Release 4.10 fs/ext4/inode.c

/*
 *  linux/fs/ext4/inode.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/inode.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  64-bit file support on 64-bit platforms by Jakub Jelinek
 *      (jj@sunsite.ms.mff.cuni.cz)
 *
 *  Assorted race fixes, rewrite of ext4_get_block() by Al Viro, 2000
 */

#include <linux/fs.h>
#include <linux/time.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/dax.h>
#include <linux/quotaops.h>
#include <linux/string.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/mpage.h>
#include <linux/namei.h>
#include <linux/uio.h>
#include <linux/bio.h>
#include <linux/workqueue.h>
#include <linux/kernel.h>
#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/bitops.h>
#include <linux/iomap.h>

#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include "truncate.h"

#include <trace/events/ext4.h>


#define MPAGE_DA_EXTENT_TAIL 0x01



static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
			      struct ext4_inode_info *ei)
{
	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
	__u32 csum;
	__u16 dummy_csum = 0;
	int offset = offsetof(struct ext4_inode, i_checksum_lo);
	unsigned int csum_size = sizeof(dummy_csum);

	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, offset);
	csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, csum_size);
	offset += csum_size;
	csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
			   EXT4_GOOD_OLD_INODE_SIZE - offset);

	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
		offset = offsetof(struct ext4_inode, i_checksum_hi);
		csum = ext4_chksum(sbi, csum, (__u8 *)raw +
				   EXT4_GOOD_OLD_INODE_SIZE,
				   offset - EXT4_GOOD_OLD_INODE_SIZE);
		if (EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
			csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum,
					   csum_size);
			offset += csum_size;
		}
		csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
				   EXT4_INODE_SIZE(inode->i_sb) - offset);
	}

	return csum;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
daeho jeong
daeho jeong
134
58.01%
2
50.00%
darrick j. wong
darrick j. wong
89
38.53%
1
25.00%
dmitriy monakhov
dmitriy monakhov
8
3.46%
1
25.00%
Total
231
100.00%
4
100.00%



static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw,
				  struct ext4_inode_info *ei)
{
	__u32 provided, calculated;

	if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
	    cpu_to_le32(EXT4_OS_LINUX) ||
	    !ext4_has_metadata_csum(inode->i_sb))
		return 1;

	provided = le16_to_cpu(raw->i_checksum_lo);
	calculated = ext4_inode_csum(inode, raw, ei);
	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
		provided |= ((__u32)le16_to_cpu(raw->i_checksum_hi)) << 16;
	else
		calculated &= 0xFFFF;

	return provided == calculated;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
darrick j. wong
darrick j. wong
120
99.17%
1
50.00%
dmitriy monakhov
dmitriy monakhov
1
0.83%
1
50.00%
Total
121
100.00%
2
100.00%



static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
				struct ext4_inode_info *ei)
{
	__u32 csum;

	if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
	    cpu_to_le32(EXT4_OS_LINUX) ||
	    !ext4_has_metadata_csum(inode->i_sb))
		return;

	csum = ext4_inode_csum(inode, raw, ei);
	raw->i_checksum_lo = cpu_to_le16(csum & 0xFFFF);
	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
		raw->i_checksum_hi = cpu_to_le16(csum >> 16);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
darrick j. wong
darrick j. wong
103
99.04%
1
50.00%
dmitriy monakhov
dmitriy monakhov
1
0.96%
1
50.00%
Total
104
100.00%
2
100.00%



static inline int ext4_begin_ordered_truncate(struct inode *inode,
					      loff_t new_size)
{
	trace_ext4_begin_ordered_truncate(inode, new_size);
	/*
         * If jinode is zero, then we never opened the file for
         * writing, so there's no need to call
         * jbd2_journal_begin_ordered_truncate() since there's no
         * outstanding writes we need to flush.
         */
	if (!EXT4_I(inode)->jinode)
		return 0;
	return jbd2_journal_begin_ordered_truncate(EXT4_JOURNAL(inode),
						   EXT4_I(inode)->jinode,
						   new_size);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
jan kara
jan kara
32
59.26%
2
50.00%
theodore tso
theodore tso
22
40.74%
2
50.00%
Total
54
100.00%
4
100.00%

static void ext4_invalidatepage(struct page *page, unsigned int offset,
				unsigned int length);
static int __ext4_journalled_writepage(struct page *page, unsigned int len);
static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh);
static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
				  int pextents);

/*
 * Test whether an inode is a fast symlink.
 */


int ext4_inode_is_fast_symlink(struct inode *inode)
{
        int ea_blocks = EXT4_I(inode)->i_file_acl ?
		EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0;

	if (ext4_has_inline_data(inode))
		return 0;

	return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
dave kleikamp
dave kleikamp
44
74.58%
1
25.00%
zheng liu
zheng liu
10
16.95%
1
25.00%
yongqiang yang
yongqiang yang
3
5.08%
1
25.00%
mingming cao
mingming cao
2
3.39%
1
25.00%
Total
59
100.00%
4
100.00%

/*
 * Restart the transaction associated with *handle.  This does a commit,
 * so before we call here everything must be consistently dirtied against
 * this transaction.
 */


int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
				 int nblocks)
{
	int ret;

	/*
         * Drop i_data_sem to avoid deadlock with ext4_map_blocks.  At this
         * moment, get_block can be called only for blocks inside i_size since
         * page cache has been already dropped and writes are blocked by
         * i_mutex. So we can safely drop the i_data_sem here.
         */
	BUG_ON(EXT4_JOURNAL(inode) == NULL);
	jbd_debug(2, "restarting handle %p\n", handle);
	up_write(&EXT4_I(inode)->i_data_sem);
	ret = ext4_journal_restart(handle, nblocks);
	down_write(&EXT4_I(inode)->i_data_sem);
	ext4_discard_preallocations(inode);

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
jan kara
jan kara
34
43.04%
1
14.29%
dave kleikamp
dave kleikamp
27
34.18%
1
14.29%
frank mayhar
frank mayhar
10
12.66%
1
14.29%
aneesh kumar
aneesh kumar
5
6.33%
1
14.29%
mingming cao
mingming cao
1
1.27%
1
14.29%
amir goldstein
amir goldstein
1
1.27%
1
14.29%
theodore tso
theodore tso
1
1.27%
1
14.29%
Total
79
100.00%
7
100.00%

/*
 * Called at the last iput() if i_nlink is zero.
 */


void ext4_evict_inode(struct inode *inode)
{
	handle_t *handle;
	int err;

	trace_ext4_evict_inode(inode);

	if (inode->i_nlink) {
		/*
                 * When journalling data dirty buffers are tracked only in the
                 * journal. So although mm thinks everything is clean and
                 * ready for reaping the inode might still have some pages to
                 * write in the running transaction or waiting to be
                 * checkpointed. Thus calling jbd2_journal_invalidatepage()
                 * (via truncate_inode_pages()) to discard these buffers can
                 * cause data loss. Also even if we did not discard these
                 * buffers, we would have no way to find them after the inode
                 * is reaped and thus user could see stale data if he tries to
                 * read them before the transaction is checkpointed. So be
                 * careful and force everything to disk here... We use
                 * ei->i_datasync_tid to store the newest transaction
                 * containing inode's data.
                 *
                 * Note that directories do not have this problem because they
                 * don't use page cache.
                 */
		if (inode->i_ino != EXT4_JOURNAL_INO &&
		    ext4_should_journal_data(inode) &&
		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
			journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
			tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;

			jbd2_complete_transaction(journal, commit_tid);
			filemap_write_and_wait(&inode->i_data);
		}
		truncate_inode_pages_final(&inode->i_data);

		goto no_delete;
	}

	if (is_bad_inode(inode))
		goto no_delete;
	dquot_initialize(inode);

	if (ext4_should_order_data(inode))
		ext4_begin_ordered_truncate(inode, 0);
	truncate_inode_pages_final(&inode->i_data);

	/*
         * Protect us against freezing - iput() caller didn't have to have any
         * protection against it
         */
	sb_start_intwrite(inode->i_sb);
	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE,
				    ext4_blocks_for_truncate(inode)+3);
	if (IS_ERR(handle)) {
		ext4_std_error(inode->i_sb, PTR_ERR(handle));
		/*
                 * If we're going to skip the normal cleanup, we still need to
                 * make sure that the in-core orphan linked list is properly
                 * cleaned up.
                 */
		ext4_orphan_del(NULL, inode);
		sb_end_intwrite(inode->i_sb);
		goto no_delete;
	}

	if (IS_SYNC(inode))
		ext4_handle_sync(handle);
	inode->i_size = 0;
	err = ext4_mark_inode_dirty(handle, inode);
	if (err) {
		ext4_warning(inode->i_sb,
			     "couldn't mark inode dirty (err %d)", err);
		goto stop_handle;
	}
	if (inode->i_blocks) {
		err = ext4_truncate(inode);
		if (err) {
			ext4_error(inode->i_sb,
				   "couldn't truncate inode %lu (err %d)",
				   inode->i_ino, err);
			goto stop_handle;
		}
	}

	/*
         * ext4_ext_truncate() doesn't reserve any slop when it
         * restarts journal transactions; therefore there may not be
         * enough credits left in the handle to remove the inode from
         * the orphan list and set the dtime field.
         */
	if (!ext4_handle_has_enough_credits(handle, 3)) {
		err = ext4_journal_extend(handle, 3);
		if (err > 0)
			err = ext4_journal_restart(handle, 3);
		if (err != 0) {
			ext4_warning(inode->i_sb,
				     "couldn't extend journal (err %d)", err);
		stop_handle:
			ext4_journal_stop(handle);
			ext4_orphan_del(NULL, inode);
			sb_end_intwrite(inode->i_sb);
			goto no_delete;
		}
	}

	/*
         * Kill off the orphan record which ext4_truncate created.
         * AKPM: I think this can be inside the above `if'.
         * Note that ext4_orphan_del() has to be able to cope with the
         * deletion of a non-existent orphan - this is because we don't
         * know if ext4_truncate() actually created an orphan record.
         * (Well, we could do this if we need to, but heck - it works)
         */
	ext4_orphan_del(handle, inode);
	EXT4_I(inode)->i_dtime	= get_seconds();

	/*
         * One subtle ordering requirement: if anything has gone wrong
         * (transaction abort, IO errors, whatever), then we can still
         * do these next steps (the fs will already have been marked as
         * having errors), but we can't free the inode if the mark_dirty
         * fails.
         */
	if (ext4_mark_inode_dirty(handle, inode))
		/* If that failed, just do the required in-core inode clear. */
		ext4_clear_inode(inode);
	else
		ext4_free_inode(handle, inode);
	ext4_journal_stop(handle);
	sb_end_intwrite(inode->i_sb);
	return;
no_delete:
	ext4_clear_inode(inode);	/* We must guarantee clearing of inode... */
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
theodore tso
theodore tso
159
36.14%
8
42.11%
dave kleikamp
dave kleikamp
118
26.82%
1
5.26%
jan kara
jan kara
106
24.09%
3
15.79%
al viro
al viro
21
4.77%
1
5.26%
christoph hellwig
christoph hellwig
12
2.73%
2
10.53%
mingming cao
mingming cao
8
1.82%
1
5.26%
frank mayhar
frank mayhar
8
1.82%
1
5.26%
vegard nossum
vegard nossum
6
1.36%
1
5.26%
johannes weiner
johannes weiner
2
0.45%
1
5.26%
Total
440
100.00%
19
100.00%

#ifdef CONFIG_QUOTA


qsize_t *ext4_get_reserved_space(struct inode *inode)
{
	return &EXT4_I(inode)->i_reserved_quota;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
amir goldstein
amir goldstein
16
80.00%
1
50.00%
dave kleikamp
dave kleikamp
4
20.00%
1
50.00%
Total
20
100.00%
2
100.00%

#endif

/*
 * Called with i_data_sem down, which is important since we can call
 * ext4_discard_preallocations() from here.
 */


void ext4_da_update_reserve_space(struct inode *inode,
					int used, int quota_claim)
{
	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
	struct ext4_inode_info *ei = EXT4_I(inode);

	spin_lock(&ei->i_block_reservation_lock);
	trace_ext4_da_update_reserve_space(inode, used, quota_claim);
	if (unlikely(used > ei->i_reserved_data_blocks)) {
		ext4_warning(inode->i_sb, "%s: ino %lu, used %d "
			 "with only %d reserved data blocks",
			 __func__, inode->i_ino, used,
			 ei->i_reserved_data_blocks);
		WARN_ON(1);
		used = ei->i_reserved_data_blocks;
	}

	/* Update per-inode reservations */
	ei->i_reserved_data_blocks -= used;
	percpu_counter_sub(&sbi->s_dirtyclusters_counter, used);

	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);

	/* Update quota subsystem for data blocks */
	if (quota_claim)
		dquot_claim_block(inode, EXT4_C2B(sbi, used));
	else {
		/*
                 * We did fallocate with an offset that is already delayed
                 * allocated. So on delayed allocated writeback we should
                 * not re-claim the quota for fallocated blocks.
                 */
		dquot_release_reservation_block(inode, EXT4_C2B(sbi, used));
	}

	/*
         * If we have done all the pending block allocations and if
         * there aren't any writers on the inode, we can discard the
         * inode's preallocations.
         */
	if ((ei->i_reserved_data_blocks == 0) &&
	    (atomic_read(&inode->i_writecount) == 0))
		ext4_discard_preallocations(inode);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
amir goldstein
amir goldstein
114
60.00%
1
12.50%
dave kleikamp
dave kleikamp
60
31.58%
1
12.50%
aditya kali
aditya kali
12
6.32%
2
25.00%
theodore tso
theodore tso
3
1.58%
3
37.50%
eric sandeen
eric sandeen
1
0.53%
1
12.50%
Total
190
100.00%
8
100.00%



static int __check_block_validity(struct inode *inode, const char *func,
				unsigned int line,
				struct ext4_map_blocks *map)
{
	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
				   map->m_len)) {
		ext4_error_inode(inode, func, line, map->m_pblk,
				 "lblock %lu mapped to illegal pblock "
				 "(length %d)", (unsigned long) map->m_lblk,
				 map->m_len);
		return -EFSCORRUPTED;
	}
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
thiemo nagel
thiemo nagel
33
39.76%
2
22.22%
amir goldstein
amir goldstein
26
31.33%
1
11.11%
theodore tso
theodore tso
16
19.28%
4
44.44%
dave kleikamp
dave kleikamp
7
8.43%
1
11.11%
darrick j. wong
darrick j. wong
1
1.20%
1
11.11%
Total
83
100.00%
9
100.00%



int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk,
		       ext4_lblk_t len)
{
	int ret;

	if (ext4_encrypted_inode(inode))
		return fscrypt_zeroout_range(inode, lblk, pblk, len);

	ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS);
	if (ret > 0)
		ret = 0;

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
jan kara
jan kara
68
98.55%
1
50.00%
jaegeuk kim
jaegeuk kim
1
1.45%
1
50.00%
Total
69
100.00%
2
100.00%


#define check_block_validity(inode, map)	\
	__check_block_validity((inode), __func__, __LINE__, (map))

#ifdef ES_AGGRESSIVE_TEST


static void ext4_map_blocks_es_recheck(handle_t *handle,
				       struct inode *inode,
				       struct ext4_map_blocks *es_map,
				       struct ext4_map_blocks *map,
				       int flags)
{
	int retval;

	map->m_flags = 0;
	/*
         * There is a race window that the result is not the same.
         * e.g. xfstests #223 when dioread_nolock enables.  The reason
         * is that we lookup a block mapping in extent status tree with
         * out taking i_data_sem.  So at the time the unwritten extent
         * could be converted.
         */
	down_read(&EXT4_I(inode)->i_data_sem);
	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
		retval = ext4_ext_map_blocks(handle, inode, map, flags &
					     EXT4_GET_BLOCKS_KEEP_SIZE);
	} else {
		retval = ext4_ind_map_blocks(handle, inode, map, flags &
					     EXT4_GET_BLOCKS_KEEP_SIZE);
	}
	up_read((&EXT4_I(inode)->i_data_sem));

	/*
         * We don't check m_len because extent will be collpased in status
         * tree.  So the m_len might not equal.
         */
	if (es_map->m_lblk != map->m_lblk ||
	    es_map->m_flags != map->m_flags ||
	    es_map->m_pblk != map->m_pblk) {
		printk("ES cache assertion failed for inode: %lu "
		       "es_cached ex [%d/%d/%llu/%x] != "
		       "found ex [%d/%d/%llu/%x] retval %d flags %x\n",
		       inode->i_ino, es_map->m_lblk, es_map->m_len,
		       es_map->m_pblk, es_map->m_flags, map->m_lblk,
		       map->m_len, map->m_pblk, map->m_flags,
		       retval, flags);
	}
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
dmitriy monakhov
dmitriy monakhov
181
99.45%
1
50.00%
theodore tso
theodore tso
1
0.55%
1
50.00%
Total
182
100.00%
2
100.00%

#endif /* ES_AGGRESSIVE_TEST */

/*
 * The ext4_map_blocks() function tries to look up the requested blocks,
 * and returns if the blocks are already mapped.
 *
 * Otherwise it takes the write lock of the i_data_sem and allocate blocks
 * and store the allocated blocks in the result buffer head and mark it
 * mapped.
 *
 * If file type is extents based, it will call ext4_ext_map_blocks(),
 * Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
 * based files
 *
 * On success, it returns the number of blocks being mapped or allocated.  if
 * create==0 and the blocks are pre-allocated and unwritten, the resulting @map
 * is marked as unwritten. If the create == 1, it will mark @map as mapped.
 *
 * It returns 0 if plain look up failed (blocks have not been allocated), in
 * that case, @map is returned as unmapped but we still do fill map->m_len to
 * indicate the length of a hole starting at map->m_lblk.
 *
 * It returns the error in case of allocation failure.
 */


int ext4_map_blocks(handle_t *handle, struct inode *inode,
		    struct ext4_map_blocks *map, int flags)
{
	struct extent_status es;
	int retval;
	int ret = 0;
#ifdef ES_AGGRESSIVE_TEST
	struct ext4_map_blocks orig_map;

	memcpy(&orig_map, map, sizeof(*map));
#endif

	map->m_flags = 0;
	ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u,"
		  "logical block %lu\n", inode->i_ino, flags, map->m_len,
		  (unsigned long) map->m_lblk);

	/*
         * ext4_map_blocks returns an int, and m_len is an unsigned int
         */
	if (unlikely(map->m_len > INT_MAX))
		map->m_len = INT_MAX;

	/* We can handle the block number less than EXT_MAX_BLOCKS */
	if (unlikely(map->m_lblk >= EXT_MAX_BLOCKS))
		return -EFSCORRUPTED;

	/* Lookup extent status tree firstly */
	if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
		if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
			map->m_pblk = ext4_es_pblock(&es) +
					map->m_lblk - es.es_lblk;
			map->m_flags |= ext4_es_is_written(&es) ?
					EXT4_MAP_MAPPED : EXT4_MAP_UNWRITTEN;
			retval = es.es_len - (map->m_lblk - es.es_lblk);
			if (retval > map->m_len)
				retval = map->m_len;
			map->m_len = retval;
		} else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) {
			map->m_pblk = 0;
			retval = es.es_len - (map->m_lblk - es.es_lblk);
			if (retval > map->m_len)
				retval = map->m_len;
			map->m_len = retval;
			retval = 0;
		} else {
			BUG_ON(1);
		}
#ifdef ES_AGGRESSIVE_TEST
		ext4_map_blocks_es_recheck(handle, inode, map,
					   &orig_map, flags);
#endif
		goto found;
	}

	/*
         * Try to see if we can get the block without requesting a new
         * file system block.
         */
	down_read(&EXT4_I(inode)->i_data_sem);
	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
		retval = ext4_ext_map_blocks(handle, inode, map, flags &
					     EXT4_GET_BLOCKS_KEEP_SIZE);
	} else {
		retval = ext4_ind_map_blocks(handle, inode, map, flags &
					     EXT4_GET_BLOCKS_KEEP_SIZE);
	}
	if (retval > 0) {
		unsigned int status;

		if (unlikely(retval != map->m_len)) {
			ext4_warning(inode->i_sb,
				     "ES len assertion failed for inode "
				     "%lu: retval %d != map->m_len %d",
				     inode->i_ino, retval, map->m_len);
			WARN_ON(1);
		}

		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
		if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
		    !(status & EXTENT_STATUS_WRITTEN) &&
		    ext4_find_delalloc_range(inode, map->m_lblk,
					     map->m_lblk + map->m_len - 1))
			status |= EXTENT_STATUS_DELAYED;
		ret = ext4_es_insert_extent(inode, map->m_lblk,
					    map->m_len, map->m_pblk, status);
		if (ret < 0)
			retval = ret;
	}
	up_read((&EXT4_I(inode)->i_data_sem));

found:
	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
		ret = check_block_validity(inode, map);
		if (ret != 0)
			return ret;
	}

	/* If it is only a block(s) look up */
	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0)
		return retval;

	/*
         * Returns if the blocks have already allocated
         *
         * Note that if blocks have been preallocated
         * ext4_ext_get_block() returns the create = 0
         * with buffer head unmapped.
         */
	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
		/*
                 * If we need to convert extent to unwritten
                 * we continue and do the actual work in
                 * ext4_ext_map_blocks()
                 */
		if (!(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN))
			return retval;

	/*
         * Here we clear m_flags because after allocating an new extent,
         * it will be set again.
         */
	map->m_flags &= ~EXT4_MAP_FLAGS;

	/*
         * New blocks allocate and/or writing to unwritten extent
         * will possibly result in updating i_data, so we take
         * the write lock of i_data_sem, and call get_block()
         * with create == 1 flag.
         */
	down_write(&EXT4_I(inode)->i_data_sem);

	/*
         * We need to check for EXT4 here because migrate
         * could have changed the inode type in between
         */
	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
		retval = ext4_ext_map_blocks(handle, inode, map, flags);
	} else {
		retval = ext4_ind_map_blocks(handle, inode, map, flags);

		if (retval > 0 && map->m_flags & EXT4_MAP_NEW) {
			/*
                         * We allocated new blocks which will result in
                         * i_data's format changing.  Force the migrate
                         * to fail by clearing migrate flags
                         */
			ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
		}

		/*
                 * Update reserved blocks/metadata blocks after successful
                 * block allocation which had been deferred till now. We don't
                 * support fallocate for non extent files. So we can update
                 * reserve space here.
                 */
		if ((retval > 0) &&
			(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
			ext4_da_update_reserve_space(inode, retval, 1);
	}

	if (retval > 0) {
		unsigned int status;

		if (unlikely(retval != map->m_len)) {
			ext4_warning(inode->i_sb,
				     "ES len assertion failed for inode "
				     "%lu: retval %d != map->m_len %d",
				     inode->i_ino, retval, map->m_len);
			WARN_ON(1);
		}

		/*
                 * We have to zeroout blocks before inserting them into extent
                 * status tree. Otherwise someone could look them up there and
                 * use them before they are really zeroed. We also have to
                 * unmap metadata before zeroing as otherwise writeback can
                 * overwrite zeros with stale data from block device.
                 */
		if (flags & EXT4_GET_BLOCKS_ZERO &&
		    map->m_flags & EXT4_MAP_MAPPED &&
		    map->m_flags & EXT4_MAP_NEW) {
			clean_bdev_aliases(inode->i_sb->s_bdev, map->m_pblk,
					   map->m_len);
			ret = ext4_issue_zeroout(inode, map->m_lblk,
						 map->m_pblk, map->m_len);
			if (ret) {
				retval = ret;
				goto out_sem;
			}
		}

		/*
                 * If the extent has been zeroed out, we don't need to update
                 * extent status tree.
                 */
		if ((flags & EXT4_GET_BLOCKS_PRE_IO) &&
		    ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
			if (ext4_es_is_written(&es))
				goto out_sem;
		}
		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
		if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
		    !(status & EXTENT_STATUS_WRITTEN) &&
		    ext4_find_delalloc_range(inode, map->m_lblk,
					     map->m_lblk + map->m_len - 1))
			status |= EXTENT_STATUS_DELAYED;
		ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
					    map->m_pblk, status);
		if (ret < 0) {
			retval = ret;
			goto out_sem;
		}
	}

out_sem:
	up_write((&EXT4_I(inode)->i_data_sem));
	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
		ret = check_block_validity(inode, map);
		if (ret != 0)
			return ret;

		/*
                 * Inodes with freshly allocated blocks where contents will be
                 * visible after transaction commit must be on transaction's
                 * ordered data list.
                 */
		if (map->m_flags & EXT4_MAP_NEW &&
		    !(map->m_flags & EXT4_MAP_UNWRITTEN) &&
		    !(flags & EXT4_GET_BLOCKS_ZERO) &&
		    !IS_NOQUOTA(inode) &&
		    ext4_should_order_data(inode)) {
			if (flags & EXT4_GET_BLOCKS_IO_SUBMIT)
				ret = ext4_jbd2_inode_add_wait(handle, inode);
			else
				ret = ext4_jbd2_inode_add_write(handle, inode);
			if (ret)
				return ret;
		}
	}
	return retval;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
zheng liu
zheng liu
362
34.22%
7
21.21%
jan kara
jan kara
189
17.86%
6
18.18%
amir goldstein
amir goldstein
175
16.54%
1
3.03%
dmitriy monakhov
dmitriy monakhov
94
8.88%
2
6.06%
dave kleikamp
dave kleikamp
83
7.84%
1
3.03%
theodore tso
theodore tso
47
4.44%
4
12.12%
lukas czerner
lukas czerner
33
3.12%
2
6.06%
aneesh kumar
aneesh kumar
28
2.65%
1
3.03%
kazuya mio
kazuya mio
15
1.42%
1
3.03%
valerie clement
valerie clement
13
1.23%
1
3.03%
frank mayhar
frank mayhar
7
0.66%
1
3.03%
aditya kali
aditya kali
4
0.38%
1
3.03%
eric sandeen
eric sandeen
4
0.38%
1
3.03%
darrick j. wong
darrick j. wong
1
0.09%
1
3.03%
seunghun lee
seunghun lee
1
0.09%
1
3.03%
tao ma
tao ma
1
0.09%
1
3.03%
allison henderson
allison henderson
1
0.09%
1
3.03%
Total
1058
100.00%
33
100.00%

/*
 * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages
 * we have to be careful as someone else may be manipulating b_state as well.
 */


static