MADV_FREE support

index be574506e6a9..0ba377b97a38 100644
@@ -75,6 +75,7 @@ enum ttu_flags {
 	TTU_UNMAP = 1,			/* unmap mode */
 	TTU_MIGRATION = 2,		/* migration mode */
 	TTU_MUNLOCK = 4,		/* munlock mode */
+	TTU_FREE = 8,			/* free mode */
 
 	TTU_IGNORE_MLOCK = (1 << 8),	/* ignore mlock */
 	TTU_IGNORE_ACCESS = (1 << 9),	/* don't age */

@@ -181,7 +182,8 @@ static inline void page_dup_rmap(struct page *page)
  * Called from mm/vmscan.c to handle paging out
  */
 int page_referenced(struct page *, int is_locked,
-			struct mem_cgroup *memcg, unsigned long *vm_flags);
+			struct mem_cgroup *memcg, unsigned long *vm_flags,
+			int *is_dirty);
 
 #define TTU_ACTION(x) ((x) & TTU_ACTION_MASK)
 

@@ -260,9 +262,12 @@ int rmap_walk(struct page *page, struct rmap_walk_control *rwc);
 
 static inline int page_referenced(struct page *page, int is_locked,
 				  struct mem_cgroup *memcg,
-				  unsigned long *vm_flags)
+				  unsigned long *vm_flags,
+				  int *is_pte_dirty)
 {
 	*vm_flags = 0;
+	if (is_pte_dirty)
+		*is_pte_dirty = 0;
 	return 0;
 }
 

index ced92345c963..e2d3fb1e9814 100644
@@ -25,6 +25,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		FOR_ALL_ZONES(PGALLOC),
 		PGFREE, PGACTIVATE, PGDEACTIVATE,
 		PGFAULT, PGMAJFAULT,
+		PGLAZYFREED,
 		FOR_ALL_ZONES(PGREFILL),
 		FOR_ALL_ZONES(PGSTEAL_KSWAPD),
 		FOR_ALL_ZONES(PGSTEAL_DIRECT),

index ddc3b36f1046..7a94102b7a02 100644
@@ -34,6 +34,7 @@
 #define MADV_SEQUENTIAL	2		/* expect sequential page references */
 #define MADV_WILLNEED	3		/* will need these pages */
 #define MADV_DONTNEED	4		/* don't need these pages */
+#define MADV_FREE	5		/* free pages only if memory pressure */
 
 /* common parameters: try to keep these consistent across architectures */
 #define MADV_REMOVE	9		/* remove these pages & resources */

170 lines not on this page · raw message

120 lines not on this page · raw message

index 27432baea971..598e2ade21f7 100644
@@ -710,13 +710,17 @@ enum page_references {
 };
 
 static enum page_references page_check_references(struct page *page,
-						  struct scan_control *sc)
+						  struct scan_control *sc,
+						  bool *freeable)
 {
 	int referenced_ptes, referenced_page;
 	unsigned long vm_flags;
+	int pte_dirty;
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
 	referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup,
-					  &vm_flags);
+					  &vm_flags, &pte_dirty);
 	referenced_page = TestClearPageReferenced(page);
 
 	/*

@@ -757,6 +761,10 @@ static enum page_references page_check_references(struct page *page,
 		return PAGEREF_KEEP;
 	}
 
+	if (PageAnon(page) && !pte_dirty && !PageSwapCache(page) &&
+			!PageDirty(page))
+		*freeable = true;
+
 	/* Reclaim if clean, defer dirty pages to writeback */
 	if (referenced_page && !PageSwapBacked(page))
 		return PAGEREF_RECLAIM_CLEAN;

@@ -825,6 +833,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		int may_enter_fs;
 		enum page_references references = PAGEREF_RECLAIM_CLEAN;
 		bool dirty, writeback;
+		bool freeable = false;
 
 		cond_resched();
 

@@ -947,7 +956,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		}
 
 		if (!force_reclaim)
-			references = page_check_references(page, sc);
+			references = page_check_references(page, sc,
+							&freeable);
 
 		switch (references) {
 		case PAGEREF_ACTIVATE:

@@ -963,7 +973,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * Anonymous process memory has backing store?
 		 * Try to allocate it some swap space here.
 		 */
-		if (PageAnon(page) && !PageSwapCache(page)) {
+		if (PageAnon(page) && !PageSwapCache(page) && !freeable) {
 			if (!(sc->gfp_mask & __GFP_IO))
 				goto keep_locked;
 			if (!add_to_swap(page, page_list))

@@ -978,8 +988,9 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * The page is mapped into the page tables of one or more
 		 * processes. Try to unmap it here.
 		 */
-		if (page_mapped(page) && mapping) {
-			switch (try_to_unmap(page, ttu_flags)) {
+		if (page_mapped(page) && (mapping || freeable)) {
+			switch (try_to_unmap(page,
+				freeable ? TTU_FREE : ttu_flags)) {
 			case SWAP_FAIL:
 				goto activate_locked;
 			case SWAP_AGAIN:

@@ -987,7 +998,20 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			case SWAP_MLOCK:
 				goto cull_mlocked;
 			case SWAP_SUCCESS:
-				; /* try to free the page below */
+				/* try to free the page below */
+				if (!freeable)
+					break;
+				/*
+				 * Freeable anon page doesn't have mapping
+				 * due to skipping of swapcache so we free
+				 * page in here rather than __remove_mapping.
+				 */
+				VM_BUG_ON_PAGE(PageSwapCache(page), page);
+				if (!page_freeze_refs(page, 1))
+					goto keep_locked;
+				__clear_page_locked(page);
+				count_vm_event(PGLAZYFREED);
+				goto free_it;
 			}
 		}
 

@@ -1727,7 +1751,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 		}
 
 		if (page_referenced(page, 0, sc->target_mem_cgroup,
-				    &vm_flags)) {
+				    &vm_flags, NULL)) {
 			nr_rotated += hpage_nr_pages(page);
 			/*
 			 * Identify referenced, file-backed active pages and

index 7e036f9db098..5414b8a88641 100644
@@ -811,6 +811,7 @@ const char * const vmstat_text[] = {
 
 	"pgfault",
 	"pgmajfault",
+	"pglazyfreed",
 
 	TEXTS_FOR_ZONES("pgrefill")
 	TEXTS_FOR_ZONES("pgsteal_kswapd")

index 0ec056012618..329865799653 100644
@@ -104,6 +104,11 @@ static inline int pmd_young(pmd_t pmd)
 	return pmd_flags(pmd) & _PAGE_ACCESSED;
 }
 
+static inline int pmd_dirty(pmd_t pmd)
+{
+	return pmd_flags(pmd) & _PAGE_DIRTY;
+}
+
 static inline int pte_write(pte_t pte)
 {
 	return pte_flags(pte) & _PAGE_RW;

@@ -267,6 +272,11 @@ static inline pmd_t pmd_mkold(pmd_t pmd)
 	return pmd_clear_flags(pmd, _PAGE_ACCESSED);
 }
 
+static inline pmd_t pmd_mkclean(pmd_t pmd)
+{
+	return pmd_clear_flags(pmd, _PAGE_DIRTY);
+}
+
 static inline pmd_t pmd_wrprotect(pmd_t pmd)
 {
 	return pmd_clear_flags(pmd, _PAGE_RW);

index 3770bf5c6e1b..b80a309d7e00 100644
@@ -666,6 +666,13 @@ static inline unsigned long pmd_young(pmd_t pmd)
 	return pte_young(pte);
 }
 
+static inline int pmd_dirty(pmd_t pmd)
+{
+	pte_t pte = __pte(pmd_val(pmd));
+
+	return pte_dirty(pte);
+}
+
 static inline unsigned long pmd_write(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));

@@ -723,6 +730,15 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
 	return __pmd(pte_val(pte));
 }
 
+static inline pmd_t pmd_mkclean(pmd_t pmd)
+{
+	pte_t pte = __pte(pmd_val(pmd));
+
+	pte = pte_mkclean(pte);
+
+	return __pmd(pte_val(pte));
+}
+
 static inline pmd_t pmd_mkyoung(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));

index eb9261024f51..c9a4bbe8e179 100644
@@ -468,9 +468,11 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd)
 
 #define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
+#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
 #define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
 

index fcba5e03839f..9862fcb0592b 100644
@@ -1586,6 +1586,18 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
 	return pmd;
 }
 
+static inline int pmd_dirty(pmd_t pmd)
+{
+	/* No dirty bit in the segment table entry */
+	return 1;
+}
+
+static inline pmd_t pmd_mkclean(pmd_t pmd)
+{
+	/* No dirty bit in the segment table entry */
+	return pmd;
+}
+
 #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
 static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long address, pmd_t *pmdp)

index 85c60adc8b60..830f84f2d277 100644
@@ -220,6 +220,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
 #endif
 
+#define pmd_dirty(pmd)		(pmd_val(pmd) & PMD_SECT_DIRTY)
+
 #define PMD_BIT_FUNC(fn,op) \
 static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
 

@@ -228,6 +230,7 @@ PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
 PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
 PMD_BIT_FUNC(mkwrite,   &= ~PMD_SECT_RDONLY);
 PMD_BIT_FUNC(mkdirty,   |= PMD_SECT_DIRTY);
+PMD_BIT_FUNC(mkclean,   &= ~PMD_SECT_DIRTY);
 PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))

index e0ccceb317d9..41dfe3c7260c 100644
@@ -240,10 +240,12 @@ static inline pmd_t pte_pmd(pte_t pte)
 #endif
 
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
+#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
 #define pmd_mksplitting(pmd)	pte_pmd(pte_mkspecial(pmd_pte(pmd)))
 #define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
 #define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+#define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
 #define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK))

index 63579cb8d3dc..25a961256d9f 100644
@@ -19,6 +19,9 @@ extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 					  unsigned long addr,
 					  pmd_t *pmd,
 					  unsigned int flags);
+extern int madvise_free_huge_pmd(struct mmu_gather *tlb,
+			struct vm_area_struct *vma,
+			pmd_t *pmd, unsigned long addr);
 extern int zap_huge_pmd(struct mmu_gather *tlb,
 			struct vm_area_struct *vma,
 			pmd_t *pmd, unsigned long addr);

@@ -56,6 +59,7 @@ extern pmd_t *page_check_address_pmd(struct page *page,
 				     unsigned long address,
 				     enum page_check_address_pmd_flag flag,
 				     spinlock_t **ptl);
+extern int pmd_freeable(pmd_t pmd);
 
 #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
 #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)

index 02559efd9827..c238a19a648f 100644
@@ -1384,6 +1384,36 @@ out:
 	return 0;
 }
 
+int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
+		 pmd_t *pmd, unsigned long addr)
+
+{
+	spinlock_t *ptl;
+	struct mm_struct *mm = tlb->mm;
+	int ret = 1;
+
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+		struct page *page;
+		pmd_t orig_pmd;
+
+		orig_pmd = pmdp_get_and_clear(mm, addr, pmd);
+
+		/* No hugepage in swapcache */
+		page = pmd_page(orig_pmd);
+		VM_BUG_ON_PAGE(PageSwapCache(page), page);
+
+		orig_pmd = pmd_mkold(orig_pmd);
+		orig_pmd = pmd_mkclean(orig_pmd);
+
+		set_pmd_at(mm, addr, pmd, orig_pmd);
+		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
+		spin_unlock(ptl);
+		ret = 0;
+	}
+
+	return ret;
+}
+
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 pmd_t *pmd, unsigned long addr)
 {

@@ -1620,6 +1650,11 @@ unlock:
 	return NULL;
 }
 
+int pmd_freeable(pmd_t pmd)
+{
+	return !pmd_dirty(pmd);
+}
+
 static int __split_huge_page_splitting(struct page *page,
 				       struct vm_area_struct *vma,
 				       unsigned long address)

index a21584235bb6..84badee5f46d 100644
@@ -271,8 +271,26 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 	spinlock_t *ptl;
 	pte_t *pte, ptent;
 	struct page *page;
+	unsigned long next;
+
+	next = pmd_addr_end(addr, end);
+	if (pmd_trans_huge(*pmd)) {
+		if (next - addr != HPAGE_PMD_SIZE) {
+#ifdef CONFIG_DEBUG_VM
+			if (!rwsem_is_locked(&mm->mmap_sem)) {
+				pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n",
+					__func__, addr, end,
+					vma->vm_start,
+					vma->vm_end);
+				BUG();
+			}
+#endif
+			split_huge_page_pmd(vma, addr, pmd);
+		} else if (!madvise_free_huge_pmd(tlb, vma, pmd, addr))
+			goto next;
+		/* fall through */
+	}
 
-	split_huge_page_pmd(vma, addr, pmd);
 	if (pmd_trans_unstable(pmd))
 		return 0;
 

@@ -316,6 +334,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 	}
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
+next:
 	cond_resched();
 	return 0;
 }

index 04c181133890..9c407576ff8e 100644
@@ -704,9 +704,13 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 			referenced++;
 
 		/*
-		 * In this implmentation, MADV_FREE doesn't support THP free
+		 * Use pmd_freeable instead of raw pmd_dirty because in some
+		 * of architecture, pmd_dirty is not defined unless
+		 * CONFIG_TRANSPARNTE_HUGE is enabled
 		 */
-		dirty++;
+		if (!pmd_freeable(*pmd))
+			dirty++;
+
 		spin_unlock(ptl);
 	} else {
 		pte_t *pte;

index 598e2ade21f7..b1428bdad88e 100644
@@ -973,17 +973,25 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * Anonymous process memory has backing store?
 		 * Try to allocate it some swap space here.
 		 */
-		if (PageAnon(page) && !PageSwapCache(page) && !freeable) {
-			if (!(sc->gfp_mask & __GFP_IO))
-				goto keep_locked;
-			if (!add_to_swap(page, page_list))
-				goto activate_locked;
-			may_enter_fs = 1;
-
-			/* Adding to swap updated mapping */
-			mapping = page_mapping(page);
+		if (PageAnon(page) && !PageSwapCache(page)) {
+			if (!freeable) {
+				if (!(sc->gfp_mask & __GFP_IO))
+					goto keep_locked;
+				if (!add_to_swap(page, page_list))
+					goto activate_locked;
+				may_enter_fs = 1;
+				/* Adding to swap updated mapping */
+				mapping = page_mapping(page);
+			} else {
+				if (likely(!PageTransHuge(page)))
+					goto unmap;
+				/* try_to_unmap isn't aware of THP page */
+				if (unlikely(split_huge_page_to_list(page,
+								page_list)))
+					goto keep_locked;
+			}
 		}
-
+unmap:
 		/*
 		 * The page is mapped into the page tables of one or more
 		 * processes. Try to unmap it here.