Merge tag 'drm-next-2023-10-31-1' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Highlights:
   - AMD adds some more upcoming HW platforms
   - Intel made Meteorlake stable and started adding Lunarlake
   - nouveau has a bunch of display rework in prepartion for the NVIDIA
     GSP firmware support
   - msm adds a7xx support
   - habanalabs has finished migration to accel subsystem

  Detail summary:

  kernel:
   - add initial vmemdup-user-array

  core:
   - fix platform remove() to return void
   - drm_file owner updated to reflect owner
   - move size calcs to drm buddy allocator
   - let GPUVM build as a module
   - allow variable number of run-queues in scheduler

  edid:
   - handle bad h/v sync_end in EDIDs

  panfrost:
   - add Boris as maintainer

  fbdev:
   - use fb_ops helpers more
   - only allow logo use from fbcon
   - rename fb_pgproto to pgprot_framebuffer
   - add HPD state to drm_connector_oob_hotplug_event
   - convert to fbdev i/o mem helpers

  i915:
   - Enable meteorlake by default
   - Early Xe2 LPD/Lunarlake display enablement
   - Rework subplatforms into IP version checks
   - GuC based TLB invalidation for Meteorlake
   - Display rework for future Xe driver integration
   - LNL FBC features
   - LNL display feature capability reads
   - update recommended fw versions for DG2+
   - drop fastboot module parameter
   - added deviceid for Arrowlake-S
   - drop preproduction workarounds
   - don't disable preemption for resets
   - cleanup inlines in headers
   - PXP firmware loading fix
   - Fix sg list lengths
   - DSC PPS state readout/verification
   - Add more RPL P/U PCI IDs
   - Add new DG2-G12 stepping
   - DP enhanced framing support to state checker
   - Improve shared link bandwidth management
   - stop using GEM macros in display code
   - refactor related code into display code
   - locally enable W=1 warnings
   - remove PSR watchdog timers on LNL

  amdgpu:
   - RAS/FRU EEPROM updatse
   - IP discovery updatses
   - GC 11.5 support
   - DCN 3.5 support
   - VPE 6.1 support
   - NBIO 7.11 support
   - DML2 support
   - lots of IP updates
   - use flexible arrays for bo list handling
   - W=1 fixes
   - Enable seamless boot in more cases
   - Enable context type property for HDMI
   - Rework GPUVM TLB flushing
   - VCN IB start/size alignment fixes

  amdkfd:
   - GC 10/11 fixes
   - GC 11.5 support
   - use partial migration in GPU faults

  radeon:
   - W=1 Fixes
   - fix some possible buffer overflow/NULL derefs

  nouveau:
   - update uapi for NO_PREFETCH
   - scheduler/fence fixes
   - rework suspend/resume for GSP-RM
   - rework display in preparation for GSP-RM

  habanalabs:
   - uapi: expose tsc clock
   - uapi: block access to eventfd through control device
   - uapi: force dma-buf export to PAGE_SIZE alignments
   - complete move to accel subsystem
   - move firmware interface include files
   - perform hard reset on PCIe AXI drain event
   - optimise user interrupt handling

  msm:
   - DP: use existing helpers for DPCD
   - DPU: interrupts reworked
   - gpu: a7xx (a730/a740) support
   - decouple msm_drv from kms for headless devices

  mediatek:
   - MT8188 dsi/dp/edp support
   - DDP GAMMA - 12 bit LUT support
   - connector dynamic selection capability

  rockchip:
   - rv1126 mipi-dsi/vop support
   - add planar formats

  ast:
   - rename constants

  panels:
   - Mitsubishi AA084XE01
   - JDI LPM102A188A
   - LTK050H3148W-CTA6

  ivpu:
   - power management fixes

  qaic:
   - add detach slice bo api

  komeda:
   - add NV12 writeback

  tegra:
   - support NVSYNC/NHSYNC
   - host1x suspend fixes

  ili9882t:
   - separate into own driver"

* tag 'drm-next-2023-10-31-1' of git://anongit.freedesktop.org/drm/drm: (1803 commits)
  drm/amdgpu: Remove unused variables from amdgpu_show_fdinfo
  drm/amdgpu: Remove duplicate fdinfo fields
  drm/amd/amdgpu: avoid to disable gfxhub interrupt when driver is unloaded
  drm/amdgpu: Add EXT_COHERENT support for APU and NUMA systems
  drm/amdgpu: Retrieve CE count from ce_count_lo_chip in EccInfo table
  drm/amdgpu: Identify data parity error corrected in replay mode
  drm/amdgpu: Fix typo in IP discovery parsing
  drm/amd/display: fix S/G display enablement
  drm/amdxcp: fix amdxcp unloads incompletely
  drm/amd/amdgpu: fix the GPU power print error in pm info
  drm/amdgpu: Use pcie domain of xcc acpi objects
  drm/amd: check num of link levels when update pcie param
  drm/amdgpu: Add a read to GFX v9.4.3 ring test
  drm/amd/pm: call smu_cmn_get_smc_version in is_mode1_reset_supported.
  drm/amdgpu: get RAS poison status from DF v4_6_2
  drm/amdgpu: Use discovery table's subrevision
  drm/amd/display: 3.2.256
  drm/amd/display: add interface to query SubVP status
  drm/amd/display: Read before writing Backlight Mode Set Register
  drm/amd/display: Disable SYMCLK32_SE RCO on DCN314
  ...

1 files changed, 33 insertions, 71 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c
index e0df9b0065f9..ddb344056d40 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c
@@ -114,7 +114,6 @@ bool cm3_helper_translate_curve_to_hw_format(
 	struct pwl_result_data *rgb;
 	struct pwl_result_data *rgb_plus_1;
 	struct pwl_result_data *rgb_minus_1;
-	struct fixed31_32 end_value;
 
 	int32_t region_start, region_end;
 	int32_t i;
@@ -176,7 +175,7 @@ bool cm3_helper_translate_curve_to_hw_format(
 				NUMBER_SW_SEGMENTS;
 		for (i = start_index; i < start_index + NUMBER_SW_SEGMENTS;
 				i += increment) {
-			if (j == hw_points - 1)
+			if (j == hw_points)
 				break;
 			rgb_resulted[j].red = output_tf->tf_pts.red[i];
 			rgb_resulted[j].green = output_tf->tf_pts.green[i];
@@ -187,13 +186,13 @@ bool cm3_helper_translate_curve_to_hw_format(
 
 	/* last point */
 	start_index = (region_end + MAX_LOW_POINT) * NUMBER_SW_SEGMENTS;
-	rgb_resulted[hw_points - 1].red = output_tf->tf_pts.red[start_index];
-	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
-	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
+	rgb_resulted[hw_points].red = output_tf->tf_pts.red[start_index];
+	rgb_resulted[hw_points].green = output_tf->tf_pts.green[start_index];
+	rgb_resulted[hw_points].blue = output_tf->tf_pts.blue[start_index];
 
-	rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red;
-	rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green;
-	rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue;
+	rgb_resulted[hw_points+1].red = rgb_resulted[hw_points].red;
+	rgb_resulted[hw_points+1].green = rgb_resulted[hw_points].green;
+	rgb_resulted[hw_points+1].blue = rgb_resulted[hw_points].blue;
 
 	// All 3 color channels have same x
 	corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
@@ -220,34 +219,16 @@ bool cm3_helper_translate_curve_to_hw_format(
 	/* see comment above, m_arrPoints[1].y should be the Y value for the
 	 * region end (m_numOfHwPoints), not last HW point(m_numOfHwPoints - 1)
 	 */
-	corner_points[1].red.y = rgb_resulted[hw_points - 1].red;
-	corner_points[1].green.y = rgb_resulted[hw_points - 1].green;
-	corner_points[1].blue.y = rgb_resulted[hw_points - 1].blue;
+	corner_points[1].red.y = rgb_resulted[hw_points].red;
+	corner_points[1].green.y = rgb_resulted[hw_points].green;
+	corner_points[1].blue.y = rgb_resulted[hw_points].blue;
 	corner_points[1].red.slope = dc_fixpt_zero;
 	corner_points[1].green.slope = dc_fixpt_zero;
 	corner_points[1].blue.slope = dc_fixpt_zero;
 
-	if (output_tf->tf == TRANSFER_FUNCTION_PQ || output_tf->tf == TRANSFER_FUNCTION_HLG) {
-		/* for PQ/HLG, we want to have a straight line from last HW X point,
-		 * and the slope to be such that we hit 1.0 at 10000/1000 nits.
-		 */
-
-		if (output_tf->tf == TRANSFER_FUNCTION_PQ)
-			end_value = dc_fixpt_from_int(125);
-		else
-			end_value = dc_fixpt_from_fraction(125, 10);
-
-		corner_points[1].red.slope = dc_fixpt_div(
-			dc_fixpt_sub(dc_fixpt_one, corner_points[1].red.y),
-			dc_fixpt_sub(end_value, corner_points[1].red.x));
-		corner_points[1].green.slope = dc_fixpt_div(
-			dc_fixpt_sub(dc_fixpt_one, corner_points[1].green.y),
-			dc_fixpt_sub(end_value, corner_points[1].green.x));
-		corner_points[1].blue.slope = dc_fixpt_div(
-			dc_fixpt_sub(dc_fixpt_one, corner_points[1].blue.y),
-			dc_fixpt_sub(end_value, corner_points[1].blue.x));
-	}
-	lut_params->hw_points_num = hw_points;
+	// DCN3+ have 257 pts in lieu of no separate slope registers
+	// Prior HW had 256 base+slope pairs
+	lut_params->hw_points_num = hw_points + 1;
 
 	k = 0;
 	for (i = 1; i < MAX_REGIONS_NUMBER; i++) {
@@ -267,38 +248,37 @@ bool cm3_helper_translate_curve_to_hw_format(
 	rgb_plus_1 = rgb_resulted + 1;
 	rgb_minus_1 = rgb;
 
-	i = 1;
-	while (i != hw_points + 1) {
-		if (i >= hw_points - 1) {
-			if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
-				rgb_plus_1->red = dc_fixpt_add(rgb->red, rgb_minus_1->delta_red);
-			if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
-				rgb_plus_1->green = dc_fixpt_add(rgb->green, rgb_minus_1->delta_green);
-			if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
-				rgb_plus_1->blue = dc_fixpt_add(rgb->blue, rgb_minus_1->delta_blue);
-		}
-
-		rgb->delta_red   = dc_fixpt_sub(rgb_plus_1->red,   rgb->red);
-		rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
-		rgb->delta_blue  = dc_fixpt_sub(rgb_plus_1->blue,  rgb->blue);
+	if (fixpoint == true) {
+		i = 1;
+		while (i != hw_points + 2) {
+			if (i >= hw_points) {
+				if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
+					rgb_plus_1->red = dc_fixpt_add(rgb->red,
+							rgb_minus_1->delta_red);
+				if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
+					rgb_plus_1->green = dc_fixpt_add(rgb->green,
+							rgb_minus_1->delta_green);
+				if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
+					rgb_plus_1->blue = dc_fixpt_add(rgb->blue,
+							rgb_minus_1->delta_blue);
+			}
 
-		if (fixpoint == true) {
 			rgb->delta_red_reg   = dc_fixpt_clamp_u0d10(rgb->delta_red);
 			rgb->delta_green_reg = dc_fixpt_clamp_u0d10(rgb->delta_green);
 			rgb->delta_blue_reg  = dc_fixpt_clamp_u0d10(rgb->delta_blue);
 			rgb->red_reg         = dc_fixpt_clamp_u0d14(rgb->red);
 			rgb->green_reg       = dc_fixpt_clamp_u0d14(rgb->green);
 			rgb->blue_reg        = dc_fixpt_clamp_u0d14(rgb->blue);
-		}
 
-		++rgb_plus_1;
-		rgb_minus_1 = rgb;
-		++rgb;
-		++i;
+			++rgb_plus_1;
+			rgb_minus_1 = rgb;
+			++rgb;
+			++i;
+		}
 	}
 	cm3_helper_convert_to_custom_float(rgb_resulted,
 						lut_params->corner_points,
-						hw_points, fixpoint);
+						hw_points+1, fixpoint);
 
 	return true;
 }
@@ -603,24 +583,6 @@ bool cm3_helper_convert_to_custom_float(
 			return false;
 		}
 
-		if (!convert_to_custom_float_format(rgb->delta_red, &fmt,
-						    &rgb->delta_red_reg)) {
-			BREAK_TO_DEBUGGER();
-			return false;
-		}
-
-		if (!convert_to_custom_float_format(rgb->delta_green, &fmt,
-						    &rgb->delta_green_reg)) {
-			BREAK_TO_DEBUGGER();
-			return false;
-		}
-
-		if (!convert_to_custom_float_format(rgb->delta_blue, &fmt,
-						    &rgb->delta_blue_reg)) {
-			BREAK_TO_DEBUGGER();
-			return false;
-		}
-
 		++rgb;
 		++i;
 	}