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, 144 insertions, 36 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 5a046a3c543a..7e672be987b5 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -31,38 +31,87 @@
 #define pr_fmt(fmt) "[TTM] " fmt
 
 #include <linux/sched.h>
-#include <linux/highmem.h>
 #include <linux/pagemap.h>
 #include <linux/shmem_fs.h>
 #include <linux/file.h>
-#include <linux/swap.h>
-#include <linux/slab.h>
-#include <linux/export.h>
 #include <drm/drm_cache.h>
-#include <drm/ttm/ttm_module.h>
 #include <drm/ttm/ttm_bo_driver.h>
-#include <drm/ttm/ttm_placement.h>
 #include <drm/ttm/ttm_page_alloc.h>
 #ifdef CONFIG_X86
 #include <asm/set_memory.h>
 #endif
 
 /**
+ * Allocates a ttm structure for the given BO.
+ */
+int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc)
+{
+	struct ttm_bo_device *bdev = bo->bdev;
+	uint32_t page_flags = 0;
+
+	reservation_object_assert_held(bo->resv);
+
+	if (bdev->need_dma32)
+		page_flags |= TTM_PAGE_FLAG_DMA32;
+
+	if (bdev->no_retry)
+		page_flags |= TTM_PAGE_FLAG_NO_RETRY;
+
+	switch (bo->type) {
+	case ttm_bo_type_device:
+		if (zero_alloc)
+			page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC;
+		break;
+	case ttm_bo_type_kernel:
+		break;
+	case ttm_bo_type_sg:
+		page_flags |= TTM_PAGE_FLAG_SG;
+		break;
+	default:
+		bo->ttm = NULL;
+		pr_err("Illegal buffer object type\n");
+		return -EINVAL;
+	}
+
+	bo->ttm = bdev->driver->ttm_tt_create(bo, page_flags);
+	if (unlikely(bo->ttm == NULL))
+		return -ENOMEM;
+
+	return 0;
+}
+
+/**
  * Allocates storage for pointers to the pages that back the ttm.
  */
-static void ttm_tt_alloc_page_directory(struct ttm_tt *ttm)
+static int ttm_tt_alloc_page_directory(struct ttm_tt *ttm)
 {
 	ttm->pages = kvmalloc_array(ttm->num_pages, sizeof(void*),
 			GFP_KERNEL | __GFP_ZERO);
+	if (!ttm->pages)
+		return -ENOMEM;
+	return 0;
 }
 
-static void ttm_dma_tt_alloc_page_directory(struct ttm_dma_tt *ttm)
+static int ttm_dma_tt_alloc_page_directory(struct ttm_dma_tt *ttm)
 {
 	ttm->ttm.pages = kvmalloc_array(ttm->ttm.num_pages,
 					  sizeof(*ttm->ttm.pages) +
 					  sizeof(*ttm->dma_address),
 					  GFP_KERNEL | __GFP_ZERO);
+	if (!ttm->ttm.pages)
+		return -ENOMEM;
 	ttm->dma_address = (void *) (ttm->ttm.pages + ttm->ttm.num_pages);
+	return 0;
+}
+
+static int ttm_sg_tt_alloc_page_directory(struct ttm_dma_tt *ttm)
+{
+	ttm->dma_address = kvmalloc_array(ttm->ttm.num_pages,
+					  sizeof(*ttm->dma_address),
+					  GFP_KERNEL | __GFP_ZERO);
+	if (!ttm->dma_address)
+		return -ENOMEM;
+	return 0;
 }
 
 #ifdef CONFIG_X86
@@ -184,21 +233,24 @@ void ttm_tt_destroy(struct ttm_tt *ttm)
 	ttm->func->destroy(ttm);
 }
 
-int ttm_tt_init(struct ttm_tt *ttm, struct ttm_bo_device *bdev,
-		unsigned long size, uint32_t page_flags,
-		struct page *dummy_read_page)
+void ttm_tt_init_fields(struct ttm_tt *ttm, struct ttm_buffer_object *bo,
+			uint32_t page_flags)
 {
-	ttm->bdev = bdev;
-	ttm->glob = bdev->glob;
-	ttm->num_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	ttm->bdev = bo->bdev;
+	ttm->num_pages = bo->num_pages;
 	ttm->caching_state = tt_cached;
 	ttm->page_flags = page_flags;
-	ttm->dummy_read_page = dummy_read_page;
 	ttm->state = tt_unpopulated;
 	ttm->swap_storage = NULL;
+	ttm->sg = bo->sg;
+}
 
-	ttm_tt_alloc_page_directory(ttm);
-	if (!ttm->pages) {
+int ttm_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo,
+		uint32_t page_flags)
+{
+	ttm_tt_init_fields(ttm, bo, page_flags);
+
+	if (ttm_tt_alloc_page_directory(ttm)) {
 		ttm_tt_destroy(ttm);
 		pr_err("Failed allocating page table\n");
 		return -ENOMEM;
@@ -214,24 +266,15 @@ void ttm_tt_fini(struct ttm_tt *ttm)
 }
 EXPORT_SYMBOL(ttm_tt_fini);
 
-int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
-		unsigned long size, uint32_t page_flags,
-		struct page *dummy_read_page)
+int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_buffer_object *bo,
+		    uint32_t page_flags)
 {
 	struct ttm_tt *ttm = &ttm_dma->ttm;
 
-	ttm->bdev = bdev;
-	ttm->glob = bdev->glob;
-	ttm->num_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	ttm->caching_state = tt_cached;
-	ttm->page_flags = page_flags;
-	ttm->dummy_read_page = dummy_read_page;
-	ttm->state = tt_unpopulated;
-	ttm->swap_storage = NULL;
+	ttm_tt_init_fields(ttm, bo, page_flags);
 
 	INIT_LIST_HEAD(&ttm_dma->pages_list);
-	ttm_dma_tt_alloc_page_directory(ttm_dma);
-	if (!ttm->pages) {
+	if (ttm_dma_tt_alloc_page_directory(ttm_dma)) {
 		ttm_tt_destroy(ttm);
 		pr_err("Failed allocating page table\n");
 		return -ENOMEM;
@@ -240,11 +283,36 @@ int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_bo_device *bdev,
 }
 EXPORT_SYMBOL(ttm_dma_tt_init);
 
+int ttm_sg_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_buffer_object *bo,
+		   uint32_t page_flags)
+{
+	struct ttm_tt *ttm = &ttm_dma->ttm;
+	int ret;
+
+	ttm_tt_init_fields(ttm, bo, page_flags);
+
+	INIT_LIST_HEAD(&ttm_dma->pages_list);
+	if (page_flags & TTM_PAGE_FLAG_SG)
+		ret = ttm_sg_tt_alloc_page_directory(ttm_dma);
+	else
+		ret = ttm_dma_tt_alloc_page_directory(ttm_dma);
+	if (ret) {
+		ttm_tt_destroy(ttm);
+		pr_err("Failed allocating page table\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ttm_sg_tt_init);
+
 void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma)
 {
 	struct ttm_tt *ttm = &ttm_dma->ttm;
 
-	kvfree(ttm->pages);
+	if (ttm->pages)
+		kvfree(ttm->pages);
+	else
+		kvfree(ttm_dma->dma_address);
 	ttm->pages = NULL;
 	ttm_dma->dma_address = NULL;
 }
@@ -272,7 +340,7 @@ int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem,
 	if (ttm->state == tt_bound)
 		return 0;
 
-	ret = ttm->bdev->driver->ttm_tt_populate(ttm, ctx);
+	ret = ttm_tt_populate(ttm, ctx);
 	if (ret)
 		return ret;
 
@@ -301,7 +369,11 @@ int ttm_tt_swapin(struct ttm_tt *ttm)
 	swap_space = swap_storage->f_mapping;
 
 	for (i = 0; i < ttm->num_pages; ++i) {
-		from_page = shmem_read_mapping_page(swap_space, i);
+		gfp_t gfp_mask = mapping_gfp_mask(swap_space);
+
+		gfp_mask |= (ttm->page_flags & TTM_PAGE_FLAG_NO_RETRY ? __GFP_RETRY_MAYFAIL : 0);
+		from_page = shmem_read_mapping_page_gfp(swap_space, i, gfp_mask);
+
 		if (IS_ERR(from_page)) {
 			ret = PTR_ERR(from_page);
 			goto out_err;
@@ -344,16 +416,22 @@ int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage)
 			pr_err("Failed allocating swap storage\n");
 			return PTR_ERR(swap_storage);
 		}
-	} else
+	} else {
 		swap_storage = persistent_swap_storage;
+	}
 
 	swap_space = swap_storage->f_mapping;
 
 	for (i = 0; i < ttm->num_pages; ++i) {
+		gfp_t gfp_mask = mapping_gfp_mask(swap_space);
+
+		gfp_mask |= (ttm->page_flags & TTM_PAGE_FLAG_NO_RETRY ? __GFP_RETRY_MAYFAIL : 0);
+
 		from_page = ttm->pages[i];
 		if (unlikely(from_page == NULL))
 			continue;
-		to_page = shmem_read_mapping_page(swap_space, i);
+
+		to_page = shmem_read_mapping_page_gfp(swap_space, i, gfp_mask);
 		if (IS_ERR(to_page)) {
 			ret = PTR_ERR(to_page);
 			goto out_err;
@@ -378,6 +456,33 @@ out_err:
 	return ret;
 }
 
+static void ttm_tt_add_mapping(struct ttm_tt *ttm)
+{
+	pgoff_t i;
+
+	if (ttm->page_flags & TTM_PAGE_FLAG_SG)
+		return;
+
+	for (i = 0; i < ttm->num_pages; ++i)
+		ttm->pages[i]->mapping = ttm->bdev->dev_mapping;
+}
+
+int ttm_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
+{
+	int ret;
+
+	if (ttm->state != tt_unpopulated)
+		return 0;
+
+	if (ttm->bdev->driver->ttm_tt_populate)
+		ret = ttm->bdev->driver->ttm_tt_populate(ttm, ctx);
+	else
+		ret = ttm_pool_populate(ttm, ctx);
+	if (!ret)
+		ttm_tt_add_mapping(ttm);
+	return ret;
+}
+
 static void ttm_tt_clear_mapping(struct ttm_tt *ttm)
 {
 	pgoff_t i;
@@ -398,5 +503,8 @@ void ttm_tt_unpopulate(struct ttm_tt *ttm)
 		return;
 
 	ttm_tt_clear_mapping(ttm);
-	ttm->bdev->driver->ttm_tt_unpopulate(ttm);
+	if (ttm->bdev->driver->ttm_tt_unpopulate)
+		ttm->bdev->driver->ttm_tt_unpopulate(ttm);
+	else
+		ttm_pool_unpopulate(ttm);
 }