Merge tag 'vfio-v7.1-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Update QAT vfio-pci variant driver for Gen 5, 420xx devices (Vijay
   Sundar Selvamani, Suman Kumar Chakraborty, Giovanni Cabiddu)

 - Fix vfio selftest MMIO DMA mapping selftest (Alex Mastro)

 - Conversions to const struct class in support of class_create()
   deprecation (Jori Koolstra)

 - Improve selftest compiler compatibility by avoiding initializer on
   variable-length array (Manish Honap)

 - Define new uAPI for drivers supporting migration to advise user-
   space of new initial data for reducing target startup latency.
   Implemented for mlx5 vfio-pci variant driver (Yishai Hadas)

 - Enable vfio selftests on aarch64, not just cross-compiles reporting
   arm64 (Ted Logan)

 - Update vfio selftest driver support to include additional DSA devices
   (Yi Lai)

 - Unconditionally include debugfs root pointer in vfio device struct,
   avoiding a build failure seen in hisi_acc variant driver without
   debugfs otherwise (Arnd Bergmann)

 - Add support for the s390 ISM (Internal Shared Memory) device via a
   new variant driver. The device is unique in the size of its BAR space
   (256TiB) and lack of mmap support (Julian Ruess)

 - Enforce that vfio-pci drivers implement a name in their ops structure
   for use in sequestering SR-IOV VFs (Alex Williamson)

 - Prune leftover group notifier code (Paolo Bonzini)

 - Fix Xe vfio-pci variant driver to avoid migration support as a
   dependency in the reset path and missing release call (Michał
   Winiarski)

* tag 'vfio-v7.1-rc1' of https://github.com/awilliam/linux-vfio: (23 commits)
  vfio/xe: Add a missing vfio_pci_core_release_dev()
  vfio/xe: Reorganize the init to decouple migration from reset
  vfio: remove dead notifier code
  vfio/pci: Require vfio_device_ops.name
  MAINTAINERS: add VFIO ISM PCI DRIVER section
  vfio/ism: Implement vfio_pci driver for ISM devices
  vfio/pci: Rename vfio_config_do_rw() to vfio_pci_config_rw_single() and export it
  vfio: unhide vdev->debug_root
  vfio/qat: add support for Intel QAT 420xx VFs
  vfio: selftests: Support DMR and GNR-D DSA devices
  vfio: selftests: Build tests on aarch64
  vfio/mlx5: Add REINIT support to VFIO_MIG_GET_PRECOPY_INFO
  vfio/mlx5: consider inflight SAVE during PRE_COPY
  net/mlx5: Add IFC bits for migration state
  vfio: Adapt drivers to use the core helper vfio_check_precopy_ioctl
  vfio: Add support for VFIO_DEVICE_FEATURE_MIG_PRECOPY_INFOv2
  vfio: Define uAPI for re-init initial bytes during the PRE_COPY phase
  vfio: selftests: Fix VLA initialisation in vfio_pci_irq_set()
  vfio: uapi: fix comment typo
  vfio: mdev: replace mtty_dev->vd_class with a const struct class
  ...

3 files changed, 79 insertions, 5 deletions

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 007f5138db2b..49f3ad4b1a7c 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -2203,7 +2203,8 @@ 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];
 
@@ -13322,13 +13323,24 @@ 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];
 
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index e90859956514..31b826efba00 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -16,6 +16,7 @@
 #include <linux/cdev.h>
 #include <uapi/linux/vfio.h>
 #include <linux/iova_bitmap.h>
+#include <linux/uaccess.h>
 
 struct kvm;
 struct iommufd_ctx;
@@ -52,6 +53,7 @@ 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 */
@@ -72,13 +74,11 @@ struct vfio_device {
 	u8 iommufd_attached:1;
 #endif
 	u8 cdev_opened:1;
-#ifdef CONFIG_DEBUG_FS
 	/*
 	 * debug_root is a static property of the vfio_device
 	 * which must be set prior to registering the vfio_device.
 	 */
 	struct dentry *debug_root;
-#endif
 };
 
 /**
@@ -284,6 +284,44 @@ 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/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index bb7b89330d35..5de618a3a5ee 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -141,7 +141,7 @@ struct vfio_info_cap_header {
  *
  * Retrieve information about the group.  Fills in provided
  * struct vfio_group_info.  Caller sets argsz.
- * Return: 0 on succes, -errno on failure.
+ * Return: 0 on success, -errno on failure.
  * Availability: Always
  */
 struct vfio_group_status {
@@ -1266,6 +1266,19 @@ 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.
+ * The new initial data may result, for example, from device reconfiguration
+ * during migration that requires additional initialization data.
+ * 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 +1314,7 @@ 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 +1524,16 @@ 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 -------- */
 
 /**