@@ -91,9 +91,13 @@ void vfio_user_disconnect(VFIOUserProxy *proxy);
void vfio_user_set_handler(VFIODevice *vbasedev,
void (*handler)(void *opaque, VFIOUserMsg *msg),
void *reqarg);
-int vfio_user_get_device(VFIODevice *vbasedev, Error **errp);
+int vfio_user_get_device(VFIOGroup *group, VFIODevice *vbasedev, Error **errp);
+VFIOGroup *vfio_user_get_group(VFIOUserProxy *proxy, AddressSpace *as,
+ Error **errp);
+void vfio_user_put_group(VFIOGroup *group);
int vfio_user_validate_version(VFIOUserProxy *proxy, Error **errp);
extern VFIODeviceIO vfio_dev_io_sock;
+extern VFIOContainerIO vfio_cont_io_sock;
#endif /* VFIO_USER_H */
@@ -94,6 +94,7 @@ typedef struct VFIOContainer {
uint64_t max_dirty_bitmap_size;
unsigned long pgsizes;
unsigned int dma_max_mappings;
+ VFIOUserProxy *proxy;
QLIST_HEAD(, VFIOGuestIOMMU) giommu_list;
QLIST_HEAD(, VFIOHostDMAWindow) hostwin_list;
QLIST_HEAD(, VFIOGroup) group_list;
@@ -236,6 +237,7 @@ typedef struct VFIODisplay {
} dmabuf;
} VFIODisplay;
+int vfio_ram_block_discard_disable(VFIOContainer *container, bool state);
void vfio_put_base_device(VFIODevice *vbasedev);
void vfio_disable_irqindex(VFIODevice *vbasedev, int index);
void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index);
@@ -244,6 +246,9 @@ void vfio_unmask_single_irq(VFIODevice *vbasedev, int index, int irq);
void vfio_mask_single_irq(VFIODevice *vbasedev, int index, int irq);
int vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex,
int action, int fd, Error **errp);
+void vfio_host_win_add(VFIOContainer *container, hwaddr min_iova,
+ hwaddr max_iova, uint64_t iova_pgsizes);
+void vfio_listener_release(VFIOContainer *container);
void vfio_region_write(void *opaque, hwaddr addr,
uint64_t data, unsigned size);
uint64_t vfio_region_read(void *opaque,
@@ -256,11 +261,16 @@ void vfio_region_unmap(VFIORegion *region);
void vfio_region_exit(VFIORegion *region);
void vfio_region_finalize(VFIORegion *region);
void vfio_reset_handler(void *opaque);
+VFIOAddressSpace *vfio_get_address_space(AddressSpace *as);
+void vfio_put_address_space(VFIOAddressSpace *space);
VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp);
void vfio_put_group(VFIOGroup *group);
int vfio_get_device(VFIOGroup *group, const char *name,
VFIODevice *vbasedev, Error **errp);
+VFIOContainer *vfio_new_container(VFIOAddressSpace *space);
+void vfio_link_container(VFIOContainer *container, VFIOGroup *group);
+void vfio_unmap_container(VFIOContainer *container);
void vfio_init_device(VFIODevice *vbasedev, VFIOGroup *group,
struct vfio_device_info *info);
@@ -164,7 +164,7 @@ static const char *index_to_str(VFIODevice *vbasedev, int index)
}
}
-static int vfio_ram_block_discard_disable(VFIOContainer *container, bool state)
+int vfio_ram_block_discard_disable(VFIOContainer *container, bool state)
{
switch (container->iommu_type) {
case VFIO_TYPE1v2_IOMMU:
@@ -532,7 +532,7 @@ static int vfio_dma_map(VFIOContainer *container, hwaddr iova,
return ret;
}
-static void vfio_host_win_add(VFIOContainer *container,
+void vfio_host_win_add(VFIOContainer *container,
hwaddr min_iova, hwaddr max_iova,
uint64_t iova_pgsizes)
{
@@ -1495,7 +1495,7 @@ static const MemoryListener vfio_memory_listener = {
.log_sync = vfio_listener_log_sync,
};
-static void vfio_listener_release(VFIOContainer *container)
+void vfio_listener_release(VFIOContainer *container)
{
memory_listener_unregister(&container->listener);
if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
@@ -1873,7 +1873,7 @@ static void vfio_kvm_device_del_group(VFIOGroup *group)
#endif
}
-static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as)
+VFIOAddressSpace *vfio_get_address_space(AddressSpace *as)
{
VFIOAddressSpace *space;
@@ -1893,7 +1893,7 @@ static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as)
return space;
}
-static void vfio_put_address_space(VFIOAddressSpace *space)
+void vfio_put_address_space(VFIOAddressSpace *space)
{
if (QLIST_EMPTY(&space->containers)) {
QLIST_REMOVE(space, list);
@@ -2024,6 +2024,34 @@ static void vfio_get_iommu_info_migration(VFIOContainer *container,
}
}
+VFIOContainer *vfio_new_container(VFIOAddressSpace *space)
+{
+ VFIOContainer *container;
+
+ container = g_malloc0(sizeof(*container));
+ container->space = space;
+ container->error = NULL;
+ QLIST_INIT(&container->giommu_list);
+ QLIST_INIT(&container->hostwin_list);
+ QLIST_INIT(&container->vrdl_list);
+ QLIST_INIT(&container->group_list);
+
+ return container;
+}
+
+void vfio_link_container(VFIOContainer *container, VFIOGroup *group)
+{
+ VFIOAddressSpace *space = container->space;
+
+ QLIST_INSERT_HEAD(&space->containers, container, next);
+
+ group->container = container;
+ QLIST_INSERT_HEAD(&container->group_list, group, container_next);
+
+ container->listener = vfio_memory_listener;
+ memory_listener_register(&container->listener, space->as);
+}
+
static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
Error **errp)
{
@@ -2099,16 +2127,11 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
goto close_fd_exit;
}
- container = g_malloc0(sizeof(*container));
- container->space = space;
+ container = vfio_new_container(space);
container->fd = fd;
- container->error = NULL;
container->dirty_pages_supported = false;
container->dma_max_mappings = 0;
container->io = &vfio_cont_io_ioctl;
- QLIST_INIT(&container->giommu_list);
- QLIST_INIT(&container->hostwin_list);
- QLIST_INIT(&container->vrdl_list);
ret = vfio_init_container(container, group->fd, errp);
if (ret) {
@@ -2223,15 +2246,7 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
vfio_kvm_device_add_group(group);
- QLIST_INIT(&container->group_list);
- QLIST_INSERT_HEAD(&space->containers, container, next);
-
- group->container = container;
- QLIST_INSERT_HEAD(&container->group_list, group, container_next);
-
- container->listener = vfio_memory_listener;
-
- memory_listener_register(&container->listener, container->space->as);
+ vfio_link_container(container, group);
if (container->error) {
ret = -1;
@@ -2264,9 +2279,31 @@ put_space_exit:
return ret;
}
+void vfio_unmap_container(VFIOContainer *container)
+{
+ VFIOGuestIOMMU *giommu, *tmp;
+ VFIOHostDMAWindow *hostwin, *next;
+
+ QLIST_REMOVE(container, next);
+
+ QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, tmp) {
+ memory_region_unregister_iommu_notifier(
+ MEMORY_REGION(giommu->iommu_mr), &giommu->n);
+ QLIST_REMOVE(giommu, giommu_next);
+ g_free(giommu);
+ }
+
+ QLIST_FOREACH_SAFE(hostwin, &container->hostwin_list, hostwin_next,
+ next) {
+ QLIST_REMOVE(hostwin, hostwin_next);
+ g_free(hostwin);
+ }
+}
+
static void vfio_disconnect_container(VFIOGroup *group)
{
VFIOContainer *container = group->container;
+ VFIOAddressSpace *space = container->space;
QLIST_REMOVE(group, container_next);
group->container = NULL;
@@ -2286,24 +2323,7 @@ static void vfio_disconnect_container(VFIOGroup *group)
}
if (QLIST_EMPTY(&container->group_list)) {
- VFIOAddressSpace *space = container->space;
- VFIOGuestIOMMU *giommu, *tmp;
- VFIOHostDMAWindow *hostwin, *next;
-
- QLIST_REMOVE(container, next);
-
- QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, tmp) {
- memory_region_unregister_iommu_notifier(
- MEMORY_REGION(giommu->iommu_mr), &giommu->n);
- QLIST_REMOVE(giommu, giommu_next);
- g_free(giommu);
- }
-
- QLIST_FOREACH_SAFE(hostwin, &container->hostwin_list, hostwin_next,
- next) {
- QLIST_REMOVE(hostwin, hostwin_next);
- g_free(hostwin);
- }
+ vfio_unmap_container(container);
trace_vfio_disconnect_container(container->fd);
close(container->fd);
@@ -2503,7 +2523,9 @@ void vfio_put_base_device(VFIODevice *vbasedev)
QLIST_REMOVE(vbasedev, next);
vbasedev->group = NULL;
trace_vfio_put_base_device(vbasedev->fd);
- close(vbasedev->fd);
+ if (vbasedev->fd != -1) {
+ close(vbasedev->fd);
+ }
}
int vfio_get_region_info(VFIODevice *vbasedev, int index,
@@ -134,6 +134,7 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
VFIODevice *vbasedev = &vdev->vbasedev;
SocketAddress addr;
VFIOUserProxy *proxy;
+ VFIOGroup *group = NULL;
int ret;
Error *err = NULL;
@@ -180,8 +181,15 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
vbasedev->use_regfds = true;
vbasedev->can_mask_irq = true;
- ret = vfio_user_get_device(vbasedev, errp);
+ group = vfio_user_get_group(proxy, pci_device_iommu_address_space(pdev),
+ errp);
+ if (!group) {
+ goto error;
+ }
+
+ ret = vfio_user_get_device(group, vbasedev, errp);
if (ret) {
+ vfio_user_put_group(group);
goto error;
}
@@ -241,6 +249,7 @@ static void vfio_user_instance_finalize(Object *obj)
{
VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
VFIODevice *vbasedev = &vdev->vbasedev;
+ VFIOGroup *group = vbasedev->group;
vfio_bars_finalize(vdev);
g_free(vdev->emulated_config_bits);
@@ -251,6 +260,7 @@ static void vfio_user_instance_finalize(Object *obj)
}
vfio_put_device(vdev);
+ vfio_user_put_group(group);
if (vbasedev->proxy != NULL) {
vfio_user_disconnect(vbasedev->proxy);
@@ -18,10 +18,14 @@
#include "hw/hw.h"
#include "hw/vfio/vfio-common.h"
#include "hw/vfio/vfio.h"
+#include "exec/address-spaces.h"
+#include "exec/memory.h"
+#include "exec/ram_addr.h"
#include "qemu/sockets.h"
#include "io/channel.h"
#include "io/channel-socket.h"
#include "io/channel-util.h"
+#include "sysemu/reset.h"
#include "sysemu/iothread.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qmp/qjson.h"
@@ -847,7 +851,102 @@ void vfio_user_disconnect(VFIOUserProxy *proxy)
g_free(proxy);
}
-int vfio_user_get_device(VFIODevice *vbasedev, Error **errp)
+static int vfio_connect_proxy(VFIOUserProxy *proxy, VFIOGroup *group,
+ AddressSpace *as, Error **errp)
+{
+ VFIOAddressSpace *space;
+ VFIOContainer *container;
+ int ret;
+
+ /*
+ * try to mirror vfio_connect_container()
+ * as much as possible
+ */
+
+ space = vfio_get_address_space(as);
+
+ container = vfio_new_container(space);
+ container->fd = -1;
+ container->io = &vfio_cont_io_sock;
+ container->proxy = proxy;
+
+ /*
+ * The proxy uses a SW IOMMU in lieu of the HW one
+ * used in the ioctl() version. Mascarade as TYPE1
+ * for maximum compatibility
+ */
+ container->iommu_type = VFIO_TYPE1_IOMMU;
+
+ /*
+ * VFIO user allows the device server to map guest
+ * memory so it has the same issue with discards as
+ * a local IOMMU has.
+ */
+ ret = vfio_ram_block_discard_disable(container, true);
+ if (ret) {
+ error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken");
+ goto free_container_exit;
+ }
+
+ vfio_host_win_add(container, 0, (hwaddr)-1, proxy->dma_pgsizes);
+ container->pgsizes = proxy->dma_pgsizes;
+ container->dma_max_mappings = proxy->max_dma;
+
+ /* setup bitmask now, but migration support won't be ready until v2 */
+ container->dirty_pages_supported = true;
+ container->max_dirty_bitmap_size = proxy->max_bitmap;
+ container->dirty_pgsizes = proxy->migr_pgsize;
+
+ vfio_link_container(container, group);
+
+ if (container->error) {
+ ret = -1;
+ error_propagate_prepend(errp, container->error,
+ "memory listener initialization failed: ");
+ goto listener_release_exit;
+ }
+
+ container->initialized = true;
+
+ return 0;
+
+listener_release_exit:
+ QLIST_REMOVE(group, container_next);
+ QLIST_REMOVE(container, next);
+ vfio_listener_release(container);
+ vfio_ram_block_discard_disable(container, false);
+
+free_container_exit:
+ g_free(container);
+
+ vfio_put_address_space(space);
+
+ return ret;
+}
+
+static void vfio_disconnect_proxy(VFIOGroup *group)
+{
+ VFIOContainer *container = group->container;
+ VFIOAddressSpace *space = container->space;
+
+ /*
+ * try to mirror vfio_disconnect_container()
+ * as much as possible, knowing each device
+ * is in one group and one container
+ */
+
+ QLIST_REMOVE(group, container_next);
+ group->container = NULL;
+
+ memory_listener_unregister(&container->listener);
+
+ vfio_unmap_container(container);
+
+ g_free(container);
+ vfio_put_address_space(space);
+}
+
+int vfio_user_get_device(VFIOGroup *group, VFIODevice *vbasedev, Error **errp)
{
struct vfio_device_info info = { .argsz = sizeof(info) };
int ret;
@@ -866,11 +965,57 @@ int vfio_user_get_device(VFIODevice *vbasedev, Error **errp)
}
vbasedev->fd = -1;
- vfio_init_device(vbasedev, NULL, &info);
+ vfio_init_device(vbasedev, group, &info);
return 0;
}
+VFIOGroup *vfio_user_get_group(VFIOUserProxy *proxy, AddressSpace *as,
+ Error **errp)
+{
+ VFIOGroup *group;
+
+ /*
+ * Mirror vfio_get_group(), except that each
+ * device gets its own group and container,
+ * unrelated to any host IOMMU groupings
+ */
+ group = g_malloc0(sizeof(*group));
+ group->fd = -1;
+ group->groupid = -1;
+ QLIST_INIT(&group->device_list);
+
+ if (vfio_connect_proxy(proxy, group, as, errp)) {
+ error_prepend(errp, "failed to connect proxy");
+ g_free(group);
+ group = NULL;
+ }
+
+ if (QLIST_EMPTY(&vfio_group_list)) {
+ qemu_register_reset(vfio_reset_handler, NULL);
+ }
+
+ QLIST_INSERT_HEAD(&vfio_group_list, group, next);
+
+ return group;
+}
+
+void vfio_user_put_group(VFIOGroup *group)
+{
+ if (!group || !QLIST_EMPTY(&group->device_list)) {
+ return;
+ }
+
+ vfio_ram_block_discard_disable(group->container, false);
+ vfio_disconnect_proxy(group);
+ QLIST_REMOVE(group, next);
+ g_free(group);
+
+ if (QLIST_EMPTY(&vfio_group_list)) {
+ qemu_unregister_reset(vfio_reset_handler, NULL);
+ }
+}
+
static void vfio_user_request_msg(VFIOUserHdr *hdr, uint16_t cmd,
uint32_t size, uint32_t flags)
{
@@ -1463,3 +1608,6 @@ VFIODeviceIO vfio_dev_io_sock = {
.region_read = vfio_user_io_region_read,
.region_write = vfio_user_io_region_write,
};
+
+VFIOContainerIO vfio_cont_io_sock = {
+};