[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20251104072306.100738-3-xieyuanbin1@huawei.com>
Date: Tue, 4 Nov 2025 15:23:06 +0800
From: Xie Yuanbin <xieyuanbin1@...wei.com>
To: <david@...hat.com>, <dave.hansen@...el.com>, <bp@...en8.de>,
<tglx@...utronix.de>, <mingo@...hat.com>, <dave.hansen@...ux.intel.com>,
<hpa@...or.com>, <akpm@...ux-foundation.org>, <lorenzo.stoakes@...cle.com>,
<Liam.Howlett@...cle.com>, <vbabka@...e.cz>, <rppt@...nel.org>,
<surenb@...gle.com>, <mhocko@...e.com>, <linmiaohe@...wei.com>,
<nao.horiguchi@...il.com>, <luto@...nel.org>, <peterz@...radead.org>,
<tony.luck@...el.com>
CC: <x86@...nel.org>, <linux-kernel@...r.kernel.org>, <linux-mm@...ck.org>,
<linux-edac@...r.kernel.org>, <will@...nel.org>, <liaohua4@...wei.com>,
<lilinjie8@...wei.com>, Xie Yuanbin <xieyuanbin1@...wei.com>
Subject: [PATCH v2 2/2] mm/memory-failure: remove the selection of RAS
The commit 97f0b13452198290799f ("tracing: add trace event for
memory-failure") introduces the selection of RAS in memory-failure.
This commit is just a tracing feature; in reality, there is no dependency
between memory-failure and RAS. RAS increases the size of the bzImage
image by 8k, which is very valuable for embedded devices.
Move the memory-failure traceing code from ras_event.h to
memory-failure.h and remove the selection of RAS.
Signed-off-by: Xie Yuanbin <xieyuanbin1@...wei.com>
Cc: David Hildenbrand <david@...hat.com>
Cc: Borislav Petkov <bp@...en8.de>
---
include/ras/ras_event.h | 86 ------------------------
include/trace/events/memory-failure.h | 97 +++++++++++++++++++++++++++
mm/Kconfig | 1 -
mm/memory-failure.c | 5 +-
4 files changed, 101 insertions(+), 88 deletions(-)
create mode 100644 include/trace/events/memory-failure.h
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index c8cd0f00c845..1e5e87020eef 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -10,11 +10,10 @@
#include <linux/edac.h>
#include <linux/ktime.h>
#include <linux/pci.h>
#include <linux/aer.h>
#include <linux/cper.h>
-#include <linux/mm.h>
/*
* MCE Extended Error Log trace event
*
* These events are generated when hardware detects a corrected or
@@ -337,94 +336,9 @@ TRACE_EVENT(aer_event,
__entry->tlp_header_valid ?
__print_array(__entry->tlp_header, PCIE_STD_MAX_TLP_HEADERLOG, 4) :
"Not available")
);
#endif /* CONFIG_PCIEAER */
-
-/*
- * memory-failure recovery action result event
- *
- * unsigned long pfn - Page Frame Number of the corrupted page
- * int type - Page types of the corrupted page
- * int result - Result of recovery action
- */
-
-#ifdef CONFIG_MEMORY_FAILURE
-#define MF_ACTION_RESULT \
- EM ( MF_IGNORED, "Ignored" ) \
- EM ( MF_FAILED, "Failed" ) \
- EM ( MF_DELAYED, "Delayed" ) \
- EMe ( MF_RECOVERED, "Recovered" )
-
-#define MF_PAGE_TYPE \
- EM ( MF_MSG_KERNEL, "reserved kernel page" ) \
- EM ( MF_MSG_KERNEL_HIGH_ORDER, "high-order kernel page" ) \
- EM ( MF_MSG_HUGE, "huge page" ) \
- EM ( MF_MSG_FREE_HUGE, "free huge page" ) \
- EM ( MF_MSG_GET_HWPOISON, "get hwpoison page" ) \
- EM ( MF_MSG_UNMAP_FAILED, "unmapping failed page" ) \
- EM ( MF_MSG_DIRTY_SWAPCACHE, "dirty swapcache page" ) \
- EM ( MF_MSG_CLEAN_SWAPCACHE, "clean swapcache page" ) \
- EM ( MF_MSG_DIRTY_MLOCKED_LRU, "dirty mlocked LRU page" ) \
- EM ( MF_MSG_CLEAN_MLOCKED_LRU, "clean mlocked LRU page" ) \
- EM ( MF_MSG_DIRTY_UNEVICTABLE_LRU, "dirty unevictable LRU page" ) \
- EM ( MF_MSG_CLEAN_UNEVICTABLE_LRU, "clean unevictable LRU page" ) \
- EM ( MF_MSG_DIRTY_LRU, "dirty LRU page" ) \
- EM ( MF_MSG_CLEAN_LRU, "clean LRU page" ) \
- EM ( MF_MSG_TRUNCATED_LRU, "already truncated LRU page" ) \
- EM ( MF_MSG_BUDDY, "free buddy page" ) \
- EM ( MF_MSG_DAX, "dax page" ) \
- EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" ) \
- EM ( MF_MSG_ALREADY_POISONED, "already poisoned" ) \
- EMe ( MF_MSG_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 /* CONFIG_MEMORY_FAILURE */
#endif /* _TRACE_HW_EVENT_MC_H */
/* This part must be outside protection */
#include <trace/define_trace.h>
diff --git a/include/trace/events/memory-failure.h b/include/trace/events/memory-failure.h
new file mode 100644
index 000000000000..6c88fb624bd7
--- /dev/null
+++ b/include/trace/events/memory-failure.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM ras
+#define TRACE_INCLUDE_FILE memory-failure
+
+#if !defined(_TRACE_MEMORY_FAILURE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MEMORY_FAILURE_H
+
+#include <linux/tracepoint.h>
+#include <linux/mm.h>
+
+/*
+ * memory-failure recovery action result event
+ *
+ * unsigned long pfn - Page Frame Number of the corrupted page
+ * int type - Page types of the corrupted page
+ * int result - Result of recovery action
+ */
+
+#define MF_ACTION_RESULT \
+ EM ( MF_IGNORED, "Ignored" ) \
+ EM ( MF_FAILED, "Failed" ) \
+ EM ( MF_DELAYED, "Delayed" ) \
+ EMe ( MF_RECOVERED, "Recovered" )
+
+#define MF_PAGE_TYPE \
+ EM ( MF_MSG_KERNEL, "reserved kernel page" ) \
+ EM ( MF_MSG_KERNEL_HIGH_ORDER, "high-order kernel page" ) \
+ EM ( MF_MSG_HUGE, "huge page" ) \
+ EM ( MF_MSG_FREE_HUGE, "free huge page" ) \
+ EM ( MF_MSG_GET_HWPOISON, "get hwpoison page" ) \
+ EM ( MF_MSG_UNMAP_FAILED, "unmapping failed page" ) \
+ EM ( MF_MSG_DIRTY_SWAPCACHE, "dirty swapcache page" ) \
+ EM ( MF_MSG_CLEAN_SWAPCACHE, "clean swapcache page" ) \
+ EM ( MF_MSG_DIRTY_MLOCKED_LRU, "dirty mlocked LRU page" ) \
+ EM ( MF_MSG_CLEAN_MLOCKED_LRU, "clean mlocked LRU page" ) \
+ EM ( MF_MSG_DIRTY_UNEVICTABLE_LRU, "dirty unevictable LRU page" ) \
+ EM ( MF_MSG_CLEAN_UNEVICTABLE_LRU, "clean unevictable LRU page" ) \
+ EM ( MF_MSG_DIRTY_LRU, "dirty LRU page" ) \
+ EM ( MF_MSG_CLEAN_LRU, "clean LRU page" ) \
+ EM ( MF_MSG_TRUNCATED_LRU, "already truncated LRU page" ) \
+ EM ( MF_MSG_BUDDY, "free buddy page" ) \
+ EM ( MF_MSG_DAX, "dax page" ) \
+ EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" ) \
+ EM ( MF_MSG_ALREADY_POISONED, "already poisoned" ) \
+ EMe ( MF_MSG_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_MEMORY_FAILURE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/mm/Kconfig b/mm/Kconfig
index a5a90b169435..c3a8e0ba1ac1 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -738,11 +738,10 @@ config ARCH_SUPPORTS_MEMORY_FAILURE
config MEMORY_FAILURE
depends on MMU
depends on ARCH_SUPPORTS_MEMORY_FAILURE
bool "Enable recovery from hardware memory errors"
- select RAS
help
Enables code to recover from some memory failures on systems
with MCA recovery. This allows a system to continue running
even when some of its memory has uncorrected errors. This requires
special hardware support and typically ECC memory.
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index f698df156bf8..a1fe6d760983 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -58,13 +58,16 @@
#include <linux/kfifo.h>
#include <linux/ratelimit.h>
#include <linux/pagewalk.h>
#include <linux/shmem_fs.h>
#include <linux/sysctl.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/memory-failure.h>
+
#include "swap.h"
#include "internal.h"
-#include "ras/ras_event.h"
#define SOFT_OFFLINE_ENABLED BIT(0)
#define SOFT_OFFLINE_SKIP_HUGETLB BIT(1)
static int sysctl_memory_failure_early_kill __read_mostly;
--
2.51.0
Powered by blists - more mailing lists