Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Tue, 20 Dec 2022 10:15:41 +0100
From:   Peter Zijlstra <peterz@infradead.org>
To:     Xin Li <xin3.li@intel.com>
Cc:     linux-kernel@vger.kernel.org, x86@kernel.org, kvm@vger.kernel.org,
        tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
        dave.hansen@linux.intel.com, hpa@zytor.com,
        andrew.cooper3@citrix.com, seanjc@google.com, pbonzini@redhat.com,
        ravi.v.shankar@intel.com
Subject: Re: [RFC PATCH 18/32] x86/fred: add a debug fault entry stub for FRED
Message-ID: <Y6F9Pan/gY5Taty1@hirez.programming.kicks-ass.net>
References: <20221220063658.19271-1-xin3.li@intel.com>
 <20221220063658.19271-19-xin3.li@intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20221220063658.19271-19-xin3.li@intel.com>
Precedence: bulk

On Mon, Dec 19, 2022 at 10:36:44PM -0800, Xin Li wrote:

> +static __always_inline void debug_kernel_common(struct pt_regs *regs,
> +						unsigned long dr6)
>  {
> -	/*
> -	 * Disable breakpoints during exception handling; recursive exceptions
> -	 * are exceedingly 'fun'.
> -	 *
> -	 * Since this function is NOKPROBE, and that also applies to
> -	 * HW_BREAKPOINT_X, we can't hit a breakpoint before this (XXX except a
> -	 * HW_BREAKPOINT_W on our stack)
> -	 *
> -	 * Entry text is excluded for HW_BP_X and cpu_entry_area, which
> -	 * includes the entry stack is excluded for everything.
> -	 */
> -	unsigned long dr7 = local_db_save();
> -	irqentry_state_t irq_state = irqentry_nmi_enter(regs);
>  	instrumentation_begin();
>  
>  	/*
> @@ -1062,7 +1050,8 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
>  	 * Catch SYSENTER with TF set and clear DR_STEP. If this hit a
>  	 * watchpoint at the same time then that will still be handled.
>  	 */
> -	if ((dr6 & DR_STEP) && is_sysenter_singlestep(regs))
> +	if (!cpu_feature_enabled(X86_FEATURE_FRED) &&
> +	    (dr6 & DR_STEP) && is_sysenter_singlestep(regs))
>  		dr6 &= ~DR_STEP;
>  
>  	/*
> @@ -1089,8 +1078,28 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
>  		regs->flags &= ~X86_EFLAGS_TF;
>  out:
>  	instrumentation_end();
> -	irqentry_nmi_exit(regs, irq_state);
> +}

Why doesn't the FRED handler get to to use irqentry_nmi_{enter,exit}() ?

> @@ -1179,6 +1188,24 @@ DEFINE_IDTENTRY_DEBUG_USER(exc_debug)
>  {
>  	exc_debug_user(regs, debug_read_clear_dr6());
>  }
> +
> +# ifdef CONFIG_X86_FRED
> +DEFINE_FRED_HANDLER(fred_exc_debug)
> +{
> +	/*
> +	 * The FRED debug information saved onto stack differs from
> +	 * DR6 in both stickiness and polarity; it is exactly what
> +	 * debug_read_clear_dr6() returns.
> +	 */
> +	unsigned long dr6 = fred_event_data(regs);
> +
> +	if (user_mode(regs))
> +		exc_debug_user(regs, dr6);
> +	else
> +		debug_kernel_common(regs, dr6);
> +}
> +# endif /* CONFIG_X86_FRED */