Message ID | 1562665760-26158-9-git-send-email-kwankhede@nvidia.com |
---|---|
State | New |
Headers | show |
Series | Add migration support for VFIO device | expand |
On Tue, Jul 09, 2019 at 05:49:15PM +0800, Kirti Wankhede wrote: > Define flags to be used as delimeter in migration file stream. > Added .save_setup and .save_cleanup functions. Mapped & unmapped migration > region from these functions at source during saving or pre-copy phase. > Set VFIO device state depending on VM's state. During live migration, VM is > running when .save_setup is called, _SAVING | _RUNNING state is set for VFIO > device. During save-restore, VM is paused, _SAVING state is set for VFIO device. > > Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com> > Reviewed-by: Neo Jia <cjia@nvidia.com> > --- > hw/vfio/migration.c | 82 +++++++++++++++++++++++++++++++++++++++++++++++++++- > hw/vfio/trace-events | 2 ++ > 2 files changed, 83 insertions(+), 1 deletion(-) > > diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c > index e4a89a6f9bc7..0597a45fda2d 100644 > --- a/hw/vfio/migration.c > +++ b/hw/vfio/migration.c > @@ -23,6 +23,17 @@ > #include "pci.h" > #include "trace.h" > > +/* > + * Flags used as delimiter: > + * 0xffffffff => MSB 32-bit all 1s > + * 0xef10 => emulated (virtual) function IO > + * 0x0000 => 16-bits reserved for flags > + */ > +#define VFIO_MIG_FLAG_END_OF_STATE (0xffffffffef100001ULL) > +#define VFIO_MIG_FLAG_DEV_CONFIG_STATE (0xffffffffef100002ULL) > +#define VFIO_MIG_FLAG_DEV_SETUP_STATE (0xffffffffef100003ULL) > +#define VFIO_MIG_FLAG_DEV_DATA_STATE (0xffffffffef100004ULL) > + > static void vfio_migration_region_exit(VFIODevice *vbasedev) > { > VFIOMigration *migration = vbasedev->migration; > @@ -106,6 +117,74 @@ static int vfio_migration_set_state(VFIODevice *vbasedev, uint32_t state) > return 0; > } > > +/* ---------------------------------------------------------------------- */ > + > +static int vfio_save_setup(QEMUFile *f, void *opaque) > +{ > + VFIODevice *vbasedev = opaque; > + VFIOMigration *migration = vbasedev->migration; > + int ret; > + > + qemu_put_be64(f, VFIO_MIG_FLAG_DEV_SETUP_STATE); > + > + if (migration->region.buffer.mmaps) { > + qemu_mutex_lock_iothread(); > + ret = vfio_region_mmap(&migration->region.buffer); > + qemu_mutex_unlock_iothread(); > + if (ret) { > + error_report("%s: Failed to mmap VFIO migration region %d: %s", > + vbasedev->name, migration->region.index, > + strerror(-ret)); > + return ret; > + } > + } > + > + if (vbasedev->vm_running) { > + ret = vfio_migration_set_state(vbasedev, > + VFIO_DEVICE_STATE_RUNNING | VFIO_DEVICE_STATE_SAVING); > + if (ret) { > + error_report("%s: Failed to set state RUNNING and SAVING", > + vbasedev->name); > + return ret; > + } > + } else { hi Kirti May I know in which condition will this "else" case happen? Thanks Yan > + ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_SAVING); > + if (ret) { > + error_report("%s: Failed to set state STOP and SAVING", > + vbasedev->name); > + return ret; > + } > + } > + > + qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE); > + > + ret = qemu_file_get_error(f); > + if (ret) { > + return ret; > + } > + > + trace_vfio_save_setup(vbasedev->name); > + return 0; > +} > + > +static void vfio_save_cleanup(void *opaque) > +{ > + VFIODevice *vbasedev = opaque; > + VFIOMigration *migration = vbasedev->migration; > + > + if (migration->region.buffer.mmaps) { > + vfio_region_unmap(&migration->region.buffer); > + } > + trace_vfio_save_cleanup(vbasedev->name); > +} > + > +static SaveVMHandlers savevm_vfio_handlers = { > + .save_setup = vfio_save_setup, > + .save_cleanup = vfio_save_cleanup, > +}; > + > +/* ---------------------------------------------------------------------- */ > + > static void vfio_vmstate_change(void *opaque, int running, RunState state) > { > VFIODevice *vbasedev = opaque; > @@ -195,7 +274,8 @@ static int vfio_migration_init(VFIODevice *vbasedev, > } > > qemu_mutex_init(&vbasedev->migration->lock); > - > + register_savevm_live(vbasedev->dev, "vfio", -1, 1, &savevm_vfio_handlers, > + vbasedev); > vbasedev->vm_state = qemu_add_vm_change_state_handler(vfio_vmstate_change, > vbasedev); > > diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events > index 69503228f20e..4bb43f18f315 100644 > --- a/hw/vfio/trace-events > +++ b/hw/vfio/trace-events > @@ -149,3 +149,5 @@ vfio_migration_probe(char *name, uint32_t index) " (%s) Region %d" > vfio_migration_set_state(char *name, uint32_t state) " (%s) state %d" > vfio_vmstate_change(char *name, int running, const char *reason, uint32_t dev_state) " (%s) running %d reason %s device state %d" > vfio_migration_state_notifier(char *name, int state) " (%s) state %d" > +vfio_save_setup(char *name) " (%s)" > +vfio_save_cleanup(char *name) " (%s)" > -- > 2.7.0 >
On 7/22/2019 2:04 PM, Yan Zhao wrote: > On Tue, Jul 09, 2019 at 05:49:15PM +0800, Kirti Wankhede wrote: >> Define flags to be used as delimeter in migration file stream. >> Added .save_setup and .save_cleanup functions. Mapped & unmapped migration >> region from these functions at source during saving or pre-copy phase. >> Set VFIO device state depending on VM's state. During live migration, VM is >> running when .save_setup is called, _SAVING | _RUNNING state is set for VFIO >> device. During save-restore, VM is paused, _SAVING state is set for VFIO device. >> >> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com> >> Reviewed-by: Neo Jia <cjia@nvidia.com> >> --- >> hw/vfio/migration.c | 82 +++++++++++++++++++++++++++++++++++++++++++++++++++- >> hw/vfio/trace-events | 2 ++ >> 2 files changed, 83 insertions(+), 1 deletion(-) >> >> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c >> index e4a89a6f9bc7..0597a45fda2d 100644 >> --- a/hw/vfio/migration.c >> +++ b/hw/vfio/migration.c >> @@ -23,6 +23,17 @@ >> #include "pci.h" >> #include "trace.h" >> >> +/* >> + * Flags used as delimiter: >> + * 0xffffffff => MSB 32-bit all 1s >> + * 0xef10 => emulated (virtual) function IO >> + * 0x0000 => 16-bits reserved for flags >> + */ >> +#define VFIO_MIG_FLAG_END_OF_STATE (0xffffffffef100001ULL) >> +#define VFIO_MIG_FLAG_DEV_CONFIG_STATE (0xffffffffef100002ULL) >> +#define VFIO_MIG_FLAG_DEV_SETUP_STATE (0xffffffffef100003ULL) >> +#define VFIO_MIG_FLAG_DEV_DATA_STATE (0xffffffffef100004ULL) >> + >> static void vfio_migration_region_exit(VFIODevice *vbasedev) >> { >> VFIOMigration *migration = vbasedev->migration; >> @@ -106,6 +117,74 @@ static int vfio_migration_set_state(VFIODevice *vbasedev, uint32_t state) >> return 0; >> } >> >> +/* ---------------------------------------------------------------------- */ >> + >> +static int vfio_save_setup(QEMUFile *f, void *opaque) >> +{ >> + VFIODevice *vbasedev = opaque; >> + VFIOMigration *migration = vbasedev->migration; >> + int ret; >> + >> + qemu_put_be64(f, VFIO_MIG_FLAG_DEV_SETUP_STATE); >> + >> + if (migration->region.buffer.mmaps) { >> + qemu_mutex_lock_iothread(); >> + ret = vfio_region_mmap(&migration->region.buffer); >> + qemu_mutex_unlock_iothread(); >> + if (ret) { >> + error_report("%s: Failed to mmap VFIO migration region %d: %s", >> + vbasedev->name, migration->region.index, >> + strerror(-ret)); >> + return ret; >> + } >> + } >> + >> + if (vbasedev->vm_running) { >> + ret = vfio_migration_set_state(vbasedev, >> + VFIO_DEVICE_STATE_RUNNING | VFIO_DEVICE_STATE_SAVING); >> + if (ret) { >> + error_report("%s: Failed to set state RUNNING and SAVING", >> + vbasedev->name); >> + return ret; >> + } >> + } else { > hi Kirti > May I know in which condition will this "else" case happen? > This can happen in savevm case. Thanks, Kirti > Thanks > Yan > >> + ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_SAVING); >> + if (ret) { >> + error_report("%s: Failed to set state STOP and SAVING", >> + vbasedev->name); >> + return ret; >> + } >> + } >> + >> + qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE); >> + >> + ret = qemu_file_get_error(f); >> + if (ret) { >> + return ret; >> + } >> + >> + trace_vfio_save_setup(vbasedev->name); >> + return 0; >> +} >> + >> +static void vfio_save_cleanup(void *opaque) >> +{ >> + VFIODevice *vbasedev = opaque; >> + VFIOMigration *migration = vbasedev->migration; >> + >> + if (migration->region.buffer.mmaps) { >> + vfio_region_unmap(&migration->region.buffer); >> + } >> + trace_vfio_save_cleanup(vbasedev->name); >> +} >> + >> +static SaveVMHandlers savevm_vfio_handlers = { >> + .save_setup = vfio_save_setup, >> + .save_cleanup = vfio_save_cleanup, >> +}; >> + >> +/* ---------------------------------------------------------------------- */ >> + >> static void vfio_vmstate_change(void *opaque, int running, RunState state) >> { >> VFIODevice *vbasedev = opaque; >> @@ -195,7 +274,8 @@ static int vfio_migration_init(VFIODevice *vbasedev, >> } >> >> qemu_mutex_init(&vbasedev->migration->lock); >> - >> + register_savevm_live(vbasedev->dev, "vfio", -1, 1, &savevm_vfio_handlers, >> + vbasedev); >> vbasedev->vm_state = qemu_add_vm_change_state_handler(vfio_vmstate_change, >> vbasedev); >> >> diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events >> index 69503228f20e..4bb43f18f315 100644 >> --- a/hw/vfio/trace-events >> +++ b/hw/vfio/trace-events >> @@ -149,3 +149,5 @@ vfio_migration_probe(char *name, uint32_t index) " (%s) Region %d" >> vfio_migration_set_state(char *name, uint32_t state) " (%s) state %d" >> vfio_vmstate_change(char *name, int running, const char *reason, uint32_t dev_state) " (%s) running %d reason %s device state %d" >> vfio_migration_state_notifier(char *name, int state) " (%s) state %d" >> +vfio_save_setup(char *name) " (%s)" >> +vfio_save_cleanup(char *name) " (%s)" >> -- >> 2.7.0 >>
On Wed, Aug 21, 2019 at 04:33:06AM +0800, Kirti Wankhede wrote: > > > On 7/22/2019 2:04 PM, Yan Zhao wrote: > > On Tue, Jul 09, 2019 at 05:49:15PM +0800, Kirti Wankhede wrote: > >> Define flags to be used as delimeter in migration file stream. > >> Added .save_setup and .save_cleanup functions. Mapped & unmapped migration > >> region from these functions at source during saving or pre-copy phase. > >> Set VFIO device state depending on VM's state. During live migration, VM is > >> running when .save_setup is called, _SAVING | _RUNNING state is set for VFIO > >> device. During save-restore, VM is paused, _SAVING state is set for VFIO device. > >> > >> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com> > >> Reviewed-by: Neo Jia <cjia@nvidia.com> > >> --- > >> hw/vfio/migration.c | 82 +++++++++++++++++++++++++++++++++++++++++++++++++++- > >> hw/vfio/trace-events | 2 ++ > >> 2 files changed, 83 insertions(+), 1 deletion(-) > >> > >> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c > >> index e4a89a6f9bc7..0597a45fda2d 100644 > >> --- a/hw/vfio/migration.c > >> +++ b/hw/vfio/migration.c > >> @@ -23,6 +23,17 @@ > >> #include "pci.h" > >> #include "trace.h" > >> > >> +/* > >> + * Flags used as delimiter: > >> + * 0xffffffff => MSB 32-bit all 1s > >> + * 0xef10 => emulated (virtual) function IO > >> + * 0x0000 => 16-bits reserved for flags > >> + */ > >> +#define VFIO_MIG_FLAG_END_OF_STATE (0xffffffffef100001ULL) > >> +#define VFIO_MIG_FLAG_DEV_CONFIG_STATE (0xffffffffef100002ULL) > >> +#define VFIO_MIG_FLAG_DEV_SETUP_STATE (0xffffffffef100003ULL) > >> +#define VFIO_MIG_FLAG_DEV_DATA_STATE (0xffffffffef100004ULL) > >> + > >> static void vfio_migration_region_exit(VFIODevice *vbasedev) > >> { > >> VFIOMigration *migration = vbasedev->migration; > >> @@ -106,6 +117,74 @@ static int vfio_migration_set_state(VFIODevice *vbasedev, uint32_t state) > >> return 0; > >> } > >> > >> +/* ---------------------------------------------------------------------- */ > >> + > >> +static int vfio_save_setup(QEMUFile *f, void *opaque) > >> +{ > >> + VFIODevice *vbasedev = opaque; > >> + VFIOMigration *migration = vbasedev->migration; > >> + int ret; > >> + > >> + qemu_put_be64(f, VFIO_MIG_FLAG_DEV_SETUP_STATE); > >> + > >> + if (migration->region.buffer.mmaps) { > >> + qemu_mutex_lock_iothread(); > >> + ret = vfio_region_mmap(&migration->region.buffer); > >> + qemu_mutex_unlock_iothread(); > >> + if (ret) { > >> + error_report("%s: Failed to mmap VFIO migration region %d: %s", > >> + vbasedev->name, migration->region.index, > >> + strerror(-ret)); > >> + return ret; > >> + } > >> + } > >> + > >> + if (vbasedev->vm_running) { > >> + ret = vfio_migration_set_state(vbasedev, > >> + VFIO_DEVICE_STATE_RUNNING | VFIO_DEVICE_STATE_SAVING); > >> + if (ret) { > >> + error_report("%s: Failed to set state RUNNING and SAVING", > >> + vbasedev->name); > >> + return ret; > >> + } > >> + } else { > > hi Kirti > > May I know in which condition will this "else" case happen? > > > > This can happen in savevm case. ok. I see it. thanks. Could we simplify the logic and only or VFIO_DEVICE_STATE_SAVING to current device state here? Because device state was already set to RUNNING or STOP in vfio_vmstate_change(). Thanks Yan > > Thanks, > Kirti > > > Thanks > > Yan > > > >> + ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_SAVING); > >> + if (ret) { > >> + error_report("%s: Failed to set state STOP and SAVING", > >> + vbasedev->name); > >> + return ret; > >> + } > >> + } > >> + > >> + qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE); > >> + > >> + ret = qemu_file_get_error(f); > >> + if (ret) { > >> + return ret; > >> + } > >> + > >> + trace_vfio_save_setup(vbasedev->name); > >> + return 0; > >> +} > >> + > >> +static void vfio_save_cleanup(void *opaque) > >> +{ > >> + VFIODevice *vbasedev = opaque; > >> + VFIOMigration *migration = vbasedev->migration; > >> + > >> + if (migration->region.buffer.mmaps) { > >> + vfio_region_unmap(&migration->region.buffer); > >> + } > >> + trace_vfio_save_cleanup(vbasedev->name); > >> +} > >> + > >> +static SaveVMHandlers savevm_vfio_handlers = { > >> + .save_setup = vfio_save_setup, > >> + .save_cleanup = vfio_save_cleanup, > >> +}; > >> + > >> +/* ---------------------------------------------------------------------- */ > >> + > >> static void vfio_vmstate_change(void *opaque, int running, RunState state) > >> { > >> VFIODevice *vbasedev = opaque; > >> @@ -195,7 +274,8 @@ static int vfio_migration_init(VFIODevice *vbasedev, > >> } > >> > >> qemu_mutex_init(&vbasedev->migration->lock); > >> - > >> + register_savevm_live(vbasedev->dev, "vfio", -1, 1, &savevm_vfio_handlers, > >> + vbasedev); > >> vbasedev->vm_state = qemu_add_vm_change_state_handler(vfio_vmstate_change, > >> vbasedev); > >> > >> diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events > >> index 69503228f20e..4bb43f18f315 100644 > >> --- a/hw/vfio/trace-events > >> +++ b/hw/vfio/trace-events > >> @@ -149,3 +149,5 @@ vfio_migration_probe(char *name, uint32_t index) " (%s) Region %d" > >> vfio_migration_set_state(char *name, uint32_t state) " (%s) state %d" > >> vfio_vmstate_change(char *name, int running, const char *reason, uint32_t dev_state) " (%s) running %d reason %s device state %d" > >> vfio_migration_state_notifier(char *name, int state) " (%s) state %d" > >> +vfio_save_setup(char *name) " (%s)" > >> +vfio_save_cleanup(char *name) " (%s)" > >> -- > >> 2.7.0 > >>
diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c index e4a89a6f9bc7..0597a45fda2d 100644 --- a/hw/vfio/migration.c +++ b/hw/vfio/migration.c @@ -23,6 +23,17 @@ #include "pci.h" #include "trace.h" +/* + * Flags used as delimiter: + * 0xffffffff => MSB 32-bit all 1s + * 0xef10 => emulated (virtual) function IO + * 0x0000 => 16-bits reserved for flags + */ +#define VFIO_MIG_FLAG_END_OF_STATE (0xffffffffef100001ULL) +#define VFIO_MIG_FLAG_DEV_CONFIG_STATE (0xffffffffef100002ULL) +#define VFIO_MIG_FLAG_DEV_SETUP_STATE (0xffffffffef100003ULL) +#define VFIO_MIG_FLAG_DEV_DATA_STATE (0xffffffffef100004ULL) + static void vfio_migration_region_exit(VFIODevice *vbasedev) { VFIOMigration *migration = vbasedev->migration; @@ -106,6 +117,74 @@ static int vfio_migration_set_state(VFIODevice *vbasedev, uint32_t state) return 0; } +/* ---------------------------------------------------------------------- */ + +static int vfio_save_setup(QEMUFile *f, void *opaque) +{ + VFIODevice *vbasedev = opaque; + VFIOMigration *migration = vbasedev->migration; + int ret; + + qemu_put_be64(f, VFIO_MIG_FLAG_DEV_SETUP_STATE); + + if (migration->region.buffer.mmaps) { + qemu_mutex_lock_iothread(); + ret = vfio_region_mmap(&migration->region.buffer); + qemu_mutex_unlock_iothread(); + if (ret) { + error_report("%s: Failed to mmap VFIO migration region %d: %s", + vbasedev->name, migration->region.index, + strerror(-ret)); + return ret; + } + } + + if (vbasedev->vm_running) { + ret = vfio_migration_set_state(vbasedev, + VFIO_DEVICE_STATE_RUNNING | VFIO_DEVICE_STATE_SAVING); + if (ret) { + error_report("%s: Failed to set state RUNNING and SAVING", + vbasedev->name); + return ret; + } + } else { + ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_SAVING); + if (ret) { + error_report("%s: Failed to set state STOP and SAVING", + vbasedev->name); + return ret; + } + } + + qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE); + + ret = qemu_file_get_error(f); + if (ret) { + return ret; + } + + trace_vfio_save_setup(vbasedev->name); + return 0; +} + +static void vfio_save_cleanup(void *opaque) +{ + VFIODevice *vbasedev = opaque; + VFIOMigration *migration = vbasedev->migration; + + if (migration->region.buffer.mmaps) { + vfio_region_unmap(&migration->region.buffer); + } + trace_vfio_save_cleanup(vbasedev->name); +} + +static SaveVMHandlers savevm_vfio_handlers = { + .save_setup = vfio_save_setup, + .save_cleanup = vfio_save_cleanup, +}; + +/* ---------------------------------------------------------------------- */ + static void vfio_vmstate_change(void *opaque, int running, RunState state) { VFIODevice *vbasedev = opaque; @@ -195,7 +274,8 @@ static int vfio_migration_init(VFIODevice *vbasedev, } qemu_mutex_init(&vbasedev->migration->lock); - + register_savevm_live(vbasedev->dev, "vfio", -1, 1, &savevm_vfio_handlers, + vbasedev); vbasedev->vm_state = qemu_add_vm_change_state_handler(vfio_vmstate_change, vbasedev); diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index 69503228f20e..4bb43f18f315 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -149,3 +149,5 @@ vfio_migration_probe(char *name, uint32_t index) " (%s) Region %d" vfio_migration_set_state(char *name, uint32_t state) " (%s) state %d" vfio_vmstate_change(char *name, int running, const char *reason, uint32_t dev_state) " (%s) running %d reason %s device state %d" vfio_migration_state_notifier(char *name, int state) " (%s) state %d" +vfio_save_setup(char *name) " (%s)" +vfio_save_cleanup(char *name) " (%s)"