linux-kernel - Re: [PATCH v2] x86/entry: Avoid redundant CR3 write on paranoid returns

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20231027185351.GD26550@noisy.programming.kicks-ass.net>
Date:   Fri, 27 Oct 2023 20:53:51 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Brendan Jackman <jackmanb@...gle.com>
Cc:     luto@...nel.org, tglx@...utronix.de, mingo@...hat.com,
        bp@...en8.de, dave.hansen@...ux.intel.com, x86@...nel.org,
        hpa@...or.com, linux-kernel@...r.kernel.org,
        laijs@...ux.alibaba.com, yosryahmed@...gle.com, reijiw@...gle.com,
        oweisse@...gle.com
Subject: Re: [PATCH v2] x86/entry: Avoid redundant CR3 write on paranoid
 returns

On Wed, Sep 20, 2023 at 03:04:43PM +0000, Brendan Jackman wrote:
> From: Lai Jiangshan <laijs@...ux.alibaba.com>
> 
> This path gets used called from:
> 
> 1. #NMI return.
> 2. paranoid_exit (i.e. #MCE, #VC, #DB and #DF return)
> 
> Contrary to the implication in commit 21e94459110252 ("x86/mm: Optimize
> RESTORE_CR3"), we never modify CR3 in any of these exceptions, except
> for switching from user to kernel pagetables under PTI. That means that
> most of the time when returning from an exception that interrupted the
> kernel no CR3 restore is necessary. Writing CR3 is expensive on some
> machines, so this commit avoids redundant writes.
> 
> I said "most of the time" because we might have interrupted the kernel
> entry before the user->kernel CR3 switch or the exit after the
> kernel->user switch. In the former case skipping the restore might
> actually be be fine, but definitely not the latter. So we do still need
> to check the saved CR3 and restore it if it's a user CR3.
> 
> To reflect the new behaviour RESTORE_CR3 is given a longer name, and a
> comment that was describing its behaviour at the call site is removed.
> We can also simplify the code around the SET_NOFLUSH_BIT invocation
> as we no longer need to branch to it from above.
> 
> Signed-off-by: Lai Jiangshan <laijs@...ux.alibaba.com>
> [Rewrote commit message; responded to review comments]
> Signed-off-by: Brendan Jackman <jackmanb@...gle.com>
> ---

Seems sensible, although I do wonder what made you care enough to
optimize the PTI paranoid path... :-)

Acked-by: Peter Zijlstra (Intel) <peterz@...radead.org>