From d1104f9327df9b26901b97cd026949f80ccab0d3 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Fri, 4 Nov 2022 15:20:06 +0100 Subject: vfio/ccw: replace vfio_init_device with _alloc_ Now that we have a reasonable separation of structs that follow the subchannel and mdev lifecycles, there's no reason we can't call the official vfio_alloc_device routine for our private data, and behave like everyone else. Signed-off-by: Eric Farman Reviewed-by: Kevin Tian Reviewed-by: Matthew Rosato Link: https://lore.kernel.org/r/20221104142007.1314999-7-farman@linux.ibm.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index e7cebeb875dd..ba809268a48e 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -176,8 +176,6 @@ struct vfio_device *_vfio_alloc_device(size_t size, struct device *dev, dev, ops), \ struct dev_struct, member) -int vfio_init_device(struct vfio_device *device, struct device *dev, - const struct vfio_device_ops *ops); void vfio_free_device(struct vfio_device *device); static inline void vfio_put_device(struct vfio_device *device) { -- cgit v1.2.3 From 913447d06f032a9e9c84870bec0b1adb8c588f29 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Fri, 4 Nov 2022 15:20:07 +0100 Subject: vfio: Remove vfio_free_device With the "mess" sorted out, we should be able to inline the vfio_free_device call introduced by commit cb9ff3f3b84c ("vfio: Add helpers for unifying vfio_device life cycle") and remove them from driver release callbacks. Signed-off-by: Eric Farman Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Reviewed-by: Cornelia Huck Reviewed-by: Tony Krowiak # vfio-ap part Reviewed-by: Matthew Rosato Link: https://lore.kernel.org/r/20221104142007.1314999-8-farman@linux.ibm.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index ba809268a48e..e7480154825e 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -176,7 +176,6 @@ struct vfio_device *_vfio_alloc_device(size_t size, struct device *dev, dev, ops), \ struct dev_struct, member) -void vfio_free_device(struct vfio_device *device); static inline void vfio_put_device(struct vfio_device *device) { put_device(&device->device); -- cgit v1.2.3 From 4e016f969529f2aec0545e90119e7eb3cb124c46 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 6 Nov 2022 19:46:18 +0200 Subject: vfio: Add an option to get migration data size Add an option to get migration data size by introducing a new migration feature named VFIO_DEVICE_FEATURE_MIG_DATA_SIZE. Upon VFIO_DEVICE_FEATURE_GET the estimated data length that will be required to complete STOP_COPY is returned. This option may better enable user space to consider before moving to STOP_COPY whether it can meet the downtime SLA based on the returned data. The patch also includes the implementation for mlx5 and hisi for this new option to make it feature complete for the existing drivers in this area. Signed-off-by: Yishai Hadas Reviewed-by: Jason Gunthorpe Reviewed-by: Longfang Liu Link: https://lore.kernel.org/r/20221106174630.25909-2-yishaih@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 5 +++++ include/uapi/linux/vfio.h | 13 +++++++++++++ 2 files changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index e7480154825e..43b67e46a2cb 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -107,6 +107,9 @@ struct vfio_device_ops { * @migration_get_state: Optional callback to get the migration state for * devices that support migration. It's mandatory for * VFIO_DEVICE_FEATURE_MIGRATION migration support. + * @migration_get_data_size: Optional callback to get the estimated data + * length that will be required to complete stop copy. It's mandatory for + * VFIO_DEVICE_FEATURE_MIGRATION migration support. */ struct vfio_migration_ops { struct file *(*migration_set_state)( @@ -114,6 +117,8 @@ struct vfio_migration_ops { enum vfio_device_mig_state new_state); int (*migration_get_state)(struct vfio_device *device, enum vfio_device_mig_state *curr_state); + int (*migration_get_data_size)(struct vfio_device *device, + unsigned long *stop_copy_length); }; /** diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index d7d8e0922376..3e45dbaf190e 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1128,6 +1128,19 @@ struct vfio_device_feature_dma_logging_report { #define VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT 8 +/* + * Upon VFIO_DEVICE_FEATURE_GET read back the estimated data length that will + * be required to complete stop copy. + * + * Note: Can be called on each device state. + */ + +struct vfio_device_feature_mig_data_size { + __aligned_u64 stop_copy_length; +}; + +#define VFIO_DEVICE_FEATURE_MIG_DATA_SIZE 9 + /* -------- API for Type1 VFIO IOMMU -------- */ /** -- cgit v1.2.3 From 8f8bcc8c720c360885639de66fe69756febed824 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 5 Dec 2022 11:29:16 -0400 Subject: vfio/pci: Move all the SPAPR PCI specific logic to vfio_pci_core.ko The vfio_spapr_pci_eeh_open/release() functions are one line wrappers around an arch function. Just call them directly. This eliminates some weird exported symbols that don't need to exist. Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Reviewed-by: Cornelia Huck Link: https://lore.kernel.org/r/1-v5-fc5346cacfd4+4c482-vfio_modules_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 43b67e46a2cb..9378ca79d548 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -233,21 +233,10 @@ int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr, int num_irqs, int max_irq_type, size_t *data_size); -struct pci_dev; #if IS_ENABLED(CONFIG_VFIO_SPAPR_EEH) -void vfio_spapr_pci_eeh_open(struct pci_dev *pdev); -void vfio_spapr_pci_eeh_release(struct pci_dev *pdev); long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group, unsigned int cmd, unsigned long arg); #else -static inline void vfio_spapr_pci_eeh_open(struct pci_dev *pdev) -{ -} - -static inline void vfio_spapr_pci_eeh_release(struct pci_dev *pdev) -{ -} - static inline long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group, unsigned int cmd, unsigned long arg) -- cgit v1.2.3 From e276e25819b8a173a21947720bb0a548c0b724b7 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 5 Dec 2022 11:29:18 -0400 Subject: vfio: Move vfio_spapr_iommu_eeh_ioctl into vfio_iommu_spapr_tce.c As with the previous patch EEH is always enabled if SPAPR_TCE_IOMMU, so move this last bit of code into the main module. Now that this function only processes VFIO_EEH_PE_OP remove a level of indenting as well, it is only called by a case statement that already checked VFIO_EEH_PE_OP. This eliminates an unnecessary module and SPAPR code in a global header. Reviewed-by: Christoph Hellwig Reviewed-by: Cornelia Huck Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/3-v5-fc5346cacfd4+4c482-vfio_modules_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 9378ca79d548..b4d5d4ca3d7d 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -233,18 +233,6 @@ int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr, int num_irqs, int max_irq_type, size_t *data_size); -#if IS_ENABLED(CONFIG_VFIO_SPAPR_EEH) -long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group, unsigned int cmd, - unsigned long arg); -#else -static inline long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group, - unsigned int cmd, - unsigned long arg) -{ - return -ENOTTY; -} -#endif /* CONFIG_VFIO_SPAPR_EEH */ - /* * IRQfd - generic */ -- cgit v1.2.3 From c943a9374d12bebca2d0de7e273b1c723b58c122 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Tue, 6 Dec 2022 10:34:25 +0200 Subject: net/mlx5: Introduce ifc bits for pre_copy Introduce ifc related stuff to enable PRE_COPY of VF during migration. Signed-off-by: Shay Drory Acked-by: Leon Romanovsky Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/20221206083438.37807-2-yishaih@nvidia.com Signed-off-by: Alex Williamson --- include/linux/mlx5/mlx5_ifc.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 5a4e914e2a6f..230a96626a5f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1882,7 +1882,12 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 max_reformat_remove_size[0x8]; u8 max_reformat_remove_offset[0x8]; - u8 reserved_at_c0[0xe0]; + u8 reserved_at_c0[0x8]; + u8 migration_multi_load[0x1]; + u8 migration_tracking_state[0x1]; + u8 reserved_at_ca[0x16]; + + u8 reserved_at_e0[0xc0]; u8 reserved_at_1a0[0xb]; u8 log_min_mkey_entity_size[0x5]; @@ -11918,7 +11923,8 @@ struct mlx5_ifc_query_vhca_migration_state_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x10]; + u8 incremental[0x1]; + u8 reserved_at_41[0xf]; u8 vhca_id[0x10]; u8 reserved_at_60[0x20]; @@ -11944,7 +11950,9 @@ struct mlx5_ifc_save_vhca_state_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x10]; + u8 incremental[0x1]; + u8 set_track[0x1]; + u8 reserved_at_42[0xe]; u8 vhca_id[0x10]; u8 reserved_at_60[0x20]; -- cgit v1.2.3 From 4db52602a6074e9cc523500b8304600ff63e7b85 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 6 Dec 2022 10:34:26 +0200 Subject: vfio: Extend the device migration protocol with PRE_COPY The optional PRE_COPY states open the saving data transfer FD before reaching STOP_COPY and allows the device to dirty track internal state changes with the general idea to reduce the volume of data transferred in the STOP_COPY stage. While in PRE_COPY the device remains RUNNING, but the saving FD is open. Only if the device also supports RUNNING_P2P can it support PRE_COPY_P2P, which halts P2P transfers while continuing the saving FD. PRE_COPY, with P2P support, requires the driver to implement 7 new arcs and exists as an optional FSM branch between RUNNING and STOP_COPY: RUNNING -> PRE_COPY -> PRE_COPY_P2P -> STOP_COPY A new ioctl VFIO_MIG_GET_PRECOPY_INFO is provided to allow userspace to query the progress of the precopy operation in the driver with the idea it will judge to move to STOP_COPY at least once the initial data set is transferred, and possibly after the dirty size has shrunk appropriately. This ioctl is valid only in PRE_COPY states and kernel driver should return -EINVAL from any other migration state. Compared to the v1 clarification, STOP_COPY -> PRE_COPY is blocked and to be defined in future. We also split the pending_bytes report into the initial and sustaining values, e.g.: initial_bytes and dirty_bytes. initial_bytes: Amount of initial precopy data. dirty_bytes: Device state changes relative to data previously retrieved. These fields are not required to have any bearing to STOP_COPY phase. It is recommended to leave PRE_COPY for STOP_COPY only after the initial_bytes field reaches zero. Leaving PRE_COPY earlier might make things slower. Signed-off-by: Jason Gunthorpe Signed-off-by: Shay Drory Reviewed-by: Kevin Tian Reviewed-by: Shameer Kolothum Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/20221206083438.37807-3-yishaih@nvidia.com Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 123 ++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 119 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 3e45dbaf190e..23105eb036fa 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -819,12 +819,20 @@ struct vfio_device_feature { * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P means that RUNNING_P2P * is supported in addition to the STOP_COPY states. * + * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY means that + * PRE_COPY is supported in addition to the STOP_COPY states. + * + * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P | VFIO_MIGRATION_PRE_COPY + * means that RUNNING_P2P, PRE_COPY and PRE_COPY_P2P are supported + * in addition to the STOP_COPY states. + * * Other combinations of flags have behavior to be defined in the future. */ struct vfio_device_feature_migration { __aligned_u64 flags; #define VFIO_MIGRATION_STOP_COPY (1 << 0) #define VFIO_MIGRATION_P2P (1 << 1) +#define VFIO_MIGRATION_PRE_COPY (1 << 2) }; #define VFIO_DEVICE_FEATURE_MIGRATION 1 @@ -875,8 +883,13 @@ struct vfio_device_feature_mig_state { * RESUMING - The device is stopped and is loading a new internal state * ERROR - The device has failed and must be reset * - * And 1 optional state to support VFIO_MIGRATION_P2P: + * And optional states to support VFIO_MIGRATION_P2P: * RUNNING_P2P - RUNNING, except the device cannot do peer to peer DMA + * And VFIO_MIGRATION_PRE_COPY: + * PRE_COPY - The device is running normally but tracking internal state + * changes + * And VFIO_MIGRATION_P2P | VFIO_MIGRATION_PRE_COPY: + * PRE_COPY_P2P - PRE_COPY, except the device cannot do peer to peer DMA * * The FSM takes actions on the arcs between FSM states. The driver implements * the following behavior for the FSM arcs: @@ -908,20 +921,48 @@ struct vfio_device_feature_mig_state { * * To abort a RESUMING session the device must be reset. * + * PRE_COPY -> RUNNING * RUNNING_P2P -> RUNNING * While in RUNNING the device is fully operational, the device may generate * interrupts, DMA, respond to MMIO, all vfio device regions are functional, * and the device may advance its internal state. * + * The PRE_COPY arc will terminate a data transfer session. + * + * PRE_COPY_P2P -> RUNNING_P2P * RUNNING -> RUNNING_P2P * STOP -> RUNNING_P2P * While in RUNNING_P2P the device is partially running in the P2P quiescent * state defined below. * + * The PRE_COPY_P2P arc will terminate a data transfer session. + * + * RUNNING -> PRE_COPY + * RUNNING_P2P -> PRE_COPY_P2P * STOP -> STOP_COPY - * This arc begin the process of saving the device state and will return a - * new data_fd. + * PRE_COPY, PRE_COPY_P2P and STOP_COPY form the "saving group" of states + * which share a data transfer session. Moving between these states alters + * what is streamed in session, but does not terminate or otherwise affect + * the associated fd. + * + * These arcs begin the process of saving the device state and will return a + * new data_fd. The migration driver may perform actions such as enabling + * dirty logging of device state when entering PRE_COPY or PER_COPY_P2P. * + * Each arc does not change the device operation, the device remains + * RUNNING, P2P quiesced or in STOP. The STOP_COPY state is described below + * in PRE_COPY_P2P -> STOP_COPY. + * + * PRE_COPY -> PRE_COPY_P2P + * Entering PRE_COPY_P2P continues all the behaviors of PRE_COPY above. + * However, while in the PRE_COPY_P2P state, the device is partially running + * in the P2P quiescent state defined below, like RUNNING_P2P. + * + * PRE_COPY_P2P -> PRE_COPY + * This arc allows returning the device to a full RUNNING behavior while + * continuing all the behaviors of PRE_COPY. + * + * PRE_COPY_P2P -> STOP_COPY * While in the STOP_COPY state the device has the same behavior as STOP * with the addition that the data transfers session continues to stream the * migration state. End of stream on the FD indicates the entire device @@ -939,6 +980,13 @@ struct vfio_device_feature_mig_state { * device state for this arc if required to prepare the device to receive the * migration data. * + * STOP_COPY -> PRE_COPY + * STOP_COPY -> PRE_COPY_P2P + * These arcs are not permitted and return error if requested. Future + * revisions of this API may define behaviors for these arcs, in this case + * support will be discoverable by a new flag in + * VFIO_DEVICE_FEATURE_MIGRATION. + * * any -> ERROR * ERROR cannot be specified as a device state, however any transition request * can be failed with an errno return and may then move the device_state into @@ -950,7 +998,7 @@ struct vfio_device_feature_mig_state { * The optional peer to peer (P2P) quiescent state is intended to be a quiescent * state for the device for the purposes of managing multiple devices within a * user context where peer-to-peer DMA between devices may be active. The - * RUNNING_P2P states must prevent the device from initiating + * RUNNING_P2P and PRE_COPY_P2P states must prevent the device from initiating * any new P2P DMA transactions. If the device can identify P2P transactions * then it can stop only P2P DMA, otherwise it must stop all DMA. The migration * driver must complete any such outstanding operations prior to completing the @@ -963,6 +1011,8 @@ struct vfio_device_feature_mig_state { * above FSM arcs. As there are multiple paths through the FSM arcs the path * should be selected based on the following rules: * - Select the shortest path. + * - The path cannot have saving group states as interior arcs, only + * starting/end states. * Refer to vfio_mig_get_next_state() for the result of the algorithm. * * The automatic transit through the FSM arcs that make up the combination @@ -976,6 +1026,9 @@ struct vfio_device_feature_mig_state { * support them. The user can discover if these states are supported by using * VFIO_DEVICE_FEATURE_MIGRATION. By using combination transitions the user can * avoid knowing about these optional states if the kernel driver supports them. + * + * Arcs touching PRE_COPY and PRE_COPY_P2P are removed if support for PRE_COPY + * is not present. */ enum vfio_device_mig_state { VFIO_DEVICE_STATE_ERROR = 0, @@ -984,8 +1037,70 @@ enum vfio_device_mig_state { VFIO_DEVICE_STATE_STOP_COPY = 3, VFIO_DEVICE_STATE_RESUMING = 4, VFIO_DEVICE_STATE_RUNNING_P2P = 5, + VFIO_DEVICE_STATE_PRE_COPY = 6, + VFIO_DEVICE_STATE_PRE_COPY_P2P = 7, +}; + +/** + * VFIO_MIG_GET_PRECOPY_INFO - _IO(VFIO_TYPE, VFIO_BASE + 21) + * + * This ioctl is used on the migration data FD in the precopy phase of the + * migration data transfer. It returns an estimate of the current data sizes + * remaining to be transferred. It allows the user to judge when it is + * appropriate to leave PRE_COPY for STOP_COPY. + * + * This ioctl is valid only in PRE_COPY states and kernel driver should + * return -EINVAL from any other migration state. + * + * The vfio_precopy_info data structure returned by this ioctl provides + * estimates of data available from the device during the PRE_COPY states. + * This estimate is split into two categories, initial_bytes and + * dirty_bytes. + * + * 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. + * It is recommended to leave PRE_COPY for STOP_COPY only after this field + * reaches zero. Leaving PRE_COPY earlier might make things slower. + * + * The dirty_bytes field tracks device state changes relative to data + * previously retrieved. This field starts at zero and may increase as + * the internal device state is modified or decrease as that modified + * state is read from the device. + * + * Userspace may use the combination of these fields to estimate the + * potential data size available during the PRE_COPY phases, as well as + * trends relative to the rate the device is dirtying its internal + * state, but these fields are not required to have any bearing relative + * to the data size available during the STOP_COPY phase. + * + * Drivers have a lot of flexibility in when and what they transfer during the + * PRE_COPY phase, and how they report this from VFIO_MIG_GET_PRECOPY_INFO. + * + * During pre-copy the migration data FD has a temporary "end of stream" that is + * reached when both initial_bytes and dirty_byte are zero. For instance, this + * may indicate that the device is idle and not currently dirtying any internal + * state. When read() is done on this temporary end of stream the kernel driver + * should return ENOMSG from read(). Userspace can wait for more data (which may + * never come) by using poll. + * + * Once in STOP_COPY the migration data FD has a permanent end of stream + * signaled in the usual way by read() always returning 0 and poll always + * returning readable. ENOMSG may not be returned in STOP_COPY. + * Support for this ioctl is mandatory if a driver claims to support + * VFIO_MIGRATION_PRE_COPY. + * + * Return: 0 on success, -1 and errno set on failure. + */ +struct vfio_precopy_info { + __u32 argsz; + __u32 flags; + __aligned_u64 initial_bytes; + __aligned_u64 dirty_bytes; }; +#define VFIO_MIG_GET_PRECOPY_INFO _IO(VFIO_TYPE, VFIO_BASE + 21) + /* * Upon VFIO_DEVICE_FEATURE_SET, allow the device to be moved into a low power * state with the platform-based power management. Device use of lower power -- cgit v1.2.3