From a6df8adf3edbb3062f087e425564df35077e8410 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 6 Nov 2015 16:02:44 +0800 Subject: virtio-pci: fix 1.0 virtqueue migration We don't migrate the followings fields for virtio-pci: uint32_t dfselect; uint32_t gfselect; uint32_t guest_features[2]; struct { uint16_t num; bool enabled; uint32_t desc[2]; uint32_t avail[2]; uint32_t used[2]; } vqs[VIRTIO_QUEUE_MAX]; This will confuse driver if migrating during initialization. Solves this issue by: - introduce transport specific callbacks to load and store extra virtqueue states. - add a new subsection for virtio to migrate transport specific modern device state. - implement pci specific callbacks. - add a new property for virtio-pci for whether or not to migrate extra state. - compat the migration for 2.4 and elder machine types Cc: Michael S. Tsirkin Signed-off-by: Jason Wang Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- hw/virtio/virtio-pci.c | 129 +++++++++++++++++++++++++++++++++++++++++ hw/virtio/virtio-pci.h | 20 ++++--- hw/virtio/virtio.c | 58 ++++++++++++++++++ include/hw/compat.h | 4 ++ include/hw/virtio/virtio-bus.h | 3 + 5 files changed, 207 insertions(+), 7 deletions(-) diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index f55dd2bf8e..ab2a372aa4 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -86,6 +86,129 @@ static void virtio_pci_save_config(DeviceState *d, QEMUFile *f) qemu_put_be16(f, vdev->config_vector); } +static void virtio_pci_load_modern_queue_state(VirtIOPCIQueue *vq, + QEMUFile *f) +{ + vq->num = qemu_get_be16(f); + vq->enabled = qemu_get_be16(f); + vq->desc[0] = qemu_get_be32(f); + vq->desc[1] = qemu_get_be32(f); + vq->avail[0] = qemu_get_be32(f); + vq->avail[1] = qemu_get_be32(f); + vq->used[0] = qemu_get_be32(f); + vq->used[1] = qemu_get_be32(f); +} + +static bool virtio_pci_has_extra_state(DeviceState *d) +{ + VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d); + + return proxy->flags & VIRTIO_PCI_FLAG_MIGRATE_EXTRA; +} + +static int get_virtio_pci_modern_state(QEMUFile *f, void *pv, size_t size) +{ + VirtIOPCIProxy *proxy = pv; + int i; + + proxy->dfselect = qemu_get_be32(f); + proxy->gfselect = qemu_get_be32(f); + proxy->guest_features[0] = qemu_get_be32(f); + proxy->guest_features[1] = qemu_get_be32(f); + for (i = 0; i < VIRTIO_QUEUE_MAX; i++) { + virtio_pci_load_modern_queue_state(&proxy->vqs[i], f); + } + + return 0; +} + +static void virtio_pci_save_modern_queue_state(VirtIOPCIQueue *vq, + QEMUFile *f) +{ + qemu_put_be16(f, vq->num); + qemu_put_be16(f, vq->enabled); + qemu_put_be32(f, vq->desc[0]); + qemu_put_be32(f, vq->desc[1]); + qemu_put_be32(f, vq->avail[0]); + qemu_put_be32(f, vq->avail[1]); + qemu_put_be32(f, vq->used[0]); + qemu_put_be32(f, vq->used[1]); +} + +static void put_virtio_pci_modern_state(QEMUFile *f, void *pv, size_t size) +{ + VirtIOPCIProxy *proxy = pv; + int i; + + qemu_put_be32(f, proxy->dfselect); + qemu_put_be32(f, proxy->gfselect); + qemu_put_be32(f, proxy->guest_features[0]); + qemu_put_be32(f, proxy->guest_features[1]); + for (i = 0; i < VIRTIO_QUEUE_MAX; i++) { + virtio_pci_save_modern_queue_state(&proxy->vqs[i], f); + } +} + +static const VMStateInfo vmstate_info_virtio_pci_modern_state = { + .name = "virtqueue_state", + .get = get_virtio_pci_modern_state, + .put = put_virtio_pci_modern_state, +}; + +static bool virtio_pci_modern_state_needed(void *opaque) +{ + VirtIOPCIProxy *proxy = opaque; + + return !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_MODERN); +} + +static const VMStateDescription vmstate_virtio_pci_modern_state = { + .name = "virtio_pci/modern_state", + .version_id = 1, + .minimum_version_id = 1, + .needed = &virtio_pci_modern_state_needed, + .fields = (VMStateField[]) { + { + .name = "modern_state", + .version_id = 0, + .field_exists = NULL, + .size = 0, + .info = &vmstate_info_virtio_pci_modern_state, + .flags = VMS_SINGLE, + .offset = 0, + }, + VMSTATE_END_OF_LIST() + } +}; + +static const VMStateDescription vmstate_virtio_pci = { + .name = "virtio_pci", + .version_id = 1, + .minimum_version_id = 1, + .minimum_version_id_old = 1, + .fields = (VMStateField[]) { + VMSTATE_END_OF_LIST() + }, + .subsections = (const VMStateDescription*[]) { + &vmstate_virtio_pci_modern_state, + NULL + } +}; + +static void virtio_pci_save_extra_state(DeviceState *d, QEMUFile *f) +{ + VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d); + + vmstate_save_state(f, &vmstate_virtio_pci, proxy, NULL); +} + +static int virtio_pci_load_extra_state(DeviceState *d, QEMUFile *f) +{ + VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d); + + return vmstate_load_state(f, &vmstate_virtio_pci, proxy, 1); +} + static void virtio_pci_save_queue(DeviceState *d, int n, QEMUFile *f) { VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d); @@ -133,6 +256,7 @@ static int virtio_pci_load_queue(DeviceState *d, int n, QEMUFile *f) if (vector != VIRTIO_NO_VECTOR) { return msix_vector_use(&proxy->pci_dev, vector); } + return 0; } @@ -1622,6 +1746,8 @@ static Property virtio_pci_properties[] = { VIRTIO_PCI_FLAG_DISABLE_LEGACY_BIT, false), DEFINE_PROP_BIT("disable-modern", VirtIOPCIProxy, flags, VIRTIO_PCI_FLAG_DISABLE_MODERN_BIT, true), + DEFINE_PROP_BIT("migrate-extra", VirtIOPCIProxy, flags, + VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT, true), DEFINE_PROP_END_OF_LIST(), }; @@ -2212,6 +2338,9 @@ static void virtio_pci_bus_class_init(ObjectClass *klass, void *data) k->load_config = virtio_pci_load_config; k->save_queue = virtio_pci_save_queue; k->load_queue = virtio_pci_load_queue; + k->save_extra_state = virtio_pci_save_extra_state; + k->load_extra_state = virtio_pci_load_extra_state; + k->has_extra_state = virtio_pci_has_extra_state; k->query_guest_notifiers = virtio_pci_query_guest_notifiers; k->set_host_notifier = virtio_pci_set_host_notifier; k->set_guest_notifiers = virtio_pci_set_guest_notifiers; diff --git a/hw/virtio/virtio-pci.h b/hw/virtio/virtio-pci.h index 801c23aef3..58679f78bf 100644 --- a/hw/virtio/virtio-pci.h +++ b/hw/virtio/virtio-pci.h @@ -75,6 +75,10 @@ typedef struct VirtioBusClass VirtioPCIBusClass; #define VIRTIO_PCI_FLAG_DISABLE_LEGACY (1 << VIRTIO_PCI_FLAG_DISABLE_LEGACY_BIT) #define VIRTIO_PCI_FLAG_DISABLE_MODERN (1 << VIRTIO_PCI_FLAG_DISABLE_MODERN_BIT) +/* migrate extra state */ +#define VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT 4 +#define VIRTIO_PCI_FLAG_MIGRATE_EXTRA (1 << VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT) + typedef struct { MSIMessage msg; int virq; @@ -104,6 +108,14 @@ typedef struct VirtIOPCIRegion { uint32_t type; } VirtIOPCIRegion; +typedef struct VirtIOPCIQueue { + uint16_t num; + bool enabled; + uint32_t desc[2]; + uint32_t avail[2]; + uint32_t used[2]; +} VirtIOPCIQueue; + struct VirtIOPCIProxy { PCIDevice pci_dev; MemoryRegion bar; @@ -124,13 +136,7 @@ struct VirtIOPCIProxy { uint32_t dfselect; uint32_t gfselect; uint32_t guest_features[2]; - struct { - uint16_t num; - bool enabled; - uint32_t desc[2]; - uint32_t avail[2]; - uint32_t used[2]; - } vqs[VIRTIO_QUEUE_MAX]; + VirtIOPCIQueue vqs[VIRTIO_QUEUE_MAX]; bool ioeventfd_disabled; bool ioeventfd_started; diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index 939f802110..1edef5945d 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -1116,6 +1116,16 @@ static bool virtio_ringsize_needed(void *opaque) return false; } +static bool virtio_extra_state_needed(void *opaque) +{ + VirtIODevice *vdev = opaque; + BusState *qbus = qdev_get_parent_bus(DEVICE(vdev)); + VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); + + return k->has_extra_state && + k->has_extra_state(qbus->parent); +} + static void put_virtqueue_state(QEMUFile *f, void *pv, size_t size) { VirtIODevice *vdev = pv; @@ -1210,6 +1220,53 @@ static const VMStateDescription vmstate_virtio_ringsize = { } }; +static int get_extra_state(QEMUFile *f, void *pv, size_t size) +{ + VirtIODevice *vdev = pv; + BusState *qbus = qdev_get_parent_bus(DEVICE(vdev)); + VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); + + if (!k->load_extra_state) { + return -1; + } else { + return k->load_extra_state(qbus->parent, f); + } +} + +static void put_extra_state(QEMUFile *f, void *pv, size_t size) +{ + VirtIODevice *vdev = pv; + BusState *qbus = qdev_get_parent_bus(DEVICE(vdev)); + VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); + + k->save_extra_state(qbus->parent, f); +} + +static const VMStateInfo vmstate_info_extra_state = { + .name = "virtqueue_extra_state", + .get = get_extra_state, + .put = put_extra_state, +}; + +static const VMStateDescription vmstate_virtio_extra_state = { + .name = "virtio/extra_state", + .version_id = 1, + .minimum_version_id = 1, + .needed = &virtio_extra_state_needed, + .fields = (VMStateField[]) { + { + .name = "extra_state", + .version_id = 0, + .field_exists = NULL, + .size = 0, + .info = &vmstate_info_extra_state, + .flags = VMS_SINGLE, + .offset = 0, + }, + VMSTATE_END_OF_LIST() + } +}; + static const VMStateDescription vmstate_virtio_device_endian = { .name = "virtio/device_endian", .version_id = 1, @@ -1245,6 +1302,7 @@ static const VMStateDescription vmstate_virtio = { &vmstate_virtio_64bit_features, &vmstate_virtio_virtqueues, &vmstate_virtio_ringsize, + &vmstate_virtio_extra_state, NULL } }; diff --git a/include/hw/compat.h b/include/hw/compat.h index 93e71afb4a..65799c1868 100644 --- a/include/hw/compat.h +++ b/include/hw/compat.h @@ -6,6 +6,10 @@ .driver = "virtio-blk-device",\ .property = "scsi",\ .value = "true",\ + },{\ + .driver = "virtio-pci",\ + .property = "migrate-extra",\ + .value = "off",\ }, #define HW_COMPAT_2_3 \ diff --git a/include/hw/virtio/virtio-bus.h b/include/hw/virtio/virtio-bus.h index 8811415fa6..6c3d4cb19e 100644 --- a/include/hw/virtio/virtio-bus.h +++ b/include/hw/virtio/virtio-bus.h @@ -44,9 +44,12 @@ typedef struct VirtioBusClass { void (*notify)(DeviceState *d, uint16_t vector); void (*save_config)(DeviceState *d, QEMUFile *f); void (*save_queue)(DeviceState *d, int n, QEMUFile *f); + void (*save_extra_state)(DeviceState *d, QEMUFile *f); int (*load_config)(DeviceState *d, QEMUFile *f); int (*load_queue)(DeviceState *d, int n, QEMUFile *f); int (*load_done)(DeviceState *d, QEMUFile *f); + int (*load_extra_state)(DeviceState *d, QEMUFile *f); + bool (*has_extra_state)(DeviceState *d); bool (*query_guest_notifiers)(DeviceState *d); int (*set_guest_notifiers)(DeviceState *d, int nvqs, bool assign); int (*set_host_notifier)(DeviceState *d, int n, bool assigned); -- cgit v1.2.3-55-g7522 From b8aecea23aaccf39da54c77ef248f5fa50dcfbc1 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 6 Nov 2015 16:02:45 +0800 Subject: memory: don't try to adjust endianness for zero length eventfd There's no need to adjust endianness for zero length eventfd since the data wrote was actually ignored by kernel. So skip the adjust in this case to fix a possible crash when trying to use wildcard mmio eventfd in ppc. Cc: Greg Kurz Cc: Peter Maydell Cc: Paolo Bonzini Acked-by: Greg Kurz Signed-off-by: Jason Wang Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- memory.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/memory.c b/memory.c index c435c8827a..e193658fc7 100644 --- a/memory.c +++ b/memory.c @@ -1688,7 +1688,9 @@ void memory_region_add_eventfd(MemoryRegion *mr, }; unsigned i; - adjust_endianness(mr, &mrfd.data, size); + if (size) { + adjust_endianness(mr, &mrfd.data, size); + } memory_region_transaction_begin(); for (i = 0; i < mr->ioeventfd_nb; ++i) { if (memory_region_ioeventfd_before(mrfd, mr->ioeventfds[i])) { @@ -1721,7 +1723,9 @@ void memory_region_del_eventfd(MemoryRegion *mr, }; unsigned i; - adjust_endianness(mr, &mrfd.data, size); + if (size) { + adjust_endianness(mr, &mrfd.data, size); + } memory_region_transaction_begin(); for (i = 0; i < mr->ioeventfd_nb; ++i) { if (memory_region_ioeventfd_equal(mrfd, mr->ioeventfds[i])) { -- cgit v1.2.3-55-g7522 From 351082238d5d45d6836ec94eabe3fe7d72b36f46 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 6 Nov 2015 16:02:46 +0800 Subject: KVM: add support for any length io eventfd Signed-off-by: Jason Wang Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin Acked-by: Paolo Bonzini --- include/sysemu/kvm.h | 8 ++++++++ kvm-all.c | 4 ++++ kvm-stub.c | 1 + 3 files changed, 13 insertions(+) diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h index 4ac6176879..b31f325fa2 100644 --- a/include/sysemu/kvm.h +++ b/include/sysemu/kvm.h @@ -53,6 +53,7 @@ extern bool kvm_gsi_routing_allowed; extern bool kvm_gsi_direct_mapping; extern bool kvm_readonly_mem_allowed; extern bool kvm_direct_msi_allowed; +extern bool kvm_ioeventfd_any_length_allowed; #if defined CONFIG_KVM || !defined NEED_CPU_H #define kvm_enabled() (kvm_allowed) @@ -153,6 +154,12 @@ extern bool kvm_direct_msi_allowed; */ #define kvm_direct_msi_enabled() (kvm_direct_msi_allowed) +/** + * kvm_ioeventfd_any_length_enabled: + * Returns: true if KVM allows any length io eventfd. + */ +#define kvm_ioeventfd_any_length_enabled() (kvm_ioeventfd_any_length_allowed) + #else #define kvm_enabled() (0) #define kvm_irqchip_in_kernel() (false) @@ -166,6 +173,7 @@ extern bool kvm_direct_msi_allowed; #define kvm_gsi_direct_mapping() (false) #define kvm_readonly_mem_enabled() (false) #define kvm_direct_msi_enabled() (false) +#define kvm_ioeventfd_any_length_enabled() (false) #endif struct kvm_run; diff --git a/kvm-all.c b/kvm-all.c index de3c8c48bb..c648b814ec 100644 --- a/kvm-all.c +++ b/kvm-all.c @@ -109,6 +109,7 @@ bool kvm_allowed; bool kvm_readonly_mem_allowed; bool kvm_vm_attributes_allowed; bool kvm_direct_msi_allowed; +bool kvm_ioeventfd_any_length_allowed; static const KVMCapabilityInfo kvm_required_capabilites[] = { KVM_CAP_INFO(USER_MEMORY), @@ -1611,6 +1612,9 @@ static int kvm_init(MachineState *ms) kvm_vm_attributes_allowed = (kvm_check_extension(s, KVM_CAP_VM_ATTRIBUTES) > 0); + kvm_ioeventfd_any_length_allowed = + (kvm_check_extension(s, KVM_CAP_IOEVENTFD_ANY_LENGTH) > 0); + ret = kvm_arch_init(ms, s); if (ret < 0) { goto err; diff --git a/kvm-stub.c b/kvm-stub.c index a5051f7c6e..dc97a5edf1 100644 --- a/kvm-stub.c +++ b/kvm-stub.c @@ -30,6 +30,7 @@ bool kvm_gsi_routing_allowed; bool kvm_gsi_direct_mapping; bool kvm_allowed; bool kvm_readonly_mem_allowed; +bool kvm_ioeventfd_any_length_allowed; int kvm_init_vcpu(CPUState *cpu) { -- cgit v1.2.3-55-g7522 From bc85ccfdf5cc045588f665c84b5707d7364c8a6c Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 6 Nov 2015 16:02:47 +0800 Subject: virtio-pci: use zero length mmio eventfd for 1.0 notification cap when possible We use data match eventfd for 1.0 notification currently. This could be slow since software decoding is needed for mmio exit. To speed this up, we can switch to use zero length mmio eventfd for 1.0 notification since we can examine the queue index directly from the writing address. KVM kernel module can utilize this by registering it to fast mmio bus which could be as fast as pio on ept capable machine when fast mmio is supported by host kernel. Lots of improvements were seen on a ept capable machine: Guest RX:(TCP) size/session/+throughput%/+cpu%/-+per cpu%/ 64/1/+1.6807%/[-16.2421%]/[+21.3984%]/ 64/2/+0.6091%/[-11.0187%]/[+13.0678%]/ 64/4/+0.0553%/[-5.9768%]/[+6.4155%]/ 64/8/+0.1206%/[-4.0057%]/[+4.2984%]/ 256/1/-0.0031%/[-10.1166%]/[+11.2517%]/ 256/2/-0.5058%/[-6.1656%]/+6.0317%]/ ... Guest TX:(TCP) size/session/+throughput%/+cpu%/-+per cpu%/ 64/1/[+18.9183%]/-0.2823%/[+19.2550%]/ 64/2/[+13.5714%]/[+2.2675%]/[+11.0533%]/ 64/4/[+13.1070%]/[+2.1817%]/[+10.6920%]/ 64/8/[+13.0426%]/[+2.0887%]/[+10.7299%]/ 256/1/[+36.2761%]/+6.3434%/[+28.1471%]/ ... 1024/1/[+44.8873%]/+2.0811%/[+41.9335%]/ ... 1024/4/+0.0228%/[-2.2044%]/[+2.2774%]/ ... 16384/2/+0.0127%/[-5.0346%]/[+5.3148%]/ ... 65535/1/[+0.0062%]/[-4.1183%]/[+4.3017%]/ 65535/2/+0.0004%/[-4.2311%]/[+4.4185%]/ 65535/4/+0.0107%/[-4.6106%]/[+4.8446%]/ 65535/8/-0.0090%/[-5.5178%]/[+5.8306%]/ Latency:(TCP_RR) size/session/+transaction rate%/+cpu%/-+per cpu%/ 64/1/[+6.5248%]/[-9.2882%]/[+17.4322%]/ 64/25/[+11.0854%]/[+0.8000%]/[+10.2038%]/ 64/50/[+12.1076%]/[+2.4627%]/[+9.4131%]/ 256/1/[+5.3677%]/[+10.5669%]/-4.7024%/ 256/25/[+5.6402%]/-0.8962%/[+6.5955%]/ 256/50/[+5.9685%]/[+1.7766%]/[+4.1188%]/ 4096/1/+0.2508%/[-10.4941%]/[+12.0047%]/ 4096/25/[+1.8533%]/-0.0273%/+1.8812%/ 4096/50/[+1.2156%]/-1.4134%/+2.6667%/ Notes: data with '[]' is the one whose significance is greater than 95%. Thanks Wenli Quan for the benchmarking. Cc: Michael S. Tsirkin Signed-off-by: Jason Wang Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/virtio/virtio-pci.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index ab2a372aa4..9c3f6e30d7 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -270,6 +270,7 @@ static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy, EventNotifier *notifier = virtio_queue_get_host_notifier(vq); bool legacy = !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_LEGACY); bool modern = !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_MODERN); + bool fast_mmio = kvm_ioeventfd_any_length_enabled(); MemoryRegion *modern_mr = &proxy->notify.mr; MemoryRegion *legacy_mr = &proxy->bar; hwaddr modern_addr = QEMU_VIRTIO_PCI_QUEUE_MEM_MULT * @@ -286,8 +287,13 @@ static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy, } virtio_queue_set_host_notifier_fd_handler(vq, true, set_handler); if (modern) { - memory_region_add_eventfd(modern_mr, modern_addr, 2, - true, n, notifier); + if (fast_mmio) { + memory_region_add_eventfd(modern_mr, modern_addr, 0, + false, n, notifier); + } else { + memory_region_add_eventfd(modern_mr, modern_addr, 2, + false, n, notifier); + } } if (legacy) { memory_region_add_eventfd(legacy_mr, legacy_addr, 2, @@ -295,8 +301,13 @@ static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy, } } else { if (modern) { - memory_region_del_eventfd(modern_mr, modern_addr, 2, - true, n, notifier); + if (fast_mmio) { + memory_region_del_eventfd(modern_mr, modern_addr, 0, + false, n, notifier); + } else { + memory_region_del_eventfd(modern_mr, modern_addr, 2, + false, n, notifier); + } } if (legacy) { memory_region_del_eventfd(legacy_mr, legacy_addr, 2, -- cgit v1.2.3-55-g7522 From 9824d2a39d9893ef9bbe71f94efb57da265b73f6 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 6 Nov 2015 16:02:48 +0800 Subject: virtio-pci: introduce pio notification capability for modern device We used to use mmio for notification. This could be slow on some arch (e.g on x86 without EPT). So this patch introduces pio bar and a pio notification cap for modern device. This ability is enabled through property "modern-pio-notify" for virtio pci devices and was disabled by default. Management can enable when it thinks it was needed. Benchmarks shows almost no obvious difference compared to legacy device on machines without ept. Thanks Wenli Quan for the benchmarking. Cc: Michael S. Tsirkin Signed-off-by: Jason Wang Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/virtio/virtio-pci.c | 122 ++++++++++++++++++++++++++++++++++++++++++------- hw/virtio/virtio-pci.h | 8 ++++ 2 files changed, 113 insertions(+), 17 deletions(-) diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index 9c3f6e30d7..e4449daeb9 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -271,7 +271,9 @@ static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy, bool legacy = !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_LEGACY); bool modern = !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_MODERN); bool fast_mmio = kvm_ioeventfd_any_length_enabled(); + bool modern_pio = proxy->flags & VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY; MemoryRegion *modern_mr = &proxy->notify.mr; + MemoryRegion *modern_notify_mr = &proxy->notify_pio.mr; MemoryRegion *legacy_mr = &proxy->bar; hwaddr modern_addr = QEMU_VIRTIO_PCI_QUEUE_MEM_MULT * virtio_get_queue_index(vq); @@ -294,6 +296,10 @@ static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy, memory_region_add_eventfd(modern_mr, modern_addr, 2, false, n, notifier); } + if (modern_pio) { + memory_region_add_eventfd(modern_notify_mr, 0, 2, + true, n, notifier); + } } if (legacy) { memory_region_add_eventfd(legacy_mr, legacy_addr, 2, @@ -308,6 +314,10 @@ static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy, memory_region_del_eventfd(modern_mr, modern_addr, 2, false, n, notifier); } + if (modern_pio) { + memory_region_del_eventfd(modern_notify_mr, 0, 2, + true, n, notifier); + } } if (legacy) { memory_region_del_eventfd(legacy_mr, legacy_addr, 2, @@ -1416,6 +1426,17 @@ static void virtio_pci_notify_write(void *opaque, hwaddr addr, } } +static void virtio_pci_notify_write_pio(void *opaque, hwaddr addr, + uint64_t val, unsigned size) +{ + VirtIODevice *vdev = opaque; + unsigned queue = val; + + if (queue < VIRTIO_QUEUE_MAX) { + virtio_queue_notify(vdev, queue); + } +} + static uint64_t virtio_pci_isr_read(void *opaque, hwaddr addr, unsigned size) { @@ -1509,6 +1530,16 @@ static void virtio_pci_modern_regions_init(VirtIOPCIProxy *proxy) }, .endianness = DEVICE_LITTLE_ENDIAN, }; + static const MemoryRegionOps notify_pio_ops = { + .read = virtio_pci_notify_read, + .write = virtio_pci_notify_write_pio, + .impl = { + .min_access_size = 1, + .max_access_size = 4, + }, + .endianness = DEVICE_LITTLE_ENDIAN, + }; + memory_region_init_io(&proxy->common.mr, OBJECT(proxy), &common_ops, @@ -1533,30 +1564,60 @@ static void virtio_pci_modern_regions_init(VirtIOPCIProxy *proxy) virtio_bus_get_device(&proxy->bus), "virtio-pci-notify", proxy->notify.size); + + memory_region_init_io(&proxy->notify_pio.mr, OBJECT(proxy), + ¬ify_pio_ops, + virtio_bus_get_device(&proxy->bus), + "virtio-pci-notify-pio", + proxy->notify.size); } static void virtio_pci_modern_region_map(VirtIOPCIProxy *proxy, VirtIOPCIRegion *region, - struct virtio_pci_cap *cap) + struct virtio_pci_cap *cap, + MemoryRegion *mr, + uint8_t bar) { - memory_region_add_subregion(&proxy->modern_bar, - region->offset, - ®ion->mr); + memory_region_add_subregion(mr, region->offset, ®ion->mr); cap->cfg_type = region->type; - cap->bar = proxy->modern_mem_bar; + cap->bar = bar; cap->offset = cpu_to_le32(region->offset); cap->length = cpu_to_le32(region->size); virtio_pci_add_mem_cap(proxy, cap); + +} + +static void virtio_pci_modern_mem_region_map(VirtIOPCIProxy *proxy, + VirtIOPCIRegion *region, + struct virtio_pci_cap *cap) +{ + virtio_pci_modern_region_map(proxy, region, cap, + &proxy->modern_bar, proxy->modern_mem_bar); } -static void virtio_pci_modern_region_unmap(VirtIOPCIProxy *proxy, - VirtIOPCIRegion *region) +static void virtio_pci_modern_io_region_map(VirtIOPCIProxy *proxy, + VirtIOPCIRegion *region, + struct virtio_pci_cap *cap) +{ + virtio_pci_modern_region_map(proxy, region, cap, + &proxy->io_bar, proxy->modern_io_bar); +} + +static void virtio_pci_modern_mem_region_unmap(VirtIOPCIProxy *proxy, + VirtIOPCIRegion *region) { memory_region_del_subregion(&proxy->modern_bar, ®ion->mr); } +static void virtio_pci_modern_io_region_unmap(VirtIOPCIProxy *proxy, + VirtIOPCIRegion *region) +{ + memory_region_del_subregion(&proxy->io_bar, + ®ion->mr); +} + /* This is called by virtio-bus just after the device is plugged. */ static void virtio_pci_device_plugged(DeviceState *d, Error **errp) { @@ -1564,6 +1625,7 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp) VirtioBusState *bus = &proxy->bus; bool legacy = !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_LEGACY); bool modern = !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_MODERN); + bool modern_pio = proxy->flags & VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY; uint8_t *config; uint32_t size; VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus); @@ -1602,16 +1664,31 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp) .cap.cap_len = sizeof cfg, .cap.cfg_type = VIRTIO_PCI_CAP_PCI_CFG, }; - struct virtio_pci_cfg_cap *cfg_mask; + struct virtio_pci_notify_cap notify_pio = { + .cap.cap_len = sizeof notify, + .notify_off_multiplier = cpu_to_le32(0x0), + }; - /* TODO: add io access for speed */ + struct virtio_pci_cfg_cap *cfg_mask; virtio_add_feature(&vdev->host_features, VIRTIO_F_VERSION_1); virtio_pci_modern_regions_init(proxy); - virtio_pci_modern_region_map(proxy, &proxy->common, &cap); - virtio_pci_modern_region_map(proxy, &proxy->isr, &cap); - virtio_pci_modern_region_map(proxy, &proxy->device, &cap); - virtio_pci_modern_region_map(proxy, &proxy->notify, ¬ify.cap); + + virtio_pci_modern_mem_region_map(proxy, &proxy->common, &cap); + virtio_pci_modern_mem_region_map(proxy, &proxy->isr, &cap); + virtio_pci_modern_mem_region_map(proxy, &proxy->device, &cap); + virtio_pci_modern_mem_region_map(proxy, &proxy->notify, ¬ify.cap); + + if (modern_pio) { + memory_region_init(&proxy->io_bar, OBJECT(proxy), + "virtio-pci-io", 0x4); + + pci_register_bar(&proxy->pci_dev, proxy->modern_io_bar, + PCI_BASE_ADDRESS_SPACE_IO, &proxy->io_bar); + + virtio_pci_modern_io_region_map(proxy, &proxy->notify_pio, + ¬ify_pio.cap); + } pci_register_bar(&proxy->pci_dev, proxy->modern_mem_bar, PCI_BASE_ADDRESS_SPACE_MEMORY | @@ -1667,14 +1744,18 @@ static void virtio_pci_device_unplugged(DeviceState *d) { VirtIOPCIProxy *proxy = VIRTIO_PCI(d); bool modern = !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_MODERN); + bool modern_pio = proxy->flags & VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY; virtio_pci_stop_ioeventfd(proxy); if (modern) { - virtio_pci_modern_region_unmap(proxy, &proxy->common); - virtio_pci_modern_region_unmap(proxy, &proxy->isr); - virtio_pci_modern_region_unmap(proxy, &proxy->device); - virtio_pci_modern_region_unmap(proxy, &proxy->notify); + virtio_pci_modern_mem_region_unmap(proxy, &proxy->common); + virtio_pci_modern_mem_region_unmap(proxy, &proxy->isr); + virtio_pci_modern_mem_region_unmap(proxy, &proxy->device); + virtio_pci_modern_mem_region_unmap(proxy, &proxy->notify); + if (modern_pio) { + virtio_pci_modern_io_region_unmap(proxy, &proxy->notify_pio); + } } } @@ -1694,6 +1775,7 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp) */ proxy->legacy_io_bar = 0; proxy->msix_bar = 1; + proxy->modern_io_bar = 2; proxy->modern_mem_bar = 4; proxy->common.offset = 0x0; @@ -1713,6 +1795,10 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp) QEMU_VIRTIO_PCI_QUEUE_MEM_MULT * VIRTIO_QUEUE_MAX; proxy->notify.type = VIRTIO_PCI_CAP_NOTIFY_CFG; + proxy->notify_pio.offset = 0x0; + proxy->notify_pio.size = 0x4; + proxy->notify_pio.type = VIRTIO_PCI_CAP_NOTIFY_CFG; + /* subclasses can enforce modern, so do this unconditionally */ memory_region_init(&proxy->modern_bar, OBJECT(proxy), "virtio-pci", 2 * QEMU_VIRTIO_PCI_QUEUE_MEM_MULT * @@ -1759,6 +1845,8 @@ static Property virtio_pci_properties[] = { VIRTIO_PCI_FLAG_DISABLE_MODERN_BIT, true), DEFINE_PROP_BIT("migrate-extra", VirtIOPCIProxy, flags, VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT, true), + DEFINE_PROP_BIT("modern-pio-notify", VirtIOPCIProxy, flags, + VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY_BIT, false), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/virtio/virtio-pci.h b/hw/virtio/virtio-pci.h index 58679f78bf..460c3c9ce0 100644 --- a/hw/virtio/virtio-pci.h +++ b/hw/virtio/virtio-pci.h @@ -79,6 +79,11 @@ typedef struct VirtioBusClass VirtioPCIBusClass; #define VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT 4 #define VIRTIO_PCI_FLAG_MIGRATE_EXTRA (1 << VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT) +/* have pio notification for modern device ? */ +#define VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY_BIT 5 +#define VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY \ + (1 << VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY_BIT) + typedef struct { MSIMessage msg; int virq; @@ -123,11 +128,14 @@ struct VirtIOPCIProxy { VirtIOPCIRegion isr; VirtIOPCIRegion device; VirtIOPCIRegion notify; + VirtIOPCIRegion notify_pio; MemoryRegion modern_bar; + MemoryRegion io_bar; MemoryRegion modern_cfg; AddressSpace modern_as; uint32_t legacy_io_bar; uint32_t msix_bar; + uint32_t modern_io_bar; uint32_t modern_mem_bar; int config_cap; uint32_t flags; -- cgit v1.2.3-55-g7522 From 393f04d3ab40d03aa2fde0017ff7f02fc34cbd4e Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 6 Nov 2015 16:02:49 +0800 Subject: virtio-pci: unbreak queue_enable read Guest always get zero when reading queue_enable. This violates spec. Fixing this by setting the queue_enable to true during any guest writing and setting it to zero during reset. Cc: Michael S. Tsirkin Signed-off-by: Jason Wang Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/virtio/virtio-pci.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index e4449daeb9..52a9e338a2 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -1384,6 +1384,7 @@ static void virtio_pci_common_write(void *opaque, hwaddr addr, proxy->vqs[vdev->queue_sel].avail[0], ((uint64_t)proxy->vqs[vdev->queue_sel].used[1]) << 32 | proxy->vqs[vdev->queue_sel].used[0]); + proxy->vqs[vdev->queue_sel].enabled = 1; break; case VIRTIO_PCI_COMMON_Q_DESCLO: proxy->vqs[vdev->queue_sel].desc[0] = val; @@ -1831,9 +1832,15 @@ static void virtio_pci_reset(DeviceState *qdev) { VirtIOPCIProxy *proxy = VIRTIO_PCI(qdev); VirtioBusState *bus = VIRTIO_BUS(&proxy->bus); + int i; + virtio_pci_stop_ioeventfd(proxy); virtio_bus_reset(bus); msix_unuse_all_vectors(&proxy->pci_dev); + + for (i = 0; i < VIRTIO_QUEUE_MAX; i++) { + proxy->vqs[i].enabled = 0; + } } static Property virtio_pci_properties[] = { -- cgit v1.2.3-55-g7522 From 2b8819c6eee517c1582983773f8555bb3f9ed645 Mon Sep 17 00:00:00 2001 From: Victor Kaplansky Date: Wed, 11 Nov 2015 16:26:02 +0200 Subject: vhost-user: modify SET_LOG_BASE to pass mmap size and offset Unlike the kernel, vhost-user application accesses log table by mmaping it to its user space. This change adds two new fields to VhostUserMsg payload: mmap_size, and mmap_offset and make QEMU to pass the to vhost-user application in VHOST_USER_SET_LOG_BASE request. Signed-off-by: Victor Kaplansky Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- docs/specs/vhost-user.txt | 8 +++++++- hw/virtio/vhost-user.c | 11 +++++++++-- tests/vhost-user-test.c | 8 ++++++++ 3 files changed, 24 insertions(+), 3 deletions(-) diff --git a/docs/specs/vhost-user.txt b/docs/specs/vhost-user.txt index e0d71e27e6..eb8f2b2020 100644 --- a/docs/specs/vhost-user.txt +++ b/docs/specs/vhost-user.txt @@ -98,6 +98,7 @@ typedef struct VhostUserMsg { struct vhost_vring_state state; struct vhost_vring_addr addr; VhostUserMemory memory; + VhostUserLog log; }; } QEMU_PACKED VhostUserMsg; @@ -282,7 +283,12 @@ Message types Master payload: u64 Slave payload: N/A - Sets the logging base address. + Sets logging shared memory space. + When slave has VHOST_USER_PROTOCOL_F_LOG_SHMFD protocol + feature, the log memory fd is provided in the ancillary data of + VHOST_USER_SET_LOG_BASE message, the size and offset of shared + memory area provided in the message. + * VHOST_USER_SET_LOG_FD diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 83c84f1cd6..46c63bc97b 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -75,6 +75,11 @@ typedef struct VhostUserMemory { VhostUserMemoryRegion regions[VHOST_MEMORY_MAX_NREGIONS]; } VhostUserMemory; +typedef struct VhostUserLog { + uint64_t mmap_size; + uint64_t mmap_offset; +} VhostUserLog; + typedef struct VhostUserMsg { VhostUserRequest request; @@ -89,6 +94,7 @@ typedef struct VhostUserMsg { struct vhost_vring_state state; struct vhost_vring_addr addr; VhostUserMemory memory; + VhostUserLog log; } payload; } QEMU_PACKED VhostUserMsg; @@ -200,8 +206,9 @@ static int vhost_user_set_log_base(struct vhost_dev *dev, uint64_t base, VhostUserMsg msg = { .request = VHOST_USER_SET_LOG_BASE, .flags = VHOST_USER_VERSION, - .payload.u64 = base, - .size = sizeof(msg.payload.u64), + .payload.log.mmap_size = log->size, + .payload.log.mmap_offset = 0, + .size = sizeof(msg.payload.log), }; if (shmfd && log->fd != -1) { diff --git a/tests/vhost-user-test.c b/tests/vhost-user-test.c index b6dde753f8..f005ecfa68 100644 --- a/tests/vhost-user-test.c +++ b/tests/vhost-user-test.c @@ -86,6 +86,11 @@ typedef struct VhostUserMemory { VhostUserMemoryRegion regions[VHOST_MEMORY_MAX_NREGIONS]; } VhostUserMemory; +typedef struct VhostUserLog { + uint64_t mmap_size; + uint64_t mmap_offset; +} VhostUserLog; + typedef struct VhostUserMsg { VhostUserRequest request; @@ -94,10 +99,13 @@ typedef struct VhostUserMsg { uint32_t flags; uint32_t size; /* the following payload size */ union { +#define VHOST_USER_VRING_IDX_MASK (0xff) +#define VHOST_USER_VRING_NOFD_MASK (0x1<<8) uint64_t u64; struct vhost_vring_state state; struct vhost_vring_addr addr; VhostUserMemory memory; + VhostUserLog log; } payload; } QEMU_PACKED VhostUserMsg; -- cgit v1.2.3-55-g7522 From 60915dc4691768c4dc62458bb3e16c843fab091d Mon Sep 17 00:00:00 2001 From: Yuanhan Liu Date: Wed, 11 Nov 2015 21:24:37 +0800 Subject: vhost: rename RESET_DEVICE backto RESET_OWNER This patch basically reverts commit d1f8b30e. It turned out that it breaks stuff, so revert it: http://lists.nongnu.org/archive/html/qemu-devel/2015-10/msg00949.html CC: "Michael S. Tsirkin" Reported-by: Paolo Bonzini Signed-off-by: Yuanhan Liu Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- docs/specs/vhost-user.txt | 4 ++-- hw/virtio/vhost-backend.c | 2 +- hw/virtio/vhost-user.c | 6 +++--- linux-headers/linux/vhost.h | 2 +- tests/vhost-user-bridge.c | 6 +++--- tests/vhost-user-test.c | 4 ++-- 6 files changed, 12 insertions(+), 12 deletions(-) diff --git a/docs/specs/vhost-user.txt b/docs/specs/vhost-user.txt index eb8f2b2020..26dde2ec42 100644 --- a/docs/specs/vhost-user.txt +++ b/docs/specs/vhost-user.txt @@ -256,10 +256,10 @@ Message types as an owner of the session. This can be used on the Slave as a "session start" flag. - * VHOST_USER_RESET_DEVICE + * VHOST_USER_RESET_OWNER Id: 4 - Equivalent ioctl: VHOST_RESET_DEVICE + Equivalent ioctl: VHOST_RESET_OWNER Master payload: N/A Issued when a new connection is about to be closed. The Master will no diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c index 1d5f684eb0..b734a601a1 100644 --- a/hw/virtio/vhost-backend.c +++ b/hw/virtio/vhost-backend.c @@ -156,7 +156,7 @@ static int vhost_kernel_set_owner(struct vhost_dev *dev) static int vhost_kernel_reset_device(struct vhost_dev *dev) { - return vhost_kernel_call(dev, VHOST_RESET_DEVICE, NULL); + return vhost_kernel_call(dev, VHOST_RESET_OWNER, NULL); } static int vhost_kernel_get_vq_index(struct vhost_dev *dev, int idx) diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 46c63bc97b..c44360219f 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -43,7 +43,7 @@ typedef enum VhostUserRequest { VHOST_USER_GET_FEATURES = 1, VHOST_USER_SET_FEATURES = 2, VHOST_USER_SET_OWNER = 3, - VHOST_USER_RESET_DEVICE = 4, + VHOST_USER_RESET_OWNER = 4, VHOST_USER_SET_MEM_TABLE = 5, VHOST_USER_SET_LOG_BASE = 6, VHOST_USER_SET_LOG_FD = 7, @@ -163,7 +163,7 @@ static bool vhost_user_one_time_request(VhostUserRequest request) { switch (request) { case VHOST_USER_SET_OWNER: - case VHOST_USER_RESET_DEVICE: + case VHOST_USER_RESET_OWNER: case VHOST_USER_SET_MEM_TABLE: case VHOST_USER_GET_QUEUE_NUM: return true; @@ -493,7 +493,7 @@ static int vhost_user_set_owner(struct vhost_dev *dev) static int vhost_user_reset_device(struct vhost_dev *dev) { VhostUserMsg msg = { - .request = VHOST_USER_RESET_DEVICE, + .request = VHOST_USER_RESET_OWNER, .flags = VHOST_USER_VERSION, }; diff --git a/linux-headers/linux/vhost.h b/linux-headers/linux/vhost.h index 14a01602f8..ead86db91a 100644 --- a/linux-headers/linux/vhost.h +++ b/linux-headers/linux/vhost.h @@ -78,7 +78,7 @@ struct vhost_memory { #define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01) /* Give up ownership, and reset the device to default values. * Allows subsequent call to VHOST_OWNER_SET to succeed. */ -#define VHOST_RESET_DEVICE _IO(VHOST_VIRTIO, 0x02) +#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02) /* Set up/modify memory layout */ #define VHOST_SET_MEM_TABLE _IOW(VHOST_VIRTIO, 0x03, struct vhost_memory) diff --git a/tests/vhost-user-bridge.c b/tests/vhost-user-bridge.c index fa18ad55fb..864f69e738 100644 --- a/tests/vhost-user-bridge.c +++ b/tests/vhost-user-bridge.c @@ -188,7 +188,7 @@ typedef enum VhostUserRequest { VHOST_USER_GET_FEATURES = 1, VHOST_USER_SET_FEATURES = 2, VHOST_USER_SET_OWNER = 3, - VHOST_USER_RESET_DEVICE = 4, + VHOST_USER_RESET_OWNER = 4, VHOST_USER_SET_MEM_TABLE = 5, VHOST_USER_SET_LOG_BASE = 6, VHOST_USER_SET_LOG_FD = 7, @@ -274,7 +274,7 @@ static const char *vubr_request_str[] = { [VHOST_USER_GET_FEATURES] = "VHOST_USER_GET_FEATURES", [VHOST_USER_SET_FEATURES] = "VHOST_USER_SET_FEATURES", [VHOST_USER_SET_OWNER] = "VHOST_USER_SET_OWNER", - [VHOST_USER_RESET_DEVICE] = "VHOST_USER_RESET_DEVICE", + [VHOST_USER_RESET_OWNER] = "VHOST_USER_RESET_OWNER", [VHOST_USER_SET_MEM_TABLE] = "VHOST_USER_SET_MEM_TABLE", [VHOST_USER_SET_LOG_BASE] = "VHOST_USER_SET_LOG_BASE", [VHOST_USER_SET_LOG_FD] = "VHOST_USER_SET_LOG_FD", @@ -921,7 +921,7 @@ vubr_execute_request(VubrDev *dev, VhostUserMsg *vmsg) return vubr_set_features_exec(dev, vmsg); case VHOST_USER_SET_OWNER: return vubr_set_owner_exec(dev, vmsg); - case VHOST_USER_RESET_DEVICE: + case VHOST_USER_RESET_OWNER: return vubr_reset_device_exec(dev, vmsg); case VHOST_USER_SET_MEM_TABLE: return vubr_set_mem_table_exec(dev, vmsg); diff --git a/tests/vhost-user-test.c b/tests/vhost-user-test.c index f005ecfa68..01cfc7e25d 100644 --- a/tests/vhost-user-test.c +++ b/tests/vhost-user-test.c @@ -57,7 +57,7 @@ typedef enum VhostUserRequest { VHOST_USER_GET_FEATURES = 1, VHOST_USER_SET_FEATURES = 2, VHOST_USER_SET_OWNER = 3, - VHOST_USER_RESET_DEVICE = 4, + VHOST_USER_RESET_OWNER = 4, VHOST_USER_SET_MEM_TABLE = 5, VHOST_USER_SET_LOG_BASE = 6, VHOST_USER_SET_LOG_FD = 7, @@ -315,7 +315,7 @@ static void chr_read(void *opaque, const uint8_t *buf, int size) g_cond_signal(&s->data_cond); break; - case VHOST_USER_RESET_DEVICE: + case VHOST_USER_RESET_OWNER: s->fds_num = 0; break; -- cgit v1.2.3-55-g7522 From 3a12f32229a046f4d4ab0a3a52fb01d2d5a1ab76 Mon Sep 17 00:00:00 2001 From: Yuanhan Liu Date: Wed, 11 Nov 2015 21:24:41 +0800 Subject: vhost: send SET_VRING_ENABLE at start/stop Send SET_VRING_ENABLE at start/stop, to give the backend an explicit sign of our state. Signed-off-by: Yuanhan Liu Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/virtio/vhost.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index de29968a79..1794f0d211 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -1226,6 +1226,11 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) } } + if (hdev->vhost_ops->vhost_set_vring_enable) { + /* only enable first vq pair by default */ + hdev->vhost_ops->vhost_set_vring_enable(hdev, hdev->vq_index == 0); + } + return 0; fail_log: vhost_log_put(hdev, false); @@ -1256,6 +1261,10 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev) hdev->vq_index + i); } + if (hdev->vhost_ops->vhost_set_vring_enable) { + hdev->vhost_ops->vhost_set_vring_enable(hdev, 0); + } + vhost_log_put(hdev, true); hdev->started = false; hdev->log = NULL; -- cgit v1.2.3-55-g7522 From 1811e64c35fe1d9bce77952937a16c001dc08465 Mon Sep 17 00:00:00 2001 From: Marcel Apfelbaum Date: Tue, 10 Nov 2015 13:41:29 +0200 Subject: hw/virtio: Add PCIe capability to virtio devices The virtio devices are converted to PCI-Express if they are plugged into a PCI-Express bus and the 'modern' protocol is enabled. Devices plugged directly into the Root Complex as Integrated Endpoints remain PCI. Signed-off-by: Marcel Apfelbaum Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/virtio/virtio-pci.c | 22 ++++++++++++++++++++++ hw/virtio/virtio-pci.h | 2 ++ include/hw/compat.h | 4 ++++ 3 files changed, 28 insertions(+) diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index 52a9e338a2..dd485629da 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -1814,6 +1814,26 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp) address_space_init(&proxy->modern_as, &proxy->modern_cfg, "virtio-pci-cfg-as"); + if (!(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_PCIE) + && !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_MODERN) + && pci_bus_is_express(pci_dev->bus) + && !pci_bus_is_root(pci_dev->bus)) { + int pos; + + pci_dev->cap_present |= QEMU_PCI_CAP_EXPRESS; + pos = pcie_endpoint_cap_init(pci_dev, 0); + assert(pos > 0); + + pos = pci_add_capability(pci_dev, PCI_CAP_ID_PM, 0, PCI_PM_SIZEOF); + assert(pos > 0); + + /* + * Indicates that this function complies with revision 1.2 of the + * PCI Power Management Interface Specification. + */ + pci_set_word(pci_dev->config + pos + PCI_PM_PMC, 0x3); + } + virtio_pci_bus_new(&proxy->bus, sizeof(proxy->bus), proxy); if (k->realize) { k->realize(proxy, errp); @@ -1854,6 +1874,8 @@ static Property virtio_pci_properties[] = { VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT, true), DEFINE_PROP_BIT("modern-pio-notify", VirtIOPCIProxy, flags, VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY_BIT, false), + DEFINE_PROP_BIT("x-disable-pcie", VirtIOPCIProxy, flags, + VIRTIO_PCI_FLAG_DISABLE_PCIE_BIT, false), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/virtio/virtio-pci.h b/hw/virtio/virtio-pci.h index 460c3c9ce0..ffb74bb908 100644 --- a/hw/virtio/virtio-pci.h +++ b/hw/virtio/virtio-pci.h @@ -72,8 +72,10 @@ typedef struct VirtioBusClass VirtioPCIBusClass; /* virtio version flags */ #define VIRTIO_PCI_FLAG_DISABLE_LEGACY_BIT 2 #define VIRTIO_PCI_FLAG_DISABLE_MODERN_BIT 3 +#define VIRTIO_PCI_FLAG_DISABLE_PCIE_BIT 4 #define VIRTIO_PCI_FLAG_DISABLE_LEGACY (1 << VIRTIO_PCI_FLAG_DISABLE_LEGACY_BIT) #define VIRTIO_PCI_FLAG_DISABLE_MODERN (1 << VIRTIO_PCI_FLAG_DISABLE_MODERN_BIT) +#define VIRTIO_PCI_FLAG_DISABLE_PCIE (1 << VIRTIO_PCI_FLAG_DISABLE_PCIE_BIT) /* migrate extra state */ #define VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT 4 diff --git a/include/hw/compat.h b/include/hw/compat.h index 65799c1868..845aace577 100644 --- a/include/hw/compat.h +++ b/include/hw/compat.h @@ -6,6 +6,10 @@ .driver = "virtio-blk-device",\ .property = "scsi",\ .value = "true",\ + },{\ + .driver = "virtio-pci",\ + .property = "x-disable-pcie",\ + .value = "on",\ },{\ .driver = "virtio-pci",\ .property = "migrate-extra",\ -- cgit v1.2.3-55-g7522 From 4652f1640e029e1f2433fa77ba6af285c7cd923a Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Thu, 22 Oct 2015 19:38:42 +0200 Subject: virtio-9p: add savem handlers We don't support migration of mounted 9p shares. This is handled by a migration blocker. One would expect, however, to be able to migrate if the share is unmounted. Unfortunately virtio-9p-device does not register savevm handlers at all ! Migration succeeds and leaves the guest with a dangling device... This patch simply registers migration handlers for virtio-9p-device. Whether migration is possible or not still depends on the migration blocker. Signed-off-by: Greg Kurz Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/9pfs/virtio-9p-device.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/hw/9pfs/virtio-9p-device.c b/hw/9pfs/virtio-9p-device.c index 93a407c459..e3abcfaffb 100644 --- a/hw/9pfs/virtio-9p-device.c +++ b/hw/9pfs/virtio-9p-device.c @@ -43,6 +43,16 @@ static void virtio_9p_get_config(VirtIODevice *vdev, uint8_t *config) g_free(cfg); } +static void virtio_9p_save(QEMUFile *f, void *opaque) +{ + virtio_save(VIRTIO_DEVICE(opaque), f); +} + +static int virtio_9p_load(QEMUFile *f, void *opaque, int version_id) +{ + return virtio_load(VIRTIO_DEVICE(opaque), f, version_id); +} + static void virtio_9p_device_realize(DeviceState *dev, Error **errp) { VirtIODevice *vdev = VIRTIO_DEVICE(dev); @@ -130,6 +140,7 @@ static void virtio_9p_device_realize(DeviceState *dev, Error **errp) } v9fs_path_free(&path); + register_savevm(dev, "virtio-9p", -1, 1, virtio_9p_save, virtio_9p_load, s); return; out: g_free(s->ctx.fs_root); -- cgit v1.2.3-55-g7522