Merge branch 'akpm' (patches from Andrew)

Merge fixes from Andrew Morton:
 "10 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  dax: move writeback calls into the filesystems
  dax: give DAX clearing code correct bdev
  ext4: online defrag not supported with DAX
  ext2, ext4: only set S_DAX for regular inodes
  block: disable block device DAX by default
  ocfs2: unlock inode if deleting inode from orphan fails
  mm: ASLR: use get_random_long()
  drivers: char: random: add get_random_long()
  mm: numa: quickly fail allocations for NUMA balancing on full nodes
  mm: thp: fix SMP race condition between THP page fault and MADV_DONTNEED

arch/arm/mm/mmap.c

@@ -173,7 +173,7 @@ unsigned long arch_mmap_rnd(void)
 {
 	unsigned long rnd;
 
-	rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1);
+	rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
 
 	return rnd << PAGE_SHIFT;
 }

arch/arm64/mm/mmap.c

@@ -53,10 +53,10 @@ unsigned long arch_mmap_rnd(void)
 
 #ifdef CONFIG_COMPAT
 	if (test_thread_flag(TIF_32BIT))
-		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1);
+		rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
 	else
 #endif
-		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1);
+		rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
 	return rnd << PAGE_SHIFT;
 }
 

arch/mips/mm/mmap.c

@@ -146,7 +146,7 @@ unsigned long arch_mmap_rnd(void)
 {
 	unsigned long rnd;
 
-	rnd = (unsigned long)get_random_int();
+	rnd = get_random_long();
 	rnd <<= PAGE_SHIFT;
 	if (TASK_IS_32BIT_ADDR)
 		rnd &= 0xfffffful;
@@ -174,7 +174,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 
 static inline unsigned long brk_rnd(void)
 {
-	unsigned long rnd = get_random_int();
+	unsigned long rnd = get_random_long();
 
 	rnd = rnd << PAGE_SHIFT;
 	/* 8MB for 32bit, 256MB for 64bit */

arch/powerpc/kernel/process.c

@@ -1768,9 +1768,9 @@ static inline unsigned long brk_rnd(void)
 
 	/* 8MB for 32bit, 1GB for 64bit */
 	if (is_32bit_task())
-		rnd = (long)(get_random_int() % (1<<(23-PAGE_SHIFT)));
+		rnd = (get_random_long() % (1UL<<(23-PAGE_SHIFT)));
 	else
-		rnd = (long)(get_random_int() % (1<<(30-PAGE_SHIFT)));
+		rnd = (get_random_long() % (1UL<<(30-PAGE_SHIFT)));
 
 	return rnd << PAGE_SHIFT;
 }

arch/powerpc/mm/mmap.c

@@ -59,9 +59,9 @@ unsigned long arch_mmap_rnd(void)
 
 	/* 8MB for 32bit, 1GB for 64bit */
 	if (is_32bit_task())
-		rnd = (unsigned long)get_random_int() % (1<<(23-PAGE_SHIFT));
+		rnd = get_random_long() % (1<<(23-PAGE_SHIFT));
 	else
-		rnd = (unsigned long)get_random_int() % (1<<(30-PAGE_SHIFT));
+		rnd = get_random_long() % (1UL<<(30-PAGE_SHIFT));
 
 	return rnd << PAGE_SHIFT;
 }

arch/sparc/kernel/sys_sparc_64.c

@@ -264,7 +264,7 @@ static unsigned long mmap_rnd(void)
 	unsigned long rnd = 0UL;
 
 	if (current->flags & PF_RANDOMIZE) {
-		unsigned long val = get_random_int();
+		unsigned long val = get_random_long();
 		if (test_thread_flag(TIF_32BIT))
 			rnd = (val % (1UL << (23UL-PAGE_SHIFT)));
 		else

arch/x86/mm/mmap.c

@@ -71,12 +71,12 @@ unsigned long arch_mmap_rnd(void)
 
 	if (mmap_is_ia32())
 #ifdef CONFIG_COMPAT
-		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1);
+		rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
 #else
-		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1);
+		rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
 #endif
 	else
-		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1);
+		rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
 
 	return rnd << PAGE_SHIFT;
 }

block/Kconfig

@@ -88,6 +88,19 @@ config BLK_DEV_INTEGRITY
 	T10/SCSI Data Integrity Field or the T13/ATA External Path
 	Protection.  If in doubt, say N.
 
+config BLK_DEV_DAX
+	bool "Block device DAX support"
+	depends on FS_DAX
+	depends on BROKEN
+	help
+	  When DAX support is available (CONFIG_FS_DAX) raw block
+	  devices can also support direct userspace access to the
+	  storage capacity via MMAP(2) similar to a file on a
+	  DAX-enabled filesystem.  However, the DAX I/O-path disables
+	  some standard I/O-statistics, and the MMAP(2) path has some
+	  operational differences due to bypassing the page
+	  cache.  If in doubt, say N.
+
 config BLK_DEV_THROTTLING
 	bool "Block layer bio throttling support"
 	depends on BLK_CGROUP=y

drivers/char/random.c

@@ -1818,6 +1818,28 @@ unsigned int get_random_int(void)
 }
 EXPORT_SYMBOL(get_random_int);
 
+/*
+ * Same as get_random_int(), but returns unsigned long.
+ */
+unsigned long get_random_long(void)
+{
+	__u32 *hash;
+	unsigned long ret;
+
+	if (arch_get_random_long(&ret))
+		return ret;
+
+	hash = get_cpu_var(get_random_int_hash);
+
+	hash[0] += current->pid + jiffies + random_get_entropy();
+	md5_transform(hash, random_int_secret);
+	ret = *(unsigned long *)hash;
+	put_cpu_var(get_random_int_hash);
+
+	return ret;
+}
+EXPORT_SYMBOL(get_random_long);
+
 /*
  * randomize_range() returns a start address such that
  *

fs/binfmt_elf.c

@@ -653,7 +653,7 @@ static unsigned long randomize_stack_top(unsigned long stack_top)
 
 	if ((current->flags & PF_RANDOMIZE) &&
 		!(current->personality & ADDR_NO_RANDOMIZE)) {
-		random_variable = (unsigned long) get_random_int();
+		random_variable = get_random_long();
 		random_variable &= STACK_RND_MASK;
 		random_variable <<= PAGE_SHIFT;
 	}

fs/block_dev.c

@@ -1201,7 +1201,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_disk = disk;
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
-		bdev->bd_inode->i_flags = disk->fops->direct_access ? S_DAX : 0;
+		if (IS_ENABLED(CONFIG_BLK_DEV_DAX) && disk->fops->direct_access)
+			bdev->bd_inode->i_flags = S_DAX;
+		else
+			bdev->bd_inode->i_flags = 0;
+
 		if (!partno) {
 			ret = -ENXIO;
 			bdev->bd_part = disk_get_part(disk, partno);
@@ -1693,13 +1697,24 @@ static int blkdev_releasepage(struct page *page, gfp_t wait)
 	return try_to_free_buffers(page);
 }
 
+static int blkdev_writepages(struct address_space *mapping,
+			     struct writeback_control *wbc)
+{
+	if (dax_mapping(mapping)) {
+		struct block_device *bdev = I_BDEV(mapping->host);
+
+		return dax_writeback_mapping_range(mapping, bdev, wbc);
+	}
+	return generic_writepages(mapping, wbc);
+}
+
 static const struct address_space_operations def_blk_aops = {
 	.readpage	= blkdev_readpage,
 	.readpages	= blkdev_readpages,
 	.writepage	= blkdev_writepage,
 	.write_begin	= blkdev_write_begin,
 	.write_end	= blkdev_write_end,
-	.writepages	= generic_writepages,
+	.writepages	= blkdev_writepages,
 	.releasepage	= blkdev_releasepage,
 	.direct_IO	= blkdev_direct_IO,
 	.is_dirty_writeback = buffer_check_dirty_writeback,

fs/dax.c

@@ -79,15 +79,14 @@ struct page *read_dax_sector(struct block_device *bdev, sector_t n)
 }
 
 /*
- * dax_clear_blocks() is called from within transaction context from XFS,
+ * dax_clear_sectors() is called from within transaction context from XFS,
  * and hence this means the stack from this point must follow GFP_NOFS
  * semantics for all operations.
  */
-int dax_clear_blocks(struct inode *inode, sector_t block, long _size)
+int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size)
 {
-	struct block_device *bdev = inode->i_sb->s_bdev;
 	struct blk_dax_ctl dax = {
-		.sector = block << (inode->i_blkbits - 9),
+		.sector = _sector,
 		.size = _size,
 	};
 
@@ -109,7 +108,7 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long _size)
 	wmb_pmem();
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dax_clear_blocks);
+EXPORT_SYMBOL_GPL(dax_clear_sectors);
 
 /* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */
 static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first,
@@ -485,11 +484,10 @@ static int dax_writeback_one(struct block_device *bdev,
  * end]. This is required by data integrity operations to ensure file data is
  * on persistent storage prior to completion of the operation.
  */
-int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
-		loff_t end)
+int dax_writeback_mapping_range(struct address_space *mapping,
+		struct block_device *bdev, struct writeback_control *wbc)
 {
 	struct inode *inode = mapping->host;
-	struct block_device *bdev = inode->i_sb->s_bdev;
 	pgoff_t start_index, end_index, pmd_index;
 	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
@@ -500,8 +498,11 @@ int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
 	if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
 		return -EIO;
 
-	start_index = start >> PAGE_CACHE_SHIFT;
-	end_index = end >> PAGE_CACHE_SHIFT;
+	if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
+		return 0;
+
+	start_index = wbc->range_start >> PAGE_CACHE_SHIFT;
+	end_index = wbc->range_end >> PAGE_CACHE_SHIFT;
 	pmd_index = DAX_PMD_INDEX(start_index);
 
 	rcu_read_lock();

fs/ext2/inode.c

@@ -737,8 +737,10 @@ static int ext2_get_blocks(struct inode *inode,
 		 * so that it's not found by another thread before it's
 		 * initialised
 		 */
-		err = dax_clear_blocks(inode, le32_to_cpu(chain[depth-1].key),
-						1 << inode->i_blkbits);
+		err = dax_clear_sectors(inode->i_sb->s_bdev,
+				le32_to_cpu(chain[depth-1].key) <<
+				(inode->i_blkbits - 9),
+				1 << inode->i_blkbits);
 		if (err) {
 			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;
@@ -874,6 +876,14 @@ ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 static int
 ext2_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
+#ifdef CONFIG_FS_DAX
+	if (dax_mapping(mapping)) {
+		return dax_writeback_mapping_range(mapping,
+						   mapping->host->i_sb->s_bdev,
+						   wbc);
+	}
+#endif
+
 	return mpage_writepages(mapping, wbc, ext2_get_block);
 }
 
@@ -1296,7 +1306,7 @@ void ext2_set_inode_flags(struct inode *inode)
 		inode->i_flags |= S_NOATIME;
 	if (flags & EXT2_DIRSYNC_FL)
 		inode->i_flags |= S_DIRSYNC;
-	if (test_opt(inode->i_sb, DAX))
+	if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode))
 		inode->i_flags |= S_DAX;
 }
 

fs/ext4/inode.c

@@ -2478,6 +2478,10 @@ static int ext4_writepages(struct address_space *mapping,
 
 	trace_ext4_writepages(inode, wbc);
 
+	if (dax_mapping(mapping))
+		return dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
+						   wbc);
+
 	/*
 	 * No pages to write? This is mainly a kludge to avoid starting
 	 * a transaction for special inodes like journal inode on last iput()
@@ -4155,7 +4159,7 @@ void ext4_set_inode_flags(struct inode *inode)
 		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
 		new_fl |= S_DIRSYNC;
-	if (test_opt(inode->i_sb, DAX))
+	if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode))
 		new_fl |= S_DAX;
 	inode_set_flags(inode, new_fl,
 			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX);

fs/ext4/ioctl.c

@@ -583,6 +583,11 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 				 "Online defrag not supported with bigalloc");
 			err = -EOPNOTSUPP;
 			goto mext_out;
+		} else if (IS_DAX(inode)) {
+			ext4_msg(sb, KERN_ERR,
+				 "Online defrag not supported with DAX");
+			err = -EOPNOTSUPP;
+			goto mext_out;
 		}
 
 		err = mnt_want_write_file(filp);

fs/ocfs2/aops.c

@@ -956,6 +956,7 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 		tmp_ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
 				update_isize, end);
 		if (tmp_ret < 0) {
+			ocfs2_inode_unlock(inode, 1);
 			ret = tmp_ret;
 			mlog_errno(ret);
 			brelse(di_bh);

fs/xfs/xfs_aops.c

@@ -55,7 +55,7 @@ xfs_count_page_state(
 	} while ((bh = bh->b_this_page) != head);
 }
 
-STATIC struct block_device *
+struct block_device *
 xfs_find_bdev_for_inode(
 	struct inode		*inode)
 {
@@ -1208,6 +1208,10 @@ xfs_vm_writepages(
 	struct writeback_control *wbc)
 {
 	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
+	if (dax_mapping(mapping))
+		return dax_writeback_mapping_range(mapping,
+				xfs_find_bdev_for_inode(mapping->host), wbc);
+
 	return generic_writepages(mapping, wbc);
 }
 

fs/xfs/xfs_aops.h

@@ -62,5 +62,6 @@ int	xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset,
 			         struct buffer_head *map_bh, int create);
 
 extern void xfs_count_page_state(struct page *, int *, int *);
+extern struct block_device *xfs_find_bdev_for_inode(struct inode *);
 
 #endif /* __XFS_AOPS_H__ */

fs/xfs/xfs_bmap_util.c

@@ -75,7 +75,8 @@ xfs_zero_extent(
 	ssize_t		size = XFS_FSB_TO_B(mp, count_fsb);
 
 	if (IS_DAX(VFS_I(ip)))
-		return dax_clear_blocks(VFS_I(ip), block, size);
+		return dax_clear_sectors(xfs_find_bdev_for_inode(VFS_I(ip)),
+				sector, size);
 
 	/*
 	 * let the block layer decide on the fastest method of

include/linux/dax.h

@@ -7,7 +7,7 @@
 
 ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
 		  get_block_t, dio_iodone_t, int flags);
-int dax_clear_blocks(struct inode *, sector_t block, long size);
+int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size);
 int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
 int dax_truncate_page(struct inode *, loff_t from, get_block_t);
 int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
@@ -52,6 +52,8 @@ static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);
 }
-int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
-		loff_t end);
+
+struct writeback_control;
+int dax_writeback_mapping_range(struct address_space *mapping,
+		struct block_device *bdev, struct writeback_control *wbc);
 #endif

include/linux/random.h

@@ -34,6 +34,7 @@ extern const struct file_operations random_fops, urandom_fops;
 #endif
 
 unsigned int get_random_int(void);
+unsigned long get_random_long(void);
 unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len);
 
 u32 prandom_u32(void);

mm/filemap.c

@@ -446,7 +446,8 @@ int filemap_write_and_wait(struct address_space *mapping)
 {
 	int err = 0;
 
-	if (mapping->nrpages) {
+	if ((!dax_mapping(mapping) && mapping->nrpages) ||
+	    (dax_mapping(mapping) && mapping->nrexceptional)) {
 		err = filemap_fdatawrite(mapping);
 		/*
 		 * Even if the above returned error, the pages may be
@@ -482,13 +483,8 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 {
 	int err = 0;
 
-	if (dax_mapping(mapping) && mapping->nrexceptional) {
-		err = dax_writeback_mapping_range(mapping, lstart, lend);
-		if (err)
-			return err;
-	}
-
-	if (mapping->nrpages) {
+	if ((!dax_mapping(mapping) && mapping->nrpages) ||
+	    (dax_mapping(mapping) && mapping->nrexceptional)) {
 		err = __filemap_fdatawrite_range(mapping, lstart, lend,
 						 WB_SYNC_ALL);
 		/* See comment of filemap_write_and_wait() */

mm/memory.c

@@ -3404,8 +3404,18 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(pmd_none(*pmd)) &&
 	    unlikely(__pte_alloc(mm, vma, pmd, address)))
 		return VM_FAULT_OOM;
-	/* if an huge pmd materialized from under us just retry later */
-	if (unlikely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd)))
+	/*
+	 * If a huge pmd materialized under us just retry later.  Use
+	 * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd
+	 * didn't become pmd_trans_huge under us and then back to pmd_none, as
+	 * a result of MADV_DONTNEED running immediately after a huge pmd fault
+	 * in a different thread of this mm, in turn leading to a misleading
+	 * pmd_trans_huge() retval.  All we have to ensure is that it is a
+	 * regular pmd that we can walk with pte_offset_map() and we can do that
+	 * through an atomic read in C, which is what pmd_trans_unstable()
+	 * provides.
+	 */
+	if (unlikely(pmd_trans_unstable(pmd) || pmd_devmap(*pmd)))
 		return 0;
 	/*
 	 * A regular pmd is established and it can't morph into a huge pmd

mm/migrate.c

@@ -1582,7 +1582,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 					 (GFP_HIGHUSER_MOVABLE |
 					  __GFP_THISNODE | __GFP_NOMEMALLOC |
 					  __GFP_NORETRY | __GFP_NOWARN) &
-					 ~(__GFP_IO | __GFP_FS), 0);
+					 ~__GFP_RECLAIM, 0);
 
 	return newpage;
 }