[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87v9maj1kx.fsf@nanos.tec.linutronix.de>
Date: Wed, 08 Apr 2020 01:52:30 +0200
From: Thomas Gleixner <tglx@...utronix.de>
To: Balbir Singh <sblbir@...zon.com>, linux-kernel@...r.kernel.org
Cc: jpoimboe@...hat.com, tony.luck@...el.com, keescook@...omium.org,
benh@...nel.crashing.org, x86@...nel.org, dave.hansen@...el.com,
Balbir Singh <sblbir@...zon.com>
Subject: Re: [PATCH v2 3/4] arch/x86: Optionally flush L1D on context switch
Balbir,
Balbir Singh <sblbir@...zon.com> writes:
> diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
> index 6f66d841262d..69e6ea20679c 100644
> --- a/arch/x86/include/asm/tlbflush.h
> +++ b/arch/x86/include/asm/tlbflush.h
> @@ -172,7 +172,7 @@ struct tlb_state {
> /* Last user mm for optimizing IBPB */
> union {
> struct mm_struct *last_user_mm;
> - unsigned long last_user_mm_ibpb;
> + unsigned long last_user_mm_spec;
> -static inline unsigned long mm_mangle_tif_spec_ib(struct task_struct *next)
> +static inline unsigned long mm_mangle_tif_spec_bits(struct task_struct *next)
> -static void cond_ibpb(struct task_struct *next)
> +static void cond_mitigation(struct task_struct *next)
> {
> + unsigned long prev_mm, next_mm;
> +
> if (!next || !next->mm)
> return;
can you please split out these preparatory changes into a separate
patch?
Thanks,
tglx
Powered by blists - more mailing lists