Merge tag 'amd-drm-next-6.13-2024-10-25' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.13-2024-10-25:

amdgpu:
- SDMA queue reset support
- SMU 13.0.6 updates
- Add debugfs interface to help limit jpeg queue scheduling for testing
- JPEG 4.0.3 updates
- Initial runtime repartitioning support
- GFX9 fixes
- Misc code cleanups
- Rework IP structures to better handle multiple instances of an IP
- DML updates
- DSC fixes
- HDR fixes
- Brightness control updates
- Runtime pm cleanup
- DMCUB fixes
- DCN 3.5 updates
- Struct drm_edid cleanup
- Fetch EDID from _DDC if available
- Ring noop optimizations
- MES logging fixes
- 3DLUT fixes
- DCN 4.x fixes
- SMU 13.x fixes
- Fixes for set_soft_freq_range()
- ACPI fixes
- SMU 14.x updates
- PSR-SU fixes
- fdinfo cleanup
- DCN documentation updates

amdkfd:
- Misc code cleanups
- Increase event FIFO size
- Copy wave state fixes for SDMA

radeon:
- Fix possible overflow in packet3 check
- Late init connector fix
- Always set GEM function pointer

Documentation:
- Update drm-memory documentation

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241025132336.2416913-1-alexander.deucher@amd.com
Signed-off-by: Dave Airlie <airlied@redhat.com>

3 files changed, 150 insertions, 19 deletions

diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 3f91926a50e9..7eefcb0f5070 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -28,6 +28,8 @@
 
 
 #define AMD_MAX_USEC_TIMEOUT		1000000  /* 1000 ms */
+struct amdgpu_ip_block;
+
 
 /*
  * Chip flags
@@ -337,6 +339,11 @@ enum DC_DEBUG_MASK {
 	 * @DC_FORCE_IPS_ENABLE: If set, force enable all IPS, all the time.
 	 */
 	DC_FORCE_IPS_ENABLE = 0x4000,
+	/**
+	 * @DC_DISABLE_ACPI_EDID: If set, don't attempt to fetch EDID for
+	 * eDP display from ACPI _DDC method.
+	 */
+	DC_DISABLE_ACPI_EDID = 0x8000,
 };
 
 enum amd_dpm_forced_level;
@@ -377,30 +384,30 @@ enum amd_dpm_forced_level;
  */
 struct amd_ip_funcs {
 	char *name;
-	int (*early_init)(void *handle);
-	int (*late_init)(void *handle);
-	int (*sw_init)(void *handle);
-	int (*sw_fini)(void *handle);
-	int (*early_fini)(void *handle);
-	int (*hw_init)(void *handle);
-	int (*hw_fini)(void *handle);
-	void (*late_fini)(void *handle);
-	int (*prepare_suspend)(void *handle);
-	int (*suspend)(void *handle);
-	int (*resume)(void *handle);
+	int (*early_init)(struct amdgpu_ip_block *ip_block);
+	int (*late_init)(struct amdgpu_ip_block *ip_block);
+	int (*sw_init)(struct amdgpu_ip_block *ip_block);
+	int (*sw_fini)(struct amdgpu_ip_block *ip_block);
+	int (*early_fini)(struct amdgpu_ip_block *ip_block);
+	int (*hw_init)(struct amdgpu_ip_block *ip_block);
+	int (*hw_fini)(struct amdgpu_ip_block *ip_block);
+	void (*late_fini)(struct amdgpu_ip_block *ip_block);
+	int (*prepare_suspend)(struct amdgpu_ip_block *ip_block);
+	int (*suspend)(struct amdgpu_ip_block *ip_block);
+	int (*resume)(struct amdgpu_ip_block *ip_block);
 	bool (*is_idle)(void *handle);
-	int (*wait_for_idle)(void *handle);
-	bool (*check_soft_reset)(void *handle);
-	int (*pre_soft_reset)(void *handle);
-	int (*soft_reset)(void *handle);
-	int (*post_soft_reset)(void *handle);
+	int (*wait_for_idle)(struct amdgpu_ip_block *ip_block);
+	bool (*check_soft_reset)(struct amdgpu_ip_block *ip_block);
+	int (*pre_soft_reset)(struct amdgpu_ip_block *ip_block);
+	int (*soft_reset)(struct amdgpu_ip_block *ip_block);
+	int (*post_soft_reset)(struct amdgpu_ip_block *ip_block);
 	int (*set_clockgating_state)(void *handle,
 				     enum amd_clockgating_state state);
 	int (*set_powergating_state)(void *handle,
 				     enum amd_powergating_state state);
 	void (*get_clockgating_state)(void *handle, u64 *flags);
-	void (*dump_ip_state)(void *handle);
-	void (*print_ip_state)(void *handle, struct drm_printer *p);
+	void (*dump_ip_state)(struct amdgpu_ip_block *ip_block);
+	void (*print_ip_state)(struct amdgpu_ip_block *ip_block, struct drm_printer *p);
 };
 
 
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_offset.h
index 2c3ce243861a..380e44230bda 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_offset.h
@@ -1232,6 +1232,29 @@
 #define mmMC_VM_MX_L1_PERFCOUNTER_HI                                                                   0x059d
 #define mmMC_VM_MX_L1_PERFCOUNTER_HI_BASE_IDX                                                          0
 
+// Stand Alone Walker Registers
+#define VMC_TAP_PDE_REQUEST_SNOOP_OFFSET								8
+#define VMC_TAP_PTE_REQUEST_SNOOP_OFFSET								11
+#define mmVM_L2_SAW_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32                                                 0x0606
+#define mmVM_L2_SAW_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32_BASE_IDX                                        0
+#define mmVM_L2_SAW_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32                                                 0x0607
+#define mmVM_L2_SAW_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32_BASE_IDX                                        0
+#define mmVM_L2_SAW_CONTEXT0_PAGE_TABLE_START_ADDR_LO32                                                0x0608
+#define mmVM_L2_SAW_CONTEXT0_PAGE_TABLE_START_ADDR_LO32_BASE_IDX                                       0
+#define mmVM_L2_SAW_CONTEXT0_PAGE_TABLE_START_ADDR_HI32                                                0x0609
+#define mmVM_L2_SAW_CONTEXT0_PAGE_TABLE_START_ADDR_HI32_BASE_IDX                                       0
+#define mmVM_L2_SAW_CONTEXT0_PAGE_TABLE_END_ADDR_LO32                                                  0x060a
+#define mmVM_L2_SAW_CONTEXT0_PAGE_TABLE_END_ADDR_LO32_BASE_IDX                                         0
+#define mmVM_L2_SAW_CONTEXT0_PAGE_TABLE_END_ADDR_HI32                                                  0x060b
+#define mmVM_L2_SAW_CONTEXT0_PAGE_TABLE_END_ADDR_HI32_BASE_IDX                                         0
+#define mmVM_L2_SAW_CONTEXT0_CNTL                                                                      0x0604
+#define mmVM_L2_SAW_CONTEXT0_CNTL_BASE_IDX                                                             0
+#define CONTEXT0_CNTL_ENABLE_OFFSET									0
+#define CONTEXT0_CNTL_PAGE_TABLE_DEPTH_OFFSET								1
+#define mmVM_L2_SAW_CONTEXTS_DISABLE                                                                   0x060c
+#define mmVM_L2_SAW_CONTEXTS_DISABLE_BASE_IDX                                                          0
+#define mmVM_L2_SAW_CNTL4                                                                              0x0603
+#define mmVM_L2_SAW_CNTL4_BASE_IDX                                                                     0
 
 // addressBlock: mmhub_utcl2_atcl2dec
 // base address: 0x69900
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index 19a48d98830a..2fa71f68205e 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -336,7 +336,8 @@ enum pp_policy_soc_pstate {
 #define MAX_CLKS 4
 #define NUM_VCN 4
 #define NUM_JPEG_ENG 32
-
+#define MAX_XCC 8
+#define NUM_XCP 8
 struct seq_file;
 enum amd_pp_clock_type;
 struct amd_pp_simple_clock_info;
@@ -350,6 +351,15 @@ struct pp_smu_wm_range_sets;
 struct pp_smu_nv_clock_table;
 struct dpm_clocks;
 
+struct amdgpu_xcp_metrics {
+	/* Utilization Instantaneous (%) */
+	u32 gfx_busy_inst[MAX_XCC];
+	u16 jpeg_busy[NUM_JPEG_ENG];
+	u16 vcn_busy[NUM_VCN];
+	/* Utilization Accumulated (%) */
+	u64 gfx_busy_acc[MAX_XCC];
+};
+
 struct amd_pm_funcs {
 /* export for dpm on ci and si */
 	int (*pre_set_power_state)(void *handle);
@@ -872,6 +882,97 @@ struct gpu_metrics_v1_5 {
 	uint16_t			padding;
 };
 
+struct gpu_metrics_v1_6 {
+	struct metrics_table_header	common_header;
+
+	/* Temperature (Celsius) */
+	uint16_t			temperature_hotspot;
+	uint16_t			temperature_mem;
+	uint16_t			temperature_vrsoc;
+
+	/* Power (Watts) */
+	uint16_t			curr_socket_power;
+
+	/* Utilization (%) */
+	uint16_t			average_gfx_activity;
+	uint16_t			average_umc_activity; // memory controller
+
+	/* Energy (15.259uJ (2^-16) units) */
+	uint64_t			energy_accumulator;
+
+	/* Driver attached timestamp (in ns) */
+	uint64_t			system_clock_counter;
+
+	/* Accumulation cycle counter */
+	uint32_t                        accumulation_counter;
+
+	/* Accumulated throttler residencies */
+	uint32_t                        prochot_residency_acc;
+	uint32_t                        ppt_residency_acc;
+	uint32_t                        socket_thm_residency_acc;
+	uint32_t                        vr_thm_residency_acc;
+	uint32_t                        hbm_thm_residency_acc;
+
+	/* Clock Lock Status. Each bit corresponds to clock instance */
+	uint32_t			gfxclk_lock_status;
+
+	/* Link width (number of lanes) and speed (in 0.1 GT/s) */
+	uint16_t			pcie_link_width;
+	uint16_t			pcie_link_speed;
+
+	/* XGMI bus width and bitrate (in Gbps) */
+	uint16_t			xgmi_link_width;
+	uint16_t			xgmi_link_speed;
+
+	/* Utilization Accumulated (%) */
+	uint32_t			gfx_activity_acc;
+	uint32_t			mem_activity_acc;
+
+	/*PCIE accumulated bandwidth (GB/sec) */
+	uint64_t			pcie_bandwidth_acc;
+
+	/*PCIE instantaneous bandwidth (GB/sec) */
+	uint64_t			pcie_bandwidth_inst;
+
+	/* PCIE L0 to recovery state transition accumulated count */
+	uint64_t			pcie_l0_to_recov_count_acc;
+
+	/* PCIE replay accumulated count */
+	uint64_t			pcie_replay_count_acc;
+
+	/* PCIE replay rollover accumulated count */
+	uint64_t			pcie_replay_rover_count_acc;
+
+	/* PCIE NAK sent  accumulated count */
+	uint32_t			pcie_nak_sent_count_acc;
+
+	/* PCIE NAK received accumulated count */
+	uint32_t			pcie_nak_rcvd_count_acc;
+
+	/* XGMI accumulated data transfer size(KiloBytes) */
+	uint64_t			xgmi_read_data_acc[NUM_XGMI_LINKS];
+	uint64_t			xgmi_write_data_acc[NUM_XGMI_LINKS];
+
+	/* PMFW attached timestamp (10ns resolution) */
+	uint64_t			firmware_timestamp;
+
+	/* Current clocks (Mhz) */
+	uint16_t			current_gfxclk[MAX_GFX_CLKS];
+	uint16_t			current_socclk[MAX_CLKS];
+	uint16_t			current_vclk0[MAX_CLKS];
+	uint16_t			current_dclk0[MAX_CLKS];
+	uint16_t			current_uclk;
+
+	/* Number of current partition */
+	uint16_t			num_partition;
+
+	/* XCP metrics stats */
+	struct amdgpu_xcp_metrics	xcp_stats[NUM_XCP];
+
+	/* PCIE other end recovery counter */
+	uint32_t			pcie_lc_perf_other_end_recovery;
+};
+
 /*
  * gpu_metrics_v2_0 is not recommended as it's not naturally aligned.
  * Use gpu_metrics_v2_1 or later instead.