Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kern…

…el/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "A lot of bug fixes and cleanups for ext4, including:

   - Fix performance problems found in dioread_nolock now that it is the
     default, caused by transaction leaks.

   - Clean up fiemap handling in ext4

   - Clean up and refactor multiple block allocator (mballoc) code

   - Fix a problem with mballoc with a smaller file systems running out
     of blocks because they couldn't properly use blocks that had been
     reserved by inode preallocation.

   - Fixed a race in ext4_sync_parent() versus rename()

   - Simplify the error handling in the extent manipulation code

   - Make sure all metadata I/O errors are felected to
     ext4_ext_dirty()'s and ext4_make_inode_dirty()'s callers.

   - Avoid passing an error pointer to brelse in ext4_xattr_set()

   - Fix race which could result to freeing an inode on the dirty last
     in data=journal mode.

   - Fix refcount handling if ext4_iget() fails

   - Fix a crash in generic/019 caused by a corrupted extent node"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (58 commits)
  ext4: avoid unnecessary transaction starts during writeback
  ext4: don't block for O_DIRECT if IOCB_NOWAIT is set
  ext4: remove the access_ok() check in ext4_ioctl_get_es_cache
  fs: remove the access_ok() check in ioctl_fiemap
  fs: handle FIEMAP_FLAG_SYNC in fiemap_prep
  fs: move fiemap range validation into the file systems instances
  iomap: fix the iomap_fiemap prototype
  fs: move the fiemap definitions out of fs.h
  fs: mark __generic_block_fiemap static
  ext4: remove the call to fiemap_check_flags in ext4_fiemap
  ext4: split _ext4_fiemap
  ext4: fix fiemap size checks for bitmap files
  ext4: fix EXT4_MAX_LOGICAL_BLOCK macro
  add comment for ext4_dir_entry_2 file_type member
  jbd2: avoid leaking transaction credits when unreserving handle
  ext4: drop ext4_journal_free_reserved()
  ext4: mballoc: use lock for checking free blocks while retrying
  ext4: mballoc: refactor ext4_mb_good_group()
  ext4: mballoc: introduce pcpu seqcnt for freeing PA to improve ENOSPC handling
  ext4: mballoc: refactor ext4_mb_discard_preallocations()
  ...

Documentation/filesystems/fiemap.rst

@@ -206,16 +206,18 @@ EINTR once fatal signal received.
 
 
 Flag checking should be done at the beginning of the ->fiemap callback via the
-fiemap_check_flags() helper::
+fiemap_prep() helper::
 
-  int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
+  int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		  u64 start, u64 *len, u32 supported_flags);
 
 The struct fieinfo should be passed in as received from ioctl_fiemap(). The
 set of fiemap flags which the fs understands should be passed via fs_flags. If
-fiemap_check_flags finds invalid user flags, it will place the bad values in
+fiemap_prep finds invalid user flags, it will place the bad values in
 fieinfo->fi_flags and return -EBADR. If the file system gets -EBADR, from
-fiemap_check_flags(), it should immediately exit, returning that error back to
-ioctl_fiemap().
+fiemap_prep(), it should immediately exit, returning that error back to
+ioctl_fiemap().  Additionally the range is validate against the supported
+maximum file size.
 
 
 For each extent in the request range, the file system should call

fs/bad_inode.c

@@ -15,6 +15,7 @@
 #include <linux/time.h>
 #include <linux/namei.h>
 #include <linux/poll.h>
+#include <linux/fiemap.h>
 
 static int bad_file_open(struct inode *inode, struct file *filp)
 {

fs/btrfs/extent_io.h

@@ -5,6 +5,7 @@
 
 #include <linux/rbtree.h>
 #include <linux/refcount.h>
+#include <linux/fiemap.h>
 #include "ulist.h"
 
 /*

fs/btrfs/inode.c

@@ -7828,14 +7828,12 @@ const struct iomap_dio_ops btrfs_dops = {
 	.submit_io		= btrfs_submit_direct,
 };
 
-#define BTRFS_FIEMAP_FLAGS	(FIEMAP_FLAG_SYNC)
-
 static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		__u64 start, __u64 len)
 {
 	int	ret;
 
-	ret = fiemap_check_flags(fieinfo, BTRFS_FIEMAP_FLAGS);
+	ret = fiemap_prep(inode, fieinfo, start, &len, 0);
 	if (ret)
 		return ret;
 

fs/cifs/inode.c

@@ -25,6 +25,7 @@
 #include <linux/freezer.h>
 #include <linux/sched/signal.h>
 #include <linux/wait_bit.h>
+#include <linux/fiemap.h>
 
 #include <asm/div64.h>
 #include "cifsfs.h"

fs/cifs/smb2ops.c

@@ -12,6 +12,7 @@
 #include <linux/uuid.h>
 #include <linux/sort.h>
 #include <crypto/aead.h>
+#include <linux/fiemap.h>
 #include "cifsfs.h"
 #include "cifsglob.h"
 #include "smb2pdu.h"
@@ -3407,8 +3408,9 @@ static int smb3_fiemap(struct cifs_tcon *tcon,
 	int i, num, rc, flags, last_blob;
 	u64 next;
 
-	if (fiemap_check_flags(fei, FIEMAP_FLAG_SYNC))
-		return -EBADR;
+	rc = fiemap_prep(d_inode(cfile->dentry), fei, start, &len, 0);
+	if (rc)
+		return rc;
 
 	xid = get_xid();
  again:

fs/ext2/inode.c

@@ -36,6 +36,7 @@
 #include <linux/iomap.h>
 #include <linux/namei.h>
 #include <linux/uio.h>
+#include <linux/fiemap.h>
 #include "ext2.h"
 #include "acl.h"
 #include "xattr.h"

fs/ext4/Kconfig

@@ -99,8 +99,7 @@ config EXT4_DEBUG
 	  Enables run-time debugging support for the ext4 filesystem.
 
 	  If you select Y here, then you will be able to turn on debugging
-	  with a command such as:
-		echo 1 > /sys/module/ext4/parameters/mballoc_debug
+	  using dynamic debug control for mb_debug() / ext_debug() msgs.
 
 config EXT4_KUNIT_TESTS
 	tristate "KUnit tests for ext4"

fs/ext4/acl.c

@@ -215,9 +215,8 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type,
 				      value, size, xattr_flags);
 
 	kfree(value);
-	if (!error) {
+	if (!error)
 		set_cached_acl(inode, type, acl);
-	}
 
 	return error;
 }
@@ -256,7 +255,7 @@ ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	if (!error && update_mode) {
 		inode->i_mode = mode;
 		inode->i_ctime = current_time(inode);
-		ext4_mark_inode_dirty(handle, inode);
+		error = ext4_mark_inode_dirty(handle, inode);
 	}
 out_stop:
 	ext4_journal_stop(handle);

fs/ext4/balloc.c

@@ -903,10 +903,11 @@ ext4_fsblk_t ext4_inode_to_goal_block(struct inode *inode)
 		return bg_start;
 
 	if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
-		colour = (current->pid % 16) *
+		colour = (task_pid_nr(current) % 16) *
 			(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
 	else
-		colour = (current->pid % 16) * ((last_block - bg_start) / 16);
+		colour = (task_pid_nr(current) % 16) *
+			((last_block - bg_start) / 16);
 	return bg_start + colour;
 }
 

fs/ext4/ext4.h

@@ -36,6 +36,7 @@
 #include <crypto/hash.h>
 #include <linux/falloc.h>
 #include <linux/percpu-rwsem.h>
+#include <linux/fiemap.h>
 #ifdef __KERNEL__
 #include <linux/compat.h>
 #endif
@@ -80,14 +81,22 @@
 #define ext4_debug(fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
 #endif
 
+ /*
+  * Turn on EXT_DEBUG to enable ext4_ext_show_path/leaf/move in extents.c
+  */
+#define EXT_DEBUG__
+
 /*
- * Turn on EXT_DEBUG to get lots of info about extents operations.
+ * Dynamic printk for controlled extents debugging.
  */
-#define EXT_DEBUG__
-#ifdef EXT_DEBUG
-#define ext_debug(fmt, ...)	printk(fmt, ##__VA_ARGS__)
+#ifdef CONFIG_EXT4_DEBUG
+#define ext_debug(ino, fmt, ...)					\
+	pr_debug("[%s/%d] EXT4-fs (%s): ino %lu: (%s, %d): %s:" fmt,	\
+		 current->comm, task_pid_nr(current),			\
+		 ino->i_sb->s_id, ino->i_ino, __FILE__, __LINE__,	\
+		 __func__, ##__VA_ARGS__)
 #else
-#define ext_debug(fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
+#define ext_debug(ino, fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
 #endif
 
 /* data type for block offset of block group */
@@ -142,6 +151,8 @@ enum SHIFT_DIRECTION {
 #define EXT4_MB_USE_ROOT_BLOCKS		0x1000
 /* Use blocks from reserved pool */
 #define EXT4_MB_USE_RESERVED		0x2000
+/* Do strict check for free blocks while retrying block allocation */
+#define EXT4_MB_STRICT_CHECK		0x4000
 
 struct ext4_allocation_request {
 	/* target inode for block we're allocating */
@@ -171,10 +182,10 @@ struct ext4_allocation_request {
  * well as to store the information returned by ext4_map_blocks().  It
  * takes less room on the stack than a struct buffer_head.
  */
-#define EXT4_MAP_NEW		(1 << BH_New)
-#define EXT4_MAP_MAPPED		(1 << BH_Mapped)
-#define EXT4_MAP_UNWRITTEN	(1 << BH_Unwritten)
-#define EXT4_MAP_BOUNDARY	(1 << BH_Boundary)
+#define EXT4_MAP_NEW		BIT(BH_New)
+#define EXT4_MAP_MAPPED		BIT(BH_Mapped)
+#define EXT4_MAP_UNWRITTEN	BIT(BH_Unwritten)
+#define EXT4_MAP_BOUNDARY	BIT(BH_Boundary)
 #define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
 				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY)
 
@@ -417,7 +428,7 @@ struct flex_groups {
 /* 0x00400000 was formerly EXT4_EOFBLOCKS_FL */
 #define EXT4_INLINE_DATA_FL		0x10000000 /* Inode has inline data. */
 #define EXT4_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
-#define EXT4_CASEFOLD_FL		0x40000000 /* Casefolded file */
+#define EXT4_CASEFOLD_FL		0x40000000 /* Casefolded directory */
 #define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
 
 #define EXT4_FL_USER_VISIBLE		0x705BDFFF /* User visible flags */
@@ -490,6 +501,7 @@ enum {
 /* 22 was formerly EXT4_INODE_EOFBLOCKS */
 	EXT4_INODE_INLINE_DATA	= 28,	/* Data in inode. */
 	EXT4_INODE_PROJINHERIT	= 29,	/* Create with parents projid */
+	EXT4_INODE_CASEFOLD	= 30,	/* Casefolded directory */
 	EXT4_INODE_RESERVED	= 31,	/* reserved for ext4 lib */
 };
 
@@ -535,6 +547,7 @@ static inline void ext4_check_flag_values(void)
 	CHECK_FLAG_VALUE(EA_INODE);
 	CHECK_FLAG_VALUE(INLINE_DATA);
 	CHECK_FLAG_VALUE(PROJINHERIT);
+	CHECK_FLAG_VALUE(CASEFOLD);
 	CHECK_FLAG_VALUE(RESERVED);
 }
 
@@ -609,8 +622,6 @@ enum {
 #define EXT4_GET_BLOCKS_METADATA_NOFAIL		0x0020
 	/* Don't normalize allocation size (used for fallocate) */
 #define EXT4_GET_BLOCKS_NO_NORMALIZE		0x0040
-	/* Request will not result in inode size update (user for fallocate) */
-#define EXT4_GET_BLOCKS_KEEP_SIZE		0x0080
 	/* Convert written extents to unwritten */
 #define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN	0x0100
 	/* Write zeros to newly created written extents */
@@ -632,6 +643,7 @@ enum {
  */
 #define EXT4_EX_NOCACHE				0x40000000
 #define EXT4_EX_FORCE_CACHE			0x20000000
+#define EXT4_EX_NOFAIL				0x10000000
 
 /*
  * Flags used by ext4_free_blocks
@@ -2051,7 +2063,7 @@ struct ext4_dir_entry_2 {
 	__le32	inode;			/* Inode number */
 	__le16	rec_len;		/* Directory entry length */
 	__u8	name_len;		/* Name length */
-	__u8	file_type;
+	__u8	file_type;		/* See file type macros EXT4_FT_* below */
 	char	name[EXT4_NAME_LEN];	/* File name */
 };
 
@@ -3354,7 +3366,7 @@ struct ext4_extent;
  */
 #define EXT_MAX_BLOCKS	0xffffffff
 
-extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
+extern void ext4_ext_tree_init(handle_t *handle, struct inode *inode);
 extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
 extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			       struct ext4_map_blocks *map, int flags);

fs/ext4/ext4_extents.h

@@ -170,10 +170,13 @@ struct partial_cluster {
 	(EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
 #define EXT_LAST_INDEX(__hdr__) \
 	(EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
-#define EXT_MAX_EXTENT(__hdr__) \
-	(EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)
+#define EXT_MAX_EXTENT(__hdr__)	\
+	((le16_to_cpu((__hdr__)->eh_max)) ? \
+	((EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) \
+					: 0)
 #define EXT_MAX_INDEX(__hdr__) \
-	(EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)
+	((le16_to_cpu((__hdr__)->eh_max)) ? \
+	((EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) : 0)
 
 static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode)
 {

fs/ext4/ext4_jbd2.h

@@ -222,7 +222,10 @@ ext4_mark_iloc_dirty(handle_t *handle,
 int ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
 			struct ext4_iloc *iloc);
 
-int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode);
+#define ext4_mark_inode_dirty(__h, __i)					\
+		__ext4_mark_inode_dirty((__h), (__i), __func__, __LINE__)
+int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode,
+				const char *func, unsigned int line);
 
 int ext4_expand_extra_isize(struct inode *inode,
 			    unsigned int new_extra_isize,
@@ -335,12 +338,6 @@ static inline handle_t *__ext4_journal_start(struct inode *inode,
 handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
 					int type);
 
-static inline void ext4_journal_free_reserved(handle_t *handle)
-{
-	if (ext4_handle_valid(handle))
-		jbd2_journal_free_reserved(handle);
-}
-
 static inline handle_t *ext4_journal_current_handle(void)
 {
 	return journal_current_handle();