Merge tag 'exfat-for-7.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/linkinjeon/exfat

Pull exfat updates from Namjae Jeon: - Implement FALLOC_FL_ALLOCATE_RANGE to add support for preallocating clusters without zeroing, helping to reduce file fragmentation - Add a unified block readahead helper for FAT chain conversion, bitmap allocation, and directory entry lookups - Optimize exfat_chain_cont_cluster() by caching buffer heads to minimize mark_buffer_dirty() and mirroring overhead during NO_FAT_CHAIN to FAT_CHAIN conversion - Switch to truncate_inode_pages_final() in evict_inode() to prevent BUG_ON caused by shadow entries during reclaim - Fix a 32-bit truncation bug in directory entry calculations by ensuring proper bitwise coercion - Fix sb->s_maxbytes calculation to correctly reflect the maximum possible volume size for a given cluster size, resolving xfstests generic/213 - Introduced exfat_cluster_walk() helper to traverse FAT chains by a specified step, handling both ALLOC_NO_FAT_CHAIN and ALLOC_FAT_CHAIN modes - Introduced exfat_chain_advance() helper to advance an exfat_chain structure, updating both the current cluster and remaining size - Remove dead assignments and fix Smatch warnings * tag 'exfat-for-7.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/linkinjeon/exfat: exfat: use exfat_chain_advance helper exfat: introduce exfat_chain_advance helper exfat: remove NULL cache pointer case in exfat_ent_get exfat: use exfat_cluster_walk helper exfat: introduce exfat_cluster_walk helper exfat: fix incorrect directory checksum after rename to shorter name exfat: fix s_maxbytes exfat: fix passing zero to ERR_PTR() in exfat_mkdir() exfat: fix error handling for FAT table operations exfat: optimize exfat_chain_cont_cluster with cached buffer heads exfat: drop redundant sec parameter from exfat_mirror_bh exfat: use readahead helper in exfat_get_dentry exfat: use readahead helper in exfat_allocate_bitmap exfat: add block readahead in exfat_chain_cont_cluster exfat: add fallocate FALLOC_FL_ALLOCATE_RANGE support exfat: Fix bitwise operation having different size exfat: Drop dead assignment of num_clusters exfat: use truncate_inode_pages_final() at evict_inode()
2026-04-18 06:44:00 -04:00 · 2026-04-13 16:57:31 -07:00
parent f2729827ae 08cf4a8181
commit a62fe21079
10 changed files with 274 additions and 227 deletions
--- a/fs/exfat/balloc.c
+++ b/fs/exfat/balloc.c
@@ -74,11 +74,10 @@ static int exfat_allocate_bitmap(struct super_block *sb,
 		struct exfat_dentry *ep)
 {
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
-	struct blk_plug plug;
 	long long map_size;
 	unsigned int i, j, need_map_size;
-	sector_t sector;
-	unsigned int max_ra_count;
+	sector_t sector, end, ra;
+	blkcnt_t ra_cnt = 0;

 	sbi->map_clu = le32_to_cpu(ep->dentry.bitmap.start_clu);
 	map_size = le64_to_cpu(ep->dentry.bitmap.size);
@@ -100,17 +99,12 @@ static int exfat_allocate_bitmap(struct super_block *sb,
 	if (!sbi->vol_amap)
 		return -ENOMEM;

-	sector = exfat_cluster_to_sector(sbi, sbi->map_clu);
-	max_ra_count = min(sb->s_bdi->ra_pages, sb->s_bdi->io_pages) <<
-		(PAGE_SHIFT - sb->s_blocksize_bits);
+	sector = ra = exfat_cluster_to_sector(sbi, sbi->map_clu);
+	end = sector + sbi->map_sectors - 1;
+
 	for (i = 0; i < sbi->map_sectors; i++) {
 		/* Trigger the next readahead in advance. */
-		if (max_ra_count && 0 == (i % max_ra_count)) {
-			blk_start_plug(&plug);
-			for (j = i; j < min(max_ra_count, sbi->map_sectors - i) + i; j++)
-				sb_breadahead(sb, sector + j);
-			blk_finish_plug(&plug);
-		}
+		exfat_blk_readahead(sb, sector + i, &ra, &ra_cnt, end);

 		sbi->vol_amap[i] = sb_bread(sb, sector + i);
 		if (!sbi->vol_amap[i])
--- a/fs/exfat/dir.c
+++ b/fs/exfat/dir.c
@@ -93,25 +93,19 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent
 	clu_offset = EXFAT_DEN_TO_CLU(dentry, sbi);
 	exfat_chain_dup(&clu, &dir);

-	if (clu.flags == ALLOC_NO_FAT_CHAIN) {
-		clu.dir += clu_offset;
-		clu.size -= clu_offset;
-	} else {
+	if (clu.flags == ALLOC_FAT_CHAIN) {
 		/* hint_information */
 		if (clu_offset > 0 && ei->hint_bmap.off != EXFAT_EOF_CLUSTER &&
 		    ei->hint_bmap.off > 0 && clu_offset >= ei->hint_bmap.off) {
 			clu_offset -= ei->hint_bmap.off;
 			clu.dir = ei->hint_bmap.clu;
-		}
-
-		while (clu_offset > 0 && clu.dir != EXFAT_EOF_CLUSTER) {
-			if (exfat_get_next_cluster(sb, &(clu.dir)))
-				return -EIO;
-
-			clu_offset--;
+			clu.size -= ei->hint_bmap.off;
 		}
 	}

+	if (exfat_chain_advance(sb, &clu, clu_offset))
+		return -EIO;
+
 	while (clu.dir != EXFAT_EOF_CLUSTER && dentry < max_dentries) {
 		i = dentry & (dentries_per_clu - 1);

@@ -160,15 +154,8 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent
 			return 0;
 		}

-		if (clu.flags == ALLOC_NO_FAT_CHAIN) {
-			if (--clu.size > 0)
-				clu.dir++;
-			else
-				clu.dir = EXFAT_EOF_CLUSTER;
-		} else {
-			if (exfat_get_next_cluster(sb, &(clu.dir)))
-				return -EIO;
-		}
+		if (exfat_chain_advance(sb, &clu, 1))
+			return -EIO;
 	}

 out:
@@ -249,7 +236,7 @@ get_new:
 		 */
 		if (err == -EIO) {
 			cpos += 1 << (sb->s_blocksize_bits);
-			cpos &= ~(sb->s_blocksize - 1);
+			cpos &= ~(loff_t)(sb->s_blocksize - 1);
 		}

 		err = -EIO;
@@ -490,6 +477,7 @@ void exfat_init_ext_entry(struct exfat_entry_set_cache *es, int num_entries,
 	unsigned short *uniname = p_uniname->name;
 	struct exfat_dentry *ep;

+	es->num_entries = num_entries;
 	ep = exfat_get_dentry_cached(es, ES_IDX_FILE);
 	ep->dentry.file.num_ext = (unsigned char)(num_entries - 1);

@@ -561,38 +549,6 @@ int exfat_put_dentry_set(struct exfat_entry_set_cache *es, int sync)
 	return err;
 }

-static int exfat_walk_fat_chain(struct super_block *sb,
-		struct exfat_chain *p_dir, unsigned int byte_offset,
-		unsigned int *clu)
-{
-	struct exfat_sb_info *sbi = EXFAT_SB(sb);
-	unsigned int clu_offset;
-	unsigned int cur_clu;
-
-	clu_offset = EXFAT_B_TO_CLU(byte_offset, sbi);
-	cur_clu = p_dir->dir;
-
-	if (p_dir->flags == ALLOC_NO_FAT_CHAIN) {
-		cur_clu += clu_offset;
-	} else {
-		while (clu_offset > 0) {
-			if (exfat_get_next_cluster(sb, &cur_clu))
-				return -EIO;
-			if (cur_clu == EXFAT_EOF_CLUSTER) {
-				exfat_fs_error(sb,
-					"invalid dentry access beyond EOF (clu : %u, eidx : %d)",
-					p_dir->dir,
-					EXFAT_B_TO_DEN(byte_offset));
-				return -EIO;
-			}
-			clu_offset--;
-		}
-	}
-
-	*clu = cur_clu;
-	return 0;
-}
-
 static int exfat_find_location(struct super_block *sb, struct exfat_chain *p_dir,
 			       int entry, sector_t *sector, int *offset)
 {
@@ -602,10 +558,19 @@ static int exfat_find_location(struct super_block *sb, struct exfat_chain *p_dir

 	off = EXFAT_DEN_TO_B(entry);

-	ret = exfat_walk_fat_chain(sb, p_dir, off, &clu);
+	clu = p_dir->dir;
+	ret = exfat_cluster_walk(sb, &clu, EXFAT_B_TO_CLU(off, sbi), p_dir->flags);
 	if (ret)
 		return ret;

+	if (clu == EXFAT_EOF_CLUSTER) {
+		exfat_fs_error(sb,
+			"unexpected early break in cluster chain (clu : %u, len : %d)",
+			p_dir->dir,
+			EXFAT_B_TO_CLU(off, sbi));
+		return -EIO;
+	}
+
 	if (!exfat_test_bitmap(sb, clu)) {
 		exfat_err(sb, "failed to test cluster bit(%u)", clu);
 		return -EIO;
@@ -623,44 +588,11 @@ static int exfat_find_location(struct super_block *sb, struct exfat_chain *p_dir
 	return 0;
 }

-#define EXFAT_MAX_RA_SIZE     (128*1024)
-static int exfat_dir_readahead(struct super_block *sb, sector_t sec)
-{
-	struct exfat_sb_info *sbi = EXFAT_SB(sb);
-	struct buffer_head *bh;
-	unsigned int max_ra_count = EXFAT_MAX_RA_SIZE >> sb->s_blocksize_bits;
-	unsigned int page_ra_count = PAGE_SIZE >> sb->s_blocksize_bits;
-	unsigned int adj_ra_count = max(sbi->sect_per_clus, page_ra_count);
-	unsigned int ra_count = min(adj_ra_count, max_ra_count);
-
-	/* Read-ahead is not required */
-	if (sbi->sect_per_clus == 1)
-		return 0;
-
-	if (sec < sbi->data_start_sector) {
-		exfat_err(sb, "requested sector is invalid(sect:%llu, root:%llu)",
-			  (unsigned long long)sec, sbi->data_start_sector);
-		return -EIO;
-	}
-
-	/* Not sector aligned with ra_count, resize ra_count to page size */
-	if ((sec - sbi->data_start_sector) & (ra_count - 1))
-		ra_count = page_ra_count;
-
-	bh = sb_find_get_block(sb, sec);
-	if (!bh || !buffer_uptodate(bh)) {
-		unsigned int i;
-
-		for (i = 0; i < ra_count; i++)
-			sb_breadahead(sb, (sector_t)(sec + i));
-	}
-	brelse(bh);
-	return 0;
-}
-
 struct exfat_dentry *exfat_get_dentry(struct super_block *sb,
 		struct exfat_chain *p_dir, int entry, struct buffer_head **bh)
 {
+	struct exfat_sb_info *sbi = EXFAT_SB(sb);
+	unsigned int sect_per_clus = sbi->sect_per_clus;
 	unsigned int dentries_per_page = EXFAT_B_TO_DEN(PAGE_SIZE);
 	int off;
 	sector_t sec;
@@ -673,9 +605,18 @@ struct exfat_dentry *exfat_get_dentry(struct super_block *sb,
 	if (exfat_find_location(sb, p_dir, entry, &sec, &off))
 		return NULL;

-	if (p_dir->dir != EXFAT_FREE_CLUSTER &&
-			!(entry & (dentries_per_page - 1)))
-		exfat_dir_readahead(sb, sec);
+	if (sect_per_clus > 1 &&
+	    (entry & (dentries_per_page - 1)) == 0) {
+		sector_t ra = sec;
+		blkcnt_t cnt = 0;
+		unsigned int ra_count = sect_per_clus;
+
+		/* Not sector aligned with ra_count, resize ra_count to page size */
+		if ((sec - sbi->data_start_sector) & (ra_count - 1))
+			ra_count = PAGE_SIZE >> sb->s_blocksize_bits;
+
+		exfat_blk_readahead(sb, sec, &ra, &cnt, sec + ra_count - 1);
+	}

 	*bh = sb_bread(sb, sec);
 	if (!*bh)
@@ -815,9 +756,7 @@ static int __exfat_get_dentry_set(struct exfat_entry_set_cache *es,
 		if (exfat_is_last_sector_in_cluster(sbi, sec)) {
 			unsigned int clu = exfat_sector_to_cluster(sbi, sec);

-			if (p_dir->flags == ALLOC_NO_FAT_CHAIN)
-				clu++;
-			else if (exfat_get_next_cluster(sb, &clu))
+			if (exfat_cluster_walk(sb, &clu, 1, p_dir->flags))
 				goto put_es;
 			sec = exfat_cluster_to_sector(sbi, clu);
 		} else {
@@ -1133,19 +1072,12 @@ rewind:
 			step = DIRENT_STEP_FILE;
 		}

-		if (clu.flags == ALLOC_NO_FAT_CHAIN) {
-			if (--clu.size > 0)
-				clu.dir++;
-			else
-				clu.dir = EXFAT_EOF_CLUSTER;
-		} else {
-			if (exfat_get_next_cluster(sb, &clu.dir))
-				return -EIO;
+		if (exfat_chain_advance(sb, &clu, 1))
+			return -EIO;

-			/* break if the cluster chain includes a loop */
-			if (unlikely(++clu_count > EXFAT_DATA_CLUSTER_COUNT(sbi)))
-				goto not_found;
-		}
+		/* break if the cluster chain includes a loop */
+		if (unlikely(++clu_count > EXFAT_DATA_CLUSTER_COUNT(sbi)))
+			goto not_found;
 	}

 not_found:
@@ -1180,14 +1112,7 @@ found:
 	if (!((dentry + 1) & (dentries_per_clu - 1))) {
 		int ret = 0;

-		if (clu.flags == ALLOC_NO_FAT_CHAIN) {
-			if (--clu.size > 0)
-				clu.dir++;
-			else
-				clu.dir = EXFAT_EOF_CLUSTER;
-		} else {
-			ret = exfat_get_next_cluster(sb, &clu.dir);
-		}
+		ret = exfat_chain_advance(sb, &clu, 1);

 		if (ret || clu.dir == EXFAT_EOF_CLUSTER) {
 			/* just initialized hint_stat */
@@ -1232,20 +1157,12 @@ int exfat_count_dir_entries(struct super_block *sb, struct exfat_chain *p_dir)
 			count++;
 		}

-		if (clu.flags == ALLOC_NO_FAT_CHAIN) {
-			if (--clu.size > 0)
-				clu.dir++;
-			else
-				clu.dir = EXFAT_EOF_CLUSTER;
-		} else {
-			if (exfat_get_next_cluster(sb, &(clu.dir)))
-				return -EIO;
-
-			if (unlikely(++clu_count > sbi->used_clusters)) {
-				exfat_fs_error(sb, "FAT or bitmap is corrupted");
-				return -EIO;
-			}
+		if (exfat_chain_advance(sb, &clu, 1))
+			return -EIO;

+		if (unlikely(++clu_count > sbi->used_clusters)) {
+			exfat_fs_error(sb, "FAT or bitmap is corrupted");
+			return -EIO;
 		}
 	}

--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -10,6 +10,7 @@
 #include <linux/ratelimit.h>
 #include <linux/nls.h>
 #include <linux/blkdev.h>
+#include <linux/backing-dev.h>
 #include <uapi/linux/exfat.h>

 #define EXFAT_ROOT_INO		1
@@ -79,6 +80,10 @@ enum {
 #define EXFAT_HINT_NONE		-1
 #define EXFAT_MIN_SUBDIR	2

+#define EXFAT_BLK_RA_SIZE(sb)		\
+	(min_t(blkcnt_t, (sb)->s_bdi->ra_pages, (sb)->s_bdi->io_pages) \
+	<< (PAGE_SHIFT - (sb)->s_blocksize_bits))
+
 /*
 * helpers for cluster size to byte conversion.
 */
@@ -117,9 +122,9 @@ enum {
 #define FAT_ENT_SIZE (4)
 #define FAT_ENT_SIZE_BITS (2)
 #define FAT_ENT_OFFSET_SECTOR(sb, loc) (EXFAT_SB(sb)->FAT1_start_sector + \
-	(((u64)loc << FAT_ENT_SIZE_BITS) >> sb->s_blocksize_bits))
+	(((u64)(loc) << FAT_ENT_SIZE_BITS) >> sb->s_blocksize_bits))
 #define FAT_ENT_OFFSET_BYTE_IN_SECTOR(sb, loc)	\
-	((loc << FAT_ENT_SIZE_BITS) & (sb->s_blocksize - 1))
+	(((loc) << FAT_ENT_SIZE_BITS) & (sb->s_blocksize - 1))

 /*
 * helpers for bitmap.
@@ -432,7 +437,8 @@ int exfat_set_volume_dirty(struct super_block *sb);
 int exfat_clear_volume_dirty(struct super_block *sb);

 /* fatent.c */
-#define exfat_get_next_cluster(sb, pclu) exfat_ent_get(sb, *(pclu), pclu, NULL)
+#define exfat_get_next_cluster(sb, pclu) \
+	exfat_cluster_walk(sb, (pclu), 1, ALLOC_FAT_CHAIN)

 int exfat_alloc_cluster(struct inode *inode, unsigned int num_alloc,
 		struct exfat_chain *p_chain, bool sync_bmap);
@@ -448,6 +454,28 @@ int exfat_find_last_cluster(struct super_block *sb, struct exfat_chain *p_chain,
 		unsigned int *ret_clu);
 int exfat_count_num_clusters(struct super_block *sb,
 		struct exfat_chain *p_chain, unsigned int *ret_count);
+int exfat_blk_readahead(struct super_block *sb, sector_t sec,
+		sector_t *ra, blkcnt_t *ra_cnt, sector_t end);
+
+static inline int
+exfat_cluster_walk(struct super_block *sb, unsigned int *clu,
+		unsigned int step, int flags)
+{
+	struct buffer_head *bh = NULL;
+
+	if (flags == ALLOC_NO_FAT_CHAIN) {
+		(*clu) += step;
+		return 0;
+	}
+
+	while (step--) {
+		if (exfat_ent_get(sb, *clu, clu, &bh))
+			return -EIO;
+	}
+	brelse(bh);
+
+	return 0;
+}

 /* balloc.c */
 int exfat_load_bitmap(struct super_block *sb);
@@ -524,6 +552,27 @@ int exfat_read_volume_label(struct super_block *sb,
 int exfat_write_volume_label(struct super_block *sb,
 			     struct exfat_uni_name *label);

+static inline int exfat_chain_advance(struct super_block *sb,
+		struct exfat_chain *chain, unsigned int step)
+{
+	unsigned int clu = chain->dir;
+
+	if (unlikely(chain->size < step))
+		return -EIO;
+
+	if (exfat_cluster_walk(sb, &clu, step, chain->flags))
+		return -EIO;
+
+	chain->size -= step;
+
+	if (chain->size == 0 && chain->flags == ALLOC_NO_FAT_CHAIN)
+		chain->dir = EXFAT_EOF_CLUSTER;
+	else
+		chain->dir = clu;
+
+	return 0;
+}
+
 /* inode.c */
 extern const struct inode_operations exfat_file_inode_operations;
 void exfat_sync_inode(struct inode *inode);
@@ -577,7 +626,7 @@ void exfat_set_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts,
 		u8 *tz, __le16 *time, __le16 *date, u8 *time_cs);
 u16 exfat_calc_chksum16(void *data, int len, u16 chksum, int type);
 u32 exfat_calc_chksum32(void *data, int len, u32 chksum, int type);
-void exfat_update_bh(struct buffer_head *bh, int sync);
+int exfat_update_bh(struct buffer_head *bh, int sync);
 int exfat_update_bhs(struct buffer_head **bhs, int nr_bhs, int sync);
 void exfat_chain_set(struct exfat_chain *ec, unsigned int dir,
 		unsigned int size, unsigned char flags);
--- a/fs/exfat/exfat_raw.h
+++ b/fs/exfat/exfat_raw.h
@@ -25,6 +25,7 @@
 #define EXFAT_FIRST_CLUSTER	2
 #define EXFAT_DATA_CLUSTER_COUNT(sbi)	\
 	((sbi)->num_clusters - EXFAT_RESERVED_CLUSTERS)
+#define EXFAT_MAX_NUM_CLUSTER		(0xFFFFFFF5)

 /* AllocationPossible and NoFatChain field in GeneralSecondaryFlags Field */
 #define ALLOC_POSSIBLE		0x01
--- a/fs/exfat/fatent.c
+++ b/fs/exfat/fatent.c
@@ -11,11 +11,11 @@
 #include "exfat_raw.h"
 #include "exfat_fs.h"

-static int exfat_mirror_bh(struct super_block *sb, sector_t sec,
-		struct buffer_head *bh)
+static int exfat_mirror_bh(struct super_block *sb, struct buffer_head *bh)
 {
 	struct buffer_head *c_bh;
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
+	sector_t sec = bh->b_blocknr;
 	sector_t sec2;
 	int err = 0;

@@ -25,22 +25,30 @@ static int exfat_mirror_bh(struct super_block *sb, sector_t sec,
 		if (!c_bh)
 			return -ENOMEM;
 		memcpy(c_bh->b_data, bh->b_data, sb->s_blocksize);
-		set_buffer_uptodate(c_bh);
-		mark_buffer_dirty(c_bh);
-		if (sb->s_flags & SB_SYNCHRONOUS)
-			err = sync_dirty_buffer(c_bh);
+		err = exfat_update_bh(c_bh, sb->s_flags & SB_SYNCHRONOUS);
 		brelse(c_bh);
 	}

 	return err;
 }

+static int exfat_end_bh(struct super_block *sb, struct buffer_head *bh)
+{
+	int err;
+
+	err = exfat_update_bh(bh, sb->s_flags & SB_SYNCHRONOUS);
+	if (!err)
+		err = exfat_mirror_bh(sb, bh);
+	brelse(bh);
+	return err;
+}
+
 static int __exfat_ent_get(struct super_block *sb, unsigned int loc,
-		unsigned int *content, struct buffer_head **last)
+		unsigned int *content, struct buffer_head **cache)
 {
 	unsigned int off;
 	sector_t sec;
-	struct buffer_head *bh = last ? *last : NULL;
+	struct buffer_head *bh = *cache;

 	sec = FAT_ENT_OFFSET_SECTOR(sb, loc);
 	off = FAT_ENT_OFFSET_BYTE_IN_SECTOR(sb, loc);
@@ -48,8 +56,7 @@ static int __exfat_ent_get(struct super_block *sb, unsigned int loc,
 	if (!bh || bh->b_blocknr != sec || !buffer_uptodate(bh)) {
 		brelse(bh);
 		bh = sb_bread(sb, sec);
-		if (last)
-			*last = bh;
+		*cache = bh;
 		if (unlikely(!bh))
 			return -EIO;
 	}
@@ -60,39 +67,48 @@ static int __exfat_ent_get(struct super_block *sb, unsigned int loc,
 	if (*content > EXFAT_BAD_CLUSTER)
 		*content = EXFAT_EOF_CLUSTER;

-	if (!last)
-		brelse(bh);
+	return 0;
+}
+
+static int __exfat_ent_set(struct super_block *sb, unsigned int loc,
+		unsigned int content, struct buffer_head **cache)
+{
+	sector_t sec;
+	__le32 *fat_entry;
+	struct buffer_head *bh = cache ? *cache : NULL;
+	unsigned int off;
+
+	sec = FAT_ENT_OFFSET_SECTOR(sb, loc);
+	off = FAT_ENT_OFFSET_BYTE_IN_SECTOR(sb, loc);
+
+	if (!bh || bh->b_blocknr != sec || !buffer_uptodate(bh)) {
+		if (bh)
+			exfat_end_bh(sb, bh);
+		bh = sb_bread(sb, sec);
+		if (cache)
+			*cache = bh;
+		if (unlikely(!bh))
+			return -EIO;
+	}
+
+	fat_entry = (__le32 *)&(bh->b_data[off]);
+	*fat_entry = cpu_to_le32(content);
+	if (!cache)
+		exfat_end_bh(sb, bh);
 	return 0;
 }

 int exfat_ent_set(struct super_block *sb, unsigned int loc,
 		unsigned int content)
 {
-	unsigned int off;
-	sector_t sec;
-	__le32 *fat_entry;
-	struct buffer_head *bh;
-
-	sec = FAT_ENT_OFFSET_SECTOR(sb, loc);
-	off = FAT_ENT_OFFSET_BYTE_IN_SECTOR(sb, loc);
-
-	bh = sb_bread(sb, sec);
-	if (!bh)
-		return -EIO;
-
-	fat_entry = (__le32 *)&(bh->b_data[off]);
-	*fat_entry = cpu_to_le32(content);
-	exfat_update_bh(bh, sb->s_flags & SB_SYNCHRONOUS);
-	exfat_mirror_bh(sb, sec, bh);
-	brelse(bh);
-	return 0;
+	return __exfat_ent_set(sb, loc, content, NULL);
 }

 /*
 * Caller must release the buffer_head if no error return.
 */
 int exfat_ent_get(struct super_block *sb, unsigned int loc,
-		unsigned int *content, struct buffer_head **last)
+		unsigned int *content, struct buffer_head **cache)
 {
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);

@@ -103,7 +119,7 @@ int exfat_ent_get(struct super_block *sb, unsigned int loc,
 		goto err;
 	}

-	if (unlikely(__exfat_ent_get(sb, loc, content, last))) {
+	if (unlikely(__exfat_ent_get(sb, loc, content, cache))) {
 		exfat_fs_error_ratelimit(sb,
 			"failed to access to FAT (entry 0x%08x)",
 			loc);
@@ -132,31 +148,69 @@ int exfat_ent_get(struct super_block *sb, unsigned int loc,
 	}

 	return 0;
-err:
-	if (last) {
-		brelse(*last);

-		/* Avoid double release */
-		*last = NULL;
-	}
+err:
+	/* Avoid double release */
+	brelse(*cache);
+	*cache = NULL;
 	return -EIO;
 }

+int exfat_blk_readahead(struct super_block *sb, sector_t sec,
+		sector_t *ra, blkcnt_t *ra_cnt, sector_t end)
+{
+	struct blk_plug plug;
+
+	if (sec < *ra)
+		return 0;
+
+	*ra += *ra_cnt;
+
+	/* No blocks left (or only the last block), skip readahead. */
+	if (*ra >= end)
+		return 0;
+
+	*ra_cnt = min(end - *ra + 1, EXFAT_BLK_RA_SIZE(sb));
+	if (*ra_cnt == 0) {
+		/* Move 'ra' to the end to disable readahead. */
+		*ra = end;
+		return 0;
+	}
+
+	blk_start_plug(&plug);
+	for (unsigned int i = 0; i < *ra_cnt; i++)
+		sb_breadahead(sb, *ra + i);
+	blk_finish_plug(&plug);
+	return 0;
+}
+
 int exfat_chain_cont_cluster(struct super_block *sb, unsigned int chain,
 		unsigned int len)
 {
+	struct buffer_head *bh = NULL;
+	sector_t sec, end, ra;
+	blkcnt_t ra_cnt = 0;
+
 	if (!len)
 		return 0;

+	ra = FAT_ENT_OFFSET_SECTOR(sb, chain);
+	end = FAT_ENT_OFFSET_SECTOR(sb, chain + len - 1);
+
 	while (len > 1) {
-		if (exfat_ent_set(sb, chain, chain + 1))
+		sec = FAT_ENT_OFFSET_SECTOR(sb, chain);
+		exfat_blk_readahead(sb, sec, &ra, &ra_cnt, end);
+
+		if (__exfat_ent_set(sb, chain, chain + 1, &bh))
 			return -EIO;
 		chain++;
 		len--;
 	}

-	if (exfat_ent_set(sb, chain, EXFAT_EOF_CLUSTER))
+	if (__exfat_ent_set(sb, chain, EXFAT_EOF_CLUSTER, &bh))
 		return -EIO;
+
+	exfat_end_bh(sb, bh);
 	return 0;
 }

--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -13,6 +13,7 @@
 #include <linux/msdos_fs.h>
 #include <linux/writeback.h>
 #include <linux/filelock.h>
+#include <linux/falloc.h>

 #include "exfat_raw.h"
 #include "exfat_fs.h"
@@ -33,6 +34,7 @@ static int exfat_cont_expand(struct inode *inode, loff_t size)
 		return ret;

 	num_clusters = EXFAT_B_TO_CLU(exfat_ondisk_size(inode), sbi);
+	/* integer overflow is already checked in inode_newsize_ok(). */
 	new_num_clusters = EXFAT_B_TO_CLU_ROUND_UP(size, sbi);

 	if (new_num_clusters == num_clusters)
@@ -90,6 +92,45 @@ free_clu:
 	return -EIO;
 }

+/*
+ * Preallocate space for a file. This implements exfat's fallocate file
+ * operation, which gets called from sys_fallocate system call. User space
+ * requests len bytes at offset. In contrary to fat, we only support
+ * FALLOC_FL_ALLOCATE_RANGE because by leaving the valid data length(VDL)
+ * field, it is unnecessary to zero out the newly allocated clusters.
+ */
+static long exfat_fallocate(struct file *file, int mode,
+			  loff_t offset, loff_t len)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t newsize = offset + len;
+	int err = 0;
+
+	/* No support for other modes */
+	if (mode != FALLOC_FL_ALLOCATE_RANGE)
+		return -EOPNOTSUPP;
+
+	/* No support for dir */
+	if (!S_ISREG(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	if (unlikely(exfat_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
+	inode_lock(inode);
+
+	if (newsize <= i_size_read(inode))
+		goto error;
+
+	/* This is just an expanding truncate */
+	err = exfat_cont_expand(inode, newsize);
+
+error:
+	inode_unlock(inode);
+
+	return err;
+}
+
 static bool exfat_allow_set_time(struct mnt_idmap *idmap,
 				 struct exfat_sb_info *sbi, struct inode *inode)
 {
@@ -771,6 +812,7 @@ const struct file_operations exfat_file_operations = {
 	.fsync		= exfat_file_fsync,
 	.splice_read	= exfat_splice_read,
 	.splice_write	= iter_file_splice_write,
+	.fallocate	= exfat_fallocate,
 	.setlease	= generic_setlease,
 };

--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -204,8 +204,9 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset,
 				 * so fat-chain should be synced with
 				 * alloc-bitmap
 				 */
-				exfat_chain_cont_cluster(sb, ei->start_clu,
-					num_clusters);
+				if (exfat_chain_cont_cluster(sb, ei->start_clu,
+						num_clusters))
+					return -EIO;
 				ei->flags = ALLOC_FAT_CHAIN;
 			}
 			if (new_clu.flags == ALLOC_FAT_CHAIN)
@@ -213,7 +214,6 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset,
 					return -EIO;
 		}

-		num_clusters += num_to_be_allocated;
 		*clu = new_clu.dir;

 		inode->i_blocks += EXFAT_CLU_TO_B(num_to_be_allocated, sbi) >> 9;
@@ -225,15 +225,8 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset,
 		 * *clu = (the first cluster of the allocated chain) =>
 		 * (the last cluster of ...)
 		 */
-		if (ei->flags == ALLOC_NO_FAT_CHAIN) {
-			*clu += num_to_be_allocated - 1;
-		} else {
-			while (num_to_be_allocated > 1) {
-				if (exfat_get_next_cluster(sb, clu))
-					return -EIO;
-				num_to_be_allocated--;
-			}
-		}
+		if (exfat_cluster_walk(sb, clu, num_to_be_allocated - 1, ei->flags))
+			return -EIO;
 		*count = 1;
 	}

@@ -686,7 +679,7 @@ out:

 void exfat_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);

 	if (!inode->i_nlink) {
 		i_size_write(inode, 0);
--- a/fs/exfat/misc.c
+++ b/fs/exfat/misc.c
@@ -161,13 +161,17 @@ u32 exfat_calc_chksum32(void *data, int len, u32 chksum, int type)
 	return chksum;
 }

-void exfat_update_bh(struct buffer_head *bh, int sync)
+int exfat_update_bh(struct buffer_head *bh, int sync)
 {
+	int err = 0;
+
 	set_buffer_uptodate(bh);
 	mark_buffer_dirty(bh);

 	if (sync)
-		sync_dirty_buffer(bh);
+		err = sync_dirty_buffer(bh);
+
+	return err;
 }

 int exfat_update_bhs(struct buffer_head **bhs, int nr_bhs, int sync)
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -246,15 +246,8 @@ static int exfat_search_empty_slot(struct super_block *sb,
 		i += ret;

 		while (i >= dentries_per_clu) {
-			if (clu.flags == ALLOC_NO_FAT_CHAIN) {
-				if (--clu.size > 0)
-					clu.dir++;
-				else
-					clu.dir = EXFAT_EOF_CLUSTER;
-			} else {
-				if (exfat_get_next_cluster(sb, &clu.dir))
-					return -EIO;
-			}
+			if (exfat_chain_advance(sb, &clu, 1))
+				return -EIO;

 			i -= dentries_per_clu;
 		}
@@ -365,7 +358,8 @@ int exfat_find_empty_entry(struct inode *inode,
 			/* no-fat-chain bit is disabled,
 			 * so fat-chain should be synced with alloc-bitmap
 			 */
-			exfat_chain_cont_cluster(sb, p_dir->dir, p_dir->size);
+			if (exfat_chain_cont_cluster(sb, p_dir->dir, p_dir->size))
+				return -EIO;
 			p_dir->flags = ALLOC_FAT_CHAIN;
 			hint_femp.cur.flags = ALLOC_FAT_CHAIN;
 		}
@@ -873,9 +867,10 @@ static struct dentry *exfat_mkdir(struct mnt_idmap *idmap, struct inode *dir,

 	i_pos = exfat_make_i_pos(&info);
 	inode = exfat_build_inode(sb, &info, i_pos);
-	err = PTR_ERR_OR_ZERO(inode);
-	if (err)
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
 		goto unlock;
+	}

 	inode_inc_iversion(inode);
 	EXFAT_I(inode)->i_crtime = simple_inode_init_ts(inode);
@@ -886,7 +881,7 @@ static struct dentry *exfat_mkdir(struct mnt_idmap *idmap, struct inode *dir,

 unlock:
 	mutex_unlock(&EXFAT_SB(sb)->s_lock);
-	return ERR_PTR(err);
+	return err ? ERR_PTR(err) : NULL;
 }

 static int exfat_check_dir_empty(struct super_block *sb,
@@ -923,19 +918,12 @@ static int exfat_check_dir_empty(struct super_block *sb,
 			return -ENOTEMPTY;
 		}

-		if (clu.flags == ALLOC_NO_FAT_CHAIN) {
-			if (--clu.size > 0)
-				clu.dir++;
-			else
-				clu.dir = EXFAT_EOF_CLUSTER;
-		} else {
-			if (exfat_get_next_cluster(sb, &(clu.dir)))
-				return -EIO;
+		if (exfat_chain_advance(sb, &clu, 1))
+			return -EIO;

-			/* break if the cluster chain includes a loop */
-			if (unlikely(++clu_count > EXFAT_DATA_CLUSTER_COUNT(sbi)))
-				break;
-		}
+		/* break if the cluster chain includes a loop */
+		if (unlikely(++clu_count > EXFAT_DATA_CLUSTER_COUNT(sbi)))
+			break;
 	}

 	return 0;
--- a/fs/exfat/super.c
+++ b/fs/exfat/super.c
@@ -531,9 +531,14 @@ static int exfat_read_boot_sector(struct super_block *sb)
 	if (sbi->vol_flags & MEDIA_FAILURE)
 		exfat_warn(sb, "Medium has reported failures. Some data may be lost.");

-	/* exFAT file size is limited by a disk volume size */
-	sb->s_maxbytes = (u64)(sbi->num_clusters - EXFAT_RESERVED_CLUSTERS) <<
-		sbi->cluster_size_bits;
+	/*
+	 * Set to the max possible volume size for this volume's cluster size so
+	 * that any integer overflow from bytes to cluster size conversion is
+	 * checked in inode_newsize_ok(). Clamped to MAX_LFS_FILESIZE for 32-bit
+	 * machines.
+	 */
+	sb->s_maxbytes = min(MAX_LFS_FILESIZE,
+			     EXFAT_CLU_TO_B((loff_t)EXFAT_MAX_NUM_CLUSTER, sbi));

 	/* check logical sector size */
 	if (exfat_calibrate_blocksize(sb, 1 << p_boot->sect_size_bits))