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, 51 insertions, 19 deletions

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index 569b5fe94c41..3f3df1166b86 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -159,6 +159,21 @@ static void gen11_disable_guc_interrupts(struct intel_guc *guc)
 	gen11_reset_guc_interrupts(guc);
 }
 
+static void guc_dead_worker_func(struct work_struct *w)
+{
+	struct intel_guc *guc = container_of(w, struct intel_guc, dead_guc_worker);
+	struct intel_gt *gt = guc_to_gt(guc);
+	unsigned long last = guc->last_dead_guc_jiffies;
+	unsigned long delta = jiffies_to_msecs(jiffies - last);
+
+	if (delta < 500) {
+		intel_gt_set_wedged(gt);
+	} else {
+		intel_gt_handle_error(gt, ALL_ENGINES, I915_ERROR_CAPTURE, "dead GuC");
+		guc->last_dead_guc_jiffies = jiffies;
+	}
+}
+
 void intel_guc_init_early(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
@@ -171,6 +186,8 @@ void intel_guc_init_early(struct intel_guc *guc)
 	intel_guc_slpc_init_early(&guc->slpc);
 	intel_guc_rc_init_early(guc);
 
+	INIT_WORK(&guc->dead_guc_worker, guc_dead_worker_func);
+
 	mutex_init(&guc->send_mutex);
 	spin_lock_init(&guc->irq_lock);
 	if (GRAPHICS_VER(i915) >= 11) {
@@ -272,18 +289,14 @@ static u32 guc_ctl_wa_flags(struct intel_guc *guc)
 	    GRAPHICS_VER_FULL(gt->i915) < IP_VER(12, 50))
 		flags |= GUC_WA_POLLCS;
 
-	/* Wa_16011759253:dg2_g10:a0 */
-	if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0))
-		flags |= GUC_WA_GAM_CREDITS;
-
 	/* Wa_14014475959 */
-	if (IS_MTL_GRAPHICS_STEP(gt->i915, M, STEP_A0, STEP_B0) ||
+	if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) ||
 	    IS_DG2(gt->i915))
 		flags |= GUC_WA_HOLD_CCS_SWITCHOUT;
 
 	/*
-	 * Wa_14012197797:dg2_g10:a0,dg2_g11:a0
-	 * Wa_22011391025:dg2_g10,dg2_g11,dg2_g12
+	 * Wa_14012197797
+	 * Wa_22011391025
 	 *
 	 * The same WA bit is used for both and 22011391025 is applicable to
 	 * all DG2.
@@ -292,28 +305,26 @@ static u32 guc_ctl_wa_flags(struct intel_guc *guc)
 		flags |= GUC_WA_DUAL_QUEUE;
 
 	/* Wa_22011802037: graphics version 11/12 */
-	if (IS_MTL_GRAPHICS_STEP(gt->i915, M, STEP_A0, STEP_B0) ||
-	    (GRAPHICS_VER(gt->i915) >= 11 &&
-	    GRAPHICS_VER_FULL(gt->i915) < IP_VER(12, 70)))
+	if (intel_engine_reset_needs_wa_22011802037(gt))
 		flags |= GUC_WA_PRE_PARSER;
 
-	/* Wa_16011777198:dg2 */
-	if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) ||
-	    IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0))
-		flags |= GUC_WA_RCS_RESET_BEFORE_RC6;
-
 	/*
-	 * Wa_22012727170:dg2_g10[a0-c0), dg2_g11[a0..)
-	 * Wa_22012727685:dg2_g11[a0..)
+	 * Wa_22012727170
+	 * Wa_22012727685
 	 */
-	if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) ||
-	    IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_FOREVER))
+	if (IS_DG2_G11(gt->i915))
 		flags |= GUC_WA_CONTEXT_ISOLATION;
 
 	/* Wa_16015675438 */
 	if (!RCS_MASK(gt))
 		flags |= GUC_WA_RCS_REGS_IN_CCS_REGS_LIST;
 
+	/* Wa_14018913170 */
+	if (GUC_FIRMWARE_VER(guc) >= MAKE_GUC_VER(70, 7, 0)) {
+		if (IS_DG2(gt->i915) || IS_METEORLAKE(gt->i915) || IS_PONTEVECCHIO(gt->i915))
+			flags |= GUC_WA_ENABLE_TSC_CHECK_ON_RC6;
+	}
+
 	return flags;
 }
 
@@ -461,6 +472,8 @@ void intel_guc_fini(struct intel_guc *guc)
 	if (!intel_uc_fw_is_loadable(&guc->fw))
 		return;
 
+	flush_work(&guc->dead_guc_worker);
+
 	if (intel_guc_slpc_is_used(guc))
 		intel_guc_slpc_fini(&guc->slpc);
 
@@ -585,6 +598,20 @@ out:
 	return ret;
 }
 
+int intel_guc_crash_process_msg(struct intel_guc *guc, u32 action)
+{
+	if (action == INTEL_GUC_ACTION_NOTIFY_CRASH_DUMP_POSTED)
+		guc_err(guc, "Crash dump notification\n");
+	else if (action == INTEL_GUC_ACTION_NOTIFY_EXCEPTION)
+		guc_err(guc, "Exception notification\n");
+	else
+		guc_err(guc, "Unknown crash notification: 0x%04X\n", action);
+
+	queue_work(system_unbound_wq, &guc->dead_guc_worker);
+
+	return 0;
+}
+
 int intel_guc_to_host_process_recv_msg(struct intel_guc *guc,
 				       const u32 *payload, u32 len)
 {
@@ -601,6 +628,9 @@ int intel_guc_to_host_process_recv_msg(struct intel_guc *guc,
 	if (msg & INTEL_GUC_RECV_MSG_EXCEPTION)
 		guc_err(guc, "Received early exception notification!\n");
 
+	if (msg & (INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED | INTEL_GUC_RECV_MSG_EXCEPTION))
+		queue_work(system_unbound_wq, &guc->dead_guc_worker);
+
 	return 0;
 }
 
@@ -640,6 +670,8 @@ int intel_guc_suspend(struct intel_guc *guc)
 		return 0;
 
 	if (intel_guc_submission_is_used(guc)) {
+		flush_work(&guc->dead_guc_worker);
+
 		/*
 		 * This H2G MMIO command tears down the GuC in two steps. First it will
 		 * generate a G2H CTB for every active context indicating a reset. In