Merge branch 'drm-ttm-pool' into drm-core-next

* drm-ttm-pool:
  drm/ttm: using kmalloc/kfree requires including slab.h
  drm/ttm: include linux/seq_file.h for seq_printf
  drm/ttm: Add sysfs interface to control pool allocator.
  drm/ttm: Use set_pages_array_wc instead of set_memory_wc.
  arch/x86: Add array variants for setting memory to wc caching.
  drm/nouveau: Add ttm page pool debugfs file.
  drm/radeon/kms: Add ttm page pool debugfs file.
  drm/ttm: Add debugfs output entry to pool allocator.
  drm/ttm: add pool wc/uc page allocator V3

arch/x86/include/asm/cacheflush.h

@@ -139,9 +139,11 @@ int set_memory_np(unsigned long addr, int numpages);
 int set_memory_4k(unsigned long addr, int numpages);
 
 int set_memory_array_uc(unsigned long *addr, int addrinarray);
+int set_memory_array_wc(unsigned long *addr, int addrinarray);
 int set_memory_array_wb(unsigned long *addr, int addrinarray);
 
 int set_pages_array_uc(struct page **pages, int addrinarray);
+int set_pages_array_wc(struct page **pages, int addrinarray);
 int set_pages_array_wb(struct page **pages, int addrinarray);
 
 /*

arch/x86/mm/pageattr.c

@@ -997,7 +997,8 @@ int set_memory_uc(unsigned long addr, int numpages)
 }
 EXPORT_SYMBOL(set_memory_uc);
 
-int set_memory_array_uc(unsigned long *addr, int addrinarray)
+int _set_memory_array(unsigned long *addr, int addrinarray,
+		unsigned long new_type)
 {
 	int i, j;
 	int ret;
@@ -1007,13 +1008,19 @@ int set_memory_array_uc(unsigned long *addr, int addrinarray)
 	 */
 	for (i = 0; i < addrinarray; i++) {
 		ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE,
-					_PAGE_CACHE_UC_MINUS, NULL);
+					new_type, NULL);
 		if (ret)
 			goto out_free;
 	}
 
 	ret = change_page_attr_set(addr, addrinarray,
 				    __pgprot(_PAGE_CACHE_UC_MINUS), 1);
+
+	if (!ret && new_type == _PAGE_CACHE_WC)
+		ret = change_page_attr_set_clr(addr, addrinarray,
+					       __pgprot(_PAGE_CACHE_WC),
+					       __pgprot(_PAGE_CACHE_MASK),
+					       0, CPA_ARRAY, NULL);
 	if (ret)
 		goto out_free;
 
@@ -1025,8 +1032,19 @@ int set_memory_array_uc(unsigned long *addr, int addrinarray)
 
 	return ret;
 }
+
+int set_memory_array_uc(unsigned long *addr, int addrinarray)
+{
+	return _set_memory_array(addr, addrinarray, _PAGE_CACHE_UC_MINUS);
+}
 EXPORT_SYMBOL(set_memory_array_uc);
 
+int set_memory_array_wc(unsigned long *addr, int addrinarray)
+{
+	return _set_memory_array(addr, addrinarray, _PAGE_CACHE_WC);
+}
+EXPORT_SYMBOL(set_memory_array_wc);
+
 int _set_memory_wc(unsigned long addr, int numpages)
 {
 	int ret;
@@ -1153,26 +1171,34 @@ int set_pages_uc(struct page *page, int numpages)
 }
 EXPORT_SYMBOL(set_pages_uc);
 
-int set_pages_array_uc(struct page **pages, int addrinarray)
+static int _set_pages_array(struct page **pages, int addrinarray,
+		unsigned long new_type)
 {
 	unsigned long start;
 	unsigned long end;
 	int i;
 	int free_idx;
+	int ret;
 
 	for (i = 0; i < addrinarray; i++) {
 		if (PageHighMem(pages[i]))
 			continue;
 		start = page_to_pfn(pages[i]) << PAGE_SHIFT;
 		end = start + PAGE_SIZE;
-		if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL))
+		if (reserve_memtype(start, end, new_type, NULL))
 			goto err_out;
 	}
 
-	if (cpa_set_pages_array(pages, addrinarray,
-			__pgprot(_PAGE_CACHE_UC_MINUS)) == 0) {
+	ret = cpa_set_pages_array(pages, addrinarray,
+			__pgprot(_PAGE_CACHE_UC_MINUS));
+	if (!ret && new_type == _PAGE_CACHE_WC)
+		ret = change_page_attr_set_clr(NULL, addrinarray,
+					       __pgprot(_PAGE_CACHE_WC),
+					       __pgprot(_PAGE_CACHE_MASK),
+					       0, CPA_PAGES_ARRAY, pages);
+	if (ret)
+		goto err_out;
 	return 0; /* Success */
-	}
 err_out:
 	free_idx = i;
 	for (i = 0; i < free_idx; i++) {
@@ -1184,8 +1210,19 @@ int set_pages_array_uc(struct page **pages, int addrinarray)
 	}
 	return -EINVAL;
 }
+
+int set_pages_array_uc(struct page **pages, int addrinarray)
+{
+	return _set_pages_array(pages, addrinarray, _PAGE_CACHE_UC_MINUS);
+}
 EXPORT_SYMBOL(set_pages_array_uc);
 
+int set_pages_array_wc(struct page **pages, int addrinarray)
+{
+	return _set_pages_array(pages, addrinarray, _PAGE_CACHE_WC);
+}
+EXPORT_SYMBOL(set_pages_array_wc);
+
 int set_pages_wb(struct page *page, int numpages)
 {
 	unsigned long addr = (unsigned long)page_address(page);

drivers/gpu/drm/nouveau/nouveau_debugfs.c

@@ -33,6 +33,8 @@
 #include "drmP.h"
 #include "nouveau_drv.h"
 
+#include <ttm/ttm_page_alloc.h>
+
 static int
 nouveau_debugfs_channel_info(struct seq_file *m, void *data)
 {
@@ -159,6 +161,7 @@ static struct drm_info_list nouveau_debugfs_list[] = {
 	{ "chipset", nouveau_debugfs_chipset_info, 0, NULL },
 	{ "memory", nouveau_debugfs_memory_info, 0, NULL },
 	{ "vbios.rom", nouveau_debugfs_vbios_image, 0, NULL },
+	{ "ttm_page_pool", ttm_page_alloc_debugfs, 0, NULL },
 };
 #define NOUVEAU_DEBUGFS_ENTRIES ARRAY_SIZE(nouveau_debugfs_list)
 

drivers/gpu/drm/radeon/radeon_ttm.c

@@ -33,6 +33,7 @@
 #include <ttm/ttm_bo_driver.h>
 #include <ttm/ttm_placement.h>
 #include <ttm/ttm_module.h>
+#include <ttm/ttm_page_alloc.h>
 #include <drm/drmP.h>
 #include <drm/radeon_drm.h>
 #include <linux/seq_file.h>
@@ -745,8 +746,8 @@ static int radeon_mm_dump_table(struct seq_file *m, void *data)
 static int radeon_ttm_debugfs_init(struct radeon_device *rdev)
 {
 #if defined(CONFIG_DEBUG_FS)
-	static struct drm_info_list radeon_mem_types_list[RADEON_DEBUGFS_MEM_TYPES];
-	static char radeon_mem_types_names[RADEON_DEBUGFS_MEM_TYPES][32];
+	static struct drm_info_list radeon_mem_types_list[RADEON_DEBUGFS_MEM_TYPES+1];
+	static char radeon_mem_types_names[RADEON_DEBUGFS_MEM_TYPES+1][32];
 	unsigned i;
 
 	for (i = 0; i < RADEON_DEBUGFS_MEM_TYPES; i++) {
@@ -763,7 +764,13 @@ static int radeon_ttm_debugfs_init(struct radeon_device *rdev)
 			radeon_mem_types_list[i].data = &rdev->mman.bdev.man[TTM_PL_TT].manager;
 
 	}
-	return radeon_debugfs_add_files(rdev, radeon_mem_types_list, RADEON_DEBUGFS_MEM_TYPES);
+	/* Add ttm page pool to debugfs */
+	sprintf(radeon_mem_types_names[i], "ttm_page_pool");
+	radeon_mem_types_list[i].name = radeon_mem_types_names[i];
+	radeon_mem_types_list[i].show = &ttm_page_alloc_debugfs;
+	radeon_mem_types_list[i].driver_features = 0;
+	radeon_mem_types_list[i].data = NULL;
+	return radeon_debugfs_add_files(rdev, radeon_mem_types_list, RADEON_DEBUGFS_MEM_TYPES+1);
 
 #endif
 	return 0;

drivers/gpu/drm/ttm/Makefile

@@ -4,6 +4,6 @@
 ccflags-y := -Iinclude/drm
 ttm-y := ttm_agp_backend.o ttm_memory.o ttm_tt.o ttm_bo.o \
 	ttm_bo_util.o ttm_bo_vm.o ttm_module.o ttm_global.o \
-	ttm_object.o ttm_lock.o ttm_execbuf_util.o
+	ttm_object.o ttm_lock.o ttm_execbuf_util.o ttm_page_alloc.o
 
 obj-$(CONFIG_DRM_TTM) += ttm.o

drivers/gpu/drm/ttm/ttm_memory.c

@@ -27,6 +27,7 @@
 
 #include "ttm/ttm_memory.h"
 #include "ttm/ttm_module.h"
+#include "ttm/ttm_page_alloc.h"
 #include <linux/spinlock.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
@@ -393,6 +394,7 @@ int ttm_mem_global_init(struct ttm_mem_global *glob)
 		       "Zone %7s: Available graphics memory: %llu kiB.\n",
 		       zone->name, (unsigned long long) zone->max_mem >> 10);
 	}
+	ttm_page_alloc_init(glob, glob->zone_kernel->max_mem/(2*PAGE_SIZE));
 	return 0;
 out_no_zone:
 	ttm_mem_global_release(glob);
@@ -405,6 +407,9 @@ void ttm_mem_global_release(struct ttm_mem_global *glob)
 	unsigned int i;
 	struct ttm_mem_zone *zone;
 
+	/* let the page allocator first stop the shrink work. */
+	ttm_page_alloc_fini();
+
 	flush_workqueue(glob->swap_queue);
 	destroy_workqueue(glob->swap_queue);
 	glob->swap_queue = NULL;

drivers/gpu/drm/ttm/ttm_tt.c

@@ -39,6 +39,7 @@
 #include "ttm/ttm_module.h"
 #include "ttm/ttm_bo_driver.h"
 #include "ttm/ttm_placement.h"
+#include "ttm/ttm_page_alloc.h"
 
 static int ttm_tt_swapin(struct ttm_tt *ttm);
 
@@ -56,21 +57,6 @@ static void ttm_tt_free_page_directory(struct ttm_tt *ttm)
 	ttm->pages = NULL;
 }
 
-static struct page *ttm_tt_alloc_page(unsigned page_flags)
-{
-	gfp_t gfp_flags = GFP_USER;
-
-	if (page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)
-		gfp_flags |= __GFP_ZERO;
-
-	if (page_flags & TTM_PAGE_FLAG_DMA32)
-		gfp_flags |= __GFP_DMA32;
-	else
-		gfp_flags |= __GFP_HIGHMEM;
-
-	return alloc_page(gfp_flags);
-}
-
 static void ttm_tt_free_user_pages(struct ttm_tt *ttm)
 {
 	int write;
@@ -111,15 +97,21 @@ static void ttm_tt_free_user_pages(struct ttm_tt *ttm)
 static struct page *__ttm_tt_get_page(struct ttm_tt *ttm, int index)
 {
 	struct page *p;
+	struct list_head h;
 	struct ttm_mem_global *mem_glob = ttm->glob->mem_glob;
 	int ret;
 
 	while (NULL == (p = ttm->pages[index])) {
-		p = ttm_tt_alloc_page(ttm->page_flags);
 
-		if (!p)
+		INIT_LIST_HEAD(&h);
+
+		ret = ttm_get_pages(&h, ttm->page_flags, ttm->caching_state, 1);
+
+		if (ret != 0)
 			return NULL;
 
+		p = list_first_entry(&h, struct page, lru);
+
 		ret = ttm_mem_global_alloc_page(mem_glob, p, false, false);
 		if (unlikely(ret != 0))
 			goto out_err;
@@ -228,10 +220,10 @@ static int ttm_tt_set_caching(struct ttm_tt *ttm,
 	if (ttm->caching_state == c_state)
 		return 0;
 
-	if (c_state != tt_cached) {
-		ret = ttm_tt_populate(ttm);
-		if (unlikely(ret != 0))
-			return ret;
+	if (ttm->state == tt_unpopulated) {
+		/* Change caching but don't populate */
+		ttm->caching_state = c_state;
+		return 0;
 	}
 
 	if (ttm->caching_state == tt_cached)
@@ -282,13 +274,17 @@ EXPORT_SYMBOL(ttm_tt_set_placement_caching);
 static void ttm_tt_free_alloced_pages(struct ttm_tt *ttm)
 {
 	int i;
+	unsigned count = 0;
+	struct list_head h;
 	struct page *cur_page;
 	struct ttm_backend *be = ttm->be;
 
+	INIT_LIST_HEAD(&h);
+
 	if (be)
 		be->func->clear(be);
-	(void)ttm_tt_set_caching(ttm, tt_cached);
 	for (i = 0; i < ttm->num_pages; ++i) {
+
 		cur_page = ttm->pages[i];
 		ttm->pages[i] = NULL;
 		if (cur_page) {
@@ -298,9 +294,11 @@ static void ttm_tt_free_alloced_pages(struct ttm_tt *ttm)
 				       "Leaking pages.\n");
 			ttm_mem_global_free_page(ttm->glob->mem_glob,
 						 cur_page);
-			__free_page(cur_page);
+			list_add(&cur_page->lru, &h);
+			count++;
 		}
 	}
+	ttm_put_pages(&h, count, ttm->page_flags, ttm->caching_state);
 	ttm->state = tt_unpopulated;
 	ttm->first_himem_page = ttm->num_pages;
 	ttm->last_lomem_page = -1;

include/drm/ttm/ttm_page_alloc.h

+/*
+ * Copyright (c) Red Hat Inc.
+
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sub license,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Dave Airlie <airlied@redhat.com>
+ *          Jerome Glisse <jglisse@redhat.com>
+ */
+#ifndef TTM_PAGE_ALLOC
+#define TTM_PAGE_ALLOC
+
+#include "ttm_bo_driver.h"
+#include "ttm_memory.h"
+
+/**
+ * Get count number of pages from pool to pages list.
+ *
+ * @pages: heado of empty linked list where pages are filled.
+ * @flags: ttm flags for page allocation.
+ * @cstate: ttm caching state for the page.
+ * @count: number of pages to allocate.
+ */
+int ttm_get_pages(struct list_head *pages,
+		  int flags,
+		  enum ttm_caching_state cstate,
+		  unsigned count);
+/**
+ * Put linked list of pages to pool.
+ *
+ * @pages: list of pages to free.
+ * @page_count: number of pages in the list. Zero can be passed for unknown
+ * count.
+ * @flags: ttm flags for page allocation.
+ * @cstate: ttm caching state.
+ */
+void ttm_put_pages(struct list_head *pages,
+		   unsigned page_count,
+		   int flags,
+		   enum ttm_caching_state cstate);
+/**
+ * Initialize pool allocator.
+ *
+ * Pool allocator is internaly reference counted so it can be initialized
+ * multiple times but ttm_page_alloc_fini has to be called same number of
+ * times.
+ */
+int ttm_page_alloc_init(struct ttm_mem_global *glob, unsigned max_pages);
+/**
+ * Free pool allocator.
+ */
+void ttm_page_alloc_fini(void);
+
+/**
+ * Output the state of pools to debugfs file
+ */
+extern int ttm_page_alloc_debugfs(struct seq_file *m, void *data);
+#endif