diff options
42 files changed, 1075 insertions, 233 deletions
diff --git a/docs/system/device-emulation.rst b/docs/system/device-emulation.rst index 7afcfd8064..19944f526c 100644 --- a/docs/system/device-emulation.rst +++ b/docs/system/device-emulation.rst @@ -88,3 +88,4 @@ Emulated Devices devices/usb.rst devices/vhost-user.rst devices/virtio-pmem.rst + devices/vhost-user-rng.rst diff --git a/docs/system/devices/vhost-user-rng.rst b/docs/system/devices/vhost-user-rng.rst new file mode 100644 index 0000000000..a145d4105c --- /dev/null +++ b/docs/system/devices/vhost-user-rng.rst @@ -0,0 +1,39 @@ +QEMU vhost-user-rng - RNG emulation +=================================== + +Background +---------- + +What follows builds on the material presented in vhost-user.rst - it should +be reviewed before moving forward with the content in this file. + +Description +----------- + +The vhost-user-rng device implementation was designed to work with a random +number generator daemon such as the one found in the vhost-device crate of +the rust-vmm project available on github [1]. + +[1]. https://github.com/rust-vmm/vhost-device + +Examples +-------- + +The daemon should be started first: + +:: + + host# vhost-device-rng --socket-path=rng.sock -c 1 -m 512 -p 1000 + +The QEMU invocation needs to create a chardev socket the device can +use to communicate as well as share the guests memory over a memfd. + +:: + + host# qemu-system \ + -chardev socket,path=$(PATH)/rng.sock,id=rng0 \ + -device vhost-user-rng-pci,chardev=rng0 \ + -m 4096 \ + -object memory-backend-file,id=mem,size=4G,mem-path=/dev/shm,share=on \ + -numa node,memdev=mem \ + ... diff --git a/hw/net/vhost_net-stub.c b/hw/net/vhost_net-stub.c index a7f4252630..89d71cfb8e 100644 --- a/hw/net/vhost_net-stub.c +++ b/hw/net/vhost_net-stub.c @@ -33,13 +33,13 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options) int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, - int total_queues) + int data_queue_pairs, int cvq) { return -ENOSYS; } void vhost_net_stop(VirtIODevice *dev, NetClientState *ncs, - int total_queues) + int data_queue_pairs, int cvq) { } diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index 386ec2eaa2..0d888f29a6 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -231,9 +231,11 @@ fail: return NULL; } -static void vhost_net_set_vq_index(struct vhost_net *net, int vq_index) +static void vhost_net_set_vq_index(struct vhost_net *net, int vq_index, + int last_index) { net->dev.vq_index = vq_index; + net->dev.last_index = last_index; } static int vhost_net_start_one(struct vhost_net *net, @@ -315,25 +317,37 @@ static void vhost_net_stop_one(struct vhost_net *net, } int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, - int total_queues) + int data_queue_pairs, int cvq) { BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(dev))); VirtioBusState *vbus = VIRTIO_BUS(qbus); VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus); + int total_notifiers = data_queue_pairs * 2 + cvq; + VirtIONet *n = VIRTIO_NET(dev); + int nvhosts = data_queue_pairs + cvq; struct vhost_net *net; - int r, e, i; + int r, e, i, last_index = data_queue_pairs * 2; NetClientState *peer; + if (!cvq) { + last_index -= 1; + } + if (!k->set_guest_notifiers) { error_report("binding does not support guest notifiers"); return -ENOSYS; } - for (i = 0; i < total_queues; i++) { + for (i = 0; i < nvhosts; i++) { + + if (i < data_queue_pairs) { + peer = qemu_get_peer(ncs, i); + } else { /* Control Virtqueue */ + peer = qemu_get_peer(ncs, n->max_queue_pairs); + } - peer = qemu_get_peer(ncs, i); net = get_vhost_net(peer); - vhost_net_set_vq_index(net, i * 2); + vhost_net_set_vq_index(net, i * 2, last_index); /* Suppress the masking guest notifiers on vhost user * because vhost user doesn't interrupt masking/unmasking @@ -344,14 +358,18 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, } } - r = k->set_guest_notifiers(qbus->parent, total_queues * 2, true); + r = k->set_guest_notifiers(qbus->parent, total_notifiers, true); if (r < 0) { error_report("Error binding guest notifier: %d", -r); goto err; } - for (i = 0; i < total_queues; i++) { - peer = qemu_get_peer(ncs, i); + for (i = 0; i < nvhosts; i++) { + if (i < data_queue_pairs) { + peer = qemu_get_peer(ncs, i); + } else { + peer = qemu_get_peer(ncs, n->max_queue_pairs); + } r = vhost_net_start_one(get_vhost_net(peer), dev); if (r < 0) { @@ -375,7 +393,7 @@ err_start: peer = qemu_get_peer(ncs , i); vhost_net_stop_one(get_vhost_net(peer), dev); } - e = k->set_guest_notifiers(qbus->parent, total_queues * 2, false); + e = k->set_guest_notifiers(qbus->parent, total_notifiers, false); if (e < 0) { fprintf(stderr, "vhost guest notifier cleanup failed: %d\n", e); fflush(stderr); @@ -385,18 +403,27 @@ err: } void vhost_net_stop(VirtIODevice *dev, NetClientState *ncs, - int total_queues) + int data_queue_pairs, int cvq) { BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(dev))); VirtioBusState *vbus = VIRTIO_BUS(qbus); VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus); + VirtIONet *n = VIRTIO_NET(dev); + NetClientState *peer; + int total_notifiers = data_queue_pairs * 2 + cvq; + int nvhosts = data_queue_pairs + cvq; int i, r; - for (i = 0; i < total_queues; i++) { - vhost_net_stop_one(get_vhost_net(ncs[i].peer), dev); + for (i = 0; i < nvhosts; i++) { + if (i < data_queue_pairs) { + peer = qemu_get_peer(ncs, i); + } else { + peer = qemu_get_peer(ncs, n->max_queue_pairs); + } + vhost_net_stop_one(get_vhost_net(peer), dev); } - r = k->set_guest_notifiers(qbus->parent, total_queues * 2, false); + r = k->set_guest_notifiers(qbus->parent, total_notifiers, false); if (r < 0) { fprintf(stderr, "vhost guest notifier cleanup failed: %d\n", r); fflush(stderr); diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 09e173a558..f2014d5ea0 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -54,7 +54,7 @@ #define VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE 256 #define VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE 256 -/* for now, only allow larger queues; with virtio-1, guest can downsize */ +/* for now, only allow larger queue_pairs; with virtio-1, guest can downsize */ #define VIRTIO_NET_RX_QUEUE_MIN_SIZE VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE #define VIRTIO_NET_TX_QUEUE_MIN_SIZE VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE @@ -131,7 +131,7 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config) int ret = 0; memset(&netcfg, 0 , sizeof(struct virtio_net_config)); virtio_stw_p(vdev, &netcfg.status, n->status); - virtio_stw_p(vdev, &netcfg.max_virtqueue_pairs, n->max_queues); + virtio_stw_p(vdev, &netcfg.max_virtqueue_pairs, n->max_queue_pairs); virtio_stw_p(vdev, &netcfg.mtu, n->net_conf.mtu); memcpy(netcfg.mac, n->mac, ETH_ALEN); virtio_stl_p(vdev, &netcfg.speed, n->net_conf.speed); @@ -243,7 +243,8 @@ static void virtio_net_vhost_status(VirtIONet *n, uint8_t status) { VirtIODevice *vdev = VIRTIO_DEVICE(n); NetClientState *nc = qemu_get_queue(n->nic); - int queues = n->multiqueue ? n->max_queues : 1; + int queue_pairs = n->multiqueue ? n->max_queue_pairs : 1; + int cvq = n->max_ncs - n->max_queue_pairs; if (!get_vhost_net(nc->peer)) { return; @@ -266,7 +267,7 @@ static void virtio_net_vhost_status(VirtIONet *n, uint8_t status) /* Any packets outstanding? Purge them to avoid touching rings * when vhost is running. */ - for (i = 0; i < queues; i++) { + for (i = 0; i < queue_pairs; i++) { NetClientState *qnc = qemu_get_subqueue(n->nic, i); /* Purge both directions: TX and RX. */ @@ -285,14 +286,14 @@ static void virtio_net_vhost_status(VirtIONet *n, uint8_t status) } n->vhost_started = 1; - r = vhost_net_start(vdev, n->nic->ncs, queues); + r = vhost_net_start(vdev, n->nic->ncs, queue_pairs, cvq); if (r < 0) { error_report("unable to start vhost net: %d: " "falling back on userspace virtio", -r); n->vhost_started = 0; } } else { - vhost_net_stop(vdev, n->nic->ncs, queues); + vhost_net_stop(vdev, n->nic->ncs, queue_pairs, cvq); n->vhost_started = 0; } } @@ -309,11 +310,11 @@ static int virtio_net_set_vnet_endian_one(VirtIODevice *vdev, } static bool virtio_net_set_vnet_endian(VirtIODevice *vdev, NetClientState *ncs, - int queues, bool enable) + int queue_pairs, bool enable) { int i; - for (i = 0; i < queues; i++) { + for (i = 0; i < queue_pairs; i++) { if (virtio_net_set_vnet_endian_one(vdev, ncs[i].peer, enable) < 0 && enable) { while (--i >= 0) { @@ -330,7 +331,7 @@ static bool virtio_net_set_vnet_endian(VirtIODevice *vdev, NetClientState *ncs, static void virtio_net_vnet_endian_status(VirtIONet *n, uint8_t status) { VirtIODevice *vdev = VIRTIO_DEVICE(n); - int queues = n->multiqueue ? n->max_queues : 1; + int queue_pairs = n->multiqueue ? n->max_queue_pairs : 1; if (virtio_net_started(n, status)) { /* Before using the device, we tell the network backend about the @@ -339,14 +340,14 @@ static void virtio_net_vnet_endian_status(VirtIONet *n, uint8_t status) * virtio-net code. */ n->needs_vnet_hdr_swap = virtio_net_set_vnet_endian(vdev, n->nic->ncs, - queues, true); + queue_pairs, true); } else if (virtio_net_started(n, vdev->status)) { /* After using the device, we need to reset the network backend to * the default (guest native endianness), otherwise the guest may * lose network connectivity if it is rebooted into a different * endianness. */ - virtio_net_set_vnet_endian(vdev, n->nic->ncs, queues, false); + virtio_net_set_vnet_endian(vdev, n->nic->ncs, queue_pairs, false); } } @@ -368,12 +369,12 @@ static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status) virtio_net_vnet_endian_status(n, status); virtio_net_vhost_status(n, status); - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { NetClientState *ncs = qemu_get_subqueue(n->nic, i); bool queue_started; q = &n->vqs[i]; - if ((!n->multiqueue && i != 0) || i >= n->curr_queues) { + if ((!n->multiqueue && i != 0) || i >= n->curr_queue_pairs) { queue_status = 0; } else { queue_status = status; @@ -540,7 +541,7 @@ static void virtio_net_reset(VirtIODevice *vdev) n->nouni = 0; n->nobcast = 0; /* multiqueue is disabled by default */ - n->curr_queues = 1; + n->curr_queue_pairs = 1; timer_del(n->announce_timer.tm); n->announce_timer.round = 0; n->status &= ~VIRTIO_NET_S_ANNOUNCE; @@ -556,7 +557,7 @@ static void virtio_net_reset(VirtIODevice *vdev) memset(n->vlans, 0, MAX_VLAN >> 3); /* Flush any async TX */ - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { NetClientState *nc = qemu_get_subqueue(n->nic, i); if (nc->peer) { @@ -610,7 +611,7 @@ static void virtio_net_set_mrg_rx_bufs(VirtIONet *n, int mergeable_rx_bufs, sizeof(struct virtio_net_hdr); } - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { nc = qemu_get_subqueue(n->nic, i); if (peer_has_vnet_hdr(n) && @@ -655,7 +656,7 @@ static int peer_attach(VirtIONet *n, int index) return 0; } - if (n->max_queues == 1) { + if (n->max_queue_pairs == 1) { return 0; } @@ -681,7 +682,7 @@ static int peer_detach(VirtIONet *n, int index) return tap_disable(nc->peer); } -static void virtio_net_set_queues(VirtIONet *n) +static void virtio_net_set_queue_pairs(VirtIONet *n) { int i; int r; @@ -690,8 +691,8 @@ static void virtio_net_set_queues(VirtIONet *n) return; } - for (i = 0; i < n->max_queues; i++) { - if (i < n->curr_queues) { + for (i = 0; i < n->max_queue_pairs; i++) { + if (i < n->curr_queue_pairs) { r = peer_attach(n, i); assert(!r); } else { @@ -905,7 +906,7 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features) virtio_net_apply_guest_offloads(n); } - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { NetClientState *nc = qemu_get_subqueue(n->nic, i); if (!get_vhost_net(nc->peer)) { @@ -1232,7 +1233,7 @@ static uint16_t virtio_net_handle_rss(VirtIONet *n, VirtIODevice *vdev = VIRTIO_DEVICE(n); struct virtio_net_rss_config cfg; size_t s, offset = 0, size_get; - uint16_t queues, i; + uint16_t queue_pairs, i; struct { uint16_t us; uint8_t b; @@ -1274,7 +1275,7 @@ static uint16_t virtio_net_handle_rss(VirtIONet *n, } n->rss_data.default_queue = do_rss ? virtio_lduw_p(vdev, &cfg.unclassified_queue) : 0; - if (n->rss_data.default_queue >= n->max_queues) { + if (n->rss_data.default_queue >= n->max_queue_pairs) { err_msg = "Invalid default queue"; err_value = n->rss_data.default_queue; goto error; @@ -1303,14 +1304,14 @@ static uint16_t virtio_net_handle_rss(VirtIONet *n, size_get = sizeof(temp); s = iov_to_buf(iov, iov_cnt, offset, &temp, size_get); if (s != size_get) { - err_msg = "Can't get queues"; + err_msg = "Can't get queue_pairs"; err_value = (uint32_t)s; goto error; } - queues = do_rss ? virtio_lduw_p(vdev, &temp.us) : n->curr_queues; - if (queues == 0 || queues > n->max_queues) { - err_msg = "Invalid number of queues"; - err_value = queues; + queue_pairs = do_rss ? virtio_lduw_p(vdev, &temp.us) : n->curr_queue_pairs; + if (queue_pairs == 0 || queue_pairs > n->max_queue_pairs) { + err_msg = "Invalid number of queue_pairs"; + err_value = queue_pairs; goto error; } if (temp.b > VIRTIO_NET_RSS_MAX_KEY_SIZE) { @@ -1325,7 +1326,7 @@ static uint16_t virtio_net_handle_rss(VirtIONet *n, } if (!temp.b && !n->rss_data.hash_types) { virtio_net_disable_rss(n); - return queues; + return queue_pairs; } offset += size_get; size_get = temp.b; @@ -1358,7 +1359,7 @@ static uint16_t virtio_net_handle_rss(VirtIONet *n, trace_virtio_net_rss_enable(n->rss_data.hash_types, n->rss_data.indirections_len, temp.b); - return queues; + return queue_pairs; error: trace_virtio_net_rss_error(err_msg, err_value); virtio_net_disable_rss(n); @@ -1369,15 +1370,15 @@ static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd, struct iovec *iov, unsigned int iov_cnt) { VirtIODevice *vdev = VIRTIO_DEVICE(n); - uint16_t queues; + uint16_t queue_pairs; virtio_net_disable_rss(n); if (cmd == VIRTIO_NET_CTRL_MQ_HASH_CONFIG) { - queues = virtio_net_handle_rss(n, iov, iov_cnt, false); - return queues ? VIRTIO_NET_OK : VIRTIO_NET_ERR; + queue_pairs = virtio_net_handle_rss(n, iov, iov_cnt, false); + return queue_pairs ? VIRTIO_NET_OK : VIRTIO_NET_ERR; } if (cmd == VIRTIO_NET_CTRL_MQ_RSS_CONFIG) { - queues = virtio_net_handle_rss(n, iov, iov_cnt, true); + queue_pairs = virtio_net_handle_rss(n, iov, iov_cnt, true); } else if (cmd == VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET) { struct virtio_net_ctrl_mq mq; size_t s; @@ -1388,24 +1389,24 @@ static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd, if (s != sizeof(mq)) { return VIRTIO_NET_ERR; } - queues = virtio_lduw_p(vdev, &mq.virtqueue_pairs); + queue_pairs = virtio_lduw_p(vdev, &mq.virtqueue_pairs); } else { return VIRTIO_NET_ERR; } - if (queues < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN || - queues > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX || - queues > n->max_queues || + if (queue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN || + queue_pairs > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX || + queue_pairs > n->max_queue_pairs || !n->multiqueue) { return VIRTIO_NET_ERR; } - n->curr_queues = queues; - /* stop the backend before changing the number of queues to avoid handling a + n->curr_queue_pairs = queue_pairs; + /* stop the backend before changing the number of queue_pairs to avoid handling a * disabled queue */ virtio_net_set_status(vdev, vdev->status); - virtio_net_set_queues(n); + virtio_net_set_queue_pairs(n); return VIRTIO_NET_OK; } @@ -1483,7 +1484,7 @@ static bool virtio_net_can_receive(NetClientState *nc) return false; } - if (nc->queue_index >= n->curr_queues) { + if (nc->queue_index >= n->curr_queue_pairs) { return false; } @@ -2763,11 +2764,11 @@ static void virtio_net_del_queue(VirtIONet *n, int index) virtio_del_queue(vdev, index * 2 + 1); } -static void virtio_net_change_num_queues(VirtIONet *n, int new_max_queues) +static void virtio_net_change_num_queue_pairs(VirtIONet *n, int new_max_queue_pairs) { VirtIODevice *vdev = VIRTIO_DEVICE(n); int old_num_queues = virtio_get_num_queues(vdev); - int new_num_queues = new_max_queues * 2 + 1; + int new_num_queues = new_max_queue_pairs * 2 + 1; int i; assert(old_num_queues >= 3); @@ -2800,12 +2801,12 @@ static void virtio_net_change_num_queues(VirtIONet *n, int new_max_queues) static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue) { - int max = multiqueue ? n->max_queues : 1; + int max = multiqueue ? n->max_queue_pairs : 1; n->multiqueue = multiqueue; - virtio_net_change_num_queues(n, max); + virtio_net_change_num_queue_pairs(n, max); - virtio_net_set_queues(n); + virtio_net_set_queue_pairs(n); } static int virtio_net_post_load_device(void *opaque, int version_id) @@ -2838,7 +2839,7 @@ static int virtio_net_post_load_device(void *opaque, int version_id) */ n->saved_guest_offloads = n->curr_guest_offloads; - virtio_net_set_queues(n); + virtio_net_set_queue_pairs(n); /* Find the first multicast entry in the saved MAC filter */ for (i = 0; i < n->mac_table.in_use; i++) { @@ -2851,7 +2852,7 @@ static int virtio_net_post_load_device(void *opaque, int version_id) /* nc.link_down can't be migrated, so infer link_down according * to link status bit in n->status */ link_down = (n->status & VIRTIO_NET_S_LINK_UP) == 0; - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { qemu_get_subqueue(n->nic, i)->link_down = link_down; } @@ -2916,9 +2917,9 @@ static const VMStateDescription vmstate_virtio_net_queue_tx_waiting = { }, }; -static bool max_queues_gt_1(void *opaque, int version_id) +static bool max_queue_pairs_gt_1(void *opaque, int version_id) { - return VIRTIO_NET(opaque)->max_queues > 1; + return VIRTIO_NET(opaque)->max_queue_pairs > 1; } static bool has_ctrl_guest_offloads(void *opaque, int version_id) @@ -2943,13 +2944,13 @@ static bool mac_table_doesnt_fit(void *opaque, int version_id) struct VirtIONetMigTmp { VirtIONet *parent; VirtIONetQueue *vqs_1; - uint16_t curr_queues_1; + uint16_t curr_queue_pairs_1; uint8_t has_ufo; uint32_t has_vnet_hdr; }; /* The 2nd and subsequent tx_waiting flags are loaded later than - * the 1st entry in the queues and only if there's more than one + * the 1st entry in the queue_pairs and only if there's more than one * entry. We use the tmp mechanism to calculate a temporary * pointer and count and also validate the count. */ @@ -2959,9 +2960,9 @@ static int virtio_net_tx_waiting_pre_save(void *opaque) struct VirtIONetMigTmp *tmp = opaque; tmp->vqs_1 = tmp->parent->vqs + 1; - tmp->curr_queues_1 = tmp->parent->curr_queues - 1; - if (tmp->parent->curr_queues == 0) { - tmp->curr_queues_1 = 0; + tmp->curr_queue_pairs_1 = tmp->parent->curr_queue_pairs - 1; + if (tmp->parent->curr_queue_pairs == 0) { + tmp->curr_queue_pairs_1 = 0; } return 0; @@ -2974,9 +2975,9 @@ static int virtio_net_tx_waiting_pre_load(void *opaque) /* Reuse the pointer setup from save */ virtio_net_tx_waiting_pre_save(opaque); - if (tmp->parent->curr_queues > tmp->parent->max_queues) { - error_report("virtio-net: curr_queues %x > max_queues %x", - tmp->parent->curr_queues, tmp->parent->max_queues); + if (tmp->parent->curr_queue_pairs > tmp->parent->max_queue_pairs) { + error_report("virtio-net: curr_queue_pairs %x > max_queue_pairs %x", + tmp->parent->curr_queue_pairs, tmp->parent->max_queue_pairs); return -EINVAL; } @@ -2990,7 +2991,7 @@ static const VMStateDescription vmstate_virtio_net_tx_waiting = { .pre_save = virtio_net_tx_waiting_pre_save, .fields = (VMStateField[]) { VMSTATE_STRUCT_VARRAY_POINTER_UINT16(vqs_1, struct VirtIONetMigTmp, - curr_queues_1, + curr_queue_pairs_1, vmstate_virtio_net_queue_tx_waiting, struct VirtIONetQueue), VMSTATE_END_OF_LIST() @@ -3132,9 +3133,9 @@ static const VMStateDescription vmstate_virtio_net_device = { VMSTATE_UINT8(nobcast, VirtIONet), VMSTATE_WITH_TMP(VirtIONet, struct VirtIONetMigTmp, vmstate_virtio_net_has_ufo), - VMSTATE_SINGLE_TEST(max_queues, VirtIONet, max_queues_gt_1, 0, + VMSTATE_SINGLE_TEST(max_queue_pairs, VirtIONet, max_queue_pairs_gt_1, 0, vmstate_info_uint16_equal, uint16_t), - VMSTATE_UINT16_TEST(curr_queues, VirtIONet, max_queues_gt_1), + VMSTATE_UINT16_TEST(curr_queue_pairs, VirtIONet, max_queue_pairs_gt_1), VMSTATE_WITH_TMP(VirtIONet, struct VirtIONetMigTmp, vmstate_virtio_net_tx_waiting), VMSTATE_UINT64_TEST(curr_guest_offloads, VirtIONet, @@ -3299,19 +3300,41 @@ static bool failover_hide_primary_device(DeviceListener *listener, if (!device_opts) { return false; } - standby_id = qdict_get_try_str(device_opts, "failover_pair_id"); - if (g_strcmp0(standby_id, n->netclient_name) != 0) { + + if (!qdict_haskey(device_opts, "failover_pair_id")) { return false; } - if (n->primary_opts) { - error_setg(errp, "Cannot attach more than one primary device to '%s'", - n->netclient_name); + if (!qdict_haskey(device_opts, "id")) { + error_setg(errp, "Device with failover_pair_id needs to have id"); return false; } - n->primary_opts = qdict_clone_shallow(device_opts); - n->primary_opts_from_json = from_json; + standby_id = qdict_get_str(device_opts, "failover_pair_id"); + if (g_strcmp0(standby_id, n->netclient_name) != 0) { + return false; + } + + /* + * The hide helper can be called several times for a given device. + * Check there is only one primary for a virtio-net device but + * don't duplicate the qdict several times if it's called for the same + * device. + */ + if (n->primary_opts) { + const char *old, *new; + /* devices with failover_pair_id always have an id */ + old = qdict_get_str(n->primary_opts, "id"); + new = qdict_get_str(device_opts, "id"); + if (strcmp(old, new) != 0) { + error_setg(errp, "Cannot attach more than one primary device to " + "'%s': '%s' and '%s'", n->netclient_name, old, new); + return false; + } + } else { + n->primary_opts = qdict_clone_shallow(device_opts); + n->primary_opts_from_json = from_json; + } /* failover_primary_hidden is set during feature negotiation */ return qatomic_read(&n->failover_primary_hidden); @@ -3389,16 +3412,30 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) return; } - n->max_queues = MAX(n->nic_conf.peers.queues, 1); - if (n->max_queues * 2 + 1 > VIRTIO_QUEUE_MAX) { - error_setg(errp, "Invalid number of queues (= %" PRIu32 "), " + n->max_ncs = MAX(n->nic_conf.peers.queues, 1); + + /* + * Figure out the datapath queue pairs since the backend could + * provide control queue via peers as well. + */ + if (n->nic_conf.peers.queues) { + for (i = 0; i < n->max_ncs; i++) { + if (n->nic_conf.peers.ncs[i]->is_datapath) { + ++n->max_queue_pairs; + } + } + } + n->max_queue_pairs = MAX(n->max_queue_pairs, 1); + + if (n->max_queue_pairs * 2 + 1 > VIRTIO_QUEUE_MAX) { + error_setg(errp, "Invalid number of queue pairs (= %" PRIu32 "), " "must be a positive integer less than %d.", - n->max_queues, (VIRTIO_QUEUE_MAX - 1) / 2); + n->max_queue_pairs, (VIRTIO_QUEUE_MAX - 1) / 2); virtio_cleanup(vdev); return; } - n->vqs = g_malloc0(sizeof(VirtIONetQueue) * n->max_queues); - n->curr_queues = 1; + n->vqs = g_malloc0(sizeof(VirtIONetQueue) * n->max_queue_pairs); + n->curr_queue_pairs = 1; n->tx_timeout = n->net_conf.txtimer; if (n->net_conf.tx && strcmp(n->net_conf.tx, "timer") @@ -3412,7 +3449,7 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) n->net_conf.tx_queue_size = MIN(virtio_net_max_tx_queue_size(n), n->net_conf.tx_queue_size); - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { virtio_net_add_queue(n, i); } @@ -3436,13 +3473,13 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) object_get_typename(OBJECT(dev)), dev->id, n); } - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { n->nic->ncs[i].do_not_pad = true; } peer_test_vnet_hdr(n); if (peer_has_vnet_hdr(n)) { - for (i = 0; i < n->max_queues; i++) { + for (i = 0; i < n->max_queue_pairs; i++) { qemu_using_vnet_hdr(qemu_get_subqueue(n->nic, i)->peer, true); } n->host_hdr_len = sizeof(struct virtio_net_hdr); @@ -3484,7 +3521,7 @@ static void virtio_net_device_unrealize(DeviceState *dev) { VirtIODevice *vdev = VIRTIO_DEVICE(dev); VirtIONet *n = VIRTIO_NET(dev); - int i, max_queues; + int i, max_queue_pairs; if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) { virtio_net_unload_ebpf(n); @@ -3509,12 +3546,12 @@ static void virtio_net_device_unrealize(DeviceState *dev) assert(n->primary_opts == NULL); } - max_queues = n->multiqueue ? n->max_queues : 1; - for (i = 0; i < max_queues; i++) { + max_queue_pairs = n->multiqueue ? n->max_queue_pairs : 1; + for (i = 0; i < max_queue_pairs; i++) { virtio_net_del_queue(n, i); } /* delete also control vq */ - virtio_del_queue(vdev, max_queues * 2); + virtio_del_queue(vdev, max_queue_pairs * 2); qemu_announce_timer_del(&n->announce_timer, false); g_free(n->vqs); qemu_del_nic(n->nic); diff --git a/hw/pci/pci_bridge.c b/hw/pci/pci_bridge.c index d1f902ee86..da34c8ebcd 100644 --- a/hw/pci/pci_bridge.c +++ b/hw/pci/pci_bridge.c @@ -448,11 +448,11 @@ int pci_bridge_qemu_reserve_cap_init(PCIDevice *dev, int cap_offset, PCIBridgeQemuCap cap = { .len = cap_len, .type = REDHAT_PCI_CAP_RESOURCE_RESERVE, - .bus_res = res_reserve.bus, - .io = res_reserve.io, - .mem = res_reserve.mem_non_pref, - .mem_pref_32 = res_reserve.mem_pref_32, - .mem_pref_64 = res_reserve.mem_pref_64 + .bus_res = cpu_to_le32(res_reserve.bus), + .io = cpu_to_le64(res_reserve.io), + .mem = cpu_to_le32(res_reserve.mem_non_pref), + .mem_pref_32 = cpu_to_le32(res_reserve.mem_pref_32), + .mem_pref_64 = cpu_to_le64(res_reserve.mem_pref_64) }; int offset = pci_add_capability(dev, PCI_CAP_ID_VNDR, diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig index 35ab45e209..c144d42f9b 100644 --- a/hw/virtio/Kconfig +++ b/hw/virtio/Kconfig @@ -63,3 +63,8 @@ config VHOST_USER_I2C bool default y depends on VIRTIO && VHOST_USER + +config VHOST_USER_RNG + bool + default y + depends on VIRTIO && VHOST_USER diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build index bc352a6009..521f7d64a8 100644 --- a/hw/virtio/meson.build +++ b/hw/virtio/meson.build @@ -27,6 +27,8 @@ virtio_ss.add(when: 'CONFIG_VIRTIO_IOMMU', if_true: files('virtio-iommu.c')) virtio_ss.add(when: 'CONFIG_VIRTIO_MEM', if_true: files('virtio-mem.c')) virtio_ss.add(when: 'CONFIG_VHOST_USER_I2C', if_true: files('vhost-user-i2c.c')) virtio_ss.add(when: ['CONFIG_VIRTIO_PCI', 'CONFIG_VHOST_USER_I2C'], if_true: files('vhost-user-i2c-pci.c')) +virtio_ss.add(when: 'CONFIG_VHOST_USER_RNG', if_true: files('vhost-user-rng.c')) +virtio_ss.add(when: ['CONFIG_VHOST_USER_RNG', 'CONFIG_VIRTIO_PCI'], if_true: files('vhost-user-rng-pci.c')) virtio_pci_ss = ss.source_set() virtio_pci_ss.add(when: 'CONFIG_VHOST_VSOCK', if_true: files('vhost-vsock-pci.c')) diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events index 8ed19e9d0c..650e521e35 100644 --- a/hw/virtio/trace-events +++ b/hw/virtio/trace-events @@ -52,6 +52,7 @@ vhost_vdpa_set_vring_call(void *dev, unsigned int index, int fd) "dev: %p index: vhost_vdpa_get_features(void *dev, uint64_t features) "dev: %p features: 0x%"PRIx64 vhost_vdpa_set_owner(void *dev) "dev: %p" vhost_vdpa_vq_get_addr(void *dev, void *vq, uint64_t desc_user_addr, uint64_t avail_user_addr, uint64_t used_user_addr) "dev: %p vq: %p desc_user_addr: 0x%"PRIx64" avail_user_addr: 0x%"PRIx64" used_user_addr: 0x%"PRIx64 +vhost_vdpa_get_iova_range(void *dev, uint64_t first, uint64_t last) "dev: %p first: 0x%"PRIx64" last: 0x%"PRIx64 # virtio.c virtqueue_alloc_element(void *elem, size_t sz, unsigned in_num, unsigned out_num) "elem %p size %zd in_num %u out_num %u" diff --git a/hw/virtio/vhost-user-rng-pci.c b/hw/virtio/vhost-user-rng-pci.c new file mode 100644 index 0000000000..c83dc86813 --- /dev/null +++ b/hw/virtio/vhost-user-rng-pci.c @@ -0,0 +1,79 @@ +/* + * Vhost-user RNG virtio device PCI glue + * + * Copyright (c) 2021 Mathieu Poirier <mathieu.poirier@linaro.org> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "hw/qdev-properties.h" +#include "hw/virtio/vhost-user-rng.h" +#include "virtio-pci.h" + +struct VHostUserRNGPCI { + VirtIOPCIProxy parent_obj; + VHostUserRNG vdev; +}; + +typedef struct VHostUserRNGPCI VHostUserRNGPCI; + +#define TYPE_VHOST_USER_RNG_PCI "vhost-user-rng-pci-base" + +DECLARE_INSTANCE_CHECKER(VHostUserRNGPCI, VHOST_USER_RNG_PCI, + TYPE_VHOST_USER_RNG_PCI) + +static Property vhost_user_rng_pci_properties[] = { + DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, + DEV_NVECTORS_UNSPECIFIED), + DEFINE_PROP_END_OF_LIST(), +}; + +static void vhost_user_rng_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VHostUserRNGPCI *dev = VHOST_USER_RNG_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&dev->vdev); + + if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) { + vpci_dev->nvectors = 1; + } + + qdev_realize(vdev, BUS(&vpci_dev->bus), errp); +} + +static void vhost_user_rng_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + k->realize = vhost_user_rng_pci_realize; + set_bit(DEVICE_CATEGORY_INPUT, dc->categories); + device_class_set_props(dc, vhost_user_rng_pci_properties); + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = 0; /* Set by virtio-pci based on virtio id */ + pcidev_k->revision = 0x00; + pcidev_k->class_id = PCI_CLASS_OTHERS; +} + +static void vhost_user_rng_pci_instance_init(Object *obj) +{ + VHostUserRNGPCI *dev = VHOST_USER_RNG_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VHOST_USER_RNG); +} + +static const VirtioPCIDeviceTypeInfo vhost_user_rng_pci_info = { + .base_name = TYPE_VHOST_USER_RNG_PCI, + .non_transitional_name = "vhost-user-rng-pci", + .instance_size = sizeof(VHostUserRNGPCI), + .instance_init = vhost_user_rng_pci_instance_init, + .class_init = vhost_user_rng_pci_class_init, +}; + +static void vhost_user_rng_pci_register(void) +{ + virtio_pci_types_register(&vhost_user_rng_pci_info); +} + +type_init(vhost_user_rng_pci_register); diff --git a/hw/virtio/vhost-user-rng.c b/hw/virtio/vhost-user-rng.c new file mode 100644 index 0000000000..209ee5bf9a --- /dev/null +++ b/hw/virtio/vhost-user-rng.c @@ -0,0 +1,289 @@ +/* + * Vhost-user RNG virtio device + * + * Copyright (c) 2021 Mathieu Poirier <mathieu.poirier@linaro.org> + * + * Implementation seriously tailored on vhost-user-i2c.c + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/qdev-properties.h" +#include "hw/virtio/virtio-bus.h" +#include "hw/virtio/vhost-user-rng.h" +#include "qemu/error-report.h" +#include "standard-headers/linux/virtio_ids.h" + +static void vu_rng_start(VirtIODevice *vdev) +{ + VHostUserRNG *rng = VHOST_USER_RNG(vdev); + BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev))); + VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); + int ret; + int i; + + if (!k->set_guest_notifiers) { + error_report("binding does not support guest notifiers"); + return; + } + + ret = vhost_dev_enable_notifiers(&rng->vhost_dev, vdev); + if (ret < 0) { + error_report("Error enabling host notifiers: %d", -ret); + return; + } + + ret = k->set_guest_notifiers(qbus->parent, rng->vhost_dev.nvqs, true); + if (ret < 0) { + error_report("Error binding guest notifier: %d", -ret); + goto err_host_notifiers; + } + + rng->vhost_dev.acked_features = vdev->guest_features; + ret = vhost_dev_start(&rng->vhost_dev, vdev); + if (ret < 0) { + error_report("Error starting vhost-user-rng: %d", -ret); + goto err_guest_notifiers; + } + + /* + * guest_notifier_mask/pending not used yet, so just unmask + * everything here. virtio-pci will do the right thing by + * enabling/disabling irqfd. + */ + for (i = 0; i < rng->vhost_dev.nvqs; i++) { + vhost_virtqueue_mask(&rng->vhost_dev, vdev, i, false); + } + + return; + +err_guest_notifiers: + k->set_guest_notifiers(qbus->parent, rng->vhost_dev.nvqs, false); +err_host_notifiers: + vhost_dev_disable_notifiers(&rng->vhost_dev, vdev); +} + +static void vu_rng_stop(VirtIODevice *vdev) +{ + VHostUserRNG *rng = VHOST_USER_RNG(vdev); + BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev))); + VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); + int ret; + + if (!k->set_guest_notifiers) { + return; + } + + vhost_dev_stop(&rng->vhost_dev, vdev); + + ret = k->set_guest_notifiers(qbus->parent, rng->vhost_dev.nvqs, false); + if (ret < 0) { + error_report("vhost guest notifier cleanup failed: %d", ret); + return; + } + + vhost_dev_disable_notifiers(&rng->vhost_dev, vdev); +} + +static void vu_rng_set_status(VirtIODevice *vdev, uint8_t status) +{ + VHostUserRNG *rng = VHOST_USER_RNG(vdev); + bool should_start = status & VIRTIO_CONFIG_S_DRIVER_OK; + + if (!vdev->vm_running) { + should_start = false; + } + + if (rng->vhost_dev.started == should_start) { + return; + } + + if (should_start) { + vu_rng_start(vdev); + } else { + vu_rng_stop(vdev); + } +} + +static uint64_t vu_rng_get_features(VirtIODevice *vdev, + uint64_t requested_features, Error **errp) +{ + /* No feature bits used yet */ + return requested_features; +} + +static void vu_rng_handle_output(VirtIODevice *vdev, VirtQueue *vq) +{ + /* + * Not normally called; it's the daemon that handles the queue; + * however virtio's cleanup path can call this. + */ +} + +static void vu_rng_guest_notifier_mask(VirtIODevice *vdev, int idx, bool mask) +{ + VHostUserRNG *rng = VHOST_USER_RNG(vdev); + + vhost_virtqueue_mask(&rng->vhost_dev, vdev, idx, mask); +} + +static bool vu_rng_guest_notifier_pending(VirtIODevice *vdev, int idx) +{ + VHostUserRNG *rng = VHOST_USER_RNG(vdev); + + return vhost_virtqueue_pending(&rng->vhost_dev, idx); +} + +static void vu_rng_connect(DeviceState *dev) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserRNG *rng = VHOST_USER_RNG(vdev); + + if (rng->connected) { + return; + } + + rng->connected = true; + + /* restore vhost state */ + if (virtio_device_started(vdev, vdev->status)) { + vu_rng_start(vdev); + } +} + +static void vu_rng_disconnect(DeviceState *dev) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserRNG *rng = VHOST_USER_RNG(vdev); + + if (!rng->connected) { + return; + } + + rng->connected = false; + + if (rng->vhost_dev.started) { + vu_rng_stop(vdev); + } +} + +static void vu_rng_event(void *opaque, QEMUChrEvent event) +{ + DeviceState *dev = opaque; + + switch (event) { + case CHR_EVENT_OPENED: + vu_rng_connect(dev); + break; + case CHR_EVENT_CLOSED: + vu_rng_disconnect(dev); + break; + case CHR_EVENT_BREAK: + case CHR_EVENT_MUX_IN: + case CHR_EVENT_MUX_OUT: + /* Ignore */ + break; + } +} + +static void vu_rng_device_realize(DeviceState *dev, Error **errp) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserRNG *rng = VHOST_USER_RNG(dev); + int ret; + + if (!rng->chardev.chr) { + error_setg(errp, "missing chardev"); + return; + } + + if (!vhost_user_init(&rng->vhost_user, &rng->chardev, errp)) { + return; + } + + virtio_init(vdev, "vhost-user-rng", VIRTIO_ID_RNG, 0); + + rng->req_vq = virtio_add_queue(vdev, 4, vu_rng_handle_output); + if (!rng->req_vq) { + error_setg_errno(errp, -1, "virtio_add_queue() failed"); + goto virtio_add_queue_failed; + } + + rng->vhost_dev.nvqs = 1; + rng->vhost_dev.vqs = g_new0(struct vhost_virtqueue, rng->vhost_dev.nvqs); + ret = vhost_dev_init(&rng->vhost_dev, &rng->vhost_user, + VHOST_BACKEND_TYPE_USER, 0, errp); + if (ret < 0) { + error_setg_errno(errp, -ret, "vhost_dev_init() failed"); + goto vhost_dev_init_failed; + } + + qemu_chr_fe_set_handlers(&rng->chardev, NULL, NULL, vu_rng_event, NULL, + dev, NULL, true); + + return; + +vhost_dev_init_failed: + virtio_delete_queue(rng->req_vq); +virtio_add_queue_failed: + virtio_cleanup(vdev); + vhost_user_cleanup(&rng->vhost_user); +} + +static void vu_rng_device_unrealize(DeviceState *dev) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserRNG *rng = VHOST_USER_RNG(dev); + + vu_rng_set_status(vdev, 0); + + vhost_dev_cleanup(&rng->vhost_dev); + g_free(rng->vhost_dev.vqs); + rng->vhost_dev.vqs = NULL; + virtio_delete_queue(rng->req_vq); + virtio_cleanup(vdev); + vhost_user_cleanup(&rng->vhost_user); +} + +static const VMStateDescription vu_rng_vmstate = { + .name = "vhost-user-rng", + .unmigratable = 1, +}; + +static Property vu_rng_properties[] = { + DEFINE_PROP_CHR("chardev", VHostUserRNG, chardev), + DEFINE_PROP_END_OF_LIST(), +}; + +static void vu_rng_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); + + device_class_set_props(dc, vu_rng_properties); + dc->vmsd = &vu_rng_vmstate; + set_bit(DEVICE_CATEGORY_INPUT, dc->categories); + + vdc->realize = vu_rng_device_realize; + vdc->unrealize = vu_rng_device_unrealize; + vdc->get_features = vu_rng_get_features; + vdc->set_status = vu_rng_set_status; + vdc->guest_notifier_mask = vu_rng_guest_notifier_mask; + vdc->guest_notifier_pending = vu_rng_guest_notifier_pending; +} + +static const TypeInfo vu_rng_info = { + .name = TYPE_VHOST_USER_RNG, + .parent = TYPE_VIRTIO_DEVICE, + .instance_size = sizeof(VHostUserRNG), + .class_init = vu_rng_class_init, +}; + +static void vu_rng_register_types(void) +{ + type_register_static(&vu_rng_info); +} + +type_init(vu_rng_register_types) diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 2c8556237f..bf6e50223c 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -1526,8 +1526,9 @@ static int vhost_user_slave_handle_vring_host_notifier(struct vhost_dev *dev, name = g_strdup_printf("vhost-user/host-notifier@%p mmaps[%d]", user, queue_idx); - memory_region_init_ram_device_ptr(&n->mr, OBJECT(vdev), name, - page_size, addr); + if (!n->mr.ram) /* Don't init again after suspend. */ + memory_region_init_ram_device_ptr(&n->mr, OBJECT(vdev), name, + page_size, addr); g_free(name); if (virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, true)) { diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c index 47d7a5a23d..12661fd5b1 100644 --- a/hw/virtio/vhost-vdpa.c +++ b/hw/virtio/vhost-vdpa.c @@ -24,19 +24,49 @@ #include "trace.h" #include "qemu-common.h" -static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section) +/* + * Return one past the end of the end of section. Be careful with uint64_t + * conversions! + */ +static Int128 vhost_vdpa_section_end(const MemoryRegionSection *section) +{ + Int128 llend = int128_make64(section->offset_within_address_space); + llend = int128_add(llend, section->size); + llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK)); + + return llend; +} + +static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section, + uint64_t iova_min, + uint64_t iova_max) { - return (!memory_region_is_ram(section->mr) && - !memory_region_is_iommu(section->mr)) || - /* vhost-vDPA doesn't allow MMIO to be mapped */ - memory_region_is_ram_device(section->mr) || - /* - * Sizing an enabled 64-bit BAR can cause spurious mappings to - * addresses in the upper part of the 64-bit address space. These - * are never accessed by the CPU and beyond the address width of - * some IOMMU hardware. TODO: VDPA should tell us the IOMMU width. - */ - section->offset_within_address_space & (1ULL << 63); + Int128 llend; + + if ((!memory_region_is_ram(section->mr) && + !memory_region_is_iommu(section->mr)) || + memory_region_is_protected(section->mr) || + /* vhost-vDPA doesn't allow MMIO to be mapped */ + memory_region_is_ram_device(section->mr)) { + return true; + } + + if (section->offset_within_address_space < iova_min) { + error_report("RAM section out of device range (min=0x%" PRIx64 + ", addr=0x%" HWADDR_PRIx ")", + iova_min, section->offset_within_address_space); + return true; + } + + llend = vhost_vdpa_section_end(section); + if (int128_gt(llend, int128_make64(iova_max))) { + error_report("RAM section out of device range (max=0x%" PRIx64 + ", end addr=0x%" PRIx64 ")", + iova_max, int128_get64(llend)); + return true; + } + + return false; } static int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size, @@ -148,7 +178,8 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener, void *vaddr; int ret; - if (vhost_vdpa_listener_skipped_section(section)) { + if (vhost_vdpa_listener_skipped_section(section, v->iova_range.first, + v->iova_range.last)) { return; } @@ -159,10 +190,7 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener, } iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); - llend = int128_make64(section->offset_within_address_space); - llend = int128_add(llend, section->size); - llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK)); - + llend = vhost_vdpa_section_end(section); if (int128_ge(int128_make64(iova), llend)) { return; } @@ -209,7 +237,8 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener, Int128 llend, llsize; int ret; - if (vhost_vdpa_listener_skipped_section(section)) { + if (vhost_vdpa_listener_skipped_section(section, v->iova_range.first, + v->iova_range.last)) { return; } @@ -220,9 +249,7 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener, } iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); - llend = int128_make64(section->offset_within_address_space); - llend = int128_add(llend, section->size); - llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK)); + llend = vhost_vdpa_section_end(section); trace_vhost_vdpa_listener_region_del(v, iova, int128_get64(llend)); @@ -279,6 +306,26 @@ static void vhost_vdpa_add_status(struct vhost_dev *dev, uint8_t status) vhost_vdpa_call(dev, VHOST_VDPA_SET_STATUS, &s); } +static void vhost_vdpa_get_iova_range(struct vhost_vdpa *v) +{ + int ret = vhost_vdpa_call(v->dev, VHOST_VDPA_GET_IOVA_RANGE, + &v->iova_range); + if (ret != 0) { + v->iova_range.first = 0; + v->iova_range.last = UINT64_MAX; + } + + trace_vhost_vdpa_get_iova_range(v->dev, v->iova_range.first, + v->iova_range.last); +} + +static bool vhost_vdpa_one_time_request(struct vhost_dev *dev) +{ + struct vhost_vdpa *v = dev->opaque; + + return v->index != 0; +} + static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp) { struct vhost_vdpa *v; @@ -291,6 +338,12 @@ static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp) v->listener = vhost_vdpa_memory_listener; v->msg_type = VHOST_IOTLB_MSG_V2; + vhost_vdpa_get_iova_range(v); + + if (vhost_vdpa_one_time_request(dev)) { + return 0; + } + vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE | VIRTIO_CONFIG_S_DRIVER); @@ -401,6 +454,10 @@ static int vhost_vdpa_memslots_limit(struct vhost_dev *dev) static int vhost_vdpa_set_mem_table(struct vhost_dev *dev, struct vhost_memory *mem) { + if (vhost_vdpa_one_time_request(dev)) { + return 0; + } + trace_vhost_vdpa_set_mem_table(dev, mem->nregions, mem->padding); if (trace_event_get_state_backends(TRACE_VHOST_VDPA_SET_MEM_TABLE) && trace_event_get_state_backends(TRACE_VHOST_VDPA_DUMP_REGIONS)) { @@ -424,6 +481,11 @@ static int vhost_vdpa_set_features(struct vhost_dev *dev, uint64_t features) { int ret; + + if (vhost_vdpa_one_time_request(dev)) { + return 0; + } + trace_vhost_vdpa_set_features(dev, features); ret = vhost_vdpa_call(dev, VHOST_SET_FEATURES, &features); uint8_t status = 0; @@ -448,9 +510,12 @@ static int vhost_vdpa_set_backend_cap(struct vhost_dev *dev) } features &= f; - r = vhost_vdpa_call(dev, VHOST_SET_BACKEND_FEATURES, &features); - if (r) { - return -EFAULT; + + if (vhost_vdpa_one_time_request(dev)) { + r = vhost_vdpa_call(dev, VHOST_SET_BACKEND_FEATURES, &features); + if (r) { + return -EFAULT; + } } dev->backend_cap = features; @@ -481,8 +546,8 @@ static int vhost_vdpa_get_vq_index(struct vhost_dev *dev, int idx) { assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs); - trace_vhost_vdpa_get_vq_index(dev, idx, idx - dev->vq_index); - return idx - dev->vq_index; + trace_vhost_vdpa_get_vq_index(dev, idx, idx); + return idx; } static int vhost_vdpa_set_vring_ready(struct vhost_dev *dev) @@ -559,11 +624,21 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) { struct vhost_vdpa *v = dev->opaque; trace_vhost_vdpa_dev_start(dev, started); + if (started) { - uint8_t status = 0; - memory_listener_register(&v->listener, &address_space_memory); vhost_vdpa_host_notifiers_init(dev); vhost_vdpa_set_vring_ready(dev); + } else { + vhost_vdpa_host_notifiers_uninit(dev, dev->nvqs); + } + + if (dev->vq_index + dev->nvqs != dev->last_index) { + return 0; + } + + if (started) { + uint8_t status = 0; + memory_listener_register(&v->listener, &address_space_memory); vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK); vhost_vdpa_call(dev, VHOST_VDPA_GET_STATUS, &status); @@ -572,7 +647,6 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) vhost_vdpa_reset_device(dev); vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE | VIRTIO_CONFIG_S_DRIVER); - vhost_vdpa_host_notifiers_uninit(dev, dev->nvqs); memory_listener_unregister(&v->listener); return 0; @@ -582,6 +656,10 @@ 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)) { + return 0; + } + trace_vhost_vdpa_set_log_base(dev, base, log->size, log->refcnt, log->fd, log->log); return vhost_vdpa_call(dev, VHOST_SET_LOG_BASE, &base); @@ -647,6 +725,10 @@ static int vhost_vdpa_get_features(struct vhost_dev *dev, static int vhost_vdpa_set_owner(struct vhost_dev *dev) { + if (vhost_vdpa_one_time_request(dev)) { + return 0; + } + trace_vhost_vdpa_set_owner(dev); return vhost_vdpa_call(dev, VHOST_SET_OWNER, NULL); } diff --git a/hw/virtio/virtio-iommu-pci.c b/hw/virtio/virtio-iommu-pci.c index 770c286be7..a160ae6b41 100644 --- a/hw/virtio/virtio-iommu-pci.c +++ b/hw/virtio/virtio-iommu-pci.c @@ -98,9 +98,7 @@ static void virtio_iommu_pci_instance_init(Object *obj) } static const VirtioPCIDeviceTypeInfo virtio_iommu_pci_info = { - .base_name = TYPE_VIRTIO_IOMMU_PCI, - .generic_name = "virtio-iommu-pci", - .non_transitional_name = "virtio-iommu-pci-non-transitional", + .generic_name = TYPE_VIRTIO_IOMMU_PCI, .instance_size = sizeof(VirtIOIOMMUPCI), .instance_init = virtio_iommu_pci_instance_init, .class_init = virtio_iommu_pci_class_init, diff --git a/include/hw/virtio/vhost-user-rng.h b/include/hw/virtio/vhost-user-rng.h new file mode 100644 index 0000000000..071539996d --- /dev/null +++ b/include/hw/virtio/vhost-user-rng.h @@ -0,0 +1,33 @@ +/* + * Vhost-user RNG virtio device + * + * Copyright (c) 2021 Mathieu Poirier <mathieu.poirier@linaro.org> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef _QEMU_VHOST_USER_RNG_H +#define _QEMU_VHOST_USER_RNG_H + +#include "hw/virtio/virtio.h" +#include "hw/virtio/vhost.h" +#include "hw/virtio/vhost-user.h" +#include "chardev/char-fe.h" + +#define TYPE_VHOST_USER_RNG "vhost-user-rng" +OBJECT_DECLARE_SIMPLE_TYPE(VHostUserRNG, VHOST_USER_RNG) + +struct VHostUserRNG { + /*< private >*/ + VirtIODevice parent; + CharBackend chardev; + struct vhost_virtqueue *vhost_vq; + struct vhost_dev vhost_dev; + VhostUserState vhost_user; + VirtQueue *req_vq; + bool connected; + + /*< public >*/ +}; + +#endif /* _QEMU_VHOST_USER_RNG_H */ diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h index a8963da2d9..3ce79a646d 100644 --- a/include/hw/virtio/vhost-vdpa.h +++ b/include/hw/virtio/vhost-vdpa.h @@ -13,6 +13,7 @@ #define HW_VIRTIO_VHOST_VDPA_H #include "hw/virtio/virtio.h" +#include "standard-headers/linux/vhost_types.h" typedef struct VhostVDPAHostNotifier { MemoryRegion mr; @@ -21,9 +22,11 @@ typedef struct VhostVDPAHostNotifier { typedef struct vhost_vdpa { int device_fd; + int index; uint32_t msg_type; bool iotlb_batch_begin_sent; MemoryListener listener; + struct vhost_vdpa_iova_range iova_range; struct vhost_dev *dev; VhostVDPAHostNotifier notifier[VIRTIO_QUEUE_MAX]; } VhostVDPA; diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h index 1a9fc65089..3fa0b554ef 100644 --- a/include/hw/virtio/vhost.h +++ b/include/hw/virtio/vhost.h @@ -74,6 +74,8 @@ struct vhost_dev { unsigned int nvqs; /* the first virtqueue which would be used by this vhost dev */ int vq_index; + /* the last vq index for the virtio device (not vhost) */ + int last_index; /* if non-zero, minimum required value for max_queues */ int num_queues; uint64_t features; diff --git a/include/hw/virtio/virtio-iommu.h b/include/hw/virtio/virtio-iommu.h index 273e35c04b..e2339e5b72 100644 --- a/include/hw/virtio/virtio-iommu.h +++ b/include/hw/virtio/virtio-iommu.h @@ -26,7 +26,7 @@ #include "qom/object.h" #define TYPE_VIRTIO_IOMMU "virtio-iommu-device" -#define TYPE_VIRTIO_IOMMU_PCI "virtio-iommu-device-base" +#define TYPE_VIRTIO_IOMMU_PCI "virtio-iommu-pci" OBJECT_DECLARE_SIMPLE_TYPE(VirtIOIOMMU, VIRTIO_IOMMU) #define TYPE_VIRTIO_IOMMU_MEMORY_REGION "virtio-iommu-memory-region" diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h index 74a10ebe85..eb87032627 100644 --- a/include/hw/virtio/virtio-net.h +++ b/include/hw/virtio/virtio-net.h @@ -194,8 +194,9 @@ struct VirtIONet { NICConf nic_conf; DeviceState *qdev; int multiqueue; - uint16_t max_queues; - uint16_t curr_queues; + uint16_t max_queue_pairs; + uint16_t curr_queue_pairs; + uint16_t max_ncs; size_t config_size; char *netclient_name; char *netclient_type; diff --git a/include/net/net.h b/include/net/net.h index 986288eb07..523136c7ac 100644 --- a/include/net/net.h +++ b/include/net/net.h @@ -105,6 +105,7 @@ struct NetClientState { int vnet_hdr_len; bool is_netdev; bool do_not_pad; /* do not pad to the minimum ethernet frame length */ + bool is_datapath; QTAILQ_HEAD(, NetFilterState) filters; }; @@ -136,6 +137,10 @@ NetClientState *qemu_new_net_client(NetClientInfo *info, NetClientState *peer, const char *model, const char *name); +NetClientState *qemu_new_net_control_client(NetClientInfo *info, + NetClientState *peer, + const char *model, + const char *name); NICState *qemu_new_nic(NetClientInfo *info, NICConf *conf, const char *model, diff --git a/include/net/vhost_net.h b/include/net/vhost_net.h index fba40cf695..387e913e4e 100644 --- a/include/net/vhost_net.h +++ b/include/net/vhost_net.h @@ -21,8 +21,10 @@ typedef struct VhostNetOptions { uint64_t vhost_net_get_max_queues(VHostNetState *net); struct vhost_net *vhost_net_init(VhostNetOptions *options); -int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, int total_queues); -void vhost_net_stop(VirtIODevice *dev, NetClientState *ncs, int total_queues); +int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, + int data_queue_pairs, int cvq); +void vhost_net_stop(VirtIODevice *dev, NetClientState *ncs, + int data_queue_pairs, int cvq); void vhost_net_cleanup(VHostNetState *net); diff --git a/meson.build b/meson.build index 9ed9a993e2..2c5b53cbe2 100644 --- a/meson.build +++ b/meson.build @@ -75,6 +75,12 @@ else kvm_targets = [] endif +kvm_targets_c = '' +if not get_option('kvm').disabled() and targetos == 'linux' + kvm_targets_c = '"' + '" ,"'.join(kvm_targets) + '"' +endif +config_host_data.set('CONFIG_KVM_TARGETS', kvm_targets_c) + accelerator_targets = { 'CONFIG_KVM': kvm_targets } if cpu in ['aarch64'] @@ -239,7 +239,8 @@ static void qemu_net_client_setup(NetClientState *nc, NetClientState *peer, const char *model, const char *name, - NetClientDestructor *destructor) + NetClientDestructor *destructor, + bool is_datapath) { nc->info = info; nc->model = g_strdup(model); @@ -258,6 +259,7 @@ static void qemu_net_client_setup(NetClientState *nc, nc->incoming_queue = qemu_new_net_queue(qemu_deliver_packet_iov, nc); nc->destructor = destructor; + nc->is_datapath = is_datapath; QTAILQ_INIT(&nc->filters); } @@ -272,7 +274,23 @@ NetClientState *qemu_new_net_client(NetClientInfo *info, nc = g_malloc0(info->size); qemu_net_client_setup(nc, info, peer, model, name, - qemu_net_client_destructor); + qemu_net_client_destructor, true); + + return nc; +} + +NetClientState *qemu_new_net_control_client(NetClientInfo *info, + NetClientState *peer, + const char *model, + const char *name) +{ + NetClientState *nc; + + assert(info->size >= sizeof(NetClientState)); + + nc = g_malloc0(info->size); + qemu_net_client_setup(nc, info, peer, model, name, + qemu_net_client_destructor, false); return nc; } @@ -297,7 +315,7 @@ NICState *qemu_new_nic(NetClientInfo *info, for (i = 0; i < queues; i++) { qemu_net_client_setup(&nic->ncs[i], info, peers[i], model, name, - NULL); + NULL, true); nic->ncs[i].queue_index = i; } diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c index 6dc68d8677..49ab322511 100644 --- a/net/vhost-vdpa.c +++ b/net/vhost-vdpa.c @@ -18,6 +18,7 @@ #include "qemu/error-report.h" #include "qemu/option.h" #include "qapi/error.h" +#include <linux/vhost.h> #include <sys/ioctl.h> #include <err.h> #include "standard-headers/linux/virtio_net.h" @@ -51,6 +52,14 @@ const int vdpa_feature_bits[] = { VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_MTU, + VIRTIO_NET_F_CTRL_RX, + VIRTIO_NET_F_CTRL_RX_EXTRA, + VIRTIO_NET_F_CTRL_VLAN, + VIRTIO_NET_F_GUEST_ANNOUNCE, + VIRTIO_NET_F_CTRL_MAC_ADDR, + VIRTIO_NET_F_RSS, + VIRTIO_NET_F_MQ, + VIRTIO_NET_F_CTRL_VQ, VIRTIO_F_IOMMU_PLATFORM, VIRTIO_F_RING_PACKED, VIRTIO_NET_F_RSS, @@ -81,7 +90,8 @@ static int vhost_vdpa_net_check_device_id(struct vhost_net *net) return ret; } -static int vhost_vdpa_add(NetClientState *ncs, void *be) +static int vhost_vdpa_add(NetClientState *ncs, void *be, + int queue_pair_index, int nvqs) { VhostNetOptions options; struct vhost_net *net = NULL; @@ -94,7 +104,7 @@ static int vhost_vdpa_add(NetClientState *ncs, void *be) options.net_backend = ncs; options.opaque = be; options.busyloop_timeout = 0; - options.nvqs = 2; + options.nvqs = nvqs; net = vhost_net_init(&options); if (!net) { @@ -169,36 +179,125 @@ static NetClientInfo net_vhost_vdpa_info = { .check_peer_type = vhost_vdpa_check_peer_type, }; -static int net_vhost_vdpa_init(NetClientState *peer, const char *device, - const char *name, const char *vhostdev) +static NetClientState *net_vhost_vdpa_init(NetClientState *peer, + const char *device, + const char *name, + int vdpa_device_fd, + int queue_pair_index, + int nvqs, + bool is_datapath) { NetClientState *nc = NULL; VhostVDPAState *s; - int vdpa_device_fd = -1; int ret = 0; assert(name); - nc = qemu_new_net_client(&net_vhost_vdpa_info, peer, device, name); + if (is_datapath) { + nc = qemu_new_net_client(&net_vhost_vdpa_info, peer, device, + name); + } else { + nc = qemu_new_net_control_client(&net_vhost_vdpa_info, peer, + device, name); + } snprintf(nc->info_str, sizeof(nc->info_str), TYPE_VHOST_VDPA); s = DO_UPCAST(VhostVDPAState, nc, nc); - vdpa_device_fd = qemu_open_old(vhostdev, O_RDWR); - if (vdpa_device_fd == -1) { - return -errno; - } + s->vhost_vdpa.device_fd = vdpa_device_fd; - ret = vhost_vdpa_add(nc, (void *)&s->vhost_vdpa); + s->vhost_vdpa.index = queue_pair_index; + ret = vhost_vdpa_add(nc, (void *)&s->vhost_vdpa, queue_pair_index, nvqs); if (ret) { - qemu_close(vdpa_device_fd); qemu_del_net_client(nc); + return NULL; } - return ret; + return nc; +} + +static int vhost_vdpa_get_max_queue_pairs(int fd, int *has_cvq, Error **errp) +{ + unsigned long config_size = offsetof(struct vhost_vdpa_config, buf); + struct vhost_vdpa_config *config; + __virtio16 *max_queue_pairs; + uint64_t features; + int ret; + + ret = ioctl(fd, VHOST_GET_FEATURES, &features); + if (ret) { + error_setg(errp, "Fail to query features from vhost-vDPA device"); + return ret; + } + + if (features & (1 << VIRTIO_NET_F_CTRL_VQ)) { + *has_cvq = 1; + } else { + *has_cvq = 0; + } + + if (features & (1 << VIRTIO_NET_F_MQ)) { + config = g_malloc0(config_size + sizeof(*max_queue_pairs)); + config->off = offsetof(struct virtio_net_config, max_virtqueue_pairs); + config->len = sizeof(*max_queue_pairs); + + ret = ioctl(fd, VHOST_VDPA_GET_CONFIG, config); + if (ret) { + error_setg(errp, "Fail to get config from vhost-vDPA device"); + return -ret; + } + + max_queue_pairs = (__virtio16 *)&config->buf; + + return lduw_le_p(max_queue_pairs); + } + + return 1; } int net_init_vhost_vdpa(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp) { const NetdevVhostVDPAOptions *opts; + int vdpa_device_fd; + NetClientState **ncs, *nc; + int queue_pairs, i, has_cvq = 0; assert(netdev->type == NET_CLIENT_DRIVER_VHOST_VDPA); opts = &netdev->u.vhost_vdpa; - return net_vhost_vdpa_init(peer, TYPE_VHOST_VDPA, name, opts->vhostdev); + + vdpa_device_fd = qemu_open_old(opts->vhostdev, O_RDWR); + if (vdpa_device_fd == -1) { + return -errno; + } + + queue_pairs = vhost_vdpa_get_max_queue_pairs(vdpa_device_fd, + &has_cvq, errp); + if (queue_pairs < 0) { + qemu_close(vdpa_device_fd); + return queue_pairs; + } + + ncs = g_malloc0(sizeof(*ncs) * queue_pairs); + + for (i = 0; i < queue_pairs; i++) { + ncs[i] = net_vhost_vdpa_init(peer, TYPE_VHOST_VDPA, name, + vdpa_device_fd, i, 2, true); + if (!ncs[i]) + goto err; + } + + if (has_cvq) { + nc = net_vhost_vdpa_init(peer, TYPE_VHOST_VDPA, name, + vdpa_device_fd, i, 1, false); + if (!nc) + goto err; + } + + g_free(ncs); + return 0; + +err: + if (i) { + qemu_del_net_client(ncs[0]); + } + qemu_close(vdpa_device_fd); + g_free(ncs); + + return -1; } diff --git a/softmmu/qdev-monitor.c b/softmmu/qdev-monitor.c index 89c473cb22..4851de51a5 100644 --- a/softmmu/qdev-monitor.c +++ b/softmmu/qdev-monitor.c @@ -639,19 +639,13 @@ DeviceState *qdev_device_add_from_qdict(const QDict *opts, } } - if (qdict_haskey(opts, "failover_pair_id")) { - if (!qdict_haskey(opts, "id")) { - error_setg(errp, "Device with failover_pair_id don't have id"); - return NULL; - } - if (qdev_should_hide_device(opts, from_json, errp)) { - if (bus && !qbus_is_hotpluggable(bus)) { - error_setg(errp, QERR_BUS_NO_HOTPLUG, bus->name); - } - return NULL; - } else if (*errp) { - return NULL; + if (qdev_should_hide_device(opts, from_json, errp)) { + if (bus && !qbus_is_hotpluggable(bus)) { + error_setg(errp, QERR_BUS_NO_HOTPLUG, bus->name); } + return NULL; + } else if (*errp) { + return NULL; } if (phase_check(PHASE_MACHINE_READY) && bus && !qbus_is_hotpluggable(bus)) { diff --git a/subprojects/libvhost-user/libvhost-user.c b/subprojects/libvhost-user/libvhost-user.c index bf09693255..787f4d2d4f 100644 --- a/subprojects/libvhost-user/libvhost-user.c +++ b/subprojects/libvhost-user/libvhost-user.c @@ -816,6 +816,7 @@ vu_rem_mem_reg(VuDev *dev, VhostUserMsg *vmsg) { shadow_regions[j].gpa = dev->regions[i].gpa; shadow_regions[j].size = dev->regions[i].size; shadow_regions[j].qva = dev->regions[i].qva; + shadow_regions[j].mmap_addr = dev->regions[i].mmap_addr; shadow_regions[j].mmap_offset = dev->regions[i].mmap_offset; j++; } else { diff --git a/tests/data/acpi/q35/APIC.xapic b/tests/data/acpi/q35/APIC.xapic Binary files differnew file mode 100644 index 0000000000..c1969c35aa --- /dev/null +++ b/tests/data/acpi/q35/APIC.xapic diff --git a/tests/data/acpi/q35/DMAR.dmar b/tests/data/acpi/q35/DMAR.dmar Binary files differnew file mode 100644 index 0000000000..0dca6e68ad --- /dev/null +++ b/tests/data/acpi/q35/DMAR.dmar diff --git a/tests/data/acpi/q35/DSDT.ivrs b/tests/data/acpi/q35/DSDT.ivrs Binary files differnew file mode 100644 index 0000000000..b0eafe90e5 --- /dev/null +++ b/tests/data/acpi/q35/DSDT.ivrs diff --git a/tests/data/acpi/q35/DSDT.multi-bridge b/tests/data/acpi/q35/DSDT.multi-bridge Binary files differnew file mode 100644 index 0000000000..a24c713d22 --- /dev/null +++ b/tests/data/acpi/q35/DSDT.multi-bridge diff --git a/tests/data/acpi/q35/DSDT.xapic b/tests/data/acpi/q35/DSDT.xapic Binary files differnew file mode 100644 index 0000000000..119fc90f1f --- /dev/null +++ b/tests/data/acpi/q35/DSDT.xapic diff --git a/tests/data/acpi/q35/FACP.xapic b/tests/data/acpi/q35/FACP.xapic Binary files differnew file mode 100644 index 0000000000..2d3659c9c6 --- /dev/null +++ b/tests/data/acpi/q35/FACP.xapic diff --git a/tests/data/acpi/q35/IVRS.ivrs b/tests/data/acpi/q35/IVRS.ivrs Binary files differnew file mode 100644 index 0000000000..17611202e5 --- /dev/null +++ b/tests/data/acpi/q35/IVRS.ivrs diff --git a/tests/data/acpi/q35/SRAT.xapic b/tests/data/acpi/q35/SRAT.xapic Binary files differnew file mode 100644 index 0000000000..1a91cfa65f --- /dev/null +++ b/tests/data/acpi/q35/SRAT.xapic diff --git a/tests/data/acpi/rebuild-expected-aml.sh b/tests/data/acpi/rebuild-expected-aml.sh index fc78770544..dcf2e2f221 100755 --- a/tests/data/acpi/rebuild-expected-aml.sh +++ b/tests/data/acpi/rebuild-expected-aml.sh @@ -12,7 +12,7 @@ # This work is licensed under the terms of the GNU GPLv2. # See the COPYING.LIB file in the top-level directory. -qemu_bins="./qemu-system-x86_64 ./qemu-system-aarch64" +qemu_arches="x86_64 aarch64" if [ ! -e "tests/qtest/bios-tables-test" ]; then echo "Test: bios-tables-test is required! Run make check before this script." @@ -20,6 +20,26 @@ if [ ! -e "tests/qtest/bios-tables-test" ]; then exit 1; fi +if grep TARGET_DIRS= config-host.mak; then + for arch in $qemu_arches; do + if grep TARGET_DIRS= config-host.mak | grep "$arch"-softmmu; + then + qemu_bins="$qemu_bins ./qemu-system-$arch" + fi + done +else + echo "config-host.mak missing!" + echo "Run this script from the build directory." + exit 1; +fi + +if [ -z "$qemu_bins" ]; then + echo "Only the following architectures are currently supported: $qemu_arches" + echo "None of these configured!" + echo "To fix, run configure --target-list=x86_64-softmmu,aarch64-softmmu" + exit 1; +fi + for qemu in $qemu_bins; do if [ ! -e $qemu ]; then echo "Run 'make' to build the following QEMU executables: $qemu_bins" diff --git a/tests/qtest/acpi-utils.c b/tests/qtest/acpi-utils.c index d2a202efca..766c48e3a6 100644 --- a/tests/qtest/acpi-utils.c +++ b/tests/qtest/acpi-utils.c @@ -98,6 +98,20 @@ void acpi_fetch_table(QTestState *qts, uint8_t **aml, uint32_t *aml_len, ACPI_ASSERT_CMP(**aml, sig); } if (verify_checksum) { + if (acpi_calc_checksum(*aml, *aml_len)) { + gint fd, ret; + char *fname = NULL; + GError *error = NULL; + + fprintf(stderr, "Invalid '%.4s'(%d)\n", *aml, *aml_len); + fd = g_file_open_tmp("malformed-XXXXXX.dat", &fname, &error); + g_assert_no_error(error); + fprintf(stderr, "Dumping invalid table into '%s'\n", fname); + ret = qemu_write_full(fd, *aml, *aml_len); + g_assert(ret == *aml_len); + close(fd); + g_free(fname); + } g_assert(!acpi_calc_checksum(*aml, *aml_len)); } } diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c index 90a87f0ea9..f76652143a 100644 --- a/tests/qtest/arm-cpu-features.c +++ b/tests/qtest/arm-cpu-features.c @@ -26,21 +26,6 @@ " 'arguments': { 'type': 'full', " #define QUERY_TAIL "}}" -static bool kvm_enabled(QTestState *qts) -{ - QDict *resp, *qdict; - bool enabled; - - resp = qtest_qmp(qts, "{ 'execute': 'query-kvm' }"); - g_assert(qdict_haskey(resp, "return")); - qdict = qdict_get_qdict(resp, "return"); - g_assert(qdict_haskey(qdict, "enabled")); - enabled = qdict_get_bool(qdict, "enabled"); - qobject_unref(resp); - - return enabled; -} - static QDict *do_query_no_props(QTestState *qts, const char *cpu_type) { return qtest_qmp(qts, QUERY_HEAD "'model': { 'name': %s }" @@ -506,14 +491,6 @@ static void test_query_cpu_model_expansion_kvm(const void *data) qts = qtest_init(MACHINE_KVM "-cpu max"); - /* - * These tests target the 'host' CPU type, so KVM must be enabled. - */ - if (!kvm_enabled(qts)) { - qtest_quit(qts); - return; - } - /* Enabling and disabling kvm-no-adjvtime should always work. */ assert_has_feature_disabled(qts, "host", "kvm-no-adjvtime"); assert_set_feature(qts, "host", "kvm-no-adjvtime", true); @@ -637,7 +614,11 @@ int main(int argc, char **argv) * order avoid attempting to run an AArch32 QEMU with KVM on * AArch64 hosts. That won't work and isn't easy to detect. */ - if (g_str_equal(qtest_get_arch(), "aarch64")) { + if (g_str_equal(qtest_get_arch(), "aarch64") && qtest_has_accel("kvm")) { + /* + * This tests target the 'host' CPU type, so register it only if + * KVM is available. + */ qtest_add_data_func("/arm/kvm/query-cpu-model-expansion", NULL, test_query_cpu_model_expansion_kvm); } diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c index 4f11d03055..258874167e 100644 --- a/tests/qtest/bios-tables-test.c +++ b/tests/qtest/bios-tables-test.c @@ -271,19 +271,28 @@ static void dump_aml_files(test_data *data, bool rebuild) } } +static bool create_tmp_asl(AcpiSdtTable *sdt) +{ + GError *error = NULL; + gint fd; + + fd = g_file_open_tmp("asl-XXXXXX.dsl", &sdt->asl_file, &error); + g_assert_no_error(error); + close(fd); + + return false; +} + static bool load_asl(GArray *sdts, AcpiSdtTable *sdt) { AcpiSdtTable *temp; GError *error = NULL; GString *command_line = g_string_new(iasl); - gint fd; gchar *out, *out_err; gboolean ret; int i; - fd = g_file_open_tmp("asl-XXXXXX.dsl", &sdt->asl_file, &error); - g_assert_no_error(error); - close(fd); + create_tmp_asl(sdt); /* build command line */ g_string_append_printf(command_line, " -p %s ", sdt->asl_file); @@ -463,11 +472,20 @@ static void test_acpi_asl(test_data *data) err = load_asl(data->tables, sdt); asl = normalize_asl(sdt->asl); - exp_err = load_asl(exp_data.tables, exp_sdt); - exp_asl = normalize_asl(exp_sdt->asl); + /* + * If expected file is empty - it's likely that it was a stub just + * created for step 1 above: we do want to decompile the actual one. + */ + if (exp_sdt->aml_len) { + exp_err = load_asl(exp_data.tables, exp_sdt); + exp_asl = normalize_asl(exp_sdt->asl); + } else { + exp_err = create_tmp_asl(exp_sdt); + exp_asl = g_string_new(""); + } /* TODO: check for warnings */ - g_assert(!err || exp_err); + g_assert(!err || exp_err || !exp_sdt->aml_len); if (g_strcmp0(asl->str, exp_asl->str)) { sdt->tmp_files_retain = true; @@ -722,13 +740,6 @@ static void test_acpi_one(const char *params, test_data *data) char *args; bool use_uefi = data->uefi_fl1 && data->uefi_fl2; -#ifndef CONFIG_TCG - if (data->tcg_only) { - g_test_skip("TCG disabled, skipping ACPI tcg_only test"); - return; - } -#endif /* CONFIG_TCG */ - args = test_acpi_create_args(data, params, use_uefi); data->qts = qtest_init(args); test_acpi_load_tables(data, use_uefi); @@ -859,6 +870,23 @@ static void test_acpi_q35_tcg_bridge(void) free_test_data(&data); } +static void test_acpi_q35_multif_bridge(void) +{ + test_data data = { + .machine = MACHINE_Q35, + .variant = ".multi-bridge", + }; + test_acpi_one("-device pcie-root-port,id=pcie-root-port-0," + "multifunction=on," + "port=0x0,chassis=1,addr=0x2,bus=pcie.0 " + "-device pcie-root-port,id=pcie-root-port-1," + "port=0x1,chassis=2,addr=0x3.0x1,bus=pcie.0 " + "-device virtio-balloon,id=balloon0," + "bus=pcie.0,addr=0x4.0x2", + &data); + free_test_data(&data); +} + static void test_acpi_q35_tcg_mmio64(void) { test_data data = { @@ -1033,6 +1061,19 @@ static void test_acpi_q35_tcg_numamem(void) free_test_data(&data); } +static void test_acpi_q35_kvm_xapic(void) +{ + test_data data; + + memset(&data, 0, sizeof(data)); + data.machine = MACHINE_Q35; + data.variant = ".xapic"; + test_acpi_one(" -object memory-backend-ram,id=ram0,size=128M" + " -numa node -numa node,memdev=ram0" + " -machine kernel-irqchip=on -smp 1,maxcpus=288", &data); + free_test_data(&data); +} + static void test_acpi_q35_tcg_nosmm(void) { test_data data; @@ -1077,6 +1118,30 @@ static void test_acpi_q35_tcg_nohpet(void) free_test_data(&data); } +static void test_acpi_q35_kvm_dmar(void) +{ + test_data data; + + memset(&data, 0, sizeof(data)); + data.machine = MACHINE_Q35; + data.variant = ".dmar"; + test_acpi_one("-machine kernel-irqchip=split -accel kvm" + " -device intel-iommu,intremap=on,device-iotlb=on", &data); + free_test_data(&data); +} + +static void test_acpi_q35_tcg_ivrs(void) +{ + test_data data; + + memset(&data, 0, sizeof(data)); + data.machine = MACHINE_Q35; + data.variant = ".ivrs"; + data.tcg_only = true, + test_acpi_one(" -device amd-iommu", &data); + free_test_data(&data); +} + static void test_acpi_piix4_tcg_numamem(void) { test_data data; @@ -1393,9 +1458,6 @@ static void test_acpi_virt_tcg(void) .scan_len = 128ULL * 1024 * 1024, }; - test_acpi_one("-cpu cortex-a57", &data); - free_test_data(&data); - data.smbios_cpu_max_speed = 2900; data.smbios_cpu_curr_speed = 2700; test_acpi_one("-cpu cortex-a57 " @@ -1509,6 +1571,8 @@ static void test_acpi_oem_fields_virt(void) int main(int argc, char *argv[]) { const char *arch = qtest_get_arch(); + const bool has_kvm = qtest_has_accel("kvm"); + const bool has_tcg = qtest_has_accel("tcg"); int ret; g_test_init(&argc, &argv, NULL); @@ -1534,6 +1598,7 @@ int main(int argc, char *argv[]) test_acpi_piix4_no_acpi_pci_hotplug); qtest_add_func("acpi/q35", test_acpi_q35_tcg); qtest_add_func("acpi/q35/bridge", test_acpi_q35_tcg_bridge); + qtest_add_func("acpi/q35/multif-bridge", test_acpi_q35_multif_bridge); qtest_add_func("acpi/q35/mmio64", test_acpi_q35_tcg_mmio64); qtest_add_func("acpi/piix4/ipmi", test_acpi_piix4_tcg_ipmi); qtest_add_func("acpi/q35/ipmi", test_acpi_q35_tcg_ipmi); @@ -1564,15 +1629,24 @@ int main(int argc, char *argv[]) qtest_add_func("acpi/microvm/rtc", test_acpi_microvm_rtc_tcg); qtest_add_func("acpi/microvm/ioapic2", test_acpi_microvm_ioapic2_tcg); qtest_add_func("acpi/microvm/oem-fields", test_acpi_oem_fields_microvm); - if (strcmp(arch, "x86_64") == 0) { - qtest_add_func("acpi/microvm/pcie", test_acpi_microvm_pcie_tcg); + if (has_tcg) { + qtest_add_func("acpi/q35/ivrs", test_acpi_q35_tcg_ivrs); + if (strcmp(arch, "x86_64") == 0) { + qtest_add_func("acpi/microvm/pcie", test_acpi_microvm_pcie_tcg); + } + } + if (has_kvm) { + qtest_add_func("acpi/q35/kvm/xapic", test_acpi_q35_kvm_xapic); + qtest_add_func("acpi/q35/kvm/dmar", test_acpi_q35_kvm_dmar); } } else if (strcmp(arch, "aarch64") == 0) { - qtest_add_func("acpi/virt", test_acpi_virt_tcg); - qtest_add_func("acpi/virt/numamem", test_acpi_virt_tcg_numamem); - qtest_add_func("acpi/virt/memhp", test_acpi_virt_tcg_memhp); - qtest_add_func("acpi/virt/pxb", test_acpi_virt_tcg_pxb); - qtest_add_func("acpi/virt/oem-fields", test_acpi_oem_fields_virt); + if (has_tcg) { + qtest_add_func("acpi/virt", test_acpi_virt_tcg); + qtest_add_func("acpi/virt/numamem", test_acpi_virt_tcg_numamem); + qtest_add_func("acpi/virt/memhp", test_acpi_virt_tcg_memhp); + qtest_add_func("acpi/virt/pxb", test_acpi_virt_tcg_pxb); + qtest_add_func("acpi/virt/oem-fields", test_acpi_oem_fields_virt); + } } ret = g_test_run(); boot_sector_cleanup(disk); diff --git a/tests/qtest/libqos/libqtest.h b/tests/qtest/libqos/libqtest.h index a68dcd79d4..59e9271195 100644 --- a/tests/qtest/libqos/libqtest.h +++ b/tests/qtest/libqos/libqtest.h @@ -589,6 +589,14 @@ bool qtest_big_endian(QTestState *s); const char *qtest_get_arch(void); /** + * qtest_has_accel: + * @accel_name: Accelerator name to check for. + * + * Returns: true if the accelerator is built in. + */ +bool qtest_has_accel(const char *accel_name); + +/** * qtest_add_func: * @str: Test case path. * @fn: Test case function diff --git a/tests/qtest/libqtest.c b/tests/qtest/libqtest.c index 73f6b977a6..25aeea385b 100644 --- a/tests/qtest/libqtest.c +++ b/tests/qtest/libqtest.c @@ -922,6 +922,33 @@ const char *qtest_get_arch(void) return end + 1; } +bool qtest_has_accel(const char *accel_name) +{ + if (g_str_equal(accel_name, "tcg")) { +#if defined(CONFIG_TCG) + return true; +#else + return false; +#endif + } else if (g_str_equal(accel_name, "kvm")) { + int i; + const char *arch = qtest_get_arch(); + const char *targets[] = { CONFIG_KVM_TARGETS }; + + for (i = 0; i < ARRAY_SIZE(targets); i++) { + if (!strncmp(targets[i], arch, strlen(arch))) { + if (!access("/dev/kvm", R_OK | W_OK)) { + return true; + } + } + } + } else { + /* not implemented */ + g_assert_not_reached(); + } + return false; +} + bool qtest_get_irq(QTestState *s, int num) { /* dummy operation in order to make sure irq is up to date */ diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c index cc5e83d98a..7b42f6fd90 100644 --- a/tests/qtest/migration-test.c +++ b/tests/qtest/migration-test.c @@ -1420,6 +1420,7 @@ static bool kvm_dirty_ring_supported(void) int main(int argc, char **argv) { char template[] = "/tmp/migration-test-XXXXXX"; + const bool has_kvm = qtest_has_accel("kvm"); int ret; g_test_init(&argc, &argv, NULL); @@ -1434,8 +1435,7 @@ int main(int argc, char **argv) * some reason) */ if (g_str_equal(qtest_get_arch(), "ppc64") && - (access("/sys/module/kvm_hv", F_OK) || - access("/dev/kvm", R_OK | W_OK))) { + (!has_kvm || access("/sys/module/kvm_hv", F_OK))) { g_test_message("Skipping test: kvm_hv not available"); return g_test_run(); } @@ -1444,16 +1444,9 @@ int main(int argc, char **argv) * Similar to ppc64, s390x seems to be touchy with TCG, so disable it * there until the problems are resolved */ - if (g_str_equal(qtest_get_arch(), "s390x")) { -#if defined(HOST_S390X) - if (access("/dev/kvm", R_OK | W_OK)) { - g_test_message("Skipping test: kvm not available"); - return g_test_run(); - } -#else - g_test_message("Skipping test: Need s390x host to work properly"); + if (g_str_equal(qtest_get_arch(), "s390x") && !has_kvm) { + g_test_message("Skipping test: s390x host with KVM is required"); return g_test_run(); -#endif } tmpfs = mkdtemp(template); diff --git a/tests/qtest/vhost-user-blk-test.c b/tests/qtest/vhost-user-blk-test.c index 6f108a1b62..62e670f39b 100644 --- a/tests/qtest/vhost-user-blk-test.c +++ b/tests/qtest/vhost-user-blk-test.c @@ -906,9 +906,9 @@ static void start_vhost_user_blk(GString *cmd_line, int vus_instances, img_path = drive_create(); g_string_append_printf(storage_daemon_command, "--blockdev driver=file,node-name=disk%d,filename=%s " - "--export type=vhost-user-blk,id=disk%d,addr.type=unix,addr.path=%s," + "--export type=vhost-user-blk,id=disk%d,addr.type=fd,addr.str=%d," "node-name=disk%i,writable=on,num-queues=%d ", - i, img_path, i, sock_path, i, num_queues); + i, img_path, i, fd, i, num_queues); g_string_append_printf(cmd_line, "-chardev socket,id=char%d,path=%s ", i + 1, sock_path); |