Merge tag 'drm-next-2024-11-29' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Merge window fixes, mostly amdgpu and xe, with a few other minor ones,
  all looks fairly normal,

  i915:
   - hdcp: Fix when the first read and write are retried

  xe:
   - Wake up waiters after wait condition set to true
   - Mark the preempt fence workqueue as reclaim
   - Update xe2 graphics name string
   - Fix a couple of guc submit races
   - Fix pat index usage in migrate
   - Ensure non-cached migrate pagetable bo mappings
   - Take a PM ref in the delayed snapshot capture worker

  amdgpu:
   - SMU 13.0.6 fixes
   - XGMI fixes
   - SMU 13.0.7 fixes
   - Misc code cleanups
   - Plane refcount fixes
   - DCN 4.0.1 fixes
   - DC power fixes
   - DTO fixes
   - NBIO 7.11 fixes
   - SMU 14.0.x fixes
   - Reset fixes
   - Enable DC on LoongArch
   - Sysfs hotplug warning fix
   - Misc small fixes
   - VCN 4.0.3 fix
   - Slab usage fix
   - Jpeg delayed work fix

  amdkfd:
   - wptr handling fixes

  radeon:
   - Use ttm_bo_move_null()
   - Constify struct pci_device_id
   - Fix spurious hotplug
   - HPD fix

  rockchip
   - fix 32-bit build"

* tag 'drm-next-2024-11-29' of https://gitlab.freedesktop.org/drm/kernel: (48 commits)
  drm/xe: Take PM ref in delayed snapshot capture worker
  drm/xe/migrate: use XE_BO_FLAG_PAGETABLE
  drm/xe/migrate: fix pat index usage
  drm/xe/guc_submit: fix race around suspend_pending
  drm/xe/guc_submit: fix race around pending_disable
  drm/xe: Update xe2_graphics name string
  drm/rockchip: avoid 64-bit division
  Revert "drm/radeon: Delay Connector detecting when HPD singals is unstable"
  drm/amdgpu/jpeg: cancel the jpeg worker
  drm/amdgpu: fix usage slab after free
  drm/amdgpu/vcn: reset fw_shared when VCPU buffers corrupted on vcn v4.0.3
  drm/amdgpu: Fix sysfs warning when hotplugging
  drm/amdgpu: Add sysfs interface for vcn reset mask
  drm/amdgpu/gmc7: fix wait_for_idle callers
  drm/amd/pm: Remove arcturus min power limit
  drm/amd/pm: skip setting the power source on smu v14.0.2/3
  drm/amd/pm: disable pcie speed switching on Intel platform for smu v14.0.2/3
  drm/amdkfd: Use the correct wptr size
  drm/xe: Mark preempt fence workqueue as reclaim
  drm/xe/ufence: Wake up waiters after setting ufence->signalled
  ...

1 files changed, 114 insertions, 4 deletions

diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index bb27c0d2a9ae..67a5de573943 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -357,11 +357,22 @@ 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];
+	uint32_t gfx_busy_inst[MAX_XCC];
+	uint16_t jpeg_busy[NUM_JPEG_ENG];
+	uint16_t vcn_busy[NUM_VCN];
 	/* Utilization Accumulated (%) */
-	u64 gfx_busy_acc[MAX_XCC];
+	uint64_t gfx_busy_acc[MAX_XCC];
+};
+
+struct amdgpu_xcp_metrics_v1_1 {
+	/* Utilization Instantaneous (%) */
+	uint32_t gfx_busy_inst[MAX_XCC];
+	uint16_t jpeg_busy[NUM_JPEG_ENG];
+	uint16_t vcn_busy[NUM_VCN];
+	/* Utilization Accumulated (%) */
+	uint64_t gfx_busy_acc[MAX_XCC];
+	/* Total App Clock Counter Accumulated */
+	uint64_t gfx_below_host_limit_acc[MAX_XCC];
 };
 
 struct amd_pm_funcs {
@@ -977,6 +988,105 @@ struct gpu_metrics_v1_6 {
 	uint32_t			pcie_lc_perf_other_end_recovery;
 };
 
+struct gpu_metrics_v1_7 {
+	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
+
+	/* VRAM max bandwidthi (in GB/sec) at max memory clock */
+	uint64_t			mem_max_bandwidth;
+
+	/* 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];
+
+	/* XGMI link status(active/inactive) */
+	uint16_t			xgmi_link_status[NUM_XGMI_LINKS];
+
+	uint16_t			padding;
+
+	/* 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_v1_1	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.