From 04b7a1523d65bb5c78832098cf3108a1aadcaf8a Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Wed, 17 Jun 2015 15:23:39 +0200 Subject: vhost: set vring endianness for legacy virtio Legacy virtio is native endian: if the guest and host endianness differ, we have to tell vhost so it can swap bytes where appropriate. This is done through a vhost ring ioctl. Signed-off-by: Greg Kurz Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/virtio/vhost.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 49 insertions(+), 1 deletion(-) (limited to 'hw') diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index 7908255..7ea45b3 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -17,9 +17,11 @@ #include "hw/hw.h" #include "qemu/atomic.h" #include "qemu/range.h" +#include "qemu/error-report.h" #include #include "exec/address-spaces.h" #include "hw/virtio/virtio-bus.h" +#include "hw/virtio/virtio-access.h" #include "migration/migration.h" static struct vhost_log *vhost_log; @@ -686,6 +688,27 @@ static void vhost_log_stop(MemoryListener *listener, /* FIXME: implement */ } +static int vhost_virtqueue_set_vring_endian_legacy(struct vhost_dev *dev, + bool is_big_endian, + int vhost_vq_index) +{ + struct vhost_vring_state s = { + .index = vhost_vq_index, + .num = is_big_endian + }; + + if (!dev->vhost_ops->vhost_call(dev, VHOST_SET_VRING_ENDIAN, &s)) { + return 0; + } + + if (errno == ENOTTY) { + error_report("vhost does not support cross-endian"); + return -ENOSYS; + } + + return -errno; +} + static int vhost_virtqueue_start(struct vhost_dev *dev, struct VirtIODevice *vdev, struct vhost_virtqueue *vq, @@ -716,6 +739,16 @@ static int vhost_virtqueue_start(struct vhost_dev *dev, return -errno; } + if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1) && + virtio_legacy_is_cross_endian(vdev)) { + r = vhost_virtqueue_set_vring_endian_legacy(dev, + virtio_is_big_endian(vdev), + vhost_vq_index); + if (r) { + return -errno; + } + } + s = l = virtio_queue_get_desc_size(vdev, idx); a = virtio_queue_get_desc_addr(vdev, idx); vq->desc = cpu_physical_memory_map(a, &l, 0); @@ -786,8 +819,9 @@ static void vhost_virtqueue_stop(struct vhost_dev *dev, struct vhost_virtqueue *vq, unsigned idx) { + int vhost_vq_index = idx - dev->vq_index; struct vhost_vring_state state = { - .index = idx - dev->vq_index + .index = vhost_vq_index, }; int r; assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs); @@ -798,6 +832,20 @@ static void vhost_virtqueue_stop(struct vhost_dev *dev, } virtio_queue_set_last_avail_idx(vdev, idx, state.num); virtio_queue_invalidate_signalled_used(vdev, idx); + + /* In the cross-endian case, we need to reset the vring endianness to + * native as legacy devices expect so by default. + */ + if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1) && + virtio_legacy_is_cross_endian(vdev)) { + r = vhost_virtqueue_set_vring_endian_legacy(dev, + !virtio_is_big_endian(vdev), + vhost_vq_index); + if (r < 0) { + error_report("failed to reset vring endianness"); + } + } + assert (r >= 0); cpu_physical_memory_unmap(vq->ring, virtio_queue_get_ring_size(vdev, idx), 0, virtio_queue_get_ring_size(vdev, idx)); -- cgit v1.1 From 5be7d9f1b1452613b95c6ba70b8d7ad3d0797991 Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Wed, 17 Jun 2015 15:23:49 +0200 Subject: vhost-net: tell tap backend about the vnet endianness The default behaviour for TAP/MACVTAP is to consider vnet as native endian. This patch handles the cases when this is not true: - virtio 1.0: always little-endian - legacy cross-endian Signed-off-by: Greg Kurz Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/net/vhost_net.c | 33 ++++++++++++++++++++++++++++++++- 1 file changed, 32 insertions(+), 1 deletion(-) (limited to 'hw') diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index 1c55517..8cbb2f6 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -38,6 +38,7 @@ #include "standard-headers/linux/virtio_ring.h" #include "hw/virtio/vhost.h" #include "hw/virtio/virtio-bus.h" +#include "hw/virtio/virtio-access.h" struct vhost_net { struct vhost_dev dev; @@ -197,6 +198,27 @@ static void vhost_net_set_vq_index(struct vhost_net *net, int vq_index) net->dev.vq_index = vq_index; } +static int vhost_net_set_vnet_endian(VirtIODevice *dev, NetClientState *peer, + bool set) +{ + int r = 0; + + if (virtio_has_feature(dev, VIRTIO_F_VERSION_1) || + (virtio_legacy_is_cross_endian(dev) && !virtio_is_big_endian(dev))) { + r = qemu_set_vnet_le(peer, set); + if (r) { + error_report("backend does not support LE vnet headers"); + } + } else if (virtio_legacy_is_cross_endian(dev)) { + r = qemu_set_vnet_be(peer, set); + if (r) { + error_report("backend does not support BE vnet headers"); + } + } + + return r; +} + static int vhost_net_start_one(struct vhost_net *net, VirtIODevice *dev) { @@ -314,6 +336,11 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, goto err; } + r = vhost_net_set_vnet_endian(dev, ncs[0].peer, true); + if (r < 0) { + goto err; + } + for (i = 0; i < total_queues; i++) { vhost_net_set_vq_index(get_vhost_net(ncs[i].peer), i * 2); } @@ -321,7 +348,7 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, r = k->set_guest_notifiers(qbus->parent, total_queues * 2, true); if (r < 0) { error_report("Error binding guest notifier: %d", -r); - goto err; + goto err_endian; } for (i = 0; i < total_queues; i++) { @@ -343,6 +370,8 @@ err_start: fprintf(stderr, "vhost guest notifier cleanup failed: %d\n", e); fflush(stderr); } +err_endian: + vhost_net_set_vnet_endian(dev, ncs[0].peer, false); err: return r; } @@ -365,6 +394,8 @@ void vhost_net_stop(VirtIODevice *dev, NetClientState *ncs, fflush(stderr); } assert(r >= 0); + + assert(vhost_net_set_vnet_endian(dev, ncs[0].peer, false) >= 0); } void vhost_net_cleanup(struct vhost_net *net) -- cgit v1.1 From 1717388645670336c48aa05d19b0acd07687a821 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Date: Wed, 17 Jun 2015 15:23:54 +0200 Subject: vhost_net: re-enable when cross endian MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Cross-endianness is now checked by the core vhost code. revert 371df9f5e0f1 "vhost-net: disable when cross-endian" Signed-off-by: Cédric Le Goater [ added commit message, Greg Kurz ] Signed-off-by: Greg Kurz Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/net/vhost_net.c | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'hw') diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index 8cbb2f6..f505c91 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -303,19 +303,6 @@ static void vhost_net_stop_one(struct vhost_net *net, vhost_dev_disable_notifiers(&net->dev, dev); } -static bool vhost_net_device_endian_ok(VirtIODevice *vdev) -{ -#ifdef TARGET_IS_BIENDIAN -#ifdef HOST_WORDS_BIGENDIAN - return virtio_is_big_endian(vdev); -#else - return !virtio_is_big_endian(vdev); -#endif -#else - return true; -#endif -} - int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, int total_queues) { @@ -324,12 +311,6 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus); int r, e, i; - if (!vhost_net_device_endian_ok(dev)) { - error_report("vhost-net does not support cross-endian"); - r = -ENOSYS; - goto err; - } - if (!k->set_guest_notifiers) { error_report("binding does not support guest notifiers"); r = -ENOSYS; -- cgit v1.1 From 5ba03e2dd785362026917e4cc8a1fd2c64e8e62c Mon Sep 17 00:00:00 2001 From: Laszlo Ersek Date: Wed, 17 Jun 2015 14:45:03 +0200 Subject: hw/core: rebase sysbus_get_fw_dev_path() to g_strdup_printf() This is done mainly for improving readability, and in preparation for the next patch, but Markus pointed out another bonus for the string being returned: "No arbitrary length limit. Before the patch, it's 39 characters, and the code breaks catastrophically when qdev_fw_name() is longer: the second snprintf() is called with its first argument pointing beyond path[], and its second argument underflowing to a huge size." Cc: qemu-stable@nongnu.org Signed-off-by: Laszlo Ersek Tested-by: Marcel Apfelbaum Reviewed-by: Marcel Apfelbaum Reviewed-by: Markus Armbruster Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/core/sysbus.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'hw') diff --git a/hw/core/sysbus.c b/hw/core/sysbus.c index b53c351..92eced9 100644 --- a/hw/core/sysbus.c +++ b/hw/core/sysbus.c @@ -281,19 +281,15 @@ static void sysbus_dev_print(Monitor *mon, DeviceState *dev, int indent) static char *sysbus_get_fw_dev_path(DeviceState *dev) { SysBusDevice *s = SYS_BUS_DEVICE(dev); - char path[40]; - int off; - - off = snprintf(path, sizeof(path), "%s", qdev_fw_name(dev)); if (s->num_mmio) { - snprintf(path + off, sizeof(path) - off, "@"TARGET_FMT_plx, - s->mmio[0].addr); - } else if (s->num_pio) { - snprintf(path + off, sizeof(path) - off, "@i%04x", s->pio[0]); + return g_strdup_printf("%s@" TARGET_FMT_plx, qdev_fw_name(dev), + s->mmio[0].addr); } - - return g_strdup(path); + if (s->num_pio) { + return g_strdup_printf("%s@i%04x", qdev_fw_name(dev), s->pio[0]); + } + return g_strdup(qdev_fw_name(dev)); } void sysbus_add_io(SysBusDevice *dev, hwaddr addr, -- cgit v1.1 From 74de5504fd063019433ec0746105da774ede790d Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Tue, 16 Jun 2015 11:24:39 +0300 Subject: pci: Don't register a specialized 'config_write' if default behavior is intended Few devices have their specialized 'config_write' methods which simply call 'pci_default_write_config' followed by a 'msix_write_config' or 'msi_write_config' calls, using exact same arguments. This is unnecessary as 'pci_default_write_config' already invokes 'msi_write_config' and 'msix_write_config'. Also, since 'pci_default_write_config' is the default 'config_write' handler, we can simply avoid the registration of these specialized versions. Cc: Leonid Shatz Signed-off-by: Shmulik Ladkani Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/misc/ivshmem.c | 1 - hw/net/vmxnet3.c | 9 --------- hw/scsi/megasas.c | 8 -------- hw/scsi/vmw_pvscsi.c | 8 -------- 4 files changed, 26 deletions(-) (limited to 'hw') diff --git a/hw/misc/ivshmem.c b/hw/misc/ivshmem.c index 5d272c8..231c35f 100644 --- a/hw/misc/ivshmem.c +++ b/hw/misc/ivshmem.c @@ -698,7 +698,6 @@ static void ivshmem_write_config(PCIDevice *pci_dev, uint32_t address, uint32_t val, int len) { pci_default_write_config(pci_dev, address, val, len); - msix_write_config(pci_dev, address, val, len); } static int pci_ivshmem_init(PCIDevice *dev) diff --git a/hw/net/vmxnet3.c b/hw/net/vmxnet3.c index dfb328d..34ffafd 100644 --- a/hw/net/vmxnet3.c +++ b/hw/net/vmxnet3.c @@ -2481,14 +2481,6 @@ static const VMStateDescription vmstate_vmxnet3 = { } }; -static void -vmxnet3_write_config(PCIDevice *pci_dev, uint32_t addr, uint32_t val, int len) -{ - pci_default_write_config(pci_dev, addr, val, len); - msix_write_config(pci_dev, addr, val, len); - msi_write_config(pci_dev, addr, val, len); -} - static Property vmxnet3_properties[] = { DEFINE_NIC_PROPERTIES(VMXNET3State, conf), DEFINE_PROP_END_OF_LIST(), @@ -2507,7 +2499,6 @@ static void vmxnet3_class_init(ObjectClass *class, void *data) c->class_id = PCI_CLASS_NETWORK_ETHERNET; c->subsystem_vendor_id = PCI_VENDOR_ID_VMWARE; c->subsystem_id = PCI_DEVICE_ID_VMWARE_VMXNET3; - c->config_write = vmxnet3_write_config, dc->desc = "VMWare Paravirtualized Ethernet v3"; dc->reset = vmxnet3_qdev_reset; dc->vmsd = &vmstate_vmxnet3; diff --git a/hw/scsi/megasas.c b/hw/scsi/megasas.c index 91a5d97..51ba9e0 100644 --- a/hw/scsi/megasas.c +++ b/hw/scsi/megasas.c @@ -2407,13 +2407,6 @@ static void megasas_scsi_realize(PCIDevice *dev, Error **errp) } } -static void -megasas_write_config(PCIDevice *pci, uint32_t addr, uint32_t val, int len) -{ - pci_default_write_config(pci, addr, val, len); - msi_write_config(pci, addr, val, len); -} - static Property megasas_properties_gen1[] = { DEFINE_PROP_UINT32("max_sge", MegasasState, fw_sge, MEGASAS_DEFAULT_SGE), @@ -2516,7 +2509,6 @@ static void megasas_class_init(ObjectClass *oc, void *data) dc->vmsd = info->vmsd; set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); dc->desc = info->desc; - pc->config_write = megasas_write_config; } static const TypeInfo megasas_info = { diff --git a/hw/scsi/vmw_pvscsi.c b/hw/scsi/vmw_pvscsi.c index c6148d3..9c71f31 100644 --- a/hw/scsi/vmw_pvscsi.c +++ b/hw/scsi/vmw_pvscsi.c @@ -1174,13 +1174,6 @@ static const VMStateDescription vmstate_pvscsi = { } }; -static void -pvscsi_write_config(PCIDevice *pci, uint32_t addr, uint32_t val, int len) -{ - pci_default_write_config(pci, addr, val, len); - msi_write_config(pci, addr, val, len); -} - static Property pvscsi_properties[] = { DEFINE_PROP_UINT8("use_msg", PVSCSIState, use_msg, 1), DEFINE_PROP_END_OF_LIST(), @@ -1202,7 +1195,6 @@ static void pvscsi_class_init(ObjectClass *klass, void *data) dc->vmsd = &vmstate_pvscsi; dc->props = pvscsi_properties; set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); - k->config_write = pvscsi_write_config; hc->unplug = pvscsi_hot_unplug; hc->plug = pvscsi_hotplug; } -- cgit v1.1 From 1e7398a140f7a6bd9f5a438e7ad0f1ef50990e25 Mon Sep 17 00:00:00 2001 From: Pankaj Gupta Date: Tue, 16 Jun 2015 13:48:59 +0530 Subject: vhost: enable vhost without without MSI-X We use vhostforce to enable vhost even if Guests don't have MSI-X support and we fall back to QEMU virtio-net. This gives a very small performance gain, but the disadvantage is that guest now controls which virtio code is running (qemu or vhost) so our attack surface is doubled. This patch will enable vhost unconditionally whenever it's requested. For compatibility, enable vhost when vhostforce is set, as well. Signed-off-by: Pankaj Gupta Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin Reviewed-by: Jason Wang --- hw/net/vhost_net.c | 12 +----------- hw/net/virtio-net.c | 4 ---- hw/scsi/vhost-scsi.c | 2 +- hw/virtio/vhost.c | 14 +------------- 4 files changed, 3 insertions(+), 29 deletions(-) (limited to 'hw') diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index f505c91..9bd360b 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -163,7 +163,7 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options) net->dev.vq_index = net->nc->queue_index; r = vhost_dev_init(&net->dev, options->opaque, - options->backend_type, options->force); + options->backend_type); if (r < 0) { goto fail; } @@ -188,11 +188,6 @@ fail: return NULL; } -bool vhost_net_query(VHostNetState *net, VirtIODevice *dev) -{ - return vhost_dev_query(&net->dev, dev); -} - static void vhost_net_set_vq_index(struct vhost_net *net, int vq_index) { net->dev.vq_index = vq_index; @@ -424,11 +419,6 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options) return NULL; } -bool vhost_net_query(VHostNetState *net, VirtIODevice *dev) -{ - return false; -} - int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, int total_queues) diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 9281aa1..d728233 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -128,10 +128,6 @@ static void virtio_net_vhost_status(VirtIONet *n, uint8_t status) if (!n->vhost_started) { int r, i; - if (!vhost_net_query(get_vhost_net(nc->peer), vdev)) { - return; - } - /* Any packets outstanding? Purge them to avoid touching rings * when vhost is running. */ diff --git a/hw/scsi/vhost-scsi.c b/hw/scsi/vhost-scsi.c index 1941aa1..1c389c4 100644 --- a/hw/scsi/vhost-scsi.c +++ b/hw/scsi/vhost-scsi.c @@ -246,7 +246,7 @@ static void vhost_scsi_realize(DeviceState *dev, Error **errp) s->dev.backend_features = 0; ret = vhost_dev_init(&s->dev, (void *)(uintptr_t)vhostfd, - VHOST_BACKEND_TYPE_KERNEL, true); + VHOST_BACKEND_TYPE_KERNEL); if (ret < 0) { error_setg(errp, "vhost-scsi: vhost initialization failed: %s", strerror(-ret)); diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index 7ea45b3..b84d21c 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -898,7 +898,7 @@ static void vhost_virtqueue_cleanup(struct vhost_virtqueue *vq) } int vhost_dev_init(struct vhost_dev *hdev, void *opaque, - VhostBackendType backend_type, bool force) + VhostBackendType backend_type) { uint64_t features; int i, r; @@ -961,7 +961,6 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, hdev->started = false; hdev->memory_changed = false; memory_listener_register(&hdev->memory_listener, &address_space_memory); - hdev->force = force; return 0; fail_vq: while (--i >= 0) { @@ -989,17 +988,6 @@ void vhost_dev_cleanup(struct vhost_dev *hdev) hdev->vhost_ops->vhost_backend_cleanup(hdev); } -bool vhost_dev_query(struct vhost_dev *hdev, VirtIODevice *vdev) -{ - BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev))); - VirtioBusState *vbus = VIRTIO_BUS(qbus); - VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus); - - return !k->query_guest_notifiers || - k->query_guest_notifiers(qbus->parent) || - hdev->force; -} - /* Stop processing guest IO notifications in qemu. * Start processing them in vhost in kernel. */ -- cgit v1.1