drm/ttm: add pool wc/uc page allocator V3

On AGP system we might allocate/free routinely uncached or wc memory,
changing page from cached (wb) to uc or wc is very expensive and involves
a lot of flushing. To improve performance this allocator use a pool
of uc,wc pages.

Pools are protected with spinlocks to allow multiple threads to allocate pages
simultanously. Expensive operations are done outside of spinlock to maximize
concurrency.

Pools are linked lists of pages that were recently freed. mm shrink callback
allows kernel to claim back pages when they are required for something else.

Fixes:
* set_pages_array_wb handles highmem pages so we don't have to remove them
  from pool.
* Add count parameter to ttm_put_pages to avoid looping in free code.
* Change looping from _safe to normal in pool fill error path.
* Initialize sum variable and make the loop prettier in get_num_unused_pages.

* Moved pages_freed reseting inside the loop in ttm_page_pool_free.
* Add warning comment about spinlock context in ttm_page_pool_free.

Based on Jerome Glisse's and Dave Airlie's pool allocator.

Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Pauli Nieminen <suokkos@gmail.com>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

1 files changed, 21 insertions, 23 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index bab6cd8d8a1e..a3269ef831c0 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -38,6 +38,7 @@
 #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);
 
@@ -55,21 +56,6 @@ 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;
@@ -110,15 +96,21 @@ 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;
@@ -227,10 +219,10 @@ 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)
@@ -281,13 +273,17 @@ 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) {
@@ -297,9 +293,11 @@ 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;