Commit 0ebff32c authored by Xishi Qiu's avatar Xishi Qiu Committed by Linus Torvalds
Browse files

memory-failure: fix an error of mce_bad_pages statistics 



When doing

    $ echo paddr > /sys/devices/system/memory/soft_offline_page

to offline a *free* page, the value of mce_bad_pages will be added, and
the page is set HWPoison flag, but it is still managed by page buddy
alocator.

   $ cat /proc/meminfo | grep HardwareCorrupted

shows the value.

If we offline the same page, the value of mce_bad_pages will be added
*again*, this means the value is incorrect now.  Assume the page is
still free during this short time.

  soft_offline_page()
    get_any_page()
      "else if (is_free_buddy_page(p))" branch return 0
        "goto done";
           "atomic_long_add(1, &mce_bad_pages);"

This patch:

Move poisoned page check at the beginning of the function in order to
fix the error.

Signed-off-by: default avatarXishi Qiu <qiuxishi@huawei.com>
Signed-off-by: default avatarJiang Liu <jiang.liu@huawei.com>
Tested-by: default avatarNaoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 194159fb

mm/memory-failure.c

+17 −21
Original line number Diff line number Diff line
@@ -1419,18 +1419,17 @@ static int soft_offline_huge_page(struct page *page, int flags) 
	unsigned long pfn = page_to_pfn(page);

	struct page *hpage = compound_head(page);



	if (PageHWPoison(hpage)) {

		pr_info("soft offline: %#lx hugepage already poisoned\n", pfn);

		return -EBUSY;

	}



	ret = get_any_page(page, pfn, flags);

	if (ret < 0)

		return ret;

	if (ret == 0)

		goto done;



	if (PageHWPoison(hpage)) {

		put_page(hpage);

		pr_info("soft offline: %#lx hugepage already poisoned\n", pfn);

		return -EBUSY;

	}



	/* Keep page count to indicate a given hugepage is isolated. */

	ret = migrate_huge_page(hpage, new_page, MPOL_MF_MOVE_ALL, false,

				MIGRATE_SYNC);
@@ -1441,12 +1440,11 @@ static int soft_offline_huge_page(struct page *page, int flags) 
		return ret;

	}

done:

	if (!PageHWPoison(hpage))

		atomic_long_add(1 << compound_trans_order(hpage),

				&mce_bad_pages);

	/* keep elevated page count for bad page */

	atomic_long_add(1 << compound_trans_order(hpage), &mce_bad_pages);

	set_page_hwpoison_huge_page(hpage);

	dequeue_hwpoisoned_huge_page(hpage);

	/* keep elevated page count for bad page */



	return ret;

}
@@ -1488,6 +1486,11 @@ int soft_offline_page(struct page *page, int flags) 
		}

	}



	if (PageHWPoison(page)) {

		pr_info("soft offline: %#lx page already poisoned\n", pfn);

		return -EBUSY;

	}



	ret = get_any_page(page, pfn, flags);

	if (ret < 0)

		return ret;
@@ -1519,19 +1522,11 @@ int soft_offline_page(struct page *page, int flags) 
		return -EIO;

	}



	lock_page(page);

	wait_on_page_writeback(page);



	/*

	 * Synchronized using the page lock with memory_failure()

	 */

	if (PageHWPoison(page)) {

		unlock_page(page);

		put_page(page);

		pr_info("soft offline: %#lx page already poisoned\n", pfn);

		return -EBUSY;

	}



	lock_page(page);

	wait_on_page_writeback(page);

	/*

	 * Try to invalidate first. This should work for

	 * non dirty unmapped page cache pages.
@@ -1583,8 +1578,9 @@ int soft_offline_page(struct page *page, int flags) 
		return ret;



done:

	/* keep elevated page count for bad page */

	atomic_long_add(1, &mce_bad_pages);

	SetPageHWPoison(page);

	/* keep elevated page count for bad page */



	return ret;

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE