Merge tag 'drm-next-2022-10-05' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Lots of stuff all over, some new AMD IP support and gang submit
  support. i915 has further DG2 and Meteorlake pieces, and a bunch of
  i915 display refactoring. msm has a shrinker rework. There are also a
  bunch of conversions to use kunit.

  This has two external pieces, some MEI changes needed for future Intel
  discrete GPUs. These should be acked by Greg. There is also a cross
  maintainer shared tree with some backlight rework from Hans in here.

  Core:
   - convert selftests to kunit
   - managed init for more objects
   - move to idr_init_base
   - rename fb and gem cma helpers to dma
   - hide unregistered connectors from getconnector ioctl
   - DSC passthrough aux support
   - backlight handling improvements
   - add dma_resv_assert_held to vmap/vunmap

  edid:
   - move luminance calculation to core

  fbdev:
   - fix aperture helper usage

  fourcc:
   - add more format helpers
   - add DRM_FORMAT_Cxx, DRM_FORMAT_Rxx, DRM_FORMAT_Dxx
   - add packed AYUV8888, XYUV8888
   - add some kunit tests

  ttm:
   - allow bos without backing store
   - rewrite placement to use intersect/compatible functions

  dma-buf:
   - docs update
   - improve signalling when debugging

  udmabuf:
   - fix failure path GPF

  dp:
   - drop dp/mst legacy code
   - atomic mst state support
   - audio infoframe packing

  panel:
   - Samsung LTL101AL01
   - B120XAN01.0
   - R140NWF5 RH
   - DMT028VGHMCMI-1A T
   - AUO B133UAN02.1
   - IVO M133NW4J-R3
   - Innolux N120ACA-EA1

  amdgpu:
   - Gang submit support
   - Mode2 reset for RDNA2
   - New IP support:
        DCN 3.1.4, 3.2
        SMU 13.x
        NBIO 7.7
        GC 11.x
        PSP 13.x
        SDMA 6.x
        GMC 11.x
   - DSC passthrough support
   - PSP fixes for TA support
   - vangogh GFXOFF stats
   - clang fixes
   - gang submit CS cleanup prep work
   - fix VRAM eviction issues

  amdkfd:
   - GC 10.3 IP ISA fixes
   - fix CRIU regression
   - CPU fault on COW mapping fixes

  i915:
   - align fw versioning with kernel practices
   - add display substruct to i915 private
   - add initial runtime info to driver info
   - split out HDCP and backlight registers
   - MEI XeHP SDV GSC support
   - add per-gt sysfs defaults
   - TLB invalidation improvements
   - Disable PCI BAR resize on 32-bit
   - GuC firmware updates and compat changes
   - GuC log timestamp translation
   - DG2 preemption workaround changes
   - DG2 improved HDMI pixel clocks support
   - PCI BAR sanity checks
   - Enable DC5 on DG2
   - DG2 DMC fw bumped
   - ADL-S PCI ID added
   - Meteorlake enablement
   - Rename ggtt_view to gtt_view
   - host RPS fixes
   - release mmaps on rpm suspend on discrete
   - clocking and dpll refactoring
   - VBT definitions and parsing updates
   - SKL watermark code extracted to separate file
   - allow seamless M/N changes on eDP panels
   - BUG_ON removal and cleanups

  msm:
   - DPU:
       simplified VBIF configuration
       cleanup CTL interfaces
   - DSI:
       removed unused msm_display_dsc_config struct
       switch regulator calls to new API
       switched to PANEL_BRIDGE for direct attached panels
   - DSI_PHY: convert drivers to parent_hws
   - DP: cleanup pixel_rate handling
   - HDMI: turned hdmi-phy-8996 into OF clk provider
   - misc dt-bindings fixes
   - choose eDP as primary display if it's available
   - support getting interconnects from either the mdss or the mdp5/dpu
     device nodes
   - gem: Shrinker + LRU re-work:
   - adds a shared GEM LRU+shrinker helper and moves msm over to that
   - reduce lock contention between retire and submit by avoiding the
     need to acquire obj lock in retire path (and instead using resv
     seeing obj's busyness in the shrinker
   - fix reclaim vs submit issues
   - GEM fault injection for triggering userspace error paths
   - Map/unmap optimization
   - Improved robustness for a6xx GPU recovery

  virtio:
   - improve error and edge conditions handling
   - convert to use managed helpers
   - stop exposing LINEAR modifier

  mgag200:
   - split modeset handling per model

  udl:
   - suspend/disconnect handling improvements

  vc4:
   - rework HDMI power up
   - depend on PM
   - better unplugging support

  ast:
   - resolution handling improvements

  ingenic:
   - add JZ4760(B) support
   - avoid a modeset when sharpness property is unchanged
   - use the new PM ops

  it6505:
   - power seq and clock updates

  ssd130x:
   - regmap bulk write
   - use atomic helpers instead of simple helpers

  via:
   - rename via_drv to via_dri1, consolidate all code.

  radeon:
   - drop DP MST experimental support
   - delayed work flush fix
   - use time_after

  ti-sn65dsi86:
   - DP support

  mediatek:
   - MT8195 DP support
   - drop of_gpio header
   - remove unneeded result
   - small DP code improvements

  vkms:
   - RGB565, XRGB64 and ARGB64 support

  sun4i:
   - tv: convert to atomic

  rcar-du:
   - Synopsys DW HDMI bridge DT bindings update

  exynos:
   - use drm_display_info.is_hdmi
   - correct return of mixer_mode_valid and hdmi_mode_valid

  omap:
   - refcounting fix

  rockchip:
   - RK3568 support
   - RK3399 gamma support"

* tag 'drm-next-2022-10-05' of git://anongit.freedesktop.org/drm/drm: (1374 commits)
  drm/amdkfd: Fix UBSAN shift-out-of-bounds warning
  drm/amdkfd: Track unified memory when switching xnack mode
  drm/amdgpu: Enable sram on vcn_4_0_2
  drm/amdgpu: Enable VCN DPG for GC11_0_1
  drm/msm: Fix build break with recent mm tree
  drm/panel: simple: Use dev_err_probe() to simplify code
  drm/panel: panel-edp: Use dev_err_probe() to simplify code
  drm/panel: simple: Add Multi-Inno Technology MI0800FT-9
  dt-bindings: display: simple: Add Multi-Inno Technology MI0800FT-9 panel
  drm/amdgpu: correct the memcpy size for ip discovery firmware
  drm/amdgpu: Skip put_reset_domain if it doesn't exist
  drm/amdgpu: remove switch from amdgpu_gmc_noretry_set
  drm/amdgpu: Fix mc_umc_status used uninitialized warning
  drm/amd/display: Prevent OTG shutdown during PSR SU
  drm/amdgpu: add page retirement handling for CPU RAS
  drm/amdgpu: use RAS error address convert api in mca notifier
  drm/amdgpu: support to convert dedicated umc mca address
  drm/amdgpu: export umc error address convert interface
  drm/amdgpu: fix sdma v4 init microcode error
  drm/amd/display: fix array-bounds error in dc_stream_remove_writeback()
  ...

1 files changed, 67 insertions, 30 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 690fd4f639f1..83b0c5d86e48 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -183,10 +183,12 @@ static void amdgpu_vm_bo_evicted(struct amdgpu_vm_bo_base *vm_bo)
 	struct amdgpu_bo *bo = vm_bo->bo;
 
 	vm_bo->moved = true;
+	spin_lock(&vm_bo->vm->status_lock);
 	if (bo->tbo.type == ttm_bo_type_kernel)
 		list_move(&vm_bo->vm_status, &vm->evicted);
 	else
 		list_move_tail(&vm_bo->vm_status, &vm->evicted);
+	spin_unlock(&vm_bo->vm->status_lock);
 }
 /**
  * amdgpu_vm_bo_moved - vm_bo is moved
@@ -198,7 +200,9 @@ static void amdgpu_vm_bo_evicted(struct amdgpu_vm_bo_base *vm_bo)
  */
 static void amdgpu_vm_bo_moved(struct amdgpu_vm_bo_base *vm_bo)
 {
+	spin_lock(&vm_bo->vm->status_lock);
 	list_move(&vm_bo->vm_status, &vm_bo->vm->moved);
+	spin_unlock(&vm_bo->vm->status_lock);
 }
 
 /**
@@ -211,7 +215,9 @@ static void amdgpu_vm_bo_moved(struct amdgpu_vm_bo_base *vm_bo)
  */
 static void amdgpu_vm_bo_idle(struct amdgpu_vm_bo_base *vm_bo)
 {
+	spin_lock(&vm_bo->vm->status_lock);
 	list_move(&vm_bo->vm_status, &vm_bo->vm->idle);
+	spin_unlock(&vm_bo->vm->status_lock);
 	vm_bo->moved = false;
 }
 
@@ -225,9 +231,9 @@ static void amdgpu_vm_bo_idle(struct amdgpu_vm_bo_base *vm_bo)
  */
 static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo)
 {
-	spin_lock(&vm_bo->vm->invalidated_lock);
+	spin_lock(&vm_bo->vm->status_lock);
 	list_move(&vm_bo->vm_status, &vm_bo->vm->invalidated);
-	spin_unlock(&vm_bo->vm->invalidated_lock);
+	spin_unlock(&vm_bo->vm->status_lock);
 }
 
 /**
@@ -240,10 +246,13 @@ static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo)
  */
 static void amdgpu_vm_bo_relocated(struct amdgpu_vm_bo_base *vm_bo)
 {
-	if (vm_bo->bo->parent)
+	if (vm_bo->bo->parent) {
+		spin_lock(&vm_bo->vm->status_lock);
 		list_move(&vm_bo->vm_status, &vm_bo->vm->relocated);
-	else
+		spin_unlock(&vm_bo->vm->status_lock);
+	} else {
 		amdgpu_vm_bo_idle(vm_bo);
+	}
 }
 
 /**
@@ -256,9 +265,9 @@ static void amdgpu_vm_bo_relocated(struct amdgpu_vm_bo_base *vm_bo)
  */
 static void amdgpu_vm_bo_done(struct amdgpu_vm_bo_base *vm_bo)
 {
-	spin_lock(&vm_bo->vm->invalidated_lock);
+	spin_lock(&vm_bo->vm->status_lock);
 	list_move(&vm_bo->vm_status, &vm_bo->vm->done);
-	spin_unlock(&vm_bo->vm->invalidated_lock);
+	spin_unlock(&vm_bo->vm->status_lock);
 }
 
 /**
@@ -363,12 +372,20 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			      int (*validate)(void *p, struct amdgpu_bo *bo),
 			      void *param)
 {
-	struct amdgpu_vm_bo_base *bo_base, *tmp;
+	struct amdgpu_vm_bo_base *bo_base;
+	struct amdgpu_bo *shadow;
+	struct amdgpu_bo *bo;
 	int r;
 
-	list_for_each_entry_safe(bo_base, tmp, &vm->evicted, vm_status) {
-		struct amdgpu_bo *bo = bo_base->bo;
-		struct amdgpu_bo *shadow = amdgpu_bo_shadowed(bo);
+	spin_lock(&vm->status_lock);
+	while (!list_empty(&vm->evicted)) {
+		bo_base = list_first_entry(&vm->evicted,
+					   struct amdgpu_vm_bo_base,
+					   vm_status);
+		spin_unlock(&vm->status_lock);
+
+		bo = bo_base->bo;
+		shadow = amdgpu_bo_shadowed(bo);
 
 		r = validate(param, bo);
 		if (r)
@@ -385,7 +402,9 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			vm->update_funcs->map_table(to_amdgpu_bo_vm(bo));
 			amdgpu_vm_bo_relocated(bo_base);
 		}
+		spin_lock(&vm->status_lock);
 	}
+	spin_unlock(&vm->status_lock);
 
 	amdgpu_vm_eviction_lock(vm);
 	vm->evicting = false;
@@ -406,13 +425,18 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
  */
 bool amdgpu_vm_ready(struct amdgpu_vm *vm)
 {
+	bool empty;
 	bool ret;
 
 	amdgpu_vm_eviction_lock(vm);
 	ret = !vm->evicting;
 	amdgpu_vm_eviction_unlock(vm);
 
-	return ret && list_empty(&vm->evicted);
+	spin_lock(&vm->status_lock);
+	empty = list_empty(&vm->evicted);
+	spin_unlock(&vm->status_lock);
+
+	return ret && empty;
 }
 
 /**
@@ -680,9 +704,14 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 	struct amdgpu_vm_update_params params;
 	struct amdgpu_vm_bo_base *entry;
 	bool flush_tlb_needed = false;
+	LIST_HEAD(relocated);
 	int r, idx;
 
-	if (list_empty(&vm->relocated))
+	spin_lock(&vm->status_lock);
+	list_splice_init(&vm->relocated, &relocated);
+	spin_unlock(&vm->status_lock);
+
+	if (list_empty(&relocated))
 		return 0;
 
 	if (!drm_dev_enter(adev_to_drm(adev), &idx))
@@ -697,7 +726,7 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 	if (r)
 		goto error;
 
-	list_for_each_entry(entry, &vm->relocated, vm_status) {
+	list_for_each_entry(entry, &relocated, vm_status) {
 		/* vm_flush_needed after updating moved PDEs */
 		flush_tlb_needed |= entry->moved;
 
@@ -713,9 +742,8 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 	if (flush_tlb_needed)
 		atomic64_inc(&vm->tlb_seq);
 
-	while (!list_empty(&vm->relocated)) {
-		entry = list_first_entry(&vm->relocated,
-					 struct amdgpu_vm_bo_base,
+	while (!list_empty(&relocated)) {
+		entry = list_first_entry(&relocated, struct amdgpu_vm_bo_base,
 					 vm_status);
 		amdgpu_vm_bo_idle(entry);
 	}
@@ -912,6 +940,7 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem,
 {
 	struct amdgpu_bo_va *bo_va, *tmp;
 
+	spin_lock(&vm->status_lock);
 	list_for_each_entry_safe(bo_va, tmp, &vm->idle, base.vm_status) {
 		if (!bo_va->base.bo)
 			continue;
@@ -936,7 +965,6 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem,
 		amdgpu_bo_get_memory(bo_va->base.bo, vram_mem,
 				gtt_mem, cpu_mem);
 	}
-	spin_lock(&vm->invalidated_lock);
 	list_for_each_entry_safe(bo_va, tmp, &vm->invalidated, base.vm_status) {
 		if (!bo_va->base.bo)
 			continue;
@@ -949,7 +977,7 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem,
 		amdgpu_bo_get_memory(bo_va->base.bo, vram_mem,
 				gtt_mem, cpu_mem);
 	}
-	spin_unlock(&vm->invalidated_lock);
+	spin_unlock(&vm->status_lock);
 }
 /**
  * amdgpu_vm_bo_update - update all BO mappings in the vm page table
@@ -1278,24 +1306,29 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
 int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 			   struct amdgpu_vm *vm)
 {
-	struct amdgpu_bo_va *bo_va, *tmp;
+	struct amdgpu_bo_va *bo_va;
 	struct dma_resv *resv;
 	bool clear;
 	int r;
 
-	list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status) {
+	spin_lock(&vm->status_lock);
+	while (!list_empty(&vm->moved)) {
+		bo_va = list_first_entry(&vm->moved, struct amdgpu_bo_va,
+					 base.vm_status);
+		spin_unlock(&vm->status_lock);
+
 		/* Per VM BOs never need to bo cleared in the page tables */
 		r = amdgpu_vm_bo_update(adev, bo_va, false);
 		if (r)
 			return r;
+		spin_lock(&vm->status_lock);
 	}
 
-	spin_lock(&vm->invalidated_lock);
 	while (!list_empty(&vm->invalidated)) {
 		bo_va = list_first_entry(&vm->invalidated, struct amdgpu_bo_va,
 					 base.vm_status);
 		resv = bo_va->base.bo->tbo.base.resv;
-		spin_unlock(&vm->invalidated_lock);
+		spin_unlock(&vm->status_lock);
 
 		/* Try to reserve the BO to avoid clearing its ptes */
 		if (!amdgpu_vm_debug && dma_resv_trylock(resv))
@@ -1310,9 +1343,9 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 
 		if (!clear)
 			dma_resv_unlock(resv);
-		spin_lock(&vm->invalidated_lock);
+		spin_lock(&vm->status_lock);
 	}
-	spin_unlock(&vm->invalidated_lock);
+	spin_unlock(&vm->status_lock);
 
 	return 0;
 }
@@ -1387,7 +1420,7 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev,
 
 	if (bo && bo->tbo.base.resv == vm->root.bo->tbo.base.resv &&
 	    !bo_va->base.moved) {
-		list_move(&bo_va->base.vm_status, &vm->moved);
+		amdgpu_vm_bo_moved(&bo_va->base);
 	}
 	trace_amdgpu_vm_bo_map(bo_va, mapping);
 }
@@ -1763,9 +1796,9 @@ void amdgpu_vm_bo_del(struct amdgpu_device *adev,
 		}
 	}
 
-	spin_lock(&vm->invalidated_lock);
+	spin_lock(&vm->status_lock);
 	list_del(&bo_va->base.vm_status);
-	spin_unlock(&vm->invalidated_lock);
+	spin_unlock(&vm->status_lock);
 
 	list_for_each_entry_safe(mapping, next, &bo_va->valids, list) {
 		list_del(&mapping->list);
@@ -2019,9 +2052,11 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	INIT_LIST_HEAD(&vm->moved);
 	INIT_LIST_HEAD(&vm->idle);
 	INIT_LIST_HEAD(&vm->invalidated);
-	spin_lock_init(&vm->invalidated_lock);
+	spin_lock_init(&vm->status_lock);
 	INIT_LIST_HEAD(&vm->freed);
 	INIT_LIST_HEAD(&vm->done);
+	INIT_LIST_HEAD(&vm->pt_freed);
+	INIT_WORK(&vm->pt_free_work, amdgpu_vm_pt_free_work);
 
 	/* create scheduler entities for page table updates */
 	r = drm_sched_entity_init(&vm->immediate, DRM_SCHED_PRIORITY_NORMAL,
@@ -2223,6 +2258,8 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 
 	amdgpu_amdkfd_gpuvm_destroy_cb(adev, vm);
 
+	flush_work(&vm->pt_free_work);
+
 	root = amdgpu_bo_ref(vm->root.bo);
 	amdgpu_bo_reserve(root, true);
 	amdgpu_vm_set_pasid(adev, vm, 0);
@@ -2547,6 +2584,7 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m)
 	unsigned int total_done_objs = 0;
 	unsigned int id = 0;
 
+	spin_lock(&vm->status_lock);
 	seq_puts(m, "\tIdle BOs:\n");
 	list_for_each_entry_safe(bo_va, tmp, &vm->idle, base.vm_status) {
 		if (!bo_va->base.bo)
@@ -2584,7 +2622,6 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m)
 	id = 0;
 
 	seq_puts(m, "\tInvalidated BOs:\n");
-	spin_lock(&vm->invalidated_lock);
 	list_for_each_entry_safe(bo_va, tmp, &vm->invalidated, base.vm_status) {
 		if (!bo_va->base.bo)
 			continue;
@@ -2599,7 +2636,7 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m)
 			continue;
 		total_done += amdgpu_bo_print_info(id++, bo_va->base.bo, m);
 	}
-	spin_unlock(&vm->invalidated_lock);
+	spin_unlock(&vm->status_lock);
 	total_done_objs = id;
 
 	seq_printf(m, "\tTotal idle size:        %12lld\tobjs:\t%d\n", total_idle,