Merge tag 'drm-next-2024-07-18' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "There's a lot of stuff in here, amd, i915 and xe have new platform
  work, lots of core rework around EDID handling, some new COMPILE_TEST
  options, maintainer changes and a lots of other stuff. Summary:

  core:
   - deprecate DRM data and return 0 date
   - connector: Create a set of helpers to help with HDMI support
   - Remove driver owner assignments
   - Allow more drivers to compile with COMPILE_TEST
   - Conversions to drm_edid
   - Sprinkle MODULE_DESCRIPTIONS everywhere they are missing
   - Remove drm_mm_replace_node
   - print: Add a drm prefix to warn level messages too, remove
            ___drm_dbg, consolidate prefix handling
   - New monochrome TV mode variant

  ttm:
   - improve number of page faults on some platforms
   - fix test builds under PREEMPT_RT
   - more test coverage

  ci:
   - Require a more recent version of mesa
   - improve farm setup and test generation

  dma-buf:
   - warn if reserving 0 fence slots
   - internal API heap enhancements

  fbdev:
   - Create memory manager optimized fbdev emulation

  panic:
   - Allow to select fonts
   - improve drm_fb_dma_get_scanout_buffer
   - Allow to dump kmsg to the screen

  bridge:
   - Remove redundant checks on bridge->encoder
   - Remove drm_bridge_chain_mode_fixup
   - bridge-connector: Plumb in the new HDMI helper
   - analogix_dp: Various improvements, handle AUX transfers timeout
   - samsung-dsim: Fix timings calculation
   - tc358767: Plenty of small fixes, fix no connector attach, fix
               clocks
   - sii902x: state validation improvements

  panels:
   - Switch panels from register table initialization to proper code
   - Now that the panel code tracks the panel state, remove every ad-hoc
     implementation in the panel drivers
   - More cleanup of prepare / enable state tracking in drivers
   - edp: Drop legacy panel compatibles
   - simple-bridge: Switch to devm_drm_bridge_add
   - New panels: Lincoln Tech Sol LCD185-101CT, Microtips Technology
                 13-101HIEBCAF0-C, Microtips Technology MF-103HIEB0GA0,
                 BOE nv110wum-l60, IVO t109nw41, WL-355608-A8, PrimeView
                 PM070WL4, Lincoln Technologies LCD197, Ortustech
                 COM35H3P70ULC, AUO G104STN01, K&d kd101ne3-40ti

  amdgpu:
   - DCN 4.0.x support
   - GC 12.0 support
   - GMC 12.0 support
   - SDMA 7.0 support
   - MES12 support
   - MMHUB 4.1 support
   - GFX12 modifier and DCC support
   - lots of IP fixes/updates

  amdkfd:
   - Contiguous VRAM allocations
   - GC 12.0 support
   - SDMA 7.0 support
   - SR-IOV fixes
   - KFD GFX ALU exceptions

  i915:
   - Battlemage Xe2 HPD display enablement
   - Panel Replay enabling
   - DP AUX-less ALPM/LOBF
   - Enable link training failure fallback for DP MST links
   - CMRR (Content Match Refresh Rate) enabling
   - Increase ADL-S/ADL-P/DG2+ max TMDS bitrate to 6 Gbps
   - Enable eDP AUX based HDR backlight
   - Support replaying GPU hangs with captured context image
   - Automate CCS Mode setting during engine resets
   - lots of refactoring
   - Support replaying GPU hangs with captured context image
   - Increase FLR timeout from 3s to 9s
   - Enable w/a 16021333562 for DG2, MTL and ARL [guc]

  xe:
   - update MAINATINERS
   - New uapi adding OA functionality to Xe
   - expose l3 bank mask
   - fix display detect on ADL-N
   - runtime PM Fixes
   - Fix silent backmerge issues
   - More prep for SR-IOV
   - HWmon additions
   - per client usage info
   - Rework GPU page fault handling
   - Drop EXEC_QUEUE_FLAG_BANNED
   - Add BMG PCI IDs
   - Scheduler fixes and improvements
   - Rename xe_exec_queue::compute to xe_exec_queue::lr
   - Use ttm_uncached for BO with NEEDS_UC flag
   - Rename xe perf layer as xe observation layer
   - lots of refactoring

  radeon:
   - Backlight workaround for iMac
   - Silence UBSAN flex array warnings

  msm:
   - Validate registers XML description against schema in CI
   - core/dpu: SM7150 support
   - mdp5: Add support for MSM8937
   - gpu: Add param for userspace to know if raytracing is supported
   - gpu: X185 support (aka gpu in X1 laptop chips)
   - gpu: a505 support

  ivpu:
   - hardware scheduler support
   - profiling support
   - improvements to the platform support layer
   - firmware handling improvements
   - clocks/power mgmt improvements
   - scheduler/logging improvements

  habanalabs:
   - Gradual sleep in polling memory macro
   - Reduce Gaudi2 MSI-X interrupt count to 128
   - Add Gaudi2-D revision support
   - Add timestamp to CPLD info
   - Gaudi2: Assume hard-reset by firmware upon MC SEI severe error
   - Align Gaudi2 interrupt names
   - Check for errors after preboot is ready
   - Change habanalabs maintainer and git repo path

  mgag200:
   - refactoring and improvements
   - Add BMC output
   - enable polling

  nouveau:
   - add registry command line

  v3d:
   - perf counters improvements

  zynqmp:
   - irq and debugfs improvements

  atmel-hlcdc:
   - Support XLCDC in sam9x7

  mipi-dbi:
   - Remove mipi_dbi_machine_little_endian
   - make SPI bits per word configurable
   - support RGB888
   - allow pixel formats to be specified in the DT

  sun4i:
   - Rework the blender setup for DE2

  panfrost:
   - Enable MT8188 support

  vc4:
   - Monochrome TV support

  exynos:
   - fix fallback mode regression
   - fix memory leak
   - Use drm_edid_duplicate() instead of kmemdup()

  etnaviv:
   - fix i.MX8MP NPU clock gating
   - workaround FE register cdc issues on some cores
   - fix DMA sync handling for cached buffers
   - fix job timeout handling
   - keep TS enabled on MMUv2 cores for improved performance

  mediatek:
   - Convert to platform remove callback returning void-
   - Drop chain_mode_fixup call in mode_valid()
   - Fixes the errors of MediaTek display driver found by IGT
   - Add display support for the MT8365-EVK board
   - Fix bit depth overwritten for mtk_ovl_set bit_depth()
   - Fix possible_crtcs calculation
   - Fix spurious kfree()

  ast:
   - refactor mode setting code

  stm:
   - Add LVDS support
   - DSI PHY updates"

* tag 'drm-next-2024-07-18' of https://gitlab.freedesktop.org/drm/kernel: (2501 commits)
  drm/amdgpu/mes12: add missing opcode string
  drm/amdgpu/mes11: update opcode strings
  Revert "drm/amd/display: Reset freesync config before update new state"
  drm/omap: Restrict compile testing to PAGE_SIZE less than 64KB
  drm/xe: Drop trace_xe_hw_fence_free
  drm/xe/uapi: Rename xe perf layer as xe observation layer
  drm/amdgpu: remove exp hw support check for gfx12
  drm/amdgpu: timely save bad pages to eeprom after gpu ras reset is completed
  drm/amdgpu: flush all cached ras bad pages to eeprom
  drm/amdgpu: select compute ME engines dynamically
  drm/amd/display: Allow display DCC for DCN401
  drm/amdgpu: select compute ME engines dynamically
  drm/amdgpu/job: Replace DRM_INFO/ERROR logging
  drm/amdgpu: select compute ME engines dynamically
  drm/amd/pm: Ignore initial value in smu response register
  drm/amdgpu: Initialize VF partition mode
  drm/amd/amdgpu: fix SDMA IRQ client ID <-> req mapping
  MAINTAINERS: fix Xinhui's name
  MAINTAINERS: update powerplay and swsmu
  drm/qxl: Pin buffer objects for internal mappings
  ...

1 files changed, 227 insertions, 1 deletions

diff --git a/drivers/gpu/drm/v3d/v3d_perfmon.c b/drivers/gpu/drm/v3d/v3d_perfmon.c
index e1be7368b87d..b7d0b02e1a95 100644
--- a/drivers/gpu/drm/v3d/v3d_perfmon.c
+++ b/drivers/gpu/drm/v3d/v3d_perfmon.c
@@ -9,6 +9,192 @@
 #define V3D_PERFMONID_MIN	1
 #define V3D_PERFMONID_MAX	U32_MAX
 
+static const struct v3d_perf_counter_desc v3d_v42_performance_counters[] = {
+	{"FEP", "FEP-valid-primitives-no-rendered-pixels", "[FEP] Valid primitives that result in no rendered pixels, for all rendered tiles"},
+	{"FEP", "FEP-valid-primitives-rendered-pixels", "[FEP] Valid primitives for all rendered tiles (primitives may be counted in more than one tile)"},
+	{"FEP", "FEP-clipped-quads", "[FEP] Early-Z/Near/Far clipped quads"},
+	{"FEP", "FEP-valid-quads", "[FEP] Valid quads"},
+	{"TLB", "TLB-quads-not-passing-stencil-test", "[TLB] Quads with no pixels passing the stencil test"},
+	{"TLB", "TLB-quads-not-passing-z-and-stencil-test", "[TLB] Quads with no pixels passing the Z and stencil tests"},
+	{"TLB", "TLB-quads-passing-z-and-stencil-test", "[TLB] Quads with any pixels passing the Z and stencil tests"},
+	{"TLB", "TLB-quads-with-zero-coverage", "[TLB] Quads with all pixels having zero coverage"},
+	{"TLB", "TLB-quads-with-non-zero-coverage", "[TLB] Quads with any pixels having non-zero coverage"},
+	{"TLB", "TLB-quads-written-to-color-buffer", "[TLB] Quads with valid pixels written to colour buffer"},
+	{"PTB", "PTB-primitives-discarded-outside-viewport", "[PTB] Primitives discarded by being outside the viewport"},
+	{"PTB", "PTB-primitives-need-clipping", "[PTB] Primitives that need clipping"},
+	{"PTB", "PTB-primitives-discarded-reversed", "[PTB] Primitives that are discarded because they are reversed"},
+	{"QPU", "QPU-total-idle-clk-cycles", "[QPU] Total idle clock cycles for all QPUs"},
+	{"QPU", "QPU-total-active-clk-cycles-vertex-coord-shading", "[QPU] Total active clock cycles for all QPUs doing vertex/coordinate/user shading (counts only when QPU is not stalled)"},
+	{"QPU", "QPU-total-active-clk-cycles-fragment-shading", "[QPU] Total active clock cycles for all QPUs doing fragment shading (counts only when QPU is not stalled)"},
+	{"QPU", "QPU-total-clk-cycles-executing-valid-instr", "[QPU] Total clock cycles for all QPUs executing valid instructions"},
+	{"QPU", "QPU-total-clk-cycles-waiting-TMU", "[QPU] Total clock cycles for all QPUs stalled waiting for TMUs only (counter won't increment if QPU also stalling for another reason)"},
+	{"QPU", "QPU-total-clk-cycles-waiting-scoreboard", "[QPU] Total clock cycles for all QPUs stalled waiting for Scoreboard only (counter won't increment if QPU also stalling for another reason)"},
+	{"QPU", "QPU-total-clk-cycles-waiting-varyings", "[QPU] Total clock cycles for all QPUs stalled waiting for Varyings only (counter won't increment if QPU also stalling for another reason)"},
+	{"QPU", "QPU-total-instr-cache-hit", "[QPU] Total instruction cache hits for all slices"},
+	{"QPU", "QPU-total-instr-cache-miss", "[QPU] Total instruction cache misses for all slices"},
+	{"QPU", "QPU-total-uniform-cache-hit", "[QPU] Total uniforms cache hits for all slices"},
+	{"QPU", "QPU-total-uniform-cache-miss", "[QPU] Total uniforms cache misses for all slices"},
+	{"TMU", "TMU-total-text-quads-access", "[TMU] Total texture cache accesses"},
+	{"TMU", "TMU-total-text-cache-miss", "[TMU] Total texture cache misses (number of fetches from memory/L2cache)"},
+	{"VPM", "VPM-total-clk-cycles-VDW-stalled", "[VPM] Total clock cycles VDW is stalled waiting for VPM access"},
+	{"VPM", "VPM-total-clk-cycles-VCD-stalled", "[VPM] Total clock cycles VCD is stalled waiting for VPM access"},
+	{"CLE", "CLE-bin-thread-active-cycles", "[CLE] Bin thread active cycles"},
+	{"CLE", "CLE-render-thread-active-cycles", "[CLE] Render thread active cycles"},
+	{"L2T", "L2T-total-cache-hit", "[L2T] Total Level 2 cache hits"},
+	{"L2T", "L2T-total-cache-miss", "[L2T] Total Level 2 cache misses"},
+	{"CORE", "cycle-count", "[CORE] Cycle counter"},
+	{"QPU", "QPU-total-clk-cycles-waiting-vertex-coord-shading", "[QPU] Total stalled clock cycles for all QPUs doing vertex/coordinate/user shading"},
+	{"QPU", "QPU-total-clk-cycles-waiting-fragment-shading", "[QPU] Total stalled clock cycles for all QPUs doing fragment shading"},
+	{"PTB", "PTB-primitives-binned", "[PTB] Total primitives binned"},
+	{"AXI", "AXI-writes-seen-watch-0", "[AXI] Writes seen by watch 0"},
+	{"AXI", "AXI-reads-seen-watch-0", "[AXI] Reads seen by watch 0"},
+	{"AXI", "AXI-writes-stalled-seen-watch-0", "[AXI] Write stalls seen by watch 0"},
+	{"AXI", "AXI-reads-stalled-seen-watch-0", "[AXI] Read stalls seen by watch 0"},
+	{"AXI", "AXI-write-bytes-seen-watch-0", "[AXI] Total bytes written seen by watch 0"},
+	{"AXI", "AXI-read-bytes-seen-watch-0", "[AXI] Total bytes read seen by watch 0"},
+	{"AXI", "AXI-writes-seen-watch-1", "[AXI] Writes seen by watch 1"},
+	{"AXI", "AXI-reads-seen-watch-1", "[AXI] Reads seen by watch 1"},
+	{"AXI", "AXI-writes-stalled-seen-watch-1", "[AXI] Write stalls seen by watch 1"},
+	{"AXI", "AXI-reads-stalled-seen-watch-1", "[AXI] Read stalls seen by watch 1"},
+	{"AXI", "AXI-write-bytes-seen-watch-1", "[AXI] Total bytes written seen by watch 1"},
+	{"AXI", "AXI-read-bytes-seen-watch-1", "[AXI] Total bytes read seen by watch 1"},
+	{"TLB", "TLB-partial-quads-written-to-color-buffer", "[TLB] Partial quads written to the colour buffer"},
+	{"TMU", "TMU-total-config-access", "[TMU] Total config accesses"},
+	{"L2T", "L2T-no-id-stalled", "[L2T] No ID stall"},
+	{"L2T", "L2T-command-queue-stalled", "[L2T] Command queue full stall"},
+	{"L2T", "L2T-TMU-writes", "[L2T] TMU write accesses"},
+	{"TMU", "TMU-active-cycles", "[TMU] Active cycles"},
+	{"TMU", "TMU-stalled-cycles", "[TMU] Stalled cycles"},
+	{"CLE", "CLE-thread-active-cycles", "[CLE] Bin or render thread active cycles"},
+	{"L2T", "L2T-TMU-reads", "[L2T] TMU read accesses"},
+	{"L2T", "L2T-CLE-reads", "[L2T] CLE read accesses"},
+	{"L2T", "L2T-VCD-reads", "[L2T] VCD read accesses"},
+	{"L2T", "L2T-TMU-config-reads", "[L2T] TMU CFG read accesses"},
+	{"L2T", "L2T-SLC0-reads", "[L2T] SLC0 read accesses"},
+	{"L2T", "L2T-SLC1-reads", "[L2T] SLC1 read accesses"},
+	{"L2T", "L2T-SLC2-reads", "[L2T] SLC2 read accesses"},
+	{"L2T", "L2T-TMU-write-miss", "[L2T] TMU write misses"},
+	{"L2T", "L2T-TMU-read-miss", "[L2T] TMU read misses"},
+	{"L2T", "L2T-CLE-read-miss", "[L2T] CLE read misses"},
+	{"L2T", "L2T-VCD-read-miss", "[L2T] VCD read misses"},
+	{"L2T", "L2T-TMU-config-read-miss", "[L2T] TMU CFG read misses"},
+	{"L2T", "L2T-SLC0-read-miss", "[L2T] SLC0 read misses"},
+	{"L2T", "L2T-SLC1-read-miss", "[L2T] SLC1 read misses"},
+	{"L2T", "L2T-SLC2-read-miss", "[L2T] SLC2 read misses"},
+	{"CORE", "core-memory-writes", "[CORE] Total memory writes"},
+	{"L2T", "L2T-memory-writes", "[L2T] Total memory writes"},
+	{"PTB", "PTB-memory-writes", "[PTB] Total memory writes"},
+	{"TLB", "TLB-memory-writes", "[TLB] Total memory writes"},
+	{"CORE", "core-memory-reads", "[CORE] Total memory reads"},
+	{"L2T", "L2T-memory-reads", "[L2T] Total memory reads"},
+	{"PTB", "PTB-memory-reads", "[PTB] Total memory reads"},
+	{"PSE", "PSE-memory-reads", "[PSE] Total memory reads"},
+	{"TLB", "TLB-memory-reads", "[TLB] Total memory reads"},
+	{"GMP", "GMP-memory-reads", "[GMP] Total memory reads"},
+	{"PTB", "PTB-memory-words-writes", "[PTB] Total memory words written"},
+	{"TLB", "TLB-memory-words-writes", "[TLB] Total memory words written"},
+	{"PSE", "PSE-memory-words-reads", "[PSE] Total memory words read"},
+	{"TLB", "TLB-memory-words-reads", "[TLB] Total memory words read"},
+	{"TMU", "TMU-MRU-hits", "[TMU] Total MRU hits"},
+	{"CORE", "compute-active-cycles", "[CORE] Compute active cycles"},
+};
+
+static const struct v3d_perf_counter_desc v3d_v71_performance_counters[] = {
+	{"CORE", "cycle-count", "[CORE] Cycle counter"},
+	{"CORE", "core-active", "[CORE] Bin/Render/Compute active cycles"},
+	{"CLE", "CLE-bin-thread-active-cycles", "[CLE] Bin thread active cycles"},
+	{"CLE", "CLE-render-thread-active-cycles", "[CLE] Render thread active cycles"},
+	{"CORE", "compute-active-cycles", "[CORE] Compute active cycles"},
+	{"FEP", "FEP-valid-primitives-no-rendered-pixels", "[FEP] Valid primitives that result in no rendered pixels, for all rendered tiles"},
+	{"FEP", "FEP-valid-primitives-rendered-pixels", "[FEP] Valid primitives for all rendered tiles (primitives may be counted in more than one tile)"},
+	{"FEP", "FEP-clipped-quads", "[FEP] Early-Z/Near/Far clipped quads"},
+	{"FEP", "FEP-valid-quads", "[FEP] Valid quads"},
+	{"TLB", "TLB-quads-not-passing-stencil-test", "[TLB] Quads with no pixels passing the stencil test"},
+	{"TLB", "TLB-quads-not-passing-z-and-stencil-test", "[TLB] Quads with no pixels passing the Z and stencil tests"},
+	{"TLB", "TLB-quads-passing-z-and-stencil-test", "[TLB] Quads with any pixels passing the Z and stencil tests"},
+	{"TLB", "TLB-quads-written-to-color-buffer", "[TLB] Quads with valid pixels written to colour buffer"},
+	{"TLB", "TLB-partial-quads-written-to-color-buffer", "[TLB] Partial quads written to the colour buffer"},
+	{"PTB", "PTB-primitives-need-clipping", "[PTB] Primitives that need clipping"},
+	{"PTB", "PTB-primitives-discarded-outside-viewport", "[PTB] Primitives discarded by being outside the viewport"},
+	{"PTB", "PTB-primitives-binned", "[PTB] Total primitives binned"},
+	{"PTB", "PTB-primitives-discarded-reversed", "[PTB] Primitives that are discarded because they are reversed"},
+	{"QPU", "QPU-total-instr-cache-hit", "[QPU] Total instruction cache hits for all slices"},
+	{"QPU", "QPU-total-instr-cache-miss", "[QPU] Total instruction cache misses for all slices"},
+	{"QPU", "QPU-total-uniform-cache-hit", "[QPU] Total uniforms cache hits for all slices"},
+	{"QPU", "QPU-total-uniform-cache-miss", "[QPU] Total uniforms cache misses for all slices"},
+	{"TMU", "TMU-active-cycles", "[TMU] Active cycles"},
+	{"TMU", "TMU-stalled-cycles", "[TMU] Stalled cycles"},
+	{"TMU", "TMU-total-text-quads-access", "[TMU] Total texture cache accesses"},
+	{"TMU", "TMU-cache-x4-active-cycles", "[TMU] Cache active cycles for x4 access"},
+	{"TMU", "TMU-cache-x4-stalled-cycles", "[TMU] Cache stalled cycles for x4 access"},
+	{"TMU", "TMU-total-text-quads-x4-access", "[TMU] Total texture cache x4 access"},
+	{"L2T", "L2T-total-cache-hit", "[L2T] Total Level 2 cache hits"},
+	{"L2T", "L2T-total-cache-miss", "[L2T] Total Level 2 cache misses"},
+	{"L2T", "L2T-local", "[L2T] Local mode access"},
+	{"L2T", "L2T-writeback", "[L2T] Writeback"},
+	{"L2T", "L2T-zero", "[L2T] Zero"},
+	{"L2T", "L2T-merge", "[L2T] Merge"},
+	{"L2T", "L2T-fill", "[L2T] Fill"},
+	{"L2T", "L2T-stalls-no-wid", "[L2T] Stalls because no WID available"},
+	{"L2T", "L2T-stalls-no-rid", "[L2T] Stalls because no RID available"},
+	{"L2T", "L2T-stalls-queue-full", "[L2T] Stalls because internal queue full"},
+	{"L2T", "L2T-stalls-wrightback", "[L2T] Stalls because writeback in flight"},
+	{"L2T", "L2T-stalls-mem", "[L2T] Stalls because AXI blocks read"},
+	{"L2T", "L2T-stalls-fill", "[L2T] Stalls because fill pending for victim cache-line"},
+	{"L2T", "L2T-hitq", "[L2T] Sent request via hit queue"},
+	{"L2T", "L2T-hitq-full", "[L2T] Sent request via main queue because hit queue is full"},
+	{"L2T", "L2T-stalls-read-data", "[L2T] Stalls because waiting for data from SDRAM"},
+	{"L2T", "L2T-TMU-read-hits", "[L2T] TMU read hits"},
+	{"L2T", "L2T-TMU-read-miss", "[L2T] TMU read misses"},
+	{"L2T", "L2T-VCD-read-hits", "[L2T] VCD read hits"},
+	{"L2T", "L2T-VCD-read-miss", "[L2T] VCD read misses"},
+	{"L2T", "L2T-SLC-read-hits", "[L2T] SLC read hits (all slices)"},
+	{"L2T", "L2T-SLC-read-miss", "[L2T] SLC read misses (all slices)"},
+	{"AXI", "AXI-writes-seen-watch-0", "[AXI] Writes seen by watch 0"},
+	{"AXI", "AXI-reads-seen-watch-0", "[AXI] Reads seen by watch 0"},
+	{"AXI", "AXI-writes-stalled-seen-watch-0", "[AXI] Write stalls seen by watch 0"},
+	{"AXI", "AXI-reads-stalled-seen-watch-0", "[AXI] Read stalls seen by watch 0"},
+	{"AXI", "AXI-write-bytes-seen-watch-0", "[AXI] Total bytes written seen by watch 0"},
+	{"AXI", "AXI-read-bytes-seen-watch-0", "[AXI] Total bytes read seen by watch 0"},
+	{"AXI", "AXI-writes-seen-watch-1", "[AXI] Writes seen by watch 1"},
+	{"AXI", "AXI-reads-seen-watch-1", "[AXI] Reads seen by watch 1"},
+	{"AXI", "AXI-writes-stalled-seen-watch-1", "[AXI] Write stalls seen by watch 1"},
+	{"AXI", "AXI-reads-stalled-seen-watch-1", "[AXI] Read stalls seen by watch 1"},
+	{"AXI", "AXI-write-bytes-seen-watch-1", "[AXI] Total bytes written seen by watch 1"},
+	{"AXI", "AXI-read-bytes-seen-watch-1", "[AXI] Total bytes read seen by watch 1"},
+	{"CORE", "core-memory-writes", "[CORE] Total memory writes"},
+	{"L2T", "L2T-memory-writes", "[L2T] Total memory writes"},
+	{"PTB", "PTB-memory-writes", "[PTB] Total memory writes"},
+	{"TLB", "TLB-memory-writes", "[TLB] Total memory writes"},
+	{"CORE", "core-memory-reads", "[CORE] Total memory reads"},
+	{"L2T", "L2T-memory-reads", "[L2T] Total memory reads"},
+	{"PTB", "PTB-memory-reads", "[PTB] Total memory reads"},
+	{"PSE", "PSE-memory-reads", "[PSE] Total memory reads"},
+	{"TLB", "TLB-memory-reads", "[TLB] Total memory reads"},
+	{"PTB", "PTB-memory-words-writes", "[PTB] Total memory words written"},
+	{"TLB", "TLB-memory-words-writes", "[TLB] Total memory words written"},
+	{"PSE", "PSE-memory-words-reads", "[PSE] Total memory words read"},
+	{"TLB", "TLB-memory-words-reads", "[TLB] Total memory words read"},
+	{"AXI", "AXI-read-trans", "[AXI] Read transaction count"},
+	{"AXI", "AXI-write-trans", "[AXI] Write transaction count"},
+	{"AXI", "AXI-read-wait-cycles", "[AXI] Read total wait cycles"},
+	{"AXI", "AXI-write-wait-cycles", "[AXI] Write total wait cycles"},
+	{"AXI", "AXI-max-outstanding-reads", "[AXI] Maximum outstanding read transactions"},
+	{"AXI", "AXI-max-outstanding-writes", "[AXI] Maximum outstanding write transactions"},
+	{"QPU", "QPU-wait-bubble", "[QPU] Pipeline bubble in qcycles due all threads waiting"},
+	{"QPU", "QPU-ic-miss-bubble", "[QPU] Pipeline bubble in qcycles due instruction-cache miss"},
+	{"QPU", "QPU-active", "[QPU] Executed shader instruction"},
+	{"QPU", "QPU-total-active-clk-cycles-fragment-shading", "[QPU] Total active clock cycles for all QPUs doing fragment shading (counts only when QPU is not stalled)"},
+	{"QPU", "QPU-stalls", "[QPU] Stalled qcycles executing shader instruction"},
+	{"QPU", "QPU-total-clk-cycles-waiting-fragment-shading", "[QPU] Total stalled clock cycles for all QPUs doing fragment shading"},
+	{"QPU", "QPU-stalls-TMU", "[QPU] Stalled qcycles waiting for TMU"},
+	{"QPU", "QPU-stalls-TLB", "[QPU] Stalled qcycles waiting for TLB"},
+	{"QPU", "QPU-stalls-VPM", "[QPU] Stalled qcycles waiting for VPM"},
+	{"QPU", "QPU-stalls-uniforms", "[QPU] Stalled qcycles waiting for uniforms"},
+	{"QPU", "QPU-stalls-SFU", "[QPU] Stalled qcycles waiting for SFU"},
+	{"QPU", "QPU-stalls-other", "[QPU] Stalled qcycles waiting for any other reason (vary/W/Z)"},
+};
+
 void v3d_perfmon_get(struct v3d_perfmon *perfmon)
 {
 	if (perfmon)
@@ -123,6 +309,7 @@ int v3d_perfmon_create_ioctl(struct drm_device *dev, void *data,
 {
 	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
 	struct drm_v3d_perfmon_create *req = data;
+	struct v3d_dev *v3d = v3d_priv->v3d;
 	struct v3d_perfmon *perfmon;
 	unsigned int i;
 	int ret;
@@ -134,7 +321,7 @@ int v3d_perfmon_create_ioctl(struct drm_device *dev, void *data,
 
 	/* Make sure all counters are valid. */
 	for (i = 0; i < req->ncounters; i++) {
-		if (req->counters[i] >= V3D_PERFCNT_NUM)
+		if (req->counters[i] >= v3d->max_counters)
 			return -EINVAL;
 	}
 
@@ -216,3 +403,42 @@ int v3d_perfmon_get_values_ioctl(struct drm_device *dev, void *data,
 
 	return ret;
 }
+
+int v3d_perfmon_get_counter_ioctl(struct drm_device *dev, void *data,
+				  struct drm_file *file_priv)
+{
+	struct drm_v3d_perfmon_get_counter *req = data;
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	const struct v3d_perf_counter_desc *counter;
+
+	for (int i = 0; i < ARRAY_SIZE(req->reserved); i++) {
+		if (req->reserved[i] != 0)
+			return -EINVAL;
+	}
+
+	/* Make sure that the counter ID is valid */
+	if (req->counter >= v3d->max_counters)
+		return -EINVAL;
+
+	BUILD_BUG_ON(ARRAY_SIZE(v3d_v42_performance_counters) !=
+		     V3D_V42_NUM_PERFCOUNTERS);
+	BUILD_BUG_ON(ARRAY_SIZE(v3d_v71_performance_counters) !=
+		     V3D_V71_NUM_PERFCOUNTERS);
+	BUILD_BUG_ON(V3D_MAX_COUNTERS < V3D_V42_NUM_PERFCOUNTERS);
+	BUILD_BUG_ON(V3D_MAX_COUNTERS < V3D_V71_NUM_PERFCOUNTERS);
+	BUILD_BUG_ON((V3D_MAX_COUNTERS != V3D_V42_NUM_PERFCOUNTERS) &&
+		     (V3D_MAX_COUNTERS != V3D_V71_NUM_PERFCOUNTERS));
+
+	if (v3d->ver >= 71)
+		counter = &v3d_v71_performance_counters[req->counter];
+	else if (v3d->ver >= 42)
+		counter = &v3d_v42_performance_counters[req->counter];
+	else
+		return -EOPNOTSUPP;
+
+	strscpy(req->name, counter->name, sizeof(req->name));
+	strscpy(req->category, counter->category, sizeof(req->category));
+	strscpy(req->description, counter->description, sizeof(req->description));
+
+	return 0;
+}