Re: [PATCH 2/2] x86, mce, amd: extend mce-inject for support threshold interrupt event injection on AMD platform

[Aravind Gopalakrishnan]

On 11/3/2014 11:05 AM, Aravind Gopalakrishnan wrote:
> There are three ways that have been used to report machine check event.
> And they are MCE, CMCI/Threshold Interrupt, and POLL. On the Intel
> platform, CMCI/Threshold Interrupt and POLL share the same event handler
> - machine_check_poll(). However, on the AMD platform, they have a
> separate event handler. amd_threshold_interrupt() is used for handling
> Threshold Interrupt event. And machine_check_poll() has been used for
> polling other events.
>
> This patch introduces a new flag MCJ_INTERRUPT that will be used to
> separate CMCI/Threshold Interrupt and POLL handler in mce-inject.
>
> Signed-off-by: Chen Yucong <slaoub@xxxxxxxxx <mailto:slaoub@xxxxxxxxx>>
> ---
>  arch/x86/include/asm/mce.h              |    5 +++--
>  arch/x86/kernel/cpu/mcheck/mce-inject.c |   16 ++++++++++++++++
>  arch/x86/kernel/cpu/mcheck/threshold.c  |    1 +
>  3 files changed, 20 insertions(+), 2 deletions(-)


We currently test decoding logic on AMD by performing mce injections 
using edac/mce_amd_inj.c,
So instead of modifying mce-inject just for testing 
amd_threshold_interrupt(),
Why not put it under mce_amd_inj? (It's AMD specific code anyway)


> diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
> index 3a430ad..cf25839 100644
> --- a/arch/x86/include/asm/mce.h
> +++ b/arch/x86/include/asm/mce.h
> @@ -70,8 +70,9 @@
>  #define MCJ_CTX_PROCESS                0x1  /* inject context: process */
>  #define MCJ_CTX_IRQ            0x2  /* inject context: IRQ */
>  #define MCJ_NMI_BROADCAST      0x4  /* do NMI broadcasting */
> -#define MCJ_EXCEPTION          0x8  /* raise as exception */
> -#define MCJ_IRQ_BROADCAST      0x10 /* do IRQ broadcasting */
> +#define MCJ_IRQ_BROADCAST      0x8  /* do IRQ broadcasting */
> +#define MCJ_EXCEPTION          0x10  /* raise as exception */
> +#define MCJ_INTERRUPT          0x20  /* raise as interruption */
>
>  #define MCE_OVERFLOW 0         /* bit 0 in flags means overflow */
>
> diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c 
> b/arch/x86/kernel/cpu/mcheck/mce-inject.c
> index 4cfba43..8428746 100644
> --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
> +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
> @@ -59,6 +59,16 @@ static void raise_poll(struct mce *m)
>         m->finished = 0;
>  }
>
> +static void raise_interrupt(struct mce *m)
> +{
> +       unsigned long flags;
> +
> +       local_irq_save(flags);
> +       mce_threshold_vector();
> +       local_irq_restore(flags);
> +       m->finished = 0;
> +}
> +
>  static void raise_exception(struct mce *m, struct pt_regs *pregs)
>  {
>         struct pt_regs regs;
> @@ -89,6 +99,8 @@ static int mce_raise_notify(unsigned int cmd, struct 
> pt_regs *regs)
>         cpumask_clear_cpu(cpu, mce_inject_cpumask);
>         if (m->inject_flags & MCJ_EXCEPTION)
>                 raise_exception(m, regs);
> +       else if (m->inject_flags & MCJ_INTERRUPT)
> +               raise_interrupt(m);
>         else if (m->status)
>                 raise_poll(m);
>         return NMI_HANDLED;
> @@ -132,6 +144,10 @@ static int raise_local(void)
>                         ret = -EINVAL;
>                 }
>                 printk(KERN_INFO "MCE exception done on CPU %d\n", cpu);
> +       } else if (m->inject_flags & MCJ_INTERRUPT) {
> +               printk(KERN_INFO "Raising threshold interrupt on CPU 
> %d\n", cpu);
> +               raise_interrupt(m);
> +               printk(KERN_INFO "Threshold interrupt done on CPU 
> %d\n", cpu);
>         } else if (m->status) {
>                 printk(KERN_INFO "Starting machine check poll CPU 
> %d\n", cpu);
>                 raise_poll(m);
> diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c 
> b/arch/x86/kernel/cpu/mcheck/threshold.c
> index 7245980..e324bf9 100644
> --- a/arch/x86/kernel/cpu/mcheck/threshold.c
> +++ b/arch/x86/kernel/cpu/mcheck/threshold.c
> @@ -17,6 +17,7 @@ static void default_threshold_interrupt(void)
>  }
>
>  void (*mce_threshold_vector)(void) = default_threshold_interrupt;
> +EXPORT_SYMBOL_GPL(mce_threshold_vector);
>
>  static inline void __smp_threshold_interrupt(void)
>  {
> --
> 1.7.10.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/