diff options
Diffstat (limited to 'hw/virtio')
| -rw-r--r-- | hw/virtio/Makefile.objs | 1 | ||||
| -rw-r--r-- | hw/virtio/dataplane/Makefile.objs | 1 | ||||
| -rw-r--r-- | hw/virtio/dataplane/vring.c | 549 | ||||
| -rw-r--r-- | hw/virtio/vhost-user.c | 20 | ||||
| -rw-r--r-- | hw/virtio/vhost.c | 43 | ||||
| -rw-r--r-- | hw/virtio/virtio-balloon.c | 33 | ||||
| -rw-r--r-- | hw/virtio/virtio-pci.c | 14 | ||||
| -rw-r--r-- | hw/virtio/virtio.c | 21 |
8 files changed, 119 insertions, 563 deletions
diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs index 19b224a44d..3e2b175da8 100644 --- a/hw/virtio/Makefile.objs +++ b/hw/virtio/Makefile.objs @@ -2,7 +2,6 @@ common-obj-y += virtio-rng.o common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o common-obj-y += virtio-bus.o common-obj-y += virtio-mmio.o -obj-$(CONFIG_VIRTIO) += dataplane/ obj-y += virtio.o virtio-balloon.o obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o diff --git a/hw/virtio/dataplane/Makefile.objs b/hw/virtio/dataplane/Makefile.objs deleted file mode 100644 index 753a9cab44..0000000000 --- a/hw/virtio/dataplane/Makefile.objs +++ /dev/null @@ -1 +0,0 @@ -obj-y += vring.o diff --git a/hw/virtio/dataplane/vring.c b/hw/virtio/dataplane/vring.c deleted file mode 100644 index 4308d9f055..0000000000 --- a/hw/virtio/dataplane/vring.c +++ /dev/null @@ -1,549 +0,0 @@ -/* Copyright 2012 Red Hat, Inc. - * Copyright IBM, Corp. 2012 - * - * Based on Linux 2.6.39 vhost code: - * Copyright (C) 2009 Red Hat, Inc. - * Copyright (C) 2006 Rusty Russell IBM Corporation - * - * Author: Michael S. Tsirkin <mst@redhat.com> - * Stefan Hajnoczi <stefanha@redhat.com> - * - * Inspiration, some code, and most witty comments come from - * Documentation/virtual/lguest/lguest.c, by Rusty Russell - * - * This work is licensed under the terms of the GNU GPL, version 2. - */ - -#include "qemu/osdep.h" -#include "trace.h" -#include "hw/hw.h" -#include "exec/memory.h" -#include "exec/address-spaces.h" -#include "hw/virtio/virtio-access.h" -#include "hw/virtio/dataplane/vring.h" -#include "hw/virtio/dataplane/vring-accessors.h" -#include "qemu/error-report.h" - -/* vring_map can be coupled with vring_unmap or (if you still have the - * value returned in *mr) memory_region_unref. - * Returns NULL on failure. - * Callers that can handle a partial mapping must supply mapped_len pointer to - * get the actual length mapped. - * Passing mapped_len == NULL requires either a full mapping or a failure. - */ -static void *vring_map(MemoryRegion **mr, hwaddr phys, - hwaddr len, hwaddr *mapped_len, - bool is_write) -{ - MemoryRegionSection section = memory_region_find(get_system_memory(), phys, len); - uint64_t size; - - if (!section.mr) { - goto out; - } - - size = int128_get64(section.size); - assert(size); - - /* Passing mapped_len == NULL requires either a full mapping or a failure. */ - if (!mapped_len && size < len) { - goto out; - } - - if (is_write && section.readonly) { - goto out; - } - if (!memory_region_is_ram(section.mr)) { - goto out; - } - - /* Ignore regions with dirty logging, we cannot mark them dirty */ - if (memory_region_get_dirty_log_mask(section.mr)) { - goto out; - } - - if (mapped_len) { - *mapped_len = MIN(size, len); - } - - *mr = section.mr; - return memory_region_get_ram_ptr(section.mr) + section.offset_within_region; - -out: - memory_region_unref(section.mr); - *mr = NULL; - return NULL; -} - -static void vring_unmap(void *buffer, bool is_write) -{ - ram_addr_t addr; - MemoryRegion *mr; - - mr = qemu_ram_addr_from_host(buffer, &addr); - memory_region_unref(mr); -} - -/* Map the guest's vring to host memory */ -bool vring_setup(Vring *vring, VirtIODevice *vdev, int n) -{ - struct vring *vr = &vring->vr; - hwaddr addr; - hwaddr size; - void *ptr; - - vring->broken = false; - vr->num = virtio_queue_get_num(vdev, n); - - addr = virtio_queue_get_desc_addr(vdev, n); - size = virtio_queue_get_desc_size(vdev, n); - /* Map the descriptor area as read only */ - ptr = vring_map(&vring->mr_desc, addr, size, NULL, false); - if (!ptr) { - error_report("Failed to map 0x%" HWADDR_PRIx " byte for vring desc " - "at 0x%" HWADDR_PRIx, - size, addr); - goto out_err_desc; - } - vr->desc = ptr; - - addr = virtio_queue_get_avail_addr(vdev, n); - size = virtio_queue_get_avail_size(vdev, n); - /* Add the size of the used_event_idx */ - size += sizeof(uint16_t); - /* Map the driver area as read only */ - ptr = vring_map(&vring->mr_avail, addr, size, NULL, false); - if (!ptr) { - error_report("Failed to map 0x%" HWADDR_PRIx " byte for vring avail " - "at 0x%" HWADDR_PRIx, - size, addr); - goto out_err_avail; - } - vr->avail = ptr; - - addr = virtio_queue_get_used_addr(vdev, n); - size = virtio_queue_get_used_size(vdev, n); - /* Add the size of the avail_event_idx */ - size += sizeof(uint16_t); - /* Map the device area as read-write */ - ptr = vring_map(&vring->mr_used, addr, size, NULL, true); - if (!ptr) { - error_report("Failed to map 0x%" HWADDR_PRIx " byte for vring used " - "at 0x%" HWADDR_PRIx, - size, addr); - goto out_err_used; - } - vr->used = ptr; - - vring->last_avail_idx = virtio_queue_get_last_avail_idx(vdev, n); - vring->last_used_idx = vring_get_used_idx(vdev, vring); - vring->signalled_used = 0; - vring->signalled_used_valid = false; - - trace_vring_setup(virtio_queue_get_ring_addr(vdev, n), - vring->vr.desc, vring->vr.avail, vring->vr.used); - return true; - -out_err_used: - memory_region_unref(vring->mr_avail); -out_err_avail: - memory_region_unref(vring->mr_desc); -out_err_desc: - vring->broken = true; - return false; -} - -void vring_teardown(Vring *vring, VirtIODevice *vdev, int n) -{ - virtio_queue_set_last_avail_idx(vdev, n, vring->last_avail_idx); - virtio_queue_invalidate_signalled_used(vdev, n); - - memory_region_unref(vring->mr_desc); - memory_region_unref(vring->mr_avail); - memory_region_unref(vring->mr_used); -} - -/* Disable guest->host notifies */ -void vring_disable_notification(VirtIODevice *vdev, Vring *vring) -{ - if (!virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) { - vring_set_used_flags(vdev, vring, VRING_USED_F_NO_NOTIFY); - } -} - -/* Enable guest->host notifies - * - * Return true if the vring is empty, false if there are more requests. - */ -bool vring_enable_notification(VirtIODevice *vdev, Vring *vring) -{ - if (virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) { - vring_avail_event(&vring->vr) = vring->vr.avail->idx; - } else { - vring_clear_used_flags(vdev, vring, VRING_USED_F_NO_NOTIFY); - } - smp_mb(); /* ensure update is seen before reading avail_idx */ - return !vring_more_avail(vdev, vring); -} - -/* This is stolen from linux/drivers/vhost/vhost.c:vhost_notify() */ -bool vring_should_notify(VirtIODevice *vdev, Vring *vring) -{ - uint16_t old, new; - bool v; - /* Flush out used index updates. This is paired - * with the barrier that the Guest executes when enabling - * interrupts. */ - smp_mb(); - - if (virtio_vdev_has_feature(vdev, VIRTIO_F_NOTIFY_ON_EMPTY) && - unlikely(!vring_more_avail(vdev, vring))) { - return true; - } - - if (!virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) { - return !(vring_get_avail_flags(vdev, vring) & - VRING_AVAIL_F_NO_INTERRUPT); - } - old = vring->signalled_used; - v = vring->signalled_used_valid; - new = vring->signalled_used = vring->last_used_idx; - vring->signalled_used_valid = true; - - if (unlikely(!v)) { - return true; - } - - return vring_need_event(virtio_tswap16(vdev, vring_used_event(&vring->vr)), - new, old); -} - -typedef struct VirtQueueCurrentElement { - unsigned in_num; - unsigned out_num; - hwaddr addr[VIRTQUEUE_MAX_SIZE]; - struct iovec iov[VIRTQUEUE_MAX_SIZE]; -} VirtQueueCurrentElement; - -static int get_desc(Vring *vring, VirtQueueCurrentElement *elem, - struct vring_desc *desc) -{ - unsigned *num; - struct iovec *iov; - hwaddr *addr; - MemoryRegion *mr; - hwaddr len; - - if (desc->flags & VRING_DESC_F_WRITE) { - num = &elem->in_num; - iov = &elem->iov[elem->out_num + *num]; - addr = &elem->addr[elem->out_num + *num]; - } else { - num = &elem->out_num; - iov = &elem->iov[*num]; - addr = &elem->addr[*num]; - - /* If it's an output descriptor, they're all supposed - * to come before any input descriptors. */ - if (unlikely(elem->in_num)) { - error_report("Descriptor has out after in"); - return -EFAULT; - } - } - - while (desc->len) { - /* Stop for now if there are not enough iovecs available. */ - if (*num >= VIRTQUEUE_MAX_SIZE) { - error_report("Invalid SG num: %u", *num); - return -EFAULT; - } - - iov->iov_base = vring_map(&mr, desc->addr, desc->len, &len, - desc->flags & VRING_DESC_F_WRITE); - if (!iov->iov_base) { - error_report("Failed to map descriptor addr %#" PRIx64 " len %u", - (uint64_t)desc->addr, desc->len); - return -EFAULT; - } - - /* The MemoryRegion is looked up again and unref'ed later, leave the - * ref in place. */ - (iov++)->iov_len = len; - *addr++ = desc->addr; - desc->len -= len; - desc->addr += len; - *num += 1; - } - - return 0; -} - -static void copy_in_vring_desc(VirtIODevice *vdev, - const struct vring_desc *guest, - struct vring_desc *host) -{ - host->addr = virtio_ldq_p(vdev, &guest->addr); - host->len = virtio_ldl_p(vdev, &guest->len); - host->flags = virtio_lduw_p(vdev, &guest->flags); - host->next = virtio_lduw_p(vdev, &guest->next); -} - -static bool read_vring_desc(VirtIODevice *vdev, - hwaddr guest, - struct vring_desc *host) -{ - if (address_space_read(&address_space_memory, guest, MEMTXATTRS_UNSPECIFIED, - (uint8_t *)host, sizeof *host)) { - return false; - } - host->addr = virtio_tswap64(vdev, host->addr); - host->len = virtio_tswap32(vdev, host->len); - host->flags = virtio_tswap16(vdev, host->flags); - host->next = virtio_tswap16(vdev, host->next); - return true; -} - -/* This is stolen from linux/drivers/vhost/vhost.c. */ -static int get_indirect(VirtIODevice *vdev, Vring *vring, - VirtQueueCurrentElement *cur_elem, - struct vring_desc *indirect) -{ - struct vring_desc desc; - unsigned int i = 0, count, found = 0; - int ret; - - /* Sanity check */ - if (unlikely(indirect->len % sizeof(desc))) { - error_report("Invalid length in indirect descriptor: " - "len %#x not multiple of %#zx", - indirect->len, sizeof(desc)); - vring->broken = true; - return -EFAULT; - } - - count = indirect->len / sizeof(desc); - /* Buffers are chained via a 16 bit next field, so - * we can have at most 2^16 of these. */ - if (unlikely(count > USHRT_MAX + 1)) { - error_report("Indirect buffer length too big: %d", indirect->len); - vring->broken = true; - return -EFAULT; - } - - do { - /* Translate indirect descriptor */ - if (!read_vring_desc(vdev, indirect->addr + found * sizeof(desc), - &desc)) { - error_report("Failed to read indirect descriptor " - "addr %#" PRIx64 " len %zu", - (uint64_t)indirect->addr + found * sizeof(desc), - sizeof(desc)); - vring->broken = true; - return -EFAULT; - } - - /* Ensure descriptor has been loaded before accessing fields */ - barrier(); /* read_barrier_depends(); */ - - if (unlikely(++found > count)) { - error_report("Loop detected: last one at %u " - "indirect size %u", i, count); - vring->broken = true; - return -EFAULT; - } - - if (unlikely(desc.flags & VRING_DESC_F_INDIRECT)) { - error_report("Nested indirect descriptor"); - vring->broken = true; - return -EFAULT; - } - - ret = get_desc(vring, cur_elem, &desc); - if (ret < 0) { - vring->broken |= (ret == -EFAULT); - return ret; - } - i = desc.next; - } while (desc.flags & VRING_DESC_F_NEXT); - return 0; -} - -static void vring_unmap_element(VirtQueueElement *elem) -{ - int i; - - /* This assumes that the iovecs, if changed, are never moved past - * the end of the valid area. This is true if iovec manipulations - * are done with iov_discard_front and iov_discard_back. - */ - for (i = 0; i < elem->out_num; i++) { - vring_unmap(elem->out_sg[i].iov_base, false); - } - - for (i = 0; i < elem->in_num; i++) { - vring_unmap(elem->in_sg[i].iov_base, true); - } -} - -/* This looks in the virtqueue and for the first available buffer, and converts - * it to an iovec for convenient access. Since descriptors consist of some - * number of output then some number of input descriptors, it's actually two - * iovecs, but we pack them into one and note how many of each there were. - * - * This function returns the descriptor number found, or vq->num (which is - * never a valid descriptor number) if none was found. A negative code is - * returned on error. - * - * Stolen from linux/drivers/vhost/vhost.c. - */ -void *vring_pop(VirtIODevice *vdev, Vring *vring, size_t sz) -{ - struct vring_desc desc; - unsigned int i, head, found = 0, num = vring->vr.num; - uint16_t avail_idx, last_avail_idx; - VirtQueueCurrentElement cur_elem; - VirtQueueElement *elem = NULL; - int ret; - - /* If there was a fatal error then refuse operation */ - if (vring->broken) { - ret = -EFAULT; - goto out; - } - - cur_elem.in_num = cur_elem.out_num = 0; - - /* Check it isn't doing very strange things with descriptor numbers. */ - last_avail_idx = vring->last_avail_idx; - avail_idx = vring_get_avail_idx(vdev, vring); - barrier(); /* load indices now and not again later */ - - if (unlikely((uint16_t)(avail_idx - last_avail_idx) > num)) { - error_report("Guest moved used index from %u to %u", - last_avail_idx, avail_idx); - ret = -EFAULT; - goto out; - } - - /* If there's nothing new since last we looked. */ - if (avail_idx == last_avail_idx) { - ret = -EAGAIN; - goto out; - } - - /* Only get avail ring entries after they have been exposed by guest. */ - smp_rmb(); - - /* Grab the next descriptor number they're advertising, and increment - * the index we've seen. */ - head = vring_get_avail_ring(vdev, vring, last_avail_idx % num); - - /* If their number is silly, that's an error. */ - if (unlikely(head >= num)) { - error_report("Guest says index %u > %u is available", head, num); - ret = -EFAULT; - goto out; - } - - i = head; - do { - if (unlikely(i >= num)) { - error_report("Desc index is %u > %u, head = %u", i, num, head); - ret = -EFAULT; - goto out; - } - if (unlikely(++found > num)) { - error_report("Loop detected: last one at %u vq size %u head %u", - i, num, head); - ret = -EFAULT; - goto out; - } - copy_in_vring_desc(vdev, &vring->vr.desc[i], &desc); - - /* Ensure descriptor is loaded before accessing fields */ - barrier(); - - if (desc.flags & VRING_DESC_F_INDIRECT) { - ret = get_indirect(vdev, vring, &cur_elem, &desc); - if (ret < 0) { - goto out; - } - continue; - } - - ret = get_desc(vring, &cur_elem, &desc); - if (ret < 0) { - goto out; - } - - i = desc.next; - } while (desc.flags & VRING_DESC_F_NEXT); - - /* On success, increment avail index. */ - vring->last_avail_idx++; - if (virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) { - vring_avail_event(&vring->vr) = - virtio_tswap16(vdev, vring->last_avail_idx); - } - - /* Now copy what we have collected and mapped */ - elem = virtqueue_alloc_element(sz, cur_elem.out_num, cur_elem.in_num); - elem->index = head; - for (i = 0; i < cur_elem.out_num; i++) { - elem->out_addr[i] = cur_elem.addr[i]; - elem->out_sg[i] = cur_elem.iov[i]; - } - for (i = 0; i < cur_elem.in_num; i++) { - elem->in_addr[i] = cur_elem.addr[cur_elem.out_num + i]; - elem->in_sg[i] = cur_elem.iov[cur_elem.out_num + i]; - } - - return elem; - -out: - assert(ret < 0); - if (ret == -EFAULT) { - vring->broken = true; - } - - for (i = 0; i < cur_elem.out_num + cur_elem.in_num; i++) { - vring_unmap(cur_elem.iov[i].iov_base, false); - } - - g_free(elem); - return NULL; -} - -/* After we've used one of their buffers, we tell them about it. - * - * Stolen from linux/drivers/vhost/vhost.c. - */ -void vring_push(VirtIODevice *vdev, Vring *vring, VirtQueueElement *elem, - int len) -{ - unsigned int head = elem->index; - uint16_t new; - - vring_unmap_element(elem); - - /* Don't touch vring if a fatal error occurred */ - if (vring->broken) { - return; - } - - /* The virtqueue contains a ring of used buffers. Get a pointer to the - * next entry in that used ring. */ - vring_set_used_ring_id(vdev, vring, vring->last_used_idx % vring->vr.num, - head); - vring_set_used_ring_len(vdev, vring, vring->last_used_idx % vring->vr.num, - len); - - /* Make sure buffer is written before we update index. */ - smp_wmb(); - - new = ++vring->last_used_idx; - vring_set_used_idx(vdev, vring, new); - if (unlikely((int16_t)(new - vring->signalled_used) < (uint16_t)1)) { - vring->signalled_used_valid = false; - } -} diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 7fde1370e0..7ed3dd9a13 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -611,6 +611,25 @@ static int vhost_user_migration_done(struct vhost_dev *dev, char* mac_addr) return -1; } +static bool vhost_user_can_merge(struct vhost_dev *dev, + uint64_t start1, uint64_t size1, + uint64_t start2, uint64_t size2) +{ + ram_addr_t ram_addr; + int mfd, rfd; + MemoryRegion *mr; + + mr = qemu_ram_addr_from_host((void *)(uintptr_t)start1, &ram_addr); + assert(mr); + mfd = qemu_get_ram_fd(ram_addr); + + mr = qemu_ram_addr_from_host((void *)(uintptr_t)start2, &ram_addr); + assert(mr); + rfd = qemu_get_ram_fd(ram_addr); + + return mfd == rfd; +} + const VhostOps user_ops = { .backend_type = VHOST_BACKEND_TYPE_USER, .vhost_backend_init = vhost_user_init, @@ -633,4 +652,5 @@ const VhostOps user_ops = { .vhost_set_vring_enable = vhost_user_set_vring_enable, .vhost_requires_shm_log = vhost_user_requires_shm_log, .vhost_migration_done = vhost_user_migration_done, + .vhost_backend_can_merge = vhost_user_can_merge, }; diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index 7dff75547d..392d848819 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -260,6 +260,13 @@ static void vhost_dev_assign_memory(struct vhost_dev *dev, continue; } + if (dev->vhost_ops->vhost_backend_can_merge && + !dev->vhost_ops->vhost_backend_can_merge(dev, uaddr, size, + reg->userspace_addr, + reg->memory_size)) { + continue; + } + if (merged) { --to; assert(to >= 0); @@ -749,6 +756,27 @@ static void vhost_log_stop(MemoryListener *listener, /* FIXME: implement */ } +/* The vhost driver natively knows how to handle the vrings of non + * cross-endian legacy devices and modern devices. Only legacy devices + * exposed to a bi-endian guest may require the vhost driver to use a + * specific endianness. + */ +static inline bool vhost_needs_vring_endian(VirtIODevice *vdev) +{ + if (virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1)) { + return false; + } +#ifdef TARGET_IS_BIENDIAN +#ifdef HOST_WORDS_BIGENDIAN + return vdev->device_endian == VIRTIO_DEVICE_ENDIAN_LITTLE; +#else + return vdev->device_endian == VIRTIO_DEVICE_ENDIAN_BIG; +#endif +#else + return false; +#endif +} + static int vhost_virtqueue_set_vring_endian_legacy(struct vhost_dev *dev, bool is_big_endian, int vhost_vq_index) @@ -799,8 +827,7 @@ static int vhost_virtqueue_start(struct vhost_dev *dev, return -errno; } - if (!virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1) && - virtio_legacy_is_cross_endian(vdev)) { + if (vhost_needs_vring_endian(vdev)) { r = vhost_virtqueue_set_vring_endian_legacy(dev, virtio_is_big_endian(vdev), vhost_vq_index); @@ -855,6 +882,14 @@ static int vhost_virtqueue_start(struct vhost_dev *dev, /* Clear and discard previous events if any. */ event_notifier_test_and_clear(&vq->masked_notifier); + /* Init vring in unmasked state, unless guest_notifier_mask + * will do it later. + */ + if (!vdev->use_guest_notifier_mask) { + /* TODO: check and handle errors. */ + vhost_virtqueue_mask(dev, vdev, idx, false); + } + return 0; fail_kick: @@ -896,8 +931,7 @@ static void vhost_virtqueue_stop(struct vhost_dev *dev, /* In the cross-endian case, we need to reset the vring endianness to * native as legacy devices expect so by default. */ - if (!virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1) && - virtio_legacy_is_cross_endian(vdev)) { + if (vhost_needs_vring_endian(vdev)) { r = vhost_virtqueue_set_vring_endian_legacy(dev, !virtio_is_big_endian(vdev), vhost_vq_index); @@ -1148,6 +1182,7 @@ void vhost_virtqueue_mask(struct vhost_dev *hdev, VirtIODevice *vdev, int n, struct vhost_vring_file file; if (mask) { + assert(vdev->use_guest_notifier_mask); file.fd = event_notifier_get_fd(&hdev->vqs[index].masked_notifier); } else { file.fd = event_notifier_get_fd(virtio_queue_get_guest_notifier(vvq)); diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c index a382f43f92..e9c30e9615 100644 --- a/hw/virtio/virtio-balloon.c +++ b/hw/virtio/virtio-balloon.c @@ -305,6 +305,39 @@ static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data) memcpy(config_data, &config, sizeof(struct virtio_balloon_config)); } +static int build_dimm_list(Object *obj, void *opaque) +{ + GSList **list = opaque; + + if (object_dynamic_cast(obj, TYPE_PC_DIMM)) { + DeviceState *dev = DEVICE(obj); + if (dev->realized) { /* only realized DIMMs matter */ + *list = g_slist_prepend(*list, dev); + } + } + + object_child_foreach(obj, build_dimm_list, opaque); + return 0; +} + +static ram_addr_t get_current_ram_size(void) +{ + GSList *list = NULL, *item; + ram_addr_t size = ram_size; + + build_dimm_list(qdev_get_machine(), &list); + for (item = list; item; item = g_slist_next(item)) { + Object *obj = OBJECT(item->data); + if (!strcmp(object_get_typename(obj), TYPE_PC_DIMM)) { + size += object_property_get_int(obj, PC_DIMM_SIZE_PROP, + &error_abort); + } + } + g_slist_free(list); + + return size; +} + static void virtio_balloon_set_config(VirtIODevice *vdev, const uint8_t *config_data) { diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index 5494ff4a49..440776c06c 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -806,7 +806,7 @@ static int kvm_virtio_pci_vector_use(VirtIOPCIProxy *proxy, int nvqs) /* If guest supports masking, set up irqfd now. * Otherwise, delay until unmasked in the frontend. */ - if (k->guest_notifier_mask) { + if (vdev->use_guest_notifier_mask && k->guest_notifier_mask) { ret = kvm_virtio_pci_irqfd_use(proxy, queue_no, vector); if (ret < 0) { kvm_virtio_pci_vq_vector_release(proxy, vector); @@ -822,7 +822,7 @@ undo: if (vector >= msix_nr_vectors_allocated(dev)) { continue; } - if (k->guest_notifier_mask) { + if (vdev->use_guest_notifier_mask && k->guest_notifier_mask) { kvm_virtio_pci_irqfd_release(proxy, queue_no, vector); } kvm_virtio_pci_vq_vector_release(proxy, vector); @@ -849,7 +849,7 @@ static void kvm_virtio_pci_vector_release(VirtIOPCIProxy *proxy, int nvqs) /* If guest supports masking, clean up irqfd now. * Otherwise, it was cleaned when masked in the frontend. */ - if (k->guest_notifier_mask) { + if (vdev->use_guest_notifier_mask && k->guest_notifier_mask) { kvm_virtio_pci_irqfd_release(proxy, queue_no, vector); } kvm_virtio_pci_vq_vector_release(proxy, vector); @@ -882,7 +882,7 @@ static int virtio_pci_vq_vector_unmask(VirtIOPCIProxy *proxy, /* If guest supports masking, irqfd is already setup, unmask it. * Otherwise, set it up now. */ - if (k->guest_notifier_mask) { + if (vdev->use_guest_notifier_mask && k->guest_notifier_mask) { k->guest_notifier_mask(vdev, queue_no, false); /* Test after unmasking to avoid losing events. */ if (k->guest_notifier_pending && @@ -905,7 +905,7 @@ static void virtio_pci_vq_vector_mask(VirtIOPCIProxy *proxy, /* If guest supports masking, keep irqfd but mask it. * Otherwise, clean it up now. */ - if (k->guest_notifier_mask) { + if (vdev->use_guest_notifier_mask && k->guest_notifier_mask) { k->guest_notifier_mask(vdev, queue_no, true); } else { kvm_virtio_pci_irqfd_release(proxy, queue_no, vector); @@ -1022,7 +1022,9 @@ static int virtio_pci_set_guest_notifier(DeviceState *d, int n, bool assign, event_notifier_cleanup(notifier); } - if (!msix_enabled(&proxy->pci_dev) && vdc->guest_notifier_mask) { + if (!msix_enabled(&proxy->pci_dev) && + vdev->use_guest_notifier_mask && + vdc->guest_notifier_mask) { vdc->guest_notifier_mask(vdev, n, !assign); } diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index 90f25451d0..08275a9848 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -1162,7 +1162,7 @@ void virtio_irq(VirtQueue *vq) virtio_notify_vector(vq->vdev, vq->vector); } -static bool vring_notify(VirtIODevice *vdev, VirtQueue *vq) +bool virtio_should_notify(VirtIODevice *vdev, VirtQueue *vq) { uint16_t old, new; bool v; @@ -1187,7 +1187,7 @@ static bool vring_notify(VirtIODevice *vdev, VirtQueue *vq) void virtio_notify(VirtIODevice *vdev, VirtQueue *vq) { - if (!vring_notify(vdev, vq)) { + if (!virtio_should_notify(vdev, vq)) { return; } @@ -1677,6 +1677,7 @@ void virtio_init(VirtIODevice *vdev, const char *name, vdev->vmstate = qemu_add_vm_change_state_handler(virtio_vmstate_change, vdev); vdev->device_endian = virtio_default_endian(); + vdev->use_guest_notifier_mask = true; } hwaddr virtio_queue_get_desc_addr(VirtIODevice *vdev, int n) @@ -1785,6 +1786,22 @@ static void virtio_queue_host_notifier_read(EventNotifier *n) } } +void virtio_queue_aio_set_host_notifier_handler(VirtQueue *vq, AioContext *ctx, + bool assign, bool set_handler) +{ + if (assign && set_handler) { + aio_set_event_notifier(ctx, &vq->host_notifier, true, + virtio_queue_host_notifier_read); + } else { + aio_set_event_notifier(ctx, &vq->host_notifier, true, NULL); + } + if (!assign) { + /* Test and clear notifier before after disabling event, + * in case poll callback didn't have time to run. */ + virtio_queue_host_notifier_read(&vq->host_notifier); + } +} + void virtio_queue_set_host_notifier_fd_handler(VirtQueue *vq, bool assign, bool set_handler) { |