[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1386973529-4884-39-git-send-email-john.stultz@linaro.org>
Date: Fri, 13 Dec 2013 14:24:12 -0800
From: John Stultz <john.stultz@...aro.org>
To: LKML <linux-kernel@...r.kernel.org>
Cc: Greg KH <gregkh@...uxfoundation.org>,
Android Kernel Team <kernel-team@...roid.com>,
Sumit Semwal <sumit.semwal@...aro.org>,
Jesse Barker <jesse.barker@....com>,
Colin Cross <ccross@...roid.com>,
Rebecca Schultz Zavin <rebecca@...roid.com>,
John Stultz <john.stultz@...aro.org>
Subject: [PATCH 038/115] gpu: ion: Modify gfp flags in ion_system_heap
From: Rebecca Schultz Zavin <rebecca@...roid.com>
When allocations larger than order 4 are made, use _GFP_NORETRY
and __GFP_NO_KSWAPD so kswapd doesn't get kicked off to reclaim
these larger chunks. For smaller allocaitons, these are
unnecessary, as the system should be able to reclaim these.
Signed-off-by: Rebecca Schultz Zavin <rebecca@...roid.com>
[jstultz: modified patch to apply to staging directory]
Signed-off-by: John Stultz <john.stultz@...aro.org>
---
drivers/staging/android/ion/ion_system_heap.c | 25 ++++++++++++++++++-------
1 file changed, 18 insertions(+), 7 deletions(-)
diff --git a/drivers/staging/android/ion/ion_system_heap.c b/drivers/staging/android/ion/ion_system_heap.c
index 35fbfff..b99fa0e 100644
--- a/drivers/staging/android/ion/ion_system_heap.c
+++ b/drivers/staging/android/ion/ion_system_heap.c
@@ -26,6 +26,11 @@
#include "ion.h"
#include "ion_priv.h"
+static unsigned int high_order_gfp_flags = (GFP_HIGHUSER | __GFP_ZERO |
+ __GFP_NOWARN | __GFP_NORETRY |
+ __GFP_NO_KSWAPD);
+static unsigned int low_order_gfp_flags = (GFP_HIGHUSER | __GFP_ZERO |
+ __GFP_NOWARN);
static const unsigned int orders[] = {8, 4, 0};
static const int num_orders = ARRAY_SIZE(orders);
static int order_to_index(unsigned int order)
@@ -63,11 +68,15 @@ static struct page *alloc_buffer_page(struct ion_system_heap *heap,
struct ion_page_pool *pool = heap->pools[order_to_index(order)];
struct page *page;
- if (!cached)
+ if (!cached) {
page = ion_page_pool_alloc(pool);
- else
- page = alloc_pages(GFP_HIGHUSER | __GFP_ZERO |
- __GFP_NOWARN | __GFP_NORETRY, order);
+ } else {
+ gfp_t gfp_flags = low_order_gfp_flags;
+
+ if (order > 4)
+ gfp_flags = high_order_gfp_flags;
+ page = alloc_pages(gfp_flags, order);
+ }
if (!page)
return 0;
if (split_pages)
@@ -342,9 +351,11 @@ struct ion_heap *ion_system_heap_create(struct ion_platform_heap *unused)
goto err_alloc_pools;
for (i = 0; i < num_orders; i++) {
struct ion_page_pool *pool;
- pool = ion_page_pool_create(GFP_HIGHUSER | __GFP_ZERO |
- __GFP_NOWARN | __GFP_NORETRY,
- orders[i]);
+ gfp_t gfp_flags = low_order_gfp_flags;
+
+ if (orders[i] > 4)
+ gfp_flags = high_order_gfp_flags;
+ pool = ion_page_pool_create(gfp_flags, orders[i]);
if (!pool)
goto err_create_pool;
heap->pools[i] = pool;
--
1.8.3.2
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists