diff options
Diffstat (limited to 'hw')
| -rw-r--r-- | hw/net/virtio-net.c | 1 | ||||
| -rw-r--r-- | hw/nvram/eeprom_at24c.c | 7 | ||||
| -rw-r--r-- | hw/virtio/meson.build | 2 | ||||
| -rw-r--r-- | hw/virtio/vhost-iova-tree.c | 110 | ||||
| -rw-r--r-- | hw/virtio/vhost-iova-tree.h | 27 | ||||
| -rw-r--r-- | hw/virtio/vhost-shadow-virtqueue.c | 636 | ||||
| -rw-r--r-- | hw/virtio/vhost-shadow-virtqueue.h | 87 | ||||
| -rw-r--r-- | hw/virtio/vhost-vdpa.c | 522 |
8 files changed, 1375 insertions, 17 deletions
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index b02a0632df..2087516253 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -1870,6 +1870,7 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf, err: for (j = 0; j < i; j++) { + virtqueue_detach_element(q->rx_vq, elems[j], lens[j]); g_free(elems[j]); } diff --git a/hw/nvram/eeprom_at24c.c b/hw/nvram/eeprom_at24c.c index da435500ba..01a3093600 100644 --- a/hw/nvram/eeprom_at24c.c +++ b/hw/nvram/eeprom_at24c.c @@ -58,9 +58,10 @@ int at24c_eeprom_event(I2CSlave *s, enum i2c_event event) switch (event) { case I2C_START_SEND: - case I2C_START_RECV: case I2C_FINISH: ee->haveaddr = 0; + /* fallthrough */ + case I2C_START_RECV: DPRINTK("clear\n"); if (ee->blk && ee->changed) { int len = blk_pwrite(ee->blk, 0, ee->mem, ee->rsize, 0); @@ -84,6 +85,10 @@ uint8_t at24c_eeprom_recv(I2CSlave *s) EEPROMState *ee = AT24C_EE(s); uint8_t ret; + if (ee->haveaddr == 1) { + return 0xff; + } + ret = ee->mem[ee->cur]; ee->cur = (ee->cur + 1u) % ee->rsize; diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build index 521f7d64a8..6047670804 100644 --- a/hw/virtio/meson.build +++ b/hw/virtio/meson.build @@ -11,7 +11,7 @@ softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost-stub.c')) virtio_ss = ss.source_set() virtio_ss.add(files('virtio.c')) -virtio_ss.add(when: 'CONFIG_VHOST', if_true: files('vhost.c', 'vhost-backend.c')) +virtio_ss.add(when: 'CONFIG_VHOST', if_true: files('vhost.c', 'vhost-backend.c', 'vhost-shadow-virtqueue.c', 'vhost-iova-tree.c')) virtio_ss.add(when: 'CONFIG_VHOST_USER', if_true: files('vhost-user.c')) virtio_ss.add(when: 'CONFIG_VHOST_VDPA', if_true: files('vhost-vdpa.c')) virtio_ss.add(when: 'CONFIG_VIRTIO_BALLOON', if_true: files('virtio-balloon.c')) diff --git a/hw/virtio/vhost-iova-tree.c b/hw/virtio/vhost-iova-tree.c new file mode 100644 index 0000000000..55fed1fefb --- /dev/null +++ b/hw/virtio/vhost-iova-tree.c @@ -0,0 +1,110 @@ +/* + * vhost software live migration iova tree + * + * SPDX-FileCopyrightText: Red Hat, Inc. 2021 + * SPDX-FileContributor: Author: Eugenio Pérez <eperezma@redhat.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qemu/iova-tree.h" +#include "vhost-iova-tree.h" + +#define iova_min_addr qemu_real_host_page_size + +/** + * VhostIOVATree, able to: + * - Translate iova address + * - Reverse translate iova address (from translated to iova) + * - Allocate IOVA regions for translated range (linear operation) + */ +struct VhostIOVATree { + /* First addressable iova address in the device */ + uint64_t iova_first; + + /* Last addressable iova address in the device */ + uint64_t iova_last; + + /* IOVA address to qemu memory maps. */ + IOVATree *iova_taddr_map; +}; + +/** + * Create a new IOVA tree + * + * Returns the new IOVA tree + */ +VhostIOVATree *vhost_iova_tree_new(hwaddr iova_first, hwaddr iova_last) +{ + VhostIOVATree *tree = g_new(VhostIOVATree, 1); + + /* Some devices do not like 0 addresses */ + tree->iova_first = MAX(iova_first, iova_min_addr); + tree->iova_last = iova_last; + + tree->iova_taddr_map = iova_tree_new(); + return tree; +} + +/** + * Delete an iova tree + */ +void vhost_iova_tree_delete(VhostIOVATree *iova_tree) +{ + iova_tree_destroy(iova_tree->iova_taddr_map); + g_free(iova_tree); +} + +/** + * Find the IOVA address stored from a memory address + * + * @tree: The iova tree + * @map: The map with the memory address + * + * Return the stored mapping, or NULL if not found. + */ +const DMAMap *vhost_iova_tree_find_iova(const VhostIOVATree *tree, + const DMAMap *map) +{ + return iova_tree_find_iova(tree->iova_taddr_map, map); +} + +/** + * Allocate a new mapping + * + * @tree: The iova tree + * @map: The iova map + * + * Returns: + * - IOVA_OK if the map fits in the container + * - IOVA_ERR_INVALID if the map does not make sense (like size overflow) + * - IOVA_ERR_NOMEM if tree cannot allocate more space. + * + * It returns assignated iova in map->iova if return value is VHOST_DMA_MAP_OK. + */ +int vhost_iova_tree_map_alloc(VhostIOVATree *tree, DMAMap *map) +{ + /* Some vhost devices do not like addr 0. Skip first page */ + hwaddr iova_first = tree->iova_first ?: qemu_real_host_page_size; + + if (map->translated_addr + map->size < map->translated_addr || + map->perm == IOMMU_NONE) { + return IOVA_ERR_INVALID; + } + + /* Allocate a node in IOVA address */ + return iova_tree_alloc_map(tree->iova_taddr_map, map, iova_first, + tree->iova_last); +} + +/** + * Remove existing mappings from iova tree + * + * @iova_tree: The vhost iova tree + * @map: The map to remove + */ +void vhost_iova_tree_remove(VhostIOVATree *iova_tree, const DMAMap *map) +{ + iova_tree_remove(iova_tree->iova_taddr_map, map); +} diff --git a/hw/virtio/vhost-iova-tree.h b/hw/virtio/vhost-iova-tree.h new file mode 100644 index 0000000000..6a4f24e0f9 --- /dev/null +++ b/hw/virtio/vhost-iova-tree.h @@ -0,0 +1,27 @@ +/* + * vhost software live migration iova tree + * + * SPDX-FileCopyrightText: Red Hat, Inc. 2021 + * SPDX-FileContributor: Author: Eugenio Pérez <eperezma@redhat.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_VIRTIO_VHOST_IOVA_TREE_H +#define HW_VIRTIO_VHOST_IOVA_TREE_H + +#include "qemu/iova-tree.h" +#include "exec/memory.h" + +typedef struct VhostIOVATree VhostIOVATree; + +VhostIOVATree *vhost_iova_tree_new(uint64_t iova_first, uint64_t iova_last); +void vhost_iova_tree_delete(VhostIOVATree *iova_tree); +G_DEFINE_AUTOPTR_CLEANUP_FUNC(VhostIOVATree, vhost_iova_tree_delete); + +const DMAMap *vhost_iova_tree_find_iova(const VhostIOVATree *iova_tree, + const DMAMap *map); +int vhost_iova_tree_map_alloc(VhostIOVATree *iova_tree, DMAMap *map); +void vhost_iova_tree_remove(VhostIOVATree *iova_tree, const DMAMap *map); + +#endif diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c new file mode 100644 index 0000000000..b232803d1b --- /dev/null +++ b/hw/virtio/vhost-shadow-virtqueue.c @@ -0,0 +1,636 @@ +/* + * vhost shadow virtqueue + * + * SPDX-FileCopyrightText: Red Hat, Inc. 2021 + * SPDX-FileContributor: Author: Eugenio Pérez <eperezma@redhat.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "hw/virtio/vhost-shadow-virtqueue.h" + +#include "qemu/error-report.h" +#include "qapi/error.h" +#include "qemu/main-loop.h" +#include "qemu/log.h" +#include "qemu/memalign.h" +#include "linux-headers/linux/vhost.h" + +/** + * Validate the transport device features that both guests can use with the SVQ + * and SVQs can use with the device. + * + * @dev_features: The features + * @errp: Error pointer + */ +bool vhost_svq_valid_features(uint64_t features, Error **errp) +{ + bool ok = true; + uint64_t svq_features = features; + + for (uint64_t b = VIRTIO_TRANSPORT_F_START; b <= VIRTIO_TRANSPORT_F_END; + ++b) { + switch (b) { + case VIRTIO_F_ANY_LAYOUT: + continue; + + case VIRTIO_F_ACCESS_PLATFORM: + /* SVQ trust in the host's IOMMU to translate addresses */ + case VIRTIO_F_VERSION_1: + /* SVQ trust that the guest vring is little endian */ + if (!(svq_features & BIT_ULL(b))) { + svq_features |= BIT_ULL(b); + ok = false; + } + continue; + + default: + if (svq_features & BIT_ULL(b)) { + svq_features &= ~BIT_ULL(b); + ok = false; + } + } + } + + if (!ok) { + error_setg(errp, "SVQ Invalid device feature flags, offer: 0x%"PRIx64 + ", ok: 0x%"PRIx64, features, svq_features); + } + return ok; +} + +/** + * Number of descriptors that the SVQ can make available from the guest. + * + * @svq: The svq + */ +static uint16_t vhost_svq_available_slots(const VhostShadowVirtqueue *svq) +{ + return svq->vring.num - (svq->shadow_avail_idx - svq->shadow_used_idx); +} + +/** + * Translate addresses between the qemu's virtual address and the SVQ IOVA + * + * @svq: Shadow VirtQueue + * @vaddr: Translated IOVA addresses + * @iovec: Source qemu's VA addresses + * @num: Length of iovec and minimum length of vaddr + */ +static bool vhost_svq_translate_addr(const VhostShadowVirtqueue *svq, + hwaddr *addrs, const struct iovec *iovec, + size_t num) +{ + if (num == 0) { + return true; + } + + for (size_t i = 0; i < num; ++i) { + DMAMap needle = { + .translated_addr = (hwaddr)(uintptr_t)iovec[i].iov_base, + .size = iovec[i].iov_len, + }; + Int128 needle_last, map_last; + size_t off; + + const DMAMap *map = vhost_iova_tree_find_iova(svq->iova_tree, &needle); + /* + * Map cannot be NULL since iova map contains all guest space and + * qemu already has a physical address mapped + */ + if (unlikely(!map)) { + qemu_log_mask(LOG_GUEST_ERROR, + "Invalid address 0x%"HWADDR_PRIx" given by guest", + needle.translated_addr); + return false; + } + + off = needle.translated_addr - map->translated_addr; + addrs[i] = map->iova + off; + + needle_last = int128_add(int128_make64(needle.translated_addr), + int128_make64(iovec[i].iov_len)); + map_last = int128_make64(map->translated_addr + map->size); + if (unlikely(int128_gt(needle_last, map_last))) { + qemu_log_mask(LOG_GUEST_ERROR, + "Guest buffer expands over iova range"); + return false; + } + } + + return true; +} + +static void vhost_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg, + const struct iovec *iovec, size_t num, + bool more_descs, bool write) +{ + uint16_t i = svq->free_head, last = svq->free_head; + unsigned n; + uint16_t flags = write ? cpu_to_le16(VRING_DESC_F_WRITE) : 0; + vring_desc_t *descs = svq->vring.desc; + + if (num == 0) { + return; + } + + for (n = 0; n < num; n++) { + if (more_descs || (n + 1 < num)) { + descs[i].flags = flags | cpu_to_le16(VRING_DESC_F_NEXT); + } else { + descs[i].flags = flags; + } + descs[i].addr = cpu_to_le64(sg[n]); + descs[i].len = cpu_to_le32(iovec[n].iov_len); + + last = i; + i = cpu_to_le16(descs[i].next); + } + + svq->free_head = le16_to_cpu(descs[last].next); +} + +static bool vhost_svq_add_split(VhostShadowVirtqueue *svq, + VirtQueueElement *elem, unsigned *head) +{ + unsigned avail_idx; + vring_avail_t *avail = svq->vring.avail; + bool ok; + g_autofree hwaddr *sgs = g_new(hwaddr, MAX(elem->out_num, elem->in_num)); + + *head = svq->free_head; + + /* We need some descriptors here */ + if (unlikely(!elem->out_num && !elem->in_num)) { + qemu_log_mask(LOG_GUEST_ERROR, + "Guest provided element with no descriptors"); + return false; + } + + ok = vhost_svq_translate_addr(svq, sgs, elem->out_sg, elem->out_num); + if (unlikely(!ok)) { + return false; + } + vhost_vring_write_descs(svq, sgs, elem->out_sg, elem->out_num, + elem->in_num > 0, false); + + + ok = vhost_svq_translate_addr(svq, sgs, elem->in_sg, elem->in_num); + if (unlikely(!ok)) { + return false; + } + + vhost_vring_write_descs(svq, sgs, elem->in_sg, elem->in_num, false, true); + + /* + * Put the entry in the available array (but don't update avail->idx until + * they do sync). + */ + avail_idx = svq->shadow_avail_idx & (svq->vring.num - 1); + avail->ring[avail_idx] = cpu_to_le16(*head); + svq->shadow_avail_idx++; + + /* Update the avail index after write the descriptor */ + smp_wmb(); + avail->idx = cpu_to_le16(svq->shadow_avail_idx); + + return true; +} + +static bool vhost_svq_add(VhostShadowVirtqueue *svq, VirtQueueElement *elem) +{ + unsigned qemu_head; + bool ok = vhost_svq_add_split(svq, elem, &qemu_head); + if (unlikely(!ok)) { + return false; + } + + svq->ring_id_maps[qemu_head] = elem; + return true; +} + +static void vhost_svq_kick(VhostShadowVirtqueue *svq) +{ + /* + * We need to expose the available array entries before checking the used + * flags + */ + smp_mb(); + if (svq->vring.used->flags & VRING_USED_F_NO_NOTIFY) { + return; + } + + event_notifier_set(&svq->hdev_kick); +} + +/** + * Forward available buffers. + * + * @svq: Shadow VirtQueue + * + * Note that this function does not guarantee that all guest's available + * buffers are available to the device in SVQ avail ring. The guest may have + * exposed a GPA / GIOVA contiguous buffer, but it may not be contiguous in + * qemu vaddr. + * + * If that happens, guest's kick notifications will be disabled until the + * device uses some buffers. + */ +static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq) +{ + /* Clear event notifier */ + event_notifier_test_and_clear(&svq->svq_kick); + + /* Forward to the device as many available buffers as possible */ + do { + virtio_queue_set_notification(svq->vq, false); + + while (true) { + VirtQueueElement *elem; + bool ok; + + if (svq->next_guest_avail_elem) { + elem = g_steal_pointer(&svq->next_guest_avail_elem); + } else { + elem = virtqueue_pop(svq->vq, sizeof(*elem)); + } + + if (!elem) { + break; + } + + if (elem->out_num + elem->in_num > vhost_svq_available_slots(svq)) { + /* + * This condition is possible since a contiguous buffer in GPA + * does not imply a contiguous buffer in qemu's VA + * scatter-gather segments. If that happens, the buffer exposed + * to the device needs to be a chain of descriptors at this + * moment. + * + * SVQ cannot hold more available buffers if we are here: + * queue the current guest descriptor and ignore further kicks + * until some elements are used. + */ + svq->next_guest_avail_elem = elem; + return; + } + + ok = vhost_svq_add(svq, elem); + if (unlikely(!ok)) { + /* VQ is broken, just return and ignore any other kicks */ + return; + } + vhost_svq_kick(svq); + } + + virtio_queue_set_notification(svq->vq, true); + } while (!virtio_queue_empty(svq->vq)); +} + +/** + * Handle guest's kick. + * + * @n: guest kick event notifier, the one that guest set to notify svq. + */ +static void vhost_handle_guest_kick_notifier(EventNotifier *n) +{ + VhostShadowVirtqueue *svq = container_of(n, VhostShadowVirtqueue, svq_kick); + event_notifier_test_and_clear(n); + vhost_handle_guest_kick(svq); +} + +static bool vhost_svq_more_used(VhostShadowVirtqueue *svq) +{ + if (svq->last_used_idx != svq->shadow_used_idx) { + return true; + } + + svq->shadow_used_idx = cpu_to_le16(svq->vring.used->idx); + + return svq->last_used_idx != svq->shadow_used_idx; +} + +/** + * Enable vhost device calls after disable them. + * + * @svq: The svq + * + * It returns false if there are pending used buffers from the vhost device, + * avoiding the possible races between SVQ checking for more work and enabling + * callbacks. True if SVQ used vring has no more pending buffers. + */ +static bool vhost_svq_enable_notification(VhostShadowVirtqueue *svq) +{ + svq->vring.avail->flags &= ~cpu_to_le16(VRING_AVAIL_F_NO_INTERRUPT); + /* Make sure the flag is written before the read of used_idx */ + smp_mb(); + return !vhost_svq_more_used(svq); +} + +static void vhost_svq_disable_notification(VhostShadowVirtqueue *svq) +{ + svq->vring.avail->flags |= cpu_to_le16(VRING_AVAIL_F_NO_INTERRUPT); +} + +static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq, + uint32_t *len) +{ + vring_desc_t *descs = svq->vring.desc; + const vring_used_t *used = svq->vring.used; + vring_used_elem_t used_elem; + uint16_t last_used; + + if (!vhost_svq_more_used(svq)) { + return NULL; + } + + /* Only get used array entries after they have been exposed by dev */ + smp_rmb(); + last_used = svq->last_used_idx & (svq->vring.num - 1); + used_elem.id = le32_to_cpu(used->ring[last_used].id); + used_elem.len = le32_to_cpu(used->ring[last_used].len); + + svq->last_used_idx++; + if (unlikely(used_elem.id >= svq->vring.num)) { + qemu_log_mask(LOG_GUEST_ERROR, "Device %s says index %u is used", + svq->vdev->name, used_elem.id); + return NULL; + } + + if (unlikely(!svq->ring_id_maps[used_elem.id])) { + qemu_log_mask(LOG_GUEST_ERROR, + "Device %s says index %u is used, but it was not available", + svq->vdev->name, used_elem.id); + return NULL; + } + + descs[used_elem.id].next = svq->free_head; + svq->free_head = used_elem.id; + + *len = used_elem.len; + return g_steal_pointer(&svq->ring_id_maps[used_elem.id]); +} + +static void vhost_svq_flush(VhostShadowVirtqueue *svq, + bool check_for_avail_queue) +{ + VirtQueue *vq = svq->vq; + + /* Forward as many used buffers as possible. */ + do { + unsigned i = 0; + + vhost_svq_disable_notification(svq); + while (true) { + uint32_t len; + g_autofree VirtQueueElement *elem = vhost_svq_get_buf(svq, &len); + if (!elem) { + break; + } + + if (unlikely(i >= svq->vring.num)) { + qemu_log_mask(LOG_GUEST_ERROR, + "More than %u used buffers obtained in a %u size SVQ", + i, svq->vring.num); + virtqueue_fill(vq, elem, len, i); + virtqueue_flush(vq, i); + return; + } + virtqueue_fill(vq, elem, len, i++); + } + + virtqueue_flush(vq, i); + event_notifier_set(&svq->svq_call); + + if (check_for_avail_queue && svq->next_guest_avail_elem) { + /* + * Avail ring was full when vhost_svq_flush was called, so it's a + * good moment to make more descriptors available if possible. + */ + vhost_handle_guest_kick(svq); + } + } while (!vhost_svq_enable_notification(svq)); +} + +/** + * Forward used buffers. + * + * @n: hdev call event notifier, the one that device set to notify svq. + * + * Note that we are not making any buffers available in the loop, there is no + * way that it runs more than virtqueue size times. + */ +static void vhost_svq_handle_call(EventNotifier *n) +{ + VhostShadowVirtqueue *svq = container_of(n, VhostShadowVirtqueue, + hdev_call); + event_notifier_test_and_clear(n); + vhost_svq_flush(svq, true); +} + +/** + * Set the call notifier for the SVQ to call the guest + * + * @svq: Shadow virtqueue + * @call_fd: call notifier + * + * Called on BQL context. + */ +void vhost_svq_set_svq_call_fd(VhostShadowVirtqueue *svq, int call_fd) +{ + if (call_fd == VHOST_FILE_UNBIND) { + /* + * Fail event_notifier_set if called handling device call. + * + * SVQ still needs device notifications, since it needs to keep + * forwarding used buffers even with the unbind. + */ + memset(&svq->svq_call, 0, sizeof(svq->svq_call)); + } else { + event_notifier_init_fd(&svq->svq_call, call_fd); + } +} + +/** + * Get the shadow vq vring address. + * @svq: Shadow virtqueue + * @addr: Destination to store address + */ +void vhost_svq_get_vring_addr(const VhostShadowVirtqueue *svq, + struct vhost_vring_addr *addr) +{ + addr->desc_user_addr = (uint64_t)(uintptr_t)svq->vring.desc; + addr->avail_user_addr = (uint64_t)(uintptr_t)svq->vring.avail; + addr->used_user_addr = (uint64_t)(uintptr_t)svq->vring.used; +} + +size_t vhost_svq_driver_area_size(const VhostShadowVirtqueue *svq) +{ + size_t desc_size = sizeof(vring_desc_t) * svq->vring.num; + size_t avail_size = offsetof(vring_avail_t, ring) + + sizeof(uint16_t) * svq->vring.num; + + return ROUND_UP(desc_size + avail_size, qemu_real_host_page_size); +} + +size_t vhost_svq_device_area_size(const VhostShadowVirtqueue *svq) +{ + size_t used_size = offsetof(vring_used_t, ring) + + sizeof(vring_used_elem_t) * svq->vring.num; + return ROUND_UP(used_size, qemu_real_host_page_size); +} + +/** + * Set a new file descriptor for the guest to kick the SVQ and notify for avail + * + * @svq: The svq + * @svq_kick_fd: The svq kick fd + * + * Note that the SVQ will never close the old file descriptor. + */ +void vhost_svq_set_svq_kick_fd(VhostShadowVirtqueue *svq, int svq_kick_fd) +{ + EventNotifier *svq_kick = &svq->svq_kick; + bool poll_stop = VHOST_FILE_UNBIND != event_notifier_get_fd(svq_kick); + bool poll_start = svq_kick_fd != VHOST_FILE_UNBIND; + + if (poll_stop) { + event_notifier_set_handler(svq_kick, NULL); + } + + /* + * event_notifier_set_handler already checks for guest's notifications if + * they arrive at the new file descriptor in the switch, so there is no + * need to explicitly check for them. + */ + if (poll_start) { + event_notifier_init_fd(svq_kick, svq_kick_fd); + event_notifier_set(svq_kick); + event_notifier_set_handler(svq_kick, vhost_handle_guest_kick_notifier); + } +} + +/** + * Start the shadow virtqueue operation. + * + * @svq: Shadow Virtqueue + * @vdev: VirtIO device + * @vq: Virtqueue to shadow + */ +void vhost_svq_start(VhostShadowVirtqueue *svq, VirtIODevice *vdev, + VirtQueue *vq) +{ + size_t desc_size, driver_size, device_size; + + svq->next_guest_avail_elem = NULL; + svq->shadow_avail_idx = 0; + svq->shadow_used_idx = 0; + svq->last_used_idx = 0; + svq->vdev = vdev; + svq->vq = vq; + + svq->vring.num = virtio_queue_get_num(vdev, virtio_get_queue_index(vq)); + driver_size = vhost_svq_driver_area_size(svq); + device_size = vhost_svq_device_area_size(svq); + svq->vring.desc = qemu_memalign(qemu_real_host_page_size, driver_size); + desc_size = sizeof(vring_desc_t) * svq->vring.num; + svq->vring.avail = (void *)((char *)svq->vring.desc + desc_size); + memset(svq->vring.desc, 0, driver_size); + svq->vring.used = qemu_memalign(qemu_real_host_page_size, device_size); + memset(svq->vring.used, 0, device_size); + svq->ring_id_maps = g_new0(VirtQueueElement *, svq->vring.num); + for (unsigned i = 0; i < svq->vring.num - 1; i++) { + svq->vring.desc[i].next = cpu_to_le16(i + 1); + } +} + +/** + * Stop the shadow virtqueue operation. + * @svq: Shadow Virtqueue + */ +void vhost_svq_stop(VhostShadowVirtqueue *svq) +{ + event_notifier_set_handler(&svq->svq_kick, NULL); + g_autofree VirtQueueElement *next_avail_elem = NULL; + + if (!svq->vq) { + return; + } + + /* Send all pending used descriptors to guest */ + vhost_svq_flush(svq, false); + + for (unsigned i = 0; i < svq->vring.num; ++i) { + g_autofree VirtQueueElement *elem = NULL; + elem = g_steal_pointer(&svq->ring_id_maps[i]); + if (elem) { + virtqueue_detach_element(svq->vq, elem, 0); + } + } + + next_avail_elem = g_steal_pointer(&svq->next_guest_avail_elem); + if (next_avail_elem) { + virtqueue_detach_element(svq->vq, next_avail_elem, 0); + } + svq->vq = NULL; + g_free(svq->ring_id_maps); + qemu_vfree(svq->vring.desc); + qemu_vfree(svq->vring.used); +} + +/** + * Creates vhost shadow virtqueue, and instructs the vhost device to use the + * shadow methods and file descriptors. + * + * @iova_tree: Tree to perform descriptors translations + * + * Returns the new virtqueue or NULL. + * + * In case of error, reason is reported through error_report. + */ +VhostShadowVirtqueue *vhost_svq_new(VhostIOVATree *iova_tree) +{ + g_autofree VhostShadowVirtqueue *svq = g_new0(VhostShadowVirtqueue, 1); + int r; + + r = event_notifier_init(&svq->hdev_kick, 0); + if (r != 0) { + error_report("Couldn't create kick event notifier: %s (%d)", + g_strerror(errno), errno); + goto err_init_hdev_kick; + } + + r = event_notifier_init(&svq->hdev_call, 0); + if (r != 0) { + error_report("Couldn't create call event notifier: %s (%d)", + g_strerror(errno), errno); + goto err_init_hdev_call; + } + + event_notifier_init_fd(&svq->svq_kick, VHOST_FILE_UNBIND); + event_notifier_set_handler(&svq->hdev_call, vhost_svq_handle_call); + svq->iova_tree = iova_tree; + return g_steal_pointer(&svq); + +err_init_hdev_call: + event_notifier_cleanup(&svq->hdev_kick); + +err_init_hdev_kick: + return NULL; +} + +/** + * Free the resources of the shadow virtqueue. + * + * @pvq: gpointer to SVQ so it can be used by autofree functions. + */ +void vhost_svq_free(gpointer pvq) +{ + VhostShadowVirtqueue *vq = pvq; + vhost_svq_stop(vq); + event_notifier_cleanup(&vq->hdev_kick); + event_notifier_set_handler(&vq->hdev_call, NULL); + event_notifier_cleanup(&vq->hdev_call); + g_free(vq); +} diff --git a/hw/virtio/vhost-shadow-virtqueue.h b/hw/virtio/vhost-shadow-virtqueue.h new file mode 100644 index 0000000000..e5e24c536d --- /dev/null +++ b/hw/virtio/vhost-shadow-virtqueue.h @@ -0,0 +1,87 @@ +/* + * vhost shadow virtqueue + * + * SPDX-FileCopyrightText: Red Hat, Inc. 2021 + * SPDX-FileContributor: Author: Eugenio Pérez <eperezma@redhat.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef VHOST_SHADOW_VIRTQUEUE_H +#define VHOST_SHADOW_VIRTQUEUE_H + +#include "qemu/event_notifier.h" +#include "hw/virtio/virtio.h" +#include "standard-headers/linux/vhost_types.h" +#include "hw/virtio/vhost-iova-tree.h" + +/* Shadow virtqueue to relay notifications */ +typedef struct VhostShadowVirtqueue { + /* Shadow vring */ + struct vring vring; + + /* Shadow kick notifier, sent to vhost */ + EventNotifier hdev_kick; + /* Shadow call notifier, sent to vhost */ + EventNotifier hdev_call; + + /* + * Borrowed virtqueue's guest to host notifier. To borrow it in this event + * notifier allows to recover the VhostShadowVirtqueue from the event loop + * easily. If we use the VirtQueue's one, we don't have an easy way to + * retrieve VhostShadowVirtqueue. + * + * So shadow virtqueue must not clean it, or we would lose VirtQueue one. + */ + EventNotifier svq_kick; + + /* Guest's call notifier, where the SVQ calls guest. */ + EventNotifier svq_call; + + /* Virtio queue shadowing */ + VirtQueue *vq; + + /* Virtio device */ + VirtIODevice *vdev; + + /* IOVA mapping */ + VhostIOVATree *iova_tree; + + /* Map for use the guest's descriptors */ + VirtQueueElement **ring_id_maps; + + /* Next VirtQueue element that guest made available */ + VirtQueueElement *next_guest_avail_elem; + + /* Next head to expose to the device */ + uint16_t shadow_avail_idx; + + /* Next free descriptor */ + uint16_t free_head; + + /* Last seen used idx */ + uint16_t shadow_used_idx; + + /* Next head to consume from the device */ + uint16_t last_used_idx; +} VhostShadowVirtqueue; + +bool vhost_svq_valid_features(uint64_t features, Error **errp); + +void vhost_svq_set_svq_kick_fd(VhostShadowVirtqueue *svq, int svq_kick_fd); +void vhost_svq_set_svq_call_fd(VhostShadowVirtqueue *svq, int call_fd); +void vhost_svq_get_vring_addr(const VhostShadowVirtqueue *svq, + struct vhost_vring_addr *addr); +size_t vhost_svq_driver_area_size(const VhostShadowVirtqueue *svq); +size_t vhost_svq_device_area_size(const VhostShadowVirtqueue *svq); + +void vhost_svq_start(VhostShadowVirtqueue *svq, VirtIODevice *vdev, + VirtQueue *vq); +void vhost_svq_stop(VhostShadowVirtqueue *svq); + +VhostShadowVirtqueue *vhost_svq_new(VhostIOVATree *iova_tree); + +void vhost_svq_free(gpointer vq); +G_DEFINE_AUTOPTR_CLEANUP_FUNC(VhostShadowVirtqueue, vhost_svq_free); + +#endif diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c index 6c67d5f034..c5ed7a3779 100644 --- a/hw/virtio/vhost-vdpa.c +++ b/hw/virtio/vhost-vdpa.c @@ -17,12 +17,14 @@ #include "hw/virtio/vhost.h" #include "hw/virtio/vhost-backend.h" #include "hw/virtio/virtio-net.h" +#include "hw/virtio/vhost-shadow-virtqueue.h" #include "hw/virtio/vhost-vdpa.h" #include "exec/address-spaces.h" #include "qemu/main-loop.h" #include "cpu.h" #include "trace.h" #include "qemu-common.h" +#include "qapi/error.h" /* * Return one past the end of the end of section. Be careful with uint64_t @@ -207,6 +209,21 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener, vaddr, section->readonly); llsize = int128_sub(llend, int128_make64(iova)); + if (v->shadow_vqs_enabled) { + DMAMap mem_region = { + .translated_addr = (hwaddr)(uintptr_t)vaddr, + .size = int128_get64(llsize) - 1, + .perm = IOMMU_ACCESS_FLAG(true, section->readonly), + }; + + int r = vhost_iova_tree_map_alloc(v->iova_tree, &mem_region); + if (unlikely(r != IOVA_OK)) { + error_report("Can't allocate a mapping (%d)", r); + goto fail; + } + + iova = mem_region.iova; + } vhost_vdpa_iotlb_batch_begin_once(v); ret = vhost_vdpa_dma_map(v, iova, int128_get64(llsize), @@ -259,6 +276,20 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener, llsize = int128_sub(llend, int128_make64(iova)); + if (v->shadow_vqs_enabled) { + const DMAMap *result; + const void *vaddr = memory_region_get_ram_ptr(section->mr) + + section->offset_within_region + + (iova - section->offset_within_address_space); + DMAMap mem_region = { + .translated_addr = (hwaddr)(uintptr_t)vaddr, + .size = int128_get64(llsize) - 1, + }; + + result = vhost_iova_tree_find_iova(v->iova_tree, &mem_region); + iova = result->iova; + vhost_iova_tree_remove(v->iova_tree, &mem_region); + } vhost_vdpa_iotlb_batch_begin_once(v); ret = vhost_vdpa_dma_unmap(v, iova, int128_get64(llsize)); if (ret) { @@ -342,6 +373,55 @@ static bool vhost_vdpa_one_time_request(struct vhost_dev *dev) return v->index != 0; } +static int vhost_vdpa_get_dev_features(struct vhost_dev *dev, + uint64_t *features) +{ + int ret; + + ret = vhost_vdpa_call(dev, VHOST_GET_FEATURES, features); + trace_vhost_vdpa_get_features(dev, *features); + return ret; +} + +static int vhost_vdpa_init_svq(struct vhost_dev *hdev, struct vhost_vdpa *v, + Error **errp) +{ + g_autoptr(GPtrArray) shadow_vqs = NULL; + uint64_t dev_features, svq_features; + int r; + bool ok; + + if (!v->shadow_vqs_enabled) { + return 0; + } + + r = vhost_vdpa_get_dev_features(hdev, &dev_features); + if (r != 0) { + error_setg_errno(errp, -r, "Can't get vdpa device features"); + return r; + } + + svq_features = dev_features; + ok = vhost_svq_valid_features(svq_features, errp); + if (unlikely(!ok)) { + return -1; + } + + shadow_vqs = g_ptr_array_new_full(hdev->nvqs, vhost_svq_free); + for (unsigned n = 0; n < hdev->nvqs; ++n) { + g_autoptr(VhostShadowVirtqueue) svq = vhost_svq_new(v->iova_tree); + + if (unlikely(!svq)) { + error_setg(errp, "Cannot create svq %u", n); + return -1; + } + g_ptr_array_add(shadow_vqs, g_steal_pointer(&svq)); + } + + v->shadow_vqs = g_steal_pointer(&shadow_vqs); + return 0; +} + static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp) { struct vhost_vdpa *v; @@ -364,6 +444,10 @@ static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp) dev->opaque = opaque ; v->listener = vhost_vdpa_memory_listener; v->msg_type = VHOST_IOTLB_MSG_V2; + ret = vhost_vdpa_init_svq(dev, v, errp); + if (ret) { + goto err; + } vhost_vdpa_get_iova_range(v); @@ -375,6 +459,10 @@ static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp) VIRTIO_CONFIG_S_DRIVER); return 0; + +err: + ram_block_discard_disable(false); + return ret; } static void vhost_vdpa_host_notifier_uninit(struct vhost_dev *dev, @@ -445,8 +533,14 @@ static void vhost_vdpa_host_notifiers_uninit(struct vhost_dev *dev, int n) static void vhost_vdpa_host_notifiers_init(struct vhost_dev *dev) { + struct vhost_vdpa *v = dev->opaque; int i; + if (v->shadow_vqs_enabled) { + /* FIXME SVQ is not compatible with host notifiers mr */ + return; + } + for (i = dev->vq_index; i < dev->vq_index + dev->nvqs; i++) { if (vhost_vdpa_host_notifier_init(dev, i)) { goto err; @@ -460,6 +554,21 @@ err: return; } +static void vhost_vdpa_svq_cleanup(struct vhost_dev *dev) +{ + struct vhost_vdpa *v = dev->opaque; + size_t idx; + + if (!v->shadow_vqs) { + return; + } + + for (idx = 0; idx < v->shadow_vqs->len; ++idx) { + vhost_svq_stop(g_ptr_array_index(v->shadow_vqs, idx)); + } + g_ptr_array_free(v->shadow_vqs, true); +} + static int vhost_vdpa_cleanup(struct vhost_dev *dev) { struct vhost_vdpa *v; @@ -468,6 +577,7 @@ static int vhost_vdpa_cleanup(struct vhost_dev *dev) trace_vhost_vdpa_cleanup(dev, v); vhost_vdpa_host_notifiers_uninit(dev, dev->nvqs); memory_listener_unregister(&v->listener); + vhost_vdpa_svq_cleanup(dev); dev->opaque = NULL; ram_block_discard_disable(false); @@ -510,12 +620,29 @@ static int vhost_vdpa_set_mem_table(struct vhost_dev *dev, static int vhost_vdpa_set_features(struct vhost_dev *dev, uint64_t features) { + struct vhost_vdpa *v = dev->opaque; int ret; if (vhost_vdpa_one_time_request(dev)) { return 0; } + if (v->shadow_vqs_enabled) { + if ((v->acked_features ^ features) == BIT_ULL(VHOST_F_LOG_ALL)) { + /* + * QEMU is just trying to enable or disable logging. SVQ handles + * this sepparately, so no need to forward this. + */ + v->acked_features = features; + return 0; + } + + v->acked_features = features; + + /* We must not ack _F_LOG if SVQ is enabled */ + features &= ~BIT_ULL(VHOST_F_LOG_ALL); + } + trace_vhost_vdpa_set_features(dev, features); ret = vhost_vdpa_call(dev, VHOST_SET_FEATURES, &features); if (ret) { @@ -559,11 +686,26 @@ static int vhost_vdpa_get_device_id(struct vhost_dev *dev, return ret; } +static void vhost_vdpa_reset_svq(struct vhost_vdpa *v) +{ + if (!v->shadow_vqs_enabled) { + return; + } + + for (unsigned i = 0; i < v->shadow_vqs->len; ++i) { + VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, i); + vhost_svq_stop(svq); + } +} + static int vhost_vdpa_reset_device(struct vhost_dev *dev) { + struct vhost_vdpa *v = dev->opaque; int ret; uint8_t status = 0; + vhost_vdpa_reset_svq(v); + ret = vhost_vdpa_call(dev, VHOST_VDPA_SET_STATUS, &status); trace_vhost_vdpa_reset_device(dev, status); return ret; @@ -647,15 +789,311 @@ static int vhost_vdpa_get_config(struct vhost_dev *dev, uint8_t *config, return ret; } +static int vhost_vdpa_set_dev_vring_base(struct vhost_dev *dev, + struct vhost_vring_state *ring) +{ + trace_vhost_vdpa_set_vring_base(dev, ring->index, ring->num); + return vhost_vdpa_call(dev, VHOST_SET_VRING_BASE, ring); +} + +static int vhost_vdpa_set_vring_dev_kick(struct vhost_dev *dev, + struct vhost_vring_file *file) +{ + trace_vhost_vdpa_set_vring_kick(dev, file->index, file->fd); + return vhost_vdpa_call(dev, VHOST_SET_VRING_KICK, file); +} + +static int vhost_vdpa_set_vring_dev_call(struct vhost_dev *dev, + struct vhost_vring_file *file) +{ + trace_vhost_vdpa_set_vring_call(dev, file->index, file->fd); + return vhost_vdpa_call(dev, VHOST_SET_VRING_CALL, file); +} + +static int vhost_vdpa_set_vring_dev_addr(struct vhost_dev *dev, + struct vhost_vring_addr *addr) +{ + trace_vhost_vdpa_set_vring_addr(dev, addr->index, addr->flags, + addr->desc_user_addr, addr->used_user_addr, + addr->avail_user_addr, + addr->log_guest_addr); + + return vhost_vdpa_call(dev, VHOST_SET_VRING_ADDR, addr); + +} + +/** + * Set the shadow virtqueue descriptors to the device + * + * @dev: The vhost device model + * @svq: The shadow virtqueue + * @idx: The index of the virtqueue in the vhost device + * @errp: Error + * + * Note that this function does not rewind kick file descriptor if cannot set + * call one. + */ +static int vhost_vdpa_svq_set_fds(struct vhost_dev *dev, + VhostShadowVirtqueue *svq, unsigned idx, + Error **errp) +{ + struct vhost_vring_file file = { + .index = dev->vq_index + idx, + }; + const EventNotifier *event_notifier = &svq->hdev_kick; + int r; + + file.fd = event_notifier_get_fd(event_notifier); + r = vhost_vdpa_set_vring_dev_kick(dev, &file); + if (unlikely(r != 0)) { + error_setg_errno(errp, -r, "Can't set device kick fd"); + return r; + } + + event_notifier = &svq->hdev_call; + file.fd = event_notifier_get_fd(event_notifier); + r = vhost_vdpa_set_vring_dev_call(dev, &file); + if (unlikely(r != 0)) { + error_setg_errno(errp, -r, "Can't set device call fd"); + } + + return r; +} + +/** + * Unmap a SVQ area in the device + */ +static bool vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v, + const DMAMap *needle) +{ + const DMAMap *result = vhost_iova_tree_find_iova(v->iova_tree, needle); + hwaddr size; + int r; + + if (unlikely(!result)) { + error_report("Unable to find SVQ address to unmap"); + return false; + } + + size = ROUND_UP(result->size, qemu_real_host_page_size); + r = vhost_vdpa_dma_unmap(v, result->iova, size); + return r == 0; +} + +static bool vhost_vdpa_svq_unmap_rings(struct vhost_dev *dev, + const VhostShadowVirtqueue *svq) +{ + DMAMap needle = {}; + struct vhost_vdpa *v = dev->opaque; + struct vhost_vring_addr svq_addr; + bool ok; + + vhost_svq_get_vring_addr(svq, &svq_addr); + + needle.translated_addr = svq_addr.desc_user_addr; + ok = vhost_vdpa_svq_unmap_ring(v, &needle); + if (unlikely(!ok)) { + return false; + } + + needle.translated_addr = svq_addr.used_user_addr; + return vhost_vdpa_svq_unmap_ring(v, &needle); +} + +/** + * Map the SVQ area in the device + * + * @v: Vhost-vdpa device + * @needle: The area to search iova + * @errorp: Error pointer + */ +static bool vhost_vdpa_svq_map_ring(struct vhost_vdpa *v, DMAMap *needle, + Error **errp) +{ + int r; + + r = vhost_iova_tree_map_alloc(v->iova_tree, needle); + if (unlikely(r != IOVA_OK)) { + error_setg(errp, "Cannot allocate iova (%d)", r); + return false; + } + + r = vhost_vdpa_dma_map(v, needle->iova, needle->size + 1, + (void *)(uintptr_t)needle->translated_addr, + needle->perm == IOMMU_RO); + if (unlikely(r != 0)) { + error_setg_errno(errp, -r, "Cannot map region to device"); + vhost_iova_tree_remove(v->iova_tree, needle); + } + + return r == 0; +} + +/** + * Map the shadow virtqueue rings in the device + * + * @dev: The vhost device + * @svq: The shadow virtqueue + * @addr: Assigned IOVA addresses + * @errp: Error pointer + */ +static bool vhost_vdpa_svq_map_rings(struct vhost_dev *dev, + const VhostShadowVirtqueue *svq, + struct vhost_vring_addr *addr, + Error **errp) +{ + DMAMap device_region, driver_region; + struct vhost_vring_addr svq_addr; + struct vhost_vdpa *v = dev->opaque; + size_t device_size = vhost_svq_device_area_size(svq); + size_t driver_size = vhost_svq_driver_area_size(svq); + size_t avail_offset; + bool ok; + + ERRP_GUARD(); + vhost_svq_get_vring_addr(svq, &svq_addr); + + driver_region = (DMAMap) { + .translated_addr = svq_addr.desc_user_addr, + .size = driver_size - 1, + .perm = IOMMU_RO, + }; + ok = vhost_vdpa_svq_map_ring(v, &driver_region, errp); + if (unlikely(!ok)) { + error_prepend(errp, "Cannot create vq driver region: "); + return false; + } + addr->desc_user_addr = driver_region.iova; + avail_offset = svq_addr.avail_user_addr - svq_addr.desc_user_addr; + addr->avail_user_addr = driver_region.iova + avail_offset; + + device_region = (DMAMap) { + .translated_addr = svq_addr.used_user_addr, + .size = device_size - 1, + .perm = IOMMU_RW, + }; + ok = vhost_vdpa_svq_map_ring(v, &device_region, errp); + if (unlikely(!ok)) { + error_prepend(errp, "Cannot create vq device region: "); + vhost_vdpa_svq_unmap_ring(v, &driver_region); + } + addr->used_user_addr = device_region.iova; + + return ok; +} + +static bool vhost_vdpa_svq_setup(struct vhost_dev *dev, + VhostShadowVirtqueue *svq, unsigned idx, + Error **errp) +{ + uint16_t vq_index = dev->vq_index + idx; + struct vhost_vring_state s = { + .index = vq_index, + }; + int r; + + r = vhost_vdpa_set_dev_vring_base(dev, &s); + if (unlikely(r)) { + error_setg_errno(errp, -r, "Cannot set vring base"); + return false; + } + + r = vhost_vdpa_svq_set_fds(dev, svq, idx, errp); + return r == 0; +} + +static bool vhost_vdpa_svqs_start(struct vhost_dev *dev) +{ + struct vhost_vdpa *v = dev->opaque; + Error *err = NULL; + unsigned i; + + if (!v->shadow_vqs) { + return true; + } + + for (i = 0; i < v->shadow_vqs->len; ++i) { + VirtQueue *vq = virtio_get_queue(dev->vdev, dev->vq_index + i); + VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, i); + struct vhost_vring_addr addr = { + .index = i, + }; + int r; + bool ok = vhost_vdpa_svq_setup(dev, svq, i, &err); + if (unlikely(!ok)) { + goto err; + } + + vhost_svq_start(svq, dev->vdev, vq); + ok = vhost_vdpa_svq_map_rings(dev, svq, &addr, &err); + if (unlikely(!ok)) { + goto err_map; + } + + /* Override vring GPA set by vhost subsystem */ + r = vhost_vdpa_set_vring_dev_addr(dev, &addr); + if (unlikely(r != 0)) { + error_setg_errno(&err, -r, "Cannot set device address"); + goto err_set_addr; + } + } + + return true; + +err_set_addr: + vhost_vdpa_svq_unmap_rings(dev, g_ptr_array_index(v->shadow_vqs, i)); + +err_map: + vhost_svq_stop(g_ptr_array_index(v->shadow_vqs, i)); + +err: + error_reportf_err(err, "Cannot setup SVQ %u: ", i); + for (unsigned j = 0; j < i; ++j) { + VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, j); + vhost_vdpa_svq_unmap_rings(dev, svq); + vhost_svq_stop(svq); + } + + return false; +} + +static bool vhost_vdpa_svqs_stop(struct vhost_dev *dev) +{ + struct vhost_vdpa *v = dev->opaque; + + if (!v->shadow_vqs) { + return true; + } + + for (unsigned i = 0; i < v->shadow_vqs->len; ++i) { + VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, i); + bool ok = vhost_vdpa_svq_unmap_rings(dev, svq); + if (unlikely(!ok)) { + return false; + } + } + + return true; +} + static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) { struct vhost_vdpa *v = dev->opaque; + bool ok; trace_vhost_vdpa_dev_start(dev, started); if (started) { vhost_vdpa_host_notifiers_init(dev); + ok = vhost_vdpa_svqs_start(dev); + if (unlikely(!ok)) { + return -1; + } vhost_vdpa_set_vring_ready(dev); } else { + ok = vhost_vdpa_svqs_stop(dev); + if (unlikely(!ok)) { + return -1; + } vhost_vdpa_host_notifiers_uninit(dev, dev->nvqs); } @@ -679,7 +1117,8 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) static int vhost_vdpa_set_log_base(struct vhost_dev *dev, uint64_t base, struct vhost_log *log) { - if (vhost_vdpa_one_time_request(dev)) { + struct vhost_vdpa *v = dev->opaque; + if (v->shadow_vqs_enabled || vhost_vdpa_one_time_request(dev)) { return 0; } @@ -691,11 +1130,17 @@ static int vhost_vdpa_set_log_base(struct vhost_dev *dev, uint64_t base, static int vhost_vdpa_set_vring_addr(struct vhost_dev *dev, struct vhost_vring_addr *addr) { - trace_vhost_vdpa_set_vring_addr(dev, addr->index, addr->flags, - addr->desc_user_addr, addr->used_user_addr, - addr->avail_user_addr, - addr->log_guest_addr); - return vhost_vdpa_call(dev, VHOST_SET_VRING_ADDR, addr); + struct vhost_vdpa *v = dev->opaque; + + if (v->shadow_vqs_enabled) { + /* + * Device vring addr was set at device start. SVQ base is handled by + * VirtQueue code. + */ + return 0; + } + + return vhost_vdpa_set_vring_dev_addr(dev, addr); } static int vhost_vdpa_set_vring_num(struct vhost_dev *dev, @@ -708,15 +1153,41 @@ static int vhost_vdpa_set_vring_num(struct vhost_dev *dev, static int vhost_vdpa_set_vring_base(struct vhost_dev *dev, struct vhost_vring_state *ring) { - trace_vhost_vdpa_set_vring_base(dev, ring->index, ring->num); - return vhost_vdpa_call(dev, VHOST_SET_VRING_BASE, ring); + struct vhost_vdpa *v = dev->opaque; + + if (v->shadow_vqs_enabled) { + /* + * Device vring base was set at device start. SVQ base is handled by + * VirtQueue code. + */ + return 0; + } + + return vhost_vdpa_set_dev_vring_base(dev, ring); } static int vhost_vdpa_get_vring_base(struct vhost_dev *dev, struct vhost_vring_state *ring) { + struct vhost_vdpa *v = dev->opaque; int ret; + if (v->shadow_vqs_enabled) { + VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, + ring->index); + + /* + * Setting base as last used idx, so destination will see as available + * all the entries that the device did not use, including the in-flight + * processing ones. + * + * TODO: This is ok for networking, but other kinds of devices might + * have problems with these retransmissions. + */ + ring->num = svq->last_used_idx; + return 0; + } + ret = vhost_vdpa_call(dev, VHOST_GET_VRING_BASE, ring); trace_vhost_vdpa_get_vring_base(dev, ring->index, ring->num); return ret; @@ -725,24 +1196,45 @@ static int vhost_vdpa_get_vring_base(struct vhost_dev *dev, static int vhost_vdpa_set_vring_kick(struct vhost_dev *dev, struct vhost_vring_file *file) { - trace_vhost_vdpa_set_vring_kick(dev, file->index, file->fd); - return vhost_vdpa_call(dev, VHOST_SET_VRING_KICK, file); + struct vhost_vdpa *v = dev->opaque; + int vdpa_idx = file->index - dev->vq_index; + + if (v->shadow_vqs_enabled) { + VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, vdpa_idx); + vhost_svq_set_svq_kick_fd(svq, file->fd); + return 0; + } else { + return vhost_vdpa_set_vring_dev_kick(dev, file); + } } static int vhost_vdpa_set_vring_call(struct vhost_dev *dev, struct vhost_vring_file *file) { - trace_vhost_vdpa_set_vring_call(dev, file->index, file->fd); - return vhost_vdpa_call(dev, VHOST_SET_VRING_CALL, file); + struct vhost_vdpa *v = dev->opaque; + + if (v->shadow_vqs_enabled) { + int vdpa_idx = file->index - dev->vq_index; + VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, vdpa_idx); + + vhost_svq_set_svq_call_fd(svq, file->fd); + return 0; + } else { + return vhost_vdpa_set_vring_dev_call(dev, file); + } } static int vhost_vdpa_get_features(struct vhost_dev *dev, uint64_t *features) { - int ret; + struct vhost_vdpa *v = dev->opaque; + int ret = vhost_vdpa_get_dev_features(dev, features); + + if (ret == 0 && v->shadow_vqs_enabled) { + /* Add SVQ logging capabilities */ + *features |= BIT_ULL(VHOST_F_LOG_ALL); + } - ret = vhost_vdpa_call(dev, VHOST_GET_FEATURES, features); - trace_vhost_vdpa_get_features(dev, *features); return ret; } |