[RFC PATCH v3 04/13] drm/ttm: Reduce the number of used allocation orders for TTM pages

[Thomas Hellström]

When swapping out, we will split multi-order pages both in order to
move them to the swap-cache and to be able to return memory to the
swap cache as soon as possible on a page-by-page basis.
By reducing the page max order to the system PMD size, we can be nicer
to the system and avoid splitting gigantic pages. On top of this we also
include the 64K page size in the page sizes tried, since that appears to
be a common size for GPU applications.

Looking forward to when we might be able to swap out PMD size folios
without splitting, this will also be a benefit.

Signed-off-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>
---
 drivers/gpu/drm/ttm/ttm_pool.c | 58 ++++++++++++++++++++++++++--------
 1 file changed, 45 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index aa116a7bbae3..dd1d0a1425a0 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -31,6 +31,8 @@
  * cause they are rather slow compared to alloc_pages+map.
  */
 
+#define pr_fmt(fmt) "[TTM POOL] " fmt
+
 #include <linux/module.h>
 #include <linux/dma-mapping.h>
 #include <linux/debugfs.h>
@@ -63,18 +65,32 @@ static unsigned long page_pool_size;
 MODULE_PARM_DESC(page_pool_size, "Number of pages in the WC/UC/DMA pool");
 module_param(page_pool_size, ulong, 0644);
 
+#define TTM_MAX_ORDER (PMD_SHIFT - PAGE_SHIFT)
+#define TTM_64K_ORDER (16 - PAGE_SHIFT)
+#if (TTM_MAX_ORDER < TTM_64K_ORDER)
+#undef TTM_MAX_ORDER
+#define TTM_MAX_ORDER TTM_64K_ORDER
+#endif
+#if (TTM_MAX_ORDER > MAX_ORDER - 1)
+#undef TTM_MAX_ORDER
+#define TTM_MAX_ORDER MAX_ORDER - 1
+#endif
+#define TTM_DIM_ORDER (TTM_MAX_ORDER + 1)
+
 static atomic_long_t allocated_pages;
 
-static struct ttm_pool_type global_write_combined[MAX_ORDER];
-static struct ttm_pool_type global_uncached[MAX_ORDER];
+static struct ttm_pool_type global_write_combined[TTM_DIM_ORDER];
+static struct ttm_pool_type global_uncached[TTM_DIM_ORDER];
 
-static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER];
-static struct ttm_pool_type global_dma32_uncached[MAX_ORDER];
+static struct ttm_pool_type global_dma32_write_combined[TTM_DIM_ORDER];
+static struct ttm_pool_type global_dma32_uncached[TTM_DIM_ORDER];
 
 static spinlock_t shrinker_lock;
 static struct list_head shrinker_list;
 static struct shrinker mm_shrinker;
 
+static unsigned int ttm_pool_orders[] = {TTM_MAX_ORDER, 0, 0};
+
 /* Allocate pages of size 1 << order with the given gfp_flags */
 static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags,
 					unsigned int order)
@@ -367,6 +383,17 @@ static int ttm_pool_page_allocated(struct ttm_pool *pool, unsigned int order,
 	return 0;
 }
 
+static unsigned int ttm_pool_select_order(unsigned int order, pgoff_t num_pages)
+{
+	unsigned int *cur_order = ttm_pool_orders;
+
+	order = min_t(unsigned int, __fls(num_pages), order);
+	while (order < *cur_order)
+		++cur_order;
+
+	return *cur_order;
+}
+
 /**
  * ttm_pool_alloc - Fill a ttm_tt object
  *
@@ -405,9 +432,8 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 	else
 		gfp_flags |= GFP_HIGHUSER;
 
-	for (order = min_t(unsigned int, MAX_ORDER - 1, __fls(num_pages));
-	     num_pages;
-	     order = min_t(unsigned int, order, __fls(num_pages))) {
+	order = ttm_pool_select_order(ttm_pool_orders[0], num_pages);
+	for (; num_pages; order = ttm_pool_select_order(order, num_pages)) {
 		struct ttm_pool_type *pt;
 
 		pt = ttm_pool_select_type(pool, tt->caching, order);
@@ -542,7 +568,7 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev,
 
 	if (use_dma_alloc) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j < MAX_ORDER; ++j)
+			for (j = 0; j < TTM_DIM_ORDER; ++j)
 				ttm_pool_type_init(&pool->caching[i].orders[j],
 						   pool, i, j);
 	}
@@ -562,7 +588,7 @@ void ttm_pool_fini(struct ttm_pool *pool)
 
 	if (pool->use_dma_alloc) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j < MAX_ORDER; ++j)
+			for (j = 0; j < TTM_DIM_ORDER; ++j)
 				ttm_pool_type_fini(&pool->caching[i].orders[j]);
 	}
 
@@ -616,7 +642,7 @@ static void ttm_pool_debugfs_header(struct seq_file *m)
 	unsigned int i;
 
 	seq_puts(m, "\t ");
-	for (i = 0; i < MAX_ORDER; ++i)
+	for (i = 0; i < TTM_DIM_ORDER; ++i)
 		seq_printf(m, " ---%2u---", i);
 	seq_puts(m, "\n");
 }
@@ -627,7 +653,7 @@ static void ttm_pool_debugfs_orders(struct ttm_pool_type *pt,
 {
 	unsigned int i;
 
-	for (i = 0; i < MAX_ORDER; ++i)
+	for (i = 0; i < TTM_DIM_ORDER; ++i)
 		seq_printf(m, " %8u", ttm_pool_type_count(&pt[i]));
 	seq_puts(m, "\n");
 }
@@ -733,10 +759,16 @@ int ttm_pool_mgr_init(unsigned long num_pages)
 	if (!page_pool_size)
 		page_pool_size = num_pages;
 
+	if (TTM_64K_ORDER < TTM_MAX_ORDER)
+		ttm_pool_orders[1] = TTM_64K_ORDER;
+
+	pr_debug("Used orders are %u %u %u\n", ttm_pool_orders[0],
+		 ttm_pool_orders[1], ttm_pool_orders[2]);
+
 	spin_lock_init(&shrinker_lock);
 	INIT_LIST_HEAD(&shrinker_list);
 
-	for (i = 0; i < MAX_ORDER; ++i) {
+	for (i = 0; i < TTM_DIM_ORDER; ++i) {
 		ttm_pool_type_init(&global_write_combined[i], NULL,
 				   ttm_write_combined, i);
 		ttm_pool_type_init(&global_uncached[i], NULL, ttm_uncached, i);
@@ -769,7 +801,7 @@ void ttm_pool_mgr_fini(void)
 {
 	unsigned int i;
 
-	for (i = 0; i < MAX_ORDER; ++i) {
+	for (i = 0; i < TTM_DIM_ORDER; ++i) {
 		ttm_pool_type_fini(&global_write_combined[i]);
 		ttm_pool_type_fini(&global_uncached[i]);
 
-- 
2.34.1