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:   Wed, 13 Oct 2021 11:02:46 -0700
From:   Eric Dumazet <edumazet@...gle.com>
To:     Peter Zijlstra <peterz@...radead.org>
Cc:     Eric Dumazet <eric.dumazet@...il.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        linux-kernel <linux-kernel@...r.kernel.org>,
        Dave Hansen <dave.hansen@...ux.intel.com>,
        Borislav Petkov <bp@...e.de>
Subject: Re: [PATCH] x86/apic: reduce cache line misses in __x2apic_send_IPI_mask()

On Tue, Oct 12, 2021 at 5:46 AM Peter Zijlstra <peterz@...radead.org> wrote:

> I'm really conflicted about this. On the one hand, yes absolutely. On
> the other hand, urgh, code ugly :-)

That was indeed some ugly hack.

I cooked this more generic patch instead, I am currently testing it.
(generic as : we no longer disable hard irqs, regardless of some CONFIG option )

diff --git a/arch/x86/kernel/apic/x2apic_cluster.c
b/arch/x86/kernel/apic/x2apic_cluster.c
index e696e22d0531976f7cba72ed17443592eac72c13..7ad81467ce33349dee1ceaf0cefc8375d60213f6
100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -22,7 +22,10 @@ struct cluster_mask {
  */
 static u32 *x86_cpu_to_logical_apicid __read_mostly;

-static DEFINE_PER_CPU(cpumask_var_t, ipi_mask);
+#define IPI_NEST_MAX 3
+static DEFINE_PER_CPU(cpumask_var_t, ipi_mask[IPI_NEST_MAX]);
+static DEFINE_PER_CPU(int, ipi_nest_level);
+
 static DEFINE_PER_CPU_READ_MOSTLY(struct cluster_mask *, cluster_masks);
 static struct cluster_mask *cluster_hotplug_mask;

@@ -45,14 +48,18 @@ __x2apic_send_IPI_mask(const struct cpumask *mask,
int vector, int apic_dest)
 {
        unsigned int cpu, clustercpu;
        struct cpumask *tmpmsk;
-       unsigned long flags;
+       int nest_level;
        u32 dest;

        /* x2apic MSRs are special and need a special fence: */
        weak_wrmsr_fence();
-       local_irq_save(flags);

-       tmpmsk = this_cpu_cpumask_var_ptr(ipi_mask);
+       preempt_disable();
+       nest_level = this_cpu_inc_return(ipi_nest_level) - 1;
+       if (WARN_ON_ONCE(nest_level >= IPI_NEST_MAX))
+               goto end;
+
+       tmpmsk = this_cpu_cpumask_var_ptr(ipi_mask[nest_level]);
        cpumask_copy(tmpmsk, mask);
        /* If IPI should not be sent to self, clear current CPU */
        if (apic_dest != APIC_DEST_ALLINC)
@@ -74,7 +81,9 @@ __x2apic_send_IPI_mask(const struct cpumask *mask,
int vector, int apic_dest)
                cpumask_andnot(tmpmsk, tmpmsk, &cmsk->mask);
        }

-       local_irq_restore(flags);
+end:
+       this_cpu_dec(ipi_nest_level);
+       preempt_enable();
 }

 static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector)
@@ -153,20 +162,26 @@ static int alloc_clustermask(unsigned int cpu, int node)

 static int x2apic_prepare_cpu(unsigned int cpu)
 {
+       int i;
+
        if (alloc_clustermask(cpu, cpu_to_node(cpu)) < 0)
                return -ENOMEM;
-       if (!zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL))
-               return -ENOMEM;
+       for (i = 0 ; i < IPI_NEST_MAX; i++) {
+               if (!zalloc_cpumask_var(&per_cpu(ipi_mask[i], cpu), GFP_KERNEL))
+                       return -ENOMEM;
+       }
        return 0;
 }

 static int x2apic_dead_cpu(unsigned int dead_cpu)
 {
        struct cluster_mask *cmsk = per_cpu(cluster_masks, dead_cpu);
+       int i;

        if (cmsk)
                cpumask_clear_cpu(dead_cpu, &cmsk->mask);
-       free_cpumask_var(per_cpu(ipi_mask, dead_cpu));
+       for (i = 0; i < IPI_NEST_MAX; i++)
+               free_cpumask_var(per_cpu(ipi_mask[i], dead_cpu));
        return 0;
 }

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ