apfs/linux-apfs
0
0
Fork 0
mirror of https://github.com/linux-apfs/linux-apfs.git synced 2026-05-01 15:00:59 -07:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Browse Source 
* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (97 commits)
  jbd2: Unify log messages in jbd2 code
  jbd/jbd2: validate sb->s_first in journal_get_superblock()
  ext4: let ext4_ext_rm_leaf work with EXT_DEBUG defined
  ext4: fix a syntax error in ext4_ext_insert_extent when debugging enabled
  ext4: fix a typo in struct ext4_allocation_context
  ext4: Don't normalize an falloc request if it can fit in 1 extent.
  ext4: remove comments about extent mount option in ext4_new_inode()
  ext4: let ext4_discard_partial_buffers handle unaligned range correctly
  ext4: return ENOMEM if find_or_create_pages fails
  ext4: move vars to local scope in ext4_discard_partial_page_buffers_no_lock()
  ext4: Create helper function for EXT4_IO_END_UNWRITTEN and i_aiodio_unwritten
  ext4: optimize locking for end_io extent conversion
  ext4: remove unnecessary call to waitqueue_active()
  ext4: Use correct locking for ext4_end_io_nolock()
  ext4: fix race in xattr block allocation path
  ext4: trace punch_hole correctly in ext4_ext_map_blocks
  ext4: clean up AGGRESSIVE_TEST code
  ext4: move variables to their scope
  ext4: fix quota accounting during migration
  ext4: migrate cleanup
  ...
This commit is contained in:
Linus Torvalds
2011-11-02 10:06:20 -07:00
parent 34116645d9 f2a44523b2
commit f1f8935a5c
34 changed files with 2916 additions and 1347 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Documentation/filesystems/ext4.txt
+16 -25
View File
@@ -160,7 +160,9 @@ noload if the filesystem was not unmounted cleanly,
lead to any number of problems.
data=journal All data are committed into the journal prior to being
written into the main file system.
written into the main file system. Enabling
this mode will disable delayed allocation and
O_DIRECT support.
data=ordered (*) All data are forced directly out to the main file
system prior to its metadata being committed to the
@@ -201,30 +203,19 @@ inode_readahead_blks=n This tuning parameter controls the maximum
table readahead algorithm will pre-read into
the buffer cache. The default value is 32 blocks.
orlov (*) This enables the new Orlov block allocator. It is
enabled by default.
oldalloc This disables the Orlov block allocator and enables
the old block allocator. Orlov should have better
performance - we'd like to get some feedback if it's
the contrary for you.
user_xattr Enables Extended User Attributes. Additionally, you
need to have extended attribute support enabled in the
kernel configuration (CONFIG_EXT4_FS_XATTR). See the
attr(5) manual page and http://acl.bestbits.at/ to
learn more about extended attributes.
nouser_xattr Disables Extended User Attributes.
acl Enables POSIX Access Control Lists support.
Additionally, you need to have ACL support enabled in
the kernel configuration (CONFIG_EXT4_FS_POSIX_ACL).
See the acl(5) manual page and http://acl.bestbits.at/
for more information.
nouser_xattr Disables Extended User Attributes. If you have extended
attribute support enabled in the kernel configuration
(CONFIG_EXT4_FS_XATTR), extended attribute support
is enabled by default on mount. See the attr(5) manual
page and http://acl.bestbits.at/ for more information
about extended attributes.
noacl This option disables POSIX Access Control List
support.
support. If ACL support is enabled in the kernel
configuration (CONFIG_EXT4_FS_POSIX_ACL), ACL is
enabled by default on mount. See the acl(5) manual
page and http://acl.bestbits.at/ for more information
about acl.
bsddf (*) Make 'df' act like BSD.
minixdf Make 'df' act like Minix.
@@ -419,8 +410,8 @@ written to the journal first, and then to its final location.
In the event of a crash, the journal can be replayed, bringing both data and
metadata into a consistent state. This mode is the slowest except when data
needs to be read from and written to disk at the same time where it
outperforms all others modes. Currently ext4 does not have delayed
allocation support if this data journalling mode is selected.
outperforms all others modes. Enabling this mode will disable delayed
allocation and O_DIRECT support.
/proc entries
=============
fs/ext4/balloc.c
+226 -157
View File
@@ -28,7 +28,8 @@
*/
/*
* Calculate the block group number and offset, given a block number
* Calculate the block group number and offset into the block/cluster
* allocation bitmap, given a block number
*/
void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp)
@@ -37,7 +38,8 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
ext4_grpblk_t offset;
blocknr = blocknr - le32_to_cpu(es->s_first_data_block);
offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb));
offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb)) >>
EXT4_SB(sb)->s_cluster_bits;
if (offsetp)
*offsetp = offset;
if (blockgrpp)
@@ -55,131 +57,170 @@ static int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block,
return 0;
}
static int ext4_group_used_meta_blocks(struct super_block *sb,
/* Return the number of clusters used for file system metadata; this
* represents the overhead needed by the file system.
*/
unsigned ext4_num_overhead_clusters(struct super_block *sb,
ext4_group_t block_group,
struct ext4_group_desc *gdp)
{
unsigned num_clusters;
int block_cluster = -1, inode_cluster = -1, itbl_cluster = -1, i, c;
ext4_fsblk_t start = ext4_group_first_block_no(sb, block_group);
ext4_fsblk_t itbl_blk;
struct ext4_sb_info *sbi = EXT4_SB(sb);
/* This is the number of clusters used by the superblock,
* block group descriptors, and reserved block group
* descriptor blocks */
num_clusters = ext4_num_base_meta_clusters(sb, block_group);
/*
* For the allocation bitmaps and inode table, we first need
* to check to see if the block is in the block group. If it
* is, then check to see if the cluster is already accounted
* for in the clusters used for the base metadata cluster, or
* if we can increment the base metadata cluster to include
* that block. Otherwise, we will have to track the cluster
* used for the allocation bitmap or inode table explicitly.
* Normally all of these blocks are contiguous, so the special
* case handling shouldn't be necessary except for *very*
* unusual file system layouts.
*/
if (ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), block_group)) {
block_cluster = EXT4_B2C(sbi, (start -
ext4_block_bitmap(sb, gdp)));
if (block_cluster < num_clusters)
block_cluster = -1;
else if (block_cluster == num_clusters) {
num_clusters++;
block_cluster = -1;
}
}
if (ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), block_group)) {
inode_cluster = EXT4_B2C(sbi,
start - ext4_inode_bitmap(sb, gdp));
if (inode_cluster < num_clusters)
inode_cluster = -1;
else if (inode_cluster == num_clusters) {
num_clusters++;
inode_cluster = -1;
}
}
itbl_blk = ext4_inode_table(sb, gdp);
for (i = 0; i < sbi->s_itb_per_group; i++) {
if (ext4_block_in_group(sb, itbl_blk + i, block_group)) {
c = EXT4_B2C(sbi, start - itbl_blk + i);
if ((c < num_clusters) || (c == inode_cluster) ||
(c == block_cluster) || (c == itbl_cluster))
continue;
if (c == num_clusters) {
num_clusters++;
continue;
}
num_clusters++;
itbl_cluster = c;
}
}
if (block_cluster != -1)
num_clusters++;
if (inode_cluster != -1)
num_clusters++;
return num_clusters;
}
static unsigned int num_clusters_in_group(struct super_block *sb,
ext4_group_t block_group)
{
unsigned int blocks;
if (block_group == ext4_get_groups_count(sb) - 1) {
/*
* Even though mke2fs always initializes the first and
* last group, just in case some other tool was used,
* we need to make sure we calculate the right free
* blocks.
*/
blocks = ext4_blocks_count(EXT4_SB(sb)->s_es) -
ext4_group_first_block_no(sb, block_group);
} else
blocks = EXT4_BLOCKS_PER_GROUP(sb);
return EXT4_NUM_B2C(EXT4_SB(sb), blocks);
}
/* Initializes an uninitialized block bitmap */
void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
ext4_group_t block_group,
struct ext4_group_desc *gdp)
{
unsigned int bit, bit_max;
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t start, tmp;
int flex_bg = 0;
J_ASSERT_BH(bh, buffer_locked(bh));
/* If checksum is bad mark all blocks used to prevent allocation
* essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
ext4_error(sb, "Checksum bad for group %u", block_group);
ext4_free_group_clusters_set(sb, gdp, 0);
ext4_free_inodes_set(sb, gdp, 0);
ext4_itable_unused_set(sb, gdp, 0);
memset(bh->b_data, 0xff, sb->s_blocksize);
return;
}
memset(bh->b_data, 0, sb->s_blocksize);
bit_max = ext4_num_base_meta_clusters(sb, block_group);
for (bit = 0; bit < bit_max; bit++)
ext4_set_bit(bit, bh->b_data);
start = ext4_group_first_block_no(sb, block_group);
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
flex_bg = 1;
/* Set bits for block and inode bitmaps, and inode table */
tmp = ext4_block_bitmap(sb, gdp);
if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
tmp = ext4_inode_bitmap(sb, gdp);
if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
tmp = ext4_inode_table(sb, gdp);
for (; tmp < ext4_inode_table(sb, gdp) +
sbi->s_itb_per_group; tmp++) {
if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
}
/*
* Also if the number of blocks within the group is less than
* the blocksize * 8 ( which is the size of bitmap ), set rest
* of the block bitmap to 1
*/
ext4_mark_bitmap_end(num_clusters_in_group(sb, block_group),
sb->s_blocksize * 8, bh->b_data);
}
/* Return the number of free blocks in a block group. It is used when
* the block bitmap is uninitialized, so we can't just count the bits
* in the bitmap. */
unsigned ext4_free_clusters_after_init(struct super_block *sb,
ext4_group_t block_group,
struct ext4_group_desc *gdp)
{
ext4_fsblk_t tmp;
struct ext4_sb_info *sbi = EXT4_SB(sb);
/* block bitmap, inode bitmap, and inode table blocks */
int used_blocks = sbi->s_itb_per_group + 2;
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
if (!ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp),
block_group))
used_blocks--;
if (!ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp),
block_group))
used_blocks--;
tmp = ext4_inode_table(sb, gdp);
for (; tmp < ext4_inode_table(sb, gdp) +
sbi->s_itb_per_group; tmp++) {
if (!ext4_block_in_group(sb, tmp, block_group))
used_blocks -= 1;
}
}
return used_blocks;
return num_clusters_in_group(sb, block_group) -
ext4_num_overhead_clusters(sb, block_group, gdp);
}
/* Initializes an uninitialized block bitmap if given, and returns the
* number of blocks free in the group. */
unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
ext4_group_t block_group, struct ext4_group_desc *gdp)
{
int bit, bit_max;
ext4_group_t ngroups = ext4_get_groups_count(sb);
unsigned free_blocks, group_blocks;
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (bh) {
J_ASSERT_BH(bh, buffer_locked(bh));
/* If checksum is bad mark all blocks used to prevent allocation
* essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
ext4_error(sb, "Checksum bad for group %u",
block_group);
ext4_free_blks_set(sb, gdp, 0);
ext4_free_inodes_set(sb, gdp, 0);
ext4_itable_unused_set(sb, gdp, 0);
memset(bh->b_data, 0xff, sb->s_blocksize);
return 0;
}
memset(bh->b_data, 0, sb->s_blocksize);
}
/* Check for superblock and gdt backups in this group */
bit_max = ext4_bg_has_super(sb, block_group);
if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) *
sbi->s_desc_per_block) {
if (bit_max) {
bit_max += ext4_bg_num_gdb(sb, block_group);
bit_max +=
le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
}
} else { /* For META_BG_BLOCK_GROUPS */
bit_max += ext4_bg_num_gdb(sb, block_group);
}
if (block_group == ngroups - 1) {
/*
* Even though mke2fs always initialize first and last group
* if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need
* to make sure we calculate the right free blocks
*/
group_blocks = ext4_blocks_count(sbi->s_es) -
ext4_group_first_block_no(sb, ngroups - 1);
} else {
group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
}
free_blocks = group_blocks - bit_max;
if (bh) {
ext4_fsblk_t start, tmp;
int flex_bg = 0;
for (bit = 0; bit < bit_max; bit++)
ext4_set_bit(bit, bh->b_data);
start = ext4_group_first_block_no(sb, block_group);
if (EXT4_HAS_INCOMPAT_FEATURE(sb,
EXT4_FEATURE_INCOMPAT_FLEX_BG))
flex_bg = 1;
/* Set bits for block and inode bitmaps, and inode table */
tmp = ext4_block_bitmap(sb, gdp);
if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
ext4_set_bit(tmp - start, bh->b_data);
tmp = ext4_inode_bitmap(sb, gdp);
if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
ext4_set_bit(tmp - start, bh->b_data);
tmp = ext4_inode_table(sb, gdp);
for (; tmp < ext4_inode_table(sb, gdp) +
sbi->s_itb_per_group; tmp++) {
if (!flex_bg ||
ext4_block_in_group(sb, tmp, block_group))
ext4_set_bit(tmp - start, bh->b_data);
}
/*
* Also if the number of blocks within the group is
* less than the blocksize * 8 ( which is the size
* of bitmap ), set rest of the block bitmap to 1
*/
ext4_mark_bitmap_end(group_blocks, sb->s_blocksize * 8,
bh->b_data);
}
return free_blocks - ext4_group_used_meta_blocks(sb, block_group, gdp);
}
/*
* The free blocks are managed by bitmaps. A file system contains several
* blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap
@@ -362,53 +403,54 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
}
/**
* ext4_has_free_blocks()
* ext4_has_free_clusters()
* @sbi: in-core super block structure.
* @nblocks: number of needed blocks
* @nclusters: number of needed blocks
* @flags: flags from ext4_mb_new_blocks()
*
* Check if filesystem has nblocks free & available for allocation.
* Check if filesystem has nclusters free & available for allocation.
* On success return 1, return 0 on failure.
*/
static int ext4_has_free_blocks(struct ext4_sb_info *sbi,
s64 nblocks, unsigned int flags)
static int ext4_has_free_clusters(struct ext4_sb_info *sbi,
s64 nclusters, unsigned int flags)
{
s64 free_blocks, dirty_blocks, root_blocks;
struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
s64 free_clusters, dirty_clusters, root_clusters;
struct percpu_counter *fcc = &sbi->s_freeclusters_counter;
struct percpu_counter *dcc = &sbi->s_dirtyclusters_counter;
free_blocks = percpu_counter_read_positive(fbc);
dirty_blocks = percpu_counter_read_positive(dbc);
root_blocks = ext4_r_blocks_count(sbi->s_es);
free_clusters = percpu_counter_read_positive(fcc);
dirty_clusters = percpu_counter_read_positive(dcc);
root_clusters = EXT4_B2C(sbi, ext4_r_blocks_count(sbi->s_es));
if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
EXT4_FREEBLOCKS_WATERMARK) {
free_blocks = percpu_counter_sum_positive(fbc);
dirty_blocks = percpu_counter_sum_positive(dbc);
if (free_clusters - (nclusters + root_clusters + dirty_clusters) <
EXT4_FREECLUSTERS_WATERMARK) {
free_clusters = EXT4_C2B(sbi, percpu_counter_sum_positive(fcc));
dirty_clusters = percpu_counter_sum_positive(dcc);
}
/* Check whether we have space after
* accounting for current dirty blocks & root reserved blocks.
/* Check whether we have space after accounting for current
* dirty clusters & root reserved clusters.
*/
if (free_blocks >= ((root_blocks + nblocks) + dirty_blocks))
if (free_clusters >= ((root_clusters + nclusters) + dirty_clusters))
return 1;
/* Hm, nope. Are (enough) root reserved blocks available? */
/* Hm, nope. Are (enough) root reserved clusters available? */
if (sbi->s_resuid == current_fsuid() ||
((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) ||
capable(CAP_SYS_RESOURCE) ||
(flags & EXT4_MB_USE_ROOT_BLOCKS)) {
if (free_blocks >= (nblocks + dirty_blocks))
if (free_clusters >= (nclusters + dirty_clusters))
return 1;
}
return 0;
}
int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
s64 nblocks, unsigned int flags)
int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
s64 nclusters, unsigned int flags)
{
if (ext4_has_free_blocks(sbi, nblocks, flags)) {
percpu_counter_add(&sbi->s_dirtyblocks_counter, nblocks);
if (ext4_has_free_clusters(sbi, nclusters, flags)) {
percpu_counter_add(&sbi->s_dirtyclusters_counter, nclusters);
return 0;
} else
return -ENOSPC;
@@ -428,7 +470,7 @@ int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
*/
int ext4_should_retry_alloc(struct super_block *sb, int *retries)
{
if (!ext4_has_free_blocks(EXT4_SB(sb), 1, 0) ||
if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) ||
(*retries)++ > 3 ||
!EXT4_SB(sb)->s_journal)
return 0;
@@ -444,7 +486,7 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
* @handle: handle to this transaction
* @inode: file inode
* @goal: given target block(filesystem wide)
* @count: pointer to total number of blocks needed
* @count: pointer to total number of clusters needed
* @errp: error code
*
* Return 1st allocated block number on success, *count stores total account
@@ -476,18 +518,19 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
EXT4_I(inode)->i_allocated_meta_blocks += ar.len;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
dquot_alloc_block_nofail(inode, ar.len);
dquot_alloc_block_nofail(inode,
EXT4_C2B(EXT4_SB(inode->i_sb), ar.len));
}
return ret;
}
/**
* ext4_count_free_blocks() -- count filesystem free blocks
* ext4_count_free_clusters() -- count filesystem free clusters
* @sb: superblock
*
* Adds up the number of free blocks from each block group.
* Adds up the number of free clusters from each block group.
*/
ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
{
ext4_fsblk_t desc_count;
struct ext4_group_desc *gdp;
@@ -508,7 +551,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
desc_count += ext4_free_blks_count(sb, gdp);
desc_count += ext4_free_group_clusters(sb, gdp);
brelse(bitmap_bh);
bitmap_bh = ext4_read_block_bitmap(sb, i);
if (bitmap_bh == NULL)
@@ -516,12 +559,13 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
x = ext4_count_free(bitmap_bh, sb->s_blocksize);
printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n",
i, ext4_free_blks_count(sb, gdp), x);
i, ext4_free_group_clusters(sb, gdp), x);
bitmap_count += x;
}
brelse(bitmap_bh);
printk(KERN_DEBUG "ext4_count_free_blocks: stored = %llu"
", computed = %llu, %llu\n", ext4_free_blocks_count(es),
printk(KERN_DEBUG "ext4_count_free_clusters: stored = %llu"
", computed = %llu, %llu\n",
EXT4_B2C(sbi, ext4_free_blocks_count(es)),
desc_count, bitmap_count);
return bitmap_count;
#else
@@ -530,7 +574,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
desc_count += ext4_free_blks_count(sb, gdp);
desc_count += ext4_free_group_clusters(sb, gdp);
}
return desc_count;
@@ -620,6 +664,31 @@ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group)
}
/*
* This function returns the number of file system metadata clusters at
* the beginning of a block group, including the reserved gdt blocks.
*/
unsigned ext4_num_base_meta_clusters(struct super_block *sb,
ext4_group_t block_group)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
unsigned num;
/* Check for superblock and gdt backups in this group */
num = ext4_bg_has_super(sb, block_group);
if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) *
sbi->s_desc_per_block) {
if (num) {
num += ext4_bg_num_gdb(sb, block_group);
num += le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
}
} else { /* For META_BG_BLOCK_GROUPS */
num += ext4_bg_num_gdb(sb, block_group);
}
return EXT4_NUM_B2C(sbi, num);
}
/**
* ext4_inode_to_goal_block - return a hint for block allocation
* @inode: inode for block allocation
fs/ext4/ext4.h
+102 -39
View File
@@ -144,9 +144,17 @@ struct ext4_allocation_request {
#define EXT4_MAP_UNWRITTEN (1 << BH_Unwritten)
#define EXT4_MAP_BOUNDARY (1 << BH_Boundary)
#define EXT4_MAP_UNINIT (1 << BH_Uninit)
/* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of
* ext4_map_blocks wants to know whether or not the underlying cluster has
* already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that
* the requested mapping was from previously mapped (or delayed allocated)
* cluster. We use BH_AllocFromCluster only for this flag. BH_AllocFromCluster
* should never appear on buffer_head's state flags.
*/
#define EXT4_MAP_FROM_CLUSTER (1 << BH_AllocFromCluster)
#define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
EXT4_MAP_UNINIT)
EXT4_MAP_UNINIT | EXT4_MAP_FROM_CLUSTER)
struct ext4_map_blocks {
ext4_fsblk_t m_pblk;
@@ -239,8 +247,11 @@ struct ext4_io_submit {
# define EXT4_BLOCK_SIZE(s) (EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
#endif
#define EXT4_ADDR_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof(__u32))
#define EXT4_CLUSTER_SIZE(s) (EXT4_BLOCK_SIZE(s) << \
EXT4_SB(s)->s_cluster_bits)
#ifdef __KERNEL__
# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits)
# define EXT4_CLUSTER_BITS(s) (EXT4_SB(s)->s_cluster_bits)
#else
# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_log_block_size + 10)
#endif
@@ -258,6 +269,14 @@ struct ext4_io_submit {
#endif
#define EXT4_BLOCK_ALIGN(size, blkbits) ALIGN((size), (1 << (blkbits)))
/* Translate a block number to a cluster number */
#define EXT4_B2C(sbi, blk) ((blk) >> (sbi)->s_cluster_bits)
/* Translate a cluster number to a block number */
#define EXT4_C2B(sbi, cluster) ((cluster) << (sbi)->s_cluster_bits)
/* Translate # of blks to # of clusters */
#define EXT4_NUM_B2C(sbi, blks) (((blks) + (sbi)->s_cluster_ratio - 1) >> \
(sbi)->s_cluster_bits)
/*
* Structure of a blocks group descriptor
*/
@@ -289,7 +308,7 @@ struct ext4_group_desc
struct flex_groups {
atomic_t free_inodes;
atomic_t free_blocks;
atomic_t free_clusters;
atomic_t used_dirs;
};
@@ -306,6 +325,7 @@ struct flex_groups {
#define EXT4_DESC_SIZE(s) (EXT4_SB(s)->s_desc_size)
#ifdef __KERNEL__
# define EXT4_BLOCKS_PER_GROUP(s) (EXT4_SB(s)->s_blocks_per_group)
# define EXT4_CLUSTERS_PER_GROUP(s) (EXT4_SB(s)->s_clusters_per_group)
# define EXT4_DESC_PER_BLOCK(s) (EXT4_SB(s)->s_desc_per_block)
# define EXT4_INODES_PER_GROUP(s) (EXT4_SB(s)->s_inodes_per_group)
# define EXT4_DESC_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_desc_per_block_bits)
@@ -358,8 +378,7 @@ struct flex_groups {
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
EXT4_SYNC_FL | EXT4_IMMUTABLE_FL | EXT4_APPEND_FL |\
EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)
@@ -520,6 +539,8 @@ struct ext4_new_group_data {
#define EXT4_GET_BLOCKS_PUNCH_OUT_EXT 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
/*
* Flags used by ext4_free_blocks
@@ -528,6 +549,13 @@ struct ext4_new_group_data {
#define EXT4_FREE_BLOCKS_FORGET 0x0002
#define EXT4_FREE_BLOCKS_VALIDATED 0x0004
#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008
#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010
#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020
/*
* Flags used by ext4_discard_partial_page_buffers
*/
#define EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED 0x0001
/*
* ioctl commands
@@ -538,9 +566,6 @@ struct ext4_new_group_data {
#define EXT4_IOC_SETVERSION _IOW('f', 4, long)
#define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION
#define EXT4_IOC_SETVERSION_OLD FS_IOC_SETVERSION
#ifdef CONFIG_JBD2_DEBUG
#define EXT4_IOC_WAIT_FOR_READONLY _IOR('f', 99, long)
#endif
#define EXT4_IOC_GETRSVSZ _IOR('f', 5, long)
#define EXT4_IOC_SETRSVSZ _IOW('f', 6, long)
#define EXT4_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long)
@@ -563,9 +588,6 @@ struct ext4_new_group_data {
#define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int)
#define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int)
#define EXT4_IOC32_GROUP_ADD _IOW('f', 8, struct compat_ext4_new_group_input)
#ifdef CONFIG_JBD2_DEBUG
#define EXT4_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int)
#endif
#define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION
#endif
@@ -837,6 +859,7 @@ struct ext4_inode_info {
ext4_group_t i_last_alloc_group;
/* allocation reservation info for delalloc */
/* In case of bigalloc, these refer to clusters rather than blocks */
unsigned int i_reserved_data_blocks;
unsigned int i_reserved_meta_blocks;
unsigned int i_allocated_meta_blocks;
@@ -886,7 +909,6 @@ struct ext4_inode_info {
/*
* Mount flags
*/
#define EXT4_MOUNT_OLDALLOC 0x00002 /* Don't use the new Orlov allocator */
#define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */
#define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */
#define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */
@@ -918,6 +940,9 @@ struct ext4_inode_info {
#define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */
#define EXT4_MOUNT_INIT_INODE_TABLE 0x80000000 /* Initialize uninitialized itables */
#define EXT4_MOUNT2_EXPLICIT_DELALLOC 0x00000001 /* User explicitly
specified delalloc */
#define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \
~EXT4_MOUNT_##opt
#define set_opt(sb, opt) EXT4_SB(sb)->s_mount_opt |= \
@@ -968,9 +993,9 @@ struct ext4_super_block {
/*10*/ __le32 s_free_inodes_count; /* Free inodes count */
__le32 s_first_data_block; /* First Data Block */
__le32 s_log_block_size; /* Block size */
__le32 s_obso_log_frag_size; /* Obsoleted fragment size */
__le32 s_log_cluster_size; /* Allocation cluster size */
/*20*/ __le32 s_blocks_per_group; /* # Blocks per group */
__le32 s_obso_frags_per_group; /* Obsoleted fragments per group */
__le32 s_clusters_per_group; /* # Clusters per group */
__le32 s_inodes_per_group; /* # Inodes per group */
__le32 s_mtime; /* Mount time */
/*30*/ __le32 s_wtime; /* Write time */
@@ -1066,7 +1091,10 @@ struct ext4_super_block {
__u8 s_last_error_func[32]; /* function where the error happened */
#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
__u8 s_mount_opts[64];
__le32 s_reserved[112]; /* Padding to the end of the block */
__le32 s_usr_quota_inum; /* inode for tracking user quota */
__le32 s_grp_quota_inum; /* inode for tracking group quota */
__le32 s_overhead_clusters; /* overhead blocks/clusters in fs */
__le32 s_reserved[109]; /* Padding to the end of the block */
};
#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)
@@ -1086,6 +1114,7 @@ struct ext4_sb_info {
unsigned long s_desc_size; /* Size of a group descriptor in bytes */
unsigned long s_inodes_per_block;/* Number of inodes per block */
unsigned long s_blocks_per_group;/* Number of blocks in a group */
unsigned long s_clusters_per_group; /* Number of clusters in a group */
unsigned long s_inodes_per_group;/* Number of inodes in a group */
unsigned long s_itb_per_group; /* Number of inode table blocks per group */
unsigned long s_gdb_count; /* Number of group descriptor blocks */
@@ -1094,6 +1123,8 @@ struct ext4_sb_info {
ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
unsigned long s_overhead_last; /* Last calculated overhead */
unsigned long s_blocks_last; /* Last seen block count */
unsigned int s_cluster_ratio; /* Number of blocks per cluster */
unsigned int s_cluster_bits; /* log2 of s_cluster_ratio */
loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */
struct buffer_head * s_sbh; /* Buffer containing the super block */
struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */
@@ -1117,10 +1148,10 @@ struct ext4_sb_info {
u32 s_hash_seed[4];
int s_def_hash_version;
int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */
struct percpu_counter s_freeblocks_counter;
struct percpu_counter s_freeclusters_counter;
struct percpu_counter s_freeinodes_counter;
struct percpu_counter s_dirs_counter;
struct percpu_counter s_dirtyblocks_counter;
struct percpu_counter s_dirtyclusters_counter;
struct blockgroup_lock *s_blockgroup_lock;
struct proc_dir_entry *s_proc;
struct kobject s_kobj;
@@ -1136,10 +1167,6 @@ struct ext4_sb_info {
u32 s_max_batch_time;
u32 s_min_batch_time;
struct block_device *journal_bdev;
#ifdef CONFIG_JBD2_DEBUG
struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */
wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */
#endif
#ifdef CONFIG_QUOTA
char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */
int s_jquota_fmt; /* Format of quota to use */
@@ -1248,6 +1275,15 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
}
static inline void ext4_set_io_unwritten_flag(struct inode *inode,
struct ext4_io_end *io_end)
{
if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
io_end->flag |= EXT4_IO_END_UNWRITTEN;
atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
}
}
/*
* Inode dynamic state flags
*/
@@ -1360,6 +1396,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040
#define EXT4_FEATURE_RO_COMPAT_QUOTA 0x0100
#define EXT4_FEATURE_RO_COMPAT_BIGALLOC 0x0200
#define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001
#define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002
@@ -1402,7 +1439,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
EXT4_FEATURE_RO_COMPAT_HUGE_FILE)
EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\
EXT4_FEATURE_RO_COMPAT_BIGALLOC)
/*
* Default values for user and/or group using reserved blocks
@@ -1735,9 +1773,9 @@ extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
unsigned int flags,
unsigned long *count,
int *errp);
extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
s64 nblocks, unsigned int flags);
extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
s64 nclusters, unsigned int flags);
extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *);
extern void ext4_check_blocks_bitmap(struct super_block *);
extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
ext4_group_t block_group,
@@ -1745,12 +1783,18 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
ext4_group_t block_group);
extern unsigned ext4_init_block_bitmap(struct super_block *sb,
struct buffer_head *bh,
ext4_group_t group,
struct ext4_group_desc *desc);
#define ext4_free_blocks_after_init(sb, group, desc) \
ext4_init_block_bitmap(sb, NULL, group, desc)
extern void ext4_init_block_bitmap(struct super_block *sb,
struct buffer_head *bh,
ext4_group_t group,
struct ext4_group_desc *desc);
extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
ext4_group_t block_group,
struct ext4_group_desc *gdp);
extern unsigned ext4_num_base_meta_clusters(struct super_block *sb,
ext4_group_t block_group);
extern unsigned ext4_num_overhead_clusters(struct super_block *sb,
ext4_group_t block_group,
struct ext4_group_desc *gdp);
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
/* dir.c */
@@ -1776,7 +1820,8 @@ extern int ext4fs_dirhash(const char *name, int len, struct
/* ialloc.c */
extern struct inode *ext4_new_inode(handle_t *, struct inode *, int,
const struct qstr *qstr, __u32 goal);
const struct qstr *qstr, __u32 goal,
uid_t *owner);
extern void ext4_free_inode(handle_t *, struct inode *);
extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
extern unsigned long ext4_count_free_inodes(struct super_block *);
@@ -1839,6 +1884,12 @@ extern int ext4_block_truncate_page(handle_t *handle,
struct address_space *mapping, loff_t from);
extern int ext4_block_zero_page_range(handle_t *handle,
struct address_space *mapping, loff_t from, loff_t length);
extern int ext4_discard_partial_page_buffers(handle_t *handle,
struct address_space *mapping, loff_t from,
loff_t length, int flags);
extern int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
struct inode *inode, struct page *page, loff_t from,
loff_t length, int flags);
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
extern void ext4_da_update_reserve_space(struct inode *inode,
@@ -1927,8 +1978,8 @@ extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
struct ext4_group_desc *bg);
extern ext4_fsblk_t ext4_inode_table(struct super_block *sb,
struct ext4_group_desc *bg);
extern __u32 ext4_free_blks_count(struct super_block *sb,
struct ext4_group_desc *bg);
extern __u32 ext4_free_group_clusters(struct super_block *sb,
struct ext4_group_desc *bg);
extern __u32 ext4_free_inodes_count(struct super_block *sb,
struct ext4_group_desc *bg);
extern __u32 ext4_used_dirs_count(struct super_block *sb,
@@ -1941,8 +1992,9 @@ extern void ext4_inode_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk);
extern void ext4_inode_table_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk);
extern void ext4_free_blks_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count);
extern void ext4_free_group_clusters_set(struct super_block *sb,
struct ext4_group_desc *bg,
__u32 count);
extern void ext4_free_inodes_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count);
extern void ext4_used_dirs_set(struct super_block *sb,
@@ -2051,13 +2103,13 @@ do { \
} while (0)
#ifdef CONFIG_SMP
/* Each CPU can accumulate percpu_counter_batch blocks in their local
* counters. So we need to make sure we have free blocks more
/* Each CPU can accumulate percpu_counter_batch clusters in their local
* counters. So we need to make sure we have free clusters more
* than percpu_counter_batch * nr_cpu_ids. Also add a window of 4 times.
*/
#define EXT4_FREEBLOCKS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
#define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
#else
#define EXT4_FREEBLOCKS_WATERMARK 0
#define EXT4_FREECLUSTERS_WATERMARK 0
#endif
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
@@ -2243,10 +2295,19 @@ extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
enum ext4_state_bits {
BH_Uninit /* blocks are allocated but uninitialized on disk */
= BH_JBDPrivateStart,
BH_AllocFromCluster, /* allocated blocks were part of already
* allocated cluster. Note that this flag will
* never, ever appear in a buffer_head's state
* flag. See EXT4_MAP_FROM_CLUSTER to see where
* this is used. */
BH_Da_Mapped, /* Delayed allocated block that now has a mapping. This
* flag is set when ext4_map_blocks is called on a
* delayed allocated block to get its real mapping. */
};
BUFFER_FNS(Uninit, uninit)
TAS_BUFFER_FNS(Uninit, uninit)
BUFFER_FNS(Da_Mapped, da_mapped)
/*
* Add new method to test wether block and inode bitmaps are properly
@@ -2282,4 +2343,6 @@ extern void ext4_resize_end(struct super_block *sb);
#endif /* __KERNEL__ */
#include "ext4_extents.h"
#endif /* _EXT4_H */
fs/ext4/ext4_extents.h
+2
View File
@@ -290,5 +290,7 @@ extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
struct ext4_ext_path *);
extern void ext4_ext_drop_refs(struct ext4_ext_path *);
extern int ext4_ext_check_inode(struct inode *inode);
extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk,
int search_hint_reverse);
#endif /* _EXT4_EXTENTS */
fs/ext4/ext4_jbd2.c
+5 -3
View File
@@ -109,9 +109,11 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
if (ext4_handle_valid(handle)) {
err = jbd2_journal_dirty_metadata(handle, bh);
if (err)
ext4_journal_abort_handle(where, line, __func__,
bh, handle, err);
if (err) {
/* Errors can only happen if there is a bug */
handle->h_err = err;
__ext4_journal_stop(where, line, handle);
}
} else {
if (inode)
mark_buffer_dirty_inode(bh, inode);
fs/ext4/extents.c
+882 -284
View File
File diff suppressed because it is too large Load Diff
fs/ext4/file.c
+2 -2
View File
@@ -181,8 +181,8 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
path.dentry = mnt->mnt_root;
cp = d_path(&path, buf, sizeof(buf));
if (!IS_ERR(cp)) {
memcpy(sbi->s_es->s_last_mounted, cp,
sizeof(sbi->s_es->s_last_mounted));
strlcpy(sbi->s_es->s_last_mounted, cp,
sizeof(sbi->s_es->s_last_mounted));
ext4_mark_super_dirty(sb);
}
}
fs/ext4/fsync.c
+3 -7
View File
@@ -75,7 +75,7 @@ static void dump_completed_IO(struct inode * inode)
* to written.
* The function return the number of pending IOs on success.
*/
extern int ext4_flush_completed_IO(struct inode *inode)
int ext4_flush_completed_IO(struct inode *inode)
{
ext4_io_end_t *io;
struct ext4_inode_info *ei = EXT4_I(inode);
@@ -83,14 +83,12 @@ extern int ext4_flush_completed_IO(struct inode *inode)
int ret = 0;
int ret2 = 0;
if (list_empty(&ei->i_completed_io_list))
return ret;
dump_completed_IO(inode);
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
while (!list_empty(&ei->i_completed_io_list)){
io = list_entry(ei->i_completed_io_list.next,
ext4_io_end_t, list);
list_del_init(&io->list);
/*
* Calling ext4_end_io_nolock() to convert completed
* IO to written.
@@ -107,11 +105,9 @@ extern int ext4_flush_completed_IO(struct inode *inode)
*/
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
ret = ext4_end_io_nolock(io);
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
if (ret < 0)
ret2 = ret;
else
list_del_init(&io->list);
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
}
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
return (ret2 < 0) ? ret2 : 0;
fs/ext4/ialloc.c
+34 -170
View File
@@ -78,7 +78,7 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb,
* allocation, essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
ext4_error(sb, "Checksum bad for group %u", block_group);
ext4_free_blks_set(sb, gdp, 0);
ext4_free_group_clusters_set(sb, gdp, 0);
ext4_free_inodes_set(sb, gdp, 0);
ext4_itable_unused_set(sb, gdp, 0);
memset(bh->b_data, 0xff, sb->s_blocksize);
@@ -293,121 +293,9 @@ error_return:
ext4_std_error(sb, fatal);
}
/*
* There are two policies for allocating an inode. If the new inode is
* a directory, then a forward search is made for a block group with both
* free space and a low directory-to-inode ratio; if that fails, then of
* the groups with above-average free space, that group with the fewest
* directories already is chosen.
*
* For other inodes, search forward from the parent directory\'s block
* group to find a free inode.
*/
static int find_group_dir(struct super_block *sb, struct inode *parent,
ext4_group_t *best_group)
{
ext4_group_t ngroups = ext4_get_groups_count(sb);
unsigned int freei, avefreei;
struct ext4_group_desc *desc, *best_desc = NULL;
ext4_group_t group;
int ret = -1;
freei = percpu_counter_read_positive(&EXT4_SB(sb)->s_freeinodes_counter);
avefreei = freei / ngroups;
for (group = 0; group < ngroups; group++) {
desc = ext4_get_group_desc(sb, group, NULL);
if (!desc || !ext4_free_inodes_count(sb, desc))
continue;
if (ext4_free_inodes_count(sb, desc) < avefreei)
continue;
if (!best_desc ||
(ext4_free_blks_count(sb, desc) >
ext4_free_blks_count(sb, best_desc))) {
*best_group = group;
best_desc = desc;
ret = 0;
}
}
return ret;
}
#define free_block_ratio 10
static int find_group_flex(struct super_block *sb, struct inode *parent,
ext4_group_t *best_group)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_desc *desc;
struct flex_groups *flex_group = sbi->s_flex_groups;
ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group);
ext4_group_t ngroups = ext4_get_groups_count(sb);
int flex_size = ext4_flex_bg_size(sbi);
ext4_group_t best_flex = parent_fbg_group;
int blocks_per_flex = sbi->s_blocks_per_group * flex_size;
int flexbg_free_blocks;
int flex_freeb_ratio;
ext4_group_t n_fbg_groups;
ext4_group_t i;
n_fbg_groups = (ngroups + flex_size - 1) >>
sbi->s_log_groups_per_flex;
find_close_to_parent:
flexbg_free_blocks = atomic_read(&flex_group[best_flex].free_blocks);
flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
if (atomic_read(&flex_group[best_flex].free_inodes) &&
flex_freeb_ratio > free_block_ratio)
goto found_flexbg;
if (best_flex && best_flex == parent_fbg_group) {
best_flex--;
goto find_close_to_parent;
}
for (i = 0; i < n_fbg_groups; i++) {
if (i == parent_fbg_group || i == parent_fbg_group - 1)
continue;
flexbg_free_blocks = atomic_read(&flex_group[i].free_blocks);
flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
if (flex_freeb_ratio > free_block_ratio &&
(atomic_read(&flex_group[i].free_inodes))) {
best_flex = i;
goto found_flexbg;
}
if ((atomic_read(&flex_group[best_flex].free_inodes) == 0) ||
((atomic_read(&flex_group[i].free_blocks) >
atomic_read(&flex_group[best_flex].free_blocks)) &&
atomic_read(&flex_group[i].free_inodes)))
best_flex = i;
}
if (!atomic_read(&flex_group[best_flex].free_inodes) ||
!atomic_read(&flex_group[best_flex].free_blocks))
return -1;
found_flexbg:
for (i = best_flex * flex_size; i < ngroups &&
i < (best_flex + 1) * flex_size; i++) {
desc = ext4_get_group_desc(sb, i, NULL);
if (ext4_free_inodes_count(sb, desc)) {
*best_group = i;
goto out;
}
}
return -1;
out:
return 0;
}
struct orlov_stats {
__u32 free_inodes;
__u32 free_blocks;
__u32 free_clusters;
__u32 used_dirs;
};
@@ -424,7 +312,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
if (flex_size > 1) {
stats->free_inodes = atomic_read(&flex_group[g].free_inodes);
stats->free_blocks = atomic_read(&flex_group[g].free_blocks);
stats->free_clusters = atomic_read(&flex_group[g].free_clusters);
stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
return;
}
@@ -432,11 +320,11 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
desc = ext4_get_group_desc(sb, g, NULL);
if (desc) {
stats->free_inodes = ext4_free_inodes_count(sb, desc);
stats->free_blocks = ext4_free_blks_count(sb, desc);
stats->free_clusters = ext4_free_group_clusters(sb, desc);
stats->used_dirs = ext4_used_dirs_count(sb, desc);
} else {
stats->free_inodes = 0;
stats->free_blocks = 0;
stats->free_clusters = 0;
stats->used_dirs = 0;
}
}
@@ -471,10 +359,10 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
ext4_group_t real_ngroups = ext4_get_groups_count(sb);
int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
unsigned int freei, avefreei;
ext4_fsblk_t freeb, avefreeb;
ext4_fsblk_t freeb, avefreec;
unsigned int ndirs;
int max_dirs, min_inodes;
ext4_grpblk_t min_blocks;
ext4_grpblk_t min_clusters;
ext4_group_t i, grp, g, ngroups;
struct ext4_group_desc *desc;
struct orlov_stats stats;
@@ -490,9 +378,10 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
avefreei = freei / ngroups;
freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
avefreeb = freeb;
do_div(avefreeb, ngroups);
freeb = EXT4_C2B(sbi,
percpu_counter_read_positive(&sbi->s_freeclusters_counter));
avefreec = freeb;
do_div(avefreec, ngroups);
ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
if (S_ISDIR(mode) &&
@@ -518,7 +407,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
continue;
if (stats.free_inodes < avefreei)
continue;
if (stats.free_blocks < avefreeb)
if (stats.free_clusters < avefreec)
continue;
grp = g;
ret = 0;
@@ -556,7 +445,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
min_inodes = avefreei - inodes_per_group*flex_size / 4;
if (min_inodes < 1)
min_inodes = 1;
min_blocks = avefreeb - EXT4_BLOCKS_PER_GROUP(sb)*flex_size / 4;
min_clusters = avefreec - EXT4_CLUSTERS_PER_GROUP(sb)*flex_size / 4;
/*
* Start looking in the flex group where we last allocated an
@@ -575,7 +464,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
continue;
if (stats.free_inodes < min_inodes)
continue;
if (stats.free_blocks < min_blocks)
if (stats.free_clusters < min_clusters)
continue;
goto found_flex_bg;
}
@@ -659,7 +548,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
*group = parent_group;
desc = ext4_get_group_desc(sb, *group, NULL);
if (desc && ext4_free_inodes_count(sb, desc) &&
ext4_free_blks_count(sb, desc))
ext4_free_group_clusters(sb, desc))
return 0;
/*
@@ -683,7 +572,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
*group -= ngroups;
desc = ext4_get_group_desc(sb, *group, NULL);
if (desc && ext4_free_inodes_count(sb, desc) &&
ext4_free_blks_count(sb, desc))
ext4_free_group_clusters(sb, desc))
return 0;
}
@@ -802,7 +691,7 @@ err_ret:
* group to find a free inode.
*/
struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
const struct qstr *qstr, __u32 goal)
const struct qstr *qstr, __u32 goal, uid_t *owner)
{
struct super_block *sb;
struct buffer_head *inode_bitmap_bh = NULL;
@@ -816,8 +705,6 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
int ret2, err = 0;
struct inode *ret;
ext4_group_t i;
int free = 0;
static int once = 1;
ext4_group_t flex_group;
/* Cannot create files in a deleted directory */
@@ -843,26 +730,9 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
goto got_group;
}
if (sbi->s_log_groups_per_flex && test_opt(sb, OLDALLOC)) {
ret2 = find_group_flex(sb, dir, &group);
if (ret2 == -1) {
ret2 = find_group_other(sb, dir, &group, mode);
if (ret2 == 0 && once) {
once = 0;
printk(KERN_NOTICE "ext4: find_group_flex "
"failed, fallback succeeded dir %lu\n",
dir->i_ino);
}
}
goto got_group;
}
if (S_ISDIR(mode)) {
if (test_opt(sb, OLDALLOC))
ret2 = find_group_dir(sb, dir, &group);
else
ret2 = find_group_orlov(sb, dir, &group, mode, qstr);
} else
if (S_ISDIR(mode))
ret2 = find_group_orlov(sb, dir, &group, mode, qstr);
else
ret2 = find_group_other(sb, dir, &group, mode);
got_group:
@@ -950,26 +820,21 @@ got:
goto fail;
}
free = 0;
ext4_lock_group(sb, group);
BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
err = ext4_handle_dirty_metadata(handle, NULL, block_bitmap_bh);
brelse(block_bitmap_bh);
/* recheck and clear flag under lock if we still need to */
ext4_lock_group(sb, group);
if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
free = ext4_free_blocks_after_init(sb, group, gdp);
gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
ext4_free_blks_set(sb, gdp, free);
ext4_free_group_clusters_set(sb, gdp,
ext4_free_clusters_after_init(sb, group, gdp));
gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
gdp);
}
ext4_unlock_group(sb, group);
/* Don't need to dirty bitmap block if we didn't change it */
if (free) {
BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
err = ext4_handle_dirty_metadata(handle,
NULL, block_bitmap_bh);
}
brelse(block_bitmap_bh);
if (err)
goto fail;
}
@@ -987,8 +852,11 @@ got:
flex_group = ext4_flex_group(sbi, group);
atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes);
}
if (test_opt(sb, GRPID)) {
if (owner) {
inode->i_mode = mode;
inode->i_uid = owner[0];
inode->i_gid = owner[1];
} else if (test_opt(sb, GRPID)) {
inode->i_mode = mode;
inode->i_uid = current_fsuid();
inode->i_gid = dir->i_gid;
@@ -1005,11 +873,7 @@ got:
ei->i_dir_start_lookup = 0;
ei->i_disksize = 0;
/*
* Don't inherit extent flag from directory, amongst others. We set
* extent flag on newly created directory and file only if -o extent
* mount option is specified
*/
/* Don't inherit extent flag from directory, amongst others. */
ei->i_flags =
ext4_mask_flags(mode, EXT4_I(dir)->i_flags & EXT4_FL_INHERITED);
ei->i_file_acl = 0;
@@ -1235,7 +1099,7 @@ unsigned long ext4_count_dirs(struct super_block * sb)
* inode allocation from the current group, so we take alloc_sem lock, to
* block ext4_claim_inode until we are finished.
*/
extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
int barrier)
{
struct ext4_group_info *grp = ext4_get_group_info(sb, group);
fs/ext4/indirect.c
+18 -2
View File
@@ -699,6 +699,13 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
/*
* Okay, we need to do block allocation.
*/
if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
EXT4_ERROR_INODE(inode, "Can't allocate blocks for "
"non-extent mapped inodes with bigalloc");
return -ENOSPC;
}
goal = ext4_find_goal(inode, map->m_lblk, partial);
/* the number of blocks need to allocate for [d,t]indirect blocks */
@@ -1343,7 +1350,9 @@ void ext4_ind_truncate(struct inode *inode)
__le32 nr = 0;
int n = 0;
ext4_lblk_t last_block, max_block;
loff_t page_len;
unsigned blocksize = inode->i_sb->s_blocksize;
int err;
handle = start_transaction(inode);
if (IS_ERR(handle))
@@ -1354,9 +1363,16 @@ void ext4_ind_truncate(struct inode *inode)
max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
>> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
if (inode->i_size & (blocksize - 1))
if (ext4_block_truncate_page(handle, mapping, inode->i_size))
if (inode->i_size % PAGE_CACHE_SIZE != 0) {
page_len = PAGE_CACHE_SIZE -
(inode->i_size & (PAGE_CACHE_SIZE - 1));
err = ext4_discard_partial_page_buffers(handle,
mapping, inode->i_size, page_len, 0);
if (err)
goto out_stop;
}
if (last_block != max_block) {
n = ext4_block_to_path(inode, last_block, offsets, NULL);
fs/ext4/inode.c
+443 -69
View File
File diff suppressed because it is too large Load Diff
fs/ext4/ioctl.c
+31 -34
View File
@@ -21,6 +21,7 @@
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = filp->f_dentry->d_inode;
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int flags;
@@ -173,33 +174,8 @@ setversion_out:
mnt_drop_write(filp->f_path.mnt);
return err;
}
#ifdef CONFIG_JBD2_DEBUG
case EXT4_IOC_WAIT_FOR_READONLY:
/*
* This is racy - by the time we're woken up and running,
* the superblock could be released. And the module could
* have been unloaded. So sue me.
*
* Returns 1 if it slept, else zero.
*/
{
struct super_block *sb = inode->i_sb;
DECLARE_WAITQUEUE(wait, current);
int ret = 0;
set_current_state(TASK_INTERRUPTIBLE);
add_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait);
if (timer_pending(&EXT4_SB(sb)->turn_ro_timer)) {
schedule();
ret = 1;
}
remove_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait);
return ret;
}
#endif
case EXT4_IOC_GROUP_EXTEND: {
ext4_fsblk_t n_blocks_count;
struct super_block *sb = inode->i_sb;
int err, err2=0;
err = ext4_resize_begin(sb);
@@ -209,6 +185,13 @@ setversion_out:
if (get_user(n_blocks_count, (__u32 __user *)arg))
return -EFAULT;
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
return -EOPNOTSUPP;
}
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
@@ -250,6 +233,13 @@ setversion_out:
goto mext_out;
}
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online defrag not supported with bigalloc");
return -EOPNOTSUPP;
}
err = mnt_want_write(filp->f_path.mnt);
if (err)
goto mext_out;
@@ -270,7 +260,6 @@ mext_out:
case EXT4_IOC_GROUP_ADD: {
struct ext4_new_group_data input;
struct super_block *sb = inode->i_sb;
int err, err2=0;
err = ext4_resize_begin(sb);
@@ -281,6 +270,13 @@ mext_out:
sizeof(input)))
return -EFAULT;
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
return -EOPNOTSUPP;
}
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
@@ -337,7 +333,6 @@ mext_out:
case FITRIM:
{
struct super_block *sb = inode->i_sb;
struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
int ret = 0;
@@ -348,7 +343,14 @@ mext_out:
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
if (copy_from_user(&range, (struct fstrim_range *)arg,
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"FITRIM not supported with bigalloc");
return -EOPNOTSUPP;
}
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
@@ -358,7 +360,7 @@ mext_out:
if (ret < 0)
return ret;
if (copy_to_user((struct fstrim_range *)arg, &range,
if (copy_to_user((struct fstrim_range __user *)arg, &range,
sizeof(range)))
return -EFAULT;
@@ -396,11 +398,6 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case EXT4_IOC32_SETVERSION_OLD:
cmd = EXT4_IOC_SETVERSION_OLD;
break;
#ifdef CONFIG_JBD2_DEBUG
case EXT4_IOC32_WAIT_FOR_READONLY:
cmd = EXT4_IOC_WAIT_FOR_READONLY;
break;
#endif
case EXT4_IOC32_GETRSVSZ:
cmd = EXT4_IOC_GETRSVSZ;
break;
fs/ext4/mballoc.c
+206 -125
View File
File diff suppressed because it is too large Load Diff
fs/ext4/mballoc.h
+6 -5
View File
@@ -106,7 +106,7 @@ struct ext4_free_data {
ext4_group_t group;
/* free block extent */
ext4_grpblk_t start_blk;
ext4_grpblk_t start_cluster;
ext4_grpblk_t count;
/* transaction which freed this extent */
@@ -139,9 +139,9 @@ enum {
struct ext4_free_extent {
ext4_lblk_t fe_logical;
ext4_grpblk_t fe_start;
ext4_grpblk_t fe_start; /* In cluster units */
ext4_group_t fe_group;
ext4_grpblk_t fe_len;
ext4_grpblk_t fe_len; /* In cluster units */
};
/*
@@ -175,7 +175,7 @@ struct ext4_allocation_context {
/* the best found extent */
struct ext4_free_extent ac_b_ex;
/* copy of the bext found extent taken before preallocation efforts */
/* copy of the best found extent taken before preallocation efforts */
struct ext4_free_extent ac_f_ex;
/* number of iterations done. we have to track to limit searching */
@@ -216,6 +216,7 @@ struct ext4_buddy {
static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
struct ext4_free_extent *fex)
{
return ext4_group_first_block_no(sb, fex->fe_group) + fex->fe_start;
return ext4_group_first_block_no(sb, fex->fe_group) +
(fex->fe_start << EXT4_SB(sb)->s_cluster_bits);
}
#endif
fs/ext4/migrate.c
+40 -69
View File
@@ -15,19 +15,18 @@
#include <linux/module.h>
#include <linux/slab.h>
#include "ext4_jbd2.h"
#include "ext4_extents.h"
/*
* The contiguous blocks details which can be
* represented by a single extent
*/
struct list_blocks_struct {
ext4_lblk_t first_block, last_block;
struct migrate_struct {
ext4_lblk_t first_block, last_block, curr_block;
ext4_fsblk_t first_pblock, last_pblock;
};
static int finish_range(handle_t *handle, struct inode *inode,
struct list_blocks_struct *lb)
struct migrate_struct *lb)
{
int retval = 0, needed;
@@ -87,8 +86,7 @@ err_out:
}
static int update_extent_range(handle_t *handle, struct inode *inode,
ext4_fsblk_t pblock, ext4_lblk_t blk_num,
struct list_blocks_struct *lb)
ext4_fsblk_t pblock, struct migrate_struct *lb)
{
int retval;
/*
@@ -96,9 +94,10 @@ static int update_extent_range(handle_t *handle, struct inode *inode,
*/
if (lb->first_pblock &&
(lb->last_pblock+1 == pblock) &&
(lb->last_block+1 == blk_num)) {
(lb->last_block+1 == lb->curr_block)) {
lb->last_pblock = pblock;
lb->last_block = blk_num;
lb->last_block = lb->curr_block;
lb->curr_block++;
return 0;
}
/*
@@ -106,64 +105,49 @@ static int update_extent_range(handle_t *handle, struct inode *inode,
*/
retval = finish_range(handle, inode, lb);
lb->first_pblock = lb->last_pblock = pblock;
lb->first_block = lb->last_block = blk_num;
lb->first_block = lb->last_block = lb->curr_block;
lb->curr_block++;
return retval;
}
static int update_ind_extent_range(handle_t *handle, struct inode *inode,
ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
struct list_blocks_struct *lb)
ext4_fsblk_t pblock,
struct migrate_struct *lb)
{
struct buffer_head *bh;
__le32 *i_data;
int i, retval = 0;
ext4_lblk_t blk_count = *blk_nump;
unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
if (!pblock) {
/* Only update the file block number */
*blk_nump += max_entries;
return 0;
}
bh = sb_bread(inode->i_sb, pblock);
if (!bh)
return -EIO;
i_data = (__le32 *)bh->b_data;
for (i = 0; i < max_entries; i++, blk_count++) {
for (i = 0; i < max_entries; i++) {
if (i_data[i]) {
retval = update_extent_range(handle, inode,
le32_to_cpu(i_data[i]),
blk_count, lb);
le32_to_cpu(i_data[i]), lb);
if (retval)
break;
} else {
lb->curr_block++;
}
}
/* Update the file block number */
*blk_nump = blk_count;
put_bh(bh);
return retval;
}
static int update_dind_extent_range(handle_t *handle, struct inode *inode,
ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
struct list_blocks_struct *lb)
ext4_fsblk_t pblock,
struct migrate_struct *lb)
{
struct buffer_head *bh;
__le32 *i_data;
int i, retval = 0;
ext4_lblk_t blk_count = *blk_nump;
unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
if (!pblock) {
/* Only update the file block number */
*blk_nump += max_entries * max_entries;
return 0;
}
bh = sb_bread(inode->i_sb, pblock);
if (!bh)
return -EIO;
@@ -172,38 +156,28 @@ static int update_dind_extent_range(handle_t *handle, struct inode *inode,
for (i = 0; i < max_entries; i++) {
if (i_data[i]) {
retval = update_ind_extent_range(handle, inode,
le32_to_cpu(i_data[i]),
&blk_count, lb);
le32_to_cpu(i_data[i]), lb);
if (retval)
break;
} else {
/* Only update the file block number */
blk_count += max_entries;
lb->curr_block += max_entries;
}
}
/* Update the file block number */
*blk_nump = blk_count;
put_bh(bh);
return retval;
}
static int update_tind_extent_range(handle_t *handle, struct inode *inode,
ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
struct list_blocks_struct *lb)
ext4_fsblk_t pblock,
struct migrate_struct *lb)
{
struct buffer_head *bh;
__le32 *i_data;
int i, retval = 0;
ext4_lblk_t blk_count = *blk_nump;
unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
if (!pblock) {
/* Only update the file block number */
*blk_nump += max_entries * max_entries * max_entries;
return 0;
}
bh = sb_bread(inode->i_sb, pblock);
if (!bh)
return -EIO;
@@ -212,16 +186,14 @@ static int update_tind_extent_range(handle_t *handle, struct inode *inode,
for (i = 0; i < max_entries; i++) {
if (i_data[i]) {
retval = update_dind_extent_range(handle, inode,
le32_to_cpu(i_data[i]),
&blk_count, lb);
le32_to_cpu(i_data[i]), lb);
if (retval)
break;
} else
} else {
/* Only update the file block number */
blk_count += max_entries * max_entries;
lb->curr_block += max_entries * max_entries;
}
}
/* Update the file block number */
*blk_nump = blk_count;
put_bh(bh);
return retval;
@@ -462,12 +434,12 @@ int ext4_ext_migrate(struct inode *inode)
handle_t *handle;
int retval = 0, i;
__le32 *i_data;
ext4_lblk_t blk_count = 0;
struct ext4_inode_info *ei;
struct inode *tmp_inode = NULL;
struct list_blocks_struct lb;
struct migrate_struct lb;
unsigned long max_entries;
__u32 goal;
uid_t owner[2];
/*
* If the filesystem does not support extents, or the inode
@@ -495,10 +467,12 @@ int ext4_ext_migrate(struct inode *inode)
}
goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;
owner[0] = inode->i_uid;
owner[1] = inode->i_gid;
tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
S_IFREG, NULL, goal);
S_IFREG, NULL, goal, owner);
if (IS_ERR(tmp_inode)) {
retval = -ENOMEM;
retval = PTR_ERR(inode);
ext4_journal_stop(handle);
return retval;
}
@@ -551,35 +525,32 @@ int ext4_ext_migrate(struct inode *inode)
/* 32 bit block address 4 bytes */
max_entries = inode->i_sb->s_blocksize >> 2;
for (i = 0; i < EXT4_NDIR_BLOCKS; i++, blk_count++) {
for (i = 0; i < EXT4_NDIR_BLOCKS; i++) {
if (i_data[i]) {
retval = update_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[i]),
blk_count, &lb);
le32_to_cpu(i_data[i]), &lb);
if (retval)
goto err_out;
}
} else
lb.curr_block++;
}
if (i_data[EXT4_IND_BLOCK]) {
retval = update_ind_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[EXT4_IND_BLOCK]),
&blk_count, &lb);
le32_to_cpu(i_data[EXT4_IND_BLOCK]), &lb);
if (retval)
goto err_out;
} else
blk_count += max_entries;
lb.curr_block += max_entries;
if (i_data[EXT4_DIND_BLOCK]) {
retval = update_dind_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[EXT4_DIND_BLOCK]),
&blk_count, &lb);
le32_to_cpu(i_data[EXT4_DIND_BLOCK]), &lb);
if (retval)
goto err_out;
} else
blk_count += max_entries * max_entries;
lb.curr_block += max_entries * max_entries;
if (i_data[EXT4_TIND_BLOCK]) {
retval = update_tind_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[EXT4_TIND_BLOCK]),
&blk_count, &lb);
le32_to_cpu(i_data[EXT4_TIND_BLOCK]), &lb);
if (retval)
goto err_out;
}
fs/ext4/mmp.c
+6 -4
View File
@@ -109,7 +109,7 @@ static int kmmpd(void *data)
mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
bdevname(bh->b_bdev, mmp->mmp_bdevname);
memcpy(mmp->mmp_nodename, init_utsname()->sysname,
memcpy(mmp->mmp_nodename, init_utsname()->nodename,
sizeof(mmp->mmp_nodename));
while (!kthread_should_stop()) {
@@ -125,8 +125,9 @@ static int kmmpd(void *data)
* Don't spew too many error messages. Print one every
* (s_mmp_update_interval * 60) seconds.
*/
if (retval && (failed_writes % 60) == 0) {
ext4_error(sb, "Error writing to MMP block");
if (retval) {
if ((failed_writes % 60) == 0)
ext4_error(sb, "Error writing to MMP block");
failed_writes++;
}
@@ -295,7 +296,8 @@ skip:
/*
* write a new random sequence number.
*/
mmp->mmp_seq = seq = cpu_to_le32(mmp_new_seq());
seq = mmp_new_seq();
mmp->mmp_seq = cpu_to_le32(seq);
retval = write_mmp_block(bh);
if (retval)
fs/ext4/move_extent.c
-1
View File
@@ -17,7 +17,6 @@
#include <linux/quotaops.h>
#include <linux/slab.h>
#include "ext4_jbd2.h"
#include "ext4_extents.h"
#include "ext4.h"
/**
fs/ext4/namei.c
+10 -11
View File
@@ -1586,7 +1586,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
dxtrace(dx_show_index("node", frames[1].entries));
dxtrace(dx_show_index("node",
((struct dx_node *) bh2->b_data)->entries));
err = ext4_handle_dirty_metadata(handle, inode, bh2);
err = ext4_handle_dirty_metadata(handle, dir, bh2);
if (err)
goto journal_error;
brelse (bh2);
@@ -1612,7 +1612,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
if (err)
goto journal_error;
}
err = ext4_handle_dirty_metadata(handle, inode, frames[0].bh);
err = ext4_handle_dirty_metadata(handle, dir, frames[0].bh);
if (err) {
ext4_std_error(inode->i_sb, err);
goto cleanup;
@@ -1707,9 +1707,8 @@ static void ext4_inc_count(handle_t *handle, struct inode *inode)
*/
static void ext4_dec_count(handle_t *handle, struct inode *inode)
{
drop_nlink(inode);
if (S_ISDIR(inode->i_mode) && inode->i_nlink == 0)
inc_nlink(inode);
if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2)
drop_nlink(inode);
}
@@ -1756,7 +1755,7 @@ retry:
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0);
inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0, NULL);
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
inode->i_op = &ext4_file_inode_operations;
@@ -1792,7 +1791,7 @@ retry:
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0);
inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0, NULL);
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
init_special_inode(inode, inode->i_mode, rdev);
@@ -1832,7 +1831,7 @@ retry:
ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, S_IFDIR | mode,
&dentry->d_name, 0);
&dentry->d_name, 0, NULL);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_stop;
@@ -1863,7 +1862,7 @@ retry:
ext4_set_de_type(dir->i_sb, de, S_IFDIR);
inode->i_nlink = 2;
BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle, dir, dir_block);
err = ext4_handle_dirty_metadata(handle, inode, dir_block);
if (err)
goto out_clear_inode;
err = ext4_mark_inode_dirty(handle, inode);
@@ -2279,7 +2278,7 @@ retry:
ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO,
&dentry->d_name, 0);
&dentry->d_name, 0, NULL);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_stop;
@@ -2530,7 +2529,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) =
cpu_to_le32(new_dir->i_ino);
BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
retval = ext4_handle_dirty_metadata(handle, old_dir, dir_bh);
retval = ext4_handle_dirty_metadata(handle, old_inode, dir_bh);
if (retval) {
ext4_std_error(old_dir->i_sb, retval);
goto end_rename;
fs/ext4/page-io.c
+25 -41
View File
@@ -70,7 +70,6 @@ static void put_io_page(struct ext4_io_page *io_page)
void ext4_free_io_end(ext4_io_end_t *io)
{
int i;
wait_queue_head_t *wq;
BUG_ON(!io);
if (io->page)
@@ -78,56 +77,43 @@ void ext4_free_io_end(ext4_io_end_t *io)
for (i = 0; i < io->num_io_pages; i++)
put_io_page(io->pages[i]);
io->num_io_pages = 0;
wq = ext4_ioend_wq(io->inode);
if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count) &&
waitqueue_active(wq))
wake_up_all(wq);
if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count))
wake_up_all(ext4_ioend_wq(io->inode));
kmem_cache_free(io_end_cachep, io);
}
/*
* check a range of space and convert unwritten extents to written.
*
* Called with inode->i_mutex; we depend on this when we manipulate
* io->flag, since we could otherwise race with ext4_flush_completed_IO()
*/
int ext4_end_io_nolock(ext4_io_end_t *io)
{
struct inode *inode = io->inode;
loff_t offset = io->offset;
ssize_t size = io->size;
wait_queue_head_t *wq;
int ret = 0;
ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
"list->prev 0x%p\n",
io, inode->i_ino, io->list.next, io->list.prev);
if (list_empty(&io->list))
return ret;
if (!(io->flag & EXT4_IO_END_UNWRITTEN))
return ret;
ret = ext4_convert_unwritten_extents(inode, offset, size);
if (ret < 0) {
printk(KERN_EMERG "%s: failed to convert unwritten "
"extents to written extents, error is %d "
"io is still on inode %lu aio dio list\n",
__func__, ret, inode->i_ino);
return ret;
ext4_msg(inode->i_sb, KERN_EMERG,
"failed to convert unwritten extents to written "
"extents -- potential data loss! "
"(inode %lu, offset %llu, size %zd, error %d)",
inode->i_ino, offset, size, ret);
}
if (io->iocb)
aio_complete(io->iocb, io->result, 0);
/* clear the DIO AIO unwritten flag */
if (io->flag & EXT4_IO_END_UNWRITTEN) {
io->flag &= ~EXT4_IO_END_UNWRITTEN;
/* Wake up anyone waiting on unwritten extent conversion */
wq = ext4_ioend_wq(io->inode);
if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten) &&
waitqueue_active(wq)) {
wake_up_all(wq);
}
}
/* Wake up anyone waiting on unwritten extent conversion */
if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten))
wake_up_all(ext4_ioend_wq(io->inode));
return ret;
}
@@ -140,9 +126,15 @@ static void ext4_end_io_work(struct work_struct *work)
struct inode *inode = io->inode;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned long flags;
int ret;
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
if (list_empty(&io->list)) {
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
goto free;
}
if (!mutex_trylock(&inode->i_mutex)) {
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
/*
* Requeue the work instead of waiting so that the work
* items queued after this can be processed.
@@ -159,17 +151,11 @@ static void ext4_end_io_work(struct work_struct *work)
io->flag |= EXT4_IO_END_QUEUED;
return;
}
ret = ext4_end_io_nolock(io);
if (ret < 0) {
mutex_unlock(&inode->i_mutex);
return;
}
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
if (!list_empty(&io->list))
list_del_init(&io->list);
list_del_init(&io->list);
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
(void) ext4_end_io_nolock(io);
mutex_unlock(&inode->i_mutex);
free:
ext4_free_io_end(io);
}
@@ -350,10 +336,8 @@ submit_and_retry:
if ((io_end->num_io_pages >= MAX_IO_PAGES) &&
(io_end->pages[io_end->num_io_pages-1] != io_page))
goto submit_and_retry;
if (buffer_uninit(bh) && !(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
io_end->flag |= EXT4_IO_END_UNWRITTEN;
atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
}
if (buffer_uninit(bh))
ext4_set_io_unwritten_flag(inode, io_end);
io->io_end->size += bh->b_size;
io->io_next_block++;
ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
fs/ext4/resize.c
+5 -5
View File
@@ -875,7 +875,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */
ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */
ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */
ext4_free_blks_set(sb, gdp, input->free_blocks_count);
ext4_free_group_clusters_set(sb, gdp, input->free_blocks_count);
ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
gdp->bg_flags = cpu_to_le16(EXT4_BG_INODE_ZEROED);
gdp->bg_checksum = ext4_group_desc_csum(sbi, input->group, gdp);
@@ -937,8 +937,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
input->reserved_blocks);
/* Update the free space counts */
percpu_counter_add(&sbi->s_freeblocks_counter,
input->free_blocks_count);
percpu_counter_add(&sbi->s_freeclusters_counter,
EXT4_B2C(sbi, input->free_blocks_count));
percpu_counter_add(&sbi->s_freeinodes_counter,
EXT4_INODES_PER_GROUP(sb));
@@ -946,8 +946,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
sbi->s_log_groups_per_flex) {
ext4_group_t flex_group;
flex_group = ext4_flex_group(sbi, input->group);
atomic_add(input->free_blocks_count,
&sbi->s_flex_groups[flex_group].free_blocks);
atomic_add(EXT4_B2C(sbi, input->free_blocks_count),
&sbi->s_flex_groups[flex_group].free_clusters);
atomic_add(EXT4_INODES_PER_GROUP(sb),
&sbi->s_flex_groups[flex_group].free_inodes);
}

Some files were not shown because too many files have changed in this diff Show More