Merge branch 'hwpoison' of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6

* 'hwpoison' of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6: (34 commits) HWPOISON: Remove stray phrase in a comment HWPOISON: Try to allocate migration page on the same node HWPOISON: Don't do early filtering if filter is disabled HWPOISON: Add a madvise() injector for soft page offlining HWPOISON: Add soft page offline support HWPOISON: Undefine short-hand macros after use to avoid namespace conflict HWPOISON: Use new shake_page in memory_failure HWPOISON: Use correct name for MADV_HWPOISON in documentation HWPOISON: mention HWPoison in Kconfig entry HWPOISON: Use get_user_page_fast in hwpoison madvise HWPOISON: add an interface to switch off/on all the page filters HWPOISON: add memory cgroup filter memcg: add accessor to mem_cgroup.css memcg: rename and export try_get_mem_cgroup_from_page() HWPOISON: add page flags filter mm: export stable page flags HWPOISON: limit hwpoison injector to known page types HWPOISON: add fs/device filters HWPOISON: return 0 to indicate success reliably HWPOISON: make semantics of IGNORED/DELAYED clear ...
2026-05-01 15:00:59 -07:00 · 2009-12-16 12:36:49 -08:00
parent 61cf693159 f2c03debdf
commit d4220f987c
19 changed files with 923 additions and 127 deletions
@@ -0,0 +1,44 @@
+What:		/sys/devices/system/memory/soft_offline_page
+Date:		Sep 2009
+KernelVersion:	2.6.33
+Contact:	andi@firstfloor.org
+Description:
+		Soft-offline the memory page containing the physical address
+		written into this file. Input is a hex number specifying the
+		physical address of the page. The kernel will then attempt
+		to soft-offline it, by moving the contents elsewhere or
+		dropping it if possible. The kernel will then be placed
+		on the bad page list and never be reused.
+
+		The offlining is done in kernel specific granuality.
+		Normally it's the base page size of the kernel, but
+		this might change.
+
+		The page must be still accessible, not poisoned. The
+		kernel will never kill anything for this, but rather
+		fail the offline.  Return value is the size of the
+		number, or a error when the offlining failed.  Reading
+		the file is not allowed.
+
+What:		/sys/devices/system/memory/hard_offline_page
+Date:		Sep 2009
+KernelVersion:	2.6.33
+Contact:	andi@firstfloor.org
+Description:
+		Hard-offline the memory page containing the physical
+		address written into this file. Input is a hex number
+		specifying the physical address of the page. The
+		kernel will then attempt to hard-offline the page, by
+		trying to drop the page or killing any owner or
+		triggering IO errors if needed.  Note this may kill
+		any processes owning the page. The kernel will avoid
+		to access this page assuming it's poisoned by the
+		hardware.
+
+		The offlining is done in kernel specific granuality.
+		Normally it's the base page size of the kernel, but
+		this might change.
+
+		Return value is the size of the number, or a error when
+		the offlining failed.
+		Reading the file is not allowed.
@@ -92,16 +92,62 @@ PR_MCE_KILL_GET

 Testing:

-madvise(MADV_POISON, ....)
+madvise(MADV_HWPOISON, ....)
 	(as root)
 	Poison a page in the process for testing


 hwpoison-inject module through debugfs
-	/sys/debug/hwpoison/corrupt-pfn

-Inject hwpoison fault at PFN echoed into this file
+/sys/debug/hwpoison/

+corrupt-pfn
+
+Inject hwpoison fault at PFN echoed into this file. This does
+some early filtering to avoid corrupted unintended pages in test suites.
+
+unpoison-pfn
+
+Software-unpoison page at PFN echoed into this file. This
+way a page can be reused again.
+This only works for Linux injected failures, not for real
+memory failures.
+
+Note these injection interfaces are not stable and might change between
+kernel versions
+
+corrupt-filter-dev-major
+corrupt-filter-dev-minor
+
+Only handle memory failures to pages associated with the file system defined
+by block device major/minor.  -1U is the wildcard value.
+This should be only used for testing with artificial injection.
+
+corrupt-filter-memcg
+
+Limit injection to pages owned by memgroup. Specified by inode number
+of the memcg.
+
+Example:
+        mkdir /cgroup/hwpoison
+
+        usemem -m 100 -s 1000 &
+        echo `jobs -p` > /cgroup/hwpoison/tasks
+
+        memcg_ino=$(ls -id /cgroup/hwpoison | cut -f1 -d' ')
+        echo $memcg_ino > /debug/hwpoison/corrupt-filter-memcg
+
+        page-types -p `pidof init`   --hwpoison  # shall do nothing
+        page-types -p `pidof usemem` --hwpoison  # poison its pages
+
+corrupt-filter-flags-mask
+corrupt-filter-flags-value
+
+When specified, only poison pages if ((page_flags & mask) == value).
+This allows stress testing of many kinds of pages. The page_flags
+are the same as in /proc/kpageflags. The flag bits are defined in
+include/linux/kernel-page-flags.h and documented in
+Documentation/vm/pagemap.txt

 Architecture specific MCE injector

@@ -1,11 +1,22 @@
 /*
 * page-types: Tool for querying page flags
 *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; version 2.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should find a copy of v2 of the GNU General Public License somewhere on
+ * your Linux system; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
 * Copyright (C) 2009 Intel corporation
 *
 * Authors: Wu Fengguang <fengguang.wu@intel.com>
- *
- * Released under the General Public License (GPL).
 */

 #define _LARGEFILE64_SOURCE
@@ -2377,6 +2377,15 @@ W:	http://www.kernel.org/pub/linux/kernel/people/fseidel/hdaps/
 S:	Maintained
 F:	drivers/hwmon/hdaps.c

+HWPOISON MEMORY FAILURE HANDLING
+M:	Andi Kleen <andi@firstfloor.org>
+L:	linux-mm@kvack.org
+L:	linux-kernel@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6.git hwpoison
+S:	Maintained
+F:	mm/memory-failure.c
+F:	mm/hwpoison-inject.c
+
 HYPERVISOR VIRTUAL CONSOLE DRIVER
 L:	linuxppc-dev@ozlabs.org
 S:	Odd Fixes
@@ -341,6 +341,64 @@ static inline int memory_probe_init(void)
 }
 #endif

+#ifdef CONFIG_MEMORY_FAILURE
+/*
+ * Support for offlining pages of memory
+ */
+
+/* Soft offline a page */
+static ssize_t
+store_soft_offline_page(struct class *class, const char *buf, size_t count)
+{
+	int ret;
+	u64 pfn;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	if (strict_strtoull(buf, 0, &pfn) < 0)
+		return -EINVAL;
+	pfn >>= PAGE_SHIFT;
+	if (!pfn_valid(pfn))
+		return -ENXIO;
+	ret = soft_offline_page(pfn_to_page(pfn), 0);
+	return ret == 0 ? count : ret;
+}
+
+/* Forcibly offline a page, including killing processes. */
+static ssize_t
+store_hard_offline_page(struct class *class, const char *buf, size_t count)
+{
+	int ret;
+	u64 pfn;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	if (strict_strtoull(buf, 0, &pfn) < 0)
+		return -EINVAL;
+	pfn >>= PAGE_SHIFT;
+	ret = __memory_failure(pfn, 0, 0);
+	return ret ? ret : count;
+}
+
+static CLASS_ATTR(soft_offline_page, 0644, NULL, store_soft_offline_page);
+static CLASS_ATTR(hard_offline_page, 0644, NULL, store_hard_offline_page);
+
+static __init int memory_fail_init(void)
+{
+	int err;
+
+	err = sysfs_create_file(&memory_sysdev_class.kset.kobj,
+				&class_attr_soft_offline_page.attr);
+	if (!err)
+		err = sysfs_create_file(&memory_sysdev_class.kset.kobj,
+				&class_attr_hard_offline_page.attr);
+	return err;
+}
+#else
+static inline int memory_fail_init(void)
+{
+	return 0;
+}
+#endif
+
 /*
 * Note that phys_device is optional.  It is here to allow for
 * differentiation between which *physical* devices each
@@ -471,6 +529,9 @@ int __init memory_dev_init(void)
 	}

 	err = memory_probe_init();
+	if (!ret)
+		ret = err;
+	err = memory_fail_init();
 	if (!ret)
 		ret = err;
 	err = block_size_init();
@@ -8,6 +8,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/hugetlb.h>
+#include <linux/kernel-page-flags.h>
 #include <asm/uaccess.h>
 #include "internal.h"

@@ -71,52 +72,12 @@ static const struct file_operations proc_kpagecount_operations = {
 * physical page flags.
 */

-/* These macros are used to decouple internal flags from exported ones */
-
-#define KPF_LOCKED		0
-#define KPF_ERROR		1
-#define KPF_REFERENCED		2
-#define KPF_UPTODATE		3
-#define KPF_DIRTY		4
-#define KPF_LRU			5
-#define KPF_ACTIVE		6
-#define KPF_SLAB		7
-#define KPF_WRITEBACK		8
-#define KPF_RECLAIM		9
-#define KPF_BUDDY		10
-
-/* 11-20: new additions in 2.6.31 */
-#define KPF_MMAP		11
-#define KPF_ANON		12
-#define KPF_SWAPCACHE		13
-#define KPF_SWAPBACKED		14
-#define KPF_COMPOUND_HEAD	15
-#define KPF_COMPOUND_TAIL	16
-#define KPF_HUGE		17
-#define KPF_UNEVICTABLE		18
-#define KPF_HWPOISON		19
-#define KPF_NOPAGE		20
-
-#define KPF_KSM			21
-
-/* kernel hacking assistances
- * WARNING: subject to change, never rely on them!
- */
-#define KPF_RESERVED		32
-#define KPF_MLOCKED		33
-#define KPF_MAPPEDTODISK	34
-#define KPF_PRIVATE		35
-#define KPF_PRIVATE_2		36
-#define KPF_OWNER_PRIVATE	37
-#define KPF_ARCH		38
-#define KPF_UNCACHED		39
-
 static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit)
 {
 	return ((kflags >> kbit) & 1) << ubit;
 }

-static u64 get_uflags(struct page *page)
+u64 stable_page_flags(struct page *page)
 {
 	u64 k;
 	u64 u;
@@ -219,7 +180,7 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf,
 		else
 			ppage = NULL;

-		if (put_user(get_uflags(ppage), out)) {
+		if (put_user(stable_page_flags(ppage), out)) {
 			ret = -EFAULT;
 			break;
 		}
@@ -40,6 +40,7 @@
 #define MADV_DONTFORK	10		/* don't inherit across fork */
 #define MADV_DOFORK	11		/* do inherit across fork */
 #define MADV_HWPOISON	100		/* poison a page for testing */
+#define MADV_SOFT_OFFLINE 101		/* soft offline page for testing */

 #define MADV_MERGEABLE   12		/* KSM may merge identical pages */
 #define MADV_UNMERGEABLE 13		/* KSM may not merge identical pages */
@@ -0,0 +1,46 @@
+#ifndef LINUX_KERNEL_PAGE_FLAGS_H
+#define LINUX_KERNEL_PAGE_FLAGS_H
+
+/*
+ * Stable page flag bits exported to user space
+ */
+
+#define KPF_LOCKED		0
+#define KPF_ERROR		1
+#define KPF_REFERENCED		2
+#define KPF_UPTODATE		3
+#define KPF_DIRTY		4
+#define KPF_LRU			5
+#define KPF_ACTIVE		6
+#define KPF_SLAB		7
+#define KPF_WRITEBACK		8
+#define KPF_RECLAIM		9
+#define KPF_BUDDY		10
+
+/* 11-20: new additions in 2.6.31 */
+#define KPF_MMAP		11
+#define KPF_ANON		12
+#define KPF_SWAPCACHE		13
+#define KPF_SWAPBACKED		14
+#define KPF_COMPOUND_HEAD	15
+#define KPF_COMPOUND_TAIL	16
+#define KPF_HUGE		17
+#define KPF_UNEVICTABLE		18
+#define KPF_HWPOISON		19
+#define KPF_NOPAGE		20
+
+#define KPF_KSM			21
+
+/* kernel hacking assistances
+ * WARNING: subject to change, never rely on them!
+ */
+#define KPF_RESERVED		32
+#define KPF_MLOCKED		33
+#define KPF_MAPPEDTODISK	34
+#define KPF_PRIVATE		35
+#define KPF_PRIVATE_2		36
+#define KPF_OWNER_PRIVATE	37
+#define KPF_ARCH		38
+#define KPF_UNCACHED		39
+
+#endif /* LINUX_KERNEL_PAGE_FLAGS_H */
@@ -73,6 +73,7 @@ extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask);
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem);

+extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
 extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);

 static inline
@@ -85,6 +86,8 @@ int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup)
 	return cgroup == mem;
 }

+extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *mem);
+
 extern int
 mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr);
 extern void mem_cgroup_end_migration(struct mem_cgroup *mem,
@@ -202,6 +205,11 @@ mem_cgroup_move_lists(struct page *page, enum lru_list from, enum lru_list to)
 {
 }

+static inline struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
+{
+	return NULL;
+}
+
 static inline int mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *mem)
 {
 	return 1;
@@ -213,6 +221,11 @@ static inline int task_in_mem_cgroup(struct task_struct *task,
 	return 1;
 }

+static inline struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *mem)
+{
+	return NULL;
+}
+
 static inline int
 mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr)
 {
@@ -1331,11 +1331,17 @@ extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
 				 size_t size);
 extern void refund_locked_memory(struct mm_struct *mm, size_t size);

+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 ref);
+extern int __memory_failure(unsigned long pfn, int trapno, int flags);
+extern int unpoison_memory(unsigned long pfn);
 extern int sysctl_memory_failure_early_kill;
 extern int sysctl_memory_failure_recovery;
+extern void shake_page(struct page *p, int access);
 extern atomic_long_t mce_bad_pages;
+extern int soft_offline_page(struct page *page, int flags);

 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */
@@ -275,13 +275,15 @@ PAGEFLAG_FALSE(Uncached)

 #ifdef CONFIG_MEMORY_FAILURE
 PAGEFLAG(HWPoison, hwpoison)
-TESTSETFLAG(HWPoison, hwpoison)
+TESTSCFLAG(HWPoison, hwpoison)
 #define __PG_HWPOISON (1UL << PG_hwpoison)
 #else
 PAGEFLAG_FALSE(HWPoison)
 #define __PG_HWPOISON 0
 #endif

+u64 stable_page_flags(struct page *page);
+
 static inline int PageUptodate(struct page *page)
 {
 	int ret = test_bit(PG_uptodate, &(page)->flags);
@@ -251,8 +251,9 @@ config MEMORY_FAILURE
 	  special hardware support and typically ECC memory.

 config HWPOISON_INJECT
-	tristate "Poison pages injector"
+	tristate "HWPoison pages injector"
 	depends on MEMORY_FAILURE && DEBUG_KERNEL
+	select PROC_PAGE_MONITOR

 config NOMMU_INITIAL_TRIM_EXCESS
 	int "Turn on mmap() excess space trimming before booting"
@@ -3,18 +3,68 @@
 #include <linux/debugfs.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/pagemap.h>
+#include "internal.h"

-static struct dentry *hwpoison_dir, *corrupt_pfn;
+static struct dentry *hwpoison_dir;

 static int hwpoison_inject(void *data, u64 val)
 {
+	unsigned long pfn = val;
+	struct page *p;
+	int err;
+
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	printk(KERN_INFO "Injecting memory failure at pfn %Lx\n", val);
-	return __memory_failure(val, 18, 0);
+
+	if (!hwpoison_filter_enable)
+		goto inject;
+	if (!pfn_valid(pfn))
+		return -ENXIO;
+
+	p = pfn_to_page(pfn);
+	/*
+	 * This implies unable to support free buddy pages.
+	 */
+	if (!get_page_unless_zero(p))
+		return 0;
+
+	if (!PageLRU(p))
+		shake_page(p, 0);
+	/*
+	 * This implies unable to support non-LRU pages.
+	 */
+	if (!PageLRU(p))
+		return 0;
+
+	/*
+	 * 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.
+	 */
+	lock_page(p);
+	err = hwpoison_filter(p);
+	unlock_page(p);
+	if (err)
+		return 0;
+
+inject:
+	printk(KERN_INFO "Injecting memory failure at pfn %lx\n", pfn);
+	return __memory_failure(pfn, 18, MF_COUNT_INCREASED);
+}
+
+static int hwpoison_unpoison(void *data, u64 val)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return unpoison_memory(val);
 }

 DEFINE_SIMPLE_ATTRIBUTE(hwpoison_fops, NULL, hwpoison_inject, "%lli\n");
+DEFINE_SIMPLE_ATTRIBUTE(unpoison_fops, NULL, hwpoison_unpoison, "%lli\n");

 static void pfn_inject_exit(void)
 {
@@ -24,16 +74,63 @@ static void pfn_inject_exit(void)

 static int pfn_inject_init(void)
 {
+	struct dentry *dentry;
+
 	hwpoison_dir = debugfs_create_dir("hwpoison", NULL);
 	if (hwpoison_dir == NULL)
 		return -ENOMEM;
-	corrupt_pfn = debugfs_create_file("corrupt-pfn", 0600, hwpoison_dir,
+
+	/*
+	 * Note that the below poison/unpoison interfaces do not involve
+	 * hardware status change, hence do not require hardware support.
+	 * They are mainly for testing hwpoison in software level.
+	 */
+	dentry = debugfs_create_file("corrupt-pfn", 0600, hwpoison_dir,
 					  NULL, &hwpoison_fops);
-	if (corrupt_pfn == NULL) {
-		pfn_inject_exit();
-		return -ENOMEM;
-	}
+	if (!dentry)
+		goto fail;
+
+	dentry = debugfs_create_file("unpoison-pfn", 0600, hwpoison_dir,
+				     NULL, &unpoison_fops);
+	if (!dentry)
+		goto fail;
+
+	dentry = debugfs_create_u32("corrupt-filter-enable", 0600,
+				    hwpoison_dir, &hwpoison_filter_enable);
+	if (!dentry)
+		goto fail;
+
+	dentry = debugfs_create_u32("corrupt-filter-dev-major", 0600,
+				    hwpoison_dir, &hwpoison_filter_dev_major);
+	if (!dentry)
+		goto fail;
+
+	dentry = debugfs_create_u32("corrupt-filter-dev-minor", 0600,
+				    hwpoison_dir, &hwpoison_filter_dev_minor);
+	if (!dentry)
+		goto fail;
+
+	dentry = debugfs_create_u64("corrupt-filter-flags-mask", 0600,
+				    hwpoison_dir, &hwpoison_filter_flags_mask);
+	if (!dentry)
+		goto fail;
+
+	dentry = debugfs_create_u64("corrupt-filter-flags-value", 0600,
+				    hwpoison_dir, &hwpoison_filter_flags_value);
+	if (!dentry)
+		goto fail;
+
+#ifdef	CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+	dentry = debugfs_create_u64("corrupt-filter-memcg", 0600,
+				    hwpoison_dir, &hwpoison_filter_memcg);
+	if (!dentry)
+		goto fail;
+#endif
+
 	return 0;
+fail:
+	pfn_inject_exit();
+	return -ENOMEM;
 }

 module_init(pfn_inject_init);
@@ -50,6 +50,9 @@ extern void putback_lru_page(struct page *page);
 */
 extern void __free_pages_bootmem(struct page *page, unsigned int order);
 extern void prep_compound_page(struct page *page, unsigned long order);
+#ifdef CONFIG_MEMORY_FAILURE
+extern bool is_free_buddy_page(struct page *page);
+#endif


 /*
@@ -247,3 +250,12 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 #define ZONE_RECLAIM_SOME	0
 #define ZONE_RECLAIM_SUCCESS	1
 #endif
+
+extern int hwpoison_filter(struct page *p);
+
+extern u32 hwpoison_filter_dev_major;
+extern u32 hwpoison_filter_dev_minor;
+extern u64 hwpoison_filter_flags_mask;
+extern u64 hwpoison_filter_flags_value;
+extern u64 hwpoison_filter_memcg;
+extern u32 hwpoison_filter_enable;
@@ -9,6 +9,7 @@
 #include <linux/pagemap.h>
 #include <linux/syscalls.h>
 #include <linux/mempolicy.h>
+#include <linux/page-isolation.h>
 #include <linux/hugetlb.h>
 #include <linux/sched.h>
 #include <linux/ksm.h>
@@ -222,7 +223,7 @@ static long madvise_remove(struct vm_area_struct *vma,
 /*
 * Error injection support for memory error handling.
 */
-static int madvise_hwpoison(unsigned long start, unsigned long end)
+static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end)
 {
 	int ret = 0;

@@ -230,15 +231,21 @@ static int madvise_hwpoison(unsigned long start, unsigned long end)
 		return -EPERM;
 	for (; start < end; start += PAGE_SIZE) {
 		struct page *p;
-		int ret = get_user_pages(current, current->mm, start, 1,
-						0, 0, &p, NULL);
+		int ret = get_user_pages_fast(start, 1, 0, &p);
 		if (ret != 1)
 			return ret;
+		if (bhv == MADV_SOFT_OFFLINE) {
+			printk(KERN_INFO "Soft offlining page %lx at %lx\n",
+				page_to_pfn(p), start);
+			ret = soft_offline_page(p, MF_COUNT_INCREASED);
+			if (ret)
+				break;
+			continue;
+		}
 		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, 1);
-		put_page(p);
+		__memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED);
 	}
 	return ret;
 }
@@ -335,8 +342,8 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	size_t len;

 #ifdef CONFIG_MEMORY_FAILURE
-	if (behavior == MADV_HWPOISON)
-		return madvise_hwpoison(start, start+len_in);
+	if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE)
+		return madvise_hwpoison(behavior, start, start+len_in);
 #endif
 	if (!madvise_behavior_valid(behavior))
 		return error;
@@ -283,6 +283,11 @@ mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
 	return &mem->info.nodeinfo[nid]->zoneinfo[zid];
 }

+struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *mem)
+{
+	return &mem->css;
+}
+
 static struct mem_cgroup_per_zone *
 page_cgroup_zoneinfo(struct page_cgroup *pc)
 {
@@ -1536,25 +1541,22 @@ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
 	return container_of(css, struct mem_cgroup, css);
 }

-static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page)
+struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 {
-	struct mem_cgroup *mem;
+	struct mem_cgroup *mem = NULL;
 	struct page_cgroup *pc;
 	unsigned short id;
 	swp_entry_t ent;

 	VM_BUG_ON(!PageLocked(page));

-	if (!PageSwapCache(page))
-		return NULL;
-
 	pc = lookup_page_cgroup(page);
 	lock_page_cgroup(pc);
 	if (PageCgroupUsed(pc)) {
 		mem = pc->mem_cgroup;
 		if (mem && !css_tryget(&mem->css))
 			mem = NULL;
-	} else {
+	} else if (PageSwapCache(page)) {
 		ent.val = page_private(page);
 		id = lookup_swap_cgroup(ent);
 		rcu_read_lock();
@@ -1874,7 +1876,7 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
 	 */
 	if (!PageSwapCache(page))
 		goto charge_cur_mm;
-	mem = try_get_mem_cgroup_from_swapcache(page);
+	mem = try_get_mem_cgroup_from_page(page);
 	if (!mem)
 		goto charge_cur_mm;
 	*ptr = mem;
@@ -2555,6 +2555,10 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		ret = VM_FAULT_MAJOR;
 		count_vm_event(PGMAJFAULT);
 	} else if (PageHWPoison(page)) {
+		/*
+		 * hwpoisoned dirty swapcache pages are kept for killing
+		 * owner processes (which may be unknown at hwpoison time)
+		 */
 		ret = VM_FAULT_HWPOISON;
 		delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
 		goto out_release;
@@ -5091,3 +5091,24 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 	spin_unlock_irqrestore(&zone->lock, flags);
 }
 #endif
+
+#ifdef CONFIG_MEMORY_FAILURE
+bool is_free_buddy_page(struct page *page)
+{
+	struct zone *zone = page_zone(page);
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long flags;
+	int order;
+
+	spin_lock_irqsave(&zone->lock, flags);
+	for (order = 0; order < MAX_ORDER; order++) {
+		struct page *page_head = page - (pfn & ((1 << order) - 1));
+
+		if (PageBuddy(page_head) && page_order(page_head) >= order)
+			break;
+	}
+	spin_unlock_irqrestore(&zone->lock, flags);
+
+	return order < MAX_ORDER;
+}
+#endif