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, 257 insertions, 8 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index da21f2786b5d..1c93e84278a0 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -15,18 +15,23 @@
 #include "display/intel_display.h"
 #include "gem/i915_gem_lmem.h"
 
+#include "intel_context.h"
 #include "intel_ggtt_gmch.h"
+#include "intel_gpu_commands.h"
 #include "intel_gt.h"
 #include "intel_gt_regs.h"
 #include "intel_pci_config.h"
+#include "intel_ring.h"
 #include "i915_drv.h"
 #include "i915_pci.h"
+#include "i915_request.h"
 #include "i915_scatterlist.h"
 #include "i915_utils.h"
 #include "i915_vgpu.h"
 
 #include "intel_gtt.h"
 #include "gen8_ppgtt.h"
+#include "intel_engine_pm.h"
 
 static void i915_ggtt_color_adjust(const struct drm_mm_node *node,
 				   unsigned long color,
@@ -201,22 +206,36 @@ static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt)
 	intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
 }
 
+static void guc_ggtt_ct_invalidate(struct intel_gt *gt)
+{
+	struct intel_uncore *uncore = gt->uncore;
+	intel_wakeref_t wakeref;
+
+	with_intel_runtime_pm_if_active(uncore->rpm, wakeref) {
+		struct intel_guc *guc = &gt->uc.guc;
+
+		intel_guc_invalidate_tlb_guc(guc);
+	}
+}
+
 static void guc_ggtt_invalidate(struct i915_ggtt *ggtt)
 {
 	struct drm_i915_private *i915 = ggtt->vm.i915;
+	struct intel_gt *gt;
 
 	gen8_ggtt_invalidate(ggtt);
 
-	if (GRAPHICS_VER(i915) >= 12) {
-		struct intel_gt *gt;
-
-		list_for_each_entry(gt, &ggtt->gt_list, ggtt_link)
+	list_for_each_entry(gt, &ggtt->gt_list, ggtt_link) {
+		if (intel_guc_tlb_invalidation_is_available(&gt->uc.guc)) {
+			guc_ggtt_ct_invalidate(gt);
+		} else if (GRAPHICS_VER(i915) >= 12) {
 			intel_uncore_write_fw(gt->uncore,
 					      GEN12_GUC_TLB_INV_CR,
 					      GEN12_GUC_TLB_INV_CR_INVALIDATE);
-	} else {
-		intel_uncore_write_fw(ggtt->vm.gt->uncore,
-				      GEN8_GTCR, GEN8_GTCR_INVALIDATE);
+		} else {
+			intel_uncore_write_fw(gt->uncore,
+					      GEN8_GTCR, GEN8_GTCR_INVALIDATE);
+		}
 	}
 }
 
@@ -252,6 +271,145 @@ u64 gen8_ggtt_pte_encode(dma_addr_t addr,
 	return pte;
 }
 
+static bool should_update_ggtt_with_bind(struct i915_ggtt *ggtt)
+{
+	struct intel_gt *gt = ggtt->vm.gt;
+
+	return intel_gt_is_bind_context_ready(gt);
+}
+
+static struct intel_context *gen8_ggtt_bind_get_ce(struct i915_ggtt *ggtt)
+{
+	struct intel_context *ce;
+	struct intel_gt *gt = ggtt->vm.gt;
+
+	if (intel_gt_is_wedged(gt))
+		return NULL;
+
+	ce = gt->engine[BCS0]->bind_context;
+	GEM_BUG_ON(!ce);
+
+	/*
+	 * If the GT is not awake already at this stage then fallback
+	 * to pci based GGTT update otherwise __intel_wakeref_get_first()
+	 * would conflict with fs_reclaim trying to allocate memory while
+	 * doing rpm_resume().
+	 */
+	if (!intel_gt_pm_get_if_awake(gt))
+		return NULL;
+
+	intel_engine_pm_get(ce->engine);
+
+	return ce;
+}
+
+static void gen8_ggtt_bind_put_ce(struct intel_context *ce)
+{
+	intel_engine_pm_put(ce->engine);
+	intel_gt_pm_put(ce->engine->gt);
+}
+
+static bool gen8_ggtt_bind_ptes(struct i915_ggtt *ggtt, u32 offset,
+				struct sg_table *pages, u32 num_entries,
+				const gen8_pte_t pte)
+{
+	struct i915_sched_attr attr = {};
+	struct intel_gt *gt = ggtt->vm.gt;
+	const gen8_pte_t scratch_pte = ggtt->vm.scratch[0]->encode;
+	struct sgt_iter iter;
+	struct i915_request *rq;
+	struct intel_context *ce;
+	u32 *cs;
+
+	if (!num_entries)
+		return true;
+
+	ce = gen8_ggtt_bind_get_ce(ggtt);
+	if (!ce)
+		return false;
+
+	if (pages)
+		iter = __sgt_iter(pages->sgl, true);
+
+	while (num_entries) {
+		int count = 0;
+		dma_addr_t addr;
+		/*
+		 * MI_UPDATE_GTT can update 512 entries in a single command but
+		 * that end up with engine reset, 511 works.
+		 */
+		u32 n_ptes = min_t(u32, 511, num_entries);
+
+		if (mutex_lock_interruptible(&ce->timeline->mutex))
+			goto put_ce;
+
+		intel_context_enter(ce);
+		rq = __i915_request_create(ce, GFP_NOWAIT | GFP_ATOMIC);
+		intel_context_exit(ce);
+		if (IS_ERR(rq)) {
+			GT_TRACE(gt, "Failed to get bind request\n");
+			mutex_unlock(&ce->timeline->mutex);
+			goto put_ce;
+		}
+
+		cs = intel_ring_begin(rq, 2 * n_ptes + 2);
+		if (IS_ERR(cs)) {
+			GT_TRACE(gt, "Failed to ring space for GGTT bind\n");
+			i915_request_set_error_once(rq, PTR_ERR(cs));
+			/* once a request is created, it must be queued */
+			goto queue_err_rq;
+		}
+
+		*cs++ = MI_UPDATE_GTT | (2 * n_ptes);
+		*cs++ = offset << 12;
+
+		if (pages) {
+			for_each_sgt_daddr_next(addr, iter) {
+				if (count == n_ptes)
+					break;
+				*cs++ = lower_32_bits(pte | addr);
+				*cs++ = upper_32_bits(pte | addr);
+				count++;
+			}
+			/* fill remaining with scratch pte, if any */
+			if (count < n_ptes) {
+				memset64((u64 *)cs, scratch_pte,
+					 n_ptes - count);
+				cs += (n_ptes - count) * 2;
+			}
+		} else {
+			memset64((u64 *)cs, pte, n_ptes);
+			cs += n_ptes * 2;
+		}
+
+		intel_ring_advance(rq, cs);
+queue_err_rq:
+		i915_request_get(rq);
+		__i915_request_commit(rq);
+		__i915_request_queue(rq, &attr);
+
+		mutex_unlock(&ce->timeline->mutex);
+		/* This will break if the request is complete or after engine reset */
+		i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
+		if (rq->fence.error)
+			goto err_rq;
+
+		i915_request_put(rq);
+
+		num_entries -= n_ptes;
+		offset += n_ptes;
+	}
+
+	gen8_ggtt_bind_put_ce(ce);
+	return true;
+
+err_rq:
+	i915_request_put(rq);
+put_ce:
+	gen8_ggtt_bind_put_ce(ce);
+	return false;
+}
+
 static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
 {
 	writeq(pte, addr);
@@ -272,6 +430,21 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm,
 	ggtt->invalidate(ggtt);
 }
 
+static void gen8_ggtt_insert_page_bind(struct i915_address_space *vm,
+				       dma_addr_t addr, u64 offset,
+				       unsigned int pat_index, u32 flags)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	gen8_pte_t pte;
+
+	pte = ggtt->vm.pte_encode(addr, pat_index, flags);
+	if (should_update_ggtt_with_bind(i915_vm_to_ggtt(vm)) &&
+	    gen8_ggtt_bind_ptes(ggtt, offset, NULL, 1, pte))
+		return ggtt->invalidate(ggtt);
+
+	gen8_ggtt_insert_page(vm, addr, offset, pat_index, flags);
+}
+
 static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct i915_vma_resource *vma_res,
 				     unsigned int pat_index,
@@ -311,6 +484,50 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 	ggtt->invalidate(ggtt);
 }
 
+static bool __gen8_ggtt_insert_entries_bind(struct i915_address_space *vm,
+					    struct i915_vma_resource *vma_res,
+					    unsigned int pat_index, u32 flags)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	gen8_pte_t scratch_pte = vm->scratch[0]->encode;
+	gen8_pte_t pte_encode;
+	u64 start, end;
+
+	pte_encode = ggtt->vm.pte_encode(0, pat_index, flags);
+	start = (vma_res->start - vma_res->guard) / I915_GTT_PAGE_SIZE;
+	end = start + vma_res->guard / I915_GTT_PAGE_SIZE;
+	if (!gen8_ggtt_bind_ptes(ggtt, start, NULL, end - start, scratch_pte))
+		goto err;
+
+	start = end;
+	end += (vma_res->node_size + vma_res->guard) / I915_GTT_PAGE_SIZE;
+	if (!gen8_ggtt_bind_ptes(ggtt, start, vma_res->bi.pages,
+	      vma_res->node_size / I915_GTT_PAGE_SIZE, pte_encode))
+		goto err;
+
+	start += vma_res->node_size / I915_GTT_PAGE_SIZE;
+	if (!gen8_ggtt_bind_ptes(ggtt, start, NULL, end - start, scratch_pte))
+		goto err;
+
+	return true;
+
+err:
+	return false;
+}
+
+static void gen8_ggtt_insert_entries_bind(struct i915_address_space *vm,
+					  struct i915_vma_resource *vma_res,
+					  unsigned int pat_index, u32 flags)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+
+	if (should_update_ggtt_with_bind(i915_vm_to_ggtt(vm)) &&
+	    __gen8_ggtt_insert_entries_bind(vm, vma_res, pat_index, flags))
+		return ggtt->invalidate(ggtt);
+
+	gen8_ggtt_insert_entries(vm, vma_res, pat_index, flags);
+}
+
 static void gen8_ggtt_clear_range(struct i915_address_space *vm,
 				  u64 start, u64 length)
 {
@@ -332,6 +549,27 @@ static void gen8_ggtt_clear_range(struct i915_address_space *vm,
 		gen8_set_pte(&gtt_base[i], scratch_pte);
 }
 
+static void gen8_ggtt_scratch_range_bind(struct i915_address_space *vm,
+					 u64 start, u64 length)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
+	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
+	const gen8_pte_t scratch_pte = vm->scratch[0]->encode;
+	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
+
+	if (WARN(num_entries > max_entries,
+		 "First entry = %d; Num entries = %d (max=%d)\n",
+		 first_entry, num_entries, max_entries))
+		num_entries = max_entries;
+
+	if (should_update_ggtt_with_bind(ggtt) && gen8_ggtt_bind_ptes(ggtt, first_entry,
+	     NULL, num_entries, scratch_pte))
+		return ggtt->invalidate(ggtt);
+
+	gen8_ggtt_clear_range(vm, start, length);
+}
+
 static void gen6_ggtt_insert_page(struct i915_address_space *vm,
 				  dma_addr_t addr,
 				  u64 offset,
@@ -1008,7 +1246,18 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 			I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;
 	}
 
-	if (intel_uc_wants_guc(&ggtt->vm.gt->uc))
+	if (i915_ggtt_require_binder(i915)) {
+		ggtt->vm.scratch_range = gen8_ggtt_scratch_range_bind;
+		ggtt->vm.insert_page = gen8_ggtt_insert_page_bind;
+		ggtt->vm.insert_entries = gen8_ggtt_insert_entries_bind;
+		/*
+		 * On GPU is hung, we might bind VMAs for error capture.
+		 * Fallback to CPU GGTT updates in that case.
+		 */
+		ggtt->vm.raw_insert_page = gen8_ggtt_insert_page;
+	}
+
+	if (intel_uc_wants_guc_submission(&ggtt->vm.gt->uc))
 		ggtt->invalidate = guc_ggtt_invalidate;
 	else
 		ggtt->invalidate = gen8_ggtt_invalidate;