[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <ee8051a64e591cff72846f7fbde0889a7ad1cdee.1323979146.git.tony.luck@intel.com>
Date: Thu, 15 Dec 2011 10:48:12 -0800
From: Tony Luck <tony.luck@...el.com>
To: linux-kernel@...r.kernel.org
Cc: Ingo Molnar <mingo@...e.hu>, Borislav Petkov <bp@...64.org>,
Chen Gong <gong.chen@...ux.intel.com>,
"Huang, Ying" <ying.huang@...el.com>,
Hidetoshi Seto <seto.hidetoshi@...fujitsu.com>
Subject: [PATCH 1/6] HWPOISON: clean up memory_failure() vs. __memory_failure()
There is only one caller of memory_failure(), all other users call
__memory_failure() and pass in the flags argument explicitly. The
lone user of memory_failure() will soon need to pass flags too.
Add flags argument to the callsite in mce.c. Delete the old memory_failure()
function, and then rename __memory_failure() without the leading "__".
Provide clearer message when action optional memory errors are ignored.
Signed-off-by: Tony Luck <tony.luck@...el.com>
---
arch/x86/kernel/cpu/mcheck/mce.c | 12 ++++++---
drivers/base/memory.c | 2 +-
include/linux/mm.h | 3 +-
mm/hwpoison-inject.c | 4 +-
mm/madvise.c | 2 +-
mm/memory-failure.c | 46 +++++++++++++++++--------------------
6 files changed, 34 insertions(+), 35 deletions(-)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 2af127d..1a08ce5 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1046,11 +1046,15 @@ out:
}
EXPORT_SYMBOL_GPL(do_machine_check);
-/* dummy to break dependency. actual code is in mm/memory-failure.c */
-void __attribute__((weak)) memory_failure(unsigned long pfn, int vector)
+#ifndef CONFIG_MEMORY_FAILURE
+int memory_failure(unsigned long pfn, int vector, int flags)
{
- printk(KERN_ERR "Action optional memory failure at %lx ignored\n", pfn);
+ printk(KERN_ERR "Uncorrected memory error in page 0x%lx ignored\n"
+ "Rebuild kernel with CONFIG_MEMORY_FAILURE=y for smarter handling\n", pfn);
+
+ return 0;
}
+#endif
/*
* Called after mce notification in process context. This code
@@ -1068,7 +1072,7 @@ void mce_notify_process(void)
unsigned long pfn;
mce_notify_irq();
while (mce_ring_get(&pfn))
- memory_failure(pfn, MCE_VECTOR);
+ memory_failure(pfn, MCE_VECTOR, 0);
}
static void mce_process_work(struct work_struct *dummy)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 8272d92..9a92444 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -474,7 +474,7 @@ store_hard_offline_page(struct class *class,
if (strict_strtoull(buf, 0, &pfn) < 0)
return -EINVAL;
pfn >>= PAGE_SHIFT;
- ret = __memory_failure(pfn, 0, 0);
+ ret = memory_failure(pfn, 0, 0);
return ret ? ret : count;
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4baadd1..bcc5234 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1607,8 +1607,7 @@ void vmemmap_populate_print_last(void);
enum mf_flags {
MF_COUNT_INCREASED = 1 << 0,
};
-extern void memory_failure(unsigned long pfn, int trapno);
-extern int __memory_failure(unsigned long pfn, int trapno, int flags);
+extern int memory_failure(unsigned long pfn, int trapno, int flags);
extern void memory_failure_queue(unsigned long pfn, int trapno, int flags);
extern int unpoison_memory(unsigned long pfn);
extern int sysctl_memory_failure_early_kill;
diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c
index c7fc7fd..cc448bb 100644
--- a/mm/hwpoison-inject.c
+++ b/mm/hwpoison-inject.c
@@ -45,7 +45,7 @@ static int hwpoison_inject(void *data, u64 val)
* do a racy check with elevated page count, to make sure PG_hwpoison
* will only be set for the targeted owner (or on a free page).
* We temporarily take page lock for try_get_mem_cgroup_from_page().
- * __memory_failure() will redo the check reliably inside page lock.
+ * memory_failure() will redo the check reliably inside page lock.
*/
lock_page(hpage);
err = hwpoison_filter(hpage);
@@ -55,7 +55,7 @@ static int hwpoison_inject(void *data, u64 val)
inject:
printk(KERN_INFO "Injecting memory failure at pfn %lx\n", pfn);
- return __memory_failure(pfn, 18, MF_COUNT_INCREASED);
+ return memory_failure(pfn, 18, MF_COUNT_INCREASED);
}
static int hwpoison_unpoison(void *data, u64 val)
diff --git a/mm/madvise.c b/mm/madvise.c
index 74bf193..f5ab745 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -251,7 +251,7 @@ static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end)
printk(KERN_INFO "Injecting memory failure for page %lx at %lx\n",
page_to_pfn(p), start);
/* Ignore return value for now */
- __memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED);
+ memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED);
}
return ret;
}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 06d3479..ab259bb 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -984,7 +984,25 @@ static void clear_page_hwpoison_huge_page(struct page *hpage)
ClearPageHWPoison(hpage + i);
}
-int __memory_failure(unsigned long pfn, int trapno, int flags)
+/**
+ * memory_failure - Handle memory failure of a page.
+ * @pfn: Page Number of the corrupted page
+ * @trapno: Trap number reported in the signal to user space.
+ * @flags: fine tune action taken
+ *
+ * This function is called by the low level machine check code
+ * of an architecture when it detects hardware memory corruption
+ * of a page. It tries its best to recover, which includes
+ * dropping pages, killing processes etc.
+ *
+ * The function is primarily of use for corruptions that
+ * happen outside the current execution context (e.g. when
+ * detected by a background scrubber)
+ *
+ * Must run in process context (e.g. a work queue) with interrupts
+ * enabled and no spinlocks hold.
+ */
+int memory_failure(unsigned long pfn, int trapno, int flags)
{
struct page_state *ps;
struct page *p;
@@ -1156,29 +1174,7 @@ out:
unlock_page(hpage);
return res;
}
-EXPORT_SYMBOL_GPL(__memory_failure);
-
-/**
- * memory_failure - Handle memory failure of a page.
- * @pfn: Page Number of the corrupted page
- * @trapno: Trap number reported in the signal to user space.
- *
- * This function is called by the low level machine check code
- * of an architecture when it detects hardware memory corruption
- * of a page. It tries its best to recover, which includes
- * dropping pages, killing processes etc.
- *
- * The function is primarily of use for corruptions that
- * happen outside the current execution context (e.g. when
- * detected by a background scrubber)
- *
- * Must run in process context (e.g. a work queue) with interrupts
- * enabled and no spinlocks hold.
- */
-void memory_failure(unsigned long pfn, int trapno)
-{
- __memory_failure(pfn, trapno, 0);
-}
+EXPORT_SYMBOL_GPL(memory_failure);
#define MEMORY_FAILURE_FIFO_ORDER 4
#define MEMORY_FAILURE_FIFO_SIZE (1 << MEMORY_FAILURE_FIFO_ORDER)
@@ -1251,7 +1247,7 @@ static void memory_failure_work_func(struct work_struct *work)
spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
if (!gotten)
break;
- __memory_failure(entry.pfn, entry.trapno, entry.flags);
+ memory_failure(entry.pfn, entry.trapno, entry.flags);
}
}
--
1.7.3.1
--
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/
Powered by blists - more mailing lists