| 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
| ||
|
Message-ID: <5528FA2B.8080400@huawei.com>
Date: Sat, 11 Apr 2015 18:40:43 +0800
From: Xie XiuQi <xiexiuqi@...wei.com>
To: Naoya Horiguchi <n-horiguchi@...jp.nec.com>
CC: "rostedt@...dmis.org" <rostedt@...dmis.org>,
"mingo@...hat.com" <mingo@...hat.com>,
"akpm@...ux-foundation.org" <akpm@...ux-foundation.org>,
"kirill.shutemov@...ux.intel.com" <kirill.shutemov@...ux.intel.com>,
"koct9i@...il.com" <koct9i@...il.com>,
"hpa@...ux.intel.com" <hpa@...ux.intel.com>,
"hannes@...xchg.org" <hannes@...xchg.org>,
"iamjoonsoo.kim@....com" <iamjoonsoo.kim@....com>,
"luto@...capital.net" <luto@...capital.net>,
"nasa4836@...il.com" <nasa4836@...il.com>,
"gong.chen@...ux.intel.com" <gong.chen@...ux.intel.com>,
"bhelgaas@...gle.com" <bhelgaas@...gle.com>,
"bp@...e.de" <bp@...e.de>,
"tony.luck@...el.com" <tony.luck@...el.com>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"linux-mm@...ck.org" <linux-mm@...ck.org>
Subject: Re: [RFC PATCH v3 2/2] tracing: add trace event for memory-failure
On 2015/4/8 9:35, Naoya Horiguchi wrote:
> On Tue, Apr 07, 2015 at 07:05:31PM +0800, Xie XiuQi wrote:
>> RAS user space tools like rasdaemon which base on trace event, could
>> receive mce error event, but no memory recovery result event. So, I
>> want to add this event to make this scenario complete.
>>
>> This patch add a event at ras group for memory-failure.
>>
>> The output like below:
>> # tracer: nop
>> #
>> # entries-in-buffer/entries-written: 2/2 #P:24
>> #
>> # _-----=> irqs-off
>> # / _----=> need-resched
>> # | / _---=> hardirq/softirq
>> # || / _--=> preempt-depth
>> # ||| / delay
>> # TASK-PID CPU# |||| TIMESTAMP FUNCTION
>> # | | | |||| | |
>> mce-inject-13150 [001] .... 277.019359: memory_failure_event: pfn 0x19869: recovery action for free buddy page: Delayed
>>
>>
>> Cc: Tony Luck <tony.luck@...el.com>
>> Cc: Steven Rostedt <rostedt@...dmis.org>
>> Signed-off-by: Xie XiuQi <xiexiuqi@...wei.com>
>> ---
>> include/ras/ras_event.h | 83 +++++++++++++++++++++++++++++++++++++++++++++++++
>> kernel/trace/trace.c | 2 +-
>> mm/memory-failure.c | 2 ++
>> 3 files changed, 86 insertions(+), 1 deletion(-)
>>
>> diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
>> index 79abb9c..52c75f2 100644
>> --- a/include/ras/ras_event.h
>> +++ b/include/ras/ras_event.h
>> @@ -11,6 +11,7 @@
>> #include <linux/pci.h>
>> #include <linux/aer.h>
>> #include <linux/cper.h>
>> +#include <linux/mm.h>
>>
>> /*
>> * MCE Extended Error Log trace event
>> @@ -232,6 +233,88 @@ TRACE_EVENT(aer_event,
>> __print_flags(__entry->status, "|", aer_uncorrectable_errors))
>> );
>>
>> +/*
>> + * memory-failure recovery action result event
>> + *
>> + * unsigned long pfn - Page Number of the corrupted page
>
> Hi XiuQi,
>
> I think "Page Frame Number" is better.
OK, I will
>
> And embracing these definition code with #ifdef CONFIG_MEMORY_FAILURE might
> be helpful if it reduces binary size for !CONFIG_MEMORY_FAILURE build?
Sorry for reply late.
I'll do it at next version.
Thanks,
Xie XiuQi
>
> Thanks,
> Naoya Horiguchi
>
>> + * int type - Page types of the corrupted page
>> + * int result - Result of recovery action
>> + */
>> +
>> +#define MF_ACTION_RESULT \
>> + EM ( MF_IGNORED, "Ignord" ) \
>> + EM ( MF_FAILED, "Failed" ) \
>> + EM ( MF_DELAYED, "Delayed" ) \
>> + EMe ( MF_RECOVERED, "Recovered" )
>> +
>> +#define MF_PAGE_TYPE \
>> + EM ( MF_KERNEL, "reserved kernel page" ) \
>> + EM ( MF_KERNEL_HIGH_ORDER, "high-order kernel page" ) \
>> + EM ( MF_SLAB, "kernel slab page" ) \
>> + EM ( MF_DIFFERENT_COMPOUND, "different compound page after locking" ) \
>> + EM ( MF_POISONED_HUGE, "huge page already hardware poisoned" ) \
>> + EM ( MF_HUGE, "huge page" ) \
>> + EM ( MF_FREE_HUGE, "free huge page" ) \
>> + EM ( MF_UNMAP_FAILED, "unmapping failed page" ) \
>> + EM ( MF_DIRTY_SWAPCACHE, "dirty swapcache page" ) \
>> + EM ( MF_CLEAN_SWAPCACHE, "clean swapcache page" ) \
>> + EM ( MF_DIRTY_MLOCKED_LRU, "dirty mlocked LRU page" ) \
>> + EM ( MF_CLEAN_MLOCKED_LRU, "clean mlocked LRU page" ) \
>> + EM ( MF_DIRTY_UNEVICTABLE_LRU, "dirty unevictable LRU page" ) \
>> + EM ( MF_CLEAN_UNEVICTABLE_LRU, "clean unevictable LRU page" ) \
>> + EM ( MF_DIRTY_LRU, "dirty LRU page" ) \
>> + EM ( MF_CLEAN_LRU, "clean LRU page" ) \
>> + EM ( MF_TRUNCATED_LRU, "already truncated LRU page" ) \
>> + EM ( MF_BUDDY, "free buddy page" ) \
>> + EM ( MF_BUDDY_2ND, "free buddy page (2nd try)" ) \
>> + EMe ( MF_UNKNOWN, "unknown page" )
>> +
>> +/*
>> + * First define the enums in MM_ACTION_RESULT to be exported to userspace
>> + * via TRACE_DEFINE_ENUM().
>> + */
>> +#undef EM
>> +#undef EMe
>> +#define EM(a,b) TRACE_DEFINE_ENUM(a);
>> +#define EMe(a,b) TRACE_DEFINE_ENUM(a);
>> +
>> +MF_ACTION_RESULT
>> +MF_PAGE_TYPE
>> +
>> +/*
>> + * Now redefine the EM() and EMe() macros to map the enums to the strings
>> + * that will be printed in the output.
>> + */
>> +#undef EM
>> +#undef EMe
>> +#define EM(a,b) { a, b },
>> +#define EMe(a,b) { a, b }
>> +
>> +TRACE_EVENT(memory_failure_event,
>> + TP_PROTO(unsigned long pfn,
>> + int type,
>> + int result),
>> +
>> + TP_ARGS(pfn, type, result),
>> +
>> + TP_STRUCT__entry(
>> + __field(unsigned long, pfn)
>> + __field(int, type)
>> + __field(int, result)
>> + ),
>> +
>> + TP_fast_assign(
>> + __entry->pfn = pfn;
>> + __entry->type = type;
>> + __entry->result = result;
>> + ),
>> +
>> + TP_printk("pfn %#lx: recovery action for %s: %s",
>> + __entry->pfn,
>> + __print_symbolic(__entry->type, MF_PAGE_TYPE),
>> + __print_symbolic(__entry->result, MF_ACTION_RESULT)
>> + )
>> +);
>> #endif /* _TRACE_HW_EVENT_MC_H */
>>
>> /* This part must be outside protection */
>> diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
>> index 25334e7..f5e8856 100644
>> --- a/kernel/trace/trace.c
>> +++ b/kernel/trace/trace.c
>> @@ -6776,7 +6776,7 @@ static struct notifier_block trace_module_nb = {
>> };
>> #endif
>>
>> -static __init int tracer_init_debugfs(void)
>> +static __init int tracer_init_tracefs(void)
>> {
>> struct dentry *d_tracer;
>>
>> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
>> index 34e9c65..d118af8 100644
>> --- a/mm/memory-failure.c
>> +++ b/mm/memory-failure.c
>> @@ -850,6 +850,8 @@ static struct page_state {
>> */
>> static void action_result(unsigned long pfn, int type, int result)
>> {
>> + trace_memory_failure_event(pfn, type, result);
>> +
>> pr_err("MCE %#lx: recovery action for %s: %s\n",
>> pfn, action_page_type[type], action_name[result]);
>> }
>> --
>> 1.8.3.1
>> --
> 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/
>
> .
>
--
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/
Powered by blists - more mailing lists