until + * we potentially re-attach it. The attach_host_notifier functions will + * ensure that notifications are enabled again when they are needed. + */ } void virtio_queue_host_notifier_read(EventNotifier *n) @@ -3592,6 +3677,11 @@ EventNotifier *virtio_queue_get_host_notifier(VirtQueue *vq) return &vq->host_notifier; } +EventNotifier *virtio_config_get_guest_notifier(VirtIODevice *vdev) +{ + return &vdev->config_notifier; +} + void virtio_queue_set_host_notifier_enabled(VirtQueue *vq, bool enabled) { vq->host_notifier_enabled = enabled; @@ -3616,7 +3706,7 @@ void virtio_device_set_child_bus_name(VirtIODevice *vdev, char *bus_name) vdev->bus_name = g_strdup(bus_name); } -void GCC_FMT_ATTR(2, 3) virtio_error(VirtIODevice *vdev, const char *fmt, ...) +void G_GNUC_PRINTF(2, 3) virtio_error(VirtIODevice *vdev, const char *fmt, ...) { va_list ap; @@ -3670,6 +3760,7 @@ static void virtio_device_realize(DeviceState *dev, Error **errp) } vdev->listener.commit = virtio_memory_listener_commit; + vdev->listener.name = "virtio"; memory_listener_register(&vdev->listener, vdev->dma_as); } @@ -3868,6 +3959,207 @@ bool virtio_device_ioeventfd_enabled(VirtIODevice *vdev) return virtio_bus_ioeventfd_enabled(vbus); } +VirtQueueStatus *qmp_x_query_virtio_queue_status(const char *path, + uint16_t queue, + Error **errp) +{ + VirtIODevice *vdev; + VirtQueueStatus *status; + + vdev = qmp_find_virtio_device(path); + if (vdev == NULL) { + error_setg(errp, "Path %s is not a VirtIODevice", path); + return NULL; + } + + if (queue >= VIRTIO_QUEUE_MAX || !virtio_queue_get_num(vdev, queue)) { + error_setg(errp, "Invalid virtqueue number %d", queue); + return NULL; + } + + status = g_new0(VirtQueueStatus, 1); + status->name = g_strdup(vdev->name); + status->queue_index = vdev->vq[queue].queue_index; + status->inuse = vdev->vq[queue].inuse; + status->vring_num = vdev->vq[queue].vring.num; + status->vring_num_default = vdev->vq[queue].vring.num_default; + status->vring_align = vdev->vq[queue].vring.align; + status->vring_desc = vdev->vq[queue].vring.desc; + status->vring_avail = vdev->vq[queue].vring.avail; + status->vring_used = vdev->vq[queue].vring.used; + status->used_idx = vdev->vq[queue].used_idx; + status->signalled_used = vdev->vq[queue].signalled_used; + status->signalled_used_valid = vdev->vq[queue].signalled_used_valid; + + if (vdev->vhost_started) { + VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(vdev); + struct vhost_dev *hdev = vdc->get_vhost(vdev); + + /* check if vq index exists for vhost as well */ + if (queue >= hdev->vq_index && queue < hdev->vq_index + hdev->nvqs) { + status->has_last_avail_idx = true; + + int vhost_vq_index = + hdev->vhost_ops->vhost_get_vq_index(hdev, queue); + struct vhost_vring_state state = { + .index = vhost_vq_index, + }; + + status->last_avail_idx = + hdev->vhost_ops->vhost_get_vring_base(hdev, &state); + } + } else { + status->has_shadow_avail_idx = true; + status->has_last_avail_idx = true; + status->last_avail_idx = vdev->vq[queue].last_avail_idx; + status->shadow_avail_idx = vdev->vq[queue].shadow_avail_idx; + } + + return status; +} + +static strList *qmp_decode_vring_desc_flags(uint16_t flags) +{ + strList *list = NULL; + strList *node; + int i; + + struct { + uint16_t flag; + const char *value; + } map[] = { + { VRING_DESC_F_NEXT, "next" }, + { VRING_DESC_F_WRITE, "write" }, + { VRING_DESC_F_INDIRECT, "indirect" }, + { 1 << VRING_PACKED_DESC_F_AVAIL, "avail" }, + { 1 << VRING_PACKED_DESC_F_USED, "used" }, + { 0, "" } + }; + + for (i = 0; map[i].flag; i++) { + if ((map[i].flag & flags) == 0) { + continue; + } + node = g_malloc0(sizeof(strList)); + node->value = g_strdup(map[i].value); + node->next = list; + list = node; + } + + return list; +} + +VirtioQueueElement *qmp_x_query_virtio_queue_element(const char *path, + uint16_t queue, + bool has_index, + uint16_t index, + Error **errp) +{ + VirtIODevice *vdev; + VirtQueue *vq; + VirtioQueueElement *element = NULL; + + vdev = qmp_find_virtio_device(path); + if (vdev == NULL) { + error_setg(errp, "Path %s is not a VirtIO device", path); + return NULL; + } + + if (queue >= VIRTIO_QUEUE_MAX || !virtio_queue_get_num(vdev, queue)) { + error_setg(errp, "Invalid virtqueue number %d", queue); + return NULL; + } + vq = &vdev->vq[queue]; + + if (virtio_vdev_has_feature(vdev, VIRTIO_F_RING_PACKED)) { + error_setg(errp, "Packed ring not supported"); + return NULL; + } else { + unsigned int head, i, max; + VRingMemoryRegionCaches *caches; + MemoryRegionCache indirect_desc_cache; + MemoryRegionCache *desc_cache; + VRingDesc desc; + VirtioRingDescList *list = NULL; + VirtioRingDescList *node; + int rc; int ndescs; + + address_space_cache_init_empty(&indirect_desc_cache); + + RCU_READ_LOCK_GUARD(); + + max = vq->vring.num; + + if (!has_index) { + head = vring_avail_ring(vq, vq->last_avail_idx % vq->vring.num); + } else { + head = vring_avail_ring(vq, index % vq->vring.num); + } + i = head; + + caches = vring_get_region_caches(vq); + if (!caches) { + error_setg(errp, "Region caches not initialized"); + return NULL; + } + if (caches->desc.len < max * sizeof(VRingDesc)) { + error_setg(errp, "Cannot map descriptor ring"); + return NULL; + } + + desc_cache = &caches->desc; + vring_split_desc_read(vdev, &desc, desc_cache, i); + if (desc.flags & VRING_DESC_F_INDIRECT) { + int64_t len; + len = address_space_cache_init(&indirect_desc_cache, vdev->dma_as, + desc.addr, desc.len, false); + desc_cache = &indirect_desc_cache; + if (len < desc.len) { + error_setg(errp, "Cannot map indirect buffer"); + goto done; + } + + max = desc.len / sizeof(VRingDesc); + i = 0; + vring_split_desc_read(vdev, &desc, desc_cache, i); + } + + element = g_new0(VirtioQueueElement, 1); + element->avail = g_new0(VirtioRingAvail, 1); + element->used = g_new0(VirtioRingUsed, 1); + element->name = g_strdup(vdev->name); + element->index = head; + element->avail->flags = vring_avail_flags(vq); + element->avail->idx = vring_avail_idx(vq); + element->avail->ring = head; + element->used->flags = vring_used_flags(vq); + element->used->idx = vring_used_idx(vq); + ndescs = 0; + + do { + /* A buggy driver may produce an infinite loop */ + if (ndescs >= max) { + break; + } + node = g_new0(VirtioRingDescList, 1); + node->value = g_new0(VirtioRingDesc, 1); + node->value->addr = desc.addr; + node->value->len = desc.len; + node->value->flags = qmp_decode_vring_desc_flags(desc.flags); + node->next = list; + list = node; + + ndescs++; + rc = virtqueue_split_read_next_desc(vdev, &desc, desc_cache, max); + } while (rc == VIRTQUEUE_READ_DESC_MORE); + element->descs = list; +done: + address_space_cache_destroy(&indirect_desc_cache); + } + + return element; +} + static const TypeInfo virtio_device_info = { .name = TYPE_VIRTIO_DEVICE, .parent = TYPE_DEVICE, |