@@ -228,7 +228,7 @@ static void vfio_ap_instance_init(Object *obj)
* handle ram_block_discard_disable().
*/
vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_AP, &vfio_ap_ops,
- DEVICE(vapdev), true);
+ &vfio_dev_io_ioctl, DEVICE(vapdev), true);
/* AP device is mdev type device */
vbasedev->mdev = true;
@@ -682,7 +682,7 @@ static void vfio_ccw_instance_init(Object *obj)
* ram_block_discard_disable().
*/
vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_CCW, &vfio_ccw_ops,
- DEVICE(vcdev), true);
+ &vfio_dev_io_ioctl, DEVICE(vcdev), true);
}
#ifdef CONFIG_IOMMUFD
@@ -971,7 +971,7 @@ static void vfio_devices_dma_logging_stop(VFIOContainerBase *bcontainer)
continue;
}
- if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
+ if (vbasedev->io->device_feature(vbasedev, feature)) {
warn_report("%s: Failed to stop DMA logging, err %d (%s)",
vbasedev->name, -errno, strerror(errno));
}
@@ -1074,10 +1074,9 @@ static bool vfio_devices_dma_logging_start(VFIOContainerBase *bcontainer,
continue;
}
- ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature);
+ ret = vbasedev->io->device_feature(vbasedev, feature);
if (ret) {
- ret = -errno;
- error_setg_errno(errp, errno, "%s: Failed to start DMA logging",
+ error_setg_errno(errp, -ret, "%s: Failed to start DMA logging",
vbasedev->name);
goto out;
}
@@ -1145,6 +1144,7 @@ static int vfio_device_dma_logging_report(VFIODevice *vbasedev, hwaddr iova,
struct vfio_device_feature *feature = (struct vfio_device_feature *)buf;
struct vfio_device_feature_dma_logging_report *report =
(struct vfio_device_feature_dma_logging_report *)feature->data;
+ int ret;
report->iova = iova;
report->length = size;
@@ -1155,8 +1155,9 @@ static int vfio_device_dma_logging_report(VFIODevice *vbasedev, hwaddr iova,
feature->flags = VFIO_DEVICE_FEATURE_GET |
VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT;
- if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
- return -errno;
+ ret = vbasedev->io->device_feature(vbasedev, feature);
+ if (ret) {
+ return -ret;
}
return 0;
@@ -44,7 +44,7 @@ void vfio_disable_irqindex(VFIODevice *vbasedev, int index)
.count = 0,
};
- ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
+ vbasedev->io->set_irqs(vbasedev, &irq_set);
}
void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index)
@@ -57,7 +57,7 @@ void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index)
.count = 1,
};
- ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
+ vbasedev->io->set_irqs(vbasedev, &irq_set);
}
void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index)
@@ -70,7 +70,7 @@ void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index)
.count = 1,
};
- ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
+ vbasedev->io->set_irqs(vbasedev, &irq_set);
}
static inline const char *action_to_str(int action)
@@ -117,6 +117,7 @@ bool vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex,
int argsz;
const char *name;
int32_t *pfd;
+ int ret;
argsz = sizeof(*irq_set) + sizeof(*pfd);
@@ -129,7 +130,9 @@ bool 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 = vbasedev->io->set_irqs(vbasedev, irq_set);
+
+ if (!ret) {
return true;
}
@@ -161,6 +164,7 @@ void vfio_region_write(void *opaque, hwaddr addr,
uint32_t dword;
uint64_t qword;
} buf;
+ int ret;
switch (size) {
case 1:
@@ -180,11 +184,12 @@ void vfio_region_write(void *opaque, hwaddr addr,
break;
}
- if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) {
+ ret = vbasedev->io->region_write(vbasedev, region->nr, addr, size, &buf);
+ if (ret != size) {
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, ret < 0 ? strerror(ret) : "short write");
}
trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size);
@@ -212,11 +217,13 @@ uint64_t vfio_region_read(void *opaque,
uint64_t qword;
} buf;
uint64_t data = 0;
+ int ret;
- if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) {
- error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m",
+ ret = vbasedev->io->region_read(vbasedev, region->nr, addr, size, &buf);
+ if (ret != size) {
+ error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %s",
__func__, vbasedev->name, region->nr,
- addr, size);
+ addr, size, ret < 0 ? strerror(ret) : "short read");
return (uint64_t)-1;
}
switch (size) {
@@ -561,6 +568,7 @@ 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) {
@@ -579,10 +587,11 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index,
retry:
(*info)->argsz = argsz;
- if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) {
+ ret = vbasedev->io->get_region_info(vbasedev, *info);
+ if (ret != 0) {
g_free(*info);
*info = NULL;
- return -errno;
+ return ret;
}
if ((*info)->argsz > argsz) {
@@ -689,11 +698,12 @@ void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp)
}
void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops,
- DeviceState *dev, bool ram_discard)
+ VFIODeviceIO *io, DeviceState *dev, bool ram_discard)
{
vbasedev->type = type;
vbasedev->ops = ops;
vbasedev->dev = dev;
+ vbasedev->io = io;
vbasedev->fd = -1;
vbasedev->ram_block_discard_allowed = ram_discard;
@@ -749,3 +759,77 @@ VFIODevice *vfio_get_vfio_device(Object *obj)
return NULL;
}
}
+
+/*
+ * Traditional ioctl() based io
+ */
+
+static int vfio_io_device_feature(VFIODevice *vbasedev,
+ struct vfio_device_feature *feature)
+{
+ int ret;
+
+ ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature);
+
+ 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;
+}
+
+VFIODeviceIO vfio_dev_io_ioctl = {
+ .device_feature = vfio_io_device_feature,
+ .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,
+};
@@ -45,6 +45,14 @@
#include "migration/qemu-file.h"
#include "system/iommufd.h"
+/* convenience macros for PCI config space */
+#define VDEV_CONFIG_READ(vbasedev, off, size, data) \
+ ((vbasedev)->io->region_read((vbasedev), VFIO_PCI_CONFIG_REGION_INDEX, \
+ (off), (size), (data)))
+#define VDEV_CONFIG_WRITE(vbasedev, off, size, data) \
+ ((vbasedev)->io->region_write((vbasedev), VFIO_PCI_CONFIG_REGION_INDEX, \
+ (off), (size), (data)))
+
#define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug"
/* Protected by BQL */
@@ -379,6 +387,7 @@ static void vfio_msi_interrupt(void *opaque)
static int vfio_enable_msix_no_vec(VFIOPCIDevice *vdev)
{
g_autofree struct vfio_irq_set *irq_set = NULL;
+ VFIODevice *vbasedev = &vdev->vbasedev;
int ret = 0, argsz;
int32_t *fd;
@@ -394,7 +403,7 @@ static int vfio_enable_msix_no_vec(VFIOPCIDevice *vdev)
fd = (int32_t *)&irq_set->data;
*fd = -1;
- ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
+ ret = vbasedev->io->set_irqs(vbasedev, irq_set);
return ret;
}
@@ -453,7 +462,7 @@ 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->vbasedev.io->set_irqs(&vdev->vbasedev, irq_set);
g_free(irq_set);
@@ -763,7 +772,8 @@ retry:
ret = vfio_enable_vectors(vdev, false);
if (ret) {
if (ret < 0) {
- error_report("vfio: Error: Failed to setup MSI fds: %m");
+ error_report("vfio: Error: Failed to setup MSI fds: %s",
+ strerror(-ret));
} else {
error_report("vfio: Error: Failed to enable %d "
"MSI vectors, retry with %d", vdev->nr_vectors, ret);
@@ -879,14 +889,17 @@ 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 = NULL;
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;
}
@@ -911,18 +924,19 @@ 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 = vbasedev->io->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;
}
}
@@ -1010,10 +1024,9 @@ 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;
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 */
@@ -1030,11 +1043,12 @@ 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;
}
@@ -1214,6 +1228,7 @@ 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);
@@ -1226,12 +1241,13 @@ 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);
}
@@ -1247,15 +1263,19 @@ 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 */
@@ -1343,9 +1363,12 @@ static bool 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");
+ ret = VDEV_CONFIG_READ(&vdev->vbasedev, pos + PCI_CAP_FLAGS,
+ sizeof(ctrl), &ctrl);
+ if (ret != sizeof(ctrl)) {
+ const char *errmsg = ret < 0 ? strerror(-ret) : "short read";
+
+ error_setg(errp, "failed reading MSI PCI_CAP_FLAGS %s", errmsg);
return false;
}
ctrl = le16_to_cpu(ctrl);
@@ -1549,34 +1572,43 @@ static bool vfio_pci_relocate_msix(VFIOPCIDevice *vdev, Error **errp)
*/
static bool vfio_msix_early_setup(VFIOPCIDevice *vdev, Error **errp)
{
+ VFIODevice *vbasedev = &vdev->vbasedev;
uint8_t pos;
uint16_t ctrl;
uint32_t table, pba;
- int ret, fd = vdev->vbasedev.fd;
struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info),
.index = VFIO_PCI_MSIX_IRQ_INDEX };
VFIOMSIXInfo *msix;
+ int ret;
pos = pci_find_capability(&vdev->pdev, PCI_CAP_ID_MSIX);
if (!pos) {
return true;
}
- 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");
+ 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);
return false;
}
- 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");
+ 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);
return false;
}
- 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");
+ 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);
return false;
}
@@ -1591,7 +1623,7 @@ static bool vfio_msix_early_setup(VFIOPCIDevice *vdev, Error **errp)
msix->pba_offset = pba & ~PCI_MSIX_FLAGS_BIRMASK;
msix->entries = (ctrl & PCI_MSIX_FLAGS_QSIZE) + 1;
- ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
+ ret = vdev->vbasedev.io->get_irq_info(&vdev->vbasedev, &irq_info);
if (ret < 0) {
error_setg_errno(errp, -ret, "failed to get MSI-X irq info");
g_free(msix);
@@ -1735,10 +1767,12 @@ 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;
}
@@ -2438,21 +2472,25 @@ void vfio_pci_pre_reset(VFIOPCIDevice *vdev)
void vfio_pci_post_reset(VFIOPCIDevice *vdev)
{
+ VFIODevice *vbasedev = &vdev->vbasedev;
Error *err = NULL;
- int nr;
+ int ret, nr;
if (!vfio_intx_enable(vdev, &err)) {
error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
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 *errmsg = ret < 0 ? strerror(-ret) : "short write";
+
+ error_report("%s(%s) reset bar %d failed: %s", __func__,
+ vbasedev->name, nr, errmsg);
}
}
@@ -2794,10 +2832,10 @@ static bool 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 = vbasedev->io->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));
+ trace_vfio_populate_device_get_irq_info_failure(strerror(-ret));
} else if (irq_info.count == 1) {
vdev->pci_aer = true;
} else {
@@ -2915,8 +2953,11 @@ 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->vbasedev.io->get_irq_info(&vdev->vbasedev, &irq_info) < 0) {
+ return;
+ }
+
+ if (irq_info.count < 1) {
return;
}
@@ -3368,7 +3409,7 @@ static void vfio_instance_init(Object *obj)
vdev->host.function = ~0U;
vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_PCI, &vfio_pci_ops,
- DEVICE(vdev), false);
+ &vfio_dev_io_ioctl, DEVICE(vdev), false);
vdev->nv_gpudirect_clique = 0xFF;
@@ -648,7 +648,7 @@ static void vfio_platform_instance_init(Object *obj)
VFIODevice *vbasedev = &vdev->vbasedev;
vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_PLATFORM, &vfio_platform_ops,
- DEVICE(vdev), false);
+ &vfio_dev_io_ioctl, DEVICE(vdev), false);
}
#ifdef CONFIG_IOMMUFD
@@ -116,6 +116,7 @@ typedef struct VFIOIOMMUFDContainer {
OBJECT_DECLARE_SIMPLE_TYPE(VFIOIOMMUFDContainer, VFIO_IOMMU_IOMMUFD);
typedef struct VFIODeviceOps VFIODeviceOps;
+typedef struct VFIODeviceIO VFIODeviceIO;
typedef struct VFIODevice {
QLIST_ENTRY(VFIODevice) next;
@@ -136,6 +137,7 @@ typedef struct VFIODevice {
OnOffAuto enable_migration;
bool migration_events;
VFIODeviceOps *ops;
+ VFIODeviceIO *io;
unsigned int num_irqs;
unsigned int num_regions;
unsigned int flags;
@@ -186,6 +188,29 @@ struct VFIODeviceOps {
int (*vfio_load_config)(VFIODevice *vdev, QEMUFile *f);
};
+#ifdef CONFIG_LINUX
+
+/*
+ * How devices communicate with the server. The default option is through
+ * ioctl() to the kernel VFIO driver, but vfio-user can use a socket to a remote
+ * process.
+ */
+struct VFIODeviceIO {
+ int (*device_feature)(VFIODevice *vdev, struct vfio_device_feature *);
+ 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);
+};
+
+extern VFIODeviceIO vfio_dev_io_ioctl;
+
+#endif /* CONFIG_LINUX */
+
typedef struct VFIOGroup {
int fd;
int groupid;
@@ -317,6 +342,6 @@ int vfio_get_dirty_bitmap(const VFIOContainerBase *bcontainer, uint64_t iova,
bool vfio_device_get_name(VFIODevice *vbasedev, Error **errp);
void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp);
void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops,
- DeviceState *dev, bool ram_discard);
+ VFIODeviceIO *io, DeviceState *dev, bool ram_discard);
int vfio_device_get_aw_bits(VFIODevice *vdev);
#endif /* HW_VFIO_VFIO_COMMON_H */