[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAGXu5jJS-PYS7ONy_neDQCqVGRwrtjg=VdktXALQnzRe1+RNuA@mail.gmail.com>
Date: Wed, 18 Apr 2018 17:11:39 -0700
From: Kees Cook <keescook@...gle.com>
To: Dave Hansen <dave.hansen@...ux.intel.com>
Cc: LKML <linux-kernel@...r.kernel.org>, Linux-MM <linux-mm@...ck.org>,
Andrea Arcangeli <aarcange@...hat.com>,
Andy Lutomirski <luto@...nel.org>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Hugh Dickins <hughd@...gle.com>,
Juergen Gross <jgross@...e.com>, X86 ML <x86@...nel.org>,
namit@...are.com
Subject: Re: [PATCH 11/11] x86/pti: leave kernel text global for !PCID
On Fri, Apr 6, 2018 at 1:55 PM, Dave Hansen <dave.hansen@...ux.intel.com> wrote:
> +/*
> + * For some configurations, map all of kernel text into the user page
> + * tables. This reduces TLB misses, especially on non-PCID systems.
> + */
> +void pti_clone_kernel_text(void)
> +{
> + unsigned long start = PFN_ALIGN(_text);
> + unsigned long end = ALIGN((unsigned long)_end, PMD_PAGE_SIZE);
I think this is too much set global: _end is after data, bss, and brk,
and all kinds of other stuff that could hold secrets. I think this
should match what mark_rodata_ro() is doing and use
__end_rodata_hpage_align. (And on i386, this should be maybe _etext.)
-Kees
--
Kees Cook
Pixel Security
Powered by blists - more mailing lists