]> git.kernelconcepts.de Git - karo-tx-linux.git/commitdiff
amdkfd: use sizeof(long) granularity for the pasid bitmask
authorSasha Levin <sasha.levin@oracle.com>
Wed, 3 Dec 2014 14:26:25 +0000 (09:26 -0500)
committerOded Gabbay <oded.gabbay@amd.com>
Wed, 3 Dec 2014 14:26:25 +0000 (09:26 -0500)
All the bit operations (such as find_first_zero_bit()) read sizeof(long) bytes
at a time. If we allocated less than sizeof(long) bytes for the bitmask we
would be accessing invalid memory when working with the bitmask.

Change the allocator to allocate sizeof(long) multiples for the bitmask.

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Oded Gabbay <oded.gabbay@amd.com>
drivers/gpu/drm/amd/amdkfd/kfd_pasid.c

index 2458ab7c0c6e3bbcd8376b203ff9ef51c4407708..71699ad97d74487d532cef2a168f8bb4d4fb5366 100644 (file)
@@ -32,8 +32,7 @@ int kfd_pasid_init(void)
 {
        pasid_limit = max_num_of_processes;
 
-       pasid_bitmap = kzalloc(DIV_ROUND_UP(pasid_limit, BITS_PER_BYTE),
-                               GFP_KERNEL);
+       pasid_bitmap = kzalloc(BITS_TO_LONGS(pasid_limit), GFP_KERNEL);
        if (!pasid_bitmap)
                return -ENOMEM;