As currently defined, initial_bytes is monotonically decreasing and precedes dirty_bytes when reading from the saving file descriptor. The transition from initial_bytes to dirty_bytes is unidirectional and irreversible. The initial_bytes are considered as critical data that is highly recommended to be transferred to the target as part of PRE_COPY, without this data, the PRE_COPY phase would be ineffective. We come to solve the case when a new chunk of critical data is introduced during the PRE_COPY phase and the driver would like to report an entirely new value for the initial_bytes. For that, we extend the VFIO_MIG_GET_PRECOPY_INFO ioctl with an output flag named VFIO_PRECOPY_INFO_REINIT to allow drivers reporting a new initial_bytes value during the PRE_COPY phase. Currently, existing VFIO_MIG_GET_PRECOPY_INFO implementations don't assign info.flags before copy_to_user(), this effectively echoes userspace-provided flags back as output, preventing the field from being used to report new reliable data from the drivers. Reliable use of the new VFIO_PRECOPY_INFO_REINIT flag requires userspace to explicitly opt in by enabling the VFIO_DEVICE_FEATURE_MIG_PRECOPY_INFOv2 device feature. When the caller opts in, the driver may report an entirely new value for initial_bytes. It may be larger, it may be smaller, it may include the previous unread initial_bytes, it may discard the previous unread initial_bytes, up to the driver logic and state. The presence of the VFIO_PRECOPY_INFO_REINIT output flag set by the driver indicates that new initial data is present on the stream. Once the caller sees this flag, the initial_bytes value should be re-evaluated relative to the readiness state for transition to STOP_COPY. Signed-off-by: Yishai Hadas --- include/uapi/linux/vfio.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index bb7b89330d35..90e51e84539d 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1266,6 +1266,17 @@ enum vfio_device_mig_state { * The initial_bytes field indicates the amount of initial precopy * data available from the device. This field should have a non-zero initial * value and decrease as migration data is read from the device. + * The presence of the VFIO_PRECOPY_INFO_REINIT output flag indicates + * that new initial data is present on the stream. + * In that case initial_bytes may report a non-zero value irrespective of + * any previously reported values, which progresses towards zero as precopy + * data is read from the data stream. dirty_bytes is also reset + * to zero and represents the state change of the device relative to the new + * initial_bytes. + * VFIO_PRECOPY_INFO_REINIT can be reported only after userspace opts in to + * VFIO_DEVICE_FEATURE_MIG_PRECOPY_INFOv2. Without this opt-in, the flags field + * of struct vfio_precopy_info is reserved for bug-compatibility reasons. + * * It is recommended to leave PRE_COPY for STOP_COPY only after this field * reaches zero. Leaving PRE_COPY earlier might make things slower. * @@ -1301,6 +1312,7 @@ enum vfio_device_mig_state { struct vfio_precopy_info { __u32 argsz; __u32 flags; +#define VFIO_PRECOPY_INFO_REINIT (1 << 0) /* output - new initial data is present */ __aligned_u64 initial_bytes; __aligned_u64 dirty_bytes; }; @@ -1510,6 +1522,16 @@ struct vfio_device_feature_dma_buf { struct vfio_region_dma_range dma_ranges[] __counted_by(nr_ranges); }; +/* + * Enables the migration precopy_info_v2 behaviour. + * + * VFIO_DEVICE_FEATURE_MIG_PRECOPY_INFOv2. + * + * On SET, enables the v2 pre_copy_info behaviour, where the + * vfio_precopy_info.flags is a valid output field. + */ +#define VFIO_DEVICE_FEATURE_MIG_PRECOPY_INFOv2 12 + /* -------- API for Type1 VFIO IOMMU -------- */ /** -- 2.18.1 Currently, existing VFIO_MIG_GET_PRECOPY_INFO implementations don't assign info.flags before copy_to_user(). Because they copy the struct in from userspace first, this effectively echoes userspace-provided flags back as output, preventing the field from being used to report new reliable data from the drivers. Add support for a new device feature named VFIO_DEVICE_FEATURE_MIG_PRECOPY_INFOv2. On SET, enables the v2 pre_copy_info behaviour, where the vfio_precopy_info.flags is a valid output field. Signed-off-by: Yishai Hadas --- drivers/vfio/pci/vfio_pci_core.c | 1 + drivers/vfio/vfio_main.c | 20 ++++++++++++++++++++ include/linux/vfio.h | 1 + 3 files changed, 22 insertions(+) diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index d43745fe4c84..1daaceb5b2c8 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -736,6 +736,7 @@ void vfio_pci_core_close_device(struct vfio_device *core_vdev) #endif vfio_pci_core_disable(vdev); + core_vdev->precopy_info_v2 = 0; vfio_pci_dma_buf_cleanup(vdev); mutex_lock(&vdev->igate); diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index 742477546b15..dcb879018f27 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -964,6 +964,23 @@ vfio_ioctl_device_feature_migration_data_size(struct vfio_device *device, return 0; } +static int +vfio_ioctl_device_feature_migration_precopy_info_v2(struct vfio_device *device, + u32 flags, size_t argsz) +{ + int ret; + + if (!(device->migration_flags & VFIO_MIGRATION_PRE_COPY)) + return -EINVAL; + + ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, 0); + if (ret != 1) + return ret; + + device->precopy_info_v2 = 1; + return 0; +} + static int vfio_ioctl_device_feature_migration(struct vfio_device *device, u32 flags, void __user *arg, size_t argsz) @@ -1251,6 +1268,9 @@ static int vfio_ioctl_device_feature(struct vfio_device *device, return vfio_ioctl_device_feature_migration_data_size( device, feature.flags, arg->data, feature.argsz - minsz); + case VFIO_DEVICE_FEATURE_MIG_PRECOPY_INFOv2: + return vfio_ioctl_device_feature_migration_precopy_info_v2( + device, feature.flags, feature.argsz - minsz); default: if (unlikely(!device->ops->device_feature)) return -ENOTTY; diff --git a/include/linux/vfio.h b/include/linux/vfio.h index e90859956514..7c1d33283e04 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -52,6 +52,7 @@ struct vfio_device { struct vfio_device_set *dev_set; struct list_head dev_set_list; unsigned int migration_flags; + u8 precopy_info_v2; struct kvm *kvm; /* Members below here are private, not for driver use */ -- 2.18.1 Introduce a core helper function for VFIO_MIG_GET_PRECOPY_INFO and adapt all drivers to use it. It centralizes the common code and ensures that output flags are cleared on entry, in case user opts in to VFIO_DEVICE_FEATURE_MIG_PRECOPY_INFOv2. This preventing any unintended echoing of userspace data back to userspace. Signed-off-by: Yishai Hadas --- .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c | 17 +++----- drivers/vfio/pci/mlx5/main.c | 18 +++------ drivers/vfio/pci/qat/main.c | 17 +++----- drivers/vfio/pci/virtio/migrate.c | 17 +++----- include/linux/vfio.h | 39 +++++++++++++++++++ samples/vfio-mdev/mtty.c | 16 +++----- 6 files changed, 68 insertions(+), 56 deletions(-) diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c index 1d367cff7dcf..bb121f635b9f 100644 --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c @@ -857,18 +857,12 @@ static long hisi_acc_vf_precopy_ioctl(struct file *filp, struct hisi_acc_vf_core_device *hisi_acc_vdev = migf->hisi_acc_vdev; loff_t *pos = &filp->f_pos; struct vfio_precopy_info info; - unsigned long minsz; int ret; - if (cmd != VFIO_MIG_GET_PRECOPY_INFO) - return -ENOTTY; - - minsz = offsetofend(struct vfio_precopy_info, dirty_bytes); - - if (copy_from_user(&info, (void __user *)arg, minsz)) - return -EFAULT; - if (info.argsz < minsz) - return -EINVAL; + ret = vfio_check_precopy_ioctl(&hisi_acc_vdev->core_device.vdev, cmd, + arg, &info); + if (ret) + return ret; mutex_lock(&hisi_acc_vdev->state_mutex); if (hisi_acc_vdev->mig_state != VFIO_DEVICE_STATE_PRE_COPY) { @@ -893,7 +887,8 @@ static long hisi_acc_vf_precopy_ioctl(struct file *filp, mutex_unlock(&migf->lock); mutex_unlock(&hisi_acc_vdev->state_mutex); - return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0; + return copy_to_user((void __user *)arg, &info, + offsetofend(struct vfio_precopy_info, dirty_bytes)) ? -EFAULT : 0; out: mutex_unlock(&migf->lock); mutex_unlock(&hisi_acc_vdev->state_mutex); diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c index dbba6173894b..fb541c17c712 100644 --- a/drivers/vfio/pci/mlx5/main.c +++ b/drivers/vfio/pci/mlx5/main.c @@ -463,21 +463,14 @@ static long mlx5vf_precopy_ioctl(struct file *filp, unsigned int cmd, struct mlx5_vhca_data_buffer *buf; struct vfio_precopy_info info = {}; loff_t *pos = &filp->f_pos; - unsigned long minsz; size_t inc_length = 0; bool end_of_data = false; int ret; - if (cmd != VFIO_MIG_GET_PRECOPY_INFO) - return -ENOTTY; - - minsz = offsetofend(struct vfio_precopy_info, dirty_bytes); - - if (copy_from_user(&info, (void __user *)arg, minsz)) - return -EFAULT; - - if (info.argsz < minsz) - return -EINVAL; + ret = vfio_check_precopy_ioctl(&mvdev->core_device.vdev, cmd, arg, + &info); + if (ret) + return ret; mutex_lock(&mvdev->state_mutex); if (mvdev->mig_state != VFIO_DEVICE_STATE_PRE_COPY && @@ -545,7 +538,8 @@ static long mlx5vf_precopy_ioctl(struct file *filp, unsigned int cmd, done: mlx5vf_state_mutex_unlock(mvdev); - if (copy_to_user((void __user *)arg, &info, minsz)) + if (copy_to_user((void __user *)arg, &info, + offsetofend(struct vfio_precopy_info, dirty_bytes))) return -EFAULT; return 0; diff --git a/drivers/vfio/pci/qat/main.c b/drivers/vfio/pci/qat/main.c index b982d4ae666c..b3a4b7a55696 100644 --- a/drivers/vfio/pci/qat/main.c +++ b/drivers/vfio/pci/qat/main.c @@ -121,18 +121,12 @@ static long qat_vf_precopy_ioctl(struct file *filp, unsigned int cmd, struct qat_mig_dev *mig_dev = qat_vdev->mdev; struct vfio_precopy_info info; loff_t *pos = &filp->f_pos; - unsigned long minsz; int ret = 0; - if (cmd != VFIO_MIG_GET_PRECOPY_INFO) - return -ENOTTY; - - minsz = offsetofend(struct vfio_precopy_info, dirty_bytes); - - if (copy_from_user(&info, (void __user *)arg, minsz)) - return -EFAULT; - if (info.argsz < minsz) - return -EINVAL; + ret = vfio_check_precopy_ioctl(&qat_vdev->core_device.vdev, cmd, arg, + &info); + if (ret) + return ret; mutex_lock(&qat_vdev->state_mutex); if (qat_vdev->mig_state != VFIO_DEVICE_STATE_PRE_COPY && @@ -160,7 +154,8 @@ static long qat_vf_precopy_ioctl(struct file *filp, unsigned int cmd, mutex_unlock(&qat_vdev->state_mutex); if (ret) return ret; - return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0; + return copy_to_user((void __user *)arg, &info, + offsetofend(struct vfio_precopy_info, dirty_bytes)) ? -EFAULT : 0; } static ssize_t qat_vf_save_read(struct file *filp, char __user *buf, diff --git a/drivers/vfio/pci/virtio/migrate.c b/drivers/vfio/pci/virtio/migrate.c index 35fa2d6ed611..7e11834ad512 100644 --- a/drivers/vfio/pci/virtio/migrate.c +++ b/drivers/vfio/pci/virtio/migrate.c @@ -443,19 +443,13 @@ static long virtiovf_precopy_ioctl(struct file *filp, unsigned int cmd, struct vfio_precopy_info info = {}; loff_t *pos = &filp->f_pos; bool end_of_data = false; - unsigned long minsz; u32 ctx_size = 0; int ret; - if (cmd != VFIO_MIG_GET_PRECOPY_INFO) - return -ENOTTY; - - minsz = offsetofend(struct vfio_precopy_info, dirty_bytes); - if (copy_from_user(&info, (void __user *)arg, minsz)) - return -EFAULT; - - if (info.argsz < minsz) - return -EINVAL; + ret = vfio_check_precopy_ioctl(&virtvdev->core_device.vdev, cmd, arg, + &info); + if (ret) + return ret; mutex_lock(&virtvdev->state_mutex); if (virtvdev->mig_state != VFIO_DEVICE_STATE_PRE_COPY && @@ -514,7 +508,8 @@ static long virtiovf_precopy_ioctl(struct file *filp, unsigned int cmd, done: virtiovf_state_mutex_unlock(virtvdev); - if (copy_to_user((void __user *)arg, &info, minsz)) + if (copy_to_user((void __user *)arg, &info, + offsetofend(struct vfio_precopy_info, dirty_bytes))) return -EFAULT; return 0; diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 7c1d33283e04..50b474334a19 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -16,6 +16,7 @@ #include #include #include +#include struct kvm; struct iommufd_ctx; @@ -285,6 +286,44 @@ static inline int vfio_check_feature(u32 flags, size_t argsz, u32 supported_ops, return 1; } +/** + * vfio_check_precopy_ioctl - Validate user input for the VFIO_MIG_GET_PRECOPY_INFO ioctl + * @vdev: The vfio device + * @cmd: Cmd from the ioctl + * @arg: Arg from the ioctl + * @info: Driver pointer to hold the userspace input to the ioctl + * + * For use in a driver's get_precopy_info. Checks that the inputs to the + * VFIO_MIG_GET_PRECOPY_INFO ioctl are correct. + + * Returns 0 on success, otherwise errno. + */ + +static inline int +vfio_check_precopy_ioctl(struct vfio_device *vdev, unsigned int cmd, + unsigned long arg, struct vfio_precopy_info *info) +{ + unsigned long minsz; + + if (cmd != VFIO_MIG_GET_PRECOPY_INFO) + return -ENOTTY; + + minsz = offsetofend(struct vfio_precopy_info, dirty_bytes); + + if (copy_from_user(info, (void __user *)arg, minsz)) + return -EFAULT; + + if (info->argsz < minsz) + return -EINVAL; + + /* keep v1 behaviour as is for compatibility reasons */ + if (vdev->precopy_info_v2) + /* flags are output, set its initial value to 0 */ + info->flags = 0; + + return 0; +} + struct vfio_device *_vfio_alloc_device(size_t size, struct device *dev, const struct vfio_device_ops *ops); #define vfio_alloc_device(dev_struct, member, dev, ops) \ diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c index bd92c38379b8..c1070af69544 100644 --- a/samples/vfio-mdev/mtty.c +++ b/samples/vfio-mdev/mtty.c @@ -837,18 +837,11 @@ static long mtty_precopy_ioctl(struct file *filp, unsigned int cmd, struct mdev_state *mdev_state = migf->mdev_state; loff_t *pos = &filp->f_pos; struct vfio_precopy_info info = {}; - unsigned long minsz; int ret; - if (cmd != VFIO_MIG_GET_PRECOPY_INFO) - return -ENOTTY; - - minsz = offsetofend(struct vfio_precopy_info, dirty_bytes); - - if (copy_from_user(&info, (void __user *)arg, minsz)) - return -EFAULT; - if (info.argsz < minsz) - return -EINVAL; + ret = vfio_check_precopy_ioctl(&mdev_state->vdev, cmd, arg, &info); + if (ret) + return ret; mutex_lock(&mdev_state->state_mutex); if (mdev_state->state != VFIO_DEVICE_STATE_PRE_COPY && @@ -875,7 +868,8 @@ static long mtty_precopy_ioctl(struct file *filp, unsigned int cmd, info.initial_bytes = migf->filled_size - *pos; mutex_unlock(&migf->lock); - ret = copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0; + ret = copy_to_user((void __user *)arg, &info, + offsetofend(struct vfio_precopy_info, dirty_bytes)) ? -EFAULT : 0; unlock: mtty_state_mutex_unlock(mdev_state); return ret; -- 2.18.1 Add the relevant IFC bits for querying an extra migration state from the device. Signed-off-by: Yishai Hadas --- include/linux/mlx5/mlx5_ifc.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 775cb0c56865..1c8922c58c8f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2173,7 +2173,8 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 sf_eq_usage[0x1]; u8 reserved_at_d3[0x5]; u8 multiplane[0x1]; - u8 reserved_at_d9[0x7]; + u8 migration_state[0x1]; + u8 reserved_at_da[0x6]; u8 cross_vhca_object_to_object_supported[0x20]; @@ -13280,13 +13281,24 @@ struct mlx5_ifc_query_vhca_migration_state_in_bits { u8 reserved_at_60[0x20]; }; +enum { + MLX5_QUERY_VHCA_MIG_STATE_UNINITIALIZED = 0x0, + MLX5_QUERY_VHCA_MIG_STATE_OPER_MIGRATION_IDLE = 0x1, + MLX5_QUERY_VHCA_MIG_STATE_OPER_MIGRATION_READY = 0x2, + MLX5_QUERY_VHCA_MIG_STATE_OPER_MIGRATION_DIRTY = 0x3, + MLX5_QUERY_VHCA_MIG_STATE_OPER_MIGRATION_INIT = 0x4, +}; + struct mlx5_ifc_query_vhca_migration_state_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x20]; + + u8 migration_state[0x4]; + u8 reserved_at_64[0x1c]; u8 required_umem_size[0x20]; -- 2.18.1 Consider an inflight SAVE operation during the PRE_COPY phase, so the caller will wait when no data is currently available but is expected to arrive. This enables a follow-up patch to avoid returning -ENOMSG while a new *initial_bytes* chunk is still pending from an asynchronous SAVE command issued by the VFIO_MIG_GET_PRECOPY_INFO ioctl. Signed-off-by: Yishai Hadas --- drivers/vfio/pci/mlx5/cmd.c | 5 +++++ drivers/vfio/pci/mlx5/cmd.h | 1 + drivers/vfio/pci/mlx5/main.c | 3 ++- 3 files changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c index ca6d95f293cd..18b8d8594070 100644 --- a/drivers/vfio/pci/mlx5/cmd.c +++ b/drivers/vfio/pci/mlx5/cmd.c @@ -606,6 +606,8 @@ static void mlx5vf_save_callback_complete(struct mlx5_vf_migration_file *migf, struct mlx5vf_async_data *async_data) { + migf->inflight_save = 0; + wake_up_interruptible(&migf->poll_wait); kvfree(async_data->out); complete(&migf->save_comp); fput(migf->filp); @@ -809,6 +811,7 @@ int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev, async_data->header_buf = header_buf; get_file(migf->filp); + migf->inflight_save = 1; err = mlx5_cmd_exec_cb(&migf->async_ctx, in, sizeof(in), async_data->out, out_size, mlx5vf_save_callback, @@ -819,6 +822,8 @@ int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev, return 0; err_exec: + migf->inflight_save = 0; + wake_up_interruptible(&migf->poll_wait); if (header_buf) mlx5vf_put_data_buffer(header_buf); fput(migf->filp); diff --git a/drivers/vfio/pci/mlx5/cmd.h b/drivers/vfio/pci/mlx5/cmd.h index d7821b5ca772..7d2c10be2e60 100644 --- a/drivers/vfio/pci/mlx5/cmd.h +++ b/drivers/vfio/pci/mlx5/cmd.h @@ -111,6 +111,7 @@ struct mlx5_vf_migration_file { struct completion save_comp; struct mlx5_async_ctx async_ctx; struct mlx5vf_async_data async_data; + u8 inflight_save:1; }; struct mlx5_vhca_cq_buf { diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c index fb541c17c712..68e051c48d40 100644 --- a/drivers/vfio/pci/mlx5/main.c +++ b/drivers/vfio/pci/mlx5/main.c @@ -179,7 +179,8 @@ static ssize_t mlx5vf_save_read(struct file *filp, char __user *buf, size_t len, !list_empty(&migf->buf_list) || migf->state == MLX5_MIGF_STATE_ERROR || migf->state == MLX5_MIGF_STATE_PRE_COPY_ERROR || - migf->state == MLX5_MIGF_STATE_PRE_COPY || + (migf->state == MLX5_MIGF_STATE_PRE_COPY && + !migf->inflight_save) || migf->state == MLX5_MIGF_STATE_COMPLETE)) return -ERESTARTSYS; } -- 2.18.1 When userspace opts into VFIO_DEVICE_FEATURE_MIG_PRECOPY_INFOv2, the driver may report the VFIO_PRECOPY_INFO_REINIT output flag in response to the VFIO_MIG_GET_PRECOPY_INFO ioctl, along with a new initial_bytes value. The presence of the VFIO_PRECOPY_INFO_REINIT flag indicates to the caller that new initial data is available in the migration stream. If the firmware reports a new initial-data chunk, any previously dirty bytes in memory are treated as initial bytes, since the caller must read both sets before reaching the end of the initial-data region. In this case, the driver issues a new SAVE command to fetch the data and prepare it for a subsequent read() from userspace. Signed-off-by: Yishai Hadas --- drivers/vfio/pci/mlx5/cmd.c | 20 ++++++-- drivers/vfio/pci/mlx5/cmd.h | 5 +- drivers/vfio/pci/mlx5/main.c | 97 +++++++++++++++++++++++------------- 3 files changed, 83 insertions(+), 39 deletions(-) diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c index 18b8d8594070..5fe0621b5fbd 100644 --- a/drivers/vfio/pci/mlx5/cmd.c +++ b/drivers/vfio/pci/mlx5/cmd.c @@ -87,7 +87,7 @@ int mlx5vf_cmd_resume_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod) int mlx5vf_cmd_query_vhca_migration_state(struct mlx5vf_pci_core_device *mvdev, size_t *state_size, u64 *total_size, - u8 query_flags) + u8 *mig_state, u8 query_flags) { u32 out[MLX5_ST_SZ_DW(query_vhca_migration_state_out)] = {}; u32 in[MLX5_ST_SZ_DW(query_vhca_migration_state_in)] = {}; @@ -152,6 +152,10 @@ int mlx5vf_cmd_query_vhca_migration_state(struct mlx5vf_pci_core_device *mvdev, MLX5_GET64(query_vhca_migration_state_out, out, remaining_total_size) : *state_size; + if (mig_state && mvdev->mig_state_cap) + *mig_state = MLX5_GET(query_vhca_migration_state_out, out, + migration_state); + return 0; } @@ -277,6 +281,9 @@ void mlx5vf_cmd_set_migratable(struct mlx5vf_pci_core_device *mvdev, if (MLX5_CAP_GEN_2(mvdev->mdev, migration_in_chunks)) mvdev->chunk_mode = 1; + if (MLX5_CAP_GEN_2(mvdev->mdev, migration_state)) + mvdev->mig_state_cap = 1; + end: mlx5_vf_put_core_dev(mvdev->mdev); } @@ -555,6 +562,7 @@ void mlx5vf_put_data_buffer(struct mlx5_vhca_data_buffer *buf) { spin_lock_irq(&buf->migf->list_lock); buf->stop_copy_chunk_num = 0; + buf->pre_copy_init_bytes_chunk = false; list_add_tail(&buf->buf_elm, &buf->migf->avail_list); spin_unlock_irq(&buf->migf->list_lock); } @@ -689,7 +697,8 @@ static void mlx5vf_save_callback(int status, struct mlx5_async_work *context) !next_required_umem_size; if (async_data->header_buf) { status = add_buf_header(async_data->header_buf, image_size, - initial_pre_copy); + initial_pre_copy || + async_data->buf->pre_copy_init_bytes_chunk); if (status) goto err; } @@ -708,9 +717,12 @@ static void mlx5vf_save_callback(int status, struct mlx5_async_work *context) } } spin_unlock_irqrestore(&migf->list_lock, flags); - if (initial_pre_copy) { + if (initial_pre_copy || async_data->buf->pre_copy_init_bytes_chunk) { migf->pre_copy_initial_bytes += image_size; - migf->state = MLX5_MIGF_STATE_PRE_COPY; + if (initial_pre_copy) + migf->state = MLX5_MIGF_STATE_PRE_COPY; + if (async_data->buf->pre_copy_init_bytes_chunk) + async_data->buf->pre_copy_init_bytes_chunk = false; } if (stop_copy_last_chunk) migf->state = MLX5_MIGF_STATE_COMPLETE; diff --git a/drivers/vfio/pci/mlx5/cmd.h b/drivers/vfio/pci/mlx5/cmd.h index 7d2c10be2e60..deed0f132f39 100644 --- a/drivers/vfio/pci/mlx5/cmd.h +++ b/drivers/vfio/pci/mlx5/cmd.h @@ -62,6 +62,7 @@ struct mlx5_vhca_data_buffer { u32 *mkey_in; enum dma_data_direction dma_dir; u8 stop_copy_chunk_num; + bool pre_copy_init_bytes_chunk; struct list_head buf_elm; struct mlx5_vf_migration_file *migf; }; @@ -97,6 +98,7 @@ struct mlx5_vf_migration_file { u32 record_tag; u64 stop_copy_prep_size; u64 pre_copy_initial_bytes; + u64 pre_copy_initial_bytes_start; size_t next_required_umem_size; u8 num_ready_chunks; /* Upon chunk mode preserve another set of buffers for stop_copy phase */ @@ -175,6 +177,7 @@ struct mlx5vf_pci_core_device { u8 mdev_detach:1; u8 log_active:1; u8 chunk_mode:1; + u8 mig_state_cap:1; struct completion tracker_comp; /* protect migration state */ struct mutex state_mutex; @@ -199,7 +202,7 @@ int mlx5vf_cmd_suspend_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod); int mlx5vf_cmd_resume_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod); int mlx5vf_cmd_query_vhca_migration_state(struct mlx5vf_pci_core_device *mvdev, size_t *state_size, u64 *total_size, - u8 query_flags); + u8 *migration_state, u8 query_flags); void mlx5vf_cmd_set_migratable(struct mlx5vf_pci_core_device *mvdev, const struct vfio_migration_ops *mig_ops, const struct vfio_log_ops *log_ops); diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c index 68e051c48d40..de306dee1d1a 100644 --- a/drivers/vfio/pci/mlx5/main.c +++ b/drivers/vfio/pci/mlx5/main.c @@ -464,8 +464,10 @@ static long mlx5vf_precopy_ioctl(struct file *filp, unsigned int cmd, struct mlx5_vhca_data_buffer *buf; struct vfio_precopy_info info = {}; loff_t *pos = &filp->f_pos; + u8 migration_state = 0; size_t inc_length = 0; - bool end_of_data = false; + bool reinit_state; + bool end_of_data; int ret; ret = vfio_check_precopy_ioctl(&mvdev->core_device.vdev, cmd, arg, @@ -492,7 +494,8 @@ static long mlx5vf_precopy_ioctl(struct file *filp, unsigned int cmd, * As so, the other code below is safe with the proper locks. */ ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &inc_length, - NULL, MLX5VF_QUERY_INC); + NULL, &migration_state, + MLX5VF_QUERY_INC); if (ret) goto err_state_unlock; } @@ -503,41 +506,67 @@ static long mlx5vf_precopy_ioctl(struct file *filp, unsigned int cmd, goto err_migf_unlock; } - if (migf->pre_copy_initial_bytes > *pos) { - info.initial_bytes = migf->pre_copy_initial_bytes - *pos; + /* + * opt-in for VFIO_DEVICE_FEATURE_MIG_PRECOPY_INFOv2 serves + * as opt-in for VFIO_PRECOPY_INFO_REINIT as well + */ + reinit_state = mvdev->core_device.vdev.precopy_info_v2 && + migration_state == MLX5_QUERY_VHCA_MIG_STATE_OPER_MIGRATION_INIT; + end_of_data = !(migf->max_pos - *pos); + if (reinit_state) { + /* + * Any bytes already present in memory are treated as initial + * bytes, since the caller is required to read them before + * reaching the new initial-bytes region. + */ + migf->pre_copy_initial_bytes_start = *pos; + migf->pre_copy_initial_bytes = migf->max_pos - *pos; + info.initial_bytes = migf->pre_copy_initial_bytes + inc_length; + info.flags |= VFIO_PRECOPY_INFO_REINIT; } else { - info.dirty_bytes = migf->max_pos - *pos; - if (!info.dirty_bytes) - end_of_data = true; - info.dirty_bytes += inc_length; + if (migf->pre_copy_initial_bytes_start + + migf->pre_copy_initial_bytes > *pos) { + WARN_ON_ONCE(end_of_data); + info.initial_bytes = migf->pre_copy_initial_bytes_start + + migf->pre_copy_initial_bytes - *pos; + } else { + info.dirty_bytes = (migf->max_pos - *pos) + inc_length; + } } + mutex_unlock(&migf->lock); - if (!end_of_data || !inc_length) { - mutex_unlock(&migf->lock); - goto done; - } + if ((reinit_state || end_of_data) && inc_length) { + /* + * In case we finished transferring the current state and the + * device has a dirty state, or that the device has a new init + * state, save a new state to be ready for. + */ + buf = mlx5vf_get_data_buffer(migf, DIV_ROUND_UP(inc_length, PAGE_SIZE), + DMA_FROM_DEVICE); + if (IS_ERR(buf)) { + ret = PTR_ERR(buf); + mlx5vf_mark_err(migf); + goto err_state_unlock; + } - mutex_unlock(&migf->lock); - /* - * We finished transferring the current state and the device has a - * dirty state, save a new state to be ready for. - */ - buf = mlx5vf_get_data_buffer(migf, DIV_ROUND_UP(inc_length, PAGE_SIZE), - DMA_FROM_DEVICE); - if (IS_ERR(buf)) { - ret = PTR_ERR(buf); - mlx5vf_mark_err(migf); - goto err_state_unlock; - } + buf->pre_copy_init_bytes_chunk = reinit_state; + ret = mlx5vf_cmd_save_vhca_state(mvdev, migf, buf, true, true); + if (ret) { + mlx5vf_mark_err(migf); + mlx5vf_put_data_buffer(buf); + goto err_state_unlock; + } - ret = mlx5vf_cmd_save_vhca_state(mvdev, migf, buf, true, true); - if (ret) { - mlx5vf_mark_err(migf); - mlx5vf_put_data_buffer(buf); - goto err_state_unlock; + /* + * SAVE appends a header record via add_buf_header(), + * let's account it as well. + */ + if (reinit_state) + info.initial_bytes += sizeof(struct mlx5_vf_migration_header); + else + info.dirty_bytes += sizeof(struct mlx5_vf_migration_header); } -done: mlx5vf_state_mutex_unlock(mvdev); if (copy_to_user((void __user *)arg, &info, offsetofend(struct vfio_precopy_info, dirty_bytes))) @@ -570,7 +599,7 @@ static int mlx5vf_pci_save_device_inc_data(struct mlx5vf_pci_core_device *mvdev) if (migf->state == MLX5_MIGF_STATE_ERROR) return -ENODEV; - ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &length, NULL, + ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &length, NULL, NULL, MLX5VF_QUERY_INC | MLX5VF_QUERY_FINAL); if (ret) goto err; @@ -636,7 +665,7 @@ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev, bool track) if (ret) goto out; - ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &length, &full_size, 0); + ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &length, &full_size, NULL, 0); if (ret) goto out_pd; @@ -1123,7 +1152,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev, enum mlx5_vf_migf_state state; size_t size; - ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &size, NULL, + ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &size, NULL, NULL, MLX5VF_QUERY_INC | MLX5VF_QUERY_CLEANUP); if (ret) return ERR_PTR(ret); @@ -1248,7 +1277,7 @@ static int mlx5vf_pci_get_data_size(struct vfio_device *vdev, mutex_lock(&mvdev->state_mutex); ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &state_size, - &total_size, 0); + &total_size, NULL, 0); if (!ret) *stop_copy_length = total_size; mlx5vf_state_mutex_unlock(mvdev); -- 2.18.1