Merge tag 'vfio-v6.2-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Replace deprecated git://github.com link in MAINTAINERS (Palmer
   Dabbelt)

 - Simplify vfio/mlx5 with module_pci_driver() helper (Shang XiaoJing)

 - Drop unnecessary buffer from ACPI call (Rafael Mendonca)

 - Correct latent missing include issue in iova-bitmap and fix support
   for unaligned bitmaps. Follow-up with better fix through refactor
   (Joao Martins)

 - Rework ccw mdev driver to split private data from parent structure,
   better aligning with the mdev lifecycle and allowing us to remove a
   temporary workaround (Eric Farman)

 - Add an interface to get an estimated migration data size for a
   device, allowing userspace to make informed decisions, ex. more
   accurately predicting VM downtime (Yishai Hadas)

 - Fix minor typo in vfio/mlx5 array declaration (Yishai Hadas)

 - Simplify module and Kconfig through consolidating SPAPR/EEH code and
   config options and folding virqfd module into main vfio module (Jason
   Gunthorpe)

 - Fix error path from device_register() across all vfio mdev and sample
   drivers (Alex Williamson)

 - Define migration pre-copy interface and implement for vfio/mlx5
   devices, allowing portions of the device state to be saved while the
   device continues operation, towards reducing the stop-copy state size
   (Jason Gunthorpe, Yishai Hadas, Shay Drory)

 - Implement pre-copy for hisi_acc devices (Shameer Kolothum)

 - Fixes to mdpy mdev driver remove path and error path on probe (Shang
   XiaoJing)

 - vfio/mlx5 fixes for incorrect return after copy_to_user() fault and
   incorrect buffer freeing (Dan Carpenter)

* tag 'vfio-v6.2-rc1' of https://github.com/awilliam/linux-vfio: (42 commits)
  vfio/mlx5: error pointer dereference in error handling
  vfio/mlx5: fix error code in mlx5vf_precopy_ioctl()
  samples: vfio-mdev: Fix missing pci_disable_device() in mdpy_fb_probe()
  hisi_acc_vfio_pci: Enable PRE_COPY flag
  hisi_acc_vfio_pci: Move the dev compatibility tests for early check
  hisi_acc_vfio_pci: Introduce support for PRE_COPY state transitions
  hisi_acc_vfio_pci: Add support for precopy IOCTL
  vfio/mlx5: Enable MIGRATION_PRE_COPY flag
  vfio/mlx5: Fallback to STOP_COPY upon specific PRE_COPY error
  vfio/mlx5: Introduce multiple loads
  vfio/mlx5: Consider temporary end of stream as part of PRE_COPY
  vfio/mlx5: Introduce vfio precopy ioctl implementation
  vfio/mlx5: Introduce SW headers for migration states
  vfio/mlx5: Introduce device transitions of PRE_COPY
  vfio/mlx5: Refactor to use queue based data chunks
  vfio/mlx5: Refactor migration file state
  vfio/mlx5: Refactor MKEY usage
  vfio/mlx5: Refactor PD usage
  vfio/mlx5: Enforce a single SAVE command at a time
  vfio: Extend the device migration protocol with PRE_COPY
  ...

3 files changed, 148 insertions, 33 deletions

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 152d2d7f8743..f3d1c62c98dd 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1891,7 +1891,12 @@ 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];
@@ -12033,7 +12038,8 @@ 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];
@@ -12059,7 +12065,9 @@ 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];
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index a615542df1e0..35be78e9ae57 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -146,6 +146,9 @@ int vfio_iommufd_emulated_attach_ioas(struct vfio_device *vdev, u32 *pt_id);
  * @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)(
@@ -153,6 +156,8 @@ 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);
 };
 
 /**
@@ -215,9 +220,6 @@ 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)
 {
 	put_device(&device->device);
@@ -271,29 +273,6 @@ 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)
-{
-	return -ENOTTY;
-}
-#endif /* CONFIG_VFIO_SPAPR_EEH */
-
 /*
  * IRQfd - generic
  */
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index d7d8e0922376..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
@@ -1128,6 +1243,19 @@ 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 -------- */
 
 /**