Merge tag 'drm-next-2022-03-24' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Lots of work all over, Intel improving DG2 support, amdkfd CRIU
  support, msm new hw support, and faster fbdev support.

  dma-buf:
   - rename dma-buf-map to iosys-map

  core:
   - move buddy allocator to core
   - add pci/platform init macros
   - improve EDID parser deep color handling
   - EDID timing type 7 support
   - add GPD Win Max quirk
   - add yes/no helpers to string_helpers
   - flatten syncobj chains
   - add nomodeset support to lots of drivers
   - improve fb-helper clipping support
   - add default property value interface

  fbdev:
   - improve fbdev ops speed

  ttm:
   - add a backpointer from ttm bo->ttm resource

  dp:
   - move displayport headers
   - add a dp helper module

  bridge:
   - anx7625 atomic support, HDCP support

  panel:
   - split out panel-lvds and lvds bindings
   - find panels in OF subnodes

  privacy:
   - add chromeos privacy screen support

  fb:
   - hot unplug fw fb on forced removal

  simpledrm:
   - request region instead of marking ioresource busy
   - add panel oreintation property

  udmabuf:
   - fix oops with 0 pages

  amdgpu:
   - power management code cleanup
   - Enable freesync video mode by default
   - RAS code cleanup
   - Improve VRAM access for debug using SDMA
   - SR-IOV rework special register access and fixes
   - profiling power state request ioctl
   - expose IP discovery via sysfs
   - Cyan skillfish updates
   - GC 10.3.7, SDMA 5.2.7, DCN 3.1.6 updates
   - expose benchmark tests via debugfs
   - add module param to disable XGMI for testing
   - GPU reset debugfs register dumping support

  amdkfd:
   - CRIU support
   - SDMA queue fixes

  radeon:
   - UVD suspend fix
   - iMac backlight fix

  i915:
   - minimal parallel submission for execlists
   - DG2-G12 subplatform added
   - DG2 programming workarounds
   - DG2 accelerated migration support
   - flat CCS and CCS engine support for XeHP
   - initial small BAR support
   - drop fake LMEM support
   - ADL-N PCH support
   - bigjoiner updates
   - introduce VMA resources and async unbinding
   - register definitions cleanups
   - multi-FBC refactoring
   - DG1 OPROM over SPI support
   - ADL-N platform enabling
   - opregion mailbox #5 support
   - DP MST ESI improvements
   - drm device based logging
   - async flip optimisation for DG2
   - CPU arch abstraction fixes
   - improve GuC ADS init to work on aarch64
   - tweak TTM LRU priority hint
   - GuC 69.0.3 support
   - remove short term execbuf pins

  nouveau:
   - higher DP/eDP bitrates
   - backlight fixes

  msm:
   - dpu + dp support for sc8180x
   - dp support for sm8350
   - dpu + dsi support for qcm2290
   - 10nm dsi phy tuning support
   - bridge support for dp encoder
   - gpu support for additional 7c3 SKUs

  ingenic:
   - HDMI support for JZ4780
   - aux channel EDID support

  ast:
   - AST2600 support
   - add wide screen support
   - create DP/DVI connectors

  omapdrm:
   - fix implicit dma_buf fencing

  vc4:
   - add CSC + full range support
   - better display firmware handoff

  panfrost:
   - add initial dual-core GPU support

  stm:
   - new revision support
   - fb handover support

  mediatek:
   - transfer display binding document to yaml format.
   - add mt8195 display device binding.
   - allow commands to be sent during video mode.
   - add wait_for_event for crtc disable by cmdq.

  tegra:
   - YUV format support

  rcar-du:
   - LVDS support for M3-W+ (R8A77961)

  exynos:
   - BGR pixel format for FIMD device"

* tag 'drm-next-2022-03-24' of git://anongit.freedesktop.org/drm/drm: (1529 commits)
  drm/i915/display: Do not re-enable PSR after it was marked as not reliable
  drm/i915/display: Fix HPD short pulse handling for eDP
  drm/amdgpu: Use drm_mode_copy()
  drm/radeon: Use drm_mode_copy()
  drm/amdgpu: Use ternary operator in `vcn_v1_0_start()`
  drm/amdgpu: Remove pointless on stack mode copies
  drm/amd/pm: fix indenting in __smu_cmn_reg_print_error()
  drm/amdgpu/dc: fix typos in comments
  drm/amdgpu: fix typos in comments
  drm/amd/pm: fix typos in comments
  drm/amdgpu: Add stolen reserved memory for MI25 SRIOV.
  drm/amdgpu: Merge get_reserved_allocation to get_vbios_allocations.
  drm/amdkfd: evict svm bo worker handle error
  drm/amdgpu/vcn: fix vcn ring test failure in igt reload test
  drm/amdgpu: only allow secure submission on rings which support that
  drm/amdgpu: fixed the warnings reported by kernel test robot
  drm/amd/display: 3.2.177
  drm/amd/display: [FW Promotion] Release 0.0.108.0
  drm/amd/display: Add save/restore PANEL_PWRSEQ_REF_DIV2
  drm/amd/display: Wait for hubp read line for Pollock
  ...

1 files changed, 91 insertions, 7 deletions

diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index af96af174dc4..42975e940758 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -32,9 +32,11 @@
  * - 1.4 - Indicate new SRAM EDC bit in device properties
  * - 1.5 - Add SVM API
  * - 1.6 - Query clear flags in SVM get_attr API
+ * - 1.7 - Checkpoint Restore (CRIU) API
+ * - 1.8 - CRIU - Support for SDMA transfers with GTT BOs
  */
 #define KFD_IOCTL_MAJOR_VERSION 1
-#define KFD_IOCTL_MINOR_VERSION 6
+#define KFD_IOCTL_MINOR_VERSION 8
 
 struct kfd_ioctl_get_version_args {
 	__u32 major_version;	/* from KFD */
@@ -194,6 +196,8 @@ struct kfd_ioctl_dbg_wave_control_args {
 	__u32 buf_size_in_bytes;	/*including gpu_id and buf_size */
 };
 
+#define KFD_INVALID_FD     0xffffffff
+
 /* Matching HSA_EVENTTYPE */
 #define KFD_IOC_EVENT_SIGNAL			0
 #define KFD_IOC_EVENT_NODECHANGE		1
@@ -462,12 +466,89 @@ enum kfd_smi_event {
 };
 
 #define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1))
+#define KFD_SMI_EVENT_MSG_SIZE	96
 
 struct kfd_ioctl_smi_events_args {
 	__u32 gpuid;	/* to KFD */
 	__u32 anon_fd;	/* from KFD */
 };
 
+/**************************************************************************************************
+ * CRIU IOCTLs (Checkpoint Restore In Userspace)
+ *
+ * When checkpointing a process, the userspace application will perform:
+ * 1. PROCESS_INFO op to determine current process information. This pauses execution and evicts
+ *    all the queues.
+ * 2. CHECKPOINT op to checkpoint process contents (BOs, queues, events, svm-ranges)
+ * 3. UNPAUSE op to un-evict all the queues
+ *
+ * When restoring a process, the CRIU userspace application will perform:
+ *
+ * 1. RESTORE op to restore process contents
+ * 2. RESUME op to start the process
+ *
+ * Note: Queues are forced into an evicted state after a successful PROCESS_INFO. User
+ * application needs to perform an UNPAUSE operation after calling PROCESS_INFO.
+ */
+
+enum kfd_criu_op {
+	KFD_CRIU_OP_PROCESS_INFO,
+	KFD_CRIU_OP_CHECKPOINT,
+	KFD_CRIU_OP_UNPAUSE,
+	KFD_CRIU_OP_RESTORE,
+	KFD_CRIU_OP_RESUME,
+};
+
+/**
+ * kfd_ioctl_criu_args - Arguments perform CRIU operation
+ * @devices:		[in/out] User pointer to memory location for devices information.
+ * 			This is an array of type kfd_criu_device_bucket.
+ * @bos:		[in/out] User pointer to memory location for BOs information
+ * 			This is an array of type kfd_criu_bo_bucket.
+ * @priv_data:		[in/out] User pointer to memory location for private data
+ * @priv_data_size:	[in/out] Size of priv_data in bytes
+ * @num_devices:	[in/out] Number of GPUs used by process. Size of @devices array.
+ * @num_bos		[in/out] Number of BOs used by process. Size of @bos array.
+ * @num_objects:	[in/out] Number of objects used by process. Objects are opaque to
+ *				 user application.
+ * @pid:		[in/out] PID of the process being checkpointed
+ * @op			[in] Type of operation (kfd_criu_op)
+ *
+ * Return: 0 on success, -errno on failure
+ */
+struct kfd_ioctl_criu_args {
+	__u64 devices;		/* Used during ops: CHECKPOINT, RESTORE */
+	__u64 bos;		/* Used during ops: CHECKPOINT, RESTORE */
+	__u64 priv_data;	/* Used during ops: CHECKPOINT, RESTORE */
+	__u64 priv_data_size;	/* Used during ops: PROCESS_INFO, RESTORE */
+	__u32 num_devices;	/* Used during ops: PROCESS_INFO, RESTORE */
+	__u32 num_bos;		/* Used during ops: PROCESS_INFO, RESTORE */
+	__u32 num_objects;	/* Used during ops: PROCESS_INFO, RESTORE */
+	__u32 pid;		/* Used during ops: PROCESS_INFO, RESUME */
+	__u32 op;
+};
+
+struct kfd_criu_device_bucket {
+	__u32 user_gpu_id;
+	__u32 actual_gpu_id;
+	__u32 drm_fd;
+	__u32 pad;
+};
+
+struct kfd_criu_bo_bucket {
+	__u64 addr;
+	__u64 size;
+	__u64 offset;
+	__u64 restored_offset;    /* During restore, updated offset for BO */
+	__u32 gpu_id;             /* This is the user_gpu_id */
+	__u32 alloc_flags;
+	__u32 dmabuf_fd;
+	__u32 pad;
+};
+
+/* CRIU IOCTLs - END */
+/**************************************************************************************************/
+
 /* Register offset inside the remapped mmio page
  */
 enum kfd_mmio_remap {
@@ -596,7 +677,7 @@ struct kfd_ioctl_svm_args {
 	__u32 op;
 	__u32 nattr;
 	/* Variable length array of attributes */
-	struct kfd_ioctl_svm_attribute attrs[0];
+	struct kfd_ioctl_svm_attribute attrs[];
 };
 
 /**
@@ -679,16 +760,16 @@ struct kfd_ioctl_set_xnack_mode_args {
 #define AMDKFD_IOC_WAIT_EVENTS			\
 		AMDKFD_IOWR(0x0C, struct kfd_ioctl_wait_events_args)
 
-#define AMDKFD_IOC_DBG_REGISTER			\
+#define AMDKFD_IOC_DBG_REGISTER_DEPRECATED	\
 		AMDKFD_IOW(0x0D, struct kfd_ioctl_dbg_register_args)
 
-#define AMDKFD_IOC_DBG_UNREGISTER		\
+#define AMDKFD_IOC_DBG_UNREGISTER_DEPRECATED	\
 		AMDKFD_IOW(0x0E, struct kfd_ioctl_dbg_unregister_args)
 
-#define AMDKFD_IOC_DBG_ADDRESS_WATCH		\
+#define AMDKFD_IOC_DBG_ADDRESS_WATCH_DEPRECATED	\
 		AMDKFD_IOW(0x0F, struct kfd_ioctl_dbg_address_watch_args)
 
-#define AMDKFD_IOC_DBG_WAVE_CONTROL		\
+#define AMDKFD_IOC_DBG_WAVE_CONTROL_DEPRECATED	\
 		AMDKFD_IOW(0x10, struct kfd_ioctl_dbg_wave_control_args)
 
 #define AMDKFD_IOC_SET_SCRATCH_BACKING_VA	\
@@ -742,7 +823,10 @@ struct kfd_ioctl_set_xnack_mode_args {
 #define AMDKFD_IOC_SET_XNACK_MODE		\
 		AMDKFD_IOWR(0x21, struct kfd_ioctl_set_xnack_mode_args)
 
+#define AMDKFD_IOC_CRIU_OP			\
+		AMDKFD_IOWR(0x22, struct kfd_ioctl_criu_args)
+
 #define AMDKFD_COMMAND_START		0x01
-#define AMDKFD_COMMAND_END		0x22
+#define AMDKFD_COMMAND_END		0x23
 
 #endif