Transparent Hugepage Support #16

@@ -218,7 +218,7 @@ get_futex_key(u32 __user *uaddr, int fsh
 {
 	unsigned long address = (unsigned long)uaddr;
 	struct mm_struct *mm = current->mm;
-	struct page *page;
+	struct page *page, *page_head;
 	int err;
 
 	/*

@@ -250,10 +250,53 @@ again:
 	if (err < 0)
 		return err;
 
-	page = compound_head(page);
-	lock_page(page);
-	if (!page->mapping) {
-		unlock_page(page);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	page_head = page;
+	if (unlikely(PageTail(page))) {
+		put_page(page);
+		/* serialize against __split_huge_page_splitting() */
+		local_irq_disable();
+		if (likely(__get_user_pages_fast(address, 1, 1, &page) == 1)) {
+			page_head = compound_head(page);
+			/*
+			 * page_head is valid pointer but we must pin
+			 * it before taking the PG_lock and/or
+			 * PG_compound_lock. The moment we re-enable
+			 * irqs __split_huge_page_splitting() can
+			 * return and the head page can be freed from
+			 * under us. We can't take the PG_lock and/or
+			 * PG_compound_lock on a page that could be
+			 * freed from under us.
+			 */
+			if (page != page_head)
+				get_page(page_head);
+			local_irq_enable();
+		} else {
+			local_irq_enable();
+			goto again;
+		}
+	}
+#else
+	page_head = compound_head(page);
+	if (page != page_head)
+		get_page(page_head);
+#endif
+
+	lock_page(page_head);
+	if (unlikely(page_head != page)) {
+		compound_lock(page_head);
+		if (unlikely(!PageTail(page))) {
+			compound_unlock(page_head);
+			unlock_page(page_head);
+			put_page(page_head);
+			put_page(page);
+			goto again;
+		}
+	}
+	if (!page_head->mapping) {
+		unlock_page(page_head);
+		if (page_head != page)
+			put_page(page_head);
 		put_page(page);
 		goto again;
 	}

@@ -265,19 +308,25 @@ again:
 	 * it's a read-only handle, it's expected that futexes attach to
 	 * the object not the particular process.
 	 */
-	if (PageAnon(page)) {
+	if (PageAnon(page_head)) {
 		key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
 		key->private.mm = mm;
 		key->private.address = address;
 	} else {
 		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
-		key->shared.inode = page->mapping->host;
-		key->shared.pgoff = page->index;
+		key->shared.inode = page_head->mapping->host;
+		key->shared.pgoff = page_head->index;
 	}
 
 	get_futex_key_refs(key);
 
-	unlock_page(page);
+	unlock_page(page_head);
+	if (page != page_head) {
+		VM_BUG_ON(!PageTail(page));
+		/* releasing compound_lock after page_lock won't matter */
+		compound_unlock(page_head);
+		put_page(page_head);
+	}
 	put_page(page);
 	return 0;
 }

@@ -390,6 +390,19 @@ static inline void set_compound_order(st
 }
 
 /*
+ * Do pte_mkwrite, but only if the vma says VM_WRITE.  We do this when
+ * servicing faults for write access.  In the normal case, do always want
+ * pte_mkwrite.  But get_user_pages can cause write faults for mappings
+ * that do not have writing enabled, when used by access_process_vm.
+ */
+static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_flags & VM_WRITE))
+		pte = pte_mkwrite(pte);
+	return pte;
+}
+
+/*
  * Multiple processes may "see" the same page. E.g. for untouched
  * mappings of /dev/null, all processes see the same page full of
  * zeroes, and text pages of executables and shared libraries have

@@ -2031,19 +2031,6 @@ static inline int pte_unmap_same(struct 
 	return same;
 }
 
-/*
- * Do pte_mkwrite, but only if the vma says VM_WRITE.  We do this when
- * servicing faults for write access.  In the normal case, do always want
- * pte_mkwrite.  But get_user_pages can cause write faults for mappings
- * that do not have writing enabled, when used by access_process_vm.
- */
-static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
-{
-	if (likely(vma->vm_flags & VM_WRITE))
-		pte = pte_mkwrite(pte);
-	return pte;
-}
-
 static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
 {
 	/*

@@ -33,6 +33,7 @@ extern struct list_head pgd_list;
 #else  /* !CONFIG_PARAVIRT */
 #define set_pte(ptep, pte)		native_set_pte(ptep, pte)
 #define set_pte_at(mm, addr, ptep, pte)	native_set_pte_at(mm, addr, ptep, pte)
+#define set_pmd_at(mm, addr, pmdp, pmd)	native_set_pmd_at(mm, addr, pmdp, pmd)
 
 #define set_pte_atomic(ptep, pte)					\
 	native_set_pte_atomic(ptep, pte)

@@ -57,6 +58,8 @@ extern struct list_head pgd_list;
 
 #define pte_update(mm, addr, ptep)              do { } while (0)
 #define pte_update_defer(mm, addr, ptep)        do { } while (0)
+#define pmd_update(mm, addr, ptep)              do { } while (0)
+#define pmd_update_defer(mm, addr, ptep)        do { } while (0)
 
 #define pgd_val(x)	native_pgd_val(x)
 #define __pgd(x)	native_make_pgd(x)

@@ -36,10 +36,11 @@ static inline pgprot_t pgprot_modify(pgp
 }
 #endif
 
-static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
+static void change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
 		int dirty_accountable)
 {
+	struct mm_struct *mm = vma->vm_mm;
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;
 

@@ -79,7 +80,7 @@ static void change_pte_range(struct mm_s
 	pte_unmap_unlock(pte - 1, ptl);
 }
 
-static inline void change_pmd_range(struct mm_struct *mm, pud_t *pud,
+static inline void change_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
 		int dirty_accountable)
 {

@@ -89,14 +90,14 @@ static inline void change_pmd_range(stru
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
-		split_huge_page_pmd(mm, pmd);
+		split_huge_page_pmd(vma->vm_mm, pmd);
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		change_pte_range(mm, pmd, addr, next, newprot, dirty_accountable);
+		change_pte_range(vma, pmd, addr, next, newprot, dirty_accountable);
 	} while (pmd++, addr = next, addr != end);
 }
 
-static inline void change_pud_range(struct mm_struct *mm, pgd_t *pgd,
+static inline void change_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
 		int dirty_accountable)
 {

@@ -108,7 +109,7 @@ static inline void change_pud_range(stru
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
 			continue;
-		change_pmd_range(mm, pud, addr, next, newprot, dirty_accountable);
+		change_pmd_range(vma, pud, addr, next, newprot, dirty_accountable);
 	} while (pud++, addr = next, addr != end);
 }
 

@@ -128,7 +129,7 @@ static void change_protection(struct vm_
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		change_pud_range(mm, pgd, addr, next, newprot, dirty_accountable);
+		change_pud_range(vma, pgd, addr, next, newprot, dirty_accountable);
 	} while (pgd++, addr = next, addr != end);
 	flush_tlb_range(vma, start, end);
 }

@@ -349,7 +349,7 @@ static inline void set_page_writeback(st
  * tests can be used in performance sensitive paths. PageCompound is
  * generally not used in hot code paths.
  */
-__PAGEFLAG(Head, head)
+__PAGEFLAG(Head, head) CLEARPAGEFLAG(Head, head)
 __PAGEFLAG(Tail, tail)
 
 static inline int PageCompound(struct page *page)

@@ -357,6 +357,13 @@ static inline int PageCompound(struct pa
 	return page->flags & ((1L << PG_head) | (1L << PG_tail));
 
 }
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline void ClearPageCompound(struct page *page)
+{
+	BUG_ON(!PageHead(page));
+	ClearPageHead(page);
+}
+#endif
 #else
 /*
  * Reduce page flag use as much as possible by overlapping

@@ -394,6 +401,14 @@ static inline void __ClearPageTail(struc
 	page->flags &= ~PG_head_tail_mask;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline void ClearPageCompound(struct page *page)
+{
+	BUG_ON((page->flags & PG_head_tail_mask) != (1 << PG_compound));
+	clear_bit(PG_compound, &page->flags);
+}
+#endif
+
 #endif /* !PAGEFLAGS_EXTENDED */
 
 #ifdef CONFIG_MMU

@@ -1067,7 +1067,8 @@ static inline int __pmd_alloc(struct mm_
 int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
 #endif
 
-int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address);
+int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+		pmd_t *pmd, unsigned long address);
 int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);
 
 /*

@@ -1136,12 +1137,14 @@ static inline void pgtable_page_dtor(str
 	pte_unmap(pte);					\
 } while (0)
 
-#define pte_alloc_map(mm, pmd, address)			\
-	((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \
-		NULL: pte_offset_map(pmd, address))
+#define pte_alloc_map(mm, vma, pmd, address)				\
+	((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, vma,	\
+							pmd, address))?	\
+	 NULL: pte_offset_map(pmd, address))
 
 #define pte_alloc_map_lock(mm, pmd, address, ptlp)	\
-	((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \
+	((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, NULL,	\
+							pmd, address))?	\
 		NULL: pte_offset_map_lock(mm, pmd, address, ptlp))
 
 #define pte_alloc_kernel(pmd, address)			\

@@ -396,9 +396,11 @@ void free_pgtables(struct mmu_gather *tl
 	}
 }
 
-int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
+int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+		pmd_t *pmd, unsigned long address)
 {
 	pgtable_t new = pte_alloc_one(mm, address);
+	int wait_split_huge_page;
 	if (!new)
 		return -ENOMEM;
 

@@ -418,14 +420,18 @@ int __pte_alloc(struct mm_struct *mm, pm
 	smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
 
 	spin_lock(&mm->page_table_lock);
-	if (!pmd_present(*pmd)) {	/* Has another populated it ? */
+	wait_split_huge_page = 0;
+	if (likely(pmd_none(*pmd))) {	/* Has another populated it ? */
 		mm->nr_ptes++;
 		pmd_populate(mm, pmd, new);
 		new = NULL;
-	}
+	} else if (unlikely(pmd_trans_splitting(*pmd)))
+		wait_split_huge_page = 1;
 	spin_unlock(&mm->page_table_lock);
 	if (new)
 		pte_free(mm, new);
+	if (wait_split_huge_page)
+		wait_split_huge_page(vma->anon_vma, pmd);
 	return 0;
 }
 

@@ -438,10 +444,11 @@ int __pte_alloc_kernel(pmd_t *pmd, unsig
 	smp_wmb(); /* See comment in __pte_alloc */
 
 	spin_lock(&init_mm.page_table_lock);
-	if (!pmd_present(*pmd)) {	/* Has another populated it ? */
+	if (likely(pmd_none(*pmd))) {	/* Has another populated it ? */
 		pmd_populate_kernel(&init_mm, pmd, new);
 		new = NULL;
-	}
+	} else
+		VM_BUG_ON(pmd_trans_splitting(*pmd));
 	spin_unlock(&init_mm.page_table_lock);
 	if (new)
 		pte_free_kernel(&init_mm, new);

@@ -3119,7 +3126,7 @@ int handle_mm_fault(struct mm_struct *mm
 	pmd = pmd_alloc(mm, pud, address);
 	if (!pmd)
 		return VM_FAULT_OOM;
-	pte = pte_alloc_map(mm, pmd, address);
+	pte = pte_alloc_map(mm, vma, pmd, address);
 	if (!pte)
 		return VM_FAULT_OOM;
 

@@ -48,7 +48,8 @@ static pmd_t *get_old_pmd(struct mm_stru
 	return pmd;
 }
 
-static pmd_t *alloc_new_pmd(struct mm_struct *mm, unsigned long addr)
+static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
+			    unsigned long addr)
 {
 	pgd_t *pgd;
 	pud_t *pud;

@@ -63,7 +64,7 @@ static pmd_t *alloc_new_pmd(struct mm_st
 	if (!pmd)
 		return NULL;
 
-	if (!pmd_present(*pmd) && __pte_alloc(mm, pmd, addr))
+	if (!pmd_present(*pmd) && __pte_alloc(mm, vma, pmd, addr))
 		return NULL;
 
 	return pmd;

@@ -148,7 +149,7 @@ unsigned long move_page_tables(struct vm
 		old_pmd = get_old_pmd(vma->vm_mm, old_addr);
 		if (!old_pmd)
 			continue;
-		new_pmd = alloc_new_pmd(vma->vm_mm, new_addr);
+		new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr);
 		if (!new_pmd)
 			break;
 		next = (new_addr + PMD_SIZE) & PMD_MASK;

@@ -5291,7 +5291,7 @@ void dump_page(struct page *page)
 {
 	printk(KERN_ALERT
 	       "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
-		page, page_count(page), page_mapcount(page),
+		page, atomic_read(&page->_count), page_mapcount(page),
 		page->mapping, page->index);
 	dump_page_flags(page->flags);
 }

@@ -179,6 +179,7 @@ static void mark_screen_rdonly(struct mm
 	if (pud_none_or_clear_bad(pud))
 		goto out;
 	pmd = pmd_offset(pud, 0xA0000);
+	split_huge_page_pmd(mm, pmd);
 	if (pmd_none_or_clear_bad(pmd))
 		goto out;
 	pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl);

@@ -443,6 +443,7 @@ static inline int check_pmd_range(struct
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
+		split_huge_page_pmd(vma->vm_mm, pmd);
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
 		if (check_pte_range(vma, pmd, addr, next, nodes,

@@ -154,6 +154,7 @@ static void mincore_pmd_range(struct vm_
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
+		split_huge_page_pmd(vma->vm_mm, pmd);
 		if (pmd_none_or_clear_bad(pmd))
 			mincore_unmapped_range(vma, addr, next, vec);
 		else

@@ -89,6 +89,7 @@ static inline void change_pmd_range(stru
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
+		split_huge_page_pmd(mm, pmd);
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
 		change_pte_range(mm, pmd, addr, next, newprot, dirty_accountable);

@@ -42,6 +42,7 @@ static pmd_t *get_old_pmd(struct mm_stru
 		return NULL;
 
 	pmd = pmd_offset(pud, addr);
+	split_huge_page_pmd(mm, pmd);
 	if (pmd_none_or_clear_bad(pmd))
 		return NULL;
 

@@ -34,6 +34,7 @@ static int walk_pmd_range(pud_t *pud, un
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
+		split_huge_page_pmd(walk->mm, pmd);
 		if (pmd_none_or_clear_bad(pmd)) {
 			if (walk->pte_hole)
 				err = walk->pte_hole(addr, next, walk);

@@ -528,6 +528,12 @@ static inline void native_set_pte_at(str
 	native_set_pte(ptep, pte);
 }
 
+static inline void native_set_pmd_at(struct mm_struct *mm, unsigned long addr,
+				     pmd_t *pmdp , pmd_t pmd)
+{
+	native_set_pmd(pmdp, pmd);
+}
+
 #ifndef CONFIG_PARAVIRT
 /*
  * Rules for using pte_update - it must be called after any PTE update which

@@ -99,6 +99,7 @@ extern void __split_huge_page_pmd(struct
 #endif
 
 extern unsigned long vma_address(struct page *page, struct vm_area_struct *vma);
+extern int hugepage_madvise(unsigned long *vm_flags);
 static inline int PageTransHuge(struct page *page)
 {
 	VM_BUG_ON(PageTail(page));

@@ -121,6 +122,11 @@ static inline int split_huge_page(struct
 #define wait_split_huge_page(__anon_vma, __pmd)	\
 	do { } while (0)
 #define PageTransHuge(page) 0
+static inline int hugepage_madvise(unsigned long *vm_flags)
+{
+	BUG_ON(0);
+	return 0;
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #endif /* _LINUX_HUGE_MM_H */

@@ -840,6 +840,22 @@ out:
 	return ret;
 }
 
+int hugepage_madvise(unsigned long *vm_flags)
+{
+	/*
+	 * Be somewhat over-protective like KSM for now!
+	 */
+	if (*vm_flags & (VM_HUGEPAGE | VM_SHARED  | VM_MAYSHARE   |
+			 VM_PFNMAP   | VM_IO      | VM_DONTEXPAND |
+			 VM_RESERVED | VM_HUGETLB | VM_INSERTPAGE |
+			 VM_MIXEDMAP | VM_SAO))
+		return -EINVAL;
+
+	*vm_flags |= VM_HUGEPAGE;
+
+	return 0;
+}
+
 void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd)
 {
 	struct page *page;

@@ -71,6 +71,11 @@ static long madvise_behavior(struct vm_a
 		if (error)
 			goto out;
 		break;
+	case MADV_HUGEPAGE:
+		error = hugepage_madvise(&new_flags);
+		if (error)
+			goto out;
+		break;
 	}
 
 	if (new_flags == vma->vm_flags) {

@@ -283,6 +288,9 @@ madvise_behavior_valid(int behavior)
 	case MADV_MERGEABLE:
 	case MADV_UNMERGEABLE:
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	case MADV_HUGEPAGE:
+#endif
 		return 1;
 
 	default:

@@ -1294,7 +1294,19 @@ next_mm:
 			if (ksm_test_exit(mm))
 				break;
 			*page = follow_page(vma, ksm_scan.address, FOLL_GET);
-			if (*page && PageAnon(*page)) {
+			if (!*page) {
+				ksm_scan.address += PAGE_SIZE;
+				cond_resched();
+				continue;
+			}
+			if (PageTransHuge(*page)) {
+				put_page(*page);
+				ksm_scan.address &= HPAGE_PMD_MASK;
+				ksm_scan.address += HPAGE_PMD_SIZE;
+				cond_resched();
+				continue;
+			}
+			if (PageAnon(*page)) {
 				flush_anon_page(vma, *page, ksm_scan.address);
 				flush_dcache_page(*page);
 				rmap_item = get_next_rmap_item(slot,

@@ -1308,8 +1320,7 @@ next_mm:
 				up_read(&mm->mmap_sem);
 				return rmap_item;
 			}
-			if (*page)
-				put_page(*page);
+			put_page(*page);
 			ksm_scan.address += PAGE_SIZE;
 			cond_resched();
 		}

@@ -378,6 +378,8 @@ static void collect_procs_anon(struct pa
 	struct task_struct *tsk;
 	struct anon_vma *av;
 
+	if (unlikely(split_huge_page(page)))
+		return;
 	read_lock(&tasklist_lock);
 	av = page_lock_anon_vma(page);
 	if (av == NULL)	/* Not actually mapped anymore */

@@ -1284,6 +1284,7 @@ int try_to_unmap(struct page *page, enum
 	int ret;
 
 	BUG_ON(!PageLocked(page));
+	BUG_ON(PageTransHuge(page));
 
 	if (unlikely(PageKsm(page)))
 		ret = try_to_unmap_ksm(page, flags);

@@ -156,6 +156,12 @@ int add_to_swap(struct page *page)
 	if (!entry.val)
 		return 0;
 
+	if (unlikely(PageTransHuge(page)))
+		if (unlikely(split_huge_page(page))) {
+			swapcache_free(entry, NULL);
+			return 0;
+		}
+
 	/*
 	 * Radix-tree node allocations from PF_MEMALLOC contexts could
 	 * completely exhaust the page allocator. __GFP_NOMEMALLOC

@@ -937,6 +937,8 @@ static inline int unuse_pmd_range(struct
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
+		if (unlikely(pmd_trans_huge(*pmd)))
+			continue;
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
 		ret = unuse_pte_range(vma, pmd, addr, next, entry, page);

@@ -101,6 +101,9 @@ static int meminfo_proc_show(struct seq_
 #ifdef CONFIG_MEMORY_FAILURE
 		"HardwareCorrupted: %5lu kB\n"
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		"AnonHugePages:  %8lu kB\n"
+#endif
 		,
 		K(i.totalram),
 		K(i.freeram),

@@ -151,6 +154,10 @@ static int meminfo_proc_show(struct seq_
 #ifdef CONFIG_MEMORY_FAILURE
 		,atomic_long_read(&mce_bad_pages) << (PAGE_SHIFT - 10)
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		,K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
+		   HPAGE_PMD_NR)
+#endif
 		);
 
 	hugetlb_report_meminfo(m);

@@ -112,6 +112,7 @@ enum zone_stat_item {
 	NUMA_LOCAL,		/* allocation from local node */
 	NUMA_OTHER,		/* allocation from other node */
 #endif
+	NR_ANON_TRANSPARENT_HUGEPAGES,
 	NR_VM_ZONE_STAT_ITEMS };
 
 /*

@@ -724,6 +724,9 @@ static void __split_huge_page_refcount(s
 		put_page(page_tail);
 	}
 
+	__dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
+	__mod_zone_page_state(zone, NR_ANON_PAGES, HPAGE_PMD_NR);
+
 	ClearPageCompound(page);
 	compound_unlock(page);
 	spin_unlock_irq(&zone->lru_lock);

@@ -795,8 +795,13 @@ void page_add_anon_rmap(struct page *pag
 	struct vm_area_struct *vma, unsigned long address)
 {
 	int first = atomic_inc_and_test(&page->_mapcount);
-	if (first)
-		__inc_zone_page_state(page, NR_ANON_PAGES);
+	if (first) {
+		if (!PageTransHuge(page))
+			__inc_zone_page_state(page, NR_ANON_PAGES);
+		else
+			__inc_zone_page_state(page,
+					      NR_ANON_TRANSPARENT_HUGEPAGES);
+	}
 	if (unlikely(PageKsm(page)))
 		return;
 

@@ -824,7 +829,10 @@ void page_add_new_anon_rmap(struct page 
 	VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
 	SetPageSwapBacked(page);
 	atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
-	__inc_zone_page_state(page, NR_ANON_PAGES);
+	if (!PageTransHuge(page))
+	    __inc_zone_page_state(page, NR_ANON_PAGES);
+	else
+	    __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
 	__page_set_anon_rmap(page, vma, address);
 	if (page_evictable(page, vma))
 		lru_cache_add_lru(page, LRU_ACTIVE_ANON);

@@ -871,7 +879,11 @@ void page_remove_rmap(struct page *page)
 	}
 	if (PageAnon(page)) {
 		mem_cgroup_uncharge_page(page);
-		__dec_zone_page_state(page, NR_ANON_PAGES);
+		if (!PageTransHuge(page))
+			__dec_zone_page_state(page, NR_ANON_PAGES);
+		else
+			__dec_zone_page_state(page,
+					      NR_ANON_TRANSPARENT_HUGEPAGES);
 	} else {
 		__dec_zone_page_state(page, NR_FILE_MAPPED);
 		mem_cgroup_update_file_mapped(page, -1);

@@ -657,6 +657,9 @@ static const char * const vmstat_text[] 
 	"numa_local",
 	"numa_other",
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	"nr_anon_transparent_hugepages",
+#endif
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
 	"pgpgin",

@@ -53,6 +53,8 @@
 #define MADV_MERGEABLE   12		/* KSM may merge identical pages */
 #define MADV_UNMERGEABLE 13		/* KSM may not merge identical pages */
 
+#define MADV_HUGEPAGE	14		/* Worth backing with hugepages */
+
 /* compatibility flags */
 #define MAP_FILE	0
 

@@ -77,6 +77,8 @@
 #define MADV_UNMERGEABLE 13		/* KSM may not merge identical pages */
 #define MADV_HWPOISON    100		/* poison a page for testing */
 
+#define MADV_HUGEPAGE	14		/* Worth backing with hugepages */
+
 /* compatibility flags */
 #define MAP_FILE	0
 

@@ -59,6 +59,8 @@
 #define MADV_MERGEABLE   65		/* KSM may merge identical pages */
 #define MADV_UNMERGEABLE 66		/* KSM may not merge identical pages */
 
+#define MADV_HUGEPAGE	67		/* Worth backing with hugepages */
+
 /* compatibility flags */
 #define MAP_FILE	0
 #define MAP_VARIABLE	0

@@ -83,6 +83,8 @@
 #define MADV_MERGEABLE   12		/* KSM may merge identical pages */
 #define MADV_UNMERGEABLE 13		/* KSM may not merge identical pages */
 
+#define MADV_HUGEPAGE	14		/* Worth backing with hugepages */
+
 /* compatibility flags */
 #define MAP_FILE	0
 

@@ -45,7 +45,7 @@
 #define MADV_MERGEABLE   12		/* KSM may merge identical pages */
 #define MADV_UNMERGEABLE 13		/* KSM may not merge identical pages */
 
-#define MADV_HUGEPAGE	15		/* Worth backing with hugepages */
+#define MADV_HUGEPAGE	14		/* Worth backing with hugepages */
 
 /* compatibility flags */
 #define MAP_FILE	0

@@ -16,6 +16,16 @@
 
 #ifdef __HAVE_ARCH_PTE_SPECIAL
 
+static inline void pin_huge_page_tail(struct page *page)
+{
+	/*
+	 * __split_huge_page_refcount() cannot run
+	 * from under us.
+	 */
+	VM_BUG_ON(atomic_read(&page->_count) < 0);
+	atomic_inc(&page->_count);
+}
+
 /*
  * The performance critical leaf functions are made noinline otherwise gcc
  * inlines everything into a single function which results in too much

@@ -47,6 +57,8 @@ static noinline int gup_pte_range(pmd_t 
 			put_page(page);
 			return 0;
 		}
+		if (PageTail(page))
+			pin_huge_page_tail(page);
 		pages[*nr] = page;
 		(*nr)++;
 

@@ -105,6 +105,16 @@ static inline void get_head_page_multipl
 	atomic_add(nr, &page->_count);
 }
 
+static inline void pin_huge_page_tail(struct page *page)
+{
+	/*
+	 * __split_huge_page_refcount() cannot run
+	 * from under us.
+	 */
+	VM_BUG_ON(atomic_read(&page->_count) < 0);
+	atomic_inc(&page->_count);
+}
+
 static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {

@@ -128,6 +138,8 @@ static noinline int gup_huge_pmd(pmd_t p
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;
+		if (PageTail(page))
+			pin_huge_page_tail(page);
 		(*nr)++;
 		page++;
 		refs++;

@@ -326,9 +326,17 @@ static inline int page_count(struct page
 
 static inline void get_page(struct page *page)
 {
-	page = compound_head(page);
-	VM_BUG_ON(atomic_read(&page->_count) == 0);
+	VM_BUG_ON(atomic_read(&page->_count) < !PageTail(page));
 	atomic_inc(&page->_count);
+	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)

96 lines not on this page · raw message

@@ -60,13 +60,15 @@ struct vm_area_struct;
 #define __GFP_NOTRACK	((__force gfp_t)0)
 #endif
 
+#define __GFP_NO_KSWAPD	((__force gfp_t)0x400000u)
+
 /*
  * This may seem redundant, but it's a way of annotating false positives vs.
  * allocations that simply cannot be supported (e.g. page tables).
  */
 #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
 
-#define __GFP_BITS_SHIFT 22	/* Room for 22 __GFP_FOO bits */
+#define __GFP_BITS_SHIFT 23	/* Room for 23 __GFP_FOO bits */
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
 /* This equals 0, but use constants in case they ever change */

@@ -1867,7 +1867,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, u
 		goto nopage;
 
 restart:
-	wake_all_kswapd(order, zonelist, high_zoneidx);
+	if (!(gfp_mask & __GFP_NO_KSWAPD))
+		wake_all_kswapd(order, zonelist, high_zoneidx);
 
 	/*
 	 * OK, we're below the kswapd watermark and have kicked background

@@ -1421,6 +1421,7 @@ int __get_user_pages(struct task_struct 
 			pmd = pmd_offset(pud, pg);
 			if (pmd_none(*pmd))
 				return i ? : -EFAULT;
+			VM_BUG_ON(pmd_trans_huge(*pmd));
 			pte = pte_offset_map(pmd, pg);
 			if (pte_none(*pte)) {
 				pte_unmap(pte);

@@ -1622,8 +1623,10 @@ pte_t *get_locked_pte(struct mm_struct *
 	pud_t * pud = pud_alloc(mm, pgd, addr);
 	if (pud) {
 		pmd_t * pmd = pmd_alloc(mm, pud, addr);
-		if (pmd)
+		if (pmd) {
+			VM_BUG_ON(pmd_trans_huge(*pmd));
 			return pte_alloc_map_lock(mm, pmd, addr, ptl);
+		}
 	}
 	return NULL;
 }

@@ -1842,6 +1845,7 @@ static inline int remap_pmd_range(struct
 	pmd = pmd_alloc(mm, pud, addr);
 	if (!pmd)
 		return -ENOMEM;
+	VM_BUG_ON(pmd_trans_huge(*pmd));
 	do {
 		next = pmd_addr_end(addr, end);
 		if (remap_pte_range(mm, pmd, addr, next,

@@ -3317,6 +3321,7 @@ static int follow_pte(struct mm_struct *
 		goto out;
 
 	pmd = pmd_offset(pud, address);
+	VM_BUG_ON(pmd_trans_huge(*pmd));
 	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
 		goto out;
 

@@ -629,6 +629,8 @@ static void __free_pages_ok(struct page 
 	trace_mm_page_free_direct(page, order);
 	kmemcheck_free_shadow(page, order);
 
+	if (PageAnon(page))
+		page->mapping = NULL;
 	for (i = 0 ; i < (1 << order) ; ++i)
 		bad += free_pages_check(page + i);
 	if (bad)

@@ -1507,5 +1507,14 @@ extern int soft_offline_page(struct page
 
 extern void dump_page(struct page *page);
 
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
+extern void clear_huge_page(struct page *page,
+			    unsigned long addr,
+			    unsigned int pages_per_huge_page);
+extern void copy_huge_page(struct page *dst, struct page *src,
+			   unsigned long addr, struct vm_area_struct *vma,
+			   unsigned int pages_per_huge_page);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */

87 lines not on this page · raw message

73 lines not on this page · raw message

@@ -160,7 +160,18 @@ static int gup_pmd_range(pud_t pud, unsi
 		pmd_t pmd = *pmdp;
 
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
+		/*
+		 * The pmd_trans_splitting() check below explains why
+		 * pmdp_splitting_flush has to flush the tlb, to stop
+		 * this gup-fast code from running while we set the
+		 * splitting bit in the pmd. Returning zero will take
+		 * the slow path that will call wait_split_huge_page()
+		 * if the pmd is still in splitting state. gup-fast
+		 * can't because it has irq disabled and
+		 * wait_split_huge_page() would never return as the
+		 * tlb flush IPI wouldn't run.
+		 */
+		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
 		if (unlikely(pmd_large(pmd))) {
 			if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))

@@ -25,6 +25,26 @@
 })
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmdp_set_access_flags(__vma, __address, __pmdp, __entry, __dirty) \
+	({								\
+		int __changed = !pmd_same(*(__pmdp), __entry);		\
+		VM_BUG_ON((__address) & ~HPAGE_PMD_MASK);		\
+		if (__changed) {					\
+			set_pmd_at((__vma)->vm_mm, __address, __pmdp,	\
+				   __entry);				\
+			flush_tlb_range(__vma, __address,		\
+					(__address) + HPAGE_PMD_SIZE);	\
+		}							\
+		__changed;						\
+	})
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+#define pmdp_set_access_flags(__vma, __address, __pmdp, __entry, __dirty) \
+	({ BUG(); 0; })
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 #define ptep_test_and_clear_young(__vma, __address, __ptep)		\
 ({									\

@@ -39,6 +59,25 @@
 })
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmdp_test_and_clear_young(__vma, __address, __pmdp)		\
+({									\
+	pmd_t __pmd = *(__pmdp);					\
+	int r = 1;							\
+	if (!pmd_young(__pmd))						\
+		r = 0;							\
+	else								\
+		set_pmd_at((__vma)->vm_mm, (__address),			\
+			   (__pmdp), pmd_mkold(__pmd));			\
+	r;								\
+})
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+#define pmdp_test_and_clear_young(__vma, __address, __pmdp)	\
+	({ BUG(); 0; })
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
 #define ptep_clear_flush_young(__vma, __address, __ptep)		\
 ({									\

@@ -50,6 +89,24 @@
 })
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmdp_clear_flush_young(__vma, __address, __pmdp)		\
+({									\
+	int __young;							\
+	VM_BUG_ON((__address) & ~HPAGE_PMD_MASK);			\
+	__young = pmdp_test_and_clear_young(__vma, __address, __pmdp);	\
+	if (__young)							\
+		flush_tlb_range(__vma, __address,			\
+				(__address) + HPAGE_PMD_SIZE);		\
+	__young;							\
+})
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+#define pmdp_clear_flush_young(__vma, __address, __pmdp)	\
+	({ BUG(); 0; })
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
 #define ptep_get_and_clear(__mm, __address, __ptep)			\
 ({									\

@@ -59,6 +116,20 @@
 })
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_GET_AND_CLEAR
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmdp_get_and_clear(__mm, __address, __pmdp)			\
+({									\
+	pmd_t __pmd = *(__pmdp);					\
+	pmd_clear((__mm), (__address), (__pmdp));			\
+	__pmd;								\
+})
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+#define pmdp_get_and_clear(__mm, __address, __pmdp)	\
+	({ BUG(); 0; })
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
 #define ptep_get_and_clear_full(__mm, __address, __ptep, __full)	\
 ({									\

@@ -90,6 +161,22 @@ do {									\
 })
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_CLEAR_FLUSH
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmdp_clear_flush(__vma, __address, __pmdp)			\
+({									\
+	pmd_t __pmd;							\
+	VM_BUG_ON((__address) & ~HPAGE_PMD_MASK);			\
+	__pmd = pmdp_get_and_clear((__vma)->vm_mm, __address, __pmdp);	\
+	flush_tlb_range(__vma, __address, (__address) + HPAGE_PMD_SIZE);\
+	__pmd;								\
+})
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+#define pmdp_clear_flush(__vma, __address, __pmdp)	\
+	({ BUG(); 0; })
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT
 struct mm_struct;
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)

@@ -99,10 +186,45 @@ static inline void ptep_set_wrprotect(st
 }
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp)
+{
+	pmd_t old_pmd = *pmdp;
+	set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd));
+}
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+#define pmdp_set_wrprotect(mm, address, pmdp) BUG()
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmdp_splitting_flush(__vma, __address, __pmdp)			\
+({									\
+	pmd_t __pmd = pmd_mksplitting(*(__pmdp));			\
+	VM_BUG_ON((__address) & ~HPAGE_PMD_MASK);			\
+	set_pmd_at((__vma)->vm_mm, __address, __pmdp, __pmd);		\
+	/* tlb flush only to serialize against gup-fast */		\
+	flush_tlb_range(__vma, __address, (__address) + HPAGE_PMD_SIZE);\
+})
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+#define pmdp_splitting_flush(__vma, __address, __pmdp) BUG()
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
 #ifndef __HAVE_ARCH_PTE_SAME
 #define pte_same(A,B)	(pte_val(A) == pte_val(B))
 #endif
 
+#ifndef __HAVE_ARCH_PMD_SAME
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmd_same(A,B)	(pmd_val(A) == pmd_val(B))
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+#define pmd_same(A,B)	({ BUG(); 0; })
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
 #ifndef __HAVE_ARCH_PAGE_TEST_DIRTY
 #define page_test_dirty(page)		(0)
 #endif

@@ -347,6 +469,9 @@ extern void untrack_pfn_vma(struct vm_ar
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd) 0
 #define pmd_trans_splitting(pmd) 0
+#ifndef __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd)	({ BUG(); 0; })
+#endif /* __HAVE_ARCH_PMD_WRITE */
 #endif
 
 #endif /* !__ASSEMBLY__ */

@@ -334,6 +334,7 @@ void prep_compound_page(struct page *pag
 	}
 }
 
+/* update __split_huge_page_refcount if you change this function */
 static int destroy_compound_page(struct page *page, unsigned long order)
 {
 	int i;

@@ -470,6 +470,15 @@ static int host_mapping_level(struct kvm
 
 	page_size = kvm_host_page_size(kvm, gfn);
 
+	/* check for transparent hugepages */
+	if (page_size == PAGE_SIZE) {
+		struct page *page = gfn_to_page(kvm, gfn);
+
+		if (!is_error_page(page) && PageTransCompound(page))
+			page_size = KVM_HPAGE_SIZE(2);
+		kvm_release_page_clean(page);
+	}
+
 	for (i = PT_PAGE_TABLE_LEVEL;
 	     i < (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES); ++i) {
 		if (page_size >= KVM_HPAGE_SIZE(i))

@@ -440,6 +440,11 @@ static inline void pte_update(struct mm_
 {
 	PVOP_VCALL3(pv_mmu_ops.pte_update, mm, addr, ptep);
 }
+static inline void pmd_update(struct mm_struct *mm, unsigned long addr,
+			      pmd_t *pmdp)
+{
+	PVOP_VCALL3(pv_mmu_ops.pmd_update, mm, addr, pmdp);
+}
 
 static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr,
 				    pte_t *ptep)

@@ -447,6 +452,12 @@ static inline void pte_update_defer(stru
 	PVOP_VCALL3(pv_mmu_ops.pte_update_defer, mm, addr, ptep);
 }
 
+static inline void pmd_update_defer(struct mm_struct *mm, unsigned long addr,
+				    pmd_t *pmdp)
+{
+	PVOP_VCALL3(pv_mmu_ops.pmd_update_defer, mm, addr, pmdp);
+}
+
 static inline pte_t __pte(pteval_t val)
 {
 	pteval_t ret;

@@ -548,6 +559,18 @@ static inline void set_pte_at(struct mm_
 		PVOP_VCALL4(pv_mmu_ops.set_pte_at, mm, addr, ptep, pte.pte);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+			      pmd_t *pmdp, pmd_t pmd)
+{
+	if (sizeof(pmdval_t) > sizeof(long))
+		/* 5 arg words */
+		pv_mmu_ops.set_pmd_at(mm, addr, pmdp, pmd);
+	else
+		PVOP_VCALL4(pv_mmu_ops.set_pmd_at, mm, addr, pmdp, pmd.pmd);
+}
+#endif
+
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
 	pmdval_t val = native_pmd_val(pmd);

@@ -266,10 +266,16 @@ struct pv_mmu_ops {
 	void (*set_pte_at)(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep, pte_t pteval);
 	void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
+	void (*set_pmd_at)(struct mm_struct *mm, unsigned long addr,
+			   pmd_t *pmdp, pmd_t pmdval);
 	void (*pte_update)(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep);
 	void (*pte_update_defer)(struct mm_struct *mm,
 				 unsigned long addr, pte_t *ptep);
+	void (*pmd_update)(struct mm_struct *mm, unsigned long addr,
+			   pmd_t *pmdp);
+	void (*pmd_update_defer)(struct mm_struct *mm,
+				 unsigned long addr, pmd_t *pmdp);
 
 	pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr,
 					pte_t *ptep);

@@ -422,8 +422,11 @@ struct pv_mmu_ops pv_mmu_ops = {
 	.set_pte = native_set_pte,
 	.set_pte_at = native_set_pte_at,
 	.set_pmd = native_set_pmd,
+	.set_pmd_at = native_set_pmd_at,
 	.pte_update = paravirt_nop,
 	.pte_update_defer = paravirt_nop,
+	.pmd_update = paravirt_nop,
+	.pmd_update_defer = paravirt_nop,
 
 	.ptep_modify_prot_start = __ptep_modify_prot_start,
 	.ptep_modify_prot_commit = __ptep_modify_prot_commit,

@@ -310,6 +310,9 @@ struct mm_struct {
 #ifdef CONFIG_MMU_NOTIFIER
 	struct mmu_notifier_mm *mmu_notifier_mm;
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	pgtable_t pmd_huge_pte; /* protected by page_table_lock */
+#endif
 };
 
 /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */

@@ -522,6 +522,9 @@ void __mmdrop(struct mm_struct *mm)
 	mm_free_pgd(mm);
 	destroy_context(mm);
 	mmu_notifier_mm_destroy(mm);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	VM_BUG_ON(mm->pmd_huge_pte);
+#endif
 	free_mm(mm);
 }
 EXPORT_SYMBOL_GPL(__mmdrop);

@@ -662,6 +665,10 @@ struct mm_struct *dup_mm(struct task_str
 	mm->token_priority = 0;
 	mm->last_interval = 0;
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	mm->pmd_huge_pte = NULL;
+#endif
+
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
 

@@ -323,6 +323,16 @@ static inline pte_t pte_modify(pte_t pte
 	return __pte(val);
 }
 
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+	pmdval_t val = pmd_val(pmd);
+
+	val &= _HPAGE_CHG_MASK;
+	val |= massage_pgprot(newprot) & ~_HPAGE_CHG_MASK;
+
+	return __pmd(val);
+}
+
 /* mprotect needs to preserve PAT bits when updating vm_page_prot */
 #define pgprot_modify pgprot_modify
 static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)

@@ -72,6 +72,7 @@
 /* Set of bits not changed in pte_modify */
 #define _PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |		\
 			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
 
 #define _PAGE_CACHE_MASK	(_PAGE_PCD | _PAGE_PWT)
 #define _PAGE_CACHE_WB		(0)

@@ -13,6 +13,7 @@
 #include <linux/debug_locks.h>
 #include <linux/mm_types.h>
 #include <linux/range.h>
+#include <linux/bit_spinlock.h>
 
 struct mempolicy;
 struct anon_vma;

@@ -297,6 +298,20 @@ static inline int is_vmalloc_or_module_a
 }
 #endif
 
+static inline void compound_lock(struct page *page)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	bit_spin_lock(PG_compound_lock, &page->flags);
+#endif
+}
+
+static inline void compound_unlock(struct page *page)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	bit_spin_unlock(PG_compound_lock, &page->flags);
+#endif
+}
+
 static inline struct page *compound_head(struct page *page)
 {
 	if (unlikely(PageTail(page)))

@@ -108,6 +108,9 @@ enum pageflags {
 #ifdef CONFIG_MEMORY_FAILURE
 	PG_hwpoison,		/* hardware poisoned page. Don't touch */
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	PG_compound_lock,
+#endif
 	__NR_PAGEFLAGS,
 
 	/* Filesystems */

@@ -399,6 +402,12 @@ static inline void __ClearPageTail(struc
 #define __PG_MLOCKED		0
 #endif
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __PG_COMPOUND_LOCK		(1 << PG_compound_lock)
+#else
+#define __PG_COMPOUND_LOCK		0
+#endif
+
 /*
  * Flags checked when a page is freed.  Pages being freed should not have
  * these flags set.  It they are, there is a problem.

@@ -408,7 +417,8 @@ static inline void __ClearPageTail(struc
 	 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 | __PG_HWPOISON)
+	 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \
+	 __PG_COMPOUND_LOCK)
 
 /*
  * Flags checked when a page is prepped for return by the page allocator.

@@ -168,6 +168,19 @@ extern void cleanup_highmap(void);
 #define	kc_offset_to_vaddr(o) ((o) | ~__VIRTUAL_MASK)
 
 #define __HAVE_ARCH_PTE_SAME
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pmd_trans_splitting(pmd_t pmd)
+{
+	return pmd_val(pmd) & _PAGE_SPLITTING;
+}
+
+static inline int pmd_trans_huge(pmd_t pmd)
+{
+	return pmd_val(pmd) & _PAGE_PSE;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PGTABLE_64_H */

@@ -22,6 +22,7 @@
 #define _PAGE_BIT_PAT_LARGE	12	/* On 2MB or 1GB pages */
 #define _PAGE_BIT_SPECIAL	_PAGE_BIT_UNUSED1
 #define _PAGE_BIT_CPA_TEST	_PAGE_BIT_UNUSED1
+#define _PAGE_BIT_SPLITTING	_PAGE_BIT_UNUSED1 /* only valid on a PSE pmd */
 #define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
 
 /* If _PAGE_BIT_PRESENT is clear, we use these: */

@@ -45,6 +46,7 @@
 #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
 #define _PAGE_SPECIAL	(_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
 #define _PAGE_CPA_TEST	(_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
+#define _PAGE_SPLITTING	(_AT(pteval_t, 1) << _PAGE_BIT_SPLITTING)
 #define __HAVE_ARCH_PTE_SPECIAL
 
 #ifdef CONFIG_KMEMCHECK

@@ -344,6 +344,11 @@ extern void untrack_pfn_vma(struct vm_ar
 				unsigned long size);
 #endif
 
+#ifndef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmd_trans_huge(pmd) 0
+#define pmd_trans_splitting(pmd) 0
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_GENERIC_PGTABLE_H */

@@ -22,6 +22,8 @@ extern int zap_huge_pmd(struct mmu_gathe
 extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, unsigned long end,
 			unsigned char *vec);
+extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+			unsigned long addr, pgprot_t newprot);
 
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_FLAG,

@@ -961,6 +961,33 @@ int mincore_huge_pmd(struct vm_area_stru
 	return ret;
 }
 
+int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+		unsigned long addr, pgprot_t newprot)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	int ret = 0;
+
+	spin_lock(&mm->page_table_lock);
+	if (likely(pmd_trans_huge(*pmd))) {
+		if (unlikely(pmd_trans_splitting(*pmd))) {
+			spin_unlock(&mm->page_table_lock);
+			wait_split_huge_page(vma->anon_vma, pmd);
+		} else {
+			pmd_t entry;
+
+			entry = pmdp_get_and_clear(mm, addr, pmd);
+			entry = pmd_modify(entry, newprot);
+			set_pmd_at(mm, addr, pmd, entry);
+			spin_unlock(&vma->vm_mm->page_table_lock);
+			flush_tlb_range(vma, addr, addr + HPAGE_PMD_SIZE);
+			ret = 1;
+		}
+	} else
+		spin_unlock(&vma->vm_mm->page_table_lock);
+
+	return ret;
+}
+
 pmd_t *page_check_address_pmd(struct page *page,
 			      struct mm_struct *mm,
 			      unsigned long address,

@@ -90,7 +90,13 @@ static inline void change_pmd_range(stru
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
-		split_huge_page_pmd(vma->vm_mm, pmd);
+		if (pmd_trans_huge(*pmd)) {
+			if (next - addr != HPAGE_PMD_SIZE)
+				split_huge_page_pmd(vma->vm_mm, pmd);
+			else if (change_huge_pmd(vma, pmd, addr, newprot))
+				continue;
+			/* fall through */
+		}
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
 		change_pte_range(vma, pmd, addr, next, newprot, dirty_accountable);

@@ -19,6 +19,9 @@ extern struct page *follow_trans_huge_pm
 extern int zap_huge_pmd(struct mmu_gather *tlb,
 			struct vm_area_struct *vma,
 			pmd_t *pmd);
+extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+			unsigned long addr, unsigned long end,
+			unsigned char *vec);
 
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_FLAG,

@@ -936,6 +936,31 @@ int zap_huge_pmd(struct mmu_gather *tlb,
 	return ret;
 }
 
+int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+		unsigned long addr, unsigned long end,
+		unsigned char *vec)
+{
+	int ret = 0;
+
+	spin_lock(&vma->vm_mm->page_table_lock);
+	if (likely(pmd_trans_huge(*pmd))) {
+		ret = !pmd_trans_splitting(*pmd);
+		spin_unlock(&vma->vm_mm->page_table_lock);
+		if (unlikely(!ret))
+			wait_split_huge_page(vma->anon_vma, pmd);
+		else {
+			/*
+			 * All logical pages in the range are present
+			 * if backed by a huge page.
+			 */
+			memset(vec, 1, (end - addr) >> PAGE_SHIFT);
+		}
+	} else
+		spin_unlock(&vma->vm_mm->page_table_lock);
+
+	return ret;
+}
+
 pmd_t *page_check_address_pmd(struct page *page,
 			      struct mm_struct *mm,
 			      unsigned long address,

@@ -154,7 +154,13 @@ static void mincore_pmd_range(struct vm_
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
-		split_huge_page_pmd(vma->vm_mm, pmd);
+		if (pmd_trans_huge(*pmd)) {
+			if (mincore_huge_pmd(vma, pmd, addr, next, vec)) {
+				vec += (next - addr) >> PAGE_SHIFT;
+				continue;
+			}
+			/* fall through */
+		}
 		if (pmd_none_or_clear_bad(pmd))
 			mincore_unmapped_range(vma, addr, next, vec);
 		else

@@ -300,15 +300,15 @@ pmd_t *populate_extra_pmd(unsigned long 
 pte_t *populate_extra_pte(unsigned long vaddr);
 #endif	/* __ASSEMBLY__ */
 
+#ifndef __ASSEMBLY__
+#include <linux/mm_types.h>
+
 #ifdef CONFIG_X86_32
 # include "pgtable_32.h"
 #else
 # include "pgtable_64.h"
 #endif
 
-#ifndef __ASSEMBLY__
-#include <linux/mm_types.h>
-
 static inline int pte_none(pte_t pte)
 {
 	return !pte.pte;

@@ -351,7 +351,7 @@ static inline unsigned long pmd_page_vad
  * Currently stuck as a macro due to indirect forward reference to
  * linux/mmzone.h's __section_mem_map_addr() definition:
  */
-#define pmd_page(pmd)	pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)
+#define pmd_page(pmd)	pfn_to_page((pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT)
 
 /*
  * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]

117 lines not on this page · raw message

84 lines not on this page · raw message

@@ -116,15 +116,17 @@ u64 stable_page_flags(struct page *page)
 	if (PageHuge(page))
 		u |= 1 << KPF_HUGE;
 
+	/*
+	 * Caveats on high order pages: page->_count will only be set
+	 * -1 on the head page; SLUB/SLQB do the same for PG_slab;
+	 * SLOB won't set PG_slab at all on compound pages.
+	 */
+	if (PageBuddy(page))
+		u |= 1 << KPF_BUDDY;
+
 	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
 
-	/*
-	 * Caveats on high order pages:
-	 * PG_buddy will only be set on the head page; SLUB/SLQB do the same
-	 * for PG_slab; SLOB won't set PG_slab at all on compound pages.
-	 */
 	u |= kpf_copy_bit(k, KPF_SLAB,		PG_slab);
-	u |= kpf_copy_bit(k, KPF_BUDDY,		PG_buddy);
 
 	u |= kpf_copy_bit(k, KPF_ERROR,		PG_error);
 	u |= kpf_copy_bit(k, KPF_DIRTY,		PG_dirty);

@@ -358,6 +358,27 @@ static inline void init_page_count(struc
 	atomic_set(&page->_count, 1);
 }
 
+/*
+ * PageBuddy() indicate that the page is free and in the buddy system
+ * (see mm/page_alloc.c).
+ */
+static inline int PageBuddy(struct page *page)
+{
+	return atomic_read(&page->_count) == -1;
+}
+
+static inline void __SetPageBuddy(struct page *page)
+{
+	VM_BUG_ON(atomic_read(&page->_count) != 0);
+	atomic_set(&page->_count, -1);
+}
+
+static inline void __ClearPageBuddy(struct page *page)
+{
+	VM_BUG_ON(!PageBuddy(page));
+	atomic_set(&page->_count, 0);
+}
+
 void put_page(struct page *page);
 void put_pages_list(struct list_head *pages);
 

@@ -48,9 +48,6 @@
  * struct page (these bits with information) are always mapped into kernel
  * address space...
  *
- * 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!

@@ -96,7 +93,6 @@ enum pageflags {
 	PG_swapcache,		/* Swap page: swp_entry_t in private */
 	PG_mappedtodisk,	/* Has blocks allocated on-disk */
 	PG_reclaim,		/* To be reclaimed asap */
-	PG_buddy,		/* Page is free, on buddy lists */
 	PG_swapbacked,		/* Page is backed by RAM/swap */
 	PG_unevictable,		/* Page is "unevictable"  */
 #ifdef CONFIG_MMU

@@ -235,7 +231,6 @@ PAGEFLAG(OwnerPriv1, owner_priv_1) TESTC
  * risky: they bypass page accounting.
  */
 TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback)
-__PAGEFLAG(Buddy, buddy)
 PAGEFLAG(MappedToDisk, mappedtodisk)
 
 /* PG_readahead is only used for file reads; PG_reclaim is only for writes */

@@ -430,7 +425,7 @@ static inline void ClearPageCompound(str
 #define PAGE_FLAGS_CHECK_AT_FREE \
 	(1 << PG_lru	 | 1 << PG_locked    | \
 	 1 << PG_private | 1 << PG_private_2 | \
-	 1 << PG_buddy	 | 1 << PG_writeback | 1 << PG_reserved | \
+	 1 << PG_writeback | 1 << PG_reserved | \
 	 1 << PG_slab	 | 1 << PG_swapcache | 1 << PG_active | \
 	 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \
 	 __PG_COMPOUND_LOCK)

@@ -426,8 +426,8 @@ __find_combined_index(unsigned long page
  * (c) a page and its buddy have the same order &&
  * (d) a page and its buddy are in the same zone.
  *
- * For recording whether a page is in the buddy system, we use PG_buddy.
- * Setting, clearing, and testing PG_buddy is serialized by zone->lock.
+ * For recording whether a page is in the buddy system, we set page->_count -1.
+ * Setting, clearing, and testing page->_count -1 is serialized by zone->lock.
  *
  * For recording page's order, we use page_private(page).
  */

@@ -440,10 +440,8 @@ static inline int page_is_buddy(struct p
 	if (page_zone_id(page) != page_zone_id(buddy))
 		return 0;
 
-	if (PageBuddy(buddy) && page_order(buddy) == order) {
-		VM_BUG_ON(page_count(buddy) != 0);
+	if (PageBuddy(buddy) && page_order(buddy) == order)
 		return 1;
-	}
 	return 0;
 }
 

@@ -460,7 +458,7 @@ static inline int page_is_buddy(struct p
  * as necessary, plus some accounting needed to play nicely with other
  * parts of the VM system.
  * At each level, we keep a list of pages, which are heads of continuous
- * free pages of length of (1 << order) and marked with PG_buddy. Page's
+ * free pages of length of (1 << order) and marked with page->count -1. Page's
  * order is recorded in page_private(page) field.
  * So when we are allocating or freeing one, we can derive the state of the
  * other.  That is, if we allocate a small block, and both were   

@@ -5251,7 +5249,6 @@ static struct trace_print_flags pageflag
 	{1UL << PG_swapcache,		"swapcache"	},
 	{1UL << PG_mappedtodisk,	"mappedtodisk"	},
 	{1UL << PG_reclaim,		"reclaim"	},
-	{1UL << PG_buddy,		"buddy"		},
 	{1UL << PG_swapbacked,		"swapbacked"	},
 	{1UL << PG_unevictable,		"unevictable"	},
 #ifdef CONFIG_MMU

@@ -116,15 +116,17 @@ u64 stable_page_flags(struct page *page)
 	if (PageHuge(page))
 		u |= 1 << KPF_HUGE;
 
+	/*
+	 * Caveats on high order pages: page->_count will only be set
+	 * -1 on the head page; SLUB/SLQB do the same for PG_slab;
+	 * SLOB won't set PG_slab at all on compound pages.
+	 */
+	if (PageBuddy(page))
+		u |= 1 << KPF_BUDDY;
+
 	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
 
-	/*
-	 * Caveats on high order pages:
-	 * PG_buddy will only be set on the head page; SLUB/SLQB do the same
-	 * for PG_slab; SLOB won't set PG_slab at all on compound pages.
-	 */
 	u |= kpf_copy_bit(k, KPF_SLAB,		PG_slab);
-	u |= kpf_copy_bit(k, KPF_BUDDY,		PG_buddy);
 
 	u |= kpf_copy_bit(k, KPF_ERROR,		PG_error);
 	u |= kpf_copy_bit(k, KPF_DIRTY,		PG_dirty);

@@ -358,6 +358,27 @@ static inline void init_page_count(struc
 	atomic_set(&page->_count, 1);
 }
 
+/*
+ * PageBuddy() indicate that the page is free and in the buddy system
+ * (see mm/page_alloc.c).
+ */
+static inline int PageBuddy(struct page *page)
+{
+	return atomic_read(&page->_mapcount) == -2;
+}
+
+static inline void __SetPageBuddy(struct page *page)
+{
+	VM_BUG_ON(atomic_read(&page->_mapcount) != -1);
+	atomic_set(&page->_mapcount, -2);
+}
+
+static inline void __ClearPageBuddy(struct page *page)
+{
+	VM_BUG_ON(!PageBuddy(page));
+	atomic_set(&page->_mapcount, -1);
+}
+
 void put_page(struct page *page);
 void put_pages_list(struct list_head *pages);
 

@@ -48,9 +48,6 @@
  * struct page (these bits with information) are always mapped into kernel
  * address space...
  *
- * 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!

@@ -96,7 +93,6 @@ enum pageflags {
 	PG_swapcache,		/* Swap page: swp_entry_t in private */
 	PG_mappedtodisk,	/* Has blocks allocated on-disk */
 	PG_reclaim,		/* To be reclaimed asap */
-	PG_buddy,		/* Page is free, on buddy lists */
 	PG_swapbacked,		/* Page is backed by RAM/swap */
 	PG_unevictable,		/* Page is "unevictable"  */
 #ifdef CONFIG_MMU

@@ -235,7 +231,6 @@ PAGEFLAG(OwnerPriv1, owner_priv_1) TESTC
  * risky: they bypass page accounting.
  */
 TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback)
-__PAGEFLAG(Buddy, buddy)
 PAGEFLAG(MappedToDisk, mappedtodisk)
 
 /* PG_readahead is only used for file reads; PG_reclaim is only for writes */

@@ -430,7 +425,7 @@ static inline void ClearPageCompound(str
 #define PAGE_FLAGS_CHECK_AT_FREE \
 	(1 << PG_lru	 | 1 << PG_locked    | \
 	 1 << PG_private | 1 << PG_private_2 | \
-	 1 << PG_buddy	 | 1 << PG_writeback | 1 << PG_reserved | \
+	 1 << PG_writeback | 1 << PG_reserved | \
 	 1 << PG_slab	 | 1 << PG_swapcache | 1 << PG_active | \
 	 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \
 	 __PG_COMPOUND_LOCK)

@@ -65,9 +65,9 @@ static void release_memory_resource(stru
 
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
-static void get_page_bootmem(unsigned long info,  struct page *page, int type)
+static void get_page_bootmem(unsigned long info,  struct page *page, long type)
 {
-	atomic_set(&page->_mapcount, type);
+	page->lru.next = (struct list_head *) type;
 	SetPagePrivate(page);
 	set_page_private(page, info);
 	atomic_inc(&page->_count);

@@ -77,15 +77,15 @@ static void get_page_bootmem(unsigned lo
  * so use __ref to tell modpost not to generate a warning */
 void __ref put_page_bootmem(struct page *page)
 {
-	int type;
+	long type;
 
-	type = atomic_read(&page->_mapcount);
-	BUG_ON(type >= -1);
+	type = (long) page->lru.next;
+	BUG_ON(type < NODE_INFO || type > SECTION_INFO);
 
 	if (atomic_dec_return(&page->_count) == 1) {
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
-		reset_page_mapcount(page);
+		INIT_LIST_HEAD(&page->lru);
 		__free_pages_bootmem(page, 0);
 	}
 

@@ -426,8 +426,8 @@ __find_combined_index(unsigned long page
  * (c) a page and its buddy have the same order &&
  * (d) a page and its buddy are in the same zone.
  *
- * For recording whether a page is in the buddy system, we use PG_buddy.
- * Setting, clearing, and testing PG_buddy is serialized by zone->lock.
+ * For recording whether a page is in the buddy system, we set ->_mapcount -2.
+ * Setting, clearing, and testing _mapcount -2 is serialized by zone->lock.
  *
  * For recording page's order, we use page_private(page).
  */

@@ -460,7 +460,7 @@ static inline int page_is_buddy(struct p
  * as necessary, plus some accounting needed to play nicely with other
  * parts of the VM system.
  * At each level, we keep a list of pages, which are heads of continuous
- * free pages of length of (1 << order) and marked with PG_buddy. Page's
+ * free pages of length of (1 << order) and marked with _mapcount -2. Page's
  * order is recorded in page_private(page) field.
  * So when we are allocating or freeing one, we can derive the state of the
  * other.  That is, if we allocate a small block, and both were   

@@ -5251,7 +5251,6 @@ static struct trace_print_flags pageflag
 	{1UL << PG_swapcache,		"swapcache"	},
 	{1UL << PG_mappedtodisk,	"mappedtodisk"	},
 	{1UL << PG_reclaim,		"reclaim"	},
-	{1UL << PG_buddy,		"buddy"		},
 	{1UL << PG_swapbacked,		"swapbacked"	},
 	{1UL << PG_unevictable,		"unevictable"	},
 #ifdef CONFIG_MMU

@@ -670,10 +670,10 @@ static void __kfree_section_memmap(struc
 static void free_map_bootmem(struct page *page, unsigned long nr_pages)
 {
 	unsigned long maps_section_nr, removing_section_nr, i;
-	int magic;
+	long magic;
 
 	for (i = 0; i < nr_pages; i++, page++) {
-		magic = atomic_read(&page->_mapcount);
+		magic = (long) page->lru.next;
 
 		BUG_ON(magic == NODE_INFO);
 

@@ -116,15 +116,17 @@ u64 stable_page_flags(struct page *page)
 	if (PageHuge(page))
 		u |= 1 << KPF_HUGE;
 
+	/*
+	 * Caveats on high order pages: page->_count will only be set
+	 * -1 on the head page; SLUB/SLQB do the same for PG_slab;
+	 * SLOB won't set PG_slab at all on compound pages.
+	 */
+	if (PageBuddy(page))
+		u |= 1 << KPF_BUDDY;
+
 	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
 
-	/*
-	 * Caveats on high order pages:
-	 * PG_buddy will only be set on the head page; SLUB/SLQB do the same
-	 * for PG_slab; SLOB won't set PG_slab at all on compound pages.
-	 */
 	u |= kpf_copy_bit(k, KPF_SLAB,		PG_slab);
-	u |= kpf_copy_bit(k, KPF_BUDDY,		PG_buddy);
 
 	u |= kpf_copy_bit(k, KPF_ERROR,		PG_error);
 	u |= kpf_copy_bit(k, KPF_DIRTY,		PG_dirty);

@@ -13,12 +13,16 @@ struct mem_section;
 #ifdef CONFIG_MEMORY_HOTPLUG
 
 /*
- * Types for free bootmem.
- * The normal smallest mapcount is -1. Here is smaller value than it.
+ * Types for free bootmem stored in page->lru.next. These have to be in
+ * some random range in unsigned long space for debugging purposes.
  */
-#define SECTION_INFO		(-1 - 1)
-#define MIX_SECTION_INFO	(-1 - 2)
-#define NODE_INFO		(-1 - 3)
+enum {
+	MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12,
+	SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE,
+	MIX_SECTION_INFO,
+	NODE_INFO,
+	MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
+};
 
 /*
  * pgdat resizing functions

@@ -358,6 +358,27 @@ static inline void init_page_count(struc
 	atomic_set(&page->_count, 1);
 }
 
+/*
+ * PageBuddy() indicate that the page is free and in the buddy system
+ * (see mm/page_alloc.c).
+ */
+static inline int PageBuddy(struct page *page)
+{
+	return atomic_read(&page->_mapcount) == -2;
+}
+
+static inline void __SetPageBuddy(struct page *page)
+{
+	VM_BUG_ON(atomic_read(&page->_mapcount) != -1);
+	atomic_set(&page->_mapcount, -2);
+}
+
+static inline void __ClearPageBuddy(struct page *page)
+{
+	VM_BUG_ON(!PageBuddy(page));
+	atomic_set(&page->_mapcount, -1);
+}
+
 void put_page(struct page *page);
 void put_pages_list(struct list_head *pages);
 

@@ -48,9 +48,6 @@
  * struct page (these bits with information) are always mapped into kernel
  * address space...
  *
- * 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!

@@ -96,7 +93,6 @@ enum pageflags {
 	PG_swapcache,		/* Swap page: swp_entry_t in private */
 	PG_mappedtodisk,	/* Has blocks allocated on-disk */
 	PG_reclaim,		/* To be reclaimed asap */
-	PG_buddy,		/* Page is free, on buddy lists */
 	PG_swapbacked,		/* Page is backed by RAM/swap */
 	PG_unevictable,		/* Page is "unevictable"  */
 #ifdef CONFIG_MMU

@@ -235,7 +231,6 @@ PAGEFLAG(OwnerPriv1, owner_priv_1) TESTC
  * risky: they bypass page accounting.
  */
 TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback)
-__PAGEFLAG(Buddy, buddy)
 PAGEFLAG(MappedToDisk, mappedtodisk)
 
 /* PG_readahead is only used for file reads; PG_reclaim is only for writes */

@@ -430,7 +425,7 @@ static inline void ClearPageCompound(str
 #define PAGE_FLAGS_CHECK_AT_FREE \
 	(1 << PG_lru	 | 1 << PG_locked    | \
 	 1 << PG_private | 1 << PG_private_2 | \
-	 1 << PG_buddy	 | 1 << PG_writeback | 1 << PG_reserved | \
+	 1 << PG_writeback | 1 << PG_reserved | \
 	 1 << PG_slab	 | 1 << PG_swapcache | 1 << PG_active | \
 	 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \
 	 __PG_COMPOUND_LOCK)

@@ -65,9 +65,10 @@ static void release_memory_resource(stru
 
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
-static void get_page_bootmem(unsigned long info,  struct page *page, int type)
+static void get_page_bootmem(unsigned long info,  struct page *page,
+			     unsigned long type)
 {
-	atomic_set(&page->_mapcount, type);
+	page->lru.next = (struct list_head *) type;
 	SetPagePrivate(page);
 	set_page_private(page, info);
 	atomic_inc(&page->_count);

@@ -77,15 +78,16 @@ static void get_page_bootmem(unsigned lo
  * so use __ref to tell modpost not to generate a warning */
 void __ref put_page_bootmem(struct page *page)
 {
-	int type;
+	unsigned long type;
 
-	type = atomic_read(&page->_mapcount);
-	BUG_ON(type >= -1);
+	type = (unsigned long) page->lru.next;
+	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
+	       type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
 
 	if (atomic_dec_return(&page->_count) == 1) {
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
-		reset_page_mapcount(page);
+		INIT_LIST_HEAD(&page->lru);
 		__free_pages_bootmem(page, 0);
 	}
 

@@ -426,8 +426,8 @@ __find_combined_index(unsigned long page
  * (c) a page and its buddy have the same order &&
  * (d) a page and its buddy are in the same zone.
  *
- * For recording whether a page is in the buddy system, we use PG_buddy.
- * Setting, clearing, and testing PG_buddy is serialized by zone->lock.
+ * For recording whether a page is in the buddy system, we set ->_mapcount -2.
+ * Setting, clearing, and testing _mapcount -2 is serialized by zone->lock.
  *
  * For recording page's order, we use page_private(page).
  */

@@ -460,7 +460,7 @@ static inline int page_is_buddy(struct p
  * as necessary, plus some accounting needed to play nicely with other
  * parts of the VM system.
  * At each level, we keep a list of pages, which are heads of continuous
- * free pages of length of (1 << order) and marked with PG_buddy. Page's
+ * free pages of length of (1 << order) and marked with _mapcount -2. Page's
  * order is recorded in page_private(page) field.
  * So when we are allocating or freeing one, we can derive the state of the
  * other.  That is, if we allocate a small block, and both were   

@@ -5251,7 +5251,6 @@ static struct trace_print_flags pageflag
 	{1UL << PG_swapcache,		"swapcache"	},
 	{1UL << PG_mappedtodisk,	"mappedtodisk"	},
 	{1UL << PG_reclaim,		"reclaim"	},
-	{1UL << PG_buddy,		"buddy"		},
 	{1UL << PG_swapbacked,		"swapbacked"	},
 	{1UL << PG_unevictable,		"unevictable"	},
 #ifdef CONFIG_MMU

@@ -670,10 +670,10 @@ static void __kfree_section_memmap(struc
 static void free_map_bootmem(struct page *page, unsigned long nr_pages)
 {
 	unsigned long maps_section_nr, removing_section_nr, i;
-	int magic;
+	unsigned long magic;
 
 	for (i = 0; i < nr_pages; i++, page++) {
-		magic = atomic_read(&page->_mapcount);
+		magic = (unsigned long) page->lru.next;
 
 		BUG_ON(magic == NODE_INFO);
 

@@ -286,6 +286,11 @@ static inline pmd_t pmd_mkwrite(pmd_t pm
 	return pmd_set_flags(pmd, _PAGE_RW);
 }
 
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+	return pmd_clear_flags(pmd, _PAGE_PRESENT);
+}
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PGTABLE_64_H */

@@ -87,6 +87,9 @@ struct vm_area_struct;
 				 __GFP_HARDWALL | __GFP_HIGHMEM | \
 				 __GFP_MOVABLE)
 #define GFP_IOFS	(__GFP_IO | __GFP_FS)
+#define GFP_TRANSHUGE	(__GFP_HARDWALL | __GFP_HIGHMEM |		\
+			 __GFP_MOVABLE | __GFP_COMP | __GFP_NOMEMALLOC | \
+			 __GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD)
 
 #ifdef CONFIG_NUMA
 #define GFP_THISNODE	(__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)

126 lines not on this page · raw message

@@ -107,6 +107,9 @@ extern unsigned int kobjsize(const void 
 #define VM_SAO		0x20000000	/* Strong Access Ordering (powerpc) */
 #define VM_PFN_AT_MMAP	0x40000000	/* PFNMAP vma that is fully mapped at mmap time */
 #define VM_MERGEABLE	0x80000000	/* KSM may merge identical pages */
+#if BITS_PER_LONG > 32
+#define VM_HUGEPAGE	0x100000000UL	/* MADV_HUGEPAGE marked this vma */
+#endif
 
 #ifndef VM_STACK_DEFAULT_FLAGS		/* arch can override this */
 #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS

@@ -235,6 +238,7 @@ struct inode;
  * files which need it (119 of them)
  */
 #include <linux/page-flags.h>
+#include <linux/huge_mm.h>
 
 /*
  * Methods to modify the page usage count.

@@ -20,11 +20,18 @@ static inline int page_is_file_cache(str
 }
 
 static inline void
+__add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l,
+		       struct list_head *head)
+{
+	list_add(&page->lru, head);
+	__inc_zone_state(zone, NR_LRU_BASE + l);
+	mem_cgroup_add_lru_list(page, l);
+}
+
+static inline void
 add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l)
 {
-	list_add(&page->lru, &zone->lru[l].list);
-	__inc_zone_state(zone, NR_LRU_BASE + l);
-	mem_cgroup_add_lru_list(page, l);
+	__add_page_to_lru_list(zone, page, l, &zone->lru[l].list);
 }
 
 static inline void

@@ -205,6 +205,8 @@ extern unsigned int nr_free_pagecache_pa
 /* linux/mm/swap.c */
 extern void __lru_cache_add(struct page *, enum lru_list lru);
 extern void lru_cache_add_lru(struct page *, enum lru_list lru);
+extern void lru_add_page_tail(struct zone* zone,
+			      struct page *page, struct page *page_tail);
 extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);

865 lines not on this page · raw message

105 lines not on this page · raw message

93 lines not on this page · raw message

@@ -461,6 +461,43 @@ void __pagevec_release(struct pagevec *p
 
 EXPORT_SYMBOL(__pagevec_release);
 
+/* used by __split_huge_page_refcount() */
+void lru_add_page_tail(struct zone* zone,
+		       struct page *page, struct page *page_tail)
+{
+	int active;
+	enum lru_list lru;
+	const int file = 0;
+	struct list_head *head;
+
+	VM_BUG_ON(!PageHead(page));
+	VM_BUG_ON(PageCompound(page_tail));
+	VM_BUG_ON(PageLRU(page_tail));
+	VM_BUG_ON(!spin_is_locked(&zone->lru_lock));
+
+	SetPageLRU(page_tail);
+
+	if (page_evictable(page_tail, NULL)) {
+		if (PageActive(page)) {
+			SetPageActive(page_tail);
+			active = 1;
+			lru = LRU_ACTIVE_ANON;
+		} else {
+			active = 0;
+			lru = LRU_INACTIVE_ANON;
+		}
+		update_page_reclaim_stat(zone, page_tail, file, active);
+		if (likely(PageLRU(page)))
+			head = page->lru.prev;
+		else
+			head = &zone->lru[lru].list;
+		__add_page_to_lru_list(zone, page_tail, lru, head);
+	} else {
+		SetPageUnevictable(page_tail);
+		add_page_to_lru_list(zone, page_tail, LRU_UNEVICTABLE);
+	}
+}
+
 /*
  * Add the passed pages to the LRU, then drop the caller's refcount
  * on them.  Reinitialises the caller's pagevec.

@@ -243,6 +243,32 @@ static inline void mmu_notifier_mm_destr
 	__pte;								\
 })
 
+#define pmdp_clear_flush_notify(__vma, __address, __pmdp)		\
+({									\
+	pmd_t __pmd;							\
+	struct vm_area_struct *___vma = __vma;				\
+	unsigned long ___address = __address;				\
+	VM_BUG_ON(__address & ~HPAGE_PMD_MASK);				\
+	mmu_notifier_invalidate_range_start(___vma->vm_mm, ___address,	\
+					    (__address)+HPAGE_PMD_SIZE);\
+	__pmd = pmdp_clear_flush(___vma, ___address, __pmdp);		\
+	mmu_notifier_invalidate_range_end(___vma->vm_mm, ___address,	\
+					  (__address)+HPAGE_PMD_SIZE);	\
+	__pmd;								\
+})
+
+#define pmdp_splitting_flush_notify(__vma, __address, __pmdp)		\
+({									\
+	struct vm_area_struct *___vma = __vma;				\
+	unsigned long ___address = __address;				\
+	VM_BUG_ON(__address & ~HPAGE_PMD_MASK);				\
+	mmu_notifier_invalidate_range_start(___vma->vm_mm, ___address,	\
+					    (__address)+HPAGE_PMD_SIZE);\
+	pmdp_splitting_flush(___vma, ___address, __pmdp);		\
+	mmu_notifier_invalidate_range_end(___vma->vm_mm, ___address,	\
+					  (__address)+HPAGE_PMD_SIZE);	\
+})
+
 #define ptep_clear_flush_young_notify(__vma, __address, __ptep)		\
 ({									\
 	int __young;							\

@@ -254,6 +280,17 @@ static inline void mmu_notifier_mm_destr
 	__young;							\
 })
 
+#define pmdp_clear_flush_young_notify(__vma, __address, __pmdp)		\
+({									\
+	int __young;							\
+	struct vm_area_struct *___vma = __vma;				\
+	unsigned long ___address = __address;				\
+	__young = pmdp_clear_flush_young(___vma, ___address, __pmdp);	\
+	__young |= mmu_notifier_clear_flush_young(___vma->vm_mm,	\
+						  ___address);		\
+	__young;							\
+})
+
 #define set_pte_at_notify(__mm, __address, __ptep, __pte)		\
 ({									\
 	struct mm_struct *___mm = __mm;					\

@@ -305,7 +342,10 @@ static inline void mmu_notifier_mm_destr
 }
 
 #define ptep_clear_flush_young_notify ptep_clear_flush_young
+#define pmdp_clear_flush_young_notify pmdp_clear_flush_young
 #define ptep_clear_flush_notify ptep_clear_flush
+#define pmdp_clear_flush_notify pmdp_clear_flush
+#define pmdp_splitting_flush_notify pmdp_splitting_flush
 #define set_pte_at_notify set_pte_at
 
 #endif /* CONFIG_MMU_NOTIFIER */

@@ -225,6 +225,7 @@ static int __do_huge_pmd_anonymous_page(
 	VM_BUG_ON(!PageCompound(page));
 	pgtable = pte_alloc_one(mm, haddr);
 	if (unlikely(!pgtable)) {
+		mem_cgroup_uncharge_page(page);
 		put_page(page);
 		return VM_FAULT_OOM;
 	}

@@ -235,6 +236,7 @@ static int __do_huge_pmd_anonymous_page(
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_none(*pmd))) {
 		spin_unlock(&mm->page_table_lock);
+		mem_cgroup_uncharge_page(page);
 		put_page(page);
 		pte_free(mm, pgtable);
 	} else {

@@ -278,6 +280,10 @@ int do_huge_pmd_anonymous_page(struct mm
 		page = alloc_hugepage(transparent_hugepage_defrag(vma));
 		if (unlikely(!page))
 			goto out;
+		if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
+			put_page(page);
+			goto out;
+		}
 
 		return __do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page);
 	}

@@ -377,9 +383,15 @@ static int do_huge_pmd_wp_page_fallback(
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
 		pages[i] = alloc_page_vma(GFP_HIGHUSER_MOVABLE,
 					  vma, address);
-		if (unlikely(!pages[i])) {
-			while (--i >= 0)
+		if (unlikely(!pages[i] ||
+			     mem_cgroup_newpage_charge(pages[i], mm,
+						       GFP_KERNEL))) {
+			if (pages[i])
 				put_page(pages[i]);
+			while (--i >= 0) {
+				mem_cgroup_uncharge_page(pages[i]);
+				put_page(pages[i]);
+			}
 			kfree(pages);
 			ret |= VM_FAULT_OOM;
 			goto out;

@@ -438,8 +450,10 @@ out:
 
 out_free_pages:
 	spin_unlock(&mm->page_table_lock);
-	for (i = 0; i < HPAGE_PMD_NR; i++)
+	for (i = 0; i < HPAGE_PMD_NR; i++) {
+		mem_cgroup_uncharge_page(pages[i]);
 		put_page(pages[i]);
+	}
 	kfree(pages);
 	goto out;
 }

@@ -482,13 +496,19 @@ int do_huge_pmd_wp_page(struct mm_struct
 		goto out;
 	}
 
+	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
+		put_page(new_page);
+		ret |= VM_FAULT_OOM;
+		goto out;
+	}
 	copy_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
 	__SetPageUptodate(new_page);
 
 	spin_lock(&mm->page_table_lock);
-	if (unlikely(!pmd_same(*pmd, orig_pmd)))
+	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
+		mem_cgroup_uncharge_page(new_page);
 		put_page(new_page);
-	else {
+	} else {
 		pmd_t entry;
 		entry = mk_pmd(new_page, vma->vm_page_prot);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);

257 lines not on this page · raw message

@@ -105,6 +105,10 @@ static inline int PageTransHuge(struct p
 	VM_BUG_ON(PageTail(page));
 	return PageHead(page);
 }
+static inline int PageTransCompound(struct page *page)
+{
+	return PageCompound(page);
+}
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 #define HPAGE_PMD_SHIFT ({ BUG(); 0; })
 #define HPAGE_PMD_MASK ({ BUG(); 0; })

@@ -122,6 +126,7 @@ static inline int split_huge_page(struct
 #define wait_split_huge_page(__anon_vma, __pmd)	\
 	do { } while (0)
 #define PageTransHuge(page) 0
+#define PageTransCompound(page) 0
 static inline int hugepage_madvise(unsigned long *vm_flags)
 {
 	BUG_ON(0);

@@ -94,6 +94,7 @@ static int remove_migration_pte(struct p
 		goto out;
 
 	pmd = pmd_offset(pud, addr);
+	VM_BUG_ON(pmd_trans_huge(*pmd));
 	if (!pmd_present(*pmd))
 		goto out;
 

@@ -810,6 +811,10 @@ static int do_move_page_to_node_array(st
 		if (PageReserved(page) || PageKsm(page))
 			goto put_and_set;
 
+		if (unlikely(PageTransCompound(page)))
+			if (unlikely(split_huge_page(page)))
+				goto put_and_set;
+
 		pp->page = page;
 		err = page_to_nid(page);