Merge tag 'drm-next-2021-08-31-1' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Highlights:

   - i915 has seen a lot of refactoring and uAPI cleanups due to a
     change in the upstream direction going forward

     This has all been audited with known userspace, but there may be
     some pitfalls that were missed.

   - i915 now uses common TTM to enable discrete memory on DG1/2 GPUs

   - i915 enables Jasper and Elkhart Lake by default and has preliminary
     XeHP/DG2 support

   - amdgpu adds support for Cyan Skillfish

   - lots of implicit fencing rules documented and fixed up in drivers

   - msm now uses the core scheduler

   - the irq midlayer has been removed for non-legacy drivers

   - the sysfb code now works on more than x86.

  Otherwise the usual smattering of stuff everywhere, panels, bridges,
  refactorings.

  Detailed summary:

  core:
   - extract i915 eDP backlight into core
   - DP aux bus support
   - drm_device.irq_enabled removed
   - port drivers to native irq interfaces
   - export gem shadow plane handling for vgem
   - print proper driver name in framebuffer registration
   - driver fixes for implicit fencing rules
   - ARM fixed rate compression modifier added
   - updated fb damage handling
   - rmfb ioctl logging/docs
   - drop drm_gem_object_put_locked
   - define DRM_FORMAT_MAX_PLANES
   - add gem fb vmap/vunmap helpers
   - add lockdep_assert(once) helpers
   - mark drm irq midlayer as legacy
   - use offset adjusted bo mapping conversion

  vgaarb:
   - cleanups

  fbdev:
   - extend efifb handling to all arches
   - div by 0 fixes for multiple drivers

  udmabuf:
   - add hugepage mapping support

  dma-buf:
   - non-dynamic exporter fixups
   - document implicit fencing rules

  amdgpu:
   - Initial Cyan Skillfish support
   - switch virtual DCE over to vkms based atomic
   - VCN/JPEG power down fixes
   - NAVI PCIE link handling fixes
   - AMD HDMI freesync fixes
   - Yellow Carp + Beige Goby fixes
   - Clockgating/S0ix/SMU/EEPROM fixes
   - embed hw fence in job
   - rework dma-resv handling
   - ensure eviction to system ram

  amdkfd:
   - uapi: SVM address range query added
   - sysfs leak fix
   - GPUVM TLB optimizations
   - vmfault/migration counters

  i915:
   - Enable JSL and EHL by default
   - preliminary XeHP/DG2 support
   - remove all CNL support (never shipped)
   - move to TTM for discrete memory support
   - allow mixed object mmap handling
   - GEM uAPI spring cleaning
       - add I915_MMAP_OBJECT_FIXED
       - reinstate ADL-P mmap ioctls
       - drop a bunch of unused by userspace features
       - disable and remove GPU relocations
   - revert some i915 misfeatures
   - major refactoring of GuC for Gen11+
   - execbuffer object locking separate step
   - reject caching/set-domain on discrete
   - Enable pipe DMC loading on XE-LPD and ADL-P
   - add PSF GV point support
   - Refactor and fix DDI buffer translations
   - Clean up FBC CFB allocation code
   - Finish INTEL_GEN() and friends macro conversions

  nouveau:
   - add eDP backlight support
   - implicit fence fix

  msm:
   - a680/7c3 support
   - drm/scheduler conversion

  panfrost:
   - rework GPU reset

  virtio:
   - fix fencing for planes

  ast:
   - add detect support

  bochs:
   - move to tiny GPU driver

  vc4:
   - use hotplug irqs
   - HDMI codec support

  vmwgfx:
   - use internal vmware device headers

  ingenic:
   - demidlayering irq

  rcar-du:
   - shutdown fixes
   - convert to bridge connector helpers

  zynqmp-dsub:
   - misc fixes

  mgag200:
   - convert PLL handling to atomic

  mediatek:
   - MT8133 AAL support
   - gem mmap object support
   - MT8167 support

  etnaviv:
   - NXP Layerscape LS1028A SoC support
   - GEM mmap cleanups

  tegra:
   - new user API

  exynos:
   - missing unlock fix
   - build warning fix
   - use refcount_t"

* tag 'drm-next-2021-08-31-1' of git://anongit.freedesktop.org/drm/drm: (1318 commits)
  drm/amd/display: Move AllowDRAMSelfRefreshOrDRAMClockChangeInVblank to bounding box
  drm/amd/display: Remove duplicate dml init
  drm/amd/display: Update bounding box states (v2)
  drm/amd/display: Update number of DCN3 clock states
  drm/amdgpu: disable GFX CGCG in aldebaran
  drm/amdgpu: Clear RAS interrupt status on aldebaran
  drm/amdgpu: Add support for RAS XGMI err query
  drm/amdkfd: Account for SH/SE count when setting up cu masks.
  drm/amdgpu: rename amdgpu_bo_get_preferred_pin_domain
  drm/amdgpu: drop redundant cancel_delayed_work_sync call
  drm/amdgpu: add missing cleanups for more ASICs on UVD/VCE suspend
  drm/amdgpu: add missing cleanups for Polaris12 UVD/VCE on suspend
  drm/amdkfd: map SVM range with correct access permission
  drm/amdkfd: check access permisson to restore retry fault
  drm/amdgpu: Update RAS XGMI Error Query
  drm/amdgpu: Add driver infrastructure for MCA RAS
  drm/amd/display: Add Logging for HDMI color depth information
  drm/amd/amdgpu: consolidate PSP TA init shared buf functions
  drm/amd/amdgpu: add name field back to ras_common_if
  drm/amdgpu: Fix build with missing pm_suspend_target_state module export
  ...

1 files changed, 56 insertions, 46 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 3a55f08e00e1..38dade421d46 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -149,14 +149,16 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 			 * BOs to be evicted from VRAM
 			 */
 			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
-							 AMDGPU_GEM_DOMAIN_GTT);
+							AMDGPU_GEM_DOMAIN_GTT |
+							AMDGPU_GEM_DOMAIN_CPU);
 			abo->placements[0].fpfn = adev->gmc.visible_vram_size >> PAGE_SHIFT;
 			abo->placements[0].lpfn = 0;
 			abo->placement.busy_placement = &abo->placements[1];
 			abo->placement.num_busy_placement = 1;
 		} else {
 			/* Move to GTT memory */
-			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT);
+			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT |
+							AMDGPU_GEM_DOMAIN_CPU);
 		}
 		break;
 	case TTM_PL_TT:
@@ -521,7 +523,7 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			hop->fpfn = 0;
 			hop->lpfn = 0;
 			hop->mem_type = TTM_PL_TT;
-			hop->flags = 0;
+			hop->flags = TTM_PL_FLAG_TEMPORARY;
 			return -EMULTIHOP;
 		}
 
@@ -1121,7 +1123,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_device *bdev,
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 
 	/* user pages are bound by amdgpu_ttm_tt_pin_userptr() */
-	if (gtt && gtt->userptr) {
+	if (gtt->userptr) {
 		ttm->sg = kzalloc(sizeof(struct sg_table), GFP_KERNEL);
 		if (!ttm->sg)
 			return -ENOMEM;
@@ -1146,7 +1148,7 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_device *bdev,
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 	struct amdgpu_device *adev;
 
-	if (gtt && gtt->userptr) {
+	if (gtt->userptr) {
 		amdgpu_ttm_tt_set_user_pages(ttm, NULL);
 		kfree(ttm->sg);
 		ttm->sg = NULL;
@@ -1394,6 +1396,41 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
 	return ttm_bo_eviction_valuable(bo, place);
 }
 
+static void amdgpu_ttm_vram_mm_access(struct amdgpu_device *adev, loff_t pos,
+				      void *buf, size_t size, bool write)
+{
+	while (size) {
+		uint64_t aligned_pos = ALIGN_DOWN(pos, 4);
+		uint64_t bytes = 4 - (pos & 0x3);
+		uint32_t shift = (pos & 0x3) * 8;
+		uint32_t mask = 0xffffffff << shift;
+		uint32_t value = 0;
+
+		if (size < bytes) {
+			mask &= 0xffffffff >> (bytes - size) * 8;
+			bytes = size;
+		}
+
+		if (mask != 0xffffffff) {
+			amdgpu_device_mm_access(adev, aligned_pos, &value, 4, false);
+			if (write) {
+				value &= ~mask;
+				value |= (*(uint32_t *)buf << shift) & mask;
+				amdgpu_device_mm_access(adev, aligned_pos, &value, 4, true);
+			} else {
+				value = (value & mask) >> shift;
+				memcpy(buf, &value, bytes);
+			}
+		} else {
+			amdgpu_device_mm_access(adev, aligned_pos, buf, 4, write);
+		}
+
+		pos += bytes;
+		buf += bytes;
+		size -= bytes;
+	}
+}
+
 /**
  * amdgpu_ttm_access_memory - Read or Write memory that backs a buffer object.
  *
@@ -1413,8 +1450,6 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo,
 	struct amdgpu_bo *abo = ttm_to_amdgpu_bo(bo);
 	struct amdgpu_device *adev = amdgpu_ttm_adev(abo->tbo.bdev);
 	struct amdgpu_res_cursor cursor;
-	unsigned long flags;
-	uint32_t value = 0;
 	int ret = 0;
 
 	if (bo->resource->mem_type != TTM_PL_VRAM)
@@ -1422,41 +1457,21 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo,
 
 	amdgpu_res_first(bo->resource, offset, len, &cursor);
 	while (cursor.remaining) {
-		uint64_t aligned_pos = cursor.start & ~(uint64_t)3;
-		uint64_t bytes = 4 - (cursor.start & 3);
-		uint32_t shift = (cursor.start & 3) * 8;
-		uint32_t mask = 0xffffffff << shift;
-
-		if (cursor.size < bytes) {
-			mask &= 0xffffffff >> (bytes - cursor.size) * 8;
-			bytes = cursor.size;
-		}
-
-		if (mask != 0xffffffff) {
-			spin_lock_irqsave(&adev->mmio_idx_lock, flags);
-			WREG32_NO_KIQ(mmMM_INDEX, ((uint32_t)aligned_pos) | 0x80000000);
-			WREG32_NO_KIQ(mmMM_INDEX_HI, aligned_pos >> 31);
-			value = RREG32_NO_KIQ(mmMM_DATA);
-			if (write) {
-				value &= ~mask;
-				value |= (*(uint32_t *)buf << shift) & mask;
-				WREG32_NO_KIQ(mmMM_DATA, value);
-			}
-			spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
-			if (!write) {
-				value = (value & mask) >> shift;
-				memcpy(buf, &value, bytes);
-			}
-		} else {
-			bytes = cursor.size & ~0x3ULL;
-			amdgpu_device_vram_access(adev, cursor.start,
-						  (uint32_t *)buf, bytes,
-						  write);
+		size_t count, size = cursor.size;
+		loff_t pos = cursor.start;
+
+		count = amdgpu_device_aper_access(adev, pos, buf, size, write);
+		size -= count;
+		if (size) {
+			/* using MM to access rest vram and handle un-aligned address */
+			pos += count;
+			buf += count;
+			amdgpu_ttm_vram_mm_access(adev, pos, buf, size, write);
 		}
 
-		ret += bytes;
-		buf = (uint8_t *)buf + bytes;
-		amdgpu_res_next(&cursor, bytes);
+		ret += cursor.size;
+		buf += cursor.size;
+		amdgpu_res_next(&cursor, cursor.size);
 	}
 
 	return ret;
@@ -2146,7 +2161,6 @@ static ssize_t amdgpu_ttm_vram_write(struct file *f, const char __user *buf,
 		return -ENXIO;
 
 	while (size) {
-		unsigned long flags;
 		uint32_t value;
 
 		if (*pos >= adev->gmc.mc_vram_size)
@@ -2156,11 +2170,7 @@ static ssize_t amdgpu_ttm_vram_write(struct file *f, const char __user *buf,
 		if (r)
 			return r;
 
-		spin_lock_irqsave(&adev->mmio_idx_lock, flags);
-		WREG32_NO_KIQ(mmMM_INDEX, ((uint32_t)*pos) | 0x80000000);
-		WREG32_NO_KIQ(mmMM_INDEX_HI, *pos >> 31);
-		WREG32_NO_KIQ(mmMM_DATA, value);
-		spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
+		amdgpu_device_mm_access(adev, *pos, &value, 4, true);
 
 		result += 4;
 		buf += 4;