diff options
Diffstat (limited to 'hw')
| -rw-r--r-- | hw/core/vm-change-state-handler.c | 14 | ||||
| -rw-r--r-- | hw/vfio/common.c | 126 | ||||
| -rw-r--r-- | hw/vfio/migration.c | 106 | ||||
| -rw-r--r-- | hw/vfio/trace-events | 3 |
4 files changed, 208 insertions, 41 deletions
diff --git a/hw/core/vm-change-state-handler.c b/hw/core/vm-change-state-handler.c index 1f3630986d..8e2639224e 100644 --- a/hw/core/vm-change-state-handler.c +++ b/hw/core/vm-change-state-handler.c @@ -56,7 +56,19 @@ VMChangeStateEntry *qdev_add_vm_change_state_handler(DeviceState *dev, VMChangeStateHandler *cb, void *opaque) { + return qdev_add_vm_change_state_handler_full(dev, cb, NULL, opaque); +} + +/* + * Exactly like qdev_add_vm_change_state_handler() but passes a prepare_cb + * argument too. + */ +VMChangeStateEntry *qdev_add_vm_change_state_handler_full( + DeviceState *dev, VMChangeStateHandler *cb, + VMChangeStateHandler *prepare_cb, void *opaque) +{ int depth = qdev_get_dev_tree_depth(dev); - return qemu_add_vm_change_state_handler_prio(cb, opaque, depth); + return qemu_add_vm_change_state_handler_prio_full(cb, prepare_cb, opaque, + depth); } diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 9aac21abb7..134649226d 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -27,6 +27,7 @@ #include "hw/vfio/vfio-common.h" #include "hw/vfio/vfio.h" +#include "hw/vfio/pci.h" #include "exec/address-spaces.h" #include "exec/memory.h" #include "exec/ram_addr.h" @@ -363,41 +364,54 @@ bool vfio_mig_active(void) static Error *multiple_devices_migration_blocker; -static unsigned int vfio_migratable_device_num(void) +/* + * Multiple devices migration is allowed only if all devices support P2P + * migration. Single device migration is allowed regardless of P2P migration + * support. + */ +static bool vfio_multiple_devices_migration_is_supported(void) { VFIOGroup *group; VFIODevice *vbasedev; unsigned int device_num = 0; + bool all_support_p2p = true; QLIST_FOREACH(group, &vfio_group_list, next) { QLIST_FOREACH(vbasedev, &group->device_list, next) { if (vbasedev->migration) { device_num++; + + if (!(vbasedev->migration->mig_flags & VFIO_MIGRATION_P2P)) { + all_support_p2p = false; + } } } } - return device_num; + return all_support_p2p || device_num <= 1; } int vfio_block_multiple_devices_migration(VFIODevice *vbasedev, Error **errp) { int ret; - if (multiple_devices_migration_blocker || - vfio_migratable_device_num() <= 1) { + if (vfio_multiple_devices_migration_is_supported()) { return 0; } if (vbasedev->enable_migration == ON_OFF_AUTO_ON) { - error_setg(errp, "Migration is currently not supported with multiple " - "VFIO devices"); + error_setg(errp, "Multiple VFIO devices migration is supported only if " + "all of them support P2P migration"); return -EINVAL; } + if (multiple_devices_migration_blocker) { + return 0; + } + error_setg(&multiple_devices_migration_blocker, - "Migration is currently not supported with multiple " - "VFIO devices"); + "Multiple VFIO devices migration is supported only if all of " + "them support P2P migration"); ret = migrate_add_blocker(multiple_devices_migration_blocker, errp); if (ret < 0) { error_free(multiple_devices_migration_blocker); @@ -410,7 +424,7 @@ int vfio_block_multiple_devices_migration(VFIODevice *vbasedev, Error **errp) void vfio_unblock_multiple_devices_migration(void) { if (!multiple_devices_migration_blocker || - vfio_migratable_device_num() > 1) { + !vfio_multiple_devices_migration_is_supported()) { return; } @@ -437,6 +451,22 @@ static void vfio_set_migration_error(int err) } } +bool vfio_device_state_is_running(VFIODevice *vbasedev) +{ + VFIOMigration *migration = vbasedev->migration; + + return migration->device_state == VFIO_DEVICE_STATE_RUNNING || + migration->device_state == VFIO_DEVICE_STATE_RUNNING_P2P; +} + +bool vfio_device_state_is_precopy(VFIODevice *vbasedev) +{ + VFIOMigration *migration = vbasedev->migration; + + return migration->device_state == VFIO_DEVICE_STATE_PRE_COPY || + migration->device_state == VFIO_DEVICE_STATE_PRE_COPY_P2P; +} + static bool vfio_devices_all_dirty_tracking(VFIOContainer *container) { VFIOGroup *group; @@ -457,8 +487,8 @@ static bool vfio_devices_all_dirty_tracking(VFIOContainer *container) } if (vbasedev->pre_copy_dirty_page_tracking == ON_OFF_AUTO_OFF && - (migration->device_state == VFIO_DEVICE_STATE_RUNNING || - migration->device_state == VFIO_DEVICE_STATE_PRE_COPY)) { + (vfio_device_state_is_running(vbasedev) || + vfio_device_state_is_precopy(vbasedev))) { return false; } } @@ -503,8 +533,8 @@ static bool vfio_devices_all_running_and_mig_active(VFIOContainer *container) return false; } - if (migration->device_state == VFIO_DEVICE_STATE_RUNNING || - migration->device_state == VFIO_DEVICE_STATE_PRE_COPY) { + if (vfio_device_state_is_running(vbasedev) || + vfio_device_state_is_precopy(vbasedev)) { continue; } else { return false; @@ -1371,6 +1401,8 @@ typedef struct VFIODirtyRanges { hwaddr max32; hwaddr min64; hwaddr max64; + hwaddr minpci64; + hwaddr maxpci64; } VFIODirtyRanges; typedef struct VFIODirtyRangesListener { @@ -1379,6 +1411,31 @@ typedef struct VFIODirtyRangesListener { MemoryListener listener; } VFIODirtyRangesListener; +static bool vfio_section_is_vfio_pci(MemoryRegionSection *section, + VFIOContainer *container) +{ + VFIOPCIDevice *pcidev; + VFIODevice *vbasedev; + VFIOGroup *group; + Object *owner; + + owner = memory_region_owner(section->mr); + + QLIST_FOREACH(group, &container->group_list, container_next) { + QLIST_FOREACH(vbasedev, &group->device_list, next) { + if (vbasedev->type != VFIO_DEVICE_TYPE_PCI) { + continue; + } + pcidev = container_of(vbasedev, VFIOPCIDevice, vbasedev); + if (OBJECT(pcidev) == owner) { + return true; + } + } + } + + return false; +} + static void vfio_dirty_tracking_update(MemoryListener *listener, MemoryRegionSection *section) { @@ -1395,19 +1452,32 @@ static void vfio_dirty_tracking_update(MemoryListener *listener, } /* - * The address space passed to the dirty tracker is reduced to two ranges: - * one for 32-bit DMA ranges, and another one for 64-bit DMA ranges. + * The address space passed to the dirty tracker is reduced to three ranges: + * one for 32-bit DMA ranges, one for 64-bit DMA ranges and one for the + * PCI 64-bit hole. + * * The underlying reports of dirty will query a sub-interval of each of * these ranges. * - * The purpose of the dual range handling is to handle known cases of big - * holes in the address space, like the x86 AMD 1T hole. The alternative - * would be an IOVATree but that has a much bigger runtime overhead and - * unnecessary complexity. + * The purpose of the three range handling is to handle known cases of big + * holes in the address space, like the x86 AMD 1T hole, and firmware (like + * OVMF) which may relocate the pci-hole64 to the end of the address space. + * The latter would otherwise generate large ranges for tracking, stressing + * the limits of supported hardware. The pci-hole32 will always be below 4G + * (overlapping or not) so it doesn't need special handling and is part of + * the 32-bit range. + * + * The alternative would be an IOVATree but that has a much bigger runtime + * overhead and unnecessary complexity. */ - min = (end <= UINT32_MAX) ? &range->min32 : &range->min64; - max = (end <= UINT32_MAX) ? &range->max32 : &range->max64; - + if (vfio_section_is_vfio_pci(section, dirty->container) && + iova >= UINT32_MAX) { + min = &range->minpci64; + max = &range->maxpci64; + } else { + min = (end <= UINT32_MAX) ? &range->min32 : &range->min64; + max = (end <= UINT32_MAX) ? &range->max32 : &range->max64; + } if (*min > iova) { *min = iova; } @@ -1432,6 +1502,7 @@ static void vfio_dirty_tracking_init(VFIOContainer *container, memset(&dirty, 0, sizeof(dirty)); dirty.ranges.min32 = UINT32_MAX; dirty.ranges.min64 = UINT64_MAX; + dirty.ranges.minpci64 = UINT64_MAX; dirty.listener = vfio_dirty_tracking_listener; dirty.container = container; @@ -1502,7 +1573,8 @@ vfio_device_feature_dma_logging_start_create(VFIOContainer *container, * DMA logging uAPI guarantees to support at least a number of ranges that * fits into a single host kernel base page. */ - control->num_ranges = !!tracking->max32 + !!tracking->max64; + control->num_ranges = !!tracking->max32 + !!tracking->max64 + + !!tracking->maxpci64; ranges = g_try_new0(struct vfio_device_feature_dma_logging_range, control->num_ranges); if (!ranges) { @@ -1521,11 +1593,17 @@ vfio_device_feature_dma_logging_start_create(VFIOContainer *container, if (tracking->max64) { ranges->iova = tracking->min64; ranges->length = (tracking->max64 - tracking->min64) + 1; + ranges++; + } + if (tracking->maxpci64) { + ranges->iova = tracking->minpci64; + ranges->length = (tracking->maxpci64 - tracking->minpci64) + 1; } trace_vfio_device_dirty_tracking_start(control->num_ranges, tracking->min32, tracking->max32, - tracking->min64, tracking->max64); + tracking->min64, tracking->max64, + tracking->minpci64, tracking->maxpci64); return feature; } diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c index 2674f4bc47..da43dcd2fe 100644 --- a/hw/vfio/migration.c +++ b/hw/vfio/migration.c @@ -71,8 +71,12 @@ static const char *mig_state_to_str(enum vfio_device_mig_state state) return "STOP_COPY"; case VFIO_DEVICE_STATE_RESUMING: return "RESUMING"; + case VFIO_DEVICE_STATE_RUNNING_P2P: + return "RUNNING_P2P"; case VFIO_DEVICE_STATE_PRE_COPY: return "PRE_COPY"; + case VFIO_DEVICE_STATE_PRE_COPY_P2P: + return "PRE_COPY_P2P"; default: return "UNKNOWN STATE"; } @@ -331,6 +335,36 @@ static bool vfio_precopy_supported(VFIODevice *vbasedev) /* ---------------------------------------------------------------------- */ +static int vfio_save_prepare(void *opaque, Error **errp) +{ + VFIODevice *vbasedev = opaque; + + /* + * Snapshot doesn't use postcopy nor background snapshot, so allow snapshot + * even if they are on. + */ + if (runstate_check(RUN_STATE_SAVE_VM)) { + return 0; + } + + if (migrate_postcopy_ram()) { + error_setg( + errp, "%s: VFIO migration is not supported with postcopy migration", + vbasedev->name); + return -EOPNOTSUPP; + } + + if (migrate_background_snapshot()) { + error_setg( + errp, + "%s: VFIO migration is not supported with background snapshot", + vbasedev->name); + return -EOPNOTSUPP; + } + + return 0; +} + static int vfio_save_setup(QEMUFile *f, void *opaque) { VFIODevice *vbasedev = opaque; @@ -383,6 +417,19 @@ static void vfio_save_cleanup(void *opaque) VFIODevice *vbasedev = opaque; VFIOMigration *migration = vbasedev->migration; + /* + * Changing device state from STOP_COPY to STOP can take time. Do it here, + * after migration has completed, so it won't increase downtime. + */ + if (migration->device_state == VFIO_DEVICE_STATE_STOP_COPY) { + /* + * If setting the device in STOP state fails, the device should be + * reset. To do so, use ERROR state as a recover state. + */ + vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_STOP, + VFIO_DEVICE_STATE_ERROR); + } + g_free(migration->data_buffer); migration->data_buffer = NULL; migration->precopy_init_size = 0; @@ -398,7 +445,7 @@ static void vfio_state_pending_estimate(void *opaque, uint64_t *must_precopy, VFIODevice *vbasedev = opaque; VFIOMigration *migration = vbasedev->migration; - if (migration->device_state != VFIO_DEVICE_STATE_PRE_COPY) { + if (!vfio_device_state_is_precopy(vbasedev)) { return; } @@ -431,7 +478,7 @@ static void vfio_state_pending_exact(void *opaque, uint64_t *must_precopy, vfio_query_stop_copy_size(vbasedev, &stop_copy_size); *must_precopy += stop_copy_size; - if (migration->device_state == VFIO_DEVICE_STATE_PRE_COPY) { + if (vfio_device_state_is_precopy(vbasedev)) { vfio_query_precopy_size(migration); *must_precopy += @@ -446,9 +493,8 @@ static void vfio_state_pending_exact(void *opaque, uint64_t *must_precopy, static bool vfio_is_active_iterate(void *opaque) { VFIODevice *vbasedev = opaque; - VFIOMigration *migration = vbasedev->migration; - return migration->device_state == VFIO_DEVICE_STATE_PRE_COPY; + return vfio_device_state_is_precopy(vbasedev); } static int vfio_save_iterate(QEMUFile *f, void *opaque) @@ -508,12 +554,6 @@ static int vfio_save_complete_precopy(QEMUFile *f, void *opaque) return ret; } - /* - * If setting the device in STOP state fails, the device should be reset. - * To do so, use ERROR state as a recover state. - */ - ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_STOP, - VFIO_DEVICE_STATE_ERROR); trace_vfio_save_complete_precopy(vbasedev->name, ret); return ret; @@ -630,6 +670,7 @@ static bool vfio_switchover_ack_needed(void *opaque) } static const SaveVMHandlers savevm_vfio_handlers = { + .save_prepare = vfio_save_prepare, .save_setup = vfio_save_setup, .save_cleanup = vfio_save_cleanup, .state_pending_estimate = vfio_state_pending_estimate, @@ -646,18 +687,50 @@ static const SaveVMHandlers savevm_vfio_handlers = { /* ---------------------------------------------------------------------- */ -static void vfio_vmstate_change(void *opaque, bool running, RunState state) +static void vfio_vmstate_change_prepare(void *opaque, bool running, + RunState state) { VFIODevice *vbasedev = opaque; VFIOMigration *migration = vbasedev->migration; enum vfio_device_mig_state new_state; int ret; + new_state = migration->device_state == VFIO_DEVICE_STATE_PRE_COPY ? + VFIO_DEVICE_STATE_PRE_COPY_P2P : + VFIO_DEVICE_STATE_RUNNING_P2P; + + /* + * If setting the device in new_state fails, the device should be reset. + * To do so, use ERROR state as a recover state. + */ + ret = vfio_migration_set_state(vbasedev, new_state, + VFIO_DEVICE_STATE_ERROR); + if (ret) { + /* + * Migration should be aborted in this case, but vm_state_notify() + * currently does not support reporting failures. + */ + if (migrate_get_current()->to_dst_file) { + qemu_file_set_error(migrate_get_current()->to_dst_file, ret); + } + } + + trace_vfio_vmstate_change_prepare(vbasedev->name, running, + RunState_str(state), + mig_state_to_str(new_state)); +} + +static void vfio_vmstate_change(void *opaque, bool running, RunState state) +{ + VFIODevice *vbasedev = opaque; + enum vfio_device_mig_state new_state; + int ret; + if (running) { new_state = VFIO_DEVICE_STATE_RUNNING; } else { new_state = - (migration->device_state == VFIO_DEVICE_STATE_PRE_COPY && + (vfio_device_state_is_precopy(vbasedev) && (state == RUN_STATE_FINISH_MIGRATE || state == RUN_STATE_PAUSED)) ? VFIO_DEVICE_STATE_STOP_COPY : VFIO_DEVICE_STATE_STOP; @@ -753,6 +826,7 @@ static int vfio_migration_init(VFIODevice *vbasedev) char id[256] = ""; g_autofree char *path = NULL, *oid = NULL; uint64_t mig_flags = 0; + VMChangeStateHandler *prepare_cb; if (!vbasedev->ops->vfio_get_object) { return -EINVAL; @@ -793,9 +867,11 @@ static int vfio_migration_init(VFIODevice *vbasedev) register_savevm_live(id, VMSTATE_INSTANCE_ID_ANY, 1, &savevm_vfio_handlers, vbasedev); - migration->vm_state = qdev_add_vm_change_state_handler(vbasedev->dev, - vfio_vmstate_change, - vbasedev); + prepare_cb = migration->mig_flags & VFIO_MIGRATION_P2P ? + vfio_vmstate_change_prepare : + NULL; + migration->vm_state = qdev_add_vm_change_state_handler_full( + vbasedev->dev, vfio_vmstate_change, prepare_cb, vbasedev); migration->migration_state.notify = vfio_migration_state_notifier; add_migration_state_change_notifier(&migration->migration_state); diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index ee7509e68e..81ec7c7a95 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -104,7 +104,7 @@ vfio_known_safe_misalignment(const char *name, uint64_t iova, uint64_t offset_wi vfio_listener_region_add_no_dma_map(const char *name, uint64_t iova, uint64_t size, uint64_t page_size) "Region \"%s\" 0x%"PRIx64" size=0x%"PRIx64" is not aligned to 0x%"PRIx64" and cannot be mapped for DMA" vfio_listener_region_del(uint64_t start, uint64_t end) "region_del 0x%"PRIx64" - 0x%"PRIx64 vfio_device_dirty_tracking_update(uint64_t start, uint64_t end, uint64_t min, uint64_t max) "section 0x%"PRIx64" - 0x%"PRIx64" -> update [0x%"PRIx64" - 0x%"PRIx64"]" -vfio_device_dirty_tracking_start(int nr_ranges, uint64_t min32, uint64_t max32, uint64_t min64, uint64_t max64) "nr_ranges %d 32:[0x%"PRIx64" - 0x%"PRIx64"], 64:[0x%"PRIx64" - 0x%"PRIx64"]" +vfio_device_dirty_tracking_start(int nr_ranges, uint64_t min32, uint64_t max32, uint64_t min64, uint64_t max64, uint64_t minpci, uint64_t maxpci) "nr_ranges %d 32:[0x%"PRIx64" - 0x%"PRIx64"], 64:[0x%"PRIx64" - 0x%"PRIx64"], pci64:[0x%"PRIx64" - 0x%"PRIx64"]" 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" @@ -167,3 +167,4 @@ vfio_save_setup(const char *name, uint64_t data_buffer_size) " (%s) data buffer vfio_state_pending_estimate(const char *name, uint64_t precopy, uint64_t postcopy, uint64_t precopy_init_size, uint64_t precopy_dirty_size) " (%s) precopy 0x%"PRIx64" postcopy 0x%"PRIx64" precopy initial size 0x%"PRIx64" precopy dirty size 0x%"PRIx64 vfio_state_pending_exact(const char *name, uint64_t precopy, uint64_t postcopy, uint64_t stopcopy_size, uint64_t precopy_init_size, uint64_t precopy_dirty_size) " (%s) precopy 0x%"PRIx64" postcopy 0x%"PRIx64" stopcopy size 0x%"PRIx64" precopy initial size 0x%"PRIx64" precopy dirty size 0x%"PRIx64 vfio_vmstate_change(const char *name, int running, const char *reason, const char *dev_state) " (%s) running %d reason %s device state %s" +vfio_vmstate_change_prepare(const char *name, int running, const char *reason, const char *dev_state) " (%s) running %d reason %s device state %s" |