Merge tag 'amd-drm-next-5.13-2021-03-23' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.13-2021-03-23:

amdgpu:
- Debugfs cleanup
- Various cleanups and spelling fixes
- Flexible array cleanups
- Initial AMD Freesync HDMI
- Display fixes
- 10bpc dithering improvements
- Display ASSR support
- Clean up and unify powerplay and swsmu interfaces
- Vangogh fixes
- Add SMU gfx busy queues for RV/PCO
- PCIE DPM fixes
- S0ix fixes
- GPU metrics data fixes
- DCN secure display support
- Backlight type override
- Add initial support for Aldebaran
- RAS fixes
- Prime fixes for A+A systems
- Reset fixes
- Initial resource cursor support
- Drop legacy IO BAR requirements
- Various power fixes

amdkfd:
- MMU notifier fixes
- APU fixes

radeon:
- Debugfs cleanups
- Flexible array cleanups

UAPI:
- amdgpu: Add a new INFO ioctl interface to query video capabilities
  rather than hardcoding them in userspace.  This allows us to provide
  fine grained asic capabilities (e.g., if a particular part is
  bandwidth limited, we can limit the capabilities).  Proposed userspace:
  https://gitlab.freedesktop.org/leoliu/drm/-/commits/info_video_caps
  https://gitlab.freedesktop.org/leoliu/mesa/-/commits/info_video_caps
- amdkfd: bump the driver version.  There was a problem with reporting
  some RAS features on older versions of the driver. Proposed userspace:
  ROCm/ROCT-Thunk-Interface@7cdd634

Danvet: A bunch of conflicts all over, but it seems to compile ... I
did put the call to dc_allow_idle_optimizations() on a single line
since it looked a bit too jarring to be left alone.

Signed-off-by: Daniel Vetter <[email protected]>
From: Alex Deucher <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: danvet

drivers/gpu/drm/amd/amdgpu/Kconfig

@@ -34,15 +34,6 @@ config DRM_AMDGPU_USERPTR
 	  This option selects CONFIG_HMM and CONFIG_HMM_MIRROR if it
 	  isn't already selected to enabled full userptr support.
 
-config DRM_AMDGPU_GART_DEBUGFS
-	bool "Allow GART access through debugfs"
-	depends on DRM_AMDGPU
-	depends on DEBUG_FS
-	default n
-	help
-	  Selecting this option creates a debugfs file to inspect the mapped
-	  pages. Uses more memory for housekeeping, enable only for debugging.
-
 source "drivers/gpu/drm/amd/acp/Kconfig"
 source "drivers/gpu/drm/amd/display/Kconfig"
 source "drivers/gpu/drm/amd/amdkfd/Kconfig"

drivers/gpu/drm/amd/amdgpu/Makefile

@@ -71,7 +71,7 @@ amdgpu-y += \
 	vi.o mxgpu_vi.o nbio_v6_1.o soc15.o emu_soc.o mxgpu_ai.o nbio_v7_0.o vega10_reg_init.o \
 	vega20_reg_init.o nbio_v7_4.o nbio_v2_3.o nv.o navi10_reg_init.o navi14_reg_init.o \
 	arct_reg_init.o navi12_reg_init.o mxgpu_nv.o sienna_cichlid_reg_init.o vangogh_reg_init.o \
-	nbio_v7_2.o dimgrey_cavefish_reg_init.o hdp_v4_0.o hdp_v5_0.o
+	nbio_v7_2.o dimgrey_cavefish_reg_init.o hdp_v4_0.o hdp_v5_0.o aldebaran_reg_init.o
 
 # add DF block
 amdgpu-y += \
@@ -83,7 +83,8 @@ amdgpu-y += \
 	gmc_v7_0.o \
 	gmc_v8_0.o \
 	gfxhub_v1_0.o mmhub_v1_0.o gmc_v9_0.o gfxhub_v1_1.o mmhub_v9_4.o \
-	gfxhub_v2_0.o mmhub_v2_0.o gmc_v10_0.o gfxhub_v2_1.o mmhub_v2_3.o
+	gfxhub_v2_0.o mmhub_v2_0.o gmc_v10_0.o gfxhub_v2_1.o mmhub_v2_3.o \
+	mmhub_v1_7.o
 
 # add UMC block
 amdgpu-y += \
@@ -106,7 +107,8 @@ amdgpu-y += \
 	psp_v3_1.o \
 	psp_v10_0.o \
 	psp_v11_0.o \
-	psp_v12_0.o
+	psp_v12_0.o \
+	psp_v13_0.o
 
 # add DCE block
 amdgpu-y += \
@@ -121,6 +123,7 @@ amdgpu-y += \
 	gfx_v8_0.o \
 	gfx_v9_0.o \
 	gfx_v9_4.o \
+	gfx_v9_4_2.o \
 	gfx_v10_0.o
 
 # add async DMA block
@@ -129,6 +132,7 @@ amdgpu-y += \
 	sdma_v2_4.o \
 	sdma_v3_0.o \
 	sdma_v4_0.o \
+	sdma_v4_4.o \
 	sdma_v5_0.o \
 	sdma_v5_2.o
 
@@ -172,7 +176,8 @@ amdgpu-y += \
 amdgpu-y += \
 	smuio_v9_0.o \
 	smuio_v11_0.o \
-	smuio_v11_0_6.o
+	smuio_v11_0_6.o \
+	smuio_v13_0.o
 
 # add amdkfd interfaces
 amdgpu-y += amdgpu_amdkfd.o
@@ -187,6 +192,7 @@ amdgpu-y += \
 	amdgpu_amdkfd_gfx_v8.o \
 	amdgpu_amdkfd_gfx_v9.o \
 	amdgpu_amdkfd_arcturus.o \
+	amdgpu_amdkfd_aldebaran.o \
 	amdgpu_amdkfd_gfx_v10.o \
 	amdgpu_amdkfd_gfx_v10_3.o
 

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

@@ -0,0 +1,54 @@
+/*
+ * Copyright 2020 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu.h"
+#include "soc15.h"
+
+#include "soc15_common.h"
+#include "aldebaran_ip_offset.h"
+
+int aldebaran_reg_base_init(struct amdgpu_device *adev)
+{
+	/* HW has more IP blocks,  only initialized the block needed by our driver  */
+	uint32_t i;
+	for (i = 0 ; i < MAX_INSTANCE ; ++i) {
+		adev->reg_offset[GC_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i]));
+		adev->reg_offset[HDP_HWIP][i] = (uint32_t *)(&(HDP_BASE.instance[i]));
+		adev->reg_offset[MMHUB_HWIP][i] = (uint32_t *)(&(MMHUB_BASE.instance[i]));
+		adev->reg_offset[ATHUB_HWIP][i] = (uint32_t *)(&(ATHUB_BASE.instance[i]));
+		adev->reg_offset[NBIO_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i]));
+		adev->reg_offset[MP0_HWIP][i] = (uint32_t *)(&(MP0_BASE.instance[i]));
+		adev->reg_offset[MP1_HWIP][i] = (uint32_t *)(&(MP1_BASE.instance[i]));
+		adev->reg_offset[DF_HWIP][i] = (uint32_t *)(&(DF_BASE.instance[i]));
+		adev->reg_offset[OSSSYS_HWIP][i] = (uint32_t *)(&(OSSSYS_BASE.instance[i]));
+		adev->reg_offset[SDMA0_HWIP][i] = (uint32_t *)(&(SDMA0_BASE.instance[i]));
+		adev->reg_offset[SDMA1_HWIP][i] = (uint32_t *)(&(SDMA1_BASE.instance[i]));
+		adev->reg_offset[SDMA2_HWIP][i] = (uint32_t *)(&(SDMA2_BASE.instance[i]));
+		adev->reg_offset[SDMA3_HWIP][i] = (uint32_t *)(&(SDMA3_BASE.instance[i]));
+		adev->reg_offset[SDMA4_HWIP][i] = (uint32_t *)(&(SDMA4_BASE.instance[i]));
+		adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i]));
+		adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i]));
+		adev->reg_offset[UMC_HWIP][i] = (uint32_t *)(&(UMC_BASE.instance[i]));
+		adev->reg_offset[VCN_HWIP][i] = (uint32_t *)(&(VCN_BASE.instance[i]));
+	}
+	return 0;
+}

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

@@ -124,6 +124,16 @@ struct amdgpu_mgpu_info
 	uint32_t			num_gpu;
 	uint32_t			num_dgpu;
 	uint32_t			num_apu;
+
+	/* delayed reset_func for XGMI configuration if necessary */
+	struct delayed_work		delayed_reset_work;
+	bool				pending_reset;
+};
+
+struct amdgpu_watchdog_timer
+{
+	bool timeout_fatal_disable;
+	uint32_t period; /* maxCycles = (1 << period), the number of cycles before a timeout */
 };
 
 #define AMDGPU_MAX_TIMEOUT_PARAM_LENGTH	256
@@ -177,14 +187,17 @@ extern int amdgpu_compute_multipipe;
 extern int amdgpu_gpu_recovery;
 extern int amdgpu_emu_mode;
 extern uint amdgpu_smu_memory_pool_size;
+extern int amdgpu_smu_pptable_id;
 extern uint amdgpu_dc_feature_mask;
+extern uint amdgpu_freesync_vid_mode;
 extern uint amdgpu_dc_debug_mask;
 extern uint amdgpu_dm_abm_level;
 extern int amdgpu_backlight;
 extern struct amdgpu_mgpu_info mgpu_info;
 extern int amdgpu_ras_enable;
 extern uint amdgpu_ras_mask;
 extern int amdgpu_bad_page_threshold;
+extern struct amdgpu_watchdog_timer amdgpu_watchdog_timer;
 extern int amdgpu_async_gfx_ring;
 extern int amdgpu_mcbp;
 extern int amdgpu_discovery;
@@ -584,6 +597,19 @@ enum amd_reset_method {
 	AMD_RESET_METHOD_PCI,
 };
 
+struct amdgpu_video_codec_info {
+	u32 codec_type;
+	u32 max_width;
+	u32 max_height;
+	u32 max_pixels_per_frame;
+	u32 max_level;
+};
+
+struct amdgpu_video_codecs {
+	const u32 codec_count;
+	const struct amdgpu_video_codec_info *codec_array;
+};
+
 /*
  * ASIC specific functions.
  */
@@ -628,6 +654,9 @@ struct amdgpu_asic_funcs {
 	void (*pre_asic_init)(struct amdgpu_device *adev);
 	/* enter/exit umd stable pstate */
 	int (*update_umd_stable_pstate)(struct amdgpu_device *adev, bool enter);
+	/* query video codecs */
+	int (*query_video_codecs)(struct amdgpu_device *adev, bool encode,
+				  const struct amdgpu_video_codecs **codecs);
 };
 
 /*
@@ -792,12 +821,7 @@ struct amdgpu_device {
 	bool				accel_working;
 	struct notifier_block		acpi_nb;
 	struct amdgpu_i2c_chan		*i2c_bus[AMDGPU_MAX_I2C_BUS];
-	struct amdgpu_debugfs		debugfs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
-	unsigned			debugfs_count;
-#if defined(CONFIG_DEBUG_FS)
-	struct dentry                   *debugfs_preempt;
-	struct dentry			*debugfs_regs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
-#endif
+	struct debugfs_blob_wrapper     debugfs_vbios_blob;
 	struct amdgpu_atif		*atif;
 	struct amdgpu_atcs		atcs;
 	struct mutex			srbm_mutex;
@@ -853,8 +877,6 @@ struct amdgpu_device {
 	spinlock_t audio_endpt_idx_lock;
 	amdgpu_block_rreg_t		audio_endpt_rreg;
 	amdgpu_block_wreg_t		audio_endpt_wreg;
-	void __iomem                    *rio_mem;
-	resource_size_t			rio_mem_size;
 	struct amdgpu_doorbell		doorbell;
 
 	/* clock/pll info */
@@ -897,6 +919,7 @@ struct amdgpu_device {
 	struct amdgpu_irq_src		vupdate_irq;
 	struct amdgpu_irq_src		pageflip_irq;
 	struct amdgpu_irq_src		hpd_irq;
+	struct amdgpu_irq_src		dmub_trace_irq;
 
 	/* rings */
 	u64				fence_context;
@@ -1024,6 +1047,7 @@ struct amdgpu_device {
 
 	int asic_reset_res;
 	struct work_struct		xgmi_reset_work;
+	struct list_head		reset_list;
 
 	long				gfx_timeout;
 	long				sdma_timeout;
@@ -1088,9 +1112,6 @@ void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev,
 void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value);
 uint8_t amdgpu_mm_rreg8(struct amdgpu_device *adev, uint32_t offset);
 
-u32 amdgpu_io_rreg(struct amdgpu_device *adev, u32 reg);
-void amdgpu_io_wreg(struct amdgpu_device *adev, u32 reg, u32 v);
-
 u32 amdgpu_device_indirect_rreg(struct amdgpu_device *adev,
 				u32 pcie_index, u32 pcie_data,
 				u32 reg_addr);
@@ -1107,6 +1128,15 @@ void amdgpu_device_indirect_wreg64(struct amdgpu_device *adev,
 bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type);
 bool amdgpu_device_has_dc_support(struct amdgpu_device *adev);
 
+int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
+				  struct amdgpu_job *job,
+				  bool *need_full_reset_arg);
+
+int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
+			  struct list_head *device_list_handle,
+			  bool *need_full_reset_arg,
+			  bool skip_hw_reset);
+
 int emu_soc_asic_init(struct amdgpu_device *adev);
 
 /*
@@ -1172,8 +1202,6 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 	} while (0)
 
 #define DREG32_SYS(sqf, adev, reg) seq_printf((sqf), #reg " : 0x%08X\n", amdgpu_device_rreg((adev), (reg), false))
-#define RREG32_IO(reg) amdgpu_io_rreg(adev, (reg))
-#define WREG32_IO(reg, v) amdgpu_io_wreg(adev, (reg), (v))
 
 #define REG_FIELD_SHIFT(reg, field) reg##__##field##__SHIFT
 #define REG_FIELD_MASK(reg, field) reg##__##field##_MASK
@@ -1227,6 +1255,7 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 #define amdgpu_asic_pre_asic_init(adev) (adev)->asic_funcs->pre_asic_init((adev))
 #define amdgpu_asic_update_umd_stable_pstate(adev, enter) \
 	((adev)->asic_funcs->update_umd_stable_pstate ? (adev)->asic_funcs->update_umd_stable_pstate((adev), (enter)) : 0)
+#define amdgpu_asic_query_video_codecs(adev, e, c) (adev)->asic_funcs->query_video_codecs((adev), (e), (c))
 
 #define amdgpu_inc_vram_lost(adev) atomic_inc(&((adev)->vram_lost_counter));
 
@@ -1247,6 +1276,7 @@ void amdgpu_device_program_register_sequence(struct amdgpu_device *adev,
 					     const u32 array_size);
 
 bool amdgpu_device_supports_atpx(struct drm_device *dev);
+int amdgpu_device_mode1_reset(struct amdgpu_device *adev);
 bool amdgpu_device_supports_boco(struct drm_device *dev);
 bool amdgpu_device_supports_baco(struct drm_device *dev);
 bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev,

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

@@ -44,7 +44,7 @@ int amdgpu_amdkfd_init(void)
 	int ret;
 
 	si_meminfo(&si);
-	amdgpu_amdkfd_total_mem_size = si.totalram - si.totalhigh;
+	amdgpu_amdkfd_total_mem_size = si.freeram - si.freehigh;
 	amdgpu_amdkfd_total_mem_size *= si.mem_unit;
 
 	ret = kgd2kfd_init();
@@ -165,7 +165,8 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 					adev->doorbell_index.last_non_cp;
 		}
 
-		kgd2kfd_device_init(adev->kfd.dev, adev_to_drm(adev), &gpu_resources);
+		adev->kfd.init_complete = kgd2kfd_device_init(adev->kfd.dev,
+						adev_to_drm(adev), &gpu_resources);
 	}
 }
 
@@ -638,13 +639,6 @@ void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 
-	/* Temp workaround to fix the soft hang observed in certain compute
-	 * applications if GFXOFF is enabled.
-	 */
-	if (adev->asic_type == CHIP_SIENNA_CICHLID) {
-		pr_debug("GFXOFF is %s\n", idle ? "enabled" : "disabled");
-		amdgpu_gfx_off_ctrl(adev, idle);
-	}
 	amdgpu_dpm_switch_power_profile(adev,
 					PP_SMC_POWER_PROFILE_COMPUTE,
 					!idle);

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

@@ -80,6 +80,7 @@ struct amdgpu_amdkfd_fence {
 struct amdgpu_kfd_dev {
 	struct kfd_dev *dev;
 	uint64_t vram_used;
+	bool init_complete;
 };
 
 enum kgd_engine_type {

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

@@ -0,0 +1,47 @@
+/*
+ * Copyright 2020 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "amdgpu.h"
+#include "amdgpu_amdkfd.h"
+#include "amdgpu_amdkfd_arcturus.h"
+#include "amdgpu_amdkfd_gfx_v9.h"
+
+const struct kfd2kgd_calls aldebaran_kfd2kgd = {
+	.program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings,
+	.set_pasid_vmid_mapping = kgd_gfx_v9_set_pasid_vmid_mapping,
+	.init_interrupts = kgd_gfx_v9_init_interrupts,
+	.hqd_load = kgd_gfx_v9_hqd_load,
+	.hiq_mqd_load = kgd_gfx_v9_hiq_mqd_load,
+	.hqd_sdma_load = kgd_arcturus_hqd_sdma_load,
+	.hqd_dump = kgd_gfx_v9_hqd_dump,
+	.hqd_sdma_dump = kgd_arcturus_hqd_sdma_dump,
+	.hqd_is_occupied = kgd_gfx_v9_hqd_is_occupied,
+	.hqd_sdma_is_occupied = kgd_arcturus_hqd_sdma_is_occupied,
+	.hqd_destroy = kgd_gfx_v9_hqd_destroy,
+	.hqd_sdma_destroy = kgd_arcturus_hqd_sdma_destroy,
+	.address_watch_disable = kgd_gfx_v9_address_watch_disable,
+	.address_watch_execute = kgd_gfx_v9_address_watch_execute,
+	.wave_control_execute = kgd_gfx_v9_wave_control_execute,
+	.address_watch_get_offset = kgd_gfx_v9_address_watch_get_offset,
+	.get_atc_vmid_pasid_mapping_info =
+				kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
+	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
+};