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
  ...

Documentation/filesystems/vfs.txt

@@ -536,6 +536,7 @@ struct address_space_operations {
 	/* migrate the contents of a page to the specified target */
 	int (*migratepage) (struct page *, struct page *);
 	int (*launder_page) (struct page *);
+	int (*error_remove_page) (struct mapping *mapping, struct page *page);
 };
 
   writepage: called by the VM to write a dirty page to backing store.
@@ -694,6 +695,12 @@ struct address_space_operations {
   	prevent redirtying the page, it is kept locked during the whole
 	operation.
 
+  error_remove_page: normally set to generic_error_remove_page if truncation
+	is ok for this address space. Used for memory failure handling.
+	Setting this implies you deal with pages going away under you,
+	unless you have them locked or reference counts increased.
+
+
 The File Object
 ===============
 

Documentation/sysctl/vm.txt

@@ -32,6 +32,8 @@ Currently, these files are in /proc/sys/vm:
 - legacy_va_layout
 - lowmem_reserve_ratio
 - max_map_count
+- memory_failure_early_kill
+- memory_failure_recovery
 - min_free_kbytes
 - min_slab_ratio
 - min_unmapped_ratio
@@ -53,7 +55,6 @@ Currently, these files are in /proc/sys/vm:
 - vfs_cache_pressure
 - zone_reclaim_mode
 
-
 ==============================================================
 
 block_dump
@@ -275,6 +276,44 @@ e.g., up to one or two maps per allocation.
 
 The default value is 65536.
 
+=============================================================
+
+memory_failure_early_kill:
+
+Control how to kill processes when uncorrected memory error (typically
+a 2bit error in a memory module) is detected in the background by hardware
+that cannot be handled by the kernel. In some cases (like the page
+still having a valid copy on disk) the kernel will handle the failure
+transparently without affecting any applications. But if there is
+no other uptodate copy of the data it will kill to prevent any data
+corruptions from propagating.
+
+1: Kill all processes that have the corrupted and not reloadable page mapped
+as soon as the corruption is detected.  Note this is not supported
+for a few types of pages, like kernel internally allocated data or
+the swap cache, but works for the majority of user pages.
+
+0: Only unmap the corrupted page from all processes and only kill a process
+who tries to access it.
+
+The kill is done using a catchable SIGBUS with BUS_MCEERR_AO, so processes can
+handle this if they want to.
+
+This is only active on architectures/platforms with advanced machine
+check handling and depends on the hardware capabilities.
+
+Applications can override this setting individually with the PR_MCE_KILL prctl
+
+==============================================================
+
+memory_failure_recovery
+
+Enable memory failure recovery (when supported by the platform)
+
+1: Attempt recovery.
+
+0: Always panic on a memory failure.
+
 ==============================================================
 
 min_free_kbytes:

arch/x86/mm/fault.c

@@ -167,6 +167,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address,
 	info.si_errno	= 0;
 	info.si_code	= si_code;
 	info.si_addr	= (void __user *)address;
+	info.si_addr_lsb = si_code == BUS_MCEERR_AR ? PAGE_SHIFT : 0;
 
 	force_sig_info(si_signo, &info, tsk);
 }
@@ -790,10 +791,12 @@ out_of_memory(struct pt_regs *regs, unsigned long error_code,
 }
 
 static void
-do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address)
+do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
+	  unsigned int fault)
 {
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
+	int code = BUS_ADRERR;
 
 	up_read(&mm->mmap_sem);
 
@@ -809,7 +812,15 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address)
 	tsk->thread.error_code	= error_code;
 	tsk->thread.trap_no	= 14;
 
-	force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
+#ifdef CONFIG_MEMORY_FAILURE
+	if (fault & VM_FAULT_HWPOISON) {
+		printk(KERN_ERR
+	"MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",
+			tsk->comm, tsk->pid, address);
+		code = BUS_MCEERR_AR;
+	}
+#endif
+	force_sig_info_fault(SIGBUS, code, address, tsk);
 }
 
 static noinline void
@@ -819,8 +830,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	if (fault & VM_FAULT_OOM) {
 		out_of_memory(regs, error_code, address);
 	} else {
-		if (fault & VM_FAULT_SIGBUS)
-			do_sigbus(regs, error_code, address);
+		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON))
+			do_sigbus(regs, error_code, address, fault);
 		else
 			BUG();
 	}

fs/btrfs/inode.c

@@ -5269,6 +5269,7 @@ static const struct address_space_operations btrfs_aops = {
 	.invalidatepage = btrfs_invalidatepage,
 	.releasepage	= btrfs_releasepage,
 	.set_page_dirty	= btrfs_set_page_dirty,
+	.error_remove_page = generic_error_remove_page,
 };
 
 static const struct address_space_operations btrfs_symlink_aops = {

fs/ext2/inode.c

@@ -819,6 +819,7 @@ const struct address_space_operations ext2_aops = {
 	.writepages		= ext2_writepages,
 	.migratepage		= buffer_migrate_page,
 	.is_partially_uptodate	= block_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
 };
 
 const struct address_space_operations ext2_aops_xip = {
@@ -837,6 +838,7 @@ const struct address_space_operations ext2_nobh_aops = {
 	.direct_IO		= ext2_direct_IO,
 	.writepages		= ext2_writepages,
 	.migratepage		= buffer_migrate_page,
+	.error_remove_page	= generic_error_remove_page,
 };
 
 /*

fs/ext3/inode.c

@@ -1830,6 +1830,7 @@ static const struct address_space_operations ext3_ordered_aops = {
 	.direct_IO		= ext3_direct_IO,
 	.migratepage		= buffer_migrate_page,
 	.is_partially_uptodate  = block_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
 };
 
 static const struct address_space_operations ext3_writeback_aops = {
@@ -1845,6 +1846,7 @@ static const struct address_space_operations ext3_writeback_aops = {
 	.direct_IO		= ext3_direct_IO,
 	.migratepage		= buffer_migrate_page,
 	.is_partially_uptodate  = block_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
 };
 
 static const struct address_space_operations ext3_journalled_aops = {
@@ -1859,6 +1861,7 @@ static const struct address_space_operations ext3_journalled_aops = {
 	.invalidatepage		= ext3_invalidatepage,
 	.releasepage		= ext3_releasepage,
 	.is_partially_uptodate  = block_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
 };
 
 void ext3_set_aops(struct inode *inode)

fs/ext4/inode.c

@@ -3386,6 +3386,7 @@ static const struct address_space_operations ext4_ordered_aops = {
 	.direct_IO		= ext4_direct_IO,
 	.migratepage		= buffer_migrate_page,
 	.is_partially_uptodate  = block_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
 };
 
 static const struct address_space_operations ext4_writeback_aops = {
@@ -3401,6 +3402,7 @@ static const struct address_space_operations ext4_writeback_aops = {
 	.direct_IO		= ext4_direct_IO,
 	.migratepage		= buffer_migrate_page,
 	.is_partially_uptodate  = block_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
 };
 
 static const struct address_space_operations ext4_journalled_aops = {
@@ -3415,6 +3417,7 @@ static const struct address_space_operations ext4_journalled_aops = {
 	.invalidatepage		= ext4_invalidatepage,
 	.releasepage		= ext4_releasepage,
 	.is_partially_uptodate  = block_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
 };
 
 static const struct address_space_operations ext4_da_aops = {
@@ -3431,6 +3434,7 @@ static const struct address_space_operations ext4_da_aops = {
 	.direct_IO		= ext4_direct_IO,
 	.migratepage		= buffer_migrate_page,
 	.is_partially_uptodate  = block_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
 };
 
 void ext4_set_aops(struct inode *inode)

fs/gfs2/aops.c

@@ -1135,6 +1135,7 @@ static const struct address_space_operations gfs2_writeback_aops = {
 	.direct_IO = gfs2_direct_IO,
 	.migratepage = buffer_migrate_page,
 	.is_partially_uptodate = block_is_partially_uptodate,
+	.error_remove_page = generic_error_remove_page,
 };
 
 static const struct address_space_operations gfs2_ordered_aops = {
@@ -1151,6 +1152,7 @@ static const struct address_space_operations gfs2_ordered_aops = {
 	.direct_IO = gfs2_direct_IO,
 	.migratepage = buffer_migrate_page,
 	.is_partially_uptodate = block_is_partially_uptodate,
+	.error_remove_page = generic_error_remove_page,
 };
 
 static const struct address_space_operations gfs2_jdata_aops = {
@@ -1166,6 +1168,7 @@ static const struct address_space_operations gfs2_jdata_aops = {
 	.invalidatepage = gfs2_invalidatepage,
 	.releasepage = gfs2_releasepage,
 	.is_partially_uptodate = block_is_partially_uptodate,
+	.error_remove_page = generic_error_remove_page,
 };
 
 void gfs2_set_aops(struct inode *inode)

fs/nfs/file.c

@@ -525,6 +525,7 @@ const struct address_space_operations nfs_file_aops = {
 	.direct_IO = nfs_direct_IO,
 	.migratepage = nfs_migrate_page,
 	.launder_page = nfs_launder_page,
+	.error_remove_page = generic_error_remove_page,
 };
 
 /*

fs/ntfs/aops.c

@@ -1550,6 +1550,7 @@ const struct address_space_operations ntfs_aops = {
 	.migratepage	= buffer_migrate_page,	/* Move a page cache page from
 						   one physical page to an
 						   other. */
+	.error_remove_page = generic_error_remove_page,
 };
 
 /**
@@ -1569,6 +1570,7 @@ const struct address_space_operations ntfs_mst_aops = {
 	.migratepage	= buffer_migrate_page,	/* Move a page cache page from
 						   one physical page to an
 						   other. */
+	.error_remove_page = generic_error_remove_page,
 };
 
 #ifdef NTFS_RW

fs/ocfs2/aops.c

@@ -2022,4 +2022,5 @@ const struct address_space_operations ocfs2_aops = {
 	.releasepage		= ocfs2_releasepage,
 	.migratepage		= buffer_migrate_page,
 	.is_partially_uptodate	= block_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
 };

fs/proc/meminfo.c

@@ -97,7 +97,11 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		"Committed_AS:   %8lu kB\n"
 		"VmallocTotal:   %8lu kB\n"
 		"VmallocUsed:    %8lu kB\n"
-		"VmallocChunk:   %8lu kB\n",
+		"VmallocChunk:   %8lu kB\n"
+#ifdef CONFIG_MEMORY_FAILURE
+		"HardwareCorrupted: %8lu kB\n"
+#endif
+		,
 		K(i.totalram),
 		K(i.freeram),
 		K(i.bufferram),
@@ -144,6 +148,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		(unsigned long)VMALLOC_TOTAL >> 10,
 		vmi.used >> 10,
 		vmi.largest_chunk >> 10
+#ifdef CONFIG_MEMORY_FAILURE
+		,atomic_long_read(&mce_bad_pages) << (PAGE_SHIFT - 10)
+#endif
 		);
 
 	hugetlb_report_meminfo(m);

fs/xfs/linux-2.6/xfs_aops.c

@@ -1635,4 +1635,5 @@ const struct address_space_operations xfs_address_space_operations = {
 	.direct_IO		= xfs_vm_direct_IO,
 	.migratepage		= buffer_migrate_page,
 	.is_partially_uptodate  = block_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
 };

include/asm-generic/mman-common.h

@@ -34,6 +34,7 @@
 #define MADV_REMOVE	9		/* remove these pages & resources */
 #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_MERGEABLE   12		/* KSM may merge identical pages */
 #define MADV_UNMERGEABLE 13		/* KSM may not merge identical pages */

include/asm-generic/siginfo.h

@@ -82,6 +82,7 @@ typedef struct siginfo {
 #ifdef __ARCH_SI_TRAPNO
 			int _trapno;	/* TRAP # which caused the signal */
 #endif
+			short _addr_lsb; /* LSB of the reported address */
 		} _sigfault;
 
 		/* SIGPOLL */
@@ -112,6 +113,7 @@ typedef struct siginfo {
 #ifdef __ARCH_SI_TRAPNO
 #define si_trapno	_sifields._sigfault._trapno
 #endif
+#define si_addr_lsb	_sifields._sigfault._addr_lsb
 #define si_band		_sifields._sigpoll._band
 #define si_fd		_sifields._sigpoll._fd
 
@@ -192,7 +194,11 @@ typedef struct siginfo {
 #define BUS_ADRALN	(__SI_FAULT|1)	/* invalid address alignment */
 #define BUS_ADRERR	(__SI_FAULT|2)	/* non-existant physical address */
 #define BUS_OBJERR	(__SI_FAULT|3)	/* object specific hardware error */
-#define NSIGBUS		3
+/* hardware memory error consumed on a machine check: action required */
+#define BUS_MCEERR_AR	(__SI_FAULT|4)
+/* hardware memory error detected in process but not consumed: action optional*/
+#define BUS_MCEERR_AO	(__SI_FAULT|5)
+#define NSIGBUS		5
 
 /*
  * SIGTRAP si_codes

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)