Merge branch 'master' into x86/memblock

Conflicts & resolutions:

* arch/x86/xen/setup.c

	dc91c728fd "xen: allow extra memory to be in multiple regions"
	24aa07882b "memblock, x86: Replace memblock_x86_reserve/free..."

	conflicted on xen_add_extra_mem() updates.  The resolution is
	trivial as the latter just want to replace
	memblock_x86_reserve_range() with memblock_reserve().

* drivers/pci/intel-iommu.c

	166e9278a3f "x86/ia64: intel-iommu: move to drivers/iommu/"
	5dfe8660a3d "bootmem: Replace work_with_active_regions() with..."

	conflicted as the former moved the file under drivers/iommu/.
	Resolved by applying the chnages from the latter on the moved
	file.

* mm/Kconfig

	6661672053a "memblock: add NO_BOOTMEM config symbol"
	c378ddd53f9 "memblock, x86: Make ARCH_DISCARD_MEMBLOCK a config option"

	conflicted trivially.  Both added config options.  Just
	letting both add their own options resolves the conflict.

* mm/memblock.c

	d1f0ece6cdc "mm/memblock.c: small function definition fixes"
	ed7b56a799c "memblock: Remove memblock_memory_can_coalesce()"

	confliected.  The former updates function removed by the
	latter.  Resolution is trivial.

Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 57 insertions, 82 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ceb1e4a1a736..6b365aee8396 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -15,6 +15,7 @@
 #include <linux/range.h>
 #include <linux/pfn.h>
 #include <linux/bit_spinlock.h>
+#include <linux/shrinker.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -355,36 +356,50 @@ static inline struct page *compound_head(struct page *page)
 	return page;
 }
 
+/*
+ * The atomic page->_mapcount, starts from -1: so that transitions
+ * both from it and to it can be tracked, using atomic_inc_and_test
+ * and atomic_add_negative(-1).
+ */
+static inline void reset_page_mapcount(struct page *page)
+{
+	atomic_set(&(page)->_mapcount, -1);
+}
+
+static inline int page_mapcount(struct page *page)
+{
+	return atomic_read(&(page)->_mapcount) + 1;
+}
+
 static inline int page_count(struct page *page)
 {
 	return atomic_read(&compound_head(page)->_count);
 }
 
+static inline void get_huge_page_tail(struct page *page)
+{
+	/*
+	 * __split_huge_page_refcount() cannot run
+	 * from under us.
+	 */
+	VM_BUG_ON(page_mapcount(page) < 0);
+	VM_BUG_ON(atomic_read(&page->_count) != 0);
+	atomic_inc(&page->_mapcount);
+}
+
+extern bool __get_page_tail(struct page *page);
+
 static inline void get_page(struct page *page)
 {
+	if (unlikely(PageTail(page)))
+		if (likely(__get_page_tail(page)))
+			return;
 	/*
 	 * Getting a normal page or the head of a compound page
-	 * requires to already have an elevated page->_count. Only if
-	 * we're getting a tail page, the elevated page->_count is
-	 * required only in the head page, so for tail pages the
-	 * bugcheck only verifies that the page->_count isn't
-	 * negative.
+	 * requires to already have an elevated page->_count.
 	 */
-	VM_BUG_ON(atomic_read(&page->_count) < !PageTail(page));
+	VM_BUG_ON(atomic_read(&page->_count) <= 0);
 	atomic_inc(&page->_count);
-	/*
-	 * Getting a tail page will elevate both the head and tail
-	 * page->_count(s).
-	 */
-	if (unlikely(PageTail(page))) {
-		/*
-		 * This is safe only because
-		 * __split_huge_page_refcount can't run under
-		 * get_page().
-		 */
-		VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0);
-		atomic_inc(&page->first_page->_count);
-	}
 }
 
 static inline struct page *virt_to_head_page(const void *x)
@@ -636,7 +651,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 #define SECTIONS_MASK		((1UL << SECTIONS_WIDTH) - 1)
 #define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)
 
-static inline enum zone_type page_zonenum(struct page *page)
+static inline enum zone_type page_zonenum(const struct page *page)
 {
 	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
 }
@@ -664,15 +679,15 @@ static inline int zone_to_nid(struct zone *zone)
 }
 
 #ifdef NODE_NOT_IN_PAGE_FLAGS
-extern int page_to_nid(struct page *page);
+extern int page_to_nid(const struct page *page);
 #else
-static inline int page_to_nid(struct page *page)
+static inline int page_to_nid(const struct page *page)
 {
 	return (page->flags >> NODES_PGSHIFT) & NODES_MASK;
 }
 #endif
 
-static inline struct zone *page_zone(struct page *page)
+static inline struct zone *page_zone(const struct page *page)
 {
 	return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
 }
@@ -684,7 +699,7 @@ static inline void set_page_section(struct page *page, unsigned long section)
 	page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
 }
 
-static inline unsigned long page_to_section(struct page *page)
+static inline unsigned long page_to_section(const struct page *page)
 {
 	return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
 }
@@ -717,7 +732,7 @@ static inline void set_page_links(struct page *page, enum zone_type zone,
  */
 #include <linux/vmstat.h>
 
-static __always_inline void *lowmem_page_address(struct page *page)
+static __always_inline void *lowmem_page_address(const struct page *page)
 {
 	return __va(PFN_PHYS(page_to_pfn(page)));
 }
@@ -736,7 +751,7 @@ static __always_inline void *lowmem_page_address(struct page *page)
 #endif
 
 #if defined(HASHED_PAGE_VIRTUAL)
-void *page_address(struct page *page);
+void *page_address(const struct page *page);
 void set_page_address(struct page *page, void *virtual);
 void page_address_init(void);
 #endif
@@ -803,21 +818,6 @@ static inline pgoff_t page_index(struct page *page)
 }
 
 /*
- * The atomic page->_mapcount, like _count, starts from -1:
- * so that transitions both from it and to it can be tracked,
- * using atomic_inc_and_test and atomic_add_negative(-1).
- */
-static inline void reset_page_mapcount(struct page *page)
-{
-	atomic_set(&(page)->_mapcount, -1);
-}
-
-static inline int page_mapcount(struct page *page)
-{
-	return atomic_read(&(page)->_mapcount) + 1;
-}
-
-/*
  * Return true if this page is mapped into pagetables.
  */
 static inline int page_mapped(struct page *page)
@@ -910,6 +910,8 @@ unsigned long unmap_vmas(struct mmu_gather *tlb,
  * @pte_entry: if set, called for each non-empty PTE (4th-level) entry
  * @pte_hole: if set, called for each hole at all levels
  * @hugetlb_entry: if set, called for each hugetlb entry
+ *		   *Caution*: The caller must hold mmap_sem() if @hugetlb_entry
+ * 			      is used.
  *
  * (see walk_page_range for more details)
  */
@@ -959,6 +961,8 @@ 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);
+extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
+			    unsigned long address, unsigned int fault_flags);
 #else
 static inline int handle_mm_fault(struct mm_struct *mm,
 			struct vm_area_struct *vma, unsigned long address,
@@ -968,6 +972,14 @@ static inline int handle_mm_fault(struct mm_struct *mm,
 	BUG();
 	return VM_FAULT_SIGBUS;
 }
+static inline int fixup_user_fault(struct task_struct *tsk,
+		struct mm_struct *mm, unsigned long address,
+		unsigned int fault_flags)
+{
+	/* should never happen if there's no MMU */
+	BUG();
+	return -EFAULT;
+}
 #endif
 
 extern int make_pages_present(unsigned long addr, unsigned long end);
@@ -1121,44 +1133,6 @@ static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm)
 }
 #endif
 
-/*
- * This struct is used to pass information from page reclaim to the shrinkers.
- * We consolidate the values for easier extention later.
- */
-struct shrink_control {
-	gfp_t gfp_mask;
-
-	/* How many slab objects shrinker() should scan and try to reclaim */
-	unsigned long nr_to_scan;
-};
-
-/*
- * A callback you can register to apply pressure to ageable caches.
- *
- * 'sc' is passed shrink_control which includes a count 'nr_to_scan'
- * and a 'gfpmask'.  It should look through the least-recently-used
- * 'nr_to_scan' entries and attempt to free them up.  It should return
- * the number of objects which remain in the cache.  If it returns -1, it means
- * it cannot do any scanning at this time (eg. there is a risk of deadlock).
- *
- * The 'gfpmask' refers to the allocation we are currently trying to
- * fulfil.
- *
- * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is
- * querying the cache size, so a fastpath for that case is appropriate.
- */
-struct shrinker {
-	int (*shrink)(struct shrinker *, struct shrink_control *sc);
-	int seeks;	/* seeks to recreate an obj */
-
-	/* These are for internal use */
-	struct list_head list;
-	long nr;	/* objs pending delete */
-};
-#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
-extern void register_shrinker(struct shrinker *);
-extern void unregister_shrinker(struct shrinker *);
-
 int vma_wants_writenotify(struct vm_area_struct *vma);
 
 extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
@@ -1377,7 +1351,8 @@ extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
 extern int after_bootmem;
 
-extern void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...);
+extern __printf(3, 4)
+void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...);
 
 extern void setup_per_cpu_pageset(void);
 
@@ -1464,8 +1439,7 @@ extern int do_munmap(struct mm_struct *, unsigned long, size_t);
 
 extern unsigned long do_brk(unsigned long, unsigned long);
 
-/* filemap.c */
-extern unsigned long page_unuse(struct page *);
+/* truncate.c */
 extern void truncate_inode_pages(struct address_space *, loff_t);
 extern void truncate_inode_pages_range(struct address_space *,
 				       loff_t lstart, loff_t lend);
@@ -1652,6 +1626,7 @@ enum mf_flags {
 };
 extern void memory_failure(unsigned long pfn, int trapno);
 extern int __memory_failure(unsigned long pfn, int trapno, int flags);
+extern void memory_failure_queue(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;