Used for communication with VFIO driver (prep work for vfio-user, which will communicate over a socket)
Signed-off-by: John G Johnson <john.g.john...@oracle.com> --- include/hw/vfio/vfio-common.h | 27 ++++++++ hw/vfio/common.c | 107 +++++++++++++++++++++++++++----- hw/vfio/pci.c | 140 ++++++++++++++++++++++++++---------------- 3 files changed, 206 insertions(+), 68 deletions(-) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 1a032f4..826cd98 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -124,6 +124,7 @@ typedef struct VFIOHostDMAWindow { } VFIOHostDMAWindow; typedef struct VFIODeviceOps VFIODeviceOps; +typedef struct VFIODevIO VFIODevIO; typedef struct VFIODevice { QLIST_ENTRY(VFIODevice) next; @@ -139,6 +140,7 @@ typedef struct VFIODevice { bool ram_block_discard_allowed; bool enable_migration; VFIODeviceOps *ops; + VFIODevIO *io_ops; unsigned int num_irqs; unsigned int num_regions; unsigned int flags; @@ -165,6 +167,30 @@ struct VFIODeviceOps { * through ioctl() to the kernel VFIO driver, but vfio-user * can use a socket to a remote process. */ +struct VFIODevIO { + int (*get_info)(VFIODevice *vdev, struct vfio_device_info *info); + int (*get_region_info)(VFIODevice *vdev, + struct vfio_region_info *info); + int (*get_irq_info)(VFIODevice *vdev, struct vfio_irq_info *irq); + int (*set_irqs)(VFIODevice *vdev, struct vfio_irq_set *irqs); + int (*region_read)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size, + void *data); + int (*region_write)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size, + void *data); +}; + +#define VDEV_GET_INFO(vdev, info) \ + ((vdev)->io_ops->get_info((vdev), (info))) +#define VDEV_GET_REGION_INFO(vdev, info) \ + ((vdev)->io_ops->get_region_info((vdev), (info))) +#define VDEV_GET_IRQ_INFO(vdev, irq) \ + ((vdev)->io_ops->get_irq_info((vdev), (irq))) +#define VDEV_SET_IRQS(vdev, irqs) \ + ((vdev)->io_ops->set_irqs((vdev), (irqs))) +#define VDEV_REGION_READ(vdev, nr, off, size, data) \ + ((vdev)->io_ops->region_read((vdev), (nr), (off), (size), (data))) +#define VDEV_REGION_WRITE(vdev, nr, off, size, data) \ + ((vdev)->io_ops->region_write((vdev), (nr), (off), (size), (data))) struct VFIOContIO { int (*dma_map)(VFIOContainer *container, @@ -184,6 +210,7 @@ struct VFIOContIO { #define CONT_DIRTY_BITMAP(cont, bitmap, range) \ ((cont)->io_ops->dirty_bitmap((cont), (bitmap), (range))) +extern VFIODevIO vfio_dev_io_ioctl; extern VFIOContIO vfio_cont_io_ioctl; #endif /* CONFIG_LINUX */ diff --git a/hw/vfio/common.c b/hw/vfio/common.c index d9290f3..0616169 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -70,7 +70,7 @@ void vfio_disable_irqindex(VFIODevice *vbasedev, int index) .count = 0, }; - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); + VDEV_SET_IRQS(vbasedev, &irq_set); } void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index) @@ -83,7 +83,7 @@ void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index) .count = 1, }; - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); + VDEV_SET_IRQS(vbasedev, &irq_set); } void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index) @@ -96,7 +96,7 @@ void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index) .count = 1, }; - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); + VDEV_SET_IRQS(vbasedev, &irq_set); } static inline const char *action_to_str(int action) @@ -177,9 +177,7 @@ int vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex, pfd = (int32_t *)&irq_set->data; *pfd = fd; - if (ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) { - ret = -errno; - } + ret = VDEV_SET_IRQS(vbasedev, irq_set); g_free(irq_set); if (!ret) { @@ -214,6 +212,7 @@ void vfio_region_write(void *opaque, hwaddr addr, uint32_t dword; uint64_t qword; } buf; + int ret; switch (size) { case 1: @@ -233,13 +232,15 @@ void vfio_region_write(void *opaque, hwaddr addr, break; } - if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) { + ret = VDEV_REGION_WRITE(vbasedev, region->nr, addr, size, &buf); + if (ret != size) { + const char *err = ret < 0 ? strerror(-ret) : "short write"; + error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64 - ",%d) failed: %m", + ",%d) failed: %s", __func__, vbasedev->name, region->nr, - addr, data, size); + addr, data, size, err); } - trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size); /* @@ -265,13 +266,18 @@ uint64_t vfio_region_read(void *opaque, uint64_t qword; } buf; uint64_t data = 0; + int ret; + + ret = VDEV_REGION_READ(vbasedev, region->nr, addr, size, &buf); + if (ret != size) { + const char *err = ret < 0 ? strerror(-ret) : "short read"; - if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) { - error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m", + error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %s", __func__, vbasedev->name, region->nr, - addr, size); + addr, size, err); return (uint64_t)-1; } + switch (size) { case 1: data = buf.byte; @@ -2418,6 +2424,7 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index, struct vfio_region_info **info) { size_t argsz = sizeof(struct vfio_region_info); + int ret; /* create region cache */ if (vbasedev->regions == NULL) { @@ -2436,10 +2443,11 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index, retry: (*info)->argsz = argsz; - if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) { + ret = VDEV_GET_REGION_INFO(vbasedev, *info); + if (ret != 0) { g_free(*info); *info = NULL; - return -errno; + return ret; } if ((*info)->argsz > argsz) { @@ -2600,6 +2608,75 @@ int vfio_eeh_as_op(AddressSpace *as, uint32_t op) * Traditional ioctl() based io_ops */ +static int vfio_io_get_info(VFIODevice *vbasedev, struct vfio_device_info *info) +{ + int ret; + + ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_INFO, info); + + return ret < 0 ? -errno : ret; +} + +static int vfio_io_get_region_info(VFIODevice *vbasedev, + struct vfio_region_info *info) +{ + int ret; + + ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, info); + + return ret < 0 ? -errno : ret; +} + +static int vfio_io_get_irq_info(VFIODevice *vbasedev, + struct vfio_irq_info *info) +{ + int ret; + + ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_IRQ_INFO, info); + + return ret < 0 ? -errno : ret; +} + +static int vfio_io_set_irqs(VFIODevice *vbasedev, struct vfio_irq_set *irqs) +{ + int ret; + + ret = ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irqs); + + return ret < 0 ? -errno : ret; +} + +static int vfio_io_region_read(VFIODevice *vbasedev, uint8_t index, off_t off, + uint32_t size, void *data) +{ + struct vfio_region_info *info = vbasedev->regions[index]; + int ret; + + ret = pread(vbasedev->fd, data, size, info->offset + off); + + return ret < 0 ? -errno : ret; +} + +static int vfio_io_region_write(VFIODevice *vbasedev, uint8_t index, off_t off, + uint32_t size, void *data) +{ + struct vfio_region_info *info = vbasedev->regions[index]; + int ret; + + ret = pwrite(vbasedev->fd, data, size, info->offset + off); + + return ret < 0 ? -errno : ret; +} + +VFIODevIO vfio_dev_io_ioctl = { + .get_info = vfio_io_get_info, + .get_region_info = vfio_io_get_region_info, + .get_irq_info = vfio_io_get_irq_info, + .set_irqs = vfio_io_set_irqs, + .region_read = vfio_io_region_read, + .region_write = vfio_io_region_write, +}; + static int vfio_io_dma_map(VFIOContainer *container, struct vfio_iommu_type1_dma_map *map) { diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 35b6551..4524342 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -43,6 +43,14 @@ #include "migration/blocker.h" #include "migration/qemu-file.h" +/* convenience macros for PCI config space */ +#define VDEV_CONFIG_READ(vbasedev, off, size, data) \ + VDEV_REGION_READ((vbasedev), VFIO_PCI_CONFIG_REGION_INDEX, (off), \ + (size), (data)) +#define VDEV_CONFIG_WRITE(vbasedev, off, size, data) \ + VDEV_REGION_WRITE((vbasedev), VFIO_PCI_CONFIG_REGION_INDEX, (off), \ + (size), (data)) + #define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug" static void vfio_disable_interrupts(VFIOPCIDevice *vdev); @@ -402,7 +410,7 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix) fds[i] = fd; } - ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set); + ret = VDEV_SET_IRQS(&vdev->vbasedev, irq_set); g_free(irq_set); @@ -775,14 +783,16 @@ static void vfio_update_msi(VFIOPCIDevice *vdev) static void vfio_pci_load_rom(VFIOPCIDevice *vdev) { + VFIODevice *vbasedev = &vdev->vbasedev; struct vfio_region_info *reg_info; uint64_t size; off_t off = 0; ssize_t bytes; + int ret; - if (vfio_get_region_info(&vdev->vbasedev, - VFIO_PCI_ROM_REGION_INDEX, ®_info)) { - error_report("vfio: Error getting ROM info: %m"); + ret = vfio_get_region_info(vbasedev, VFIO_PCI_ROM_REGION_INDEX, ®_info); + if (ret < 0) { + error_report("vfio: Error getting ROM info: %s", strerror(-ret)); return; } @@ -807,18 +817,19 @@ static void vfio_pci_load_rom(VFIOPCIDevice *vdev) memset(vdev->rom, 0xff, size); while (size) { - bytes = pread(vdev->vbasedev.fd, vdev->rom + off, - size, vdev->rom_offset + off); + bytes = VDEV_REGION_READ(vbasedev, VFIO_PCI_ROM_REGION_INDEX, off, + size, vdev->rom + off); if (bytes == 0) { break; } else if (bytes > 0) { off += bytes; size -= bytes; } else { - if (errno == EINTR || errno == EAGAIN) { + if (bytes == -EINTR || bytes == -EAGAIN) { continue; } - error_report("vfio: Error reading device ROM: %m"); + error_report("vfio: Error reading device ROM: %s", + strerror(-bytes)); break; } } @@ -906,11 +917,10 @@ static const MemoryRegionOps vfio_rom_ops = { static void vfio_pci_size_rom(VFIOPCIDevice *vdev) { + VFIODevice *vbasedev = &vdev->vbasedev; 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; - int fd = vdev->vbasedev.fd; if (vdev->pdev.romfile || !vdev->pdev.rom_bar) { /* Since pci handles romfile, just print a message and return */ @@ -927,11 +937,12 @@ static void vfio_pci_size_rom(VFIOPCIDevice *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(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(%s) failed: %m", __func__, vdev->vbasedev.name); + if (VDEV_CONFIG_READ(vbasedev, PCI_ROM_ADDRESS, 4, &orig) != 4 || + VDEV_CONFIG_WRITE(vbasedev, PCI_ROM_ADDRESS, 4, &size) != 4 || + VDEV_CONFIG_READ(vbasedev, PCI_ROM_ADDRESS, 4, &size) != 4 || + VDEV_CONFIG_WRITE(vbasedev, PCI_ROM_ADDRESS, 4, &orig) != 4) { + + error_report("%s(%s) ROM access failed", __func__, vbasedev->name); return; } @@ -1111,6 +1122,7 @@ static void vfio_sub_page_bar_update_mapping(PCIDevice *pdev, int bar) uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len) { VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev); + VFIODevice *vbasedev = &vdev->vbasedev; uint32_t emu_bits = 0, emu_val = 0, phys_val = 0, val; memcpy(&emu_bits, vdev->emulated_config_bits + addr, len); @@ -1123,12 +1135,13 @@ 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->vbasedev.fd, &phys_val, len, - vdev->config_offset + addr); + ret = VDEV_CONFIG_READ(vbasedev, addr, len, &phys_val); if (ret != len) { - error_report("%s(%s, 0x%x, 0x%x) failed: %m", - __func__, vdev->vbasedev.name, addr, len); - return -errno; + const char *err = ret < 0 ? strerror(-ret) : "short read"; + + error_report("%s(%s, 0x%x, 0x%x) failed: %s", + __func__, vbasedev->name, addr, len, err); + return -1; } phys_val = le32_to_cpu(phys_val); } @@ -1144,15 +1157,19 @@ void vfio_pci_write_config(PCIDevice *pdev, uint32_t addr, uint32_t val, int len) { VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev); + VFIODevice *vbasedev = &vdev->vbasedev; uint32_t val_le = cpu_to_le32(val); + int ret; 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->vbasedev.fd, &val_le, len, vdev->config_offset + addr) - != len) { - error_report("%s(%s, 0x%x, 0x%x, 0x%x) failed: %m", - __func__, vdev->vbasedev.name, addr, val, len); + ret = VDEV_CONFIG_WRITE(vbasedev, addr, len, &val_le); + if (ret != len) { + const char *err = ret < 0 ? strerror(-ret) : "short write"; + + error_report("%s(%s, 0x%x, 0x%x, 0x%x) failed: %s", + __func__, vbasedev->name, addr, val, len, err); } /* MSI/MSI-X Enabling/Disabling */ @@ -1240,10 +1257,13 @@ static int vfio_msi_setup(VFIOPCIDevice *vdev, int pos, Error **errp) int ret, entries; Error *err = NULL; - if (pread(vdev->vbasedev.fd, &ctrl, sizeof(ctrl), - vdev->config_offset + pos + PCI_CAP_FLAGS) != sizeof(ctrl)) { - error_setg_errno(errp, errno, "failed reading MSI PCI_CAP_FLAGS"); - return -errno; + ret = VDEV_CONFIG_READ(&vdev->vbasedev, pos + PCI_CAP_FLAGS, + sizeof(ctrl), &ctrl); + if (ret != sizeof(ctrl)) { + const char *err = ret < 0 ? strerror(-ret) : "short read"; + + error_setg(errp, "failed reading MSI PCI_CAP_FLAGS %s", err); + return ret; } ctrl = le16_to_cpu(ctrl); @@ -1445,33 +1465,39 @@ static void vfio_pci_relocate_msix(VFIOPCIDevice *vdev, Error **errp) */ static void vfio_msix_early_setup(VFIOPCIDevice *vdev, Error **errp) { + VFIODevice *vbasedev = &vdev->vbasedev; uint8_t pos; uint16_t ctrl; uint32_t table, pba; - int fd = vdev->vbasedev.fd; VFIOMSIXInfo *msix; + int ret; pos = pci_find_capability(&vdev->pdev, PCI_CAP_ID_MSIX); if (!pos) { return; } - if (pread(fd, &ctrl, sizeof(ctrl), - vdev->config_offset + pos + PCI_MSIX_FLAGS) != sizeof(ctrl)) { - error_setg_errno(errp, errno, "failed to read PCI MSIX FLAGS"); - return; + ret = VDEV_CONFIG_READ(vbasedev, pos + PCI_MSIX_FLAGS, + sizeof(ctrl), &ctrl); + if (ret != sizeof(ctrl)) { + const char *err = ret < 0 ? strerror(-ret) : "short read"; + + error_setg(errp, "failed to read PCI MSIX FLAGS %s", err); } - if (pread(fd, &table, sizeof(table), - vdev->config_offset + pos + PCI_MSIX_TABLE) != sizeof(table)) { - error_setg_errno(errp, errno, "failed to read PCI MSIX TABLE"); - return; + ret = VDEV_CONFIG_READ(vbasedev, pos + PCI_MSIX_TABLE, + sizeof(table), &table); + if (ret != sizeof(table)) { + const char *err = ret < 0 ? strerror(-ret) : "short read"; + + error_setg(errp, "failed to read PCI MSIX TABLE %s", err); } - if (pread(fd, &pba, sizeof(pba), - vdev->config_offset + pos + PCI_MSIX_PBA) != sizeof(pba)) { - error_setg_errno(errp, errno, "failed to read PCI MSIX PBA"); - return; + ret = VDEV_CONFIG_READ(vbasedev, pos + PCI_MSIX_PBA, sizeof(pba), &pba); + if (ret != sizeof(pba)) { + const char *err = ret < 0 ? strerror(-ret) : "short read"; + + error_setg(errp, "failed to read PCI MSIX PBA %s", err); } ctrl = le16_to_cpu(ctrl); @@ -1609,7 +1635,6 @@ static void vfio_mmap_set_enabled(VFIOPCIDevice *vdev, bool enabled) static void vfio_bar_prepare(VFIOPCIDevice *vdev, int nr) { VFIOBAR *bar = &vdev->bars[nr]; - uint32_t pci_bar; int ret; @@ -1619,10 +1644,12 @@ static void vfio_bar_prepare(VFIOPCIDevice *vdev, int nr) } /* Determine what type of BAR this is for registration */ - ret = pread(vdev->vbasedev.fd, &pci_bar, sizeof(pci_bar), - vdev->config_offset + PCI_BASE_ADDRESS_0 + (4 * nr)); + ret = VDEV_CONFIG_READ(&vdev->vbasedev, PCI_BASE_ADDRESS_0 + (4 * nr), + sizeof(pci_bar), &pci_bar); if (ret != sizeof(pci_bar)) { - error_report("vfio: Failed to read BAR %d (%m)", nr); + const char *err = ret < 0 ? strerror(-ret) : "short read"; + + error_report("vfio: Failed to read BAR %d (%s)", nr, err); return; } @@ -2170,8 +2197,9 @@ static void vfio_pci_pre_reset(VFIOPCIDevice *vdev) static void vfio_pci_post_reset(VFIOPCIDevice *vdev) { + VFIODevice *vbasedev = &vdev->vbasedev; Error *err = NULL; - int nr; + int ret, nr; vfio_intx_enable(vdev, &err); if (err) { @@ -2179,13 +2207,16 @@ static void vfio_pci_post_reset(VFIOPCIDevice *vdev) } for (nr = 0; nr < PCI_NUM_REGIONS - 1; ++nr) { - off_t addr = vdev->config_offset + PCI_BASE_ADDRESS_0 + (4 * nr); + off_t addr = PCI_BASE_ADDRESS_0 + (4 * nr); uint32_t val = 0; uint32_t len = sizeof(val); - if (pwrite(vdev->vbasedev.fd, &val, len, addr) != len) { - error_report("%s(%s) reset bar %d failed: %m", __func__, - vdev->vbasedev.name, nr); + ret = VDEV_CONFIG_WRITE(vbasedev, addr, len, &val); + if (ret != len) { + const char *err = ret < 0 ? strerror(-ret) : "short write"; + + error_report("%s(%s) reset bar %d failed: %s", __func__, + vbasedev->name, nr, err); } } @@ -2632,7 +2663,7 @@ static void vfio_populate_device(VFIOPCIDevice *vdev, Error **errp) irq_info.index = VFIO_PCI_ERR_IRQ_INDEX; - ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info); + ret = VDEV_GET_IRQ_INFO(vbasedev, &irq_info); if (ret) { /* This can fail for an old kernel or legacy PCI dev */ trace_vfio_populate_device_get_irq_info_failure(strerror(errno)); @@ -2751,8 +2782,10 @@ static void vfio_register_req_notifier(VFIOPCIDevice *vdev) return; } - if (ioctl(vdev->vbasedev.fd, - VFIO_DEVICE_GET_IRQ_INFO, &irq_info) < 0 || irq_info.count < 1) { + if (VDEV_GET_IRQ_INFO(&vdev->vbasedev, &irq_info) < 0) { + return; + } + if (irq_info.count < 1) { return; } @@ -2830,6 +2863,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) vdev->vbasedev.ops = &vfio_pci_ops; vdev->vbasedev.type = VFIO_DEVICE_TYPE_PCI; vdev->vbasedev.dev = DEVICE(vdev); + vdev->vbasedev.io_ops = &vfio_dev_io_ioctl; tmp = g_strdup_printf("%s/iommu_group", vdev->vbasedev.sysfsdev); len = readlink(tmp, group_path, sizeof(group_path)); -- 1.8.3.1