mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Ilpo Järvinen" <ilpo.jarvinen@linux.intel.com>
To: Tony Luck <tony.luck@intel.com>
Cc: Hans de Goede <hansg@kernel.org>, Borislav Petkov <bp@alien8.de>,
	 Breno Leitao <leitao@debian.org>,
	platform-driver-x86@vger.kernel.org,
	 LKML <linux-kernel@vger.kernel.org>,
	patches@lists.linux.dev,  Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Subject: Re: [PATCH 6/7] platform/x86/intel/bff: Compute unique ID for overflowed filter
Date: Wed, 26 Aug 2026 11:26:37 +0300 (EEST)	[thread overview]
Message-ID: <c62f28a7-25a0-8b74-ae8c-9aca146c8ea9@linux.intel.com> (raw)
In-Reply-To: <20260825181526.13203-7-tony.luck@intel.com>

On Tue, 25 Aug 2026, Tony Luck wrote:

> Each L2 cache instance has its own bitfix filter, but always reports
> errors in machine check bank 3 (on Diamond Rapids).
> 
> Compute a unique bitfix filter instance number based on the CPU that
> logged the error and the machine check bank number.
> 
> Special case for banks associated with the Integrated Memory Hub (IMH).
> Here the "even" numbered CPU modules are associated with IMH0 and the
> "odd" modules with IMH1.
> 
> The unique id will be used to store a time stamp of when the bitfix
> filter overflowed so that frequent overflows can be logged.
> 
> Co-developed-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
> Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
> Signed-off-by: Tony Luck <tony.luck@intel.com>
> ---
>  drivers/platform/x86/intel/bff.c | 74 ++++++++++++++++++++++++++++++++
>  1 file changed, 74 insertions(+)
> 
> diff --git a/drivers/platform/x86/intel/bff.c b/drivers/platform/x86/intel/bff.c
> index 8cc29d11e019..ae9dc0bf2777 100644
> --- a/drivers/platform/x86/intel/bff.c
> +++ b/drivers/platform/x86/intel/bff.c
> @@ -18,13 +18,18 @@
>  #define pr_fmt(fmt) "bff: " fmt
>  
>  #include <linux/bits.h>
> +#include <linux/cacheinfo.h>
> +#include <linux/cleanup.h>
>  #include <linux/cpufeature.h>
> +#include <linux/cpuhplock.h>
>  #include <linux/device-id/x86_cpu.h>
>  #include <linux/errno.h>
>  #include <linux/init.h>
> +#include <linux/limits.h>
>  #include <linux/module.h>
>  #include <linux/notifier.h>
>  #include <linux/printk.h>
> +#include <linux/topology.h>
>  #include <linux/types.h>
>  
>  #include <asm/cpu_device_id.h>
> @@ -34,6 +39,8 @@
>  #include <asm/msr.h>
>  #include <asm/msr-index.h>
>  
> +#define NUM_IMH_PER_SKT		2
> +
>  /* Intel bitfix filter control register defines */
>  #define MSR_MC0_BFF_CTL		0x000006c0
>  #define MSR_MCx_BFF_CTL(x)	(MSR_MC0_BFF_CTL + (x))
> @@ -67,11 +74,78 @@ MODULE_DEVICE_TABLE(x86cpu, bff_cpu_ids);
>  
>  static const enum bff_type *bank_types;
>  
> +/* Diamond Rapids maps APICID[2] to the IMH instance. */
> +static void bff_set_imh_id(struct mce *mce, unsigned long *id)
> +{
> +	int imh_num = (NUM_IMH_PER_SKT * topology_physical_package_id(mce->extcpu)) +
> +		      ((mce->apicid >> 2) & 0x1);

FIELD_GET(), I suggest moving comment where you define the field for that.

> +
> +	*id |= imh_num;
> +}
> +
> +static bool bff_set_cache_id(int cpu, int level, unsigned long *id)
> +{
> +	int cacheid;
> +
> +	guard(cpus_read_lock)();
> +
> +	cacheid = get_cpu_cacheinfo_id(cpu, level);
> +	if (cacheid == -1) {
> +		pr_warn("Could not get L%d cache id for CPU %d\n", level, cpu);
> +		return false;
> +	}
> +
> +	*id |= cacheid;
> +
> +	return true;
> +}
> +
> +#define BFF_ID_BANK_SHIFT	16
> +
> +/*
> + * Cache IDs are only unique within a cache level.
> + * Include the MCA bank number so each BFF-capable hardware
> + * resource has a unique tracking ID.
> + */
> +static unsigned long get_bff_id(struct mce *mce)
> +{
> +	unsigned long id = (unsigned long)mce->bank << BFF_ID_BANK_SHIFT;

FIELD_PREP() ?

> +
> +	switch (bank_types[mce->bank]) {
> +	case BFF_BANK_DCU:
> +	case BFF_BANK_DTLB:
> +		if (!bff_set_cache_id(mce->extcpu, 1, &id))
> +			return ULONG_MAX;
> +		break;
> +
> +	case BFF_BANK_MLC:
> +		if (!bff_set_cache_id(mce->extcpu, 2, &id))
> +			return ULONG_MAX;
> +		break;
> +
> +	case BFF_BANK_CCF:
> +		if (!bff_set_cache_id(mce->extcpu, 3, &id))
> +			return ULONG_MAX;
> +		break;
> +
> +	case BFF_BANK_HSF:
> +	case BFF_BANK_IOCACHE:
> +		bff_set_imh_id(mce, &id);
> +		break;
> +	default:
> +		return ULONG_MAX;
> +	}
> +
> +	return id;
> +}
> +
>  static void handle_bff(struct mce *mce)
>  {
>  	/* The bitfix filter overflowed, get the target CPU to reset it. */
>  	if (wrmsrq_on_cpu(mce->extcpu, MSR_MCx_BFF_CTL(mce->bank), MCI_BFF_RESET))
>  		pr_warn("Failed to reset bitfix filter for CPU %d Bank %d\n", mce->extcpu, mce->bank);
> +
> +	pr_debug("unique_id = 0x%lx\n", get_bff_id(mce));
>  }
>  
>  static int bff_mce_notify(struct notifier_block *nb, unsigned long val, void *data)
> 

-- 
 i.


  reply	other threads:[~2026-08-26  8:26 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-25 18:15 [PATCH 0/7] Intel platform driver to reset bitfix filters Tony Luck
2026-08-25 18:15 ` [PATCH 1/7] cacheinfo: Export get_cpu_cacheinfo_id() for loadable modules Tony Luck
2026-08-25 18:15 ` [PATCH 2/7] x86/mce: Enumeration updates for Intel bitfix filter reset Tony Luck
2026-08-26  8:15   ` Ilpo Järvinen
2026-08-25 18:15 ` [PATCH 3/7] platform/x86/intel/bff: Add stub Intel bitfix filter driver Tony Luck
2026-08-25 18:15 ` [PATCH 4/7] platform/x86/intel/bff: Add Diamond Rapids support Tony Luck
2026-08-26  8:17   ` Ilpo Järvinen
2026-08-26 16:10     ` Luck, Tony
2026-08-25 18:15 ` [PATCH 5/7] platform/x86/intel/bff: Reset bitfix filter when it overflows Tony Luck
2026-08-25 18:15 ` [PATCH 6/7] platform/x86/intel/bff: Compute unique ID for overflowed filter Tony Luck
2026-08-26  8:26   ` Ilpo Järvinen [this message]
2026-08-25 18:15 ` [PATCH 7/7] platform/x86/intel/bff: Report frequent filter resets Tony Luck
2026-08-26  8:39   ` Ilpo Järvinen
2026-08-25 18:28 ` [PATCH 0/7] Intel platform driver to reset bitfix filters Borislav Petkov
2026-08-25 18:55   ` Luck, Tony
2026-08-25 19:23     ` Borislav Petkov

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=c62f28a7-25a0-8b74-ae8c-9aca146c8ea9@linux.intel.com \
    --to=ilpo.jarvinen@linux.intel.com \
    --cc=bp@alien8.de \
    --cc=hansg@kernel.org \
    --cc=leitao@debian.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=patches@lists.linux.dev \
    --cc=platform-driver-x86@vger.kernel.org \
    --cc=qiuxu.zhuo@intel.com \
    --cc=tony.luck@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®