mirror of
https://github.com/Motorhead1991/qemu.git
synced 2025-08-04 00:03:54 -06:00
vfio: Introduce new files for VFIORegion definitions and declarations
Gather all VFIORegion related declarations and definitions into their own files to reduce exposure of VFIO internals in "hw/vfio/vfio-common.h". They were introduced for 'vfio-platform' support in commitsdb0da029a1("vfio: Generalize region support") anda664477db8("hw/vfio/pci: Introduce VFIORegion"). To be noted that the 'vfio-platform' devices have been deprecated and will be removed in QEMU 10.2. Until then, make the declarations available externally for 'sysbus-fdt.c'. Cc: Eric Auger <eric.auger@redhat.com> Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com> Link: https://lore.kernel.org/qemu-devel/20250326075122.1299361-12-clg@redhat.com Signed-off-by: Cédric Le Goater <clg@redhat.com>
This commit is contained in:
Cédric Le Goater
parent
d4a8f286e9
commit
499e53cce9
11 changed files with 458 additions and 401 deletions
|
|
@ -35,6 +35,7 @@
|
|||
#include "hw/vfio/vfio-platform.h"
|
||||
#include "hw/vfio/vfio-calxeda-xgmac.h"
|
||||
#include "hw/vfio/vfio-amd-xgbe.h"
|
||||
#include "hw/vfio/vfio-region.h"
|
||||
#include "hw/display/ramfb.h"
|
||||
#include "hw/uefi/var-service-api.h"
|
||||
#include "hw/arm/fdt.h"
|
||||
|
|
|
|||
|
|
@ -147,118 +147,6 @@ bool vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex,
|
|||
return false;
|
||||
}
|
||||
|
||||
/*
|
||||
* 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;
|
||||
case 8:
|
||||
buf.qword = cpu_to_le64(data);
|
||||
break;
|
||||
default:
|
||||
hw_error("vfio: unsupported write size, %u 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;
|
||||
case 8:
|
||||
data = le64_to_cpu(buf.qword);
|
||||
break;
|
||||
default:
|
||||
hw_error("vfio: unsupported read size, %u 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,
|
||||
.valid = {
|
||||
.min_access_size = 1,
|
||||
.max_access_size = 8,
|
||||
},
|
||||
.impl = {
|
||||
.min_access_size = 1,
|
||||
.max_access_size = 8,
|
||||
},
|
||||
};
|
||||
|
||||
int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size)
|
||||
{
|
||||
vbmap->pages = REAL_HOST_PAGE_ALIGN(size) / qemu_real_host_page_size();
|
||||
|
|
@ -306,257 +194,6 @@ vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id)
|
|||
return vfio_get_cap((void *)info, info->cap_offset, id);
|
||||
}
|
||||
|
||||
static int vfio_setup_region_sparse_mmaps(VFIORegion *region,
|
||||
struct vfio_region_info *info)
|
||||
{
|
||||
struct vfio_info_cap_header *hdr;
|
||||
struct vfio_region_info_cap_sparse_mmap *sparse;
|
||||
int i, j;
|
||||
|
||||
hdr = vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMAP);
|
||||
if (!hdr) {
|
||||
return -ENODEV;
|
||||
}
|
||||
|
||||
sparse = container_of(hdr, struct vfio_region_info_cap_sparse_mmap, header);
|
||||
|
||||
trace_vfio_region_sparse_mmap_header(region->vbasedev->name,
|
||||
region->nr, sparse->nr_areas);
|
||||
|
||||
region->mmaps = g_new0(VFIOMmap, sparse->nr_areas);
|
||||
|
||||
for (i = 0, j = 0; i < sparse->nr_areas; i++) {
|
||||
if (sparse->areas[i].size) {
|
||||
trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset,
|
||||
sparse->areas[i].offset +
|
||||
sparse->areas[i].size - 1);
|
||||
region->mmaps[j].offset = sparse->areas[i].offset;
|
||||
region->mmaps[j].size = sparse->areas[i].size;
|
||||
j++;
|
||||
}
|
||||
}
|
||||
|
||||
region->nr_mmaps = j;
|
||||
region->mmaps = g_realloc(region->mmaps, j * sizeof(VFIOMmap));
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
|
||||
int index, const char *name)
|
||||
{
|
||||
g_autofree struct vfio_region_info *info = NULL;
|
||||
int ret;
|
||||
|
||||
ret = vfio_get_region_info(vbasedev, index, &info);
|
||||
if (ret) {
|
||||
return ret;
|
||||
}
|
||||
|
||||
region->vbasedev = vbasedev;
|
||||
region->flags = info->flags;
|
||||
region->size = info->size;
|
||||
region->fd_offset = info->offset;
|
||||
region->nr = index;
|
||||
|
||||
if (region->size) {
|
||||
region->mem = g_new0(MemoryRegion, 1);
|
||||
memory_region_init_io(region->mem, obj, &vfio_region_ops,
|
||||
region, name, region->size);
|
||||
|
||||
if (!vbasedev->no_mmap &&
|
||||
region->flags & VFIO_REGION_INFO_FLAG_MMAP) {
|
||||
|
||||
ret = vfio_setup_region_sparse_mmaps(region, info);
|
||||
|
||||
if (ret) {
|
||||
region->nr_mmaps = 1;
|
||||
region->mmaps = g_new0(VFIOMmap, region->nr_mmaps);
|
||||
region->mmaps[0].offset = 0;
|
||||
region->mmaps[0].size = region->size;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
trace_vfio_region_setup(vbasedev->name, index, name,
|
||||
region->flags, region->fd_offset, region->size);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static void vfio_subregion_unmap(VFIORegion *region, int index)
|
||||
{
|
||||
trace_vfio_region_unmap(memory_region_name(®ion->mmaps[index].mem),
|
||||
region->mmaps[index].offset,
|
||||
region->mmaps[index].offset +
|
||||
region->mmaps[index].size - 1);
|
||||
memory_region_del_subregion(region->mem, ®ion->mmaps[index].mem);
|
||||
munmap(region->mmaps[index].mmap, region->mmaps[index].size);
|
||||
object_unparent(OBJECT(®ion->mmaps[index].mem));
|
||||
region->mmaps[index].mmap = NULL;
|
||||
}
|
||||
|
||||
int vfio_region_mmap(VFIORegion *region)
|
||||
{
|
||||
int i, ret, prot = 0;
|
||||
char *name;
|
||||
|
||||
if (!region->mem) {
|
||||
return 0;
|
||||
}
|
||||
|
||||
prot |= region->flags & VFIO_REGION_INFO_FLAG_READ ? PROT_READ : 0;
|
||||
prot |= region->flags & VFIO_REGION_INFO_FLAG_WRITE ? PROT_WRITE : 0;
|
||||
|
||||
for (i = 0; i < region->nr_mmaps; i++) {
|
||||
size_t align = MIN(1ULL << ctz64(region->mmaps[i].size), 1 * GiB);
|
||||
void *map_base, *map_align;
|
||||
|
||||
/*
|
||||
* Align the mmap for more efficient mapping in the kernel. Ideally
|
||||
* we'd know the PMD and PUD mapping sizes to use as discrete alignment
|
||||
* intervals, but we don't. As of Linux v6.12, the largest PUD size
|
||||
* supporting huge pfnmap is 1GiB (ARCH_SUPPORTS_PUD_PFNMAP is only set
|
||||
* on x86_64). Align by power-of-two size, capped at 1GiB.
|
||||
*
|
||||
* NB. qemu_memalign() and friends actually allocate memory, whereas
|
||||
* the region size here can exceed host memory, therefore we manually
|
||||
* create an oversized anonymous mapping and clean it up for alignment.
|
||||
*/
|
||||
map_base = mmap(0, region->mmaps[i].size + align, PROT_NONE,
|
||||
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
|
||||
if (map_base == MAP_FAILED) {
|
||||
ret = -errno;
|
||||
goto no_mmap;
|
||||
}
|
||||
|
||||
map_align = (void *)ROUND_UP((uintptr_t)map_base, (uintptr_t)align);
|
||||
munmap(map_base, map_align - map_base);
|
||||
munmap(map_align + region->mmaps[i].size,
|
||||
align - (map_align - map_base));
|
||||
|
||||
region->mmaps[i].mmap = mmap(map_align, region->mmaps[i].size, prot,
|
||||
MAP_SHARED | MAP_FIXED,
|
||||
region->vbasedev->fd,
|
||||
region->fd_offset +
|
||||
region->mmaps[i].offset);
|
||||
if (region->mmaps[i].mmap == MAP_FAILED) {
|
||||
ret = -errno;
|
||||
goto no_mmap;
|
||||
}
|
||||
|
||||
name = g_strdup_printf("%s mmaps[%d]",
|
||||
memory_region_name(region->mem), i);
|
||||
memory_region_init_ram_device_ptr(®ion->mmaps[i].mem,
|
||||
memory_region_owner(region->mem),
|
||||
name, region->mmaps[i].size,
|
||||
region->mmaps[i].mmap);
|
||||
g_free(name);
|
||||
memory_region_add_subregion(region->mem, region->mmaps[i].offset,
|
||||
®ion->mmaps[i].mem);
|
||||
|
||||
trace_vfio_region_mmap(memory_region_name(®ion->mmaps[i].mem),
|
||||
region->mmaps[i].offset,
|
||||
region->mmaps[i].offset +
|
||||
region->mmaps[i].size - 1);
|
||||
}
|
||||
|
||||
return 0;
|
||||
|
||||
no_mmap:
|
||||
trace_vfio_region_mmap_fault(memory_region_name(region->mem), i,
|
||||
region->fd_offset + region->mmaps[i].offset,
|
||||
region->fd_offset + region->mmaps[i].offset +
|
||||
region->mmaps[i].size - 1, ret);
|
||||
|
||||
region->mmaps[i].mmap = NULL;
|
||||
|
||||
for (i--; i >= 0; i--) {
|
||||
vfio_subregion_unmap(region, i);
|
||||
}
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
void vfio_region_unmap(VFIORegion *region)
|
||||
{
|
||||
int i;
|
||||
|
||||
if (!region->mem) {
|
||||
return;
|
||||
}
|
||||
|
||||
for (i = 0; i < region->nr_mmaps; i++) {
|
||||
if (region->mmaps[i].mmap) {
|
||||
vfio_subregion_unmap(region, i);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
void vfio_region_exit(VFIORegion *region)
|
||||
{
|
||||
int i;
|
||||
|
||||
if (!region->mem) {
|
||||
return;
|
||||
}
|
||||
|
||||
for (i = 0; i < region->nr_mmaps; i++) {
|
||||
if (region->mmaps[i].mmap) {
|
||||
memory_region_del_subregion(region->mem, ®ion->mmaps[i].mem);
|
||||
}
|
||||
}
|
||||
|
||||
trace_vfio_region_exit(region->vbasedev->name, region->nr);
|
||||
}
|
||||
|
||||
void vfio_region_finalize(VFIORegion *region)
|
||||
{
|
||||
int i;
|
||||
|
||||
if (!region->mem) {
|
||||
return;
|
||||
}
|
||||
|
||||
for (i = 0; i < region->nr_mmaps; i++) {
|
||||
if (region->mmaps[i].mmap) {
|
||||
munmap(region->mmaps[i].mmap, region->mmaps[i].size);
|
||||
object_unparent(OBJECT(®ion->mmaps[i].mem));
|
||||
}
|
||||
}
|
||||
|
||||
object_unparent(OBJECT(region->mem));
|
||||
|
||||
g_free(region->mem);
|
||||
g_free(region->mmaps);
|
||||
|
||||
trace_vfio_region_finalize(region->vbasedev->name, region->nr);
|
||||
|
||||
region->mem = NULL;
|
||||
region->mmaps = NULL;
|
||||
region->nr_mmaps = 0;
|
||||
region->size = 0;
|
||||
region->flags = 0;
|
||||
region->nr = 0;
|
||||
}
|
||||
|
||||
void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled)
|
||||
{
|
||||
int i;
|
||||
|
||||
if (!region->mem) {
|
||||
return;
|
||||
}
|
||||
|
||||
for (i = 0; i < region->nr_mmaps; i++) {
|
||||
if (region->mmaps[i].mmap) {
|
||||
memory_region_set_enabled(®ion->mmaps[i].mem, enabled);
|
||||
}
|
||||
}
|
||||
|
||||
trace_vfio_region_mmaps_set_enabled(memory_region_name(region->mem),
|
||||
enabled);
|
||||
}
|
||||
|
||||
int vfio_get_region_info(VFIODevice *vbasedev, int index,
|
||||
struct vfio_region_info **info)
|
||||
{
|
||||
|
|
|
|||
|
|
@ -23,6 +23,7 @@ system_ss.add(when: 'CONFIG_VFIO', if_true: files(
|
|||
'migration.c',
|
||||
'migration-multifd.c',
|
||||
'cpr.c',
|
||||
'region.c',
|
||||
))
|
||||
system_ss.add(when: ['CONFIG_VFIO', 'CONFIG_IOMMUFD'], if_true: files(
|
||||
'iommufd.c',
|
||||
|
|
|
|||
|
|
@ -15,6 +15,7 @@
|
|||
#include "system/memory.h"
|
||||
#include "hw/pci/pci_device.h"
|
||||
#include "hw/vfio/vfio-common.h"
|
||||
#include "hw/vfio/vfio-region.h"
|
||||
#include "qemu/event_notifier.h"
|
||||
#include "qemu/queue.h"
|
||||
#include "qemu/timer.h"
|
||||
|
|
|
|||
|
|
@ -37,6 +37,7 @@
|
|||
#include "hw/platform-bus.h"
|
||||
#include "hw/qdev-properties.h"
|
||||
#include "system/kvm.h"
|
||||
#include "hw/vfio/vfio-region.h"
|
||||
|
||||
/*
|
||||
* Functions used whatever the injection method
|
||||
|
|
|
|||
394
hw/vfio/region.c
Normal file
394
hw/vfio/region.c
Normal file
|
|
@ -0,0 +1,394 @@
|
|||
/*
|
||||
* VFIO regions
|
||||
*
|
||||
* 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 "qemu/osdep.h"
|
||||
#include <sys/ioctl.h>
|
||||
|
||||
#include "hw/vfio/vfio-common.h"
|
||||
#include "hw/vfio/pci.h"
|
||||
#include "hw/hw.h"
|
||||
#include "trace.h"
|
||||
#include "qapi/error.h"
|
||||
#include "qemu/error-report.h"
|
||||
#include "qemu/units.h"
|
||||
#include "monitor/monitor.h"
|
||||
|
||||
/*
|
||||
* 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;
|
||||
case 8:
|
||||
buf.qword = cpu_to_le64(data);
|
||||
break;
|
||||
default:
|
||||
hw_error("vfio: unsupported write size, %u 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;
|
||||
case 8:
|
||||
data = le64_to_cpu(buf.qword);
|
||||
break;
|
||||
default:
|
||||
hw_error("vfio: unsupported read size, %u 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;
|
||||
}
|
||||
|
||||
static const MemoryRegionOps vfio_region_ops = {
|
||||
.read = vfio_region_read,
|
||||
.write = vfio_region_write,
|
||||
.endianness = DEVICE_LITTLE_ENDIAN,
|
||||
.valid = {
|
||||
.min_access_size = 1,
|
||||
.max_access_size = 8,
|
||||
},
|
||||
.impl = {
|
||||
.min_access_size = 1,
|
||||
.max_access_size = 8,
|
||||
},
|
||||
};
|
||||
|
||||
static int vfio_setup_region_sparse_mmaps(VFIORegion *region,
|
||||
struct vfio_region_info *info)
|
||||
{
|
||||
struct vfio_info_cap_header *hdr;
|
||||
struct vfio_region_info_cap_sparse_mmap *sparse;
|
||||
int i, j;
|
||||
|
||||
hdr = vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMAP);
|
||||
if (!hdr) {
|
||||
return -ENODEV;
|
||||
}
|
||||
|
||||
sparse = container_of(hdr, struct vfio_region_info_cap_sparse_mmap, header);
|
||||
|
||||
trace_vfio_region_sparse_mmap_header(region->vbasedev->name,
|
||||
region->nr, sparse->nr_areas);
|
||||
|
||||
region->mmaps = g_new0(VFIOMmap, sparse->nr_areas);
|
||||
|
||||
for (i = 0, j = 0; i < sparse->nr_areas; i++) {
|
||||
if (sparse->areas[i].size) {
|
||||
trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset,
|
||||
sparse->areas[i].offset +
|
||||
sparse->areas[i].size - 1);
|
||||
region->mmaps[j].offset = sparse->areas[i].offset;
|
||||
region->mmaps[j].size = sparse->areas[i].size;
|
||||
j++;
|
||||
}
|
||||
}
|
||||
|
||||
region->nr_mmaps = j;
|
||||
region->mmaps = g_realloc(region->mmaps, j * sizeof(VFIOMmap));
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
|
||||
int index, const char *name)
|
||||
{
|
||||
g_autofree struct vfio_region_info *info = NULL;
|
||||
int ret;
|
||||
|
||||
ret = vfio_get_region_info(vbasedev, index, &info);
|
||||
if (ret) {
|
||||
return ret;
|
||||
}
|
||||
|
||||
region->vbasedev = vbasedev;
|
||||
region->flags = info->flags;
|
||||
region->size = info->size;
|
||||
region->fd_offset = info->offset;
|
||||
region->nr = index;
|
||||
|
||||
if (region->size) {
|
||||
region->mem = g_new0(MemoryRegion, 1);
|
||||
memory_region_init_io(region->mem, obj, &vfio_region_ops,
|
||||
region, name, region->size);
|
||||
|
||||
if (!vbasedev->no_mmap &&
|
||||
region->flags & VFIO_REGION_INFO_FLAG_MMAP) {
|
||||
|
||||
ret = vfio_setup_region_sparse_mmaps(region, info);
|
||||
|
||||
if (ret) {
|
||||
region->nr_mmaps = 1;
|
||||
region->mmaps = g_new0(VFIOMmap, region->nr_mmaps);
|
||||
region->mmaps[0].offset = 0;
|
||||
region->mmaps[0].size = region->size;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
trace_vfio_region_setup(vbasedev->name, index, name,
|
||||
region->flags, region->fd_offset, region->size);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static void vfio_subregion_unmap(VFIORegion *region, int index)
|
||||
{
|
||||
trace_vfio_region_unmap(memory_region_name(®ion->mmaps[index].mem),
|
||||
region->mmaps[index].offset,
|
||||
region->mmaps[index].offset +
|
||||
region->mmaps[index].size - 1);
|
||||
memory_region_del_subregion(region->mem, ®ion->mmaps[index].mem);
|
||||
munmap(region->mmaps[index].mmap, region->mmaps[index].size);
|
||||
object_unparent(OBJECT(®ion->mmaps[index].mem));
|
||||
region->mmaps[index].mmap = NULL;
|
||||
}
|
||||
|
||||
int vfio_region_mmap(VFIORegion *region)
|
||||
{
|
||||
int i, ret, prot = 0;
|
||||
char *name;
|
||||
|
||||
if (!region->mem) {
|
||||
return 0;
|
||||
}
|
||||
|
||||
prot |= region->flags & VFIO_REGION_INFO_FLAG_READ ? PROT_READ : 0;
|
||||
prot |= region->flags & VFIO_REGION_INFO_FLAG_WRITE ? PROT_WRITE : 0;
|
||||
|
||||
for (i = 0; i < region->nr_mmaps; i++) {
|
||||
size_t align = MIN(1ULL << ctz64(region->mmaps[i].size), 1 * GiB);
|
||||
void *map_base, *map_align;
|
||||
|
||||
/*
|
||||
* Align the mmap for more efficient mapping in the kernel. Ideally
|
||||
* we'd know the PMD and PUD mapping sizes to use as discrete alignment
|
||||
* intervals, but we don't. As of Linux v6.12, the largest PUD size
|
||||
* supporting huge pfnmap is 1GiB (ARCH_SUPPORTS_PUD_PFNMAP is only set
|
||||
* on x86_64). Align by power-of-two size, capped at 1GiB.
|
||||
*
|
||||
* NB. qemu_memalign() and friends actually allocate memory, whereas
|
||||
* the region size here can exceed host memory, therefore we manually
|
||||
* create an oversized anonymous mapping and clean it up for alignment.
|
||||
*/
|
||||
map_base = mmap(0, region->mmaps[i].size + align, PROT_NONE,
|
||||
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
|
||||
if (map_base == MAP_FAILED) {
|
||||
ret = -errno;
|
||||
goto no_mmap;
|
||||
}
|
||||
|
||||
map_align = (void *)ROUND_UP((uintptr_t)map_base, (uintptr_t)align);
|
||||
munmap(map_base, map_align - map_base);
|
||||
munmap(map_align + region->mmaps[i].size,
|
||||
align - (map_align - map_base));
|
||||
|
||||
region->mmaps[i].mmap = mmap(map_align, region->mmaps[i].size, prot,
|
||||
MAP_SHARED | MAP_FIXED,
|
||||
region->vbasedev->fd,
|
||||
region->fd_offset +
|
||||
region->mmaps[i].offset);
|
||||
if (region->mmaps[i].mmap == MAP_FAILED) {
|
||||
ret = -errno;
|
||||
goto no_mmap;
|
||||
}
|
||||
|
||||
name = g_strdup_printf("%s mmaps[%d]",
|
||||
memory_region_name(region->mem), i);
|
||||
memory_region_init_ram_device_ptr(®ion->mmaps[i].mem,
|
||||
memory_region_owner(region->mem),
|
||||
name, region->mmaps[i].size,
|
||||
region->mmaps[i].mmap);
|
||||
g_free(name);
|
||||
memory_region_add_subregion(region->mem, region->mmaps[i].offset,
|
||||
®ion->mmaps[i].mem);
|
||||
|
||||
trace_vfio_region_mmap(memory_region_name(®ion->mmaps[i].mem),
|
||||
region->mmaps[i].offset,
|
||||
region->mmaps[i].offset +
|
||||
region->mmaps[i].size - 1);
|
||||
}
|
||||
|
||||
return 0;
|
||||
|
||||
no_mmap:
|
||||
trace_vfio_region_mmap_fault(memory_region_name(region->mem), i,
|
||||
region->fd_offset + region->mmaps[i].offset,
|
||||
region->fd_offset + region->mmaps[i].offset +
|
||||
region->mmaps[i].size - 1, ret);
|
||||
|
||||
region->mmaps[i].mmap = NULL;
|
||||
|
||||
for (i--; i >= 0; i--) {
|
||||
vfio_subregion_unmap(region, i);
|
||||
}
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
void vfio_region_unmap(VFIORegion *region)
|
||||
{
|
||||
int i;
|
||||
|
||||
if (!region->mem) {
|
||||
return;
|
||||
}
|
||||
|
||||
for (i = 0; i < region->nr_mmaps; i++) {
|
||||
if (region->mmaps[i].mmap) {
|
||||
vfio_subregion_unmap(region, i);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
void vfio_region_exit(VFIORegion *region)
|
||||
{
|
||||
int i;
|
||||
|
||||
if (!region->mem) {
|
||||
return;
|
||||
}
|
||||
|
||||
for (i = 0; i < region->nr_mmaps; i++) {
|
||||
if (region->mmaps[i].mmap) {
|
||||
memory_region_del_subregion(region->mem, ®ion->mmaps[i].mem);
|
||||
}
|
||||
}
|
||||
|
||||
trace_vfio_region_exit(region->vbasedev->name, region->nr);
|
||||
}
|
||||
|
||||
void vfio_region_finalize(VFIORegion *region)
|
||||
{
|
||||
int i;
|
||||
|
||||
if (!region->mem) {
|
||||
return;
|
||||
}
|
||||
|
||||
for (i = 0; i < region->nr_mmaps; i++) {
|
||||
if (region->mmaps[i].mmap) {
|
||||
munmap(region->mmaps[i].mmap, region->mmaps[i].size);
|
||||
object_unparent(OBJECT(®ion->mmaps[i].mem));
|
||||
}
|
||||
}
|
||||
|
||||
object_unparent(OBJECT(region->mem));
|
||||
|
||||
g_free(region->mem);
|
||||
g_free(region->mmaps);
|
||||
|
||||
trace_vfio_region_finalize(region->vbasedev->name, region->nr);
|
||||
|
||||
region->mem = NULL;
|
||||
region->mmaps = NULL;
|
||||
region->nr_mmaps = 0;
|
||||
region->size = 0;
|
||||
region->flags = 0;
|
||||
region->nr = 0;
|
||||
}
|
||||
|
||||
void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled)
|
||||
{
|
||||
int i;
|
||||
|
||||
if (!region->mem) {
|
||||
return;
|
||||
}
|
||||
|
||||
for (i = 0; i < region->nr_mmaps; i++) {
|
||||
if (region->mmaps[i].mmap) {
|
||||
memory_region_set_enabled(®ion->mmaps[i].mem, enabled);
|
||||
}
|
||||
}
|
||||
|
||||
trace_vfio_region_mmaps_set_enabled(memory_region_name(region->mem),
|
||||
enabled);
|
||||
}
|
||||
|
|
@ -90,8 +90,6 @@ vfio_pci_igd_host_bridge_enabled(const char *name) "%s"
|
|||
vfio_pci_igd_lpc_bridge_enabled(const char *name) "%s"
|
||||
|
||||
# common.c
|
||||
vfio_region_write(const char *name, int index, uint64_t addr, uint64_t data, unsigned size) " (%s:region%d+0x%"PRIx64", 0x%"PRIx64 ", %d)"
|
||||
vfio_region_read(char *name, int index, uint64_t addr, unsigned size, uint64_t data) " (%s:region%d+0x%"PRIx64", %d) = 0x%"PRIx64
|
||||
vfio_iommu_map_notify(const char *op, uint64_t iova_start, uint64_t iova_end) "iommu %s @ 0x%"PRIx64" - 0x%"PRIx64
|
||||
vfio_listener_region_skip(const char *name, uint64_t start, uint64_t end) "SKIPPING %s 0x%"PRIx64" - 0x%"PRIx64
|
||||
vfio_spapr_group_attach(int groupfd, int tablefd) "Attached groupfd %d to liobn fd %d"
|
||||
|
|
@ -107,6 +105,15 @@ vfio_disconnect_container(int fd) "close container->fd=%d"
|
|||
vfio_put_group(int fd) "close group->fd=%d"
|
||||
vfio_get_device(const char * name, unsigned int flags, unsigned int num_regions, unsigned int num_irqs) "Device %s flags: %u, regions: %u, irqs: %u"
|
||||
vfio_put_base_device(int fd) "close vdev->fd=%d"
|
||||
vfio_get_dev_region(const char *name, int index, uint32_t type, uint32_t subtype) "%s index %d, %08x/%08x"
|
||||
vfio_legacy_dma_unmap_overflow_workaround(void) ""
|
||||
vfio_get_dirty_bitmap(uint64_t iova, uint64_t size, uint64_t bitmap_size, uint64_t start, uint64_t dirty_pages) "iova=0x%"PRIx64" size= 0x%"PRIx64" bitmap_size=0x%"PRIx64" start=0x%"PRIx64" dirty_pages=%"PRIu64
|
||||
vfio_iommu_map_dirty_notify(uint64_t iova_start, uint64_t iova_end) "iommu dirty @ 0x%"PRIx64" - 0x%"PRIx64
|
||||
vfio_reset_handler(void) ""
|
||||
|
||||
# region.c
|
||||
vfio_region_write(const char *name, int index, uint64_t addr, uint64_t data, unsigned size) " (%s:region%d+0x%"PRIx64", 0x%"PRIx64 ", %d)"
|
||||
vfio_region_read(char *name, int index, uint64_t addr, unsigned size, uint64_t data) " (%s:region%d+0x%"PRIx64", %d) = 0x%"PRIx64
|
||||
vfio_region_setup(const char *dev, int index, const char *name, unsigned long flags, unsigned long offset, unsigned long size) "Device %s, region %d \"%s\", flags: 0x%lx, offset: 0x%lx, size: 0x%lx"
|
||||
vfio_region_mmap_fault(const char *name, int index, unsigned long offset, unsigned long size, int fault) "Region %s mmaps[%d], [0x%lx - 0x%lx], fault: %d"
|
||||
vfio_region_mmap(const char *name, unsigned long offset, unsigned long end) "Region %s [0x%lx - 0x%lx]"
|
||||
|
|
@ -116,11 +123,6 @@ vfio_region_mmaps_set_enabled(const char *name, bool enabled) "Region %s mmaps e
|
|||
vfio_region_unmap(const char *name, unsigned long offset, unsigned long end) "Region %s unmap [0x%lx - 0x%lx]"
|
||||
vfio_region_sparse_mmap_header(const char *name, int index, int nr_areas) "Device %s region %d: %d sparse mmap entries"
|
||||
vfio_region_sparse_mmap_entry(int i, unsigned long start, unsigned long end) "sparse entry %d [0x%lx - 0x%lx]"
|
||||
vfio_get_dev_region(const char *name, int index, uint32_t type, uint32_t subtype) "%s index %d, %08x/%08x"
|
||||
vfio_legacy_dma_unmap_overflow_workaround(void) ""
|
||||
vfio_get_dirty_bitmap(uint64_t iova, uint64_t size, uint64_t bitmap_size, uint64_t start, uint64_t dirty_pages) "iova=0x%"PRIx64" size= 0x%"PRIx64" bitmap_size=0x%"PRIx64" start=0x%"PRIx64" dirty_pages=%"PRIu64
|
||||
vfio_iommu_map_dirty_notify(uint64_t iova_start, uint64_t iova_end) "iommu dirty @ 0x%"PRIx64" - 0x%"PRIx64
|
||||
vfio_reset_handler(void) ""
|
||||
|
||||
# platform.c
|
||||
vfio_platform_realize(char *name, char *compat) "vfio device %s, compat = %s"
|
||||
|
|
|
|||
|
|
@ -11,6 +11,7 @@
|
|||
|
||||
#include "ui/console.h"
|
||||
#include "hw/display/ramfb.h"
|
||||
#include "hw/vfio/vfio-region.h"
|
||||
|
||||
typedef struct VFIODMABuf {
|
||||
QemuDmaBuf *buf;
|
||||
|
|
|
|||
|
|
@ -39,25 +39,6 @@ enum {
|
|||
VFIO_DEVICE_TYPE_CCW = 2,
|
||||
VFIO_DEVICE_TYPE_AP = 3,
|
||||
};
|
||||
|
||||
typedef struct VFIOMmap {
|
||||
MemoryRegion mem;
|
||||
void *mmap;
|
||||
off_t offset;
|
||||
size_t size;
|
||||
} VFIOMmap;
|
||||
|
||||
typedef struct VFIORegion {
|
||||
struct VFIODevice *vbasedev;
|
||||
off_t fd_offset; /* offset of region within device fd */
|
||||
MemoryRegion *mem; /* slow, read/write access */
|
||||
size_t size;
|
||||
uint32_t flags; /* VFIO region flags (rd/wr/mmap) */
|
||||
uint32_t nr_mmaps;
|
||||
VFIOMmap *mmaps;
|
||||
uint8_t nr; /* cache the region number for debug */
|
||||
} VFIORegion;
|
||||
|
||||
struct VFIOGroup;
|
||||
|
||||
typedef struct VFIOContainer {
|
||||
|
|
@ -168,17 +149,7 @@ void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index);
|
|||
void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index);
|
||||
bool vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex,
|
||||
int action, int fd, Error **errp);
|
||||
void vfio_region_write(void *opaque, hwaddr addr,
|
||||
uint64_t data, unsigned size);
|
||||
uint64_t vfio_region_read(void *opaque,
|
||||
hwaddr addr, unsigned size);
|
||||
int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
|
||||
int index, const char *name);
|
||||
int vfio_region_mmap(VFIORegion *region);
|
||||
void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled);
|
||||
void vfio_region_unmap(VFIORegion *region);
|
||||
void vfio_region_exit(VFIORegion *region);
|
||||
void vfio_region_finalize(VFIORegion *region);
|
||||
|
||||
void vfio_reset_handler(void *opaque);
|
||||
struct vfio_device_info *vfio_get_device_info(int fd);
|
||||
bool vfio_device_is_mdev(VFIODevice *vbasedev);
|
||||
|
|
@ -194,7 +165,6 @@ int vfio_kvm_device_del_fd(int fd, Error **errp);
|
|||
bool vfio_cpr_register_container(VFIOContainerBase *bcontainer, Error **errp);
|
||||
void vfio_cpr_unregister_container(VFIOContainerBase *bcontainer);
|
||||
|
||||
extern const MemoryRegionOps vfio_region_ops;
|
||||
typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList;
|
||||
typedef QLIST_HEAD(VFIODeviceList, VFIODevice) VFIODeviceList;
|
||||
extern VFIOGroupList vfio_group_list;
|
||||
|
|
|
|||
|
|
@ -47,6 +47,8 @@ typedef struct VFIOINTp {
|
|||
/* function type for user side eventfd handler */
|
||||
typedef void (*eventfd_user_side_handler_t)(VFIOINTp *intp);
|
||||
|
||||
typedef struct VFIORegion VFIORegion;
|
||||
|
||||
struct VFIOPlatformDevice {
|
||||
SysBusDevice sbdev;
|
||||
VFIODevice vbasedev; /* not a QOM object */
|
||||
|
|
|
|||
47
include/hw/vfio/vfio-region.h
Normal file
47
include/hw/vfio/vfio-region.h
Normal file
|
|
@ -0,0 +1,47 @@
|
|||
/*
|
||||
* VFIO region
|
||||
*
|
||||
* Copyright Red Hat, Inc. 2025
|
||||
*
|
||||
* SPDX-License-Identifier: GPL-2.0-or-later
|
||||
*/
|
||||
|
||||
#ifndef HW_VFIO_REGION_H
|
||||
#define HW_VFIO_REGION_H
|
||||
|
||||
#include "system/memory.h"
|
||||
|
||||
typedef struct VFIOMmap {
|
||||
MemoryRegion mem;
|
||||
void *mmap;
|
||||
off_t offset;
|
||||
size_t size;
|
||||
} VFIOMmap;
|
||||
|
||||
typedef struct VFIODevice VFIODevice;
|
||||
|
||||
typedef struct VFIORegion {
|
||||
struct VFIODevice *vbasedev;
|
||||
off_t fd_offset; /* offset of region within device fd */
|
||||
MemoryRegion *mem; /* slow, read/write access */
|
||||
size_t size;
|
||||
uint32_t flags; /* VFIO region flags (rd/wr/mmap) */
|
||||
uint32_t nr_mmaps;
|
||||
VFIOMmap *mmaps;
|
||||
uint8_t nr; /* cache the region number for debug */
|
||||
} VFIORegion;
|
||||
|
||||
|
||||
void vfio_region_write(void *opaque, hwaddr addr,
|
||||
uint64_t data, unsigned size);
|
||||
uint64_t vfio_region_read(void *opaque,
|
||||
hwaddr addr, unsigned size);
|
||||
int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
|
||||
int index, const char *name);
|
||||
int vfio_region_mmap(VFIORegion *region);
|
||||
void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled);
|
||||
void vfio_region_unmap(VFIORegion *region);
|
||||
void vfio_region_exit(VFIORegion *region);
|
||||
void vfio_region_finalize(VFIORegion *region);
|
||||
|
||||
#endif /* HW_VFIO_REGION_H */
|
||||
Loading…
Add table
Add a link
Reference in a new issue