Merge tag 'amd-drm-next-5.14-2021-05-19' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.14-2021-05-19:

amdgpu:
- Aldebaran updates
- More LTTPR display work
- Vangogh updates
- SDMA 5.x GCR fixes
- RAS fixes
- PCIe ASPM support
- Modifier fixes
- Enable TMZ on Renoir
- Buffer object code cleanup
- Display overlay fixes
- Initial support for multiple eDP panels
- Initial SR-IOV support for Aldebaran
- DP link training refactor
- Misc code cleanups and bug fixes
- SMU regression fixes for variable sized arrays
- MAINTAINERS fixes for amdgpu

amdkfd:
- Initial SR-IOV support for Aldebaran
- Topology fixes
- Initial HMM SVM support
- Misc code cleanups and bug fixes

radeon:
- Misc code cleanups and bug fixes
- SMU regression fixes for variable sized arrays
- Flickering fix for Oland with multiple 4K displays

UAPI:
- amdgpu: Drop AMDGPU_GEM_CREATE_SHADOW flag.
  This was always a kernel internal flag and userspace use of it has always been blocked.
  It's no longer needed so remove it.
- amdkgd: HMM SVM support
  Overview: https://patchwork.freedesktop.org/series/85562/
  Porposed userspace: https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/tree/fxkamd/hmm-wip

Signed-off-by: Dave Airlie <[email protected]>

From: Alex Deucher <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: airlied

MAINTAINERS

@@ -878,7 +878,7 @@ M:	Harry Wentland <[email protected]>
 M:	Leo Li <[email protected]>
 L:	[email protected]
 S:	Supported
-T:	git git://people.freedesktop.org/~agd5f/linux
+T:	git https://gitlab.freedesktop.org/agd5f/linux.git
 F:	drivers/gpu/drm/amd/display/
 
 AMD FAM15H PROCESSOR POWER MONITORING DRIVER
@@ -954,7 +954,7 @@ AMD POWERPLAY
 M:	Evan Quan <[email protected]>
 L:	[email protected]
 S:	Supported
-T:	git git://people.freedesktop.org/~agd5f/linux
+T:	git https://gitlab.freedesktop.org/agd5f/linux.git
 F:	drivers/gpu/drm/amd/pm/powerplay/
 
 AMD SEATTLE DEVICE TREE SUPPORT

drivers/gpu/drm/amd/amdgpu/Makefile

@@ -56,7 +56,7 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
 	amdgpu_gmc.o amdgpu_mmhub.o amdgpu_xgmi.o amdgpu_csa.o amdgpu_ras.o amdgpu_vm_cpu.o \
 	amdgpu_vm_sdma.o amdgpu_discovery.o amdgpu_ras_eeprom.o amdgpu_nbio.o \
 	amdgpu_umc.o smu_v11_0_i2c.o amdgpu_fru_eeprom.o amdgpu_rap.o \
-	amdgpu_fw_attestation.o amdgpu_securedisplay.o
+	amdgpu_fw_attestation.o amdgpu_securedisplay.o amdgpu_hdp.o
 
 amdgpu-$(CONFIG_PROC_FS) += amdgpu_fdinfo.o
 

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -1075,7 +1075,8 @@ struct amdgpu_device {
 
 	atomic_t			throttling_logging_enabled;
 	struct ratelimit_state		throttling_logging_rs;
-	uint32_t			ras_features;
+	uint32_t                        ras_hw_enabled;
+	uint32_t                        ras_enabled;
 
 	bool                            in_pci_err_recovery;
 	struct pci_saved_state          *pci_state;

drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c

@@ -76,7 +76,7 @@ struct amdgpu_atif {
 /**
  * amdgpu_atif_call - call an ATIF method
  *
- * @handle: acpi handle
+ * @atif: acpi handle
  * @function: the ATIF function to execute
  * @params: ATIF function params
  *
@@ -166,7 +166,6 @@ static void amdgpu_atif_parse_functions(struct amdgpu_atif_functions *f, u32 mas
 /**
  * amdgpu_atif_verify_interface - verify ATIF
  *
- * @handle: acpi handle
  * @atif: amdgpu atif struct
  *
  * Execute the ATIF_FUNCTION_VERIFY_INTERFACE ATIF function
@@ -240,8 +239,7 @@ static acpi_handle amdgpu_atif_probe_handle(acpi_handle dhandle)
 /**
  * amdgpu_atif_get_notification_params - determine notify configuration
  *
- * @handle: acpi handle
- * @n: atif notification configuration struct
+ * @atif: acpi handle
  *
  * Execute the ATIF_FUNCTION_GET_SYSTEM_PARAMETERS ATIF function
  * to determine if a notifier is used and if so which one
@@ -304,7 +302,7 @@ static int amdgpu_atif_get_notification_params(struct amdgpu_atif *atif)
 /**
  * amdgpu_atif_query_backlight_caps - get min and max backlight input signal
  *
- * @handle: acpi handle
+ * @atif: acpi handle
  *
  * Execute the QUERY_BRIGHTNESS_TRANSFER_CHARACTERISTICS ATIF function
  * to determine the acceptable range of backlight values
@@ -363,7 +361,7 @@ static int amdgpu_atif_query_backlight_caps(struct amdgpu_atif *atif)
 /**
  * amdgpu_atif_get_sbios_requests - get requested sbios event
  *
- * @handle: acpi handle
+ * @atif: acpi handle
  * @req: atif sbios request struct
  *
  * Execute the ATIF_FUNCTION_GET_SYSTEM_BIOS_REQUESTS ATIF function
@@ -899,6 +897,8 @@ void amdgpu_acpi_fini(struct amdgpu_device *adev)
 /**
  * amdgpu_acpi_is_s0ix_supported
  *
+ * @adev: amdgpu_device_pointer
+ *
  * returns true if supported, false if not.
  */
 bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev)

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h

@@ -75,6 +75,7 @@ struct amdgpu_amdkfd_fence {
 	struct mm_struct *mm;
 	spinlock_t lock;
 	char timeline_name[TASK_COMM_LEN];
+	struct svm_range_bo *svm_bo;
 };
 
 struct amdgpu_kfd_dev {
@@ -148,7 +149,8 @@ int amdgpu_queue_mask_bit_to_set_resource_bit(struct amdgpu_device *adev,
 					int queue_bit);
 
 struct amdgpu_amdkfd_fence *amdgpu_amdkfd_fence_create(u64 context,
-								struct mm_struct *mm);
+				struct mm_struct *mm,
+				struct svm_range_bo *svm_bo);
 #if IS_ENABLED(CONFIG_HSA_AMD)
 bool amdkfd_fence_check_mm(struct dma_fence *f, struct mm_struct *mm);
 struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f);
@@ -234,22 +236,27 @@ uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *s
 	})
 
 /* GPUVM API */
+#define drm_priv_to_vm(drm_priv)					\
+	(&((struct amdgpu_fpriv *)					\
+		((struct drm_file *)(drm_priv))->driver_priv)->vm)
+
 int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
 					struct file *filp, u32 pasid,
-					void **vm, void **process_info,
+					void **process_info,
 					struct dma_fence **ef);
-void amdgpu_amdkfd_gpuvm_release_process_vm(struct kgd_dev *kgd, void *vm);
-uint64_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *vm);
+void amdgpu_amdkfd_gpuvm_release_process_vm(struct kgd_dev *kgd, void *drm_priv);
+uint64_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *drm_priv);
 int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 		struct kgd_dev *kgd, uint64_t va, uint64_t size,
-		void *vm, struct kgd_mem **mem,
+		void *drm_priv, struct kgd_mem **mem,
 		uint64_t *offset, uint32_t flags);
 int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
-		struct kgd_dev *kgd, struct kgd_mem *mem, uint64_t *size);
+		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv,
+		uint64_t *size);
 int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
-		struct kgd_dev *kgd, struct kgd_mem *mem, void *vm);
+		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv);
 int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
-		struct kgd_dev *kgd, struct kgd_mem *mem, void *vm);
+		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv);
 int amdgpu_amdkfd_gpuvm_sync_memory(
 		struct kgd_dev *kgd, struct kgd_mem *mem, bool intr);
 int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,
@@ -260,7 +267,7 @@ int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
 					      struct kfd_vm_fault_info *info);
 int amdgpu_amdkfd_gpuvm_import_dmabuf(struct kgd_dev *kgd,
 				      struct dma_buf *dmabuf,
-				      uint64_t va, void *vm,
+				      uint64_t va, void *drm_priv,
 				      struct kgd_mem **mem, uint64_t *size,
 				      uint64_t *mmap_offset);
 int amdgpu_amdkfd_get_tile_config(struct kgd_dev *kgd,
@@ -270,6 +277,7 @@ void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
 void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
 				struct amdgpu_vm *vm);
 void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo);
+void amdgpu_amdkfd_reserve_system_mem(uint64_t size);
 #else
 static inline
 void amdgpu_amdkfd_gpuvm_init_mem_limits(void)

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c

@@ -25,6 +25,7 @@
 #include <linux/firmware.h>
 #include "amdgpu.h"
 #include "amdgpu_amdkfd.h"
+#include "amdgpu_amdkfd_arcturus.h"
 #include "sdma0/sdma0_4_2_2_offset.h"
 #include "sdma0/sdma0_4_2_2_sh_mask.h"
 #include "sdma1/sdma1_4_2_2_offset.h"

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c

@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/sched/mm.h>
 #include "amdgpu_amdkfd.h"
+#include "kfd_svm.h"
 
 static const struct dma_fence_ops amdkfd_fence_ops;
 static atomic_t fence_seq = ATOMIC_INIT(0);
@@ -60,7 +61,8 @@ static atomic_t fence_seq = ATOMIC_INIT(0);
  */
 
 struct amdgpu_amdkfd_fence *amdgpu_amdkfd_fence_create(u64 context,
-						       struct mm_struct *mm)
+				struct mm_struct *mm,
+				struct svm_range_bo *svm_bo)
 {
 	struct amdgpu_amdkfd_fence *fence;
 
@@ -73,7 +75,7 @@ struct amdgpu_amdkfd_fence *amdgpu_amdkfd_fence_create(u64 context,
 	fence->mm = mm;
 	get_task_comm(fence->timeline_name, current);
 	spin_lock_init(&fence->lock);
-
+	fence->svm_bo = svm_bo;
 	dma_fence_init(&fence->base, &amdkfd_fence_ops, &fence->lock,
 		   context, atomic_inc_return(&fence_seq));
 
@@ -111,6 +113,8 @@ static const char *amdkfd_fence_get_timeline_name(struct dma_fence *f)
  *  a KFD BO and schedules a job to move the BO.
  *  If fence is already signaled return true.
  *  If fence is not signaled schedule a evict KFD process work item.
+ *
+ *  @f: dma_fence
  */
 static bool amdkfd_fence_enable_signaling(struct dma_fence *f)
 {
@@ -122,16 +126,20 @@ static bool amdkfd_fence_enable_signaling(struct dma_fence *f)
 	if (dma_fence_is_signaled(f))
 		return true;
 
-	if (!kgd2kfd_schedule_evict_and_restore_process(fence->mm, f))
-		return true;
-
+	if (!fence->svm_bo) {
+		if (!kgd2kfd_schedule_evict_and_restore_process(fence->mm, f))
+			return true;
+	} else {
+		if (!svm_range_schedule_evict_svm_bo(fence))
+			return true;
+	}
 	return false;
 }
 
 /**
  * amdkfd_fence_release - callback that fence can be freed
  *
- * @fence: fence
+ * @f: dma_fence
  *
  * This function is called when the reference count becomes zero.
  * Drops the mm_struct reference and RCU schedules freeing up the fence.

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c

@@ -719,7 +719,7 @@ static void unlock_spi_csq_mutexes(struct amdgpu_device *adev)
 }
 
 /**
- * @get_wave_count: Read device registers to get number of waves in flight for
+ * get_wave_count: Read device registers to get number of waves in flight for
  * a particular queue. The method also returns the VMID associated with the
  * queue.
  *
@@ -755,19 +755,19 @@ static void get_wave_count(struct amdgpu_device *adev, int queue_idx,
 }
 
 /**
- * @kgd_gfx_v9_get_cu_occupancy: Reads relevant registers associated with each
+ * kgd_gfx_v9_get_cu_occupancy: Reads relevant registers associated with each
  * shader engine and aggregates the number of waves that are in flight for the
  * process whose pasid is provided as a parameter. The process could have ZERO
  * or more queues running and submitting waves to compute units.
  *
  * @kgd: Handle of device from which to get number of waves in flight
  * @pasid: Identifies the process for which this query call is invoked
- * @wave_cnt: Output parameter updated with number of waves in flight that
+ * @pasid_wave_cnt: Output parameter updated with number of waves in flight that
  * belong to process with given pasid
  * @max_waves_per_cu: Output parameter updated with maximum number of waves
  * possible per Compute Unit
  *
- * @note: It's possible that the device has too many queues (oversubscription)
+ * Note: It's possible that the device has too many queues (oversubscription)
  * in which case a VMID could be remapped to a different PASID. This could lead
  * to an iaccurate wave count. Following is a high-level sequence:
  *    Time T1: vmid = getVmid(); vmid is associated with Pasid P1