diff options
author | Peter Maydell <peter.maydell@linaro.org> | 2014-12-23 14:01:13 +0000 |
---|---|---|
committer | Peter Maydell <peter.maydell@linaro.org> | 2014-12-23 14:01:14 +0000 |
commit | 03de06dde54df1f64bb099efe22edfa773b16e8e (patch) | |
tree | a5342cf9e45ca21e6ee73a60f6117bd94795344e /hw | |
parent | 7e58e2ac7778cca3234c33387e49577bb7732714 (diff) | |
parent | dcbfc5cefb22e9219f8253dba87de33104ca73fe (diff) | |
download | hqemu-03de06dde54df1f64bb099efe22edfa773b16e8e.zip hqemu-03de06dde54df1f64bb099efe22edfa773b16e8e.tar.gz |
Merge remote-tracking branch 'remotes/awilliam/tags/vfio-update-20141222.0' into staging
VFIO updates:
- Conversion to tracepoints (Eric Auger)
- Fix memory listener address space (Frank Blaschka)
- Move to hw/vfio/ and split common vs pci (Eric Auger & Kim Phillips)
- Trivial error_report() fixes (Alex Williamson)
In addition to enabling S390 with the address space fix and updating
to use tracepoints rather than compile time debug, this set of patches
moves hw/misc/vfio.c to hw/vfio/ and paves the way for vfio-platform
support by splitting common functionality from PCI specific code.
# gpg: Signature made Mon 22 Dec 2014 20:19:43 GMT using RSA key ID 3BB08B22
# gpg: Good signature from "Alex Williamson <alex.williamson@redhat.com>"
# gpg: aka "Alex Williamson <alex@shazbot.org>"
# gpg: aka "Alex Williamson <alwillia@redhat.com>"
# gpg: aka "Alex Williamson <alex.l.williamson@gmail.com>"
* remotes/awilliam/tags/vfio-update-20141222.0:
vfio: Cleanup error_report()s
hw/vfio: create common module
hw/vfio/pci: use name field in format strings
hw/vfio/pci: rename group_list into vfio_group_list
hw/vfio/pci: split vfio_get_device
hw/vfio/pci: Introduce VFIORegion
hw/vfio/pci: handle reset at VFIODevice
hw/vfio/pci: add type, name and group fields in VFIODevice
hw/vfio/pci: introduce minimalist VFIODevice with fd
hw/vfio/pci: generalize mask/unmask to any IRQ index
hw/vfio/pci: Rename VFIODevice into VFIOPCIDevice
vfio: move hw/misc/vfio.c to hw/vfio/pci.c Move vfio.h into include/hw/vfio
vfio: fix adding memory listener to the right address space
vfio: migration to trace points
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Diffstat (limited to 'hw')
-rw-r--r-- | hw/Makefile.objs | 1 | ||||
-rw-r--r-- | hw/misc/Makefile.objs | 1 | ||||
-rw-r--r-- | hw/ppc/spapr_pci_vfio.c | 2 | ||||
-rw-r--r-- | hw/vfio/Makefile.objs | 4 | ||||
-rw-r--r-- | hw/vfio/common.c | 959 | ||||
-rw-r--r-- | hw/vfio/pci.c (renamed from hw/misc/vfio.c) | 1723 |
6 files changed, 1313 insertions, 1377 deletions
diff --git a/hw/Makefile.objs b/hw/Makefile.objs index 52a1464..73afa41 100644 --- a/hw/Makefile.objs +++ b/hw/Makefile.objs @@ -26,6 +26,7 @@ devices-dirs-$(CONFIG_SOFTMMU) += ssi/ devices-dirs-$(CONFIG_SOFTMMU) += timer/ devices-dirs-$(CONFIG_TPM) += tpm/ devices-dirs-$(CONFIG_SOFTMMU) += usb/ +devices-dirs-$(CONFIG_SOFTMMU) += vfio/ devices-dirs-$(CONFIG_VIRTIO) += virtio/ devices-dirs-$(CONFIG_SOFTMMU) += watchdog/ devices-dirs-$(CONFIG_SOFTMMU) += xen/ diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs index 979e532..e47fea8 100644 --- a/hw/misc/Makefile.objs +++ b/hw/misc/Makefile.objs @@ -21,7 +21,6 @@ common-obj-$(CONFIG_MACIO) += macio/ ifeq ($(CONFIG_PCI), y) obj-$(CONFIG_KVM) += ivshmem.o -obj-$(CONFIG_LINUX) += vfio.o endif obj-$(CONFIG_REALVIEW) += arm_sysctl.o diff --git a/hw/ppc/spapr_pci_vfio.c b/hw/ppc/spapr_pci_vfio.c index d3bddf2..144912b 100644 --- a/hw/ppc/spapr_pci_vfio.c +++ b/hw/ppc/spapr_pci_vfio.c @@ -20,7 +20,7 @@ #include "hw/ppc/spapr.h" #include "hw/pci-host/spapr.h" #include "linux/vfio.h" -#include "hw/misc/vfio.h" +#include "hw/vfio/vfio.h" static Property spapr_phb_vfio_properties[] = { DEFINE_PROP_INT32("iommu", sPAPRPHBVFIOState, iommugroupid, -1), diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs new file mode 100644 index 0000000..e31f30e --- /dev/null +++ b/hw/vfio/Makefile.objs @@ -0,0 +1,4 @@ +ifeq ($(CONFIG_LINUX), y) +obj-$(CONFIG_SOFTMMU) += common.o +obj-$(CONFIG_PCI) += pci.o +endif diff --git a/hw/vfio/common.c b/hw/vfio/common.c new file mode 100644 index 0000000..cf483ff --- /dev/null +++ b/hw/vfio/common.c @@ -0,0 +1,959 @@ +/* + * generic functions used by VFIO devices + * + * Copyright Red Hat, Inc. 2012 + * + * Authors: + * Alex Williamson <alex.williamson@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Based on qemu-kvm device-assignment: + * Adapted for KVM by Qumranet. + * Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com) + * Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com) + * Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com) + * Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com) + * Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com) + */ + +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <linux/vfio.h> + +#include "hw/vfio/vfio-common.h" +#include "hw/vfio/vfio.h" +#include "exec/address-spaces.h" +#include "exec/memory.h" +#include "hw/hw.h" +#include "qemu/error-report.h" +#include "sysemu/kvm.h" +#include "trace.h" + +struct vfio_group_head vfio_group_list = + QLIST_HEAD_INITIALIZER(vfio_address_spaces); +struct vfio_as_head vfio_address_spaces = + QLIST_HEAD_INITIALIZER(vfio_address_spaces); + +#ifdef CONFIG_KVM +/* + * We have a single VFIO pseudo device per KVM VM. Once created it lives + * for the life of the VM. Closing the file descriptor only drops our + * reference to it and the device's reference to kvm. Therefore once + * initialized, this file descriptor is only released on QEMU exit and + * we'll re-use it should another vfio device be attached before then. + */ +static int vfio_kvm_device_fd = -1; +#endif + +/* + * Common VFIO interrupt disable + */ +void vfio_disable_irqindex(VFIODevice *vbasedev, int index) +{ + struct vfio_irq_set irq_set = { + .argsz = sizeof(irq_set), + .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER, + .index = index, + .start = 0, + .count = 0, + }; + + ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); +} + +void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index) +{ + struct vfio_irq_set irq_set = { + .argsz = sizeof(irq_set), + .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK, + .index = index, + .start = 0, + .count = 1, + }; + + ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); +} + +void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index) +{ + struct vfio_irq_set irq_set = { + .argsz = sizeof(irq_set), + .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK, + .index = index, + .start = 0, + .count = 1, + }; + + ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); +} + +/* + * IO Port/MMIO - Beware of the endians, VFIO is always little endian + */ +void vfio_region_write(void *opaque, hwaddr addr, + uint64_t data, unsigned size) +{ + VFIORegion *region = opaque; + VFIODevice *vbasedev = region->vbasedev; + union { + uint8_t byte; + uint16_t word; + uint32_t dword; + uint64_t qword; + } buf; + + switch (size) { + case 1: + buf.byte = data; + break; + case 2: + buf.word = cpu_to_le16(data); + break; + case 4: + buf.dword = cpu_to_le32(data); + break; + default: + hw_error("vfio: unsupported write size, %d bytes", size); + break; + } + + if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) { + error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64 + ",%d) failed: %m", + __func__, vbasedev->name, region->nr, + addr, data, size); + } + + trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size); + + /* + * A read or write to a BAR always signals an INTx EOI. This will + * do nothing if not pending (including not in INTx mode). We assume + * that a BAR access is in response to an interrupt and that BAR + * accesses will service the interrupt. Unfortunately, we don't know + * which access will service the interrupt, so we're potentially + * getting quite a few host interrupts per guest interrupt. + */ + vbasedev->ops->vfio_eoi(vbasedev); +} + +uint64_t vfio_region_read(void *opaque, + hwaddr addr, unsigned size) +{ + VFIORegion *region = opaque; + VFIODevice *vbasedev = region->vbasedev; + union { + uint8_t byte; + uint16_t word; + uint32_t dword; + uint64_t qword; + } buf; + uint64_t data = 0; + + if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) { + error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m", + __func__, vbasedev->name, region->nr, + addr, size); + return (uint64_t)-1; + } + switch (size) { + case 1: + data = buf.byte; + break; + case 2: + data = le16_to_cpu(buf.word); + break; + case 4: + data = le32_to_cpu(buf.dword); + break; + default: + hw_error("vfio: unsupported read size, %d bytes", size); + break; + } + + trace_vfio_region_read(vbasedev->name, region->nr, addr, size, data); + + /* Same as write above */ + vbasedev->ops->vfio_eoi(vbasedev); + + return data; +} + +const MemoryRegionOps vfio_region_ops = { + .read = vfio_region_read, + .write = vfio_region_write, + .endianness = DEVICE_LITTLE_ENDIAN, +}; + +/* + * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86 + */ +static int vfio_dma_unmap(VFIOContainer *container, + hwaddr iova, ram_addr_t size) +{ + struct vfio_iommu_type1_dma_unmap unmap = { + .argsz = sizeof(unmap), + .flags = 0, + .iova = iova, + .size = size, + }; + + if (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) { + error_report("VFIO_UNMAP_DMA: %d\n", -errno); + return -errno; + } + + return 0; +} + +static int vfio_dma_map(VFIOContainer *container, hwaddr iova, + ram_addr_t size, void *vaddr, bool readonly) +{ + struct vfio_iommu_type1_dma_map map = { + .argsz = sizeof(map), + .flags = VFIO_DMA_MAP_FLAG_READ, + .vaddr = (__u64)(uintptr_t)vaddr, + .iova = iova, + .size = size, + }; + + if (!readonly) { + map.flags |= VFIO_DMA_MAP_FLAG_WRITE; + } + + /* + * Try the mapping, if it fails with EBUSY, unmap the region and try + * again. This shouldn't be necessary, but we sometimes see it in + * the the VGA ROM space. + */ + if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 || + (errno == EBUSY && vfio_dma_unmap(container, iova, size) == 0 && + ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) { + return 0; + } + + error_report("VFIO_MAP_DMA: %d\n", -errno); + return -errno; +} + +static bool vfio_listener_skipped_section(MemoryRegionSection *section) +{ + return (!memory_region_is_ram(section->mr) && + !memory_region_is_iommu(section->mr)) || + /* + * Sizing an enabled 64-bit BAR can cause spurious mappings to + * addresses in the upper part of the 64-bit address space. These + * are never accessed by the CPU and beyond the address width of + * some IOMMU hardware. TODO: VFIO should tell us the IOMMU width. + */ + section->offset_within_address_space & (1ULL << 63); +} + +static void vfio_iommu_map_notify(Notifier *n, void *data) +{ + VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n); + VFIOContainer *container = giommu->container; + IOMMUTLBEntry *iotlb = data; + MemoryRegion *mr; + hwaddr xlat; + hwaddr len = iotlb->addr_mask + 1; + void *vaddr; + int ret; + + trace_vfio_iommu_map_notify(iotlb->iova, + iotlb->iova + iotlb->addr_mask); + + /* + * The IOMMU TLB entry we have just covers translation through + * this IOMMU to its immediate target. We need to translate + * it the rest of the way through to memory. + */ + mr = address_space_translate(&address_space_memory, + iotlb->translated_addr, + &xlat, &len, iotlb->perm & IOMMU_WO); + if (!memory_region_is_ram(mr)) { + error_report("iommu map to non memory area %"HWADDR_PRIx"\n", + xlat); + return; + } + /* + * Translation truncates length to the IOMMU page size, + * check that it did not truncate too much. + */ + if (len & iotlb->addr_mask) { + error_report("iommu has granularity incompatible with target AS\n"); + return; + } + + if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) { + vaddr = memory_region_get_ram_ptr(mr) + xlat; + ret = vfio_dma_map(container, iotlb->iova, + iotlb->addr_mask + 1, vaddr, + !(iotlb->perm & IOMMU_WO) || mr->readonly); + if (ret) { + error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", " + "0x%"HWADDR_PRIx", %p) = %d (%m)", + container, iotlb->iova, + iotlb->addr_mask + 1, vaddr, ret); + } + } else { + ret = vfio_dma_unmap(container, iotlb->iova, iotlb->addr_mask + 1); + if (ret) { + error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", " + "0x%"HWADDR_PRIx") = %d (%m)", + container, iotlb->iova, + iotlb->addr_mask + 1, ret); + } + } +} + +static void vfio_listener_region_add(MemoryListener *listener, + MemoryRegionSection *section) +{ + VFIOContainer *container = container_of(listener, VFIOContainer, + iommu_data.type1.listener); + hwaddr iova, end; + Int128 llend; + void *vaddr; + int ret; + + if (vfio_listener_skipped_section(section)) { + trace_vfio_listener_region_add_skip( + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(int128_sub(section->size, int128_one()))); + return; + } + + if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) != + (section->offset_within_region & ~TARGET_PAGE_MASK))) { + error_report("%s received unaligned region", __func__); + return; + } + + iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); + llend = int128_make64(section->offset_within_address_space); + llend = int128_add(llend, section->size); + llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK)); + + if (int128_ge(int128_make64(iova), llend)) { + return; + } + + memory_region_ref(section->mr); + + if (memory_region_is_iommu(section->mr)) { + VFIOGuestIOMMU *giommu; + + trace_vfio_listener_region_add_iommu(iova, + int128_get64(int128_sub(llend, int128_one()))); + /* + * FIXME: We should do some checking to see if the + * capabilities of the host VFIO IOMMU are adequate to model + * the guest IOMMU + * + * FIXME: For VFIO iommu types which have KVM acceleration to + * avoid bouncing all map/unmaps through qemu this way, this + * would be the right place to wire that up (tell the KVM + * device emulation the VFIO iommu handles to use). + */ + /* + * This assumes that the guest IOMMU is empty of + * mappings at this point. + * + * One way of doing this is: + * 1. Avoid sharing IOMMUs between emulated devices or different + * IOMMU groups. + * 2. Implement VFIO_IOMMU_ENABLE in the host kernel to fail if + * there are some mappings in IOMMU. + * + * VFIO on SPAPR does that. Other IOMMU models may do that different, + * they must make sure there are no existing mappings or + * loop through existing mappings to map them into VFIO. + */ + giommu = g_malloc0(sizeof(*giommu)); + giommu->iommu = section->mr; + giommu->container = container; + giommu->n.notify = vfio_iommu_map_notify; + QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next); + memory_region_register_iommu_notifier(giommu->iommu, &giommu->n); + + return; + } + + /* Here we assume that memory_region_is_ram(section->mr)==true */ + + end = int128_get64(llend); + vaddr = memory_region_get_ram_ptr(section->mr) + + section->offset_within_region + + (iova - section->offset_within_address_space); + + trace_vfio_listener_region_add_ram(iova, end - 1, vaddr); + + ret = vfio_dma_map(container, iova, end - iova, vaddr, section->readonly); + if (ret) { + error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", " + "0x%"HWADDR_PRIx", %p) = %d (%m)", + container, iova, end - iova, vaddr, ret); + + /* + * On the initfn path, store the first error in the container so we + * can gracefully fail. Runtime, there's not much we can do other + * than throw a hardware error. + */ + if (!container->iommu_data.type1.initialized) { + if (!container->iommu_data.type1.error) { + container->iommu_data.type1.error = ret; + } + } else { + hw_error("vfio: DMA mapping failed, unable to continue"); + } + } +} + +static void vfio_listener_region_del(MemoryListener *listener, + MemoryRegionSection *section) +{ + VFIOContainer *container = container_of(listener, VFIOContainer, + iommu_data.type1.listener); + hwaddr iova, end; + int ret; + + if (vfio_listener_skipped_section(section)) { + trace_vfio_listener_region_del_skip( + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(int128_sub(section->size, int128_one()))); + return; + } + + if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) != + (section->offset_within_region & ~TARGET_PAGE_MASK))) { + error_report("%s received unaligned region", __func__); + return; + } + + if (memory_region_is_iommu(section->mr)) { + VFIOGuestIOMMU *giommu; + + QLIST_FOREACH(giommu, &container->giommu_list, giommu_next) { + if (giommu->iommu == section->mr) { + memory_region_unregister_iommu_notifier(&giommu->n); + QLIST_REMOVE(giommu, giommu_next); + g_free(giommu); + break; + } + } + + /* + * FIXME: We assume the one big unmap below is adequate to + * remove any individual page mappings in the IOMMU which + * might have been copied into VFIO. This works for a page table + * based IOMMU where a big unmap flattens a large range of IO-PTEs. + * That may not be true for all IOMMU types. + */ + } + + iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); + end = (section->offset_within_address_space + int128_get64(section->size)) & + TARGET_PAGE_MASK; + + if (iova >= end) { + return; + } + + trace_vfio_listener_region_del(iova, end - 1); + + ret = vfio_dma_unmap(container, iova, end - iova); + memory_region_unref(section->mr); + if (ret) { + error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", " + "0x%"HWADDR_PRIx") = %d (%m)", + container, iova, end - iova, ret); + } +} + +const MemoryListener vfio_memory_listener = { + .region_add = vfio_listener_region_add, + .region_del = vfio_listener_region_del, +}; + +void vfio_listener_release(VFIOContainer *container) +{ + memory_listener_unregister(&container->iommu_data.type1.listener); +} + +int vfio_mmap_region(Object *obj, VFIORegion *region, + MemoryRegion *mem, MemoryRegion *submem, + void **map, size_t size, off_t offset, + const char *name) +{ + int ret = 0; + VFIODevice *vbasedev = region->vbasedev; + + if (VFIO_ALLOW_MMAP && size && region->flags & + VFIO_REGION_INFO_FLAG_MMAP) { + int prot = 0; + + if (region->flags & VFIO_REGION_INFO_FLAG_READ) { + prot |= PROT_READ; + } + + if (region->flags & VFIO_REGION_INFO_FLAG_WRITE) { + prot |= PROT_WRITE; + } + + *map = mmap(NULL, size, prot, MAP_SHARED, + vbasedev->fd, + region->fd_offset + offset); + if (*map == MAP_FAILED) { + *map = NULL; + ret = -errno; + goto empty_region; + } + + memory_region_init_ram_ptr(submem, obj, name, size, *map); + memory_region_set_skip_dump(submem); + } else { +empty_region: + /* Create a zero sized sub-region to make cleanup easy. */ + memory_region_init(submem, obj, name, 0); + } + + memory_region_add_subregion(mem, offset, submem); + + return ret; +} + +void vfio_reset_handler(void *opaque) +{ + VFIOGroup *group; + VFIODevice *vbasedev; + + QLIST_FOREACH(group, &vfio_group_list, next) { + QLIST_FOREACH(vbasedev, &group->device_list, next) { + vbasedev->ops->vfio_compute_needs_reset(vbasedev); + } + } + + QLIST_FOREACH(group, &vfio_group_list, next) { + QLIST_FOREACH(vbasedev, &group->device_list, next) { + if (vbasedev->needs_reset) { + vbasedev->ops->vfio_hot_reset_multi(vbasedev); + } + } + } +} + +static void vfio_kvm_device_add_group(VFIOGroup *group) +{ +#ifdef CONFIG_KVM + struct kvm_device_attr attr = { + .group = KVM_DEV_VFIO_GROUP, + .attr = KVM_DEV_VFIO_GROUP_ADD, + .addr = (uint64_t)(unsigned long)&group->fd, + }; + + if (!kvm_enabled()) { + return; + } + + if (vfio_kvm_device_fd < 0) { + struct kvm_create_device cd = { + .type = KVM_DEV_TYPE_VFIO, + }; + + if (kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd)) { + error_report("Failed to create KVM VFIO device: %m\n"); + return; + } + + vfio_kvm_device_fd = cd.fd; + } + + if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { + error_report("Failed to add group %d to KVM VFIO device: %m", + group->groupid); + } +#endif +} + +static void vfio_kvm_device_del_group(VFIOGroup *group) +{ +#ifdef CONFIG_KVM + struct kvm_device_attr attr = { + .group = KVM_DEV_VFIO_GROUP, + .attr = KVM_DEV_VFIO_GROUP_DEL, + .addr = (uint64_t)(unsigned long)&group->fd, + }; + + if (vfio_kvm_device_fd < 0) { + return; + } + + if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { + error_report("Failed to remove group %d from KVM VFIO device: %m", + group->groupid); + } +#endif +} + +static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) +{ + VFIOAddressSpace *space; + + QLIST_FOREACH(space, &vfio_address_spaces, list) { + if (space->as == as) { + return space; + } + } + + /* No suitable VFIOAddressSpace, create a new one */ + space = g_malloc0(sizeof(*space)); + space->as = as; + QLIST_INIT(&space->containers); + + QLIST_INSERT_HEAD(&vfio_address_spaces, space, list); + + return space; +} + +static void vfio_put_address_space(VFIOAddressSpace *space) +{ + if (QLIST_EMPTY(&space->containers)) { + QLIST_REMOVE(space, list); + g_free(space); + } +} + +static int vfio_connect_container(VFIOGroup *group, AddressSpace *as) +{ + VFIOContainer *container; + int ret, fd; + VFIOAddressSpace *space; + + space = vfio_get_address_space(as); + + QLIST_FOREACH(container, &space->containers, next) { + if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) { + group->container = container; + QLIST_INSERT_HEAD(&container->group_list, group, container_next); + return 0; + } + } + + fd = qemu_open("/dev/vfio/vfio", O_RDWR); + if (fd < 0) { + error_report("vfio: failed to open /dev/vfio/vfio: %m"); + ret = -errno; + goto put_space_exit; + } + + ret = ioctl(fd, VFIO_GET_API_VERSION); + if (ret != VFIO_API_VERSION) { + error_report("vfio: supported vfio version: %d, " + "reported version: %d", VFIO_API_VERSION, ret); + ret = -EINVAL; + goto close_fd_exit; + } + + container = g_malloc0(sizeof(*container)); + container->space = space; + container->fd = fd; + if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1_IOMMU)) { + ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd); + if (ret) { + error_report("vfio: failed to set group container: %m"); + ret = -errno; + goto free_container_exit; + } + + ret = ioctl(fd, VFIO_SET_IOMMU, VFIO_TYPE1_IOMMU); + if (ret) { + error_report("vfio: failed to set iommu for container: %m"); + ret = -errno; + goto free_container_exit; + } + + container->iommu_data.type1.listener = vfio_memory_listener; + container->iommu_data.release = vfio_listener_release; + + memory_listener_register(&container->iommu_data.type1.listener, + container->space->as); + + if (container->iommu_data.type1.error) { + ret = container->iommu_data.type1.error; + error_report("vfio: memory listener initialization failed for container"); + goto listener_release_exit; + } + + container->iommu_data.type1.initialized = true; + + } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU)) { + ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd); + if (ret) { + error_report("vfio: failed to set group container: %m"); + ret = -errno; + goto free_container_exit; + } + ret = ioctl(fd, VFIO_SET_IOMMU, VFIO_SPAPR_TCE_IOMMU); + if (ret) { + error_report("vfio: failed to set iommu for container: %m"); + ret = -errno; + goto free_container_exit; + } + + /* + * The host kernel code implementing VFIO_IOMMU_DISABLE is called + * when container fd is closed so we do not call it explicitly + * in this file. + */ + ret = ioctl(fd, VFIO_IOMMU_ENABLE); + if (ret) { + error_report("vfio: failed to enable container: %m"); + ret = -errno; + goto free_container_exit; + } + + container->iommu_data.type1.listener = vfio_memory_listener; + container->iommu_data.release = vfio_listener_release; + + memory_listener_register(&container->iommu_data.type1.listener, + container->space->as); + + } else { + error_report("vfio: No available IOMMU models"); + ret = -EINVAL; + goto free_container_exit; + } + + QLIST_INIT(&container->group_list); + QLIST_INSERT_HEAD(&space->containers, container, next); + + group->container = container; + QLIST_INSERT_HEAD(&container->group_list, group, container_next); + + return 0; +listener_release_exit: + vfio_listener_release(container); + +free_container_exit: + g_free(container); + +close_fd_exit: + close(fd); + +put_space_exit: + vfio_put_address_space(space); + + return ret; +} + +static void vfio_disconnect_container(VFIOGroup *group) +{ + VFIOContainer *container = group->container; + + if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, &container->fd)) { + error_report("vfio: error disconnecting group %d from container", + group->groupid); + } + + QLIST_REMOVE(group, container_next); + group->container = NULL; + + if (QLIST_EMPTY(&container->group_list)) { + VFIOAddressSpace *space = container->space; + + if (container->iommu_data.release) { + container->iommu_data.release(container); + } + QLIST_REMOVE(container, next); + trace_vfio_disconnect_container(container->fd); + close(container->fd); + g_free(container); + + vfio_put_address_space(space); + } +} + +VFIOGroup *vfio_get_group(int groupid, AddressSpace *as) +{ + VFIOGroup *group; + char path[32]; + struct vfio_group_status status = { .argsz = sizeof(status) }; + + QLIST_FOREACH(group, &vfio_group_list, next) { + if (group->groupid == groupid) { + /* Found it. Now is it already in the right context? */ + if (group->container->space->as == as) { + return group; + } else { + error_report("vfio: group %d used in multiple address spaces", + group->groupid); + return NULL; + } + } + } + + group = g_malloc0(sizeof(*group)); + + snprintf(path, sizeof(path), "/dev/vfio/%d", groupid); + group->fd = qemu_open(path, O_RDWR); + if (group->fd < 0) { + error_report("vfio: error opening %s: %m", path); + goto free_group_exit; + } + + if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &status)) { + error_report("vfio: error getting group status: %m"); + goto close_fd_exit; + } + + if (!(status.flags & VFIO_GROUP_FLAGS_VIABLE)) { + error_report("vfio: error, group %d is not viable, please ensure " + "all devices within the iommu_group are bound to their " + "vfio bus driver.", groupid); + goto close_fd_exit; + } + + group->groupid = groupid; + QLIST_INIT(&group->device_list); + + if (vfio_connect_container(group, as)) { + error_report("vfio: failed to setup container for group %d", groupid); + goto close_fd_exit; + } + + if (QLIST_EMPTY(&vfio_group_list)) { + qemu_register_reset(vfio_reset_handler, NULL); + } + + QLIST_INSERT_HEAD(&vfio_group_list, group, next); + + vfio_kvm_device_add_group(group); + + return group; + +close_fd_exit: + close(group->fd); + +free_group_exit: + g_free(group); + + return NULL; +} + +void vfio_put_group(VFIOGroup *group) +{ + if (!QLIST_EMPTY(&group->device_list)) { + return; + } + + vfio_kvm_device_del_group(group); + vfio_disconnect_container(group); + QLIST_REMOVE(group, next); + trace_vfio_put_group(group->fd); + close(group->fd); + g_free(group); + + if (QLIST_EMPTY(&vfio_group_list)) { + qemu_unregister_reset(vfio_reset_handler, NULL); + } +} + +int vfio_get_device(VFIOGroup *group, const char *name, + VFIODevice *vbasedev) +{ + struct vfio_device_info dev_info = { .argsz = sizeof(dev_info) }; + int ret; + + ret = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name); + if (ret < 0) { + error_report("vfio: error getting device %s from group %d: %m", + name, group->groupid); + error_printf("Verify all devices in group %d are bound to vfio-<bus> " + "or pci-stub and not already in use\n", group->groupid); + return ret; + } + + vbasedev->fd = ret; + vbasedev->group = group; + QLIST_INSERT_HEAD(&group->device_list, vbasedev, next); + + ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_INFO, &dev_info); + if (ret) { + error_report("vfio: error getting device info: %m"); + goto error; + } + + vbasedev->num_irqs = dev_info.num_irqs; + vbasedev->num_regions = dev_info.num_regions; + vbasedev->flags = dev_info.flags; + + trace_vfio_get_device(name, dev_info.flags, dev_info.num_regions, + dev_info.num_irqs); + + vbasedev->reset_works = !!(dev_info.flags & VFIO_DEVICE_FLAGS_RESET); + + ret = vbasedev->ops->vfio_populate_device(vbasedev); + +error: + if (ret) { + vfio_put_base_device(vbasedev); + } + return ret; +} + +void vfio_put_base_device(VFIODevice *vbasedev) +{ + QLIST_REMOVE(vbasedev, next); + vbasedev->group = NULL; + trace_vfio_put_base_device(vbasedev->fd); + close(vbasedev->fd); +} + +static int vfio_container_do_ioctl(AddressSpace *as, int32_t groupid, + int req, void *param) +{ + VFIOGroup *group; + VFIOContainer *container; + int ret = -1; + + group = vfio_get_group(groupid, as); + if (!group) { + error_report("vfio: group %d not registered", groupid); + return ret; + } + + container = group->container; + if (group->container) { + ret = ioctl(container->fd, req, param); + if (ret < 0) { + error_report("vfio: failed to ioctl container: ret=%d, %s", + ret, strerror(errno)); + } + } + + vfio_put_group(group); + + return ret; +} + +int vfio_container_ioctl(AddressSpace *as, int32_t groupid, + int req, void *param) +{ + /* We allow only certain ioctls to the container */ + switch (req) { + case VFIO_CHECK_EXTENSION: + case VFIO_IOMMU_SPAPR_TCE_GET_INFO: + break; + default: + /* Return an error on unknown requests */ + error_report("vfio: unsupported ioctl %X", req); + return -1; + } + + return vfio_container_do_ioctl(as, groupid, req, param); +} diff --git a/hw/misc/vfio.c b/hw/vfio/pci.c index a315c3a..b4e73d1 100644 --- a/hw/misc/vfio.c +++ b/hw/vfio/pci.c @@ -39,28 +39,15 @@ #include "qemu/range.h" #include "sysemu/kvm.h" #include "sysemu/sysemu.h" -#include "hw/misc/vfio.h" +#include "trace.h" +#include "hw/vfio/vfio.h" +#include "hw/vfio/vfio-common.h" -/* #define DEBUG_VFIO */ -#ifdef DEBUG_VFIO -#define DPRINTF(fmt, ...) \ - do { fprintf(stderr, "vfio: " fmt, ## __VA_ARGS__); } while (0) -#else -#define DPRINTF(fmt, ...) \ - do { } while (0) -#endif - -/* Extra debugging, trap acceleration paths for more logging */ -#define VFIO_ALLOW_MMAP 1 -#define VFIO_ALLOW_KVM_INTX 1 -#define VFIO_ALLOW_KVM_MSI 1 -#define VFIO_ALLOW_KVM_MSIX 1 - -struct VFIODevice; +struct VFIOPCIDevice; typedef struct VFIOQuirk { MemoryRegion mem; - struct VFIODevice *vdev; + struct VFIOPCIDevice *vdev; QLIST_ENTRY(VFIOQuirk) next; struct { uint32_t base_offset:TARGET_PAGE_BITS; @@ -82,14 +69,7 @@ typedef struct VFIOQuirk { } VFIOQuirk; typedef struct VFIOBAR { - off_t fd_offset; /* offset of BAR within device fd */ - int fd; /* device fd, allows us to pass VFIOBAR as opaque data */ - MemoryRegion mem; /* slow, read/write access */ - MemoryRegion mmap_mem; /* direct mapped access */ - void *mmap; - size_t size; - uint32_t flags; /* VFIO region flags (rd/wr/mmap) */ - uint8_t nr; /* cache the BAR number for debug */ + VFIORegion region; bool ioport; bool mem64; QLIST_HEAD(, VFIOQuirk) quirks; @@ -131,7 +111,7 @@ typedef struct VFIOMSIVector { */ EventNotifier interrupt; EventNotifier kvm_interrupt; - struct VFIODevice *vdev; /* back pointer to device */ + struct VFIOPCIDevice *vdev; /* back pointer to device */ int virq; bool use; } VFIOMSIVector; @@ -143,45 +123,6 @@ enum { VFIO_INT_MSIX = 3, }; -typedef struct VFIOAddressSpace { - AddressSpace *as; - QLIST_HEAD(, VFIOContainer) containers; - QLIST_ENTRY(VFIOAddressSpace) list; -} VFIOAddressSpace; - -static QLIST_HEAD(, VFIOAddressSpace) vfio_address_spaces = - QLIST_HEAD_INITIALIZER(vfio_address_spaces); - -struct VFIOGroup; - -typedef struct VFIOType1 { - MemoryListener listener; - int error; - bool initialized; -} VFIOType1; - -typedef struct VFIOContainer { - VFIOAddressSpace *space; - int fd; /* /dev/vfio/vfio, empowered by the attached groups */ - struct { - /* enable abstraction to support various iommu backends */ - union { - VFIOType1 type1; - }; - void (*release)(struct VFIOContainer *); - } iommu_data; - QLIST_HEAD(, VFIOGuestIOMMU) giommu_list; - QLIST_HEAD(, VFIOGroup) group_list; - QLIST_ENTRY(VFIOContainer) next; -} VFIOContainer; - -typedef struct VFIOGuestIOMMU { - VFIOContainer *container; - MemoryRegion *iommu; - Notifier n; - QLIST_ENTRY(VFIOGuestIOMMU) giommu_next; -} VFIOGuestIOMMU; - /* Cache of MSI-X setup plus extra mmap and memory region for split BAR map */ typedef struct VFIOMSIXInfo { uint8_t table_bar; @@ -193,9 +134,9 @@ typedef struct VFIOMSIXInfo { void *mmap; } VFIOMSIXInfo; -typedef struct VFIODevice { +typedef struct VFIOPCIDevice { PCIDevice pdev; - int fd; + VFIODevice vbasedev; VFIOINTx intx; unsigned int config_size; uint8_t *emulated_config_bits; /* QEMU emulated bits, little-endian */ @@ -211,31 +152,18 @@ typedef struct VFIODevice { VFIOBAR bars[PCI_NUM_REGIONS - 1]; /* No ROM */ VFIOVGA vga; /* 0xa0000, 0x3b0, 0x3c0 */ PCIHostDeviceAddress host; - QLIST_ENTRY(VFIODevice) next; - struct VFIOGroup *group; EventNotifier err_notifier; uint32_t features; #define VFIO_FEATURE_ENABLE_VGA_BIT 0 #define VFIO_FEATURE_ENABLE_VGA (1 << VFIO_FEATURE_ENABLE_VGA_BIT) int32_t bootindex; uint8_t pm_cap; - bool reset_works; bool has_vga; bool pci_aer; bool has_flr; bool has_pm_reset; - bool needs_reset; bool rom_read_failed; -} VFIODevice; - -typedef struct VFIOGroup { - int fd; - int groupid; - VFIOContainer *container; - QLIST_HEAD(, VFIODevice) device_list; - QLIST_ENTRY(VFIOGroup) next; - QLIST_ENTRY(VFIOGroup) container_next; -} VFIOGroup; +} VFIOPCIDevice; typedef struct VFIORomBlacklistEntry { uint16_t vendor_id; @@ -262,72 +190,12 @@ static const VFIORomBlacklistEntry romblacklist[] = { #define MSIX_CAP_LENGTH 12 -static QLIST_HEAD(, VFIOGroup) - group_list = QLIST_HEAD_INITIALIZER(group_list); - -#ifdef CONFIG_KVM -/* - * We have a single VFIO pseudo device per KVM VM. Once created it lives - * for the life of the VM. Closing the file descriptor only drops our - * reference to it and the device's reference to kvm. Therefore once - * initialized, this file descriptor is only released on QEMU exit and - * we'll re-use it should another vfio device be attached before then. - */ -static int vfio_kvm_device_fd = -1; -#endif - -static void vfio_disable_interrupts(VFIODevice *vdev); +static void vfio_disable_interrupts(VFIOPCIDevice *vdev); static uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len); static void vfio_pci_write_config(PCIDevice *pdev, uint32_t addr, uint32_t val, int len); -static void vfio_mmap_set_enabled(VFIODevice *vdev, bool enabled); - -/* - * Common VFIO interrupt disable - */ -static void vfio_disable_irqindex(VFIODevice *vdev, int index) -{ - struct vfio_irq_set irq_set = { - .argsz = sizeof(irq_set), - .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER, - .index = index, - .start = 0, - .count = 0, - }; - - ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); -} - -/* - * INTx - */ -static void vfio_unmask_intx(VFIODevice *vdev) -{ - struct vfio_irq_set irq_set = { - .argsz = sizeof(irq_set), - .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK, - .index = VFIO_PCI_INTX_IRQ_INDEX, - .start = 0, - .count = 1, - }; - - ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); -} - -#ifdef CONFIG_KVM /* Unused outside of CONFIG_KVM code */ -static void vfio_mask_intx(VFIODevice *vdev) -{ - struct vfio_irq_set irq_set = { - .argsz = sizeof(irq_set), - .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK, - .index = VFIO_PCI_INTX_IRQ_INDEX, - .start = 0, - .count = 1, - }; - - ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); -} -#endif +static void vfio_mmap_set_enabled(VFIOPCIDevice *vdev, bool enabled); +static int vfio_populate_device(VFIODevice *vbasedev); /* * Disabling BAR mmaping can be slow, but toggling it around INTx can @@ -346,7 +214,7 @@ static void vfio_mask_intx(VFIODevice *vdev) */ static void vfio_intx_mmap_enable(void *opaque) { - VFIODevice *vdev = opaque; + VFIOPCIDevice *vdev = opaque; if (vdev->intx.pending) { timer_mod(vdev->intx.mmap_timer, @@ -359,15 +227,13 @@ static void vfio_intx_mmap_enable(void *opaque) static void vfio_intx_interrupt(void *opaque) { - VFIODevice *vdev = opaque; + VFIOPCIDevice *vdev = opaque; if (!event_notifier_test_and_clear(&vdev->intx.interrupt)) { return; } - DPRINTF("%s(%04x:%02x:%02x.%x) Pin %c\n", __func__, vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function, - 'A' + vdev->intx.pin); + trace_vfio_intx_interrupt(vdev->vbasedev.name, 'A' + vdev->intx.pin); vdev->intx.pending = true; pci_irq_assert(&vdev->pdev); @@ -378,21 +244,22 @@ static void vfio_intx_interrupt(void *opaque) } } -static void vfio_eoi(VFIODevice *vdev) +static void vfio_eoi(VFIODevice *vbasedev) { + VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev); + if (!vdev->intx.pending) { return; } - DPRINTF("%s(%04x:%02x:%02x.%x) EOI\n", __func__, vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function); + trace_vfio_eoi(vbasedev->name); vdev->intx.pending = false; pci_irq_deassert(&vdev->pdev); - vfio_unmask_intx(vdev); + vfio_unmask_single_irqindex(vbasedev, VFIO_PCI_INTX_IRQ_INDEX); } -static void vfio_enable_intx_kvm(VFIODevice *vdev) +static void vfio_enable_intx_kvm(VFIOPCIDevice *vdev) { #ifdef CONFIG_KVM struct kvm_irqfd irqfd = { @@ -412,7 +279,7 @@ static void vfio_enable_intx_kvm(VFIODevice *vdev) /* Get to a known interrupt state */ qemu_set_fd_handler(irqfd.fd, NULL, NULL, vdev); - vfio_mask_intx(vdev); + vfio_mask_single_irqindex(&vdev->vbasedev, VFIO_PCI_INTX_IRQ_INDEX); vdev->intx.pending = false; pci_irq_deassert(&vdev->pdev); @@ -442,7 +309,7 @@ static void vfio_enable_intx_kvm(VFIODevice *vdev) *pfd = irqfd.resamplefd; - ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set); + ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set); g_free(irq_set); if (ret) { error_report("vfio: Error: Failed to setup INTx unmask fd: %m"); @@ -450,13 +317,11 @@ static void vfio_enable_intx_kvm(VFIODevice *vdev) } /* Let'em rip */ - vfio_unmask_intx(vdev); + vfio_unmask_single_irqindex(&vdev->vbasedev, VFIO_PCI_INTX_IRQ_INDEX); vdev->intx.kvm_accel = true; - DPRINTF("%s(%04x:%02x:%02x.%x) KVM INTx accel enabled\n", - __func__, vdev->host.domain, vdev->host.bus, - vdev->host.slot, vdev->host.function); + trace_vfio_enable_intx_kvm(vdev->vbasedev.name); return; @@ -467,11 +332,11 @@ fail_irqfd: event_notifier_cleanup(&vdev->intx.unmask); fail: qemu_set_fd_handler(irqfd.fd, vfio_intx_interrupt, NULL, vdev); - vfio_unmask_intx(vdev); + vfio_unmask_single_irqindex(&vdev->vbasedev, VFIO_PCI_INTX_IRQ_INDEX); #endif } -static void vfio_disable_intx_kvm(VFIODevice *vdev) +static void vfio_disable_intx_kvm(VFIOPCIDevice *vdev) { #ifdef CONFIG_KVM struct kvm_irqfd irqfd = { @@ -488,7 +353,7 @@ static void vfio_disable_intx_kvm(VFIODevice *vdev) * Get to a known state, hardware masked, QEMU ready to accept new * interrupts, QEMU IRQ de-asserted. */ - vfio_mask_intx(vdev); + vfio_mask_single_irqindex(&vdev->vbasedev, VFIO_PCI_INTX_IRQ_INDEX); vdev->intx.pending = false; pci_irq_deassert(&vdev->pdev); @@ -506,17 +371,15 @@ static void vfio_disable_intx_kvm(VFIODevice *vdev) vdev->intx.kvm_accel = false; /* If we've missed an event, let it re-fire through QEMU */ - vfio_unmask_intx(vdev); + vfio_unmask_single_irqindex(&vdev->vbasedev, VFIO_PCI_INTX_IRQ_INDEX); - DPRINTF("%s(%04x:%02x:%02x.%x) KVM INTx accel disabled\n", - __func__, vdev->host.domain, vdev->host.bus, - vdev->host.slot, vdev->host.function); + trace_vfio_disable_intx_kvm(vdev->vbasedev.name); #endif } static void vfio_update_irq(PCIDevice *pdev) { - VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev); + VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev); PCIINTxRoute route; if (vdev->interrupt != VFIO_INT_INTx) { @@ -529,9 +392,8 @@ static void vfio_update_irq(PCIDevice *pdev) return; /* Nothing changed */ } - DPRINTF("%s(%04x:%02x:%02x.%x) IRQ moved %d -> %d\n", __func__, - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function, vdev->intx.route.irq, route.irq); + trace_vfio_update_irq(vdev->vbasedev.name, + vdev->intx.route.irq, route.irq); vfio_disable_intx_kvm(vdev); @@ -544,10 +406,10 @@ static void vfio_update_irq(PCIDevice *pdev) vfio_enable_intx_kvm(vdev); /* Re-enable the interrupt in cased we missed an EOI */ - vfio_eoi(vdev); + vfio_eoi(&vdev->vbasedev); } -static int vfio_enable_intx(VFIODevice *vdev) +static int vfio_enable_intx(VFIOPCIDevice *vdev) { uint8_t pin = vfio_pci_read_config(&vdev->pdev, PCI_INTERRUPT_PIN, 1); int ret, argsz; @@ -593,7 +455,7 @@ static int vfio_enable_intx(VFIODevice *vdev) *pfd = event_notifier_get_fd(&vdev->intx.interrupt); qemu_set_fd_handler(*pfd, vfio_intx_interrupt, NULL, vdev); - ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set); + ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set); g_free(irq_set); if (ret) { error_report("vfio: Error: Failed to setup INTx fd: %m"); @@ -606,19 +468,18 @@ static int vfio_enable_intx(VFIODevice *vdev) vdev->interrupt = VFIO_INT_INTx; - DPRINTF("%s(%04x:%02x:%02x.%x)\n", __func__, vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function); + trace_vfio_enable_intx(vdev->vbasedev.name); return 0; } -static void vfio_disable_intx(VFIODevice *vdev) +static void vfio_disable_intx(VFIOPCIDevice *vdev) { int fd; timer_del(vdev->intx.mmap_timer); vfio_disable_intx_kvm(vdev); - vfio_disable_irqindex(vdev, VFIO_PCI_INTX_IRQ_INDEX); + vfio_disable_irqindex(&vdev->vbasedev, VFIO_PCI_INTX_IRQ_INDEX); vdev->intx.pending = false; pci_irq_deassert(&vdev->pdev); vfio_mmap_set_enabled(vdev, true); @@ -629,8 +490,7 @@ static void vfio_disable_intx(VFIODevice *vdev) vdev->interrupt = VFIO_INT_NONE; - DPRINTF("%s(%04x:%02x:%02x.%x)\n", __func__, vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function); + trace_vfio_disable_intx(vdev->vbasedev.name); } /* @@ -639,7 +499,7 @@ static void vfio_disable_intx(VFIODevice *vdev) static void vfio_msi_interrupt(void *opaque) { VFIOMSIVector *vector = opaque; - VFIODevice *vdev = vector->vdev; + VFIOPCIDevice *vdev = vector->vdev; int nr = vector - vdev->msi_vectors; if (!event_notifier_test_and_clear(&vector->interrupt)) { @@ -657,9 +517,7 @@ static void vfio_msi_interrupt(void *opaque) abort(); } - DPRINTF("%s(%04x:%02x:%02x.%x) vector %d 0x%"PRIx64"/0x%x\n", __func__, - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function, nr, msg.address, msg.data); + trace_vfio_msi_interrupt(vbasedev->name, nr, msg.address, msg.data); #endif if (vdev->interrupt == VFIO_INT_MSIX) { @@ -671,7 +529,7 @@ static void vfio_msi_interrupt(void *opaque) } } -static int vfio_enable_vectors(VFIODevice *vdev, bool msix) +static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix) { struct vfio_irq_set *irq_set; int ret = 0, i, argsz; @@ -708,7 +566,7 @@ static int vfio_enable_vectors(VFIODevice *vdev, bool msix) fds[i] = fd; } - ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set); + ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set); g_free(irq_set); @@ -762,13 +620,11 @@ static void vfio_update_kvm_msi_virq(VFIOMSIVector *vector, MSIMessage msg) static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, MSIMessage *msg, IOHandler *handler) { - VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev); + VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev); VFIOMSIVector *vector; int ret; - DPRINTF("%s(%04x:%02x:%02x.%x) vector %d used\n", __func__, - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function, nr); + trace_vfio_msix_vector_do_use(vdev->vbasedev.name, nr); vector = &vdev->msi_vectors[nr]; @@ -805,7 +661,7 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, * increase them as needed. */ if (vdev->nr_vectors < nr + 1) { - vfio_disable_irqindex(vdev, VFIO_PCI_MSIX_IRQ_INDEX); + vfio_disable_irqindex(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX); vdev->nr_vectors = nr + 1; ret = vfio_enable_vectors(vdev, true); if (ret) { @@ -833,7 +689,7 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, *pfd = event_notifier_get_fd(&vector->interrupt); } - ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set); + ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set); g_free(irq_set); if (ret) { error_report("vfio: failed to modify vector, %d", ret); @@ -851,12 +707,10 @@ static int vfio_msix_vector_use(PCIDevice *pdev, static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr) { - VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev); + VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev); VFIOMSIVector *vector = &vdev->msi_vectors[nr]; - DPRINTF("%s(%04x:%02x:%02x.%x) vector %d released\n", __func__, - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function, nr); + trace_vfio_msix_vector_release(vdev->vbasedev.name, nr); /* * There are still old guests that mask and unmask vectors on every @@ -884,13 +738,13 @@ static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr) *pfd = event_notifier_get_fd(&vector->interrupt); - ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set); + ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set); g_free(irq_set); } } -static void vfio_enable_msix(VFIODevice *vdev) +static void vfio_enable_msix(VFIOPCIDevice *vdev) { vfio_disable_interrupts(vdev); @@ -919,11 +773,10 @@ static void vfio_enable_msix(VFIODevice *vdev) error_report("vfio: msix_set_vector_notifiers failed"); } - DPRINTF("%s(%04x:%02x:%02x.%x)\n", __func__, vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function); + trace_vfio_enable_msix(vdev->vbasedev.name); } -static void vfio_enable_msi(VFIODevice *vdev) +static void vfio_enable_msi(VFIOPCIDevice *vdev) { int ret, i; @@ -996,12 +849,10 @@ retry: return; } - DPRINTF("%s(%04x:%02x:%02x.%x) Enabled %d MSI vectors\n", __func__, - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function, vdev->nr_vectors); + trace_vfio_enable_msi(vdev->vbasedev.name, vdev->nr_vectors); } -static void vfio_disable_msi_common(VFIODevice *vdev) +static void vfio_disable_msi_common(VFIOPCIDevice *vdev) { int i; @@ -1025,7 +876,7 @@ static void vfio_disable_msi_common(VFIODevice *vdev) vfio_enable_intx(vdev); } -static void vfio_disable_msix(VFIODevice *vdev) +static void vfio_disable_msix(VFIOPCIDevice *vdev) { int i; @@ -1043,25 +894,23 @@ static void vfio_disable_msix(VFIODevice *vdev) } if (vdev->nr_vectors) { - vfio_disable_irqindex(vdev, VFIO_PCI_MSIX_IRQ_INDEX); + vfio_disable_irqindex(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX); } vfio_disable_msi_common(vdev); - DPRINTF("%s(%04x:%02x:%02x.%x)\n", __func__, vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function); + trace_vfio_disable_msix(vdev->vbasedev.name); } -static void vfio_disable_msi(VFIODevice *vdev) +static void vfio_disable_msi(VFIOPCIDevice *vdev) { - vfio_disable_irqindex(vdev, VFIO_PCI_MSI_IRQ_INDEX); + vfio_disable_irqindex(&vdev->vbasedev, VFIO_PCI_MSI_IRQ_INDEX); vfio_disable_msi_common(vdev); - DPRINTF("%s(%04x:%02x:%02x.%x)\n", __func__, vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function); + trace_vfio_disable_msi(vdev->vbasedev.name); } -static void vfio_update_msi(VFIODevice *vdev) +static void vfio_update_msi(VFIOPCIDevice *vdev) { int i; @@ -1078,119 +927,7 @@ static void vfio_update_msi(VFIODevice *vdev) } } -/* - * IO Port/MMIO - Beware of the endians, VFIO is always little endian - */ -static void vfio_bar_write(void *opaque, hwaddr addr, - uint64_t data, unsigned size) -{ - VFIOBAR *bar = opaque; - union { - uint8_t byte; - uint16_t word; - uint32_t dword; - uint64_t qword; - } buf; - - switch (size) { - case 1: - buf.byte = data; - break; - case 2: - buf.word = cpu_to_le16(data); - break; - case 4: - buf.dword = cpu_to_le32(data); - break; - default: - hw_error("vfio: unsupported write size, %d bytes", size); - break; - } - - if (pwrite(bar->fd, &buf, size, bar->fd_offset + addr) != size) { - error_report("%s(,0x%"HWADDR_PRIx", 0x%"PRIx64", %d) failed: %m", - __func__, addr, data, size); - } - -#ifdef DEBUG_VFIO - { - VFIODevice *vdev = container_of(bar, VFIODevice, bars[bar->nr]); - - DPRINTF("%s(%04x:%02x:%02x.%x:BAR%d+0x%"HWADDR_PRIx", 0x%"PRIx64 - ", %d)\n", __func__, vdev->host.domain, vdev->host.bus, - vdev->host.slot, vdev->host.function, bar->nr, addr, - data, size); - } -#endif - - /* - * A read or write to a BAR always signals an INTx EOI. This will - * do nothing if not pending (including not in INTx mode). We assume - * that a BAR access is in response to an interrupt and that BAR - * accesses will service the interrupt. Unfortunately, we don't know - * which access will service the interrupt, so we're potentially - * getting quite a few host interrupts per guest interrupt. - */ - vfio_eoi(container_of(bar, VFIODevice, bars[bar->nr])); -} - -static uint64_t vfio_bar_read(void *opaque, - hwaddr addr, unsigned size) -{ - VFIOBAR *bar = opaque; - union { - uint8_t byte; - uint16_t word; - uint32_t dword; - uint64_t qword; - } buf; - uint64_t data = 0; - - if (pread(bar->fd, &buf, size, bar->fd_offset + addr) != size) { - error_report("%s(,0x%"HWADDR_PRIx", %d) failed: %m", - __func__, addr, size); - return (uint64_t)-1; - } - - switch (size) { - case 1: - data = buf.byte; - break; - case 2: - data = le16_to_cpu(buf.word); - break; - case 4: - data = le32_to_cpu(buf.dword); - break; - default: - hw_error("vfio: unsupported read size, %d bytes", size); - break; - } - -#ifdef DEBUG_VFIO - { - VFIODevice *vdev = container_of(bar, VFIODevice, bars[bar->nr]); - - DPRINTF("%s(%04x:%02x:%02x.%x:BAR%d+0x%"HWADDR_PRIx - ", %d) = 0x%"PRIx64"\n", __func__, vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function, - bar->nr, addr, size, data); - } -#endif - - /* Same as write above */ - vfio_eoi(container_of(bar, VFIODevice, bars[bar->nr])); - - return data; -} - -static const MemoryRegionOps vfio_bar_ops = { - .read = vfio_bar_read, - .write = vfio_bar_write, - .endianness = DEVICE_LITTLE_ENDIAN, -}; - -static void vfio_pci_load_rom(VFIODevice *vdev) +static void vfio_pci_load_rom(VFIOPCIDevice *vdev) { struct vfio_region_info reg_info = { .argsz = sizeof(reg_info), @@ -1200,16 +937,14 @@ static void vfio_pci_load_rom(VFIODevice *vdev) off_t off = 0; size_t bytes; - if (ioctl(vdev->fd, VFIO_DEVICE_GET_REGION_INFO, ®_info)) { + if (ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_REGION_INFO, ®_info)) { error_report("vfio: Error getting ROM info: %m"); return; } - DPRINTF("Device %04x:%02x:%02x.%x ROM:\n", vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function); - DPRINTF(" size: 0x%lx, offset: 0x%lx, flags: 0x%lx\n", - (unsigned long)reg_info.size, (unsigned long)reg_info.offset, - (unsigned long)reg_info.flags); + trace_vfio_pci_load_rom(vdev->vbasedev.name, (unsigned long)reg_info.size, + (unsigned long)reg_info.offset, + (unsigned long)reg_info.flags); vdev->rom_size = size = reg_info.size; vdev->rom_offset = reg_info.offset; @@ -1217,9 +952,7 @@ static void vfio_pci_load_rom(VFIODevice *vdev) if (!vdev->rom_size) { vdev->rom_read_failed = true; error_report("vfio-pci: Cannot read device rom at " - "%04x:%02x:%02x.%x", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function); + "%s", vdev->vbasedev.name); error_printf("Device option ROM contents are probably invalid " "(check dmesg).\nSkip option ROM probe with rombar=0, " "or load from file with romfile=\n"); @@ -1230,7 +963,8 @@ static void vfio_pci_load_rom(VFIODevice *vdev) memset(vdev->rom, 0xff, size); while (size) { - bytes = pread(vdev->fd, vdev->rom + off, size, vdev->rom_offset + off); + bytes = pread(vdev->vbasedev.fd, vdev->rom + off, + size, vdev->rom_offset + off); if (bytes == 0) { break; } else if (bytes > 0) { @@ -1248,7 +982,7 @@ static void vfio_pci_load_rom(VFIODevice *vdev) static uint64_t vfio_rom_read(void *opaque, hwaddr addr, unsigned size) { - VFIODevice *vdev = opaque; + VFIOPCIDevice *vdev = opaque; union { uint8_t byte; uint16_t word; @@ -1280,9 +1014,7 @@ static uint64_t vfio_rom_read(void *opaque, hwaddr addr, unsigned size) break; } - DPRINTF("%s(%04x:%02x:%02x.%x, 0x%"HWADDR_PRIx", 0x%x) = 0x%"PRIx64"\n", - __func__, vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function, addr, size, data); + trace_vfio_rom_read(vdev->vbasedev.name, addr, size, data); return data; } @@ -1298,7 +1030,7 @@ static const MemoryRegionOps vfio_rom_ops = { .endianness = DEVICE_LITTLE_ENDIAN, }; -static bool vfio_blacklist_opt_rom(VFIODevice *vdev) +static bool vfio_blacklist_opt_rom(VFIOPCIDevice *vdev) { PCIDevice *pdev = &vdev->pdev; uint16_t vendor_id, device_id; @@ -1318,12 +1050,13 @@ static bool vfio_blacklist_opt_rom(VFIODevice *vdev) return false; } -static void vfio_pci_size_rom(VFIODevice *vdev) +static void vfio_pci_size_rom(VFIOPCIDevice *vdev) { uint32_t orig, size = cpu_to_le32((uint32_t)PCI_ROM_ADDRESS_MASK); off_t offset = vdev->config_offset + PCI_ROM_ADDRESS; DeviceState *dev = DEVICE(vdev); char name[32]; + int fd = vdev->vbasedev.fd; if (vdev->pdev.romfile || !vdev->pdev.rom_bar) { /* Since pci handles romfile, just print a message and return */ @@ -1342,10 +1075,10 @@ static void vfio_pci_size_rom(VFIODevice *vdev) * Use the same size ROM BAR as the physical device. The contents * will get filled in later when the guest tries to read it. */ - if (pread(vdev->fd, &orig, 4, offset) != 4 || - pwrite(vdev->fd, &size, 4, offset) != 4 || - pread(vdev->fd, &size, 4, offset) != 4 || - pwrite(vdev->fd, &orig, 4, offset) != 4) { + if (pread(fd, &orig, 4, offset) != 4 || + pwrite(fd, &size, 4, offset) != 4 || + pread(fd, &size, 4, offset) != 4 || + pwrite(fd, &orig, 4, offset) != 4) { error_report("%s(%04x:%02x:%02x.%x) failed: %m", __func__, vdev->host.domain, vdev->host.bus, vdev->host.slot, vdev->host.function); @@ -1378,8 +1111,7 @@ static void vfio_pci_size_rom(VFIODevice *vdev) } } - DPRINTF("%04x:%02x:%02x.%x ROM size 0x%x\n", vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function, size); + trace_vfio_pci_size_rom(vdev->vbasedev.name, size); snprintf(name, sizeof(name), "vfio[%04x:%02x:%02x.%x].rom", vdev->host.domain, vdev->host.bus, vdev->host.slot, @@ -1428,8 +1160,7 @@ static void vfio_vga_write(void *opaque, hwaddr addr, __func__, region->offset + addr, data, size); } - DPRINTF("%s(0x%"HWADDR_PRIx", 0x%"PRIx64", %d)\n", - __func__, region->offset + addr, data, size); + trace_vfio_vga_write(region->offset + addr, data, size); } static uint64_t vfio_vga_read(void *opaque, hwaddr addr, unsigned size) @@ -1466,8 +1197,7 @@ static uint64_t vfio_vga_read(void *opaque, hwaddr addr, unsigned size) break; } - DPRINTF("%s(0x%"HWADDR_PRIx", %d) = 0x%"PRIx64"\n", - __func__, region->offset + addr, size, data); + trace_vfio_vga_read(region->offset + addr, size, data); return data; } @@ -1497,7 +1227,7 @@ static uint64_t vfio_generic_window_quirk_read(void *opaque, hwaddr addr, unsigned size) { VFIOQuirk *quirk = opaque; - VFIODevice *vdev = quirk->vdev; + VFIOPCIDevice *vdev = quirk->vdev; uint64_t data; if (vfio_flags_enabled(quirk->data.flags, quirk->data.read_flags) && @@ -1514,13 +1244,13 @@ static uint64_t vfio_generic_window_quirk_read(void *opaque, data = vfio_pci_read_config(&vdev->pdev, quirk->data.address_val + offset, size); - DPRINTF("%s read(%04x:%02x:%02x.%x:BAR%d+0x%"HWADDR_PRIx", %d) = 0x%" - PRIx64"\n", memory_region_name(&quirk->mem), vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function, - quirk->data.bar, addr, size, data); + trace_vfio_generic_window_quirk_read(memory_region_name(&quirk->mem), + vdev->vbasedev.name, + quirk->data.bar, + addr, size, data); } else { - data = vfio_bar_read(&vdev->bars[quirk->data.bar], - addr + quirk->data.base_offset, size); + data = vfio_region_read(&vdev->bars[quirk->data.bar].region, + addr + quirk->data.base_offset, size); } return data; @@ -1530,7 +1260,7 @@ static void vfio_generic_window_quirk_write(void *opaque, hwaddr addr, uint64_t data, unsigned size) { VFIOQuirk *quirk = opaque; - VFIODevice *vdev = quirk->vdev; + VFIOPCIDevice *vdev = quirk->vdev; if (ranges_overlap(addr, size, quirk->data.address_offset, quirk->data.address_size)) { @@ -1563,14 +1293,14 @@ static void vfio_generic_window_quirk_write(void *opaque, hwaddr addr, vfio_pci_write_config(&vdev->pdev, quirk->data.address_val + offset, data, size); - DPRINTF("%s write(%04x:%02x:%02x.%x:BAR%d+0x%"HWADDR_PRIx", 0x%" - PRIx64", %d)\n", memory_region_name(&quirk->mem), - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function, quirk->data.bar, addr, data, size); + trace_vfio_generic_window_quirk_write(memory_region_name(&quirk->mem), + vdev->vbasedev.name, + quirk->data.bar, + addr, data, size); return; } - vfio_bar_write(&vdev->bars[quirk->data.bar], + vfio_region_write(&vdev->bars[quirk->data.bar].region, addr + quirk->data.base_offset, data, size); } @@ -1584,7 +1314,7 @@ static uint64_t vfio_generic_quirk_read(void *opaque, hwaddr addr, unsigned size) { VFIOQuirk *quirk = opaque; - VFIODevice *vdev = quirk->vdev; + VFIOPCIDevice *vdev = quirk->vdev; hwaddr base = quirk->data.address_match & TARGET_PAGE_MASK; hwaddr offset = quirk->data.address_match & ~TARGET_PAGE_MASK; uint64_t data; @@ -1599,12 +1329,12 @@ static uint64_t vfio_generic_quirk_read(void *opaque, data = vfio_pci_read_config(&vdev->pdev, addr - offset, size); - DPRINTF("%s read(%04x:%02x:%02x.%x:BAR%d+0x%"HWADDR_PRIx", %d) = 0x%" - PRIx64"\n", memory_region_name(&quirk->mem), vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function, - quirk->data.bar, addr + base, size, data); + trace_vfio_generic_quirk_read(memory_region_name(&quirk->mem), + vdev->vbasedev.name, quirk->data.bar, + addr + base, size, data); } else { - data = vfio_bar_read(&vdev->bars[quirk->data.bar], addr + base, size); + data = vfio_region_read(&vdev->bars[quirk->data.bar].region, + addr + base, size); } return data; @@ -1614,7 +1344,7 @@ static void vfio_generic_quirk_write(void *opaque, hwaddr addr, uint64_t data, unsigned size) { VFIOQuirk *quirk = opaque; - VFIODevice *vdev = quirk->vdev; + VFIOPCIDevice *vdev = quirk->vdev; hwaddr base = quirk->data.address_match & TARGET_PAGE_MASK; hwaddr offset = quirk->data.address_match & ~TARGET_PAGE_MASK; @@ -1628,12 +1358,12 @@ static void vfio_generic_quirk_write(void *opaque, hwaddr addr, vfio_pci_write_config(&vdev->pdev, addr - offset, data, size); - DPRINTF("%s write(%04x:%02x:%02x.%x:BAR%d+0x%"HWADDR_PRIx", 0x%" - PRIx64", %d)\n", memory_region_name(&quirk->mem), - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function, quirk->data.bar, addr + base, data, size); + trace_vfio_generic_quirk_write(memory_region_name(&quirk->mem), + vdev->vbasedev.name, quirk->data.bar, + addr + base, data, size); } else { - vfio_bar_write(&vdev->bars[quirk->data.bar], addr + base, data, size); + vfio_region_write(&vdev->bars[quirk->data.bar].region, + addr + base, data, size); } } @@ -1659,11 +1389,11 @@ static uint64_t vfio_ati_3c3_quirk_read(void *opaque, hwaddr addr, unsigned size) { VFIOQuirk *quirk = opaque; - VFIODevice *vdev = quirk->vdev; + VFIOPCIDevice *vdev = quirk->vdev; uint64_t data = vfio_pci_read_config(&vdev->pdev, PCI_BASE_ADDRESS_0 + (4 * 4) + 1, size); - DPRINTF("%s(0x3c3, 1) = 0x%"PRIx64"\n", __func__, data); + trace_vfio_ati_3c3_quirk_read(data); return data; } @@ -1673,7 +1403,7 @@ static const MemoryRegionOps vfio_ati_3c3_quirk = { .endianness = DEVICE_LITTLE_ENDIAN, }; -static void vfio_vga_probe_ati_3c3_quirk(VFIODevice *vdev) +static void vfio_vga_probe_ati_3c3_quirk(VFIOPCIDevice *vdev) { PCIDevice *pdev = &vdev->pdev; VFIOQuirk *quirk; @@ -1686,7 +1416,7 @@ static void vfio_vga_probe_ati_3c3_quirk(VFIODevice *vdev) * As long as the BAR is >= 256 bytes it will be aligned such that the * lower byte is always zero. Filter out anything else, if it exists. */ - if (!vdev->bars[4].ioport || vdev->bars[4].size < 256) { + if (!vdev->bars[4].ioport || vdev->bars[4].region.size < 256) { return; } @@ -1701,9 +1431,7 @@ static void vfio_vga_probe_ati_3c3_quirk(VFIODevice *vdev) QLIST_INSERT_HEAD(&vdev->vga.region[QEMU_PCI_VGA_IO_HI].quirks, quirk, next); - DPRINTF("Enabled ATI/AMD quirk 0x3c3 BAR4for device %04x:%02x:%02x.%x\n", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function); + trace_vfio_vga_probe_ati_3c3_quirk(vdev->vbasedev.name); } /* @@ -1716,7 +1444,7 @@ static void vfio_vga_probe_ati_3c3_quirk(VFIODevice *vdev) * that only read-only access is provided, but we drop writes when the window * is enabled to config space nonetheless. */ -static void vfio_probe_ati_bar4_window_quirk(VFIODevice *vdev, int nr) +static void vfio_probe_ati_bar4_window_quirk(VFIOPCIDevice *vdev, int nr) { PCIDevice *pdev = &vdev->pdev; VFIOQuirk *quirk; @@ -1739,14 +1467,12 @@ static void vfio_probe_ati_bar4_window_quirk(VFIODevice *vdev, int nr) memory_region_init_io(&quirk->mem, OBJECT(vdev), &vfio_generic_window_quirk, quirk, "vfio-ati-bar4-window-quirk", 8); - memory_region_add_subregion_overlap(&vdev->bars[nr].mem, + memory_region_add_subregion_overlap(&vdev->bars[nr].region.mem, quirk->data.base_offset, &quirk->mem, 1); QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next); - DPRINTF("Enabled ATI/AMD BAR4 window quirk for device %04x:%02x:%02x.%x\n", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function); + trace_vfio_probe_ati_bar4_window_quirk(vdev->vbasedev.name); } #define PCI_VENDOR_ID_REALTEK 0x10ec @@ -1778,14 +1504,14 @@ static uint64_t vfio_rtl8168_window_quirk_read(void *opaque, hwaddr addr, unsigned size) { VFIOQuirk *quirk = opaque; - VFIODevice *vdev = quirk->vdev; + VFIOPCIDevice *vdev = quirk->vdev; switch (addr) { case 4: /* address */ if (quirk->data.flags) { - DPRINTF("%s fake read(%04x:%02x:%02x.%d)\n", - memory_region_name(&quirk->mem), vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function); + trace_vfio_rtl8168_window_quirk_read_fake( + memory_region_name(&quirk->mem), + vdev->vbasedev.name); return quirk->data.address_match ^ 0x10000000U; } @@ -1794,9 +1520,9 @@ static uint64_t vfio_rtl8168_window_quirk_read(void *opaque, if (quirk->data.flags) { uint64_t val; - DPRINTF("%s MSI-X table read(%04x:%02x:%02x.%d)\n", - memory_region_name(&quirk->mem), vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function); + trace_vfio_rtl8168_window_quirk_read_table( + memory_region_name(&quirk->mem), + vdev->vbasedev.name); if (!(vdev->pdev.cap_present & QEMU_PCI_CAP_MSIX)) { return 0; @@ -1809,18 +1535,18 @@ static uint64_t vfio_rtl8168_window_quirk_read(void *opaque, } } - DPRINTF("%s direct read(%04x:%02x:%02x.%d)\n", - memory_region_name(&quirk->mem), vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function); + trace_vfio_rtl8168_window_quirk_read_direct(memory_region_name(&quirk->mem), + vdev->vbasedev.name); - return vfio_bar_read(&vdev->bars[quirk->data.bar], addr + 0x70, size); + return vfio_region_read(&vdev->bars[quirk->data.bar].region, + addr + 0x70, size); } static void vfio_rtl8168_window_quirk_write(void *opaque, hwaddr addr, uint64_t data, unsigned size) { VFIOQuirk *quirk = opaque; - VFIODevice *vdev = quirk->vdev; + VFIOPCIDevice *vdev = quirk->vdev; switch (addr) { case 4: /* address */ @@ -1828,9 +1554,9 @@ static void vfio_rtl8168_window_quirk_write(void *opaque, hwaddr addr, if (data & 0x10000000U && vdev->pdev.cap_present & QEMU_PCI_CAP_MSIX) { - DPRINTF("%s MSI-X table write(%04x:%02x:%02x.%d)\n", - memory_region_name(&quirk->mem), vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function); + trace_vfio_rtl8168_window_quirk_write_table( + memory_region_name(&quirk->mem), + vdev->vbasedev.name); io_mem_write(&vdev->pdev.msix_table_mmio, (hwaddr)(quirk->data.address_match & 0xfff), @@ -1849,11 +1575,12 @@ static void vfio_rtl8168_window_quirk_write(void *opaque, hwaddr addr, break; } - DPRINTF("%s direct write(%04x:%02x:%02x.%d)\n", - memory_region_name(&quirk->mem), vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function); + trace_vfio_rtl8168_window_quirk_write_direct( + memory_region_name(&quirk->mem), + vdev->vbasedev.name); - vfio_bar_write(&vdev->bars[quirk->data.bar], addr + 0x70, data, size); + vfio_region_write(&vdev->bars[quirk->data.bar].region, + addr + 0x70, data, size); } static const MemoryRegionOps vfio_rtl8168_window_quirk = { @@ -1867,7 +1594,7 @@ static const MemoryRegionOps vfio_rtl8168_window_quirk = { .endianness = DEVICE_LITTLE_ENDIAN, }; -static void vfio_probe_rtl8168_bar2_window_quirk(VFIODevice *vdev, int nr) +static void vfio_probe_rtl8168_bar2_window_quirk(VFIOPCIDevice *vdev, int nr) { PCIDevice *pdev = &vdev->pdev; VFIOQuirk *quirk; @@ -1883,19 +1610,17 @@ static void vfio_probe_rtl8168_bar2_window_quirk(VFIODevice *vdev, int nr) memory_region_init_io(&quirk->mem, OBJECT(vdev), &vfio_rtl8168_window_quirk, quirk, "vfio-rtl8168-window-quirk", 8); - memory_region_add_subregion_overlap(&vdev->bars[nr].mem, + memory_region_add_subregion_overlap(&vdev->bars[nr].region.mem, 0x70, &quirk->mem, 1); QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next); - DPRINTF("Enabled RTL8168 BAR2 window quirk for device %04x:%02x:%02x.%x\n", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function); + trace_vfio_probe_rtl8168_bar2_window_quirk(vdev->vbasedev.name); } /* * Trap the BAR2 MMIO window to config space as well. */ -static void vfio_probe_ati_bar2_4000_quirk(VFIODevice *vdev, int nr) +static void vfio_probe_ati_bar2_4000_quirk(VFIOPCIDevice *vdev, int nr) { PCIDevice *pdev = &vdev->pdev; VFIOQuirk *quirk; @@ -1916,15 +1641,13 @@ static void vfio_probe_ati_bar2_4000_quirk(VFIODevice *vdev, int nr) memory_region_init_io(&quirk->mem, OBJECT(vdev), &vfio_generic_quirk, quirk, "vfio-ati-bar2-4000-quirk", TARGET_PAGE_ALIGN(quirk->data.address_mask + 1)); - memory_region_add_subregion_overlap(&vdev->bars[nr].mem, + memory_region_add_subregion_overlap(&vdev->bars[nr].region.mem, quirk->data.address_match & TARGET_PAGE_MASK, &quirk->mem, 1); QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next); - DPRINTF("Enabled ATI/AMD BAR2 0x4000 quirk for device %04x:%02x:%02x.%x\n", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function); + trace_vfio_probe_ati_bar2_4000_quirk(vdev->vbasedev.name); } /* @@ -1963,14 +1686,14 @@ static uint64_t vfio_nvidia_3d0_quirk_read(void *opaque, hwaddr addr, unsigned size) { VFIOQuirk *quirk = opaque; - VFIODevice *vdev = quirk->vdev; + VFIOPCIDevice *vdev = quirk->vdev; PCIDevice *pdev = &vdev->pdev; uint64_t data = vfio_vga_read(&vdev->vga.region[QEMU_PCI_VGA_IO_HI], addr + quirk->data.base_offset, size); if (quirk->data.flags == NV_3D0_READ && addr == quirk->data.data_offset) { data = vfio_pci_read_config(pdev, quirk->data.address_val, size); - DPRINTF("%s(0x3d0, %d) = 0x%"PRIx64"\n", __func__, size, data); + trace_vfio_nvidia_3d0_quirk_read(size, data); } quirk->data.flags = NV_3D0_NONE; @@ -1982,7 +1705,7 @@ static void vfio_nvidia_3d0_quirk_write(void *opaque, hwaddr addr, uint64_t data, unsigned size) { VFIOQuirk *quirk = opaque; - VFIODevice *vdev = quirk->vdev; + VFIOPCIDevice *vdev = quirk->vdev; PCIDevice *pdev = &vdev->pdev; switch (quirk->data.flags) { @@ -2013,7 +1736,7 @@ static void vfio_nvidia_3d0_quirk_write(void *opaque, hwaddr addr, quirk->data.flags = NV_3D0_NONE; if (addr == quirk->data.data_offset) { vfio_pci_write_config(pdev, quirk->data.address_val, data, size); - DPRINTF("%s(0x3d0, 0x%"PRIx64", %d)\n", __func__, data, size); + trace_vfio_nvidia_3d0_quirk_write(data, size); return; } break; @@ -2029,13 +1752,13 @@ static const MemoryRegionOps vfio_nvidia_3d0_quirk = { .endianness = DEVICE_LITTLE_ENDIAN, }; -static void vfio_vga_probe_nvidia_3d0_quirk(VFIODevice *vdev) +static void vfio_vga_probe_nvidia_3d0_quirk(VFIOPCIDevice *vdev) { PCIDevice *pdev = &vdev->pdev; VFIOQuirk *quirk; if (pci_get_word(pdev->config + PCI_VENDOR_ID) != PCI_VENDOR_ID_NVIDIA || - !vdev->bars[1].size) { + !vdev->bars[1].region.size) { return; } @@ -2057,9 +1780,7 @@ static void vfio_vga_probe_nvidia_3d0_quirk(VFIODevice *vdev) QLIST_INSERT_HEAD(&vdev->vga.region[QEMU_PCI_VGA_IO_HI].quirks, quirk, next); - DPRINTF("Enabled NVIDIA VGA 0x3d0 quirk for device %04x:%02x:%02x.%x\n", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function); + trace_vfio_vga_probe_nvidia_3d0_quirk(vdev->vbasedev.name); } /* @@ -2121,7 +1842,7 @@ static const MemoryRegionOps vfio_nvidia_bar5_window_quirk = { .endianness = DEVICE_LITTLE_ENDIAN, }; -static void vfio_probe_nvidia_bar5_window_quirk(VFIODevice *vdev, int nr) +static void vfio_probe_nvidia_bar5_window_quirk(VFIOPCIDevice *vdev, int nr) { PCIDevice *pdev = &vdev->pdev; VFIOQuirk *quirk; @@ -2143,20 +1864,19 @@ static void vfio_probe_nvidia_bar5_window_quirk(VFIODevice *vdev, int nr) memory_region_init_io(&quirk->mem, OBJECT(vdev), &vfio_nvidia_bar5_window_quirk, quirk, "vfio-nvidia-bar5-window-quirk", 16); - memory_region_add_subregion_overlap(&vdev->bars[nr].mem, 0, &quirk->mem, 1); + memory_region_add_subregion_overlap(&vdev->bars[nr].region.mem, + 0, &quirk->mem, 1); QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next); - DPRINTF("Enabled NVIDIA BAR5 window quirk for device %04x:%02x:%02x.%x\n", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function); + trace_vfio_probe_nvidia_bar5_window_quirk(vdev->vbasedev.name); } static void vfio_nvidia_88000_quirk_write(void *opaque, hwaddr addr, uint64_t data, unsigned size) { VFIOQuirk *quirk = opaque; - VFIODevice *vdev = quirk->vdev; + VFIOPCIDevice *vdev = quirk->vdev; PCIDevice *pdev = &vdev->pdev; hwaddr base = quirk->data.address_match & TARGET_PAGE_MASK; @@ -2170,7 +1890,8 @@ static void vfio_nvidia_88000_quirk_write(void *opaque, hwaddr addr, */ if ((pdev->cap_present & QEMU_PCI_CAP_MSI) && vfio_range_contained(addr, size, pdev->msi_cap, PCI_MSI_FLAGS)) { - vfio_bar_write(&vdev->bars[quirk->data.bar], addr + base, data, size); + vfio_region_write(&vdev->bars[quirk->data.bar].region, + addr + base, data, size); } } @@ -2189,7 +1910,7 @@ static const MemoryRegionOps vfio_nvidia_88000_quirk = { * * Here's offset 0x88000... */ -static void vfio_probe_nvidia_bar0_88000_quirk(VFIODevice *vdev, int nr) +static void vfio_probe_nvidia_bar0_88000_quirk(VFIOPCIDevice *vdev, int nr) { PCIDevice *pdev = &vdev->pdev; VFIOQuirk *quirk; @@ -2213,21 +1934,19 @@ static void vfio_probe_nvidia_bar0_88000_quirk(VFIODevice *vdev, int nr) memory_region_init_io(&quirk->mem, OBJECT(vdev), &vfio_nvidia_88000_quirk, quirk, "vfio-nvidia-bar0-88000-quirk", TARGET_PAGE_ALIGN(quirk->data.address_mask + 1)); - memory_region_add_subregion_overlap(&vdev->bars[nr].mem, + memory_region_add_subregion_overlap(&vdev->bars[nr].region.mem, quirk->data.address_match & TARGET_PAGE_MASK, &quirk->mem, 1); QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next); - DPRINTF("Enabled NVIDIA BAR0 0x88000 quirk for device %04x:%02x:%02x.%x\n", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function); + trace_vfio_probe_nvidia_bar0_88000_quirk(vdev->vbasedev.name); } /* * And here's the same for BAR0 offset 0x1800... */ -static void vfio_probe_nvidia_bar0_1800_quirk(VFIODevice *vdev, int nr) +static void vfio_probe_nvidia_bar0_1800_quirk(VFIOPCIDevice *vdev, int nr) { PCIDevice *pdev = &vdev->pdev; VFIOQuirk *quirk; @@ -2238,8 +1957,9 @@ static void vfio_probe_nvidia_bar0_1800_quirk(VFIODevice *vdev, int nr) } /* Log the chipset ID */ - DPRINTF("Nvidia NV%02x\n", - (unsigned int)(vfio_bar_read(&vdev->bars[0], 0, 4) >> 20) & 0xff); + trace_vfio_probe_nvidia_bar0_1800_quirk_id( + (unsigned int)(vfio_region_read(&vdev->bars[0].region, 0, 4) >> 20) + & 0xff); quirk = g_malloc0(sizeof(*quirk)); quirk->vdev = vdev; @@ -2251,15 +1971,13 @@ static void vfio_probe_nvidia_bar0_1800_quirk(VFIODevice *vdev, int nr) memory_region_init_io(&quirk->mem, OBJECT(vdev), &vfio_generic_quirk, quirk, "vfio-nvidia-bar0-1800-quirk", TARGET_PAGE_ALIGN(quirk->data.address_mask + 1)); - memory_region_add_subregion_overlap(&vdev->bars[nr].mem, + memory_region_add_subregion_overlap(&vdev->bars[nr].region.mem, quirk->data.address_match & TARGET_PAGE_MASK, &quirk->mem, 1); QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next); - DPRINTF("Enabled NVIDIA BAR0 0x1800 quirk for device %04x:%02x:%02x.%x\n", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function); + trace_vfio_probe_nvidia_bar0_1800_quirk(vdev->vbasedev.name); } /* @@ -2271,13 +1989,13 @@ static void vfio_probe_nvidia_bar0_1800_quirk(VFIODevice *vdev, int nr) /* * Common quirk probe entry points. */ -static void vfio_vga_quirk_setup(VFIODevice *vdev) +static void vfio_vga_quirk_setup(VFIOPCIDevice *vdev) { vfio_vga_probe_ati_3c3_quirk(vdev); vfio_vga_probe_nvidia_3d0_quirk(vdev); } -static void vfio_vga_quirk_teardown(VFIODevice *vdev) +static void vfio_vga_quirk_teardown(VFIOPCIDevice *vdev) { int i; @@ -2292,7 +2010,7 @@ static void vfio_vga_quirk_teardown(VFIODevice *vdev) } } -static void vfio_bar_quirk_setup(VFIODevice *vdev, int nr) +static void vfio_bar_quirk_setup(VFIOPCIDevice *vdev, int nr) { vfio_probe_ati_bar4_window_quirk(vdev, nr); vfio_probe_ati_bar2_4000_quirk(vdev, nr); @@ -2302,13 +2020,13 @@ static void vfio_bar_quirk_setup(VFIODevice *vdev, int nr) vfio_probe_rtl8168_bar2_window_quirk(vdev, nr); } -static void vfio_bar_quirk_teardown(VFIODevice *vdev, int nr) +static void vfio_bar_quirk_teardown(VFIOPCIDevice *vdev, int nr) { VFIOBAR *bar = &vdev->bars[nr]; while (!QLIST_EMPTY(&bar->quirks)) { VFIOQuirk *quirk = QLIST_FIRST(&bar->quirks); - memory_region_del_subregion(&bar->mem, &quirk->mem); + memory_region_del_subregion(&bar->region.mem, &quirk->mem); object_unparent(OBJECT(&quirk->mem)); QLIST_REMOVE(quirk, next); g_free(quirk); @@ -2320,7 +2038,7 @@ static void vfio_bar_quirk_teardown(VFIODevice *vdev, int nr) */ static uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len) { - VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev); + VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev); uint32_t emu_bits = 0, emu_val = 0, phys_val = 0, val; memcpy(&emu_bits, vdev->emulated_config_bits + addr, len); @@ -2333,7 +2051,8 @@ static uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len) if (~emu_bits & (0xffffffffU >> (32 - len * 8))) { ssize_t ret; - ret = pread(vdev->fd, &phys_val, len, vdev->config_offset + addr); + ret = pread(vdev->vbasedev.fd, &phys_val, len, + vdev->config_offset + addr); if (ret != len) { error_report("%s(%04x:%02x:%02x.%x, 0x%x, 0x%x) failed: %m", __func__, vdev->host.domain, vdev->host.bus, @@ -2345,9 +2064,7 @@ static uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len) val = (emu_val & emu_bits) | (phys_val & ~emu_bits); - DPRINTF("%s(%04x:%02x:%02x.%x, @0x%x, len=0x%x) %x\n", __func__, - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function, addr, len, val); + trace_vfio_pci_read_config(vdev->vbasedev.name, addr, len, val); return val; } @@ -2355,15 +2072,14 @@ static uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len) static void vfio_pci_write_config(PCIDevice *pdev, uint32_t addr, uint32_t val, int len) { - VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev); + VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev); uint32_t val_le = cpu_to_le32(val); - DPRINTF("%s(%04x:%02x:%02x.%x, @0x%x, 0x%x, len=0x%x)\n", __func__, - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function, addr, val, len); + trace_vfio_pci_write_config(vdev->vbasedev.name, addr, val, len); /* Write everything to VFIO, let it filter out what we can't write */ - if (pwrite(vdev->fd, &val_le, len, vdev->config_offset + addr) != len) { + if (pwrite(vdev->vbasedev.fd, &val_le, len, vdev->config_offset + addr) + != len) { error_report("%s(%04x:%02x:%02x.%x, 0x%x, 0x%x, 0x%x) failed: %m", __func__, vdev->host.domain, vdev->host.bus, vdev->host.slot, vdev->host.function, addr, val, len); @@ -2409,310 +2125,9 @@ static void vfio_pci_write_config(PCIDevice *pdev, uint32_t addr, } /* - * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86 - */ -static int vfio_dma_unmap(VFIOContainer *container, - hwaddr iova, ram_addr_t size) -{ - struct vfio_iommu_type1_dma_unmap unmap = { - .argsz = sizeof(unmap), - .flags = 0, - .iova = iova, - .size = size, - }; - - if (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) { - DPRINTF("VFIO_UNMAP_DMA: %d\n", -errno); - return -errno; - } - - return 0; -} - -static int vfio_dma_map(VFIOContainer *container, hwaddr iova, - ram_addr_t size, void *vaddr, bool readonly) -{ - struct vfio_iommu_type1_dma_map map = { - .argsz = sizeof(map), - .flags = VFIO_DMA_MAP_FLAG_READ, - .vaddr = (__u64)(uintptr_t)vaddr, - .iova = iova, - .size = size, - }; - - if (!readonly) { - map.flags |= VFIO_DMA_MAP_FLAG_WRITE; - } - - /* - * Try the mapping, if it fails with EBUSY, unmap the region and try - * again. This shouldn't be necessary, but we sometimes see it in - * the the VGA ROM space. - */ - if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 || - (errno == EBUSY && vfio_dma_unmap(container, iova, size) == 0 && - ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) { - return 0; - } - - DPRINTF("VFIO_MAP_DMA: %d\n", -errno); - return -errno; -} - -static bool vfio_listener_skipped_section(MemoryRegionSection *section) -{ - return (!memory_region_is_ram(section->mr) && - !memory_region_is_iommu(section->mr)) || - /* - * Sizing an enabled 64-bit BAR can cause spurious mappings to - * addresses in the upper part of the 64-bit address space. These - * are never accessed by the CPU and beyond the address width of - * some IOMMU hardware. TODO: VFIO should tell us the IOMMU width. - */ - section->offset_within_address_space & (1ULL << 63); -} - -static void vfio_iommu_map_notify(Notifier *n, void *data) -{ - VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n); - VFIOContainer *container = giommu->container; - IOMMUTLBEntry *iotlb = data; - MemoryRegion *mr; - hwaddr xlat; - hwaddr len = iotlb->addr_mask + 1; - void *vaddr; - int ret; - - DPRINTF("iommu map @ %"HWADDR_PRIx" - %"HWADDR_PRIx"\n", - iotlb->iova, iotlb->iova + iotlb->addr_mask); - - /* - * The IOMMU TLB entry we have just covers translation through - * this IOMMU to its immediate target. We need to translate - * it the rest of the way through to memory. - */ - mr = address_space_translate(&address_space_memory, - iotlb->translated_addr, - &xlat, &len, iotlb->perm & IOMMU_WO); - if (!memory_region_is_ram(mr)) { - DPRINTF("iommu map to non memory area %"HWADDR_PRIx"\n", - xlat); - return; - } - /* - * Translation truncates length to the IOMMU page size, - * check that it did not truncate too much. - */ - if (len & iotlb->addr_mask) { - DPRINTF("iommu has granularity incompatible with target AS\n"); - return; - } - - if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) { - vaddr = memory_region_get_ram_ptr(mr) + xlat; - - ret = vfio_dma_map(container, iotlb->iova, - iotlb->addr_mask + 1, vaddr, - !(iotlb->perm & IOMMU_WO) || mr->readonly); - if (ret) { - error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", " - "0x%"HWADDR_PRIx", %p) = %d (%m)", - container, iotlb->iova, - iotlb->addr_mask + 1, vaddr, ret); - } - } else { - ret = vfio_dma_unmap(container, iotlb->iova, iotlb->addr_mask + 1); - if (ret) { - error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", " - "0x%"HWADDR_PRIx") = %d (%m)", - container, iotlb->iova, - iotlb->addr_mask + 1, ret); - } - } -} - -static void vfio_listener_region_add(MemoryListener *listener, - MemoryRegionSection *section) -{ - VFIOContainer *container = container_of(listener, VFIOContainer, - iommu_data.type1.listener); - hwaddr iova, end; - Int128 llend; - void *vaddr; - int ret; - - if (vfio_listener_skipped_section(section)) { - DPRINTF("SKIPPING region_add %"HWADDR_PRIx" - %"PRIx64"\n", - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(int128_sub(section->size, int128_one()))); - return; - } - - if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) != - (section->offset_within_region & ~TARGET_PAGE_MASK))) { - error_report("%s received unaligned region", __func__); - return; - } - - iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); - llend = int128_make64(section->offset_within_address_space); - llend = int128_add(llend, section->size); - llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK)); - - if (int128_ge(int128_make64(iova), llend)) { - return; - } - - memory_region_ref(section->mr); - - if (memory_region_is_iommu(section->mr)) { - VFIOGuestIOMMU *giommu; - - DPRINTF("region_add [iommu] %"HWADDR_PRIx" - %"HWADDR_PRIx"\n", - iova, int128_get64(int128_sub(llend, int128_one()))); - /* - * FIXME: We should do some checking to see if the - * capabilities of the host VFIO IOMMU are adequate to model - * the guest IOMMU - * - * FIXME: For VFIO iommu types which have KVM acceleration to - * avoid bouncing all map/unmaps through qemu this way, this - * would be the right place to wire that up (tell the KVM - * device emulation the VFIO iommu handles to use). - */ - /* - * This assumes that the guest IOMMU is empty of - * mappings at this point. - * - * One way of doing this is: - * 1. Avoid sharing IOMMUs between emulated devices or different - * IOMMU groups. - * 2. Implement VFIO_IOMMU_ENABLE in the host kernel to fail if - * there are some mappings in IOMMU. - * - * VFIO on SPAPR does that. Other IOMMU models may do that different, - * they must make sure there are no existing mappings or - * loop through existing mappings to map them into VFIO. - */ - giommu = g_malloc0(sizeof(*giommu)); - giommu->iommu = section->mr; - giommu->container = container; - giommu->n.notify = vfio_iommu_map_notify; - QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next); - memory_region_register_iommu_notifier(giommu->iommu, &giommu->n); - - return; - } - - /* Here we assume that memory_region_is_ram(section->mr)==true */ - - end = int128_get64(llend); - vaddr = memory_region_get_ram_ptr(section->mr) + - section->offset_within_region + - (iova - section->offset_within_address_space); - - DPRINTF("region_add [ram] %"HWADDR_PRIx" - %"HWADDR_PRIx" [%p]\n", - iova, end - 1, vaddr); - - ret = vfio_dma_map(container, iova, end - iova, vaddr, section->readonly); - if (ret) { - error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", " - "0x%"HWADDR_PRIx", %p) = %d (%m)", - container, iova, end - iova, vaddr, ret); - - /* - * On the initfn path, store the first error in the container so we - * can gracefully fail. Runtime, there's not much we can do other - * than throw a hardware error. - */ - if (!container->iommu_data.type1.initialized) { - if (!container->iommu_data.type1.error) { - container->iommu_data.type1.error = ret; - } - } else { - hw_error("vfio: DMA mapping failed, unable to continue"); - } - } -} - -static void vfio_listener_region_del(MemoryListener *listener, - MemoryRegionSection *section) -{ - VFIOContainer *container = container_of(listener, VFIOContainer, - iommu_data.type1.listener); - hwaddr iova, end; - int ret; - - if (vfio_listener_skipped_section(section)) { - DPRINTF("SKIPPING region_del %"HWADDR_PRIx" - %"PRIx64"\n", - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(int128_sub(section->size, int128_one()))); - return; - } - - if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) != - (section->offset_within_region & ~TARGET_PAGE_MASK))) { - error_report("%s received unaligned region", __func__); - return; - } - - if (memory_region_is_iommu(section->mr)) { - VFIOGuestIOMMU *giommu; - - QLIST_FOREACH(giommu, &container->giommu_list, giommu_next) { - if (giommu->iommu == section->mr) { - memory_region_unregister_iommu_notifier(&giommu->n); - QLIST_REMOVE(giommu, giommu_next); - g_free(giommu); - break; - } - } - - /* - * FIXME: We assume the one big unmap below is adequate to - * remove any individual page mappings in the IOMMU which - * might have been copied into VFIO. This works for a page table - * based IOMMU where a big unmap flattens a large range of IO-PTEs. - * That may not be true for all IOMMU types. - */ - } - - iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); - end = (section->offset_within_address_space + int128_get64(section->size)) & - TARGET_PAGE_MASK; - - if (iova >= end) { - return; - } - - DPRINTF("region_del %"HWADDR_PRIx" - %"HWADDR_PRIx"\n", - iova, end - 1); - - ret = vfio_dma_unmap(container, iova, end - iova); - memory_region_unref(section->mr); - if (ret) { - error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", " - "0x%"HWADDR_PRIx") = %d (%m)", - container, iova, end - iova, ret); - } -} - -static MemoryListener vfio_memory_listener = { - .region_add = vfio_listener_region_add, - .region_del = vfio_listener_region_del, -}; - -static void vfio_listener_release(VFIOContainer *container) -{ - memory_listener_unregister(&container->iommu_data.type1.listener); -} - -/* * Interrupt setup */ -static void vfio_disable_interrupts(VFIODevice *vdev) +static void vfio_disable_interrupts(VFIOPCIDevice *vdev) { switch (vdev->interrupt) { case VFIO_INT_INTx: @@ -2727,13 +2142,13 @@ static void vfio_disable_interrupts(VFIODevice *vdev) } } -static int vfio_setup_msi(VFIODevice *vdev, int pos) +static int vfio_setup_msi(VFIOPCIDevice *vdev, int pos) { uint16_t ctrl; bool msi_64bit, msi_maskbit; int ret, entries; - if (pread(vdev->fd, &ctrl, sizeof(ctrl), + if (pread(vdev->vbasedev.fd, &ctrl, sizeof(ctrl), vdev->config_offset + pos + PCI_CAP_FLAGS) != sizeof(ctrl)) { return -errno; } @@ -2743,8 +2158,7 @@ static int vfio_setup_msi(VFIODevice *vdev, int pos) msi_maskbit = !!(ctrl & PCI_MSI_FLAGS_MASKBIT); entries = 1 << ((ctrl & PCI_MSI_FLAGS_QMASK) >> 1); - DPRINTF("%04x:%02x:%02x.%x PCI MSI CAP @0x%x\n", vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function, pos); + trace_vfio_setup_msi(vdev->vbasedev.name, pos); ret = msi_init(&vdev->pdev, pos, entries, msi_64bit, msi_maskbit); if (ret < 0) { @@ -2767,28 +2181,29 @@ static int vfio_setup_msi(VFIODevice *vdev, int pos) * need to first look for where the MSI-X table lives. So we * unfortunately split MSI-X setup across two functions. */ -static int vfio_early_setup_msix(VFIODevice *vdev) +static int vfio_early_setup_msix(VFIOPCIDevice *vdev) { uint8_t pos; uint16_t ctrl; uint32_t table, pba; + int fd = vdev->vbasedev.fd; pos = pci_find_capability(&vdev->pdev, PCI_CAP_ID_MSIX); if (!pos) { return 0; } - if (pread(vdev->fd, &ctrl, sizeof(ctrl), + if (pread(fd, &ctrl, sizeof(ctrl), vdev->config_offset + pos + PCI_CAP_FLAGS) != sizeof(ctrl)) { return -errno; } - if (pread(vdev->fd, &table, sizeof(table), + if (pread(fd, &table, sizeof(table), vdev->config_offset + pos + PCI_MSIX_TABLE) != sizeof(table)) { return -errno; } - if (pread(vdev->fd, &pba, sizeof(pba), + if (pread(fd, &pba, sizeof(pba), vdev->config_offset + pos + PCI_MSIX_PBA) != sizeof(pba)) { return -errno; } @@ -2804,23 +2219,22 @@ static int vfio_early_setup_msix(VFIODevice *vdev) vdev->msix->pba_offset = pba & ~PCI_MSIX_FLAGS_BIRMASK; vdev->msix->entries = (ctrl & PCI_MSIX_FLAGS_QSIZE) + 1; - DPRINTF("%04x:%02x:%02x.%x " - "PCI MSI-X CAP @0x%x, BAR %d, offset 0x%x, entries %d\n", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function, pos, vdev->msix->table_bar, - vdev->msix->table_offset, vdev->msix->entries); + trace_vfio_early_setup_msix(vdev->vbasedev.name, pos, + vdev->msix->table_bar, + vdev->msix->table_offset, + vdev->msix->entries); return 0; } -static int vfio_setup_msix(VFIODevice *vdev, int pos) +static int vfio_setup_msix(VFIOPCIDevice *vdev, int pos) { int ret; ret = msix_init(&vdev->pdev, vdev->msix->entries, - &vdev->bars[vdev->msix->table_bar].mem, + &vdev->bars[vdev->msix->table_bar].region.mem, vdev->msix->table_bar, vdev->msix->table_offset, - &vdev->bars[vdev->msix->pba_bar].mem, + &vdev->bars[vdev->msix->pba_bar].region.mem, vdev->msix->pba_bar, vdev->msix->pba_offset, pos); if (ret < 0) { if (ret == -ENOTSUP) { @@ -2833,99 +2247,61 @@ static int vfio_setup_msix(VFIODevice *vdev, int pos) return 0; } -static void vfio_teardown_msi(VFIODevice *vdev) +static void vfio_teardown_msi(VFIOPCIDevice *vdev) { msi_uninit(&vdev->pdev); if (vdev->msix) { - msix_uninit(&vdev->pdev, &vdev->bars[vdev->msix->table_bar].mem, - &vdev->bars[vdev->msix->pba_bar].mem); + msix_uninit(&vdev->pdev, + &vdev->bars[vdev->msix->table_bar].region.mem, + &vdev->bars[vdev->msix->pba_bar].region.mem); } } /* * Resource setup */ -static void vfio_mmap_set_enabled(VFIODevice *vdev, bool enabled) +static void vfio_mmap_set_enabled(VFIOPCIDevice *vdev, bool enabled) { int i; for (i = 0; i < PCI_ROM_SLOT; i++) { VFIOBAR *bar = &vdev->bars[i]; - if (!bar->size) { + if (!bar->region.size) { continue; } - memory_region_set_enabled(&bar->mmap_mem, enabled); + memory_region_set_enabled(&bar->region.mmap_mem, enabled); if (vdev->msix && vdev->msix->table_bar == i) { memory_region_set_enabled(&vdev->msix->mmap_mem, enabled); } } } -static void vfio_unmap_bar(VFIODevice *vdev, int nr) +static void vfio_unmap_bar(VFIOPCIDevice *vdev, int nr) { VFIOBAR *bar = &vdev->bars[nr]; - if (!bar->size) { + if (!bar->region.size) { return; } vfio_bar_quirk_teardown(vdev, nr); - memory_region_del_subregion(&bar->mem, &bar->mmap_mem); - munmap(bar->mmap, memory_region_size(&bar->mmap_mem)); + memory_region_del_subregion(&bar->region.mem, &bar->region.mmap_mem); + munmap(bar->region.mmap, memory_region_size(&bar->region.mmap_mem)); if (vdev->msix && vdev->msix->table_bar == nr) { - memory_region_del_subregion(&bar->mem, &vdev->msix->mmap_mem); + memory_region_del_subregion(&bar->region.mem, &vdev->msix->mmap_mem); munmap(vdev->msix->mmap, memory_region_size(&vdev->msix->mmap_mem)); } } -static int vfio_mmap_bar(VFIODevice *vdev, VFIOBAR *bar, - MemoryRegion *mem, MemoryRegion *submem, - void **map, size_t size, off_t offset, - const char *name) -{ - int ret = 0; - - if (VFIO_ALLOW_MMAP && size && bar->flags & VFIO_REGION_INFO_FLAG_MMAP) { - int prot = 0; - - if (bar->flags & VFIO_REGION_INFO_FLAG_READ) { - prot |= PROT_READ; - } - - if (bar->flags & VFIO_REGION_INFO_FLAG_WRITE) { - prot |= PROT_WRITE; - } - - *map = mmap(NULL, size, prot, MAP_SHARED, - bar->fd, bar->fd_offset + offset); - if (*map == MAP_FAILED) { - *map = NULL; - ret = -errno; - goto empty_region; - } - - memory_region_init_ram_ptr(submem, OBJECT(vdev), name, size, *map); - memory_region_set_skip_dump(submem); - } else { -empty_region: - /* Create a zero sized sub-region to make cleanup easy. */ - memory_region_init(submem, OBJECT(vdev), name, 0); - } - - memory_region_add_subregion(mem, offset, submem); - - return ret; -} - -static void vfio_map_bar(VFIODevice *vdev, int nr) +static void vfio_map_bar(VFIOPCIDevice *vdev, int nr) { VFIOBAR *bar = &vdev->bars[nr]; - unsigned size = bar->size; + unsigned size = bar->region.size; char name[64]; uint32_t pci_bar; uint8_t type; @@ -2941,7 +2317,7 @@ static void vfio_map_bar(VFIODevice *vdev, int nr) vdev->host.function, nr); /* Determine what type of BAR this is for registration */ - ret = pread(vdev->fd, &pci_bar, sizeof(pci_bar), + ret = pread(vdev->vbasedev.fd, &pci_bar, sizeof(pci_bar), vdev->config_offset + PCI_BASE_ADDRESS_0 + (4 * nr)); if (ret != sizeof(pci_bar)) { error_report("vfio: Failed to read BAR %d (%m)", nr); @@ -2955,9 +2331,9 @@ static void vfio_map_bar(VFIODevice *vdev, int nr) ~PCI_BASE_ADDRESS_MEM_MASK); /* A "slow" read/write mapping underlies all BARs */ - memory_region_init_io(&bar->mem, OBJECT(vdev), &vfio_bar_ops, + memory_region_init_io(&bar->region.mem, OBJECT(vdev), &vfio_region_ops, bar, name, size); - pci_register_bar(&vdev->pdev, nr, type, &bar->mem); + pci_register_bar(&vdev->pdev, nr, type, &bar->region.mem); /* * We can't mmap areas overlapping the MSIX vector table, so we @@ -2968,8 +2344,9 @@ static void vfio_map_bar(VFIODevice *vdev, int nr) } strncat(name, " mmap", sizeof(name) - strlen(name) - 1); - if (vfio_mmap_bar(vdev, bar, &bar->mem, - &bar->mmap_mem, &bar->mmap, size, 0, name)) { + if (vfio_mmap_region(OBJECT(vdev), &bar->region, &bar->region.mem, + &bar->region.mmap_mem, &bar->region.mmap, + size, 0, name)) { error_report("%s unsupported. Performance may be slow", name); } @@ -2979,10 +2356,11 @@ static void vfio_map_bar(VFIODevice *vdev, int nr) start = HOST_PAGE_ALIGN(vdev->msix->table_offset + (vdev->msix->entries * PCI_MSIX_ENTRY_SIZE)); - size = start < bar->size ? bar->size - start : 0; + size = start < bar->region.size ? bar->region.size - start : 0; strncat(name, " msix-hi", sizeof(name) - strlen(name) - 1); /* VFIOMSIXInfo contains another MemoryRegion for this mapping */ - if (vfio_mmap_bar(vdev, bar, &bar->mem, &vdev->msix->mmap_mem, + if (vfio_mmap_region(OBJECT(vdev), &bar->region, &bar->region.mem, + &vdev->msix->mmap_mem, &vdev->msix->mmap, size, start, name)) { error_report("%s unsupported. Performance may be slow", name); } @@ -2991,7 +2369,7 @@ static void vfio_map_bar(VFIODevice *vdev, int nr) vfio_bar_quirk_setup(vdev, nr); } -static void vfio_map_bars(VFIODevice *vdev) +static void vfio_map_bars(VFIOPCIDevice *vdev) { int i; @@ -3023,7 +2401,7 @@ static void vfio_map_bars(VFIODevice *vdev) } } -static void vfio_unmap_bars(VFIODevice *vdev) +static void vfio_unmap_bars(VFIOPCIDevice *vdev) { int i; @@ -3059,7 +2437,7 @@ static void vfio_set_word_bits(uint8_t *buf, uint16_t val, uint16_t mask) pci_set_word(buf, (pci_get_word(buf) & ~mask) | val); } -static void vfio_add_emulated_word(VFIODevice *vdev, int pos, +static void vfio_add_emulated_word(VFIOPCIDevice *vdev, int pos, uint16_t val, uint16_t mask) { vfio_set_word_bits(vdev->pdev.config + pos, val, mask); @@ -3072,7 +2450,7 @@ static void vfio_set_long_bits(uint8_t *buf, uint32_t val, uint32_t mask) pci_set_long(buf, (pci_get_long(buf) & ~mask) | val); } -static void vfio_add_emulated_long(VFIODevice *vdev, int pos, +static void vfio_add_emulated_long(VFIOPCIDevice *vdev, int pos, uint32_t val, uint32_t mask) { vfio_set_long_bits(vdev->pdev.config + pos, val, mask); @@ -3080,7 +2458,7 @@ static void vfio_add_emulated_long(VFIODevice *vdev, int pos, vfio_set_long_bits(vdev->emulated_config_bits + pos, mask, mask); } -static int vfio_setup_pcie_cap(VFIODevice *vdev, int pos, uint8_t size) +static int vfio_setup_pcie_cap(VFIOPCIDevice *vdev, int pos, uint8_t size) { uint16_t flags; uint8_t type; @@ -3172,43 +2550,37 @@ static int vfio_setup_pcie_cap(VFIODevice *vdev, int pos, uint8_t size) return pos; } -static void vfio_check_pcie_flr(VFIODevice *vdev, uint8_t pos) +static void vfio_check_pcie_flr(VFIOPCIDevice *vdev, uint8_t pos) { uint32_t cap = pci_get_long(vdev->pdev.config + pos + PCI_EXP_DEVCAP); if (cap & PCI_EXP_DEVCAP_FLR) { - DPRINTF("%04x:%02x:%02x.%x Supports FLR via PCIe cap\n", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function); + trace_vfio_check_pcie_flr(vdev->vbasedev.name); vdev->has_flr = true; } } -static void vfio_check_pm_reset(VFIODevice *vdev, uint8_t pos) +static void vfio_check_pm_reset(VFIOPCIDevice *vdev, uint8_t pos) { uint16_t csr = pci_get_word(vdev->pdev.config + pos + PCI_PM_CTRL); if (!(csr & PCI_PM_CTRL_NO_SOFT_RESET)) { - DPRINTF("%04x:%02x:%02x.%x Supports PM reset\n", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function); + trace_vfio_check_pm_reset(vdev->vbasedev.name); vdev->has_pm_reset = true; } } -static void vfio_check_af_flr(VFIODevice *vdev, uint8_t pos) +static void vfio_check_af_flr(VFIOPCIDevice *vdev, uint8_t pos) { uint8_t cap = pci_get_byte(vdev->pdev.config + pos + PCI_AF_CAP); if ((cap & PCI_AF_CAP_TP) && (cap & PCI_AF_CAP_FLR)) { - DPRINTF("%04x:%02x:%02x.%x Supports FLR via AF cap\n", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function); + trace_vfio_check_af_flr(vdev->vbasedev.name); vdev->has_flr = true; } } -static int vfio_add_std_cap(VFIODevice *vdev, uint8_t pos) +static int vfio_add_std_cap(VFIOPCIDevice *vdev, uint8_t pos) { PCIDevice *pdev = &vdev->pdev; uint8_t cap_id, next, size; @@ -3283,7 +2655,7 @@ static int vfio_add_std_cap(VFIODevice *vdev, uint8_t pos) return 0; } -static int vfio_add_capabilities(VFIODevice *vdev) +static int vfio_add_capabilities(VFIOPCIDevice *vdev) { PCIDevice *pdev = &vdev->pdev; @@ -3295,7 +2667,7 @@ static int vfio_add_capabilities(VFIODevice *vdev) return vfio_add_std_cap(vdev, pdev->config[PCI_CAPABILITY_LIST]); } -static void vfio_pci_pre_reset(VFIODevice *vdev) +static void vfio_pci_pre_reset(VFIOPCIDevice *vdev) { PCIDevice *pdev = &vdev->pdev; uint16_t cmd; @@ -3332,7 +2704,7 @@ static void vfio_pci_pre_reset(VFIODevice *vdev) vfio_pci_write_config(pdev, PCI_COMMAND, cmd, 2); } -static void vfio_pci_post_reset(VFIODevice *vdev) +static void vfio_pci_post_reset(VFIOPCIDevice *vdev) { vfio_enable_intx(vdev); } @@ -3344,7 +2716,7 @@ static bool vfio_pci_host_match(PCIHostDeviceAddress *host1, host1->slot == host2->slot && host1->function == host2->function); } -static int vfio_pci_hot_reset(VFIODevice *vdev, bool single) +static int vfio_pci_hot_reset(VFIOPCIDevice *vdev, bool single) { VFIOGroup *group; struct vfio_pci_hot_reset_info *info; @@ -3354,17 +2726,15 @@ static int vfio_pci_hot_reset(VFIODevice *vdev, bool single) int ret, i, count; bool multi = false; - DPRINTF("%s(%04x:%02x:%02x.%x) %s\n", __func__, vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function, - single ? "one" : "multi"); + trace_vfio_pci_hot_reset(vdev->vbasedev.name, single ? "one" : "multi"); vfio_pci_pre_reset(vdev); - vdev->needs_reset = false; + vdev->vbasedev.needs_reset = false; info = g_malloc0(sizeof(*info)); info->argsz = sizeof(*info); - ret = ioctl(vdev->fd, VFIO_DEVICE_GET_PCI_HOT_RESET_INFO, info); + ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_PCI_HOT_RESET_INFO, info); if (ret && errno != ENOSPC) { ret = -errno; if (!vdev->has_pm_reset) { @@ -3380,35 +2750,34 @@ static int vfio_pci_hot_reset(VFIODevice *vdev, bool single) info->argsz = sizeof(*info) + (count * sizeof(*devices)); devices = &info->devices[0]; - ret = ioctl(vdev->fd, VFIO_DEVICE_GET_PCI_HOT_RESET_INFO, info); + ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_PCI_HOT_RESET_INFO, info); if (ret) { ret = -errno; error_report("vfio: hot reset info failed: %m"); goto out_single; } - DPRINTF("%04x:%02x:%02x.%x: hot reset dependent devices:\n", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function); + trace_vfio_pci_hot_reset_has_dep_devices(vdev->vbasedev.name); /* Verify that we have all the groups required */ for (i = 0; i < info->count; i++) { PCIHostDeviceAddress host; - VFIODevice *tmp; + VFIOPCIDevice *tmp; + VFIODevice *vbasedev_iter; host.domain = devices[i].segment; host.bus = devices[i].bus; host.slot = PCI_SLOT(devices[i].devfn); host.function = PCI_FUNC(devices[i].devfn); - DPRINTF("\t%04x:%02x:%02x.%x group %d\n", host.domain, + trace_vfio_pci_hot_reset_dep_devices(host.domain, host.bus, host.slot, host.function, devices[i].group_id); if (vfio_pci_host_match(&host, &vdev->host)) { continue; } - QLIST_FOREACH(group, &group_list, next) { + QLIST_FOREACH(group, &vfio_group_list, next) { if (group->groupid == devices[i].group_id) { break; } @@ -3416,27 +2785,27 @@ static int vfio_pci_hot_reset(VFIODevice *vdev, bool single) if (!group) { if (!vdev->has_pm_reset) { - error_report("vfio: Cannot reset device %04x:%02x:%02x.%x, " + error_report("vfio: Cannot reset device %s, " "depends on group %d which is not owned.", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function, devices[i].group_id); + vdev->vbasedev.name, devices[i].group_id); } ret = -EPERM; goto out; } /* Prep dependent devices for reset and clear our marker. */ - QLIST_FOREACH(tmp, &group->device_list, next) { + QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { + if (vbasedev_iter->type != VFIO_DEVICE_TYPE_PCI) { + continue; + } + tmp = container_of(vbasedev_iter, VFIOPCIDevice, vbasedev); if (vfio_pci_host_match(&host, &tmp->host)) { if (single) { - DPRINTF("vfio: found another in-use device " - "%04x:%02x:%02x.%x\n", host.domain, host.bus, - host.slot, host.function); ret = -EINVAL; goto out_single; } vfio_pci_pre_reset(tmp); - tmp->needs_reset = false; + tmp->vbasedev.needs_reset = false; multi = true; break; } @@ -3444,14 +2813,13 @@ static int vfio_pci_hot_reset(VFIODevice *vdev, bool single) } if (!single && !multi) { - DPRINTF("vfio: No other in-use devices for multi hot reset\n"); ret = -EINVAL; goto out_single; } /* Determine how many group fds need to be passed */ count = 0; - QLIST_FOREACH(group, &group_list, next) { + QLIST_FOREACH(group, &vfio_group_list, next) { for (i = 0; i < info->count; i++) { if (group->groupid == devices[i].group_id) { count++; @@ -3465,7 +2833,7 @@ static int vfio_pci_hot_reset(VFIODevice *vdev, bool single) fds = &reset->group_fds[0]; /* Fill in group fds */ - QLIST_FOREACH(group, &group_list, next) { + QLIST_FOREACH(group, &vfio_group_list, next) { for (i = 0; i < info->count; i++) { if (group->groupid == devices[i].group_id) { fds[reset->count++] = group->fd; @@ -3475,18 +2843,18 @@ static int vfio_pci_hot_reset(VFIODevice *vdev, bool single) } /* Bus reset! */ - ret = ioctl(vdev->fd, VFIO_DEVICE_PCI_HOT_RESET, reset); + ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_PCI_HOT_RESET, reset); g_free(reset); - DPRINTF("%04x:%02x:%02x.%x hot reset: %s\n", vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function, - ret ? "%m" : "Success"); + trace_vfio_pci_hot_reset_result(vdev->vbasedev.name, + ret ? "%m" : "Success"); out: /* Re-enable INTx on affected devices */ for (i = 0; i < info->count; i++) { PCIHostDeviceAddress host; - VFIODevice *tmp; + VFIOPCIDevice *tmp; + VFIODevice *vbasedev_iter; host.domain = devices[i].segment; host.bus = devices[i].bus; @@ -3497,7 +2865,7 @@ out: continue; } - QLIST_FOREACH(group, &group_list, next) { + QLIST_FOREACH(group, &vfio_group_list, next) { if (group->groupid == devices[i].group_id) { break; } @@ -3507,7 +2875,11 @@ out: break; } - QLIST_FOREACH(tmp, &group->device_list, next) { + QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { + if (vbasedev_iter->type != VFIO_DEVICE_TYPE_PCI) { + continue; + } + tmp = container_of(vbasedev_iter, VFIOPCIDevice, vbasedev); if (vfio_pci_host_match(&host, &tmp->host)) { vfio_pci_post_reset(tmp); break; @@ -3536,439 +2908,90 @@ out_single: * _one() will only do a hot reset for the one in-use devices case, calling * _multi() will do nothing if a _one() would have been sufficient. */ -static int vfio_pci_hot_reset_one(VFIODevice *vdev) +static int vfio_pci_hot_reset_one(VFIOPCIDevice *vdev) { return vfio_pci_hot_reset(vdev, true); } -static int vfio_pci_hot_reset_multi(VFIODevice *vdev) +static int vfio_pci_hot_reset_multi(VFIODevice *vbasedev) { + VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev); return vfio_pci_hot_reset(vdev, false); } -static void vfio_pci_reset_handler(void *opaque) -{ - VFIOGroup *group; - VFIODevice *vdev; - - QLIST_FOREACH(group, &group_list, next) { - QLIST_FOREACH(vdev, &group->device_list, next) { - if (!vdev->reset_works || (!vdev->has_flr && vdev->has_pm_reset)) { - vdev->needs_reset = true; - } - } - } - - QLIST_FOREACH(group, &group_list, next) { - QLIST_FOREACH(vdev, &group->device_list, next) { - if (vdev->needs_reset) { - vfio_pci_hot_reset_multi(vdev); - } - } - } -} - -static void vfio_kvm_device_add_group(VFIOGroup *group) -{ -#ifdef CONFIG_KVM - struct kvm_device_attr attr = { - .group = KVM_DEV_VFIO_GROUP, - .attr = KVM_DEV_VFIO_GROUP_ADD, - .addr = (uint64_t)(unsigned long)&group->fd, - }; - - if (!kvm_enabled()) { - return; - } - - if (vfio_kvm_device_fd < 0) { - struct kvm_create_device cd = { - .type = KVM_DEV_TYPE_VFIO, - }; - - if (kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd)) { - DPRINTF("KVM_CREATE_DEVICE: %m\n"); - return; - } - - vfio_kvm_device_fd = cd.fd; - } - - if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { - error_report("Failed to add group %d to KVM VFIO device: %m", - group->groupid); - } -#endif -} - -static void vfio_kvm_device_del_group(VFIOGroup *group) -{ -#ifdef CONFIG_KVM - struct kvm_device_attr attr = { - .group = KVM_DEV_VFIO_GROUP, - .attr = KVM_DEV_VFIO_GROUP_DEL, - .addr = (uint64_t)(unsigned long)&group->fd, - }; - - if (vfio_kvm_device_fd < 0) { - return; - } - - if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { - error_report("Failed to remove group %d from KVM VFIO device: %m", - group->groupid); - } -#endif -} - -static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) -{ - VFIOAddressSpace *space; - - QLIST_FOREACH(space, &vfio_address_spaces, list) { - if (space->as == as) { - return space; - } - } - - /* No suitable VFIOAddressSpace, create a new one */ - space = g_malloc0(sizeof(*space)); - space->as = as; - QLIST_INIT(&space->containers); - - QLIST_INSERT_HEAD(&vfio_address_spaces, space, list); - - return space; -} - -static void vfio_put_address_space(VFIOAddressSpace *space) -{ - if (QLIST_EMPTY(&space->containers)) { - QLIST_REMOVE(space, list); - g_free(space); - } -} - -static int vfio_connect_container(VFIOGroup *group, AddressSpace *as) -{ - VFIOContainer *container; - int ret, fd; - VFIOAddressSpace *space; - - space = vfio_get_address_space(as); - - QLIST_FOREACH(container, &space->containers, next) { - if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) { - group->container = container; - QLIST_INSERT_HEAD(&container->group_list, group, container_next); - return 0; - } - } - - fd = qemu_open("/dev/vfio/vfio", O_RDWR); - if (fd < 0) { - error_report("vfio: failed to open /dev/vfio/vfio: %m"); - ret = -errno; - goto put_space_exit; - } - - ret = ioctl(fd, VFIO_GET_API_VERSION); - if (ret != VFIO_API_VERSION) { - error_report("vfio: supported vfio version: %d, " - "reported version: %d", VFIO_API_VERSION, ret); - ret = -EINVAL; - goto close_fd_exit; - } - - container = g_malloc0(sizeof(*container)); - container->space = space; - container->fd = fd; - - if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1_IOMMU)) { - ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd); - if (ret) { - error_report("vfio: failed to set group container: %m"); - ret = -errno; - goto free_container_exit; - } - - ret = ioctl(fd, VFIO_SET_IOMMU, VFIO_TYPE1_IOMMU); - if (ret) { - error_report("vfio: failed to set iommu for container: %m"); - ret = -errno; - goto free_container_exit; - } - - container->iommu_data.type1.listener = vfio_memory_listener; - container->iommu_data.release = vfio_listener_release; - - memory_listener_register(&container->iommu_data.type1.listener, - &address_space_memory); - - if (container->iommu_data.type1.error) { - ret = container->iommu_data.type1.error; - error_report("vfio: memory listener initialization failed for container"); - goto listener_release_exit; - } - - container->iommu_data.type1.initialized = true; - - } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU)) { - ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd); - if (ret) { - error_report("vfio: failed to set group container: %m"); - ret = -errno; - goto free_container_exit; - } - - ret = ioctl(fd, VFIO_SET_IOMMU, VFIO_SPAPR_TCE_IOMMU); - if (ret) { - error_report("vfio: failed to set iommu for container: %m"); - ret = -errno; - goto free_container_exit; - } - - /* - * The host kernel code implementing VFIO_IOMMU_DISABLE is called - * when container fd is closed so we do not call it explicitly - * in this file. - */ - ret = ioctl(fd, VFIO_IOMMU_ENABLE); - if (ret) { - error_report("vfio: failed to enable container: %m"); - ret = -errno; - goto free_container_exit; - } - - container->iommu_data.type1.listener = vfio_memory_listener; - container->iommu_data.release = vfio_listener_release; - - memory_listener_register(&container->iommu_data.type1.listener, - container->space->as); - - } else { - error_report("vfio: No available IOMMU models"); - ret = -EINVAL; - goto free_container_exit; - } - - QLIST_INIT(&container->group_list); - QLIST_INSERT_HEAD(&space->containers, container, next); - - group->container = container; - QLIST_INSERT_HEAD(&container->group_list, group, container_next); - - return 0; - -listener_release_exit: - vfio_listener_release(container); - -free_container_exit: - g_free(container); - -close_fd_exit: - close(fd); - -put_space_exit: - vfio_put_address_space(space); - - return ret; -} - -static void vfio_disconnect_container(VFIOGroup *group) +static void vfio_pci_compute_needs_reset(VFIODevice *vbasedev) { - VFIOContainer *container = group->container; - - if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, &container->fd)) { - error_report("vfio: error disconnecting group %d from container", - group->groupid); - } - - QLIST_REMOVE(group, container_next); - group->container = NULL; - - if (QLIST_EMPTY(&container->group_list)) { - VFIOAddressSpace *space = container->space; - - if (container->iommu_data.release) { - container->iommu_data.release(container); - } - QLIST_REMOVE(container, next); - DPRINTF("vfio_disconnect_container: close container->fd\n"); - close(container->fd); - g_free(container); - - vfio_put_address_space(space); + VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev); + if (!vbasedev->reset_works || (!vdev->has_flr && vdev->has_pm_reset)) { + vbasedev->needs_reset = true; } } -static VFIOGroup *vfio_get_group(int groupid, AddressSpace *as) -{ - VFIOGroup *group; - char path[32]; - struct vfio_group_status status = { .argsz = sizeof(status) }; - - QLIST_FOREACH(group, &group_list, next) { - if (group->groupid == groupid) { - /* Found it. Now is it already in the right context? */ - if (group->container->space->as == as) { - return group; - } else { - error_report("vfio: group %d used in multiple address spaces", - group->groupid); - return NULL; - } - } - } - - group = g_malloc0(sizeof(*group)); - - snprintf(path, sizeof(path), "/dev/vfio/%d", groupid); - group->fd = qemu_open(path, O_RDWR); - if (group->fd < 0) { - error_report("vfio: error opening %s: %m", path); - goto free_group_exit; - } - - if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &status)) { - error_report("vfio: error getting group status: %m"); - goto close_fd_exit; - } - - if (!(status.flags & VFIO_GROUP_FLAGS_VIABLE)) { - error_report("vfio: error, group %d is not viable, please ensure " - "all devices within the iommu_group are bound to their " - "vfio bus driver.", groupid); - goto close_fd_exit; - } - - group->groupid = groupid; - QLIST_INIT(&group->device_list); - - if (vfio_connect_container(group, as)) { - error_report("vfio: failed to setup container for group %d", groupid); - goto close_fd_exit; - } - - if (QLIST_EMPTY(&group_list)) { - qemu_register_reset(vfio_pci_reset_handler, NULL); - } - - QLIST_INSERT_HEAD(&group_list, group, next); - - vfio_kvm_device_add_group(group); - - return group; - -close_fd_exit: - close(group->fd); - -free_group_exit: - g_free(group); - - return NULL; -} - -static void vfio_put_group(VFIOGroup *group) -{ - if (!QLIST_EMPTY(&group->device_list)) { - return; - } - - vfio_kvm_device_del_group(group); - vfio_disconnect_container(group); - QLIST_REMOVE(group, next); - DPRINTF("vfio_put_group: close group->fd\n"); - close(group->fd); - g_free(group); - - if (QLIST_EMPTY(&group_list)) { - qemu_unregister_reset(vfio_pci_reset_handler, NULL); - } -} +static VFIODeviceOps vfio_pci_ops = { + .vfio_compute_needs_reset = vfio_pci_compute_needs_reset, + .vfio_hot_reset_multi = vfio_pci_hot_reset_multi, + .vfio_eoi = vfio_eoi, + .vfio_populate_device = vfio_populate_device, +}; -static int vfio_get_device(VFIOGroup *group, const char *name, VFIODevice *vdev) +static int vfio_populate_device(VFIODevice *vbasedev) { - struct vfio_device_info dev_info = { .argsz = sizeof(dev_info) }; + VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev); struct vfio_region_info reg_info = { .argsz = sizeof(reg_info) }; struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info) }; - int ret, i; - - ret = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name); - if (ret < 0) { - error_report("vfio: error getting device %s from group %d: %m", - name, group->groupid); - error_printf("Verify all devices in group %d are bound to vfio-pci " - "or pci-stub and not already in use\n", group->groupid); - return ret; - } - - vdev->fd = ret; - vdev->group = group; - QLIST_INSERT_HEAD(&group->device_list, vdev, next); + int i, ret = -1; /* Sanity check device */ - ret = ioctl(vdev->fd, VFIO_DEVICE_GET_INFO, &dev_info); - if (ret) { - error_report("vfio: error getting device info: %m"); - goto error; - } - - DPRINTF("Device %s flags: %u, regions: %u, irgs: %u\n", name, - dev_info.flags, dev_info.num_regions, dev_info.num_irqs); - - if (!(dev_info.flags & VFIO_DEVICE_FLAGS_PCI)) { + if (!(vbasedev->flags & VFIO_DEVICE_FLAGS_PCI)) { error_report("vfio: Um, this isn't a PCI device"); goto error; } - vdev->reset_works = !!(dev_info.flags & VFIO_DEVICE_FLAGS_RESET); - - if (dev_info.num_regions < VFIO_PCI_CONFIG_REGION_INDEX + 1) { + if (vbasedev->num_regions < VFIO_PCI_CONFIG_REGION_INDEX + 1) { error_report("vfio: unexpected number of io regions %u", - dev_info.num_regions); + vbasedev->num_regions); goto error; } - if (dev_info.num_irqs < VFIO_PCI_MSIX_IRQ_INDEX + 1) { - error_report("vfio: unexpected number of irqs %u", dev_info.num_irqs); + if (vbasedev->num_irqs < VFIO_PCI_MSIX_IRQ_INDEX + 1) { + error_report("vfio: unexpected number of irqs %u", vbasedev->num_irqs); goto error; } for (i = VFIO_PCI_BAR0_REGION_INDEX; i < VFIO_PCI_ROM_REGION_INDEX; i++) { reg_info.index = i; - ret = ioctl(vdev->fd, VFIO_DEVICE_GET_REGION_INFO, ®_info); + ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, ®_info); if (ret) { error_report("vfio: Error getting region %d info: %m", i); goto error; } - DPRINTF("Device %s region %d:\n", name, i); - DPRINTF(" size: 0x%lx, offset: 0x%lx, flags: 0x%lx\n", - (unsigned long)reg_info.size, (unsigned long)reg_info.offset, - (unsigned long)reg_info.flags); + trace_vfio_populate_device_region(vbasedev->name, i, + (unsigned long)reg_info.size, + (unsigned long)reg_info.offset, + (unsigned long)reg_info.flags); - vdev->bars[i].flags = reg_info.flags; - vdev->bars[i].size = reg_info.size; - vdev->bars[i].fd_offset = reg_info.offset; - vdev->bars[i].fd = vdev->fd; - vdev->bars[i].nr = i; + vdev->bars[i].region.vbasedev = vbasedev; + vdev->bars[i].region.flags = reg_info.flags; + vdev->bars[i].region.size = reg_info.size; + vdev->bars[i].region.fd_offset = reg_info.offset; + vdev->bars[i].region.nr = i; QLIST_INIT(&vdev->bars[i].quirks); } reg_info.index = VFIO_PCI_CONFIG_REGION_INDEX; - ret = ioctl(vdev->fd, VFIO_DEVICE_GET_REGION_INFO, ®_info); + ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_REGION_INFO, ®_info); if (ret) { error_report("vfio: Error getting config info: %m"); goto error; } - DPRINTF("Device %s config:\n", name); - DPRINTF(" size: 0x%lx, offset: 0x%lx, flags: 0x%lx\n", - (unsigned long)reg_info.size, (unsigned long)reg_info.offset, - (unsigned long)reg_info.flags); + trace_vfio_populate_device_config(vdev->vbasedev.name, + (unsigned long)reg_info.size, + (unsigned long)reg_info.offset, + (unsigned long)reg_info.flags); vdev->config_size = reg_info.size; if (vdev->config_size == PCI_CONFIG_SPACE_SIZE) { @@ -3977,13 +3000,13 @@ static int vfio_get_device(VFIOGroup *group, const char *name, VFIODevice *vdev) vdev->config_offset = reg_info.offset; if ((vdev->features & VFIO_FEATURE_ENABLE_VGA) && - dev_info.num_regions > VFIO_PCI_VGA_REGION_INDEX) { + vbasedev->num_regions > VFIO_PCI_VGA_REGION_INDEX) { struct vfio_region_info vga_info = { .argsz = sizeof(vga_info), .index = VFIO_PCI_VGA_REGION_INDEX, }; - ret = ioctl(vdev->fd, VFIO_DEVICE_GET_REGION_INFO, &vga_info); + ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_REGION_INFO, &vga_info); if (ret) { error_report( "vfio: Device does not support requested feature x-vga"); @@ -4000,7 +3023,7 @@ static int vfio_get_device(VFIOGroup *group, const char *name, VFIODevice *vdev) } vdev->vga.fd_offset = vga_info.offset; - vdev->vga.fd = vdev->fd; + vdev->vga.fd = vdev->vbasedev.fd; vdev->vga.region[QEMU_PCI_VGA_MEM].offset = QEMU_PCI_VGA_MEM_BASE; vdev->vga.region[QEMU_PCI_VGA_MEM].nr = QEMU_PCI_VGA_MEM; @@ -4018,44 +3041,36 @@ static int vfio_get_device(VFIOGroup *group, const char *name, VFIODevice *vdev) } irq_info.index = VFIO_PCI_ERR_IRQ_INDEX; - ret = ioctl(vdev->fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info); + ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info); if (ret) { /* This can fail for an old kernel or legacy PCI dev */ - DPRINTF("VFIO_DEVICE_GET_IRQ_INFO failure: %m\n"); + trace_vfio_populate_device_get_irq_info_failure(); ret = 0; } else if (irq_info.count == 1) { vdev->pci_aer = true; } else { - error_report("vfio: %04x:%02x:%02x.%x " + error_report("vfio: %s " "Could not enable error recovery for the device", - vdev->host.domain, vdev->host.bus, vdev->host.slot, - vdev->host.function); + vbasedev->name); } error: - if (ret) { - QLIST_REMOVE(vdev, next); - vdev->group = NULL; - close(vdev->fd); - } return ret; } -static void vfio_put_device(VFIODevice *vdev) +static void vfio_put_device(VFIOPCIDevice *vdev) { - QLIST_REMOVE(vdev, next); - vdev->group = NULL; - DPRINTF("vfio_put_device: close vdev->fd\n"); - close(vdev->fd); + g_free(vdev->vbasedev.name); if (vdev->msix) { g_free(vdev->msix); vdev->msix = NULL; } + vfio_put_base_device(&vdev->vbasedev); } static void vfio_err_notifier_handler(void *opaque) { - VFIODevice *vdev = opaque; + VFIOPCIDevice *vdev = opaque; if (!event_notifier_test_and_clear(&vdev->err_notifier)) { return; @@ -4084,7 +3099,7 @@ static void vfio_err_notifier_handler(void *opaque) * and continue after disabling error recovery support for the * device. */ -static void vfio_register_err_notifier(VFIODevice *vdev) +static void vfio_register_err_notifier(VFIOPCIDevice *vdev) { int ret; int argsz; @@ -4115,7 +3130,7 @@ static void vfio_register_err_notifier(VFIODevice *vdev) *pfd = event_notifier_get_fd(&vdev->err_notifier); qemu_set_fd_handler(*pfd, vfio_err_notifier_handler, NULL, vdev); - ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set); + ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set); if (ret) { error_report("vfio: Failed to set up error notification"); qemu_set_fd_handler(*pfd, NULL, NULL, vdev); @@ -4125,7 +3140,7 @@ static void vfio_register_err_notifier(VFIODevice *vdev) g_free(irq_set); } -static void vfio_unregister_err_notifier(VFIODevice *vdev) +static void vfio_unregister_err_notifier(VFIOPCIDevice *vdev) { int argsz; struct vfio_irq_set *irq_set; @@ -4148,7 +3163,7 @@ static void vfio_unregister_err_notifier(VFIODevice *vdev) pfd = (int32_t *)&irq_set->data; *pfd = -1; - ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set); + ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set); if (ret) { error_report("vfio: Failed to de-assign error fd: %m"); } @@ -4160,7 +3175,8 @@ static void vfio_unregister_err_notifier(VFIODevice *vdev) static int vfio_initfn(PCIDevice *pdev) { - VFIODevice *pvdev, *vdev = DO_UPCAST(VFIODevice, pdev, pdev); + VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev); + VFIODevice *vbasedev_iter; VFIOGroup *group; char path[PATH_MAX], iommu_group_path[PATH_MAX], *group_name; ssize_t len; @@ -4178,6 +3194,13 @@ static int vfio_initfn(PCIDevice *pdev) return -errno; } + vdev->vbasedev.ops = &vfio_pci_ops; + + vdev->vbasedev.type = VFIO_DEVICE_TYPE_PCI; + vdev->vbasedev.name = g_strdup_printf("%04x:%02x:%02x.%01x", + vdev->host.domain, vdev->host.bus, + vdev->host.slot, vdev->host.function); + strncat(path, "iommu_group", sizeof(path) - strlen(path) - 1); len = readlink(path, iommu_group_path, sizeof(path)); @@ -4194,8 +3217,7 @@ static int vfio_initfn(PCIDevice *pdev) return -errno; } - DPRINTF("%s(%04x:%02x:%02x.%x) group %d\n", __func__, vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function, groupid); + trace_vfio_initfn(vdev->vbasedev.name, groupid); group = vfio_get_group(groupid, pci_device_iommu_address_space(pdev)); if (!group) { @@ -4207,19 +3229,15 @@ static int vfio_initfn(PCIDevice *pdev) vdev->host.domain, vdev->host.bus, vdev->host.slot, vdev->host.function); - QLIST_FOREACH(pvdev, &group->device_list, next) { - if (pvdev->host.domain == vdev->host.domain && - pvdev->host.bus == vdev->host.bus && - pvdev->host.slot == vdev->host.slot && - pvdev->host.function == vdev->host.function) { - + QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { + if (strcmp(vbasedev_iter->name, vdev->vbasedev.name) == 0) { error_report("vfio: error: device %s is already attached", path); vfio_put_group(group); return -EBUSY; } } - ret = vfio_get_device(group, path, vdev); + ret = vfio_get_device(group, path, &vdev->vbasedev); if (ret) { error_report("vfio: failed to get device %s", path); vfio_put_group(group); @@ -4227,7 +3245,7 @@ static int vfio_initfn(PCIDevice *pdev) } /* Get a copy of config space */ - ret = pread(vdev->fd, vdev->pdev.config, + ret = pread(vdev->vbasedev.fd, vdev->pdev.config, MIN(pci_config_size(&vdev->pdev), vdev->config_size), vdev->config_offset); if (ret < (int)MIN(pci_config_size(&vdev->pdev), vdev->config_size)) { @@ -4313,8 +3331,8 @@ out_put: static void vfio_exitfn(PCIDevice *pdev) { - VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev); - VFIOGroup *group = vdev->group; + VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev); + VFIOGroup *group = vdev->vbasedev.group; vfio_unregister_err_notifier(vdev); pci_device_set_intx_routing_notifier(&vdev->pdev, NULL); @@ -4333,17 +3351,16 @@ static void vfio_exitfn(PCIDevice *pdev) static void vfio_pci_reset(DeviceState *dev) { PCIDevice *pdev = DO_UPCAST(PCIDevice, qdev, dev); - VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev); + VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev); - DPRINTF("%s(%04x:%02x:%02x.%x)\n", __func__, vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function); + trace_vfio_pci_reset(vdev->vbasedev.name); vfio_pci_pre_reset(vdev); - if (vdev->reset_works && (vdev->has_flr || !vdev->has_pm_reset) && - !ioctl(vdev->fd, VFIO_DEVICE_RESET)) { - DPRINTF("%04x:%02x:%02x.%x FLR/VFIO_DEVICE_RESET\n", vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function); + if (vdev->vbasedev.reset_works && + (vdev->has_flr || !vdev->has_pm_reset) && + !ioctl(vdev->vbasedev.fd, VFIO_DEVICE_RESET)) { + trace_vfio_pci_reset_flr(vdev->vbasedev.name); goto post_reset; } @@ -4353,10 +3370,9 @@ static void vfio_pci_reset(DeviceState *dev) } /* If nothing else works and the device supports PM reset, use it */ - if (vdev->reset_works && vdev->has_pm_reset && - !ioctl(vdev->fd, VFIO_DEVICE_RESET)) { - DPRINTF("%04x:%02x:%02x.%x PCI PM Reset\n", vdev->host.domain, - vdev->host.bus, vdev->host.slot, vdev->host.function); + if (vdev->vbasedev.reset_works && vdev->has_pm_reset && + !ioctl(vdev->vbasedev.fd, VFIO_DEVICE_RESET)) { + trace_vfio_pci_reset_pm(vdev->vbasedev.name); goto post_reset; } @@ -4367,7 +3383,7 @@ post_reset: static void vfio_instance_init(Object *obj) { PCIDevice *pci_dev = PCI_DEVICE(obj); - VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, PCI_DEVICE(obj)); + VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, PCI_DEVICE(obj)); device_add_bootindex_property(obj, &vdev->bootindex, "bootindex", NULL, @@ -4375,15 +3391,16 @@ static void vfio_instance_init(Object *obj) } static Property vfio_pci_dev_properties[] = { - DEFINE_PROP_PCI_HOST_DEVADDR("host", VFIODevice, host), - DEFINE_PROP_UINT32("x-intx-mmap-timeout-ms", VFIODevice, + DEFINE_PROP_PCI_HOST_DEVADDR("host", VFIOPCIDevice, host), + DEFINE_PROP_UINT32("x-intx-mmap-timeout-ms", VFIOPCIDevice, intx.mmap_timeout, 1100), - DEFINE_PROP_BIT("x-vga", VFIODevice, features, + DEFINE_PROP_BIT("x-vga", VFIOPCIDevice, features, VFIO_FEATURE_ENABLE_VGA_BIT, false), + DEFINE_PROP_INT32("bootindex", VFIOPCIDevice, bootindex, -1), /* * TODO - support passed fds... is this necessary? - * DEFINE_PROP_STRING("vfiofd", VFIODevice, vfiofd_name), - * DEFINE_PROP_STRING("vfiogroupfd, VFIODevice, vfiogroupfd_name), + * DEFINE_PROP_STRING("vfiofd", VFIOPCIDevice, vfiofd_name), + * DEFINE_PROP_STRING("vfiogroupfd, VFIOPCIDevice, vfiogroupfd_name), */ DEFINE_PROP_END_OF_LIST(), }; @@ -4413,7 +3430,7 @@ static void vfio_pci_dev_class_init(ObjectClass *klass, void *data) static const TypeInfo vfio_pci_dev_info = { .name = "vfio-pci", .parent = TYPE_PCI_DEVICE, - .instance_size = sizeof(VFIODevice), + .instance_size = sizeof(VFIOPCIDevice), .class_init = vfio_pci_dev_class_init, .instance_init = vfio_instance_init, }; @@ -4424,47 +3441,3 @@ static void register_vfio_pci_dev_type(void) } type_init(register_vfio_pci_dev_type) - -static int vfio_container_do_ioctl(AddressSpace *as, int32_t groupid, - int req, void *param) -{ - VFIOGroup *group; - VFIOContainer *container; - int ret = -1; - - group = vfio_get_group(groupid, as); - if (!group) { - error_report("vfio: group %d not registered", groupid); - return ret; - } - - container = group->container; - if (group->container) { - ret = ioctl(container->fd, req, param); - if (ret < 0) { - error_report("vfio: failed to ioctl container: ret=%d, %s", - ret, strerror(errno)); - } - } - - vfio_put_group(group); - - return ret; -} - -int vfio_container_ioctl(AddressSpace *as, int32_t groupid, - int req, void *param) -{ - /* We allow only certain ioctls to the container */ - switch (req) { - case VFIO_CHECK_EXTENSION: - case VFIO_IOMMU_SPAPR_TCE_GET_INFO: - break; - default: - /* Return an error on unknown requests */ - error_report("vfio: unsupported ioctl %X", req); - return -1; - } - - return vfio_container_do_ioctl(as, groupid, req, param); -} |