[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <Ys/k2gPLanPoF+ML@worktop.programming.kicks-ass.net>
Date: Thu, 14 Jul 2022 11:41:46 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Alexandre Chartre <alexandre.chartre@...cle.com>
Cc: bp@...en8.de, x86@...nel.org, linux-kernel@...r.kernel.org,
konrad.wilk@...cle.com, boris.ostrovsky@...cle.com,
ankur.a.arora@...cle.com, maciej.szmigiero@...cle.com
Subject: Re: [PATCH] x86/entry: Remove UNTRAIN_RET from native_irq_return_ldt
On Wed, Jul 13, 2022 at 09:58:08PM +0200, Alexandre Chartre wrote:
> UNTRAIN_RET is not needed in native_irq_return_ldt because ret untrain
> has already be done at this point. In addition, when the RETBleed
> mitigation is IBPB, UNTRAIN_RET clobbers several registers (AX, CX, DX)
> so here it trashes user values which are in these registers.
>
> Signed-off-by: Alexandre Chartre <alexandre.chartre@...cle.com>
Acked-by: Peter Zijlstra (Intel) <peterz@...radead.org>
> ---
> arch/x86/entry/entry_64.S | 1 -
> 1 file changed, 1 deletion(-)
>
> diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
> index 285e043a3e40..9953d966d124 100644
> --- a/arch/x86/entry/entry_64.S
> +++ b/arch/x86/entry/entry_64.S
> @@ -727,7 +727,6 @@ native_irq_return_ldt:
> pushq %rdi /* Stash user RDI */
> swapgs /* to kernel GS */
> SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi /* to kernel CR3 */
> - UNTRAIN_RET
>
> movq PER_CPU_VAR(espfix_waddr), %rdi
> movq %rax, (0*8)(%rdi) /* user RAX */
> --
> 2.31.1
>
Powered by blists - more mailing lists