Commit 913bd9060195 ("[PATCH] x86_64: Increase the variability of the
process stack on 64bit architectures"), merged in 2006, increased stack
randomisation from 8 MiB to an ostensible 1 GiB for 64-bit systems.

However the commit actually introduced a mask of 0x3fffff * 4 KiB pages
which provides 16 GiB of randomisation, not 1 GiB.

It appears Andi perhaps typo'd an additional 'f', as 0x3ffff would indeed
provide the stated 1 GiB.

Since this value has been in use for 20 years it seems sensible to retain
it, so correct the comment instead.

Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 arch/x86/include/asm/elf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 0de9df759c99..4133c790e71a 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -322,7 +322,7 @@ extern unsigned long get_sigframe_size(void);
 
 #else /* CONFIG_X86_32 */
 
-/* 1GB for 64bit, 8MB for 32bit */
+/* 16GB for 64bit, 8MB for 32bit */
 #define __STACK_RND_MASK(is32bit) ((is32bit) ? 0x7ff : 0x3fffff)
 #define STACK_RND_MASK __STACK_RND_MASK(mmap_is_ia32())
 

---
base-commit: 248951ddc14de84de3910f9b13f51491a8cd91df
change-id: 20260722-fix-x86-comment-af666535315d

Cheers,
-- 
Lorenzo Stoakes (ARM) <ljs@kernel.org>

On Wed, 22 Jul 2026 19:44:43 +0100, Lorenzo Stoakes (ARM) wrote:
> Commit 913bd9060195 ("[PATCH] x86_64: Increase the variability of the
> process stack on 64bit architectures"), merged in 2006, increased stack
> randomisation from 8 MiB to an ostensible 1 GiB for 64-bit systems.
> 
> However the commit actually introduced a mask of 0x3fffff * 4 KiB pages
> which provides 16 GiB of randomisation, not 1 GiB.
> 
> [...]

Applied to for-next/execve, thanks!

[1/1] x86/elf: Correct comment for STACK_RND_MASK()
      https://git.kernel.org/kees/c/ab11176bd3a7

Take care,

-- 
Kees Cook

On Wed, 22 Jul 2026 19:44:43 +0100 "Lorenzo Stoakes (ARM)" <ljs@kernel.org> wrote:

> Commit 913bd9060195 ("[PATCH] x86_64: Increase the variability of the
> process stack on 64bit architectures"), merged in 2006, increased stack
> randomisation from 8 MiB to an ostensible 1 GiB for 64-bit systems.
> 
> However the commit actually introduced a mask of 0x3fffff * 4 KiB pages
> which provides 16 GiB of randomisation, not 1 GiB.
> 
> It appears Andi perhaps typo'd an additional 'f', as 0x3ffff would indeed
> provide the stated 1 GiB.
> 
> Since this value has been in use for 20 years it seems sensible to retain
> it, so correct the comment instead.

Good catch, and sounds reasonable fix to me.

> 
> Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>

Acked-by: SJ Park <sj@kernel.org>


Thanks,
SJ

[...]