Merge tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for v4.15.

  Core:
   - Atomic object lifetime fixes
   - Atomic iterator improvements
   - Sparse/smatch fixes
   - Legacy kms ioctls to be interruptible
   - EDID override improvements
   - fb/gem helper cleanups
   - Simple outreachy patches
   - Documentation improvements
   - Fix dma-buf rcu races
   - DRM mode object leasing for improving VR use cases.
   - vgaarb improvements for non-x86 platforms.

  New driver:
   - tve200: Faraday Technology TVE200 block.

     This "TV Encoder" encodes a ITU-T BT.656 stream and can be found in
     the StorLink SL3516 (later Cortina Systems CS3516) as well as the
     Grain Media GM8180.

  New bridges:
   - SiI9234 support

  New panels:
   - S6E63J0X03, OTM8009A, Seiko 43WVF1G, 7" rpi touch panel, Toshiba
     LT089AC19000, Innolux AT043TN24

  i915:
   - Remove Coffeelake from alpha support
   - Cannonlake workarounds
   - Infoframe refactoring for DisplayPort
   - VBT updates
   - DisplayPort vswing/emph/buffer translation refactoring
   - CCS fixes
   - Restore GPU clock boost on missed vblanks
   - Scatter list updates for userptr allocations
   - Gen9+ transition watermarks
   - Display IPC (Isochronous Priority Control)
   - Private PAT management
   - GVT: improved error handling and pci config sanitizing
   - Execlist refactoring
   - Transparent Huge Page support
   - User defined priorities support
   - HuC/GuC firmware refactoring
   - DP MST fixes
   - eDP power sequencing fixes
   - Use RCU instead of stop_machine
   - PSR state tracking support
   - Eviction fixes
   - BDW DP aux channel timeout fixes
   - LSPCON fixes
   - Cannonlake PLL fixes

  amdgpu:
   - Per VM BO support
   - Powerplay cleanups
   - CI powerplay support
   - PASID mgr for kfd
   - SR-IOV fixes
   - initial GPU reset for vega10
   - Prime mmap support
   - TTM updates
   - Clock query interface for Raven
   - Fence to handle ioctl
   - UVD encode ring support on Polaris
   - Transparent huge page DMA support
   - Compute LRU pipe tweaks
   - BO flag to allow buffers to opt out of implicit sync
   - CTX priority setting API
   - VRAM lost infrastructure plumbing

  qxl:
   - fix flicker since atomic rework

  amdkfd:
   - Further improvements from internal AMD tree
   - Usermode events
   - Drop radeon support

  nouveau:
   - Pascal temperature sensor support
   - Improved BAR2 handling
   - MMU rework to support Pascal MMU

  exynos:
   - Improved HDMI/mixer support
   - HDMI audio interface support

  tegra:
   - Prep work for tegra186
   - Cleanup/fixes

  msm:
   - Preemption support for a5xx
   - Display fixes for 8x96 (snapdragon 820)
   - Async cursor plane fixes
   - FW loading rework
   - GPU debugging improvements

  vc4:
   - Prep for DSI panels
   - fix T-format tiling scanout
   - New madvise ioctl

  Rockchip:
   - LVDS support

  omapdrm:
   - omap4 HDMI CEC support

  etnaviv:
   - GPU performance counters groundwork

  sun4i:
   - refactor driver load + TCON backend
   - HDMI improvements
   - A31 support
   - Misc fixes

  udl:
   - Probe/EDID read fixes.

  tilcdc:
   - Misc fixes.

  pl111:
   - Support more variants

  adv7511:
   - Improve EDID handling.
   - HDMI CEC support

  sii8620:
   - Add remote control support"

* tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux: (1480 commits)
  drm/rockchip: analogix_dp: Use mutex rather than spinlock
  drm/mode_object: fix documentation for object lookups.
  drm/i915: Reorder context-close to avoid calling i915_vma_close() under RCU
  drm/i915: Move init_clock_gating() back to where it was
  drm/i915: Prune the reservation shared fence array
  drm/i915: Idle the GPU before shinking everything
  drm/i915: Lock llist_del_first() vs llist_del_all()
  drm/i915: Calculate ironlake intermediate watermarks correctly, v2.
  drm/i915: Disable lazy PPGTT page table optimization for vGPU
  drm/i915/execlists: Remove the priority "optimisation"
  drm/i915: Filter out spurious execlists context-switch interrupts
  drm/amdgpu: use irq-safe lock for kiq->ring_lock
  drm/amdgpu: bypass lru touch for KIQ ring submission
  drm/amdgpu: Potential uninitialized variable in amdgpu_vm_update_directories()
  drm/amdgpu: potential uninitialized variable in amdgpu_vce_ring_parse_cs()
  drm/amd/powerplay: initialize a variable before using it
  drm/amd/powerplay: suppress KASAN out of bounds warning in vega10_populate_all_memory_levels
  drm/amd/amdgpu: fix evicted VRAM bo adjudgement condition
  drm/vblank: Tune drm_crtc_accurate_vblank_count() WARN down to a debug
  drm/rockchip: add CONFIG_OF dependency for lvds
  ...

5 files changed, 519 insertions, 199 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 180ce6296416..c088703777e2 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -150,8 +150,7 @@ static void ttm_bo_release_list(struct kref *list_kref)
 	ttm_tt_destroy(bo->ttm);
 	atomic_dec(&bo->glob->bo_count);
 	dma_fence_put(bo->moving);
-	if (bo->resv == &bo->ttm_resv)
-		reservation_object_fini(&bo->ttm_resv);
+	reservation_object_fini(&bo->ttm_resv);
 	mutex_destroy(&bo->wu_mutex);
 	if (bo->destroy)
 		bo->destroy(bo);
@@ -402,14 +401,11 @@ static int ttm_bo_individualize_resv(struct ttm_buffer_object *bo)
 	if (bo->resv == &bo->ttm_resv)
 		return 0;
 
-	reservation_object_init(&bo->ttm_resv);
 	BUG_ON(!reservation_object_trylock(&bo->ttm_resv));
 
 	r = reservation_object_copy_fences(&bo->ttm_resv, bo->resv);
-	if (r) {
+	if (r)
 		reservation_object_unlock(&bo->ttm_resv);
-		reservation_object_fini(&bo->ttm_resv);
-	}
 
 	return r;
 }
@@ -440,28 +436,30 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 	struct ttm_bo_global *glob = bo->glob;
 	int ret;
 
+	ret = ttm_bo_individualize_resv(bo);
+	if (ret) {
+		/* Last resort, if we fail to allocate memory for the
+		 * fences block for the BO to become idle
+		 */
+		reservation_object_wait_timeout_rcu(bo->resv, true, false,
+						    30 * HZ);
+		spin_lock(&glob->lru_lock);
+		goto error;
+	}
+
 	spin_lock(&glob->lru_lock);
 	ret = __ttm_bo_reserve(bo, false, true, NULL);
-
 	if (!ret) {
-		if (!ttm_bo_wait(bo, false, true)) {
+		if (reservation_object_test_signaled_rcu(&bo->ttm_resv, true)) {
 			ttm_bo_del_from_lru(bo);
 			spin_unlock(&glob->lru_lock);
-			ttm_bo_cleanup_memtype_use(bo);
+			if (bo->resv != &bo->ttm_resv)
+				reservation_object_unlock(&bo->ttm_resv);
 
-			return;
-		}
-
-		ret = ttm_bo_individualize_resv(bo);
-		if (ret) {
-			/* Last resort, if we fail to allocate memory for the
-			 * fences block for the BO to become idle and free it.
-			 */
-			spin_unlock(&glob->lru_lock);
-			ttm_bo_wait(bo, true, true);
 			ttm_bo_cleanup_memtype_use(bo);
 			return;
 		}
+
 		ttm_bo_flush_all_fences(bo);
 
 		/*
@@ -474,11 +472,12 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 			ttm_bo_add_to_lru(bo);
 		}
 
-		if (bo->resv != &bo->ttm_resv)
-			reservation_object_unlock(&bo->ttm_resv);
 		__ttm_bo_unreserve(bo);
 	}
+	if (bo->resv != &bo->ttm_resv)
+		reservation_object_unlock(&bo->ttm_resv);
 
+error:
 	kref_get(&bo->list_kref);
 	list_add_tail(&bo->ddestroy, &bdev->ddestroy);
 	spin_unlock(&glob->lru_lock);
@@ -1203,8 +1202,8 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 		lockdep_assert_held(&bo->resv->lock.base);
 	} else {
 		bo->resv = &bo->ttm_resv;
-		reservation_object_init(&bo->ttm_resv);
 	}
+	reservation_object_init(&bo->ttm_resv);
 	atomic_inc(&bo->glob->bo_count);
 	drm_vma_node_reset(&bo->vma_node);
 	bo->priority = 0;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index c934ad5b3903..e7a519f1849b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -474,6 +474,7 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	INIT_LIST_HEAD(&fbo->lru);
 	INIT_LIST_HEAD(&fbo->swap);
 	INIT_LIST_HEAD(&fbo->io_reserve_lru);
+	mutex_init(&fbo->wu_mutex);
 	fbo->moving = NULL;
 	drm_vma_node_reset(&fbo->vma_node);
 	atomic_set(&fbo->cpu_writers, 0);
@@ -587,7 +588,6 @@ int ttm_bo_kmap(struct ttm_buffer_object *bo,
 	unsigned long offset, size;
 	int ret;
 
-	BUG_ON(!list_empty(&bo->swap));
 	map->virtual = NULL;
 	map->bo = bo;
 	if (num_pages > bo->num_pages)
diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c
index 29855be96be0..e96374990398 100644
--- a/drivers/gpu/drm/ttm/ttm_memory.c
+++ b/drivers/gpu/drm/ttm/ttm_memory.c
@@ -546,8 +546,7 @@ int ttm_mem_global_alloc(struct ttm_mem_global *glob, uint64_t memory,
 EXPORT_SYMBOL(ttm_mem_global_alloc);
 
 int ttm_mem_global_alloc_page(struct ttm_mem_global *glob,
-			      struct page *page,
-			      bool no_wait, bool interruptible)
+			      struct page *page, uint64_t size)
 {
 
 	struct ttm_mem_zone *zone = NULL;
@@ -564,11 +563,11 @@ int ttm_mem_global_alloc_page(struct ttm_mem_global *glob,
 	if (glob->zone_dma32 && page_to_pfn(page) > 0x00100000UL)
 		zone = glob->zone_kernel;
 #endif
-	return ttm_mem_global_alloc_zone(glob, zone, PAGE_SIZE, no_wait,
-					 interruptible);
+	return ttm_mem_global_alloc_zone(glob, zone, size, false, false);
 }
 
-void ttm_mem_global_free_page(struct ttm_mem_global *glob, struct page *page)
+void ttm_mem_global_free_page(struct ttm_mem_global *glob, struct page *page,
+			      uint64_t size)
 {
 	struct ttm_mem_zone *zone = NULL;
 
@@ -579,10 +578,9 @@ void ttm_mem_global_free_page(struct ttm_mem_global *glob, struct page *page)
 	if (glob->zone_dma32 && page_to_pfn(page) > 0x00100000UL)
 		zone = glob->zone_kernel;
 #endif
-	ttm_mem_global_free_zone(glob, zone, PAGE_SIZE);
+	ttm_mem_global_free_zone(glob, zone, size);
 }
 
-
 size_t ttm_round_pot(size_t size)
 {
 	if ((size & (size - 1)) == 0)
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 871599826773..316f831ad5f0 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -95,7 +95,7 @@ struct ttm_pool_opts {
 	unsigned	small;
 };
 
-#define NUM_POOLS 4
+#define NUM_POOLS 6
 
 /**
  * struct ttm_pool_manager - Holds memory pools for fst allocation
@@ -122,6 +122,8 @@ struct ttm_pool_manager {
 			struct ttm_page_pool	uc_pool;
 			struct ttm_page_pool	wc_pool_dma32;
 			struct ttm_page_pool	uc_pool_dma32;
+			struct ttm_page_pool	wc_pool_huge;
+			struct ttm_page_pool	uc_pool_huge;
 		} ;
 	};
 };
@@ -256,8 +258,8 @@ static int set_pages_array_uc(struct page **pages, int addrinarray)
 
 /**
  * Select the right pool or requested caching state and ttm flags. */
-static struct ttm_page_pool *ttm_get_pool(int flags,
-		enum ttm_caching_state cstate)
+static struct ttm_page_pool *ttm_get_pool(int flags, bool huge,
+					  enum ttm_caching_state cstate)
 {
 	int pool_index;
 
@@ -269,9 +271,15 @@ static struct ttm_page_pool *ttm_get_pool(int flags,
 	else
 		pool_index = 0x1;
 
-	if (flags & TTM_PAGE_FLAG_DMA32)
+	if (flags & TTM_PAGE_FLAG_DMA32) {
+		if (huge)
+			return NULL;
 		pool_index |= 0x2;
 
+	} else if (huge) {
+		pool_index |= 0x4;
+	}
+
 	return &_manager->pools[pool_index];
 }
 
@@ -321,7 +329,7 @@ static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free,
 		pages_to_free = kmalloc(npages_to_free * sizeof(struct page *),
 					GFP_KERNEL);
 	if (!pages_to_free) {
-		pr_err("Failed to allocate memory for pool free operation\n");
+		pr_debug("Failed to allocate memory for pool free operation\n");
 		return 0;
 	}
 
@@ -494,12 +502,14 @@ static void ttm_handle_caching_state_failure(struct list_head *pages,
  * pages returned in pages array.
  */
 static int ttm_alloc_new_pages(struct list_head *pages, gfp_t gfp_flags,
-		int ttm_flags, enum ttm_caching_state cstate, unsigned count)
+			       int ttm_flags, enum ttm_caching_state cstate,
+			       unsigned count, unsigned order)
 {
 	struct page **caching_array;
 	struct page *p;
 	int r = 0;
-	unsigned i, cpages;
+	unsigned i, j, cpages;
+	unsigned npages = 1 << order;
 	unsigned max_cpages = min(count,
 			(unsigned)(PAGE_SIZE/sizeof(struct page *)));
 
@@ -507,15 +517,15 @@ static int ttm_alloc_new_pages(struct list_head *pages, gfp_t gfp_flags,
 	caching_array = kmalloc(max_cpages*sizeof(struct page *), GFP_KERNEL);
 
 	if (!caching_array) {
-		pr_err("Unable to allocate table for new pages\n");
+		pr_debug("Unable to allocate table for new pages\n");
 		return -ENOMEM;
 	}
 
 	for (i = 0, cpages = 0; i < count; ++i) {
-		p = alloc_page(gfp_flags);
+		p = alloc_pages(gfp_flags, order);
 
 		if (!p) {
-			pr_err("Unable to get page %u\n", i);
+			pr_debug("Unable to get page %u\n", i);
 
 			/* store already allocated pages in the pool after
 			 * setting the caching state */
@@ -531,14 +541,18 @@ static int ttm_alloc_new_pages(struct list_head *pages, gfp_t gfp_flags,
 			goto out;
 		}
 
+		list_add(&p->lru, pages);
+
 #ifdef CONFIG_HIGHMEM
 		/* gfp flags of highmem page should never be dma32 so we
 		 * we should be fine in such case
 		 */
-		if (!PageHighMem(p))
+		if (PageHighMem(p))
+			continue;
+
 #endif
-		{
-			caching_array[cpages++] = p;
+		for (j = 0; j < npages; ++j) {
+			caching_array[cpages++] = p++;
 			if (cpages == max_cpages) {
 
 				r = ttm_set_pages_caching(caching_array,
@@ -552,8 +566,6 @@ static int ttm_alloc_new_pages(struct list_head *pages, gfp_t gfp_flags,
 				cpages = 0;
 			}
 		}
-
-		list_add(&p->lru, pages);
 	}
 
 	if (cpages) {
@@ -573,9 +585,9 @@ out:
  * Fill the given pool if there aren't enough pages and the requested number of
  * pages is small.
  */
-static void ttm_page_pool_fill_locked(struct ttm_page_pool *pool,
-		int ttm_flags, enum ttm_caching_state cstate, unsigned count,
-		unsigned long *irq_flags)
+static void ttm_page_pool_fill_locked(struct ttm_page_pool *pool, int ttm_flags,
+				      enum ttm_caching_state cstate,
+				      unsigned count, unsigned long *irq_flags)
 {
 	struct page *p;
 	int r;
@@ -605,7 +617,7 @@ static void ttm_page_pool_fill_locked(struct ttm_page_pool *pool,
 
 		INIT_LIST_HEAD(&new_pages);
 		r = ttm_alloc_new_pages(&new_pages, pool->gfp_flags, ttm_flags,
-				cstate,	alloc_size);
+					cstate, alloc_size, 0);
 		spin_lock_irqsave(&pool->lock, *irq_flags);
 
 		if (!r) {
@@ -613,7 +625,7 @@ static void ttm_page_pool_fill_locked(struct ttm_page_pool *pool,
 			++pool->nrefills;
 			pool->npages += alloc_size;
 		} else {
-			pr_err("Failed to fill pool (%p)\n", pool);
+			pr_debug("Failed to fill pool (%p)\n", pool);
 			/* If we have any pages left put them to the pool. */
 			list_for_each_entry(p, &new_pages, lru) {
 				++cpages;
@@ -627,22 +639,25 @@ static void ttm_page_pool_fill_locked(struct ttm_page_pool *pool,
 }
 
 /**
- * Cut 'count' number of pages from the pool and put them on the return list.
+ * Allocate pages from the pool and put them on the return list.
  *
- * @return count of pages still required to fulfill the request.
+ * @return zero for success or negative error code.
  */
-static unsigned ttm_page_pool_get_pages(struct ttm_page_pool *pool,
-					struct list_head *pages,
-					int ttm_flags,
-					enum ttm_caching_state cstate,
-					unsigned count)
+static int ttm_page_pool_get_pages(struct ttm_page_pool *pool,
+				   struct list_head *pages,
+				   int ttm_flags,
+				   enum ttm_caching_state cstate,
+				   unsigned count, unsigned order)
 {
 	unsigned long irq_flags;
 	struct list_head *p;
 	unsigned i;
+	int r = 0;
 
 	spin_lock_irqsave(&pool->lock, irq_flags);
-	ttm_page_pool_fill_locked(pool, ttm_flags, cstate, count, &irq_flags);
+	if (!order)
+		ttm_page_pool_fill_locked(pool, ttm_flags, cstate, count,
+					  &irq_flags);
 
 	if (count >= pool->npages) {
 		/* take all pages from the pool */
@@ -672,32 +687,126 @@ static unsigned ttm_page_pool_get_pages(struct ttm_page_pool *pool,
 	count = 0;
 out:
 	spin_unlock_irqrestore(&pool->lock, irq_flags);
-	return count;
+
+	/* clear the pages coming from the pool if requested */
+	if (ttm_flags & TTM_PAGE_FLAG_ZERO_ALLOC) {
+		struct page *page;
+
+		list_for_each_entry(page, pages, lru) {
+			if (PageHighMem(page))
+				clear_highpage(page);
+			else
+				clear_page(page_address(page));
+		}
+	}
+
+	/* If pool didn't have enough pages allocate new one. */
+	if (count) {
+		gfp_t gfp_flags = pool->gfp_flags;
+
+		/* set zero flag for page allocation if required */
+		if (ttm_flags & TTM_PAGE_FLAG_ZERO_ALLOC)
+			gfp_flags |= __GFP_ZERO;
+
+		/* ttm_alloc_new_pages doesn't reference pool so we can run
+		 * multiple requests in parallel.
+		 **/
+		r = ttm_alloc_new_pages(pages, gfp_flags, ttm_flags, cstate,
+					count, order);
+	}
+
+	return r;
 }
 
 /* Put all pages in pages list to correct pool to wait for reuse */
 static void ttm_put_pages(struct page **pages, unsigned npages, int flags,
 			  enum ttm_caching_state cstate)
 {
+	struct ttm_page_pool *pool = ttm_get_pool(flags, false, cstate);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	struct ttm_page_pool *huge = ttm_get_pool(flags, true, cstate);
+#endif
 	unsigned long irq_flags;
-	struct ttm_page_pool *pool = ttm_get_pool(flags, cstate);
 	unsigned i;
 
 	if (pool == NULL) {
 		/* No pool for this memory type so free the pages */
-		for (i = 0; i < npages; i++) {
-			if (pages[i]) {
-				if (page_count(pages[i]) != 1)
-					pr_err("Erroneous page count. Leaking pages.\n");
-				__free_page(pages[i]);
-				pages[i] = NULL;
+		i = 0;
+		while (i < npages) {
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+			struct page *p = pages[i];
+#endif
+			unsigned order = 0, j;
+
+			if (!pages[i]) {
+				++i;
+				continue;
+			}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+			for (j = 0; j < HPAGE_PMD_NR; ++j)
+				if (p++ != pages[i + j])
+				    break;
+
+			if (j == HPAGE_PMD_NR)
+				order = HPAGE_PMD_ORDER;
+#endif
+
+			if (page_count(pages[i]) != 1)
+				pr_err("Erroneous page count. Leaking pages.\n");
+			__free_pages(pages[i], order);
+
+			j = 1 << order;
+			while (j) {
+				pages[i++] = NULL;
+				--j;
 			}
 		}
 		return;
 	}
 
+	i = 0;
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (huge) {
+		unsigned max_size, n2free;
+
+		spin_lock_irqsave(&huge->lock, irq_flags);
+		while (i < npages) {
+			struct page *p = pages[i];
+			unsigned j;
+
+			if (!p)
+				break;
+
+			for (j = 0; j < HPAGE_PMD_NR; ++j)
+				if (p++ != pages[i + j])
+				    break;
+
+			if (j != HPAGE_PMD_NR)
+				break;
+
+			list_add_tail(&pages[i]->lru, &huge->list);
+
+			for (j = 0; j < HPAGE_PMD_NR; ++j)
+				pages[i++] = NULL;
+			huge->npages++;
+		}
+
+		/* Check that we don't go over the pool limit */
+		max_size = _manager->options.max_size;
+		max_size /= HPAGE_PMD_NR;
+		if (huge->npages > max_size)
+			n2free = huge->npages - max_size;
+		else
+			n2free = 0;
+		spin_unlock_irqrestore(&huge->lock, irq_flags);
+		if (n2free)
+			ttm_page_pool_free(huge, n2free, false);
+	}
+#endif
+
 	spin_lock_irqsave(&pool->lock, irq_flags);
-	for (i = 0; i < npages; i++) {
+	while (i < npages) {
 		if (pages[i]) {
 			if (page_count(pages[i]) != 1)
 				pr_err("Erroneous page count. Leaking pages.\n");
@@ -705,6 +814,7 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags,
 			pages[i] = NULL;
 			pool->npages++;
 		}
+		++i;
 	}
 	/* Check that we don't go over the pool limit */
 	npages = 0;
@@ -727,75 +837,96 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags,
 static int ttm_get_pages(struct page **pages, unsigned npages, int flags,
 			 enum ttm_caching_state cstate)
 {
-	struct ttm_page_pool *pool = ttm_get_pool(flags, cstate);
+	struct ttm_page_pool *pool = ttm_get_pool(flags, false, cstate);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	struct ttm_page_pool *huge = ttm_get_pool(flags, true, cstate);
+#endif
 	struct list_head plist;
 	struct page *p = NULL;
-	gfp_t gfp_flags = GFP_USER;
 	unsigned count;
 	int r;
 
-	/* set zero flag for page allocation if required */
-	if (flags & TTM_PAGE_FLAG_ZERO_ALLOC)
-		gfp_flags |= __GFP_ZERO;
-
 	/* No pool for cached pages */
 	if (pool == NULL) {
+		gfp_t gfp_flags = GFP_USER;
+		unsigned i;
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		unsigned j;
+#endif
+
+		/* set zero flag for page allocation if required */
+		if (flags & TTM_PAGE_FLAG_ZERO_ALLOC)
+			gfp_flags |= __GFP_ZERO;
+
 		if (flags & TTM_PAGE_FLAG_DMA32)
 			gfp_flags |= GFP_DMA32;
 		else
 			gfp_flags |= GFP_HIGHUSER;
 
-		for (r = 0; r < npages; ++r) {
+		i = 0;
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		while (npages >= HPAGE_PMD_NR) {
+			gfp_t huge_flags = gfp_flags;
+
+			huge_flags |= GFP_TRANSHUGE;
+			huge_flags &= ~__GFP_MOVABLE;
+			huge_flags &= ~__GFP_COMP;
+			p = alloc_pages(huge_flags, HPAGE_PMD_ORDER);
+			if (!p)
+				break;
+
+			for (j = 0; j < HPAGE_PMD_NR; ++j)
+				pages[i++] = p++;
+
+			npages -= HPAGE_PMD_NR;
+		}
+#endif
+
+		while (npages) {
 			p = alloc_page(gfp_flags);
 			if (!p) {
-
-				pr_err("Unable to allocate page\n");
+				pr_debug("Unable to allocate page\n");
 				return -ENOMEM;
 			}
 
-			pages[r] = p;
+			pages[i++] = p;
+			--npages;
 		}
 		return 0;
 	}
 
-	/* combine zero flag to pool flags */
-	gfp_flags |= pool->gfp_flags;
-
-	/* First we take pages from the pool */
-	INIT_LIST_HEAD(&plist);
-	npages = ttm_page_pool_get_pages(pool, &plist, flags, cstate, npages);
 	count = 0;
-	list_for_each_entry(p, &plist, lru) {
-		pages[count++] = p;
-	}
 
-	/* clear the pages coming from the pool if requested */
-	if (flags & TTM_PAGE_FLAG_ZERO_ALLOC) {
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (huge && npages >= HPAGE_PMD_NR) {
+		INIT_LIST_HEAD(&plist);
+		ttm_page_pool_get_pages(huge, &plist, flags, cstate,
+					npages / HPAGE_PMD_NR,
+					HPAGE_PMD_ORDER);
+
 		list_for_each_entry(p, &plist, lru) {
-			if (PageHighMem(p))
-				clear_highpage(p);
-			else
-				clear_page(page_address(p));
+			unsigned j;
+
+			for (j = 0; j < HPAGE_PMD_NR; ++j)
+				pages[count++] = &p[j];
 		}
 	}
+#endif
 
-	/* If pool didn't have enough pages allocate new one. */
-	if (npages > 0) {
-		/* ttm_alloc_new_pages doesn't reference pool so we can run
-		 * multiple requests in parallel.
-		 **/
-		INIT_LIST_HEAD(&plist);
-		r = ttm_alloc_new_pages(&plist, gfp_flags, flags, cstate, npages);
-		list_for_each_entry(p, &plist, lru) {
-			pages[count++] = p;
-		}
-		if (r) {
-			/* If there is any pages in the list put them back to
-			 * the pool. */
-			pr_err("Failed to allocate extra pages for large request\n");
-			ttm_put_pages(pages, count, flags, cstate);
-			return r;
-		}
+	INIT_LIST_HEAD(&plist);
+	r = ttm_page_pool_get_pages(pool, &plist, flags, cstate,
+				    npages - count, 0);
+
+	list_for_each_entry(p, &plist, lru)
+		pages[count++] = p;
+
+	if (r) {
+		/* If there is any pages in the list put them back to
+		 * the pool.
+		 */
+		pr_debug("Failed to allocate extra pages for large request\n");
+		ttm_put_pages(pages, count, flags, cstate);
+		return r;
 	}
 
 	return 0;
@@ -832,6 +963,14 @@ int ttm_page_alloc_init(struct ttm_mem_global *glob, unsigned max_pages)
 	ttm_page_pool_init_locked(&_manager->uc_pool_dma32,
 				  GFP_USER | GFP_DMA32, "uc dma");
 
+	ttm_page_pool_init_locked(&_manager->wc_pool_huge,
+				  GFP_TRANSHUGE	& ~(__GFP_MOVABLE | __GFP_COMP),
+				  "wc huge");
+
+	ttm_page_pool_init_locked(&_manager->uc_pool_huge,
+				  GFP_TRANSHUGE	& ~(__GFP_MOVABLE | __GFP_COMP)
+				  , "uc huge");
+
 	_manager->options.max_size = max_pages;
 	_manager->options.small = SMALL_ALLOCATION;
 	_manager->options.alloc_size = NUM_PAGES_TO_ALLOC;
@@ -873,17 +1012,16 @@ int ttm_pool_populate(struct ttm_tt *ttm)
 	if (ttm->state != tt_unpopulated)
 		return 0;
 
-	for (i = 0; i < ttm->num_pages; ++i) {
-		ret = ttm_get_pages(&ttm->pages[i], 1,
-				    ttm->page_flags,
-				    ttm->caching_state);
-		if (ret != 0) {
-			ttm_pool_unpopulate(ttm);
-			return -ENOMEM;
-		}
+	ret = ttm_get_pages(ttm->pages, ttm->num_pages, ttm->page_flags,
+			    ttm->caching_state);
+	if (unlikely(ret != 0)) {
+		ttm_pool_unpopulate(ttm);
+		return ret;
+	}
 
+	for (i = 0; i < ttm->num_pages; ++i) {
 		ret = ttm_mem_global_alloc_page(mem_glob, ttm->pages[i],
-						false, false);
+						PAGE_SIZE);
 		if (unlikely(ret != 0)) {
 			ttm_pool_unpopulate(ttm);
 			return -ENOMEM;
@@ -908,18 +1046,91 @@ void ttm_pool_unpopulate(struct ttm_tt *ttm)
 	unsigned i;
 
 	for (i = 0; i < ttm->num_pages; ++i) {
-		if (ttm->pages[i]) {
-			ttm_mem_global_free_page(ttm->glob->mem_glob,
-						 ttm->pages[i]);
-			ttm_put_pages(&ttm->pages[i], 1,
-				      ttm->page_flags,
-				      ttm->caching_state);
-		}
+		if (!ttm->pages[i])
+			continue;
+
+		ttm_mem_global_free_page(ttm->glob->mem_glob, ttm->pages[i],
+					 PAGE_SIZE);
 	}
+	ttm_put_pages(ttm->pages, ttm->num_pages, ttm->page_flags,
+		      ttm->caching_state);
 	ttm->state = tt_unpopulated;
 }
 EXPORT_SYMBOL(ttm_pool_unpopulate);
 
+#if defined(CONFIG_SWIOTLB) || defined(CONFIG_INTEL_IOMMU)
+int ttm_populate_and_map_pages(struct device *dev, struct ttm_dma_tt *tt)
+{
+	unsigned i, j;
+	int r;
+
+	r = ttm_pool_populate(&tt->ttm);
+	if (r)
+		return r;
+
+	for (i = 0; i < tt->ttm.num_pages; ++i) {
+		struct page *p = tt->ttm.pages[i];
+		size_t num_pages = 1;
+
+		for (j = i + 1; j < tt->ttm.num_pages; ++j) {
+			if (++p != tt->ttm.pages[j])
+				break;
+
+			++num_pages;
+		}
+
+		tt->dma_address[i] = dma_map_page(dev, tt->ttm.pages[i],
+						  0, num_pages * PAGE_SIZE,
+						  DMA_BIDIRECTIONAL);
+		if (dma_mapping_error(dev, tt->dma_address[i])) {
+			while (i--) {
+				dma_unmap_page(dev, tt->dma_address[i],
+					       PAGE_SIZE, DMA_BIDIRECTIONAL);
+				tt->dma_address[i] = 0;
+			}
+			ttm_pool_unpopulate(&tt->ttm);
+			return -EFAULT;
+		}
+
+		for (j = 1; j < num_pages; ++j) {
+			tt->dma_address[i + 1] = tt->dma_address[i] + PAGE_SIZE;
+			++i;
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ttm_populate_and_map_pages);
+
+void ttm_unmap_and_unpopulate_pages(struct device *dev, struct ttm_dma_tt *tt)
+{
+	unsigned i, j;
+
+	for (i = 0; i < tt->ttm.num_pages;) {
+		struct page *p = tt->ttm.pages[i];
+		size_t num_pages = 1;
+
+		if (!tt->dma_address[i] || !tt->ttm.pages[i]) {
+			++i;
+			continue;
+		}
+
+		for (j = i + 1; j < tt->ttm.num_pages; ++j) {
+			if (++p != tt->ttm.pages[j])
+				break;
+
+			++num_pages;
+		}
+
+		dma_unmap_page(dev, tt->dma_address[i], num_pages * PAGE_SIZE,
+			       DMA_BIDIRECTIONAL);
+
+		i += num_pages;
+	}
+	ttm_pool_unpopulate(&tt->ttm);
+}
+EXPORT_SYMBOL(ttm_unmap_and_unpopulate_pages);
+#endif
+
 int ttm_page_alloc_debugfs(struct seq_file *m, void *data)
 {
 	struct ttm_page_pool *p;
@@ -929,12 +1140,12 @@ int ttm_page_alloc_debugfs(struct seq_file *m, void *data)
 		seq_printf(m, "No pool allocator running.\n");
 		return 0;
 	}
-	seq_printf(m, "%6s %12s %13s %8s\n",
+	seq_printf(m, "%7s %12s %13s %8s\n",
 			h[0], h[1], h[2], h[3]);
 	for (i = 0; i < NUM_POOLS; ++i) {
 		p = &_manager->pools[i];
 
-		seq_printf(m, "%6s %12ld %13ld %8d\n",
+		seq_printf(m, "%7s %12ld %13ld %8d\n",
 				p->name, p->nrefills,
 				p->nfrees, p->npages);
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index 90ddbdca93bd..6b2627fe9bc1 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -60,37 +60,32 @@
 #define NUM_PAGES_TO_ALLOC		(PAGE_SIZE/sizeof(struct page *))
 #define SMALL_ALLOCATION		4
 #define FREE_ALL_PAGES			(~0U)
-/* times are in msecs */
-#define IS_UNDEFINED			(0)
-#define IS_WC				(1<<1)
-#define IS_UC				(1<<2)
-#define IS_CACHED			(1<<3)
-#define IS_DMA32			(1<<4)
+#define VADDR_FLAG_HUGE_POOL		1UL
 
 enum pool_type {
-	POOL_IS_UNDEFINED,
-	POOL_IS_WC = IS_WC,
-	POOL_IS_UC = IS_UC,
-	POOL_IS_CACHED = IS_CACHED,
-	POOL_IS_WC_DMA32 = IS_WC | IS_DMA32,
-	POOL_IS_UC_DMA32 = IS_UC | IS_DMA32,
-	POOL_IS_CACHED_DMA32 = IS_CACHED | IS_DMA32,
+	IS_UNDEFINED	= 0,
+	IS_WC		= 1 << 1,
+	IS_UC		= 1 << 2,
+	IS_CACHED	= 1 << 3,
+	IS_DMA32	= 1 << 4,
+	IS_HUGE		= 1 << 5
 };
+
 /*
- * The pool structure. There are usually six pools:
+ * The pool structure. There are up to nine pools:
  *  - generic (not restricted to DMA32):
  *      - write combined, uncached, cached.
  *  - dma32 (up to 2^32 - so up 4GB):
  *      - write combined, uncached, cached.
+ *  - huge (not restricted to DMA32):
+ *      - write combined, uncached, cached.
  * for each 'struct device'. The 'cached' is for pages that are actively used.
  * The other ones can be shrunk by the shrinker API if neccessary.
  * @pools: The 'struct device->dma_pools' link.
  * @type: Type of the pool
- * @lock: Protects the inuse_list and free_list from concurrnet access. Must be
+ * @lock: Protects the free_list from concurrnet access. Must be
  * used with irqsave/irqrestore variants because pool allocator maybe called
  * from delayed work.
- * @inuse_list: Pool of pages that are in use. The order is very important and
- *   it is in the order that the TTM pages that are put back are in.
  * @free_list: Pool of pages that are free to be used. No order requirements.
  * @dev: The device that is associated with these pools.
  * @size: Size used during DMA allocation.
@@ -107,7 +102,6 @@ struct dma_pool {
 	struct list_head pools; /* The 'struct device->dma_pools link */
 	enum pool_type type;
 	spinlock_t lock;
-	struct list_head inuse_list;
 	struct list_head free_list;
 	struct device *dev;
 	unsigned size;
@@ -124,13 +118,14 @@ struct dma_pool {
  * The accounting page keeping track of the allocated page along with
  * the DMA address.
  * @page_list: The link to the 'page_list' in 'struct dma_pool'.
- * @vaddr: The virtual address of the page
+ * @vaddr: The virtual address of the page and a flag if the page belongs to a
+ * huge pool
  * @dma: The bus address of the page. If the page is not allocated
  *   via the DMA API, it will be -1.
  */
 struct dma_page {
 	struct list_head page_list;
-	void *vaddr;
+	unsigned long vaddr;
 	struct page *p;
 	dma_addr_t dma;
 };
@@ -329,7 +324,8 @@ static int ttm_set_pages_caching(struct dma_pool *pool,
 static void __ttm_dma_free_page(struct dma_pool *pool, struct dma_page *d_page)
 {
 	dma_addr_t dma = d_page->dma;
-	dma_free_coherent(pool->dev, pool->size, d_page->vaddr, dma);
+	d_page->vaddr &= ~VADDR_FLAG_HUGE_POOL;
+	dma_free_coherent(pool->dev, pool->size, (void *)d_page->vaddr, dma);
 
 	kfree(d_page);
 	d_page = NULL;
@@ -337,19 +333,22 @@ static void __ttm_dma_free_page(struct dma_pool *pool, struct dma_page *d_page)
 static struct dma_page *__ttm_dma_alloc_page(struct dma_pool *pool)
 {
 	struct dma_page *d_page;
+	void *vaddr;
 
 	d_page = kmalloc(sizeof(struct dma_page), GFP_KERNEL);
 	if (!d_page)
 		return NULL;
 
-	d_page->vaddr = dma_alloc_coherent(pool->dev, pool->size,
-					   &d_page->dma,
-					   pool->gfp_flags);
-	if (d_page->vaddr) {
-		if (is_vmalloc_addr(d_page->vaddr))
-			d_page->p = vmalloc_to_page(d_page->vaddr);
+	vaddr = dma_alloc_coherent(pool->dev, pool->size, &d_page->dma,
+				   pool->gfp_flags);
+	if (vaddr) {
+		if (is_vmalloc_addr(vaddr))
+			d_page->p = vmalloc_to_page(vaddr);
 		else
-			d_page->p = virt_to_page(d_page->vaddr);
+			d_page->p = virt_to_page(vaddr);
+		d_page->vaddr = (unsigned long)vaddr;
+		if (pool->type & IS_HUGE)
+			d_page->vaddr |= VADDR_FLAG_HUGE_POOL;
 	} else {
 		kfree(d_page);
 		d_page = NULL;
@@ -381,11 +380,40 @@ static void ttm_pool_update_free_locked(struct dma_pool *pool,
 }
 
 /* set memory back to wb and free the pages. */
+static void ttm_dma_page_put(struct dma_pool *pool, struct dma_page *d_page)
+{
+	struct page *page = d_page->p;
+	unsigned i, num_pages;
+	int ret;
+
+	/* Don't set WB on WB page pool. */
+	if (!(pool->type & IS_CACHED)) {
+		num_pages = pool->size / PAGE_SIZE;
+		for (i = 0; i < num_pages; ++i, ++page) {
+			ret = set_pages_array_wb(&page, 1);
+			if (ret) {
+				pr_err("%s: Failed to set %d pages to wb!\n",
+				       pool->dev_name, 1);
+			}
+		}
+	}
+
+	list_del(&d_page->page_list);
+	__ttm_dma_free_page(pool, d_page);
+}
+
 static void ttm_dma_pages_put(struct dma_pool *pool, struct list_head *d_pages,
 			      struct page *pages[], unsigned npages)
 {
 	struct dma_page *d_page, *tmp;
 
+	if (pool->type & IS_HUGE) {
+		list_for_each_entry_safe(d_page, tmp, d_pages, page_list)
+			ttm_dma_page_put(pool, d_page);
+
+		return;
+	}
+
 	/* Don't set WB on WB page pool. */
 	if (npages && !(pool->type & IS_CACHED) &&
 	    set_pages_array_wb(pages, npages))
@@ -398,17 +426,6 @@ static void ttm_dma_pages_put(struct dma_pool *pool, struct list_head *d_pages,
 	}
 }
 
-static void ttm_dma_page_put(struct dma_pool *pool, struct dma_page *d_page)
-{
-	/* Don't set WB on WB page pool. */
-	if (!(pool->type & IS_CACHED) && set_pages_array_wb(&d_page->p, 1))
-		pr_err("%s: Failed to set %d pages to wb!\n",
-		       pool->dev_name, 1);
-
-	list_del(&d_page->page_list);
-	__ttm_dma_free_page(pool, d_page);
-}
-
 /*
  * Free pages from pool.
  *
@@ -446,7 +463,7 @@ static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free,
 					GFP_KERNEL);
 
 	if (!pages_to_free) {
-		pr_err("%s: Failed to allocate memory for pool free operation\n",
+		pr_debug("%s: Failed to allocate memory for pool free operation\n",
 		       pool->dev_name);
 		return 0;
 	}
@@ -577,8 +594,8 @@ static int ttm_dma_pool_match(struct device *dev, void *res, void *match_data)
 static struct dma_pool *ttm_dma_pool_init(struct device *dev, gfp_t flags,
 					  enum pool_type type)
 {
-	char *n[] = {"wc", "uc", "cached", " dma32", "unknown",};
-	enum pool_type t[] = {IS_WC, IS_UC, IS_CACHED, IS_DMA32, IS_UNDEFINED};
+	const char *n[] = {"wc", "uc", "cached", " dma32", "huge"};
+	enum pool_type t[] = {IS_WC, IS_UC, IS_CACHED, IS_DMA32, IS_HUGE};
 	struct device_pools *sec_pool = NULL;
 	struct dma_pool *pool = NULL, **ptr;
 	unsigned i;
@@ -609,18 +626,24 @@ static struct dma_pool *ttm_dma_pool_init(struct device *dev, gfp_t flags,
 	sec_pool->pool =  pool;
 
 	INIT_LIST_HEAD(&pool->free_list);
-	INIT_LIST_HEAD(&pool->inuse_list);
 	INIT_LIST_HEAD(&pool->pools);
 	spin_lock_init(&pool->lock);
 	pool->dev = dev;
 	pool->npages_free = pool->npages_in_use = 0;
 	pool->nfrees = 0;
 	pool->gfp_flags = flags;
-	pool->size = PAGE_SIZE;
+	if (type & IS_HUGE)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		pool->size = HPAGE_PMD_SIZE;
+#else
+		BUG();
+#endif
+	else
+		pool->size = PAGE_SIZE;
 	pool->type = type;
 	pool->nrefills = 0;
 	p = pool->name;
-	for (i = 0; i < 5; i++) {
+	for (i = 0; i < ARRAY_SIZE(t); i++) {
 		if (type & t[i]) {
 			p += snprintf(p, sizeof(pool->name) - (p - pool->name),
 				      "%s", n[i]);
@@ -724,7 +747,7 @@ static int ttm_dma_pool_alloc_new_pages(struct dma_pool *pool,
 	struct dma_page *dma_p;
 	struct page *p;
 	int r = 0;
-	unsigned i, cpages;
+	unsigned i, j, npages, cpages;
 	unsigned max_cpages = min(count,
 			(unsigned)(PAGE_SIZE/sizeof(struct page *)));
 
@@ -732,7 +755,7 @@ static int ttm_dma_pool_alloc_new_pages(struct dma_pool *pool,
 	caching_array = kmalloc(max_cpages*sizeof(struct page *), GFP_KERNEL);
 
 	if (!caching_array) {
-		pr_err("%s: Unable to allocate table for new pages\n",
+		pr_debug("%s: Unable to allocate table for new pages\n",
 		       pool->dev_name);
 		return -ENOMEM;
 	}
@@ -745,8 +768,8 @@ static int ttm_dma_pool_alloc_new_pages(struct dma_pool *pool,
 	for (i = 0, cpages = 0; i < count; ++i) {
 		dma_p = __ttm_dma_alloc_page(pool);
 		if (!dma_p) {
-			pr_err("%s: Unable to get page %u\n",
-			       pool->dev_name, i);
+			pr_debug("%s: Unable to get page %u\n",
+				 pool->dev_name, i);
 
 			/* store already allocated pages in the pool after
 			 * setting the caching state */
@@ -762,28 +785,32 @@ static int ttm_dma_pool_alloc_new_pages(struct dma_pool *pool,
 			goto out;
 		}
 		p = dma_p->p;
+		list_add(&dma_p->page_list, d_pages);
+
 #ifdef CONFIG_HIGHMEM
 		/* gfp flags of highmem page should never be dma32 so we
 		 * we should be fine in such case
 		 */
-		if (!PageHighMem(p))
+		if (PageHighMem(p))
+			continue;
 #endif
-		{
-			caching_array[cpages++] = p;
+
+		npages = pool->size / PAGE_SIZE;
+		for (j = 0; j < npages; ++j) {
+			caching_array[cpages++] = p + j;
 			if (cpages == max_cpages) {
 				/* Note: Cannot hold the spinlock */
 				r = ttm_set_pages_caching(pool, caching_array,
-						 cpages);
+							  cpages);
 				if (r) {
 					ttm_dma_handle_caching_state_failure(
-						pool, d_pages, caching_array,
-						cpages);
+					     pool, d_pages, caching_array,
+					     cpages);
 					goto out;
 				}
 				cpages = 0;
 			}
 		}
-		list_add(&dma_p->page_list, d_pages);
 	}
 
 	if (cpages) {
@@ -828,8 +855,8 @@ static int ttm_dma_page_pool_fill_locked(struct dma_pool *pool,
 			struct dma_page *d_page;
 			unsigned cpages = 0;
 
-			pr_err("%s: Failed to fill %s pool (r:%d)!\n",
-			       pool->dev_name, pool->name, r);
+			pr_debug("%s: Failed to fill %s pool (r:%d)!\n",
+				 pool->dev_name, pool->name, r);
 
 			list_for_each_entry(d_page, &d_pages, page_list) {
 				cpages++;
@@ -871,6 +898,27 @@ static int ttm_dma_pool_get_pages(struct dma_pool *pool,
 	return r;
 }
 
+static gfp_t ttm_dma_pool_gfp_flags(struct ttm_dma_tt *ttm_dma, bool huge)
+{
+	struct ttm_tt *ttm = &ttm_dma->ttm;
+	gfp_t gfp_flags;
+
+	if (ttm->page_flags & TTM_PAGE_FLAG_DMA32)
+		gfp_flags = GFP_USER | GFP_DMA32;
+	else
+		gfp_flags = GFP_HIGHUSER;
+	if (ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)
+		gfp_flags |= __GFP_ZERO;
+
+	if (huge) {
+		gfp_flags |= GFP_TRANSHUGE;
+		gfp_flags &= ~__GFP_MOVABLE;
+		gfp_flags &= ~__GFP_COMP;
+	}
+
+	return gfp_flags;
+}
+
 /*
  * On success pages list will hold count number of correctly
  * cached pages. On failure will hold the negative return value (-ENOMEM, etc).
@@ -879,33 +927,70 @@ int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 {
 	struct ttm_tt *ttm = &ttm_dma->ttm;
 	struct ttm_mem_global *mem_glob = ttm->glob->mem_glob;
+	unsigned long num_pages = ttm->num_pages;
 	struct dma_pool *pool;
 	enum pool_type type;
 	unsigned i;
-	gfp_t gfp_flags;
 	int ret;
 
 	if (ttm->state != tt_unpopulated)
 		return 0;
 
+	INIT_LIST_HEAD(&ttm_dma->pages_list);
+	i = 0;
+
 	type = ttm_to_type(ttm->page_flags, ttm->caching_state);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	if (ttm->page_flags & TTM_PAGE_FLAG_DMA32)
-		gfp_flags = GFP_USER | GFP_DMA32;
-	else
-		gfp_flags = GFP_HIGHUSER;
-	if (ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)
-		gfp_flags |= __GFP_ZERO;
+		goto skip_huge;
+
+	pool = ttm_dma_find_pool(dev, type | IS_HUGE);
+	if (!pool) {
+		gfp_t gfp_flags = ttm_dma_pool_gfp_flags(ttm_dma, true);
+
+		pool = ttm_dma_pool_init(dev, gfp_flags, type | IS_HUGE);
+		if (IS_ERR_OR_NULL(pool))
+			goto skip_huge;
+	}
+
+	while (num_pages >= HPAGE_PMD_NR) {
+		unsigned j;
+
+		ret = ttm_dma_pool_get_pages(pool, ttm_dma, i);
+		if (ret != 0)
+			break;
+
+		ret = ttm_mem_global_alloc_page(mem_glob, ttm->pages[i],
+						pool->size);
+		if (unlikely(ret != 0)) {
+			ttm_dma_unpopulate(ttm_dma, dev);
+			return -ENOMEM;
+		}
+
+		for (j = i + 1; j < (i + HPAGE_PMD_NR); ++j) {
+			ttm->pages[j] = ttm->pages[j - 1] + 1;
+			ttm_dma->dma_address[j] = ttm_dma->dma_address[j - 1] +
+				PAGE_SIZE;
+		}
+
+		i += HPAGE_PMD_NR;
+		num_pages -= HPAGE_PMD_NR;
+	}
+
+skip_huge:
+#endif
 
 	pool = ttm_dma_find_pool(dev, type);
 	if (!pool) {
+		gfp_t gfp_flags = ttm_dma_pool_gfp_flags(ttm_dma, false);
+
 		pool = ttm_dma_pool_init(dev, gfp_flags, type);
-		if (IS_ERR_OR_NULL(pool)) {
+		if (IS_ERR_OR_NULL(pool))
 			return -ENOMEM;
-		}
 	}
 
-	INIT_LIST_HEAD(&ttm_dma->pages_list);
-	for (i = 0; i < ttm->num_pages; ++i) {
+	while (num_pages) {
 		ret = ttm_dma_pool_get_pages(pool, ttm_dma, i);
 		if (ret != 0) {
 			ttm_dma_unpopulate(ttm_dma, dev);
@@ -913,11 +998,14 @@ int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 		}
 
 		ret = ttm_mem_global_alloc_page(mem_glob, ttm->pages[i],
-						false, false);
+						pool->size);
 		if (unlikely(ret != 0)) {
 			ttm_dma_unpopulate(ttm_dma, dev);
 			return -ENOMEM;
 		}
+
+		++i;
+		--num_pages;
 	}
 
 	if (unlikely(ttm->page_flags & TTM_PAGE_FLAG_SWAPPED)) {
@@ -941,10 +1029,33 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 	struct dma_page *d_page, *next;
 	enum pool_type type;
 	bool is_cached = false;
-	unsigned count = 0, i, npages = 0;
+	unsigned count, i, npages = 0;
 	unsigned long irq_flags;
 
 	type = ttm_to_type(ttm->page_flags, ttm->caching_state);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	pool = ttm_dma_find_pool(dev, type | IS_HUGE);
+	if (pool) {
+		count = 0;
+		list_for_each_entry_safe(d_page, next, &ttm_dma->pages_list,
+					 page_list) {
+			if (!(d_page->vaddr & VADDR_FLAG_HUGE_POOL))
+				continue;
+
+			count++;
+			ttm_mem_global_free_page(ttm->glob->mem_glob,
+						 d_page->p, pool->size);
+			ttm_dma_page_put(pool, d_page);
+		}
+
+		spin_lock_irqsave(&pool->lock, irq_flags);
+		pool->npages_in_use -= count;
+		pool->nfrees += count;
+		spin_unlock_irqrestore(&pool->lock, irq_flags);
+	}
+#endif
+
 	pool = ttm_dma_find_pool(dev, type);
 	if (!pool)
 		return;
@@ -953,6 +1064,7 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 		     ttm_to_type(ttm->page_flags, tt_cached)) == pool);
 
 	/* make sure pages array match list and count number of pages */
+	count = 0;
 	list_for_each_entry(d_page, &ttm_dma->pages_list, page_list) {
 		ttm->pages[count] = d_page->p;
 		count++;
@@ -978,13 +1090,13 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 	if (is_cached) {
 		list_for_each_entry_safe(d_page, next, &ttm_dma->pages_list, page_list) {
 			ttm_mem_global_free_page(ttm->glob->mem_glob,
-						 d_page->p);
+						 d_page->p, pool->size);
 			ttm_dma_page_put(pool, d_page);
 		}
 	} else {
 		for (i = 0; i < count; i++) {
 			ttm_mem_global_free_page(ttm->glob->mem_glob,
-						 ttm->pages[i]);
+						 ttm->pages[i], pool->size);
 		}
 	}