Merge tag 'amd-drm-next-5.18-2022-02-11-1' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.18-2022-02-11-1:

amdgpu:
- Clean up of power management code
- Enable freesync video mode by default
- Clean up of RAS code
- Improve VRAM access for debug using SDMA
- Coding style cleanups
- SR-IOV fixes
- More display FP reorg
- TLB flush fixes for Arcuturus, Vega20
- Misc display fixes
- Rework special register access methods for SR-IOV
- DP2 fixes
- DP tunneling fixes
- DSC fixes
- More IP discovery cleanups
- Misc RAS fixes
- Enable both SMU i2c buses where applicable
- s2idle improvements
- DPCS header cleanup
- Add new CAP firmware support for SR-IOV

amdkfd:
- Misc cleanups
- SVM fixes
- CRIU support
- Clean up MQD manager

UAPI:
- Add interface to amdgpu CTX ioctl to request a stable power state for profiling
  https://gitlab.freedesktop.org/mesa/drm/-/merge_requests/207
- Add amdkfd support for CRIU
  https://github.com/checkpoint-restore/criu/pull/1709
- Remove old unused amdkfd debugger interface
  Was only implemented for Kaveri and was only ever used by an old HSA tool that was never open sourced

radeon:
- Fix error handling in radeon_driver_open_kms
- UVD suspend fix
- Misc fixes

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220211220706.5803-1-alexander.deucher@amd.com

2 files changed, 104 insertions, 7 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 0b94ec7b73e7..76b580d10a52 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -206,6 +206,8 @@ union drm_amdgpu_bo_list {
 #define AMDGPU_CTX_OP_FREE_CTX	2
 #define AMDGPU_CTX_OP_QUERY_STATE	3
 #define AMDGPU_CTX_OP_QUERY_STATE2	4
+#define AMDGPU_CTX_OP_GET_STABLE_PSTATE	5
+#define AMDGPU_CTX_OP_SET_STABLE_PSTATE	6
 
 /* GPU reset status */
 #define AMDGPU_CTX_NO_RESET		0
@@ -238,10 +240,18 @@ union drm_amdgpu_bo_list {
 #define AMDGPU_CTX_PRIORITY_HIGH        512
 #define AMDGPU_CTX_PRIORITY_VERY_HIGH   1023
 
+/* select a stable profiling pstate for perfmon tools */
+#define AMDGPU_CTX_STABLE_PSTATE_FLAGS_MASK  0xf
+#define AMDGPU_CTX_STABLE_PSTATE_NONE  0
+#define AMDGPU_CTX_STABLE_PSTATE_STANDARD  1
+#define AMDGPU_CTX_STABLE_PSTATE_MIN_SCLK  2
+#define AMDGPU_CTX_STABLE_PSTATE_MIN_MCLK  3
+#define AMDGPU_CTX_STABLE_PSTATE_PEAK  4
+
 struct drm_amdgpu_ctx_in {
 	/** AMDGPU_CTX_OP_* */
 	__u32	op;
-	/** For future use, no flags defined so far */
+	/** Flags */
 	__u32	flags;
 	__u32	ctx_id;
 	/** AMDGPU_CTX_PRIORITY_* */
@@ -262,6 +272,11 @@ union drm_amdgpu_ctx_out {
 			/** Reset status since the last call of the ioctl. */
 			__u32	reset_status;
 		} state;
+
+		struct {
+			__u32	flags;
+			__u32	_pad;
+		} pstate;
 };
 
 union drm_amdgpu_ctx {
@@ -728,6 +743,8 @@ struct drm_amdgpu_cs_chunk_data {
 	#define AMDGPU_INFO_FW_DMCUB		0x14
 	/* Subquery id: Query TOC firmware version */
 	#define AMDGPU_INFO_FW_TOC		0x15
+	/* Subquery id: Query CAP firmware version */
+	#define AMDGPU_INFO_FW_CAP		0x16
 
 /* number of bytes moved for TTM migration */
 #define AMDGPU_INFO_NUM_BYTES_MOVED		0x0f
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index af96af174dc4..6e4268f5e482 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -32,9 +32,10 @@
  * - 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
  */
 #define KFD_IOCTL_MAJOR_VERSION 1
-#define KFD_IOCTL_MINOR_VERSION 6
+#define KFD_IOCTL_MINOR_VERSION 7
 
 struct kfd_ioctl_get_version_args {
 	__u32 major_version;	/* from KFD */
@@ -468,6 +469,82 @@ struct kfd_ioctl_smi_events_args {
 	__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 {
@@ -679,16 +756,16 @@ 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 +819,10 @@ 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