Transparent Hugepage Support #15

@@ -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);
 }

@@ -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;
 }

@@ -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

@@ -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,

@@ -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

@@ -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;

@@ -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.

@@ -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)

@@ -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)
 {
 	/*

@@ -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

@@ -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)

@@ -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 */