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.hellst...@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 1cc7591a9542..8787fb6a218b 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>
@@ -47,6 +49,18 @@
#include "ttm_module.h"
+#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 ((MAX_ORDER - 1) < TTM_MAX_ORDER)
+#undef TTM_MAX_ORDER
+#define TTM_MAX_ORDER (MAX_ORDER - 1)
+#endif
+#define TTM_DIM_ORDER (TTM_MAX_ORDER + 1)
+
/**
* struct ttm_pool_dma - Helper object for coherent DMA mappings
*
@@ -65,16 +79,18 @@ module_param(page_pool_size, ulong, 0644);
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)
@@ -400,6 +416,17 @@ static void __ttm_pool_free(struct ttm_pool
*pool, struct ttm_tt *tt,
}
}
+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
*
@@ -439,9 +466,8 @@ 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;
page_caching = tt->caching;
@@ -558,7 +584,7 @@ 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);
}
@@ -578,7 +604,7 @@ 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]);
}
@@ -632,7 +658,7 @@ 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");
}
@@ -643,7 +669,7 @@ 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");
}
@@ -749,10 +775,16 @@ 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);
@@ -785,7 +817,7 @@ 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]);
