linux-kernel - Re: [PATCH v2 3/3] x86, x2apic: use multiple cluster members for the irq destination only with the explicit affinity

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]

Date:	Thu, 21 Jun 2012 15:35:40 -0700
From:	Yinghai Lu <yinghai@...nel.org>
To:	Suresh Siddha <suresh.b.siddha@...el.com>
Cc:	Alexander Gordeev <agordeev@...hat.com>,
	Ingo Molnar <mingo@...nel.org>, linux-kernel@...r.kernel.org,
	x86@...nel.org, gorcunov@...nvz.org
Subject: Re: [PATCH v2 3/3] x86, x2apic: use multiple cluster members for the
 irq destination only with the explicit affinity

On Thu, Jun 21, 2012 at 3:02 PM, Suresh Siddha
<suresh.b.siddha@...el.com> wrote:
> During boot or driver load etc, interrupt destination is setup using default
> target cpu's. Later the user (irqbalance etc) or the driver (irq_set_affinity/
> irq_set_affinity_hint) can request the interrupt to be migrated to some
> specific set of cpu's.
>
> In the x2apic cluster routing, for the default scenario use single cpu as the
> interrupt destination and when there is an explicit interrupt affinity
> request, route the interrupt to multiple members of a x2apic cluster
> specified in the cpumask of the migration request.
>
> This will minmize the vector pressure when there are lot of interrupt
> sources and relatively few x2apic clusters (for example a single socket
> server). This will allow the performance critical interrupts to be
> routed to multiple cpu's in the x2apic cluster (irqbalance for example
> uses the cache siblings etc while specifying the interrupt destination) and
> allow non-critical interrupts to be serviced by a single logical cpu.
>
> Signed-off-by: Suresh Siddha <suresh.b.siddha@...el.com>
> ---
>  arch/x86/kernel/apic/x2apic_cluster.c |   21 +++++++++++++++++++--
>  1 files changed, 19 insertions(+), 2 deletions(-)
>
> diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
> index bde78d0..c88baa4 100644
> --- a/arch/x86/kernel/apic/x2apic_cluster.c
> +++ b/arch/x86/kernel/apic/x2apic_cluster.c
> @@ -209,13 +209,30 @@ static int x2apic_cluster_probe(void)
>                return 0;
>  }
>
> +static const struct cpumask *x2apic_cluster_target_cpus(void)
> +{
> +       return cpu_all_mask;
> +}
> +
>  /*
>  * Each x2apic cluster is an allocation domain.
>  */
>  static void cluster_vector_allocation_domain(int cpu, struct cpumask *retmask,
>                                             const struct cpumask *mask)
>  {
> -       cpumask_and(retmask, mask, per_cpu(cpus_in_cluster, cpu));
> +       /*
> +        * To minimize vector pressure, default case of boot, device bringup
> +        * etc will use a single cpu for the interrupt destination.
> +        *
> +        * On explicit migration requests coming from irqbalance etc,
> +        * interrupts will be routed to the x2apic cluster (cluster-id
> +        * derived from the first cpu in the mask) members specified
> +        * in the mask.
> +        */
> +       if (mask == x2apic_cluster_target_cpus())
> +               cpumask_copy(retmask, cpumask_of(cpu));
> +       else
> +               cpumask_and(retmask, mask, per_cpu(cpus_in_cluster, cpu));

great, that remove the startup limitation.

Acked-by: Yinghai Lu <yinghai@...nel.org>

>  }
>
>  static struct apic apic_x2apic_cluster = {
> @@ -229,7 +246,7 @@ static struct apic apic_x2apic_cluster = {
>        .irq_delivery_mode              = dest_LowestPrio,
>        .irq_dest_mode                  = 1, /* logical */
>
> -       .target_cpus                    = online_target_cpus,
> +       .target_cpus                    = x2apic_cluster_target_cpus,
>        .disable_esr                    = 0,
>        .dest_logical                   = APIC_DEST_LOGICAL,
>        .check_apicid_used              = NULL,
> --
> 1.7.6.5
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/