Merge tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "Cannonlake and Vega12 support are probably the two major things. This
  pull lacks nouveau, Ben had some unforseen leave and a few other
  blockers so we'll see how things look or maybe leave it for this merge
  window.

  core:
   - Device links to handle sound/gpu pm dependency
   - Color encoding/range properties
   - Plane clipping into plane check helper
   - Backlight helpers
   - DP TP4 + HBR3 helper support

  amdgpu:
   - Vega12 support
   - Enable DC by default on all supported GPUs
   - Powerplay restructuring and cleanup
   - DC bandwidth calc updates
   - DC backlight on pre-DCE11
   - TTM backing store dropping support
   - SR-IOV fixes
   - Adding "wattman" like functionality
   - DC crc support
   - Improved DC dual-link handling

  amdkfd:
   - GPUVM support for dGPU
   - KFD events for dGPU
   - Enable PCIe atomics for dGPUs
   - HSA process eviction support
   - Live-lock fixes for process eviction
   - VM page table allocation fix for large-bar systems

  panel:
   - Raydium RM68200
   - AUO G104SN02 V2
   - KEO TX31D200VM0BAA
   - ARM Versatile panels

  i915:
   - Cannonlake support enabled
   - AUX-F port support added
   - Icelake base enabling until internal milestone of forcewake support
   - Query uAPI interface (used for GPU topology information currently)
   - Compressed framebuffer support for sprites
   - kmem cache shrinking when GPU is idle
   - Avoid boosting GPU when waited item is being processed already
   - Avoid retraining LSPCON link unnecessarily
   - Decrease request signaling latency
   - Deprecation of I915_SET_COLORKEY_NONE
   - Kerneldoc and compiler warning cleanup for upcoming CI enforcements
   - Full range ycbcr toggling
   - HDCP support

  i915/gvt:
   - Big refactor for shadow ppgtt
   - KBL context save/restore via LRI cmd (Weinan)
   - Properly unmap dma for guest page (Changbin)

  vmwgfx:
   - Lots of various improvements

  etnaviv:
   - Use the drm gpu scheduler
   - prep work for GC7000L support

  vc4:
   - fix alpha blending
   - Expose perf counters to userspace

  pl111:
   - Bandwidth checking/limiting
   - Versatile panel support

  sun4i:
   - A83T HDMI support
   - A80 support
   - YUV plane support
   - H3/H5 HDMI support

  omapdrm:
   - HPD support for DVI connector
   - remove lots of static variables

  msm:
   - DSI updates from 10nm / SDM845
   - fix for race condition with a3xx/a4xx fence completion irq
   - some refactoring/prep work for eventual a6xx support (ie. when we
     have a userspace)
   - a5xx debugfs enhancements
   - some mdp5 fixes/cleanups to prepare for eventually merging
     writeback
   - support (ie. when we have a userspace)

  tegra:
   - mmap() fixes for fbdev devices
   - Overlay plane for hw cursor fix
   - dma-buf cache maintenance support

  mali-dp:
   - YUV->RGB conversion support

  rockchip:
   - rk3399/chromebook fixes and improvements

  rcar-du:
   - LVDS support move to drm bridge
   - DT bindings for R8A77995
   - Driver/DT support for R8A77970

  tilcdc:
   - DRM panel support"

* tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux: (1646 commits)
  drm/i915: Fix hibernation with ACPI S0 target state
  drm/i915/execlists: Use a locked clear_bit() for synchronisation with interrupt
  drm/i915: Specify which engines to reset following semaphore/event lockups
  drm/i915/dp: Write to SET_POWER dpcd to enable MST hub.
  drm/amdkfd: Use ordered workqueue to restore processes
  drm/amdgpu: Fix acquiring VM on large-BAR systems
  drm/amd/pp: clean header file hwmgr.h
  drm/amd/pp: use mlck_table.count for array loop index limit
  drm: Fix uabi regression by allowing garbage mode->type from userspace
  drm/amdgpu: Add an ATPX quirk for hybrid laptop
  drm/amdgpu: fix spelling mistake: "asssert" -> "assert"
  drm/amd/pp: Add new asic support in pp_psm.c
  drm/amd/pp: Clean up powerplay code on Vega12
  drm/amd/pp: Add smu irq handlers for legacy asics
  drm/amd/pp: Fix set wrong temperature range on smu7
  drm/amdgpu: Don't change preferred domian when fallback GTT v5
  drm/vmwgfx: Bump version patchlevel and date
  drm/vmwgfx: use monotonic event timestamps
  drm/vmwgfx: Unpin the screen object backup buffer when not used
  drm/vmwgfx: Stricter count of legacy surface device resources
  ...

1 files changed, 65 insertions, 63 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 1220322c1680..fac4b6067efd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -36,6 +36,7 @@
 #include <drm/drm_cache.h>
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
+#include "amdgpu_amdkfd.h"
 
 static bool amdgpu_need_backup(struct amdgpu_device *adev)
 {
@@ -54,6 +55,9 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 	struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
 	struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo);
 
+	if (bo->kfd_bo)
+		amdgpu_amdkfd_unreserve_system_memory_limit(bo);
+
 	amdgpu_bo_kunmap(bo);
 
 	if (bo->gem_base.import_attach)
@@ -85,7 +89,7 @@ void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 	u32 c = 0;
 
 	if (domain & AMDGPU_GEM_DOMAIN_VRAM) {
-		unsigned visible_pfn = adev->mc.visible_vram_size >> PAGE_SHIFT;
+		unsigned visible_pfn = adev->gmc.visible_vram_size >> PAGE_SHIFT;
 
 		places[c].fpfn = 0;
 		places[c].lpfn = 0;
@@ -105,7 +109,7 @@ void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 	if (domain & AMDGPU_GEM_DOMAIN_GTT) {
 		places[c].fpfn = 0;
 		if (flags & AMDGPU_GEM_CREATE_SHADOW)
-			places[c].lpfn = adev->mc.gart_size >> PAGE_SHIFT;
+			places[c].lpfn = adev->gmc.gart_size >> PAGE_SHIFT;
 		else
 			places[c].lpfn = 0;
 		places[c].flags = TTM_PL_FLAG_TT;
@@ -171,13 +175,15 @@ void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
  * @size: size for the new BO
  * @align: alignment for the new BO
  * @domain: where to place it
- * @bo_ptr: resulting BO
+ * @bo_ptr: used to initialize BOs in structures
  * @gpu_addr: GPU addr of the pinned BO
  * @cpu_addr: optional CPU address mapping
  *
  * Allocates and pins a BO for kernel internal use, and returns it still
  * reserved.
  *
+ * Note: For bo_ptr new BO is only created if bo_ptr points to NULL.
+ *
  * Returns 0 on success, negative error code otherwise.
  */
 int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
@@ -189,10 +195,10 @@ int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
 	int r;
 
 	if (!*bo_ptr) {
-		r = amdgpu_bo_create(adev, size, align, true, domain,
+		r = amdgpu_bo_create(adev, size, align, domain,
 				     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
 				     AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS,
-				     NULL, NULL, 0, bo_ptr);
+				     ttm_bo_type_kernel, NULL, bo_ptr);
 		if (r) {
 			dev_err(adev->dev, "(%d) failed to allocate kernel bo\n",
 				r);
@@ -240,12 +246,14 @@ error_free:
  * @size: size for the new BO
  * @align: alignment for the new BO
  * @domain: where to place it
- * @bo_ptr: resulting BO
+ * @bo_ptr:  used to initialize BOs in structures
  * @gpu_addr: GPU addr of the pinned BO
  * @cpu_addr: optional CPU address mapping
  *
  * Allocates and pins a BO for kernel internal use.
  *
+ * Note: For bo_ptr new BO is only created if bo_ptr points to NULL.
+ *
  * Returns 0 on success, negative error code otherwise.
  */
 int amdgpu_bo_create_kernel(struct amdgpu_device *adev,
@@ -333,24 +341,22 @@ fail:
 	return false;
 }
 
-static int amdgpu_bo_do_create(struct amdgpu_device *adev,
-			       unsigned long size, int byte_align,
-			       bool kernel, u32 domain, u64 flags,
-			       struct sg_table *sg,
+static int amdgpu_bo_do_create(struct amdgpu_device *adev, unsigned long size,
+			       int byte_align, u32 domain,
+			       u64 flags, enum ttm_bo_type type,
 			       struct reservation_object *resv,
-			       uint64_t init_value,
 			       struct amdgpu_bo **bo_ptr)
 {
 	struct ttm_operation_ctx ctx = {
-		.interruptible = !kernel,
+		.interruptible = (type != ttm_bo_type_kernel),
 		.no_wait_gpu = false,
-		.allow_reserved_eviction = true,
-		.resv = resv
+		.resv = resv,
+		.flags = TTM_OPT_FLAG_ALLOW_RES_EVICT
 	};
 	struct amdgpu_bo *bo;
-	enum ttm_bo_type type;
 	unsigned long page_align;
 	size_t acc_size;
+	u32 domains;
 	int r;
 
 	page_align = roundup(byte_align, PAGE_SIZE) >> PAGE_SHIFT;
@@ -359,13 +365,6 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 	if (!amdgpu_bo_validate_size(adev, size, domain))
 		return -ENOMEM;
 
-	if (kernel) {
-		type = ttm_bo_type_kernel;
-	} else if (sg) {
-		type = ttm_bo_type_sg;
-	} else {
-		type = ttm_bo_type_device;
-	}
 	*bo_ptr = NULL;
 
 	acc_size = ttm_bo_dma_acc_size(&adev->mman.bdev, size,
@@ -374,11 +373,7 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 	bo = kzalloc(sizeof(struct amdgpu_bo), GFP_KERNEL);
 	if (bo == NULL)
 		return -ENOMEM;
-	r = drm_gem_object_init(adev->ddev, &bo->gem_base, size);
-	if (unlikely(r)) {
-		kfree(bo);
-		return r;
-	}
+	drm_gem_private_object_init(adev->ddev, &bo->gem_base, size);
 	INIT_LIST_HEAD(&bo->shadow_list);
 	INIT_LIST_HEAD(&bo->va);
 	bo->preferred_domains = domain & (AMDGPU_GEM_DOMAIN_VRAM |
@@ -388,7 +383,8 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 					 AMDGPU_GEM_DOMAIN_GWS |
 					 AMDGPU_GEM_DOMAIN_OA);
 	bo->allowed_domains = bo->preferred_domains;
-	if (!kernel && bo->allowed_domains == AMDGPU_GEM_DOMAIN_VRAM)
+	if (type != ttm_bo_type_kernel &&
+	    bo->allowed_domains == AMDGPU_GEM_DOMAIN_VRAM)
 		bo->allowed_domains |= AMDGPU_GEM_DOMAIN_GTT;
 
 	bo->flags = flags;
@@ -422,30 +418,41 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 #endif
 
 	bo->tbo.bdev = &adev->mman.bdev;
-	amdgpu_ttm_placement_from_domain(bo, domain);
-
+	domains = bo->preferred_domains;
+retry:
+	amdgpu_ttm_placement_from_domain(bo, domains);
 	r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, type,
-				 &bo->placement, page_align, &ctx, NULL,
-				 acc_size, sg, resv, &amdgpu_ttm_bo_destroy);
-	if (unlikely(r != 0))
+				 &bo->placement, page_align, &ctx, acc_size,
+				 NULL, resv, &amdgpu_ttm_bo_destroy);
+
+	if (unlikely(r && r != -ERESTARTSYS)) {
+		if (bo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) {
+			bo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+			goto retry;
+		} else if (domains != bo->preferred_domains) {
+			domains = bo->allowed_domains;
+			goto retry;
+		}
+	}
+	if (unlikely(r))
 		return r;
 
-	if (adev->mc.visible_vram_size < adev->mc.real_vram_size &&
+	if (adev->gmc.visible_vram_size < adev->gmc.real_vram_size &&
 	    bo->tbo.mem.mem_type == TTM_PL_VRAM &&
-	    bo->tbo.mem.start < adev->mc.visible_vram_size >> PAGE_SHIFT)
+	    bo->tbo.mem.start < adev->gmc.visible_vram_size >> PAGE_SHIFT)
 		amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved,
 					     ctx.bytes_moved);
 	else
 		amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, 0);
 
-	if (kernel)
+	if (type == ttm_bo_type_kernel)
 		bo->tbo.priority = 1;
 
 	if (flags & AMDGPU_GEM_CREATE_VRAM_CLEARED &&
 	    bo->tbo.mem.placement & TTM_PL_FLAG_VRAM) {
 		struct dma_fence *fence;
 
-		r = amdgpu_fill_buffer(bo, init_value, bo->tbo.resv, &fence);
+		r = amdgpu_fill_buffer(bo, 0, bo->tbo.resv, &fence);
 		if (unlikely(r))
 			goto fail_unreserve;
 
@@ -482,12 +489,11 @@ static int amdgpu_bo_create_shadow(struct amdgpu_device *adev,
 	if (bo->shadow)
 		return 0;
 
-	r = amdgpu_bo_do_create(adev, size, byte_align, true,
-				AMDGPU_GEM_DOMAIN_GTT,
+	r = amdgpu_bo_do_create(adev, size, byte_align, AMDGPU_GEM_DOMAIN_GTT,
 				AMDGPU_GEM_CREATE_CPU_GTT_USWC |
 				AMDGPU_GEM_CREATE_SHADOW,
-				NULL, bo->tbo.resv, 0,
-				&bo->shadow);
+				ttm_bo_type_kernel,
+				bo->tbo.resv, &bo->shadow);
 	if (!r) {
 		bo->shadow->parent = amdgpu_bo_ref(bo);
 		mutex_lock(&adev->shadow_list_lock);
@@ -498,22 +504,17 @@ static int amdgpu_bo_create_shadow(struct amdgpu_device *adev,
 	return r;
 }
 
-/* init_value will only take effect when flags contains
- * AMDGPU_GEM_CREATE_VRAM_CLEARED.
- */
-int amdgpu_bo_create(struct amdgpu_device *adev,
-		     unsigned long size, int byte_align,
-		     bool kernel, u32 domain, u64 flags,
-		     struct sg_table *sg,
+int amdgpu_bo_create(struct amdgpu_device *adev, unsigned long size,
+		     int byte_align, u32 domain,
+		     u64 flags, enum ttm_bo_type type,
 		     struct reservation_object *resv,
-		     uint64_t init_value,
 		     struct amdgpu_bo **bo_ptr)
 {
 	uint64_t parent_flags = flags & ~AMDGPU_GEM_CREATE_SHADOW;
 	int r;
 
-	r = amdgpu_bo_do_create(adev, size, byte_align, kernel, domain,
-				parent_flags, sg, resv, init_value, bo_ptr);
+	r = amdgpu_bo_do_create(adev, size, byte_align, domain,
+				parent_flags, type, resv, bo_ptr);
 	if (r)
 		return r;
 
@@ -828,31 +829,32 @@ static const char *amdgpu_vram_names[] = {
 	"GDDR4",
 	"GDDR5",
 	"HBM",
-	"DDR3"
+	"DDR3",
+	"DDR4",
 };
 
 int amdgpu_bo_init(struct amdgpu_device *adev)
 {
 	/* reserve PAT memory space to WC for VRAM */
-	arch_io_reserve_memtype_wc(adev->mc.aper_base,
-				   adev->mc.aper_size);
+	arch_io_reserve_memtype_wc(adev->gmc.aper_base,
+				   adev->gmc.aper_size);
 
 	/* Add an MTRR for the VRAM */
-	adev->mc.vram_mtrr = arch_phys_wc_add(adev->mc.aper_base,
-					      adev->mc.aper_size);
+	adev->gmc.vram_mtrr = arch_phys_wc_add(adev->gmc.aper_base,
+					      adev->gmc.aper_size);
 	DRM_INFO("Detected VRAM RAM=%lluM, BAR=%lluM\n",
-		 adev->mc.mc_vram_size >> 20,
-		 (unsigned long long)adev->mc.aper_size >> 20);
+		 adev->gmc.mc_vram_size >> 20,
+		 (unsigned long long)adev->gmc.aper_size >> 20);
 	DRM_INFO("RAM width %dbits %s\n",
-		 adev->mc.vram_width, amdgpu_vram_names[adev->mc.vram_type]);
+		 adev->gmc.vram_width, amdgpu_vram_names[adev->gmc.vram_type]);
 	return amdgpu_ttm_init(adev);
 }
 
 void amdgpu_bo_fini(struct amdgpu_device *adev)
 {
 	amdgpu_ttm_fini(adev);
-	arch_phys_wc_del(adev->mc.vram_mtrr);
-	arch_io_free_memtype_wc(adev->mc.aper_base, adev->mc.aper_size);
+	arch_phys_wc_del(adev->gmc.vram_mtrr);
+	arch_io_free_memtype_wc(adev->gmc.aper_base, adev->gmc.aper_size);
 }
 
 int amdgpu_bo_fbdev_mmap(struct amdgpu_bo *bo,
@@ -982,7 +984,7 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 
 	size = bo->mem.num_pages << PAGE_SHIFT;
 	offset = bo->mem.start << PAGE_SHIFT;
-	if ((offset + size) <= adev->mc.visible_vram_size)
+	if ((offset + size) <= adev->gmc.visible_vram_size)
 		return 0;
 
 	/* Can't move a pinned BO to visible VRAM */
@@ -1005,7 +1007,7 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	offset = bo->mem.start << PAGE_SHIFT;
 	/* this should never happen */
 	if (bo->mem.mem_type == TTM_PL_VRAM &&
-	    (offset + size) > adev->mc.visible_vram_size)
+	    (offset + size) > adev->gmc.visible_vram_size)
 		return -EINVAL;
 
 	return 0;