linux-kernel - Re: [PATCH 04/13] x86/x2apic: Support x2apic self IPI with NMI

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: Windows password security audit tool. GUI, reports in PDF.

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

Message-ID: <Y1AZgWn5V/bTMAg7@a4bf019067fa.jf.intel.com>
Date:   Wed, 19 Oct 2022 08:36:33 -0700
From:   Ashok Raj <ashok.raj@...el.com>
To:     Borislav Petkov <bp@...en8.de>,
        Thomas Gleixner <tglx@...utronix.de>
CC:     Tony Luck <tony.luck@...el.com>,
        Dave Hansen <dave.hansen@...el.com>,
        LKML Mailing List <linux-kernel@...r.kernel.org>,
        X86-kernel <x86@...nel.org>,
        Tom Lendacky <thomas.lendacky@....com>,
        Arjan van de Ven <arjan.van.de.ven@...el.com>,
        Jacob Jun Pan <jacob.jun.pan@...el.com>,
        "Jacob Pan" <jacob.jun.pan@...ux.intel.com>,
        Ashok Raj <ashok.raj@...el.com>
Subject: Re: [PATCH 04/13] x86/x2apic: Support x2apic self IPI with NMI_VECTOR

On Fri, Oct 14, 2022 at 01:09:04PM -0700, Ashok Raj wrote:
> From: Jacob Pan <jacob.jun.pan@...ux.intel.com>
> 
> X2APIC architecture introduced a dedicated register for sending self-IPI.
> Though highly optimized for performance, its semantics limit the delivery
> mode to fixed mode.  NMI vector is not supported, this created an
> inconsistent behavior between X2APIC and others.
> 
> This patch adds support for X2APIC NMI_VECTOR by fall back to the slower
> ICR method.
> 
> Suggested-by: Ashok Raj <ashok.raj@...el.com>
> Signed-off-by: Jacob Pan <jacob.jun.pan@...ux.intel.com>

Forgot to add my sob here.. I;ll fix it in the resend.
> ---
>  arch/x86/kernel/apic/x2apic_phys.c | 6 +++++-
>  1 file changed, 5 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
> index 6bde05a86b4e..5f533b76adf6 100644
> --- a/arch/x86/kernel/apic/x2apic_phys.c
> +++ b/arch/x86/kernel/apic/x2apic_phys.c
> @@ -149,7 +149,11 @@ int x2apic_phys_pkg_id(int initial_apicid, int index_msb)
>  
>  void x2apic_send_IPI_self(int vector)
>  {
> -	apic_write(APIC_SELF_IPI, vector);
> +	if (vector == NMI_VECTOR)
> +		apic->send_IPI_mask(cpumask_of(smp_processor_id()),
> +				    NMI_VECTOR);
> +	else
> +		apic_write(APIC_SELF_IPI, vector);
>  }

Wanted to send this early if people are planning to test

Similar helper is required for legacy xapic as well. The lack of it helped
test the timeout path's :-).. I'll integrated it when i send the next round
with feedback once i have enough. I'll also send this in the next update.

diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 2a6509e8c840..e967c49609ef 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -239,7 +239,11 @@ void default_send_IPI_all(int vector)

 void default_send_IPI_self(int vector)
 {
-       __default_send_IPI_shortcut(APIC_DEST_SELF, vector);
+       if (unlikely(vector == NMI_VECTOR))
+               apic->send_IPI_mask(cpumask_of(smp_processor_id()),
+                                   NMI_VECTOR);
+       else
+               __default_send_IPI_shortcut(APIC_DEST_SELF, vector);
 }

 #ifdef CONFIG_X86_32



>  
>  static struct apic apic_x2apic_phys __ro_after_init = {
> -- 
> 2.34.1
>