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: (21 commits)
  HWPOISON: Enable error_remove_page on btrfs
  HWPOISON: Add simple debugfs interface to inject hwpoison on arbitary PFNs
  HWPOISON: Add madvise() based injector for hardware poisoned pages v4
  HWPOISON: Enable error_remove_page for NFS
  HWPOISON: Enable .remove_error_page for migration aware file systems
  HWPOISON: The high level memory error handler in the VM v7
  HWPOISON: Add PR_MCE_KILL prctl to control early kill behaviour per process
  HWPOISON: shmem: call set_page_dirty() with locked page
  HWPOISON: Define a new error_remove_page address space op for async truncation
  HWPOISON: Add invalidate_inode_page
  HWPOISON: Refactor truncate to allow direct truncating of page v2
  HWPOISON: check and isolate corrupted free pages v2
  HWPOISON: Handle hardware poisoned pages in try_to_unmap
  HWPOISON: Use bitmask/action code for try_to_unmap behaviour
  HWPOISON: x86: Add VM_FAULT_HWPOISON handling to x86 page fault handler v2
  HWPOISON: Add poison check to page fault handling
  HWPOISON: Add basic support for poisoned pages in fault handler v3
  HWPOISON: Add new SIGBUS error codes for hardware poison signals
  HWPOISON: Add support for poison swap entries v2
  HWPOISON: Export some rmap vma locking to outside world
  ...

include/linux/fs.h

@@ -595,6 +595,7 @@ struct address_space_operations {
 	int (*launder_page) (struct page *);
 	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
 					unsigned long);
+	int (*error_remove_page)(struct address_space *, struct page *);
 };
 
 /*

include/linux/mm.h

@@ -695,11 +695,12 @@ static inline int page_mapped(struct page *page)
 #define VM_FAULT_SIGBUS	0x0002
 #define VM_FAULT_MAJOR	0x0004
 #define VM_FAULT_WRITE	0x0008	/* Special case for get_user_pages */
+#define VM_FAULT_HWPOISON 0x0010	/* Hit poisoned page */
 
 #define VM_FAULT_NOPAGE	0x0100	/* ->fault installed the pte, not return page */
 #define VM_FAULT_LOCKED	0x0200	/* ->fault locked the returned page */
 
-#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS)
+#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON)
 
 /*
  * Can be called by the pagefault handler when it gets a VM_FAULT_OOM.
@@ -794,6 +795,11 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
 extern int vmtruncate(struct inode * inode, loff_t offset);
 extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end);
 
+int truncate_inode_page(struct address_space *mapping, struct page *page);
+int generic_error_remove_page(struct address_space *mapping, struct page *page);
+
+int invalidate_inode_page(struct page *page);
+
 #ifdef CONFIG_MMU
 extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, unsigned int flags);
@@ -1308,5 +1314,12 @@ void vmemmap_populate_print_last(void);
 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);
+
+extern void memory_failure(unsigned long pfn, int trapno);
+extern int __memory_failure(unsigned long pfn, int trapno, int ref);
+extern int sysctl_memory_failure_early_kill;
+extern int sysctl_memory_failure_recovery;
+extern atomic_long_t mce_bad_pages;
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */

include/linux/page-flags.h

@@ -51,6 +51,9 @@
  * PG_buddy is set to indicate that the page is free and in the buddy system
  * (see mm/page_alloc.c).
  *
+ * PG_hwpoison indicates that a page got corrupted in hardware and contains
+ * data with incorrect ECC bits that triggered a machine check. Accessing is
+ * not safe since it may cause another machine check. Don't touch!
  */
 
 /*
@@ -101,6 +104,9 @@ enum pageflags {
 #endif
 #ifdef CONFIG_ARCH_USES_PG_UNCACHED
 	PG_uncached,		/* Page has been mapped as uncached */
+#endif
+#ifdef CONFIG_MEMORY_FAILURE
+	PG_hwpoison,		/* hardware poisoned page. Don't touch */
 #endif
 	__NR_PAGEFLAGS,
 
@@ -269,6 +275,15 @@ PAGEFLAG(Uncached, uncached)
 PAGEFLAG_FALSE(Uncached)
 #endif
 
+#ifdef CONFIG_MEMORY_FAILURE
+PAGEFLAG(HWPoison, hwpoison)
+TESTSETFLAG(HWPoison, hwpoison)
+#define __PG_HWPOISON (1UL << PG_hwpoison)
+#else
+PAGEFLAG_FALSE(HWPoison)
+#define __PG_HWPOISON 0
+#endif
+
 static inline int PageUptodate(struct page *page)
 {
 	int ret = test_bit(PG_uptodate, &(page)->flags);
@@ -393,7 +408,7 @@ static inline void __ClearPageTail(struct page *page)
 	 1 << PG_private | 1 << PG_private_2 | \
 	 1 << PG_buddy	 | 1 << PG_writeback | 1 << PG_reserved | \
 	 1 << PG_slab	 | 1 << PG_swapcache | 1 << PG_active | \
-	 1 << PG_unevictable | __PG_MLOCKED)
+	 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON)
 
 /*
  * Flags checked when a page is prepped for return by the page allocator.

include/linux/prctl.h

@@ -88,4 +88,6 @@
 #define PR_TASK_PERF_EVENTS_DISABLE		31
 #define PR_TASK_PERF_EVENTS_ENABLE		32
 
+#define PR_MCE_KILL	33
+
 #endif /* _LINUX_PRCTL_H */

include/linux/rmap.h

@@ -81,7 +81,19 @@ static inline void page_dup_rmap(struct page *page)
  */
 int page_referenced(struct page *, int is_locked,
 			struct mem_cgroup *cnt, unsigned long *vm_flags);
-int try_to_unmap(struct page *, int ignore_refs);
+enum ttu_flags {
+	TTU_UNMAP = 0,			/* unmap mode */
+	TTU_MIGRATION = 1,		/* migration mode */
+	TTU_MUNLOCK = 2,		/* munlock mode */
+	TTU_ACTION_MASK = 0xff,
+
+	TTU_IGNORE_MLOCK = (1 << 8),	/* ignore mlock */
+	TTU_IGNORE_ACCESS = (1 << 9),	/* don't age */
+	TTU_IGNORE_HWPOISON = (1 << 10),/* corrupted page is recoverable */
+};
+#define TTU_ACTION(x) ((x) & TTU_ACTION_MASK)
+
+int try_to_unmap(struct page *, enum ttu_flags flags);
 
 /*
  * Called from mm/filemap_xip.c to unmap empty zero page
@@ -108,6 +120,13 @@ int page_mkclean(struct page *);
  */
 int try_to_munlock(struct page *);
 
+/*
+ * Called by memory-failure.c to kill processes.
+ */
+struct anon_vma *page_lock_anon_vma(struct page *page);
+void page_unlock_anon_vma(struct anon_vma *anon_vma);
+int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
+
 #else	/* !CONFIG_MMU */
 
 #define anon_vma_init()		do {} while (0)

include/linux/sched.h

@@ -1734,6 +1734,7 @@ extern cputime_t task_gtime(struct task_struct *p);
 #define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
 #define PF_VCPU		0x00000010	/* I'm a virtual CPU */
 #define PF_FORKNOEXEC	0x00000040	/* forked but didn't exec */
+#define PF_MCE_PROCESS  0x00000080      /* process policy on mce errors */
 #define PF_SUPERPRIV	0x00000100	/* used super-user privileges */
 #define PF_DUMPCORE	0x00000200	/* dumped core */
 #define PF_SIGNALED	0x00000400	/* killed by a signal */
@@ -1753,6 +1754,7 @@ extern cputime_t task_gtime(struct task_struct *p);
 #define PF_SPREAD_PAGE	0x01000000	/* Spread page cache over cpuset */
 #define PF_SPREAD_SLAB	0x02000000	/* Spread some slab caches over cpuset */
 #define PF_THREAD_BOUND	0x04000000	/* Thread bound to specific cpu */
+#define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
 #define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
 #define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezeable */

include/linux/swap.h

@@ -34,15 +34,37 @@ static inline int current_is_kswapd(void)
  * the type/offset into the pte as 5/27 as well.
  */
 #define MAX_SWAPFILES_SHIFT	5
-#ifndef CONFIG_MIGRATION
-#define MAX_SWAPFILES		(1 << MAX_SWAPFILES_SHIFT)
+
+/*
+ * Use some of the swap files numbers for other purposes. This
+ * is a convenient way to hook into the VM to trigger special
+ * actions on faults.
+ */
+
+/*
+ * NUMA node memory migration support
+ */
+#ifdef CONFIG_MIGRATION
+#define SWP_MIGRATION_NUM 2
+#define SWP_MIGRATION_READ	(MAX_SWAPFILES + SWP_HWPOISON_NUM)
+#define SWP_MIGRATION_WRITE	(MAX_SWAPFILES + SWP_HWPOISON_NUM + 1)
 #else
-/* Use last two entries for page migration swap entries */
-#define MAX_SWAPFILES		((1 << MAX_SWAPFILES_SHIFT)-2)
-#define SWP_MIGRATION_READ	MAX_SWAPFILES
-#define SWP_MIGRATION_WRITE	(MAX_SWAPFILES + 1)
+#define SWP_MIGRATION_NUM 0
 #endif
 
+/*
+ * Handling of hardware poisoned pages with memory corruption.
+ */
+#ifdef CONFIG_MEMORY_FAILURE
+#define SWP_HWPOISON_NUM 1
+#define SWP_HWPOISON		MAX_SWAPFILES
+#else
+#define SWP_HWPOISON_NUM 0
+#endif
+
+#define MAX_SWAPFILES \
+	((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM)
+
 /*
  * Magic header for a swap area. The first part of the union is
  * what the swap magic looks like for the old (limited to 128MB)

include/linux/swapops.h

@@ -131,3 +131,41 @@ static inline int is_write_migration_entry(swp_entry_t entry)
 
 #endif
 
+#ifdef CONFIG_MEMORY_FAILURE
+/*
+ * Support for hardware poisoned pages
+ */
+static inline swp_entry_t make_hwpoison_entry(struct page *page)
+{
+	BUG_ON(!PageLocked(page));
+	return swp_entry(SWP_HWPOISON, page_to_pfn(page));
+}
+
+static inline int is_hwpoison_entry(swp_entry_t entry)
+{
+	return swp_type(entry) == SWP_HWPOISON;
+}
+#else
+
+static inline swp_entry_t make_hwpoison_entry(struct page *page)
+{
+	return swp_entry(0, 0);
+}
+
+static inline int is_hwpoison_entry(swp_entry_t swp)
+{
+	return 0;
+}
+#endif
+
+#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION)
+static inline int non_swap_entry(swp_entry_t entry)
+{
+	return swp_type(entry) >= MAX_SWAPFILES;
+}
+#else
+static inline int non_swap_entry(swp_entry_t entry)
+{
+	return 0;
+}
+#endif