Merge tag 'drm-next-2020-10-15' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Not a major amount of change, the i915 trees got split into display
  and gt trees to better facilitate higher level review, and there's a
  major refactoring of i915 GEM locking to use more core kernel concepts
  (like ww-mutexes). msm gets per-process pagetables, older AMD SI cards
  get DC support, nouveau got a bump in displayport support with common
  code extraction from i915.

  Outside of drm this contains a couple of patches for hexint
  moduleparams which you've acked, and a virtio common code tree that
  you should also get via it's regular path.

  New driver:
   - Cadence MHDP8546 DisplayPort bridge driver

  core:
   - cross-driver scatterlist cleanups
   - devm_drm conversions
   - remove drm_dev_init
   - devm_drm_dev_alloc conversion

  ttm:
   - lots of refactoring and cleanups

  bridges:
   - chained bridge support in more drivers

  panel:
   - misc new panels

  scheduler:
   - cleanup priority levels

  displayport:
   - refactor i915 code into helpers for nouveau

  i915:
   - split into display and GT trees
   - WW locking refactoring in GEM
   - execbuf2 extension mechanism
   - syncobj timeline support
   - GEN 12 HOBL display powersaving
   - Rocket Lake display additions
   - Disable FBC on Tigerlake
   - Tigerlake Type-C + DP improvements
   - Hotplug interrupt refactoring

  amdgpu:
   - Sienna Cichlid updates
   - Navy Flounder updates
   - DCE6 (SI) support for DC
   - Plane rotation enabled
   - TMZ state info ioctl
   - PCIe DPC recovery support
   - DC interrupt handling refactor
   - OLED panel fixes

  amdkfd:
   - add SMI events for thermal throttling
   - SMI interface events ioctl update
   - process eviction counters

  radeon:
   - move to dma_ for allocations
   - expose sclk via sysfs

  msm:
   - DSI support for sm8150/sm8250
   - per-process GPU pagetable support
   - Displayport support

  mediatek:
   - move HDMI phy driver to PHY
   - convert mtk-dpi to bridge API
   - disable mt2701 tmds

  tegra:
   - bridge support

  exynos:
   - misc cleanups

  vc4:
   - dual display cleanups

  ast:
   - cleanups

  gma500:
   - conversion to GPIOd API

  hisilicon:
   - misc reworks

  ingenic:
   - clock handling and format improvements

  mcde:
   - DSI support

  mgag200:
   - desktop g200 support

  mxsfb:
   - i.MX7 + i.MX8M
   - alpha plane support

  panfrost:
   - devfreq support
   - amlogic SoC support

  ps8640:
   - EDID from eDP retrieval

  tidss:
   - AM65xx YUV workaround

  virtio:
   - virtio-gpu exported resources

  rcar-du:
   - R8A7742, R8A774E1 and R8A77961 support
   - YUV planar format fixes
   - non-visible plane handling
   - VSP device reference count fix
   - Kconfig fix to avoid displaying disabled options in .config"

* tag 'drm-next-2020-10-15' of git://anongit.freedesktop.org/drm/drm: (1494 commits)
  drm/ingenic: Fix bad revert
  drm/amdgpu: Fix invalid number of character '{' in amdgpu_acpi_init
  drm/amdgpu: Remove warning for virtual_display
  drm/amdgpu: kfd_initialized can be static
  drm/amd/pm: setup APU dpm clock table in SMU HW initialization
  drm/amdgpu: prevent spurious warning
  drm/amdgpu/swsmu: fix ARC build errors
  drm/amd/display: Fix OPTC_DATA_FORMAT programming
  drm/amd/display: Don't allow pstate if no support in blank
  drm/panfrost: increase readl_relaxed_poll_timeout values
  MAINTAINERS: Update entry for st7703 driver after the rename
  Revert "gpu/drm: ingenic: Add option to mmap GEM buffers cached"
  drm/amd/display: HDMI remote sink need mode validation for Linux
  drm/amd/display: Change to correct unit on audio rate
  drm/amd/display: Avoid set zero in the requested clk
  drm/amdgpu: align frag_end to covered address space
  drm/amdgpu: fix NULL pointer dereference for Renoir
  drm/vmwgfx: fix regression in thp code due to ttm init refactor.
  drm/amdgpu/swsmu: add interrupt work handler for smu11 parts
  drm/amdgpu/swsmu: add interrupt work function
  ...

1 files changed, 48 insertions, 58 deletions

diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
index cdc0b9c54305..fd0d24d28763 100644
--- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
@@ -16,8 +16,10 @@ static inline void gen6_write_pde(const struct gen6_ppgtt *ppgtt,
 				  const unsigned int pde,
 				  const struct i915_page_table *pt)
 {
+	dma_addr_t addr = pt ? px_dma(pt) : px_dma(ppgtt->base.vm.scratch[1]);
+
 	/* Caller needs to make sure the write completes if necessary */
-	iowrite32(GEN6_PDE_ADDR_ENCODE(px_dma(pt)) | GEN6_PDE_VALID,
+	iowrite32(GEN6_PDE_ADDR_ENCODE(addr) | GEN6_PDE_VALID,
 		  ppgtt->pd_addr + pde);
 }
 
@@ -79,7 +81,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 {
 	struct gen6_ppgtt * const ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
 	const unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
-	const gen6_pte_t scratch_pte = vm->scratch[0].encode;
+	const gen6_pte_t scratch_pte = vm->scratch[0]->encode;
 	unsigned int pde = first_entry / GEN6_PTES;
 	unsigned int pte = first_entry % GEN6_PTES;
 	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
@@ -90,8 +92,6 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 		const unsigned int count = min(num_entries, GEN6_PTES - pte);
 		gen6_pte_t *vaddr;
 
-		GEM_BUG_ON(px_base(pt) == px_base(&vm->scratch[1]));
-
 		num_entries -= count;
 
 		GEM_BUG_ON(count > atomic_read(&pt->used));
@@ -127,7 +127,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 	struct sgt_dma iter = sgt_dma(vma);
 	gen6_pte_t *vaddr;
 
-	GEM_BUG_ON(pd->entry[act_pt] == &vm->scratch[1]);
+	GEM_BUG_ON(!pd->entry[act_pt]);
 
 	vaddr = kmap_atomic_px(i915_pt_entry(pd, act_pt));
 	do {
@@ -177,39 +177,36 @@ static void gen6_flush_pd(struct gen6_ppgtt *ppgtt, u64 start, u64 end)
 	mutex_unlock(&ppgtt->flush);
 }
 
-static int gen6_alloc_va_range(struct i915_address_space *vm,
-			       u64 start, u64 length)
+static void gen6_alloc_va_range(struct i915_address_space *vm,
+				struct i915_vm_pt_stash *stash,
+				u64 start, u64 length)
 {
 	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
 	struct i915_page_directory * const pd = ppgtt->base.pd;
-	struct i915_page_table *pt, *alloc = NULL;
+	struct i915_page_table *pt;
 	bool flush = false;
 	u64 from = start;
 	unsigned int pde;
-	int ret = 0;
 
 	spin_lock(&pd->lock);
 	gen6_for_each_pde(pt, pd, start, length, pde) {
 		const unsigned int count = gen6_pte_count(start, length);
 
-		if (px_base(pt) == px_base(&vm->scratch[1])) {
+		if (!pt) {
 			spin_unlock(&pd->lock);
 
-			pt = fetch_and_zero(&alloc);
-			if (!pt)
-				pt = alloc_pt(vm);
-			if (IS_ERR(pt)) {
-				ret = PTR_ERR(pt);
-				goto unwind_out;
-			}
+			pt = stash->pt[0];
+			__i915_gem_object_pin_pages(pt->base);
+			i915_gem_object_make_unshrinkable(pt->base);
 
-			fill32_px(pt, vm->scratch[0].encode);
+			fill32_px(pt, vm->scratch[0]->encode);
 
 			spin_lock(&pd->lock);
-			if (pd->entry[pde] == &vm->scratch[1]) {
+			if (!pd->entry[pde]) {
+				stash->pt[0] = pt->stash;
+				atomic_set(&pt->used, 0);
 				pd->entry[pde] = pt;
 			} else {
-				alloc = pt;
 				pt = pd->entry[pde];
 			}
 
@@ -226,38 +223,32 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 		with_intel_runtime_pm(&vm->i915->runtime_pm, wakeref)
 			gen6_flush_pd(ppgtt, from, start);
 	}
-
-	goto out;
-
-unwind_out:
-	gen6_ppgtt_clear_range(vm, from, start - from);
-out:
-	if (alloc)
-		free_px(vm, alloc);
-	return ret;
 }
 
 static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt)
 {
 	struct i915_address_space * const vm = &ppgtt->base.vm;
-	struct i915_page_directory * const pd = ppgtt->base.pd;
 	int ret;
 
-	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
+	ret = setup_scratch_page(vm);
 	if (ret)
 		return ret;
 
-	vm->scratch[0].encode =
-		vm->pte_encode(px_dma(&vm->scratch[0]),
+	vm->scratch[0]->encode =
+		vm->pte_encode(px_dma(vm->scratch[0]),
 			       I915_CACHE_NONE, PTE_READ_ONLY);
 
-	if (unlikely(setup_page_dma(vm, px_base(&vm->scratch[1])))) {
-		cleanup_scratch_page(vm);
-		return -ENOMEM;
+	vm->scratch[1] = vm->alloc_pt_dma(vm, I915_GTT_PAGE_SIZE_4K);
+	if (IS_ERR(vm->scratch[1]))
+		return PTR_ERR(vm->scratch[1]);
+
+	ret = pin_pt_dma(vm, vm->scratch[1]);
+	if (ret) {
+		i915_gem_object_put(vm->scratch[1]);
+		return ret;
 	}
 
-	fill32_px(&vm->scratch[1], vm->scratch[0].encode);
-	memset_p(pd->entry, &vm->scratch[1], I915_PDES);
+	fill32_px(vm->scratch[1], vm->scratch[0]->encode);
 
 	return 0;
 }
@@ -265,14 +256,12 @@ static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt)
 static void gen6_ppgtt_free_pd(struct gen6_ppgtt *ppgtt)
 {
 	struct i915_page_directory * const pd = ppgtt->base.pd;
-	struct i915_page_dma * const scratch =
-		px_base(&ppgtt->base.vm.scratch[1]);
 	struct i915_page_table *pt;
 	u32 pde;
 
 	gen6_for_all_pdes(pt, pd, pde)
-		if (px_base(pt) != scratch)
-			free_px(&ppgtt->base.vm, pt);
+		if (pt)
+			free_pt(&ppgtt->base.vm, pt);
 }
 
 static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
@@ -286,7 +275,8 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 
 	mutex_destroy(&ppgtt->flush);
 	mutex_destroy(&ppgtt->pin_mutex);
-	kfree(ppgtt->base.pd);
+
+	free_pd(&ppgtt->base.vm, ppgtt->base.pd);
 }
 
 static int pd_vma_set_pages(struct i915_vma *vma)
@@ -302,28 +292,26 @@ static void pd_vma_clear_pages(struct i915_vma *vma)
 	vma->pages = NULL;
 }
 
-static int pd_vma_bind(struct i915_address_space *vm,
-		       struct i915_vma *vma,
-		       enum i915_cache_level cache_level,
-		       u32 unused)
+static void pd_vma_bind(struct i915_address_space *vm,
+			struct i915_vm_pt_stash *stash,
+			struct i915_vma *vma,
+			enum i915_cache_level cache_level,
+			u32 unused)
 {
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
 	struct gen6_ppgtt *ppgtt = vma->private;
 	u32 ggtt_offset = i915_ggtt_offset(vma) / I915_GTT_PAGE_SIZE;
 
-	px_base(ppgtt->base.pd)->ggtt_offset = ggtt_offset * sizeof(gen6_pte_t);
+	ppgtt->pp_dir = ggtt_offset * sizeof(gen6_pte_t) << 10;
 	ppgtt->pd_addr = (gen6_pte_t __iomem *)ggtt->gsm + ggtt_offset;
 
 	gen6_flush_pd(ppgtt, 0, ppgtt->base.vm.total);
-	return 0;
 }
 
 static void pd_vma_unbind(struct i915_address_space *vm, struct i915_vma *vma)
 {
 	struct gen6_ppgtt *ppgtt = vma->private;
 	struct i915_page_directory * const pd = ppgtt->base.pd;
-	struct i915_page_dma * const scratch =
-		px_base(&ppgtt->base.vm.scratch[1]);
 	struct i915_page_table *pt;
 	unsigned int pde;
 
@@ -332,11 +320,11 @@ static void pd_vma_unbind(struct i915_address_space *vm, struct i915_vma *vma)
 
 	/* Free all no longer used page tables */
 	gen6_for_all_pdes(pt, ppgtt->base.pd, pde) {
-		if (px_base(pt) == scratch || atomic_read(&pt->used))
+		if (!pt || atomic_read(&pt->used))
 			continue;
 
-		free_px(&ppgtt->base.vm, pt);
-		pd->entry[pde] = scratch;
+		free_pt(&ppgtt->base.vm, pt);
+		pd->entry[pde] = NULL;
 	}
 
 	ppgtt->scan_for_unused_pt = false;
@@ -380,7 +368,7 @@ static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size)
 	return vma;
 }
 
-int gen6_ppgtt_pin(struct i915_ppgtt *base)
+int gen6_ppgtt_pin(struct i915_ppgtt *base, struct i915_gem_ww_ctx *ww)
 {
 	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
 	int err;
@@ -406,7 +394,7 @@ int gen6_ppgtt_pin(struct i915_ppgtt *base)
 	 */
 	err = 0;
 	if (!atomic_read(&ppgtt->pin_count))
-		err = i915_ggtt_pin(ppgtt->vma, GEN6_PD_ALIGN, PIN_HIGH);
+		err = i915_ggtt_pin(ppgtt->vma, ww, GEN6_PD_ALIGN, PIN_HIGH);
 	if (!err)
 		atomic_inc(&ppgtt->pin_count);
 	mutex_unlock(&ppgtt->pin_mutex);
@@ -448,6 +436,7 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt)
 	mutex_init(&ppgtt->pin_mutex);
 
 	ppgtt_init(&ppgtt->base, gt);
+	ppgtt->base.vm.pd_shift = ilog2(SZ_4K * SZ_4K / sizeof(gen6_pte_t));
 	ppgtt->base.vm.top = 1;
 
 	ppgtt->base.vm.bind_async_flags = I915_VMA_LOCAL_BIND;
@@ -456,9 +445,10 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt)
 	ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries;
 	ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup;
 
+	ppgtt->base.vm.alloc_pt_dma = alloc_pt_dma;
 	ppgtt->base.vm.pte_encode = ggtt->vm.pte_encode;
 
-	ppgtt->base.pd = __alloc_pd(sizeof(*ppgtt->base.pd));
+	ppgtt->base.pd = __alloc_pd(I915_PDES);
 	if (!ppgtt->base.pd) {
 		err = -ENOMEM;
 		goto err_free;
@@ -479,7 +469,7 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt)
 err_scratch:
 	free_scratch(&ppgtt->base.vm);
 err_pd:
-	kfree(ppgtt->base.pd);
+	free_pd(&ppgtt->base.vm, ppgtt->base.pd);
 err_free:
 	mutex_destroy(&ppgtt->pin_mutex);
 	kfree(ppgtt);