Re: [PATCH v3 1/6] x86/uaccess: Avoid barrier_nospec() in 64-bit copy_from_user()
From: Kirill A . Shutemov <hidden>
Date: 2024-10-29 08:14:10
Also in:
lkml
On Mon, Oct 28, 2024 at 06:56:14PM -0700, Josh Poimboeuf wrote:
The barrier_nospec() in 64-bit copy_from_user() is slow. Instead use
pointer masking to force the user pointer to all 1's if the access_ok()
mispredicted true for an invalid address.
The kernel test robot reports a 2.6% improvement in the per_thread_ops
benchmark (see link below).
To avoid regressing powerpc and 32-bit x86, move their barrier_nospec()
calls to their respective raw_copy_from_user() implementations so
there's no functional change there.
Note that for safety on some AMD CPUs, this relies on recent commit
86e6b1547b3d ("x86: fix user address masking non-canonical speculation
issue").
Link: https://lore.kernel.org/202410281344.d02c72a2-oliver.sang@intel.com (local)
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>Acked-by: Kirill A. Shutemov <redacted> -- Kiryl Shutsemau / Kirill A. Shutemov