svn commit: r352451 - head/stand/libsa
Ian Lepore
ian at freebsd.org
Tue Sep 17 16:21:03 UTC 2019
On Tue, 2019-09-17 at 16:16 +0000, Toomas Soome wrote:
> Author: tsoome
> Date: Tue Sep 17 16:16:46 2019
> New Revision: 352451
> URL: https://svnweb.freebsd.org/changeset/base/352451
>
> Log:
> loader: revert r352421
>
> As insisted by kib, malloc(0) is quite legal.
>
> Modified:
> head/stand/libsa/zalloc_malloc.c
>
> Modified: head/stand/libsa/zalloc_malloc.c
> ==============================================================================
> --- head/stand/libsa/zalloc_malloc.c Tue Sep 17 15:53:40 2019 (r352450)
> +++ head/stand/libsa/zalloc_malloc.c Tue Sep 17 16:16:46 2019 (r352451)
> @@ -73,9 +73,6 @@ Malloc_align(size_t bytes, size_t alignment)
> {
> Guard *res;
>
> - if (bytes == 0)
> - return (NULL);
> -
> #ifdef USEENDGUARD
> bytes += MALLOCALIGN + 1;
> #else
For the record, you're both right. In both the C and posix standards
for malloc(), an implementation is allowed to return either NULL or a
unique pointer which cannot be used to access any memory but must be
passed to free().
-- Ian
More information about the svn-src-head
mailing list