nv-tegra-mirror/linux-nvgpu
1
0
Fork 0
mirror of git://nv-tegra.nvidia.com/linux-nvgpu.git synced 2025-12-24 02:22:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

gpu: nvgpu: Check for split_order > max_order

Browse Source 
When choosing an order of buddy to start splitting from (happens when
no buddies of the requested alloc order exist) don't sit in the while
loop past max_order. This makes no sense and hangs the system.

Bug 1647902

Change-Id: I6900597d24944d3170bc76cd75f33794b07707d1
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/756591
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
This commit is contained in:
Alex Waterman
2015-06-10 13:53:23 -07:00
committed by Terje Bergstrom
parent 0035aff307
commit ed776185ec
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
drivers/gpu/nvgpu/gk20a/gk20a_allocator.c
View File

@@ -604,10 +604,11 @@ static struct gk20a_buddy *__balloc_find_buddy(struct gk20a_allocator *a,
static u64 __balloc_do_alloc(struct gk20a_allocator *a, u64 order, int pte_size)
{
u64 split_order;
struct gk20a_buddy *bud;
struct gk20a_buddy *bud = NULL;
split_order = order;
while (!(bud = __balloc_find_buddy(a, split_order, pte_size)))
while (split_order <= a->max_order &&
!(bud = __balloc_find_buddy(a, split_order, pte_size)))
split_order++;
/* Out of memory! */