| Message ID | 20180405104834.10457-4-pagupta@redhat.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On 05.04.2018 12:48, Pankaj Gupta wrote: > This patch adds virtio-pmem Qemu device. > > This device configures memory address range information with file > backend type. It acts like persistent memory device for KVM guest. > It presents the memory address range to virtio-pmem driver over > virtio channel and does the block flush whenever there is request > from guest to flush/sync. (Qemu part for backing file flush > is yet to be implemented). > > Current code is a RFC to support guest with persistent memory > range & DAX. > > Signed-off-by: Pankaj Gupta <pagupta@redhat.com> > --- > hw/virtio/Makefile.objs | 2 +- > hw/virtio/virtio-pci.c | 44 +++++++++ > hw/virtio/virtio-pci.h | 14 +++ > hw/virtio/virtio-pmem.c | 133 ++++++++++++++++++++++++++++ > include/hw/pci/pci.h | 1 + > include/hw/virtio/virtio-pmem.h | 43 +++++++++ > include/standard-headers/linux/virtio_ids.h | 1 + > 7 files changed, 237 insertions(+), 1 deletion(-) > create mode 100644 hw/virtio/virtio-pmem.c > create mode 100644 include/hw/virtio/virtio-pmem.h > > diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs > index 765d363c1f..bb5573d2ef 100644 > --- a/hw/virtio/Makefile.objs > +++ b/hw/virtio/Makefile.objs > @@ -5,7 +5,7 @@ common-obj-y += virtio-bus.o > common-obj-y += virtio-mmio.o > > obj-y += virtio.o virtio-balloon.o > -obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o > +obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o virtio-pmem.o > obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock.o > obj-y += virtio-crypto.o > obj-$(CONFIG_VIRTIO_PCI) += virtio-crypto-pci.o > diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c > index c20537f31d..114ca05497 100644 > --- a/hw/virtio/virtio-pci.c > +++ b/hw/virtio/virtio-pci.c > @@ -2491,6 +2491,49 @@ static const TypeInfo virtio_rng_pci_info = { > .class_init = virtio_rng_pci_class_init, > }; > > +/* virtio-pmem-pci */ > + > +static void virtio_pmem_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) > +{ > + VirtIOPMEMPCI *vpmem = VIRTIO_PMEM_PCI(vpci_dev); > + DeviceState *vdev = DEVICE(&vpmem->vdev); > + > + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); > + object_property_set_bool(OBJECT(vdev), true, "realized", errp); > +} > + > +static void virtio_pmem_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 = virtio_pmem_pci_realize; > + set_bit(DEVICE_CATEGORY_MISC, dc->categories); > + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; > + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_PMEM; > + pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; > + pcidev_k->class_id = PCI_CLASS_OTHERS; > +} > + > +static void virtio_pmem_pci_instance_init(Object *obj) > +{ > + VirtIOPMEMPCI *dev = VIRTIO_PMEM_PCI(obj); > + > + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), > + TYPE_VIRTIO_PMEM); > + object_property_add_alias(obj, "memdev", OBJECT(&dev->vdev), "memdev", > + &error_abort); > +} > + > +static const TypeInfo virtio_pmem_pci_info = { > + .name = TYPE_VIRTIO_PMEM_PCI, > + .parent = TYPE_VIRTIO_PCI, > + .instance_size = sizeof(VirtIOPMEMPCI), > + .instance_init = virtio_pmem_pci_instance_init, > + .class_init = virtio_pmem_pci_class_init, > +}; > + > + > /* virtio-input-pci */ > > static Property virtio_input_pci_properties[] = { > @@ -2683,6 +2726,7 @@ static void virtio_pci_register_types(void) > type_register_static(&virtio_balloon_pci_info); > type_register_static(&virtio_serial_pci_info); > type_register_static(&virtio_net_pci_info); > + type_register_static(&virtio_pmem_pci_info); > #ifdef CONFIG_VHOST_SCSI > type_register_static(&vhost_scsi_pci_info); > #endif > diff --git a/hw/virtio/virtio-pci.h b/hw/virtio/virtio-pci.h > index 813082b0d7..fe74fcad3f 100644 > --- a/hw/virtio/virtio-pci.h > +++ b/hw/virtio/virtio-pci.h > @@ -19,6 +19,7 @@ > #include "hw/virtio/virtio-blk.h" > #include "hw/virtio/virtio-net.h" > #include "hw/virtio/virtio-rng.h" > +#include "hw/virtio/virtio-pmem.h" > #include "hw/virtio/virtio-serial.h" > #include "hw/virtio/virtio-scsi.h" > #include "hw/virtio/virtio-balloon.h" > @@ -57,6 +58,7 @@ typedef struct VirtIOInputHostPCI VirtIOInputHostPCI; > typedef struct VirtIOGPUPCI VirtIOGPUPCI; > typedef struct VHostVSockPCI VHostVSockPCI; > typedef struct VirtIOCryptoPCI VirtIOCryptoPCI; > +typedef struct VirtIOPMEMPCI VirtIOPMEMPCI; > > /* virtio-pci-bus */ > > @@ -274,6 +276,18 @@ struct VirtIOBlkPCI { > VirtIOBlock vdev; > }; > > +/* > + * virtio-pmem-pci: This extends VirtioPCIProxy. > + */ > +#define TYPE_VIRTIO_PMEM_PCI "virtio-pmem-pci" > +#define VIRTIO_PMEM_PCI(obj) \ > + OBJECT_CHECK(VirtIOPMEMPCI, (obj), TYPE_VIRTIO_PMEM_PCI) > + > +struct VirtIOPMEMPCI { > + VirtIOPCIProxy parent_obj; > + VirtIOPMEM vdev; > +}; > + > /* > * virtio-balloon-pci: This extends VirtioPCIProxy. > */ > diff --git a/hw/virtio/virtio-pmem.c b/hw/virtio/virtio-pmem.c > new file mode 100644 > index 0000000000..28d06fc501 > --- /dev/null > +++ b/hw/virtio/virtio-pmem.c > @@ -0,0 +1,133 @@ > +/* > + * Virtio pmem device > + * > + */ > + > + > +#include "qemu/osdep.h" > +#include "qapi/error.h" > +#include "qemu-common.h" > +#include "qemu/error-report.h" > +#include "hw/virtio/virtio-pmem.h" > + > + > +static void virtio_pmem_system_reset(void *opaque) > +{ > + > +} > + > +static void virtio_pmem_flush(VirtIODevice *vdev, VirtQueue *vq) > +{ > + VirtQueueElement *elem; > + > + elem = virtqueue_pop(vq, sizeof(VirtQueueElement)); > + if (!elem) { > + return; > + } > + /* todo flush raw file */ > + > + virtio_notify(vdev, vq); > + g_free(elem); > + > +} > + > +static void virtio_pmem_get_config(VirtIODevice *vdev, uint8_t *config) > +{ > + VirtIOPMEM *pmem = VIRTIO_PMEM(vdev); > + struct virtio_pmem_config *pmemcfg = (struct virtio_pmem_config *) config; > + > + pmemcfg->start = pmem->start; > + pmemcfg->size = pmem->size; > + pmemcfg->align = pmem->align; > +} > + > +static uint64_t virtio_pmem_get_features(VirtIODevice *vdev, uint64_t features, > + Error **errp) > +{ > + virtio_add_feature(&features, VIRTIO_PMEM_PLUG); > + return features; > +} > + > + > +static void virtio_pmem_realize(DeviceState *dev, Error **errp) > +{ > + VirtIODevice *vdev = VIRTIO_DEVICE(dev); > + VirtIOPMEM *pmem = VIRTIO_PMEM(dev); > + MachineState *ms = MACHINE(qdev_get_machine()); > + MemoryRegion *mr; > + PCMachineState *pcms = PC_MACHINE(object_dynamic_cast(OBJECT(ms), TYPE_PC_MACHINE)); > + uint64_t addr; > + > + if (!pmem->memdev) { > + error_setg(errp, "virtio-pmem not set"); > + return; > + } > + > + mr = host_memory_backend_get_memory(pmem->memdev, errp); > + addr = pcms->hotplug_memory.base; > + pmem->start = addr; > + pmem->size = memory_region_size(mr); > + pmem->align = memory_region_get_alignment(mr); > + > + memory_region_init_alias(&pmem->mr, OBJECT(ms), > + "virtio_pmem-memory", mr, 0, pmem->size); > + > + host_memory_backend_set_mapped(pmem->memdev, true); > + virtio_init(vdev, TYPE_VIRTIO_PMEM, VIRTIO_ID_PMEM, > + sizeof(struct virtio_pmem_config)); > + > + pmem->rq_vq = virtio_add_queue(vdev, 128, virtio_pmem_flush); > + qemu_register_reset(virtio_pmem_system_reset, pmem); So right now you're just using some memdev for testing. I assume that the memory region we will provide to the guest will be a simple memory mapped raw file. Dirty tracking (using the kvm slot) will be used to detect which blocks actually changed and have to be flushed to disk. Will this raw file already have the "disk information header" (no idea how that stuff is called) encoded? Are there any plans/possible ways to a) automatically create the headers? (if that's even possible) b) support anything but raw files? Please note that under x86, a KVM memory slot still has a (in my opinion) fairly big overhead depending on the size of the slot (rmap, page_track). We might have to optimize that.
Hi David, > > This patch adds virtio-pmem Qemu device. > > > > This device configures memory address range information with file > > backend type. It acts like persistent memory device for KVM guest. > > It presents the memory address range to virtio-pmem driver over > > virtio channel and does the block flush whenever there is request > > from guest to flush/sync. (Qemu part for backing file flush > > is yet to be implemented). > > > > Current code is a RFC to support guest with persistent memory > > range & DAX. > > > > Signed-off-by: Pankaj Gupta <pagupta@redhat.com> > > --- > > hw/virtio/Makefile.objs | 2 +- > > hw/virtio/virtio-pci.c | 44 +++++++++ > > hw/virtio/virtio-pci.h | 14 +++ > > hw/virtio/virtio-pmem.c | 133 > > ++++++++++++++++++++++++++++ > > include/hw/pci/pci.h | 1 + > > include/hw/virtio/virtio-pmem.h | 43 +++++++++ > > include/standard-headers/linux/virtio_ids.h | 1 + > > 7 files changed, 237 insertions(+), 1 deletion(-) > > create mode 100644 hw/virtio/virtio-pmem.c > > create mode 100644 include/hw/virtio/virtio-pmem.h > > > > diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs > > index 765d363c1f..bb5573d2ef 100644 > > --- a/hw/virtio/Makefile.objs > > +++ b/hw/virtio/Makefile.objs > > @@ -5,7 +5,7 @@ common-obj-y += virtio-bus.o > > common-obj-y += virtio-mmio.o > > > > obj-y += virtio.o virtio-balloon.o > > -obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o > > +obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o virtio-pmem.o > > obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock.o > > obj-y += virtio-crypto.o > > obj-$(CONFIG_VIRTIO_PCI) += virtio-crypto-pci.o > > diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c > > index c20537f31d..114ca05497 100644 > > --- a/hw/virtio/virtio-pci.c > > +++ b/hw/virtio/virtio-pci.c > > @@ -2491,6 +2491,49 @@ static const TypeInfo virtio_rng_pci_info = { > > .class_init = virtio_rng_pci_class_init, > > }; > > > > +/* virtio-pmem-pci */ > > + > > +static void virtio_pmem_pci_realize(VirtIOPCIProxy *vpci_dev, Error > > **errp) > > +{ > > + VirtIOPMEMPCI *vpmem = VIRTIO_PMEM_PCI(vpci_dev); > > + DeviceState *vdev = DEVICE(&vpmem->vdev); > > + > > + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); > > + object_property_set_bool(OBJECT(vdev), true, "realized", errp); > > +} > > + > > +static void virtio_pmem_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 = virtio_pmem_pci_realize; > > + set_bit(DEVICE_CATEGORY_MISC, dc->categories); > > + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; > > + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_PMEM; > > + pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; > > + pcidev_k->class_id = PCI_CLASS_OTHERS; > > +} > > + > > +static void virtio_pmem_pci_instance_init(Object *obj) > > +{ > > + VirtIOPMEMPCI *dev = VIRTIO_PMEM_PCI(obj); > > + > > + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), > > + TYPE_VIRTIO_PMEM); > > + object_property_add_alias(obj, "memdev", OBJECT(&dev->vdev), "memdev", > > + &error_abort); > > +} > > + > > +static const TypeInfo virtio_pmem_pci_info = { > > + .name = TYPE_VIRTIO_PMEM_PCI, > > + .parent = TYPE_VIRTIO_PCI, > > + .instance_size = sizeof(VirtIOPMEMPCI), > > + .instance_init = virtio_pmem_pci_instance_init, > > + .class_init = virtio_pmem_pci_class_init, > > +}; > > + > > + > > /* virtio-input-pci */ > > > > static Property virtio_input_pci_properties[] = { > > @@ -2683,6 +2726,7 @@ static void virtio_pci_register_types(void) > > type_register_static(&virtio_balloon_pci_info); > > type_register_static(&virtio_serial_pci_info); > > type_register_static(&virtio_net_pci_info); > > + type_register_static(&virtio_pmem_pci_info); > > #ifdef CONFIG_VHOST_SCSI > > type_register_static(&vhost_scsi_pci_info); > > #endif > > diff --git a/hw/virtio/virtio-pci.h b/hw/virtio/virtio-pci.h > > index 813082b0d7..fe74fcad3f 100644 > > --- a/hw/virtio/virtio-pci.h > > +++ b/hw/virtio/virtio-pci.h > > @@ -19,6 +19,7 @@ > > #include "hw/virtio/virtio-blk.h" > > #include "hw/virtio/virtio-net.h" > > #include "hw/virtio/virtio-rng.h" > > +#include "hw/virtio/virtio-pmem.h" > > #include "hw/virtio/virtio-serial.h" > > #include "hw/virtio/virtio-scsi.h" > > #include "hw/virtio/virtio-balloon.h" > > @@ -57,6 +58,7 @@ typedef struct VirtIOInputHostPCI VirtIOInputHostPCI; > > typedef struct VirtIOGPUPCI VirtIOGPUPCI; > > typedef struct VHostVSockPCI VHostVSockPCI; > > typedef struct VirtIOCryptoPCI VirtIOCryptoPCI; > > +typedef struct VirtIOPMEMPCI VirtIOPMEMPCI; > > > > /* virtio-pci-bus */ > > > > @@ -274,6 +276,18 @@ struct VirtIOBlkPCI { > > VirtIOBlock vdev; > > }; > > > > +/* > > + * virtio-pmem-pci: This extends VirtioPCIProxy. > > + */ > > +#define TYPE_VIRTIO_PMEM_PCI "virtio-pmem-pci" > > +#define VIRTIO_PMEM_PCI(obj) \ > > + OBJECT_CHECK(VirtIOPMEMPCI, (obj), TYPE_VIRTIO_PMEM_PCI) > > + > > +struct VirtIOPMEMPCI { > > + VirtIOPCIProxy parent_obj; > > + VirtIOPMEM vdev; > > +}; > > + > > /* > > * virtio-balloon-pci: This extends VirtioPCIProxy. > > */ > > diff --git a/hw/virtio/virtio-pmem.c b/hw/virtio/virtio-pmem.c > > new file mode 100644 > > index 0000000000..28d06fc501 > > --- /dev/null > > +++ b/hw/virtio/virtio-pmem.c > > @@ -0,0 +1,133 @@ > > +/* > > + * Virtio pmem device > > + * > > + */ > > + > > + > > +#include "qemu/osdep.h" > > +#include "qapi/error.h" > > +#include "qemu-common.h" > > +#include "qemu/error-report.h" > > +#include "hw/virtio/virtio-pmem.h" > > + > > + > > +static void virtio_pmem_system_reset(void *opaque) > > +{ > > + > > +} > > + > > +static void virtio_pmem_flush(VirtIODevice *vdev, VirtQueue *vq) > > +{ > > + VirtQueueElement *elem; > > + > > + elem = virtqueue_pop(vq, sizeof(VirtQueueElement)); > > + if (!elem) { > > + return; > > + } > > + /* todo flush raw file */ > > + > > + virtio_notify(vdev, vq); > > + g_free(elem); > > + > > +} > > + > > +static void virtio_pmem_get_config(VirtIODevice *vdev, uint8_t *config) > > +{ > > + VirtIOPMEM *pmem = VIRTIO_PMEM(vdev); > > + struct virtio_pmem_config *pmemcfg = (struct virtio_pmem_config *) > > config; > > + > > + pmemcfg->start = pmem->start; > > + pmemcfg->size = pmem->size; > > + pmemcfg->align = pmem->align; > > +} > > + > > +static uint64_t virtio_pmem_get_features(VirtIODevice *vdev, uint64_t > > features, > > + Error **errp) > > +{ > > + virtio_add_feature(&features, VIRTIO_PMEM_PLUG); > > + return features; > > +} > > + > > + > > +static void virtio_pmem_realize(DeviceState *dev, Error **errp) > > +{ > > + VirtIODevice *vdev = VIRTIO_DEVICE(dev); > > + VirtIOPMEM *pmem = VIRTIO_PMEM(dev); > > + MachineState *ms = MACHINE(qdev_get_machine()); > > + MemoryRegion *mr; > > + PCMachineState *pcms = PC_MACHINE(object_dynamic_cast(OBJECT(ms), > > TYPE_PC_MACHINE)); > > + uint64_t addr; > > + > > + if (!pmem->memdev) { > > + error_setg(errp, "virtio-pmem not set"); > > + return; > > + } > > + > > + mr = host_memory_backend_get_memory(pmem->memdev, errp); > > + addr = pcms->hotplug_memory.base; > > + pmem->start = addr; > > + pmem->size = memory_region_size(mr); > > + pmem->align = memory_region_get_alignment(mr); > > + > > + memory_region_init_alias(&pmem->mr, OBJECT(ms), > > + "virtio_pmem-memory", mr, 0, pmem->size); > > + > > + host_memory_backend_set_mapped(pmem->memdev, true); > > + virtio_init(vdev, TYPE_VIRTIO_PMEM, VIRTIO_ID_PMEM, > > + sizeof(struct virtio_pmem_config)); > > + > > + pmem->rq_vq = virtio_add_queue(vdev, 128, virtio_pmem_flush); > > + qemu_register_reset(virtio_pmem_system_reset, pmem); > > > So right now you're just using some memdev for testing. yes. > > I assume that the memory region we will provide to the guest will be a > simple memory mapped raw file. Dirty tracking (using the kvm slot) will > be used to detect which blocks actually changed and have to be flushed > to disk. Not really, we will perform fsync on raw file. As this file is created on regular storage and not nvdimm, so host page cache radix tree would have the dirty pages information which will be used for fsync. > > Will this raw file already have the "disk information header" (no idea > how that stuff is called) encoded? Are there any plans/possible ways to > > a) automatically create the headers? (if that's even possible) Its raw. Right now we are just supporting raw format. As this is direct mapping of memory into guest address space, I don't think we can have an abstraction of headers for block specific features. Or may be we can get opinion of others(Qemu block people) it is at all possible? > b) support anything but raw files? > > Please note that under x86, a KVM memory slot still has a (in my > opinion) fairly big overhead depending on the size of the slot (rmap, > page_track). We might have to optimize that. I have not tried/observed this. Right now I just used single memory slot and cold add few MB's of memory in Qemu. Can you please provide more details on this? > > -- > > Thanks, > > David / dhildenb > >
>> >> So right now you're just using some memdev for testing. > > yes. > >> >> I assume that the memory region we will provide to the guest will be a >> simple memory mapped raw file. Dirty tracking (using the kvm slot) will >> be used to detect which blocks actually changed and have to be flushed >> to disk. > > Not really, we will perform fsync on raw file. As this file is created > on regular storage and not nvdimm, so host page cache radix tree would have > the dirty pages information which will be used for fsync. Ah right. That makes things a lot easier! > >> >> Will this raw file already have the "disk information header" (no idea >> how that stuff is called) encoded? Are there any plans/possible ways to >> >> a) automatically create the headers? (if that's even possible) > > Its raw. Right now we are just supporting raw format. > > As this is direct mapping of memory into guest address space, I don't > think we can have an abstraction of headers for block specific features. > Or may be we can get opinion of others(Qemu block people) it is at all possible? > >> b) support anything but raw files? >> >> Please note that under x86, a KVM memory slot still has a (in my >> opinion) fairly big overhead depending on the size of the slot (rmap, >> page_track). We might have to optimize that. > > I have not tried/observed this. Right now I just used single memory slot and cold add > few MB's of memory in Qemu. Can you please provide more details on this? > You can have a look at kvm_arch_create_memslot() in arch/x86/kvm/x86.c. "npages" is used to allocate certain arrays (rmap for shadow page tables). Also kvm_page_track_create_memslot() allocates data for page_track. Having a big disk involves a lot of memory overhead due to the big kvm memory slot. This is already the case for NVDIMMs as of now. Other architectures (e.g. s390x) don't have this "problem". They don't allocate any such data depending on the size of a memory slot. This is certainly something to work on in the future.
On Thu, Apr 05, 2018 at 08:09:26AM -0400, Pankaj Gupta wrote: > > Will this raw file already have the "disk information header" (no idea > > how that stuff is called) encoded? Are there any plans/possible ways to > > > > a) automatically create the headers? (if that's even possible) > > Its raw. Right now we are just supporting raw format. > > As this is direct mapping of memory into guest address space, I don't > think we can have an abstraction of headers for block specific features. > Or may be we can get opinion of others(Qemu block people) it is at all possible? memdev and the block layer are completely separate. The block layer isn't designed for memory-mapped access. I think it makes sense to use memdev here. If the user wants a block device, they should use an emulated block device, not virtio-pmem, because buffering is necessary anyway when an image file format is used. Stefan
On 09.04.2018 05:26, Stefan Hajnoczi wrote: > On Thu, Apr 05, 2018 at 08:09:26AM -0400, Pankaj Gupta wrote: >>> Will this raw file already have the "disk information header" (no idea >>> how that stuff is called) encoded? Are there any plans/possible ways to >>> >>> a) automatically create the headers? (if that's even possible) >> >> Its raw. Right now we are just supporting raw format. >> >> As this is direct mapping of memory into guest address space, I don't >> think we can have an abstraction of headers for block specific features. >> Or may be we can get opinion of others(Qemu block people) it is at all possible? > > memdev and the block layer are completely separate. The block layer > isn't designed for memory-mapped access. > Not questioning if this is the right thing to do now. I was wondering if we could expose any block device in the future as virtio-pmem. And I think with quite some work it could be possible. As you said, we will need some buffering. Maybe userfaultfd and friends (WP) could allow to implement that. > I think it makes sense to use memdev here. If the user wants a block > device, they should use an emulated block device, not virtio-pmem, > because buffering is necessary anyway when an image file format is used. > > Stefan >
diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs index 765d363c1f..bb5573d2ef 100644 --- a/hw/virtio/Makefile.objs +++ b/hw/virtio/Makefile.objs @@ -5,7 +5,7 @@ common-obj-y += virtio-bus.o common-obj-y += virtio-mmio.o obj-y += virtio.o virtio-balloon.o -obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o +obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o virtio-pmem.o obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock.o obj-y += virtio-crypto.o obj-$(CONFIG_VIRTIO_PCI) += virtio-crypto-pci.o diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index c20537f31d..114ca05497 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -2491,6 +2491,49 @@ static const TypeInfo virtio_rng_pci_info = { .class_init = virtio_rng_pci_class_init, }; +/* virtio-pmem-pci */ + +static void virtio_pmem_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VirtIOPMEMPCI *vpmem = VIRTIO_PMEM_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&vpmem->vdev); + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static void virtio_pmem_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 = virtio_pmem_pci_realize; + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_PMEM; + pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; + pcidev_k->class_id = PCI_CLASS_OTHERS; +} + +static void virtio_pmem_pci_instance_init(Object *obj) +{ + VirtIOPMEMPCI *dev = VIRTIO_PMEM_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_PMEM); + object_property_add_alias(obj, "memdev", OBJECT(&dev->vdev), "memdev", + &error_abort); +} + +static const TypeInfo virtio_pmem_pci_info = { + .name = TYPE_VIRTIO_PMEM_PCI, + .parent = TYPE_VIRTIO_PCI, + .instance_size = sizeof(VirtIOPMEMPCI), + .instance_init = virtio_pmem_pci_instance_init, + .class_init = virtio_pmem_pci_class_init, +}; + + /* virtio-input-pci */ static Property virtio_input_pci_properties[] = { @@ -2683,6 +2726,7 @@ static void virtio_pci_register_types(void) type_register_static(&virtio_balloon_pci_info); type_register_static(&virtio_serial_pci_info); type_register_static(&virtio_net_pci_info); + type_register_static(&virtio_pmem_pci_info); #ifdef CONFIG_VHOST_SCSI type_register_static(&vhost_scsi_pci_info); #endif diff --git a/hw/virtio/virtio-pci.h b/hw/virtio/virtio-pci.h index 813082b0d7..fe74fcad3f 100644 --- a/hw/virtio/virtio-pci.h +++ b/hw/virtio/virtio-pci.h @@ -19,6 +19,7 @@ #include "hw/virtio/virtio-blk.h" #include "hw/virtio/virtio-net.h" #include "hw/virtio/virtio-rng.h" +#include "hw/virtio/virtio-pmem.h" #include "hw/virtio/virtio-serial.h" #include "hw/virtio/virtio-scsi.h" #include "hw/virtio/virtio-balloon.h" @@ -57,6 +58,7 @@ typedef struct VirtIOInputHostPCI VirtIOInputHostPCI; typedef struct VirtIOGPUPCI VirtIOGPUPCI; typedef struct VHostVSockPCI VHostVSockPCI; typedef struct VirtIOCryptoPCI VirtIOCryptoPCI; +typedef struct VirtIOPMEMPCI VirtIOPMEMPCI; /* virtio-pci-bus */ @@ -274,6 +276,18 @@ struct VirtIOBlkPCI { VirtIOBlock vdev; }; +/* + * virtio-pmem-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VIRTIO_PMEM_PCI "virtio-pmem-pci" +#define VIRTIO_PMEM_PCI(obj) \ + OBJECT_CHECK(VirtIOPMEMPCI, (obj), TYPE_VIRTIO_PMEM_PCI) + +struct VirtIOPMEMPCI { + VirtIOPCIProxy parent_obj; + VirtIOPMEM vdev; +}; + /* * virtio-balloon-pci: This extends VirtioPCIProxy. */ diff --git a/hw/virtio/virtio-pmem.c b/hw/virtio/virtio-pmem.c new file mode 100644 index 0000000000..28d06fc501 --- /dev/null +++ b/hw/virtio/virtio-pmem.c @@ -0,0 +1,133 @@ +/* + * Virtio pmem device + * + */ + + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu-common.h" +#include "qemu/error-report.h" +#include "hw/virtio/virtio-pmem.h" + + +static void virtio_pmem_system_reset(void *opaque) +{ + +} + +static void virtio_pmem_flush(VirtIODevice *vdev, VirtQueue *vq) +{ + VirtQueueElement *elem; + + elem = virtqueue_pop(vq, sizeof(VirtQueueElement)); + if (!elem) { + return; + } + /* todo flush raw file */ + + virtio_notify(vdev, vq); + g_free(elem); + +} + +static void virtio_pmem_get_config(VirtIODevice *vdev, uint8_t *config) +{ + VirtIOPMEM *pmem = VIRTIO_PMEM(vdev); + struct virtio_pmem_config *pmemcfg = (struct virtio_pmem_config *) config; + + pmemcfg->start = pmem->start; + pmemcfg->size = pmem->size; + pmemcfg->align = pmem->align; +} + +static uint64_t virtio_pmem_get_features(VirtIODevice *vdev, uint64_t features, + Error **errp) +{ + virtio_add_feature(&features, VIRTIO_PMEM_PLUG); + return features; +} + + +static void virtio_pmem_realize(DeviceState *dev, Error **errp) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VirtIOPMEM *pmem = VIRTIO_PMEM(dev); + MachineState *ms = MACHINE(qdev_get_machine()); + MemoryRegion *mr; + PCMachineState *pcms = PC_MACHINE(object_dynamic_cast(OBJECT(ms), TYPE_PC_MACHINE)); + uint64_t addr; + + if (!pmem->memdev) { + error_setg(errp, "virtio-pmem not set"); + return; + } + + mr = host_memory_backend_get_memory(pmem->memdev, errp); + addr = pcms->hotplug_memory.base; + pmem->start = addr; + pmem->size = memory_region_size(mr); + pmem->align = memory_region_get_alignment(mr); + + memory_region_init_alias(&pmem->mr, OBJECT(ms), + "virtio_pmem-memory", mr, 0, pmem->size); + + host_memory_backend_set_mapped(pmem->memdev, true); + virtio_init(vdev, TYPE_VIRTIO_PMEM, VIRTIO_ID_PMEM, + sizeof(struct virtio_pmem_config)); + + pmem->rq_vq = virtio_add_queue(vdev, 128, virtio_pmem_flush); + qemu_register_reset(virtio_pmem_system_reset, pmem); +} + +static void virtio_mem_check_memdev(Object *obj, const char *name, Object *val, + Error **errp) +{ + if (host_memory_backend_is_mapped(MEMORY_BACKEND(val))) { + + char *path = object_get_canonical_path_component(val); + error_setg(errp, "Can't use already busy memdev: %s", path); + g_free(path); + return; + } + + qdev_prop_allow_set_link_before_realize(obj, name, val, errp); +} + +static void virtio_pmem_instance_init(Object *obj) +{ + + VirtIOPMEM *vm = VIRTIO_PMEM(obj); + + object_property_add_link(obj, "memdev", TYPE_MEMORY_BACKEND, + (Object **)&vm->memdev, + (void *) virtio_mem_check_memdev, + OBJ_PROP_LINK_UNREF_ON_RELEASE, + &error_abort); +} + + +static void virtio_pmem_class_init(ObjectClass *klass, void *data) +{ + VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); + + vdc->realize = virtio_pmem_realize; + vdc->get_config = virtio_pmem_get_config; + vdc->get_features = virtio_pmem_get_features; +} + +static TypeInfo virtio_pmem_info = { + .name = TYPE_VIRTIO_PMEM, + .parent = TYPE_VIRTIO_DEVICE, + .class_size = sizeof(VirtIOPMEM), + .class_init = virtio_pmem_class_init, + .instance_init = virtio_pmem_instance_init, +}; + + +static void virtio_register_types(void) +{ + type_register_static(&virtio_pmem_info); +} + +type_init(virtio_register_types) diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h index 15ced9648c..0f9091e6cc 100644 --- a/include/hw/pci/pci.h +++ b/include/hw/pci/pci.h @@ -85,6 +85,7 @@ extern bool pci_available; #define PCI_DEVICE_ID_VIRTIO_RNG 0x1005 #define PCI_DEVICE_ID_VIRTIO_9P 0x1009 #define PCI_DEVICE_ID_VIRTIO_VSOCK 0x1012 +#define PCI_DEVICE_ID_VIRTIO_PMEM 0x1013 #define PCI_VENDOR_ID_REDHAT 0x1b36 #define PCI_DEVICE_ID_REDHAT_BRIDGE 0x0001 diff --git a/include/hw/virtio/virtio-pmem.h b/include/hw/virtio/virtio-pmem.h new file mode 100644 index 0000000000..f4be2f54f3 --- /dev/null +++ b/include/hw/virtio/virtio-pmem.h @@ -0,0 +1,43 @@ +/* + * Virtio pmem Device + * + * + */ + +#ifndef QEMU_VIRTIO_PMEM_H +#define QEMU_VIRTIO_PMEM_H + +#include "hw/virtio/virtio.h" +#include "exec/memory.h" +#include "sysemu/hostmem.h" +#include "standard-headers/linux/virtio_ids.h" +#include "hw/boards.h" +#include "hw/i386/pc.h" + +#define VIRTIO_PMEM_PLUG 0 + +#define TYPE_VIRTIO_PMEM "virtio-pmem" + +#define VIRTIO_PMEM(obj) \ + OBJECT_CHECK(VirtIOPMEM, (obj), TYPE_VIRTIO_PMEM) + +typedef struct VirtIOPMEM { + + VirtIODevice parent_obj; + VirtQueue *rq_vq; + uint64_t start; + uint64_t size; + uint64_t align; + + MemoryRegion mr; + HostMemoryBackend *memdev; +} VirtIOPMEM; + +struct virtio_pmem_config { + + uint64_t start; + uint64_t size; + uint64_t align; +}; + +#endif diff --git a/include/standard-headers/linux/virtio_ids.h b/include/standard-headers/linux/virtio_ids.h index 6d5c3b2d4f..5ebd04980d 100644 --- a/include/standard-headers/linux/virtio_ids.h +++ b/include/standard-headers/linux/virtio_ids.h @@ -43,5 +43,6 @@ #define VIRTIO_ID_INPUT 18 /* virtio input */ #define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */ #define VIRTIO_ID_CRYPTO 20 /* virtio crypto */ +#define VIRTIO_ID_PMEM 21 /* virtio pmem */ #endif /* _LINUX_VIRTIO_IDS_H */
This patch adds virtio-pmem Qemu device. This device configures memory address range information with file backend type. It acts like persistent memory device for KVM guest. It presents the memory address range to virtio-pmem driver over virtio channel and does the block flush whenever there is request from guest to flush/sync. (Qemu part for backing file flush is yet to be implemented). Current code is a RFC to support guest with persistent memory range & DAX. Signed-off-by: Pankaj Gupta <pagupta@redhat.com> --- hw/virtio/Makefile.objs | 2 +- hw/virtio/virtio-pci.c | 44 +++++++++ hw/virtio/virtio-pci.h | 14 +++ hw/virtio/virtio-pmem.c | 133 ++++++++++++++++++++++++++++ include/hw/pci/pci.h | 1 + include/hw/virtio/virtio-pmem.h | 43 +++++++++ include/standard-headers/linux/virtio_ids.h | 1 + 7 files changed, 237 insertions(+), 1 deletion(-) create mode 100644 hw/virtio/virtio-pmem.c create mode 100644 include/hw/virtio/virtio-pmem.h