Merge tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "Highlights are usual, more AMD IP blocks for future hw, i915/xe
  changes, Displayport tunnelling support for i915, msm YUV over DP
  changes, new tests for ttm, but its mostly a lot of stuff all over the
  place from lots of people.

  core:
   - EDID cleanups
   - scheduler error handling fixes
   - managed: add drmm_release_action() with tests
   - add ratelimited drm debug print
   - DPCD PSR early transport macro
   - DP tunneling and bandwidth allocation helpers
   - remove built-in edids
   - dp: Avoid AUX transfers on powered-down displays
   - dp: Add VSC SDP helpers

  cross drivers:
   - use new drm print helpers
   - switch to ->read_edid callback
   - gem: add stats for shared buffers plus updates to amdgpu, i915, xe

  syncobj:
   - fixes to waiting and sleeping

  ttm:
   - add tests
   - fix errno codes
   - simply busy-placement handling
   - fix page decryption

  media:
   - tc358743: fix v4l device registration

  video:
   - move all kernel parameters for video behind CONFIG_VIDEO

  sound:
   - remove <drm/drm_edid.h> include from header

  ci:
   - add tests for msm
   - fix apq8016 runner

  efifb:
   - use copy of global screen_info state

  vesafb:
   - use copy of global screen_info state

  simplefb:
   - fix logging

  bridge:
   - ite-6505: fix DP link-training bug
   - samsung-dsim: fix error checking in probe
   - samsung-dsim: add bsh-smm-s2/pro boards
   - tc358767: fix regmap usage
   - imx: add i.MX8MP HDMI PVI plus DT bindings
   - imx: add i.MX8MP HDMI TX plus DT bindings
   - sii902x: fix probing and unregistration
   - tc358767: limit pixel PLL input range
   - switch to new drm_bridge_read_edid() interface

  panel:
   - ltk050h3146w: error-handling fixes
   - panel-edp: support delay between power-on and enable; use put_sync
     in unprepare; support Mediatek MT8173 Chromebooks, BOE NV116WHM-N49
     V8.0, BOE NV122WUM-N41, CSO MNC207QS1-1 plus DT bindings
   - panel-lvds: support EDT ETML0700Z9NDHA plus DT bindings
   - panel-novatek: FRIDA FRD400B25025-A-CTK plus DT bindings
   - add BOE TH101MB31IG002-28A plus DT bindings
   - add EDT ETML1010G3DRA plus DT bindings
   - add Novatek NT36672E LCD DSI plus DT bindings
   - nt36523: support 120Hz timings, fix includes
   - simple: fix display timings on RK32FN48H
   - visionox-vtdr6130: fix initialization
   - add Powkiddy RGB10MAX3 plus DT bindings
   - st7703: support panel rotation plus DT bindings
   - add Himax HX83112A plus DT bindings
   - ltk500hd1829: add support for ltk101b4029w and admatec 9904370
   - simple: add BOE BP082WX1-100 8.2" panel plus DT bindungs

  panel-orientation-quirks:
   - GPD Win Mini

  amdgpu:
   - Validate DMABuf imports in compute VMs
   - Add RAS ACA framework
   - PSP 13 fixes
   - Misc code cleanups
   - Replay fixes
   - Atom interpretor PS, WS bounds checking
   - DML2 fixes
   - Audio fixes
   - DCN 3.5 Z state fixes
   - Remove deprecated ida_simple usage
   - UBSAN fixes
   - RAS fixes
   - Enable seq64 infrastructure
   - DC color block enablement
   - Documentation updates
   - DC documentation updates
   - DMCUB updates
   - ATHUB 4.1 support
   - LSDMA 7.0 support
   - JPEG DPG support
   - IH 7.0 support
   - HDP 7.0 support
   - VCN 5.0 support
   - SMU 13.0.6 updates
   - NBIO 7.11 updates
   - SDMA 6.1 updates
   - MMHUB 3.3 updates
   - DCN 3.5.1 support
   - NBIF 6.3.1 support
   - VPE 6.1.1 support

  amdkfd:
   - Validate DMABuf imports in compute VMs
   - SVM fixes
   - Trap handler updates and enhancements
   - Fix cache size reporting
   - Relocate the trap handler

  radeon:
   - Atom interpretor PS, WS bounds checking
   - Misc code cleanups

  xe:
   - new query for GuC submission version
   - Remove unused persistent exec_queues
   - Add vram frequency sysfs attributes
   - Add the flag XE_VM_BIND_FLAG_DUMPABLE
   - Drop pre-production workarounds
   - Drop kunit tests for unsupported platforms
   - Start pumbling SR-IOV support with memory based interrupts for VF
   - Allow to map BO in GGTT with PAT index corresponding to XE_CACHE_UC
     to work with memory based interrupts
   - Add GuC Doorbells Manager as prep work SR-IOV
   - Implement additional workarounds for xe2 and MTL
   - Program a few registers according to perfomance guide spec for Xe2
   - Fix remaining 32b build issues and enable it back
   - Fix build with CONFIG_DEBUG_FS=n
   - Fix warnings from GuC ABI headers
   - Introduce Relay Communication for SR-IOV for VF <-> GuC <-> PF
   - Release mmap mappings on rpm suspend
   - Disable mid-thread preemption when not properly supported by
     hardware
   - Fix xe_exec by reserving extra fence slot for CPU bind
   - Fix xe_exec with full long running exec queue
   - Canonicalize addresses where needed for Xe2 and add to devcoredum
   - Toggle USM support for Xe2
   - Only allow 1 ufence per exec / bind IOCTL
   - Add GuC firmware loading for Lunar Lake
   - Add XE_VMA_PTE_64K VMA flag

  i915:
   - Add more ADL-N PCI IDs
   - Enable fastboot also on older platforms
   - Early transport for panel replay and PSR
   - New ARL PCI IDs
   - DP TPS4 PHY test pattern support
   - Unify and improve VSC SDP for PSR and non-PSR cases
   - Refactor memory regions and improve debug logging
   - Rework global state serialization
   - Remove unused CDCLK divider fields
   - Unify HDCP connector logging format
   - Use display instead of graphics version in display code
   - Move VBT and opregion debugfs next to the implementation
   - Abstract opregion interface, use opaque type
   - MTL fixes
   - HPD handling fixes
   - Add GuC submission interface version query
   - Atomically invalidate userptr on mmu-notifier
   - Update handling of MMIO triggered reports
   - Don't make assumptions about intel_wakeref_t type
   - Extend driver code of Xe_LPG to Xe_LPG+
   - Add flex arrays to struct i915_syncmap
   - Allow for very slow HuC loading
   - DP tunneling and bandwidth allocation support

  msm:
   - Correct bindings for MSM8976 and SM8650 platforms
   - Start migration of MDP5 platforms to DPU driver
   - X1E80100 MDSS support
   - DPU:
      - Improve DSC allocation, fixing several important corner cases
      - Add support for SDM630/SDM660 platforms
      - Simplify dpu_encoder_phys_ops
      - Apply fixes targeting DSC support with a single DSC encoder
      - Apply fixes for HCTL_EN timing configuration
      - X1E80100 support
      - Add support for YUV420 over DP
   - GPU:
      - fix sc7180 UBWC config
      - fix a7xx LLC config
      - new gpu support: a305B, a750, a702
      - machine support: SM7150 (different power levels than other a618)
      - a7xx devcoredump support

  habanalabs:
   - configure IRQ affinity according to NUMA node
   - move HBM MMU page tables inside the HBM
   - improve device reset
   - check extended PCIe errors

  ivpu:
   - updates to firmware API
   - refactor BO allocation

  imx:
   - use devm_ functions during init

  hisilicon:
   - fix EDID includes

  mgag200:
   - improve ioremap usage
   - convert to struct drm_edid
   - Work around PCI write bursts

  nouveau:
   - disp: use kmemdup()
   - fix EDID includes
   - documentation fixes

  qaic:
   - fixes to BO handling
   - make use of DRM managed release
   - fix order of remove operations

  rockchip:
   - analogix_dp: get encoder port from DT
   - inno_hdmi: support HDMI for RK3128
   - lvds: error-handling fixes

  ssd130x:
   - support SSD133x plus DT bindings

  tegra:
   - fix error handling

  tilcdc:
   - make use of DRM managed release

  v3d:
   - show memory stats in debugfs
   - Support display MMU page size

  vc4:
   - fix error handling in plane prepare_fb
   - fix framebuffer test in plane helpers

  virtio:
   - add venus capset defines

  vkms:
   - fix OOB access when programming the LUT
   - Kconfig improvements

  vmwgfx:
   - unmap surface before changing plane state
   - fix memory leak in error handling
   - documentation fixes
   - list command SVGA_3D_CMD_DEFINE_GB_SURFACE_V4 as invalid
   - fix null-pointer deref in execbuf
   - refactor display-mode probing
   - fix fencing for creating cursor MOBs
   - fix cursor-memory lifetime

  xlnx:
   - fix live video input for ZynqMP DPSUB

  lima:
   - fix memory leak

  loongson:
   - fail if no VRAM present

  meson:
   - switch to new drm_bridge_read_edid() interface

  renesas:
   - add RZ/G2L DU support plus DT bindings

  mxsfb:
   - Use managed mode config

  sun4i:
   - HDMI: updates to atomic mode setting

  mediatek:
   - Add display driver for MT8188 VDOSYS1
   - DSI driver cleanups
   - Filter modes according to hardware capability
   - Fix a null pointer crash in mtk_drm_crtc_finish_page_flip

  etnaviv:
   - enhancements for NPU and MRT support"

* tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel: (1420 commits)
  drm/amd/display: Removed redundant @ symbol to fix kernel-doc warnings in -next repo
  drm/amd/pm: wait for completion of the EnableGfxImu message
  drm/amdgpu/soc21: add mode2 asic reset for SMU IP v14.0.1
  drm/amdgpu: add smu 14.0.1 support
  drm/amdgpu: add VPE 6.1.1 discovery support
  drm/amdgpu/vpe: add VPE 6.1.1 support
  drm/amdgpu/vpe: don't emit cond exec command under collaborate mode
  drm/amdgpu/vpe: add collaborate mode support for VPE
  drm/amdgpu/vpe: add PRED_EXE and COLLAB_SYNC OPCODE
  drm/amdgpu/vpe: add multi instance VPE support
  drm/amdgpu/discovery: add nbif v6_3_1 ip block
  drm/amdgpu: Add nbif v6_3_1 ip block support
  drm/amdgpu: Add pcie v6_1_0 ip headers (v5)
  drm/amdgpu: Add nbif v6_3_1 ip headers (v5)
  arch/powerpc: Remove <linux/fb.h> from backlight code
  macintosh/via-pmu-backlight: Include <linux/backlight.h>
  fbdev/chipsfb: Include <linux/backlight.h>
  drm/etnaviv: Restore some id values
  drm/amdkfd: make kfd_class constant
  drm/amdgpu: add ring timeout information in devcoredump
  ...

1 files changed, 49 insertions, 14 deletions

diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c
index 926e2de00eb5..f8b33999d43f 100644
--- a/drivers/gpu/drm/i915/display/intel_cursor.c
+++ b/drivers/gpu/drm/i915/display/intel_cursor.c
@@ -22,6 +22,7 @@
 #include "intel_frontbuffer.h"
 #include "intel_psr.h"
 #include "intel_psr_regs.h"
+#include "intel_vblank.h"
 #include "skl_watermark.h"
 
 #include "gem/i915_gem_object.h"
@@ -47,12 +48,23 @@ static u32 intel_cursor_base(const struct intel_plane_state *plane_state)
 	return base + plane_state->view.color_plane[0].offset;
 }
 
-static u32 intel_cursor_position(const struct intel_plane_state *plane_state)
+static u32 intel_cursor_position(const struct intel_crtc_state *crtc_state,
+				 const struct intel_plane_state *plane_state,
+				 bool early_tpt)
 {
 	int x = plane_state->uapi.dst.x1;
 	int y = plane_state->uapi.dst.y1;
 	u32 pos = 0;
 
+	/*
+	 * Formula from Bspec:
+	 * MAX(-1 * <Cursor vertical size from CUR_CTL base on cursor mode
+	 * select setting> + 1, CUR_POS Y Position - Update region Y position
+	 */
+	if (early_tpt)
+		y = max(-1 * drm_rect_height(&plane_state->uapi.dst) + 1,
+			y - crtc_state->psr2_su_area.y1);
+
 	if (x < 0) {
 		pos |= CURSOR_POS_X_SIGN;
 		x = -x;
@@ -274,7 +286,7 @@ static void i845_cursor_update_arm(struct intel_plane *plane,
 		size = CURSOR_HEIGHT(height) | CURSOR_WIDTH(width);
 
 		base = intel_cursor_base(plane_state);
-		pos = intel_cursor_position(plane_state);
+		pos = intel_cursor_position(crtc_state, plane_state, false);
 	}
 
 	/* On these chipsets we can only modify the base/size/stride
@@ -503,17 +515,24 @@ static void i9xx_cursor_update_sel_fetch_arm(struct intel_plane *plane,
 					     const struct intel_crtc_state *crtc_state,
 					     const struct intel_plane_state *plane_state)
 {
-	struct drm_i915_private *i915 = to_i915(plane->base.dev);
+	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum pipe pipe = plane->pipe;
 
 	if (!crtc_state->enable_psr2_sel_fetch)
 		return;
 
-	if (drm_rect_height(&plane_state->psr2_sel_fetch_area) > 0)
-		intel_de_write_fw(i915, PLANE_SEL_FETCH_CTL(pipe, plane->id),
+	if (drm_rect_height(&plane_state->psr2_sel_fetch_area) > 0) {
+		if (crtc_state->enable_psr2_su_region_et) {
+			u32 val = intel_cursor_position(crtc_state, plane_state,
+				true);
+			intel_de_write_fw(dev_priv, CURPOS_ERLY_TPT(pipe), val);
+		}
+
+		intel_de_write_fw(dev_priv, PLANE_SEL_FETCH_CTL(pipe, plane->id),
 				  plane_state->ctl);
-	else
+	} else {
 		i9xx_cursor_disable_sel_fetch_arm(plane, crtc_state);
+	}
 }
 
 /* TODO: split into noarm+arm pair */
@@ -536,7 +555,7 @@ static void i9xx_cursor_update_arm(struct intel_plane *plane,
 			fbc_ctl = CUR_FBC_EN | CUR_FBC_HEIGHT(height - 1);
 
 		base = intel_cursor_base(plane_state);
-		pos = intel_cursor_position(plane_state);
+		pos = intel_cursor_position(crtc_state, plane_state, false);
 	}
 
 	/*
@@ -647,12 +666,14 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 {
 	struct intel_plane *plane = to_intel_plane(_plane);
 	struct intel_crtc *crtc = to_intel_crtc(_crtc);
+	struct drm_i915_private *i915 = to_i915(plane->base.dev);
 	struct intel_plane_state *old_plane_state =
 		to_intel_plane_state(plane->base.state);
 	struct intel_plane_state *new_plane_state;
 	struct intel_crtc_state *crtc_state =
 		to_intel_crtc_state(crtc->base.state);
 	struct intel_crtc_state *new_crtc_state;
+	struct intel_vblank_evade_ctx evade;
 	int ret;
 
 	/*
@@ -745,13 +766,25 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 	 */
 	crtc_state->active_planes = new_crtc_state->active_planes;
 
-	/*
-	 * Technically we should do a vblank evasion here to make
-	 * sure all the cursor registers update on the same frame.
-	 * For now just make sure the register writes happen as
-	 * quickly as possible to minimize the race window.
-	 */
-	local_irq_disable();
+	intel_vblank_evade_init(crtc_state, crtc_state, &evade);
+
+	intel_psr_lock(crtc_state);
+
+	if (!drm_WARN_ON(&i915->drm, drm_crtc_vblank_get(&crtc->base))) {
+		/*
+		 * TODO: maybe check if we're still in PSR
+		 * and skip the vblank evasion entirely?
+		 */
+		intel_psr_wait_for_idle_locked(crtc_state);
+
+		local_irq_disable();
+
+		intel_vblank_evade(&evade);
+
+		drm_crtc_vblank_put(&crtc->base);
+	} else {
+		local_irq_disable();
+	}
 
 	if (new_plane_state->uapi.visible) {
 		intel_plane_update_noarm(plane, crtc_state, new_plane_state);
@@ -762,6 +795,8 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 
 	local_irq_enable();
 
+	intel_psr_unlock(crtc_state);
+
 	intel_plane_unpin_fb(old_plane_state);
 
 out_free: