Merge branch 'akpm' (patches from Andrew Morton)

Merge a bunch of fixes from Andrew Morton.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  fs/proc/task_mmu.c: fix buffer overflow in add_page_map()
  arch: *: Kconfig: add "kernel/Kconfig.freezer" to "arch/*/Kconfig"
  ocfs2: fix null pointer dereference in ocfs2_dir_foreach_blk_id()
  x86 get_unmapped_area(): use proper mmap base for bottom-up direction
  ocfs2: fix NULL pointer dereference in ocfs2_duplicate_clusters_by_page
  ocfs2: Revert 40bd62eb to avoid regression in extended allocation
  drivers/rtc/rtc-stmp3xxx.c: provide timeout for potentially endless loop polling a HW bit
  hugetlb: fix lockdep splat caused by pmd sharing
  aoe: adjust ref of head for compound page tails
  microblaze: fix clone syscall
  mm: save soft-dirty bits on file pages
  mm: save soft-dirty bits on swapped pages
  memcg: don't initialize kmem-cache destroying work for root caches

arch/Kconfig

@@ -407,6 +407,12 @@ config CLONE_BACKWARDS2
 	help
 	  Architecture has the first two arguments of clone(2) swapped.
 
+config CLONE_BACKWARDS3
+	bool
+	help
+	  Architecture has tls passed as the 3rd argument of clone(2),
+	  not the 5th one.
+
 config ODD_RT_SIGACTION
 	bool
 	help

arch/hexagon/Kconfig

@@ -158,6 +158,7 @@ source "kernel/Kconfig.hz"
 endmenu
 
 source "init/Kconfig"
+source "kernel/Kconfig.freezer"
 source "drivers/Kconfig"
 source "fs/Kconfig"
 

arch/microblaze/Kconfig

@@ -28,7 +28,7 @@ config MICROBLAZE
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_IDLE_POLL_SETUP
 	select MODULES_USE_ELF_RELA
-	select CLONE_BACKWARDS
+	select CLONE_BACKWARDS3
 
 config SWAP
 	def_bool n

arch/openrisc/Kconfig

@@ -55,6 +55,7 @@ config GENERIC_CSUM
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
 
 menu "Processor type and features"
 

arch/score/Kconfig

@@ -87,6 +87,8 @@ config STACKTRACE_SUPPORT
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 config MMU
 	def_bool y
 

arch/x86/include/asm/pgtable-2level.h

@@ -55,9 +55,53 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
 #endif
 
+#ifdef CONFIG_MEM_SOFT_DIRTY
+
+/*
+ * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE, _PAGE_BIT_SOFT_DIRTY and
+ * _PAGE_BIT_PROTNONE are taken, split up the 28 bits of offset
+ * into this range.
+ */
+#define PTE_FILE_MAX_BITS	28
+#define PTE_FILE_SHIFT1		(_PAGE_BIT_PRESENT + 1)
+#define PTE_FILE_SHIFT2		(_PAGE_BIT_FILE + 1)
+#define PTE_FILE_SHIFT3		(_PAGE_BIT_PROTNONE + 1)
+#define PTE_FILE_SHIFT4		(_PAGE_BIT_SOFT_DIRTY + 1)
+#define PTE_FILE_BITS1		(PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1)
+#define PTE_FILE_BITS2		(PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1)
+#define PTE_FILE_BITS3		(PTE_FILE_SHIFT4 - PTE_FILE_SHIFT3 - 1)
+
+#define pte_to_pgoff(pte)						\
+	((((pte).pte_low >> (PTE_FILE_SHIFT1))				\
+	  & ((1U << PTE_FILE_BITS1) - 1)))				\
+	+ ((((pte).pte_low >> (PTE_FILE_SHIFT2))			\
+	    & ((1U << PTE_FILE_BITS2) - 1))				\
+	   << (PTE_FILE_BITS1))						\
+	+ ((((pte).pte_low >> (PTE_FILE_SHIFT3))			\
+	    & ((1U << PTE_FILE_BITS3) - 1))				\
+	   << (PTE_FILE_BITS1 + PTE_FILE_BITS2))			\
+	+ ((((pte).pte_low >> (PTE_FILE_SHIFT4)))			\
+	    << (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3))
+
+#define pgoff_to_pte(off)						\
+	((pte_t) { .pte_low =						\
+	 ((((off)) & ((1U << PTE_FILE_BITS1) - 1)) << PTE_FILE_SHIFT1)	\
+	 + ((((off) >> PTE_FILE_BITS1)					\
+	     & ((1U << PTE_FILE_BITS2) - 1))				\
+	    << PTE_FILE_SHIFT2)						\
+	 + ((((off) >> (PTE_FILE_BITS1 + PTE_FILE_BITS2))		\
+	     & ((1U << PTE_FILE_BITS3) - 1))				\
+	    << PTE_FILE_SHIFT3)						\
+	 + ((((off) >>							\
+	      (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3)))	\
+	    << PTE_FILE_SHIFT4)						\
+	 + _PAGE_FILE })
+
+#else /* CONFIG_MEM_SOFT_DIRTY */
+
 /*
  * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken,
- * split up the 29 bits of offset into this range:
+ * split up the 29 bits of offset into this range.
  */
 #define PTE_FILE_MAX_BITS	29
 #define PTE_FILE_SHIFT1		(_PAGE_BIT_PRESENT + 1)
@@ -88,6 +132,8 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 	    << PTE_FILE_SHIFT3)						\
 	 + _PAGE_FILE })
 
+#endif /* CONFIG_MEM_SOFT_DIRTY */
+
 /* Encode and de-code a swap entry */
 #if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
 #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)

arch/x86/include/asm/pgtable-3level.h

@@ -179,6 +179,9 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
 /*
  * Bits 0, 6 and 7 are taken in the low part of the pte,
  * put the 32 bits of offset into the high part.
+ *
+ * For soft-dirty tracking 11 bit is taken from
+ * the low part of pte as well.
  */
 #define pte_to_pgoff(pte) ((pte).pte_high)
 #define pgoff_to_pte(off)						\

arch/x86/include/asm/pgtable.h

@@ -314,6 +314,36 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
 	return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY);
 }
 
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+	return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline int pte_swp_soft_dirty(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
+}
+
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+	return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline pte_t pte_file_clear_soft_dirty(pte_t pte)
+{
+	return pte_clear_flags(pte, _PAGE_SOFT_DIRTY);
+}
+
+static inline pte_t pte_file_mksoft_dirty(pte_t pte)
+{
+	return pte_set_flags(pte, _PAGE_SOFT_DIRTY);
+}
+
+static inline int pte_file_soft_dirty(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_SOFT_DIRTY;
+}
+
 /*
  * Mask out unsupported bits in a present pgprot.  Non-present pgprots
  * can use those bits for other purposes, so leave them be.

arch/x86/include/asm/pgtable_types.h

@@ -61,12 +61,27 @@
  * they do not conflict with each other.
  */
 
+#define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_HIDDEN
+
 #ifdef CONFIG_MEM_SOFT_DIRTY
-#define _PAGE_SOFT_DIRTY	(_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN)
+#define _PAGE_SOFT_DIRTY	(_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY)
 #else
 #define _PAGE_SOFT_DIRTY	(_AT(pteval_t, 0))
 #endif
 
+/*
+ * Tracking soft dirty bit when a page goes to a swap is tricky.
+ * We need a bit which can be stored in pte _and_ not conflict
+ * with swap entry format. On x86 bits 6 and 7 are *not* involved
+ * into swap entry computation, but bit 6 is used for nonlinear
+ * file mapping, so we borrow bit 7 for soft dirty tracking.
+ */
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define _PAGE_SWP_SOFT_DIRTY	_PAGE_PSE
+#else
+#define _PAGE_SWP_SOFT_DIRTY	(_AT(pteval_t, 0))
+#endif
+
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 #define _PAGE_NX	(_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #else

arch/x86/kernel/sys_x86_64.c

@@ -101,7 +101,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin,
 				*begin = new_begin;
 		}
 	} else {
-		*begin = TASK_UNMAPPED_BASE;
+		*begin = mmap_legacy_base();
 		*end = TASK_SIZE;
 	}
 }

arch/x86/mm/mmap.c

@@ -98,7 +98,7 @@ static unsigned long mmap_base(void)
  * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64
  * does, but not when emulating X86_32
  */
-static unsigned long mmap_legacy_base(void)
+unsigned long mmap_legacy_base(void)
 {
 	if (mmap_is_ia32())
 		return TASK_UNMAPPED_BASE;

drivers/block/aoe/aoecmd.c

@@ -906,16 +906,10 @@ bio_pageinc(struct bio *bio)
 	int i;
 
 	bio_for_each_segment(bv, bio, i) {
-		page = bv->bv_page;
 		/* Non-zero page count for non-head members of
-		 * compound pages is no longer allowed by the kernel,
-		 * but this has never been seen here.
+		 * compound pages is no longer allowed by the kernel.
 		 */
-		if (unlikely(PageCompound(page)))
-			if (compound_trans_head(page) != page) {
-				pr_crit("page tail used for block I/O\n");
-				BUG();
-			}
+		page = compound_trans_head(bv->bv_page);
 		atomic_inc(&page->_count);
 	}
 }
@@ -924,10 +918,13 @@ static void
 bio_pagedec(struct bio *bio)
 {
 	struct bio_vec *bv;
+	struct page *page;
 	int i;
 
-	bio_for_each_segment(bv, bio, i)
-		atomic_dec(&bv->bv_page->_count);
+	bio_for_each_segment(bv, bio, i) {
+		page = compound_trans_head(bv->bv_page);
+		atomic_dec(&page->_count);
+	}
 }
 
 static void

drivers/rtc/rtc-stmp3xxx.c

@@ -23,6 +23,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
+#include <linux/delay.h>
 #include <linux/rtc.h>
 #include <linux/slab.h>
 #include <linux/of_device.h>
@@ -119,24 +120,39 @@ static void stmp3xxx_wdt_register(struct platform_device *rtc_pdev)
 }
 #endif /* CONFIG_STMP3XXX_RTC_WATCHDOG */
 
-static void stmp3xxx_wait_time(struct stmp3xxx_rtc_data *rtc_data)
+static int stmp3xxx_wait_time(struct stmp3xxx_rtc_data *rtc_data)
 {
+	int timeout = 5000; /* 3ms according to i.MX28 Ref Manual */
 	/*
-	 * The datasheet doesn't say which way round the
-	 * NEW_REGS/STALE_REGS bitfields go. In fact it's 0x1=P0,
-	 * 0x2=P1, .., 0x20=P5, 0x40=ALARM, 0x80=SECONDS
+	 * The i.MX28 Applications Processor Reference Manual, Rev. 1, 2010
+	 * states:
+	 * | The order in which registers are updated is
+	 * | Persistent 0, 1, 2, 3, 4, 5, Alarm, Seconds.
+	 * | (This list is in bitfield order, from LSB to MSB, as they would
+	 * | appear in the STALE_REGS and NEW_REGS bitfields of the HW_RTC_STAT
+	 * | register. For example, the Seconds register corresponds to
+	 * | STALE_REGS or NEW_REGS containing 0x80.)
 	 */
-	while (readl(rtc_data->io + STMP3XXX_RTC_STAT) &
-			(0x80 << STMP3XXX_RTC_STAT_STALE_SHIFT))
-		cpu_relax();
+	do {
+		if (!(readl(rtc_data->io + STMP3XXX_RTC_STAT) &
+				(0x80 << STMP3XXX_RTC_STAT_STALE_SHIFT)))
+			return 0;
+		udelay(1);
+	} while (--timeout > 0);
+	return (readl(rtc_data->io + STMP3XXX_RTC_STAT) &
+		(0x80 << STMP3XXX_RTC_STAT_STALE_SHIFT)) ? -ETIME : 0;
 }
 
 /* Time read/write */
 static int stmp3xxx_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm)
 {
+	int ret;
 	struct stmp3xxx_rtc_data *rtc_data = dev_get_drvdata(dev);
 
-	stmp3xxx_wait_time(rtc_data);
+	ret = stmp3xxx_wait_time(rtc_data);
+	if (ret)
+		return ret;
+
 	rtc_time_to_tm(readl(rtc_data->io + STMP3XXX_RTC_SECONDS), rtc_tm);
 	return 0;
 }
@@ -146,8 +162,7 @@ static int stmp3xxx_rtc_set_mmss(struct device *dev, unsigned long t)
 	struct stmp3xxx_rtc_data *rtc_data = dev_get_drvdata(dev);
 
 	writel(t, rtc_data->io + STMP3XXX_RTC_SECONDS);
-	stmp3xxx_wait_time(rtc_data);
-	return 0;
+	return stmp3xxx_wait_time(rtc_data);
 }
 
 /* interrupt(s) handler */

fs/hugetlbfs/inode.c

@@ -463,6 +463,14 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
 	return inode;
 }
 
+/*
+ * Hugetlbfs is not reclaimable; therefore its i_mmap_mutex will never
+ * be taken from reclaim -- unlike regular filesystems. This needs an
+ * annotation because huge_pmd_share() does an allocation under
+ * i_mmap_mutex.
+ */
+struct lock_class_key hugetlbfs_i_mmap_mutex_key;
+
 static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 					struct inode *dir,
 					umode_t mode, dev_t dev)
@@ -474,6 +482,8 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		struct hugetlbfs_inode_info *info;
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
+		lockdep_set_class(&inode->i_mapping->i_mmap_mutex,
+				&hugetlbfs_i_mmap_mutex_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
 		inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;

fs/ocfs2/aops.c

@@ -1757,7 +1757,7 @@ int ocfs2_write_begin_nolock(struct file *filp,
 		goto out;
 	} else if (ret == 1) {
 		clusters_need = wc->w_clen;
-		ret = ocfs2_refcount_cow(inode, filp, di_bh,
+		ret = ocfs2_refcount_cow(inode, di_bh,
 					 wc->w_cpos, wc->w_clen, UINT_MAX);
 		if (ret) {
 			mlog_errno(ret);

fs/ocfs2/dir.c

@@ -2153,11 +2153,9 @@ int ocfs2_empty_dir(struct inode *inode)
 {
 	int ret;
 	struct ocfs2_empty_dir_priv priv = {
-		.ctx.actor = ocfs2_empty_dir_filldir
+		.ctx.actor = ocfs2_empty_dir_filldir,
 	};
 
-	memset(&priv, 0, sizeof(priv));
-
 	if (ocfs2_dir_indexed(inode)) {
 		ret = ocfs2_empty_dir_dx(inode, &priv);
 		if (ret)

fs/ocfs2/file.c

@@ -370,7 +370,7 @@ static int ocfs2_cow_file_pos(struct inode *inode,
 	if (!(ext_flags & OCFS2_EXT_REFCOUNTED))
 		goto out;
 
-	return ocfs2_refcount_cow(inode, NULL, fe_bh, cpos, 1, cpos+1);
+	return ocfs2_refcount_cow(inode, fe_bh, cpos, 1, cpos+1);
 
 out:
 	return status;
@@ -899,7 +899,7 @@ static int ocfs2_zero_extend_get_range(struct inode *inode,
 		zero_clusters = last_cpos - zero_cpos;
 
 	if (needs_cow) {
-		rc = ocfs2_refcount_cow(inode, NULL, di_bh, zero_cpos,
+		rc = ocfs2_refcount_cow(inode, di_bh, zero_cpos,
 					zero_clusters, UINT_MAX);
 		if (rc) {
 			mlog_errno(rc);
@@ -2078,7 +2078,7 @@ static int ocfs2_prepare_inode_for_refcount(struct inode *inode,
 
 	*meta_level = 1;
 
-	ret = ocfs2_refcount_cow(inode, file, di_bh, cpos, clusters, UINT_MAX);
+	ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX);
 	if (ret)
 		mlog_errno(ret);
 out:

fs/ocfs2/journal.h

@@ -537,7 +537,7 @@ static inline int ocfs2_calc_extend_credits(struct super_block *sb,
 	extent_blocks = 1 + 1 + le16_to_cpu(root_el->l_tree_depth);
 
 	return bitmap_blocks + sysfile_bitmap_blocks + extent_blocks +
-	       ocfs2_quota_trans_credits(sb) + bits_wanted;
+	       ocfs2_quota_trans_credits(sb);
 }
 
 static inline int ocfs2_calc_symlink_credits(struct super_block *sb)

fs/ocfs2/move_extents.c

@@ -69,7 +69,7 @@ static int __ocfs2_move_extent(handle_t *handle,
 	u64 ino = ocfs2_metadata_cache_owner(context->et.et_ci);
 	u64 old_blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cpos);
 
-	ret = ocfs2_duplicate_clusters_by_page(handle, context->file, cpos,
+	ret = ocfs2_duplicate_clusters_by_page(handle, inode, cpos,
 					       p_cpos, new_p_cpos, len);
 	if (ret) {
 		mlog_errno(ret);

fs/ocfs2/refcounttree.c

@@ -49,7 +49,6 @@
 
 struct ocfs2_cow_context {
 	struct inode *inode;
-	struct file *file;
 	u32 cow_start;
 	u32 cow_len;
 	struct ocfs2_extent_tree data_et;
@@ -66,7 +65,7 @@ struct ocfs2_cow_context {
 			    u32 *num_clusters,
 			    unsigned int *extent_flags);
 	int (*cow_duplicate_clusters)(handle_t *handle,
-				      struct file *file,
+				      struct inode *inode,
 				      u32 cpos, u32 old_cluster,
 				      u32 new_cluster, u32 new_len);
 };
@@ -2922,14 +2921,12 @@ static int ocfs2_clear_cow_buffer(handle_t *handle, struct buffer_head *bh)
 }
 
 int ocfs2_duplicate_clusters_by_page(handle_t *handle,
-				     struct file *file,
+				     struct inode *inode,
 				     u32 cpos, u32 old_cluster,
 				     u32 new_cluster, u32 new_len)
 {
 	int ret = 0, partial;
-	struct inode *inode = file_inode(file);
-	struct ocfs2_caching_info *ci = INODE_CACHE(inode);
-	struct super_block *sb = ocfs2_metadata_cache_get_super(ci);
+	struct super_block *sb = inode->i_sb;
 	u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster);
 	struct page *page;
 	pgoff_t page_index;
@@ -2978,13 +2975,6 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 		if (PAGE_CACHE_SIZE <= OCFS2_SB(sb)->s_clustersize)
 			BUG_ON(PageDirty(page));
 
-		if (PageReadahead(page)) {
-			page_cache_async_readahead(mapping,
-						   &file->f_ra, file,
-						   page, page_index,
-						   readahead_pages);
-		}
-
 		if (!PageUptodate(page)) {
 			ret = block_read_full_page(page, ocfs2_get_block);
 			if (ret) {
@@ -3004,7 +2994,8 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 			}
 		}
 
-		ocfs2_map_and_dirty_page(inode, handle, from, to,
+		ocfs2_map_and_dirty_page(inode,
+					 handle, from, to,
 					 page, 0, &new_block);
 		mark_page_accessed(page);
 unlock:
@@ -3020,12 +3011,11 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 }
 
 int ocfs2_duplicate_clusters_by_jbd(handle_t *handle,
-				    struct file *file,
+				    struct inode *inode,
 				    u32 cpos, u32 old_cluster,
 				    u32 new_cluster, u32 new_len)
 {
 	int ret = 0;
-	struct inode *inode = file_inode(file);
 	struct super_block *sb = inode->i_sb;
 	struct ocfs2_caching_info *ci = INODE_CACHE(inode);
 	int i, blocks = ocfs2_clusters_to_blocks(sb, new_len);
@@ -3150,7 +3140,7 @@ static int ocfs2_replace_clusters(handle_t *handle,
 
 	/*If the old clusters is unwritten, no need to duplicate. */
 	if (!(ext_flags & OCFS2_EXT_UNWRITTEN)) {
-		ret = context->cow_duplicate_clusters(handle, context->file,
+		ret = context->cow_duplicate_clusters(handle, context->inode,
 						      cpos, old, new, len);
 		if (ret) {
 			mlog_errno(ret);
@@ -3428,35 +3418,12 @@ static int ocfs2_replace_cow(struct ocfs2_cow_context *context)
 	return ret;
 }
 
-static void ocfs2_readahead_for_cow(struct inode *inode,
-				    struct file *file,
-				    u32 start, u32 len)
-{
-	struct address_space *mapping;
-	pgoff_t index;
-	unsigned long num_pages;
-	int cs_bits = OCFS2_SB(inode->i_sb)->s_clustersize_bits;
-
-	if (!file)
-		return;
-
-	mapping = file->f_mapping;
-	num_pages = (len << cs_bits) >> PAGE_CACHE_SHIFT;
-	if (!num_pages)
-		num_pages = 1;
-
-	index = ((loff_t)start << cs_bits) >> PAGE_CACHE_SHIFT;
-	page_cache_sync_readahead(mapping, &file->f_ra, file,
-				  index, num_pages);
-}
-
 /*
  * Starting at cpos, try to CoW write_len clusters.  Don't CoW
  * past max_cpos.  This will stop when it runs into a hole or an
  * unrefcounted extent.
  */
 static int ocfs2_refcount_cow_hunk(struct inode *inode,
-				   struct file *file,
 				   struct buffer_head *di_bh,
 				   u32 cpos, u32 write_len, u32 max_cpos)
 {
@@ -3485,8 +3452,6 @@ static int ocfs2_refcount_cow_hunk(struct inode *inode,
 
 	BUG_ON(cow_len == 0);
 
-	ocfs2_readahead_for_cow(inode, file, cow_start, cow_len);
-
 	context = kzalloc(sizeof(struct ocfs2_cow_context), GFP_NOFS);
 	if (!context) {
 		ret = -ENOMEM;
@@ -3508,7 +3473,6 @@ static int ocfs2_refcount_cow_hunk(struct inode *inode,
 	context->ref_root_bh = ref_root_bh;
 	context->cow_duplicate_clusters = ocfs2_duplicate_clusters_by_page;
 	context->get_clusters = ocfs2_di_get_clusters;
-	context->file = file;
 
 	ocfs2_init_dinode_extent_tree(&context->data_et,
 				      INODE_CACHE(inode), di_bh);
@@ -3537,7 +3501,6 @@ static int ocfs2_refcount_cow_hunk(struct inode *inode,
  * clusters between cpos and cpos+write_len are safe to modify.
  */
 int ocfs2_refcount_cow(struct inode *inode,
-		       struct file *file,
 		       struct buffer_head *di_bh,
 		       u32 cpos, u32 write_len, u32 max_cpos)
 {
@@ -3557,7 +3520,7 @@ int ocfs2_refcount_cow(struct inode *inode,
 			num_clusters = write_len;
 
 		if (ext_flags & OCFS2_EXT_REFCOUNTED) {
-			ret = ocfs2_refcount_cow_hunk(inode, file, di_bh, cpos,
+			ret = ocfs2_refcount_cow_hunk(inode, di_bh, cpos,
 						      num_clusters, max_cpos);
 			if (ret) {
 				mlog_errno(ret);

fs/ocfs2/refcounttree.h

@@ -53,7 +53,7 @@ int ocfs2_prepare_refcount_change_for_del(struct inode *inode,
 					  int *credits,
 					  int *ref_blocks);
 int ocfs2_refcount_cow(struct inode *inode,
-		       struct file *filep, struct buffer_head *di_bh,
+		       struct buffer_head *di_bh,
 		       u32 cpos, u32 write_len, u32 max_cpos);
 
 typedef int (ocfs2_post_refcount_func)(struct inode *inode,
@@ -85,11 +85,11 @@ int ocfs2_refcount_cow_xattr(struct inode *inode,
 			     u32 cpos, u32 write_len,
 			     struct ocfs2_post_refcount *post);
 int ocfs2_duplicate_clusters_by_page(handle_t *handle,
-				     struct file *file,
+				     struct inode *inode,
 				     u32 cpos, u32 old_cluster,
 				     u32 new_cluster, u32 new_len);
 int ocfs2_duplicate_clusters_by_jbd(handle_t *handle,
-				    struct file *file,
+				    struct inode *inode,
 				    u32 cpos, u32 old_cluster,
 				    u32 new_cluster, u32 new_len);
 int ocfs2_cow_sync_writeback(struct super_block *sb,

fs/proc/task_mmu.c

@@ -730,8 +730,16 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 	 * of how soft-dirty works.
 	 */
 	pte_t ptent = *pte;
-	ptent = pte_wrprotect(ptent);
-	ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+
+	if (pte_present(ptent)) {
+		ptent = pte_wrprotect(ptent);
+		ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+	} else if (is_swap_pte(ptent)) {
+		ptent = pte_swp_clear_soft_dirty(ptent);
+	} else if (pte_file(ptent)) {
+		ptent = pte_file_clear_soft_dirty(ptent);
+	}
+
 	set_pte_at(vma->vm_mm, addr, pte, ptent);
 #endif
 }
@@ -752,14 +760,15 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
 		ptent = *pte;
-		if (!pte_present(ptent))
-			continue;
 
 		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
 			clear_soft_dirty(vma, addr, pte);
 			continue;
 		}
 
+		if (!pte_present(ptent))
+			continue;
+
 		page = vm_normal_page(vma, addr, ptent);
 		if (!page)
 			continue;
@@ -859,7 +868,7 @@ typedef struct {
 } pagemap_entry_t;
 
 struct pagemapread {
-	int pos, len;
+	int pos, len;		/* units: PM_ENTRY_BYTES, not bytes */
 	pagemap_entry_t *buffer;
 	bool v2;
 };
@@ -867,7 +876,7 @@ struct pagemapread {
 #define PAGEMAP_WALK_SIZE	(PMD_SIZE)
 #define PAGEMAP_WALK_MASK	(PMD_MASK)
 
-#define PM_ENTRY_BYTES      sizeof(u64)
+#define PM_ENTRY_BYTES      sizeof(pagemap_entry_t)
 #define PM_STATUS_BITS      3
 #define PM_STATUS_OFFSET    (64 - PM_STATUS_BITS)
 #define PM_STATUS_MASK      (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
@@ -930,8 +939,10 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
 		flags = PM_PRESENT;
 		page = vm_normal_page(vma, addr, pte);
 	} else if (is_swap_pte(pte)) {
-		swp_entry_t entry = pte_to_swp_entry(pte);
-
+		swp_entry_t entry;
+		if (pte_swp_soft_dirty(pte))
+			flags2 |= __PM_SOFT_DIRTY;
+		entry = pte_to_swp_entry(pte);
 		frame = swp_type(entry) |
 			(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
 		flags = PM_SWAP;
@@ -1116,8 +1127,8 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 		goto out_task;
 
 	pm.v2 = soft_dirty_cleared;
-	pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
-	pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
+	pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
+	pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY);
 	ret = -ENOMEM;
 	if (!pm.buffer)
 		goto out_task;

include/asm-generic/pgtable.h

@@ -417,6 +417,36 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
 {
 	return pmd;
 }
+
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+	return pte;
+}
+
+static inline int pte_swp_soft_dirty(pte_t pte)
+{
+	return 0;
+}
+
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+	return pte;
+}
+
+static inline pte_t pte_file_clear_soft_dirty(pte_t pte)
+{
+       return pte;
+}
+
+static inline pte_t pte_file_mksoft_dirty(pte_t pte)
+{
+       return pte;
+}
+
+static inline int pte_file_soft_dirty(pte_t pte)
+{
+       return 0;
+}
 #endif
 
 #ifndef __HAVE_PFNMAP_TRACKING

include/linux/sched.h

@@ -314,6 +314,7 @@ struct nsproxy;
 struct user_namespace;
 
 #ifdef CONFIG_MMU
+extern unsigned long mmap_legacy_base(void);
 extern void arch_pick_mmap_layout(struct mm_struct *mm);
 extern unsigned long
 arch_get_unmapped_area(struct file *, unsigned long, unsigned long,

include/linux/swapops.h

@@ -67,6 +67,8 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte)
 	swp_entry_t arch_entry;
 
 	BUG_ON(pte_file(pte));
+	if (pte_swp_soft_dirty(pte))
+		pte = pte_swp_clear_soft_dirty(pte);
 	arch_entry = __pte_to_swp_entry(pte);
 	return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
 }

include/linux/syscalls.h

@@ -802,9 +802,14 @@ asmlinkage long sys_vfork(void);
 asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, int,
 	       int __user *);
 #else
+#ifdef CONFIG_CLONE_BACKWARDS3
+asmlinkage long sys_clone(unsigned long, unsigned long, int, int __user *,
+			  int __user *, int);
+#else
 asmlinkage long sys_clone(unsigned long, unsigned long, int __user *,
 	       int __user *, int);
 #endif
+#endif
 
 asmlinkage long sys_execve(const char __user *filename,
 		const char __user *const __user *argv,

kernel/fork.c

@@ -1679,6 +1679,12 @@ SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags,
 		 int __user *, parent_tidptr,
 		 int __user *, child_tidptr,
 		 int, tls_val)
+#elif defined(CONFIG_CLONE_BACKWARDS3)
+SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp,
+		int, stack_size,
+		int __user *, parent_tidptr,
+		int __user *, child_tidptr,
+		int, tls_val)
 #else
 SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 		 int __user *, parent_tidptr,

mm/fremap.c

@@ -57,17 +57,22 @@ static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long addr, unsigned long pgoff, pgprot_t prot)
 {
 	int err = -ENOMEM;
-	pte_t *pte;
+	pte_t *pte, ptfile;
 	spinlock_t *ptl;
 
 	pte = get_locked_pte(mm, addr, &ptl);
 	if (!pte)
 		goto out;
 
-	if (!pte_none(*pte))
+	ptfile = pgoff_to_pte(pgoff);
+
+	if (!pte_none(*pte)) {
+		if (pte_present(*pte) && pte_soft_dirty(*pte))
+			pte_file_mksoft_dirty(ptfile);
 		zap_pte(mm, vma, addr, pte);
+	}
 
-	set_pte_at(mm, addr, pte, pgoff_to_pte(pgoff));
+	set_pte_at(mm, addr, pte, ptfile);
 	/*
 	 * We don't need to run update_mmu_cache() here because the "file pte"
 	 * being installed by install_file_pte() is not a real pte - it's a

mm/memcontrol.c

@@ -3195,11 +3195,11 @@ int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
 	if (!s->memcg_params)
 		return -ENOMEM;
 
-	INIT_WORK(&s->memcg_params->destroy,
-			kmem_cache_destroy_work_func);
 	if (memcg) {
 		s->memcg_params->memcg = memcg;
 		s->memcg_params->root_cache = root_cache;
+		INIT_WORK(&s->memcg_params->destroy,
+				kmem_cache_destroy_work_func);
 	} else
 		s->memcg_params->is_root_cache = true;
 

mm/memory.c

@@ -1141,9 +1141,12 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 				continue;
 			if (unlikely(details) && details->nonlinear_vma
 			    && linear_page_index(details->nonlinear_vma,
-						addr) != page->index)
-				set_pte_at(mm, addr, pte,
-					   pgoff_to_pte(page->index));
+						addr) != page->index) {
+				pte_t ptfile = pgoff_to_pte(page->index);
+				if (pte_soft_dirty(ptent))
+					pte_file_mksoft_dirty(ptfile);
+				set_pte_at(mm, addr, pte, ptfile);
+			}
 			if (PageAnon(page))
 				rss[MM_ANONPAGES]--;
 			else {
@@ -3115,6 +3118,8 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		exclusive = 1;
 	}
 	flush_icache_page(vma, page);
+	if (pte_swp_soft_dirty(orig_pte))
+		pte = pte_mksoft_dirty(pte);
 	set_pte_at(mm, address, page_table, pte);
 	if (page == swapcache)
 		do_page_add_anon_rmap(page, vma, address, exclusive);
@@ -3408,6 +3413,8 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		entry = mk_pte(page, vma->vm_page_prot);
 		if (flags & FAULT_FLAG_WRITE)
 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		else if (pte_file(orig_pte) && pte_file_soft_dirty(orig_pte))
+			pte_mksoft_dirty(entry);
 		if (anon) {
 			inc_mm_counter_fast(mm, MM_ANONPAGES);
 			page_add_new_anon_rmap(page, vma, address);

mm/rmap.c

@@ -1236,6 +1236,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			   swp_entry_to_pte(make_hwpoison_entry(page)));
 	} else if (PageAnon(page)) {
 		swp_entry_t entry = { .val = page_private(page) };
+		pte_t swp_pte;
 
 		if (PageSwapCache(page)) {
 			/*
@@ -1264,7 +1265,10 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION);
 			entry = make_migration_entry(page, pte_write(pteval));
 		}
-		set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
+		swp_pte = swp_entry_to_pte(entry);
+		if (pte_soft_dirty(pteval))
+			swp_pte = pte_swp_mksoft_dirty(swp_pte);
+		set_pte_at(mm, address, pte, swp_pte);
 		BUG_ON(pte_file(*pte));
 	} else if (IS_ENABLED(CONFIG_MIGRATION) &&
 		   (TTU_ACTION(flags) == TTU_MIGRATION)) {
@@ -1401,8 +1405,12 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 		pteval = ptep_clear_flush(vma, address, pte);
 
 		/* If nonlinear, store the file page offset in the pte. */
-		if (page->index != linear_page_index(vma, address))
-			set_pte_at(mm, address, pte, pgoff_to_pte(page->index));
+		if (page->index != linear_page_index(vma, address)) {
+			pte_t ptfile = pgoff_to_pte(page->index);
+			if (pte_soft_dirty(pteval))
+				pte_file_mksoft_dirty(ptfile);
+			set_pte_at(mm, address, pte, ptfile);
+		}
 
 		/* Move the dirty bit to the physical page now the pte is gone. */
 		if (pte_dirty(pteval))

mm/swapfile.c

@@ -866,6 +866,21 @@ unsigned int count_swap_pages(int type, int free)
 }
 #endif /* CONFIG_HIBERNATION */
 
+static inline int maybe_same_pte(pte_t pte, pte_t swp_pte)
+{
+#ifdef CONFIG_MEM_SOFT_DIRTY
+	/*
+	 * When pte keeps soft dirty bit the pte generated
+	 * from swap entry does not has it, still it's same
+	 * pte from logical point of view.
+	 */
+	pte_t swp_pte_dirty = pte_swp_mksoft_dirty(swp_pte);
+	return pte_same(pte, swp_pte) || pte_same(pte, swp_pte_dirty);
+#else
+	return pte_same(pte, swp_pte);
+#endif
+}
+
 /*
  * No need to decide whether this PTE shares the swap entry with others,
  * just let do_wp_page work it out if a write is requested later - to
@@ -892,7 +907,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	}
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) {
+	if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) {
 		mem_cgroup_cancel_charge_swapin(memcg);
 		ret = 0;
 		goto out;
@@ -947,7 +962,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		 * swapoff spends a _lot_ of time in this loop!
 		 * Test inline before going to call unuse_pte.
 		 */
-		if (unlikely(pte_same(*pte, swp_pte))) {
+		if (unlikely(maybe_same_pte(*pte, swp_pte))) {
 			pte_unmap(pte);
 			ret = unuse_pte(vma, pmd, addr, entry, page);
 			if (ret)