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, 82 insertions, 26 deletions

diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c
index 56588d6e24ae..c6b9be80d83c 100644
--- a/drivers/gpu/drm/i915/display/skl_watermark.c
+++ b/drivers/gpu/drm/i915/display/skl_watermark.c
@@ -23,6 +23,12 @@
 #include "skl_watermark.h"
 #include "skl_watermark_regs.h"
 
+/*It is expected that DSB can do posted writes to every register in
+ * the pipe and planes within 100us. For flip queue use case, the
+ * recommended DSB execution time is 100us + one SAGV block time.
+ */
+#define DSB_EXE_TIME 100
+
 static void skl_sagv_disable(struct drm_i915_private *i915);
 
 /* Stores plane specific WM parameters */
@@ -443,12 +449,35 @@ static int intel_compute_sagv_mask(struct intel_atomic_state *state)
 
 	for_each_new_intel_crtc_in_state(state, crtc,
 					 new_crtc_state, i) {
+		struct skl_pipe_wm *pipe_wm = &new_crtc_state->wm.skl.optimal;
+
 		new_bw_state = intel_atomic_get_bw_state(state);
 		if (IS_ERR(new_bw_state))
 			return PTR_ERR(new_bw_state);
 
 		old_bw_state = intel_atomic_get_old_bw_state(state);
 
+		/*
+		 * We store use_sagv_wm in the crtc state rather than relying on
+		 * that bw state since we have no convenient way to get at the
+		 * latter from the plane commit hooks (especially in the legacy
+		 * cursor case).
+		 *
+		 * drm_atomic_check_only() gets upset if we pull more crtcs
+		 * into the state, so we have to calculate this based on the
+		 * individual intel_crtc_can_enable_sagv() rather than
+		 * the overall intel_can_enable_sagv(). Otherwise the
+		 * crtcs not included in the commit would not switch to the
+		 * SAGV watermarks when we are about to enable SAGV, and that
+		 * would lead to underruns. This does mean extra power draw
+		 * when only a subset of the crtcs are blocking SAGV as the
+		 * other crtcs can't be allowed to use the more optimal
+		 * normal (ie. non-SAGV) watermarks.
+		 */
+		pipe_wm->use_sagv_wm = !HAS_HW_SAGV_WM(i915) &&
+			DISPLAY_VER(i915) >= 12 &&
+			intel_crtc_can_enable_sagv(new_crtc_state);
+
 		if (intel_crtc_can_enable_sagv(new_crtc_state))
 			new_bw_state->pipe_sagv_reject &= ~BIT(crtc->pipe);
 		else
@@ -478,21 +507,6 @@ static int intel_compute_sagv_mask(struct intel_atomic_state *state)
 			return ret;
 	}
 
-	for_each_new_intel_crtc_in_state(state, crtc,
-					 new_crtc_state, i) {
-		struct skl_pipe_wm *pipe_wm = &new_crtc_state->wm.skl.optimal;
-
-		/*
-		 * We store use_sagv_wm in the crtc state rather than relying on
-		 * that bw state since we have no convenient way to get at the
-		 * latter from the plane commit hooks (especially in the legacy
-		 * cursor case)
-		 */
-		pipe_wm->use_sagv_wm = !HAS_HW_SAGV_WM(i915) &&
-			DISPLAY_VER(i915) >= 12 &&
-			intel_can_enable_sagv(i915, new_bw_state);
-	}
-
 	return 0;
 }
 
@@ -1367,7 +1381,7 @@ skl_total_relative_data_rate(const struct intel_crtc_state *crtc_state)
 	u64 data_rate = 0;
 
 	for_each_plane_id_on_crtc(crtc, plane_id) {
-		if (plane_id == PLANE_CURSOR && DISPLAY_VER(i915) < 20)
+		if (plane_id == PLANE_CURSOR)
 			continue;
 
 		data_rate += crtc_state->rel_data_rate[plane_id];
@@ -1514,12 +1528,10 @@ skl_crtc_allocate_plane_ddb(struct intel_atomic_state *state,
 		return 0;
 
 	/* Allocate fixed number of blocks for cursor. */
-	if (DISPLAY_VER(i915) < 20) {
-		cursor_size = skl_cursor_allocation(crtc_state, num_active);
-		iter.size -= cursor_size;
-		skl_ddb_entry_init(&crtc_state->wm.skl.plane_ddb[PLANE_CURSOR],
-				   alloc->end - cursor_size, alloc->end);
-	}
+	cursor_size = skl_cursor_allocation(crtc_state, num_active);
+	iter.size -= cursor_size;
+	skl_ddb_entry_init(&crtc_state->wm.skl.plane_ddb[PLANE_CURSOR],
+			   alloc->end - cursor_size, alloc->end);
 
 	iter.data_rate = skl_total_relative_data_rate(crtc_state);
 
@@ -1533,7 +1545,7 @@ skl_crtc_allocate_plane_ddb(struct intel_atomic_state *state,
 			const struct skl_plane_wm *wm =
 				&crtc_state->wm.skl.optimal.planes[plane_id];
 
-			if (plane_id == PLANE_CURSOR && DISPLAY_VER(i915) < 20) {
+			if (plane_id == PLANE_CURSOR) {
 				const struct skl_ddb_entry *ddb =
 					&crtc_state->wm.skl.plane_ddb[plane_id];
 
@@ -1581,7 +1593,7 @@ skl_crtc_allocate_plane_ddb(struct intel_atomic_state *state,
 		const struct skl_plane_wm *wm =
 			&crtc_state->wm.skl.optimal.planes[plane_id];
 
-		if (plane_id == PLANE_CURSOR && DISPLAY_VER(i915) < 20)
+		if (plane_id == PLANE_CURSOR)
 			continue;
 
 		if (DISPLAY_VER(i915) < 11 &&
@@ -2898,12 +2910,51 @@ static int skl_wm_add_affected_planes(struct intel_atomic_state *state,
 	return 0;
 }
 
+/*
+ * If Fixed Refresh Rate:
+ * Program DEEP PKG_C_LATENCY Pkg C with highest valid latency from
+ * watermark level1 and up and above. If watermark level 1 is
+ * invalid program it with all 1's.
+ * Program PKG_C_LATENCY Added Wake Time = DSB execution time
+ * If Variable Refresh Rate:
+ * Program DEEP PKG_C_LATENCY Pkg C with all 1's.
+ * Program PKG_C_LATENCY Added Wake Time = 0
+ */
+static void
+skl_program_dpkgc_latency(struct drm_i915_private *i915, bool vrr_enabled)
+{
+	u32 max_latency = 0;
+	u32 clear = 0, val = 0;
+	u32 added_wake_time = 0;
+
+	if (DISPLAY_VER(i915) < 20)
+		return;
+
+	if (vrr_enabled) {
+		max_latency = LNL_PKG_C_LATENCY_MASK;
+		added_wake_time = 0;
+	} else {
+		max_latency = skl_watermark_max_latency(i915, 1);
+		if (max_latency == 0)
+			max_latency = LNL_PKG_C_LATENCY_MASK;
+		added_wake_time = DSB_EXE_TIME +
+			i915->display.sagv.block_time_us;
+	}
+
+	clear |= LNL_ADDED_WAKE_TIME_MASK | LNL_PKG_C_LATENCY_MASK;
+	val |= REG_FIELD_PREP(LNL_PKG_C_LATENCY_MASK, max_latency);
+	val |= REG_FIELD_PREP(LNL_ADDED_WAKE_TIME_MASK, added_wake_time);
+
+	intel_uncore_rmw(&i915->uncore, LNL_PKG_C_LATENCY, clear, val);
+}
+
 static int
 skl_compute_wm(struct intel_atomic_state *state)
 {
 	struct intel_crtc *crtc;
 	struct intel_crtc_state __maybe_unused *new_crtc_state;
 	int ret, i;
+	bool vrr_enabled = false;
 
 	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
 		ret = skl_build_pipe_wm(state, crtc);
@@ -2928,8 +2979,13 @@ skl_compute_wm(struct intel_atomic_state *state)
 		ret = skl_wm_add_affected_planes(state, crtc);
 		if (ret)
 			return ret;
+
+		if (new_crtc_state->vrr.enable)
+			vrr_enabled = true;
 	}
 
+	skl_program_dpkgc_latency(to_i915(state->base.dev), vrr_enabled);
+
 	skl_print_wm_changes(state);
 
 	return 0;
@@ -3725,11 +3781,11 @@ void skl_watermark_debugfs_register(struct drm_i915_private *i915)
 				    &intel_sagv_status_fops);
 }
 
-unsigned int skl_watermark_max_latency(struct drm_i915_private *i915)
+unsigned int skl_watermark_max_latency(struct drm_i915_private *i915, int initial_wm_level)
 {
 	int level;
 
-	for (level = i915->display.wm.num_levels - 1; level >= 0; level--) {
+	for (level = i915->display.wm.num_levels - 1; level >= initial_wm_level; level--) {
 		unsigned int latency = skl_wm_latency(i915, level, NULL);
 
 		if (latency)