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: (22 commits)
  Add _addr_lsb field to ia64 siginfo
  Fix migration.c compilation on s390
  HWPOISON: Remove retry loop for try_to_unmap
  HWPOISON: Turn addr_valid from bitfield into char
  HWPOISON: Disable DEBUG by default
  HWPOISON: Convert pr_debugs to pr_info
  HWPOISON: Improve comments in memory-failure.c
  x86: HWPOISON: Report correct address granuality for huge hwpoison faults
  Encode huge page size for VM_FAULT_HWPOISON errors
  Fix build error with !CONFIG_MIGRATION
  hugepage: move is_hugepage_on_freelist inside ifdef to avoid warning
  Clean up __page_set_anon_rmap
  HWPOISON, hugetlb: fix unpoison for hugepage
  HWPOISON, hugetlb: soft offlining for hugepage
  HWPOSION, hugetlb: recover from free hugepage error when !MF_COUNT_INCREASED
  hugetlb: move refcounting in hugepage allocation inside hugetlb_lock
  HWPOISON, hugetlb: add free check to dequeue_hwpoison_huge_page()
  hugetlb: hugepage migration core
  hugetlb: redefine hugepage copy functions
  hugetlb: add allocate function for hugepage migration
  ...

arch/ia64/include/asm/siginfo.h

@@ -62,6 +62,7 @@ typedef struct siginfo {
 			int _imm;		/* immediate value for "break" */
 			unsigned int _flags;	/* see below */
 			unsigned long _isr;	/* isr */
+			short _addr_lsb;	/* lsb of faulting address */
 		} _sigfault;
 
 		/* SIGPOLL */

arch/x86/mm/fault.c

@@ -11,6 +11,7 @@
 #include <linux/kprobes.h>		/* __kprobes, ...		*/
 #include <linux/mmiotrace.h>		/* kmmio_handler, ...		*/
 #include <linux/perf_event.h>		/* perf_sw_event		*/
+#include <linux/hugetlb.h>		/* hstate_index_to_shift	*/
 
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
@@ -160,15 +161,20 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
 
 static void
 force_sig_info_fault(int si_signo, int si_code, unsigned long address,
-		     struct task_struct *tsk)
+		     struct task_struct *tsk, int fault)
 {
+	unsigned lsb = 0;
 	siginfo_t info;
 
 	info.si_signo	= si_signo;
 	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;
+	if (fault & VM_FAULT_HWPOISON_LARGE)
+		lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault)); 
+	if (fault & VM_FAULT_HWPOISON)
+		lsb = PAGE_SHIFT;
+	info.si_addr_lsb = lsb;
 
 	force_sig_info(si_signo, &info, tsk);
 }
@@ -722,7 +728,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		tsk->thread.error_code	= error_code | (address >= TASK_SIZE);
 		tsk->thread.trap_no	= 14;
 
-		force_sig_info_fault(SIGSEGV, si_code, address, tsk);
+		force_sig_info_fault(SIGSEGV, si_code, address, tsk, 0);
 
 		return;
 	}
@@ -807,14 +813,14 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 	tsk->thread.trap_no	= 14;
 
 #ifdef CONFIG_MEMORY_FAILURE
-	if (fault & VM_FAULT_HWPOISON) {
+	if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
 		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);
+	force_sig_info_fault(SIGBUS, code, address, tsk, fault);
 }
 
 static noinline void
@@ -824,7 +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|VM_FAULT_HWPOISON))
+		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
+			     VM_FAULT_HWPOISON_LARGE))
 			do_sigbus(regs, error_code, address, fault);
 		else
 			BUG();

fs/hugetlbfs/inode.c

@@ -31,6 +31,7 @@
 #include <linux/statfs.h>
 #include <linux/security.h>
 #include <linux/magic.h>
+#include <linux/migrate.h>
 
 #include <asm/uaccess.h>
 
@@ -573,6 +574,19 @@ static int hugetlbfs_set_page_dirty(struct page *page)
 	return 0;
 }
 
+static int hugetlbfs_migrate_page(struct address_space *mapping,
+				struct page *newpage, struct page *page)
+{
+	int rc;
+
+	rc = migrate_huge_page_move_mapping(mapping, newpage, page);
+	if (rc)
+		return rc;
+	migrate_page_copy(newpage, page);
+
+	return 0;
+}
+
 static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb);
@@ -659,6 +673,7 @@ static const struct address_space_operations hugetlbfs_aops = {
 	.write_begin	= hugetlbfs_write_begin,
 	.write_end	= hugetlbfs_write_end,
 	.set_page_dirty	= hugetlbfs_set_page_dirty,
+	.migratepage    = hugetlbfs_migrate_page,
 };
 
 

fs/signalfd.c

@@ -98,6 +98,16 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
 		err |= __put_user((long) kinfo->si_addr, &uinfo->ssi_addr);
 #ifdef __ARCH_SI_TRAPNO
 		err |= __put_user(kinfo->si_trapno, &uinfo->ssi_trapno);
+#endif
+#ifdef BUS_MCEERR_AO
+		/* 
+		 * Other callers might not initialize the si_lsb field,
+		 * so check explicitly for the right codes here.
+		 */
+		if (kinfo->si_code == BUS_MCEERR_AR ||
+		    kinfo->si_code == BUS_MCEERR_AO)
+			err |= __put_user((short) kinfo->si_addr_lsb,
+					  &uinfo->ssi_addr_lsb);
 #endif
 		break;
 	case __SI_CHLD:

include/linux/hugetlb.h

@@ -43,7 +43,8 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						struct vm_area_struct *vma,
 						int acctflags);
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
-void __isolate_hwpoisoned_huge_page(struct page *page);
+int dequeue_hwpoisoned_huge_page(struct page *page);
+void copy_huge_page(struct page *dst, struct page *src);
 
 extern unsigned long hugepages_treat_as_movable;
 extern const unsigned long hugetlb_zero, hugetlb_infinity;
@@ -101,7 +102,10 @@ static inline void hugetlb_report_meminfo(struct seq_file *m)
 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
 #define hugetlb_fault(mm, vma, addr, flags)	({ BUG(); 0; })
 #define huge_pte_offset(mm, address)	0
-#define __isolate_hwpoisoned_huge_page(page)	0
+#define dequeue_hwpoisoned_huge_page(page)	0
+static inline void copy_huge_page(struct page *dst, struct page *src)
+{
+}
 
 #define hugetlb_change_protection(vma, address, end, newprot)
 
@@ -228,6 +232,8 @@ struct huge_bootmem_page {
 	struct hstate *hstate;
 };
 
+struct page *alloc_huge_page_node(struct hstate *h, int nid);
+
 /* arch callback */
 int __init alloc_bootmem_huge_page(struct hstate *h);
 
@@ -301,8 +307,14 @@ static inline struct hstate *page_hstate(struct page *page)
 	return size_to_hstate(PAGE_SIZE << compound_order(page));
 }
 
+static inline unsigned hstate_index_to_shift(unsigned index)
+{
+	return hstates[index].order + PAGE_SHIFT;
+}
+
 #else
 struct hstate {};
+#define alloc_huge_page_node(h, nid) NULL
 #define alloc_bootmem_huge_page(h) NULL
 #define hstate_file(f) NULL
 #define hstate_vma(v) NULL
@@ -317,6 +329,7 @@ static inline unsigned int pages_per_huge_page(struct hstate *h)
 {
 	return 1;
 }
+#define hstate_index_to_shift(index) 0
 #endif
 
 #endif /* _LINUX_HUGETLB_H */

include/linux/migrate.h

@@ -14,6 +14,8 @@ extern int migrate_page(struct address_space *,
 			struct page *, struct page *);
 extern int migrate_pages(struct list_head *l, new_page_t x,
 			unsigned long private, int offlining);
+extern int migrate_huge_pages(struct list_head *l, new_page_t x,
+			unsigned long private, int offlining);
 
 extern int fail_migrate_page(struct address_space *,
 			struct page *, struct page *);
@@ -23,12 +25,17 @@ extern int migrate_prep_local(void);
 extern int migrate_vmas(struct mm_struct *mm,
 		const nodemask_t *from, const nodemask_t *to,
 		unsigned long flags);
+extern void migrate_page_copy(struct page *newpage, struct page *page);
+extern int migrate_huge_page_move_mapping(struct address_space *mapping,
+				  struct page *newpage, struct page *page);
 #else
 #define PAGE_MIGRATION 0
 
 static inline void putback_lru_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t x,
 		unsigned long private, int offlining) { return -ENOSYS; }
+static inline int migrate_huge_pages(struct list_head *l, new_page_t x,
+		unsigned long private, int offlining) { return -ENOSYS; }
 
 static inline int migrate_prep(void) { return -ENOSYS; }
 static inline int migrate_prep_local(void) { return -ENOSYS; }
@@ -40,6 +47,15 @@ static inline int migrate_vmas(struct mm_struct *mm,
 	return -ENOSYS;
 }
 
+static inline void migrate_page_copy(struct page *newpage,
+				     struct page *page) {}
+
+static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
+				  struct page *newpage, struct page *page)
+{
+	return -ENOSYS;
+}
+
 /* Possible settings for the migrate_page() method in address_operations */
 #define migrate_page NULL
 #define fail_migrate_page NULL

include/linux/mm.h

@@ -718,12 +718,20 @@ 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_HWPOISON 0x0010	/* Hit poisoned small page */
+#define VM_FAULT_HWPOISON_LARGE 0x0020  /* Hit poisoned large page. Index encoded in upper bits */
 
 #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 | VM_FAULT_HWPOISON)
+#define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
+
+#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \
+			 VM_FAULT_HWPOISON_LARGE)
+
+/* Encode hstate index for a hwpoisoned large page */
+#define VM_FAULT_SET_HINDEX(x) ((x) << 12)
+#define VM_FAULT_GET_HINDEX(x) (((x) >> 12) & 0xf)
 
 /*
  * Can be called by the pagefault handler when it gets a VM_FAULT_OOM.

include/linux/signalfd.h

@@ -33,6 +33,7 @@ struct signalfd_siginfo {
 	__u64 ssi_utime;
 	__u64 ssi_stime;
 	__u64 ssi_addr;
+	__u16 ssi_addr_lsb;
 
 	/*
 	 * Pad strcture to 128 bytes. Remember to update the
@@ -43,7 +44,7 @@ struct signalfd_siginfo {
 	 * comes out of a read(2) and we really don't want to have
 	 * a compat on read(2).
 	 */
-	__u8 __pad[48];
+	__u8 __pad[46];
 };
 
 

mm/memory.c

@@ -1450,7 +1450,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 					if (ret & VM_FAULT_OOM)
 						return i ? i : -ENOMEM;
 					if (ret &
-					    (VM_FAULT_HWPOISON|VM_FAULT_SIGBUS))
+					    (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE|
+					     VM_FAULT_SIGBUS))
 						return i ? i : -EFAULT;
 					BUG();
 				}

mm/migrate.c

@@ -32,6 +32,7 @@
 #include <linux/security.h>
 #include <linux/memcontrol.h>
 #include <linux/syscalls.h>
+#include <linux/hugetlb.h>
 #include <linux/gfp.h>
 
 #include "internal.h"
@@ -95,6 +96,12 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 	pte_t *ptep, pte;
  	spinlock_t *ptl;
 
+	if (unlikely(PageHuge(new))) {
+		ptep = huge_pte_offset(mm, addr);
+		if (!ptep)
+			goto out;
+		ptl = &mm->page_table_lock;
+	} else {
 		pgd = pgd_offset(mm, addr);
 		if (!pgd_present(*pgd))
 			goto out;
@@ -115,6 +122,8 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 		}
 
 		ptl = pte_lockptr(mm, pmd);
+	}
+
  	spin_lock(ptl);
 	pte = *ptep;
 	if (!is_swap_pte(pte))
@@ -130,10 +139,19 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 	pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
 	if (is_write_migration_entry(entry))
 		pte = pte_mkwrite(pte);
+#ifdef CONFIG_HUGETLB_PAGE
+	if (PageHuge(new))
+		pte = pte_mkhuge(pte);
+#endif
 	flush_cache_page(vma, addr, pte_pfn(pte));
 	set_pte_at(mm, addr, ptep, pte);
 
+	if (PageHuge(new)) {
 		if (PageAnon(new))
+			hugepage_add_anon_rmap(new, vma, addr);
+		else
+			page_dup_rmap(new);
+	} else if (PageAnon(new))
 		page_add_anon_rmap(new, vma, addr);
 	else
 		page_add_file_rmap(new);
@@ -275,11 +293,59 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	return 0;
 }
 
+/*
+ * The expected number of remaining references is the same as that
+ * of migrate_page_move_mapping().
+ */
+int migrate_huge_page_move_mapping(struct address_space *mapping,
+				   struct page *newpage, struct page *page)
+{
+	int expected_count;
+	void **pslot;
+
+	if (!mapping) {
+		if (page_count(page) != 1)
+			return -EAGAIN;
+		return 0;
+	}
+
+	spin_lock_irq(&mapping->tree_lock);
+
+	pslot = radix_tree_lookup_slot(&mapping->page_tree,
+					page_index(page));
+
+	expected_count = 2 + page_has_private(page);
+	if (page_count(page) != expected_count ||
+	    (struct page *)radix_tree_deref_slot(pslot) != page) {
+		spin_unlock_irq(&mapping->tree_lock);
+		return -EAGAIN;
+	}
+
+	if (!page_freeze_refs(page, expected_count)) {
+		spin_unlock_irq(&mapping->tree_lock);
+		return -EAGAIN;
+	}
+
+	get_page(newpage);
+
+	radix_tree_replace_slot(pslot, newpage);
+
+	page_unfreeze_refs(page, expected_count);
+
+	__put_page(page);
+
+	spin_unlock_irq(&mapping->tree_lock);
+	return 0;
+}
+
 /*
  * Copy the page to its new location
  */
-static void migrate_page_copy(struct page *newpage, struct page *page)
+void migrate_page_copy(struct page *newpage, struct page *page)
 {
+	if (PageHuge(page))
+		copy_huge_page(newpage, page);
+	else
 		copy_highpage(newpage, page);
 
 	if (PageError(page))
@@ -723,6 +789,92 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	return rc;
 }
 
+/*
+ * Counterpart of unmap_and_move_page() for hugepage migration.
+ *
+ * This function doesn't wait the completion of hugepage I/O
+ * because there is no race between I/O and migration for hugepage.
+ * Note that currently hugepage I/O occurs only in direct I/O
+ * where no lock is held and PG_writeback is irrelevant,
+ * and writeback status of all subpages are counted in the reference
+ * count of the head page (i.e. if all subpages of a 2MB hugepage are
+ * under direct I/O, the reference of the head page is 512 and a bit more.)
+ * This means that when we try to migrate hugepage whose subpages are
+ * doing direct I/O, some references remain after try_to_unmap() and
+ * hugepage migration fails without data corruption.
+ *
+ * There is also no race when direct I/O is issued on the page under migration,
+ * because then pte is replaced with migration swap entry and direct I/O code
+ * will wait in the page fault for migration to complete.
+ */
+static int unmap_and_move_huge_page(new_page_t get_new_page,
+				unsigned long private, struct page *hpage,
+				int force, int offlining)
+{
+	int rc = 0;
+	int *result = NULL;
+	struct page *new_hpage = get_new_page(hpage, private, &result);
+	int rcu_locked = 0;
+	struct anon_vma *anon_vma = NULL;
+
+	if (!new_hpage)
+		return -ENOMEM;
+
+	rc = -EAGAIN;
+
+	if (!trylock_page(hpage)) {
+		if (!force)
+			goto out;
+		lock_page(hpage);
+	}
+
+	if (PageAnon(hpage)) {
+		rcu_read_lock();
+		rcu_locked = 1;
+
+		if (page_mapped(hpage)) {
+			anon_vma = page_anon_vma(hpage);
+			atomic_inc(&anon_vma->external_refcount);
+		}
+	}
+
+	try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
+
+	if (!page_mapped(hpage))
+		rc = move_to_new_page(new_hpage, hpage, 1);
+
+	if (rc)
+		remove_migration_ptes(hpage, hpage);
+
+	if (anon_vma && atomic_dec_and_lock(&anon_vma->external_refcount,
+					    &anon_vma->lock)) {
+		int empty = list_empty(&anon_vma->head);
+		spin_unlock(&anon_vma->lock);
+		if (empty)
+			anon_vma_free(anon_vma);
+	}
+
+	if (rcu_locked)
+		rcu_read_unlock();
+out:
+	unlock_page(hpage);
+
+	if (rc != -EAGAIN) {
+		list_del(&hpage->lru);
+		put_page(hpage);
+	}
+
+	put_page(new_hpage);
+
+	if (result) {
+		if (rc)
+			*result = rc;
+		else
+			*result = page_to_nid(new_hpage);
+	}
+	return rc;
+}
+
 /*
  * migrate_pages
  *
@@ -788,6 +940,52 @@ int migrate_pages(struct list_head *from,
 	return nr_failed + retry;
 }
 
+int migrate_huge_pages(struct list_head *from,
+		new_page_t get_new_page, unsigned long private, int offlining)
+{
+	int retry = 1;
+	int nr_failed = 0;
+	int pass = 0;
+	struct page *page;
+	struct page *page2;
+	int rc;
+
+	for (pass = 0; pass < 10 && retry; pass++) {
+		retry = 0;
+
+		list_for_each_entry_safe(page, page2, from, lru) {
+			cond_resched();
+
+			rc = unmap_and_move_huge_page(get_new_page,
+					private, page, pass > 2, offlining);
+
+			switch(rc) {
+			case -ENOMEM:
+				goto out;
+			case -EAGAIN:
+				retry++;
+				break;
+			case 0:
+				break;
+			default:
+				/* Permanent failure */
+				nr_failed++;
+				break;
+			}
+		}
+	}
+	rc = 0;
+out:
+
+	list_for_each_entry_safe(page, page2, from, lru)
+		put_page(page);
+
+	if (rc)
+		return rc;
+
+	return nr_failed + retry;
+}
+
 #ifdef CONFIG_NUMA
 /*
  * Move a list of individual pages

mm/rmap.c

@@ -780,10 +780,10 @@ void page_move_anon_rmap(struct page *page,
 }
 
 /**
- * __page_set_anon_rmap - setup new anonymous rmap
- * @page:	the page to add the mapping to
- * @vma:	the vm area in which the mapping is added
- * @address:	the user virtual address mapped
+ * __page_set_anon_rmap - set up new anonymous rmap
+ * @page:	Page to add to rmap	
+ * @vma:	VM area to add page to.
+ * @address:	User virtual address of the mapping	
  * @exclusive:	the page is exclusively owned by the current process
  */
 static void __page_set_anon_rmap(struct page *page,
@@ -793,25 +793,16 @@ static void __page_set_anon_rmap(struct page *page,
 
 	BUG_ON(!anon_vma);
 
+	if (PageAnon(page))
+		return;
+
 	/*
 	 * If the page isn't exclusively mapped into this vma,
 	 * we must use the _oldest_ possible anon_vma for the
 	 * page mapping!
 	 */
-	if (!exclusive) {
-		if (PageAnon(page))
-			return;
+	if (!exclusive)
 		anon_vma = anon_vma->root;
-	} else {
-		/*
-		 * In this case, swapped-out-but-not-discarded swap-cache
-		 * is remapped. So, no need to update page->mapping here.
-		 * We convice anon_vma poitned by page->mapping is not obsolete
-		 * because vma->anon_vma is necessary to be a family of it.
-		 */
-		if (PageAnon(page))
-			return;
-	}
 
 	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
 	page->mapping = (struct address_space *) anon_vma;